[PATCH V3 00/19] vDPA driver for virtio-pci device

[PATCH V3 00/19] vDPA driver for virtio-pci device

[Jason Wang]

Hi all:

This series tries to implement a vDPA driver for virtio-pci device
which will bridge between vDPA bus and virtio-pci device.

This could be used for future feature prototyping and testing.

Please review

Changes since V2:

- tweak config prompt
- switch from 'cb' to 'config_cb' for vp_vdpa config interrupt
- use a macro for vp_vdpa msix name length

Changes since V1:

- don't try to use devres for virtio-pci core
- tweak the commit log
- split the patches furtherly to ease the reviewing

Changes since RFC:

- Split common codes from virito-pci and share it with vDPA driver
- Use dynamic id in order to be less confusing with virtio-pci driver
- No feature whitelist, supporting any features (mq, config etc)

Thanks

Jason Wang (19):
  virtio-pci: do not access iomem via struct virtio_pci_device directly
  virtio-pci: split out modern device
  virtio-pci-modern: factor out modern device initialization logic
  virtio-pci-modern: introduce vp_modern_remove()
  virtio-pci-modern: introduce helper to set config vector
  virtio-pci-modern: introduce helpers for setting and getting status
  virtio-pci-modern: introduce helpers for setting and getting features
  virtio-pci-modern: introduce vp_modern_generation()
  virtio-pci-modern: introduce vp_modern_set_queue_vector()
  virtio-pci-modern: introduce vp_modern_queue_address()
  virtio-pci-modern: introduce helper to set/get queue_enable
  virtio-pci-modern: introduce helper for setting/geting queue size
  virtio-pci-modern: introduce helper for getting queue nums
  virtio-pci-modern: introduce helper to get notification offset
  virito-pci-modern: rename map_capability() to
    vp_modern_map_capability()
  virtio-pci: introduce modern device module
  vdpa: set the virtqueue num during register
  virtio_vdpa: don't warn when fail to disable vq
  vdpa: introduce virtio pci driver

 drivers/vdpa/Kconfig                   |   6 +
 drivers/vdpa/Makefile                  |   1 +
 drivers/vdpa/ifcvf/ifcvf_main.c        |   5 +-
 drivers/vdpa/mlx5/net/mlx5_vnet.c      |   5 +-
 drivers/vdpa/vdpa.c                    |   8 +-
 drivers/vdpa/vdpa_sim/vdpa_sim.c       |   4 +-
 drivers/vdpa/virtio_pci/Makefile       |   2 +
 drivers/vdpa/virtio_pci/vp_vdpa.c      | 456 +++++++++++++++++++
 drivers/virtio/Kconfig                 |  10 +-
 drivers/virtio/Makefile                |   1 +
 drivers/virtio/virtio_pci_common.h     |  22 +-
 drivers/virtio/virtio_pci_modern.c     | 506 +++------------------
 drivers/virtio/virtio_pci_modern_dev.c | 599 +++++++++++++++++++++++++
 drivers/virtio/virtio_vdpa.c           |   3 +-
 include/linux/vdpa.h                   |   7 +-
 include/linux/virtio_pci_modern.h      | 111 +++++
 16 files changed, 1274 insertions(+), 472 deletions(-)
 create mode 100644 drivers/vdpa/virtio_pci/Makefile
 create mode 100644 drivers/vdpa/virtio_pci/vp_vdpa.c
 create mode 100644 drivers/virtio/virtio_pci_modern_dev.c
 create mode 100644 include/linux/virtio_pci_modern.h

-- 
2.25.1

[PATCH V3 01/19] virtio-pci: do not access iomem via struct virtio_pci_device directly

[Jason Wang]

Instead of accessing iomem via struct virito_pci_device directly,
tweak to call the io accessors through the iomem structure. This will
ease the splitting of modern virtio device logic.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 76 ++++++++++++++++++------------
 1 file changed, 46 insertions(+), 30 deletions(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 3d6ae5a5e252..df1481fd400c 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -141,12 +141,13 @@ static void __iomem *map_capability(struct pci_dev *dev, int off,
 static u64 vp_get_features(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
 	u64 features;
 
-	vp_iowrite32(0, &vp_dev->common->device_feature_select);
-	features = vp_ioread32(&vp_dev->common->device_feature);
-	vp_iowrite32(1, &vp_dev->common->device_feature_select);
-	features |= ((u64)vp_ioread32(&vp_dev->common->device_feature) << 32);
+	vp_iowrite32(0, &cfg->device_feature_select);
+	features = vp_ioread32(&cfg->device_feature);
+	vp_iowrite32(1, &cfg->device_feature_select);
+	features |= ((u64)vp_ioread32(&cfg->device_feature) << 32);
 
 	return features;
 }
@@ -165,6 +166,7 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features)
 static int vp_finalize_features(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
 	u64 features = vdev->features;
 
 	/* Give virtio_ring a chance to accept features. */
@@ -179,10 +181,10 @@ static int vp_finalize_features(struct virtio_device *vdev)
 		return -EINVAL;
 	}
 
-	vp_iowrite32(0, &vp_dev->common->guest_feature_select);
-	vp_iowrite32((u32)vdev->features, &vp_dev->common->guest_feature);
-	vp_iowrite32(1, &vp_dev->common->guest_feature_select);
-	vp_iowrite32(vdev->features >> 32, &vp_dev->common->guest_feature);
+	vp_iowrite32(0, &cfg->guest_feature_select);
+	vp_iowrite32((u32)vdev->features, &cfg->guest_feature);
+	vp_iowrite32(1, &cfg->guest_feature_select);
+	vp_iowrite32(vdev->features >> 32, &cfg->guest_feature);
 
 	return 0;
 }
@@ -192,6 +194,7 @@ static void vp_get(struct virtio_device *vdev, unsigned offset,
 		   void *buf, unsigned len)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	void __iomem *device = vp_dev->device;
 	u8 b;
 	__le16 w;
 	__le32 l;
@@ -200,21 +203,21 @@ static void vp_get(struct virtio_device *vdev, unsigned offset,
 
 	switch (len) {
 	case 1:
-		b = ioread8(vp_dev->device + offset);
+		b = ioread8(device + offset);
 		memcpy(buf, &b, sizeof b);
 		break;
 	case 2:
-		w = cpu_to_le16(ioread16(vp_dev->device + offset));
+		w = cpu_to_le16(ioread16(device + offset));
 		memcpy(buf, &w, sizeof w);
 		break;
 	case 4:
-		l = cpu_to_le32(ioread32(vp_dev->device + offset));
+		l = cpu_to_le32(ioread32(device + offset));
 		memcpy(buf, &l, sizeof l);
 		break;
 	case 8:
-		l = cpu_to_le32(ioread32(vp_dev->device + offset));
+		l = cpu_to_le32(ioread32(device + offset));
 		memcpy(buf, &l, sizeof l);
-		l = cpu_to_le32(ioread32(vp_dev->device + offset + sizeof l));
+		l = cpu_to_le32(ioread32(device + offset + sizeof l));
 		memcpy(buf + sizeof l, &l, sizeof l);
 		break;
 	default:
@@ -228,6 +231,7 @@ static void vp_set(struct virtio_device *vdev, unsigned offset,
 		   const void *buf, unsigned len)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	void __iomem *device = vp_dev->device;
 	u8 b;
 	__le16 w;
 	__le32 l;
@@ -237,21 +241,21 @@ static void vp_set(struct virtio_device *vdev, unsigned offset,
 	switch (len) {
 	case 1:
 		memcpy(&b, buf, sizeof b);
-		iowrite8(b, vp_dev->device + offset);
+		iowrite8(b, device + offset);
 		break;
 	case 2:
 		memcpy(&w, buf, sizeof w);
-		iowrite16(le16_to_cpu(w), vp_dev->device + offset);
+		iowrite16(le16_to_cpu(w), device + offset);
 		break;
 	case 4:
 		memcpy(&l, buf, sizeof l);
-		iowrite32(le32_to_cpu(l), vp_dev->device + offset);
+		iowrite32(le32_to_cpu(l), device + offset);
 		break;
 	case 8:
 		memcpy(&l, buf, sizeof l);
-		iowrite32(le32_to_cpu(l), vp_dev->device + offset);
+		iowrite32(le32_to_cpu(l), device + offset);
 		memcpy(&l, buf + sizeof l, sizeof l);
-		iowrite32(le32_to_cpu(l), vp_dev->device + offset + sizeof l);
+		iowrite32(le32_to_cpu(l), device + offset + sizeof l);
 		break;
 	default:
 		BUG();
@@ -261,35 +265,43 @@ static void vp_set(struct virtio_device *vdev, unsigned offset,
 static u32 vp_generation(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	return vp_ioread8(&vp_dev->common->config_generation);
+	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+
+	return vp_ioread8(&cfg->config_generation);
 }
 
 /* config->{get,set}_status() implementations */
 static u8 vp_get_status(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	return vp_ioread8(&vp_dev->common->device_status);
+	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+
+	return vp_ioread8(&cfg->device_status);
 }
 
 static void vp_set_status(struct virtio_device *vdev, u8 status)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+
 	/* We should never be setting status to 0. */
 	BUG_ON(status == 0);
-	vp_iowrite8(status, &vp_dev->common->device_status);
+	vp_iowrite8(status, &cfg->device_status);
 }
 
 static void vp_reset(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+
 	/* 0 status means a reset. */
-	vp_iowrite8(0, &vp_dev->common->device_status);
+	vp_iowrite8(0, &cfg->device_status);
 	/* After writing 0 to device_status, the driver MUST wait for a read of
 	 * device_status to return 0 before reinitializing the device.
 	 * This will flush out the status write, and flush in device writes,
 	 * including MSI-X interrupts, if any.
 	 */
-	while (vp_ioread8(&vp_dev->common->device_status))
+	while (vp_ioread8(&cfg->device_status))
 		msleep(1);
 	/* Flush pending VQ/configuration callbacks. */
 	vp_synchronize_vectors(vdev);
@@ -297,11 +309,13 @@ static void vp_reset(struct virtio_device *vdev)
 
 static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 {
+	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+
 	/* Setup the vector used for configuration events */
-	vp_iowrite16(vector, &vp_dev->common->msix_config);
+	vp_iowrite16(vector, &cfg->msix_config);
 	/* Verify we had enough resources to assign the vector */
 	/* Will also flush the write out to device */
-	return vp_ioread16(&vp_dev->common->msix_config);
+	return vp_ioread16(&cfg->msix_config);
 }
 
 static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
@@ -407,6 +421,7 @@ static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 			      struct irq_affinity *desc)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
 	struct virtqueue *vq;
 	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, ctx, desc);
 
@@ -417,8 +432,8 @@ static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 	 * this, there's no way to go back except reset.
 	 */
 	list_for_each_entry(vq, &vdev->vqs, list) {
-		vp_iowrite16(vq->index, &vp_dev->common->queue_select);
-		vp_iowrite16(1, &vp_dev->common->queue_enable);
+		vp_iowrite16(vq->index, &cfg->queue_select);
+		vp_iowrite16(1, &cfg->queue_enable);
 	}
 
 	return 0;
@@ -428,14 +443,15 @@ static void del_vq(struct virtio_pci_vq_info *info)
 {
 	struct virtqueue *vq = info->vq;
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
 
-	vp_iowrite16(vq->index, &vp_dev->common->queue_select);
+	vp_iowrite16(vq->index, &cfg->queue_select);
 
 	if (vp_dev->msix_enabled) {
 		vp_iowrite16(VIRTIO_MSI_NO_VECTOR,
-			     &vp_dev->common->queue_msix_vector);
+			     &cfg->queue_msix_vector);
 		/* Flush the write out to device */
-		vp_ioread16(&vp_dev->common->queue_msix_vector);
+		vp_ioread16(&cfg->queue_msix_vector);
 	}
 
 	if (!vp_dev->notify_base)
-- 
2.25.1

[PATCH V3 02/19] virtio-pci: split out modern device

[Jason Wang]

This patch splits out the virtio-pci modern device only attributes
into another structure. While at it, a dedicated probe method for
modern only attributes is introduced. This may help for split the
logic into a dedicated module.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_common.h |  25 +++--
 drivers/virtio/virtio_pci_modern.c | 159 ++++++++++++++++-------------
 2 files changed, 105 insertions(+), 79 deletions(-)

diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index b2f0eb4067cb..f35ff5b6b467 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -39,22 +39,16 @@ struct virtio_pci_vq_info {
 	unsigned msix_vector;
 };
 
-/* Our device structure */
-struct virtio_pci_device {
-	struct virtio_device vdev;
+struct virtio_pci_modern_device {
 	struct pci_dev *pci_dev;
 
-	/* In legacy mode, these two point to within ->legacy. */
-	/* Where to read and clear interrupt */
-	u8 __iomem *isr;
-
-	/* Modern only fields */
-	/* The IO mapping for the PCI config space (non-legacy mode) */
 	struct virtio_pci_common_cfg __iomem *common;
 	/* Device-specific data (non-legacy mode)  */
 	void __iomem *device;
 	/* Base of vq notifications (non-legacy mode). */
 	void __iomem *notify_base;
+	/* Where to read and clear interrupt */
+	u8 __iomem *isr;
 
 	/* So we can sanity-check accesses. */
 	size_t notify_len;
@@ -68,6 +62,19 @@ struct virtio_pci_device {
 
 	int modern_bars;
 
+	struct virtio_device_id id;
+};
+
+/* Our device structure */
+struct virtio_pci_device {
+	struct virtio_device vdev;
+	struct pci_dev *pci_dev;
+	struct virtio_pci_modern_device mdev;
+
+	/* In legacy mode, these two point to within ->legacy. */
+	/* Where to read and clear interrupt */
+	u8 __iomem *isr;
+
 	/* Legacy only field */
 	/* the IO mapping for the PCI config space */
 	void __iomem *ioaddr;
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index df1481fd400c..524490a94ca4 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -141,7 +141,8 @@ static void __iomem *map_capability(struct pci_dev *dev, int off,
 static u64 vp_get_features(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 	u64 features;
 
 	vp_iowrite32(0, &cfg->device_feature_select);
@@ -166,7 +167,8 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features)
 static int vp_finalize_features(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 	u64 features = vdev->features;
 
 	/* Give virtio_ring a chance to accept features. */
@@ -194,12 +196,13 @@ static void vp_get(struct virtio_device *vdev, unsigned offset,
 		   void *buf, unsigned len)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	void __iomem *device = vp_dev->device;
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	void __iomem *device = mdev->device;
 	u8 b;
 	__le16 w;
 	__le32 l;
 
-	BUG_ON(offset + len > vp_dev->device_len);
+	BUG_ON(offset + len > mdev->device_len);
 
 	switch (len) {
 	case 1:
@@ -231,12 +234,13 @@ static void vp_set(struct virtio_device *vdev, unsigned offset,
 		   const void *buf, unsigned len)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	void __iomem *device = vp_dev->device;
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	void __iomem *device = mdev->device;
 	u8 b;
 	__le16 w;
 	__le32 l;
 
-	BUG_ON(offset + len > vp_dev->device_len);
+	BUG_ON(offset + len > mdev->device_len);
 
 	switch (len) {
 	case 1:
@@ -265,7 +269,8 @@ static void vp_set(struct virtio_device *vdev, unsigned offset,
 static u32 vp_generation(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 
 	return vp_ioread8(&cfg->config_generation);
 }
@@ -274,7 +279,8 @@ static u32 vp_generation(struct virtio_device *vdev)
 static u8 vp_get_status(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 
 	return vp_ioread8(&cfg->device_status);
 }
@@ -282,7 +288,8 @@ static u8 vp_get_status(struct virtio_device *vdev)
 static void vp_set_status(struct virtio_device *vdev, u8 status)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 
 	/* We should never be setting status to 0. */
 	BUG_ON(status == 0);
@@ -292,7 +299,8 @@ static void vp_set_status(struct virtio_device *vdev, u8 status)
 static void vp_reset(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 
 	/* 0 status means a reset. */
 	vp_iowrite8(0, &cfg->device_status);
@@ -309,7 +317,8 @@ static void vp_reset(struct virtio_device *vdev)
 
 static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 {
-	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 
 	/* Setup the vector used for configuration events */
 	vp_iowrite16(vector, &cfg->msix_config);
@@ -326,7 +335,9 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 				  bool ctx,
 				  u16 msix_vec)
 {
-	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 	struct virtqueue *vq;
 	u16 num, off;
 	int err;
@@ -369,25 +380,25 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	vp_iowrite64_twopart(virtqueue_get_used_addr(vq),
 			     &cfg->queue_used_lo, &cfg->queue_used_hi);
 
-	if (vp_dev->notify_base) {
+	if (mdev->notify_base) {
 		/* offset should not wrap */
-		if ((u64)off * vp_dev->notify_offset_multiplier + 2
-		    > vp_dev->notify_len) {
-			dev_warn(&vp_dev->pci_dev->dev,
+		if ((u64)off * mdev->notify_offset_multiplier + 2
+		    > mdev->notify_len) {
+			dev_warn(&mdev->pci_dev->dev,
 				 "bad notification offset %u (x %u) "
 				 "for queue %u > %zd",
-				 off, vp_dev->notify_offset_multiplier,
-				 index, vp_dev->notify_len);
+				 off, mdev->notify_offset_multiplier,
+				 index, mdev->notify_len);
 			err = -EINVAL;
 			goto err_map_notify;
 		}
-		vq->priv = (void __force *)vp_dev->notify_base +
-			off * vp_dev->notify_offset_multiplier;
+		vq->priv = (void __force *)mdev->notify_base +
+			off * mdev->notify_offset_multiplier;
 	} else {
-		vq->priv = (void __force *)map_capability(vp_dev->pci_dev,
-					  vp_dev->notify_map_cap, 2, 2,
-					  off * vp_dev->notify_offset_multiplier, 2,
-					  NULL);
+		vq->priv = (void __force *)map_capability(mdev->pci_dev,
+							  mdev->notify_map_cap, 2, 2,
+							  off * mdev->notify_offset_multiplier, 2,
+							  NULL);
 	}
 
 	if (!vq->priv) {
@@ -407,8 +418,8 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	return vq;
 
 err_assign_vector:
-	if (!vp_dev->notify_base)
-		pci_iounmap(vp_dev->pci_dev, (void __iomem __force *)vq->priv);
+	if (!mdev->notify_base)
+		pci_iounmap(mdev->pci_dev, (void __iomem __force *)vq->priv);
 err_map_notify:
 	vring_del_virtqueue(vq);
 	return ERR_PTR(err);
@@ -421,7 +432,7 @@ static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 			      struct irq_affinity *desc)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->mdev.common;
 	struct virtqueue *vq;
 	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, ctx, desc);
 
@@ -443,7 +454,9 @@ static void del_vq(struct virtio_pci_vq_info *info)
 {
 	struct virtqueue *vq = info->vq;
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
-	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
 
 	vp_iowrite16(vq->index, &cfg->queue_select);
 
@@ -454,8 +467,8 @@ static void del_vq(struct virtio_pci_vq_info *info)
 		vp_ioread16(&cfg->queue_msix_vector);
 	}
 
-	if (!vp_dev->notify_base)
-		pci_iounmap(vp_dev->pci_dev, (void __force __iomem *)vq->priv);
+	if (!mdev->notify_base)
+		pci_iounmap(mdev->pci_dev, (void __force __iomem *)vq->priv);
 
 	vring_del_virtqueue(vq);
 }
@@ -693,6 +706,7 @@ static inline void check_offsets(void)
 /* the PCI probing function */
 int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 {
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 	struct pci_dev *pci_dev = vp_dev->pci_dev;
 	int err, common, isr, notify, device;
 	u32 notify_length;
@@ -700,6 +714,8 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 
 	check_offsets();
 
+	mdev->pci_dev = pci_dev;
+
 	/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
 	if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
 		return -ENODEV;
@@ -708,17 +724,17 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 		/* Transitional devices: use the PCI subsystem device id as
 		 * virtio device id, same as legacy driver always did.
 		 */
-		vp_dev->vdev.id.device = pci_dev->subsystem_device;
+		mdev->id.device = pci_dev->subsystem_device;
 	} else {
 		/* Modern devices: simply use PCI device id, but start from 0x1040. */
-		vp_dev->vdev.id.device = pci_dev->device - 0x1040;
+		mdev->id.device = pci_dev->device - 0x1040;
 	}
-	vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;
+	mdev->id.vendor = pci_dev->subsystem_vendor;
 
 	/* check for a common config: if not, use legacy mode (bar 0). */
 	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
 					    IORESOURCE_IO | IORESOURCE_MEM,
-					    &vp_dev->modern_bars);
+					    &mdev->modern_bars);
 	if (!common) {
 		dev_info(&pci_dev->dev,
 			 "virtio_pci: leaving for legacy driver\n");
@@ -728,10 +744,10 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	/* If common is there, these should be too... */
 	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
 					 IORESOURCE_IO | IORESOURCE_MEM,
-					 &vp_dev->modern_bars);
+					 &mdev->modern_bars);
 	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
 					    IORESOURCE_IO | IORESOURCE_MEM,
-					    &vp_dev->modern_bars);
+					    &mdev->modern_bars);
 	if (!isr || !notify) {
 		dev_err(&pci_dev->dev,
 			"virtio_pci: missing capabilities %i/%i/%i\n",
@@ -751,31 +767,31 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	 */
 	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
 					    IORESOURCE_IO | IORESOURCE_MEM,
-					    &vp_dev->modern_bars);
+					    &mdev->modern_bars);
 
-	err = pci_request_selected_regions(pci_dev, vp_dev->modern_bars,
+	err = pci_request_selected_regions(pci_dev, mdev->modern_bars,
 					   "virtio-pci-modern");
 	if (err)
 		return err;
 
 	err = -EINVAL;
-	vp_dev->common = map_capability(pci_dev, common,
-					sizeof(struct virtio_pci_common_cfg), 4,
-					0, sizeof(struct virtio_pci_common_cfg),
-					NULL);
-	if (!vp_dev->common)
+	mdev->common = map_capability(pci_dev, common,
+				      sizeof(struct virtio_pci_common_cfg), 4,
+				      0, sizeof(struct virtio_pci_common_cfg),
+				      NULL);
+	if (!mdev->common)
 		goto err_map_common;
-	vp_dev->isr = map_capability(pci_dev, isr, sizeof(u8), 1,
-				     0, 1,
-				     NULL);
-	if (!vp_dev->isr)
+	mdev->isr = map_capability(pci_dev, isr, sizeof(u8), 1,
+				   0, 1,
+				   NULL);
+	if (!mdev->isr)
 		goto err_map_isr;
 
 	/* Read notify_off_multiplier from config space. */
 	pci_read_config_dword(pci_dev,
 			      notify + offsetof(struct virtio_pci_notify_cap,
 						notify_off_multiplier),
-			      &vp_dev->notify_offset_multiplier);
+			      &mdev->notify_offset_multiplier);
 	/* Read notify length and offset from config space. */
 	pci_read_config_dword(pci_dev,
 			      notify + offsetof(struct virtio_pci_notify_cap,
@@ -792,23 +808,23 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	 * Otherwise, map each VQ individually later.
 	 */
 	if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) {
-		vp_dev->notify_base = map_capability(pci_dev, notify, 2, 2,
-						     0, notify_length,
-						     &vp_dev->notify_len);
-		if (!vp_dev->notify_base)
+		mdev->notify_base = map_capability(pci_dev, notify, 2, 2,
+						   0, notify_length,
+						   &mdev->notify_len);
+		if (!mdev->notify_base)
 			goto err_map_notify;
 	} else {
-		vp_dev->notify_map_cap = notify;
+		mdev->notify_map_cap = notify;
 	}
 
 	/* Again, we don't know how much we should map, but PAGE_SIZE
 	 * is more than enough for all existing devices.
 	 */
 	if (device) {
-		vp_dev->device = map_capability(pci_dev, device, 0, 4,
-						0, PAGE_SIZE,
-						&vp_dev->device_len);
-		if (!vp_dev->device)
+		mdev->device = map_capability(pci_dev, device, 0, 4,
+					      0, PAGE_SIZE,
+					      &mdev->device_len);
+		if (!mdev->device)
 			goto err_map_device;
 
 		vp_dev->vdev.config = &virtio_pci_config_ops;
@@ -819,29 +835,32 @@ 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->isr = mdev->isr;
+	vp_dev->vdev.id = mdev->id;
 
 	return 0;
 
 err_map_device:
-	if (vp_dev->notify_base)
-		pci_iounmap(pci_dev, vp_dev->notify_base);
+	if (mdev->notify_base)
+		pci_iounmap(pci_dev, mdev->notify_base);
 err_map_notify:
-	pci_iounmap(pci_dev, vp_dev->isr);
+	pci_iounmap(pci_dev, mdev->isr);
 err_map_isr:
-	pci_iounmap(pci_dev, vp_dev->common);
+	pci_iounmap(pci_dev, mdev->common);
 err_map_common:
 	return err;
 }
 
 void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
 {
-	struct pci_dev *pci_dev = vp_dev->pci_dev;
-
-	if (vp_dev->device)
-		pci_iounmap(pci_dev, vp_dev->device);
-	if (vp_dev->notify_base)
-		pci_iounmap(pci_dev, vp_dev->notify_base);
-	pci_iounmap(pci_dev, vp_dev->isr);
-	pci_iounmap(pci_dev, vp_dev->common);
-	pci_release_selected_regions(pci_dev, vp_dev->modern_bars);
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	struct pci_dev *pci_dev = mdev->pci_dev;
+
+	if (mdev->device)
+		pci_iounmap(pci_dev, mdev->device);
+	if (mdev->notify_base)
+		pci_iounmap(pci_dev, mdev->notify_base);
+	pci_iounmap(pci_dev, mdev->isr);
+	pci_iounmap(pci_dev, mdev->common);
+	pci_release_selected_regions(pci_dev, mdev->modern_bars);
 }
-- 
2.25.1

[PATCH V3 03/19] virtio-pci-modern: factor out modern device initialization logic

[Jason Wang]

This patch factors out the modern device initialization logic into a
helper. Note that it still depends on the caller to enable pci device
which allows the caller to use e.g devres.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 50 +++++++++++++++++++++---------
 1 file changed, 36 insertions(+), 14 deletions(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 524490a94ca4..5d2d2ae0dfdb 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -703,11 +703,16 @@ static inline void check_offsets(void)
 		     offsetof(struct virtio_pci_common_cfg, queue_used_hi));
 }
 
-/* the PCI probing function */
-int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
+/*
+ * vp_modern_probe: probe the modern virtio pci device, note that the
+ * caller is required to enable PCI device before calling this function.
+ * @mdev: the modern virtio-pci device
+ *
+ * Return 0 on succeed otherwise fail
+ */
+static int vp_modern_probe(struct virtio_pci_modern_device *mdev)
 {
-	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
-	struct pci_dev *pci_dev = vp_dev->pci_dev;
+	struct pci_dev *pci_dev = mdev->pci_dev;
 	int err, common, isr, notify, device;
 	u32 notify_length;
 	u32 notify_offset;
@@ -826,18 +831,8 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 					      &mdev->device_len);
 		if (!mdev->device)
 			goto err_map_device;
-
-		vp_dev->vdev.config = &virtio_pci_config_ops;
-	} else {
-		vp_dev->vdev.config = &virtio_pci_config_nodev_ops;
 	}
 
-	vp_dev->config_vector = vp_config_vector;
-	vp_dev->setup_vq = setup_vq;
-	vp_dev->del_vq = del_vq;
-	vp_dev->isr = mdev->isr;
-	vp_dev->vdev.id = mdev->id;
-
 	return 0;
 
 err_map_device:
@@ -851,6 +846,33 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	return err;
 }
 
+/* the PCI probing function */
+int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
+{
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	struct pci_dev *pci_dev = vp_dev->pci_dev;
+	int err;
+
+	mdev->pci_dev = pci_dev;
+
+	err = vp_modern_probe(mdev);
+	if (err)
+		return err;
+
+	if (mdev->device)
+		vp_dev->vdev.config = &virtio_pci_config_ops;
+	else
+		vp_dev->vdev.config = &virtio_pci_config_nodev_ops;
+
+	vp_dev->config_vector = vp_config_vector;
+	vp_dev->setup_vq = setup_vq;
+	vp_dev->del_vq = del_vq;
+	vp_dev->isr = mdev->isr;
+	vp_dev->vdev.id = mdev->id;
+
+	return 0;
+}
+
 void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
 {
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
-- 
2.25.1

[PATCH V3 04/19] virtio-pci-modern: introduce vp_modern_remove()

[Jason Wang]

This patch introduces vp_modern_remove() doing device resources
cleanup to make it can be used.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 5d2d2ae0dfdb..4be9afad547e 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -873,9 +873,12 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	return 0;
 }
 
-void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
+/*
+ * vp_modern_probe: remove and cleanup the modern virtio pci device
+ * @mdev: the modern virtio-pci device
+ */
+static void vp_modern_remove(struct virtio_pci_modern_device *mdev)
 {
-	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 	struct pci_dev *pci_dev = mdev->pci_dev;
 
 	if (mdev->device)
@@ -886,3 +889,10 @@ void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
 	pci_iounmap(pci_dev, mdev->common);
 	pci_release_selected_regions(pci_dev, mdev->modern_bars);
 }
+
+void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
+{
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+
+	vp_modern_remove(mdev);
+}
-- 
2.25.1

[PATCH V3 05/19] virtio-pci-modern: introduce helper to set config vector

[Jason Wang]

This patch introduces vp_modern_config_vector() for setting config
vector.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 4be9afad547e..2e37bfc89655 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -315,9 +315,16 @@ static void vp_reset(struct virtio_device *vdev)
 	vp_synchronize_vectors(vdev);
 }
 
-static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
+/*
+ * vp_modern_config_vector - set the vector for config interrupt
+ * @mdev: the modern virtio-pci device
+ * @vector: the config vector
+ *
+ * Returns the config vector read from the device
+ */
+static u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev,
+				   u16 vector)
 {
-	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 
 	/* Setup the vector used for configuration events */
@@ -327,6 +334,11 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 	return vp_ioread16(&cfg->msix_config);
 }
 
+static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
+{
+	return vp_modern_config_vector(&vp_dev->mdev, vector);
+}
+
 static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 				  struct virtio_pci_vq_info *info,
 				  unsigned index,
-- 
2.25.1

[PATCH V3 06/19] virtio-pci-modern: introduce helpers for setting and getting status

[Jason Wang]

This patch introduces helpers to allow set and get device status.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 37 +++++++++++++++++++++++-------
 1 file changed, 29 insertions(+), 8 deletions(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 2e37bfc89655..ccde0a41209a 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -275,41 +275,62 @@ static u32 vp_generation(struct virtio_device *vdev)
 	return vp_ioread8(&cfg->config_generation);
 }
 
+/*
+ * vp_modern_get_status - get the device status
+ * @mdev: the modern virtio-pci device
+ *
+ * Returns the status read from device
+ */
+static u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	return vp_ioread8(&cfg->device_status);
+}
+
 /* config->{get,set}_status() implementations */
 static u8 vp_get_status(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+
+	return vp_modern_get_status(&vp_dev->mdev);
+}
+
+/*
+ * vp_modern_set_status - set status to device
+ * @mdev: the modern virtio-pci device
+ * @status: the status set to device
+ */
+static void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
+				 u8 status)
+{
 	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 
-	return vp_ioread8(&cfg->device_status);
+	vp_iowrite8(status, &cfg->device_status);
 }
 
 static void vp_set_status(struct virtio_device *vdev, u8 status)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
-	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 
 	/* We should never be setting status to 0. */
 	BUG_ON(status == 0);
-	vp_iowrite8(status, &cfg->device_status);
+	vp_modern_set_status(&vp_dev->mdev, status);
 }
 
 static void vp_reset(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
-	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 
 	/* 0 status means a reset. */
-	vp_iowrite8(0, &cfg->device_status);
+	vp_modern_set_status(mdev, 0);
 	/* After writing 0 to device_status, the driver MUST wait for a read of
 	 * device_status to return 0 before reinitializing the device.
 	 * This will flush out the status write, and flush in device writes,
 	 * including MSI-X interrupts, if any.
 	 */
-	while (vp_ioread8(&cfg->device_status))
+	while (vp_modern_get_status(mdev))
 		msleep(1);
 	/* Flush pending VQ/configuration callbacks. */
 	vp_synchronize_vectors(vdev);
-- 
2.25.1

[PATCH V3 07/19] virtio-pci-modern: introduce helpers for setting and getting features

[Jason Wang]

This patch introduces helpers for setting and getting features.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 43 +++++++++++++++++++++++-------
 1 file changed, 33 insertions(+), 10 deletions(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index ccde0a41209a..cb14fc334a9c 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -137,12 +137,16 @@ static void __iomem *map_capability(struct pci_dev *dev, int off,
 	return p;
 }
 
-/* virtio config->get_features() implementation */
-static u64 vp_get_features(struct virtio_device *vdev)
+/*
+ * vp_modern_get_features - get features from device
+ * @mdev: the modern virtio-pci device
+ *
+ * Returns the features read from the device
+ */
+static u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev)
 {
-	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
 	u64 features;
 
 	vp_iowrite32(0, &cfg->device_feature_select);
@@ -153,6 +157,14 @@ static u64 vp_get_features(struct virtio_device *vdev)
 	return features;
 }
 
+/* virtio config->get_features() implementation */
+static u64 vp_get_features(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	return vp_modern_get_features(&vp_dev->mdev);
+}
+
 static void vp_transport_features(struct virtio_device *vdev, u64 features)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -163,12 +175,26 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features)
 		__virtio_set_bit(vdev, VIRTIO_F_SR_IOV);
 }
 
+/*
+ * vp_modern_set_features - set features to device
+ * @mdev: the modern virtio-pci device
+ * @features: the features set to device
+ */
+static void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
+				   u64 features)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	vp_iowrite32(0, &cfg->guest_feature_select);
+	vp_iowrite32((u32)features, &cfg->guest_feature);
+	vp_iowrite32(1, &cfg->guest_feature_select);
+	vp_iowrite32(features >> 32, &cfg->guest_feature);
+}
+
 /* virtio config->finalize_features() implementation */
 static int vp_finalize_features(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
-	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 	u64 features = vdev->features;
 
 	/* Give virtio_ring a chance to accept features. */
@@ -183,10 +209,7 @@ static int vp_finalize_features(struct virtio_device *vdev)
 		return -EINVAL;
 	}
 
-	vp_iowrite32(0, &cfg->guest_feature_select);
-	vp_iowrite32((u32)vdev->features, &cfg->guest_feature);
-	vp_iowrite32(1, &cfg->guest_feature_select);
-	vp_iowrite32(vdev->features >> 32, &cfg->guest_feature);
+	vp_modern_set_features(&vp_dev->mdev, vdev->features);
 
 	return 0;
 }
-- 
2.25.1

[PATCH V3 08/19] virtio-pci-modern: introduce vp_modern_generation()

[Jason Wang]

This patch introduces vp_modern_generation() to get device generation.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index cb14fc334a9c..a128e5814045 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -289,15 +289,26 @@ static void vp_set(struct virtio_device *vdev, unsigned offset,
 	}
 }
 
-static u32 vp_generation(struct virtio_device *vdev)
+/*
+ * vp_modern_generation - get the device genreation
+ * @mdev: the modern virtio-pci device
+ *
+ * Returns the genreation read from device
+ */
+static u32 vp_modern_generation(struct virtio_pci_modern_device *mdev)
 {
-	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 
 	return vp_ioread8(&cfg->config_generation);
 }
 
+static u32 vp_generation(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	return vp_modern_generation(&vp_dev->mdev);
+}
+
 /*
  * vp_modern_get_status - get the device status
  * @mdev: the modern virtio-pci device
-- 
2.25.1

[PATCH V3 09/19] virtio-pci-modern: introduce vp_modern_set_queue_vector()

[Jason Wang]

This patch introduces a helper to set virtqueue MSI vector.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 35 ++++++++++++++++++++----------
 1 file changed, 23 insertions(+), 12 deletions(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index a128e5814045..05cd409c0731 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -191,6 +191,25 @@ static void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
 	vp_iowrite32(features >> 32, &cfg->guest_feature);
 }
 
+/*
+ * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: queue index
+ * @vector: the config vector
+ *
+ * Returns the config vector read from the device
+ */
+static u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
+				  u16 index, u16 vector)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	vp_iowrite16(index, &cfg->queue_select);
+	vp_iowrite16(vector, &cfg->queue_msix_vector);
+	/* Flush the write out to device */
+	return vp_ioread16(&cfg->queue_msix_vector);
+}
+
 /* virtio config->finalize_features() implementation */
 static int vp_finalize_features(struct virtio_device *vdev)
 {
@@ -474,8 +493,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	}
 
 	if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
-		vp_iowrite16(msix_vec, &cfg->queue_msix_vector);
-		msix_vec = vp_ioread16(&cfg->queue_msix_vector);
+		msix_vec = vp_modern_queue_vector(mdev, index, msix_vec);
 		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
 			err = -EBUSY;
 			goto err_assign_vector;
@@ -522,17 +540,10 @@ static void del_vq(struct virtio_pci_vq_info *info)
 	struct virtqueue *vq = info->vq;
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
-	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
-
 
-	vp_iowrite16(vq->index, &cfg->queue_select);
-
-	if (vp_dev->msix_enabled) {
-		vp_iowrite16(VIRTIO_MSI_NO_VECTOR,
-			     &cfg->queue_msix_vector);
-		/* Flush the write out to device */
-		vp_ioread16(&cfg->queue_msix_vector);
-	}
+	if (vp_dev->msix_enabled)
+		vp_modern_queue_vector(mdev, vq->index,
+				       VIRTIO_MSI_NO_VECTOR);
 
 	if (!mdev->notify_base)
 		pci_iounmap(mdev->pci_dev, (void __force __iomem *)vq->priv);
-- 
2.25.1

