Merge tag 'vfio-v5.15-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Fix dma-valid return WAITED implementation (Anthony Yznaga)

 - SPDX license cleanups (Cai Huoqing)

 - Split vfio-pci-core from vfio-pci and enhance PCI driver matching to
   support future vendor provided vfio-pci variants (Yishai Hadas, Max
   Gurtovoy, Jason Gunthorpe)

 - Replace duplicated reflck with core support for managing first open,
   last close, and device sets (Jason Gunthorpe, Max Gurtovoy, Yishai
   Hadas)

 - Fix non-modular mdev support and don't nag about request callback
   support (Christoph Hellwig)

 - Add semaphore to protect instruction intercept handler and replace
   open-coded locks in vfio-ap driver (Tony Krowiak)

 - Convert vfio-ap to vfio_register_group_dev() API (Jason Gunthorpe)

* tag 'vfio-v5.15-rc1' of git://github.com/awilliam/linux-vfio: (37 commits)
  vfio/pci: Introduce vfio_pci_core.ko
  vfio: Use kconfig if XX/endif blocks instead of repeating 'depends on'
  vfio: Use select for eventfd
  PCI / VFIO: Add 'override_only' support for VFIO PCI sub system
  PCI: Add 'override_only' field to struct pci_device_id
  vfio/pci: Move module parameters to vfio_pci.c
  vfio/pci: Move igd initialization to vfio_pci.c
  vfio/pci: Split the pci_driver code out of vfio_pci_core.c
  vfio/pci: Include vfio header in vfio_pci_core.h
  vfio/pci: Rename ops functions to fit core namings
  vfio/pci: Rename vfio_pci_device to vfio_pci_core_device
  vfio/pci: Rename vfio_pci_private.h to vfio_pci_core.h
  vfio/pci: Rename vfio_pci.c to vfio_pci_core.c
  vfio/ap_ops: Convert to use vfio_register_group_dev()
  s390/vfio-ap: replace open coded locks for VFIO_GROUP_NOTIFY_SET_KVM notification
  s390/vfio-ap: r/w lock for PQAP interception handler function pointer
  vfio/type1: Fix vfio_find_dma_valid return
  vfio-pci/zdev: Remove repeated verbose license text
  vfio: platform: reset: Convert to SPDX identifier
  vfio: Remove struct vfio_device_ops open/release
  ...

25 files changed, 2547 insertions, 2812 deletions

diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index 67d0bf4efa16..6130d00252ed 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -1,12 +1,22 @@
 # SPDX-License-Identifier: GPL-2.0-only
+menuconfig VFIO
+	tristate "VFIO Non-Privileged userspace driver framework"
+	select IOMMU_API
+	select VFIO_IOMMU_TYPE1 if MMU && (X86 || S390 || ARM || ARM64)
+	help
+	  VFIO provides a framework for secure userspace device drivers.
+	  See Documentation/driver-api/vfio.rst for more details.
+
+	  If you don't know what to do here, say N.
+
+if VFIO
 config VFIO_IOMMU_TYPE1
 	tristate
-	depends on VFIO
 	default n
 
 config VFIO_IOMMU_SPAPR_TCE
 	tristate
-	depends on VFIO && SPAPR_TCE_IOMMU
+	depends on SPAPR_TCE_IOMMU
 	default VFIO
 
 config VFIO_SPAPR_EEH
@@ -16,22 +26,11 @@ config VFIO_SPAPR_EEH
 
 config VFIO_VIRQFD
 	tristate
-	depends on VFIO && EVENTFD
+	select EVENTFD
 	default n
 
