Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:
 "virtio,vdpa,qemu_fw_cfg: features, cleanups, and fixes.

   - partial support for < MAX_ORDER - 1 granularity for virtio-mem

   - driver_override for vdpa

   - sysfs ABI documentation for vdpa

   - multiqueue config support for mlx5 vdpa

   - and misc fixes, cleanups"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (42 commits)
  vdpa/mlx5: Fix tracking of current number of VQs
  vdpa/mlx5: Fix is_index_valid() to refer to features
  vdpa: Protect vdpa reset with cf_mutex
  vdpa: Avoid taking cf_mutex lock on get status
  vdpa/vdpa_sim_net: Report max device capabilities
  vdpa: Use BIT_ULL for bit operations
  vdpa/vdpa_sim: Configure max supported virtqueues
  vdpa/mlx5: Report max device capabilities
  vdpa: Support reporting max device capabilities
  vdpa/mlx5: Restore cur_num_vqs in case of failure in change_num_qps()
  vdpa: Add support for returning device configuration information
  vdpa/mlx5: Support configuring max data virtqueue
  vdpa/mlx5: Fix config_attr_mask assignment
  vdpa: Allow to configure max data virtqueues
  vdpa: Read device configuration only if FEATURES_OK
  vdpa: Sync calls set/get config/status with cf_mutex
  vdpa/mlx5: Distribute RX virtqueues in RQT object
  vdpa: Provide interface to read driver features
  vdpa: clean up get_config_size ret value handling
  virtio_ring: mark ring unused on error
  ...

Documentation/ABI/testing/sysfs-bus-vdpa

+What:		/sys/bus/vdpa/driver_autoprobe
+Date:		March 2020
+Contact:	virtualization@lists.linux-foundation.org
+Description:
+		This file determines whether new devices are immediately bound
+		to a driver after the creation. It initially contains 1, which
+		means the kernel automatically binds devices to a compatible
+		driver immediately after they are created.
+
+		Writing "0" to this file disable this feature, any other string
+		enable it.
+
+What:		/sys/bus/vdpa/driver_probe
+Date:		March 2020
+Contact:	virtualization@lists.linux-foundation.org
+Description:
+		Writing a device name to this file will cause the kernel binds
+		devices to a compatible driver.
+
+		This can be useful when /sys/bus/vdpa/driver_autoprobe is
+		disabled.
+
+What:		/sys/bus/vdpa/drivers/.../bind
+Date:		March 2020
+Contact:	virtualization@lists.linux-foundation.org
+Description:
+		Writing a device name to this file will cause the driver to
+		attempt to bind to the device. This is useful for overriding
+		default bindings.
+
+What:		/sys/bus/vdpa/drivers/.../unbind
+Date:		March 2020
+Contact:	virtualization@lists.linux-foundation.org
+Description:
+		Writing a device name to this file will cause the driver to
+		attempt to unbind from the device. This may be useful when
+		overriding default bindings.
+
+What:		/sys/bus/vdpa/devices/.../driver_override
+Date:		November 2021
+Contact:	virtualization@lists.linux-foundation.org
+Description:
+		This file allows the driver for a device to be specified.
+		When specified, only a driver with a name matching the value
+		written to driver_override will have an opportunity to bind to
+		the device. The override is specified by writing a string to the
+		driver_override file (echo vhost-vdpa > driver_override) and may
+		be cleared with an empty string (echo > driver_override).
+		This returns the device to standard matching rules binding.
+		Writing to driver_override does not automatically unbind the
+		device from its current driver or make any attempt to
+		automatically load the specified driver. If no driver with a
+		matching name is currently loaded in the kernel, the device will
+		not bind to any driver. This also allows devices to opt-out of
+		driver binding using a driver_override name such as "none".
+		Only a single driver may be specified in the override, there is
+		no support for parsing delimiters.

MAINTAINERS

@@ -20377,6 +20377,7 @@ M:	"Michael S. Tsirkin" <mst@redhat.com>
 M:	Jason Wang <jasowang@redhat.com>
 L:	virtualization@lists.linux-foundation.org
 S:	Maintained
+F:	Documentation/ABI/testing/sysfs-bus-vdpa
 F:	Documentation/devicetree/bindings/virtio/
 F:	drivers/block/virtio_blk.c
 F:	drivers/crypto/virtio/

arch/um/drivers/virt-pci.c

@@ -616,7 +616,7 @@ static void um_pci_virtio_remove(struct virtio_device *vdev)
 	int i;
 
         /* Stop all virtqueues */
-        vdev->config->reset(vdev);
+        virtio_reset_device(vdev);
         vdev->config->del_vqs(vdev);
 
 	device_set_wakeup_enable(&vdev->dev, false);

drivers/block/virtio_blk.c

@@ -976,7 +976,7 @@ static void virtblk_remove(struct virtio_device *vdev)
 	mutex_lock(&vblk->vdev_mutex);
 
 	/* Stop all the virtqueues. */
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 
 	/* Virtqueues are stopped, nothing can use vblk->vdev anymore. */
 	vblk->vdev = NULL;
@@ -995,7 +995,7 @@ static int virtblk_freeze(struct virtio_device *vdev)
 	struct virtio_blk *vblk = vdev->priv;
 
 	/* Ensure we don't receive any more interrupts */
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 
 	/* Make sure no work handler is accessing the device. */
 	flush_work(&vblk->config_work);

drivers/bluetooth/virtio_bt.c

@@ -367,7 +367,7 @@ static void virtbt_remove(struct virtio_device *vdev)
 	struct hci_dev *hdev = vbt->hdev;
 
 	hci_unregister_dev(hdev);
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 
 	hci_free_dev(hdev);
 	vbt->hdev = NULL;

drivers/char/hw_random/virtio-rng.c

@@ -179,9 +179,9 @@ static void remove_common(struct virtio_device *vdev)
 	vi->data_avail = 0;
 	vi->data_idx = 0;
 	complete(&vi->have_data);
-	vdev->config->reset(vdev);
 	if (vi->hwrng_register_done)
 		hwrng_unregister(&vi->hwrng);
+	virtio_reset_device(vdev);
 	vdev->config->del_vqs(vdev);
 	ida_simple_remove(&rng_index_ida, vi->index);
 	kfree(vi);

drivers/char/virtio_console.c

@@ -1958,7 +1958,7 @@ static void virtcons_remove(struct virtio_device *vdev)
 	spin_unlock_irq(&pdrvdata_lock);
 
 	/* Disable interrupts for vqs */
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	/* Finish up work that's lined up */
 	if (use_multiport(portdev))
 		cancel_work_sync(&portdev->control_work);
@@ -2148,7 +2148,7 @@ static int virtcons_freeze(struct virtio_device *vdev)
 
 	portdev = vdev->priv;
 
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 
 	if (use_multiport(portdev))
 		virtqueue_disable_cb(portdev->c_ivq);

drivers/crypto/virtio/virtio_crypto_core.c

@@ -404,7 +404,7 @@ static int virtcrypto_probe(struct virtio_device *vdev)
 free_engines:
 	virtcrypto_clear_crypto_engines(vcrypto);
 free_vqs:
-	vcrypto->vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	virtcrypto_del_vqs(vcrypto);
 free_dev:
 	virtcrypto_devmgr_rm_dev(vcrypto);
@@ -436,7 +436,7 @@ static void virtcrypto_remove(struct virtio_device *vdev)
 
 	if (virtcrypto_dev_started(vcrypto))
 		virtcrypto_dev_stop(vcrypto);
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	virtcrypto_free_unused_reqs(vcrypto);
 	virtcrypto_clear_crypto_engines(vcrypto);
 	virtcrypto_del_vqs(vcrypto);
@@ -456,7 +456,7 @@ static int virtcrypto_freeze(struct virtio_device *vdev)
 {
 	struct virtio_crypto *vcrypto = vdev->priv;
 