[PATCH V3 10/19] virtio-pci-modern: introduce vp_modern_queue_address()

[Jason Wang]

This patch introduce a helper to set virtqueue address for modern address.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 33 ++++++++++++++++++++++++------
 1 file changed, 27 insertions(+), 6 deletions(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 05cd409c0731..05b21e18f46c 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -210,6 +210,30 @@ static u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
 	return vp_ioread16(&cfg->queue_msix_vector);
 }
 
+/*
+ * vp_modern_queue_address - set the virtqueue address
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ * @desc_addr: address of the descriptor area
+ * @driver_addr: address of the driver area
+ * @device_addr: address of the device area
+ */
+static void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
+				    u16 index, u64 desc_addr, u64 driver_addr,
+				    u64 device_addr)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	vp_iowrite16(index, &cfg->queue_select);
+
+	vp_iowrite64_twopart(desc_addr, &cfg->queue_desc_lo,
+			     &cfg->queue_desc_hi);
+	vp_iowrite64_twopart(driver_addr, &cfg->queue_avail_lo,
+			     &cfg->queue_avail_hi);
+	vp_iowrite64_twopart(device_addr, &cfg->queue_used_lo,
+			     &cfg->queue_used_hi);
+}
+
 /* virtio config->finalize_features() implementation */
 static int vp_finalize_features(struct virtio_device *vdev)
 {
@@ -459,12 +483,9 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 
 	/* activate the queue */
 	vp_iowrite16(virtqueue_get_vring_size(vq), &cfg->queue_size);
-	vp_iowrite64_twopart(virtqueue_get_desc_addr(vq),
-			     &cfg->queue_desc_lo, &cfg->queue_desc_hi);
-	vp_iowrite64_twopart(virtqueue_get_avail_addr(vq),
-			     &cfg->queue_avail_lo, &cfg->queue_avail_hi);
-	vp_iowrite64_twopart(virtqueue_get_used_addr(vq),
-			     &cfg->queue_used_lo, &cfg->queue_used_hi);
+	vp_modern_queue_address(mdev, index, virtqueue_get_desc_addr(vq),
+				virtqueue_get_avail_addr(vq),
+				virtqueue_get_used_addr(vq));
 
 	if (mdev->notify_base) {
 		/* offset should not wrap */
-- 
2.25.1

[PATCH V3 11/19] virtio-pci-modern: introduce helper to set/get queue_enable

[Jason Wang]

This patch introduces a helper to set/get queue_enable for modern device.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 37 +++++++++++++++++++++++++-----
 1 file changed, 31 insertions(+), 6 deletions(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 05b21e18f46c..0e62820b83ff 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -234,6 +234,34 @@ static void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
 			     &cfg->queue_used_hi);
 }
 
+/*
+ * vp_modern_set_queue_enable - enable a virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ * @enable: whether the virtqueue is enable or not
+ */
+static void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev,
+				       u16 index, bool enable)
+{
+	vp_iowrite16(index, &mdev->common->queue_select);
+	vp_iowrite16(enable, &mdev->common->queue_enable);
+}
+
+/*
+ * vp_modern_get_queue_enable - enable a virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ *
+ * Returns whether a virtqueue is enabled or not
+ */
+static bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
+				       u16 index)
+{
+	vp_iowrite16(index, &mdev->common->queue_select);
+
+	return vp_ioread16(&mdev->common->queue_enable);
+}
+
 /* virtio config->finalize_features() implementation */
 static int vp_finalize_features(struct virtio_device *vdev)
 {
@@ -460,7 +488,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 
 	/* Check if queue is either not available or already active. */
 	num = vp_ioread16(&cfg->queue_size);
-	if (!num || vp_ioread16(&cfg->queue_enable))
+	if (!num || vp_modern_get_queue_enable(mdev, index))
 		return ERR_PTR(-ENOENT);
 
 	if (num & (num - 1)) {
@@ -538,7 +566,6 @@ static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 			      struct irq_affinity *desc)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->mdev.common;
 	struct virtqueue *vq;
 	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, ctx, desc);
 
@@ -548,10 +575,8 @@ static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 	/* Select and activate all queues. Has to be done last: once we do
 	 * this, there's no way to go back except reset.
 	 */
-	list_for_each_entry(vq, &vdev->vqs, list) {
-		vp_iowrite16(vq->index, &cfg->queue_select);
-		vp_iowrite16(1, &cfg->queue_enable);
-	}
+	list_for_each_entry(vq, &vdev->vqs, list)
+		vp_modern_set_queue_enable(&vp_dev->mdev, vq->index, true);
 
 	return 0;
 }
-- 
2.25.1

[PATCH V3 12/19] virtio-pci-modern: introduce helper for setting/geting queue size

[Jason Wang]

This patch introduces helper for setting/getting queue size for modern
device.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 34 ++++++++++++++++++++++++++++--
 1 file changed, 32 insertions(+), 2 deletions(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 0e62820b83ff..7a89226135af 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -262,6 +262,36 @@ static bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
 	return vp_ioread16(&mdev->common->queue_enable);
 }
 
+/*
+ * vp_modern_set_queue_size - set size for a virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ * @size: the size of the virtqueue
+ */
+static void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev,
+				     u16 index, u16 size)
+{
+	vp_iowrite16(index, &mdev->common->queue_select);
+	vp_iowrite16(size, &mdev->common->queue_size);
+
+}
+
+/*
+ * vp_modern_get_queue_size - get size for a virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ *
+ * Returns the size of the virtqueue
+ */
+static u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
+				    u16 index)
+{
+	vp_iowrite16(index, &mdev->common->queue_select);
+
+	return vp_ioread16(&mdev->common->queue_size);
+
+}
+
 /* virtio config->finalize_features() implementation */
 static int vp_finalize_features(struct virtio_device *vdev)
 {
@@ -487,7 +517,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	vp_iowrite16(index, &cfg->queue_select);
 
 	/* Check if queue is either not available or already active. */
-	num = vp_ioread16(&cfg->queue_size);
+	num = vp_modern_get_queue_size(mdev, index);
 	if (!num || vp_modern_get_queue_enable(mdev, index))
 		return ERR_PTR(-ENOENT);
 
@@ -510,7 +540,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 		return ERR_PTR(-ENOMEM);
 
 	/* activate the queue */
-	vp_iowrite16(virtqueue_get_vring_size(vq), &cfg->queue_size);
+	vp_modern_set_queue_size(mdev, index, virtqueue_get_vring_size(vq));
 	vp_modern_queue_address(mdev, index, virtqueue_get_desc_addr(vq),
 				virtqueue_get_avail_addr(vq),
 				virtqueue_get_used_addr(vq));
-- 
2.25.1

[PATCH V3 13/19] virtio-pci-modern: introduce helper for getting queue nums

[Jason Wang]

This patch introduces helper for getting queue num of modern device.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 7a89226135af..bccad1329871 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -292,6 +292,17 @@ static u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
 
 }
 
+/*
+ * vp_modern_get_num_queues - get the number of virtqueues
+ * @mdev: the modern virtio-pci device
+ *
+ * Returns the number of virtqueues
+ */
+static u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev)
+{
+	return vp_ioread16(&mdev->common->num_queues);
+}
+
 /* virtio config->finalize_features() implementation */
 static int vp_finalize_features(struct virtio_device *vdev)
 {
@@ -510,7 +521,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	u16 num, off;
 	int err;
 
-	if (index >= vp_ioread16(&cfg->num_queues))
+	if (index >= vp_modern_get_num_queues(mdev))
 		return ERR_PTR(-ENOENT);
 
 	/* Select the queue we're interested in */
-- 
2.25.1

[PATCH V3 14/19] virtio-pci-modern: introduce helper to get notification offset

[Jason Wang]

This patch introduces help to get notification offset of modern device.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index bccad1329871..217573f2588d 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -303,6 +303,21 @@ static u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev)
 	return vp_ioread16(&mdev->common->num_queues);
 }
 
+/*
+ * vp_modern_get_queue_notify_off - get notification offset for a virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ *
+ * Returns the notification offset for a virtqueue
+ */
+static u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev,
+					  u16 index)
+{
+	vp_iowrite16(index, &mdev->common->queue_select);
+
+	return vp_ioread16(&mdev->common->queue_notify_off);
+}
+
 /* virtio config->finalize_features() implementation */
 static int vp_finalize_features(struct virtio_device *vdev)
 {
@@ -516,7 +531,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 {
 
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
-	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 	struct virtqueue *vq;
 	u16 num, off;
 	int err;
@@ -524,9 +538,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	if (index >= vp_modern_get_num_queues(mdev))
 		return ERR_PTR(-ENOENT);
 
-	/* Select the queue we're interested in */
-	vp_iowrite16(index, &cfg->queue_select);
-
 	/* 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))
@@ -538,7 +549,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	}
 
 	/* get offset of notification word for this vq */
-	off = vp_ioread16(&cfg->queue_notify_off);
+	off = vp_modern_get_queue_notify_off(mdev, index);
 
 	info->msix_vector = msix_vec;
 
-- 
2.25.1

[PATCH V3 15/19] virito-pci-modern: rename map_capability() to vp_modern_map_capability()

[Jason Wang]

To ease the split, map_capability() was renamed to
vp_modern_map_capability(). While at it, add the comments for the
arguments and switch to use virtio_pci_modern_device as the first
parameter.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 46 +++++++++++++++++++-----------
 1 file changed, 30 insertions(+), 16 deletions(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 217573f2588d..a5e3a5e40323 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -63,12 +63,25 @@ static void vp_iowrite64_twopart(u64 val,
 	vp_iowrite32(val >> 32, hi);
 }
 
-static void __iomem *map_capability(struct pci_dev *dev, int off,
-				    size_t minlen,
-				    u32 align,
-				    u32 start, u32 size,
-				    size_t *len)
+/*
+ * vp_modern_map_capability - map a part of virtio pci capability
+ * @mdev: the modern virtio-pci device
+ * @off: offset of the capability
+ * @minlen: minimal length of the capability
+ * @align: align requirement
+ * @start: start from the capability
+ * @size: map size
+ * @len: the length that is actually mapped
+ *
+ * Returns the io address of for the part of the capability
+ */
+void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off,
+				       size_t minlen,
+				       u32 align,
+				       u32 start, u32 size,
+				       size_t *len)
 {
+	struct pci_dev *dev = mdev->pci_dev;
 	u8 bar;
 	u32 offset, length;
 	void __iomem *p;
@@ -582,7 +595,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 		vq->priv = (void __force *)mdev->notify_base +
 			off * mdev->notify_offset_multiplier;
 	} else {
-		vq->priv = (void __force *)map_capability(mdev->pci_dev,
+		vq->priv = (void __force *)vp_modern_map_capability(mdev,
 							  mdev->notify_map_cap, 2, 2,
 							  off * mdev->notify_offset_multiplier, 2,
 							  NULL);
@@ -956,15 +969,15 @@ static int vp_modern_probe(struct virtio_pci_modern_device *mdev)
 		return err;
 
 	err = -EINVAL;
-	mdev->common = map_capability(pci_dev, common,
+	mdev->common = vp_modern_map_capability(mdev, common,
 				      sizeof(struct virtio_pci_common_cfg), 4,
 				      0, sizeof(struct virtio_pci_common_cfg),
 				      NULL);
 	if (!mdev->common)
 		goto err_map_common;
-	mdev->isr = map_capability(pci_dev, isr, sizeof(u8), 1,
-				   0, 1,
-				   NULL);
+	mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1,
+					     0, 1,
+					     NULL);
 	if (!mdev->isr)
 		goto err_map_isr;
 
@@ -989,9 +1002,10 @@ static int vp_modern_probe(struct virtio_pci_modern_device *mdev)
 	 * Otherwise, map each VQ individually later.
 	 */
 	if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) {
-		mdev->notify_base = map_capability(pci_dev, notify, 2, 2,
-						   0, notify_length,
-						   &mdev->notify_len);
+		mdev->notify_base = vp_modern_map_capability(mdev, notify,
+							     2, 2,
+							     0, notify_length,
+							     &mdev->notify_len);
 		if (!mdev->notify_base)
 			goto err_map_notify;
 	} else {
@@ -1002,9 +1016,9 @@ static int vp_modern_probe(struct virtio_pci_modern_device *mdev)
 	 * is more than enough for all existing devices.
 	 */
 	if (device) {
-		mdev->device = map_capability(pci_dev, device, 0, 4,
-					      0, PAGE_SIZE,
-					      &mdev->device_len);
+		mdev->device = vp_modern_map_capability(mdev, device, 0, 4,
+							0, PAGE_SIZE,
+							&mdev->device_len);
 		if (!mdev->device)
 			goto err_map_device;
 	}
-- 
2.25.1

[PATCH V3 16/19] virtio-pci: introduce modern device module

[Jason Wang]

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/Kconfig                 |  10 +-
 drivers/virtio/Makefile                |   1 +
 drivers/virtio/virtio_pci_common.h     |  27 +-
 drivers/virtio/virtio_pci_modern.c     | 617 -------------------------
 drivers/virtio/virtio_pci_modern_dev.c | 599 ++++++++++++++++++++++++
 include/linux/virtio_pci_modern.h      | 111 +++++
 6 files changed, 721 insertions(+), 644 deletions(-)
 create mode 100644 drivers/virtio/virtio_pci_modern_dev.c
 create mode 100644 include/linux/virtio_pci_modern.h

diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 7b41130d3f35..6b9b81f4b8c2 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -12,6 +12,14 @@ config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
 	  This option is selected if the architecture may need to enforce
 	  VIRTIO_F_ACCESS_PLATFORM
 
+config VIRTIO_PCI_MODERN
+	tristate "Modern Virtio PCI Device"
+	depends on PCI
+	help
+	  Modern PCI device implementation. This module implements the
+	  basic probe and control for devices which are based on modern
+	  PCI device with possible vendor specific extensions.
+
 menuconfig VIRTIO_MENU
 	bool "Virtio drivers"
 	default y
@@ -20,7 +28,7 @@ if VIRTIO_MENU
 
 config VIRTIO_PCI
 	tristate "PCI driver for virtio devices"
-	depends on PCI
+	depends on VIRTIO_PCI_MODERN
 	select VIRTIO
 	help
 	  This driver provides support for virtio based paravirtual device
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index 591e6f72aa54..f097578aaa8f 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o
+obj-$(CONFIG_VIRTIO_PCI_MODERN) += virtio_pci_modern_dev.o
 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
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index f35ff5b6b467..beec047a8f8d 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -25,6 +25,7 @@
 #include <linux/virtio_config.h>
 #include <linux/virtio_ring.h>
 #include <linux/virtio_pci.h>
+#include <linux/virtio_pci_modern.h>
 #include <linux/highmem.h>
 #include <linux/spinlock.h>
 
@@ -39,32 +40,6 @@ struct virtio_pci_vq_info {
 	unsigned msix_vector;
 };
 
-struct virtio_pci_modern_device {
-	struct pci_dev *pci_dev;
-
-	struct virtio_pci_common_cfg __iomem *common;
-	/* Device-specific data (non-legacy mode)  */
-	void __iomem *device;
-	/* Base of vq notifications (non-legacy mode). */
-	void __iomem *notify_base;
-	/* Where to read and clear interrupt */
-	u8 __iomem *isr;
-
-	/* So we can sanity-check accesses. */
-	size_t notify_len;
-	size_t device_len;
-
-	/* Capability for when we need to map notifications per-vq. */
-	int notify_map_cap;
-
-	/* Multiply queue_notify_off by this value. (non-legacy mode). */
-	u32 notify_offset_multiplier;
-
-	int modern_bars;
-
-	struct virtio_device_id id;
-};
-
 /* Our device structure */
 struct virtio_pci_device {
 	struct virtio_device vdev;
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index a5e3a5e40323..fbd4ebc00eb6 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -19,158 +19,6 @@
 #define VIRTIO_RING_NO_LEGACY
 #include "virtio_pci_common.h"
 
-/*
- * Type-safe wrappers for io accesses.
- * Use these to enforce at compile time the following spec requirement:
- *
- * The driver MUST access each field using the “natural” access
- * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses
- * for 16-bit fields and 8-bit accesses for 8-bit fields.
- */
-static inline u8 vp_ioread8(const u8 __iomem *addr)
-{
-	return ioread8(addr);
-}
-static inline u16 vp_ioread16 (const __le16 __iomem *addr)
-{
-	return ioread16(addr);
-}
-
-static inline u32 vp_ioread32(const __le32 __iomem *addr)
-{
-	return ioread32(addr);
-}
-
-static inline void vp_iowrite8(u8 value, u8 __iomem *addr)
-{
-	iowrite8(value, addr);
-}
-
-static inline void vp_iowrite16(u16 value, __le16 __iomem *addr)
-{
-	iowrite16(value, addr);
-}
-
-static inline void vp_iowrite32(u32 value, __le32 __iomem *addr)
-{
-	iowrite32(value, addr);
-}
-
-static void vp_iowrite64_twopart(u64 val,
-				 __le32 __iomem *lo, __le32 __iomem *hi)
-{
-	vp_iowrite32((u32)val, lo);
-	vp_iowrite32(val >> 32, hi);
-}
-
-/*
- * vp_modern_map_capability - map a part of virtio pci capability
- * @mdev: the modern virtio-pci device
- * @off: offset of the capability
- * @minlen: minimal length of the capability
- * @align: align requirement
- * @start: start from the capability
- * @size: map size
- * @len: the length that is actually mapped
- *
- * Returns the io address of for the part of the capability
- */
-void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off,
-				       size_t minlen,
-				       u32 align,
-				       u32 start, u32 size,
-				       size_t *len)
-{
-	struct pci_dev *dev = mdev->pci_dev;
-	u8 bar;
-	u32 offset, length;
-	void __iomem *p;
-
-	pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap,
-						 bar),
-			     &bar);
-	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset),
-			     &offset);
-	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length),
-			      &length);
-
-	if (length <= start) {
-		dev_err(&dev->dev,
-			"virtio_pci: bad capability len %u (>%u expected)\n",
-			length, start);
-		return NULL;
-	}
-
-	if (length - start < minlen) {
-		dev_err(&dev->dev,
-			"virtio_pci: bad capability len %u (>=%zu expected)\n",
-			length, minlen);
-		return NULL;
-	}
-
-	length -= start;
-
-	if (start + offset < offset) {
-		dev_err(&dev->dev,
-			"virtio_pci: map wrap-around %u+%u\n",
-			start, offset);
-		return NULL;
-	}
-
-	offset += start;
-
-	if (offset & (align - 1)) {
-		dev_err(&dev->dev,
-			"virtio_pci: offset %u not aligned to %u\n",
-			offset, align);
-		return NULL;
-	}
-
-	if (length > size)
-		length = size;
-
-	if (len)
-		*len = length;
-
-	if (minlen + offset < minlen ||
-	    minlen + offset > pci_resource_len(dev, bar)) {
-		dev_err(&dev->dev,
-			"virtio_pci: map virtio %zu@%u "
-			"out of range on bar %i length %lu\n",
-			minlen, offset,
-			bar, (unsigned long)pci_resource_len(dev, bar));
-		return NULL;
-	}
-
-	p = pci_iomap_range(dev, bar, offset, length);
-	if (!p)
-		dev_err(&dev->dev,
-			"virtio_pci: unable to map virtio %u@%u on bar %i\n",
-			length, offset, bar);
-	return p;
-}
-
-/*
- * vp_modern_get_features - get features from device
- * @mdev: the modern virtio-pci device
- *
- * Returns the features read from the device
- */
-static u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev)
-{
-	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
-
-	u64 features;
-
-	vp_iowrite32(0, &cfg->device_feature_select);
-	features = vp_ioread32(&cfg->device_feature);
-	vp_iowrite32(1, &cfg->device_feature_select);
-	features |= ((u64)vp_ioread32(&cfg->device_feature) << 32);
-
-	return features;
-}
-
-/* virtio config->get_features() implementation */
 static u64 vp_get_features(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -188,149 +36,6 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features)
 		__virtio_set_bit(vdev, VIRTIO_F_SR_IOV);
 }
 
-/*
- * vp_modern_set_features - set features to device
- * @mdev: the modern virtio-pci device
- * @features: the features set to device
- */
-static void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
-				   u64 features)
-{
-	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
-
-	vp_iowrite32(0, &cfg->guest_feature_select);
-	vp_iowrite32((u32)features, &cfg->guest_feature);
-	vp_iowrite32(1, &cfg->guest_feature_select);
-	vp_iowrite32(features >> 32, &cfg->guest_feature);
-}
-
-/*
- * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue
- * @mdev: the modern virtio-pci device
- * @index: queue index
- * @vector: the config vector
- *
- * Returns the config vector read from the device
- */
-static u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
-				  u16 index, u16 vector)
-{
-	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
-
-	vp_iowrite16(index, &cfg->queue_select);
-	vp_iowrite16(vector, &cfg->queue_msix_vector);
-	/* Flush the write out to device */
-	return vp_ioread16(&cfg->queue_msix_vector);
-}
-
-/*
- * vp_modern_queue_address - set the virtqueue address
- * @mdev: the modern virtio-pci device
- * @index: the queue index
- * @desc_addr: address of the descriptor area
- * @driver_addr: address of the driver area
- * @device_addr: address of the device area
- */
-static void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
-				    u16 index, u64 desc_addr, u64 driver_addr,
-				    u64 device_addr)
-{
-	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
-
-	vp_iowrite16(index, &cfg->queue_select);
-
-	vp_iowrite64_twopart(desc_addr, &cfg->queue_desc_lo,
-			     &cfg->queue_desc_hi);
-	vp_iowrite64_twopart(driver_addr, &cfg->queue_avail_lo,
-			     &cfg->queue_avail_hi);
-	vp_iowrite64_twopart(device_addr, &cfg->queue_used_lo,
-			     &cfg->queue_used_hi);
-}
-
-/*
- * vp_modern_set_queue_enable - enable a virtqueue
- * @mdev: the modern virtio-pci device
- * @index: the queue index
- * @enable: whether the virtqueue is enable or not
- */
-static void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev,
-				       u16 index, bool enable)
-{
-	vp_iowrite16(index, &mdev->common->queue_select);
-	vp_iowrite16(enable, &mdev->common->queue_enable);
-}
-
-/*
- * vp_modern_get_queue_enable - enable a virtqueue
- * @mdev: the modern virtio-pci device
- * @index: the queue index
- *
- * Returns whether a virtqueue is enabled or not
- */
-static bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
-				       u16 index)
-{
-	vp_iowrite16(index, &mdev->common->queue_select);
-
-	return vp_ioread16(&mdev->common->queue_enable);
-}
-
-/*
- * vp_modern_set_queue_size - set size for a virtqueue
- * @mdev: the modern virtio-pci device
- * @index: the queue index
- * @size: the size of the virtqueue
- */
-static void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev,
-				     u16 index, u16 size)
-{
-	vp_iowrite16(index, &mdev->common->queue_select);
-	vp_iowrite16(size, &mdev->common->queue_size);
-
-}
-
-/*
- * vp_modern_get_queue_size - get size for a virtqueue
- * @mdev: the modern virtio-pci device
- * @index: the queue index
- *
- * Returns the size of the virtqueue
- */
-static u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
-				    u16 index)
-{
-	vp_iowrite16(index, &mdev->common->queue_select);
-
-	return vp_ioread16(&mdev->common->queue_size);
-
-}
-
-/*
- * vp_modern_get_num_queues - get the number of virtqueues
- * @mdev: the modern virtio-pci device
- *
- * Returns the number of virtqueues
- */
-static u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev)
-{
-	return vp_ioread16(&mdev->common->num_queues);
-}
-
-/*
- * vp_modern_get_queue_notify_off - get notification offset for a virtqueue
- * @mdev: the modern virtio-pci device
- * @index: the queue index
- *
- * Returns the notification offset for a virtqueue
- */
-static u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev,
-					  u16 index)
-{
-	vp_iowrite16(index, &mdev->common->queue_select);
-
-	return vp_ioread16(&mdev->common->queue_notify_off);
-}
-
 /* virtio config->finalize_features() implementation */
 static int vp_finalize_features(struct virtio_device *vdev)
 {
@@ -429,19 +134,6 @@ static void vp_set(struct virtio_device *vdev, unsigned offset,
 	}
 }
 
-/*
- * vp_modern_generation - get the device genreation
- * @mdev: the modern virtio-pci device
- *
- * Returns the genreation read from device
- */
-static u32 vp_modern_generation(struct virtio_pci_modern_device *mdev)
-{
-	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
-
-	return vp_ioread8(&cfg->config_generation);
-}
-
 static u32 vp_generation(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -449,19 +141,6 @@ static u32 vp_generation(struct virtio_device *vdev)
 	return vp_modern_generation(&vp_dev->mdev);
 }
 
-/*
- * vp_modern_get_status - get the device status
- * @mdev: the modern virtio-pci device
- *
- * Returns the status read from device
- */
-static u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev)
-{
-	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
-
-	return vp_ioread8(&cfg->device_status);
-}
-
 /* config->{get,set}_status() implementations */
 static u8 vp_get_status(struct virtio_device *vdev)
 {
@@ -470,19 +149,6 @@ static u8 vp_get_status(struct virtio_device *vdev)
 	return vp_modern_get_status(&vp_dev->mdev);
 }
 
-/*
- * vp_modern_set_status - set status to device
- * @mdev: the modern virtio-pci device
- * @status: the status set to device
- */
-static void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
-				 u8 status)
-{
-	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
-
-	vp_iowrite8(status, &cfg->device_status);
-}
-
 static void vp_set_status(struct virtio_device *vdev, u8 status)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -510,25 +176,6 @@ static void vp_reset(struct virtio_device *vdev)
 	vp_synchronize_vectors(vdev);
 }
 
-/*
- * vp_modern_config_vector - set the vector for config interrupt
- * @mdev: the modern virtio-pci device
- * @vector: the config vector
- *
- * Returns the config vector read from the device
- */
-static u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev,
-				   u16 vector)
-{
-	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
-
-	/* Setup the vector used for configuration events */
-	vp_iowrite16(vector, &cfg->msix_config);
-	/* Verify we had enough resources to assign the vector */
-	/* Will also flush the write out to device */
-	return vp_ioread16(&cfg->msix_config);
-}
-
 static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 {
 	return vp_modern_config_vector(&vp_dev->mdev, vector);
@@ -789,253 +436,6 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.get_shm_region  = vp_get_shm_region,
 };
 
-/**
- * virtio_pci_find_capability - walk capabilities to find device info.
- * @dev: the pci device
- * @cfg_type: the VIRTIO_PCI_CAP_* value we seek
- * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
- * @bars: the bitmask of BARs
- *
- * Returns offset of the capability, or 0.
- */
-static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
-					     u32 ioresource_types, int *bars)
-{
-	int pos;
-
-	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
-	     pos > 0;
-	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
-		u8 type, bar;
-		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
-							 cfg_type),
-				     &type);
-		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
-							 bar),
-				     &bar);
-
-		/* Ignore structures with reserved BAR values */
-		if (bar > 0x5)
-			continue;
-
-		if (type == cfg_type) {
-			if (pci_resource_len(dev, bar) &&
-			    pci_resource_flags(dev, bar) & ioresource_types) {
-				*bars |= (1 << bar);
-				return pos;
-			}
-		}
-	}
-	return 0;
-}
-
-/* This is part of the ABI.  Don't screw with it. */
-static inline void check_offsets(void)
-{
-	/* Note: disk space was harmed in compilation of this function. */
-	BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR !=
-		     offsetof(struct virtio_pci_cap, cap_vndr));
-	BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT !=
-		     offsetof(struct virtio_pci_cap, cap_next));
-	BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN !=
-		     offsetof(struct virtio_pci_cap, cap_len));
-	BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE !=
-		     offsetof(struct virtio_pci_cap, cfg_type));
-	BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR !=
-		     offsetof(struct virtio_pci_cap, bar));
-	BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET !=
-		     offsetof(struct virtio_pci_cap, offset));
-	BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH !=
-		     offsetof(struct virtio_pci_cap, length));
-	BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT !=
-		     offsetof(struct virtio_pci_notify_cap,
-			      notify_off_multiplier));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT !=
-		     offsetof(struct virtio_pci_common_cfg,
-			      device_feature_select));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF !=
-		     offsetof(struct virtio_pci_common_cfg, device_feature));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT !=
-		     offsetof(struct virtio_pci_common_cfg,
-			      guest_feature_select));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF !=
-		     offsetof(struct virtio_pci_common_cfg, guest_feature));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX !=
-		     offsetof(struct virtio_pci_common_cfg, msix_config));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ !=
-		     offsetof(struct virtio_pci_common_cfg, num_queues));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS !=
-		     offsetof(struct virtio_pci_common_cfg, device_status));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION !=
-		     offsetof(struct virtio_pci_common_cfg, config_generation));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT !=
-		     offsetof(struct virtio_pci_common_cfg, queue_select));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE !=
-		     offsetof(struct virtio_pci_common_cfg, queue_size));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX !=
-		     offsetof(struct virtio_pci_common_cfg, queue_msix_vector));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE !=
-		     offsetof(struct virtio_pci_common_cfg, queue_enable));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF !=
-		     offsetof(struct virtio_pci_common_cfg, queue_notify_off));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO !=
-		     offsetof(struct virtio_pci_common_cfg, queue_desc_lo));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI !=
-		     offsetof(struct virtio_pci_common_cfg, queue_desc_hi));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO !=
-		     offsetof(struct virtio_pci_common_cfg, queue_avail_lo));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI !=
-		     offsetof(struct virtio_pci_common_cfg, queue_avail_hi));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO !=
-		     offsetof(struct virtio_pci_common_cfg, queue_used_lo));
-	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI !=
-		     offsetof(struct virtio_pci_common_cfg, queue_used_hi));
-}
-
-/*
- * vp_modern_probe: probe the modern virtio pci device, note that the
- * caller is required to enable PCI device before calling this function.
- * @mdev: the modern virtio-pci device
- *
- * Return 0 on succeed otherwise fail
- */
-static int vp_modern_probe(struct virtio_pci_modern_device *mdev)
-{
-	struct pci_dev *pci_dev = mdev->pci_dev;
-	int err, common, isr, notify, device;
-	u32 notify_length;
-	u32 notify_offset;
-
-	check_offsets();
-
-	mdev->pci_dev = pci_dev;
-
-	/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
-	if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
-		return -ENODEV;
-
-	if (pci_dev->device < 0x1040) {
-		/* Transitional devices: use the PCI subsystem device id as
-		 * virtio device id, same as legacy driver always did.
-		 */
-		mdev->id.device = pci_dev->subsystem_device;
-	} else {
-		/* Modern devices: simply use PCI device id, but start from 0x1040. */
-		mdev->id.device = pci_dev->device - 0x1040;
-	}
-	mdev->id.vendor = pci_dev->subsystem_vendor;
-
-	/* check for a common config: if not, use legacy mode (bar 0). */
-	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
-					    IORESOURCE_IO | IORESOURCE_MEM,
-					    &mdev->modern_bars);
-	if (!common) {
-		dev_info(&pci_dev->dev,
-			 "virtio_pci: leaving for legacy driver\n");
-		return -ENODEV;
-	}
-
-	/* If common is there, these should be too... */
-	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
-					 IORESOURCE_IO | IORESOURCE_MEM,
-					 &mdev->modern_bars);
-	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
-					    IORESOURCE_IO | IORESOURCE_MEM,
-					    &mdev->modern_bars);
-	if (!isr || !notify) {
-		dev_err(&pci_dev->dev,
-			"virtio_pci: missing capabilities %i/%i/%i\n",
-			common, isr, notify);
-		return -EINVAL;
-	}
-
-	err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
-	if (err)
-		err = dma_set_mask_and_coherent(&pci_dev->dev,
-						DMA_BIT_MASK(32));
-	if (err)
-		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
-
-	/* Device capability is only mandatory for devices that have
-	 * device-specific configuration.
-	 */
-	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
-					    IORESOURCE_IO | IORESOURCE_MEM,
-					    &mdev->modern_bars);
-
-	err = pci_request_selected_regions(pci_dev, mdev->modern_bars,
-					   "virtio-pci-modern");
-	if (err)
-		return err;
-
-	err = -EINVAL;
-	mdev->common = vp_modern_map_capability(mdev, common,
-				      sizeof(struct virtio_pci_common_cfg), 4,
-				      0, sizeof(struct virtio_pci_common_cfg),
-				      NULL);
-	if (!mdev->common)
-		goto err_map_common;
-	mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1,
-					     0, 1,
-					     NULL);
-	if (!mdev->isr)
-		goto err_map_isr;
-
-	/* Read notify_off_multiplier from config space. */
-	pci_read_config_dword(pci_dev,
-			      notify + offsetof(struct virtio_pci_notify_cap,
-						notify_off_multiplier),
-			      &mdev->notify_offset_multiplier);
-	/* Read notify length and offset from config space. */
-	pci_read_config_dword(pci_dev,
-			      notify + offsetof(struct virtio_pci_notify_cap,
-						cap.length),
-			      &notify_length);
-
-	pci_read_config_dword(pci_dev,
-			      notify + offsetof(struct virtio_pci_notify_cap,
-						cap.offset),
-			      &notify_offset);
-
-	/* We don't know how many VQs we'll map, ahead of the time.
-	 * If notify length is small, map it all now.
-	 * Otherwise, map each VQ individually later.
-	 */
-	if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) {
-		mdev->notify_base = vp_modern_map_capability(mdev, notify,
-							     2, 2,
-							     0, notify_length,
-							     &mdev->notify_len);
-		if (!mdev->notify_base)
-			goto err_map_notify;
-	} else {
-		mdev->notify_map_cap = notify;
-	}
-
-	/* Again, we don't know how much we should map, but PAGE_SIZE
-	 * is more than enough for all existing devices.
-	 */
-	if (device) {
-		mdev->device = vp_modern_map_capability(mdev, device, 0, 4,
-							0, PAGE_SIZE,
-							&mdev->device_len);
-		if (!mdev->device)
-			goto err_map_device;
-	}
-
-	return 0;
-
-err_map_device:
-	if (mdev->notify_base)
-		pci_iounmap(pci_dev, mdev->notify_base);
-err_map_notify:
-	pci_iounmap(pci_dev, mdev->isr);
-err_map_isr:
-	pci_iounmap(pci_dev, mdev->common);
-err_map_common:
-	return err;
-}
-
 /* the PCI probing function */
 int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 {
@@ -1063,23 +463,6 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	return 0;
 }
 