-menuconfig VFIO
-	tristate "VFIO Non-Privileged userspace driver framework"
-	select IOMMU_API
-	select VFIO_IOMMU_TYPE1 if MMU && (X86 || S390 || ARM || ARM64)
-	help
-	  VFIO provides a framework for secure userspace device drivers.
-	  See Documentation/driver-api/vfio.rst for more details.
-
-	  If you don't know what to do here, say N.
-
-menuconfig VFIO_NOIOMMU
+config VFIO_NOIOMMU
 	bool "VFIO No-IOMMU support"
-	depends on VFIO
 	help
 	  VFIO is built on the ability to isolate devices using the IOMMU.
 	  Only with an IOMMU can userspace access to DMA capable devices be
@@ -48,4 +47,6 @@ source "drivers/vfio/pci/Kconfig"
 source "drivers/vfio/platform/Kconfig"
 source "drivers/vfio/mdev/Kconfig"
 source "drivers/vfio/fsl-mc/Kconfig"
+endif
+
 source "virt/lib/Kconfig"
diff --git a/drivers/vfio/fsl-mc/Kconfig b/drivers/vfio/fsl-mc/Kconfig
index b1a527d6b6f2..597d338c5c8a 100644
--- a/drivers/vfio/fsl-mc/Kconfig
+++ b/drivers/vfio/fsl-mc/Kconfig
@@ -1,6 +1,7 @@
 config VFIO_FSL_MC
 	tristate "VFIO support for QorIQ DPAA2 fsl-mc bus devices"
-	depends on VFIO && FSL_MC_BUS && EVENTFD
+	depends on FSL_MC_BUS
+	select EVENTFD
 	help
 	  Driver to enable support for the VFIO QorIQ DPAA2 fsl-mc
 	  (Management Complex) devices. This is required to passthrough
diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c
index 90cad109583b..0ead91bfa838 100644
--- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c
+++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c
@@ -19,81 +19,10 @@
 
 static struct fsl_mc_driver vfio_fsl_mc_driver;
 
-static DEFINE_MUTEX(reflck_lock);
-
-static void vfio_fsl_mc_reflck_get(struct vfio_fsl_mc_reflck *reflck)
-{
-	kref_get(&reflck->kref);
-}
-
-static void vfio_fsl_mc_reflck_release(struct kref *kref)
-{
-	struct vfio_fsl_mc_reflck *reflck = container_of(kref,
-						      struct vfio_fsl_mc_reflck,
-						      kref);
-
-	mutex_destroy(&reflck->lock);
-	kfree(reflck);
-	mutex_unlock(&reflck_lock);
-}
-
-static void vfio_fsl_mc_reflck_put(struct vfio_fsl_mc_reflck *reflck)
-{
-	kref_put_mutex(&reflck->kref, vfio_fsl_mc_reflck_release, &reflck_lock);
-}
-
-static struct vfio_fsl_mc_reflck *vfio_fsl_mc_reflck_alloc(void)
-{
-	struct vfio_fsl_mc_reflck *reflck;
-
-	reflck = kzalloc(sizeof(*reflck), GFP_KERNEL);
-	if (!reflck)
-		return ERR_PTR(-ENOMEM);
-
-	kref_init(&reflck->kref);
-	mutex_init(&reflck->lock);
-
-	return reflck;
-}
-
-static int vfio_fsl_mc_reflck_attach(struct vfio_fsl_mc_device *vdev)
-{
-	int ret = 0;
-
-	mutex_lock(&reflck_lock);
-	if (is_fsl_mc_bus_dprc(vdev->mc_dev)) {
-		vdev->reflck = vfio_fsl_mc_reflck_alloc();
-		ret = PTR_ERR_OR_ZERO(vdev->reflck);
-	} else {
-		struct device *mc_cont_dev = vdev->mc_dev->dev.parent;
-		struct vfio_device *device;
-		struct vfio_fsl_mc_device *cont_vdev;
-
-		device = vfio_device_get_from_dev(mc_cont_dev);
-		if (!device) {
-			ret = -ENODEV;
-			goto unlock;
-		}
-
-		cont_vdev =
-			container_of(device, struct vfio_fsl_mc_device, vdev);
-		if (!cont_vdev || !cont_vdev->reflck) {
-			vfio_device_put(device);
-			ret = -ENODEV;
-			goto unlock;
-		}
-		vfio_fsl_mc_reflck_get(cont_vdev->reflck);
-		vdev->reflck = cont_vdev->reflck;
-		vfio_device_put(device);
-	}
-
-unlock:
-	mutex_unlock(&reflck_lock);
-	return ret;
-}
-
-static int vfio_fsl_mc_regions_init(struct vfio_fsl_mc_device *vdev)
+static int vfio_fsl_mc_open_device(struct vfio_device *core_vdev)
 {
+	struct vfio_fsl_mc_device *vdev =
+		container_of(core_vdev, struct vfio_fsl_mc_device, vdev);
 	struct fsl_mc_device *mc_dev = vdev->mc_dev;
 	int count = mc_dev->obj_desc.region_count;
 	int i;
@@ -136,58 +65,30 @@ static void vfio_fsl_mc_regions_cleanup(struct vfio_fsl_mc_device *vdev)
 	kfree(vdev->regions);
 }
 
