Merge tag 'vfio-v5.8-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Block accesses to disabled MMIO space (Alex Williamson)

 - VFIO device migration API (Kirti Wankhede)

 - type1 IOMMU dirty bitmap API and implementation (Kirti Wankhede)

 - PCI NULL capability masking (Alex Williamson)

 - Memory leak fixes (Qian Cai)

 - Reference leak fix (Qiushi Wu)

* tag 'vfio-v5.8-rc1' of git://github.com/awilliam/linux-vfio:
  vfio iommu: typecast corrections
  vfio iommu: Use shift operation for 64-bit integer division
  vfio/mdev: Fix reference count leak in add_mdev_supported_type
  vfio: Selective dirty page tracking if IOMMU backed device pins pages
  vfio iommu: Add migration capability to report supported features
  vfio iommu: Update UNMAP_DMA ioctl to get dirty bitmap before unmap
  vfio iommu: Implementation of ioctl for dirty pages tracking
  vfio iommu: Add ioctl definition for dirty pages tracking
  vfio iommu: Cache pgsize_bitmap in struct vfio_iommu
  vfio iommu: Remove atomicity of ref_count of pinned pages
  vfio: UAPI for migration interface for device state
  vfio/pci: fix memory leaks of eventfd ctx
  vfio/pci: fix memory leaks in alloc_perm_bits()
  vfio-pci: Mask cap zero
  vfio-pci: Invalidate mmaps and block MMIO access on disabled memory
  vfio-pci: Fault mmaps to enable vma tracking
  vfio/type1: Support faulting PFNMAP vmas

drivers/vfio/mdev/mdev_sysfs.c

@@ -110,7 +110,7 @@ static struct mdev_type *add_mdev_supported_type(struct mdev_parent *parent,
 				   "%s-%s", dev_driver_string(parent->dev),
 				   group->name);
 	if (ret) {
-		kfree(type);
+		kobject_put(&type->kobj);
 		return ERR_PTR(ret);
 	}
 

drivers/vfio/pci/vfio_pci.c

@@ -26,6 +26,7 @@
 #include <linux/vfio.h>
 #include <linux/vgaarb.h>
 #include <linux/nospec.h>
+#include <linux/sched/mm.h>
 
 #include "vfio_pci_private.h"
 
@@ -184,6 +185,7 @@ static void vfio_pci_probe_mmaps(struct vfio_pci_device *vdev)
 
 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
@@ -519,6 +521,10 @@ static void vfio_pci_release(void *device_data)
 		vfio_pci_vf_token_user_add(vdev, -1);
 		vfio_spapr_pci_eeh_release(vdev->pdev);
 		vfio_pci_disable(vdev);
+		if (vdev->err_trigger)
+			eventfd_ctx_put(vdev->err_trigger);
+		if (vdev->req_trigger)
+			eventfd_ctx_put(vdev->req_trigger);
 	}
 
 	mutex_unlock(&vdev->reflck->lock);
@@ -736,6 +742,12 @@ int vfio_pci_register_dev_region(struct vfio_pci_device *vdev,
 	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)
 {
@@ -809,7 +821,7 @@ static long vfio_pci_ioctl(void *device_data,
 		{
 			void __iomem *io;
 			size_t size;
-			u16 orig_cmd;
+			u16 cmd;
 
 			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
 			info.flags = 0;
@@ -829,10 +841,7 @@ static long vfio_pci_ioctl(void *device_data,
 			 * 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;
@@ -840,8 +849,8 @@ static long vfio_pci_ioctl(void *device_data,
 			} 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:
@@ -984,8 +993,16 @@ static long vfio_pci_ioctl(void *device_data,
 		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;
@@ -1065,8 +1082,9 @@ static long vfio_pci_ioctl(void *device_data,
 		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);
 
@@ -1118,9 +1136,9 @@ static long vfio_pci_ioctl(void *device_data,
 		 * 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;
@@ -1133,8 +1151,9 @@ static long vfio_pci_ioctl(void *device_data,
 				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);
@@ -1153,13 +1172,63 @@ static long vfio_pci_ioctl(void *device_data,
 		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;
@@ -1299,6 +1368,202 @@ static ssize_t vfio_pci_write(void *device_data, const char __user *buf,
 	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;
+	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;
+		mutex_unlock(&vdev->vma_lock);
+		goto up_out;
+	}
+
+	if (__vfio_pci_add_vma(vdev, vma)) {
+		ret = VM_FAULT_OOM;
+		mutex_unlock(&vdev->vma_lock);
+		goto up_out;
+	}
+
+	mutex_unlock(&vdev->vma_lock);
+
+	if (remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+			    vma->vm_end - vma->vm_start, vma->vm_page_prot))
+		ret = VM_FAULT_SIGBUS;
+
+up_out:
+	up_read(&vdev->memory_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;
@@ -1357,8 +1622,14 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 	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)
@@ -1608,6 +1879,9 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	spin_lock_init(&vdev->irqlock);
 	mutex_init(&vdev->ioeventfds_lock);
 	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)
@@ -1861,12 +2135,6 @@ static void vfio_pci_reflck_put(struct vfio_pci_reflck *reflck)
 	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;
@@ -1897,6 +2165,39 @@ static int vfio_pci_get_unused_devs(struct pci_dev *pdev, void *data)
 	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

drivers/vfio/pci/vfio_pci_config.c

@@ -395,6 +395,14 @@ static inline void p_setd(struct perm_bits *p, int off, u32 virt, u32 write)
 	*(__le32 *)(&p->write[off]) = cpu_to_le32(write);
 }
 
+/* Caller should hold memory_lock semaphore */
+bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev)
+{
+	u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]);
+
+	return 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)
@@ -556,13 +564,18 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
 
 		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
@@ -579,8 +592,11 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
 	}
 
 	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
@@ -591,6 +607,8 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
 
 		*virt_cmd &= cpu_to_le16(~mask);
 		*virt_cmd |= cpu_to_le16(new_cmd & mask);
+
+		up_write(&vdev->memory_lock);
 	}
 
 	/* Emulate INTx disable */
@@ -828,8 +846,11 @@ static int vfio_exp_config_write(struct vfio_pci_device *vdev, int pos,
 						 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);
+		}
 	}
 
 	/*
@@ -907,8 +928,11 @@ static int vfio_af_config_write(struct vfio_pci_device *vdev, int pos,
 						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;
@@ -1462,7 +1486,12 @@ static int vfio_cap_init(struct vfio_pci_device *vdev)
 		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);
@@ -1728,8 +1757,11 @@ void vfio_config_free(struct vfio_pci_device *vdev)
 	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;
+	}
 }
 
 /*

drivers/vfio/pci/vfio_pci_intrs.c

@@ -249,6 +249,7 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)
 	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 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)
 		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 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 	struct pci_dev *pdev = vdev->pdev;
 	struct eventfd_ctx *trigger;
 	int irq, ret;
+	u16 cmd;
 
 	if (vector < 0 || vector >= vdev->num_ctx)
 		return -EINVAL;
@@ -295,7 +300,11 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 
 	if (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 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 	 * 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 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 
 	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);
@@ -376,6 +387,7 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix)
 {
 	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 +396,9 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix)
 
 	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

drivers/vfio/pci/vfio_pci_private.h

@@ -92,6 +92,11 @@ struct vfio_pci_vf_token {
 	int			users;
 };
 
