Update Linux to v5.4.148

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz

Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index fd17db9..65743de 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -21,15 +21,15 @@
 
 menuconfig VFIO
 	tristate "VFIO Non-Privileged userspace driver framework"
-	depends on IOMMU_API
-	select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM || ARM64)
+	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
diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c
index 7570c76..ca94768 100644
--- a/drivers/vfio/mdev/mdev_sysfs.c
+++ b/drivers/vfio/mdev/mdev_sysfs.c
@@ -105,12 +105,13 @@
 		return ERR_PTR(-ENOMEM);
 
 	type->kobj.kset = parent->mdev_types_kset;
+	type->parent = parent;
 
 	ret = kobject_init_and_add(&type->kobj, &mdev_type_ktype, NULL,
 				   "%s-%s", dev_driver_string(parent->dev),
 				   group->name);
 	if (ret) {
-		kfree(type);
+		kobject_put(&type->kobj);
 		return ERR_PTR(ret);
 	}
 
@@ -132,7 +133,6 @@
 	}
 
 	type->group = group;
-	type->parent = parent;
 	return type;
 
 attrs_failed:
diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index ac3c1dd..c691127 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/drivers/vfio/pci/Kconfig
@@ -2,6 +2,7 @@
 config VFIO_PCI
 	tristate "VFIO support for PCI devices"
 	depends on VFIO && PCI && EVENTFD
+	depends on MMU
 	select VFIO_VIRQFD
 	select IRQ_BYPASS_MANAGER
 	help
@@ -42,6 +43,6 @@
 
 config VFIO_PCI_NVLINK2
 	def_bool y
-	depends on VFIO_PCI && PPC_POWERNV
+	depends on VFIO_PCI && PPC_POWERNV && SPAPR_TCE_IOMMU
 	help
 	  VFIO PCI support for P9 Witherspoon machine with NVIDIA V100 GPUs
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 0220616..b06d762 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -27,6 +27,7 @@
 #include <linux/vfio.h>
 #include <linux/vgaarb.h>
 #include <linux/nospec.h>
+#include <linux/sched/mm.h>
 
 #include "vfio_pci_private.h"
 
@@ -113,8 +114,6 @@
 	int bar;
 	struct vfio_pci_dummy_resource *dummy_res;
 
-	INIT_LIST_HEAD(&vdev->dummy_resources_list);
-
 	for (bar = PCI_STD_RESOURCES; bar <= PCI_STD_RESOURCE_END; bar++) {
 		res = vdev->pdev->resource + bar;
 
@@ -177,6 +176,7 @@
 
 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
@@ -332,7 +332,7 @@
 	    pdev->vendor == PCI_VENDOR_ID_INTEL &&
 	    IS_ENABLED(CONFIG_VFIO_PCI_IGD)) {
 		ret = vfio_pci_igd_init(vdev);
-		if (ret) {
+		if (ret && ret != -ENODEV) {
 			pci_warn(pdev, "Failed to setup Intel IGD regions\n");
 			goto disable_exit;
 		}
@@ -472,6 +472,19 @@
 	if (!(--vdev->refcnt)) {
 		vfio_spapr_pci_eeh_release(vdev->pdev);
 		vfio_pci_disable(vdev);
+		mutex_lock(&vdev->igate);
+		if (vdev->err_trigger) {
+			eventfd_ctx_put(vdev->err_trigger);
+			vdev->err_trigger = NULL;
+		}
+		mutex_unlock(&vdev->igate);
+
+		mutex_lock(&vdev->igate);
+		if (vdev->req_trigger) {
+			eventfd_ctx_put(vdev->req_trigger);
+			vdev->req_trigger = NULL;
+		}
+		mutex_unlock(&vdev->igate);
 	}
 
 	mutex_unlock(&vdev->reflck->lock);
@@ -688,6 +701,12 @@
 	return 0;
 }
 
+struct vfio_devices {
+	struct vfio_device **devices;
+	int cur_index;
+	int max_index;
+};
+
 static long vfio_pci_ioctl(void *device_data,
 			   unsigned int cmd, unsigned long arg)
 {
@@ -761,7 +780,7 @@
 		{
 			void __iomem *io;
 			size_t size;
-			u16 orig_cmd;
+			u16 cmd;
 
 			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
 			info.flags = 0;
@@ -781,10 +800,7 @@
 			 * Is it really there?  Enable memory decode for
 			 * implicit access in pci_map_rom().
 			 */
-			pci_read_config_word(pdev, PCI_COMMAND, &orig_cmd);
-			pci_write_config_word(pdev, PCI_COMMAND,
-					      orig_cmd | PCI_COMMAND_MEMORY);
-
+			cmd = vfio_pci_memory_lock_and_enable(vdev);
 			io = pci_map_rom(pdev, &size);
 			if (io) {
 				info.flags = VFIO_REGION_INFO_FLAG_READ;
@@ -792,8 +808,8 @@
 			} else {
 				info.size = 0;
 			}
+			vfio_pci_memory_unlock_and_restore(vdev, cmd);
 
-			pci_write_config_word(pdev, PCI_COMMAND, orig_cmd);
 			break;
 		}
 		case VFIO_PCI_VGA_REGION_INDEX:
@@ -936,8 +952,16 @@
 		return ret;
 
 	} else if (cmd == VFIO_DEVICE_RESET) {
-		return vdev->reset_works ?
-			pci_try_reset_function(vdev->pdev) : -EINVAL;
+		int ret;
+
+		if (!vdev->reset_works)
+			return -EINVAL;
+
+		vfio_pci_zap_and_down_write_memory_lock(vdev);
+		ret = pci_try_reset_function(vdev->pdev);
+		up_write(&vdev->memory_lock);
+
+		return ret;
 