-static int vfio_fsl_mc_open(struct vfio_device *core_vdev)
-{
-	struct vfio_fsl_mc_device *vdev =
-		container_of(core_vdev, struct vfio_fsl_mc_device, vdev);
-	int ret = 0;
-
-	mutex_lock(&vdev->reflck->lock);
-	if (!vdev->refcnt) {
-		ret = vfio_fsl_mc_regions_init(vdev);
-		if (ret)
-			goto out;
-	}
-	vdev->refcnt++;
-out:
-	mutex_unlock(&vdev->reflck->lock);
-
-	return ret;
-}
 
-static void vfio_fsl_mc_release(struct vfio_device *core_vdev)
+static void vfio_fsl_mc_close_device(struct vfio_device *core_vdev)
 {
 	struct vfio_fsl_mc_device *vdev =
 		container_of(core_vdev, struct vfio_fsl_mc_device, vdev);
+	struct fsl_mc_device *mc_dev = vdev->mc_dev;
+	struct device *cont_dev = fsl_mc_cont_dev(&mc_dev->dev);
+	struct fsl_mc_device *mc_cont = to_fsl_mc_device(cont_dev);
 	int ret;
 
-	mutex_lock(&vdev->reflck->lock);
+	vfio_fsl_mc_regions_cleanup(vdev);
 
-	if (!(--vdev->refcnt)) {
-		struct fsl_mc_device *mc_dev = vdev->mc_dev;
-		struct device *cont_dev = fsl_mc_cont_dev(&mc_dev->dev);
-		struct fsl_mc_device *mc_cont = to_fsl_mc_device(cont_dev);
+	/* reset the device before cleaning up the interrupts */
+	ret = dprc_reset_container(mc_cont->mc_io, 0, mc_cont->mc_handle,
+				   mc_cont->obj_desc.id,
+				   DPRC_RESET_OPTION_NON_RECURSIVE);
 
-		vfio_fsl_mc_regions_cleanup(vdev);
+	if (WARN_ON(ret))
+		dev_warn(&mc_cont->dev,
+			 "VFIO_FLS_MC: reset device has failed (%d)\n", ret);
 
-		/* reset the device before cleaning up the interrupts */
-		ret = dprc_reset_container(mc_cont->mc_io, 0,
-		      mc_cont->mc_handle,
-			  mc_cont->obj_desc.id,
-			  DPRC_RESET_OPTION_NON_RECURSIVE);
+	vfio_fsl_mc_irqs_cleanup(vdev);
 
-		if (ret) {
-			dev_warn(&mc_cont->dev, "VFIO_FLS_MC: reset device has failed (%d)\n",
-				 ret);
-			WARN_ON(1);
-		}
-
-		vfio_fsl_mc_irqs_cleanup(vdev);
-
-		fsl_mc_cleanup_irq_pool(mc_cont);
-	}
-
-	mutex_unlock(&vdev->reflck->lock);
+	fsl_mc_cleanup_irq_pool(mc_cont);
 }
 
 static long vfio_fsl_mc_ioctl(struct vfio_device *core_vdev,
@@ -504,8 +405,8 @@ static int vfio_fsl_mc_mmap(struct vfio_device *core_vdev,
 
 static const struct vfio_device_ops vfio_fsl_mc_ops = {
 	.name		= "vfio-fsl-mc",
-	.open		= vfio_fsl_mc_open,
-	.release	= vfio_fsl_mc_release,
+	.open_device	= vfio_fsl_mc_open_device,
+	.close_device	= vfio_fsl_mc_close_device,
 	.ioctl		= vfio_fsl_mc_ioctl,
 	.read		= vfio_fsl_mc_read,
 	.write		= vfio_fsl_mc_write,
@@ -625,13 +526,16 @@ static int vfio_fsl_mc_probe(struct fsl_mc_device *mc_dev)
 	vdev->mc_dev = mc_dev;
 	mutex_init(&vdev->igate);
 