+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_NUM_BARS];
@@ -132,6 +137,9 @@ struct vfio_pci_device {
 	struct list_head	ioeventfds_list;
 	struct vfio_pci_vf_token	*vf_token;
 	struct notifier_block	nb;
+	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)
@@ -174,6 +182,13 @@ extern int vfio_pci_register_dev_region(struct vfio_pci_device *vdev,
 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

drivers/vfio/pci/vfio_pci_rdwr.c

@@ -162,6 +162,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
 	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 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
 
 	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 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
 		 * 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 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
 
 	if (bar == PCI_ROM_RESOURCE)
 		pci_unmap_rom(pdev, io);
+out:
+	if (res->flags & IORESOURCE_MEM)
+		up_read(&vdev->memory_lock);
 
 	return done;
 }

drivers/vfio/vfio.c

@@ -85,6 +85,7 @@ struct vfio_group {
 	atomic_t			opened;
 	wait_queue_head_t		container_q;
 	bool				noiommu;
+	unsigned int			dev_counter;
 	struct kvm			*kvm;
 	struct blocking_notifier_head	notifier;
 };
@@ -555,6 +556,7 @@ struct vfio_device *vfio_group_create_device(struct vfio_group *group,
 
 	mutex_lock(&group->device_lock);
 	list_add(&device->group_next, &group->device_list);
+	group->dev_counter++;
 	mutex_unlock(&group->device_lock);
 
 	return device;
@@ -567,6 +569,7 @@ static void vfio_device_release(struct kref *kref)
 	struct vfio_group *group = device->group;
 
 	list_del(&device->group_next);
+	group->dev_counter--;
 	mutex_unlock(&group->device_lock);
 
 	dev_set_drvdata(device->dev, NULL);
@@ -1945,6 +1948,9 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage,
 	if (!group)
 		return -ENODEV;
 
+	if (group->dev_counter > 1)
+		return -EINVAL;
+
 	ret = vfio_group_add_container_user(group);
 	if (ret)
 		goto err_pin_pages;
@@ -1952,7 +1958,8 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage,
 	container = group->container;
 	driver = container->iommu_driver;
 	if (likely(driver && driver->ops->pin_pages))
-		ret = driver->ops->pin_pages(container->iommu_data, user_pfn,
+		ret = driver->ops->pin_pages(container->iommu_data,
+					     group->iommu_group, user_pfn,
 					     npage, prot, phys_pfn);
 	else
 		ret = -ENOTTY;
@@ -2050,8 +2057,8 @@ int vfio_group_pin_pages(struct vfio_group *group,
 	driver = container->iommu_driver;
 	if (likely(driver && driver->ops->pin_pages))
 		ret = driver->ops->pin_pages(container->iommu_data,
-					     user_iova_pfn, npage,
-					     prot, phys_pfn);
+					     group->iommu_group, user_iova_pfn,
+					     npage, prot, phys_pfn);
 	else
 		ret = -ENOTTY;
 

drivers/vfio/vfio_iommu_type1.c

@@ -69,8 +69,11 @@ struct vfio_iommu {
 	struct rb_root		dma_list;
 	struct blocking_notifier_head notifier;
 	unsigned int		dma_avail;
+	uint64_t		pgsize_bitmap;
 	bool			v2;
 	bool			nesting;
+	bool			dirty_page_tracking;
+	bool			pinned_page_dirty_scope;
 };
 
 struct vfio_domain {
@@ -91,12 +94,14 @@ struct vfio_dma {
 	bool			lock_cap;	/* capable(CAP_IPC_LOCK) */
 	struct task_struct	*task;
 	struct rb_root		pfn_list;	/* Ex-user pinned pfn list */
+	unsigned long		*bitmap;
 };
 
 struct vfio_group {
 	struct iommu_group	*iommu_group;
 	struct list_head	next;
 	bool			mdev_group;	/* An mdev group */
+	bool			pinned_page_dirty_scope;
 };
 
 struct vfio_iova {
@@ -112,7 +117,7 @@ struct vfio_pfn {
 	struct rb_node		node;
 	dma_addr_t		iova;		/* Device address */
 	unsigned long		pfn;		/* Host pfn */
-	atomic_t		ref_count;
+	unsigned int		ref_count;
 };
 
 struct vfio_regions {
@@ -125,8 +130,25 @@ struct vfio_regions {
 #define IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu)	\
 					(!list_empty(&iommu->domain_list))
 
+#define DIRTY_BITMAP_BYTES(n)	(ALIGN(n, BITS_PER_TYPE(u64)) / BITS_PER_BYTE)
+
+/*
+ * Input argument of number of bits to bitmap_set() is unsigned integer, which
+ * further casts to signed integer for unaligned multi-bit operation,
+ * __bitmap_set().
+ * Then maximum bitmap size supported is 2^31 bits divided by 2^3 bits/byte,
+ * that is 2^28 (256 MB) which maps to 2^31 * 2^12 = 2^43 (8TB) on 4K page
+ * system.
+ */
+#define DIRTY_BITMAP_PAGES_MAX	 ((u64)INT_MAX)
+#define DIRTY_BITMAP_SIZE_MAX	 DIRTY_BITMAP_BYTES(DIRTY_BITMAP_PAGES_MAX)
+
 static int put_pfn(unsigned long pfn, int prot);
 
+static struct vfio_group *vfio_iommu_find_iommu_group(struct vfio_iommu *iommu,
+					       struct iommu_group *iommu_group);
+
+static void update_pinned_page_dirty_scope(struct vfio_iommu *iommu);
 /*
  * This code handles mapping and unmapping of user data buffers
  * into DMA'ble space using the IOMMU
@@ -175,6 +197,81 @@ static void vfio_unlink_dma(struct vfio_iommu *iommu, struct vfio_dma *old)
 	rb_erase(&old->node, &iommu->dma_list);
 }
 
+
+static int vfio_dma_bitmap_alloc(struct vfio_dma *dma, size_t pgsize)
+{
+	uint64_t npages = dma->size / pgsize;
+
+	if (npages > DIRTY_BITMAP_PAGES_MAX)
+		return -EINVAL;
+
+	/*
+	 * Allocate extra 64 bits that are used to calculate shift required for
+	 * bitmap_shift_left() to manipulate and club unaligned number of pages
+	 * in adjacent vfio_dma ranges.
+	 */
+	dma->bitmap = kvzalloc(DIRTY_BITMAP_BYTES(npages) + sizeof(u64),
+			       GFP_KERNEL);
+	if (!dma->bitmap)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void vfio_dma_bitmap_free(struct vfio_dma *dma)
+{
+	kfree(dma->bitmap);
+	dma->bitmap = NULL;
+}
+
+static void vfio_dma_populate_bitmap(struct vfio_dma *dma, size_t pgsize)
+{
+	struct rb_node *p;
+	unsigned long pgshift = __ffs(pgsize);
+
+	for (p = rb_first(&dma->pfn_list); p; p = rb_next(p)) {
+		struct vfio_pfn *vpfn = rb_entry(p, struct vfio_pfn, node);
+
+		bitmap_set(dma->bitmap, (vpfn->iova - dma->iova) >> pgshift, 1);
+	}
+}
+
+static int vfio_dma_bitmap_alloc_all(struct vfio_iommu *iommu, size_t pgsize)
+{
+	struct rb_node *n;
+
+	for (n = rb_first(&iommu->dma_list); n; n = rb_next(n)) {
+		struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node);
+		int ret;
+
+		ret = vfio_dma_bitmap_alloc(dma, pgsize);
+		if (ret) {
+			struct rb_node *p;
+
+			for (p = rb_prev(n); p; p = rb_prev(p)) {
+				struct vfio_dma *dma = rb_entry(n,
+							struct vfio_dma, node);
+
+				vfio_dma_bitmap_free(dma);
+			}
+			return ret;
+		}
+		vfio_dma_populate_bitmap(dma, pgsize);
+	}
+	return 0;
+}
+
+static void vfio_dma_bitmap_free_all(struct vfio_iommu *iommu)
+{
+	struct rb_node *n;
+
+	for (n = rb_first(&iommu->dma_list); n; n = rb_next(n)) {
+		struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node);
+
+		vfio_dma_bitmap_free(dma);
+	}
+}
+
 /*
  * Helper Functions for host iova-pfn list
  */
@@ -233,7 +330,7 @@ static int vfio_add_to_pfn_list(struct vfio_dma *dma, dma_addr_t iova,
 