-/*
- * vp_modern_probe: remove and cleanup the modern virtio pci device
- * @mdev: the modern virtio-pci device
- */
-static void vp_modern_remove(struct virtio_pci_modern_device *mdev)
-{
-	struct pci_dev *pci_dev = mdev->pci_dev;
-
-	if (mdev->device)
-		pci_iounmap(pci_dev, mdev->device);
-	if (mdev->notify_base)
-		pci_iounmap(pci_dev, mdev->notify_base);
-	pci_iounmap(pci_dev, mdev->isr);
-	pci_iounmap(pci_dev, mdev->common);
-	pci_release_selected_regions(pci_dev, mdev->modern_bars);
-}
-
 void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
 {
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
new file mode 100644
index 000000000000..cbd667496bb1
--- /dev/null
+++ b/drivers/virtio/virtio_pci_modern_dev.c
@@ -0,0 +1,599 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/virtio_pci_modern.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+/*
+ * vp_modern_map_capability - map a part of virtio pci capability
+ * @mdev: the modern virtio-pci device
+ * @off: offset of the capability
+ * @minlen: minimal length of the capability
+ * @align: align requirement
+ * @start: start from the capability
+ * @size: map size
+ * @len: the length that is actually mapped
+ *
+ * Returns the io address of for the part of the capability
+ */
+void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off,
+				       size_t minlen,
+				       u32 align,
+				       u32 start, u32 size,
+				       size_t *len)
+{
+	struct pci_dev *dev = mdev->pci_dev;
+	u8 bar;
+	u32 offset, length;
+	void __iomem *p;
+
+	pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap,
+						 bar),
+			     &bar);
+	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset),
+			     &offset);
+	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length),
+			      &length);
+
+	if (length <= start) {
+		dev_err(&dev->dev,
+			"virtio_pci: bad capability len %u (>%u expected)\n",
+			length, start);
+		return NULL;
+	}
+
+	if (length - start < minlen) {
+		dev_err(&dev->dev,
+			"virtio_pci: bad capability len %u (>=%zu expected)\n",
+			length, minlen);
+		return NULL;
+	}
+
+	length -= start;
+
+	if (start + offset < offset) {
+		dev_err(&dev->dev,
+			"virtio_pci: map wrap-around %u+%u\n",
+			start, offset);
+		return NULL;
+	}
+
+	offset += start;
+
+	if (offset & (align - 1)) {
+		dev_err(&dev->dev,
+			"virtio_pci: offset %u not aligned to %u\n",
+			offset, align);
+		return NULL;
+	}
+
+	if (length > size)
+		length = size;
+
+	if (len)
+		*len = length;
+
+	if (minlen + offset < minlen ||
+	    minlen + offset > pci_resource_len(dev, bar)) {
+		dev_err(&dev->dev,
+			"virtio_pci: map virtio %zu@%u "
+			"out of range on bar %i length %lu\n",
+			minlen, offset,
+			bar, (unsigned long)pci_resource_len(dev, bar));
+		return NULL;
+	}
+
+	p = pci_iomap_range(dev, bar, offset, length);
+	if (!p)
+		dev_err(&dev->dev,
+			"virtio_pci: unable to map virtio %u@%u on bar %i\n",
+			length, offset, bar);
+	return p;
+}
+EXPORT_SYMBOL_GPL(vp_modern_map_capability);
+
+/**
+ * virtio_pci_find_capability - walk capabilities to find device info.
+ * @dev: the pci device
+ * @cfg_type: the VIRTIO_PCI_CAP_* value we seek
+ * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
+ * @bars: the bitmask of BARs
+ *
+ * Returns offset of the capability, or 0.
+ */
+static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
+					     u32 ioresource_types, int *bars)
+{
+	int pos;
+
+	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
+	     pos > 0;
+	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
+		u8 type, bar;
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+							 cfg_type),
+				     &type);
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+							 bar),
+				     &bar);
+
+		/* Ignore structures with reserved BAR values */
+		if (bar > 0x5)
+			continue;
+
+		if (type == cfg_type) {
+			if (pci_resource_len(dev, bar) &&
+			    pci_resource_flags(dev, bar) & ioresource_types) {
+				*bars |= (1 << bar);
+				return pos;
+			}
+		}
+	}
+	return 0;
+}
+
+/* This is part of the ABI.  Don't screw with it. */
+static inline void check_offsets(void)
+{
+	/* Note: disk space was harmed in compilation of this function. */
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR !=
+		     offsetof(struct virtio_pci_cap, cap_vndr));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT !=
+		     offsetof(struct virtio_pci_cap, cap_next));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN !=
+		     offsetof(struct virtio_pci_cap, cap_len));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE !=
+		     offsetof(struct virtio_pci_cap, cfg_type));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR !=
+		     offsetof(struct virtio_pci_cap, bar));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET !=
+		     offsetof(struct virtio_pci_cap, offset));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH !=
+		     offsetof(struct virtio_pci_cap, length));
+	BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT !=
+		     offsetof(struct virtio_pci_notify_cap,
+			      notify_off_multiplier));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT !=
+		     offsetof(struct virtio_pci_common_cfg,
+			      device_feature_select));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF !=
+		     offsetof(struct virtio_pci_common_cfg, device_feature));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT !=
+		     offsetof(struct virtio_pci_common_cfg,
+			      guest_feature_select));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF !=
+		     offsetof(struct virtio_pci_common_cfg, guest_feature));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX !=
+		     offsetof(struct virtio_pci_common_cfg, msix_config));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ !=
+		     offsetof(struct virtio_pci_common_cfg, num_queues));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS !=
+		     offsetof(struct virtio_pci_common_cfg, device_status));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION !=
+		     offsetof(struct virtio_pci_common_cfg, config_generation));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT !=
+		     offsetof(struct virtio_pci_common_cfg, queue_select));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE !=
+		     offsetof(struct virtio_pci_common_cfg, queue_size));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX !=
+		     offsetof(struct virtio_pci_common_cfg, queue_msix_vector));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE !=
+		     offsetof(struct virtio_pci_common_cfg, queue_enable));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF !=
+		     offsetof(struct virtio_pci_common_cfg, queue_notify_off));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO !=
+		     offsetof(struct virtio_pci_common_cfg, queue_desc_lo));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI !=
+		     offsetof(struct virtio_pci_common_cfg, queue_desc_hi));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO !=
+		     offsetof(struct virtio_pci_common_cfg, queue_avail_lo));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI !=
+		     offsetof(struct virtio_pci_common_cfg, queue_avail_hi));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO !=
+		     offsetof(struct virtio_pci_common_cfg, queue_used_lo));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI !=
+		     offsetof(struct virtio_pci_common_cfg, queue_used_hi));
+}
+
+/*
+ * vp_modern_probe: probe the modern virtio pci device, note that the
+ * caller is required to enable PCI device before calling this function.
+ * @mdev: the modern virtio-pci device
+ *
+ * Return 0 on succeed otherwise fail
+ */
+int vp_modern_probe(struct virtio_pci_modern_device *mdev)
+{
+	struct pci_dev *pci_dev = mdev->pci_dev;
+	int err, common, isr, notify, device;
+	u32 notify_length;
+	u32 notify_offset;
+
+	check_offsets();
+
+	mdev->pci_dev = pci_dev;
+
+	/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
+	if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
+		return -ENODEV;
+
+	if (pci_dev->device < 0x1040) {
+		/* Transitional devices: use the PCI subsystem device id as
+		 * virtio device id, same as legacy driver always did.
+		 */
+		mdev->id.device = pci_dev->subsystem_device;
+	} else {
+		/* Modern devices: simply use PCI device id, but start from 0x1040. */
+		mdev->id.device = pci_dev->device - 0x1040;
+	}
+	mdev->id.vendor = pci_dev->subsystem_vendor;
+
+	/* check for a common config: if not, use legacy mode (bar 0). */
+	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
+					    IORESOURCE_IO | IORESOURCE_MEM,
+					    &mdev->modern_bars);
+	if (!common) {
+		dev_info(&pci_dev->dev,
+			 "virtio_pci: leaving for legacy driver\n");
+		return -ENODEV;
+	}
+
+	/* If common is there, these should be too... */
+	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
+					 IORESOURCE_IO | IORESOURCE_MEM,
+					 &mdev->modern_bars);
+	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
+					    IORESOURCE_IO | IORESOURCE_MEM,
+					    &mdev->modern_bars);
+	if (!isr || !notify) {
+		dev_err(&pci_dev->dev,
+			"virtio_pci: missing capabilities %i/%i/%i\n",
+			common, isr, notify);
+		return -EINVAL;
+	}
+
+	err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
+	if (err)
+		err = dma_set_mask_and_coherent(&pci_dev->dev,
+						DMA_BIT_MASK(32));
+	if (err)
+		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
+
+	/* Device capability is only mandatory for devices that have
+	 * device-specific configuration.
+	 */
+	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
+					    IORESOURCE_IO | IORESOURCE_MEM,
+					    &mdev->modern_bars);
+
+	err = pci_request_selected_regions(pci_dev, mdev->modern_bars,
+					   "virtio-pci-modern");
+	if (err)
+		return err;
+
+	err = -EINVAL;
+	mdev->common = vp_modern_map_capability(mdev, common,
+				      sizeof(struct virtio_pci_common_cfg), 4,
+				      0, sizeof(struct virtio_pci_common_cfg),
+				      NULL);
+	if (!mdev->common)
+		goto err_map_common;
+	mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1,
+					     0, 1,
+					     NULL);
+	if (!mdev->isr)
+		goto err_map_isr;
+
+	/* Read notify_off_multiplier from config space. */
+	pci_read_config_dword(pci_dev,
+			      notify + offsetof(struct virtio_pci_notify_cap,
+						notify_off_multiplier),
+			      &mdev->notify_offset_multiplier);
+	/* Read notify length and offset from config space. */
+	pci_read_config_dword(pci_dev,
+			      notify + offsetof(struct virtio_pci_notify_cap,
+						cap.length),
+			      &notify_length);
+
+	pci_read_config_dword(pci_dev,
+			      notify + offsetof(struct virtio_pci_notify_cap,
+						cap.offset),
+			      &notify_offset);
+
+	/* We don't know how many VQs we'll map, ahead of the time.
+	 * If notify length is small, map it all now.
+	 * Otherwise, map each VQ individually later.
+	 */
+	if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) {
+		mdev->notify_base = vp_modern_map_capability(mdev, notify,
+							     2, 2,
+							     0, notify_length,
+							     &mdev->notify_len);
+		if (!mdev->notify_base)
+			goto err_map_notify;
+	} else {
+		mdev->notify_map_cap = notify;
+	}
+
+	/* Again, we don't know how much we should map, but PAGE_SIZE
+	 * is more than enough for all existing devices.
+	 */
+	if (device) {
+		mdev->device = vp_modern_map_capability(mdev, device, 0, 4,
+							0, PAGE_SIZE,
+							&mdev->device_len);
+		if (!mdev->device)
+			goto err_map_device;
+	}
+
+	return 0;
+
+err_map_device:
+	if (mdev->notify_base)
+		pci_iounmap(pci_dev, mdev->notify_base);
+err_map_notify:
+	pci_iounmap(pci_dev, mdev->isr);
+err_map_isr:
+	pci_iounmap(pci_dev, mdev->common);
+err_map_common:
+	return err;
+}
+EXPORT_SYMBOL_GPL(vp_modern_probe);
+
+/*
+ * vp_modern_probe: remove and cleanup the modern virtio pci device
+ * @mdev: the modern virtio-pci device
+ */
+void vp_modern_remove(struct virtio_pci_modern_device *mdev)
+{
+	struct pci_dev *pci_dev = mdev->pci_dev;
+
+	if (mdev->device)
+		pci_iounmap(pci_dev, mdev->device);
+	if (mdev->notify_base)
+		pci_iounmap(pci_dev, mdev->notify_base);
+	pci_iounmap(pci_dev, mdev->isr);
+	pci_iounmap(pci_dev, mdev->common);
+	pci_release_selected_regions(pci_dev, mdev->modern_bars);
+}
+EXPORT_SYMBOL_GPL(vp_modern_remove);
+
+/*
+ * vp_modern_get_features - get features from device
+ * @mdev: the modern virtio-pci device
+ *
+ * Returns the features read from the device
+ */
+u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	u64 features;
+
+	vp_iowrite32(0, &cfg->device_feature_select);
+	features = vp_ioread32(&cfg->device_feature);
+	vp_iowrite32(1, &cfg->device_feature_select);
+	features |= ((u64)vp_ioread32(&cfg->device_feature) << 32);
+
+	return features;
+}
+EXPORT_SYMBOL_GPL(vp_modern_get_features);
+
+/*
+ * vp_modern_set_features - set features to device
+ * @mdev: the modern virtio-pci device
+ * @features: the features set to device
+ */
+void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
+			    u64 features)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	vp_iowrite32(0, &cfg->guest_feature_select);
+	vp_iowrite32((u32)features, &cfg->guest_feature);
+	vp_iowrite32(1, &cfg->guest_feature_select);
+	vp_iowrite32(features >> 32, &cfg->guest_feature);
+}
+EXPORT_SYMBOL_GPL(vp_modern_set_features);
+
+/*
+ * vp_modern_generation - get the device genreation
+ * @mdev: the modern virtio-pci device
+ *
+ * Returns the genreation read from device
+ */
+u32 vp_modern_generation(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	return vp_ioread8(&cfg->config_generation);
+}
+EXPORT_SYMBOL_GPL(vp_modern_generation);
+
+/*
+ * vp_modern_get_status - get the device status
+ * @mdev: the modern virtio-pci device
+ *
+ * Returns the status read from device
+ */
+u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	return vp_ioread8(&cfg->device_status);
+}
+EXPORT_SYMBOL_GPL(vp_modern_get_status);
+
+/*
+ * vp_modern_set_status - set status to device
+ * @mdev: the modern virtio-pci device
+ * @status: the status set to device
+ */
+void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
+				 u8 status)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	vp_iowrite8(status, &cfg->device_status);
+}
+EXPORT_SYMBOL_GPL(vp_modern_set_status);
+
+/*
+ * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: queue index
+ * @vector: the config vector
+ *
+ * Returns the config vector read from the device
+ */
+u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
+			   u16 index, u16 vector)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	vp_iowrite16(index, &cfg->queue_select);
+	vp_iowrite16(vector, &cfg->queue_msix_vector);
+	/* Flush the write out to device */
+	return vp_ioread16(&cfg->queue_msix_vector);
+}
+EXPORT_SYMBOL_GPL(vp_modern_queue_vector);
+
+/*
+ * vp_modern_config_vector - set the vector for config interrupt
+ * @mdev: the modern virtio-pci device
+ * @vector: the config vector
+ *
+ * Returns the config vector read from the device
+ */
+u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev,
+			    u16 vector)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	/* Setup the vector used for configuration events */
+	vp_iowrite16(vector, &cfg->msix_config);
+	/* Verify we had enough resources to assign the vector */
+	/* Will also flush the write out to device */
+	return vp_ioread16(&cfg->msix_config);
+}
+EXPORT_SYMBOL_GPL(vp_modern_config_vector);
+
+/*
+ * vp_modern_queue_address - set the virtqueue address
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ * @desc_addr: address of the descriptor area
+ * @driver_addr: address of the driver area
+ * @device_addr: address of the device area
+ */
+void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
+			     u16 index, u64 desc_addr, u64 driver_addr,
+			     u64 device_addr)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	vp_iowrite16(index, &cfg->queue_select);
+
+	vp_iowrite64_twopart(desc_addr, &cfg->queue_desc_lo,
+			     &cfg->queue_desc_hi);
+	vp_iowrite64_twopart(driver_addr, &cfg->queue_avail_lo,
+			     &cfg->queue_avail_hi);
+	vp_iowrite64_twopart(device_addr, &cfg->queue_used_lo,
+			     &cfg->queue_used_hi);
+}
+EXPORT_SYMBOL_GPL(vp_modern_queue_address);
+
+/*
+ * vp_modern_set_queue_enable - enable a virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ * @enable: whether the virtqueue is enable or not
+ */
+void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev,
+				u16 index, bool enable)
+{
+	vp_iowrite16(index, &mdev->common->queue_select);
+	vp_iowrite16(enable, &mdev->common->queue_enable);
+}
+EXPORT_SYMBOL_GPL(vp_modern_set_queue_enable);
+
+/*
+ * vp_modern_get_queue_enable - enable a virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ *
+ * Returns whether a virtqueue is enabled or not
+ */
+bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
+				u16 index)
+{
+	vp_iowrite16(index, &mdev->common->queue_select);
+
+	return vp_ioread16(&mdev->common->queue_enable);
+}
+EXPORT_SYMBOL_GPL(vp_modern_get_queue_enable);
+
+/*
+ * vp_modern_set_queue_size - set size for a virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ * @size: the size of the virtqueue
+ */
+void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev,
+			      u16 index, u16 size)
+{
+	vp_iowrite16(index, &mdev->common->queue_select);
+	vp_iowrite16(size, &mdev->common->queue_size);
+
+}
+EXPORT_SYMBOL_GPL(vp_modern_set_queue_size);
+
+/*
+ * vp_modern_get_queue_size - get size for a virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ *
+ * Returns the size of the virtqueue
+ */
+u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
+			     u16 index)
+{
+	vp_iowrite16(index, &mdev->common->queue_select);
+
+	return vp_ioread16(&mdev->common->queue_size);
+
+}
+EXPORT_SYMBOL_GPL(vp_modern_get_queue_size);
+
+/*
+ * vp_modern_get_num_queues - get the number of virtqueues
+ * @mdev: the modern virtio-pci device
+ *
+ * Returns the number of virtqueues
+ */
+u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev)
+{
+	return vp_ioread16(&mdev->common->num_queues);
+}
+EXPORT_SYMBOL_GPL(vp_modern_get_num_queues);
+
+/*
+ * vp_modern_get_queue_notify_off - get notification offset for a virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ *
+ * Returns the notification offset for a virtqueue
+ */
+u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev,
+				   u16 index)
+{
+	vp_iowrite16(index, &mdev->common->queue_select);
+
+	return vp_ioread16(&mdev->common->queue_notify_off);
+}
+EXPORT_SYMBOL_GPL(vp_modern_get_queue_notify_off);
+
+MODULE_VERSION("0.1");
+MODULE_DESCRIPTION("Modern Virtio PCI Device");
+MODULE_AUTHOR("Jason Wang <jasowang@redhat.com>");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h
new file mode 100644
index 000000000000..f26acbeec965
--- /dev/null
+++ b/include/linux/virtio_pci_modern.h
@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_VIRTIO_PCI_MODERN_H
+#define _LINUX_VIRTIO_PCI_MODERN_H
+
+#include <linux/pci.h>
+#include <linux/virtio_pci.h>
+
+struct virtio_pci_modern_device {
+	struct pci_dev *pci_dev;
+
+	struct virtio_pci_common_cfg __iomem *common;
+	/* Device-specific data (non-legacy mode)  */
+	void __iomem *device;
+	/* Base of vq notifications (non-legacy mode). */
+	void __iomem *notify_base;
+	/* Where to read and clear interrupt */
+	u8 __iomem *isr;
+
+	/* So we can sanity-check accesses. */
+	size_t notify_len;
+	size_t device_len;
+
+	/* Capability for when we need to map notifications per-vq. */
+	int notify_map_cap;
+
+	/* Multiply queue_notify_off by this value. (non-legacy mode). */
+	u32 notify_offset_multiplier;
+
+	int modern_bars;
+
+	struct virtio_device_id id;
+};
+
+/*
+ * Type-safe wrappers for io accesses.
+ * Use these to enforce at compile time the following spec requirement:
+ *
+ * The driver MUST access each field using the “natural” access
+ * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses
+ * for 16-bit fields and 8-bit accesses for 8-bit fields.
+ */
+static inline u8 vp_ioread8(const u8 __iomem *addr)
+{
+	return ioread8(addr);
+}
+static inline u16 vp_ioread16 (const __le16 __iomem *addr)
+{
+	return ioread16(addr);
+}
+
+static inline u32 vp_ioread32(const __le32 __iomem *addr)
+{
+	return ioread32(addr);
+}
+
+static inline void vp_iowrite8(u8 value, u8 __iomem *addr)
+{
+	iowrite8(value, addr);
+}
+
+static inline void vp_iowrite16(u16 value, __le16 __iomem *addr)
+{
+	iowrite16(value, addr);
+}
+
+static inline void vp_iowrite32(u32 value, __le32 __iomem *addr)
+{
+	iowrite32(value, addr);
+}
+
+static inline void vp_iowrite64_twopart(u64 val,
+					__le32 __iomem *lo,
+					__le32 __iomem *hi)
+{
+	vp_iowrite32((u32)val, lo);
+	vp_iowrite32(val >> 32, hi);
+}
+
+u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev);
+void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
+		     u64 features);
+u32 vp_modern_generation(struct virtio_pci_modern_device *mdev);
+u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev);
+void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
+		   u8 status);
+u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
+			   u16 idx, u16 vector);
+u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev,
+		     u16 vector);
+void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
+			     u16 index, u64 desc_addr, u64 driver_addr,
+			     u64 device_addr);
+void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev,
+				u16 idx, bool enable);
+bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
+				u16 idx);
+void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev,
+			      u16 idx, u16 size);
+u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
+			     u16 idx);
+u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev);
+u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev,
+				   u16 idx);
+void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off,
+				       size_t minlen,
+				       u32 align,
+				       u32 start, u32 size,
+				       size_t *len);
+int vp_modern_probe(struct virtio_pci_modern_device *mdev);
+void vp_modern_remove(struct virtio_pci_modern_device *mdev);
+#endif
-- 
2.25.1

[PATCH V3 17/19] vdpa: set the virtqueue num during register

[Jason Wang]

This patch delay the queue number setting to vDPA device
registering. This allows us to probe the virtqueue numbers between
device allocation and registering.

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vdpa/ifcvf/ifcvf_main.c   | 5 ++---
 drivers/vdpa/mlx5/net/mlx5_vnet.c | 5 ++---
 drivers/vdpa/vdpa.c               | 8 ++++----
 drivers/vdpa/vdpa_sim/vdpa_sim.c  | 4 ++--
 include/linux/vdpa.h              | 7 +++----
 5 files changed, 13 insertions(+), 16 deletions(-)

diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index 8b4028556cb6..d65f3221d8ed 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -438,8 +438,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 	adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
-				    dev, &ifc_vdpa_ops,
-				    IFCVF_MAX_QUEUE_PAIRS * 2);
+				    dev, &ifc_vdpa_ops);
 	if (adapter == NULL) {
 		IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
 		return -ENOMEM;
@@ -463,7 +462,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++)
 		vf->vring[i].irq = -EINVAL;
 
-	ret = vdpa_register_device(&adapter->vdpa);
+	ret = vdpa_register_device(&adapter->vdpa, IFCVF_MAX_QUEUE_PAIRS * 2);
 	if (ret) {
 		IFCVF_ERR(pdev, "Failed to register ifcvf to vdpa bus");
 		goto err;
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index f1d54814db97..a1b9260bf04d 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1958,8 +1958,7 @@ static int mlx5v_probe(struct auxiliary_device *adev,
 	max_vqs = MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues);
 	max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS);
 
-	ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops,
-				 2 * mlx5_vdpa_max_qps(max_vqs));
+	ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops);
 	if (IS_ERR(ndev))
 		return PTR_ERR(ndev);
 
@@ -1986,7 +1985,7 @@ static int mlx5v_probe(struct auxiliary_device *adev,
 	if (err)
 		goto err_res;
 
-	err = vdpa_register_device(&mvdev->vdev);
+	err = vdpa_register_device(&mvdev->vdev, 2 * mlx5_vdpa_max_qps(max_vqs));
 	if (err)
 		goto err_reg;
 
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index a69ffc991e13..ba89238f9898 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -61,7 +61,6 @@ static void vdpa_release_dev(struct device *d)
  * initialized but before registered.
  * @parent: the parent device
  * @config: the bus operations that is supported by this device
- * @nvqs: number of virtqueues supported by this device
  * @size: size of the parent structure that contains private data
  *
  * Driver should use vdpa_alloc_device() wrapper macro instead of
@@ -72,7 +71,6 @@ static void vdpa_release_dev(struct device *d)
  */
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
-					int nvqs,
 					size_t size)
 {
 	struct vdpa_device *vdev;
@@ -99,7 +97,6 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 	vdev->index = err;
 	vdev->config = config;
 	vdev->features_valid = false;
-	vdev->nvqs = nvqs;
 
 	err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index);
 	if (err)
@@ -122,11 +119,14 @@ EXPORT_SYMBOL_GPL(__vdpa_alloc_device);
  * vdpa_register_device - register a vDPA device
  * Callers must have a succeed call of vdpa_alloc_device() before.
  * @vdev: the vdpa device to be registered to vDPA bus
+ * @nvqs: number of virtqueues supported by this device
  *
  * Returns an error when fail to add to vDPA bus
  */
-int vdpa_register_device(struct vdpa_device *vdev)
+int vdpa_register_device(struct vdpa_device *vdev, int nvqs)
 {
+	vdev->nvqs = nvqs;
+
 	return device_add(&vdev->dev);
 }
 EXPORT_SYMBOL_GPL(vdpa_register_device);
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 6a90fdb9cbfc..b129cb4dd013 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -357,7 +357,7 @@ static struct vdpasim *vdpasim_create(void)
 	else
 		ops = &vdpasim_net_config_ops;
 
-	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, VDPASIM_VQ_NUM);
+	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops);
 	if (!vdpasim)
 		goto err_alloc;
 
@@ -393,7 +393,7 @@ static struct vdpasim *vdpasim_create(void)
 	vringh_set_iotlb(&vdpasim->vqs[1].vring, vdpasim->iommu);
 
 	vdpasim->vdpa.dma_dev = dev;
-	ret = vdpa_register_device(&vdpasim->vdpa);
+	ret = vdpa_register_device(&vdpasim->vdpa, VDPASIM_VQ_NUM);
 	if (ret)
 		goto err_iommu;
 
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 30bc7a7223bb..d9e9d17b9083 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -244,18 +244,17 @@ struct vdpa_config_ops {
 
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
-					int nvqs,
 					size_t size);
 
-#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs)   \
+#define vdpa_alloc_device(dev_struct, member, parent, config)   \
 			  container_of(__vdpa_alloc_device( \
-				       parent, config, nvqs, \
+				       parent, config, \
 				       sizeof(dev_struct) + \
 				       BUILD_BUG_ON_ZERO(offsetof( \
 				       dev_struct, member))), \
 				       dev_struct, member)
 
-int vdpa_register_device(struct vdpa_device *vdev);
+int vdpa_register_device(struct vdpa_device *vdev, int nvqs);
 void vdpa_unregister_device(struct vdpa_device *vdev);
 
 /**
-- 
2.25.1

[PATCH V3 18/19] virtio_vdpa: don't warn when fail to disable vq

[Jason Wang]

There's no guarantee that the device can disable a specific virtqueue
through set_vq_ready(). One example is the modern virtio-pci
device. So this patch removes the warning.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_vdpa.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c
index 4a9ddb44b2a7..e28acf482e0c 100644
--- a/drivers/virtio/virtio_vdpa.c
+++ b/drivers/virtio/virtio_vdpa.c
@@ -225,9 +225,8 @@ static void virtio_vdpa_del_vq(struct virtqueue *vq)
 	list_del(&info->node);
 	spin_unlock_irqrestore(&vd_dev->lock, flags);
 
-	/* Select and deactivate the queue */
+	/* Select and deactivate the queue (best effort) */
 	ops->set_vq_ready(vdpa, index, 0);
-	WARN_ON(ops->get_vq_ready(vdpa, index));
 
 	vring_del_virtqueue(vq);
 
-- 
2.25.1

[PATCH V3 19/19] vdpa: introduce virtio pci driver

[Jason Wang]

This patch introduce a vDPA driver for virtio-pci device. It bridges
the virtio-pci control command to the vDPA bus. This will be used for
features prototyping and testing.

Note that get/restore virtqueue state is not supported which needs
extension on the virtio specification.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vdpa/Kconfig              |   6 +
 drivers/vdpa/Makefile             |   1 +
 drivers/vdpa/virtio_pci/Makefile  |   2 +
 drivers/vdpa/virtio_pci/vp_vdpa.c | 456 ++++++++++++++++++++++++++++++
 4 files changed, 465 insertions(+)
 create mode 100644 drivers/vdpa/virtio_pci/Makefile
 create mode 100644 drivers/vdpa/virtio_pci/vp_vdpa.c

diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig
index 6caf539091e5..81c6a3520813 100644
--- a/drivers/vdpa/Kconfig
+++ b/drivers/vdpa/Kconfig
@@ -49,4 +49,10 @@ config MLX5_VDPA_NET
 	  be executed by the hardware. It also supports a variety of stateless
 	  offloads depending on the actual device used and firmware version.
 
+config VP_VDPA
+	tristate "Virtio PCI bridge vDPA driver"
+	depends on PCI_MSI && VIRTIO_PCI_MODERN
+	help
+	  This kernel module bridges virtio PCI device to vDPA bus.
+
 endif # VDPA
diff --git a/drivers/vdpa/Makefile b/drivers/vdpa/Makefile
index d160e9b63a66..67fe7f3d6943 100644
--- a/drivers/vdpa/Makefile
+++ b/drivers/vdpa/Makefile
@@ -3,3 +3,4 @@ obj-$(CONFIG_VDPA) += vdpa.o
 obj-$(CONFIG_VDPA_SIM) += vdpa_sim/
 obj-$(CONFIG_IFCVF)    += ifcvf/
 obj-$(CONFIG_MLX5_VDPA) += mlx5/
+obj-$(CONFIG_VP_VDPA)    += virtio_pci/
diff --git a/drivers/vdpa/virtio_pci/Makefile b/drivers/vdpa/virtio_pci/Makefile
new file mode 100644
index 000000000000..231088d3af7d
--- /dev/null
+++ b/drivers/vdpa/virtio_pci/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_VP_VDPA) += vp_vdpa.o
diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c
new file mode 100644
index 000000000000..4eda926493d9
--- /dev/null
+++ b/drivers/vdpa/virtio_pci/vp_vdpa.c
@@ -0,0 +1,456 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vDPA bridge driver for modern virtio-pci device
+ *
+ * Copyright (c) 2020, Red Hat Inc. All rights reserved.
+ * Author: Jason Wang <jasowang@redhat.com>
+ *
+ * Based on virtio_pci_modern.c.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/vdpa.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+#include <linux/virtio_pci.h>
+#include <linux/virtio_pci_modern.h>
+
+#define VP_VDPA_QUEUE_MAX 256
+#define VP_VDPA_DRIVER_NAME "vp_vdpa"
+#define VP_VDPA_NAME_SIZE 256
+
+struct vp_vring {
+	void __iomem *notify;
+	char msix_name[VP_VDPA_NAME_SIZE];
+	struct vdpa_callback cb;
+	int irq;
+};
+
+struct vp_vdpa {
+	struct vdpa_device vdpa;
+	struct virtio_pci_modern_device mdev;
+	struct vp_vring *vring;
+	struct vdpa_callback config_cb;
+	char msix_name[VP_VDPA_NAME_SIZE];
+	int config_irq;
+	int queues;
+	int vectors;
+};
+
+static struct vp_vdpa *vdpa_to_vp(struct vdpa_device *vdpa)
+{
+	return container_of(vdpa, struct vp_vdpa, vdpa);
+}
+
+static struct virtio_pci_modern_device *vdpa_to_mdev(struct vdpa_device *vdpa)
+{
+	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
+
+	return &vp_vdpa->mdev;
+}
+
+static u64 vp_vdpa_get_features(struct vdpa_device *vdpa)
+{
+	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
+
+	return vp_modern_get_features(mdev);
+}
+
+static int vp_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
+{
+	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
+
+	vp_modern_set_features(mdev, features);
+
+	return 0;
+}
+
+static u8 vp_vdpa_get_status(struct vdpa_device *vdpa)
+{
+	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
+
+	return vp_modern_get_status(mdev);
+}
+
+static void vp_vdpa_free_irq(struct vp_vdpa *vp_vdpa)
+{
+	struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev;
+	struct pci_dev *pdev = mdev->pci_dev;
+	int i;
+
+	for (i = 0; i < vp_vdpa->queues; i++) {
+		if (vp_vdpa->vring[i].irq != VIRTIO_MSI_NO_VECTOR) {
+			vp_modern_queue_vector(mdev, i, VIRTIO_MSI_NO_VECTOR);
+			devm_free_irq(&pdev->dev, vp_vdpa->vring[i].irq,
+				      &vp_vdpa->vring[i]);
+			vp_vdpa->vring[i].irq = VIRTIO_MSI_NO_VECTOR;
+		}
+	}
+
+	if (vp_vdpa->config_irq != VIRTIO_MSI_NO_VECTOR) {
+		vp_modern_config_vector(mdev, VIRTIO_MSI_NO_VECTOR);
+		devm_free_irq(&pdev->dev, vp_vdpa->config_irq, vp_vdpa);
+		vp_vdpa->config_irq = VIRTIO_MSI_NO_VECTOR;
+	}
+
+	if (vp_vdpa->vectors) {
+		pci_free_irq_vectors(pdev);
+		vp_vdpa->vectors = 0;
+	}
+}
+
+static irqreturn_t vp_vdpa_vq_handler(int irq, void *arg)
+{
+	struct vp_vring *vring = arg;
+
+	if (vring->cb.callback)
+		return vring->cb.callback(vring->cb.private);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t vp_vdpa_config_handler(int irq, void *arg)
+{
+	struct vp_vdpa *vp_vdpa = arg;
+
+	if (vp_vdpa->config_cb.callback)
+		return vp_vdpa->config_cb.callback(vp_vdpa->config_cb.private);
+
+	return IRQ_HANDLED;
+}
+
+static int vp_vdpa_request_irq(struct vp_vdpa *vp_vdpa)
+{
+	struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev;
+	struct pci_dev *pdev = mdev->pci_dev;
+	int i, ret, irq;
+	int queues = vp_vdpa->queues;
+	int vectors = queues + 1;
+
+	ret = pci_alloc_irq_vectors(pdev, vectors, vectors, PCI_IRQ_MSIX);
+	if (ret != vectors) {
+		dev_err(&pdev->dev,
+			"vp_vdpa: fail to allocate irq vectors want %d but %d\n",
+			vectors, ret);
+		return ret;
+	}
+
+	vp_vdpa->vectors = vectors;
+
+	for (i = 0; i < queues; i++) {
+		snprintf(vp_vdpa->vring[i].msix_name, VP_VDPA_NAME_SIZE,
+			"vp-vdpa[%s]-%d\n", pci_name(pdev), i);
+		irq = pci_irq_vector(pdev, i);
+		ret = devm_request_irq(&pdev->dev, irq,
+				       vp_vdpa_vq_handler,
+				       0, vp_vdpa->vring[i].msix_name,
+				       &vp_vdpa->vring[i]);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"vp_vdpa: fail to request irq for vq %d\n", i);
+			goto err;
+		}
+		vp_modern_queue_vector(mdev, i, i);
+		vp_vdpa->vring[i].irq = irq;
+	}
+
+	snprintf(vp_vdpa->msix_name, VP_VDPA_NAME_SIZE, "vp-vdpa[%s]-config\n",
+		 pci_name(pdev));
+	irq = pci_irq_vector(pdev, queues);
+	ret = devm_request_irq(&pdev->dev, irq,	vp_vdpa_config_handler, 0,
+			       vp_vdpa->msix_name, vp_vdpa);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"vp_vdpa: fail to request irq for vq %d\n", i);
+			goto err;
+	}
+	vp_modern_config_vector(mdev, queues);
+	vp_vdpa->config_irq = irq;
+
+	return 0;
+err:
+	vp_vdpa_free_irq(vp_vdpa);
+	return ret;
+}
+
+static void vp_vdpa_set_status(struct vdpa_device *vdpa, u8 status)
+{
+	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
+	struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev;
+	u8 s = vp_vdpa_get_status(vdpa);
+
+	if (status & VIRTIO_CONFIG_S_DRIVER_OK &&
+	    !(s & VIRTIO_CONFIG_S_DRIVER_OK)) {
+		vp_vdpa_request_irq(vp_vdpa);
+	}
+
+	vp_modern_set_status(mdev, status);
+
+	if (!(status & VIRTIO_CONFIG_S_DRIVER_OK) &&
+	    (s & VIRTIO_CONFIG_S_DRIVER_OK))
+		vp_vdpa_free_irq(vp_vdpa);
+}
+
+static u16 vp_vdpa_get_vq_num_max(struct vdpa_device *vdpa)
+{
+	return VP_VDPA_QUEUE_MAX;
+}
+
+static int vp_vdpa_get_vq_state(struct vdpa_device *vdpa, u16 qid,
+				struct vdpa_vq_state *state)
+{
+	/* Note that this is not supported by virtio specification, so
+	 * we return -EOPNOTSUPP here. This means we can't support live
+	 * migration, vhost device start/stop.
+	 */
+	return -EOPNOTSUPP;
+}
+
+static int vp_vdpa_set_vq_state(struct vdpa_device *vdpa, u16 qid,
+				const struct vdpa_vq_state *state)
+{
+	/* Note that this is not supported by virtio specification, so
+	 * we return -ENOPOTSUPP here. This means we can't support live
+	 * migration, vhost device start/stop.
+	 */
+	return -EOPNOTSUPP;
+}
+
+static void vp_vdpa_set_vq_cb(struct vdpa_device *vdpa, u16 qid,
+			      struct vdpa_callback *cb)
+{
+	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
+
+	vp_vdpa->vring[qid].cb = *cb;
+}
+
+static void vp_vdpa_set_vq_ready(struct vdpa_device *vdpa,
+				 u16 qid, bool ready)
+{
+	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
+
+	vp_modern_set_queue_enable(mdev, qid, ready);
+}
+
+static bool vp_vdpa_get_vq_ready(struct vdpa_device *vdpa, u16 qid)
+{
+	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
+
+	return vp_modern_get_queue_enable(mdev, qid);
+}
+
+static void vp_vdpa_set_vq_num(struct vdpa_device *vdpa, u16 qid,
+			       u32 num)
+{
+	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
+
+	vp_modern_set_queue_size(mdev, qid, num);
+}
+
+static int vp_vdpa_set_vq_address(struct vdpa_device *vdpa, u16 qid,
+				  u64 desc_area, u64 driver_area,
+				  u64 device_area)
+{
+	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
+
+	vp_modern_queue_address(mdev, qid, desc_area,
+				driver_area, device_area);
+
+	return 0;
+}
+
+static void vp_vdpa_kick_vq(struct vdpa_device *vdpa, u16 qid)
+{
+	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
+
+	vp_iowrite16(qid, vp_vdpa->vring[qid].notify);
+}
+
+static u32 vp_vdpa_get_generation(struct vdpa_device *vdpa)
+{
+	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
+
+	return vp_modern_generation(mdev);
+}
+
+static u32 vp_vdpa_get_device_id(struct vdpa_device *vdpa)
+{
+	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
+
+	return mdev->id.device;
+}
+
+static u32 vp_vdpa_get_vendor_id(struct vdpa_device *vdpa)
+{
+	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
+
+	return mdev->id.vendor;
+}
+
+static u32 vp_vdpa_get_vq_align(struct vdpa_device *vdpa)
+{
+	return PAGE_SIZE;
+}
+
+static void vp_vdpa_get_config(struct vdpa_device *vdpa,
+			       unsigned int offset,
+			       void *buf, unsigned int len)
+{
+	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
+	struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev;
+	u8 old, new;
+	u8 *p;
+	int i;
+
+	do {
+		old = vp_ioread8(&mdev->common->config_generation);
+		p = buf;
+		for (i = 0; i < len; i++)
+			*p++ = vp_ioread8(mdev->device + offset + i);
+
+		new = vp_ioread8(&mdev->common->config_generation);
+	} while (old != new);
+}
+
+static void vp_vdpa_set_config(struct vdpa_device *vdpa,
+			       unsigned int offset, const void *buf,
+			       unsigned int len)
+{
+	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
+	struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev;
+	const u8 *p = buf;
+	int i;
+
+	for (i = 0; i < len; i++)
+		vp_iowrite8(*p++, mdev->device + offset + i);
+}
+
+static void vp_vdpa_set_config_cb(struct vdpa_device *vdpa,
+				  struct vdpa_callback *cb)
+{
+	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
+
+	vp_vdpa->config_cb = *cb;
+}
+
+static const struct vdpa_config_ops vp_vdpa_ops = {
+	.get_features	= vp_vdpa_get_features,
+	.set_features	= vp_vdpa_set_features,
+	.get_status	= vp_vdpa_get_status,
+	.set_status	= vp_vdpa_set_status,
+	.get_vq_num_max	= vp_vdpa_get_vq_num_max,
+	.get_vq_state	= vp_vdpa_get_vq_state,
+	.set_vq_state	= vp_vdpa_set_vq_state,
+	.set_vq_cb	= vp_vdpa_set_vq_cb,
+	.set_vq_ready	= vp_vdpa_set_vq_ready,
+	.get_vq_ready	= vp_vdpa_get_vq_ready,
+	.set_vq_num	= vp_vdpa_set_vq_num,
+	.set_vq_address	= vp_vdpa_set_vq_address,
+	.kick_vq	= vp_vdpa_kick_vq,
+	.get_generation	= vp_vdpa_get_generation,
+	.get_device_id	= vp_vdpa_get_device_id,
+	.get_vendor_id	= vp_vdpa_get_vendor_id,
+	.get_vq_align	= vp_vdpa_get_vq_align,
+	.get_config	= vp_vdpa_get_config,
+	.set_config	= vp_vdpa_set_config,
+	.set_config_cb  = vp_vdpa_set_config_cb,
+};
+
+static void vp_vdpa_free_irq_vectors(void *data)
+{
+	pci_free_irq_vectors(data);
+}
+
+static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct virtio_pci_modern_device *mdev;
+	struct device *dev = &pdev->dev;
+	struct vp_vdpa *vp_vdpa;
+	u16 notify_off;
+	int ret, i;
+
+	ret = pcim_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	vp_vdpa = vdpa_alloc_device(struct vp_vdpa, vdpa,
+				    dev, &vp_vdpa_ops);
+	if (vp_vdpa == NULL) {
+		dev_err(dev, "vp_vdpa: Failed to allocate vDPA structure\n");
+		return -ENOMEM;
+	}
+
+	mdev = &vp_vdpa->mdev;
+	mdev->pci_dev = pdev;
+
+	if (vp_modern_probe(mdev)) {
+		dev_err(&pdev->dev, "Failed to probe modern PCI device\n");
+		goto err;
+	}
+
+	pci_set_master(pdev);
+	pci_set_drvdata(pdev, vp_vdpa);
+
+	vp_vdpa->vdpa.dma_dev = &pdev->dev;
+	vp_vdpa->queues = vp_modern_get_num_queues(mdev);
+
+	ret = devm_add_action_or_reset(dev, vp_vdpa_free_irq_vectors, pdev);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"Failed for adding devres for freeing irq vectors\n");
+		goto err;
+	}
+
+	vp_vdpa->vring = devm_kcalloc(&pdev->dev, vp_vdpa->queues,
+				      sizeof(*vp_vdpa->vring),
+				      GFP_KERNEL);
+	if (!vp_vdpa->vring) {
+		dev_err(&pdev->dev, "Fail to allocate virtqueues\n");
+		goto err;
+	}
+
+	for (i = 0; i < vp_vdpa->queues; i++) {
+		notify_off = vp_modern_get_queue_notify_off(mdev, i);
+		vp_vdpa->vring[i].irq = VIRTIO_MSI_NO_VECTOR;
+		vp_vdpa->vring[i].notify = mdev->notify_base +
+			notify_off * mdev->notify_offset_multiplier;
+	}
+	vp_vdpa->config_irq = VIRTIO_MSI_NO_VECTOR;
+
+	ret = vdpa_register_device(&vp_vdpa->vdpa, vp_vdpa->queues);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to register to vdpa bus\n");
+		goto err;
+	}
+
+	return 0;
+
+err:
+	put_device(&vp_vdpa->vdpa.dev);
+	return ret;
+}
+
+static void vp_vdpa_remove(struct pci_dev *pdev)
+{
+	struct vp_vdpa *vp_vdpa = pci_get_drvdata(pdev);
+
+	vdpa_unregister_device(&vp_vdpa->vdpa);
+	vp_modern_remove(&vp_vdpa->mdev);
+}
+
+static struct pci_driver vp_vdpa_driver = {
+	.name		= "vp-vdpa",
+	.id_table	= NULL, /* only dynamic ids */
+	.probe		= vp_vdpa_probe,
+	.remove		= vp_vdpa_remove,
+};
+
+module_pci_driver(vp_vdpa_driver);
+
+MODULE_AUTHOR("Jason Wang <jasowang@redhat.com>");
+MODULE_DESCRIPTION("vp-vdpa");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1");
-- 
2.25.1

Re: [PATCH V3 00/19] vDPA driver for virtio-pci device

[Jason Wang]

On 2021/1/4 下午2:54, Jason Wang wrote:
> Hi all:
>
> This series tries to implement a vDPA driver for virtio-pci device
> which will bridge between vDPA bus and virtio-pci device.
>
> This could be used for future feature prototyping and testing.
>
> Please review
>
> Changes since V2:
>
> - tweak config prompt
> - switch from 'cb' to 'config_cb' for vp_vdpa config interrupt
> - use a macro for vp_vdpa msix name length


Hi Michael:

Any comments on this series?