 	} else if (cmd == VFIO_DEVICE_GET_PCI_HOT_RESET_INFO) {
 		struct vfio_pci_hot_reset_info hdr;
@@ -1017,8 +1041,9 @@
 		int32_t *group_fds;
 		struct vfio_pci_group_entry *groups;
 		struct vfio_pci_group_info info;
+		struct vfio_devices devs = { .cur_index = 0 };
 		bool slot = false;
-		int i, count = 0, ret = 0;
+		int i, group_idx, mem_idx = 0, count = 0, ret = 0;
 
 		minsz = offsetofend(struct vfio_pci_hot_reset, count);
 
@@ -1070,9 +1095,9 @@
 		 * user interface and store the group and iommu ID.  This
 		 * ensures the group is held across the reset.
 		 */
-		for (i = 0; i < hdr.count; i++) {
+		for (group_idx = 0; group_idx < hdr.count; group_idx++) {
 			struct vfio_group *group;
-			struct fd f = fdget(group_fds[i]);
+			struct fd f = fdget(group_fds[group_idx]);
 			if (!f.file) {
 				ret = -EBADF;
 				break;
@@ -1085,8 +1110,9 @@
 				break;
 			}
 
-			groups[i].group = group;
-			groups[i].id = vfio_external_user_iommu_id(group);
+			groups[group_idx].group = group;
+			groups[group_idx].id =
+					vfio_external_user_iommu_id(group);
 		}
 
 		kfree(group_fds);
@@ -1105,13 +1131,63 @@
 		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
 						    vfio_pci_validate_devs,
 						    &info, slot);
-		if (!ret)
-			/* User has access, do the reset */
-			ret = pci_reset_bus(vdev->pdev);
+		if (ret)
+			goto hot_reset_release;
+
+		devs.max_index = count;
+		devs.devices = kcalloc(count, sizeof(struct vfio_device *),
+				       GFP_KERNEL);
+		if (!devs.devices) {
+			ret = -ENOMEM;
+			goto hot_reset_release;
+		}
+
+		/*
+		 * We need to get memory_lock for each device, but devices
+		 * can share mmap_sem, therefore we need to zap and hold
+		 * the vma_lock for each device, and only then get each
+		 * memory_lock.
+		 */
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+					    vfio_pci_try_zap_and_vma_lock_cb,
+					    &devs, slot);
+		if (ret)
+			goto hot_reset_release;
+
+		for (; mem_idx < devs.cur_index; mem_idx++) {
+			struct vfio_pci_device *tmp;
+
+			tmp = vfio_device_data(devs.devices[mem_idx]);
+
+			ret = down_write_trylock(&tmp->memory_lock);
+			if (!ret) {
+				ret = -EBUSY;
+				goto hot_reset_release;
+			}
+			mutex_unlock(&tmp->vma_lock);
+		}
+
+		/* User has access, do the reset */
+		ret = pci_reset_bus(vdev->pdev);
 
 hot_reset_release:
-		for (i--; i >= 0; i--)
-			vfio_group_put_external_user(groups[i].group);
+		for (i = 0; i < devs.cur_index; i++) {
+			struct vfio_device *device;
+			struct vfio_pci_device *tmp;
+
+			device = devs.devices[i];
+			tmp = vfio_device_data(device);
+
+			if (i < mem_idx)
+				up_write(&tmp->memory_lock);
+			else
+				mutex_unlock(&tmp->vma_lock);
+			vfio_device_put(device);
+		}
+		kfree(devs.devices);
+
+		for (group_idx--; group_idx >= 0; group_idx--)
+			vfio_group_put_external_user(groups[group_idx].group);
 
 		kfree(groups);
 		return ret;
@@ -1192,6 +1268,215 @@
 	return vfio_pci_rw(device_data, (char __user *)buf, count, ppos, true);
 }
 