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	virtcrypto_free_unused_reqs(vcrypto);
 	if (virtcrypto_dev_started(vcrypto))
 		virtcrypto_dev_stop(vcrypto);
@@ -492,7 +492,7 @@ static int virtcrypto_restore(struct virtio_device *vdev)
 free_engines:
 	virtcrypto_clear_crypto_engines(vcrypto);
 free_vqs:
-	vcrypto->vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	virtcrypto_del_vqs(vcrypto);
 	return err;
 }

drivers/firmware/arm_scmi/virtio.c

@@ -452,7 +452,7 @@ static void scmi_vio_remove(struct virtio_device *vdev)
 	 * outstanding message on any vqueue to be ignored by complete_cb: now
 	 * we can just stop processing buffers and destroy the vqueues.
 	 */
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	vdev->config->del_vqs(vdev);
 	/* Ensure scmi_vdev is visible as NULL */
 	smp_store_mb(scmi_vdev, NULL);

drivers/gpio/gpio-virtio.c

@@ -450,7 +450,7 @@ static void virtio_gpio_request_vq(struct virtqueue *vq)
 
 static void virtio_gpio_free_vqs(struct virtio_device *vdev)
 {
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	vdev->config->del_vqs(vdev);
 }
 

drivers/gpu/drm/virtio/virtgpu_kms.c

@@ -279,7 +279,7 @@ void virtio_gpu_deinit(struct drm_device *dev)
 	flush_work(&vgdev->ctrlq.dequeue_work);
 	flush_work(&vgdev->cursorq.dequeue_work);
 	flush_work(&vgdev->config_changed_work);
-	vgdev->vdev->config->reset(vgdev->vdev);
+	virtio_reset_device(vgdev->vdev);
 	vgdev->vdev->config->del_vqs(vgdev->vdev);
 }
 

drivers/i2c/busses/i2c-virtio.c

@@ -165,7 +165,7 @@ static int virtio_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs,
 
 static void virtio_i2c_del_vqs(struct virtio_device *vdev)
 {
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	vdev->config->del_vqs(vdev);
 }
 

drivers/iommu/virtio-iommu.c

@@ -1189,7 +1189,7 @@ static void viommu_remove(struct virtio_device *vdev)
 	iommu_device_unregister(&viommu->iommu);
 
 	/* Stop all virtqueues */
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	vdev->config->del_vqs(vdev);
 
 	dev_info(&vdev->dev, "device removed\n");

drivers/net/caif/caif_virtio.c

@@ -754,7 +754,7 @@ static void cfv_remove(struct virtio_device *vdev)
 	debugfs_remove_recursive(cfv->debugfs);
 
 	vringh_kiov_cleanup(&cfv->ctx.riov);
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	vdev->vringh_config->del_vrhs(cfv->vdev);
 	cfv->vr_rx = NULL;
 	vdev->config->del_vqs(cfv->vdev);

drivers/net/virtio_net.c

@@ -3312,7 +3312,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	return 0;
 
 free_unregister_netdev:
-	vi->vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 
 	unregister_netdev(dev);
 free_failover:
@@ -3328,7 +3328,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 
 static void remove_vq_common(struct virtnet_info *vi)
 {
-	vi->vdev->config->reset(vi->vdev);
+	virtio_reset_device(vi->vdev);
 
 	/* Free unused buffers in both send and recv, if any. */
 	free_unused_bufs(vi);

drivers/net/wireless/mac80211_hwsim.c

@@ -4498,7 +4498,7 @@ static void remove_vqs(struct virtio_device *vdev)
 {
 	int i;
 
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 
 	for (i = 0; i < ARRAY_SIZE(hwsim_vqs); i++) {
 		struct virtqueue *vq = hwsim_vqs[i];

drivers/nvdimm/virtio_pmem.c

@@ -105,7 +105,7 @@ static void virtio_pmem_remove(struct virtio_device *vdev)
 
 	nvdimm_bus_unregister(nvdimm_bus);
 	vdev->config->del_vqs(vdev);
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 }
 
 static struct virtio_driver virtio_pmem_driver = {

drivers/rpmsg/virtio_rpmsg_bus.c

@@ -1024,7 +1024,7 @@ static void rpmsg_remove(struct virtio_device *vdev)
 	size_t total_buf_space = vrp->num_bufs * vrp->buf_size;
 	int ret;
 
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 
 	ret = device_for_each_child(&vdev->dev, NULL, rpmsg_remove_device);
 	if (ret)

drivers/scsi/virtio_scsi.c

@@ -778,7 +778,7 @@ static void virtscsi_init_vq(struct virtio_scsi_vq *virtscsi_vq,
 static void virtscsi_remove_vqs(struct virtio_device *vdev)
 {
 	/* Stop all the virtqueues. */
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	vdev->config->del_vqs(vdev);
 }
 

drivers/vdpa/alibaba/eni_vdpa.c

@@ -58,7 +58,7 @@ static struct virtio_pci_legacy_device *vdpa_to_ldev(struct vdpa_device *vdpa)
 	return &eni_vdpa->ldev;
 }
 
-static u64 eni_vdpa_get_features(struct vdpa_device *vdpa)
+static u64 eni_vdpa_get_device_features(struct vdpa_device *vdpa)
 {
 	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
 	u64 features = vp_legacy_get_features(ldev);
@@ -69,7 +69,7 @@ static u64 eni_vdpa_get_features(struct vdpa_device *vdpa)
 	return features;
 }
 
-static int eni_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
+static int eni_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features)
 {
 	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
 
@@ -84,6 +84,13 @@ static int eni_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
 	return 0;
 }
 
+static u64 eni_vdpa_get_driver_features(struct vdpa_device *vdpa)
+{
+	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+	return vp_legacy_get_driver_features(ldev);
+}
+
 static u8 eni_vdpa_get_status(struct vdpa_device *vdpa)
 {
 	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
@@ -401,8 +408,9 @@ static void eni_vdpa_set_config_cb(struct vdpa_device *vdpa,
 }
 
 static const struct vdpa_config_ops eni_vdpa_ops = {
-	.get_features	= eni_vdpa_get_features,
-	.set_features	= eni_vdpa_set_features,
+	.get_device_features = eni_vdpa_get_device_features,
+	.set_driver_features = eni_vdpa_set_driver_features,
+	.get_driver_features = eni_vdpa_get_driver_features,
 	.get_status	= eni_vdpa_get_status,
 	.set_status	= eni_vdpa_set_status,
 	.reset		= eni_vdpa_reset,
@@ -450,11 +458,6 @@ static u16 eni_vdpa_get_num_queues(struct eni_vdpa *eni_vdpa)
 	return num;
 }
 
-static void eni_vdpa_free_irq_vectors(void *data)
-{
-	pci_free_irq_vectors(data);
-}
-
 static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct device *dev = &pdev->dev;
@@ -488,13 +491,6 @@ static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	eni_vdpa->vdpa.dma_dev = &pdev->dev;
 	eni_vdpa->queues = eni_vdpa_get_num_queues(eni_vdpa);
 
-	ret = devm_add_action_or_reset(dev, eni_vdpa_free_irq_vectors, pdev);
-	if (ret) {
-		ENI_ERR(pdev,
-			"failed for adding devres for freeing irq vectors\n");
-		goto err;
-	}
-
 	eni_vdpa->vring = devm_kcalloc(&pdev->dev, eni_vdpa->queues,
 				      sizeof(*eni_vdpa->vring),
 				      GFP_KERNEL);

drivers/vdpa/ifcvf/ifcvf_base.c

@@ -143,8 +143,8 @@ int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *pdev)
 			IFCVF_DBG(pdev, "hw->isr = %p\n", hw->isr);
 			break;
 		case VIRTIO_PCI_CAP_DEVICE_CFG:
-			hw->net_cfg = get_cap_addr(hw, &cap);
-			IFCVF_DBG(pdev, "hw->net_cfg = %p\n", hw->net_cfg);
+			hw->dev_cfg = get_cap_addr(hw, &cap);
+			IFCVF_DBG(pdev, "hw->dev_cfg = %p\n", hw->dev_cfg);
 			break;
 		}
 