Thanks


>
> Changes since V1:
>
> - don't try to use devres for virtio-pci core
> - tweak the commit log
> - split the patches furtherly to ease the reviewing
>
> Changes since RFC:
>
> - Split common codes from virito-pci and share it with vDPA driver
> - Use dynamic id in order to be less confusing with virtio-pci driver
> - No feature whitelist, supporting any features (mq, config etc)
>
> Thanks
>
> Jason Wang (19):
>    virtio-pci: do not access iomem via struct virtio_pci_device directly
>    virtio-pci: split out modern device
>    virtio-pci-modern: factor out modern device initialization logic
>    virtio-pci-modern: introduce vp_modern_remove()
>    virtio-pci-modern: introduce helper to set config vector
>    virtio-pci-modern: introduce helpers for setting and getting status
>    virtio-pci-modern: introduce helpers for setting and getting features
>    virtio-pci-modern: introduce vp_modern_generation()
>    virtio-pci-modern: introduce vp_modern_set_queue_vector()
>    virtio-pci-modern: introduce vp_modern_queue_address()
>    virtio-pci-modern: introduce helper to set/get queue_enable
>    virtio-pci-modern: introduce helper for setting/geting queue size
>    virtio-pci-modern: introduce helper for getting queue nums
>    virtio-pci-modern: introduce helper to get notification offset
>    virito-pci-modern: rename map_capability() to
>      vp_modern_map_capability()
>    virtio-pci: introduce modern device module
>    vdpa: set the virtqueue num during register
>    virtio_vdpa: don't warn when fail to disable vq
>    vdpa: introduce virtio pci driver
>
>   drivers/vdpa/Kconfig                   |   6 +
>   drivers/vdpa/Makefile                  |   1 +
>   drivers/vdpa/ifcvf/ifcvf_main.c        |   5 +-
>   drivers/vdpa/mlx5/net/mlx5_vnet.c      |   5 +-
>   drivers/vdpa/vdpa.c                    |   8 +-
>   drivers/vdpa/vdpa_sim/vdpa_sim.c       |   4 +-
>   drivers/vdpa/virtio_pci/Makefile       |   2 +
>   drivers/vdpa/virtio_pci/vp_vdpa.c      | 456 +++++++++++++++++++
>   drivers/virtio/Kconfig                 |  10 +-
>   drivers/virtio/Makefile                |   1 +
>   drivers/virtio/virtio_pci_common.h     |  22 +-
>   drivers/virtio/virtio_pci_modern.c     | 506 +++------------------
>   drivers/virtio/virtio_pci_modern_dev.c | 599 +++++++++++++++++++++++++
>   drivers/virtio/virtio_vdpa.c           |   3 +-
>   include/linux/vdpa.h                   |   7 +-
>   include/linux/virtio_pci_modern.h      | 111 +++++
>   16 files changed, 1274 insertions(+), 472 deletions(-)
>   create mode 100644 drivers/vdpa/virtio_pci/Makefile
>   create mode 100644 drivers/vdpa/virtio_pci/vp_vdpa.c
>   create mode 100644 drivers/virtio/virtio_pci_modern_dev.c
>   create mode 100644 include/linux/virtio_pci_modern.h
>

Re: [PATCH V3 18/19] virtio_vdpa: don't warn when fail to disable vq

[Michael S. Tsirkin]

On Mon, Jan 04, 2021 at 02:55:02PM +0800, Jason Wang wrote:
> There's no guarantee that the device can disable a specific virtqueue
> through set_vq_ready(). One example is the modern virtio-pci
> device. So this patch removes the warning.
> 
> Signed-off-by: Jason Wang <jasowang@redhat.com>


Do we need the read as a kind of flush though?

> ---
>  drivers/virtio/virtio_vdpa.c | 3 +--
>  1 file changed, 1 insertion(+), 2 deletions(-)
> 
> diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c
> index 4a9ddb44b2a7..e28acf482e0c 100644
> --- a/drivers/virtio/virtio_vdpa.c
> +++ b/drivers/virtio/virtio_vdpa.c
> @@ -225,9 +225,8 @@ static void virtio_vdpa_del_vq(struct virtqueue *vq)
>  	list_del(&info->node);
>  	spin_unlock_irqrestore(&vd_dev->lock, flags);
>  
> -	/* Select and deactivate the queue */
> +	/* Select and deactivate the queue (best effort) */
>  	ops->set_vq_ready(vdpa, index, 0);
> -	WARN_ON(ops->get_vq_ready(vdpa, index));
>  
>  	vring_del_virtqueue(vq);
>  
> -- 
> 2.25.1

Re: [PATCH V3 17/19] vdpa: set the virtqueue num during register

[Michael S. Tsirkin]

On Mon, Jan 04, 2021 at 02:55:01PM +0800, Jason Wang wrote:
> This patch delay the queue number setting to vDPA device
> registering. This allows us to probe the virtqueue numbers between
> device allocation and registering.
> 
> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
> Signed-off-by: Jason Wang <jasowang@redhat.com>

Conflicts with other patches in the vhost tree.
Can you rebase please?

> ---
>  drivers/vdpa/ifcvf/ifcvf_main.c   | 5 ++---
>  drivers/vdpa/mlx5/net/mlx5_vnet.c | 5 ++---
>  drivers/vdpa/vdpa.c               | 8 ++++----
>  drivers/vdpa/vdpa_sim/vdpa_sim.c  | 4 ++--
>  include/linux/vdpa.h              | 7 +++----
>  5 files changed, 13 insertions(+), 16 deletions(-)
> 
> diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
> index 8b4028556cb6..d65f3221d8ed 100644
> --- a/drivers/vdpa/ifcvf/ifcvf_main.c
> +++ b/drivers/vdpa/ifcvf/ifcvf_main.c
> @@ -438,8 +438,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
>  	}
>  
>  	adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
> -				    dev, &ifc_vdpa_ops,
> -				    IFCVF_MAX_QUEUE_PAIRS * 2);
> +				    dev, &ifc_vdpa_ops);
>  	if (adapter == NULL) {
>  		IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
>  		return -ENOMEM;
> @@ -463,7 +462,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
>  	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++)
>  		vf->vring[i].irq = -EINVAL;
>  
> -	ret = vdpa_register_device(&adapter->vdpa);
> +	ret = vdpa_register_device(&adapter->vdpa, IFCVF_MAX_QUEUE_PAIRS * 2);
>  	if (ret) {
>  		IFCVF_ERR(pdev, "Failed to register ifcvf to vdpa bus");
>  		goto err;
> diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> index f1d54814db97..a1b9260bf04d 100644
> --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
> +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> @@ -1958,8 +1958,7 @@ static int mlx5v_probe(struct auxiliary_device *adev,
>  	max_vqs = MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues);
>  	max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS);
>  
> -	ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops,
> -				 2 * mlx5_vdpa_max_qps(max_vqs));
> +	ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops);
>  	if (IS_ERR(ndev))
>  		return PTR_ERR(ndev);
>  
> @@ -1986,7 +1985,7 @@ static int mlx5v_probe(struct auxiliary_device *adev,
>  	if (err)
>  		goto err_res;
>  
> -	err = vdpa_register_device(&mvdev->vdev);
> +	err = vdpa_register_device(&mvdev->vdev, 2 * mlx5_vdpa_max_qps(max_vqs));
>  	if (err)
>  		goto err_reg;
>  
> diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
> index a69ffc991e13..ba89238f9898 100644
> --- a/drivers/vdpa/vdpa.c
> +++ b/drivers/vdpa/vdpa.c
> @@ -61,7 +61,6 @@ static void vdpa_release_dev(struct device *d)
>   * initialized but before registered.
>   * @parent: the parent device
>   * @config: the bus operations that is supported by this device
> - * @nvqs: number of virtqueues supported by this device
>   * @size: size of the parent structure that contains private data
>   *
>   * Driver should use vdpa_alloc_device() wrapper macro instead of
> @@ -72,7 +71,6 @@ static void vdpa_release_dev(struct device *d)
>   */
>  struct vdpa_device *__vdpa_alloc_device(struct device *parent,
>  					const struct vdpa_config_ops *config,
> -					int nvqs,
>  					size_t size)
>  {
>  	struct vdpa_device *vdev;
> @@ -99,7 +97,6 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
>  	vdev->index = err;
>  	vdev->config = config;
>  	vdev->features_valid = false;
> -	vdev->nvqs = nvqs;
>  
>  	err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index);
>  	if (err)
> @@ -122,11 +119,14 @@ EXPORT_SYMBOL_GPL(__vdpa_alloc_device);
>   * vdpa_register_device - register a vDPA device
>   * Callers must have a succeed call of vdpa_alloc_device() before.
>   * @vdev: the vdpa device to be registered to vDPA bus
> + * @nvqs: number of virtqueues supported by this device
>   *
>   * Returns an error when fail to add to vDPA bus
>   */
> -int vdpa_register_device(struct vdpa_device *vdev)
> +int vdpa_register_device(struct vdpa_device *vdev, int nvqs)
>  {
> +	vdev->nvqs = nvqs;
> +
>  	return device_add(&vdev->dev);
>  }
>  EXPORT_SYMBOL_GPL(vdpa_register_device);
> diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
> index 6a90fdb9cbfc..b129cb4dd013 100644
> --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
> +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
> @@ -357,7 +357,7 @@ static struct vdpasim *vdpasim_create(void)
>  	else
>  		ops = &vdpasim_net_config_ops;
>  
> -	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, VDPASIM_VQ_NUM);
> +	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops);
>  	if (!vdpasim)
>  		goto err_alloc;
>  
> @@ -393,7 +393,7 @@ static struct vdpasim *vdpasim_create(void)
>  	vringh_set_iotlb(&vdpasim->vqs[1].vring, vdpasim->iommu);
>  
>  	vdpasim->vdpa.dma_dev = dev;
> -	ret = vdpa_register_device(&vdpasim->vdpa);
> +	ret = vdpa_register_device(&vdpasim->vdpa, VDPASIM_VQ_NUM);
>  	if (ret)
>  		goto err_iommu;
>  
> diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
> index 30bc7a7223bb..d9e9d17b9083 100644
> --- a/include/linux/vdpa.h
> +++ b/include/linux/vdpa.h
> @@ -244,18 +244,17 @@ struct vdpa_config_ops {
>  
>  struct vdpa_device *__vdpa_alloc_device(struct device *parent,
>  					const struct vdpa_config_ops *config,
> -					int nvqs,
>  					size_t size);
>  
> -#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs)   \
> +#define vdpa_alloc_device(dev_struct, member, parent, config)   \
>  			  container_of(__vdpa_alloc_device( \
> -				       parent, config, nvqs, \
> +				       parent, config, \
>  				       sizeof(dev_struct) + \
>  				       BUILD_BUG_ON_ZERO(offsetof( \
>  				       dev_struct, member))), \
>  				       dev_struct, member)
>  
> -int vdpa_register_device(struct vdpa_device *vdev);
> +int vdpa_register_device(struct vdpa_device *vdev, int nvqs);
>  void vdpa_unregister_device(struct vdpa_device *vdev);
>  
>  /**
> -- 
> 2.25.1

Re: [PATCH V3 16/19] virtio-pci: introduce modern device module

[Michael S. Tsirkin]

On Mon, Jan 04, 2021 at 02:55:00PM +0800, Jason Wang wrote:
> Signed-off-by: Jason Wang <jasowang@redhat.com>

I don't exactly get why we need to split the modern driver out,
and it can confuse people who are used to be seeing virtio-pci.

The vdpa thing so far looks like a development tool, why do
we care that it depends on a bit of extra code?