+/* Return 1 on zap and vma_lock acquired, 0 on contention (only with @try) */
+static int vfio_pci_zap_and_vma_lock(struct vfio_pci_device *vdev, bool try)
+{
+	struct vfio_pci_mmap_vma *mmap_vma, *tmp;
+
+	/*
+	 * Lock ordering:
+	 * vma_lock is nested under mmap_sem for vm_ops callback paths.
+	 * The memory_lock semaphore is used by both code paths calling
+	 * into this function to zap vmas and the vm_ops.fault callback
+	 * to protect the memory enable state of the device.
+	 *
+	 * When zapping vmas we need to maintain the mmap_sem => vma_lock
+	 * ordering, which requires using vma_lock to walk vma_list to
+	 * acquire an mm, then dropping vma_lock to get the mmap_sem and
+	 * reacquiring vma_lock.  This logic is derived from similar
+	 * requirements in uverbs_user_mmap_disassociate().
+	 *
+	 * mmap_sem must always be the top-level lock when it is taken.
+	 * Therefore we can only hold the memory_lock write lock when
+	 * vma_list is empty, as we'd need to take mmap_sem to clear
+	 * entries.  vma_list can only be guaranteed empty when holding
+	 * vma_lock, thus memory_lock is nested under vma_lock.
+	 *
+	 * This enables the vm_ops.fault callback to acquire vma_lock,
+	 * followed by memory_lock read lock, while already holding
+	 * mmap_sem without risk of deadlock.
+	 */
+	while (1) {
+		struct mm_struct *mm = NULL;
+
+		if (try) {
+			if (!mutex_trylock(&vdev->vma_lock))
+				return 0;
+		} else {
+			mutex_lock(&vdev->vma_lock);
+		}
+		while (!list_empty(&vdev->vma_list)) {
+			mmap_vma = list_first_entry(&vdev->vma_list,
+						    struct vfio_pci_mmap_vma,
+						    vma_next);
+			mm = mmap_vma->vma->vm_mm;
+			if (mmget_not_zero(mm))
+				break;
+
+			list_del(&mmap_vma->vma_next);
+			kfree(mmap_vma);
+			mm = NULL;
+		}
+		if (!mm)
+			return 1;
+		mutex_unlock(&vdev->vma_lock);
+
+		if (try) {
+			if (!down_read_trylock(&mm->mmap_sem)) {
+				mmput(mm);
+				return 0;
+			}
+		} else {
+			down_read(&mm->mmap_sem);
+		}
+		if (mmget_still_valid(mm)) {
+			if (try) {
+				if (!mutex_trylock(&vdev->vma_lock)) {
+					up_read(&mm->mmap_sem);
+					mmput(mm);
+					return 0;
+				}
+			} else {
+				mutex_lock(&vdev->vma_lock);
+			}
+			list_for_each_entry_safe(mmap_vma, tmp,
+						 &vdev->vma_list, vma_next) {
+				struct vm_area_struct *vma = mmap_vma->vma;
+
+				if (vma->vm_mm != mm)
+					continue;
+
+				list_del(&mmap_vma->vma_next);
+				kfree(mmap_vma);
+
+				zap_vma_ptes(vma, vma->vm_start,
+					     vma->vm_end - vma->vm_start);
+			}
+			mutex_unlock(&vdev->vma_lock);
+		}
+		up_read(&mm->mmap_sem);
+		mmput(mm);
+	}
+}
+
+void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_device *vdev)
+{
+	vfio_pci_zap_and_vma_lock(vdev, false);
+	down_write(&vdev->memory_lock);
+	mutex_unlock(&vdev->vma_lock);
+}
+
+u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_device *vdev)
+{
+	u16 cmd;
+
+	down_write(&vdev->memory_lock);
+	pci_read_config_word(vdev->pdev, PCI_COMMAND, &cmd);
+	if (!(cmd & PCI_COMMAND_MEMORY))
+		pci_write_config_word(vdev->pdev, PCI_COMMAND,
+				      cmd | PCI_COMMAND_MEMORY);
+
+	return cmd;
+}
+
+void vfio_pci_memory_unlock_and_restore(struct vfio_pci_device *vdev, u16 cmd)
+{
+	pci_write_config_word(vdev->pdev, PCI_COMMAND, cmd);
+	up_write(&vdev->memory_lock);
+}
+
+/* Caller holds vma_lock */
+static int __vfio_pci_add_vma(struct vfio_pci_device *vdev,
+			      struct vm_area_struct *vma)
+{
+	struct vfio_pci_mmap_vma *mmap_vma;
+
+	mmap_vma = kmalloc(sizeof(*mmap_vma), GFP_KERNEL);
+	if (!mmap_vma)
+		return -ENOMEM;
+
+	mmap_vma->vma = vma;
+	list_add(&mmap_vma->vma_next, &vdev->vma_list);
+
+	return 0;
+}
+
+/*
+ * Zap mmaps on open so that we can fault them in on access and therefore
+ * our vma_list only tracks mappings accessed since last zap.
+ */
+static void vfio_pci_mmap_open(struct vm_area_struct *vma)
+{
+	zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start);
+}
+
+static void vfio_pci_mmap_close(struct vm_area_struct *vma)
+{
+	struct vfio_pci_device *vdev = vma->vm_private_data;
+	struct vfio_pci_mmap_vma *mmap_vma;
+
+	mutex_lock(&vdev->vma_lock);
+	list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) {
+		if (mmap_vma->vma == vma) {
+			list_del(&mmap_vma->vma_next);
+			kfree(mmap_vma);
+			break;
+		}
+	}
+	mutex_unlock(&vdev->vma_lock);
+}
+
+static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct vfio_pci_device *vdev = vma->vm_private_data;
+	struct vfio_pci_mmap_vma *mmap_vma;
+	vm_fault_t ret = VM_FAULT_NOPAGE;
+
+	mutex_lock(&vdev->vma_lock);
+	down_read(&vdev->memory_lock);
+
+	if (!__vfio_pci_memory_enabled(vdev)) {
+		ret = VM_FAULT_SIGBUS;
+		goto up_out;
+	}
+
+	/*
+	 * We populate the whole vma on fault, so we need to test whether
+	 * the vma has already been mapped, such as for concurrent faults
+	 * to the same vma.  io_remap_pfn_range() will trigger a BUG_ON if
+	 * we ask it to fill the same range again.
+	 */
+	list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) {
+		if (mmap_vma->vma == vma)
+			goto up_out;
+	}
+
+	if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+			       vma->vm_end - vma->vm_start,
+			       vma->vm_page_prot)) {
+		ret = VM_FAULT_SIGBUS;
+		zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start);
+		goto up_out;
+	}
+
+	if (__vfio_pci_add_vma(vdev, vma)) {
+		ret = VM_FAULT_OOM;
+		zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start);
+	}
+
+up_out:
+	up_read(&vdev->memory_lock);
+	mutex_unlock(&vdev->vma_lock);
+	return ret;
+}
+
+static const struct vm_operations_struct vfio_pci_mmap_ops = {
+	.open = vfio_pci_mmap_open,
+	.close = vfio_pci_mmap_close,
+	.fault = vfio_pci_mmap_fault,
+};
+
 static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 {
 	struct vfio_pci_device *vdev = device_data;
@@ -1202,6 +1487,8 @@
 
 	index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT);
 
+	if (index >= VFIO_PCI_NUM_REGIONS + vdev->num_regions)
+		return -EINVAL;
 	if (vma->vm_end < vma->vm_start)
 		return -EINVAL;
 	if ((vma->vm_flags & VM_SHARED) == 0)
@@ -1210,7 +1497,7 @@
 		int regnum = index - VFIO_PCI_NUM_REGIONS;
 		struct vfio_pci_region *region = vdev->region + regnum;
 