-	ret = vfio_fsl_mc_reflck_attach(vdev);
+	if (is_fsl_mc_bus_dprc(mc_dev))
+		ret = vfio_assign_device_set(&vdev->vdev, &mc_dev->dev);
+	else
+		ret = vfio_assign_device_set(&vdev->vdev, mc_dev->dev.parent);
 	if (ret)
-		goto out_kfree;
+		goto out_uninit;
 
 	ret = vfio_fsl_mc_init_device(vdev);
 	if (ret)
-		goto out_reflck;
+		goto out_uninit;
 
 	ret = vfio_register_group_dev(&vdev->vdev);
 	if (ret) {
@@ -639,12 +543,6 @@ static int vfio_fsl_mc_probe(struct fsl_mc_device *mc_dev)
 		goto out_device;
 	}
 
-	/*
-	 * This triggers recursion into vfio_fsl_mc_probe() on another device
-	 * and the vfio_fsl_mc_reflck_attach() must succeed, which relies on the
-	 * vfio_add_group_dev() above. It has no impact on this vdev, so it is
-	 * safe to be after the vfio device is made live.
-	 */
 	ret = vfio_fsl_mc_scan_container(mc_dev);
 	if (ret)
 		goto out_group_dev;
@@ -655,9 +553,8 @@ out_group_dev:
 	vfio_unregister_group_dev(&vdev->vdev);
 out_device:
 	vfio_fsl_uninit_device(vdev);
-out_reflck:
-	vfio_fsl_mc_reflck_put(vdev->reflck);
-out_kfree:
+out_uninit:
+	vfio_uninit_group_dev(&vdev->vdev);
 	kfree(vdev);
 out_group_put:
 	vfio_iommu_group_put(group, dev);
@@ -674,8 +571,8 @@ static int vfio_fsl_mc_remove(struct fsl_mc_device *mc_dev)
 
 	dprc_remove_devices(mc_dev, NULL, 0);
 	vfio_fsl_uninit_device(vdev);
-	vfio_fsl_mc_reflck_put(vdev->reflck);
 
+	vfio_uninit_group_dev(&vdev->vdev);
 	kfree(vdev);
 	vfio_iommu_group_put(mc_dev->dev.iommu_group, dev);
 
diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
index 0d9f3002df7f..77e584093a23 100644
--- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
+++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
@@ -120,7 +120,7 @@ static int vfio_fsl_mc_set_irq_trigger(struct vfio_fsl_mc_device *vdev,
 	if (start != 0 || count != 1)
 		return -EINVAL;
 
-	mutex_lock(&vdev->reflck->lock);
+	mutex_lock(&vdev->vdev.dev_set->lock);
 	ret = fsl_mc_populate_irq_pool(mc_cont,
 			FSL_MC_IRQ_POOL_MAX_TOTAL_IRQS);
 	if (ret)
@@ -129,7 +129,7 @@ static int vfio_fsl_mc_set_irq_trigger(struct vfio_fsl_mc_device *vdev,
 	ret = vfio_fsl_mc_irqs_allocate(vdev);
 	if (ret)
 		goto unlock;
-	mutex_unlock(&vdev->reflck->lock);
+	mutex_unlock(&vdev->vdev.dev_set->lock);
 
 	if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
 		s32 fd = *(s32 *)data;
@@ -154,7 +154,7 @@ static int vfio_fsl_mc_set_irq_trigger(struct vfio_fsl_mc_device *vdev,
 	return 0;
 
 unlock:
-	mutex_unlock(&vdev->reflck->lock);
+	mutex_unlock(&vdev->vdev.dev_set->lock);
 	return ret;
 
 }
diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h
index 89700e00e77d..4ad63ececb91 100644
--- a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h
+++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h
@@ -22,11 +22,6 @@ struct vfio_fsl_mc_irq {
 	char            *name;
 };
 
