Merge tag 'vfio-v6.8-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Add debugfs support, initially used for reporting device migration
   state (Longfang Liu)

 - Fixes and support for migration dirty tracking across multiple IOVA
   regions in the pds-vfio-pci driver (Brett Creeley)

 - Improved IOMMU allocation accounting visibility (Pasha Tatashin)

 - Virtio infrastructure and a new virtio-vfio-pci variant driver, which
   provides emulation of a legacy virtio interfaces on modern virtio
   hardware for virtio-net VF devices where the PF driver exposes
   support for legacy admin queues, ie. an emulated IO BAR on an SR-IOV
   VF to provide driver ABI compatibility to legacy devices (Yishai
   Hadas & Feng Liu)

 - Migration fixes for the hisi-acc-vfio-pci variant driver (Shameer
   Kolothum)

 - Kconfig dependency fix for new virtio-vfio-pci variant driver (Arnd
   Bergmann)

* tag 'vfio-v6.8-rc1' of https://github.com/awilliam/linux-vfio: (22 commits)
  vfio/virtio: fix virtio-pci dependency
  hisi_acc_vfio_pci: Update migration data pointer correctly on saving/resume
  vfio/virtio: Declare virtiovf_pci_aer_reset_done() static
  vfio/virtio: Introduce a vfio driver over virtio devices
  vfio/pci: Expose vfio_pci_core_iowrite/read##size()
  vfio/pci: Expose vfio_pci_core_setup_barmap()
  virtio-pci: Introduce APIs to execute legacy IO admin commands
  virtio-pci: Initialize the supported admin commands
  virtio-pci: Introduce admin commands
  virtio-pci: Introduce admin command sending function
  virtio-pci: Introduce admin virtqueue
  virtio: Define feature bit for administration virtqueue
  vfio/type1: account iommu allocations
  vfio/pds: Add multi-region support
  vfio/pds: Move seq/ack bitmaps into region struct
  vfio/pds: Pass region info to relevant functions
  vfio/pds: Move and rename region specific info
  vfio/pds: Only use a single SGL for both seq and ack
  vfio/pds: Fix calculations in pds_vfio_dirty_sync
  MAINTAINERS: Add vfio debugfs interface doc link
  ...

Documentation/ABI/testing/debugfs-vfio

+What:		/sys/kernel/debug/vfio
+Date:		December 2023
+KernelVersion:	6.8
+Contact:	Longfang Liu <liulongfang@huawei.com>
+Description:	This debugfs file directory is used for debugging
+		of vfio devices, it's a common directory for all vfio devices.
+		Vfio core will create a device subdirectory under this
+		directory.
+
+What:		/sys/kernel/debug/vfio/<device>/migration
+Date:		December 2023
+KernelVersion:	6.8
+Contact:	Longfang Liu <liulongfang@huawei.com>
+Description:	This debugfs file directory is used for debugging
+		of vfio devices that support live migration.
+		The debugfs of each vfio device that supports live migration
+		could be created under this directory.
+
+What:		/sys/kernel/debug/vfio/<device>/migration/state
+Date:		December 2023
+KernelVersion:	6.8
+Contact:	Longfang Liu <liulongfang@huawei.com>
+Description:	Read the live migration status of the vfio device.
+		The contents of the state file reflects the migration state
+		relative to those defined in the vfio_device_mig_state enum

MAINTAINERS

@@ -23002,6 +23002,7 @@ M:	Alex Williamson <alex.williamson@redhat.com>
 L:	kvm@vger.kernel.org
 S:	Maintained
 T:	git https://github.com/awilliam/linux-vfio.git
+F:	Documentation/ABI/testing/debugfs-vfio
 F:	Documentation/ABI/testing/sysfs-devices-vfio-dev
 F:	Documentation/driver-api/vfio.rst
 F:	drivers/vfio/
@@ -23037,6 +23038,13 @@ L:	kvm@vger.kernel.org
 S:	Maintained
 F:	drivers/vfio/pci/mlx5/
 
+VFIO VIRTIO PCI DRIVER
+M:	Yishai Hadas <yishaih@nvidia.com>
+L:	kvm@vger.kernel.org
+L:	virtualization@lists.linux-foundation.org
+S:	Maintained
+F:	drivers/vfio/pci/virtio
+
 VFIO PCI DEVICE SPECIFIC DRIVERS
 R:	Jason Gunthorpe <jgg@nvidia.com>
 R:	Yishai Hadas <yishaih@nvidia.com>

drivers/vfio/Kconfig

@@ -80,6 +80,16 @@ config VFIO_VIRQFD
 	select EVENTFD
 	default n
 
+config VFIO_DEBUGFS
+	bool "Export VFIO internals in DebugFS"
+	depends on DEBUG_FS
+	help
+	  Allows exposure of VFIO device internals. This option enables
+	  the use of debugfs by VFIO drivers as required. The device can
+	  cause the VFIO code create a top-level debug/vfio directory
+	  during initialization, and then populate a subdirectory with
+	  entries as required.
+
 source "drivers/vfio/pci/Kconfig"
 source "drivers/vfio/platform/Kconfig"
 source "drivers/vfio/mdev/Kconfig"

drivers/vfio/Makefile

@@ -7,6 +7,7 @@ vfio-$(CONFIG_VFIO_GROUP) += group.o
 vfio-$(CONFIG_IOMMUFD) += iommufd.o
 vfio-$(CONFIG_VFIO_CONTAINER) += container.o
 vfio-$(CONFIG_VFIO_VIRQFD) += virqfd.o
+vfio-$(CONFIG_VFIO_DEBUGFS) += debugfs.o
 
 obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
 obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o

drivers/vfio/debugfs.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, HiSilicon Ltd.
+ */
+
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/vfio.h>
+#include "vfio.h"
+
+static struct dentry *vfio_debugfs_root;
+
+static int vfio_device_state_read(struct seq_file *seq, void *data)
+{
+	struct device *vf_dev = seq->private;
+	struct vfio_device *vdev = container_of(vf_dev,
+						struct vfio_device, device);
+	enum vfio_device_mig_state state;
+	int ret;
+
+	BUILD_BUG_ON(VFIO_DEVICE_STATE_NR !=
+		     VFIO_DEVICE_STATE_PRE_COPY_P2P + 1);
+
+	ret = vdev->mig_ops->migration_get_state(vdev, &state);
+	if (ret)
+		return -EINVAL;
+
+	switch (state) {
+	case VFIO_DEVICE_STATE_ERROR:
+		seq_puts(seq, "ERROR\n");
+		break;
+	case VFIO_DEVICE_STATE_STOP:
+		seq_puts(seq, "STOP\n");
+		break;
+	case VFIO_DEVICE_STATE_RUNNING:
+		seq_puts(seq, "RUNNING\n");
+		break;
+	case VFIO_DEVICE_STATE_STOP_COPY:
+		seq_puts(seq, "STOP_COPY\n");
+		break;
+	case VFIO_DEVICE_STATE_RESUMING:
+		seq_puts(seq, "RESUMING\n");
+		break;
+	case VFIO_DEVICE_STATE_RUNNING_P2P:
+		seq_puts(seq, "RUNNING_P2P\n");
+		break;
+	case VFIO_DEVICE_STATE_PRE_COPY:
+		seq_puts(seq, "PRE_COPY\n");
+		break;
+	case VFIO_DEVICE_STATE_PRE_COPY_P2P:
+		seq_puts(seq, "PRE_COPY_P2P\n");
+		break;
+	default:
+		seq_puts(seq, "Invalid\n");
+	}
+
+	return 0;
+}
+
+void vfio_device_debugfs_init(struct vfio_device *vdev)
+{
+	struct device *dev = &vdev->device;
+
+	vdev->debug_root = debugfs_create_dir(dev_name(vdev->dev),
+					      vfio_debugfs_root);
+
+	if (vdev->mig_ops) {
+		struct dentry *vfio_dev_migration = NULL;
+
+		vfio_dev_migration = debugfs_create_dir("migration",
+							vdev->debug_root);
+		debugfs_create_devm_seqfile(dev, "state", vfio_dev_migration,
+					    vfio_device_state_read);
+	}
+}
+
+void vfio_device_debugfs_exit(struct vfio_device *vdev)
+{
+	debugfs_remove_recursive(vdev->debug_root);
+}
+
+void vfio_debugfs_create_root(void)
+{
+	vfio_debugfs_root = debugfs_create_dir("vfio", NULL);
+}
+
+void vfio_debugfs_remove_root(void)
+{
+	debugfs_remove_recursive(vfio_debugfs_root);
+	vfio_debugfs_root = NULL;
+}

drivers/vfio/pci/Kconfig

@@ -65,4 +65,6 @@ source "drivers/vfio/pci/hisilicon/Kconfig"
 
 source "drivers/vfio/pci/pds/Kconfig"
 
+source "drivers/vfio/pci/virtio/Kconfig"
+
 endmenu

drivers/vfio/pci/Makefile

@@ -13,3 +13,5 @@ obj-$(CONFIG_MLX5_VFIO_PCI)           += mlx5/
 obj-$(CONFIG_HISI_ACC_VFIO_PCI) += hisilicon/
 
 obj-$(CONFIG_PDS_VFIO_PCI) += pds/
+
+obj-$(CONFIG_VIRTIO_VFIO_PCI) += virtio/

drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c

@@ -694,6 +694,7 @@ static ssize_t hisi_acc_vf_resume_write(struct file *filp, const char __user *bu
 					size_t len, loff_t *pos)
 {
 	struct hisi_acc_vf_migration_file *migf = filp->private_data;
+	u8 *vf_data = (u8 *)&migf->vf_data;
 	loff_t requested_length;
 	ssize_t done = 0;
 	int ret;
@@ -715,7 +716,7 @@ static ssize_t hisi_acc_vf_resume_write(struct file *filp, const char __user *bu
 		goto out_unlock;
 	}
 
-	ret = copy_from_user(&migf->vf_data, buf, len);
+	ret = copy_from_user(vf_data + *pos, buf, len);
 	if (ret) {
 		done = -EFAULT;
 		goto out_unlock;
@@ -835,7 +836,9 @@ static ssize_t hisi_acc_vf_save_read(struct file *filp, char __user *buf, size_t
 
 	len = min_t(size_t, migf->total_length - *pos, len);
 	if (len) {
-		ret = copy_to_user(buf, &migf->vf_data, len);
+		u8 *vf_data = (u8 *)&migf->vf_data;
+
+		ret = copy_to_user(buf, vf_data + *pos, len);
 		if (ret) {
 			done = -EFAULT;
 			goto out_unlock;

drivers/vfio/pci/pds/dirty.c

@@ -70,7 +70,7 @@ pds_vfio_print_guest_region_info(struct pds_vfio_pci_device *pds_vfio,
 	kfree(region_info);
 }
 
-static int pds_vfio_dirty_alloc_bitmaps(struct pds_vfio_dirty *dirty,
+static int pds_vfio_dirty_alloc_bitmaps(struct pds_vfio_region *region,
 					unsigned long bytes)
 {
 	unsigned long *host_seq_bmp, *host_ack_bmp;
@@ -85,46 +85,62 @@ static int pds_vfio_dirty_alloc_bitmaps(struct pds_vfio_dirty *dirty,
 		return -ENOMEM;
 	}
 
-	dirty->host_seq.bmp = host_seq_bmp;
-	dirty->host_ack.bmp = host_ack_bmp;
+	region->host_seq = host_seq_bmp;
+	region->host_ack = host_ack_bmp;
+	region->bmp_bytes = bytes;
 
 	return 0;
 }
 
 static void pds_vfio_dirty_free_bitmaps(struct pds_vfio_dirty *dirty)
 {
-	vfree(dirty->host_seq.bmp);
-	vfree(dirty->host_ack.bmp);
-	dirty->host_seq.bmp = NULL;
-	dirty->host_ack.bmp = NULL;
+	if (!dirty->regions)
+		return;
+
+	for (int i = 0; i < dirty->num_regions; i++) {
+		struct pds_vfio_region *region = &dirty->regions[i];
+
+		vfree(region->host_seq);
+		vfree(region->host_ack);
+		region->host_seq = NULL;
+		region->host_ack = NULL;
+		region->bmp_bytes = 0;
+	}
 }
 
 static void __pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio,
-				      struct pds_vfio_bmp_info *bmp_info)
+				      struct pds_vfio_region *region)
 {
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
 