-		if (region && region->ops && region->ops->mmap &&
+		if (region->ops && region->ops->mmap &&
 		    (region->flags & VFIO_REGION_INFO_FLAG_MMAP))
 			return region->ops->mmap(vdev, region, vma);
 		return -EINVAL;
@@ -1250,8 +1537,14 @@
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	vma->vm_pgoff = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff;
 
-	return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
-			       req_len, vma->vm_page_prot);
+	/*
+	 * See remap_pfn_range(), called from vfio_pci_fault() but we can't
+	 * change vm_flags within the fault handler.  Set them now.
+	 */
+	vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_ops = &vfio_pci_mmap_ops;
+
+	return 0;
 }
 
 static void vfio_pci_request(void *device_data, unsigned int count)
@@ -1326,7 +1619,11 @@
 	mutex_init(&vdev->igate);
 	spin_lock_init(&vdev->irqlock);
 	mutex_init(&vdev->ioeventfds_lock);
+	INIT_LIST_HEAD(&vdev->dummy_resources_list);
 	INIT_LIST_HEAD(&vdev->ioeventfds_list);
+	mutex_init(&vdev->vma_lock);
+	INIT_LIST_HEAD(&vdev->vma_list);
+	init_rwsem(&vdev->memory_lock);
 
 	ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
 	if (ret) {
@@ -1516,12 +1813,6 @@
 	kref_put_mutex(&reflck->kref, vfio_pci_reflck_release, &reflck_lock);
 }
 
-struct vfio_devices {
-	struct vfio_device **devices;
-	int cur_index;
-	int max_index;
-};
-
 static int vfio_pci_get_unused_devs(struct pci_dev *pdev, void *data)
 {
 	struct vfio_devices *devs = data;
@@ -1552,6 +1843,39 @@
 	return 0;
 }
 
+static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data)
+{
+	struct vfio_devices *devs = data;
+	struct vfio_device *device;
+	struct vfio_pci_device *vdev;
+
+	if (devs->cur_index == devs->max_index)
+		return -ENOSPC;
+
+	device = vfio_device_get_from_dev(&pdev->dev);
+	if (!device)
+		return -EINVAL;
+
+	if (pci_dev_driver(pdev) != &vfio_pci_driver) {
+		vfio_device_put(device);
+		return -EBUSY;
+	}
+
+	vdev = vfio_device_data(device);
+
+	/*
+	 * Locking multiple devices is prone to deadlock, runaway and
+	 * unwind if we hit contention.
+	 */
+	if (!vfio_pci_zap_and_vma_lock(vdev, true)) {
+		vfio_device_put(device);
+		return -EBUSY;
+	}
+
+	devs->devices[devs->cur_index++] = device;
+	return 0;
+}
+
 /*
  * If a bus or slot reset is available for the provided device and:
  *  - All of the devices affected by that bus or slot reset are unused
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index f0891bd..50cd17f 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -395,6 +395,20 @@
 	*(__le32 *)(&p->write[off]) = cpu_to_le32(write);
 }
 
+/* Caller should hold memory_lock semaphore */
+bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]);
+
+	/*
+	 * SR-IOV VF memory enable is handled by the MSE bit in the
+	 * PF SR-IOV capability, there's therefore no need to trigger
+	 * faults based on the virtual value.
+	 */
+	return pdev->no_command_memory || (cmd & PCI_COMMAND_MEMORY);
+}
+
 /*
  * Restore the *real* BARs after we detect a FLR or backdoor reset.
  * (backdoor = some device specific technique that we didn't catch)
@@ -504,8 +518,8 @@
 
 	count = vfio_default_config_read(vdev, pos, count, perm, offset, val);
 
-	/* Mask in virtual memory enable for SR-IOV devices */
-	if (offset == PCI_COMMAND && vdev->pdev->is_virtfn) {
+	/* Mask in virtual memory enable */
+	if (offset == PCI_COMMAND && vdev->pdev->no_command_memory) {
 		u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]);
 		u32 tmp_val = le32_to_cpu(*val);
 
@@ -554,13 +568,18 @@
 
 		new_cmd = le32_to_cpu(val);
 
+		phys_io = !!(phys_cmd & PCI_COMMAND_IO);
+		virt_io = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_IO);
+		new_io = !!(new_cmd & PCI_COMMAND_IO);
+
 		phys_mem = !!(phys_cmd & PCI_COMMAND_MEMORY);
 		virt_mem = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_MEMORY);
 		new_mem = !!(new_cmd & PCI_COMMAND_MEMORY);
 
-		phys_io = !!(phys_cmd & PCI_COMMAND_IO);
-		virt_io = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_IO);
-		new_io = !!(new_cmd & PCI_COMMAND_IO);
+		if (!new_mem)
+			vfio_pci_zap_and_down_write_memory_lock(vdev);
+		else
+			down_write(&vdev->memory_lock);
 
 		/*
 		 * If the user is writing mem/io enable (new_mem/io) and we
@@ -568,17 +587,22 @@
 		 * shows it disabled (phys_mem/io, then the device has
 		 * undergone some kind of backdoor reset and needs to be
 		 * restored before we allow it to enable the bars.
-		 * SR-IOV devices will trigger this, but we catch them later
+		 * SR-IOV devices will trigger this - for mem enable let's
+		 * catch this now and for io enable it will be caught later
 		 */
-		if ((new_mem && virt_mem && !phys_mem) ||
+		if ((new_mem && virt_mem && !phys_mem &&
+		     !pdev->no_command_memory) ||
 		    (new_io && virt_io && !phys_io) ||
 		    vfio_need_bar_restore(vdev))
 			vfio_bar_restore(vdev);
 	}
 
 	count = vfio_default_config_write(vdev, pos, count, perm, offset, val);
-	if (count < 0)
+	if (count < 0) {
+		if (offset == PCI_COMMAND)
+			up_write(&vdev->memory_lock);
 		return count;
+	}
 