-struct vfio_fsl_mc_reflck {
-	struct kref		kref;
-	struct mutex		lock;
-};
-
 struct vfio_fsl_mc_region {
 	u32			flags;
 	u32			type;
@@ -39,9 +34,7 @@ struct vfio_fsl_mc_device {
 	struct vfio_device		vdev;
 	struct fsl_mc_device		*mc_dev;
 	struct notifier_block        nb;
-	int				refcnt;
 	struct vfio_fsl_mc_region	*regions;
-	struct vfio_fsl_mc_reflck   *reflck;
 	struct mutex         igate;
 	struct vfio_fsl_mc_irq      *mc_irqs;
 };
diff --git a/drivers/vfio/mdev/Kconfig b/drivers/vfio/mdev/Kconfig
index 763c877a1318..646dbed44eb2 100644
--- a/drivers/vfio/mdev/Kconfig
+++ b/drivers/vfio/mdev/Kconfig
@@ -2,7 +2,6 @@
 
 config VFIO_MDEV
 	tristate "Mediated device driver framework"
-	depends on VFIO
 	default n
 	help
 	  Provides a framework to virtualize devices.
diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c
index e4581ec093a6..b314101237fe 100644
--- a/drivers/vfio/mdev/mdev_core.c
+++ b/drivers/vfio/mdev/mdev_core.c
@@ -138,10 +138,6 @@ int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops)
 	if (!dev)
 		return -EINVAL;
 
-	/* Not mandatory, but its absence could be a problem */
-	if (!ops->request)
-		dev_info(dev, "Driver cannot be asked to release device\n");
-
 	mutex_lock(&parent_list_lock);
 
 	/* Check for duplicate */
@@ -398,7 +394,7 @@ static void __exit mdev_exit(void)
 	mdev_bus_unregister();
 }
 
-module_init(mdev_init)
+subsys_initcall(mdev_init)
 module_exit(mdev_exit)
 
 MODULE_VERSION(DRIVER_VERSION);
diff --git a/drivers/vfio/mdev/vfio_mdev.c b/drivers/vfio/mdev/vfio_mdev.c
index 39ef7489fe47..7a9883048216 100644
--- a/drivers/vfio/mdev/vfio_mdev.c
+++ b/drivers/vfio/mdev/vfio_mdev.c
@@ -17,24 +17,24 @@
 
 #include "mdev_private.h"
 
-static int vfio_mdev_open(struct vfio_device *core_vdev)
+static int vfio_mdev_open_device(struct vfio_device *core_vdev)
 {
 	struct mdev_device *mdev = to_mdev_device(core_vdev->dev);
 	struct mdev_parent *parent = mdev->type->parent;
 
-	if (unlikely(!parent->ops->open))
-		return -EINVAL;
+	if (unlikely(!parent->ops->open_device))
+		return 0;
 
-	return parent->ops->open(mdev);
+	return parent->ops->open_device(mdev);
 }
 
-static void vfio_mdev_release(struct vfio_device *core_vdev)
+static void vfio_mdev_close_device(struct vfio_device *core_vdev)
 {
 	struct mdev_device *mdev = to_mdev_device(core_vdev->dev);
 	struct mdev_parent *parent = mdev->type->parent;
 
-	if (likely(parent->ops->release))
-		parent->ops->release(mdev);
+	if (likely(parent->ops->close_device))
+		parent->ops->close_device(mdev);
 }
 
 static long vfio_mdev_unlocked_ioctl(struct vfio_device *core_vdev,
@@ -44,7 +44,7 @@ static long vfio_mdev_unlocked_ioctl(struct vfio_device *core_vdev,
 	struct mdev_parent *parent = mdev->type->parent;
 
 	if (unlikely(!parent->ops->ioctl))
-		return -EINVAL;
+		return 0;
 
 	return parent->ops->ioctl(mdev, cmd, arg);
 }
@@ -100,8 +100,8 @@ static void vfio_mdev_request(struct vfio_device *core_vdev, unsigned int count)
 
 static const struct vfio_device_ops vfio_mdev_dev_ops = {
 	.name		= "vfio-mdev",
-	.open		= vfio_mdev_open,
-	.release	= vfio_mdev_release,
+	.open_device	= vfio_mdev_open_device,
+	.close_device	= vfio_mdev_close_device,
 	.ioctl		= vfio_mdev_unlocked_ioctl,
 	.read		= vfio_mdev_read,
 	.write		= vfio_mdev_write,
@@ -120,12 +120,16 @@ static int vfio_mdev_probe(struct mdev_device *mdev)
 