@@ -153,7 +153,7 @@ int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *pdev)
 	}
 
 	if (hw->common_cfg == NULL || hw->notify_base == NULL ||
-	    hw->isr == NULL || hw->net_cfg == NULL) {
+	    hw->isr == NULL || hw->dev_cfg == NULL) {
 		IFCVF_ERR(pdev, "Incomplete PCI capabilities\n");
 		return -EIO;
 	}
@@ -174,7 +174,7 @@ int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *pdev)
 	IFCVF_DBG(pdev,
 		  "PCI capability mapping: common cfg: %p, notify base: %p\n, isr cfg: %p, device cfg: %p, multiplier: %u\n",
 		  hw->common_cfg, hw->notify_base, hw->isr,
-		  hw->net_cfg, hw->notify_off_multiplier);
+		  hw->dev_cfg, hw->notify_off_multiplier);
 
 	return 0;
 }
@@ -242,33 +242,54 @@ int ifcvf_verify_min_features(struct ifcvf_hw *hw, u64 features)
 	return 0;
 }
 
-void ifcvf_read_net_config(struct ifcvf_hw *hw, u64 offset,
+u32 ifcvf_get_config_size(struct ifcvf_hw *hw)
+{
+	struct ifcvf_adapter *adapter;
+	u32 config_size;
+
+	adapter = vf_to_adapter(hw);
+	switch (hw->dev_type) {
+	case VIRTIO_ID_NET:
+		config_size = sizeof(struct virtio_net_config);
+		break;
+	case VIRTIO_ID_BLOCK:
+		config_size = sizeof(struct virtio_blk_config);
+		break;
+	default:
+		config_size = 0;
+		IFCVF_ERR(adapter->pdev, "VIRTIO ID %u not supported\n", hw->dev_type);
+	}
+
+	return config_size;
+}
+
+void ifcvf_read_dev_config(struct ifcvf_hw *hw, u64 offset,
 			   void *dst, int length)
 {
 	u8 old_gen, new_gen, *p;
 	int i;
 
-	WARN_ON(offset + length > sizeof(struct virtio_net_config));
+	WARN_ON(offset + length > hw->config_size);
 	do {
 		old_gen = ifc_ioread8(&hw->common_cfg->config_generation);
 		p = dst;
 		for (i = 0; i < length; i++)
-			*p++ = ifc_ioread8(hw->net_cfg + offset + i);
+			*p++ = ifc_ioread8(hw->dev_cfg + offset + i);
 
 		new_gen = ifc_ioread8(&hw->common_cfg->config_generation);
 	} while (old_gen != new_gen);
 }
 
-void ifcvf_write_net_config(struct ifcvf_hw *hw, u64 offset,
+void ifcvf_write_dev_config(struct ifcvf_hw *hw, u64 offset,
 			    const void *src, int length)
 {
 	const u8 *p;
 	int i;
 
 	p = src;
-	WARN_ON(offset + length > sizeof(struct virtio_net_config));
+	WARN_ON(offset + length > hw->config_size);
 	for (i = 0; i < length; i++)
-		ifc_iowrite8(*p++, hw->net_cfg + offset + i);
+		ifc_iowrite8(*p++, hw->dev_cfg + offset + i);
 }
 
 static void ifcvf_set_features(struct ifcvf_hw *hw, u64 features)

drivers/vdpa/ifcvf/ifcvf_base.h

@@ -71,12 +71,14 @@ struct ifcvf_hw {
 	u64 hw_features;
 	u32 dev_type;
 	struct virtio_pci_common_cfg __iomem *common_cfg;
-	void __iomem *net_cfg;
+	void __iomem *dev_cfg;
 	struct vring_info vring[IFCVF_MAX_QUEUES];
 	void __iomem * const *base;
 	char config_msix_name[256];
 	struct vdpa_callback config_cb;
 	unsigned int config_irq;
+	/* virtio-net or virtio-blk device config size */
+	u32 config_size;
 };
 
 struct ifcvf_adapter {
@@ -105,9 +107,9 @@ int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *dev);
 int ifcvf_start_hw(struct ifcvf_hw *hw);
 void ifcvf_stop_hw(struct ifcvf_hw *hw);
 void ifcvf_notify_queue(struct ifcvf_hw *hw, u16 qid);
-void ifcvf_read_net_config(struct ifcvf_hw *hw, u64 offset,
+void ifcvf_read_dev_config(struct ifcvf_hw *hw, u64 offset,
 			   void *dst, int length);
-void ifcvf_write_net_config(struct ifcvf_hw *hw, u64 offset,
+void ifcvf_write_dev_config(struct ifcvf_hw *hw, u64 offset,
 			    const void *src, int length);
 u8 ifcvf_get_status(struct ifcvf_hw *hw);
 void ifcvf_set_status(struct ifcvf_hw *hw, u8 status);
@@ -120,4 +122,5 @@ u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid);
 int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num);
 struct ifcvf_adapter *vf_to_adapter(struct ifcvf_hw *hw);
 int ifcvf_probed_virtio_net(struct ifcvf_hw *hw);
+u32 ifcvf_get_config_size(struct ifcvf_hw *hw);
 #endif /* _IFCVF_H_ */

drivers/vdpa/ifcvf/ifcvf_main.c

@@ -169,7 +169,7 @@ static struct ifcvf_hw *vdpa_to_vf(struct vdpa_device *vdpa_dev)
 	return &adapter->vf;
 }
 
-static u64 ifcvf_vdpa_get_features(struct vdpa_device *vdpa_dev)
+static u64 ifcvf_vdpa_get_device_features(struct vdpa_device *vdpa_dev)
 {
 	struct ifcvf_adapter *adapter = vdpa_to_adapter(vdpa_dev);
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
@@ -187,7 +187,7 @@ static u64 ifcvf_vdpa_get_features(struct vdpa_device *vdpa_dev)
 	return features;
 }
 
-static int ifcvf_vdpa_set_features(struct vdpa_device *vdpa_dev, u64 features)
+static int ifcvf_vdpa_set_driver_features(struct vdpa_device *vdpa_dev, u64 features)
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
 	int ret;
@@ -201,6 +201,13 @@ static int ifcvf_vdpa_set_features(struct vdpa_device *vdpa_dev, u64 features)
 	return 0;
 }
 
+static u64 ifcvf_vdpa_get_driver_features(struct vdpa_device *vdpa_dev)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	return vf->req_features;
+}
+
 static u8 ifcvf_vdpa_get_status(struct vdpa_device *vdpa_dev)
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
@@ -366,24 +373,9 @@ static u32 ifcvf_vdpa_get_vq_align(struct vdpa_device *vdpa_dev)
 
 static size_t ifcvf_vdpa_get_config_size(struct vdpa_device *vdpa_dev)
 {
-	struct ifcvf_adapter *adapter = vdpa_to_adapter(vdpa_dev);
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
-	struct pci_dev *pdev = adapter->pdev;
-	size_t size;
-
-	switch (vf->dev_type) {
-	case VIRTIO_ID_NET:
-		size = sizeof(struct virtio_net_config);
-		break;
-	case VIRTIO_ID_BLOCK:
-		size = sizeof(struct virtio_blk_config);
-		break;
-	default:
-		size = 0;
-		IFCVF_ERR(pdev, "VIRTIO ID %u not supported\n", vf->dev_type);
-	}
 
-	return size;
+	return  vf->config_size;
 }
 
 static void ifcvf_vdpa_get_config(struct vdpa_device *vdpa_dev,
@@ -392,8 +384,7 @@ static void ifcvf_vdpa_get_config(struct vdpa_device *vdpa_dev,
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
 
-	WARN_ON(offset + len > sizeof(struct virtio_net_config));
-	ifcvf_read_net_config(vf, offset, buf, len);
+	ifcvf_read_dev_config(vf, offset, buf, len);
 }
 
 static void ifcvf_vdpa_set_config(struct vdpa_device *vdpa_dev,
@@ -402,8 +393,7 @@ static void ifcvf_vdpa_set_config(struct vdpa_device *vdpa_dev,
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
 