 	/*
 	 * Save current memory/io enable bits in vconfig to allow for
@@ -589,6 +613,8 @@
 
 		*virt_cmd &= cpu_to_le16(~mask);
 		*virt_cmd |= cpu_to_le16(new_cmd & mask);
+
+		up_write(&vdev->memory_lock);
 	}
 
 	/* Emulate INTx disable */
@@ -826,8 +852,11 @@
 						 pos - offset + PCI_EXP_DEVCAP,
 						 &cap);
 
-		if (!ret && (cap & PCI_EXP_DEVCAP_FLR))
+		if (!ret && (cap & PCI_EXP_DEVCAP_FLR)) {
+			vfio_pci_zap_and_down_write_memory_lock(vdev);
 			pci_try_reset_function(vdev->pdev);
+			up_write(&vdev->memory_lock);
+		}
 	}
 
 	/*
@@ -905,8 +934,11 @@
 						pos - offset + PCI_AF_CAP,
 						&cap);
 
-		if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP))
+		if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP)) {
+			vfio_pci_zap_and_down_write_memory_lock(vdev);
 			pci_try_reset_function(vdev->pdev);
+			up_write(&vdev->memory_lock);
+		}
 	}
 
 	return count;
@@ -1460,7 +1492,12 @@
 		if (ret)
 			return ret;
 
-		if (cap <= PCI_CAP_ID_MAX) {
+		/*
+		 * ID 0 is a NULL capability, conflicting with our fake
+		 * PCI_CAP_ID_BASIC.  As it has no content, consider it
+		 * hidden for now.
+		 */
+		if (cap && cap <= PCI_CAP_ID_MAX) {
 			len = pci_cap_length[cap];
 			if (len == 0xFF) { /* Variable length */
 				len = vfio_cap_len(vdev, cap, pos);
@@ -1539,7 +1576,7 @@
 			if (len == 0xFF) {
 				len = vfio_ext_cap_len(vdev, ecap, epos);
 				if (len < 0)
-					return ret;
+					return len;
 			}
 		}
 
@@ -1698,6 +1735,17 @@
 
 		vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */
 	}
+	if (pdev->no_command_memory) {
+		/*
+		 * VFs and devices that set pdev->no_command_memory do not
+		 * implement the memory enable bit of the COMMAND register
+		 * therefore we'll not have it set in our initial copy of
+		 * config space after pci_enable_device().  For consistency
+		 * with PFs, set the virtual enable bit here.
+		 */
+		*(__le16 *)&vconfig[PCI_COMMAND] |=
+					cpu_to_le16(PCI_COMMAND_MEMORY);
+	}
 
 	if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx)
 		vconfig[PCI_INTERRUPT_PIN] = 0;
@@ -1726,8 +1774,11 @@
 	vdev->vconfig = NULL;
 	kfree(vdev->pci_config_map);
 	vdev->pci_config_map = NULL;
-	kfree(vdev->msi_perm);
-	vdev->msi_perm = NULL;
+	if (vdev->msi_perm) {
+		free_perm_bits(vdev->msi_perm);
+		kfree(vdev->msi_perm);
+		vdev->msi_perm = NULL;
+	}
 }
 
 /*
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 3fa3f72..869dce5 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -249,6 +249,7 @@
 	struct pci_dev *pdev = vdev->pdev;
 	unsigned int flag = msix ? PCI_IRQ_MSIX : PCI_IRQ_MSI;
 	int ret;
+	u16 cmd;
 
 	if (!is_irq_none(vdev))
 		return -EINVAL;
@@ -258,13 +259,16 @@
 		return -ENOMEM;
 
 	/* return the number of supported vectors if we can't get all: */
+	cmd = vfio_pci_memory_lock_and_enable(vdev);
 	ret = pci_alloc_irq_vectors(pdev, 1, nvec, flag);
 	if (ret < nvec) {
 		if (ret > 0)
 			pci_free_irq_vectors(pdev);
+		vfio_pci_memory_unlock_and_restore(vdev, cmd);
 		kfree(vdev->ctx);
 		return ret;
 	}
+	vfio_pci_memory_unlock_and_restore(vdev, cmd);
 
 	vdev->num_ctx = nvec;
 	vdev->irq_type = msix ? VFIO_PCI_MSIX_IRQ_INDEX :
@@ -287,6 +291,7 @@
 	struct pci_dev *pdev = vdev->pdev;
 	struct eventfd_ctx *trigger;
 	int irq, ret;
+	u16 cmd;
 
 	if (vector < 0 || vector >= vdev->num_ctx)
 		return -EINVAL;
@@ -294,8 +299,12 @@
 	irq = pci_irq_vector(pdev, vector);
 
 	if (vdev->ctx[vector].trigger) {
-		free_irq(irq, vdev->ctx[vector].trigger);
 		irq_bypass_unregister_producer(&vdev->ctx[vector].producer);
+
+		cmd = vfio_pci_memory_lock_and_enable(vdev);
+		free_irq(irq, vdev->ctx[vector].trigger);
+		vfio_pci_memory_unlock_and_restore(vdev, cmd);
+
 		kfree(vdev->ctx[vector].name);
 		eventfd_ctx_put(vdev->ctx[vector].trigger);
 		vdev->ctx[vector].trigger = NULL;
@@ -323,6 +332,7 @@
 	 * such a reset it would be unsuccessful. To avoid this, restore the
 	 * cached value of the message prior to enabling.
 	 */
+	cmd = vfio_pci_memory_lock_and_enable(vdev);
 	if (msix) {
 		struct msi_msg msg;
 