 	vfio_init_group_dev(vdev, &mdev->dev, &vfio_mdev_dev_ops);
 	ret = vfio_register_group_dev(vdev);
-	if (ret) {
-		kfree(vdev);
-		return ret;
-	}
+	if (ret)
+		goto out_uninit;
+
 	dev_set_drvdata(&mdev->dev, vdev);
 	return 0;
+
+out_uninit:
+	vfio_uninit_group_dev(vdev);
+	kfree(vdev);
+	return ret;
 }
 
 static void vfio_mdev_remove(struct mdev_device *mdev)
@@ -133,6 +137,7 @@ static void vfio_mdev_remove(struct mdev_device *mdev)
 	struct vfio_device *vdev = dev_get_drvdata(&mdev->dev);
 
 	vfio_unregister_group_dev(vdev);
+	vfio_uninit_group_dev(vdev);
 	kfree(vdev);
 }
 
diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index 5e2e1b9a9fd3..860424ccda1b 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/drivers/vfio/pci/Kconfig
@@ -1,19 +1,29 @@
 # SPDX-License-Identifier: GPL-2.0-only
-config VFIO_PCI
-	tristate "VFIO support for PCI devices"
-	depends on VFIO && PCI && EVENTFD
-	depends on MMU
+if PCI && MMU
+config VFIO_PCI_CORE
+	tristate
 	select VFIO_VIRQFD
 	select IRQ_BYPASS_MANAGER
+
+config VFIO_PCI_MMAP
+	def_bool y if !S390
+
+config VFIO_PCI_INTX
+	def_bool y if !S390
+
+config VFIO_PCI
+	tristate "Generic VFIO support for any PCI device"
+	select VFIO_PCI_CORE
 	help
-	  Support for the PCI VFIO bus driver.  This is required to make
-	  use of PCI drivers using the VFIO framework.
+	  Support for the generic PCI VFIO bus driver which can connect any
+	  PCI device to the VFIO framework.
 
 	  If you don't know what to do here, say N.
 
+if VFIO_PCI
 config VFIO_PCI_VGA
-	bool "VFIO PCI support for VGA devices"
-	depends on VFIO_PCI && X86 && VGA_ARB
+	bool "Generic VFIO PCI support for VGA devices"
+	depends on X86 && VGA_ARB
 	help
 	  Support for VGA extension to VFIO PCI.  This exposes an additional
 	  region on VGA devices for accessing legacy VGA addresses used by
@@ -21,17 +31,9 @@ config VFIO_PCI_VGA
 
 	  If you don't know what to do here, say N.
 
-config VFIO_PCI_MMAP
-	depends on VFIO_PCI
-	def_bool y if !S390
-
-config VFIO_PCI_INTX
-	depends on VFIO_PCI
-	def_bool y if !S390
-
 config VFIO_PCI_IGD
-	bool "VFIO PCI extensions for Intel graphics (GVT-d)"
-	depends on VFIO_PCI && X86
+	bool "Generic VFIO PCI extensions for Intel graphics (GVT-d)"
+	depends on X86
 	default y
 	help
 	  Support for Intel IGD specific extensions to enable direct
@@ -40,3 +42,5 @@ config VFIO_PCI_IGD
 	  and LPC bridge config space.
 
 	  To enable Intel IGD assignment through vfio-pci, say Y.
+endif
+endif
diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile
index 3ff42093962f..349d68d242b4 100644
--- a/drivers/vfio/pci/Makefile
+++ b/drivers/vfio/pci/Makefile
@@ -1,7 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
-vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o
-vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o
-vfio-pci-$(CONFIG_S390) += vfio_pci_zdev.o
+vfio-pci-core-y := vfio_pci_core.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o
+vfio-pci-core-$(CONFIG_S390) += vfio_pci_zdev.o
+obj-$(CONFIG_VFIO_PCI_CORE) += vfio-pci-core.o
 
+vfio-pci-y := vfio_pci.o
+vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o
 obj-$(CONFIG_VFIO_PCI) += vfio-pci.o
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index cf27df8048db..a5ce92beb655 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
+ * Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ *
  * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
  *     Author: Alex Williamson <alex.williamson@redhat.com>
  *
@@ -18,19 +20,13 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/notifier.h>
-#include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/uaccess.h>
-#include <linux/vfio.h>
-#include <linux/vgaarb.h>
-#include <linux/nospec.h>
-#include <linux/sched/mm.h>
 