> ---
>  drivers/virtio/Kconfig                 |  10 +-
>  drivers/virtio/Makefile                |   1 +
>  drivers/virtio/virtio_pci_common.h     |  27 +-
>  drivers/virtio/virtio_pci_modern.c     | 617 -------------------------
>  drivers/virtio/virtio_pci_modern_dev.c | 599 ++++++++++++++++++++++++
>  include/linux/virtio_pci_modern.h      | 111 +++++
>  6 files changed, 721 insertions(+), 644 deletions(-)
>  create mode 100644 drivers/virtio/virtio_pci_modern_dev.c
>  create mode 100644 include/linux/virtio_pci_modern.h
> 
> diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
> index 7b41130d3f35..6b9b81f4b8c2 100644
> --- a/drivers/virtio/Kconfig
> +++ b/drivers/virtio/Kconfig
> @@ -12,6 +12,14 @@ config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
>  	  This option is selected if the architecture may need to enforce
>  	  VIRTIO_F_ACCESS_PLATFORM
>  
> +config VIRTIO_PCI_MODERN
> +	tristate "Modern Virtio PCI Device"
> +	depends on PCI
> +	help
> +	  Modern PCI device implementation. This module implements the
> +	  basic probe and control for devices which are based on modern
> +	  PCI device with possible vendor specific extensions.
> +
>  menuconfig VIRTIO_MENU
>  	bool "Virtio drivers"
>  	default y
> @@ -20,7 +28,7 @@ if VIRTIO_MENU
>  
>  config VIRTIO_PCI
>  	tristate "PCI driver for virtio devices"
> -	depends on PCI
> +	depends on VIRTIO_PCI_MODERN
>  	select VIRTIO
>  	help
>  	  This driver provides support for virtio based paravirtual device
> diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
> index 591e6f72aa54..f097578aaa8f 100644
> --- a/drivers/virtio/Makefile
> +++ b/drivers/virtio/Makefile
> @@ -1,5 +1,6 @@
>  # SPDX-License-Identifier: GPL-2.0
>  obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o
> +obj-$(CONFIG_VIRTIO_PCI_MODERN) += virtio_pci_modern_dev.o
>  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
> diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
> index f35ff5b6b467..beec047a8f8d 100644
> --- a/drivers/virtio/virtio_pci_common.h
> +++ b/drivers/virtio/virtio_pci_common.h
> @@ -25,6 +25,7 @@
>  #include <linux/virtio_config.h>
>  #include <linux/virtio_ring.h>
>  #include <linux/virtio_pci.h>
> +#include <linux/virtio_pci_modern.h>
>  #include <linux/highmem.h>
>  #include <linux/spinlock.h>
>  
> @@ -39,32 +40,6 @@ struct virtio_pci_vq_info {
>  	unsigned msix_vector;
>  };
>  
> -struct virtio_pci_modern_device {
> -	struct pci_dev *pci_dev;
> -
> -	struct virtio_pci_common_cfg __iomem *common;
> -	/* Device-specific data (non-legacy mode)  */
> -	void __iomem *device;
> -	/* Base of vq notifications (non-legacy mode). */
> -	void __iomem *notify_base;
> -	/* Where to read and clear interrupt */
> -	u8 __iomem *isr;
> -
> -	/* So we can sanity-check accesses. */
> -	size_t notify_len;
> -	size_t device_len;
> -
> -	/* Capability for when we need to map notifications per-vq. */
> -	int notify_map_cap;
> -
> -	/* Multiply queue_notify_off by this value. (non-legacy mode). */
> -	u32 notify_offset_multiplier;
> -
> -	int modern_bars;
> -
> -	struct virtio_device_id id;
> -};
> -
>  /* Our device structure */
>  struct virtio_pci_device {
>  	struct virtio_device vdev;
> diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
> index a5e3a5e40323..fbd4ebc00eb6 100644
> --- a/drivers/virtio/virtio_pci_modern.c
> +++ b/drivers/virtio/virtio_pci_modern.c
> @@ -19,158 +19,6 @@
>  #define VIRTIO_RING_NO_LEGACY
>  #include "virtio_pci_common.h"
>  
> -/*
> - * Type-safe wrappers for io accesses.
> - * Use these to enforce at compile time the following spec requirement:
> - *
> - * The driver MUST access each field using the “natural” access
> - * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses
> - * for 16-bit fields and 8-bit accesses for 8-bit fields.
> - */
> -static inline u8 vp_ioread8(const u8 __iomem *addr)
> -{
> -	return ioread8(addr);
> -}
> -static inline u16 vp_ioread16 (const __le16 __iomem *addr)
> -{
> -	return ioread16(addr);
> -}
> -
> -static inline u32 vp_ioread32(const __le32 __iomem *addr)
> -{
> -	return ioread32(addr);
> -}
> -
> -static inline void vp_iowrite8(u8 value, u8 __iomem *addr)
> -{
> -	iowrite8(value, addr);
> -}
> -
> -static inline void vp_iowrite16(u16 value, __le16 __iomem *addr)
> -{
> -	iowrite16(value, addr);
> -}
> -
> -static inline void vp_iowrite32(u32 value, __le32 __iomem *addr)
> -{
> -	iowrite32(value, addr);
> -}
> -
> -static void vp_iowrite64_twopart(u64 val,
> -				 __le32 __iomem *lo, __le32 __iomem *hi)
> -{
> -	vp_iowrite32((u32)val, lo);
> -	vp_iowrite32(val >> 32, hi);
> -}
> -
> -/*
> - * vp_modern_map_capability - map a part of virtio pci capability
> - * @mdev: the modern virtio-pci device
> - * @off: offset of the capability
> - * @minlen: minimal length of the capability
> - * @align: align requirement
> - * @start: start from the capability
> - * @size: map size
> - * @len: the length that is actually mapped
> - *
> - * Returns the io address of for the part of the capability
> - */
> -void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off,
> -				       size_t minlen,
> -				       u32 align,
> -				       u32 start, u32 size,
> -				       size_t *len)
> -{
> -	struct pci_dev *dev = mdev->pci_dev;
> -	u8 bar;
> -	u32 offset, length;
> -	void __iomem *p;
> -
> -	pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap,
> -						 bar),
> -			     &bar);
> -	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset),
> -			     &offset);
> -	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length),
> -			      &length);
> -
> -	if (length <= start) {
> -		dev_err(&dev->dev,
> -			"virtio_pci: bad capability len %u (>%u expected)\n",
> -			length, start);
> -		return NULL;
> -	}
> -
> -	if (length - start < minlen) {
> -		dev_err(&dev->dev,
> -			"virtio_pci: bad capability len %u (>=%zu expected)\n",
> -			length, minlen);
> -		return NULL;
> -	}
> -
> -	length -= start;
> -
> -	if (start + offset < offset) {
> -		dev_err(&dev->dev,
> -			"virtio_pci: map wrap-around %u+%u\n",
> -			start, offset);
> -		return NULL;
> -	}
> -
> -	offset += start;
> -
> -	if (offset & (align - 1)) {
> -		dev_err(&dev->dev,
> -			"virtio_pci: offset %u not aligned to %u\n",
> -			offset, align);
> -		return NULL;
> -	}
> -
> -	if (length > size)
> -		length = size;
> -
> -	if (len)
> -		*len = length;
> -
> -	if (minlen + offset < minlen ||
> -	    minlen + offset > pci_resource_len(dev, bar)) {
> -		dev_err(&dev->dev,
> -			"virtio_pci: map virtio %zu@%u "
> -			"out of range on bar %i length %lu\n",
> -			minlen, offset,
> -			bar, (unsigned long)pci_resource_len(dev, bar));
> -		return NULL;
> -	}
> -
> -	p = pci_iomap_range(dev, bar, offset, length);
> -	if (!p)
> -		dev_err(&dev->dev,
> -			"virtio_pci: unable to map virtio %u@%u on bar %i\n",
> -			length, offset, bar);
> -	return p;
> -}
> -
> -/*
> - * vp_modern_get_features - get features from device
> - * @mdev: the modern virtio-pci device
> - *
> - * Returns the features read from the device
> - */
> -static u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	u64 features;
> -
> -	vp_iowrite32(0, &cfg->device_feature_select);
> -	features = vp_ioread32(&cfg->device_feature);
> -	vp_iowrite32(1, &cfg->device_feature_select);
> -	features |= ((u64)vp_ioread32(&cfg->device_feature) << 32);
> -
> -	return features;
> -}
> -
> -/* virtio config->get_features() implementation */
>  static u64 vp_get_features(struct virtio_device *vdev)
>  {
>  	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
> @@ -188,149 +36,6 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features)
>  		__virtio_set_bit(vdev, VIRTIO_F_SR_IOV);
>  }
>  
> -/*
> - * vp_modern_set_features - set features to device
> - * @mdev: the modern virtio-pci device
> - * @features: the features set to device
> - */
> -static void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
> -				   u64 features)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	vp_iowrite32(0, &cfg->guest_feature_select);
> -	vp_iowrite32((u32)features, &cfg->guest_feature);
> -	vp_iowrite32(1, &cfg->guest_feature_select);
> -	vp_iowrite32(features >> 32, &cfg->guest_feature);
> -}
> -
> -/*
> - * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue
> - * @mdev: the modern virtio-pci device
> - * @index: queue index
> - * @vector: the config vector
> - *
> - * Returns the config vector read from the device
> - */
> -static u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
> -				  u16 index, u16 vector)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	vp_iowrite16(index, &cfg->queue_select);
> -	vp_iowrite16(vector, &cfg->queue_msix_vector);
> -	/* Flush the write out to device */
> -	return vp_ioread16(&cfg->queue_msix_vector);
> -}
> -
> -/*
> - * vp_modern_queue_address - set the virtqueue address
> - * @mdev: the modern virtio-pci device
> - * @index: the queue index
> - * @desc_addr: address of the descriptor area
> - * @driver_addr: address of the driver area
> - * @device_addr: address of the device area
> - */
> -static void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
> -				    u16 index, u64 desc_addr, u64 driver_addr,
> -				    u64 device_addr)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	vp_iowrite16(index, &cfg->queue_select);
> -
> -	vp_iowrite64_twopart(desc_addr, &cfg->queue_desc_lo,
> -			     &cfg->queue_desc_hi);
> -	vp_iowrite64_twopart(driver_addr, &cfg->queue_avail_lo,
> -			     &cfg->queue_avail_hi);
> -	vp_iowrite64_twopart(device_addr, &cfg->queue_used_lo,
> -			     &cfg->queue_used_hi);
> -}
> -
> -/*
> - * vp_modern_set_queue_enable - enable a virtqueue
> - * @mdev: the modern virtio-pci device
> - * @index: the queue index
> - * @enable: whether the virtqueue is enable or not
> - */
> -static void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev,
> -				       u16 index, bool enable)
> -{
> -	vp_iowrite16(index, &mdev->common->queue_select);
> -	vp_iowrite16(enable, &mdev->common->queue_enable);
> -}
> -
> -/*
> - * vp_modern_get_queue_enable - enable a virtqueue
> - * @mdev: the modern virtio-pci device
> - * @index: the queue index
> - *
> - * Returns whether a virtqueue is enabled or not
> - */
> -static bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
> -				       u16 index)
> -{
> -	vp_iowrite16(index, &mdev->common->queue_select);
> -
> -	return vp_ioread16(&mdev->common->queue_enable);
> -}
> -
> -/*
> - * vp_modern_set_queue_size - set size for a virtqueue
> - * @mdev: the modern virtio-pci device
> - * @index: the queue index
> - * @size: the size of the virtqueue
> - */
> -static void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev,
> -				     u16 index, u16 size)
> -{
> -	vp_iowrite16(index, &mdev->common->queue_select);
> -	vp_iowrite16(size, &mdev->common->queue_size);
> -
> -}
> -
> -/*
> - * vp_modern_get_queue_size - get size for a virtqueue
> - * @mdev: the modern virtio-pci device
> - * @index: the queue index
> - *
> - * Returns the size of the virtqueue
> - */
> -static u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
> -				    u16 index)
> -{
> -	vp_iowrite16(index, &mdev->common->queue_select);
> -
> -	return vp_ioread16(&mdev->common->queue_size);
> -
> -}
> -
> -/*
> - * vp_modern_get_num_queues - get the number of virtqueues
> - * @mdev: the modern virtio-pci device
> - *
> - * Returns the number of virtqueues
> - */
> -static u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev)
> -{
> -	return vp_ioread16(&mdev->common->num_queues);
> -}
> -
> -/*
> - * vp_modern_get_queue_notify_off - get notification offset for a virtqueue
> - * @mdev: the modern virtio-pci device
> - * @index: the queue index
> - *
> - * Returns the notification offset for a virtqueue
> - */
> -static u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev,
> -					  u16 index)
> -{
> -	vp_iowrite16(index, &mdev->common->queue_select);
> -
> -	return vp_ioread16(&mdev->common->queue_notify_off);
> -}
> -
>  /* virtio config->finalize_features() implementation */
>  static int vp_finalize_features(struct virtio_device *vdev)
>  {
> @@ -429,19 +134,6 @@ static void vp_set(struct virtio_device *vdev, unsigned offset,
>  	}
>  }
>  
> -/*
> - * vp_modern_generation - get the device genreation
> - * @mdev: the modern virtio-pci device
> - *
> - * Returns the genreation read from device
> - */
> -static u32 vp_modern_generation(struct virtio_pci_modern_device *mdev)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	return vp_ioread8(&cfg->config_generation);
> -}
> -
>  static u32 vp_generation(struct virtio_device *vdev)
>  {
>  	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
> @@ -449,19 +141,6 @@ static u32 vp_generation(struct virtio_device *vdev)
>  	return vp_modern_generation(&vp_dev->mdev);
>  }
>  
> -/*
> - * vp_modern_get_status - get the device status
> - * @mdev: the modern virtio-pci device
> - *
> - * Returns the status read from device
> - */
> -static u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	return vp_ioread8(&cfg->device_status);
> -}
> -
>  /* config->{get,set}_status() implementations */
>  static u8 vp_get_status(struct virtio_device *vdev)
>  {
> @@ -470,19 +149,6 @@ static u8 vp_get_status(struct virtio_device *vdev)
>  	return vp_modern_get_status(&vp_dev->mdev);
>  }
>  
> -/*
> - * vp_modern_set_status - set status to device
> - * @mdev: the modern virtio-pci device
> - * @status: the status set to device
> - */
> -static void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
> -				 u8 status)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	vp_iowrite8(status, &cfg->device_status);
> -}
> -
>  static void vp_set_status(struct virtio_device *vdev, u8 status)
>  {
>  	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
> @@ -510,25 +176,6 @@ static void vp_reset(struct virtio_device *vdev)
>  	vp_synchronize_vectors(vdev);
>  }
>  
> -/*
> - * vp_modern_config_vector - set the vector for config interrupt
> - * @mdev: the modern virtio-pci device
> - * @vector: the config vector
> - *
> - * Returns the config vector read from the device
> - */
> -static u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev,
> -				   u16 vector)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	/* Setup the vector used for configuration events */
> -	vp_iowrite16(vector, &cfg->msix_config);
> -	/* Verify we had enough resources to assign the vector */
> -	/* Will also flush the write out to device */
> -	return vp_ioread16(&cfg->msix_config);
> -}
> -
>  static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
>  {
>  	return vp_modern_config_vector(&vp_dev->mdev, vector);
> @@ -789,253 +436,6 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
>  	.get_shm_region  = vp_get_shm_region,
>  };
>  
> -/**
> - * virtio_pci_find_capability - walk capabilities to find device info.
> - * @dev: the pci device
> - * @cfg_type: the VIRTIO_PCI_CAP_* value we seek
> - * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
> - * @bars: the bitmask of BARs
> - *
> - * Returns offset of the capability, or 0.
> - */
> -static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
> -					     u32 ioresource_types, int *bars)
> -{
> -	int pos;
> -
> -	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
> -	     pos > 0;
> -	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
> -		u8 type, bar;
> -		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
> -							 cfg_type),
> -				     &type);
> -		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
> -							 bar),
> -				     &bar);
> -
> -		/* Ignore structures with reserved BAR values */
> -		if (bar > 0x5)
> -			continue;
> -
> -		if (type == cfg_type) {
> -			if (pci_resource_len(dev, bar) &&
> -			    pci_resource_flags(dev, bar) & ioresource_types) {
> -				*bars |= (1 << bar);
> -				return pos;
> -			}
> -		}
> -	}
> -	return 0;
> -}
> -
> -/* This is part of the ABI.  Don't screw with it. */
> -static inline void check_offsets(void)
> -{
> -	/* Note: disk space was harmed in compilation of this function. */
> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR !=
> -		     offsetof(struct virtio_pci_cap, cap_vndr));
> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT !=
> -		     offsetof(struct virtio_pci_cap, cap_next));
> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN !=
> -		     offsetof(struct virtio_pci_cap, cap_len));
> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE !=
> -		     offsetof(struct virtio_pci_cap, cfg_type));
> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR !=
> -		     offsetof(struct virtio_pci_cap, bar));
> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET !=
> -		     offsetof(struct virtio_pci_cap, offset));
> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH !=
> -		     offsetof(struct virtio_pci_cap, length));
> -	BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT !=
> -		     offsetof(struct virtio_pci_notify_cap,
> -			      notify_off_multiplier));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT !=
> -		     offsetof(struct virtio_pci_common_cfg,
> -			      device_feature_select));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF !=
> -		     offsetof(struct virtio_pci_common_cfg, device_feature));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT !=
> -		     offsetof(struct virtio_pci_common_cfg,
> -			      guest_feature_select));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF !=
> -		     offsetof(struct virtio_pci_common_cfg, guest_feature));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX !=
> -		     offsetof(struct virtio_pci_common_cfg, msix_config));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ !=
> -		     offsetof(struct virtio_pci_common_cfg, num_queues));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS !=
> -		     offsetof(struct virtio_pci_common_cfg, device_status));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION !=
> -		     offsetof(struct virtio_pci_common_cfg, config_generation));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_select));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_size));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_msix_vector));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_enable));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_notify_off));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_desc_lo));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_desc_hi));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_avail_lo));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_avail_hi));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_used_lo));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_used_hi));
> -}
> -
> -/*
> - * vp_modern_probe: probe the modern virtio pci device, note that the
> - * caller is required to enable PCI device before calling this function.
> - * @mdev: the modern virtio-pci device
> - *
> - * Return 0 on succeed otherwise fail
> - */
> -static int vp_modern_probe(struct virtio_pci_modern_device *mdev)
> -{
> -	struct pci_dev *pci_dev = mdev->pci_dev;
> -	int err, common, isr, notify, device;
> -	u32 notify_length;
> -	u32 notify_offset;
> -
> -	check_offsets();
> -
> -	mdev->pci_dev = pci_dev;
> -
> -	/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
> -	if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
> -		return -ENODEV;
> -
> -	if (pci_dev->device < 0x1040) {
> -		/* Transitional devices: use the PCI subsystem device id as
> -		 * virtio device id, same as legacy driver always did.
> -		 */
> -		mdev->id.device = pci_dev->subsystem_device;
> -	} else {
> -		/* Modern devices: simply use PCI device id, but start from 0x1040. */
> -		mdev->id.device = pci_dev->device - 0x1040;
> -	}
> -	mdev->id.vendor = pci_dev->subsystem_vendor;
> -
> -	/* check for a common config: if not, use legacy mode (bar 0). */
> -	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
> -					    IORESOURCE_IO | IORESOURCE_MEM,
> -					    &mdev->modern_bars);
> -	if (!common) {
> -		dev_info(&pci_dev->dev,
> -			 "virtio_pci: leaving for legacy driver\n");
> -		return -ENODEV;
> -	}
> -
> -	/* If common is there, these should be too... */
> -	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
> -					 IORESOURCE_IO | IORESOURCE_MEM,
> -					 &mdev->modern_bars);
> -	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
> -					    IORESOURCE_IO | IORESOURCE_MEM,
> -					    &mdev->modern_bars);
> -	if (!isr || !notify) {
> -		dev_err(&pci_dev->dev,
> -			"virtio_pci: missing capabilities %i/%i/%i\n",
> -			common, isr, notify);
> -		return -EINVAL;
> -	}
> -
> -	err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
> -	if (err)
> -		err = dma_set_mask_and_coherent(&pci_dev->dev,
> -						DMA_BIT_MASK(32));
> -	if (err)
> -		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
> -
> -	/* Device capability is only mandatory for devices that have
> -	 * device-specific configuration.
> -	 */
> -	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
> -					    IORESOURCE_IO | IORESOURCE_MEM,
> -					    &mdev->modern_bars);
> -
> -	err = pci_request_selected_regions(pci_dev, mdev->modern_bars,
> -					   "virtio-pci-modern");
> -	if (err)
> -		return err;
> -
> -	err = -EINVAL;
> -	mdev->common = vp_modern_map_capability(mdev, common,
> -				      sizeof(struct virtio_pci_common_cfg), 4,
> -				      0, sizeof(struct virtio_pci_common_cfg),
> -				      NULL);
> -	if (!mdev->common)
> -		goto err_map_common;
> -	mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1,
> -					     0, 1,
> -					     NULL);
> -	if (!mdev->isr)
> -		goto err_map_isr;
> -
> -	/* Read notify_off_multiplier from config space. */
> -	pci_read_config_dword(pci_dev,
> -			      notify + offsetof(struct virtio_pci_notify_cap,
> -						notify_off_multiplier),
> -			      &mdev->notify_offset_multiplier);
> -	/* Read notify length and offset from config space. */
> -	pci_read_config_dword(pci_dev,
> -			      notify + offsetof(struct virtio_pci_notify_cap,
> -						cap.length),
> -			      &notify_length);
> -
> -	pci_read_config_dword(pci_dev,
> -			      notify + offsetof(struct virtio_pci_notify_cap,
> -						cap.offset),
> -			      &notify_offset);
> -
> -	/* We don't know how many VQs we'll map, ahead of the time.
> -	 * If notify length is small, map it all now.
> -	 * Otherwise, map each VQ individually later.
> -	 */
> -	if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) {
> -		mdev->notify_base = vp_modern_map_capability(mdev, notify,
> -							     2, 2,
> -							     0, notify_length,
> -							     &mdev->notify_len);
> -		if (!mdev->notify_base)
> -			goto err_map_notify;
> -	} else {
> -		mdev->notify_map_cap = notify;
> -	}
> -
> -	/* Again, we don't know how much we should map, but PAGE_SIZE
> -	 * is more than enough for all existing devices.
> -	 */
> -	if (device) {
> -		mdev->device = vp_modern_map_capability(mdev, device, 0, 4,
> -							0, PAGE_SIZE,
> -							&mdev->device_len);
> -		if (!mdev->device)
> -			goto err_map_device;
> -	}
> -
> -	return 0;
> -
> -err_map_device:
> -	if (mdev->notify_base)
> -		pci_iounmap(pci_dev, mdev->notify_base);
> -err_map_notify:
> -	pci_iounmap(pci_dev, mdev->isr);
> -err_map_isr:
> -	pci_iounmap(pci_dev, mdev->common);
> -err_map_common:
> -	return err;
> -}
> -
>  /* the PCI probing function */
>  int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
>  {
> @@ -1063,23 +463,6 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
>  	return 0;
>  }
>  
> -/*
> - * vp_modern_probe: remove and cleanup the modern virtio pci device
> - * @mdev: the modern virtio-pci device
> - */
> -static void vp_modern_remove(struct virtio_pci_modern_device *mdev)
> -{
> -	struct pci_dev *pci_dev = mdev->pci_dev;
> -
> -	if (mdev->device)
> -		pci_iounmap(pci_dev, mdev->device);
> -	if (mdev->notify_base)
> -		pci_iounmap(pci_dev, mdev->notify_base);
> -	pci_iounmap(pci_dev, mdev->isr);
> -	pci_iounmap(pci_dev, mdev->common);
> -	pci_release_selected_regions(pci_dev, mdev->modern_bars);
> -}
> -
>  void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
>  {
>  	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
> diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
> new file mode 100644
> index 000000000000..cbd667496bb1
> --- /dev/null
> +++ b/drivers/virtio/virtio_pci_modern_dev.c
> @@ -0,0 +1,599 @@
> +// SPDX-License-Identifier: GPL-2.0-or-later
> +
> +#include <linux/virtio_pci_modern.h>
> +#include <linux/module.h>
> +#include <linux/pci.h>
> +
> +/*
> + * vp_modern_map_capability - map a part of virtio pci capability
> + * @mdev: the modern virtio-pci device
> + * @off: offset of the capability
> + * @minlen: minimal length of the capability
> + * @align: align requirement
> + * @start: start from the capability
> + * @size: map size
> + * @len: the length that is actually mapped
> + *
> + * Returns the io address of for the part of the capability
> + */
> +void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off,
> +				       size_t minlen,
> +				       u32 align,
> +				       u32 start, u32 size,
> +				       size_t *len)
> +{
> +	struct pci_dev *dev = mdev->pci_dev;
> +	u8 bar;
> +	u32 offset, length;
> +	void __iomem *p;
> +
> +	pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap,
> +						 bar),
> +			     &bar);
> +	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset),
> +			     &offset);
> +	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length),
> +			      &length);
> +
> +	if (length <= start) {
> +		dev_err(&dev->dev,
> +			"virtio_pci: bad capability len %u (>%u expected)\n",
> +			length, start);
> +		return NULL;
> +	}
> +
> +	if (length - start < minlen) {
> +		dev_err(&dev->dev,
> +			"virtio_pci: bad capability len %u (>=%zu expected)\n",
> +			length, minlen);
> +		return NULL;
> +	}
> +
> +	length -= start;
> +
> +	if (start + offset < offset) {
> +		dev_err(&dev->dev,
> +			"virtio_pci: map wrap-around %u+%u\n",
> +			start, offset);
> +		return NULL;
> +	}
> +
> +	offset += start;
> +
> +	if (offset & (align - 1)) {
> +		dev_err(&dev->dev,
> +			"virtio_pci: offset %u not aligned to %u\n",
> +			offset, align);
> +		return NULL;
> +	}
> +
> +	if (length > size)
> +		length = size;
> +
> +	if (len)
> +		*len = length;
> +
> +	if (minlen + offset < minlen ||
> +	    minlen + offset > pci_resource_len(dev, bar)) {
> +		dev_err(&dev->dev,
> +			"virtio_pci: map virtio %zu@%u "
> +			"out of range on bar %i length %lu\n",
> +			minlen, offset,
> +			bar, (unsigned long)pci_resource_len(dev, bar));
> +		return NULL;
> +	}
> +
> +	p = pci_iomap_range(dev, bar, offset, length);
> +	if (!p)
> +		dev_err(&dev->dev,
> +			"virtio_pci: unable to map virtio %u@%u on bar %i\n",
> +			length, offset, bar);
> +	return p;
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_map_capability);
> +
> +/**
> + * virtio_pci_find_capability - walk capabilities to find device info.
> + * @dev: the pci device
> + * @cfg_type: the VIRTIO_PCI_CAP_* value we seek
> + * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
> + * @bars: the bitmask of BARs
> + *
> + * Returns offset of the capability, or 0.
> + */
> +static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
> +					     u32 ioresource_types, int *bars)
> +{
> +	int pos;
> +
> +	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
> +	     pos > 0;
> +	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
> +		u8 type, bar;
> +		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
> +							 cfg_type),
> +				     &type);
> +		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
> +							 bar),
> +				     &bar);
> +
> +		/* Ignore structures with reserved BAR values */
> +		if (bar > 0x5)
> +			continue;
> +
> +		if (type == cfg_type) {
> +			if (pci_resource_len(dev, bar) &&
> +			    pci_resource_flags(dev, bar) & ioresource_types) {
> +				*bars |= (1 << bar);
> +				return pos;
> +			}
> +		}
> +	}
> +	return 0;
> +}
> +
> +/* This is part of the ABI.  Don't screw with it. */
> +static inline void check_offsets(void)
> +{
> +	/* Note: disk space was harmed in compilation of this function. */
> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR !=
> +		     offsetof(struct virtio_pci_cap, cap_vndr));
> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT !=
> +		     offsetof(struct virtio_pci_cap, cap_next));
> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN !=
> +		     offsetof(struct virtio_pci_cap, cap_len));
> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE !=
> +		     offsetof(struct virtio_pci_cap, cfg_type));
> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR !=
> +		     offsetof(struct virtio_pci_cap, bar));
> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET !=
> +		     offsetof(struct virtio_pci_cap, offset));
> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH !=
> +		     offsetof(struct virtio_pci_cap, length));
> +	BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT !=
> +		     offsetof(struct virtio_pci_notify_cap,
> +			      notify_off_multiplier));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT !=
> +		     offsetof(struct virtio_pci_common_cfg,
> +			      device_feature_select));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF !=
> +		     offsetof(struct virtio_pci_common_cfg, device_feature));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT !=
> +		     offsetof(struct virtio_pci_common_cfg,
> +			      guest_feature_select));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF !=
> +		     offsetof(struct virtio_pci_common_cfg, guest_feature));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX !=
> +		     offsetof(struct virtio_pci_common_cfg, msix_config));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ !=
> +		     offsetof(struct virtio_pci_common_cfg, num_queues));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS !=
> +		     offsetof(struct virtio_pci_common_cfg, device_status));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION !=
> +		     offsetof(struct virtio_pci_common_cfg, config_generation));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_select));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_size));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_msix_vector));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_enable));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_notify_off));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_desc_lo));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_desc_hi));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_avail_lo));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_avail_hi));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_used_lo));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_used_hi));
> +}
> +
> +/*
> + * vp_modern_probe: probe the modern virtio pci device, note that the
> + * caller is required to enable PCI device before calling this function.
> + * @mdev: the modern virtio-pci device
> + *
> + * Return 0 on succeed otherwise fail
> + */
> +int vp_modern_probe(struct virtio_pci_modern_device *mdev)
> +{
> +	struct pci_dev *pci_dev = mdev->pci_dev;
> +	int err, common, isr, notify, device;
> +	u32 notify_length;
> +	u32 notify_offset;
> +
> +	check_offsets();
> +
> +	mdev->pci_dev = pci_dev;
> +
> +	/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
> +	if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
> +		return -ENODEV;
> +
> +	if (pci_dev->device < 0x1040) {
> +		/* Transitional devices: use the PCI subsystem device id as
> +		 * virtio device id, same as legacy driver always did.
> +		 */
> +		mdev->id.device = pci_dev->subsystem_device;
> +	} else {
> +		/* Modern devices: simply use PCI device id, but start from 0x1040. */
> +		mdev->id.device = pci_dev->device - 0x1040;
> +	}
> +	mdev->id.vendor = pci_dev->subsystem_vendor;
> +
> +	/* check for a common config: if not, use legacy mode (bar 0). */
> +	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
> +					    IORESOURCE_IO | IORESOURCE_MEM,
> +					    &mdev->modern_bars);
> +	if (!common) {
> +		dev_info(&pci_dev->dev,
> +			 "virtio_pci: leaving for legacy driver\n");
> +		return -ENODEV;
> +	}
> +
> +	/* If common is there, these should be too... */
> +	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
> +					 IORESOURCE_IO | IORESOURCE_MEM,
> +					 &mdev->modern_bars);
> +	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
> +					    IORESOURCE_IO | IORESOURCE_MEM,
> +					    &mdev->modern_bars);
> +	if (!isr || !notify) {
> +		dev_err(&pci_dev->dev,
> +			"virtio_pci: missing capabilities %i/%i/%i\n",
> +			common, isr, notify);
> +		return -EINVAL;
> +	}
> +
> +	err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
> +	if (err)
> +		err = dma_set_mask_and_coherent(&pci_dev->dev,
> +						DMA_BIT_MASK(32));
> +	if (err)
> +		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
> +
> +	/* Device capability is only mandatory for devices that have
> +	 * device-specific configuration.
> +	 */
> +	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
> +					    IORESOURCE_IO | IORESOURCE_MEM,
> +					    &mdev->modern_bars);
> +
> +	err = pci_request_selected_regions(pci_dev, mdev->modern_bars,
> +					   "virtio-pci-modern");
> +	if (err)
> +		return err;
> +
> +	err = -EINVAL;
> +	mdev->common = vp_modern_map_capability(mdev, common,
> +				      sizeof(struct virtio_pci_common_cfg), 4,
> +				      0, sizeof(struct virtio_pci_common_cfg),
> +				      NULL);
> +	if (!mdev->common)
> +		goto err_map_common;
> +	mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1,
> +					     0, 1,
> +					     NULL);
> +	if (!mdev->isr)
> +		goto err_map_isr;
> +
> +	/* Read notify_off_multiplier from config space. */
> +	pci_read_config_dword(pci_dev,
> +			      notify + offsetof(struct virtio_pci_notify_cap,
> +						notify_off_multiplier),
> +			      &mdev->notify_offset_multiplier);
> +	/* Read notify length and offset from config space. */
> +	pci_read_config_dword(pci_dev,
> +			      notify + offsetof(struct virtio_pci_notify_cap,
> +						cap.length),
> +			      &notify_length);
> +
> +	pci_read_config_dword(pci_dev,
> +			      notify + offsetof(struct virtio_pci_notify_cap,
> +						cap.offset),
> +			      &notify_offset);
> +
> +	/* We don't know how many VQs we'll map, ahead of the time.
> +	 * If notify length is small, map it all now.
> +	 * Otherwise, map each VQ individually later.
> +	 */
> +	if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) {
> +		mdev->notify_base = vp_modern_map_capability(mdev, notify,
> +							     2, 2,
> +							     0, notify_length,
> +							     &mdev->notify_len);
> +		if (!mdev->notify_base)
> +			goto err_map_notify;
> +	} else {
> +		mdev->notify_map_cap = notify;
> +	}
> +
> +	/* Again, we don't know how much we should map, but PAGE_SIZE
> +	 * is more than enough for all existing devices.
> +	 */
> +	if (device) {
> +		mdev->device = vp_modern_map_capability(mdev, device, 0, 4,
> +							0, PAGE_SIZE,
> +							&mdev->device_len);
> +		if (!mdev->device)
> +			goto err_map_device;
> +	}
> +
> +	return 0;
> +
> +err_map_device:
> +	if (mdev->notify_base)
> +		pci_iounmap(pci_dev, mdev->notify_base);
> +err_map_notify:
> +	pci_iounmap(pci_dev, mdev->isr);
> +err_map_isr:
> +	pci_iounmap(pci_dev, mdev->common);
> +err_map_common:
> +	return err;
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_probe);
> +
> +/*
> + * vp_modern_probe: remove and cleanup the modern virtio pci device
> + * @mdev: the modern virtio-pci device
> + */
> +void vp_modern_remove(struct virtio_pci_modern_device *mdev)
> +{
> +	struct pci_dev *pci_dev = mdev->pci_dev;
> +
> +	if (mdev->device)
> +		pci_iounmap(pci_dev, mdev->device);
> +	if (mdev->notify_base)
> +		pci_iounmap(pci_dev, mdev->notify_base);
> +	pci_iounmap(pci_dev, mdev->isr);
> +	pci_iounmap(pci_dev, mdev->common);
> +	pci_release_selected_regions(pci_dev, mdev->modern_bars);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_remove);
> +
> +/*
> + * vp_modern_get_features - get features from device
> + * @mdev: the modern virtio-pci device
> + *
> + * Returns the features read from the device
> + */
> +u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	u64 features;
> +
> +	vp_iowrite32(0, &cfg->device_feature_select);
> +	features = vp_ioread32(&cfg->device_feature);
> +	vp_iowrite32(1, &cfg->device_feature_select);
> +	features |= ((u64)vp_ioread32(&cfg->device_feature) << 32);
> +
> +	return features;
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_get_features);
> +
> +/*
> + * vp_modern_set_features - set features to device
> + * @mdev: the modern virtio-pci device
> + * @features: the features set to device
> + */
> +void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
> +			    u64 features)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	vp_iowrite32(0, &cfg->guest_feature_select);
> +	vp_iowrite32((u32)features, &cfg->guest_feature);
> +	vp_iowrite32(1, &cfg->guest_feature_select);
> +	vp_iowrite32(features >> 32, &cfg->guest_feature);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_set_features);
> +
> +/*
> + * vp_modern_generation - get the device genreation
> + * @mdev: the modern virtio-pci device
> + *
> + * Returns the genreation read from device
> + */
> +u32 vp_modern_generation(struct virtio_pci_modern_device *mdev)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	return vp_ioread8(&cfg->config_generation);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_generation);
> +
> +/*
> + * vp_modern_get_status - get the device status
> + * @mdev: the modern virtio-pci device
> + *
> + * Returns the status read from device
> + */
> +u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	return vp_ioread8(&cfg->device_status);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_get_status);
> +
> +/*
> + * vp_modern_set_status - set status to device
> + * @mdev: the modern virtio-pci device
> + * @status: the status set to device
> + */
> +void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
> +				 u8 status)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	vp_iowrite8(status, &cfg->device_status);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_set_status);
> +
> +/*
> + * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue
> + * @mdev: the modern virtio-pci device
> + * @index: queue index
> + * @vector: the config vector
> + *
> + * Returns the config vector read from the device
> + */
> +u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
> +			   u16 index, u16 vector)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	vp_iowrite16(index, &cfg->queue_select);
> +	vp_iowrite16(vector, &cfg->queue_msix_vector);
> +	/* Flush the write out to device */
> +	return vp_ioread16(&cfg->queue_msix_vector);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_queue_vector);
> +
> +/*
> + * vp_modern_config_vector - set the vector for config interrupt
> + * @mdev: the modern virtio-pci device
> + * @vector: the config vector
> + *
> + * Returns the config vector read from the device
> + */
> +u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev,
> +			    u16 vector)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	/* Setup the vector used for configuration events */
> +	vp_iowrite16(vector, &cfg->msix_config);
> +	/* Verify we had enough resources to assign the vector */
> +	/* Will also flush the write out to device */
> +	return vp_ioread16(&cfg->msix_config);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_config_vector);
> +
> +/*
> + * vp_modern_queue_address - set the virtqueue address
> + * @mdev: the modern virtio-pci device
> + * @index: the queue index
> + * @desc_addr: address of the descriptor area
> + * @driver_addr: address of the driver area
> + * @device_addr: address of the device area
> + */
> +void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
> +			     u16 index, u64 desc_addr, u64 driver_addr,
> +			     u64 device_addr)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	vp_iowrite16(index, &cfg->queue_select);
> +
> +	vp_iowrite64_twopart(desc_addr, &cfg->queue_desc_lo,
> +			     &cfg->queue_desc_hi);
> +	vp_iowrite64_twopart(driver_addr, &cfg->queue_avail_lo,
> +			     &cfg->queue_avail_hi);
> +	vp_iowrite64_twopart(device_addr, &cfg->queue_used_lo,
> +			     &cfg->queue_used_hi);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_queue_address);
> +
> +/*
> + * vp_modern_set_queue_enable - enable a virtqueue
> + * @mdev: the modern virtio-pci device
> + * @index: the queue index
> + * @enable: whether the virtqueue is enable or not
> + */
> +void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev,
> +				u16 index, bool enable)
> +{
> +	vp_iowrite16(index, &mdev->common->queue_select);
> +	vp_iowrite16(enable, &mdev->common->queue_enable);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_set_queue_enable);
> +
> +/*
> + * vp_modern_get_queue_enable - enable a virtqueue
> + * @mdev: the modern virtio-pci device
> + * @index: the queue index
> + *
> + * Returns whether a virtqueue is enabled or not
> + */
> +bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
> +				u16 index)
> +{
> +	vp_iowrite16(index, &mdev->common->queue_select);
> +
> +	return vp_ioread16(&mdev->common->queue_enable);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_get_queue_enable);
> +
> +/*
> + * vp_modern_set_queue_size - set size for a virtqueue
> + * @mdev: the modern virtio-pci device
> + * @index: the queue index
> + * @size: the size of the virtqueue
> + */
> +void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev,
> +			      u16 index, u16 size)
> +{
> +	vp_iowrite16(index, &mdev->common->queue_select);
> +	vp_iowrite16(size, &mdev->common->queue_size);
> +
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_set_queue_size);
> +
> +/*
> + * vp_modern_get_queue_size - get size for a virtqueue
> + * @mdev: the modern virtio-pci device
> + * @index: the queue index
> + *
> + * Returns the size of the virtqueue
> + */
> +u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
> +			     u16 index)
> +{
> +	vp_iowrite16(index, &mdev->common->queue_select);
> +
> +	return vp_ioread16(&mdev->common->queue_size);
> +
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_get_queue_size);
> +
> +/*
> + * vp_modern_get_num_queues - get the number of virtqueues
> + * @mdev: the modern virtio-pci device
> + *
> + * Returns the number of virtqueues
> + */
> +u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev)
> +{
> +	return vp_ioread16(&mdev->common->num_queues);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_get_num_queues);
> +
> +/*
> + * vp_modern_get_queue_notify_off - get notification offset for a virtqueue
> + * @mdev: the modern virtio-pci device
> + * @index: the queue index
> + *
> + * Returns the notification offset for a virtqueue
> + */
> +u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev,
> +				   u16 index)
> +{
> +	vp_iowrite16(index, &mdev->common->queue_select);
> +
> +	return vp_ioread16(&mdev->common->queue_notify_off);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_get_queue_notify_off);
> +
> +MODULE_VERSION("0.1");
> +MODULE_DESCRIPTION("Modern Virtio PCI Device");
> +MODULE_AUTHOR("Jason Wang <jasowang@redhat.com>");
> +MODULE_LICENSE("GPL");
> diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h
> new file mode 100644
> index 000000000000..f26acbeec965
> --- /dev/null
> +++ b/include/linux/virtio_pci_modern.h
> @@ -0,0 +1,111 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef _LINUX_VIRTIO_PCI_MODERN_H
> +#define _LINUX_VIRTIO_PCI_MODERN_H
> +
> +#include <linux/pci.h>
> +#include <linux/virtio_pci.h>
> +
> +struct virtio_pci_modern_device {
> +	struct pci_dev *pci_dev;
> +
> +	struct virtio_pci_common_cfg __iomem *common;
> +	/* Device-specific data (non-legacy mode)  */
> +	void __iomem *device;
> +	/* Base of vq notifications (non-legacy mode). */
> +	void __iomem *notify_base;
> +	/* Where to read and clear interrupt */
> +	u8 __iomem *isr;
> +
> +	/* So we can sanity-check accesses. */
> +	size_t notify_len;
> +	size_t device_len;
> +
> +	/* Capability for when we need to map notifications per-vq. */
> +	int notify_map_cap;
> +
> +	/* Multiply queue_notify_off by this value. (non-legacy mode). */
> +	u32 notify_offset_multiplier;
> +
> +	int modern_bars;
> +
> +	struct virtio_device_id id;
> +};
> +
> +/*
> + * Type-safe wrappers for io accesses.
> + * Use these to enforce at compile time the following spec requirement:
> + *
> + * The driver MUST access each field using the “natural” access
> + * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses
> + * for 16-bit fields and 8-bit accesses for 8-bit fields.
> + */
> +static inline u8 vp_ioread8(const u8 __iomem *addr)
> +{
> +	return ioread8(addr);
> +}
> +static inline u16 vp_ioread16 (const __le16 __iomem *addr)
> +{
> +	return ioread16(addr);
> +}
> +
> +static inline u32 vp_ioread32(const __le32 __iomem *addr)
> +{
> +	return ioread32(addr);
> +}
> +
> +static inline void vp_iowrite8(u8 value, u8 __iomem *addr)
> +{
> +	iowrite8(value, addr);
> +}
> +
> +static inline void vp_iowrite16(u16 value, __le16 __iomem *addr)
> +{
> +	iowrite16(value, addr);
> +}
> +
> +static inline void vp_iowrite32(u32 value, __le32 __iomem *addr)
> +{
> +	iowrite32(value, addr);
> +}
> +
> +static inline void vp_iowrite64_twopart(u64 val,
> +					__le32 __iomem *lo,
> +					__le32 __iomem *hi)
> +{
> +	vp_iowrite32((u32)val, lo);
> +	vp_iowrite32(val >> 32, hi);
> +}
> +
> +u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev);
> +void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
> +		     u64 features);
> +u32 vp_modern_generation(struct virtio_pci_modern_device *mdev);
> +u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev);
> +void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
> +		   u8 status);
> +u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
> +			   u16 idx, u16 vector);
> +u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev,
> +		     u16 vector);
> +void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
> +			     u16 index, u64 desc_addr, u64 driver_addr,
> +			     u64 device_addr);
> +void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev,
> +				u16 idx, bool enable);
> +bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
> +				u16 idx);
> +void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev,
> +			      u16 idx, u16 size);
> +u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
> +			     u16 idx);
> +u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev);
> +u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev,
> +				   u16 idx);
> +void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off,
> +				       size_t minlen,
> +				       u32 align,
> +				       u32 start, u32 size,
> +				       size_t *len);
> +int vp_modern_probe(struct virtio_pci_modern_device *mdev);
> +void vp_modern_remove(struct virtio_pci_modern_device *mdev);
> +#endif
> -- 
> 2.25.1

Re: [PATCH V3 18/19] virtio_vdpa: don't warn when fail to disable vq

[Jason Wang]

On 2021/2/5 下午11:24, Michael S. Tsirkin wrote:
> On Mon, Jan 04, 2021 at 02:55:02PM +0800, Jason Wang wrote:
>> There's no guarantee that the device can disable a specific virtqueue
>> through set_vq_ready(). One example is the modern virtio-pci
>> device. So this patch removes the warning.
>>
>> Signed-off-by: Jason Wang <jasowang@redhat.com>
>
> Do we need the read as a kind of flush though?


The problem is that PCI forbids write 0 to queue_enable. So I'm not sure 
what kind of flush do we need here?

Thanks


>
>> ---
>>   drivers/virtio/virtio_vdpa.c | 3 +--
>>   1 file changed, 1 insertion(+), 2 deletions(-)
>>
>> diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c
>> index 4a9ddb44b2a7..e28acf482e0c 100644
>> --- a/drivers/virtio/virtio_vdpa.c
>> +++ b/drivers/virtio/virtio_vdpa.c
>> @@ -225,9 +225,8 @@ static void virtio_vdpa_del_vq(struct virtqueue *vq)
>>   	list_del(&info->node);
>>   	spin_unlock_irqrestore(&vd_dev->lock, flags);
>>   
>> -	/* Select and deactivate the queue */
>> +	/* Select and deactivate the queue (best effort) */
>>   	ops->set_vq_ready(vdpa, index, 0);
>> -	WARN_ON(ops->get_vq_ready(vdpa, index));
>>   
>>   	vring_del_virtqueue(vq);
>>   
>> -- 
>> 2.25.1

Re: [PATCH V3 17/19] vdpa: set the virtqueue num during register

[Jason Wang]

On 2021/2/5 下午11:27, Michael S. Tsirkin wrote:
> On Mon, Jan 04, 2021 at 02:55:01PM +0800, Jason Wang wrote:
>> This patch delay the queue number setting to vDPA device
>> registering. This allows us to probe the virtqueue numbers between
>> device allocation and registering.
>>
>> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
>> Signed-off-by: Jason Wang <jasowang@redhat.com>
> Conflicts with other patches in the vhost tree.
> Can you rebase please?


Will do.

Thanks


>
>> ---
>>   drivers/vdpa/ifcvf/ifcvf_main.c   | 5 ++---
>>   drivers/vdpa/mlx5/net/mlx5_vnet.c | 5 ++---
>>   drivers/vdpa/vdpa.c               | 8 ++++----
>>   drivers/vdpa/vdpa_sim/vdpa_sim.c  | 4 ++--
>>   include/linux/vdpa.h              | 7 +++----
>>   5 files changed, 13 insertions(+), 16 deletions(-)
>>
>> diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
>> index 8b4028556cb6..d65f3221d8ed 100644
>> --- a/drivers/vdpa/ifcvf/ifcvf_main.c
>> +++ b/drivers/vdpa/ifcvf/ifcvf_main.c
>> @@ -438,8 +438,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
>>   	}
>>   
>>   	adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
>> -				    dev, &ifc_vdpa_ops,
>> -				    IFCVF_MAX_QUEUE_PAIRS * 2);
>> +				    dev, &ifc_vdpa_ops);
>>   	if (adapter == NULL) {
>>   		IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
>>   		return -ENOMEM;
>> @@ -463,7 +462,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
>>   	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++)
>>   		vf->vring[i].irq = -EINVAL;
>>   
>> -	ret = vdpa_register_device(&adapter->vdpa);
>> +	ret = vdpa_register_device(&adapter->vdpa, IFCVF_MAX_QUEUE_PAIRS * 2);
>>   	if (ret) {
>>   		IFCVF_ERR(pdev, "Failed to register ifcvf to vdpa bus");
>>   		goto err;
>> diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
>> index f1d54814db97..a1b9260bf04d 100644
>> --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
>> +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
>> @@ -1958,8 +1958,7 @@ static int mlx5v_probe(struct auxiliary_device *adev,
>>   	max_vqs = MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues);
>>   	max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS);
>>   
>> -	ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops,
>> -				 2 * mlx5_vdpa_max_qps(max_vqs));
>> +	ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops);
>>   	if (IS_ERR(ndev))
>>   		return PTR_ERR(ndev);
>>   
>> @@ -1986,7 +1985,7 @@ static int mlx5v_probe(struct auxiliary_device *adev,
>>   	if (err)
>>   		goto err_res;
>>   
>> -	err = vdpa_register_device(&mvdev->vdev);
>> +	err = vdpa_register_device(&mvdev->vdev, 2 * mlx5_vdpa_max_qps(max_vqs));
>>   	if (err)
>>   		goto err_reg;
>>   
>> diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
>> index a69ffc991e13..ba89238f9898 100644
>> --- a/drivers/vdpa/vdpa.c
>> +++ b/drivers/vdpa/vdpa.c
>> @@ -61,7 +61,6 @@ static void vdpa_release_dev(struct device *d)
>>    * initialized but before registered.
>>    * @parent: the parent device
>>    * @config: the bus operations that is supported by this device
>> - * @nvqs: number of virtqueues supported by this device
>>    * @size: size of the parent structure that contains private data
>>    *
>>    * Driver should use vdpa_alloc_device() wrapper macro instead of
>> @@ -72,7 +71,6 @@ static void vdpa_release_dev(struct device *d)
>>    */
>>   struct vdpa_device *__vdpa_alloc_device(struct device *parent,
>>   					const struct vdpa_config_ops *config,
>> -					int nvqs,
>>   					size_t size)
>>   {
>>   	struct vdpa_device *vdev;
>> @@ -99,7 +97,6 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
>>   	vdev->index = err;
>>   	vdev->config = config;
>>   	vdev->features_valid = false;
>> -	vdev->nvqs = nvqs;
>>   
>>   	err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index);
>>   	if (err)
>> @@ -122,11 +119,14 @@ EXPORT_SYMBOL_GPL(__vdpa_alloc_device);
>>    * vdpa_register_device - register a vDPA device
>>    * Callers must have a succeed call of vdpa_alloc_device() before.
>>    * @vdev: the vdpa device to be registered to vDPA bus
>> + * @nvqs: number of virtqueues supported by this device
>>    *
>>    * Returns an error when fail to add to vDPA bus
>>    */
>> -int vdpa_register_device(struct vdpa_device *vdev)
>> +int vdpa_register_device(struct vdpa_device *vdev, int nvqs)
>>   {
>> +	vdev->nvqs = nvqs;
>> +
>>   	return device_add(&vdev->dev);
>>   }
>>   EXPORT_SYMBOL_GPL(vdpa_register_device);
>> diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
>> index 6a90fdb9cbfc..b129cb4dd013 100644
>> --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
>> +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
>> @@ -357,7 +357,7 @@ static struct vdpasim *vdpasim_create(void)
>>   	else
>>   		ops = &vdpasim_net_config_ops;
>>   
>> -	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, VDPASIM_VQ_NUM);
>> +	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops);
>>   	if (!vdpasim)
>>   		goto err_alloc;
>>   
>> @@ -393,7 +393,7 @@ static struct vdpasim *vdpasim_create(void)
>>   	vringh_set_iotlb(&vdpasim->vqs[1].vring, vdpasim->iommu);
>>   
>>   	vdpasim->vdpa.dma_dev = dev;
>> -	ret = vdpa_register_device(&vdpasim->vdpa);
>> +	ret = vdpa_register_device(&vdpasim->vdpa, VDPASIM_VQ_NUM);
>>   	if (ret)
>>   		goto err_iommu;
>>   
>> diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
>> index 30bc7a7223bb..d9e9d17b9083 100644
>> --- a/include/linux/vdpa.h
>> +++ b/include/linux/vdpa.h
>> @@ -244,18 +244,17 @@ struct vdpa_config_ops {
>>   
>>   struct vdpa_device *__vdpa_alloc_device(struct device *parent,
>>   					const struct vdpa_config_ops *config,
>> -					int nvqs,
>>   					size_t size);
>>   
>> -#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs)   \
>> +#define vdpa_alloc_device(dev_struct, member, parent, config)   \
>>   			  container_of(__vdpa_alloc_device( \
>> -				       parent, config, nvqs, \
>> +				       parent, config, \
>>   				       sizeof(dev_struct) + \
>>   				       BUILD_BUG_ON_ZERO(offsetof( \
>>   				       dev_struct, member))), \
>>   				       dev_struct, member)
>>   
>> -int vdpa_register_device(struct vdpa_device *vdev);
>> +int vdpa_register_device(struct vdpa_device *vdev, int nvqs);
>>   void vdpa_unregister_device(struct vdpa_device *vdev);
>>   
>>   /**
>> -- 
>> 2.25.1

Re: [PATCH V3 16/19] virtio-pci: introduce modern device module

[Jason Wang]

On 2021/2/5 下午11:34, Michael S. Tsirkin wrote:
> On Mon, Jan 04, 2021 at 02:55:00PM +0800, Jason Wang wrote:
>> Signed-off-by: Jason Wang<jasowang@redhat.com>
> I don't exactly get why we need to split the modern driver out,
> and it can confuse people who are used to be seeing virtio-pci.


The virtio-pci module still there. No user visible changes. Just some 
codes that could be shared with other driver were split out.


>
> The vdpa thing so far looks like a development tool, why do
> we care that it depends on a bit of extra code?


If I'm not misunderstanding, trying to share codes is proposed by you here:

https://lkml.org/lkml/2020/6/10/232

We also had the plan to convert IFCVF to use this library.

Thanks

>

Re: [PATCH V3 16/19] virtio-pci: introduce modern device module

[Michael S. Tsirkin]

On Mon, Feb 08, 2021 at 01:42:27PM +0800, Jason Wang wrote:
> 
> On 2021/2/5 下午11:34, Michael S. Tsirkin wrote:
> > On Mon, Jan 04, 2021 at 02:55:00PM +0800, Jason Wang wrote:
> > > Signed-off-by: Jason Wang<jasowang@redhat.com>
> > I don't exactly get why we need to split the modern driver out,
> > and it can confuse people who are used to be seeing virtio-pci.
> 
> 
> The virtio-pci module still there. No user visible changes. Just some codes
> that could be shared with other driver were split out.
> 

What I am saying is this: we can have virtio-vdpa depend on
virtio-pci without splitting the common code out to an
extra module.

> > 
> > The vdpa thing so far looks like a development tool, why do
> > we care that it depends on a bit of extra code?
> 
> 
> If I'm not misunderstanding, trying to share codes is proposed by you here:
> 
> https://lkml.org/lkml/2020/6/10/232
> 
> We also had the plan to convert IFCVF to use this library.
> 
> Thanks

If that happens then an extra module might become useful.

-- 
MST

Re: [PATCH V3 16/19] virtio-pci: introduce modern device module

[Jason Wang]

On 2021/2/8 下午8:04, Michael S. Tsirkin wrote:
> On Mon, Feb 08, 2021 at 01:42:27PM +0800, Jason Wang wrote:
>> On 2021/2/5 下午11:34, Michael S. Tsirkin wrote:
>>> On Mon, Jan 04, 2021 at 02:55:00PM +0800, Jason Wang wrote:
>>>> Signed-off-by: Jason Wang<jasowang@redhat.com>
>>> I don't exactly get why we need to split the modern driver out,
>>> and it can confuse people who are used to be seeing virtio-pci.
>>
>> The virtio-pci module still there. No user visible changes. Just some codes
>> that could be shared with other driver were split out.
>>
> What I am saying is this: we can have virtio-vdpa depend on
> virtio-pci without splitting the common code out to an
> extra module.


Ok.


>
>>> The vdpa thing so far looks like a development tool, why do
>>> we care that it depends on a bit of extra code?
>>
>> If I'm not misunderstanding, trying to share codes is proposed by you here:
>>
>> https://lkml.org/lkml/2020/6/10/232
>>
>> We also had the plan to convert IFCVF to use this library.
>>
>> Thanks
> If that happens then an extra module might become useful.


So does it make sense that I post a new version and let's merge it 
first. Then Intel or I can convert IFCVF to use the library?

Thanks


>

Re: [PATCH V3 16/19] virtio-pci: introduce modern device module

[Michael S. Tsirkin]

On Tue, Feb 09, 2021 at 11:29:46AM +0800, Jason Wang wrote:
> 
> On 2021/2/8 下午8:04, Michael S. Tsirkin wrote:
> > On Mon, Feb 08, 2021 at 01:42:27PM +0800, Jason Wang wrote:
> > > On 2021/2/5 下午11:34, Michael S. Tsirkin wrote:
> > > > On Mon, Jan 04, 2021 at 02:55:00PM +0800, Jason Wang wrote:
> > > > > Signed-off-by: Jason Wang<jasowang@redhat.com>
> > > > I don't exactly get why we need to split the modern driver out,
> > > > and it can confuse people who are used to be seeing virtio-pci.
> > > 
> > > The virtio-pci module still there. No user visible changes. Just some codes
> > > that could be shared with other driver were split out.
> > > 
> > What I am saying is this: we can have virtio-vdpa depend on
> > virtio-pci without splitting the common code out to an
> > extra module.
> 
> 
> Ok.
> 
> 
> > 
> > > > The vdpa thing so far looks like a development tool, why do
> > > > we care that it depends on a bit of extra code?
> > > 
> > > If I'm not misunderstanding, trying to share codes is proposed by you here:
> > > 
> > > https://lkml.org/lkml/2020/6/10/232
> > > 
> > > We also had the plan to convert IFCVF to use this library.
> > > 
> > > Thanks
> > If that happens then an extra module might become useful.
> 
> 
> So does it make sense that I post a new version and let's merge it first.
> Then Intel or I can convert IFCVF to use the library?
> 
> Thanks

Generally it's best if we actually have a couple of users before we bother
with refactoring - it's hard to predict the future,
so we don't really know what kind of refactoring will work for IFCVF ...