@@ -332,6 +342,7 @@
 
 	ret = request_irq(irq, vfio_msihandler, 0,
 			  vdev->ctx[vector].name, trigger);
+	vfio_pci_memory_unlock_and_restore(vdev, cmd);
 	if (ret) {
 		kfree(vdev->ctx[vector].name);
 		eventfd_ctx_put(trigger);
@@ -341,11 +352,13 @@
 	vdev->ctx[vector].producer.token = trigger;
 	vdev->ctx[vector].producer.irq = irq;
 	ret = irq_bypass_register_producer(&vdev->ctx[vector].producer);
-	if (unlikely(ret))
+	if (unlikely(ret)) {
 		dev_info(&pdev->dev,
 		"irq bypass producer (token %p) registration fails: %d\n",
 		vdev->ctx[vector].producer.token, ret);
 
+		vdev->ctx[vector].producer.token = NULL;
+	}
 	vdev->ctx[vector].trigger = trigger;
 
 	return 0;
@@ -376,6 +389,7 @@
 {
 	struct pci_dev *pdev = vdev->pdev;
 	int i;
+	u16 cmd;
 
 	for (i = 0; i < vdev->num_ctx; i++) {
 		vfio_virqfd_disable(&vdev->ctx[i].unmask);
@@ -384,7 +398,9 @@
 
 	vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix);
 
+	cmd = vfio_pci_memory_lock_and_enable(vdev);
 	pci_free_irq_vectors(pdev);
+	vfio_pci_memory_unlock_and_restore(vdev, cmd);
 
 	/*
 	 * Both disable paths above use pci_intx_for_msi() to clear DisINTx
diff --git a/drivers/vfio/pci/vfio_pci_nvlink2.c b/drivers/vfio/pci/vfio_pci_nvlink2.c
index f2983f0..08f1783 100644
--- a/drivers/vfio/pci/vfio_pci_nvlink2.c
+++ b/drivers/vfio/pci/vfio_pci_nvlink2.c
@@ -97,8 +97,10 @@
 
 	/* If there were any mappings at all... */
 	if (data->mm) {
-		ret = mm_iommu_put(data->mm, data->mem);
-		WARN_ON(ret);
+		if (data->mem) {
+			ret = mm_iommu_put(data->mm, data->mem);
+			WARN_ON(ret);
+		}
 
 		mmdrop(data->mm);
 	}
@@ -229,7 +231,7 @@
 		return -EINVAL;
 
 	if (of_property_read_u32(npu_node, "memory-region", &mem_phandle))
-		return -EINVAL;
+		return -ENODEV;
 
 	mem_node = of_find_node_by_phandle(mem_phandle);
 	if (!mem_node)
@@ -391,7 +393,7 @@
 	int ret;
 	struct vfio_pci_npu2_data *data;
 	struct device_node *nvlink_dn;
-	u32 nvlink_index = 0;
+	u32 nvlink_index = 0, mem_phandle = 0;
 	struct pci_dev *npdev = vdev->pdev;
 	struct device_node *npu_node = pci_device_to_OF_node(npdev);
 	struct pci_controller *hose = pci_bus_to_host(npdev->bus);
@@ -406,6 +408,9 @@
 	if (!pnv_pci_get_gpu_dev(vdev->pdev))
 		return -ENODEV;
 
+	if (of_property_read_u32(npu_node, "memory-region", &mem_phandle))
+		return -ENODEV;
+
 	/*
 	 * NPU2 normally has 8 ATSD registers (for concurrency) and 6 links
 	 * so we can allocate one register per link, using nvlink index as
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
index ee6ee91..987b4d3 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -84,6 +84,11 @@
 	struct mutex		lock;
 };
 
+struct vfio_pci_mmap_vma {
+	struct vm_area_struct	*vma;
+	struct list_head	vma_next;
+};
+
 struct vfio_pci_device {
 	struct pci_dev		*pdev;
 	void __iomem		*barmap[PCI_STD_RESOURCE_END + 1];
@@ -122,6 +127,9 @@
 	struct list_head	dummy_resources_list;
 	struct mutex		ioeventfds_lock;
 	struct list_head	ioeventfds_list;
+	struct mutex		vma_lock;
+	struct list_head	vma_list;
+	struct rw_semaphore	memory_lock;
 };
 
 #define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX)
@@ -164,6 +172,13 @@
 extern int vfio_pci_set_power_state(struct vfio_pci_device *vdev,
 				    pci_power_t state);
 
+extern bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev);
+extern void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_device
+						    *vdev);
+extern u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_device *vdev);
+extern void vfio_pci_memory_unlock_and_restore(struct vfio_pci_device *vdev,
+					       u16 cmd);
+
 #ifdef CONFIG_VFIO_PCI_IGD
 extern int vfio_pci_igd_init(struct vfio_pci_device *vdev);
 #else
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 0120d83..83f81d2 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -162,6 +162,7 @@
 	size_t x_start = 0, x_end = 0;
 	resource_size_t end;
 	void __iomem *io;
+	struct resource *res = &vdev->pdev->resource[bar];
 	ssize_t done;
 
 	if (pci_resource_start(pdev, bar))
@@ -177,6 +178,14 @@
 
 	count = min(count, (size_t)(end - pos));
 
+	if (res->flags & IORESOURCE_MEM) {
+		down_read(&vdev->memory_lock);
+		if (!__vfio_pci_memory_enabled(vdev)) {
+			up_read(&vdev->memory_lock);
+			return -EIO;
+		}
+	}
+
 	if (bar == PCI_ROM_RESOURCE) {
 		/*
 		 * The ROM can fill less space than the BAR, so we start the
@@ -184,13 +193,17 @@
 		 * filling large ROM BARs much faster.
 		 */
 		io = pci_map_rom(pdev, &x_start);
-		if (!io)
-			return -ENOMEM;
+		if (!io) {
+			done = -ENOMEM;
+			goto out;
+		}
 		x_end = end;
 	} else {
 		int ret = vfio_pci_setup_barmap(vdev, bar);
-		if (ret)
-			return ret;
+		if (ret) {
+			done = ret;
+			goto out;
+		}
 
 		io = vdev->barmap[bar];
 	}
@@ -207,6 +220,9 @@
 
 	if (bar == PCI_ROM_RESOURCE)
 		pci_unmap_rom(pdev, io);
+out:
+	if (res->flags & IORESOURCE_MEM)
+		up_read(&vdev->memory_lock);
 
 	return done;
 }
diff --git a/drivers/vfio/platform/vfio_platform.c b/drivers/vfio/platform/vfio_platform.c
index ae1a5eb..1e27690 100644
--- a/drivers/vfio/platform/vfio_platform.c
+++ b/drivers/vfio/platform/vfio_platform.c
@@ -44,7 +44,7 @@
 {
 	struct platform_device *pdev = (struct platform_device *) vdev->opaque;
 