-	dma_unmap_single(pdsc_dev, bmp_info->sgl_addr,
-			 bmp_info->num_sge * sizeof(struct pds_lm_sg_elem),
+	dma_unmap_single(pdsc_dev, region->sgl_addr,
+			 region->num_sge * sizeof(struct pds_lm_sg_elem),
 			 DMA_BIDIRECTIONAL);
-	kfree(bmp_info->sgl);
+	kfree(region->sgl);
 
-	bmp_info->num_sge = 0;
-	bmp_info->sgl = NULL;
-	bmp_info->sgl_addr = 0;
+	region->num_sge = 0;
+	region->sgl = NULL;
+	region->sgl_addr = 0;
 }
 
 static void pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio)
 {
-	if (pds_vfio->dirty.host_seq.sgl)
-		__pds_vfio_dirty_free_sgl(pds_vfio, &pds_vfio->dirty.host_seq);
-	if (pds_vfio->dirty.host_ack.sgl)
-		__pds_vfio_dirty_free_sgl(pds_vfio, &pds_vfio->dirty.host_ack);
+	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+
+	if (!dirty->regions)
+		return;
+
+	for (int i = 0; i < dirty->num_regions; i++) {
+		struct pds_vfio_region *region = &dirty->regions[i];
+
+		if (region->sgl)
+			__pds_vfio_dirty_free_sgl(pds_vfio, region);
+	}
 }
 
-static int __pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
-				      struct pds_vfio_bmp_info *bmp_info,
+static int pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
+				    struct pds_vfio_region *region,
 				    u32 page_count)
 {
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
@@ -147,32 +163,81 @@ static int __pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
 		return -EIO;
 	}
 
-	bmp_info->sgl = sgl;
-	bmp_info->num_sge = max_sge;
-	bmp_info->sgl_addr = sgl_addr;
+	region->sgl = sgl;
+	region->num_sge = max_sge;
+	region->sgl_addr = sgl_addr;
 
 	return 0;
 }
 
-static int pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
-				    u32 page_count)
+static void pds_vfio_dirty_free_regions(struct pds_vfio_dirty *dirty)
+{
+	vfree(dirty->regions);
+	dirty->regions = NULL;
+	dirty->num_regions = 0;
+}
+
+static int pds_vfio_dirty_alloc_regions(struct pds_vfio_pci_device *pds_vfio,
+					struct pds_lm_dirty_region_info *region_info,
+					u64 region_page_size, u8 num_regions)
 {
+	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+	u32 dev_bmp_offset_byte = 0;
 	int err;
 
-	err = __pds_vfio_dirty_alloc_sgl(pds_vfio, &dirty->host_seq,
-					 page_count);
-	if (err)
-		return err;
+	dirty->regions = vcalloc(num_regions, sizeof(struct pds_vfio_region));
+	if (!dirty->regions)
+		return -ENOMEM;
+	dirty->num_regions = num_regions;
+
+	for (int i = 0; i < num_regions; i++) {
+		struct pds_lm_dirty_region_info *ri = &region_info[i];
+		struct pds_vfio_region *region = &dirty->regions[i];
+		u64 region_size, region_start;
+		u32 page_count;
+
+		/* page_count might be adjusted by the device */
+		page_count = le32_to_cpu(ri->page_count);
+		region_start = le64_to_cpu(ri->dma_base);
+		region_size = page_count * region_page_size;
 
-	err = __pds_vfio_dirty_alloc_sgl(pds_vfio, &dirty->host_ack,
-					 page_count);
+		err = pds_vfio_dirty_alloc_bitmaps(region,
+						   page_count / BITS_PER_BYTE);
 		if (err) {
-		__pds_vfio_dirty_free_sgl(pds_vfio, &dirty->host_seq);
-		return err;
+			dev_err(&pdev->dev, "Failed to alloc dirty bitmaps: %pe\n",
+				ERR_PTR(err));
+			goto out_free_regions;
+		}
+
+		err = pds_vfio_dirty_alloc_sgl(pds_vfio, region, page_count);
+		if (err) {
+			dev_err(&pdev->dev, "Failed to alloc dirty sg lists: %pe\n",
+				ERR_PTR(err));
+			goto out_free_regions;
+		}
+
+		region->size = region_size;
+		region->start = region_start;
+		region->page_size = region_page_size;
+		region->dev_bmp_offset_start_byte = dev_bmp_offset_byte;
+
+		dev_bmp_offset_byte += page_count / BITS_PER_BYTE;
+		if (dev_bmp_offset_byte % BITS_PER_BYTE) {
+			dev_err(&pdev->dev, "Device bitmap offset is mis-aligned\n");
+			err = -EINVAL;
+			goto out_free_regions;
+		}
 	}
 
 	return 0;
+
+out_free_regions:
+	pds_vfio_dirty_free_bitmaps(dirty);
+	pds_vfio_dirty_free_sgl(pds_vfio);
+	pds_vfio_dirty_free_regions(dirty);
+
+	return err;
 }
 
 static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
@@ -181,16 +246,14 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
 {
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
-	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
-	u64 region_start, region_size, region_page_size;
 	struct pds_lm_dirty_region_info *region_info;
 	struct interval_tree_node *node = NULL;
+	u64 region_page_size = *page_size;
 	u8 max_regions = 0, num_regions;
 	dma_addr_t regions_dma = 0;
 	u32 num_ranges = nnodes;
-	u32 page_count;
-	u16 len;
 	int err;
+	u16 len;
 
 	dev_dbg(&pdev->dev, "vf%u: Start dirty page tracking\n",
 		pds_vfio->vf_id);
@@ -217,39 +280,38 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
 		return -EOPNOTSUPP;
 	}
 
-	/*
-	 * Only support 1 region for now. If there are any large gaps in the
-	 * VM's address regions, then this would be a waste of memory as we are
-	 * generating 2 bitmaps (ack/seq) from the min address to the max
-	 * address of the VM's address regions. In the future, if we support
-	 * more than one region in the device/driver we can split the bitmaps
-	 * on the largest address region gaps. We can do this split up to the
-	 * max_regions times returned from the dirty_status command.
-	 */
-	max_regions = 1;
 	if (num_ranges > max_regions) {
 		vfio_combine_iova_ranges(ranges, nnodes, max_regions);
 		num_ranges = max_regions;
 	}
 
+	region_info = kcalloc(num_ranges, sizeof(*region_info), GFP_KERNEL);
+	if (!region_info)
+		return -ENOMEM;
+	len = num_ranges * sizeof(*region_info);
+
 	node = interval_tree_iter_first(ranges, 0, ULONG_MAX);
 	if (!node)
 		return -EINVAL;
+	for (int i = 0; i < num_ranges; i++) {
+		struct pds_lm_dirty_region_info *ri = &region_info[i];
+		u64 region_size = node->last - node->start + 1;
+		u64 region_start = node->start;
+		u32 page_count;
 
-	region_size = node->last - node->start + 1;
-	region_start = node->start;
-	region_page_size = *page_size;
+		page_count = DIV_ROUND_UP(region_size, region_page_size);
 
-	len = sizeof(*region_info);
-	region_info = kzalloc(len, GFP_KERNEL);
-	if (!region_info)
-		return -ENOMEM;
+		ri->dma_base = cpu_to_le64(region_start);
+		ri->page_count = cpu_to_le32(page_count);
+		ri->page_size_log2 = ilog2(region_page_size);
 
-	page_count = DIV_ROUND_UP(region_size, region_page_size);
+		dev_dbg(&pdev->dev,
+			"region_info[%d]: region_start 0x%llx region_end 0x%lx region_size 0x%llx page_count %u page_size %llu\n",
+			i, region_start, node->last, region_size, page_count,
+			region_page_size);
 
-	region_info->dma_base = cpu_to_le64(region_start);
-	region_info->page_count = cpu_to_le32(page_count);
-	region_info->page_size_log2 = ilog2(region_page_size);
+		node = interval_tree_iter_next(node, 0, ULONG_MAX);
+	}
 
 	regions_dma = dma_map_single(pdsc_dev, (void *)region_info, len,
 				     DMA_BIDIRECTIONAL);
@@ -258,39 +320,20 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
 		goto out_free_region_info;
 	}
 
-	err = pds_vfio_dirty_enable_cmd(pds_vfio, regions_dma, max_regions);
+	err = pds_vfio_dirty_enable_cmd(pds_vfio, regions_dma, num_ranges);
 	dma_unmap_single(pdsc_dev, regions_dma, len, DMA_BIDIRECTIONAL);
 	if (err)
 		goto out_free_region_info;
 
-	/*
-	 * page_count might be adjusted by the device,
-	 * update it before freeing region_info DMA
-	 */
-	page_count = le32_to_cpu(region_info->page_count);
-
-	dev_dbg(&pdev->dev,
-		"region_info: regions_dma 0x%llx dma_base 0x%llx page_count %u page_size_log2 %u\n",
-		regions_dma, region_start, page_count,
-		(u8)ilog2(region_page_size));
-
-	err = pds_vfio_dirty_alloc_bitmaps(dirty, page_count / BITS_PER_BYTE);
-	if (err) {
-		dev_err(&pdev->dev, "Failed to alloc dirty bitmaps: %pe\n",
-			ERR_PTR(err));
-		goto out_free_region_info;
-	}
-
-	err = pds_vfio_dirty_alloc_sgl(pds_vfio, page_count);
+	err = pds_vfio_dirty_alloc_regions(pds_vfio, region_info,
+					   region_page_size, num_ranges);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to alloc dirty sg lists: %pe\n",
-			ERR_PTR(err));
-		goto out_free_bitmaps;
+		dev_err(&pdev->dev,
+			"Failed to allocate %d regions for tracking dirty regions: %pe\n",
+			num_regions, ERR_PTR(err));
+		goto out_dirty_disable;
 	}
 
-	dirty->region_start = region_start;
-	dirty->region_size = region_size;
-	dirty->region_page_size = region_page_size;
 	pds_vfio_dirty_set_enabled(pds_vfio);
 
 	pds_vfio_print_guest_region_info(pds_vfio, max_regions);
@@ -299,8 +342,8 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
 
 	return 0;
 
-out_free_bitmaps:
-	pds_vfio_dirty_free_bitmaps(dirty);
+out_dirty_disable:
+	pds_vfio_dirty_disable_cmd(pds_vfio);
 out_free_region_info:
 	kfree(region_info);
 	return err;
@@ -314,6 +357,7 @@ void pds_vfio_dirty_disable(struct pds_vfio_pci_device *pds_vfio, bool send_cmd)
 			pds_vfio_dirty_disable_cmd(pds_vfio);
 		pds_vfio_dirty_free_sgl(pds_vfio);
 		pds_vfio_dirty_free_bitmaps(&pds_vfio->dirty);
+		pds_vfio_dirty_free_regions(&pds_vfio->dirty);
 	}
 
 	if (send_cmd)
@@ -321,8 +365,9 @@ void pds_vfio_dirty_disable(struct pds_vfio_pci_device *pds_vfio, bool send_cmd)
 }
 
 static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
-				  struct pds_vfio_bmp_info *bmp_info,
-				  u32 offset, u32 bmp_bytes, bool read_seq)
+				  struct pds_vfio_region *region,
+				  unsigned long *seq_ack_bmp, u32 offset,
+				  u32 bmp_bytes, bool read_seq)
 {
 	const char *bmp_type_str = read_seq ? "read_seq" : "write_ack";
 	u8 dma_dir = read_seq ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
@@ -339,7 +384,7 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 	int err;
 	int i;
 
-	bmp = (void *)((u64)bmp_info->bmp + offset);
+	bmp = (void *)((u64)seq_ack_bmp + offset);
 	page_offset = offset_in_page(bmp);
 	bmp -= page_offset;
 