-	WARN_ON(offset + len > sizeof(struct virtio_net_config));
-	ifcvf_write_net_config(vf, offset, buf, len);
+	ifcvf_write_dev_config(vf, offset, buf, len);
 }
 
 static void ifcvf_vdpa_set_config_cb(struct vdpa_device *vdpa_dev,
@@ -443,8 +433,9 @@ static struct vdpa_notification_area ifcvf_get_vq_notification(struct vdpa_devic
  * implemented set_map()/dma_map()/dma_unmap()
  */
 static const struct vdpa_config_ops ifc_vdpa_ops = {
-	.get_features	= ifcvf_vdpa_get_features,
-	.set_features	= ifcvf_vdpa_set_features,
+	.get_device_features = ifcvf_vdpa_get_device_features,
+	.set_driver_features = ifcvf_vdpa_set_driver_features,
+	.get_driver_features = ifcvf_vdpa_get_driver_features,
 	.get_status	= ifcvf_vdpa_get_status,
 	.set_status	= ifcvf_vdpa_set_status,
 	.reset		= ifcvf_vdpa_reset,
@@ -542,6 +533,7 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
 		vf->vring[i].irq = -EINVAL;
 
 	vf->hw_features = ifcvf_get_hw_features(vf);
+	vf->config_size = ifcvf_get_config_size(vf);
 
 	adapter->vdpa.mdev = &ifcvf_mgmt_dev->mdev;
 	ret = _vdpa_register_device(&adapter->vdpa, vf->nr_vring);

drivers/vdpa/vdpa.c

@@ -21,6 +21,14 @@ static LIST_HEAD(mdev_head);
 static DEFINE_MUTEX(vdpa_dev_mutex);
 static DEFINE_IDA(vdpa_index_ida);
 
+void vdpa_set_status(struct vdpa_device *vdev, u8 status)
+{
+	mutex_lock(&vdev->cf_mutex);
+	vdev->config->set_status(vdev, status);
+	mutex_unlock(&vdev->cf_mutex);
+}
+EXPORT_SYMBOL(vdpa_set_status);
+
 static struct genl_family vdpa_nl_family;
 
 static int vdpa_dev_probe(struct device *d)
@@ -52,8 +60,81 @@ static void vdpa_dev_remove(struct device *d)
 		drv->remove(vdev);
 }
 
+static int vdpa_dev_match(struct device *dev, struct device_driver *drv)
+{
+	struct vdpa_device *vdev = dev_to_vdpa(dev);
+
+	/* Check override first, and if set, only use the named driver */
+	if (vdev->driver_override)
+		return strcmp(vdev->driver_override, drv->name) == 0;
+
+	/* Currently devices must be supported by all vDPA bus drivers */
+	return 1;
+}
+
+static ssize_t driver_override_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	struct vdpa_device *vdev = dev_to_vdpa(dev);
+	const char *driver_override, *old;
+	char *cp;
+
+	/* We need to keep extra room for a newline */
+	if (count >= (PAGE_SIZE - 1))
+		return -EINVAL;
+
+	driver_override = kstrndup(buf, count, GFP_KERNEL);
+	if (!driver_override)
+		return -ENOMEM;
+
+	cp = strchr(driver_override, '\n');
+	if (cp)
+		*cp = '\0';
+
+	device_lock(dev);
+	old = vdev->driver_override;
+	if (strlen(driver_override)) {
+		vdev->driver_override = driver_override;
+	} else {
+		kfree(driver_override);
+		vdev->driver_override = NULL;
+	}
+	device_unlock(dev);
+
+	kfree(old);
+
+	return count;
+}
+
+static ssize_t driver_override_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct vdpa_device *vdev = dev_to_vdpa(dev);
+	ssize_t len;
+
+	device_lock(dev);
+	len = snprintf(buf, PAGE_SIZE, "%s\n", vdev->driver_override);
+	device_unlock(dev);
+
+	return len;
+}
+static DEVICE_ATTR_RW(driver_override);
+
+static struct attribute *vdpa_dev_attrs[] = {
+	&dev_attr_driver_override.attr,
+	NULL,
+};
+
+static const struct attribute_group vdpa_dev_group = {
+	.attrs  = vdpa_dev_attrs,
+};
+__ATTRIBUTE_GROUPS(vdpa_dev);
+
 static struct bus_type vdpa_bus = {
 	.name  = "vdpa",
+	.dev_groups = vdpa_dev_groups,
+	.match = vdpa_dev_match,
 	.probe = vdpa_dev_probe,
 	.remove = vdpa_dev_remove,
 };
@@ -68,6 +149,7 @@ static void vdpa_release_dev(struct device *d)
 
 	ida_simple_remove(&vdpa_index_ida, vdev->index);
 	mutex_destroy(&vdev->cf_mutex);
+	kfree(vdev->driver_override);
 	kfree(vdev);
 }
 
@@ -300,6 +382,21 @@ void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev)
 }
 EXPORT_SYMBOL_GPL(vdpa_mgmtdev_unregister);
 
+static void vdpa_get_config_unlocked(struct vdpa_device *vdev,
+				     unsigned int offset,
+				     void *buf, unsigned int len)
+{
+	const struct vdpa_config_ops *ops = vdev->config;
+
+	/*
+	 * Config accesses aren't supposed to trigger before features are set.
+	 * If it does happen we assume a legacy guest.
+	 */
+	if (!vdev->features_valid)
+		vdpa_set_features(vdev, 0, true);
+	ops->get_config(vdev, offset, buf, len);
+}
+
 /**
  * vdpa_get_config - Get one or more device configuration fields.
  * @vdev: vdpa device to operate on
@@ -310,16 +407,8 @@ EXPORT_SYMBOL_GPL(vdpa_mgmtdev_unregister);
 void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset,
 		     void *buf, unsigned int len)
 {
-	const struct vdpa_config_ops *ops = vdev->config;
-
 	mutex_lock(&vdev->cf_mutex);
-	/*
-	 * Config accesses aren't supposed to trigger before features are set.
-	 * If it does happen we assume a legacy guest.
-	 */
-	if (!vdev->features_valid)
-		vdpa_set_features(vdev, 0);
-	ops->get_config(vdev, offset, buf, len);
+	vdpa_get_config_unlocked(vdev, offset, buf, len);
 	mutex_unlock(&vdev->cf_mutex);
 }
 EXPORT_SYMBOL_GPL(vdpa_get_config);
@@ -414,6 +503,16 @@ static int vdpa_mgmtdev_fill(const struct vdpa_mgmt_dev *mdev, struct sk_buff *m
 		err = -EMSGSIZE;
 		goto msg_err;
 	}
+	if (nla_put_u32(msg, VDPA_ATTR_DEV_MGMTDEV_MAX_VQS,
+			mdev->max_supported_vqs)) {
+		err = -EMSGSIZE;
+		goto msg_err;
+	}
+	if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_SUPPORTED_FEATURES,
+			      mdev->supported_features, VDPA_ATTR_PAD)) {
+		err = -EMSGSIZE;
+		goto msg_err;
+	}
 
 	genlmsg_end(msg, hdr);
 	return 0;
@@ -480,8 +579,9 @@ vdpa_nl_cmd_mgmtdev_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb)
 	return msg->len;
 }
 
-#define VDPA_DEV_NET_ATTRS_MASK ((1 << VDPA_ATTR_DEV_NET_CFG_MACADDR) | \
-				 (1 << VDPA_ATTR_DEV_NET_CFG_MTU))
+#define VDPA_DEV_NET_ATTRS_MASK (BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR) | \
+				 BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MTU)     | \
+				 BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP))
 
 static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *info)
 {
@@ -500,12 +600,22 @@ static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *i
 	if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]) {
 		macaddr = nla_data(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]);
 		memcpy(config.net.mac, macaddr, sizeof(config.net.mac));
-		config.mask |= (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR);
+		config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR);
 	}
 	if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MTU]) {
 		config.net.mtu =
 			nla_get_u16(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MTU]);
-		config.mask |= (1 << VDPA_ATTR_DEV_NET_CFG_MTU);
+		config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MTU);
+	}
+	if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MAX_VQP]) {
+		config.net.max_vq_pairs =
+			nla_get_u16(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MAX_VQP]);
+		if (!config.net.max_vq_pairs) {
+			NL_SET_ERR_MSG_MOD(info->extack,
+					   "At least one pair of VQs is required");
+			return -EINVAL;
+		}
+		config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP);
 	}
 
 	/* Skip checking capability if user didn't prefer to configure any
@@ -707,7 +817,7 @@ static int vdpa_dev_net_mq_config_fill(struct vdpa_device *vdev,
 {
 	u16 val_u16;
 