 	vpfn->iova = iova;
 	vpfn->pfn = pfn;
-	atomic_set(&vpfn->ref_count, 1);
+	vpfn->ref_count = 1;
 	vfio_link_pfn(dma, vpfn);
 	return 0;
 }
@@ -251,7 +348,7 @@ static struct vfio_pfn *vfio_iova_get_vfio_pfn(struct vfio_dma *dma,
 	struct vfio_pfn *vpfn = vfio_find_vpfn(dma, iova);
 
 	if (vpfn)
-		atomic_inc(&vpfn->ref_count);
+		vpfn->ref_count++;
 	return vpfn;
 }
 
@@ -259,7 +356,8 @@ static int vfio_iova_put_vfio_pfn(struct vfio_dma *dma, struct vfio_pfn *vpfn)
 {
 	int ret = 0;
 
-	if (atomic_dec_and_test(&vpfn->ref_count)) {
+	vpfn->ref_count--;
+	if (!vpfn->ref_count) {
 		ret = put_pfn(vpfn->pfn, dma->prot);
 		vfio_remove_from_pfn_list(dma, vpfn);
 	}
@@ -317,6 +415,32 @@ static int put_pfn(unsigned long pfn, int prot)
 	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)
+{
+	int ret;
+
+	ret = follow_pfn(vma, vaddr, pfn);
+	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_pfn(vma, vaddr, pfn);
+	}
+
+	return ret;
+}
+
 static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 			 int prot, unsigned long *pfn)
 {
@@ -339,12 +463,16 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 
 	vaddr = untagged_addr(vaddr);
 
+retry:
 	vma = find_vma_intersection(mm, vaddr, vaddr + 1);
 
 	if (vma && vma->vm_flags & VM_PFNMAP) {
-		if (!follow_pfn(vma, vaddr, pfn) &&
-		    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;
 	}
 done:
 	up_read(&mm->mmap_sem);
@@ -501,11 +629,13 @@ static int vfio_unpin_page_external(struct vfio_dma *dma, dma_addr_t iova,
 }
 
 static int vfio_iommu_type1_pin_pages(void *iommu_data,
+				      struct iommu_group *iommu_group,
 				      unsigned long *user_pfn,
 				      int npage, int prot,
 				      unsigned long *phys_pfn)
 {
 	struct vfio_iommu *iommu = iommu_data;
+	struct vfio_group *group;
 	int i, j, ret;
 	unsigned long remote_vaddr;
 	struct vfio_dma *dma;
@@ -566,9 +696,26 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
 			vfio_unpin_page_external(dma, iova, do_accounting);
 			goto pin_unwind;
 		}
-	}
 
+		if (iommu->dirty_page_tracking) {
+			unsigned long pgshift = __ffs(iommu->pgsize_bitmap);
+
+			/*
+			 * Bitmap populated with the smallest supported page
+			 * size
+			 */
+			bitmap_set(dma->bitmap,
+				   (iova - dma->iova) >> pgshift, 1);
+		}
+	}
 	ret = i;
+
+	group = vfio_iommu_find_iommu_group(iommu, iommu_group);
+	if (!group->pinned_page_dirty_scope) {
+		group->pinned_page_dirty_scope = true;
+		update_pinned_page_dirty_scope(iommu);
+	}
+
 	goto pin_done;
 
 pin_unwind:
@@ -800,19 +947,19 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
 	vfio_unmap_unpin(iommu, dma, true);
 	vfio_unlink_dma(iommu, dma);
 	put_task_struct(dma->task);
+	vfio_dma_bitmap_free(dma);
 	kfree(dma);
 	iommu->dma_avail++;
 }
 
-static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
+static void vfio_update_pgsize_bitmap(struct vfio_iommu *iommu)
 {
 	struct vfio_domain *domain;
-	unsigned long bitmap = ULONG_MAX;
 
-	mutex_lock(&iommu->lock);
+	iommu->pgsize_bitmap = ULONG_MAX;
+
 	list_for_each_entry(domain, &iommu->domain_list, next)
-		bitmap &= domain->domain->pgsize_bitmap;
-	mutex_unlock(&iommu->lock);
+		iommu->pgsize_bitmap &= domain->domain->pgsize_bitmap;
 
 	/*
 	 * In case the IOMMU supports page sizes smaller than PAGE_SIZE
@@ -822,36 +969,143 @@ static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
 	 * granularity while iommu driver can use the sub-PAGE_SIZE size
 	 * to map the buffer.
 	 */
-	if (bitmap & ~PAGE_MASK) {
-		bitmap &= PAGE_MASK;
-		bitmap |= PAGE_SIZE;
+	if (iommu->pgsize_bitmap & ~PAGE_MASK) {
+		iommu->pgsize_bitmap &= PAGE_MASK;
+		iommu->pgsize_bitmap |= PAGE_SIZE;
 	}
+}
+
+static int update_user_bitmap(u64 __user *bitmap, struct vfio_iommu *iommu,
+			      struct vfio_dma *dma, dma_addr_t base_iova,
+			      size_t pgsize)
+{
+	unsigned long pgshift = __ffs(pgsize);
+	unsigned long nbits = dma->size >> pgshift;
+	unsigned long bit_offset = (dma->iova - base_iova) >> pgshift;
+	unsigned long copy_offset = bit_offset / BITS_PER_LONG;
+	unsigned long shift = bit_offset % BITS_PER_LONG;
+	unsigned long leftover;
+
+	/*
+	 * mark all pages dirty if any IOMMU capable device is not able
+	 * to report dirty pages and all pages are pinned and mapped.
+	 */
+	if (!iommu->pinned_page_dirty_scope && dma->iommu_mapped)
+		bitmap_set(dma->bitmap, 0, nbits);
 