-#include "vfio_pci_private.h"
+#include <linux/vfio_pci_core.h>
 
-#define DRIVER_VERSION  "0.2"
 #define DRIVER_AUTHOR   "Alex Williamson <alex.williamson@redhat.com>"
 #define DRIVER_DESC     "VFIO PCI - User Level meta-driver"
 
@@ -64,15 +60,6 @@ static bool disable_denylist;
 module_param(disable_denylist, bool, 0444);
 MODULE_PARM_DESC(disable_denylist, "Disable use of device denylist. Disabling the denylist allows binding to devices with known errata that may lead to exploitable stability or security issues when accessed by untrusted users.");
 
-static inline bool vfio_vga_disabled(void)
-{
-#ifdef CONFIG_VFIO_PCI_VGA
-	return disable_vga;
-#else
-	return true;
-#endif
-}
-
 static bool vfio_pci_dev_in_denylist(struct pci_dev *pdev)
 {
 	switch (pdev->vendor) {
@@ -111,2269 +98,103 @@ static bool vfio_pci_is_denylisted(struct pci_dev *pdev)
 	return true;
 }
 
-/*
- * Our VGA arbiter participation is limited since we don't know anything
- * about the device itself.  However, if the device is the only VGA device
- * downstream of a bridge and VFIO VGA support is disabled, then we can
- * safely return legacy VGA IO and memory as not decoded since the user
- * has no way to get to it and routing can be disabled externally at the
- * bridge.
- */
-static unsigned int vfio_pci_set_decode(struct pci_dev *pdev, bool single_vga)
-{
-	struct pci_dev *tmp = NULL;
-	unsigned char max_busnr;
-	unsigned int decodes;
-
-	if (single_vga || !vfio_vga_disabled() || pci_is_root_bus(pdev->bus))
-		return VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM |
-		       VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM;
-
-	max_busnr = pci_bus_max_busnr(pdev->bus);
-	decodes = VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM;
-
-	while ((tmp = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, tmp)) != NULL) {
-		if (tmp == pdev ||
-		    pci_domain_nr(tmp->bus) != pci_domain_nr(pdev->bus) ||
-		    pci_is_root_bus(tmp->bus))
-			continue;
-
-		if (tmp->bus->number >= pdev->bus->number &&
-		    tmp->bus->number <= max_busnr) {
-			pci_dev_put(tmp);
-			decodes |= VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM;
-			break;
-		}
-	}
-
-	return decodes;
-}
-
-static inline bool vfio_pci_is_vga(struct pci_dev *pdev)
-{
-	return (pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA;
-}
-
-static void vfio_pci_probe_mmaps(struct vfio_pci_device *vdev)
-{
-	struct resource *res;
-	int i;
-	struct vfio_pci_dummy_resource *dummy_res;
-
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		int bar = i + PCI_STD_RESOURCES;
-
-		res = &vdev->pdev->resource[bar];
-
-		if (!IS_ENABLED(CONFIG_VFIO_PCI_MMAP))
-			goto no_mmap;
-
-		if (!(res->flags & IORESOURCE_MEM))
-			goto no_mmap;
-
-		/*
-		 * The PCI core shouldn't set up a resource with a
-		 * type but zero size. But there may be bugs that
-		 * cause us to do that.
-		 */
-		if (!resource_size(res))
-			goto no_mmap;
-
-		if (resource_size(res) >= PAGE_SIZE) {
-			vdev->bar_mmap_supported[bar] = true;
-			continue;
-		}
-
-		if (!(res->start & ~PAGE_MASK)) {
-			/*
-			 * Add a dummy resource to reserve the remainder
-			 * of the exclusive page in case that hot-add
-			 * device's bar is assigned into it.
-			 */
-			dummy_res = kzalloc(sizeof(*dummy_res), GFP_KERNEL);
-			if (dummy_res == NULL)
-				goto no_mmap;
-
-			dummy_res->resource.name = "vfio sub-page reserved";
-			dummy_res->resource.start = res->end + 1;
-			dummy_res->resource.end = res->start + PAGE_SIZE - 1;