-	if ((features & (1ULL << VIRTIO_NET_F_MQ)) == 0)
+	if ((features & BIT_ULL(VIRTIO_NET_F_MQ)) == 0)
 		return 0;
 
 	val_u16 = le16_to_cpu(config->max_virtqueue_pairs);
@@ -720,7 +830,7 @@ static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *ms
 	u64 features;
 	u16 val_u16;
 
-	vdpa_get_config(vdev, 0, &config, sizeof(config));
+	vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config));
 
 	if (nla_put(msg, VDPA_ATTR_DEV_NET_CFG_MACADDR, sizeof(config.mac),
 		    config.mac))
@@ -734,7 +844,10 @@ static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *ms
 	if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MTU, val_u16))
 		return -EMSGSIZE;
 
-	features = vdev->config->get_features(vdev);
+	features = vdev->config->get_driver_features(vdev);
+	if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES, features,
+			      VDPA_ATTR_PAD))
+		return -EMSGSIZE;
 
 	return vdpa_dev_net_mq_config_fill(vdev, msg, features, &config);
 }
@@ -745,12 +858,23 @@ vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid,
 {
 	u32 device_id;
 	void *hdr;
+	u8 status;
 	int err;
 
+	mutex_lock(&vdev->cf_mutex);
+	status = vdev->config->get_status(vdev);
+	if (!(status & VIRTIO_CONFIG_S_FEATURES_OK)) {
+		NL_SET_ERR_MSG_MOD(extack, "Features negotiation not completed");
+		err = -EAGAIN;
+		goto out;
+	}
+
 	hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags,
 			  VDPA_CMD_DEV_CONFIG_GET);
-	if (!hdr)
-		return -EMSGSIZE;
+	if (!hdr) {
+		err = -EMSGSIZE;
+		goto out;
+	}
 
 	if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) {
 		err = -EMSGSIZE;
@@ -774,11 +898,14 @@ vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid,
 	if (err)
 		goto msg_err;
 
+	mutex_unlock(&vdev->cf_mutex);
 	genlmsg_end(msg, hdr);
 	return 0;
 
 msg_err:
 	genlmsg_cancel(msg, hdr);
+out:
+	mutex_unlock(&vdev->cf_mutex);
 	return err;
 }
 

drivers/vdpa/vdpa_sim/vdpa_sim.c

@@ -399,14 +399,14 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)
 	return VDPASIM_QUEUE_ALIGN;
 }
 
-static u64 vdpasim_get_features(struct vdpa_device *vdpa)
+static u64 vdpasim_get_device_features(struct vdpa_device *vdpa)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
 
 	return vdpasim->dev_attr.supported_features;
 }
 
-static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features)
+static int vdpasim_set_driver_features(struct vdpa_device *vdpa, u64 features)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
 
@@ -419,6 +419,13 @@ static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features)
 	return 0;
 }
 
+static u64 vdpasim_get_driver_features(struct vdpa_device *vdpa)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	return vdpasim->features;
+}
+
 static void vdpasim_set_config_cb(struct vdpa_device *vdpa,
 				  struct vdpa_callback *cb)
 {
@@ -613,8 +620,9 @@ static const struct vdpa_config_ops vdpasim_config_ops = {
 	.set_vq_state           = vdpasim_set_vq_state,
 	.get_vq_state           = vdpasim_get_vq_state,
 	.get_vq_align           = vdpasim_get_vq_align,
-	.get_features           = vdpasim_get_features,
-	.set_features           = vdpasim_set_features,
+	.get_device_features    = vdpasim_get_device_features,
+	.set_driver_features    = vdpasim_set_driver_features,
+	.get_driver_features    = vdpasim_get_driver_features,
 	.set_config_cb          = vdpasim_set_config_cb,
 	.get_vq_num_max         = vdpasim_get_vq_num_max,
 	.get_device_id          = vdpasim_get_device_id,
@@ -642,8 +650,9 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = {
 	.set_vq_state           = vdpasim_set_vq_state,
 	.get_vq_state           = vdpasim_get_vq_state,
 	.get_vq_align           = vdpasim_get_vq_align,
-	.get_features           = vdpasim_get_features,
-	.set_features           = vdpasim_set_features,
+	.get_device_features    = vdpasim_get_device_features,
+	.set_driver_features    = vdpasim_set_driver_features,
+	.get_driver_features    = vdpasim_get_driver_features,
 	.set_config_cb          = vdpasim_set_config_cb,
 	.get_vq_num_max         = vdpasim_get_vq_num_max,
 	.get_device_id          = vdpasim_get_device_id,

drivers/vdpa/vdpa_sim/vdpa_sim_net.c

@@ -191,6 +191,8 @@ static struct vdpa_mgmt_dev mgmt_dev = {
 	.ops = &vdpasim_net_mgmtdev_ops,
 	.config_attr_mask = (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR |
 			     1 << VDPA_ATTR_DEV_NET_CFG_MTU),
+	.max_supported_vqs = VDPASIM_NET_VQ_NUM,
+	.supported_features = VDPASIM_NET_FEATURES,
 };
 
 static int __init vdpasim_net_init(void)

drivers/vdpa/vdpa_user/vduse_dev.c

@@ -573,14 +573,14 @@ static u32 vduse_vdpa_get_vq_align(struct vdpa_device *vdpa)
 	return dev->vq_align;
 }
 
-static u64 vduse_vdpa_get_features(struct vdpa_device *vdpa)
+static u64 vduse_vdpa_get_device_features(struct vdpa_device *vdpa)
 {
 	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
 
 	return dev->device_features;
 }
 
-static int vduse_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
+static int vduse_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features)
 {
 	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
 
@@ -588,6 +588,13 @@ static int vduse_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
 	return 0;
 }
 
+static u64 vduse_vdpa_get_driver_features(struct vdpa_device *vdpa)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+	return dev->driver_features;
+}
+
 static void vduse_vdpa_set_config_cb(struct vdpa_device *vdpa,
 				  struct vdpa_callback *cb)
 {
@@ -721,8 +728,9 @@ static const struct vdpa_config_ops vduse_vdpa_config_ops = {
 	.set_vq_state		= vduse_vdpa_set_vq_state,
 	.get_vq_state		= vduse_vdpa_get_vq_state,
 	.get_vq_align		= vduse_vdpa_get_vq_align,
-	.get_features		= vduse_vdpa_get_features,
-	.set_features		= vduse_vdpa_set_features,
+	.get_device_features	= vduse_vdpa_get_device_features,
+	.set_driver_features	= vduse_vdpa_set_driver_features,
+	.get_driver_features	= vduse_vdpa_get_driver_features,
 	.set_config_cb		= vduse_vdpa_set_config_cb,
 	.get_vq_num_max		= vduse_vdpa_get_vq_num_max,
 	.get_device_id		= vduse_vdpa_get_device_id,
@@ -1357,7 +1365,6 @@ static int vduse_create_dev(struct vduse_dev_config *config,
 err_str:
 	vduse_dev_destroy(dev);
 err:
-	kvfree(config_buf);
 	return ret;
 }
 
@@ -1408,6 +1415,8 @@ static long vduse_ioctl(struct file *file, unsigned int cmd,
 		}
 		config.name[VDUSE_NAME_MAX - 1] = '\0';
 		ret = vduse_create_dev(&config, buf, control->api_version);
+		if (ret)
+			kvfree(buf);
 		break;
 	}
 	case VDUSE_DESTROY_DEV: {

drivers/vdpa/virtio_pci/vp_vdpa.c

@@ -53,14 +53,14 @@ static struct virtio_pci_modern_device *vdpa_to_mdev(struct vdpa_device *vdpa)
 	return &vp_vdpa->mdev;
 }
 
-static u64 vp_vdpa_get_features(struct vdpa_device *vdpa)
+static u64 vp_vdpa_get_device_features(struct vdpa_device *vdpa)
 {
 	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
 
 	return vp_modern_get_features(mdev);
 }
 
-static int vp_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
+static int vp_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features)
 {
 	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
 
@@ -69,6 +69,13 @@ static int vp_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
 	return 0;
 }
 