-	return platform_get_irq(pdev, i);
+	return platform_get_irq_optional(pdev, i);
 }
 
 static int vfio_platform_probe(struct platform_device *pdev)
diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c
index e8f2bdb..6f72703 100644
--- a/drivers/vfio/platform/vfio_platform_common.c
+++ b/drivers/vfio/platform/vfio_platform_common.c
@@ -267,7 +267,7 @@
 
 		ret = pm_runtime_get_sync(vdev->device);
 		if (ret < 0)
-			goto err_pm;
+			goto err_rst;
 
 		ret = vfio_platform_call_reset(vdev, &extra_dbg);
 		if (ret && vdev->reset_required) {
@@ -284,13 +284,12 @@
 
 err_rst:
 	pm_runtime_put(vdev->device);
-err_pm:
 	vfio_platform_irq_cleanup(vdev);
 err_irq:
 	vfio_platform_regions_cleanup(vdev);
 err_reg:
 	mutex_unlock(&driver_lock);
-	module_put(THIS_MODULE);
+	module_put(vdev->parent_module);
 	return ret;
 }
 
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index d864277..6b1e8cb 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -24,6 +24,7 @@
 #include <linux/compat.h>
 #include <linux/device.h>
 #include <linux/fs.h>
+#include <linux/highmem.h>
 #include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/mm.h>
@@ -335,6 +336,42 @@
 	return 0;
 }
 
+static int follow_fault_pfn(struct vm_area_struct *vma, struct mm_struct *mm,
+			    unsigned long vaddr, unsigned long *pfn,
+			    bool write_fault)
+{
+	pte_t *ptep;
+	spinlock_t *ptl;
+	int ret;
+
+	ret = follow_pte(vma->vm_mm, vaddr, &ptep, &ptl);
+	if (ret) {
+		bool unlocked = false;
+
+		ret = fixup_user_fault(NULL, mm, vaddr,
+				       FAULT_FLAG_REMOTE |
+				       (write_fault ?  FAULT_FLAG_WRITE : 0),
+				       &unlocked);
+		if (unlocked)
+			return -EAGAIN;
+
+		if (ret)
+			return ret;
+
+		ret = follow_pte(vma->vm_mm, vaddr, &ptep, &ptl);
+		if (ret)
+			return ret;
+	}
+
+	if (write_fault && !pte_write(*ptep))
+		ret = -EFAULT;
+	else
+		*pfn = pte_pfn(*ptep);
+
+	pte_unmap_unlock(ptep, ptl);
+	return ret;
+}
+
 static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 			 int prot, unsigned long *pfn)
 {
@@ -377,12 +414,16 @@
 
 	vaddr = untagged_addr(vaddr);
 
+retry:
 	vma = find_vma_intersection(mm, vaddr, vaddr + 1);
 
 	if (vma && vma->vm_flags & VM_PFNMAP) {
-		*pfn = ((vaddr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
-		if (is_invalid_reserved_pfn(*pfn))
-			ret = 0;
+		ret = follow_fault_pfn(vma, mm, vaddr, pfn, prot & IOMMU_WRITE);
+		if (ret == -EAGAIN)
+			goto retry;
+
+		if (!ret && !is_invalid_reserved_pfn(*pfn))
+			ret = -EFAULT;
 	}
 
 	up_read(&mm->mmap_sem);
@@ -593,7 +634,7 @@
 			continue;
 		}
 
-		remote_vaddr = dma->vaddr + iova - dma->iova;
+		remote_vaddr = dma->vaddr + (iova - dma->iova);
 		ret = vfio_pin_page_external(dma, remote_vaddr, &phys_pfn[i],
 					     do_accounting);
 		if (ret)
@@ -601,7 +642,8 @@
 
 		ret = vfio_add_to_pfn_list(dma, iova, phys_pfn[i]);
 		if (ret) {
-			vfio_unpin_page_external(dma, iova, do_accounting);
+			if (put_pfn(phys_pfn[i], dma->prot) && do_accounting)
+				vfio_lock_acct(dma, -1, true);
 			goto pin_unwind;
 		}
 	}
@@ -835,6 +877,7 @@
 
 static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
 {
+	WARN_ON(!RB_EMPTY_ROOT(&dma->pfn_list));
 	vfio_unmap_unpin(iommu, dma, true);
 	vfio_unlink_dma(iommu, dma);
 	put_task_struct(dma->task);
@@ -1187,13 +1230,16 @@
 static int vfio_iommu_replay(struct vfio_iommu *iommu,
 			     struct vfio_domain *domain)
 {
-	struct vfio_domain *d;
+	struct vfio_domain *d = NULL;
 	struct rb_node *n;
 	unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 	int ret;
 
 	/* Arbitrarily pick the first domain in the list for lookups */
-	d = list_first_entry(&iommu->domain_list, struct vfio_domain, next);
+	if (!list_empty(&iommu->domain_list))
+		d = list_first_entry(&iommu->domain_list,
+				     struct vfio_domain, next);
+
 	n = rb_first(&iommu->dma_list);
 
 	for (; n; n = rb_next(n)) {
@@ -1211,6 +1257,11 @@
 				phys_addr_t p;
 				dma_addr_t i;
 