-			dummy_res->resource.flags = res->flags;
-			if (request_resource(res->parent,
-						&dummy_res->resource)) {
-				kfree(dummy_res);
-				goto no_mmap;
-			}
-			dummy_res->index = bar;
-			list_add(&dummy_res->res_next,
-					&vdev->dummy_resources_list);
-			vdev->bar_mmap_supported[bar] = true;
-			continue;
-		}
-		/*
-		 * Here we don't handle the case when the BAR is not page
-		 * aligned because we can't expect the BAR will be
-		 * assigned into the same location in a page in guest
-		 * when we passthrough the BAR. And it's hard to access
-		 * this BAR in userspace because we have no way to get
-		 * the BAR's location in a page.
-		 */
-no_mmap:
-		vdev->bar_mmap_supported[bar] = false;
-	}
-}
-
-static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev);
-static void vfio_pci_disable(struct vfio_pci_device *vdev);
-static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data);
-
-/*
- * INTx masking requires the ability to disable INTx signaling via PCI_COMMAND
- * _and_ the ability detect when the device is asserting INTx via PCI_STATUS.
- * If a device implements the former but not the latter we would typically
- * expect broken_intx_masking be set and require an exclusive interrupt.
- * However since we do have control of the device's ability to assert INTx,
- * we can instead pretend that the device does not implement INTx, virtualizing
- * the pin register to report zero and maintaining DisINTx set on the host.
- */
-static bool vfio_pci_nointx(struct pci_dev *pdev)
-{
-	switch (pdev->vendor) {
-	case PCI_VENDOR_ID_INTEL:
-		switch (pdev->device) {
-		/* All i40e (XL710/X710/XXV710) 10/20/25/40GbE NICs */
-		case 0x1572:
-		case 0x1574:
-		case 0x1580 ... 0x1581:
-		case 0x1583 ... 0x158b:
-		case 0x37d0 ... 0x37d2:
-		/* X550 */
-		case 0x1563:
-			return true;
-		default:
-			return false;
-		}
-	}
-
-	return false;
-}
-
-static void vfio_pci_probe_power_state(struct vfio_pci_device *vdev)
+static int vfio_pci_open_device(struct vfio_device *core_vdev)
 {
+	struct vfio_pci_core_device *vdev =
+		container_of(core_vdev, struct vfio_pci_core_device, vdev);
 	struct pci_dev *pdev = vdev->pdev;
-	u16 pmcsr;
-
-	if (!pdev->pm_cap)
-		return;
-
-	pci_read_config_word(pdev, pdev->pm_cap + PCI_PM_CTRL, &pmcsr);
-
-	vdev->needs_pm_restore = !(pmcsr & PCI_PM_CTRL_NO_SOFT_RESET);
-}
-
-/*
- * pci_set_power_state() wrapper handling devices which perform a soft reset on
- * D3->D0 transition.  Save state prior to D0/1/2->D3, stash it on the vdev,
- * restore when returned to D0.  Saved separately from pci_saved_state for use
- * by PM capability emulation and separately from pci_dev internal saved state
- * to avoid it being overwritten and consumed around other resets.
- */
-int vfio_pci_set_power_state(struct vfio_pci_device *vdev, pci_power_t state)
-{
-	struct pci_dev *pdev = vdev->pdev;
-	bool needs_restore = false, needs_save = false;
 	int ret;
 
-	if (vdev->needs_pm_restore) {
-		if (pdev->current_state < PCI_D3hot && state >= PCI_D3hot) {
-			pci_save_state(pdev);
-			needs_save = true;
-		}
-
-		if (pdev->current_state >= PCI_D3hot && state <= PCI_D0)
-			needs_restore = true;
-	}
-
-	ret = pci_set_power_state(pdev, state);
-
-	if (!ret) {
-		/* D3 might be unsupported via quirk, skip unless in D3 */
-		if (needs_save && pdev->current_state >= PCI_D3hot) {
-			vdev->pm_save = pci_store_saved_state(pdev);
-		} else if (needs_restore) {
-			pci_load_and_free_saved_state(pdev, &vdev->pm_save);
-			pci_restore_state(pdev);