> 
> > 

Re: [PATCH V3 16/19] virtio-pci: introduce modern device module

[Naresh Kamboju]

Hi Jason,

On Mon, 4 Jan 2021 at 12:28, Jason Wang <jasowang@redhat.com> wrote:
>
> Signed-off-by: Jason Wang <jasowang@redhat.com>
> ---
>  drivers/virtio/Kconfig                 |  10 +-
>  drivers/virtio/Makefile                |   1 +
>  drivers/virtio/virtio_pci_common.h     |  27 +-
>  drivers/virtio/virtio_pci_modern.c     | 617 -------------------------
>  drivers/virtio/virtio_pci_modern_dev.c | 599 ++++++++++++++++++++++++
>  include/linux/virtio_pci_modern.h      | 111 +++++
>  6 files changed, 721 insertions(+), 644 deletions(-)
>  create mode 100644 drivers/virtio/virtio_pci_modern_dev.c
>  create mode 100644 include/linux/virtio_pci_modern.h
>
> diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
> index 7b41130d3f35..6b9b81f4b8c2 100644
> --- a/drivers/virtio/Kconfig
> +++ b/drivers/virtio/Kconfig
> @@ -12,6 +12,14 @@ config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
>           This option is selected if the architecture may need to enforce
>           VIRTIO_F_ACCESS_PLATFORM
>
> +config VIRTIO_PCI_MODERN
> +       tristate "Modern Virtio PCI Device"
> +       depends on PCI
> +       help
> +         Modern PCI device implementation. This module implements the
> +         basic probe and control for devices which are based on modern
> +         PCI device with possible vendor specific extensions.
> +
>  menuconfig VIRTIO_MENU
>         bool "Virtio drivers"
>         default y
> @@ -20,7 +28,7 @@ if VIRTIO_MENU
>
>  config VIRTIO_PCI
>         tristate "PCI driver for virtio devices"
> -       depends on PCI
> +       depends on VIRTIO_PCI_MODERN

While booting Linux next tag 20210208 kernel on qemu_arm64 and qemu_arm
mount rootfs failed.  The root cause seems to be due to missing configs
CONFIG_VIRTIO_PCI=y
CONFIG_VIRTIO_PCI_LEGACY=y

Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>

Then I have to force to enable this MODERN config
CONFIG_VIRTIO_PCI_MODERN=y
and which enabled
CONFIG_VIRTIO_PCI=y
CONFIG_VIRTIO_PCI_LEGACY=y

and the qemu_arm64 and qemu_arm boot pass.


New build link,
https://builds.tuxbuild.com/1oEse4EFsoQr1FkKBfiLmhMCe7j/


-- 
Linaro LKFT
https://lkft.linaro.org

Re: [PATCH V3 16/19] virtio-pci: introduce modern device module

[Michael S. Tsirkin]

On Mon, Jan 04, 2021 at 02:55:00PM +0800, Jason Wang wrote:
> Signed-off-by: Jason Wang <jasowang@redhat.com>
> ---
>  drivers/virtio/Kconfig                 |  10 +-
>  drivers/virtio/Makefile                |   1 +
>  drivers/virtio/virtio_pci_common.h     |  27 +-
>  drivers/virtio/virtio_pci_modern.c     | 617 -------------------------
>  drivers/virtio/virtio_pci_modern_dev.c | 599 ++++++++++++++++++++++++
>  include/linux/virtio_pci_modern.h      | 111 +++++
>  6 files changed, 721 insertions(+), 644 deletions(-)
>  create mode 100644 drivers/virtio/virtio_pci_modern_dev.c
>  create mode 100644 include/linux/virtio_pci_modern.h
> 
> diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
> index 7b41130d3f35..6b9b81f4b8c2 100644
> --- a/drivers/virtio/Kconfig
> +++ b/drivers/virtio/Kconfig
> @@ -12,6 +12,14 @@ config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
>  	  This option is selected if the architecture may need to enforce
>  	  VIRTIO_F_ACCESS_PLATFORM
>  
> +config VIRTIO_PCI_MODERN
> +	tristate "Modern Virtio PCI Device"
> +	depends on PCI
> +	help
> +	  Modern PCI device implementation. This module implements the
> +	  basic probe and control for devices which are based on modern
> +	  PCI device with possible vendor specific extensions.
> +
>  menuconfig VIRTIO_MENU
>  	bool "Virtio drivers"
>  	default y
> @@ -20,7 +28,7 @@ if VIRTIO_MENU
>  
>  config VIRTIO_PCI
>  	tristate "PCI driver for virtio devices"
> -	depends on PCI
> +	depends on VIRTIO_PCI_MODERN
>  	select VIRTIO
>  	help
>  	  This driver provides support for virtio based paravirtual device

Looks like VIRTIO_PCI_MODERN is actually just a library that
virtio pci uses. Is that right? In that case just select it
automatically, let's not make users enable it manually.

-- 
MST

Re: [PATCH V3 16/19] virtio-pci: introduce modern device module

[Jason Wang]

On 2021/2/9 下午6:15, Naresh Kamboju wrote:
> Hi Jason,
>
> On Mon, 4 Jan 2021 at 12:28, Jason Wang <jasowang@redhat.com> wrote:
>> Signed-off-by: Jason Wang <jasowang@redhat.com>
>> ---
>>   drivers/virtio/Kconfig                 |  10 +-
>>   drivers/virtio/Makefile                |   1 +
>>   drivers/virtio/virtio_pci_common.h     |  27 +-
>>   drivers/virtio/virtio_pci_modern.c     | 617 -------------------------
>>   drivers/virtio/virtio_pci_modern_dev.c | 599 ++++++++++++++++++++++++
>>   include/linux/virtio_pci_modern.h      | 111 +++++
>>   6 files changed, 721 insertions(+), 644 deletions(-)
>>   create mode 100644 drivers/virtio/virtio_pci_modern_dev.c
>>   create mode 100644 include/linux/virtio_pci_modern.h
>>
>> diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
>> index 7b41130d3f35..6b9b81f4b8c2 100644
>> --- a/drivers/virtio/Kconfig
>> +++ b/drivers/virtio/Kconfig
>> @@ -12,6 +12,14 @@ config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
>>            This option is selected if the architecture may need to enforce
>>            VIRTIO_F_ACCESS_PLATFORM
>>
>> +config VIRTIO_PCI_MODERN
>> +       tristate "Modern Virtio PCI Device"
>> +       depends on PCI
>> +       help
>> +         Modern PCI device implementation. This module implements the
>> +         basic probe and control for devices which are based on modern
>> +         PCI device with possible vendor specific extensions.
>> +
>>   menuconfig VIRTIO_MENU
>>          bool "Virtio drivers"
>>          default y
>> @@ -20,7 +28,7 @@ if VIRTIO_MENU
>>
>>   config VIRTIO_PCI
>>          tristate "PCI driver for virtio devices"
>> -       depends on PCI
>> +       depends on VIRTIO_PCI_MODERN
> While booting Linux next tag 20210208 kernel on qemu_arm64 and qemu_arm
> mount rootfs failed.  The root cause seems to be due to missing configs
> CONFIG_VIRTIO_PCI=y
> CONFIG_VIRTIO_PCI_LEGACY=y
>
> Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
>
> Then I have to force to enable this MODERN config
> CONFIG_VIRTIO_PCI_MODERN=y
> and which enabled
> CONFIG_VIRTIO_PCI=y
> CONFIG_VIRTIO_PCI_LEGACY=y
>
> and the qemu_arm64 and qemu_arm boot pass.
>
>
> New build link,
> https://builds.tuxbuild.com/1oEse4EFsoQr1FkKBfiLmhMCe7j/


Thanks for the reporting.

I will post a patch to fix the def config to enable VIRTIO_PCI_MODERN.

Thanks


>
>

Re: [PATCH V3 16/19] virtio-pci: introduce modern device module

[Jason Wang]

On 2021/2/9 下午10:20, Michael S. Tsirkin wrote:
> On Mon, Jan 04, 2021 at 02:55:00PM +0800, Jason Wang wrote:
>> Signed-off-by: Jason Wang <jasowang@redhat.com>
>> ---
>>   drivers/virtio/Kconfig                 |  10 +-
>>   drivers/virtio/Makefile                |   1 +
>>   drivers/virtio/virtio_pci_common.h     |  27 +-
>>   drivers/virtio/virtio_pci_modern.c     | 617 -------------------------
>>   drivers/virtio/virtio_pci_modern_dev.c | 599 ++++++++++++++++++++++++
>>   include/linux/virtio_pci_modern.h      | 111 +++++
>>   6 files changed, 721 insertions(+), 644 deletions(-)
>>   create mode 100644 drivers/virtio/virtio_pci_modern_dev.c
>>   create mode 100644 include/linux/virtio_pci_modern.h
>>
>> diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
>> index 7b41130d3f35..6b9b81f4b8c2 100644
>> --- a/drivers/virtio/Kconfig
>> +++ b/drivers/virtio/Kconfig
>> @@ -12,6 +12,14 @@ config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
>>   	  This option is selected if the architecture may need to enforce
>>   	  VIRTIO_F_ACCESS_PLATFORM
>>   
>> +config VIRTIO_PCI_MODERN
>> +	tristate "Modern Virtio PCI Device"
>> +	depends on PCI
>> +	help
>> +	  Modern PCI device implementation. This module implements the
>> +	  basic probe and control for devices which are based on modern
>> +	  PCI device with possible vendor specific extensions.
>> +
>>   menuconfig VIRTIO_MENU
>>   	bool "Virtio drivers"
>>   	default y
>> @@ -20,7 +28,7 @@ if VIRTIO_MENU
>>   
>>   config VIRTIO_PCI
>>   	tristate "PCI driver for virtio devices"
>> -	depends on PCI
>> +	depends on VIRTIO_PCI_MODERN
>>   	select VIRTIO
>>   	help
>>   	  This driver provides support for virtio based paravirtual device
> Looks like VIRTIO_PCI_MODERN is actually just a library that
> virtio pci uses. Is that right?


Right.


> In that case just select it
> automatically, let's not make users enable it manually.


I've considered to do this but the problem is that the module depends on 
PCI so it can't be selected I think.

Thanks


>

Re: [PATCH V3 16/19] virtio-pci: introduce modern device module

[Michael S. Tsirkin]

On Wed, Feb 10, 2021 at 12:44:03PM +0800, Jason Wang wrote:
> 
> On 2021/2/9 下午10:20, Michael S. Tsirkin wrote:
> > On Mon, Jan 04, 2021 at 02:55:00PM +0800, Jason Wang wrote:
> > > Signed-off-by: Jason Wang <jasowang@redhat.com>
> > > ---
> > >   drivers/virtio/Kconfig                 |  10 +-
> > >   drivers/virtio/Makefile                |   1 +
> > >   drivers/virtio/virtio_pci_common.h     |  27 +-
> > >   drivers/virtio/virtio_pci_modern.c     | 617 -------------------------
> > >   drivers/virtio/virtio_pci_modern_dev.c | 599 ++++++++++++++++++++++++
> > >   include/linux/virtio_pci_modern.h      | 111 +++++
> > >   6 files changed, 721 insertions(+), 644 deletions(-)
> > >   create mode 100644 drivers/virtio/virtio_pci_modern_dev.c
> > >   create mode 100644 include/linux/virtio_pci_modern.h
> > > 
> > > diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
> > > index 7b41130d3f35..6b9b81f4b8c2 100644
> > > --- a/drivers/virtio/Kconfig
> > > +++ b/drivers/virtio/Kconfig
> > > @@ -12,6 +12,14 @@ config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
> > >   	  This option is selected if the architecture may need to enforce
> > >   	  VIRTIO_F_ACCESS_PLATFORM
> > > +config VIRTIO_PCI_MODERN
> > > +	tristate "Modern Virtio PCI Device"
> > > +	depends on PCI
> > > +	help
> > > +	  Modern PCI device implementation. This module implements the
> > > +	  basic probe and control for devices which are based on modern
> > > +	  PCI device with possible vendor specific extensions.
> > > +
> > >   menuconfig VIRTIO_MENU
> > >   	bool "Virtio drivers"
> > >   	default y
> > > @@ -20,7 +28,7 @@ if VIRTIO_MENU
> > >   config VIRTIO_PCI
> > >   	tristate "PCI driver for virtio devices"
> > > -	depends on PCI
> > > +	depends on VIRTIO_PCI_MODERN
> > >   	select VIRTIO
> > >   	help
> > >   	  This driver provides support for virtio based paravirtual device
> > Looks like VIRTIO_PCI_MODERN is actually just a library that
> > virtio pci uses. Is that right?
> 
> 
> Right.
> 
> 
> > In that case just select it
> > automatically, let's not make users enable it manually.
> 
> 
> I've considered to do this but the problem is that the module depends on PCI
> so it can't be selected I think.

Drop the dependency, document that whoever selects it must depend on PCI.

> Thanks
> 
> 
> > 

Re: [PATCH V3 16/19] virtio-pci: introduce modern device module

[Guenter Roeck]

On Mon, Jan 04, 2021 at 02:55:00PM +0800, Jason Wang wrote:
> Signed-off-by: Jason Wang <jasowang@redhat.com>
> Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>

I don't really see the point of having to enable VIRTIO_PCI_MODERN
because otherwise VIRTIO_PCI no longer works. If VIRTIO_PCI now
requires VIRTIO_PCI_MODERN, maybe it should select it instead of
depending on it ? Alternatively, you could just drop the new
configuration flag entirely and build virtio_pci_modern_dev.o with
VIRTIO_PCI. One doesn't work without the other anyway, after all.

Guenter

> ---
>  drivers/virtio/Kconfig                 |  10 +-
>  drivers/virtio/Makefile                |   1 +
>  drivers/virtio/virtio_pci_common.h     |  27 +-
>  drivers/virtio/virtio_pci_modern.c     | 617 -------------------------
>  drivers/virtio/virtio_pci_modern_dev.c | 599 ++++++++++++++++++++++++
>  include/linux/virtio_pci_modern.h      | 111 +++++
>  6 files changed, 721 insertions(+), 644 deletions(-)
>  create mode 100644 drivers/virtio/virtio_pci_modern_dev.c
>  create mode 100644 include/linux/virtio_pci_modern.h
> 
> diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
> index 7b41130d3f35..6b9b81f4b8c2 100644
> --- a/drivers/virtio/Kconfig
> +++ b/drivers/virtio/Kconfig
> @@ -12,6 +12,14 @@ config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
>  	  This option is selected if the architecture may need to enforce
>  	  VIRTIO_F_ACCESS_PLATFORM
>  
> +config VIRTIO_PCI_MODERN
> +	tristate "Modern Virtio PCI Device"
> +	depends on PCI
> +	help
> +	  Modern PCI device implementation. This module implements the
> +	  basic probe and control for devices which are based on modern
> +	  PCI device with possible vendor specific extensions.
> +
>  menuconfig VIRTIO_MENU
>  	bool "Virtio drivers"
>  	default y
> @@ -20,7 +28,7 @@ if VIRTIO_MENU
>  
>  config VIRTIO_PCI
>  	tristate "PCI driver for virtio devices"
> -	depends on PCI
> +	depends on VIRTIO_PCI_MODERN
>  	select VIRTIO
>  	help
>  	  This driver provides support for virtio based paravirtual device
> diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
> index 591e6f72aa54..f097578aaa8f 100644
> --- a/drivers/virtio/Makefile
> +++ b/drivers/virtio/Makefile
> @@ -1,5 +1,6 @@
>  # SPDX-License-Identifier: GPL-2.0
>  obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o
> +obj-$(CONFIG_VIRTIO_PCI_MODERN) += virtio_pci_modern_dev.o
>  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
> diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
> index f35ff5b6b467..beec047a8f8d 100644
> --- a/drivers/virtio/virtio_pci_common.h
> +++ b/drivers/virtio/virtio_pci_common.h
> @@ -25,6 +25,7 @@
>  #include <linux/virtio_config.h>
>  #include <linux/virtio_ring.h>
>  #include <linux/virtio_pci.h>
> +#include <linux/virtio_pci_modern.h>
>  #include <linux/highmem.h>
>  #include <linux/spinlock.h>
>  
> @@ -39,32 +40,6 @@ struct virtio_pci_vq_info {
>  	unsigned msix_vector;
>  };
>  
> -struct virtio_pci_modern_device {
> -	struct pci_dev *pci_dev;
> -
> -	struct virtio_pci_common_cfg __iomem *common;
> -	/* Device-specific data (non-legacy mode)  */
> -	void __iomem *device;
> -	/* Base of vq notifications (non-legacy mode). */
> -	void __iomem *notify_base;
> -	/* Where to read and clear interrupt */
> -	u8 __iomem *isr;
> -
> -	/* So we can sanity-check accesses. */
> -	size_t notify_len;
> -	size_t device_len;
> -
> -	/* Capability for when we need to map notifications per-vq. */
> -	int notify_map_cap;
> -
> -	/* Multiply queue_notify_off by this value. (non-legacy mode). */
> -	u32 notify_offset_multiplier;
> -
> -	int modern_bars;
> -
> -	struct virtio_device_id id;
> -};
> -
>  /* Our device structure */
>  struct virtio_pci_device {
>  	struct virtio_device vdev;
> diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
> index a5e3a5e40323..fbd4ebc00eb6 100644
> --- a/drivers/virtio/virtio_pci_modern.c
> +++ b/drivers/virtio/virtio_pci_modern.c
> @@ -19,158 +19,6 @@
>  #define VIRTIO_RING_NO_LEGACY
>  #include "virtio_pci_common.h"
>  
> -/*
> - * Type-safe wrappers for io accesses.
> - * Use these to enforce at compile time the following spec requirement:
> - *
> - * The driver MUST access each field using the “natural” access
> - * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses
> - * for 16-bit fields and 8-bit accesses for 8-bit fields.
> - */
> -static inline u8 vp_ioread8(const u8 __iomem *addr)
> -{
> -	return ioread8(addr);
> -}
> -static inline u16 vp_ioread16 (const __le16 __iomem *addr)
> -{
> -	return ioread16(addr);
> -}
> -
> -static inline u32 vp_ioread32(const __le32 __iomem *addr)
> -{
> -	return ioread32(addr);
> -}
> -
> -static inline void vp_iowrite8(u8 value, u8 __iomem *addr)
> -{
> -	iowrite8(value, addr);
> -}
> -
> -static inline void vp_iowrite16(u16 value, __le16 __iomem *addr)
> -{
> -	iowrite16(value, addr);
> -}
> -
> -static inline void vp_iowrite32(u32 value, __le32 __iomem *addr)
> -{
> -	iowrite32(value, addr);
> -}
> -
> -static void vp_iowrite64_twopart(u64 val,
> -				 __le32 __iomem *lo, __le32 __iomem *hi)
> -{
> -	vp_iowrite32((u32)val, lo);
> -	vp_iowrite32(val >> 32, hi);
> -}
> -
> -/*
> - * vp_modern_map_capability - map a part of virtio pci capability
> - * @mdev: the modern virtio-pci device
> - * @off: offset of the capability
> - * @minlen: minimal length of the capability
> - * @align: align requirement
> - * @start: start from the capability
> - * @size: map size
> - * @len: the length that is actually mapped
> - *
> - * Returns the io address of for the part of the capability
> - */
> -void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off,
> -				       size_t minlen,
> -				       u32 align,
> -				       u32 start, u32 size,
> -				       size_t *len)
> -{
> -	struct pci_dev *dev = mdev->pci_dev;
> -	u8 bar;
> -	u32 offset, length;
> -	void __iomem *p;
> -
> -	pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap,
> -						 bar),
> -			     &bar);
> -	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset),
> -			     &offset);
> -	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length),
> -			      &length);
> -
> -	if (length <= start) {
> -		dev_err(&dev->dev,
> -			"virtio_pci: bad capability len %u (>%u expected)\n",
> -			length, start);
> -		return NULL;
> -	}
> -
> -	if (length - start < minlen) {
> -		dev_err(&dev->dev,
> -			"virtio_pci: bad capability len %u (>=%zu expected)\n",
> -			length, minlen);
> -		return NULL;
> -	}
> -
> -	length -= start;
> -
> -	if (start + offset < offset) {
> -		dev_err(&dev->dev,
> -			"virtio_pci: map wrap-around %u+%u\n",
> -			start, offset);
> -		return NULL;
> -	}
> -
> -	offset += start;
> -
> -	if (offset & (align - 1)) {
> -		dev_err(&dev->dev,
> -			"virtio_pci: offset %u not aligned to %u\n",
> -			offset, align);
> -		return NULL;
> -	}
> -
> -	if (length > size)
> -		length = size;
> -
> -	if (len)
> -		*len = length;
> -
> -	if (minlen + offset < minlen ||
> -	    minlen + offset > pci_resource_len(dev, bar)) {
> -		dev_err(&dev->dev,
> -			"virtio_pci: map virtio %zu@%u "
> -			"out of range on bar %i length %lu\n",
> -			minlen, offset,
> -			bar, (unsigned long)pci_resource_len(dev, bar));
> -		return NULL;
> -	}
> -
> -	p = pci_iomap_range(dev, bar, offset, length);
> -	if (!p)
> -		dev_err(&dev->dev,
> -			"virtio_pci: unable to map virtio %u@%u on bar %i\n",
> -			length, offset, bar);
> -	return p;
> -}
> -
> -/*
> - * vp_modern_get_features - get features from device
> - * @mdev: the modern virtio-pci device
> - *
> - * Returns the features read from the device
> - */
> -static u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	u64 features;
> -
> -	vp_iowrite32(0, &cfg->device_feature_select);
> -	features = vp_ioread32(&cfg->device_feature);
> -	vp_iowrite32(1, &cfg->device_feature_select);
> -	features |= ((u64)vp_ioread32(&cfg->device_feature) << 32);
> -
> -	return features;
> -}
> -
> -/* virtio config->get_features() implementation */
>  static u64 vp_get_features(struct virtio_device *vdev)
>  {
>  	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
> @@ -188,149 +36,6 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features)
>  		__virtio_set_bit(vdev, VIRTIO_F_SR_IOV);
>  }
>  
> -/*
> - * vp_modern_set_features - set features to device
> - * @mdev: the modern virtio-pci device
> - * @features: the features set to device
> - */
> -static void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
> -				   u64 features)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	vp_iowrite32(0, &cfg->guest_feature_select);
> -	vp_iowrite32((u32)features, &cfg->guest_feature);
> -	vp_iowrite32(1, &cfg->guest_feature_select);
> -	vp_iowrite32(features >> 32, &cfg->guest_feature);
> -}
> -
> -/*
> - * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue
> - * @mdev: the modern virtio-pci device
> - * @index: queue index
> - * @vector: the config vector
> - *
> - * Returns the config vector read from the device
> - */
> -static u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
> -				  u16 index, u16 vector)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	vp_iowrite16(index, &cfg->queue_select);
> -	vp_iowrite16(vector, &cfg->queue_msix_vector);
> -	/* Flush the write out to device */
> -	return vp_ioread16(&cfg->queue_msix_vector);
> -}
> -
> -/*
> - * vp_modern_queue_address - set the virtqueue address
> - * @mdev: the modern virtio-pci device
> - * @index: the queue index
> - * @desc_addr: address of the descriptor area
> - * @driver_addr: address of the driver area
> - * @device_addr: address of the device area
> - */
> -static void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
> -				    u16 index, u64 desc_addr, u64 driver_addr,
> -				    u64 device_addr)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	vp_iowrite16(index, &cfg->queue_select);
> -
> -	vp_iowrite64_twopart(desc_addr, &cfg->queue_desc_lo,
> -			     &cfg->queue_desc_hi);
> -	vp_iowrite64_twopart(driver_addr, &cfg->queue_avail_lo,
> -			     &cfg->queue_avail_hi);
> -	vp_iowrite64_twopart(device_addr, &cfg->queue_used_lo,
> -			     &cfg->queue_used_hi);
> -}
> -
> -/*
> - * vp_modern_set_queue_enable - enable a virtqueue
> - * @mdev: the modern virtio-pci device
> - * @index: the queue index
> - * @enable: whether the virtqueue is enable or not
> - */
> -static void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev,
> -				       u16 index, bool enable)
> -{
> -	vp_iowrite16(index, &mdev->common->queue_select);
> -	vp_iowrite16(enable, &mdev->common->queue_enable);
> -}
> -
> -/*
> - * vp_modern_get_queue_enable - enable a virtqueue
> - * @mdev: the modern virtio-pci device
> - * @index: the queue index
> - *
> - * Returns whether a virtqueue is enabled or not
> - */
> -static bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
> -				       u16 index)
> -{
> -	vp_iowrite16(index, &mdev->common->queue_select);
> -
> -	return vp_ioread16(&mdev->common->queue_enable);
> -}
> -
> -/*
> - * vp_modern_set_queue_size - set size for a virtqueue
> - * @mdev: the modern virtio-pci device
> - * @index: the queue index
> - * @size: the size of the virtqueue
> - */
> -static void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev,
> -				     u16 index, u16 size)
> -{
> -	vp_iowrite16(index, &mdev->common->queue_select);
> -	vp_iowrite16(size, &mdev->common->queue_size);
> -
> -}
> -
> -/*
> - * vp_modern_get_queue_size - get size for a virtqueue
> - * @mdev: the modern virtio-pci device
> - * @index: the queue index
> - *
> - * Returns the size of the virtqueue
> - */
> -static u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
> -				    u16 index)
> -{
> -	vp_iowrite16(index, &mdev->common->queue_select);
> -
> -	return vp_ioread16(&mdev->common->queue_size);
> -
> -}
> -
> -/*
> - * vp_modern_get_num_queues - get the number of virtqueues
> - * @mdev: the modern virtio-pci device
> - *
> - * Returns the number of virtqueues
> - */
> -static u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev)
> -{
> -	return vp_ioread16(&mdev->common->num_queues);
> -}
> -
> -/*
> - * vp_modern_get_queue_notify_off - get notification offset for a virtqueue
> - * @mdev: the modern virtio-pci device
> - * @index: the queue index
> - *
> - * Returns the notification offset for a virtqueue
> - */
> -static u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev,
> -					  u16 index)
> -{
> -	vp_iowrite16(index, &mdev->common->queue_select);
> -
> -	return vp_ioread16(&mdev->common->queue_notify_off);
> -}
> -
>  /* virtio config->finalize_features() implementation */
>  static int vp_finalize_features(struct virtio_device *vdev)
>  {
> @@ -429,19 +134,6 @@ static void vp_set(struct virtio_device *vdev, unsigned offset,
>  	}
>  }
>  
> -/*
> - * vp_modern_generation - get the device genreation
> - * @mdev: the modern virtio-pci device
> - *
> - * Returns the genreation read from device
> - */
> -static u32 vp_modern_generation(struct virtio_pci_modern_device *mdev)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	return vp_ioread8(&cfg->config_generation);
> -}
> -
>  static u32 vp_generation(struct virtio_device *vdev)
>  {
>  	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
> @@ -449,19 +141,6 @@ static u32 vp_generation(struct virtio_device *vdev)
>  	return vp_modern_generation(&vp_dev->mdev);
>  }
>  
> -/*
> - * vp_modern_get_status - get the device status
> - * @mdev: the modern virtio-pci device
> - *
> - * Returns the status read from device
> - */
> -static u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	return vp_ioread8(&cfg->device_status);
> -}
> -
>  /* config->{get,set}_status() implementations */
>  static u8 vp_get_status(struct virtio_device *vdev)
>  {
> @@ -470,19 +149,6 @@ static u8 vp_get_status(struct virtio_device *vdev)
>  	return vp_modern_get_status(&vp_dev->mdev);
>  }
>  
> -/*
> - * vp_modern_set_status - set status to device
> - * @mdev: the modern virtio-pci device
> - * @status: the status set to device
> - */
> -static void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
> -				 u8 status)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	vp_iowrite8(status, &cfg->device_status);
> -}
> -
>  static void vp_set_status(struct virtio_device *vdev, u8 status)
>  {
>  	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
> @@ -510,25 +176,6 @@ static void vp_reset(struct virtio_device *vdev)
>  	vp_synchronize_vectors(vdev);
>  }
>  
> -/*
> - * vp_modern_config_vector - set the vector for config interrupt
> - * @mdev: the modern virtio-pci device
> - * @vector: the config vector
> - *
> - * Returns the config vector read from the device
> - */
> -static u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev,
> -				   u16 vector)
> -{
> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> -
> -	/* Setup the vector used for configuration events */
> -	vp_iowrite16(vector, &cfg->msix_config);
> -	/* Verify we had enough resources to assign the vector */
> -	/* Will also flush the write out to device */
> -	return vp_ioread16(&cfg->msix_config);
> -}
> -
>  static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
>  {
>  	return vp_modern_config_vector(&vp_dev->mdev, vector);
> @@ -789,253 +436,6 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
>  	.get_shm_region  = vp_get_shm_region,
>  };
>  
> -/**
> - * virtio_pci_find_capability - walk capabilities to find device info.
> - * @dev: the pci device
> - * @cfg_type: the VIRTIO_PCI_CAP_* value we seek
> - * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
> - * @bars: the bitmask of BARs
> - *
> - * Returns offset of the capability, or 0.
> - */
> -static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
> -					     u32 ioresource_types, int *bars)
> -{
> -	int pos;
> -
> -	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
> -	     pos > 0;
> -	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
> -		u8 type, bar;
> -		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
> -							 cfg_type),
> -				     &type);
> -		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
> -							 bar),
> -				     &bar);
> -
> -		/* Ignore structures with reserved BAR values */
> -		if (bar > 0x5)
> -			continue;
> -
> -		if (type == cfg_type) {
> -			if (pci_resource_len(dev, bar) &&
> -			    pci_resource_flags(dev, bar) & ioresource_types) {
> -				*bars |= (1 << bar);
> -				return pos;
> -			}
> -		}
> -	}
> -	return 0;
> -}
> -
> -/* This is part of the ABI.  Don't screw with it. */
> -static inline void check_offsets(void)
> -{
> -	/* Note: disk space was harmed in compilation of this function. */
> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR !=
> -		     offsetof(struct virtio_pci_cap, cap_vndr));
> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT !=
> -		     offsetof(struct virtio_pci_cap, cap_next));
> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN !=
> -		     offsetof(struct virtio_pci_cap, cap_len));
> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE !=
> -		     offsetof(struct virtio_pci_cap, cfg_type));
> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR !=
> -		     offsetof(struct virtio_pci_cap, bar));
> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET !=
> -		     offsetof(struct virtio_pci_cap, offset));
> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH !=
> -		     offsetof(struct virtio_pci_cap, length));
> -	BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT !=
> -		     offsetof(struct virtio_pci_notify_cap,
> -			      notify_off_multiplier));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT !=
> -		     offsetof(struct virtio_pci_common_cfg,
> -			      device_feature_select));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF !=
> -		     offsetof(struct virtio_pci_common_cfg, device_feature));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT !=
> -		     offsetof(struct virtio_pci_common_cfg,
> -			      guest_feature_select));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF !=
> -		     offsetof(struct virtio_pci_common_cfg, guest_feature));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX !=
> -		     offsetof(struct virtio_pci_common_cfg, msix_config));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ !=
> -		     offsetof(struct virtio_pci_common_cfg, num_queues));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS !=
> -		     offsetof(struct virtio_pci_common_cfg, device_status));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION !=
> -		     offsetof(struct virtio_pci_common_cfg, config_generation));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_select));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_size));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_msix_vector));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_enable));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_notify_off));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_desc_lo));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_desc_hi));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_avail_lo));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_avail_hi));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_used_lo));
> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI !=
> -		     offsetof(struct virtio_pci_common_cfg, queue_used_hi));
> -}
> -
> -/*
> - * vp_modern_probe: probe the modern virtio pci device, note that the
> - * caller is required to enable PCI device before calling this function.
> - * @mdev: the modern virtio-pci device
> - *
> - * Return 0 on succeed otherwise fail
> - */
> -static int vp_modern_probe(struct virtio_pci_modern_device *mdev)
> -{
> -	struct pci_dev *pci_dev = mdev->pci_dev;
> -	int err, common, isr, notify, device;
> -	u32 notify_length;
> -	u32 notify_offset;
> -
> -	check_offsets();
> -
> -	mdev->pci_dev = pci_dev;
> -
> -	/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
> -	if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
> -		return -ENODEV;
> -
> -	if (pci_dev->device < 0x1040) {
> -		/* Transitional devices: use the PCI subsystem device id as
> -		 * virtio device id, same as legacy driver always did.
> -		 */
> -		mdev->id.device = pci_dev->subsystem_device;
> -	} else {
> -		/* Modern devices: simply use PCI device id, but start from 0x1040. */
> -		mdev->id.device = pci_dev->device - 0x1040;
> -	}
> -	mdev->id.vendor = pci_dev->subsystem_vendor;
> -
> -	/* check for a common config: if not, use legacy mode (bar 0). */
> -	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
> -					    IORESOURCE_IO | IORESOURCE_MEM,
> -					    &mdev->modern_bars);
> -	if (!common) {
> -		dev_info(&pci_dev->dev,
> -			 "virtio_pci: leaving for legacy driver\n");
> -		return -ENODEV;
> -	}
> -
> -	/* If common is there, these should be too... */
> -	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
> -					 IORESOURCE_IO | IORESOURCE_MEM,
> -					 &mdev->modern_bars);
> -	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
> -					    IORESOURCE_IO | IORESOURCE_MEM,
> -					    &mdev->modern_bars);
> -	if (!isr || !notify) {
> -		dev_err(&pci_dev->dev,
> -			"virtio_pci: missing capabilities %i/%i/%i\n",
> -			common, isr, notify);
> -		return -EINVAL;
> -	}
> -
> -	err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
> -	if (err)
> -		err = dma_set_mask_and_coherent(&pci_dev->dev,
> -						DMA_BIT_MASK(32));
> -	if (err)
> -		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
> -
> -	/* Device capability is only mandatory for devices that have
> -	 * device-specific configuration.
> -	 */
> -	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
> -					    IORESOURCE_IO | IORESOURCE_MEM,
> -					    &mdev->modern_bars);
> -
> -	err = pci_request_selected_regions(pci_dev, mdev->modern_bars,
> -					   "virtio-pci-modern");
> -	if (err)
> -		return err;
> -
> -	err = -EINVAL;
> -	mdev->common = vp_modern_map_capability(mdev, common,
> -				      sizeof(struct virtio_pci_common_cfg), 4,
> -				      0, sizeof(struct virtio_pci_common_cfg),
> -				      NULL);
> -	if (!mdev->common)
> -		goto err_map_common;
> -	mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1,
> -					     0, 1,
> -					     NULL);
> -	if (!mdev->isr)
> -		goto err_map_isr;
> -
> -	/* Read notify_off_multiplier from config space. */
> -	pci_read_config_dword(pci_dev,
> -			      notify + offsetof(struct virtio_pci_notify_cap,
> -						notify_off_multiplier),
> -			      &mdev->notify_offset_multiplier);
> -	/* Read notify length and offset from config space. */
> -	pci_read_config_dword(pci_dev,
> -			      notify + offsetof(struct virtio_pci_notify_cap,
> -						cap.length),
> -			      &notify_length);
> -
> -	pci_read_config_dword(pci_dev,
> -			      notify + offsetof(struct virtio_pci_notify_cap,
> -						cap.offset),
> -			      &notify_offset);
> -
> -	/* We don't know how many VQs we'll map, ahead of the time.
> -	 * If notify length is small, map it all now.
> -	 * Otherwise, map each VQ individually later.
> -	 */
> -	if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) {
> -		mdev->notify_base = vp_modern_map_capability(mdev, notify,
> -							     2, 2,
> -							     0, notify_length,
> -							     &mdev->notify_len);
> -		if (!mdev->notify_base)
> -			goto err_map_notify;
> -	} else {
> -		mdev->notify_map_cap = notify;
> -	}
> -
> -	/* Again, we don't know how much we should map, but PAGE_SIZE
> -	 * is more than enough for all existing devices.
> -	 */
> -	if (device) {
> -		mdev->device = vp_modern_map_capability(mdev, device, 0, 4,
> -							0, PAGE_SIZE,
> -							&mdev->device_len);
> -		if (!mdev->device)
> -			goto err_map_device;
> -	}
> -
> -	return 0;
> -
> -err_map_device:
> -	if (mdev->notify_base)
> -		pci_iounmap(pci_dev, mdev->notify_base);
> -err_map_notify:
> -	pci_iounmap(pci_dev, mdev->isr);
> -err_map_isr:
> -	pci_iounmap(pci_dev, mdev->common);
> -err_map_common:
> -	return err;
> -}
> -
>  /* the PCI probing function */
>  int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
>  {
> @@ -1063,23 +463,6 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
>  	return 0;
>  }
>  
> -/*
> - * vp_modern_probe: remove and cleanup the modern virtio pci device
> - * @mdev: the modern virtio-pci device
> - */
> -static void vp_modern_remove(struct virtio_pci_modern_device *mdev)
> -{
> -	struct pci_dev *pci_dev = mdev->pci_dev;
> -
> -	if (mdev->device)
> -		pci_iounmap(pci_dev, mdev->device);
> -	if (mdev->notify_base)
> -		pci_iounmap(pci_dev, mdev->notify_base);
> -	pci_iounmap(pci_dev, mdev->isr);
> -	pci_iounmap(pci_dev, mdev->common);
> -	pci_release_selected_regions(pci_dev, mdev->modern_bars);
> -}
> -
>  void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
>  {
>  	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
> diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
> new file mode 100644
> index 000000000000..cbd667496bb1
> --- /dev/null
> +++ b/drivers/virtio/virtio_pci_modern_dev.c
> @@ -0,0 +1,599 @@
> +// SPDX-License-Identifier: GPL-2.0-or-later
> +
> +#include <linux/virtio_pci_modern.h>
> +#include <linux/module.h>
> +#include <linux/pci.h>
> +
> +/*
> + * vp_modern_map_capability - map a part of virtio pci capability
> + * @mdev: the modern virtio-pci device
> + * @off: offset of the capability
> + * @minlen: minimal length of the capability
> + * @align: align requirement
> + * @start: start from the capability
> + * @size: map size
> + * @len: the length that is actually mapped
> + *
> + * Returns the io address of for the part of the capability
> + */
> +void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off,
> +				       size_t minlen,
> +				       u32 align,
> +				       u32 start, u32 size,
> +				       size_t *len)
> +{
> +	struct pci_dev *dev = mdev->pci_dev;
> +	u8 bar;
> +	u32 offset, length;
> +	void __iomem *p;
> +
> +	pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap,
> +						 bar),
> +			     &bar);
> +	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset),
> +			     &offset);
> +	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length),
> +			      &length);
> +
> +	if (length <= start) {
> +		dev_err(&dev->dev,
> +			"virtio_pci: bad capability len %u (>%u expected)\n",
> +			length, start);
> +		return NULL;
> +	}
> +
> +	if (length - start < minlen) {
> +		dev_err(&dev->dev,
> +			"virtio_pci: bad capability len %u (>=%zu expected)\n",
> +			length, minlen);
> +		return NULL;
> +	}
> +
> +	length -= start;
> +
> +	if (start + offset < offset) {
> +		dev_err(&dev->dev,
> +			"virtio_pci: map wrap-around %u+%u\n",
> +			start, offset);
> +		return NULL;
> +	}
> +
> +	offset += start;
> +
> +	if (offset & (align - 1)) {
> +		dev_err(&dev->dev,
> +			"virtio_pci: offset %u not aligned to %u\n",
> +			offset, align);
> +		return NULL;
> +	}
> +
> +	if (length > size)
> +		length = size;
> +
> +	if (len)
> +		*len = length;
> +
> +	if (minlen + offset < minlen ||
> +	    minlen + offset > pci_resource_len(dev, bar)) {
> +		dev_err(&dev->dev,
> +			"virtio_pci: map virtio %zu@%u "
> +			"out of range on bar %i length %lu\n",
> +			minlen, offset,
> +			bar, (unsigned long)pci_resource_len(dev, bar));
> +		return NULL;
> +	}
> +
> +	p = pci_iomap_range(dev, bar, offset, length);
> +	if (!p)
> +		dev_err(&dev->dev,
> +			"virtio_pci: unable to map virtio %u@%u on bar %i\n",
> +			length, offset, bar);
> +	return p;
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_map_capability);
> +
> +/**
> + * virtio_pci_find_capability - walk capabilities to find device info.
> + * @dev: the pci device
> + * @cfg_type: the VIRTIO_PCI_CAP_* value we seek
> + * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
> + * @bars: the bitmask of BARs
> + *
> + * Returns offset of the capability, or 0.
> + */
> +static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
> +					     u32 ioresource_types, int *bars)
> +{
> +	int pos;
> +
> +	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
> +	     pos > 0;
> +	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
> +		u8 type, bar;
> +		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
> +							 cfg_type),
> +				     &type);
> +		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
> +							 bar),
> +				     &bar);
> +
> +		/* Ignore structures with reserved BAR values */
> +		if (bar > 0x5)
> +			continue;
> +
> +		if (type == cfg_type) {
> +			if (pci_resource_len(dev, bar) &&
> +			    pci_resource_flags(dev, bar) & ioresource_types) {
> +				*bars |= (1 << bar);
> +				return pos;
> +			}
> +		}
> +	}
> +	return 0;
> +}
> +
> +/* This is part of the ABI.  Don't screw with it. */
> +static inline void check_offsets(void)
> +{
> +	/* Note: disk space was harmed in compilation of this function. */
> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR !=
> +		     offsetof(struct virtio_pci_cap, cap_vndr));
> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT !=
> +		     offsetof(struct virtio_pci_cap, cap_next));
> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN !=
> +		     offsetof(struct virtio_pci_cap, cap_len));
> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE !=
> +		     offsetof(struct virtio_pci_cap, cfg_type));
> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR !=
> +		     offsetof(struct virtio_pci_cap, bar));
> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET !=
> +		     offsetof(struct virtio_pci_cap, offset));
> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH !=
> +		     offsetof(struct virtio_pci_cap, length));
> +	BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT !=
> +		     offsetof(struct virtio_pci_notify_cap,
> +			      notify_off_multiplier));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT !=
> +		     offsetof(struct virtio_pci_common_cfg,
> +			      device_feature_select));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF !=
> +		     offsetof(struct virtio_pci_common_cfg, device_feature));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT !=
> +		     offsetof(struct virtio_pci_common_cfg,
> +			      guest_feature_select));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF !=
> +		     offsetof(struct virtio_pci_common_cfg, guest_feature));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX !=
> +		     offsetof(struct virtio_pci_common_cfg, msix_config));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ !=
> +		     offsetof(struct virtio_pci_common_cfg, num_queues));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS !=
> +		     offsetof(struct virtio_pci_common_cfg, device_status));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION !=
> +		     offsetof(struct virtio_pci_common_cfg, config_generation));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_select));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_size));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_msix_vector));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_enable));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_notify_off));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_desc_lo));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_desc_hi));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_avail_lo));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_avail_hi));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_used_lo));
> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI !=
> +		     offsetof(struct virtio_pci_common_cfg, queue_used_hi));
> +}
> +
> +/*
> + * vp_modern_probe: probe the modern virtio pci device, note that the
> + * caller is required to enable PCI device before calling this function.
> + * @mdev: the modern virtio-pci device
> + *
> + * Return 0 on succeed otherwise fail
> + */
> +int vp_modern_probe(struct virtio_pci_modern_device *mdev)
> +{
> +	struct pci_dev *pci_dev = mdev->pci_dev;
> +	int err, common, isr, notify, device;
> +	u32 notify_length;
> +	u32 notify_offset;
> +
> +	check_offsets();
> +
> +	mdev->pci_dev = pci_dev;
> +
> +	/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
> +	if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
> +		return -ENODEV;
> +
> +	if (pci_dev->device < 0x1040) {
> +		/* Transitional devices: use the PCI subsystem device id as
> +		 * virtio device id, same as legacy driver always did.
> +		 */
> +		mdev->id.device = pci_dev->subsystem_device;
> +	} else {
> +		/* Modern devices: simply use PCI device id, but start from 0x1040. */
> +		mdev->id.device = pci_dev->device - 0x1040;
> +	}
> +	mdev->id.vendor = pci_dev->subsystem_vendor;
> +
> +	/* check for a common config: if not, use legacy mode (bar 0). */
> +	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
> +					    IORESOURCE_IO | IORESOURCE_MEM,
> +					    &mdev->modern_bars);
> +	if (!common) {
> +		dev_info(&pci_dev->dev,
> +			 "virtio_pci: leaving for legacy driver\n");
> +		return -ENODEV;
> +	}
> +
> +	/* If common is there, these should be too... */
> +	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
> +					 IORESOURCE_IO | IORESOURCE_MEM,
> +					 &mdev->modern_bars);
> +	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
> +					    IORESOURCE_IO | IORESOURCE_MEM,
> +					    &mdev->modern_bars);
> +	if (!isr || !notify) {
> +		dev_err(&pci_dev->dev,
> +			"virtio_pci: missing capabilities %i/%i/%i\n",
> +			common, isr, notify);
> +		return -EINVAL;
> +	}
> +
> +	err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
> +	if (err)
> +		err = dma_set_mask_and_coherent(&pci_dev->dev,
> +						DMA_BIT_MASK(32));
> +	if (err)
> +		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
> +
> +	/* Device capability is only mandatory for devices that have
> +	 * device-specific configuration.
> +	 */
> +	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
> +					    IORESOURCE_IO | IORESOURCE_MEM,
> +					    &mdev->modern_bars);
> +
> +	err = pci_request_selected_regions(pci_dev, mdev->modern_bars,
> +					   "virtio-pci-modern");
> +	if (err)
> +		return err;
> +
> +	err = -EINVAL;
> +	mdev->common = vp_modern_map_capability(mdev, common,
> +				      sizeof(struct virtio_pci_common_cfg), 4,
> +				      0, sizeof(struct virtio_pci_common_cfg),
> +				      NULL);
> +	if (!mdev->common)
> +		goto err_map_common;
> +	mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1,
> +					     0, 1,
> +					     NULL);
> +	if (!mdev->isr)
> +		goto err_map_isr;
> +
> +	/* Read notify_off_multiplier from config space. */
> +	pci_read_config_dword(pci_dev,
> +			      notify + offsetof(struct virtio_pci_notify_cap,
> +						notify_off_multiplier),
> +			      &mdev->notify_offset_multiplier);
> +	/* Read notify length and offset from config space. */
> +	pci_read_config_dword(pci_dev,
> +			      notify + offsetof(struct virtio_pci_notify_cap,
> +						cap.length),
> +			      &notify_length);
> +
> +	pci_read_config_dword(pci_dev,
> +			      notify + offsetof(struct virtio_pci_notify_cap,
> +						cap.offset),
> +			      &notify_offset);
> +
> +	/* We don't know how many VQs we'll map, ahead of the time.
> +	 * If notify length is small, map it all now.
> +	 * Otherwise, map each VQ individually later.
> +	 */
> +	if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) {
> +		mdev->notify_base = vp_modern_map_capability(mdev, notify,
> +							     2, 2,
> +							     0, notify_length,
> +							     &mdev->notify_len);
> +		if (!mdev->notify_base)
> +			goto err_map_notify;
> +	} else {
> +		mdev->notify_map_cap = notify;
> +	}
> +
> +	/* Again, we don't know how much we should map, but PAGE_SIZE
> +	 * is more than enough for all existing devices.
> +	 */
> +	if (device) {
> +		mdev->device = vp_modern_map_capability(mdev, device, 0, 4,
> +							0, PAGE_SIZE,
> +							&mdev->device_len);
> +		if (!mdev->device)
> +			goto err_map_device;
> +	}
> +
> +	return 0;
> +
> +err_map_device:
> +	if (mdev->notify_base)
> +		pci_iounmap(pci_dev, mdev->notify_base);
> +err_map_notify:
> +	pci_iounmap(pci_dev, mdev->isr);
> +err_map_isr:
> +	pci_iounmap(pci_dev, mdev->common);
> +err_map_common:
> +	return err;
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_probe);
> +
> +/*
> + * vp_modern_probe: remove and cleanup the modern virtio pci device
> + * @mdev: the modern virtio-pci device
> + */
> +void vp_modern_remove(struct virtio_pci_modern_device *mdev)
> +{
> +	struct pci_dev *pci_dev = mdev->pci_dev;
> +
> +	if (mdev->device)
> +		pci_iounmap(pci_dev, mdev->device);
> +	if (mdev->notify_base)
> +		pci_iounmap(pci_dev, mdev->notify_base);
> +	pci_iounmap(pci_dev, mdev->isr);
> +	pci_iounmap(pci_dev, mdev->common);
> +	pci_release_selected_regions(pci_dev, mdev->modern_bars);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_remove);
> +
> +/*
> + * vp_modern_get_features - get features from device
> + * @mdev: the modern virtio-pci device
> + *
> + * Returns the features read from the device
> + */
> +u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	u64 features;
> +
> +	vp_iowrite32(0, &cfg->device_feature_select);
> +	features = vp_ioread32(&cfg->device_feature);
> +	vp_iowrite32(1, &cfg->device_feature_select);
> +	features |= ((u64)vp_ioread32(&cfg->device_feature) << 32);
> +
> +	return features;
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_get_features);
> +
> +/*
> + * vp_modern_set_features - set features to device
> + * @mdev: the modern virtio-pci device
> + * @features: the features set to device
> + */
> +void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
> +			    u64 features)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	vp_iowrite32(0, &cfg->guest_feature_select);
> +	vp_iowrite32((u32)features, &cfg->guest_feature);
> +	vp_iowrite32(1, &cfg->guest_feature_select);
> +	vp_iowrite32(features >> 32, &cfg->guest_feature);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_set_features);
> +
> +/*
> + * vp_modern_generation - get the device genreation
> + * @mdev: the modern virtio-pci device
> + *
> + * Returns the genreation read from device
> + */
> +u32 vp_modern_generation(struct virtio_pci_modern_device *mdev)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	return vp_ioread8(&cfg->config_generation);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_generation);
> +
> +/*
> + * vp_modern_get_status - get the device status
> + * @mdev: the modern virtio-pci device
> + *
> + * Returns the status read from device
> + */
> +u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	return vp_ioread8(&cfg->device_status);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_get_status);
> +
> +/*
> + * vp_modern_set_status - set status to device
> + * @mdev: the modern virtio-pci device
> + * @status: the status set to device
> + */
> +void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
> +				 u8 status)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	vp_iowrite8(status, &cfg->device_status);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_set_status);
> +
> +/*
> + * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue
> + * @mdev: the modern virtio-pci device
> + * @index: queue index
> + * @vector: the config vector
> + *
> + * Returns the config vector read from the device
> + */
> +u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
> +			   u16 index, u16 vector)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	vp_iowrite16(index, &cfg->queue_select);
> +	vp_iowrite16(vector, &cfg->queue_msix_vector);
> +	/* Flush the write out to device */
> +	return vp_ioread16(&cfg->queue_msix_vector);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_queue_vector);
> +
> +/*
> + * vp_modern_config_vector - set the vector for config interrupt
> + * @mdev: the modern virtio-pci device
> + * @vector: the config vector
> + *
> + * Returns the config vector read from the device
> + */
> +u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev,
> +			    u16 vector)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	/* Setup the vector used for configuration events */
> +	vp_iowrite16(vector, &cfg->msix_config);
> +	/* Verify we had enough resources to assign the vector */
> +	/* Will also flush the write out to device */
> +	return vp_ioread16(&cfg->msix_config);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_config_vector);
> +
> +/*
> + * vp_modern_queue_address - set the virtqueue address
> + * @mdev: the modern virtio-pci device
> + * @index: the queue index
> + * @desc_addr: address of the descriptor area
> + * @driver_addr: address of the driver area
> + * @device_addr: address of the device area
> + */
> +void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
> +			     u16 index, u64 desc_addr, u64 driver_addr,
> +			     u64 device_addr)
> +{
> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
> +
> +	vp_iowrite16(index, &cfg->queue_select);
> +
> +	vp_iowrite64_twopart(desc_addr, &cfg->queue_desc_lo,
> +			     &cfg->queue_desc_hi);
> +	vp_iowrite64_twopart(driver_addr, &cfg->queue_avail_lo,
> +			     &cfg->queue_avail_hi);
> +	vp_iowrite64_twopart(device_addr, &cfg->queue_used_lo,
> +			     &cfg->queue_used_hi);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_queue_address);
> +
> +/*
> + * vp_modern_set_queue_enable - enable a virtqueue
> + * @mdev: the modern virtio-pci device
> + * @index: the queue index
> + * @enable: whether the virtqueue is enable or not
> + */
> +void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev,
> +				u16 index, bool enable)
> +{
> +	vp_iowrite16(index, &mdev->common->queue_select);
> +	vp_iowrite16(enable, &mdev->common->queue_enable);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_set_queue_enable);
> +
> +/*
> + * vp_modern_get_queue_enable - enable a virtqueue
> + * @mdev: the modern virtio-pci device
> + * @index: the queue index
> + *
> + * Returns whether a virtqueue is enabled or not
> + */
> +bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
> +				u16 index)
> +{
> +	vp_iowrite16(index, &mdev->common->queue_select);
> +
> +	return vp_ioread16(&mdev->common->queue_enable);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_get_queue_enable);
> +
> +/*
> + * vp_modern_set_queue_size - set size for a virtqueue
> + * @mdev: the modern virtio-pci device
> + * @index: the queue index
> + * @size: the size of the virtqueue
> + */
> +void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev,
> +			      u16 index, u16 size)
> +{
> +	vp_iowrite16(index, &mdev->common->queue_select);
> +	vp_iowrite16(size, &mdev->common->queue_size);
> +
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_set_queue_size);
> +
> +/*
> + * vp_modern_get_queue_size - get size for a virtqueue
> + * @mdev: the modern virtio-pci device
> + * @index: the queue index
> + *
> + * Returns the size of the virtqueue
> + */
> +u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
> +			     u16 index)
> +{
> +	vp_iowrite16(index, &mdev->common->queue_select);
> +
> +	return vp_ioread16(&mdev->common->queue_size);
> +
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_get_queue_size);
> +
> +/*
> + * vp_modern_get_num_queues - get the number of virtqueues
> + * @mdev: the modern virtio-pci device
> + *
> + * Returns the number of virtqueues
> + */
> +u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev)
> +{
> +	return vp_ioread16(&mdev->common->num_queues);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_get_num_queues);
> +
> +/*
> + * vp_modern_get_queue_notify_off - get notification offset for a virtqueue
> + * @mdev: the modern virtio-pci device
> + * @index: the queue index
> + *
> + * Returns the notification offset for a virtqueue
> + */
> +u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev,
> +				   u16 index)
> +{
> +	vp_iowrite16(index, &mdev->common->queue_select);
> +
> +	return vp_ioread16(&mdev->common->queue_notify_off);
> +}
> +EXPORT_SYMBOL_GPL(vp_modern_get_queue_notify_off);
> +
> +MODULE_VERSION("0.1");
> +MODULE_DESCRIPTION("Modern Virtio PCI Device");
> +MODULE_AUTHOR("Jason Wang <jasowang@redhat.com>");
> +MODULE_LICENSE("GPL");
> diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h
> new file mode 100644
> index 000000000000..f26acbeec965
> --- /dev/null
> +++ b/include/linux/virtio_pci_modern.h
> @@ -0,0 +1,111 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef _LINUX_VIRTIO_PCI_MODERN_H
> +#define _LINUX_VIRTIO_PCI_MODERN_H
> +
> +#include <linux/pci.h>
> +#include <linux/virtio_pci.h>
> +
> +struct virtio_pci_modern_device {
> +	struct pci_dev *pci_dev;
> +
> +	struct virtio_pci_common_cfg __iomem *common;
> +	/* Device-specific data (non-legacy mode)  */
> +	void __iomem *device;
> +	/* Base of vq notifications (non-legacy mode). */
> +	void __iomem *notify_base;
> +	/* Where to read and clear interrupt */
> +	u8 __iomem *isr;
> +
> +	/* So we can sanity-check accesses. */
> +	size_t notify_len;
> +	size_t device_len;
> +
> +	/* Capability for when we need to map notifications per-vq. */
> +	int notify_map_cap;
> +
> +	/* Multiply queue_notify_off by this value. (non-legacy mode). */
> +	u32 notify_offset_multiplier;
> +
> +	int modern_bars;
> +
> +	struct virtio_device_id id;
> +};
> +
> +/*
> + * Type-safe wrappers for io accesses.
> + * Use these to enforce at compile time the following spec requirement:
> + *
> + * The driver MUST access each field using the “natural” access
> + * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses
> + * for 16-bit fields and 8-bit accesses for 8-bit fields.
> + */
> +static inline u8 vp_ioread8(const u8 __iomem *addr)
> +{
> +	return ioread8(addr);
> +}
> +static inline u16 vp_ioread16 (const __le16 __iomem *addr)
> +{
> +	return ioread16(addr);
> +}
> +
> +static inline u32 vp_ioread32(const __le32 __iomem *addr)
> +{
> +	return ioread32(addr);
> +}
> +
> +static inline void vp_iowrite8(u8 value, u8 __iomem *addr)
> +{
> +	iowrite8(value, addr);
> +}
> +
> +static inline void vp_iowrite16(u16 value, __le16 __iomem *addr)
> +{
> +	iowrite16(value, addr);
> +}
> +
> +static inline void vp_iowrite32(u32 value, __le32 __iomem *addr)
> +{
> +	iowrite32(value, addr);
> +}
> +
> +static inline void vp_iowrite64_twopart(u64 val,
> +					__le32 __iomem *lo,
> +					__le32 __iomem *hi)
> +{
> +	vp_iowrite32((u32)val, lo);
> +	vp_iowrite32(val >> 32, hi);
> +}
> +
> +u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev);
> +void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
> +		     u64 features);
> +u32 vp_modern_generation(struct virtio_pci_modern_device *mdev);
> +u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev);
> +void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
> +		   u8 status);
> +u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
> +			   u16 idx, u16 vector);
> +u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev,
> +		     u16 vector);
> +void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
> +			     u16 index, u64 desc_addr, u64 driver_addr,
> +			     u64 device_addr);
> +void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev,
> +				u16 idx, bool enable);
> +bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
> +				u16 idx);
> +void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev,
> +			      u16 idx, u16 size);
> +u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
> +			     u16 idx);
> +u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev);
> +u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev,
> +				   u16 idx);
> +void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off,
> +				       size_t minlen,
> +				       u32 align,
> +				       u32 start, u32 size,
> +				       size_t *len);
> +int vp_modern_probe(struct virtio_pci_modern_device *mdev);
> +void vp_modern_remove(struct virtio_pci_modern_device *mdev);
> +#endif