+static u64 vp_vdpa_get_driver_features(struct vdpa_device *vdpa)
+{
+	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
+
+	return vp_modern_get_driver_features(mdev);
+}
+
 static u8 vp_vdpa_get_status(struct vdpa_device *vdpa)
 {
 	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
@@ -415,8 +422,9 @@ vp_vdpa_get_vq_notification(struct vdpa_device *vdpa, u16 qid)
 }
 
 static const struct vdpa_config_ops vp_vdpa_ops = {
-	.get_features	= vp_vdpa_get_features,
-	.set_features	= vp_vdpa_set_features,
+	.get_device_features = vp_vdpa_get_device_features,
+	.set_driver_features = vp_vdpa_set_driver_features,
+	.get_driver_features = vp_vdpa_get_driver_features,
 	.get_status	= vp_vdpa_get_status,
 	.set_status	= vp_vdpa_set_status,
 	.reset		= vp_vdpa_reset,

drivers/vhost/test.c

@@ -166,6 +166,7 @@ static int vhost_test_release(struct inode *inode, struct file *f)
 	/* We do an extra flush before freeing memory,
 	 * since jobs can re-queue themselves. */
 	vhost_test_flush(n);
+	kfree(n->dev.vqs);
 	kfree(n);
 	return 0;
 }

drivers/vhost/vdpa.c

@@ -170,7 +170,7 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp)
 	 * Userspace shouldn't remove status bits unless reset the
 	 * status to 0.
 	 */
-	if (status != 0 && (ops->get_status(vdpa) & ~status) != 0)
+	if (status != 0 && (status_old & ~status) != 0)
 		return -EINVAL;
 
 	if ((status_old & VIRTIO_CONFIG_S_DRIVER_OK) && !(status & VIRTIO_CONFIG_S_DRIVER_OK))
@@ -178,11 +178,11 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp)
 			vhost_vdpa_unsetup_vq_irq(v, i);
 
 	if (status == 0) {
-		ret = ops->reset(vdpa);
+		ret = vdpa_reset(vdpa);
 		if (ret)
 			return ret;
 	} else
-		ops->set_status(vdpa, status);
+		vdpa_set_status(vdpa, status);
 
 	if ((status & VIRTIO_CONFIG_S_DRIVER_OK) && !(status_old & VIRTIO_CONFIG_S_DRIVER_OK))
 		for (i = 0; i < nvqs; i++)
@@ -195,7 +195,7 @@ static int vhost_vdpa_config_validate(struct vhost_vdpa *v,
 				      struct vhost_vdpa_config *c)
 {
 	struct vdpa_device *vdpa = v->vdpa;
-	long size = vdpa->config->get_config_size(vdpa);
+	size_t size = vdpa->config->get_config_size(vdpa);
 
 	if (c->len == 0 || c->off > size)
 		return -EINVAL;
@@ -262,7 +262,7 @@ static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep)
 	const struct vdpa_config_ops *ops = vdpa->config;
 	u64 features;
 
-	features = ops->get_features(vdpa);
+	features = ops->get_device_features(vdpa);
 
 	if (copy_to_user(featurep, &features, sizeof(features)))
 		return -EFAULT;
@@ -286,7 +286,7 @@ static long vhost_vdpa_set_features(struct vhost_vdpa *v, u64 __user *featurep)
 	if (copy_from_user(&features, featurep, sizeof(features)))
 		return -EFAULT;
 
-	if (vdpa_set_features(vdpa, features))
+	if (vdpa_set_features(vdpa, features, false))
 		return -EINVAL;
 
 	return 0;

drivers/virtio/virtio.c

@@ -204,6 +204,12 @@ int virtio_finalize_features(struct virtio_device *dev)
 }
 EXPORT_SYMBOL_GPL(virtio_finalize_features);
 
+void virtio_reset_device(struct virtio_device *dev)
+{
+	dev->config->reset(dev);
+}
+EXPORT_SYMBOL_GPL(virtio_reset_device);
+
 static int virtio_dev_probe(struct device *_d)
 {
 	int err, i;

drivers/virtio/virtio_balloon.c

@@ -1056,7 +1056,7 @@ static void remove_common(struct virtio_balloon *vb)
 		return_free_pages_to_mm(vb, ULONG_MAX);
 
 	/* Now we reset the device so we can clean up the queues. */
-	vb->vdev->config->reset(vb->vdev);
+	virtio_reset_device(vb->vdev);
 
 	vb->vdev->config->del_vqs(vb->vdev);
 }

drivers/virtio/virtio_input.c

@@ -347,7 +347,7 @@ static void virtinput_remove(struct virtio_device *vdev)
 	spin_unlock_irqrestore(&vi->lock, flags);
 
 	input_unregister_device(vi->idev);
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	while ((buf = virtqueue_detach_unused_buf(vi->sts)) != NULL)
 		kfree(buf);
 	vdev->config->del_vqs(vdev);

drivers/virtio/virtio_mem.c

@@ -20,6 +20,7 @@
 #include <linux/mutex.h>
 #include <linux/bitmap.h>
 #include <linux/lockdep.h>
+#include <linux/log2.h>
 
 #include <acpi/acpi_numa.h>
 
@@ -592,7 +593,7 @@ static int virtio_mem_sbm_sb_states_prepare_next_mb(struct virtio_mem *vm)
 		return -ENOMEM;
 
 	mutex_lock(&vm->hotplug_mutex);
-	if (new_bitmap)
+	if (vm->sbm.sb_states)
 		memcpy(new_bitmap, vm->sbm.sb_states, old_pages * PAGE_SIZE);
 
 	old_bitmap = vm->sbm.sb_states;
@@ -1120,15 +1121,18 @@ static void virtio_mem_clear_fake_offline(unsigned long pfn,
  */
 static void virtio_mem_fake_online(unsigned long pfn, unsigned long nr_pages)
 {
-	const unsigned long max_nr_pages = MAX_ORDER_NR_PAGES;
+	unsigned long order = MAX_ORDER - 1;
 	unsigned long i;
 
 	/*
-	 * We are always called at least with MAX_ORDER_NR_PAGES
-	 * granularity/alignment (e.g., the way subblocks work). All pages
-	 * inside such a block are alike.
+	 * We might get called for ranges that don't cover properly aligned
+	 * MAX_ORDER - 1 pages; however, we can only online properly aligned
+	 * pages with an order of MAX_ORDER - 1 at maximum.
 	 */
-	for (i = 0; i < nr_pages; i += max_nr_pages) {
+	while (!IS_ALIGNED(pfn | nr_pages, 1 << order))
+		order--;
+
+	for (i = 0; i < nr_pages; i += 1 << order) {
 		struct page *page = pfn_to_page(pfn + i);
 
 		/*
@@ -1138,14 +1142,12 @@ static void virtio_mem_fake_online(unsigned long pfn, unsigned long nr_pages)
 		 * alike.
 		 */
 		if (PageDirty(page)) {
-			virtio_mem_clear_fake_offline(pfn + i, max_nr_pages,
-						      false);
-			generic_online_page(page, MAX_ORDER - 1);
+			virtio_mem_clear_fake_offline(pfn + i, 1 << order, false);
+			generic_online_page(page, order);
 		} else {
-			virtio_mem_clear_fake_offline(pfn + i, max_nr_pages,
-						      true);
-			free_contig_range(pfn + i, max_nr_pages);
-			adjust_managed_page_count(page, max_nr_pages);
+			virtio_mem_clear_fake_offline(pfn + i, 1 << order, true);
+			free_contig_range(pfn + i, 1 << order);
+			adjust_managed_page_count(page, 1 << order);
 		}
 	}
 }
@@ -1228,28 +1230,46 @@ static void virtio_mem_fake_offline_cancel_offline(unsigned long pfn,
 		page_ref_inc(pfn_to_page(pfn + i));
 }
 