+				if (WARN_ON(!d)) { /* mapped w/o a domain?! */
+					ret = -EINVAL;
+					goto unwind;
+				}
+
 				phys = iommu_iova_to_phys(d->domain, iova);
 
 				if (WARN_ON(!phys)) {
@@ -1240,7 +1291,7 @@
 				if (npage <= 0) {
 					WARN_ON(!npage);
 					ret = (int)npage;
-					return ret;
+					goto unwind;
 				}
 
 				phys = pfn << PAGE_SHIFT;
@@ -1249,14 +1300,67 @@
 
 			ret = iommu_map(domain->domain, iova, phys,
 					size, dma->prot | domain->prot);
-			if (ret)
-				return ret;
+			if (ret) {
+				if (!dma->iommu_mapped)
+					vfio_unpin_pages_remote(dma, iova,
+							phys >> PAGE_SHIFT,
+							size >> PAGE_SHIFT,
+							true);
+				goto unwind;
+			}
 
 			iova += size;
 		}
+	}
+
+	/* All dmas are now mapped, defer to second tree walk for unwind */
+	for (n = rb_first(&iommu->dma_list); n; n = rb_next(n)) {
+		struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node);
+
 		dma->iommu_mapped = true;
 	}
+
 	return 0;
+
+unwind:
+	for (; n; n = rb_prev(n)) {
+		struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node);
+		dma_addr_t iova;
+
+		if (dma->iommu_mapped) {
+			iommu_unmap(domain->domain, dma->iova, dma->size);
+			continue;
+		}
+
+		iova = dma->iova;
+		while (iova < dma->iova + dma->size) {
+			phys_addr_t phys, p;
+			size_t size;
+			dma_addr_t i;
+
+			phys = iommu_iova_to_phys(domain->domain, iova);
+			if (!phys) {
+				iova += PAGE_SIZE;
+				continue;
+			}
+
+			size = PAGE_SIZE;
+			p = phys + size;
+			i = iova + size;
+			while (i < dma->iova + dma->size &&
+			       p == iommu_iova_to_phys(domain->domain, i)) {
+				size += PAGE_SIZE;
+				p += PAGE_SIZE;
+				i += PAGE_SIZE;
+			}
+
+			iommu_unmap(domain->domain, iova, size);
+			vfio_unpin_pages_remote(dma, iova, phys >> PAGE_SHIFT,
+						size >> PAGE_SHIFT, true);
+		}
+	}
+
+	return ret;
 }
 
 /*
@@ -1882,23 +1986,6 @@
 	}
 }
 
-static void vfio_sanity_check_pfn_list(struct vfio_iommu *iommu)
-{
-	struct rb_node *n;
-
-	n = rb_first(&iommu->dma_list);
-	for (; n; n = rb_next(n)) {
-		struct vfio_dma *dma;
-
-		dma = rb_entry(n, struct vfio_dma, node);
-
-		if (WARN_ON(!RB_EMPTY_ROOT(&dma->pfn_list)))
-			break;
-	}
-	/* mdev vendor driver must unregister notifier */
-	WARN_ON(iommu->notifier.head);
-}
-
 /*
  * Called when a domain is removed in detach. It is possible that
  * the removed domain decided the iova aperture window. Modify the
@@ -1996,10 +2083,10 @@
 			kfree(group);
 
 			if (list_empty(&iommu->external_domain->group_list)) {
-				vfio_sanity_check_pfn_list(iommu);
-
-				if (!IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu))
+				if (!IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu)) {
+					WARN_ON(iommu->notifier.head);
 					vfio_iommu_unmap_unpin_all(iommu);
+				}
 
 				kfree(iommu->external_domain);
 				iommu->external_domain = NULL;
@@ -2032,10 +2119,12 @@
 		 */
 		if (list_empty(&domain->group_list)) {
 			if (list_is_singular(&iommu->domain_list)) {
-				if (!iommu->external_domain)
+				if (!iommu->external_domain) {
+					WARN_ON(iommu->notifier.head);
 					vfio_iommu_unmap_unpin_all(iommu);
-				else
+				} else {
 					vfio_iommu_unmap_unpin_reaccount(iommu);
+				}
 			}
 			iommu_domain_free(domain->domain);
 			list_del(&domain->next);
@@ -2109,7 +2198,6 @@
 
 	if (iommu->external_domain) {
 		vfio_release_domain(iommu->external_domain, true);
-		vfio_sanity_check_pfn_list(iommu);
 		kfree(iommu->external_domain);
 	}
 
@@ -2211,6 +2299,24 @@
 	return ret;
 }
 
+static int vfio_iommu_dma_avail_build_caps(struct vfio_iommu *iommu,
+					   struct vfio_info_cap *caps)
+{
+	struct vfio_iommu_type1_info_dma_avail cap_dma_avail;
+	int ret;
+
+	mutex_lock(&iommu->lock);
+	cap_dma_avail.header.id = VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL;
+	cap_dma_avail.header.version = 1;
+
+	cap_dma_avail.avail = iommu->dma_avail;
+
+	ret = vfio_info_add_capability(caps, &cap_dma_avail.header,
+				       sizeof(cap_dma_avail));
+	mutex_unlock(&iommu->lock);
+	return ret;
+}
+
 static long vfio_iommu_type1_ioctl(void *iommu_data,
 				   unsigned int cmd, unsigned long arg)
 {
@@ -2257,6 +2363,10 @@
 		info.iova_pgsizes = vfio_pgsize_bitmap(iommu);
 
 		ret = vfio_iommu_iova_build_caps(iommu, &caps);
+
+		if (!ret)
+			ret = vfio_iommu_dma_avail_build_caps(iommu, &caps);
+
 		if (ret)
 			return ret;