Re: [PATCH V3 16/19] virtio-pci: introduce modern device module

[Jason Wang]

On 2021/2/10 下午8:35, Michael S. Tsirkin wrote:
> On Wed, Feb 10, 2021 at 12:44:03PM +0800, Jason Wang wrote:
>> On 2021/2/9 下午10:20, Michael S. Tsirkin wrote:
>>> On Mon, Jan 04, 2021 at 02:55:00PM +0800, Jason Wang wrote:
>>>> Signed-off-by: Jason Wang <jasowang@redhat.com>
>>>> ---
>>>>    drivers/virtio/Kconfig                 |  10 +-
>>>>    drivers/virtio/Makefile                |   1 +
>>>>    drivers/virtio/virtio_pci_common.h     |  27 +-
>>>>    drivers/virtio/virtio_pci_modern.c     | 617 -------------------------
>>>>    drivers/virtio/virtio_pci_modern_dev.c | 599 ++++++++++++++++++++++++
>>>>    include/linux/virtio_pci_modern.h      | 111 +++++
>>>>    6 files changed, 721 insertions(+), 644 deletions(-)
>>>>    create mode 100644 drivers/virtio/virtio_pci_modern_dev.c
>>>>    create mode 100644 include/linux/virtio_pci_modern.h
>>>>
>>>> diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
>>>> index 7b41130d3f35..6b9b81f4b8c2 100644
>>>> --- a/drivers/virtio/Kconfig
>>>> +++ b/drivers/virtio/Kconfig
>>>> @@ -12,6 +12,14 @@ config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
>>>>    	  This option is selected if the architecture may need to enforce
>>>>    	  VIRTIO_F_ACCESS_PLATFORM
>>>> +config VIRTIO_PCI_MODERN
>>>> +	tristate "Modern Virtio PCI Device"
>>>> +	depends on PCI
>>>> +	help
>>>> +	  Modern PCI device implementation. This module implements the
>>>> +	  basic probe and control for devices which are based on modern
>>>> +	  PCI device with possible vendor specific extensions.
>>>> +
>>>>    menuconfig VIRTIO_MENU
>>>>    	bool "Virtio drivers"
>>>>    	default y
>>>> @@ -20,7 +28,7 @@ if VIRTIO_MENU
>>>>    config VIRTIO_PCI
>>>>    	tristate "PCI driver for virtio devices"
>>>> -	depends on PCI
>>>> +	depends on VIRTIO_PCI_MODERN
>>>>    	select VIRTIO
>>>>    	help
>>>>    	  This driver provides support for virtio based paravirtual device
>>> Looks like VIRTIO_PCI_MODERN is actually just a library that
>>> virtio pci uses. Is that right?
>>
>> Right.
>>
>>
>>> In that case just select it
>>> automatically, let's not make users enable it manually.
>>
>> I've considered to do this but the problem is that the module depends on PCI
>> so it can't be selected I think.
> Drop the dependency, document that whoever selects it must depend on PCI.


Fine with me. Will post a patch.

Thanks


>
>> Thanks
>>
>>

Re: [PATCH V3 16/19] virtio-pci: introduce modern device module

[Jason Wang]

On 2021/2/13 4:14 上午, Guenter Roeck wrote:
> On Mon, Jan 04, 2021 at 02:55:00PM +0800, Jason Wang wrote:
>> Signed-off-by: Jason Wang <jasowang@redhat.com>
>> Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
> I don't really see the point of having to enable VIRTIO_PCI_MODERN
> because otherwise VIRTIO_PCI no longer works. If VIRTIO_PCI now
> requires VIRTIO_PCI_MODERN, maybe it should select it instead of
> depending on it ?


Right.

I will post a patch soon to select that.