-	return bitmap;
+	if (shift) {
+		bitmap_shift_left(dma->bitmap, dma->bitmap, shift,
+				  nbits + shift);
+
+		if (copy_from_user(&leftover,
+				   (void __user *)(bitmap + copy_offset),
+				   sizeof(leftover)))
+			return -EFAULT;
+
+		bitmap_or(dma->bitmap, dma->bitmap, &leftover, shift);
+	}
+
+	if (copy_to_user((void __user *)(bitmap + copy_offset), dma->bitmap,
+			 DIRTY_BITMAP_BYTES(nbits + shift)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int vfio_iova_dirty_bitmap(u64 __user *bitmap, struct vfio_iommu *iommu,
+				  dma_addr_t iova, size_t size, size_t pgsize)
+{
+	struct vfio_dma *dma;
+	struct rb_node *n;
+	unsigned long pgshift = __ffs(pgsize);
+	int ret;
+
+	/*
+	 * GET_BITMAP request must fully cover vfio_dma mappings.  Multiple
+	 * vfio_dma mappings may be clubbed by specifying large ranges, but
+	 * there must not be any previous mappings bisected by the range.
+	 * An error will be returned if these conditions are not met.
+	 */
+	dma = vfio_find_dma(iommu, iova, 1);
+	if (dma && dma->iova != iova)
+		return -EINVAL;
+
+	dma = vfio_find_dma(iommu, iova + size - 1, 0);
+	if (dma && dma->iova + dma->size != iova + size)
+		return -EINVAL;
+
+	for (n = rb_first(&iommu->dma_list); n; n = rb_next(n)) {
+		struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node);
+
+		if (dma->iova < iova)
+			continue;
+
+		if (dma->iova > iova + size - 1)
+			break;
+
+		ret = update_user_bitmap(bitmap, iommu, dma, iova, pgsize);
+		if (ret)
+			return ret;
+
+		/*
+		 * Re-populate bitmap to include all pinned pages which are
+		 * considered as dirty but exclude pages which are unpinned and
+		 * pages which are marked dirty by vfio_dma_rw()
+		 */
+		bitmap_clear(dma->bitmap, 0, dma->size >> pgshift);
+		vfio_dma_populate_bitmap(dma, pgsize);
+	}
+	return 0;
+}
+
+static int verify_bitmap_size(uint64_t npages, uint64_t bitmap_size)
+{
+	if (!npages || !bitmap_size || (bitmap_size > DIRTY_BITMAP_SIZE_MAX) ||
+	    (bitmap_size < DIRTY_BITMAP_BYTES(npages)))
+		return -EINVAL;
+
+	return 0;
 }
 
 static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
-			     struct vfio_iommu_type1_dma_unmap *unmap)
+			     struct vfio_iommu_type1_dma_unmap *unmap,
+			     struct vfio_bitmap *bitmap)
 {
-	uint64_t mask;
 	struct vfio_dma *dma, *dma_last = NULL;
-	size_t unmapped = 0;
+	size_t unmapped = 0, pgsize;
 	int ret = 0, retries = 0;
+	unsigned long pgshift;
+
+	mutex_lock(&iommu->lock);
 
-	mask = ((uint64_t)1 << __ffs(vfio_pgsize_bitmap(iommu))) - 1;
+	pgshift = __ffs(iommu->pgsize_bitmap);
+	pgsize = (size_t)1 << pgshift;
+
+	if (unmap->iova & (pgsize - 1)) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	if (!unmap->size || unmap->size & (pgsize - 1)) {
+		ret = -EINVAL;
+		goto unlock;
+	}
 
-	if (unmap->iova & mask)
-		return -EINVAL;
-	if (!unmap->size || unmap->size & mask)
-		return -EINVAL;
 	if (unmap->iova + unmap->size - 1 < unmap->iova ||
-	    unmap->size > SIZE_MAX)
-		return -EINVAL;
+	    unmap->size > SIZE_MAX) {
+		ret = -EINVAL;
+		goto unlock;
+	}
 
-	WARN_ON(mask & PAGE_MASK);
-again:
-	mutex_lock(&iommu->lock);
+	/* When dirty tracking is enabled, allow only min supported pgsize */
+	if ((unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) &&
+	    (!iommu->dirty_page_tracking || (bitmap->pgsize != pgsize))) {
+		ret = -EINVAL;
+		goto unlock;
+	}
 
+	WARN_ON((pgsize - 1) & PAGE_MASK);
+again:
 	/*
 	 * vfio-iommu-type1 (v1) - User mappings were coalesced together to
 	 * avoid tracking individual mappings.  This means that the granularity
@@ -929,8 +1183,17 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
 			blocking_notifier_call_chain(&iommu->notifier,
 						    VFIO_IOMMU_NOTIFY_DMA_UNMAP,
 						    &nb_unmap);
+			mutex_lock(&iommu->lock);
 			goto again;
 		}
+
+		if (unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) {
+			ret = update_user_bitmap(bitmap->data, iommu, dma,
+						 unmap->iova, pgsize);
+			if (ret)
+				break;
+		}
+
 		unmapped += dma->size;
 		vfio_remove_dma(iommu, dma);
 	}
@@ -1037,31 +1300,35 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
 	unsigned long vaddr = map->vaddr;
 	size_t size = map->size;
 	int ret = 0, prot = 0;
-	uint64_t mask;
+	size_t pgsize;
 	struct vfio_dma *dma;
 
 	/* Verify that none of our __u64 fields overflow */
 	if (map->size != size || map->vaddr != vaddr || map->iova != iova)
 		return -EINVAL;
 
-	mask = ((uint64_t)1 << __ffs(vfio_pgsize_bitmap(iommu))) - 1;
-
-	WARN_ON(mask & PAGE_MASK);
-
 	/* READ/WRITE from device perspective */
 	if (map->flags & VFIO_DMA_MAP_FLAG_WRITE)
 		prot |= IOMMU_WRITE;
 	if (map->flags & VFIO_DMA_MAP_FLAG_READ)
 		prot |= IOMMU_READ;
 
-	if (!prot || !size || (size | iova | vaddr) & mask)
-		return -EINVAL;
+	mutex_lock(&iommu->lock);
 
-	/* Don't allow IOVA or virtual address wrap */
-	if (iova + size - 1 < iova || vaddr + size - 1 < vaddr)
-		return -EINVAL;
+	pgsize = (size_t)1 << __ffs(iommu->pgsize_bitmap);
 
-	mutex_lock(&iommu->lock);
+	WARN_ON((pgsize - 1) & PAGE_MASK);
+
+	if (!prot || !size || (size | iova | vaddr) & (pgsize - 1)) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	/* Don't allow IOVA or virtual address wrap */
+	if (iova + size - 1 < iova || vaddr + size - 1 < vaddr) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
 
 	if (vfio_find_dma(iommu, iova, size)) {
 		ret = -EEXIST;
@@ -1129,6 +1396,12 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
 	else
 		ret = vfio_pin_map_dma(iommu, dma, size);
 
+	if (!ret && iommu->dirty_page_tracking) {
+		ret = vfio_dma_bitmap_alloc(dma, pgsize);
+		if (ret)
+			vfio_remove_dma(iommu, dma);
+	}
+
 out_unlock:
 	mutex_unlock(&iommu->lock);
 	return ret;
@@ -1267,6 +1540,51 @@ static struct vfio_group *find_iommu_group(struct vfio_domain *domain,
 	return NULL;
 }
 