-static void virtio_mem_online_page_cb(struct page *page, unsigned int order)
+static void virtio_mem_online_page(struct virtio_mem *vm,
+				   struct page *page, unsigned int order)
 {
-	const unsigned long addr = page_to_phys(page);
-	unsigned long id, sb_id;
-	struct virtio_mem *vm;
+	const unsigned long start = page_to_phys(page);
+	const unsigned long end = start + PFN_PHYS(1 << order);
+	unsigned long addr, next, id, sb_id, count;
 	bool do_online;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(vm, &virtio_mem_devices, next) {
-		if (!virtio_mem_contains_range(vm, addr, PFN_PHYS(1 << order)))
-			continue;
+	/*
+	 * We can get called with any order up to MAX_ORDER - 1. If our
+	 * subblock size is smaller than that and we have a mixture of plugged
+	 * and unplugged subblocks within such a page, we have to process in
+	 * smaller granularity. In that case we'll adjust the order exactly once
+	 * within the loop.
+	 */
+	for (addr = start; addr < end; ) {
+		next = addr + PFN_PHYS(1 << order);
 
 		if (vm->in_sbm) {
-			/*
-			 * We exploit here that subblocks have at least
-			 * MAX_ORDER_NR_PAGES size/alignment - so we cannot
-			 * cross subblocks within one call.
-			 */
 			id = virtio_mem_phys_to_mb_id(addr);
 			sb_id = virtio_mem_phys_to_sb_id(vm, addr);
-			do_online = virtio_mem_sbm_test_sb_plugged(vm, id,
-								   sb_id, 1);
+			count = virtio_mem_phys_to_sb_id(vm, next - 1) - sb_id + 1;
+
+			if (virtio_mem_sbm_test_sb_plugged(vm, id, sb_id, count)) {
+				/* Fully plugged. */
+				do_online = true;
+			} else if (count == 1 ||
+				   virtio_mem_sbm_test_sb_unplugged(vm, id, sb_id, count)) {
+				/* Fully unplugged. */
+				do_online = false;
+			} else {
+				/*
+				 * Mixture, process sub-blocks instead. This
+				 * will be at least the size of a pageblock.
+				 * We'll run into this case exactly once.
+				 */
+				order = ilog2(vm->sbm.sb_size) - PAGE_SHIFT;
+				do_online = virtio_mem_sbm_test_sb_plugged(vm, id, sb_id, 1);
+				continue;
+			}
 		} else {
 			/*
 			 * If the whole block is marked fake offline, keep
@@ -1260,18 +1280,38 @@ static void virtio_mem_online_page_cb(struct page *page, unsigned int order)
 				    VIRTIO_MEM_BBM_BB_FAKE_OFFLINE;
 		}
 
+		if (do_online)
+			generic_online_page(pfn_to_page(PFN_DOWN(addr)), order);
+		else
+			virtio_mem_set_fake_offline(PFN_DOWN(addr), 1 << order,
+						    false);
+		addr = next;
+	}
+}
+
+static void virtio_mem_online_page_cb(struct page *page, unsigned int order)
+{
+	const unsigned long addr = page_to_phys(page);
+	struct virtio_mem *vm;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(vm, &virtio_mem_devices, next) {
+		/*
+		 * Pages we're onlining will never cross memory blocks and,
+		 * therefore, not virtio-mem devices.
+		 */
+		if (!virtio_mem_contains_range(vm, addr, PFN_PHYS(1 << order)))
+			continue;
+
 		/*
-		 * virtio_mem_set_fake_offline() might sleep, we don't need
-		 * the device anymore. See virtio_mem_remove() how races
+		 * virtio_mem_set_fake_offline() might sleep. We can safely
+		 * drop the RCU lock at this point because the device
+		 * cannot go away. See virtio_mem_remove() how races
 		 * between memory onlining and device removal are handled.
 		 */
 		rcu_read_unlock();
 
-		if (do_online)
-			generic_online_page(page, order);
-		else
-			virtio_mem_set_fake_offline(PFN_DOWN(addr), 1 << order,
-						    false);
+		virtio_mem_online_page(vm, page, order);
 		return;
 	}
 	rcu_read_unlock();
@@ -2438,8 +2478,6 @@ static int virtio_mem_init_hotplug(struct virtio_mem *vm)
 	/*
 	 * We want subblocks to span at least MAX_ORDER_NR_PAGES and
 	 * pageblock_nr_pages pages. This:
-	 * - Simplifies our page onlining code (virtio_mem_online_page_cb)
-	 *   and fake page onlining code (virtio_mem_fake_online).
 	 * - Is required for now for alloc_contig_range() to work reliably -
 	 *   it doesn't properly handle smaller granularity on ZONE_NORMAL.
 	 */
@@ -2850,7 +2888,7 @@ static void virtio_mem_remove(struct virtio_device *vdev)
 		virtio_mem_deinit_hotplug(vm);
 
 	/* reset the device and cleanup the queues */
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	vdev->config->del_vqs(vdev);
 
 	kfree(vm);

drivers/virtio/virtio_pci_legacy.c

@@ -138,7 +138,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	q_pfn = virtqueue_get_desc_addr(vq) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT;
 	if (q_pfn >> 32) {
 		dev_err(&vp_dev->pci_dev->dev,
-			"platform bug: legacy virtio-mmio must not be used with RAM above 0x%llxGB\n",
+			"platform bug: legacy virtio-pci must not be used with RAM above 0x%llxGB\n",
 			0x1ULL << (32 + PAGE_SHIFT - 30));
 		err = -E2BIG;
 		goto out_del_vq;

drivers/virtio/virtio_pci_legacy_dev.c

@@ -45,8 +45,10 @@ int vp_legacy_probe(struct virtio_pci_legacy_device *ldev)
 		return rc;
 
 	ldev->ioaddr = pci_iomap(pci_dev, 0, 0);
-	if (!ldev->ioaddr)
+	if (!ldev->ioaddr) {
+		rc = -EIO;
 		goto err_iomap;
+	}
 
 	ldev->isr = ldev->ioaddr + VIRTIO_PCI_ISR;
 

drivers/virtio/virtio_pci_modern_dev.c

@@ -345,7 +345,7 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev)
 EXPORT_SYMBOL_GPL(vp_modern_probe);
 
 /*
- * vp_modern_probe: remove and cleanup the modern virtio pci device
+ * vp_modern_remove: remove and cleanup the modern virtio pci device
  * @mdev: the modern virtio-pci device
  */
 void vp_modern_remove(struct virtio_pci_modern_device *mdev)

drivers/virtio/virtio_ring.c

@@ -1197,8 +1197,10 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
 	if (virtqueue_use_indirect(_vq, total_sg)) {
 		err = virtqueue_add_indirect_packed(vq, sgs, total_sg, out_sgs,
 						    in_sgs, data, gfp);
-		if (err != -ENOMEM)
+		if (err != -ENOMEM) {
+			END_USE(vq);
 			return err;
+		}
 
 		/* fall back on direct */
 	}

drivers/virtio/virtio_vdpa.c

@@ -91,9 +91,8 @@ static u8 virtio_vdpa_get_status(struct virtio_device *vdev)
 static void virtio_vdpa_set_status(struct virtio_device *vdev, u8 status)
 {
 	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
-	const struct vdpa_config_ops *ops = vdpa->config;
 
-	return ops->set_status(vdpa, status);
+	return vdpa_set_status(vdpa, status);
 }
 
 static void virtio_vdpa_reset(struct virtio_device *vdev)
@@ -308,7 +307,7 @@ static u64 virtio_vdpa_get_features(struct virtio_device *vdev)
 	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
 	const struct vdpa_config_ops *ops = vdpa->config;
 
-	return ops->get_features(vdpa);
+	return ops->get_device_features(vdpa);
 }
 
 static int virtio_vdpa_finalize_features(struct virtio_device *vdev)
@@ -318,7 +317,7 @@ static int virtio_vdpa_finalize_features(struct virtio_device *vdev)
 	/* Give virtio_ring a chance to accept features. */
 	vring_transport_features(vdev);
 
-	return vdpa_set_features(vdpa, vdev->features);
+	return vdpa_set_features(vdpa, vdev->features, false);
 }
 
 static const char *virtio_vdpa_bus_name(struct virtio_device *vdev)

fs/fuse/virtio_fs.c

@@ -891,7 +891,7 @@ static int virtio_fs_probe(struct virtio_device *vdev)
 	return 0;
 
 out_vqs:
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	virtio_fs_cleanup_vqs(vdev, fs);
 	kfree(fs->vqs);
 