Thanks


> Alternatively, you could just drop the new
> configuration flag entirely and build virtio_pci_modern_dev.o with
> VIRTIO_PCI. One doesn't work without the other anyway, after all.
>
> Guenter
>
>> ---
>>   drivers/virtio/Kconfig                 |  10 +-
>>   drivers/virtio/Makefile                |   1 +
>>   drivers/virtio/virtio_pci_common.h     |  27 +-
>>   drivers/virtio/virtio_pci_modern.c     | 617 -------------------------
>>   drivers/virtio/virtio_pci_modern_dev.c | 599 ++++++++++++++++++++++++
>>   include/linux/virtio_pci_modern.h      | 111 +++++
>>   6 files changed, 721 insertions(+), 644 deletions(-)
>>   create mode 100644 drivers/virtio/virtio_pci_modern_dev.c
>>   create mode 100644 include/linux/virtio_pci_modern.h
>>
>> diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
>> index 7b41130d3f35..6b9b81f4b8c2 100644
>> --- a/drivers/virtio/Kconfig
>> +++ b/drivers/virtio/Kconfig
>> @@ -12,6 +12,14 @@ config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
>>   	  This option is selected if the architecture may need to enforce
>>   	  VIRTIO_F_ACCESS_PLATFORM
>>   
>> +config VIRTIO_PCI_MODERN
>> +	tristate "Modern Virtio PCI Device"
>> +	depends on PCI
>> +	help
>> +	  Modern PCI device implementation. This module implements the
>> +	  basic probe and control for devices which are based on modern
>> +	  PCI device with possible vendor specific extensions.
>> +
>>   menuconfig VIRTIO_MENU
>>   	bool "Virtio drivers"
>>   	default y
>> @@ -20,7 +28,7 @@ if VIRTIO_MENU
>>   
>>   config VIRTIO_PCI
>>   	tristate "PCI driver for virtio devices"
>> -	depends on PCI
>> +	depends on VIRTIO_PCI_MODERN
>>   	select VIRTIO
>>   	help
>>   	  This driver provides support for virtio based paravirtual device
>> diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
>> index 591e6f72aa54..f097578aaa8f 100644
>> --- a/drivers/virtio/Makefile
>> +++ b/drivers/virtio/Makefile
>> @@ -1,5 +1,6 @@
>>   # SPDX-License-Identifier: GPL-2.0
>>   obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o
>> +obj-$(CONFIG_VIRTIO_PCI_MODERN) += virtio_pci_modern_dev.o
>>   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
>> diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
>> index f35ff5b6b467..beec047a8f8d 100644
>> --- a/drivers/virtio/virtio_pci_common.h
>> +++ b/drivers/virtio/virtio_pci_common.h
>> @@ -25,6 +25,7 @@
>>   #include <linux/virtio_config.h>
>>   #include <linux/virtio_ring.h>
>>   #include <linux/virtio_pci.h>
>> +#include <linux/virtio_pci_modern.h>
>>   #include <linux/highmem.h>
>>   #include <linux/spinlock.h>
>>   
>> @@ -39,32 +40,6 @@ struct virtio_pci_vq_info {
>>   	unsigned msix_vector;
>>   };
>>   
>> -struct virtio_pci_modern_device {
>> -	struct pci_dev *pci_dev;
>> -
>> -	struct virtio_pci_common_cfg __iomem *common;
>> -	/* Device-specific data (non-legacy mode)  */
>> -	void __iomem *device;
>> -	/* Base of vq notifications (non-legacy mode). */
>> -	void __iomem *notify_base;
>> -	/* Where to read and clear interrupt */
>> -	u8 __iomem *isr;
>> -
>> -	/* So we can sanity-check accesses. */
>> -	size_t notify_len;
>> -	size_t device_len;
>> -
>> -	/* Capability for when we need to map notifications per-vq. */
>> -	int notify_map_cap;
>> -
>> -	/* Multiply queue_notify_off by this value. (non-legacy mode). */
>> -	u32 notify_offset_multiplier;
>> -
>> -	int modern_bars;
>> -
>> -	struct virtio_device_id id;
>> -};
>> -
>>   /* Our device structure */
>>   struct virtio_pci_device {
>>   	struct virtio_device vdev;
>> diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
>> index a5e3a5e40323..fbd4ebc00eb6 100644
>> --- a/drivers/virtio/virtio_pci_modern.c
>> +++ b/drivers/virtio/virtio_pci_modern.c
>> @@ -19,158 +19,6 @@
>>   #define VIRTIO_RING_NO_LEGACY
>>   #include "virtio_pci_common.h"
>>   
>> -/*
>> - * Type-safe wrappers for io accesses.
>> - * Use these to enforce at compile time the following spec requirement:
>> - *
>> - * The driver MUST access each field using the “natural” access
>> - * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses
>> - * for 16-bit fields and 8-bit accesses for 8-bit fields.
>> - */
>> -static inline u8 vp_ioread8(const u8 __iomem *addr)
>> -{
>> -	return ioread8(addr);
>> -}
>> -static inline u16 vp_ioread16 (const __le16 __iomem *addr)
>> -{
>> -	return ioread16(addr);
>> -}
>> -
>> -static inline u32 vp_ioread32(const __le32 __iomem *addr)
>> -{
>> -	return ioread32(addr);
>> -}
>> -
>> -static inline void vp_iowrite8(u8 value, u8 __iomem *addr)
>> -{
>> -	iowrite8(value, addr);
>> -}
>> -
>> -static inline void vp_iowrite16(u16 value, __le16 __iomem *addr)
>> -{
>> -	iowrite16(value, addr);
>> -}
>> -
>> -static inline void vp_iowrite32(u32 value, __le32 __iomem *addr)
>> -{
>> -	iowrite32(value, addr);
>> -}
>> -
>> -static void vp_iowrite64_twopart(u64 val,
>> -				 __le32 __iomem *lo, __le32 __iomem *hi)
>> -{
>> -	vp_iowrite32((u32)val, lo);
>> -	vp_iowrite32(val >> 32, hi);
>> -}
>> -
>> -/*
>> - * vp_modern_map_capability - map a part of virtio pci capability
>> - * @mdev: the modern virtio-pci device
>> - * @off: offset of the capability
>> - * @minlen: minimal length of the capability
>> - * @align: align requirement
>> - * @start: start from the capability
>> - * @size: map size
>> - * @len: the length that is actually mapped
>> - *
>> - * Returns the io address of for the part of the capability
>> - */
>> -void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off,
>> -				       size_t minlen,
>> -				       u32 align,
>> -				       u32 start, u32 size,
>> -				       size_t *len)
>> -{
>> -	struct pci_dev *dev = mdev->pci_dev;
>> -	u8 bar;
>> -	u32 offset, length;
>> -	void __iomem *p;
>> -
>> -	pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap,
>> -						 bar),
>> -			     &bar);
>> -	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset),
>> -			     &offset);
>> -	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length),
>> -			      &length);
>> -
>> -	if (length <= start) {
>> -		dev_err(&dev->dev,
>> -			"virtio_pci: bad capability len %u (>%u expected)\n",
>> -			length, start);
>> -		return NULL;
>> -	}
>> -
>> -	if (length - start < minlen) {
>> -		dev_err(&dev->dev,
>> -			"virtio_pci: bad capability len %u (>=%zu expected)\n",
>> -			length, minlen);
>> -		return NULL;
>> -	}
>> -
>> -	length -= start;
>> -
>> -	if (start + offset < offset) {
>> -		dev_err(&dev->dev,
>> -			"virtio_pci: map wrap-around %u+%u\n",
>> -			start, offset);
>> -		return NULL;
>> -	}
>> -
>> -	offset += start;
>> -
>> -	if (offset & (align - 1)) {
>> -		dev_err(&dev->dev,
>> -			"virtio_pci: offset %u not aligned to %u\n",
>> -			offset, align);
>> -		return NULL;
>> -	}
>> -
>> -	if (length > size)
>> -		length = size;
>> -
>> -	if (len)
>> -		*len = length;
>> -
>> -	if (minlen + offset < minlen ||
>> -	    minlen + offset > pci_resource_len(dev, bar)) {
>> -		dev_err(&dev->dev,
>> -			"virtio_pci: map virtio %zu@%u "
>> -			"out of range on bar %i length %lu\n",
>> -			minlen, offset,
>> -			bar, (unsigned long)pci_resource_len(dev, bar));
>> -		return NULL;
>> -	}
>> -
>> -	p = pci_iomap_range(dev, bar, offset, length);
>> -	if (!p)
>> -		dev_err(&dev->dev,
>> -			"virtio_pci: unable to map virtio %u@%u on bar %i\n",
>> -			length, offset, bar);
>> -	return p;
>> -}
>> -
>> -/*
>> - * vp_modern_get_features - get features from device
>> - * @mdev: the modern virtio-pci device
>> - *
>> - * Returns the features read from the device
>> - */
>> -static u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev)
>> -{
>> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> -
>> -	u64 features;
>> -
>> -	vp_iowrite32(0, &cfg->device_feature_select);
>> -	features = vp_ioread32(&cfg->device_feature);
>> -	vp_iowrite32(1, &cfg->device_feature_select);
>> -	features |= ((u64)vp_ioread32(&cfg->device_feature) << 32);
>> -
>> -	return features;
>> -}
>> -
>> -/* virtio config->get_features() implementation */
>>   static u64 vp_get_features(struct virtio_device *vdev)
>>   {
>>   	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
>> @@ -188,149 +36,6 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features)
>>   		__virtio_set_bit(vdev, VIRTIO_F_SR_IOV);
>>   }
>>   
>> -/*
>> - * vp_modern_set_features - set features to device
>> - * @mdev: the modern virtio-pci device
>> - * @features: the features set to device
>> - */
>> -static void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
>> -				   u64 features)
>> -{
>> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> -
>> -	vp_iowrite32(0, &cfg->guest_feature_select);
>> -	vp_iowrite32((u32)features, &cfg->guest_feature);
>> -	vp_iowrite32(1, &cfg->guest_feature_select);
>> -	vp_iowrite32(features >> 32, &cfg->guest_feature);
>> -}
>> -
>> -/*
>> - * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue
>> - * @mdev: the modern virtio-pci device
>> - * @index: queue index
>> - * @vector: the config vector
>> - *
>> - * Returns the config vector read from the device
>> - */
>> -static u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
>> -				  u16 index, u16 vector)
>> -{
>> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> -
>> -	vp_iowrite16(index, &cfg->queue_select);
>> -	vp_iowrite16(vector, &cfg->queue_msix_vector);
>> -	/* Flush the write out to device */
>> -	return vp_ioread16(&cfg->queue_msix_vector);
>> -}
>> -
>> -/*
>> - * vp_modern_queue_address - set the virtqueue address
>> - * @mdev: the modern virtio-pci device
>> - * @index: the queue index
>> - * @desc_addr: address of the descriptor area
>> - * @driver_addr: address of the driver area
>> - * @device_addr: address of the device area
>> - */
>> -static void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
>> -				    u16 index, u64 desc_addr, u64 driver_addr,
>> -				    u64 device_addr)
>> -{
>> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> -
>> -	vp_iowrite16(index, &cfg->queue_select);
>> -
>> -	vp_iowrite64_twopart(desc_addr, &cfg->queue_desc_lo,
>> -			     &cfg->queue_desc_hi);
>> -	vp_iowrite64_twopart(driver_addr, &cfg->queue_avail_lo,
>> -			     &cfg->queue_avail_hi);
>> -	vp_iowrite64_twopart(device_addr, &cfg->queue_used_lo,
>> -			     &cfg->queue_used_hi);
>> -}
>> -
>> -/*
>> - * vp_modern_set_queue_enable - enable a virtqueue
>> - * @mdev: the modern virtio-pci device
>> - * @index: the queue index
>> - * @enable: whether the virtqueue is enable or not
>> - */
>> -static void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev,
>> -				       u16 index, bool enable)
>> -{
>> -	vp_iowrite16(index, &mdev->common->queue_select);
>> -	vp_iowrite16(enable, &mdev->common->queue_enable);
>> -}
>> -
>> -/*
>> - * vp_modern_get_queue_enable - enable a virtqueue
>> - * @mdev: the modern virtio-pci device
>> - * @index: the queue index
>> - *
>> - * Returns whether a virtqueue is enabled or not
>> - */
>> -static bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
>> -				       u16 index)
>> -{
>> -	vp_iowrite16(index, &mdev->common->queue_select);
>> -
>> -	return vp_ioread16(&mdev->common->queue_enable);
>> -}
>> -
>> -/*
>> - * vp_modern_set_queue_size - set size for a virtqueue
>> - * @mdev: the modern virtio-pci device
>> - * @index: the queue index
>> - * @size: the size of the virtqueue
>> - */
>> -static void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev,
>> -				     u16 index, u16 size)
>> -{
>> -	vp_iowrite16(index, &mdev->common->queue_select);
>> -	vp_iowrite16(size, &mdev->common->queue_size);
>> -
>> -}
>> -
>> -/*
>> - * vp_modern_get_queue_size - get size for a virtqueue
>> - * @mdev: the modern virtio-pci device
>> - * @index: the queue index
>> - *
>> - * Returns the size of the virtqueue
>> - */
>> -static u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
>> -				    u16 index)
>> -{
>> -	vp_iowrite16(index, &mdev->common->queue_select);
>> -
>> -	return vp_ioread16(&mdev->common->queue_size);
>> -
>> -}
>> -
>> -/*
>> - * vp_modern_get_num_queues - get the number of virtqueues
>> - * @mdev: the modern virtio-pci device
>> - *
>> - * Returns the number of virtqueues
>> - */
>> -static u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev)
>> -{
>> -	return vp_ioread16(&mdev->common->num_queues);
>> -}
>> -
>> -/*
>> - * vp_modern_get_queue_notify_off - get notification offset for a virtqueue
>> - * @mdev: the modern virtio-pci device
>> - * @index: the queue index
>> - *
>> - * Returns the notification offset for a virtqueue
>> - */
>> -static u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev,
>> -					  u16 index)
>> -{
>> -	vp_iowrite16(index, &mdev->common->queue_select);
>> -
>> -	return vp_ioread16(&mdev->common->queue_notify_off);
>> -}
>> -
>>   /* virtio config->finalize_features() implementation */
>>   static int vp_finalize_features(struct virtio_device *vdev)
>>   {
>> @@ -429,19 +134,6 @@ static void vp_set(struct virtio_device *vdev, unsigned offset,
>>   	}
>>   }
>>   
>> -/*
>> - * vp_modern_generation - get the device genreation
>> - * @mdev: the modern virtio-pci device
>> - *
>> - * Returns the genreation read from device
>> - */
>> -static u32 vp_modern_generation(struct virtio_pci_modern_device *mdev)
>> -{
>> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> -
>> -	return vp_ioread8(&cfg->config_generation);
>> -}
>> -
>>   static u32 vp_generation(struct virtio_device *vdev)
>>   {
>>   	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
>> @@ -449,19 +141,6 @@ static u32 vp_generation(struct virtio_device *vdev)
>>   	return vp_modern_generation(&vp_dev->mdev);
>>   }
>>   
>> -/*
>> - * vp_modern_get_status - get the device status
>> - * @mdev: the modern virtio-pci device
>> - *
>> - * Returns the status read from device
>> - */
>> -static u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev)
>> -{
>> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> -
>> -	return vp_ioread8(&cfg->device_status);
>> -}
>> -
>>   /* config->{get,set}_status() implementations */
>>   static u8 vp_get_status(struct virtio_device *vdev)
>>   {
>> @@ -470,19 +149,6 @@ static u8 vp_get_status(struct virtio_device *vdev)
>>   	return vp_modern_get_status(&vp_dev->mdev);
>>   }
>>   
>> -/*
>> - * vp_modern_set_status - set status to device
>> - * @mdev: the modern virtio-pci device
>> - * @status: the status set to device
>> - */
>> -static void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
>> -				 u8 status)
>> -{
>> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> -
>> -	vp_iowrite8(status, &cfg->device_status);
>> -}
>> -
>>   static void vp_set_status(struct virtio_device *vdev, u8 status)
>>   {
>>   	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
>> @@ -510,25 +176,6 @@ static void vp_reset(struct virtio_device *vdev)
>>   	vp_synchronize_vectors(vdev);
>>   }
>>   
>> -/*
>> - * vp_modern_config_vector - set the vector for config interrupt
>> - * @mdev: the modern virtio-pci device
>> - * @vector: the config vector
>> - *
>> - * Returns the config vector read from the device
>> - */
>> -static u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev,
>> -				   u16 vector)
>> -{
>> -	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> -
>> -	/* Setup the vector used for configuration events */
>> -	vp_iowrite16(vector, &cfg->msix_config);
>> -	/* Verify we had enough resources to assign the vector */
>> -	/* Will also flush the write out to device */
>> -	return vp_ioread16(&cfg->msix_config);
>> -}
>> -
>>   static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
>>   {
>>   	return vp_modern_config_vector(&vp_dev->mdev, vector);
>> @@ -789,253 +436,6 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
>>   	.get_shm_region  = vp_get_shm_region,
>>   };
>>   
>> -/**
>> - * virtio_pci_find_capability - walk capabilities to find device info.
>> - * @dev: the pci device
>> - * @cfg_type: the VIRTIO_PCI_CAP_* value we seek
>> - * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
>> - * @bars: the bitmask of BARs
>> - *
>> - * Returns offset of the capability, or 0.
>> - */
>> -static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
>> -					     u32 ioresource_types, int *bars)
>> -{
>> -	int pos;
>> -
>> -	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
>> -	     pos > 0;
>> -	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
>> -		u8 type, bar;
>> -		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
>> -							 cfg_type),
>> -				     &type);
>> -		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
>> -							 bar),
>> -				     &bar);
>> -
>> -		/* Ignore structures with reserved BAR values */
>> -		if (bar > 0x5)
>> -			continue;
>> -
>> -		if (type == cfg_type) {
>> -			if (pci_resource_len(dev, bar) &&
>> -			    pci_resource_flags(dev, bar) & ioresource_types) {
>> -				*bars |= (1 << bar);
>> -				return pos;
>> -			}
>> -		}
>> -	}
>> -	return 0;
>> -}
>> -
>> -/* This is part of the ABI.  Don't screw with it. */
>> -static inline void check_offsets(void)
>> -{
>> -	/* Note: disk space was harmed in compilation of this function. */
>> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR !=
>> -		     offsetof(struct virtio_pci_cap, cap_vndr));
>> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT !=
>> -		     offsetof(struct virtio_pci_cap, cap_next));
>> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN !=
>> -		     offsetof(struct virtio_pci_cap, cap_len));
>> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE !=
>> -		     offsetof(struct virtio_pci_cap, cfg_type));
>> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR !=
>> -		     offsetof(struct virtio_pci_cap, bar));
>> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET !=
>> -		     offsetof(struct virtio_pci_cap, offset));
>> -	BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH !=
>> -		     offsetof(struct virtio_pci_cap, length));
>> -	BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT !=
>> -		     offsetof(struct virtio_pci_notify_cap,
>> -			      notify_off_multiplier));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT !=
>> -		     offsetof(struct virtio_pci_common_cfg,
>> -			      device_feature_select));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF !=
>> -		     offsetof(struct virtio_pci_common_cfg, device_feature));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT !=
>> -		     offsetof(struct virtio_pci_common_cfg,
>> -			      guest_feature_select));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF !=
>> -		     offsetof(struct virtio_pci_common_cfg, guest_feature));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX !=
>> -		     offsetof(struct virtio_pci_common_cfg, msix_config));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ !=
>> -		     offsetof(struct virtio_pci_common_cfg, num_queues));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS !=
>> -		     offsetof(struct virtio_pci_common_cfg, device_status));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION !=
>> -		     offsetof(struct virtio_pci_common_cfg, config_generation));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT !=
>> -		     offsetof(struct virtio_pci_common_cfg, queue_select));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE !=
>> -		     offsetof(struct virtio_pci_common_cfg, queue_size));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX !=
>> -		     offsetof(struct virtio_pci_common_cfg, queue_msix_vector));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE !=
>> -		     offsetof(struct virtio_pci_common_cfg, queue_enable));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF !=
>> -		     offsetof(struct virtio_pci_common_cfg, queue_notify_off));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO !=
>> -		     offsetof(struct virtio_pci_common_cfg, queue_desc_lo));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI !=
>> -		     offsetof(struct virtio_pci_common_cfg, queue_desc_hi));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO !=
>> -		     offsetof(struct virtio_pci_common_cfg, queue_avail_lo));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI !=
>> -		     offsetof(struct virtio_pci_common_cfg, queue_avail_hi));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO !=
>> -		     offsetof(struct virtio_pci_common_cfg, queue_used_lo));
>> -	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI !=
>> -		     offsetof(struct virtio_pci_common_cfg, queue_used_hi));
>> -}
>> -
>> -/*
>> - * vp_modern_probe: probe the modern virtio pci device, note that the
>> - * caller is required to enable PCI device before calling this function.
>> - * @mdev: the modern virtio-pci device
>> - *
>> - * Return 0 on succeed otherwise fail
>> - */
>> -static int vp_modern_probe(struct virtio_pci_modern_device *mdev)
>> -{
>> -	struct pci_dev *pci_dev = mdev->pci_dev;
>> -	int err, common, isr, notify, device;
>> -	u32 notify_length;
>> -	u32 notify_offset;
>> -
>> -	check_offsets();
>> -
>> -	mdev->pci_dev = pci_dev;
>> -
>> -	/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
>> -	if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
>> -		return -ENODEV;
>> -
>> -	if (pci_dev->device < 0x1040) {
>> -		/* Transitional devices: use the PCI subsystem device id as
>> -		 * virtio device id, same as legacy driver always did.
>> -		 */
>> -		mdev->id.device = pci_dev->subsystem_device;
>> -	} else {
>> -		/* Modern devices: simply use PCI device id, but start from 0x1040. */
>> -		mdev->id.device = pci_dev->device - 0x1040;
>> -	}
>> -	mdev->id.vendor = pci_dev->subsystem_vendor;
>> -
>> -	/* check for a common config: if not, use legacy mode (bar 0). */
>> -	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
>> -					    IORESOURCE_IO | IORESOURCE_MEM,
>> -					    &mdev->modern_bars);
>> -	if (!common) {
>> -		dev_info(&pci_dev->dev,
>> -			 "virtio_pci: leaving for legacy driver\n");
>> -		return -ENODEV;
>> -	}
>> -
>> -	/* If common is there, these should be too... */
>> -	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
>> -					 IORESOURCE_IO | IORESOURCE_MEM,
>> -					 &mdev->modern_bars);
>> -	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
>> -					    IORESOURCE_IO | IORESOURCE_MEM,
>> -					    &mdev->modern_bars);
>> -	if (!isr || !notify) {
>> -		dev_err(&pci_dev->dev,
>> -			"virtio_pci: missing capabilities %i/%i/%i\n",
>> -			common, isr, notify);
>> -		return -EINVAL;
>> -	}
>> -
>> -	err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
>> -	if (err)
>> -		err = dma_set_mask_and_coherent(&pci_dev->dev,
>> -						DMA_BIT_MASK(32));
>> -	if (err)
>> -		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
>> -
>> -	/* Device capability is only mandatory for devices that have
>> -	 * device-specific configuration.
>> -	 */
>> -	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
>> -					    IORESOURCE_IO | IORESOURCE_MEM,
>> -					    &mdev->modern_bars);
>> -
>> -	err = pci_request_selected_regions(pci_dev, mdev->modern_bars,
>> -					   "virtio-pci-modern");
>> -	if (err)
>> -		return err;
>> -
>> -	err = -EINVAL;
>> -	mdev->common = vp_modern_map_capability(mdev, common,
>> -				      sizeof(struct virtio_pci_common_cfg), 4,
>> -				      0, sizeof(struct virtio_pci_common_cfg),
>> -				      NULL);
>> -	if (!mdev->common)
>> -		goto err_map_common;
>> -	mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1,
>> -					     0, 1,
>> -					     NULL);
>> -	if (!mdev->isr)
>> -		goto err_map_isr;
>> -
>> -	/* Read notify_off_multiplier from config space. */
>> -	pci_read_config_dword(pci_dev,
>> -			      notify + offsetof(struct virtio_pci_notify_cap,
>> -						notify_off_multiplier),
>> -			      &mdev->notify_offset_multiplier);
>> -	/* Read notify length and offset from config space. */
>> -	pci_read_config_dword(pci_dev,
>> -			      notify + offsetof(struct virtio_pci_notify_cap,
>> -						cap.length),
>> -			      &notify_length);
>> -
>> -	pci_read_config_dword(pci_dev,
>> -			      notify + offsetof(struct virtio_pci_notify_cap,
>> -						cap.offset),
>> -			      &notify_offset);
>> -
>> -	/* We don't know how many VQs we'll map, ahead of the time.
>> -	 * If notify length is small, map it all now.
>> -	 * Otherwise, map each VQ individually later.
>> -	 */
>> -	if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) {
>> -		mdev->notify_base = vp_modern_map_capability(mdev, notify,
>> -							     2, 2,
>> -							     0, notify_length,
>> -							     &mdev->notify_len);
>> -		if (!mdev->notify_base)
>> -			goto err_map_notify;
>> -	} else {
>> -		mdev->notify_map_cap = notify;
>> -	}
>> -
>> -	/* Again, we don't know how much we should map, but PAGE_SIZE
>> -	 * is more than enough for all existing devices.
>> -	 */
>> -	if (device) {
>> -		mdev->device = vp_modern_map_capability(mdev, device, 0, 4,
>> -							0, PAGE_SIZE,
>> -							&mdev->device_len);
>> -		if (!mdev->device)
>> -			goto err_map_device;
>> -	}
>> -
>> -	return 0;
>> -
>> -err_map_device:
>> -	if (mdev->notify_base)
>> -		pci_iounmap(pci_dev, mdev->notify_base);
>> -err_map_notify:
>> -	pci_iounmap(pci_dev, mdev->isr);
>> -err_map_isr:
>> -	pci_iounmap(pci_dev, mdev->common);
>> -err_map_common:
>> -	return err;
>> -}
>> -
>>   /* the PCI probing function */
>>   int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
>>   {
>> @@ -1063,23 +463,6 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
>>   	return 0;
>>   }
>>   
>> -/*
>> - * vp_modern_probe: remove and cleanup the modern virtio pci device
>> - * @mdev: the modern virtio-pci device
>> - */
>> -static void vp_modern_remove(struct virtio_pci_modern_device *mdev)
>> -{
>> -	struct pci_dev *pci_dev = mdev->pci_dev;
>> -
>> -	if (mdev->device)
>> -		pci_iounmap(pci_dev, mdev->device);
>> -	if (mdev->notify_base)
>> -		pci_iounmap(pci_dev, mdev->notify_base);
>> -	pci_iounmap(pci_dev, mdev->isr);
>> -	pci_iounmap(pci_dev, mdev->common);
>> -	pci_release_selected_regions(pci_dev, mdev->modern_bars);
>> -}
>> -
>>   void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
>>   {
>>   	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
>> diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
>> new file mode 100644
>> index 000000000000..cbd667496bb1
>> --- /dev/null
>> +++ b/drivers/virtio/virtio_pci_modern_dev.c
>> @@ -0,0 +1,599 @@
>> +// SPDX-License-Identifier: GPL-2.0-or-later
>> +
>> +#include <linux/virtio_pci_modern.h>
>> +#include <linux/module.h>
>> +#include <linux/pci.h>
>> +
>> +/*
>> + * vp_modern_map_capability - map a part of virtio pci capability
>> + * @mdev: the modern virtio-pci device
>> + * @off: offset of the capability
>> + * @minlen: minimal length of the capability
>> + * @align: align requirement
>> + * @start: start from the capability
>> + * @size: map size
>> + * @len: the length that is actually mapped
>> + *
>> + * Returns the io address of for the part of the capability
>> + */
>> +void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off,
>> +				       size_t minlen,
>> +				       u32 align,
>> +				       u32 start, u32 size,
>> +				       size_t *len)
>> +{
>> +	struct pci_dev *dev = mdev->pci_dev;
>> +	u8 bar;
>> +	u32 offset, length;
>> +	void __iomem *p;
>> +
>> +	pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap,
>> +						 bar),
>> +			     &bar);
>> +	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset),
>> +			     &offset);
>> +	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length),
>> +			      &length);
>> +
>> +	if (length <= start) {
>> +		dev_err(&dev->dev,
>> +			"virtio_pci: bad capability len %u (>%u expected)\n",
>> +			length, start);
>> +		return NULL;
>> +	}
>> +
>> +	if (length - start < minlen) {
>> +		dev_err(&dev->dev,
>> +			"virtio_pci: bad capability len %u (>=%zu expected)\n",
>> +			length, minlen);
>> +		return NULL;
>> +	}
>> +
>> +	length -= start;
>> +
>> +	if (start + offset < offset) {
>> +		dev_err(&dev->dev,
>> +			"virtio_pci: map wrap-around %u+%u\n",
>> +			start, offset);
>> +		return NULL;
>> +	}
>> +
>> +	offset += start;
>> +
>> +	if (offset & (align - 1)) {
>> +		dev_err(&dev->dev,
>> +			"virtio_pci: offset %u not aligned to %u\n",
>> +			offset, align);
>> +		return NULL;
>> +	}
>> +
>> +	if (length > size)
>> +		length = size;
>> +
>> +	if (len)
>> +		*len = length;
>> +
>> +	if (minlen + offset < minlen ||
>> +	    minlen + offset > pci_resource_len(dev, bar)) {
>> +		dev_err(&dev->dev,
>> +			"virtio_pci: map virtio %zu@%u "
>> +			"out of range on bar %i length %lu\n",
>> +			minlen, offset,
>> +			bar, (unsigned long)pci_resource_len(dev, bar));
>> +		return NULL;
>> +	}
>> +
>> +	p = pci_iomap_range(dev, bar, offset, length);
>> +	if (!p)
>> +		dev_err(&dev->dev,
>> +			"virtio_pci: unable to map virtio %u@%u on bar %i\n",
>> +			length, offset, bar);
>> +	return p;
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_map_capability);
>> +
>> +/**
>> + * virtio_pci_find_capability - walk capabilities to find device info.
>> + * @dev: the pci device
>> + * @cfg_type: the VIRTIO_PCI_CAP_* value we seek
>> + * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
>> + * @bars: the bitmask of BARs
>> + *
>> + * Returns offset of the capability, or 0.
>> + */
>> +static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
>> +					     u32 ioresource_types, int *bars)
>> +{
>> +	int pos;
>> +
>> +	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
>> +	     pos > 0;
>> +	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
>> +		u8 type, bar;
>> +		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
>> +							 cfg_type),
>> +				     &type);
>> +		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
>> +							 bar),
>> +				     &bar);
>> +
>> +		/* Ignore structures with reserved BAR values */
>> +		if (bar > 0x5)
>> +			continue;
>> +
>> +		if (type == cfg_type) {
>> +			if (pci_resource_len(dev, bar) &&
>> +			    pci_resource_flags(dev, bar) & ioresource_types) {
>> +				*bars |= (1 << bar);
>> +				return pos;
>> +			}
>> +		}
>> +	}
>> +	return 0;
>> +}
>> +
>> +/* This is part of the ABI.  Don't screw with it. */
>> +static inline void check_offsets(void)
>> +{
>> +	/* Note: disk space was harmed in compilation of this function. */
>> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR !=
>> +		     offsetof(struct virtio_pci_cap, cap_vndr));
>> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT !=
>> +		     offsetof(struct virtio_pci_cap, cap_next));
>> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN !=
>> +		     offsetof(struct virtio_pci_cap, cap_len));
>> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE !=
>> +		     offsetof(struct virtio_pci_cap, cfg_type));
>> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR !=
>> +		     offsetof(struct virtio_pci_cap, bar));
>> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET !=
>> +		     offsetof(struct virtio_pci_cap, offset));
>> +	BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH !=
>> +		     offsetof(struct virtio_pci_cap, length));
>> +	BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT !=
>> +		     offsetof(struct virtio_pci_notify_cap,
>> +			      notify_off_multiplier));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT !=
>> +		     offsetof(struct virtio_pci_common_cfg,
>> +			      device_feature_select));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF !=
>> +		     offsetof(struct virtio_pci_common_cfg, device_feature));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT !=
>> +		     offsetof(struct virtio_pci_common_cfg,
>> +			      guest_feature_select));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF !=
>> +		     offsetof(struct virtio_pci_common_cfg, guest_feature));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX !=
>> +		     offsetof(struct virtio_pci_common_cfg, msix_config));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ !=
>> +		     offsetof(struct virtio_pci_common_cfg, num_queues));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS !=
>> +		     offsetof(struct virtio_pci_common_cfg, device_status));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION !=
>> +		     offsetof(struct virtio_pci_common_cfg, config_generation));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT !=
>> +		     offsetof(struct virtio_pci_common_cfg, queue_select));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE !=
>> +		     offsetof(struct virtio_pci_common_cfg, queue_size));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX !=
>> +		     offsetof(struct virtio_pci_common_cfg, queue_msix_vector));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE !=
>> +		     offsetof(struct virtio_pci_common_cfg, queue_enable));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF !=
>> +		     offsetof(struct virtio_pci_common_cfg, queue_notify_off));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO !=
>> +		     offsetof(struct virtio_pci_common_cfg, queue_desc_lo));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI !=
>> +		     offsetof(struct virtio_pci_common_cfg, queue_desc_hi));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO !=
>> +		     offsetof(struct virtio_pci_common_cfg, queue_avail_lo));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI !=
>> +		     offsetof(struct virtio_pci_common_cfg, queue_avail_hi));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO !=
>> +		     offsetof(struct virtio_pci_common_cfg, queue_used_lo));
>> +	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI !=
>> +		     offsetof(struct virtio_pci_common_cfg, queue_used_hi));
>> +}
>> +
>> +/*
>> + * vp_modern_probe: probe the modern virtio pci device, note that the
>> + * caller is required to enable PCI device before calling this function.
>> + * @mdev: the modern virtio-pci device
>> + *
>> + * Return 0 on succeed otherwise fail
>> + */
>> +int vp_modern_probe(struct virtio_pci_modern_device *mdev)
>> +{
>> +	struct pci_dev *pci_dev = mdev->pci_dev;
>> +	int err, common, isr, notify, device;
>> +	u32 notify_length;
>> +	u32 notify_offset;
>> +
>> +	check_offsets();
>> +
>> +	mdev->pci_dev = pci_dev;
>> +
>> +	/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
>> +	if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
>> +		return -ENODEV;
>> +
>> +	if (pci_dev->device < 0x1040) {
>> +		/* Transitional devices: use the PCI subsystem device id as
>> +		 * virtio device id, same as legacy driver always did.
>> +		 */
>> +		mdev->id.device = pci_dev->subsystem_device;
>> +	} else {
>> +		/* Modern devices: simply use PCI device id, but start from 0x1040. */
>> +		mdev->id.device = pci_dev->device - 0x1040;
>> +	}
>> +	mdev->id.vendor = pci_dev->subsystem_vendor;
>> +
>> +	/* check for a common config: if not, use legacy mode (bar 0). */
>> +	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
>> +					    IORESOURCE_IO | IORESOURCE_MEM,
>> +					    &mdev->modern_bars);
>> +	if (!common) {
>> +		dev_info(&pci_dev->dev,
>> +			 "virtio_pci: leaving for legacy driver\n");
>> +		return -ENODEV;
>> +	}
>> +
>> +	/* If common is there, these should be too... */
>> +	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
>> +					 IORESOURCE_IO | IORESOURCE_MEM,
>> +					 &mdev->modern_bars);
>> +	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
>> +					    IORESOURCE_IO | IORESOURCE_MEM,
>> +					    &mdev->modern_bars);
>> +	if (!isr || !notify) {
>> +		dev_err(&pci_dev->dev,
>> +			"virtio_pci: missing capabilities %i/%i/%i\n",
>> +			common, isr, notify);
>> +		return -EINVAL;
>> +	}
>> +
>> +	err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
>> +	if (err)
>> +		err = dma_set_mask_and_coherent(&pci_dev->dev,
>> +						DMA_BIT_MASK(32));
>> +	if (err)
>> +		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
>> +
>> +	/* Device capability is only mandatory for devices that have
>> +	 * device-specific configuration.
>> +	 */
>> +	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
>> +					    IORESOURCE_IO | IORESOURCE_MEM,
>> +					    &mdev->modern_bars);
>> +
>> +	err = pci_request_selected_regions(pci_dev, mdev->modern_bars,
>> +					   "virtio-pci-modern");
>> +	if (err)
>> +		return err;
>> +
>> +	err = -EINVAL;
>> +	mdev->common = vp_modern_map_capability(mdev, common,
>> +				      sizeof(struct virtio_pci_common_cfg), 4,
>> +				      0, sizeof(struct virtio_pci_common_cfg),
>> +				      NULL);
>> +	if (!mdev->common)
>> +		goto err_map_common;
>> +	mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1,
>> +					     0, 1,
>> +					     NULL);
>> +	if (!mdev->isr)
>> +		goto err_map_isr;
>> +
>> +	/* Read notify_off_multiplier from config space. */
>> +	pci_read_config_dword(pci_dev,
>> +			      notify + offsetof(struct virtio_pci_notify_cap,
>> +						notify_off_multiplier),
>> +			      &mdev->notify_offset_multiplier);
>> +	/* Read notify length and offset from config space. */
>> +	pci_read_config_dword(pci_dev,
>> +			      notify + offsetof(struct virtio_pci_notify_cap,
>> +						cap.length),
>> +			      &notify_length);
>> +
>> +	pci_read_config_dword(pci_dev,
>> +			      notify + offsetof(struct virtio_pci_notify_cap,
>> +						cap.offset),
>> +			      &notify_offset);
>> +
>> +	/* We don't know how many VQs we'll map, ahead of the time.
>> +	 * If notify length is small, map it all now.
>> +	 * Otherwise, map each VQ individually later.
>> +	 */
>> +	if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) {
>> +		mdev->notify_base = vp_modern_map_capability(mdev, notify,
>> +							     2, 2,
>> +							     0, notify_length,
>> +							     &mdev->notify_len);
>> +		if (!mdev->notify_base)
>> +			goto err_map_notify;
>> +	} else {
>> +		mdev->notify_map_cap = notify;
>> +	}
>> +
>> +	/* Again, we don't know how much we should map, but PAGE_SIZE
>> +	 * is more than enough for all existing devices.
>> +	 */
>> +	if (device) {
>> +		mdev->device = vp_modern_map_capability(mdev, device, 0, 4,
>> +							0, PAGE_SIZE,
>> +							&mdev->device_len);
>> +		if (!mdev->device)
>> +			goto err_map_device;
>> +	}
>> +
>> +	return 0;
>> +
>> +err_map_device:
>> +	if (mdev->notify_base)
>> +		pci_iounmap(pci_dev, mdev->notify_base);
>> +err_map_notify:
>> +	pci_iounmap(pci_dev, mdev->isr);
>> +err_map_isr:
>> +	pci_iounmap(pci_dev, mdev->common);
>> +err_map_common:
>> +	return err;
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_probe);
>> +
>> +/*
>> + * vp_modern_probe: remove and cleanup the modern virtio pci device
>> + * @mdev: the modern virtio-pci device
>> + */
>> +void vp_modern_remove(struct virtio_pci_modern_device *mdev)
>> +{
>> +	struct pci_dev *pci_dev = mdev->pci_dev;
>> +
>> +	if (mdev->device)
>> +		pci_iounmap(pci_dev, mdev->device);
>> +	if (mdev->notify_base)
>> +		pci_iounmap(pci_dev, mdev->notify_base);
>> +	pci_iounmap(pci_dev, mdev->isr);
>> +	pci_iounmap(pci_dev, mdev->common);
>> +	pci_release_selected_regions(pci_dev, mdev->modern_bars);
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_remove);
>> +
>> +/*
>> + * vp_modern_get_features - get features from device
>> + * @mdev: the modern virtio-pci device
>> + *
>> + * Returns the features read from the device
>> + */
>> +u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev)
>> +{
>> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> +
>> +	u64 features;
>> +
>> +	vp_iowrite32(0, &cfg->device_feature_select);
>> +	features = vp_ioread32(&cfg->device_feature);
>> +	vp_iowrite32(1, &cfg->device_feature_select);
>> +	features |= ((u64)vp_ioread32(&cfg->device_feature) << 32);
>> +
>> +	return features;
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_get_features);
>> +
>> +/*
>> + * vp_modern_set_features - set features to device
>> + * @mdev: the modern virtio-pci device
>> + * @features: the features set to device
>> + */
>> +void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
>> +			    u64 features)
>> +{
>> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> +
>> +	vp_iowrite32(0, &cfg->guest_feature_select);
>> +	vp_iowrite32((u32)features, &cfg->guest_feature);
>> +	vp_iowrite32(1, &cfg->guest_feature_select);
>> +	vp_iowrite32(features >> 32, &cfg->guest_feature);
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_set_features);
>> +
>> +/*
>> + * vp_modern_generation - get the device genreation
>> + * @mdev: the modern virtio-pci device
>> + *
>> + * Returns the genreation read from device
>> + */
>> +u32 vp_modern_generation(struct virtio_pci_modern_device *mdev)
>> +{
>> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> +
>> +	return vp_ioread8(&cfg->config_generation);
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_generation);
>> +
>> +/*
>> + * vp_modern_get_status - get the device status
>> + * @mdev: the modern virtio-pci device
>> + *
>> + * Returns the status read from device
>> + */
>> +u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev)
>> +{
>> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> +
>> +	return vp_ioread8(&cfg->device_status);
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_get_status);
>> +
>> +/*
>> + * vp_modern_set_status - set status to device
>> + * @mdev: the modern virtio-pci device
>> + * @status: the status set to device
>> + */
>> +void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
>> +				 u8 status)
>> +{
>> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> +
>> +	vp_iowrite8(status, &cfg->device_status);
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_set_status);
>> +
>> +/*
>> + * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue
>> + * @mdev: the modern virtio-pci device
>> + * @index: queue index
>> + * @vector: the config vector
>> + *
>> + * Returns the config vector read from the device
>> + */
>> +u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
>> +			   u16 index, u16 vector)
>> +{
>> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> +
>> +	vp_iowrite16(index, &cfg->queue_select);
>> +	vp_iowrite16(vector, &cfg->queue_msix_vector);
>> +	/* Flush the write out to device */
>> +	return vp_ioread16(&cfg->queue_msix_vector);
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_queue_vector);
>> +
>> +/*
>> + * vp_modern_config_vector - set the vector for config interrupt
>> + * @mdev: the modern virtio-pci device
>> + * @vector: the config vector
>> + *
>> + * Returns the config vector read from the device
>> + */
>> +u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev,
>> +			    u16 vector)
>> +{
>> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> +
>> +	/* Setup the vector used for configuration events */
>> +	vp_iowrite16(vector, &cfg->msix_config);
>> +	/* Verify we had enough resources to assign the vector */
>> +	/* Will also flush the write out to device */
>> +	return vp_ioread16(&cfg->msix_config);
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_config_vector);
>> +
>> +/*
>> + * vp_modern_queue_address - set the virtqueue address
>> + * @mdev: the modern virtio-pci device
>> + * @index: the queue index
>> + * @desc_addr: address of the descriptor area
>> + * @driver_addr: address of the driver area
>> + * @device_addr: address of the device area
>> + */
>> +void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
>> +			     u16 index, u64 desc_addr, u64 driver_addr,
>> +			     u64 device_addr)
>> +{
>> +	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
>> +
>> +	vp_iowrite16(index, &cfg->queue_select);
>> +
>> +	vp_iowrite64_twopart(desc_addr, &cfg->queue_desc_lo,
>> +			     &cfg->queue_desc_hi);
>> +	vp_iowrite64_twopart(driver_addr, &cfg->queue_avail_lo,
>> +			     &cfg->queue_avail_hi);
>> +	vp_iowrite64_twopart(device_addr, &cfg->queue_used_lo,
>> +			     &cfg->queue_used_hi);
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_queue_address);
>> +
>> +/*
>> + * vp_modern_set_queue_enable - enable a virtqueue
>> + * @mdev: the modern virtio-pci device
>> + * @index: the queue index
>> + * @enable: whether the virtqueue is enable or not
>> + */
>> +void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev,
>> +				u16 index, bool enable)
>> +{
>> +	vp_iowrite16(index, &mdev->common->queue_select);
>> +	vp_iowrite16(enable, &mdev->common->queue_enable);
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_set_queue_enable);
>> +
>> +/*
>> + * vp_modern_get_queue_enable - enable a virtqueue
>> + * @mdev: the modern virtio-pci device
>> + * @index: the queue index
>> + *
>> + * Returns whether a virtqueue is enabled or not
>> + */
>> +bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
>> +				u16 index)
>> +{
>> +	vp_iowrite16(index, &mdev->common->queue_select);
>> +
>> +	return vp_ioread16(&mdev->common->queue_enable);
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_get_queue_enable);
>> +
>> +/*
>> + * vp_modern_set_queue_size - set size for a virtqueue
>> + * @mdev: the modern virtio-pci device
>> + * @index: the queue index
>> + * @size: the size of the virtqueue
>> + */
>> +void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev,
>> +			      u16 index, u16 size)
>> +{
>> +	vp_iowrite16(index, &mdev->common->queue_select);
>> +	vp_iowrite16(size, &mdev->common->queue_size);
>> +
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_set_queue_size);
>> +
>> +/*
>> + * vp_modern_get_queue_size - get size for a virtqueue
>> + * @mdev: the modern virtio-pci device
>> + * @index: the queue index
>> + *
>> + * Returns the size of the virtqueue
>> + */
>> +u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
>> +			     u16 index)
>> +{
>> +	vp_iowrite16(index, &mdev->common->queue_select);
>> +
>> +	return vp_ioread16(&mdev->common->queue_size);
>> +
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_get_queue_size);
>> +
>> +/*
>> + * vp_modern_get_num_queues - get the number of virtqueues
>> + * @mdev: the modern virtio-pci device
>> + *
>> + * Returns the number of virtqueues
>> + */
>> +u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev)
>> +{
>> +	return vp_ioread16(&mdev->common->num_queues);
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_get_num_queues);
>> +
>> +/*
>> + * vp_modern_get_queue_notify_off - get notification offset for a virtqueue
>> + * @mdev: the modern virtio-pci device
>> + * @index: the queue index
>> + *
>> + * Returns the notification offset for a virtqueue
>> + */
>> +u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev,
>> +				   u16 index)
>> +{
>> +	vp_iowrite16(index, &mdev->common->queue_select);
>> +
>> +	return vp_ioread16(&mdev->common->queue_notify_off);
>> +}
>> +EXPORT_SYMBOL_GPL(vp_modern_get_queue_notify_off);
>> +
>> +MODULE_VERSION("0.1");
>> +MODULE_DESCRIPTION("Modern Virtio PCI Device");
>> +MODULE_AUTHOR("Jason Wang <jasowang@redhat.com>");
>> +MODULE_LICENSE("GPL");
>> diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h
>> new file mode 100644
>> index 000000000000..f26acbeec965
>> --- /dev/null
>> +++ b/include/linux/virtio_pci_modern.h
>> @@ -0,0 +1,111 @@
>> +/* SPDX-License-Identifier: GPL-2.0 */
>> +#ifndef _LINUX_VIRTIO_PCI_MODERN_H
>> +#define _LINUX_VIRTIO_PCI_MODERN_H
>> +
>> +#include <linux/pci.h>
>> +#include <linux/virtio_pci.h>
>> +
>> +struct virtio_pci_modern_device {
>> +	struct pci_dev *pci_dev;
>> +
>> +	struct virtio_pci_common_cfg __iomem *common;
>> +	/* Device-specific data (non-legacy mode)  */
>> +	void __iomem *device;
>> +	/* Base of vq notifications (non-legacy mode). */
>> +	void __iomem *notify_base;
>> +	/* Where to read and clear interrupt */
>> +	u8 __iomem *isr;
>> +
>> +	/* So we can sanity-check accesses. */
>> +	size_t notify_len;
>> +	size_t device_len;
>> +
>> +	/* Capability for when we need to map notifications per-vq. */
>> +	int notify_map_cap;
>> +
>> +	/* Multiply queue_notify_off by this value. (non-legacy mode). */
>> +	u32 notify_offset_multiplier;
>> +
>> +	int modern_bars;
>> +
>> +	struct virtio_device_id id;
>> +};
>> +
>> +/*
>> + * Type-safe wrappers for io accesses.
>> + * Use these to enforce at compile time the following spec requirement:
>> + *
>> + * The driver MUST access each field using the “natural” access
>> + * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses
>> + * for 16-bit fields and 8-bit accesses for 8-bit fields.
>> + */
>> +static inline u8 vp_ioread8(const u8 __iomem *addr)
>> +{
>> +	return ioread8(addr);
>> +}
>> +static inline u16 vp_ioread16 (const __le16 __iomem *addr)
>> +{
>> +	return ioread16(addr);
>> +}
>> +
>> +static inline u32 vp_ioread32(const __le32 __iomem *addr)
>> +{
>> +	return ioread32(addr);
>> +}
>> +
>> +static inline void vp_iowrite8(u8 value, u8 __iomem *addr)
>> +{
>> +	iowrite8(value, addr);
>> +}
>> +
>> +static inline void vp_iowrite16(u16 value, __le16 __iomem *addr)
>> +{
>> +	iowrite16(value, addr);
>> +}
>> +
>> +static inline void vp_iowrite32(u32 value, __le32 __iomem *addr)
>> +{
>> +	iowrite32(value, addr);
>> +}
>> +
>> +static inline void vp_iowrite64_twopart(u64 val,
>> +					__le32 __iomem *lo,
>> +					__le32 __iomem *hi)
>> +{
>> +	vp_iowrite32((u32)val, lo);
>> +	vp_iowrite32(val >> 32, hi);
>> +}
>> +
>> +u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev);
>> +void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
>> +		     u64 features);
>> +u32 vp_modern_generation(struct virtio_pci_modern_device *mdev);
>> +u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev);
>> +void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
>> +		   u8 status);
>> +u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
>> +			   u16 idx, u16 vector);
>> +u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev,
>> +		     u16 vector);
>> +void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
>> +			     u16 index, u64 desc_addr, u64 driver_addr,
>> +			     u64 device_addr);
>> +void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev,
>> +				u16 idx, bool enable);
>> +bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
>> +				u16 idx);
>> +void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev,
>> +			      u16 idx, u16 size);
>> +u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
>> +			     u16 idx);
>> +u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev);
>> +u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev,
>> +				   u16 idx);
>> +void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off,
>> +				       size_t minlen,
>> +				       u32 align,
>> +				       u32 start, u32 size,
>> +				       size_t *len);
>> +int vp_modern_probe(struct virtio_pci_modern_device *mdev);
>> +void vp_modern_remove(struct virtio_pci_modern_device *mdev);
>> +#endif