+static struct vfio_group *vfio_iommu_find_iommu_group(struct vfio_iommu *iommu,
+					       struct iommu_group *iommu_group)
+{
+	struct vfio_domain *domain;
+	struct vfio_group *group = NULL;
+
+	list_for_each_entry(domain, &iommu->domain_list, next) {
+		group = find_iommu_group(domain, iommu_group);
+		if (group)
+			return group;
+	}
+
+	if (iommu->external_domain)
+		group = find_iommu_group(iommu->external_domain, iommu_group);
+
+	return group;
+}
+
+static void update_pinned_page_dirty_scope(struct vfio_iommu *iommu)
+{
+	struct vfio_domain *domain;
+	struct vfio_group *group;
+
+	list_for_each_entry(domain, &iommu->domain_list, next) {
+		list_for_each_entry(group, &domain->group_list, next) {
+			if (!group->pinned_page_dirty_scope) {
+				iommu->pinned_page_dirty_scope = false;
+				return;
+			}
+		}
+	}
+
+	if (iommu->external_domain) {
+		domain = iommu->external_domain;
+		list_for_each_entry(group, &domain->group_list, next) {
+			if (!group->pinned_page_dirty_scope) {
+				iommu->pinned_page_dirty_scope = false;
+				return;
+			}
+		}
+	}
+
+	iommu->pinned_page_dirty_scope = true;
+}
+
 static bool vfio_iommu_has_sw_msi(struct list_head *group_resv_regions,
 				  phys_addr_t *base)
 {
@@ -1667,12 +1985,23 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 			if (!iommu->external_domain) {
 				INIT_LIST_HEAD(&domain->group_list);
 				iommu->external_domain = domain;
+				vfio_update_pgsize_bitmap(iommu);
 			} else {
 				kfree(domain);
 			}
 
 			list_add(&group->next,
 				 &iommu->external_domain->group_list);
+			/*
+			 * Non-iommu backed group cannot dirty memory directly,
+			 * it can only use interfaces that provide dirty
+			 * tracking.
+			 * The iommu scope can only be promoted with the
+			 * addition of a dirty tracking group.
+			 */
+			group->pinned_page_dirty_scope = true;
+			if (!iommu->pinned_page_dirty_scope)
+				update_pinned_page_dirty_scope(iommu);
 			mutex_unlock(&iommu->lock);
 
 			return 0;
@@ -1792,9 +2121,17 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	}
 
 	list_add(&domain->next, &iommu->domain_list);
+	vfio_update_pgsize_bitmap(iommu);
 done:
 	/* Delete the old one and insert new iova list */
 	vfio_iommu_iova_insert_copy(iommu, &iova_copy);
+
+	/*
+	 * An iommu backed group can dirty memory directly and therefore
+	 * demotes the iommu scope until it declares itself dirty tracking
+	 * capable via the page pinning interface.
+	 */
+	iommu->pinned_page_dirty_scope = false;
 	mutex_unlock(&iommu->lock);
 	vfio_iommu_resv_free(&group_resv_regions);
 
@@ -1947,6 +2284,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 	struct vfio_iommu *iommu = iommu_data;
 	struct vfio_domain *domain;
 	struct vfio_group *group;
+	bool update_dirty_scope = false;
 	LIST_HEAD(iova_copy);
 
 	mutex_lock(&iommu->lock);
@@ -1954,6 +2292,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 	if (iommu->external_domain) {
 		group = find_iommu_group(iommu->external_domain, iommu_group);
 		if (group) {
+			update_dirty_scope = !group->pinned_page_dirty_scope;
 			list_del(&group->next);
 			kfree(group);
 
@@ -1983,6 +2322,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 			continue;
 
 		vfio_iommu_detach_group(domain, group);
+		update_dirty_scope = !group->pinned_page_dirty_scope;
 		list_del(&group->next);
 		kfree(group);
 		/*
@@ -2003,6 +2343,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 			list_del(&domain->next);
 			kfree(domain);
 			vfio_iommu_aper_expand(iommu, &iova_copy);
+			vfio_update_pgsize_bitmap(iommu);
 		}
 		break;
 	}
@@ -2013,6 +2354,12 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 		vfio_iommu_iova_free(&iova_copy);
 
 detach_group_done:
+	/*
+	 * Removal of a group without dirty tracking may allow the iommu scope
+	 * to be promoted.
+	 */
+	if (update_dirty_scope)
+		update_pinned_page_dirty_scope(iommu);
 	mutex_unlock(&iommu->lock);
 }
 
@@ -2135,8 +2482,6 @@ static int vfio_iommu_iova_build_caps(struct vfio_iommu *iommu,
 	size_t size;
 	int iovas = 0, i = 0, ret;
 
-	mutex_lock(&iommu->lock);
-
 	list_for_each_entry(iova, &iommu->iova_list, list)
 		iovas++;
 
@@ -2145,17 +2490,14 @@ static int vfio_iommu_iova_build_caps(struct vfio_iommu *iommu,
 		 * Return 0 as a container with a single mdev device
 		 * will have an empty list
 		 */
-		ret = 0;
-		goto out_unlock;
+		return 0;
 	}
 
 	size = sizeof(*cap_iovas) + (iovas * sizeof(*cap_iovas->iova_ranges));
 
 	cap_iovas = kzalloc(size, GFP_KERNEL);
-	if (!cap_iovas) {
-		ret = -ENOMEM;
-		goto out_unlock;
-	}
+	if (!cap_iovas)
+		return -ENOMEM;
 
 	cap_iovas->nr_iovas = iovas;
 
@@ -2168,11 +2510,25 @@ static int vfio_iommu_iova_build_caps(struct vfio_iommu *iommu,
 	ret = vfio_iommu_iova_add_cap(caps, cap_iovas, size);
 
 	kfree(cap_iovas);
-out_unlock:
-	mutex_unlock(&iommu->lock);
 	return ret;
 }
 
+static int vfio_iommu_migration_build_caps(struct vfio_iommu *iommu,
+					   struct vfio_info_cap *caps)
+{
+	struct vfio_iommu_type1_info_cap_migration cap_mig;
+
+	cap_mig.header.id = VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION;
+	cap_mig.header.version = 1;
+
+	cap_mig.flags = 0;
+	/* support minimum pgsize */
+	cap_mig.pgsize_bitmap = (size_t)1 << __ffs(iommu->pgsize_bitmap);
+	cap_mig.max_dirty_bitmap_size = DIRTY_BITMAP_SIZE_MAX;
+
+	return vfio_info_add_capability(caps, &cap_mig.header, sizeof(cap_mig));
+}
+
 static long vfio_iommu_type1_ioctl(void *iommu_data,
 				   unsigned int cmd, unsigned long arg)
 {
@@ -2214,11 +2570,18 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 			info.cap_offset = 0; /* output, no-recopy necessary */
 		}
 
+		mutex_lock(&iommu->lock);
 		info.flags = VFIO_IOMMU_INFO_PGSIZES;
 
-		info.iova_pgsizes = vfio_pgsize_bitmap(iommu);
+		info.iova_pgsizes = iommu->pgsize_bitmap;
+
+		ret = vfio_iommu_migration_build_caps(iommu, &caps);
+
+		if (!ret)
+			ret = vfio_iommu_iova_build_caps(iommu, &caps);
+
+		mutex_unlock(&iommu->lock);
 
-		ret = vfio_iommu_iova_build_caps(iommu, &caps);
 		if (ret)
 			return ret;
 
@@ -2261,22 +2624,143 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 
 	} else if (cmd == VFIO_IOMMU_UNMAP_DMA) {
 		struct vfio_iommu_type1_dma_unmap unmap;
-		long ret;
+		struct vfio_bitmap bitmap = { 0 };
+		int ret;
 
 		minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size);
 
 		if (copy_from_user(&unmap, (void __user *)arg, minsz))
 			return -EFAULT;
 
-		if (unmap.argsz < minsz || unmap.flags)
+		if (unmap.argsz < minsz ||
+		    unmap.flags & ~VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP)
 			return -EINVAL;
 