@@ -375,7 +420,7 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 		goto out_free_sg_table;
 
 	for_each_sgtable_dma_sg(&sg_table, sg, i) {
-		struct pds_lm_sg_elem *sg_elem = &bmp_info->sgl[i];
+		struct pds_lm_sg_elem *sg_elem = &region->sgl[i];
 
 		sg_elem->addr = cpu_to_le64(sg_dma_address(sg));
 		sg_elem->len = cpu_to_le32(sg_dma_len(sg));
@@ -383,15 +428,16 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 
 	num_sge = sg_table.nents;
 	size = num_sge * sizeof(struct pds_lm_sg_elem);
-	dma_sync_single_for_device(pdsc_dev, bmp_info->sgl_addr, size, dma_dir);
-	err = pds_vfio_dirty_seq_ack_cmd(pds_vfio, bmp_info->sgl_addr, num_sge,
+	offset += region->dev_bmp_offset_start_byte;
+	dma_sync_single_for_device(pdsc_dev, region->sgl_addr, size, dma_dir);
+	err = pds_vfio_dirty_seq_ack_cmd(pds_vfio, region->sgl_addr, num_sge,
 					 offset, bmp_bytes, read_seq);
 	if (err)
 		dev_err(&pdev->dev,
 			"Dirty bitmap %s failed offset %u bmp_bytes %u num_sge %u DMA 0x%llx: %pe\n",
 			bmp_type_str, offset, bmp_bytes,
-			num_sge, bmp_info->sgl_addr, ERR_PTR(err));
-	dma_sync_single_for_cpu(pdsc_dev, bmp_info->sgl_addr, size, dma_dir);
+			num_sge, region->sgl_addr, ERR_PTR(err));
+	dma_sync_single_for_cpu(pdsc_dev, region->sgl_addr, size, dma_dir);
 
 	dma_unmap_sgtable(pdsc_dev, &sg_table, dma_dir, 0);
 out_free_sg_table:
@@ -403,32 +449,36 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 }
 
 static int pds_vfio_dirty_write_ack(struct pds_vfio_pci_device *pds_vfio,
+				   struct pds_vfio_region *region,
 				    u32 offset, u32 len)
 {
-	return pds_vfio_dirty_seq_ack(pds_vfio, &pds_vfio->dirty.host_ack,
+
+	return pds_vfio_dirty_seq_ack(pds_vfio, region, region->host_ack,
 				      offset, len, WRITE_ACK);
 }
 
 static int pds_vfio_dirty_read_seq(struct pds_vfio_pci_device *pds_vfio,
+				   struct pds_vfio_region *region,
 				   u32 offset, u32 len)
 {
-	return pds_vfio_dirty_seq_ack(pds_vfio, &pds_vfio->dirty.host_seq,
+	return pds_vfio_dirty_seq_ack(pds_vfio, region, region->host_seq,
 				      offset, len, READ_SEQ);
 }
 
 static int pds_vfio_dirty_process_bitmaps(struct pds_vfio_pci_device *pds_vfio,
+					  struct pds_vfio_region *region,
 					  struct iova_bitmap *dirty_bitmap,
 					  u32 bmp_offset, u32 len_bytes)
 {
-	u64 page_size = pds_vfio->dirty.region_page_size;
-	u64 region_start = pds_vfio->dirty.region_start;
+	u64 page_size = region->page_size;
+	u64 region_start = region->start;
 	u32 bmp_offset_bit;
 	__le64 *seq, *ack;
 	int dword_count;
 
 	dword_count = len_bytes / sizeof(u64);
-	seq = (__le64 *)((u64)pds_vfio->dirty.host_seq.bmp + bmp_offset);
-	ack = (__le64 *)((u64)pds_vfio->dirty.host_ack.bmp + bmp_offset);
+	seq = (__le64 *)((u64)region->host_seq + bmp_offset);
+	ack = (__le64 *)((u64)region->host_ack + bmp_offset);
 	bmp_offset_bit = bmp_offset * 8;
 
 	for (int i = 0; i < dword_count; i++) {
@@ -451,12 +501,28 @@ static int pds_vfio_dirty_process_bitmaps(struct pds_vfio_pci_device *pds_vfio,
 	return 0;
 }
 
+static struct pds_vfio_region *
+pds_vfio_get_region(struct pds_vfio_pci_device *pds_vfio, unsigned long iova)
+{
+	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+
+	for (int i = 0; i < dirty->num_regions; i++) {
+		struct pds_vfio_region *region = &dirty->regions[i];
+
+		if (iova >= region->start &&
+		    iova < (region->start + region->size))
+			return region;
+	}
+
+	return NULL;
+}
+
 static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 			       struct iova_bitmap *dirty_bitmap,
 			       unsigned long iova, unsigned long length)
 {
 	struct device *dev = &pds_vfio->vfio_coredev.pdev->dev;
-	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+	struct pds_vfio_region *region;
 	u64 bmp_offset, bmp_bytes;
 	u64 bitmap_size, pages;
 	int err;
@@ -469,26 +535,31 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 		return -EINVAL;
 	}
 
-	pages = DIV_ROUND_UP(length, pds_vfio->dirty.region_page_size);
+	region = pds_vfio_get_region(pds_vfio, iova);
+	if (!region) {
+		dev_err(dev, "vf%u: Failed to find region that contains iova 0x%lx length 0x%lx\n",
+			pds_vfio->vf_id, iova, length);
+		return -EINVAL;
+	}
+
+	pages = DIV_ROUND_UP(length, region->page_size);
 	bitmap_size =
 		round_up(pages, sizeof(u64) * BITS_PER_BYTE) / BITS_PER_BYTE;
 
 	dev_dbg(dev,
 		"vf%u: iova 0x%lx length %lu page_size %llu pages %llu bitmap_size %llu\n",
-		pds_vfio->vf_id, iova, length, pds_vfio->dirty.region_page_size,
+		pds_vfio->vf_id, iova, length, region->page_size,
 		pages, bitmap_size);
 
-	if (!length || ((dirty->region_start + iova + length) >
-			(dirty->region_start + dirty->region_size))) {
+	if (!length || ((iova - region->start + length) > region->size)) {
 		dev_err(dev, "Invalid iova 0x%lx and/or length 0x%lx to sync\n",
 			iova, length);
 		return -EINVAL;
 	}
 
 	/* bitmap is modified in 64 bit chunks */
-	bmp_bytes = ALIGN(DIV_ROUND_UP(length / dirty->region_page_size,
-				       sizeof(u64)),
-			  sizeof(u64));
+	bmp_bytes = ALIGN(DIV_ROUND_UP(length / region->page_size,
+				       sizeof(u64)), sizeof(u64));
 	if (bmp_bytes != bitmap_size) {
 		dev_err(dev,
 			"Calculated bitmap bytes %llu not equal to bitmap size %llu\n",
@@ -496,22 +567,30 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 		return -EINVAL;
 	}
 
-	bmp_offset = DIV_ROUND_UP(iova / dirty->region_page_size, sizeof(u64));
+	if (bmp_bytes > region->bmp_bytes) {
+		dev_err(dev,
+			"Calculated bitmap bytes %llu larger than region's cached bmp_bytes %llu\n",
+			bmp_bytes, region->bmp_bytes);
+		return -EINVAL;
+	}
+
+	bmp_offset = DIV_ROUND_UP((iova - region->start) /
+				  region->page_size, sizeof(u64));
 
 	dev_dbg(dev,
 		"Syncing dirty bitmap, iova 0x%lx length 0x%lx, bmp_offset %llu bmp_bytes %llu\n",
 		iova, length, bmp_offset, bmp_bytes);
 
-	err = pds_vfio_dirty_read_seq(pds_vfio, bmp_offset, bmp_bytes);
+	err = pds_vfio_dirty_read_seq(pds_vfio, region, bmp_offset, bmp_bytes);
 	if (err)
 		return err;
 
-	err = pds_vfio_dirty_process_bitmaps(pds_vfio, dirty_bitmap, bmp_offset,
-					     bmp_bytes);
+	err = pds_vfio_dirty_process_bitmaps(pds_vfio, region, dirty_bitmap,
+					     bmp_offset, bmp_bytes);
 	if (err)
 		return err;
 
-	err = pds_vfio_dirty_write_ack(pds_vfio, bmp_offset, bmp_bytes);
+	err = pds_vfio_dirty_write_ack(pds_vfio, region, bmp_offset, bmp_bytes);
 	if (err)
 		return err;
 

drivers/vfio/pci/pds/dirty.h

@@ -4,20 +4,22 @@
 #ifndef _DIRTY_H_
 #define _DIRTY_H_
 
-struct pds_vfio_bmp_info {
-	unsigned long *bmp;
-	u32 bmp_bytes;
+struct pds_vfio_region {
+	unsigned long *host_seq;
+	unsigned long *host_ack;
+	u64 bmp_bytes;
+	u64 size;
+	u64 start;
+	u64 page_size;
 	struct pds_lm_sg_elem *sgl;
 	dma_addr_t sgl_addr;
+	u32 dev_bmp_offset_start_byte;
 	u16 num_sge;
 };
 
 struct pds_vfio_dirty {
-	struct pds_vfio_bmp_info host_seq;
-	struct pds_vfio_bmp_info host_ack;
-	u64 region_size;
-	u64 region_start;
-	u64 region_page_size;
+	struct pds_vfio_region *regions;
+	u8 num_regions;
 	bool is_enabled;
 };
 

drivers/vfio/pci/vfio_pci_rdwr.c

@@ -38,7 +38,7 @@
 #define vfio_iowrite8	iowrite8
 
 #define VFIO_IOWRITE(size) \
-static int vfio_pci_iowrite##size(struct vfio_pci_core_device *vdev,		\
+int vfio_pci_core_iowrite##size(struct vfio_pci_core_device *vdev,	\
 			bool test_mem, u##size val, void __iomem *io)	\
 {									\
 	if (test_mem) {							\
@@ -55,7 +55,8 @@ static int vfio_pci_iowrite##size(struct vfio_pci_core_device *vdev,		\
 		up_read(&vdev->memory_lock);				\
 									\
 	return 0;							\
-}
+}									\
+EXPORT_SYMBOL_GPL(vfio_pci_core_iowrite##size);
 
 VFIO_IOWRITE(8)
 VFIO_IOWRITE(16)
@@ -65,7 +66,7 @@ VFIO_IOWRITE(64)
 #endif
 
 #define VFIO_IOREAD(size) \
-static int vfio_pci_ioread##size(struct vfio_pci_core_device *vdev,		\
+int vfio_pci_core_ioread##size(struct vfio_pci_core_device *vdev,	\
 			bool test_mem, u##size *val, void __iomem *io)	\
 {									\
 	if (test_mem) {							\
@@ -82,7 +83,8 @@ static int vfio_pci_ioread##size(struct vfio_pci_core_device *vdev,		\
 		up_read(&vdev->memory_lock);				\
 									\
 	return 0;							\
-}
+}									\
+EXPORT_SYMBOL_GPL(vfio_pci_core_ioread##size);
 
 VFIO_IOREAD(8)
 VFIO_IOREAD(16)
@@ -119,12 +121,12 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 				if (copy_from_user(&val, buf, 4))
 					return -EFAULT;
 
-				ret = vfio_pci_iowrite32(vdev, test_mem,
+				ret = vfio_pci_core_iowrite32(vdev, test_mem,
 							      val, io + off);
 				if (ret)
 					return ret;
 			} else {
-				ret = vfio_pci_ioread32(vdev, test_mem,
+				ret = vfio_pci_core_ioread32(vdev, test_mem,
 							     &val, io + off);
 				if (ret)
 					return ret;
@@ -141,12 +143,12 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 				if (copy_from_user(&val, buf, 2))
 					return -EFAULT;
 
-				ret = vfio_pci_iowrite16(vdev, test_mem,
+				ret = vfio_pci_core_iowrite16(vdev, test_mem,
 							      val, io + off);
 				if (ret)
 					return ret;
 			} else {
-				ret = vfio_pci_ioread16(vdev, test_mem,
+				ret = vfio_pci_core_ioread16(vdev, test_mem,
 							     &val, io + off);
 				if (ret)
 					return ret;
@@ -163,12 +165,12 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 				if (copy_from_user(&val, buf, 1))
 					return -EFAULT;
 
-				ret = vfio_pci_iowrite8(vdev, test_mem,
+				ret = vfio_pci_core_iowrite8(vdev, test_mem,
 							     val, io + off);
 				if (ret)
 					return ret;
 			} else {
-				ret = vfio_pci_ioread8(vdev, test_mem,
+				ret = vfio_pci_core_ioread8(vdev, test_mem,
 							    &val, io + off);
 				if (ret)
 					return ret;
@@ -200,7 +202,7 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 	return done;
 }
 
-static int vfio_pci_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
+int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
 {
 	struct pci_dev *pdev = vdev->pdev;
 	int ret;
@@ -223,6 +225,7 @@ static int vfio_pci_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(vfio_pci_core_setup_barmap);
 
 ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 			size_t count, loff_t *ppos, bool iswrite)
@@ -262,7 +265,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 		}
 		x_end = end;
 	} else {
-		int ret = vfio_pci_setup_barmap(vdev, bar);
+		int ret = vfio_pci_core_setup_barmap(vdev, bar);
 		if (ret) {
 			done = ret;
 			goto out;
@@ -363,20 +366,20 @@ static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd,
 {
 	switch (ioeventfd->count) {
 	case 1:
-		vfio_pci_iowrite8(ioeventfd->vdev, test_mem,
+		vfio_pci_core_iowrite8(ioeventfd->vdev, test_mem,
 				       ioeventfd->data, ioeventfd->addr);
 		break;
 	case 2:
-		vfio_pci_iowrite16(ioeventfd->vdev, test_mem,
+		vfio_pci_core_iowrite16(ioeventfd->vdev, test_mem,
 					ioeventfd->data, ioeventfd->addr);
 		break;
 	case 4:
-		vfio_pci_iowrite32(ioeventfd->vdev, test_mem,
+		vfio_pci_core_iowrite32(ioeventfd->vdev, test_mem,
 					ioeventfd->data, ioeventfd->addr);
 		break;
 #ifdef iowrite64
 	case 8:
-		vfio_pci_iowrite64(ioeventfd->vdev, test_mem,
+		vfio_pci_core_iowrite64(ioeventfd->vdev, test_mem,
 					ioeventfd->data, ioeventfd->addr);
 		break;
 #endif
@@ -438,7 +441,7 @@ int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
 		return -EINVAL;
 #endif
 
-	ret = vfio_pci_setup_barmap(vdev, bar);
+	ret = vfio_pci_core_setup_barmap(vdev, bar);
 	if (ret)
 		return ret;
 

drivers/vfio/pci/virtio/Kconfig

+# SPDX-License-Identifier: GPL-2.0-only
+config VIRTIO_VFIO_PCI
+        tristate "VFIO support for VIRTIO NET PCI devices"
+        depends on VIRTIO_PCI && VIRTIO_PCI_ADMIN_LEGACY
+        select VFIO_PCI_CORE
+        help
+          This provides support for exposing VIRTIO NET VF devices which support
+          legacy IO access, using the VFIO framework that can work with a legacy
+          virtio driver in the guest.
+          Based on PCIe spec, VFs do not support I/O Space.
+          As of that this driver emulates I/O BAR in software to let a VF be
+          seen as a transitional device by its users and let it work with
+          a legacy driver.
+
+          If you don't know what to do here, say N.

drivers/vfio/pci/virtio/Makefile

+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_VIRTIO_VFIO_PCI) += virtio-vfio-pci.o
+virtio-vfio-pci-y := main.o

drivers/vfio/pci/virtio/main.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/pm_runtime.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+#include <linux/vfio_pci_core.h>
+#include <linux/virtio_pci.h>
+#include <linux/virtio_net.h>
+#include <linux/virtio_pci_admin.h>
+
+struct virtiovf_pci_core_device {
+	struct vfio_pci_core_device core_device;
+	u8 *bar0_virtual_buf;
+	/* synchronize access to the virtual buf */
+	struct mutex bar_mutex;
+	void __iomem *notify_addr;
+	u64 notify_offset;
+	__le32 pci_base_addr_0;
+	__le16 pci_cmd;
+	u8 bar0_virtual_buf_size;
+	u8 notify_bar;
+};
+
+static int
+virtiovf_issue_legacy_rw_cmd(struct virtiovf_pci_core_device *virtvdev,
+			     loff_t pos, char __user *buf,
+			     size_t count, bool read)
+{
+	bool msix_enabled =
+		(virtvdev->core_device.irq_type == VFIO_PCI_MSIX_IRQ_INDEX);
+	struct pci_dev *pdev = virtvdev->core_device.pdev;
+	u8 *bar0_buf = virtvdev->bar0_virtual_buf;
+	bool common;
+	u8 offset;
+	int ret;
+
+	common = pos < VIRTIO_PCI_CONFIG_OFF(msix_enabled);
+	/* offset within the relevant configuration area */
+	offset = common ? pos : pos - VIRTIO_PCI_CONFIG_OFF(msix_enabled);
+	mutex_lock(&virtvdev->bar_mutex);
+	if (read) {
+		if (common)
+			ret = virtio_pci_admin_legacy_common_io_read(pdev, offset,
+					count, bar0_buf + pos);
+		else
+			ret = virtio_pci_admin_legacy_device_io_read(pdev, offset,
+					count, bar0_buf + pos);
+		if (ret)
+			goto out;
+		if (copy_to_user(buf, bar0_buf + pos, count))
+			ret = -EFAULT;
+	} else {
+		if (copy_from_user(bar0_buf + pos, buf, count)) {
+			ret = -EFAULT;
+			goto out;
+		}
+
+		if (common)
+			ret = virtio_pci_admin_legacy_common_io_write(pdev, offset,
+					count, bar0_buf + pos);
+		else
+			ret = virtio_pci_admin_legacy_device_io_write(pdev, offset,
+					count, bar0_buf + pos);
+	}
+out:
+	mutex_unlock(&virtvdev->bar_mutex);
+	return ret;
+}
+
+static int
+virtiovf_pci_bar0_rw(struct virtiovf_pci_core_device *virtvdev,
+		     loff_t pos, char __user *buf,
+		     size_t count, bool read)
+{
+	struct vfio_pci_core_device *core_device = &virtvdev->core_device;
+	struct pci_dev *pdev = core_device->pdev;
+	u16 queue_notify;
+	int ret;
+
+	if (!(le16_to_cpu(virtvdev->pci_cmd) & PCI_COMMAND_IO))
+		return -EIO;
+
+	if (pos + count > virtvdev->bar0_virtual_buf_size)
+		return -EINVAL;
+
+	ret = pm_runtime_resume_and_get(&pdev->dev);
+	if (ret) {
+		pci_info_ratelimited(pdev, "runtime resume failed %d\n", ret);
+		return -EIO;
+	}
+
+	switch (pos) {
+	case VIRTIO_PCI_QUEUE_NOTIFY:
+		if (count != sizeof(queue_notify)) {
+			ret = -EINVAL;
+			goto end;
+		}
+		if (read) {
+			ret = vfio_pci_core_ioread16(core_device, true, &queue_notify,
+						     virtvdev->notify_addr);
+			if (ret)
+				goto end;
+			if (copy_to_user(buf, &queue_notify,
+					 sizeof(queue_notify))) {
+				ret = -EFAULT;
+				goto end;
+			}
+		} else {
+			if (copy_from_user(&queue_notify, buf, count)) {
+				ret = -EFAULT;
+				goto end;
+			}
+			ret = vfio_pci_core_iowrite16(core_device, true, queue_notify,
+						      virtvdev->notify_addr);
+		}
+		break;
+	default:
+		ret = virtiovf_issue_legacy_rw_cmd(virtvdev, pos, buf, count,
+						   read);
+	}
+
+end:
+	pm_runtime_put(&pdev->dev);
+	return ret ? ret : count;
+}
+
+static bool range_intersect_range(loff_t range1_start, size_t count1,
+				  loff_t range2_start, size_t count2,
+				  loff_t *start_offset,
+				  size_t *intersect_count,
+				  size_t *register_offset)
+{
+	if (range1_start <= range2_start &&
+	    range1_start + count1 > range2_start) {
+		*start_offset = range2_start - range1_start;
+		*intersect_count = min_t(size_t, count2,
+					 range1_start + count1 - range2_start);
+		*register_offset = 0;
+		return true;
+	}
+
+	if (range1_start > range2_start &&
+	    range1_start < range2_start + count2) {
+		*start_offset = 0;
+		*intersect_count = min_t(size_t, count1,
+					 range2_start + count2 - range1_start);
+		*register_offset = range1_start - range2_start;
+		return true;
+	}
+
+	return false;
+}
+
+static ssize_t virtiovf_pci_read_config(struct vfio_device *core_vdev,
+					char __user *buf, size_t count,
+					loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+	size_t register_offset;
+	loff_t copy_offset;
+	size_t copy_count;
+	__le32 val32;
+	__le16 val16;
+	u8 val8;
+	int ret;
+
+	ret = vfio_pci_core_read(core_vdev, buf, count, ppos);
+	if (ret < 0)
+		return ret;
+
+	if (range_intersect_range(pos, count, PCI_DEVICE_ID, sizeof(val16),
+				  &copy_offset, &copy_count, &register_offset)) {
+		val16 = cpu_to_le16(VIRTIO_TRANS_ID_NET);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset, copy_count))
+			return -EFAULT;
+	}
+
+	if ((le16_to_cpu(virtvdev->pci_cmd) & PCI_COMMAND_IO) &&
+	    range_intersect_range(pos, count, PCI_COMMAND, sizeof(val16),
+				  &copy_offset, &copy_count, &register_offset)) {
+		if (copy_from_user((void *)&val16 + register_offset, buf + copy_offset,
+				   copy_count))
+			return -EFAULT;
+		val16 |= cpu_to_le16(PCI_COMMAND_IO);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset,
+				 copy_count))
+			return -EFAULT;
+	}
+
+	if (range_intersect_range(pos, count, PCI_REVISION_ID, sizeof(val8),
+				  &copy_offset, &copy_count, &register_offset)) {
+		/* Transional needs to have revision 0 */
+		val8 = 0;
+		if (copy_to_user(buf + copy_offset, &val8, copy_count))
+			return -EFAULT;
+	}
+
+	if (range_intersect_range(pos, count, PCI_BASE_ADDRESS_0, sizeof(val32),
+				  &copy_offset, &copy_count, &register_offset)) {
+		u32 bar_mask = ~(virtvdev->bar0_virtual_buf_size - 1);
+		u32 pci_base_addr_0 = le32_to_cpu(virtvdev->pci_base_addr_0);
+
+		val32 = cpu_to_le32((pci_base_addr_0 & bar_mask) | PCI_BASE_ADDRESS_SPACE_IO);
+		if (copy_to_user(buf + copy_offset, (void *)&val32 + register_offset, copy_count))
+			return -EFAULT;
+	}
+
+	if (range_intersect_range(pos, count, PCI_SUBSYSTEM_ID, sizeof(val16),
+				  &copy_offset, &copy_count, &register_offset)) {
+		/*
+		 * Transitional devices use the PCI subsystem device id as
+		 * virtio device id, same as legacy driver always did.
+		 */
+		val16 = cpu_to_le16(VIRTIO_ID_NET);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset,
+				 copy_count))
+			return -EFAULT;
+	}
+
+	if (range_intersect_range(pos, count, PCI_SUBSYSTEM_VENDOR_ID, sizeof(val16),
+				  &copy_offset, &copy_count, &register_offset)) {
+		val16 = cpu_to_le16(PCI_VENDOR_ID_REDHAT_QUMRANET);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset,
+				 copy_count))
+			return -EFAULT;
+	}
+
+	return count;
+}
+
+static ssize_t
+virtiovf_pci_core_read(struct vfio_device *core_vdev, char __user *buf,
+		       size_t count, loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+
+	if (!count)
+		return 0;
+
+	if (index == VFIO_PCI_CONFIG_REGION_INDEX)
+		return virtiovf_pci_read_config(core_vdev, buf, count, ppos);
+
+	if (index == VFIO_PCI_BAR0_REGION_INDEX)
+		return virtiovf_pci_bar0_rw(virtvdev, pos, buf, count, true);
+
+	return vfio_pci_core_read(core_vdev, buf, count, ppos);
+}
+
+static ssize_t virtiovf_pci_write_config(struct vfio_device *core_vdev,
+					 const char __user *buf, size_t count,
+					 loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+	size_t register_offset;
+	loff_t copy_offset;
+	size_t copy_count;
+
+	if (range_intersect_range(pos, count, PCI_COMMAND, sizeof(virtvdev->pci_cmd),
+				  &copy_offset, &copy_count,
+				  &register_offset)) {
+		if (copy_from_user((void *)&virtvdev->pci_cmd + register_offset,
+				   buf + copy_offset,
+				   copy_count))
+			return -EFAULT;
+	}
+
+	if (range_intersect_range(pos, count, PCI_BASE_ADDRESS_0,
+				  sizeof(virtvdev->pci_base_addr_0),
+				  &copy_offset, &copy_count,
+				  &register_offset)) {
+		if (copy_from_user((void *)&virtvdev->pci_base_addr_0 + register_offset,
+				   buf + copy_offset,
+				   copy_count))
+			return -EFAULT;
+	}
+
+	return vfio_pci_core_write(core_vdev, buf, count, ppos);
+}
+
+static ssize_t
+virtiovf_pci_core_write(struct vfio_device *core_vdev, const char __user *buf,
+			size_t count, loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+
+	if (!count)
+		return 0;
+
+	if (index == VFIO_PCI_CONFIG_REGION_INDEX)
+		return virtiovf_pci_write_config(core_vdev, buf, count, ppos);
+
+	if (index == VFIO_PCI_BAR0_REGION_INDEX)
+		return virtiovf_pci_bar0_rw(virtvdev, pos, (char __user *)buf, count, false);
+
+	return vfio_pci_core_write(core_vdev, buf, count, ppos);
+}
+
+static int
+virtiovf_pci_ioctl_get_region_info(struct vfio_device *core_vdev,
+				   unsigned int cmd, unsigned long arg)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	unsigned long minsz = offsetofend(struct vfio_region_info, offset);
+	void __user *uarg = (void __user *)arg;
+	struct vfio_region_info info = {};
+
+	if (copy_from_user(&info, uarg, minsz))
+		return -EFAULT;
+
+	if (info.argsz < minsz)
+		return -EINVAL;
+
+	switch (info.index) {
+	case VFIO_PCI_BAR0_REGION_INDEX:
+		info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
+		info.size = virtvdev->bar0_virtual_buf_size;
+		info.flags = VFIO_REGION_INFO_FLAG_READ |
+			     VFIO_REGION_INFO_FLAG_WRITE;
+		return copy_to_user(uarg, &info, minsz) ? -EFAULT : 0;
+	default:
+		return vfio_pci_core_ioctl(core_vdev, cmd, arg);
+	}
+}
+
+static long
+virtiovf_vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd,
+			     unsigned long arg)
+{
+	switch (cmd) {
+	case VFIO_DEVICE_GET_REGION_INFO:
+		return virtiovf_pci_ioctl_get_region_info(core_vdev, cmd, arg);
+	default:
+		return vfio_pci_core_ioctl(core_vdev, cmd, arg);
+	}
+}
+
+static int
+virtiovf_set_notify_addr(struct virtiovf_pci_core_device *virtvdev)
+{
+	struct vfio_pci_core_device *core_device = &virtvdev->core_device;
+	int ret;
+
+	/*
+	 * Setup the BAR where the 'notify' exists to be used by vfio as well
+	 * This will let us mmap it only once and use it when needed.
+	 */
+	ret = vfio_pci_core_setup_barmap(core_device,
+					 virtvdev->notify_bar);
+	if (ret)
+		return ret;
+
+	virtvdev->notify_addr = core_device->barmap[virtvdev->notify_bar] +
+			virtvdev->notify_offset;
+	return 0;
+}
+
+static int virtiovf_pci_open_device(struct vfio_device *core_vdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	struct vfio_pci_core_device *vdev = &virtvdev->core_device;
+	int ret;
+
+	ret = vfio_pci_core_enable(vdev);
+	if (ret)
+		return ret;
+
+	if (virtvdev->bar0_virtual_buf) {
+		/*
+		 * Upon close_device() the vfio_pci_core_disable() is called
+		 * and will close all the previous mmaps, so it seems that the
+		 * valid life cycle for the 'notify' addr is per open/close.
+		 */
+		ret = virtiovf_set_notify_addr(virtvdev);
+		if (ret) {
+			vfio_pci_core_disable(vdev);
+			return ret;
+		}
+	}
+
+	vfio_pci_core_finish_enable(vdev);
+	return 0;
+}
+
+static int virtiovf_get_device_config_size(unsigned short device)
+{
+	/* Network card */
+	return offsetofend(struct virtio_net_config, status);
+}
+
+static int virtiovf_read_notify_info(struct virtiovf_pci_core_device *virtvdev)
+{
+	u64 offset;
+	int ret;
+	u8 bar;
+
+	ret = virtio_pci_admin_legacy_io_notify_info(virtvdev->core_device.pdev,
+				VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_MEM,
+				&bar, &offset);
+	if (ret)
+		return ret;
+
+	virtvdev->notify_bar = bar;
+	virtvdev->notify_offset = offset;
+	return 0;
+}
+
+static int virtiovf_pci_init_device(struct vfio_device *core_vdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	struct pci_dev *pdev;
+	int ret;
+
+	ret = vfio_pci_core_init_dev(core_vdev);
+	if (ret)
+		return ret;
+
+	pdev = virtvdev->core_device.pdev;
+	ret = virtiovf_read_notify_info(virtvdev);
+	if (ret)
+		return ret;
+
+	virtvdev->bar0_virtual_buf_size = VIRTIO_PCI_CONFIG_OFF(true) +
+				virtiovf_get_device_config_size(pdev->device);
+	BUILD_BUG_ON(!is_power_of_2(virtvdev->bar0_virtual_buf_size));
+	virtvdev->bar0_virtual_buf = kzalloc(virtvdev->bar0_virtual_buf_size,
+					     GFP_KERNEL);
+	if (!virtvdev->bar0_virtual_buf)
+		return -ENOMEM;
+	mutex_init(&virtvdev->bar_mutex);
+	return 0;
+}
+
+static void virtiovf_pci_core_release_dev(struct vfio_device *core_vdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+
+	kfree(virtvdev->bar0_virtual_buf);
+	vfio_pci_core_release_dev(core_vdev);
+}
+
+static const struct vfio_device_ops virtiovf_vfio_pci_tran_ops = {
+	.name = "virtio-vfio-pci-trans",
+	.init = virtiovf_pci_init_device,
+	.release = virtiovf_pci_core_release_dev,
+	.open_device = virtiovf_pci_open_device,
+	.close_device = vfio_pci_core_close_device,
+	.ioctl = virtiovf_vfio_pci_core_ioctl,
+	.device_feature = vfio_pci_core_ioctl_feature,
+	.read = virtiovf_pci_core_read,
+	.write = virtiovf_pci_core_write,
+	.mmap = vfio_pci_core_mmap,
+	.request = vfio_pci_core_request,
+	.match = vfio_pci_core_match,
+	.bind_iommufd = vfio_iommufd_physical_bind,
+	.unbind_iommufd = vfio_iommufd_physical_unbind,
+	.attach_ioas = vfio_iommufd_physical_attach_ioas,
+	.detach_ioas = vfio_iommufd_physical_detach_ioas,
+};
+
+static const struct vfio_device_ops virtiovf_vfio_pci_ops = {
+	.name = "virtio-vfio-pci",
+	.init = vfio_pci_core_init_dev,
+	.release = vfio_pci_core_release_dev,
+	.open_device = virtiovf_pci_open_device,
+	.close_device = vfio_pci_core_close_device,
+	.ioctl = vfio_pci_core_ioctl,
+	.device_feature = vfio_pci_core_ioctl_feature,
+	.read = vfio_pci_core_read,
+	.write = vfio_pci_core_write,
+	.mmap = vfio_pci_core_mmap,
+	.request = vfio_pci_core_request,
+	.match = vfio_pci_core_match,
+	.bind_iommufd = vfio_iommufd_physical_bind,
+	.unbind_iommufd = vfio_iommufd_physical_unbind,
+	.attach_ioas = vfio_iommufd_physical_attach_ioas,
+	.detach_ioas = vfio_iommufd_physical_detach_ioas,
+};
+
+static bool virtiovf_bar0_exists(struct pci_dev *pdev)
+{
+	struct resource *res = pdev->resource;
+
+	return res->flags;
+}
+
+static int virtiovf_pci_probe(struct pci_dev *pdev,
+			      const struct pci_device_id *id)
+{
+	const struct vfio_device_ops *ops = &virtiovf_vfio_pci_ops;
+	struct virtiovf_pci_core_device *virtvdev;
+	int ret;
+
+	if (pdev->is_virtfn && virtio_pci_admin_has_legacy_io(pdev) &&
+	    !virtiovf_bar0_exists(pdev))
+		ops = &virtiovf_vfio_pci_tran_ops;
+
+	virtvdev = vfio_alloc_device(virtiovf_pci_core_device, core_device.vdev,
+				     &pdev->dev, ops);
+	if (IS_ERR(virtvdev))
+		return PTR_ERR(virtvdev);
+
+	dev_set_drvdata(&pdev->dev, &virtvdev->core_device);
+	ret = vfio_pci_core_register_device(&virtvdev->core_device);
+	if (ret)
+		goto out;
+	return 0;
+out:
+	vfio_put_device(&virtvdev->core_device.vdev);
+	return ret;
+}
+
+static void virtiovf_pci_remove(struct pci_dev *pdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = dev_get_drvdata(&pdev->dev);
+
+	vfio_pci_core_unregister_device(&virtvdev->core_device);
+	vfio_put_device(&virtvdev->core_device.vdev);
+}
+
+static const struct pci_device_id virtiovf_pci_table[] = {
+	/* Only virtio-net is supported/tested so far */
+	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_REDHAT_QUMRANET, 0x1041) },
+	{}
+};
+
+MODULE_DEVICE_TABLE(pci, virtiovf_pci_table);
+
+static void virtiovf_pci_aer_reset_done(struct pci_dev *pdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = dev_get_drvdata(&pdev->dev);
+
+	virtvdev->pci_cmd = 0;
+}
+
+static const struct pci_error_handlers virtiovf_err_handlers = {
+	.reset_done = virtiovf_pci_aer_reset_done,
+	.error_detected = vfio_pci_core_aer_err_detected,
+};
+
+static struct pci_driver virtiovf_pci_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = virtiovf_pci_table,
+	.probe = virtiovf_pci_probe,
+	.remove = virtiovf_pci_remove,
+	.err_handler = &virtiovf_err_handlers,
+	.driver_managed_dma = true,
+};
+
+module_pci_driver(virtiovf_pci_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Yishai Hadas <yishaih@nvidia.com>");
+MODULE_DESCRIPTION(
+	"VIRTIO VFIO PCI - User Level meta-driver for VIRTIO NET devices");

drivers/vfio/vfio.h

@@ -448,4 +448,18 @@ static inline void vfio_device_put_kvm(struct vfio_device *device)
 }
 #endif
 
+#ifdef CONFIG_VFIO_DEBUGFS
+void vfio_debugfs_create_root(void);
+void vfio_debugfs_remove_root(void);
+
+void vfio_device_debugfs_init(struct vfio_device *vdev);
+void vfio_device_debugfs_exit(struct vfio_device *vdev);
+#else
+static inline void vfio_debugfs_create_root(void) { }
+static inline void vfio_debugfs_remove_root(void) { }
+
+static inline void vfio_device_debugfs_init(struct vfio_device *vdev) { }
+static inline void vfio_device_debugfs_exit(struct vfio_device *vdev) { }
+#endif /* CONFIG_VFIO_DEBUGFS */
+
 #endif

drivers/vfio/vfio_iommu_type1.c

@@ -1436,7 +1436,7 @@ static int vfio_iommu_map(struct vfio_iommu *iommu, dma_addr_t iova,
 	list_for_each_entry(d, &iommu->domain_list, next) {
 		ret = iommu_map(d->domain, iova, (phys_addr_t)pfn << PAGE_SHIFT,
 				npage << PAGE_SHIFT, prot | IOMMU_CACHE,
-				GFP_KERNEL);
+				GFP_KERNEL_ACCOUNT);
 		if (ret)
 			goto unwind;
 
@@ -1750,7 +1750,8 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
 			}
 
 			ret = iommu_map(domain->domain, iova, phys, size,
-					dma->prot | IOMMU_CACHE, GFP_KERNEL);
+					dma->prot | IOMMU_CACHE,
+					GFP_KERNEL_ACCOUNT);
 			if (ret) {
 				if (!dma->iommu_mapped) {
 					vfio_unpin_pages_remote(dma, iova,
@@ -1845,7 +1846,8 @@ static void vfio_test_domain_fgsp(struct vfio_domain *domain, struct list_head *
 			continue;
 
 		ret = iommu_map(domain->domain, start, page_to_phys(pages), PAGE_SIZE * 2,
-				IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE, GFP_KERNEL);
+				IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE,
+				GFP_KERNEL_ACCOUNT);
 		if (!ret) {
 			size_t unmapped = iommu_unmap(domain->domain, start, PAGE_SIZE);
 

drivers/vfio/vfio_main.c

@@ -311,6 +311,7 @@ static int __vfio_register_dev(struct vfio_device *device,
 	refcount_set(&device->refcount, 1);
 
 	vfio_device_group_register(device);
+	vfio_device_debugfs_init(device);
 
 	return 0;
 err_out:
@@ -378,6 +379,7 @@ void vfio_unregister_group_dev(struct vfio_device *device)
 		}
 	}
 
+	vfio_device_debugfs_exit(device);
 	/* Balances vfio_device_set_group in register path */
 	vfio_device_remove_group(device);
 }
@@ -1676,6 +1678,7 @@ static int __init vfio_init(void)
 	if (ret)
 		goto err_alloc_dev_chrdev;
 
+	vfio_debugfs_create_root();
 	pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
 	return 0;
 
@@ -1691,6 +1694,7 @@ static int __init vfio_init(void)
 
 static void __exit vfio_cleanup(void)
 {
+	vfio_debugfs_remove_root();
 	ida_destroy(&vfio.device_ida);
 	vfio_cdev_cleanup();
 	class_destroy(vfio.device_class);

drivers/virtio/Kconfig

@@ -60,6 +60,11 @@ config VIRTIO_PCI
 
 	  If unsure, say M.
 
+config VIRTIO_PCI_ADMIN_LEGACY
+	bool
+	depends on VIRTIO_PCI && (X86 || COMPILE_TEST)
+	default y
+
 config VIRTIO_PCI_LEGACY
 	bool "Support for legacy virtio draft 0.9.X and older devices"
 	default y

drivers/virtio/Makefile

@@ -7,6 +7,7 @@ obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
 obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
 virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o
 virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o
+virtio_pci-$(CONFIG_VIRTIO_PCI_ADMIN_LEGACY) += virtio_pci_admin_legacy_io.o
 obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
 obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o
 obj-$(CONFIG_VIRTIO_VDPA) += virtio_vdpa.o

drivers/virtio/virtio.c

@@ -302,9 +302,15 @@ static int virtio_dev_probe(struct device *_d)
 	if (err)
 		goto err;
 
-	err = drv->probe(dev);
+	if (dev->config->create_avq) {
+		err = dev->config->create_avq(dev);
 		if (err)
 			goto err;
+	}
+
+	err = drv->probe(dev);
+	if (err)
+		goto err_probe;
 
 	/* If probe didn't do it, mark device DRIVER_OK ourselves. */
 	if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK))
@@ -316,6 +322,10 @@ static int virtio_dev_probe(struct device *_d)
 	virtio_config_enable(dev);
 
 	return 0;
+
+err_probe:
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
 err:
 	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
 	return err;
@@ -331,6 +341,9 @@ static void virtio_dev_remove(struct device *_d)
 
 	drv->remove(dev);
 
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
+
 	/* Driver should have reset device. */
 	WARN_ON_ONCE(dev->config->get_status(dev));
 
@@ -489,13 +502,20 @@ EXPORT_SYMBOL_GPL(unregister_virtio_device);
 int virtio_device_freeze(struct virtio_device *dev)
 {
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+	int ret;
 
 	virtio_config_disable(dev);
 
 	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
 
-	if (drv && drv->freeze)
-		return drv->freeze(dev);
+	if (drv && drv->freeze) {
+		ret = drv->freeze(dev);
+		if (ret)
+			return ret;
+	}
+
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
 
 	return 0;
 }
@@ -532,10 +552,16 @@ int virtio_device_restore(struct virtio_device *dev)
 	if (ret)
 		goto err;
 
+	if (dev->config->create_avq) {
+		ret = dev->config->create_avq(dev);
+		if (ret)
+			goto err;
+	}
+
 	if (drv->restore) {
 		ret = drv->restore(dev);
 		if (ret)
-			goto err;
+			goto err_restore;
 	}
 
 	/* If restore didn't do it, mark device DRIVER_OK ourselves. */
@@ -546,6 +572,9 @@ int virtio_device_restore(struct virtio_device *dev)
 
 	return 0;
 
+err_restore:
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
 err:
 	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
 	return ret;

drivers/virtio/virtio_pci_admin_legacy_io.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#include <linux/virtio_pci_admin.h>
+#include "virtio_pci_common.h"
+
+/*
+ * virtio_pci_admin_has_legacy_io - Checks whether the legacy IO
+ * commands are supported
+ * @dev: VF pci_dev
+ *
+ * Returns true on success.
+ */
+bool virtio_pci_admin_has_legacy_io(struct pci_dev *pdev)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_pci_device *vp_dev;
+
+	if (!virtio_dev)
+		return false;
+
+	if (!virtio_has_feature(virtio_dev, VIRTIO_F_ADMIN_VQ))
+		return false;
+
+	vp_dev = to_vp_device(virtio_dev);
+
+	if ((vp_dev->admin_vq.supported_cmds & VIRTIO_LEGACY_ADMIN_CMD_BITMAP) ==
+		VIRTIO_LEGACY_ADMIN_CMD_BITMAP)
+		return true;
+	return false;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_has_legacy_io);
+
+static int virtio_pci_admin_legacy_io_write(struct pci_dev *pdev, u16 opcode,
+					    u8 offset, u8 size, u8 *buf)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_legacy_wr_data *data;
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist data_sg;
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	data = kzalloc(sizeof(*data) + size, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->offset = offset;
+	memcpy(data->registers, buf, size);
+	sg_init_one(&data_sg, data, sizeof(*data) + size);
+	cmd.opcode = cpu_to_le16(opcode);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = &data_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+
+	kfree(data);
+	return ret;
+}
+
+/*
+ * virtio_pci_admin_legacy_io_write_common - Write legacy common configuration
+ * of a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the common configuration area to write to
+ * @size: size of the data to write
+ * @buf: buffer which holds the data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_common_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_write(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_common_io_write);
+
+/*
+ * virtio_pci_admin_legacy_io_write_device - Write legacy device configuration
+ * of a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the device configuration area to write to
+ * @size: size of the data to write
+ * @buf: buffer which holds the data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_device_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_write(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_device_io_write);
+
+static int virtio_pci_admin_legacy_io_read(struct pci_dev *pdev, u16 opcode,
+					   u8 offset, u8 size, u8 *buf)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_legacy_rd_data *data;
+	struct scatterlist data_sg, result_sg;
+	struct virtio_admin_cmd cmd = {};
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->offset = offset;
+	sg_init_one(&data_sg, data, sizeof(*data));
+	sg_init_one(&result_sg, buf, size);
+	cmd.opcode = cpu_to_le16(opcode);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = &data_sg;
+	cmd.result_sg = &result_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+
+	kfree(data);
+	return ret;
+}
+
+/*
+ * virtio_pci_admin_legacy_device_io_read - Read legacy device configuration of
+ * a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the device configuration area to read from
+ * @size: size of the data to be read
+ * @buf: buffer to hold the returned data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_device_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_read(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_device_io_read);
+
+/*
+ * virtio_pci_admin_legacy_common_io_read - Read legacy common configuration of
+ * a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the common configuration area to read from
+ * @size: size of the data to be read
+ * @buf: buffer to hold the returned data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_common_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_read(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_common_io_read);
+
+/*
+ * virtio_pci_admin_legacy_io_notify_info - Read the queue notification
+ * information for legacy interface
+ * @dev: VF pci_dev
+ * @req_bar_flags: requested bar flags
+ * @bar: on output the BAR number of the owner or member device
+ * @bar_offset: on output the offset within bar
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_io_notify_info(struct pci_dev *pdev,
+					   u8 req_bar_flags, u8 *bar,
+					   u64 *bar_offset)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_notify_info_result *result;
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist result_sg;
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	result = kzalloc(sizeof(*result), GFP_KERNEL);
+	if (!result)
+		return -ENOMEM;
+
+	sg_init_one(&result_sg, result, sizeof(*result));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.result_sg = &result_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (!ret) {
+		struct virtio_admin_cmd_notify_info_data *entry;
+		int i;
+
+		ret = -ENOENT;
+		for (i = 0; i < VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO; i++) {
+			entry = &result->entries[i];
+			if (entry->flags == VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_END)
+				break;
+			if (entry->flags != req_bar_flags)
+				continue;
+			*bar = entry->bar;
+			*bar_offset = le64_to_cpu(entry->offset);
+			ret = 0;
+			break;
+		}
+	}
+
+	kfree(result);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_io_notify_info);

drivers/virtio/virtio_pci_common.c

@@ -236,6 +236,9 @@ void vp_del_vqs(struct virtio_device *vdev)
 	int i;
 
 	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
+		if (vp_dev->is_avq(vdev, vq->index))
+			continue;
+
 		if (vp_dev->per_vq_vectors) {
 			int v = vp_dev->vqs[vq->index]->msix_vector;
 
@@ -642,6 +645,17 @@ static struct pci_driver virtio_pci_driver = {
 	.sriov_configure = virtio_pci_sriov_configure,
 };
 
+struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev)
+{
+	struct virtio_pci_device *pf_vp_dev;
+
+	pf_vp_dev = pci_iov_get_pf_drvdata(pdev, &virtio_pci_driver);
+	if (IS_ERR(pf_vp_dev))
+		return NULL;
+
+	return &pf_vp_dev->vdev;
+}
+
 module_pci_driver(virtio_pci_driver);
 
 MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>");

drivers/virtio/virtio_pci_common.h

@@ -29,6 +29,7 @@
 #include <linux/virtio_pci_modern.h>
 #include <linux/highmem.h>
 #include <linux/spinlock.h>
+#include <linux/mutex.h>
 
 struct virtio_pci_vq_info {
 	/* the actual virtqueue */
@@ -41,6 +42,17 @@ struct virtio_pci_vq_info {
 	unsigned int msix_vector;
 };
 
+struct virtio_pci_admin_vq {
+	/* Virtqueue info associated with this admin queue. */
+	struct virtio_pci_vq_info info;
+	/* serializing admin commands execution and virtqueue deletion */
+	struct mutex cmd_lock;
+	u64 supported_cmds;
+	/* Name of the admin queue: avq.$vq_index. */
+	char name[10];
+	u16 vq_index;
+};
+
 /* Our device structure */
 struct virtio_pci_device {
 	struct virtio_device vdev;
@@ -58,9 +70,13 @@ struct virtio_pci_device {
 	spinlock_t lock;
 	struct list_head virtqueues;
 
-	/* array of all queues for house-keeping */
+	/* Array of all virtqueues reported in the
+	 * PCI common config num_queues field
+	 */
 	struct virtio_pci_vq_info **vqs;
 
+	struct virtio_pci_admin_vq admin_vq;
+
 	/* MSI-X support */
 	int msix_enabled;
 	int intx_enabled;
@@ -86,6 +102,7 @@ struct virtio_pci_device {
 	void (*del_vq)(struct virtio_pci_vq_info *info);
 
 	u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
+	bool (*is_avq)(struct virtio_device *vdev, unsigned int index);
 };
 
 /* Constants for MSI-X */
@@ -139,4 +156,27 @@ static inline void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
 int virtio_pci_modern_probe(struct virtio_pci_device *);
 void virtio_pci_modern_remove(struct virtio_pci_device *);
 
+struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev);
+
+#define VIRTIO_LEGACY_ADMIN_CMD_BITMAP \
+	(BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO))
+
+/* Unlike modern drivers which support hardware virtio devices, legacy drivers
+ * assume software-based devices: e.g. they don't use proper memory barriers
+ * on ARM, use big endian on PPC, etc. X86 drivers are mostly ok though, more
+ * or less by chance. For now, only support legacy IO on X86.
+ */
+#ifdef CONFIG_VIRTIO_PCI_ADMIN_LEGACY
+#define VIRTIO_ADMIN_CMD_BITMAP VIRTIO_LEGACY_ADMIN_CMD_BITMAP
+#else
+#define VIRTIO_ADMIN_CMD_BITMAP 0
+#endif
+
+int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
+			     struct virtio_admin_cmd *cmd);
+
 #endif

drivers/virtio/virtio_pci_modern.c

@@ -19,6 +19,8 @@
 #define VIRTIO_RING_NO_LEGACY
 #include "virtio_pci_common.h"
 
+#define VIRTIO_AVQ_SGS_MAX	4
+
 static u64 vp_get_features(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -26,6 +28,187 @@ static u64 vp_get_features(struct virtio_device *vdev)
 	return vp_modern_get_features(&vp_dev->mdev);
 }
 
+static bool vp_is_avq(struct virtio_device *vdev, unsigned int index)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return false;
+
+	return index == vp_dev->admin_vq.vq_index;
+}
+
+static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq,
+				    u16 opcode,
+				    struct scatterlist **sgs,
+				    unsigned int out_num,
+				    unsigned int in_num,
+				    void *data)
+{
+	struct virtqueue *vq;
+	int ret, len;
+
+	vq = admin_vq->info.vq;
+	if (!vq)
+		return -EIO;
+
+	if (opcode != VIRTIO_ADMIN_CMD_LIST_QUERY &&
+	    opcode != VIRTIO_ADMIN_CMD_LIST_USE &&
+	    !((1ULL << opcode) & admin_vq->supported_cmds))
+		return -EOPNOTSUPP;
+
+	ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, data, GFP_KERNEL);
+	if (ret < 0)
+		return -EIO;
+
+	if (unlikely(!virtqueue_kick(vq)))
+		return -EIO;
+
+	while (!virtqueue_get_buf(vq, &len) &&
+	       !virtqueue_is_broken(vq))
+		cpu_relax();
+
+	if (virtqueue_is_broken(vq))
+		return -EIO;
+
+	return 0;
+}
+
+int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
+			     struct virtio_admin_cmd *cmd)
+{
+	struct scatterlist *sgs[VIRTIO_AVQ_SGS_MAX], hdr, stat;
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_admin_cmd_status *va_status;
+	unsigned int out_num = 0, in_num = 0;
+	struct virtio_admin_cmd_hdr *va_hdr;
+	u16 status;
+	int ret;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return -EOPNOTSUPP;
+
+	va_status = kzalloc(sizeof(*va_status), GFP_KERNEL);
+	if (!va_status)
+		return -ENOMEM;
+
+	va_hdr = kzalloc(sizeof(*va_hdr), GFP_KERNEL);
+	if (!va_hdr) {
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
+
+	va_hdr->opcode = cmd->opcode;
+	va_hdr->group_type = cmd->group_type;
+	va_hdr->group_member_id = cmd->group_member_id;
+
+	/* Add header */
+	sg_init_one(&hdr, va_hdr, sizeof(*va_hdr));
+	sgs[out_num] = &hdr;
+	out_num++;
+
+	if (cmd->data_sg) {
+		sgs[out_num] = cmd->data_sg;
+		out_num++;
+	}
+
+	/* Add return status */
+	sg_init_one(&stat, va_status, sizeof(*va_status));
+	sgs[out_num + in_num] = &stat;
+	in_num++;
+
+	if (cmd->result_sg) {
+		sgs[out_num + in_num] = cmd->result_sg;
+		in_num++;
+	}
+
+	mutex_lock(&vp_dev->admin_vq.cmd_lock);
+	ret = virtqueue_exec_admin_cmd(&vp_dev->admin_vq,
+				       le16_to_cpu(cmd->opcode),
+				       sgs, out_num, in_num, sgs);
+	mutex_unlock(&vp_dev->admin_vq.cmd_lock);
+
+	if (ret) {
+		dev_err(&vdev->dev,
+			"Failed to execute command on admin vq: %d\n.", ret);
+		goto err_cmd_exec;
+	}
+
+	status = le16_to_cpu(va_status->status);
+	if (status != VIRTIO_ADMIN_STATUS_OK) {
+		dev_err(&vdev->dev,
+			"admin command error: status(%#x) qualifier(%#x)\n",
+			status, le16_to_cpu(va_status->status_qualifier));
+		ret = -status;
+	}
+
+err_cmd_exec:
+	kfree(va_hdr);
+err_alloc:
+	kfree(va_status);
+	return ret;
+}
+
+static void virtio_pci_admin_cmd_list_init(struct virtio_device *virtio_dev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(virtio_dev);
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist result_sg;
+	struct scatterlist data_sg;
+	__le64 *data;
+	int ret;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return;
+
+	sg_init_one(&result_sg, data, sizeof(*data));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_LIST_QUERY);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.result_sg = &result_sg;
+
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (ret)
+		goto end;
+
+	*data &= cpu_to_le64(VIRTIO_ADMIN_CMD_BITMAP);
+	sg_init_one(&data_sg, data, sizeof(*data));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_LIST_USE);
+	cmd.data_sg = &data_sg;
+	cmd.result_sg = NULL;
+
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (ret)
+		goto end;
+
+	vp_dev->admin_vq.supported_cmds = le64_to_cpu(*data);
+end:
+	kfree(data);
+}
+
+static void vp_modern_avq_activate(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return;
+
+	__virtqueue_unbreak(admin_vq->info.vq);
+	virtio_pci_admin_cmd_list_init(vdev);
+}
+
+static void vp_modern_avq_deactivate(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return;
+
+	__virtqueue_break(admin_vq->info.vq);
+}
+
 static void vp_transport_features(struct virtio_device *vdev, u64 features)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -37,6 +220,9 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features)
 
 	if (features & BIT_ULL(VIRTIO_F_RING_RESET))
 		__virtio_set_bit(vdev, VIRTIO_F_RING_RESET);
+
+	if (features & BIT_ULL(VIRTIO_F_ADMIN_VQ))
+		__virtio_set_bit(vdev, VIRTIO_F_ADMIN_VQ);
 }
 
 static int __vp_check_common_size_one_feature(struct virtio_device *vdev, u32 fbit,
@@ -69,6 +255,9 @@ static int vp_check_common_size(struct virtio_device *vdev)
 	if (vp_check_common_size_one_feature(vdev, VIRTIO_F_RING_RESET, queue_reset))
 		return -EINVAL;
 
+	if (vp_check_common_size_one_feature(vdev, VIRTIO_F_ADMIN_VQ, admin_queue_num))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -195,6 +384,8 @@ static void vp_set_status(struct virtio_device *vdev, u8 status)
 	/* We should never be setting status to 0. */
 	BUG_ON(status == 0);
 	vp_modern_set_status(&vp_dev->mdev, status);
+	if (status & VIRTIO_CONFIG_S_DRIVER_OK)
+		vp_modern_avq_activate(vdev);
 }
 
 static void vp_reset(struct virtio_device *vdev)
@@ -211,6 +402,9 @@ static void vp_reset(struct virtio_device *vdev)
 	 */
 	while (vp_modern_get_status(mdev))
 		msleep(1);
+
+	vp_modern_avq_deactivate(vdev);
+
 	/* Flush pending VQ/configuration callbacks. */
 	vp_synchronize_vectors(vdev);
 }
@@ -345,6 +539,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 	bool (*notify)(struct virtqueue *vq);
 	struct virtqueue *vq;
+	bool is_avq;
 	u16 num;
 	int err;
 
@@ -353,11 +548,13 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	else
 		notify = vp_notify;
 
-	if (index >= vp_modern_get_num_queues(mdev))
+	is_avq = vp_is_avq(&vp_dev->vdev, index);
+	if (index >= vp_modern_get_num_queues(mdev) && !is_avq)
 		return ERR_PTR(-EINVAL);
 
+	num = is_avq ?
+		VIRTIO_AVQ_SGS_MAX : vp_modern_get_queue_size(mdev, index);
 	/* Check if queue is either not available or already active. */
-	num = vp_modern_get_queue_size(mdev, index);
 	if (!num || vp_modern_get_queue_enable(mdev, index))
 		return ERR_PTR(-ENOENT);
 
@@ -383,6 +580,12 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 		goto err;
 	}
 
+	if (is_avq) {
+		mutex_lock(&vp_dev->admin_vq.cmd_lock);
+		vp_dev->admin_vq.info.vq = vq;
+		mutex_unlock(&vp_dev->admin_vq.cmd_lock);
+	}
+
 	return vq;
 
 err:
@@ -418,6 +621,12 @@ static void del_vq(struct virtio_pci_vq_info *info)
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 
+	if (vp_is_avq(&vp_dev->vdev, vq->index)) {
+		mutex_lock(&vp_dev->admin_vq.cmd_lock);
+		vp_dev->admin_vq.info.vq = NULL;
+		mutex_unlock(&vp_dev->admin_vq.cmd_lock);
+	}
+
 	if (vp_dev->msix_enabled)
 		vp_modern_queue_vector(mdev, vq->index,
 				       VIRTIO_MSI_NO_VECTOR);
@@ -527,6 +736,45 @@ static bool vp_get_shm_region(struct virtio_device *vdev,
 	return true;
 }
 
+static int vp_modern_create_avq(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *avq;
+	struct virtqueue *vq;
+	u16 admin_q_num;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return 0;
+
+	admin_q_num = vp_modern_avq_num(&vp_dev->mdev);
+	if (!admin_q_num)
+		return -EINVAL;
+
+	avq = &vp_dev->admin_vq;
+	avq->vq_index = vp_modern_avq_index(&vp_dev->mdev);
+	sprintf(avq->name, "avq.%u", avq->vq_index);
+	vq = vp_dev->setup_vq(vp_dev, &vp_dev->admin_vq.info, avq->vq_index, NULL,
+			      avq->name, NULL, VIRTIO_MSI_NO_VECTOR);
+	if (IS_ERR(vq)) {
+		dev_err(&vdev->dev, "failed to setup admin virtqueue, err=%ld",
+			PTR_ERR(vq));
+		return PTR_ERR(vq);
+	}
+
+	vp_modern_set_queue_enable(&vp_dev->mdev, avq->info.vq->index, true);
+	return 0;
+}
+
+static void vp_modern_destroy_avq(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return;
+
+	vp_dev->del_vq(&vp_dev->admin_vq.info);
+}
+
 static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.get		= NULL,
 	.set		= NULL,
@@ -545,6 +793,8 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.get_shm_region  = vp_get_shm_region,
 	.disable_vq_and_reset = vp_modern_disable_vq_and_reset,
 	.enable_vq_after_reset = vp_modern_enable_vq_after_reset,
+	.create_avq = vp_modern_create_avq,
+	.destroy_avq = vp_modern_destroy_avq,
 };
 
 static const struct virtio_config_ops virtio_pci_config_ops = {
@@ -565,6 +815,8 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.get_shm_region  = vp_get_shm_region,
 	.disable_vq_and_reset = vp_modern_disable_vq_and_reset,
 	.enable_vq_after_reset = vp_modern_enable_vq_after_reset,
+	.create_avq = vp_modern_create_avq,
+	.destroy_avq = vp_modern_destroy_avq,
 };
 
 /* the PCI probing function */
@@ -588,9 +840,11 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	vp_dev->config_vector = vp_config_vector;
 	vp_dev->setup_vq = setup_vq;
 	vp_dev->del_vq = del_vq;
+	vp_dev->is_avq = vp_is_avq;
 	vp_dev->isr = mdev->isr;
 	vp_dev->vdev.id = mdev->id;
 
+	mutex_init(&vp_dev->admin_vq.cmd_lock);
 	return 0;
 }
 
@@ -598,5 +852,6 @@ void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
 {
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 
+	mutex_destroy(&vp_dev->admin_vq.cmd_lock);
 	vp_modern_remove(mdev);
 }

drivers/virtio/virtio_pci_modern_dev.c

@@ -207,6 +207,10 @@ static inline void check_offsets(void)
 		     offsetof(struct virtio_pci_modern_common_cfg, queue_notify_data));
 	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_RESET !=
 		     offsetof(struct virtio_pci_modern_common_cfg, queue_reset));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_ADM_Q_IDX !=
+		     offsetof(struct virtio_pci_modern_common_cfg, admin_queue_index));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_ADM_Q_NUM !=
+		     offsetof(struct virtio_pci_modern_common_cfg, admin_queue_num));
 }
 
 /*
@@ -296,7 +300,7 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev)
 	mdev->common = vp_modern_map_capability(mdev, common,
 			      sizeof(struct virtio_pci_common_cfg), 4, 0,
 			      offsetofend(struct virtio_pci_modern_common_cfg,
-					  queue_reset),
+					  admin_queue_num),
 			      &mdev->common_len, NULL);
 	if (!mdev->common)
 		goto err_map_common;
@@ -719,6 +723,24 @@ void __iomem *vp_modern_map_vq_notify(struct virtio_pci_modern_device *mdev,
 }
 EXPORT_SYMBOL_GPL(vp_modern_map_vq_notify);
 
+u16 vp_modern_avq_num(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_modern_common_cfg __iomem *cfg;
+
+	cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common;
+	return vp_ioread16(&cfg->admin_queue_num);
+}
+EXPORT_SYMBOL_GPL(vp_modern_avq_num);
+
+u16 vp_modern_avq_index(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_modern_common_cfg __iomem *cfg;
+
+	cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common;
+	return vp_ioread16(&cfg->admin_queue_index);
+}
+EXPORT_SYMBOL_GPL(vp_modern_avq_index);
+
 MODULE_VERSION("0.1");
 MODULE_DESCRIPTION("Modern Virtio PCI Device");
 MODULE_AUTHOR("Jason Wang <jasowang@redhat.com>");

include/linux/vfio.h

@@ -69,6 +69,13 @@ struct vfio_device {
 	u8 iommufd_attached:1;
 #endif
 	u8 cdev_opened:1;
+#ifdef CONFIG_DEBUG_FS
+	/*
+	 * debug_root is a static property of the vfio_device
+	 * which must be set prior to registering the vfio_device.
+	 */
+	struct dentry *debug_root;
+#endif
 };
 
 /**

include/linux/vfio_pci_core.h

@@ -127,7 +127,27 @@ int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf);
 int vfio_pci_core_enable(struct vfio_pci_core_device *vdev);
 void vfio_pci_core_disable(struct vfio_pci_core_device *vdev);
 void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev);
+int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar);
 pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev,
 						pci_channel_state_t state);
 
+#define VFIO_IOWRITE_DECLATION(size) \
+int vfio_pci_core_iowrite##size(struct vfio_pci_core_device *vdev,	\
+			bool test_mem, u##size val, void __iomem *io);
+
+VFIO_IOWRITE_DECLATION(8)
+VFIO_IOWRITE_DECLATION(16)
+VFIO_IOWRITE_DECLATION(32)
+#ifdef iowrite64
+VFIO_IOWRITE_DECLATION(64)
+#endif
+
+#define VFIO_IOREAD_DECLATION(size) \
+int vfio_pci_core_ioread##size(struct vfio_pci_core_device *vdev,	\
+			bool test_mem, u##size *val, void __iomem *io);
+
+VFIO_IOREAD_DECLATION(8)
+VFIO_IOREAD_DECLATION(16)
+VFIO_IOREAD_DECLATION(32)
+
 #endif /* VFIO_PCI_CORE_H */

include/linux/virtio.h

@@ -103,6 +103,14 @@ int virtqueue_resize(struct virtqueue *vq, u32 num,
 int virtqueue_reset(struct virtqueue *vq,
 		    void (*recycle)(struct virtqueue *vq, void *buf));
 
+struct virtio_admin_cmd {
+	__le16 opcode;
+	__le16 group_type;
+	__le64 group_member_id;
+	struct scatterlist *data_sg;
+	struct scatterlist *result_sg;
+};
+
 /**
  * struct virtio_device - representation of a device using virtio
  * @index: unique position on the virtio bus

include/linux/virtio_config.h

@@ -93,6 +93,8 @@ typedef void vq_callback_t(struct virtqueue *);
  *	Returns 0 on success or error status
  *	If disable_vq_and_reset is set, then enable_vq_after_reset must also be
  *	set.
+ * @create_avq: create admin virtqueue resource.
+ * @destroy_avq: destroy admin virtqueue resource.
  */
 struct virtio_config_ops {
 	void (*get)(struct virtio_device *vdev, unsigned offset,
@@ -120,6 +122,8 @@ struct virtio_config_ops {
 			       struct virtio_shm_region *region, u8 id);
 	int (*disable_vq_and_reset)(struct virtqueue *vq);
 	int (*enable_vq_after_reset)(struct virtqueue *vq);
+	int (*create_avq)(struct virtio_device *vdev);
+	void (*destroy_avq)(struct virtio_device *vdev);
 };
 
 /* If driver didn't advertise the feature, it will never appear. */

include/linux/virtio_pci_admin.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_VIRTIO_PCI_ADMIN_H
+#define _LINUX_VIRTIO_PCI_ADMIN_H
+
+#include <linux/types.h>
+#include <linux/pci.h>
+
+#ifdef CONFIG_VIRTIO_PCI_ADMIN_LEGACY
+bool virtio_pci_admin_has_legacy_io(struct pci_dev *pdev);
+int virtio_pci_admin_legacy_common_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf);
+int virtio_pci_admin_legacy_common_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf);
+int virtio_pci_admin_legacy_device_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf);
+int virtio_pci_admin_legacy_device_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf);
+int virtio_pci_admin_legacy_io_notify_info(struct pci_dev *pdev,
+					   u8 req_bar_flags, u8 *bar,
+					   u64 *bar_offset);
+#endif
+
+#endif /* _LINUX_VIRTIO_PCI_ADMIN_H */

include/linux/virtio_pci_modern.h

@@ -125,4 +125,6 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev);
 void vp_modern_remove(struct virtio_pci_modern_device *mdev);
 int vp_modern_get_queue_reset(struct virtio_pci_modern_device *mdev, u16 index);
 void vp_modern_set_queue_reset(struct virtio_pci_modern_device *mdev, u16 index);
+u16 vp_modern_avq_num(struct virtio_pci_modern_device *mdev);
+u16 vp_modern_avq_index(struct virtio_pci_modern_device *mdev);
 #endif

include/uapi/linux/vfio.h

@@ -1219,6 +1219,7 @@ enum vfio_device_mig_state {
 	VFIO_DEVICE_STATE_RUNNING_P2P = 5,
 	VFIO_DEVICE_STATE_PRE_COPY = 6,
 	VFIO_DEVICE_STATE_PRE_COPY_P2P = 7,
+	VFIO_DEVICE_STATE_NR,
 };
 
 /**

include/uapi/linux/virtio_config.h

@@ -52,7 +52,7 @@
  * rest are per-device feature bits.
  */
 #define VIRTIO_TRANSPORT_F_START	28
-#define VIRTIO_TRANSPORT_F_END		41
+#define VIRTIO_TRANSPORT_F_END		42
 
 #ifndef VIRTIO_CONFIG_NO_LEGACY
 /* Do we get callbacks when the ring is completely used, even if we've
@@ -114,4 +114,10 @@
  * This feature indicates that the driver can reset a queue individually.
  */
 #define VIRTIO_F_RING_RESET		40
+
+/*
+ * This feature indicates that the device support administration virtqueues.
+ */
+#define VIRTIO_F_ADMIN_VQ		41
+
 #endif /* _UAPI_LINUX_VIRTIO_CONFIG_H */

include/uapi/linux/virtio_pci.h

@@ -175,6 +175,9 @@ struct virtio_pci_modern_common_cfg {
 
 	__le16 queue_notify_data;	/* read-write */
 	__le16 queue_reset;		/* read-write */
+
+	__le16 admin_queue_index;	/* read-only */
+	__le16 admin_queue_num;		/* read-only */
 };
 
 /* Fields in VIRTIO_PCI_CAP_PCI_CFG: */
@@ -215,7 +218,72 @@ struct virtio_pci_cfg_cap {
 #define VIRTIO_PCI_COMMON_Q_USEDHI	52
 #define VIRTIO_PCI_COMMON_Q_NDATA	56
 #define VIRTIO_PCI_COMMON_Q_RESET	58
+#define VIRTIO_PCI_COMMON_ADM_Q_IDX	60
+#define VIRTIO_PCI_COMMON_ADM_Q_NUM	62
 
 #endif /* VIRTIO_PCI_NO_MODERN */
 
+/* Admin command status. */
+#define VIRTIO_ADMIN_STATUS_OK		0
+
+/* Admin command opcode. */
+#define VIRTIO_ADMIN_CMD_LIST_QUERY	0x0
+#define VIRTIO_ADMIN_CMD_LIST_USE	0x1
+
+/* Admin command group type. */
+#define VIRTIO_ADMIN_GROUP_TYPE_SRIOV	0x1
+
+/* Transitional device admin command. */
+#define VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE	0x2
+#define VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ		0x3
+#define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE		0x4
+#define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ		0x5
+#define VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO		0x6
+
+struct __packed virtio_admin_cmd_hdr {
+	__le16 opcode;
+	/*
+	 * 1 - SR-IOV
+	 * 2-65535 - reserved
+	 */
+	__le16 group_type;
+	/* Unused, reserved for future extensions. */
+	__u8 reserved1[12];
+	__le64 group_member_id;
+};
+
+struct __packed virtio_admin_cmd_status {
+	__le16 status;
+	__le16 status_qualifier;
+	/* Unused, reserved for future extensions. */
+	__u8 reserved2[4];
+};
+
+struct __packed virtio_admin_cmd_legacy_wr_data {
+	__u8 offset; /* Starting offset of the register(s) to write. */
+	__u8 reserved[7];
+	__u8 registers[];
+};
+
+struct __packed virtio_admin_cmd_legacy_rd_data {
+	__u8 offset; /* Starting offset of the register(s) to read. */
+};
+
+#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_END 0
+#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_DEV 0x1
+#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_MEM 0x2
+
+#define VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO 4
+
+struct __packed virtio_admin_cmd_notify_info_data {
+	__u8 flags; /* 0 = end of list, 1 = owner device, 2 = member device */
+	__u8 bar; /* BAR of the member or the owner device */
+	__u8 padding[6];
+	__le64 offset; /* Offset within bar. */
+};
+
+struct virtio_admin_cmd_notify_info_result {
+	struct virtio_admin_cmd_notify_info_data entries[VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO];
+};
+
 #endif