@@ -923,7 +923,7 @@ static void virtio_fs_remove(struct virtio_device *vdev)
 	list_del_init(&fs->list);
 	virtio_fs_stop_all_queues(fs);
 	virtio_fs_drain_all_queues_locked(fs);
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	virtio_fs_cleanup_vqs(vdev, fs);
 
 	vdev->priv = NULL;

include/linux/vdpa.h

@@ -64,6 +64,7 @@ struct vdpa_mgmt_dev;
  * struct vdpa_device - representation of a vDPA device
  * @dev: underlying device
  * @dma_dev: the actual device that is performing DMA
+ * @driver_override: driver name to force a match
  * @config: the configuration ops for this device.
  * @cf_mutex: Protects get and set access to configuration layout.
  * @index: device index
@@ -76,6 +77,7 @@ struct vdpa_mgmt_dev;
 struct vdpa_device {
 	struct device dev;
 	struct device *dma_dev;
+	const char *driver_override;
 	const struct vdpa_config_ops *config;
 	struct mutex cf_mutex; /* Protects get/set config */
 	unsigned int index;
@@ -99,6 +101,7 @@ struct vdpa_dev_set_config {
 	struct {
 		u8 mac[ETH_ALEN];
 		u16 mtu;
+		u16 max_vq_pairs;
 	} net;
 	u64 mask;
 };
@@ -155,7 +158,7 @@ struct vdpa_map_file {
  *				@vdev: vdpa device
  *				@idx: virtqueue index
  *				@state: pointer to returned state (last_avail_idx)
- * @get_vq_notification:	Get the notification area for a virtqueue
+ * @get_vq_notification:	Get the notification area for a virtqueue (optional)
  *				@vdev: vdpa device
  *				@idx: virtqueue index
  *				Returns the notifcation area
@@ -169,14 +172,17 @@ struct vdpa_map_file {
  *				for the device
  *				@vdev: vdpa device
  *				Returns virtqueue algin requirement
- * @get_features:		Get virtio features supported by the device
+ * @get_device_features:	Get virtio features supported by the device
  *				@vdev: vdpa device
  *				Returns the virtio features support by the
  *				device
- * @set_features:		Set virtio features supported by the driver
+ * @set_driver_features:	Set virtio features supported by the driver
  *				@vdev: vdpa device
  *				@features: feature support by the driver
  *				Returns integer: success (0) or error (< 0)
+ * @get_driver_features:	Get the virtio driver features in action
+ *				@vdev: vdpa device
+ *				Returns the virtio features accepted
  * @set_config_cb:		Set the config interrupt callback
  *				@vdev: vdpa device
  *				@cb: virtio-vdev interrupt callback structure
@@ -276,8 +282,9 @@ struct vdpa_config_ops {
 
 	/* Device ops */
 	u32 (*get_vq_align)(struct vdpa_device *vdev);
-	u64 (*get_features)(struct vdpa_device *vdev);
-	int (*set_features)(struct vdpa_device *vdev, u64 features);
+	u64 (*get_device_features)(struct vdpa_device *vdev);
+	int (*set_driver_features)(struct vdpa_device *vdev, u64 features);
+	u64 (*get_driver_features)(struct vdpa_device *vdev);
 	void (*set_config_cb)(struct vdpa_device *vdev,
 			      struct vdpa_callback *cb);
 	u16 (*get_vq_num_max)(struct vdpa_device *vdev);
@@ -385,23 +392,37 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev)
 static inline int vdpa_reset(struct vdpa_device *vdev)
 {
 	const struct vdpa_config_ops *ops = vdev->config;
+	int ret;
 
+	mutex_lock(&vdev->cf_mutex);
 	vdev->features_valid = false;
-	return ops->reset(vdev);
+	ret = ops->reset(vdev);
+	mutex_unlock(&vdev->cf_mutex);
+	return ret;
 }
 
-static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features)
+static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features, bool locked)
 {
 	const struct vdpa_config_ops *ops = vdev->config;
+	int ret;
+
+	if (!locked)
+		mutex_lock(&vdev->cf_mutex);
 
 	vdev->features_valid = true;
-	return ops->set_features(vdev, features);
+	ret = ops->set_driver_features(vdev, features);
+	if (!locked)
+		mutex_unlock(&vdev->cf_mutex);
+
+	return ret;
 }
 
 void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset,
 		     void *buf, unsigned int len);
 void vdpa_set_config(struct vdpa_device *dev, unsigned int offset,
 		     const void *buf, unsigned int length);
+void vdpa_set_status(struct vdpa_device *vdev, u8 status);
+
 /**
  * struct vdpa_mgmtdev_ops - vdpa device ops
  * @dev_add: Add a vdpa device using alloc and register
@@ -438,6 +459,8 @@ struct vdpa_mgmt_dev {
 	const struct virtio_device_id *id_table;
 	u64 config_attr_mask;
 	struct list_head list;
+	u64 supported_features;
+	u32 max_supported_vqs;
 };
 
 int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev);

include/linux/virtio.h

@@ -138,6 +138,7 @@ int virtio_finalize_features(struct virtio_device *dev);
 int virtio_device_freeze(struct virtio_device *dev);
 int virtio_device_restore(struct virtio_device *dev);
 #endif
+void virtio_reset_device(struct virtio_device *dev);
 
 size_t virtio_max_dma_size(struct virtio_device *vdev);
 

include/uapi/linux/vdpa.h

@@ -23,6 +23,9 @@ enum vdpa_command {
 enum vdpa_attr {
 	VDPA_ATTR_UNSPEC,
 
+	/* Pad attribute for 64b alignment */
+	VDPA_ATTR_PAD = VDPA_ATTR_UNSPEC,
+
 	/* bus name (optional) + dev name together make the parent device handle */
 	VDPA_ATTR_MGMTDEV_BUS_NAME,		/* string */
 	VDPA_ATTR_MGMTDEV_DEV_NAME,		/* string */
@@ -40,6 +43,9 @@ enum vdpa_attr {
 	VDPA_ATTR_DEV_NET_CFG_MAX_VQP,		/* u16 */
 	VDPA_ATTR_DEV_NET_CFG_MTU,		/* u16 */
 
+	VDPA_ATTR_DEV_NEGOTIATED_FEATURES,	/* u64 */
+	VDPA_ATTR_DEV_MGMTDEV_MAX_VQS,		/* u32 */
+	VDPA_ATTR_DEV_SUPPORTED_FEATURES,	/* u64 */
 	/* new attributes must be added above here */
 	VDPA_ATTR_MAX,
 };

net/9p/trans_virtio.c

@@ -721,7 +721,7 @@ static void p9_virtio_remove(struct virtio_device *vdev)
 
 	mutex_unlock(&virtio_9p_lock);
 
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 	vdev->config->del_vqs(vdev);
 
 	sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);

net/vmw_vsock/virtio_transport.c

@@ -665,7 +665,7 @@ static void virtio_vsock_remove(struct virtio_device *vdev)
 	vsock_for_each_connected_socket(virtio_vsock_reset_sock);
 
 	/* Stop all work handlers to make sure no one is accessing the device,
-	 * so we can safely call vdev->config->reset().
+	 * so we can safely call virtio_reset_device().
 	 */
 	mutex_lock(&vsock->rx_lock);
 	vsock->rx_run = false;
@@ -682,7 +682,7 @@ static void virtio_vsock_remove(struct virtio_device *vdev)
 	/* Flush all device writes and interrupts, device will not use any
 	 * more buffers.
 	 */
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 
 	mutex_lock(&vsock->rx_lock);
 	while ((pkt = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_RX])))

sound/virtio/virtio_card.c

@@ -350,7 +350,7 @@ static void virtsnd_remove(struct virtio_device *vdev)
 		snd_card_free(snd->card);
 
 	vdev->config->del_vqs(vdev);
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 
 	for (i = 0; snd->substreams && i < snd->nsubstreams; ++i) {
 		struct virtio_pcm_substream *vss = &snd->substreams[i];
@@ -379,7 +379,7 @@ static int virtsnd_freeze(struct virtio_device *vdev)
 	virtsnd_ctl_msg_cancel_all(snd);
 
 	vdev->config->del_vqs(vdev);
-	vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 
 	for (i = 0; i < snd->nsubstreams; ++i)
 		cancel_work_sync(&snd->substreams[i].elapsed_period);