-		ret = vfio_dma_do_unmap(iommu, &unmap);
+		if (unmap.flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) {
+			unsigned long pgshift;
+
+			if (unmap.argsz < (minsz + sizeof(bitmap)))
+				return -EINVAL;
+
+			if (copy_from_user(&bitmap,
+					   (void __user *)(arg + minsz),
+					   sizeof(bitmap)))
+				return -EFAULT;
+
+			if (!access_ok((void __user *)bitmap.data, bitmap.size))
+				return -EINVAL;
+
+			pgshift = __ffs(bitmap.pgsize);
+			ret = verify_bitmap_size(unmap.size >> pgshift,
+						 bitmap.size);
+			if (ret)
+				return ret;
+		}
+
+		ret = vfio_dma_do_unmap(iommu, &unmap, &bitmap);
 		if (ret)
 			return ret;
 
 		return copy_to_user((void __user *)arg, &unmap, minsz) ?
 			-EFAULT : 0;
+	} else if (cmd == VFIO_IOMMU_DIRTY_PAGES) {
+		struct vfio_iommu_type1_dirty_bitmap dirty;
+		uint32_t mask = VFIO_IOMMU_DIRTY_PAGES_FLAG_START |
+				VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP |
+				VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP;
+		int ret = 0;
+
+		if (!iommu->v2)
+			return -EACCES;
+
+		minsz = offsetofend(struct vfio_iommu_type1_dirty_bitmap,
+				    flags);
+
+		if (copy_from_user(&dirty, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (dirty.argsz < minsz || dirty.flags & ~mask)
+			return -EINVAL;
+
+		/* only one flag should be set at a time */
+		if (__ffs(dirty.flags) != __fls(dirty.flags))
+			return -EINVAL;
+
+		if (dirty.flags & VFIO_IOMMU_DIRTY_PAGES_FLAG_START) {
+			size_t pgsize;
+
+			mutex_lock(&iommu->lock);
+			pgsize = 1 << __ffs(iommu->pgsize_bitmap);
+			if (!iommu->dirty_page_tracking) {
+				ret = vfio_dma_bitmap_alloc_all(iommu, pgsize);
+				if (!ret)
+					iommu->dirty_page_tracking = true;
+			}
+			mutex_unlock(&iommu->lock);
+			return ret;
+		} else if (dirty.flags & VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP) {
+			mutex_lock(&iommu->lock);
+			if (iommu->dirty_page_tracking) {
+				iommu->dirty_page_tracking = false;
+				vfio_dma_bitmap_free_all(iommu);
+			}
+			mutex_unlock(&iommu->lock);
+			return 0;
+		} else if (dirty.flags &
+				 VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP) {
+			struct vfio_iommu_type1_dirty_bitmap_get range;
+			unsigned long pgshift;
+			size_t data_size = dirty.argsz - minsz;
+			size_t iommu_pgsize;
+
+			if (!data_size || data_size < sizeof(range))
+				return -EINVAL;
+
+			if (copy_from_user(&range, (void __user *)(arg + minsz),
+					   sizeof(range)))
+				return -EFAULT;
+
+			if (range.iova + range.size < range.iova)
+				return -EINVAL;
+			if (!access_ok((void __user *)range.bitmap.data,
+				       range.bitmap.size))
+				return -EINVAL;
+
+			pgshift = __ffs(range.bitmap.pgsize);
+			ret = verify_bitmap_size(range.size >> pgshift,
+						 range.bitmap.size);
+			if (ret)
+				return ret;
+
+			mutex_lock(&iommu->lock);
+
+			iommu_pgsize = (size_t)1 << __ffs(iommu->pgsize_bitmap);
+
+			/* allow only smallest supported pgsize */
+			if (range.bitmap.pgsize != iommu_pgsize) {
+				ret = -EINVAL;
+				goto out_unlock;
+			}
+			if (range.iova & (iommu_pgsize - 1)) {
+				ret = -EINVAL;
+				goto out_unlock;
+			}
+			if (!range.size || range.size & (iommu_pgsize - 1)) {
+				ret = -EINVAL;
+				goto out_unlock;
+			}
+
+			if (iommu->dirty_page_tracking)
+				ret = vfio_iova_dirty_bitmap(range.bitmap.data,
+						iommu, range.iova, range.size,
+						range.bitmap.pgsize);
+			else
+				ret = -EINVAL;
+out_unlock:
+			mutex_unlock(&iommu->lock);
+
+			return ret;
+		}
 	}
 
 	return -ENOTTY;
@@ -2344,10 +2828,19 @@ static int vfio_iommu_type1_dma_rw_chunk(struct vfio_iommu *iommu,
 
 	vaddr = dma->vaddr + offset;
 
-	if (write)
+	if (write) {
 		*copied = copy_to_user((void __user *)vaddr, data,
 					 count) ? 0 : count;
-	else
+		if (*copied && iommu->dirty_page_tracking) {
+			unsigned long pgshift = __ffs(iommu->pgsize_bitmap);
+			/*
+			 * Bitmap populated with the smallest supported page
+			 * size
+			 */
+			bitmap_set(dma->bitmap, offset >> pgshift,
+				   *copied >> pgshift);
+		}
+	} else
 		*copied = copy_from_user(data, (void __user *)vaddr,
 					   count) ? 0 : count;
 	if (kthread)

include/linux/vfio.h

@@ -76,7 +76,9 @@ struct vfio_iommu_driver_ops {
 					struct iommu_group *group);
 	void		(*detach_group)(void *iommu_data,
 					struct iommu_group *group);
-	int		(*pin_pages)(void *iommu_data, unsigned long *user_pfn,
+	int		(*pin_pages)(void *iommu_data,
+				     struct iommu_group *group,
+				     unsigned long *user_pfn,
 				     int npage, int prot,
 				     unsigned long *phys_pfn);
 	int		(*unpin_pages)(void *iommu_data,

include/uapi/linux/vfio.h

@@ -305,6 +305,7 @@ struct vfio_region_info_cap_type {
 #define VFIO_REGION_TYPE_PCI_VENDOR_MASK	(0xffff)
 #define VFIO_REGION_TYPE_GFX                    (1)
 #define VFIO_REGION_TYPE_CCW			(2)
+#define VFIO_REGION_TYPE_MIGRATION              (3)
 
 /* sub-types for VFIO_REGION_TYPE_PCI_* */
 
@@ -379,6 +380,233 @@ struct vfio_region_gfx_edid {
 /* sub-types for VFIO_REGION_TYPE_CCW */
 #define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD	(1)
 
+/* sub-types for VFIO_REGION_TYPE_MIGRATION */
+#define VFIO_REGION_SUBTYPE_MIGRATION           (1)
+
+/*
+ * The structure vfio_device_migration_info is placed at the 0th offset of
+ * the VFIO_REGION_SUBTYPE_MIGRATION region to get and set VFIO device related
+ * migration information. Field accesses from this structure are only supported
+ * at their native width and alignment. Otherwise, the result is undefined and
+ * vendor drivers should return an error.
+ *
+ * device_state: (read/write)
+ *      - The user application writes to this field to inform the vendor driver
+ *        about the device state to be transitioned to.
+ *      - The vendor driver should take the necessary actions to change the
+ *        device state. After successful transition to a given state, the
+ *        vendor driver should return success on write(device_state, state)
+ *        system call. If the device state transition fails, the vendor driver
+ *        should return an appropriate -errno for the fault condition.
+ *      - On the user application side, if the device state transition fails,
+ *	  that is, if write(device_state, state) returns an error, read
+ *	  device_state again to determine the current state of the device from
+ *	  the vendor driver.
+ *      - The vendor driver should return previous state of the device unless
+ *        the vendor driver has encountered an internal error, in which case
+ *        the vendor driver may report the device_state VFIO_DEVICE_STATE_ERROR.
+ *      - The user application must use the device reset ioctl to recover the
+ *        device from VFIO_DEVICE_STATE_ERROR state. If the device is
+ *        indicated to be in a valid device state by reading device_state, the
+ *        user application may attempt to transition the device to any valid
+ *        state reachable from the current state or terminate itself.
+ *
+ *      device_state consists of 3 bits:
+ *      - If bit 0 is set, it indicates the _RUNNING state. If bit 0 is clear,
+ *        it indicates the _STOP state. When the device state is changed to
+ *        _STOP, driver should stop the device before write() returns.
+ *      - If bit 1 is set, it indicates the _SAVING state, which means that the
+ *        driver should start gathering device state information that will be
+ *        provided to the VFIO user application to save the device's state.
+ *      - If bit 2 is set, it indicates the _RESUMING state, which means that
+ *        the driver should prepare to resume the device. Data provided through
+ *        the migration region should be used to resume the device.
+ *      Bits 3 - 31 are reserved for future use. To preserve them, the user
+ *      application should perform a read-modify-write operation on this
+ *      field when modifying the specified bits.
+ *
+ *  +------- _RESUMING
+ *  |+------ _SAVING
+ *  ||+----- _RUNNING
+ *  |||
+ *  000b => Device Stopped, not saving or resuming
+ *  001b => Device running, which is the default state
+ *  010b => Stop the device & save the device state, stop-and-copy state
+ *  011b => Device running and save the device state, pre-copy state
+ *  100b => Device stopped and the device state is resuming
+ *  101b => Invalid state
+ *  110b => Error state
+ *  111b => Invalid state
+ *
+ * State transitions:
+ *
+ *              _RESUMING  _RUNNING    Pre-copy    Stop-and-copy   _STOP
+ *                (100b)     (001b)     (011b)        (010b)       (000b)
+ * 0. Running or default state
+ *                             |
+ *
+ * 1. Normal Shutdown (optional)
+ *                             |------------------------------------->|
+ *
+ * 2. Save the state or suspend
+ *                             |------------------------->|---------->|
+ *
+ * 3. Save the state during live migration
+ *                             |----------->|------------>|---------->|
+ *
+ * 4. Resuming
+ *                  |<---------|
+ *
+ * 5. Resumed
+ *                  |--------->|
+ *
+ * 0. Default state of VFIO device is _RUNNNG when the user application starts.
+ * 1. During normal shutdown of the user application, the user application may
+ *    optionally change the VFIO device state from _RUNNING to _STOP. This
+ *    transition is optional. The vendor driver must support this transition but
+ *    must not require it.
+ * 2. When the user application saves state or suspends the application, the
+ *    device state transitions from _RUNNING to stop-and-copy and then to _STOP.
+ *    On state transition from _RUNNING to stop-and-copy, driver must stop the
+ *    device, save the device state and send it to the application through the
+ *    migration region. The sequence to be followed for such transition is given
+ *    below.
+ * 3. In live migration of user application, the state transitions from _RUNNING
+ *    to pre-copy, to stop-and-copy, and to _STOP.
+ *    On state transition from _RUNNING to pre-copy, the driver should start
+ *    gathering the device state while the application is still running and send
+ *    the device state data to application through the migration region.
+ *    On state transition from pre-copy to stop-and-copy, the driver must stop
+ *    the device, save the device state and send it to the user application
+ *    through the migration region.
+ *    Vendor drivers must support the pre-copy state even for implementations
+ *    where no data is provided to the user before the stop-and-copy state. The
+ *    user must not be required to consume all migration data before the device
+ *    transitions to a new state, including the stop-and-copy state.
+ *    The sequence to be followed for above two transitions is given below.
+ * 4. To start the resuming phase, the device state should be transitioned from
+ *    the _RUNNING to the _RESUMING state.
+ *    In the _RESUMING state, the driver should use the device state data
+ *    received through the migration region to resume the device.
+ * 5. After providing saved device data to the driver, the application should
+ *    change the state from _RESUMING to _RUNNING.
+ *
+ * reserved:
+ *      Reads on this field return zero and writes are ignored.
+ *
+ * pending_bytes: (read only)
+ *      The number of pending bytes still to be migrated from the vendor driver.
+ *
+ * data_offset: (read only)
+ *      The user application should read data_offset field from the migration
+ *      region. The user application should read the device data from this
+ *      offset within the migration region during the _SAVING state or write
+ *      the device data during the _RESUMING state. See below for details of
+ *      sequence to be followed.
+ *
+ * data_size: (read/write)
+ *      The user application should read data_size to get the size in bytes of
+ *      the data copied in the migration region during the _SAVING state and
+ *      write the size in bytes of the data copied in the migration region
+ *      during the _RESUMING state.
+ *
+ * The format of the migration region is as follows:
+ *  ------------------------------------------------------------------
+ * |vfio_device_migration_info|    data section                      |
+ * |                          |     ///////////////////////////////  |
+ * ------------------------------------------------------------------
+ *   ^                              ^
+ *  offset 0-trapped part        data_offset
+ *
+ * The structure vfio_device_migration_info is always followed by the data
+ * section in the region, so data_offset will always be nonzero. The offset
+ * from where the data is copied is decided by the kernel driver. The data
+ * section can be trapped, mmapped, or partitioned, depending on how the kernel
+ * driver defines the data section. The data section partition can be defined
+ * as mapped by the sparse mmap capability. If mmapped, data_offset must be
+ * page aligned, whereas initial section which contains the
+ * vfio_device_migration_info structure, might not end at the offset, which is
+ * page aligned. The user is not required to access through mmap regardless
+ * of the capabilities of the region mmap.
+ * The vendor driver should determine whether and how to partition the data
+ * section. The vendor driver should return data_offset accordingly.
+ *
+ * The sequence to be followed while in pre-copy state and stop-and-copy state
+ * is as follows:
+ * a. Read pending_bytes, indicating the start of a new iteration to get device
+ *    data. Repeated read on pending_bytes at this stage should have no side
+ *    effects.
+ *    If pending_bytes == 0, the user application should not iterate to get data
+ *    for that device.
+ *    If pending_bytes > 0, perform the following steps.
+ * b. Read data_offset, indicating that the vendor driver should make data
+ *    available through the data section. The vendor driver should return this
+ *    read operation only after data is available from (region + data_offset)
+ *    to (region + data_offset + data_size).
+ * c. Read data_size, which is the amount of data in bytes available through
+ *    the migration region.
+ *    Read on data_offset and data_size should return the offset and size of
+ *    the current buffer if the user application reads data_offset and
+ *    data_size more than once here.
+ * d. Read data_size bytes of data from (region + data_offset) from the
+ *    migration region.
+ * e. Process the data.
+ * f. Read pending_bytes, which indicates that the data from the previous
+ *    iteration has been read. If pending_bytes > 0, go to step b.
+ *
+ * The user application can transition from the _SAVING|_RUNNING
+ * (pre-copy state) to the _SAVING (stop-and-copy) state regardless of the
+ * number of pending bytes. The user application should iterate in _SAVING
+ * (stop-and-copy) until pending_bytes is 0.
+ *
+ * The sequence to be followed while _RESUMING device state is as follows:
+ * While data for this device is available, repeat the following steps:
+ * a. Read data_offset from where the user application should write data.
+ * b. Write migration data starting at the migration region + data_offset for
+ *    the length determined by data_size from the migration source.
+ * c. Write data_size, which indicates to the vendor driver that data is
+ *    written in the migration region. Vendor driver must return this write
+ *    operations on consuming data. Vendor driver should apply the
+ *    user-provided migration region data to the device resume state.
+ *
+ * If an error occurs during the above sequences, the vendor driver can return
+ * an error code for next read() or write() operation, which will terminate the
+ * loop. The user application should then take the next necessary action, for
+ * example, failing migration or terminating the user application.
+ *
+ * For the user application, data is opaque. The user application should write
+ * data in the same order as the data is received and the data should be of
+ * same transaction size at the source.
+ */
+
+struct vfio_device_migration_info {
+	__u32 device_state;         /* VFIO device state */
+#define VFIO_DEVICE_STATE_STOP      (0)
+#define VFIO_DEVICE_STATE_RUNNING   (1 << 0)
+#define VFIO_DEVICE_STATE_SAVING    (1 << 1)
+#define VFIO_DEVICE_STATE_RESUMING  (1 << 2)
+#define VFIO_DEVICE_STATE_MASK      (VFIO_DEVICE_STATE_RUNNING | \
+				     VFIO_DEVICE_STATE_SAVING |  \
+				     VFIO_DEVICE_STATE_RESUMING)
+
+#define VFIO_DEVICE_STATE_VALID(state) \
+	(state & VFIO_DEVICE_STATE_RESUMING ? \
+	(state & VFIO_DEVICE_STATE_MASK) == VFIO_DEVICE_STATE_RESUMING : 1)
+
+#define VFIO_DEVICE_STATE_IS_ERROR(state) \
+	((state & VFIO_DEVICE_STATE_MASK) == (VFIO_DEVICE_STATE_SAVING | \
+					      VFIO_DEVICE_STATE_RESUMING))
+
+#define VFIO_DEVICE_STATE_SET_ERROR(state) \
+	((state & ~VFIO_DEVICE_STATE_MASK) | VFIO_DEVICE_SATE_SAVING | \
+					     VFIO_DEVICE_STATE_RESUMING)
+
+	__u32 reserved;
+	__u64 pending_bytes;
+	__u64 data_offset;
+	__u64 data_size;
+};
+
 /*
  * The MSIX mappable capability informs that MSIX data of a BAR can be mmapped
  * which allows direct access to non-MSIX registers which happened to be within
@@ -785,6 +1013,29 @@ struct vfio_iommu_type1_info_cap_iova_range {
 	struct	vfio_iova_range iova_ranges[];
 };
 
+/*
+ * The migration capability allows to report supported features for migration.
+ *
+ * The structures below define version 1 of this capability.
+ *
+ * The existence of this capability indicates that IOMMU kernel driver supports
+ * dirty page logging.
+ *
+ * pgsize_bitmap: Kernel driver returns bitmap of supported page sizes for dirty
+ * page logging.
+ * max_dirty_bitmap_size: Kernel driver returns maximum supported dirty bitmap
+ * size in bytes that can be used by user applications when getting the dirty
+ * bitmap.
+ */
+#define VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION  1
+
+struct vfio_iommu_type1_info_cap_migration {
+	struct	vfio_info_cap_header header;
+	__u32	flags;
+	__u64	pgsize_bitmap;
+	__u64	max_dirty_bitmap_size;		/* in bytes */
+};
+
 #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)
 
 /**
@@ -805,6 +1056,12 @@ struct vfio_iommu_type1_dma_map {
 
 #define VFIO_IOMMU_MAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 13)
 
+struct vfio_bitmap {
+	__u64        pgsize;	/* page size for bitmap in bytes */
+	__u64        size;	/* in bytes */
+	__u64 __user *data;	/* one bit per page */
+};
+
 /**
  * VFIO_IOMMU_UNMAP_DMA - _IOWR(VFIO_TYPE, VFIO_BASE + 14,
  *							struct vfio_dma_unmap)
@@ -814,12 +1071,23 @@ struct vfio_iommu_type1_dma_map {
  * field.  No guarantee is made to the user that arbitrary unmaps of iova
  * or size different from those used in the original mapping call will
  * succeed.
+ * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get the dirty bitmap
+ * before unmapping IO virtual addresses. When this flag is set, the user must
+ * provide a struct vfio_bitmap in data[]. User must provide zero-allocated
+ * memory via vfio_bitmap.data and its size in the vfio_bitmap.size field.
+ * A bit in the bitmap represents one page, of user provided page size in
+ * vfio_bitmap.pgsize field, consecutively starting from iova offset. Bit set
+ * indicates that the page at that offset from iova is dirty. A Bitmap of the
+ * pages in the range of unmapped size is returned in the user-provided
+ * vfio_bitmap.data.
  */
 struct vfio_iommu_type1_dma_unmap {
 	__u32	argsz;
 	__u32	flags;
+#define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0)
 	__u64	iova;				/* IO virtual address */
 	__u64	size;				/* Size of mapping (bytes) */
+	__u8    data[];
 };
 
 #define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14)
@@ -831,6 +1099,57 @@ struct vfio_iommu_type1_dma_unmap {
 #define VFIO_IOMMU_ENABLE	_IO(VFIO_TYPE, VFIO_BASE + 15)
 #define VFIO_IOMMU_DISABLE	_IO(VFIO_TYPE, VFIO_BASE + 16)
 
+/**
+ * VFIO_IOMMU_DIRTY_PAGES - _IOWR(VFIO_TYPE, VFIO_BASE + 17,
+ *                                     struct vfio_iommu_type1_dirty_bitmap)
+ * IOCTL is used for dirty pages logging.
+ * Caller should set flag depending on which operation to perform, details as
+ * below:
+ *
+ * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_START flag set, instructs
+ * the IOMMU driver to log pages that are dirtied or potentially dirtied by
+ * the device; designed to be used when a migration is in progress. Dirty pages
+ * are logged until logging is disabled by user application by calling the IOCTL
+ * with VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP flag.
+ *
+ * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP flag set, instructs
+ * the IOMMU driver to stop logging dirtied pages.
+ *
+ * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP flag set
+ * returns the dirty pages bitmap for IOMMU container for a given IOVA range.
+ * The user must specify the IOVA range and the pgsize through the structure
+ * vfio_iommu_type1_dirty_bitmap_get in the data[] portion. This interface
+ * supports getting a bitmap of the smallest supported pgsize only and can be
+ * modified in future to get a bitmap of any specified supported pgsize. The
+ * user must provide a zeroed memory area for the bitmap memory and specify its
+ * size in bitmap.size. One bit is used to represent one page consecutively
+ * starting from iova offset. The user should provide page size in bitmap.pgsize
+ * field. A bit set in the bitmap indicates that the page at that offset from
+ * iova is dirty. The caller must set argsz to a value including the size of
+ * structure vfio_iommu_type1_dirty_bitmap_get, but excluding the size of the
+ * actual bitmap. If dirty pages logging is not enabled, an error will be
+ * returned.
+ *
+ * Only one of the flags _START, _STOP and _GET may be specified at a time.
+ *
+ */
+struct vfio_iommu_type1_dirty_bitmap {
+	__u32        argsz;
+	__u32        flags;
+#define VFIO_IOMMU_DIRTY_PAGES_FLAG_START	(1 << 0)
+#define VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP	(1 << 1)
+#define VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP	(1 << 2)
+	__u8         data[];
+};
+
+struct vfio_iommu_type1_dirty_bitmap_get {
+	__u64              iova;	/* IO virtual address */
+	__u64              size;	/* