Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

8 files changed, 832 insertions, 150 deletions

diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index 8125e5f378..18c397df56 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/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
diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile
index 45167be462..046139a4ec 100644
--- a/drivers/vfio/pci/Makefile
+++ b/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/
diff --git a/drivers/vfio/pci/pds/dirty.c b/drivers/vfio/pci/pds/dirty.c
index 27607d7b90..8ddf4346fc 100644
--- a/drivers/vfio/pci/pds/dirty.c
+++ b/drivers/vfio/pci/pds/dirty.c
@@ -70,7 +70,7 @@ out_free_region_info:
 	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;
@@ -85,47 +85,63 @@ 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,
-				      u32 page_count)
+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;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
@@ -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_bitmaps(region,
+						   page_count / BITS_PER_BYTE);
+		if (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, &dirty->host_ack,
-					 page_count);
-	if (err) {
-		__pds_vfio_dirty_free_sgl(pds_vfio, &dirty->host_seq);
-		return err;
+		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 @@ out_free_pages:
 }
 
 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;
@@ -469,25 +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 || ((iova - dirty->region_start + length) > 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",
@@ -495,23 +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_start) /
-				  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;
 
diff --git a/drivers/vfio/pci/pds/dirty.h b/drivers/vfio/pci/pds/dirty.h
index f78da25d75..c8e23018b8 100644
--- a/drivers/vfio/pci/pds/dirty.h
+++ b/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;
 };
 
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index e27de61ac9..07fea08ea8 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/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)
@@ -119,13 +121,13 @@ 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,
-							 val, io + off);
+				ret = vfio_pci_core_iowrite32(vdev, test_mem,
+							      val, io + off);
 				if (ret)
 					return ret;
 			} else {
-				ret = vfio_pci_ioread32(vdev, test_mem,
-							&val, io + off);
+				ret = vfio_pci_core_ioread32(vdev, test_mem,
+							     &val, io + off);
 				if (ret)
 					return ret;
 
@@ -141,13 +143,13 @@ 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,
-							 val, io + off);
+				ret = vfio_pci_core_iowrite16(vdev, test_mem,
+							      val, io + off);
 				if (ret)
 					return ret;
 			} else {
-				ret = vfio_pci_ioread16(vdev, test_mem,
-							&val, io + off);
+				ret = vfio_pci_core_ioread16(vdev, test_mem,
+							     &val, io + off);
 				if (ret)
 					return ret;
 
@@ -163,13 +165,13 @@ 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,
-							val, io + off);
+				ret = vfio_pci_core_iowrite8(vdev, test_mem,
+							     val, io + off);
 				if (ret)
 					return ret;
 			} else {
-				ret = vfio_pci_ioread8(vdev, test_mem,
-						       &val, io + off);
+				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;
@@ -363,21 +366,21 @@ static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd,
 {
 	switch (ioeventfd->count) {
 	case 1:
-		vfio_pci_iowrite8(ioeventfd->vdev, test_mem,
-				  ioeventfd->data, ioeventfd->addr);
+		vfio_pci_core_iowrite8(ioeventfd->vdev, test_mem,
+				       ioeventfd->data, ioeventfd->addr);
 		break;
 	case 2:
-		vfio_pci_iowrite16(ioeventfd->vdev, test_mem,
-				   ioeventfd->data, ioeventfd->addr);
+		vfio_pci_core_iowrite16(ioeventfd->vdev, test_mem,
+					ioeventfd->data, ioeventfd->addr);
 		break;
 	case 4:
-		vfio_pci_iowrite32(ioeventfd->vdev, test_mem,
-				   ioeventfd->data, ioeventfd->addr);
+		vfio_pci_core_iowrite32(ioeventfd->vdev, test_mem,
+					ioeventfd->data, ioeventfd->addr);
 		break;
 #ifdef iowrite64
 	case 8:
-		vfio_pci_iowrite64(ioeventfd->vdev, test_mem,
-				   ioeventfd->data, ioeventfd->addr);
+		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;
 
diff --git a/drivers/vfio/pci/virtio/Kconfig b/drivers/vfio/pci/virtio/Kconfig
new file mode 100644
index 0000000000..bd80eca4a1
--- /dev/null
+++ b/drivers/vfio/pci/virtio/Kconfig
@@ -0,0 +1,15 @@
+# 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.
diff --git a/drivers/vfio/pci/virtio/Makefile b/drivers/vfio/pci/virtio/Makefile
new file mode 100644
index 0000000000..7171105baf
--- /dev/null
+++ b/drivers/vfio/pci/virtio/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_VIRTIO_VFIO_PCI) += virtio-vfio-pci.o
+virtio-vfio-pci-y := main.o
diff --git a/drivers/vfio/pci/virtio/main.c b/drivers/vfio/pci/virtio/main.c
new file mode 100644
index 0000000000..d5af683837
--- /dev/null
+++ b/drivers/vfio/pci/virtio/main.c
@@ -0,0 +1,576 @@
+// 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");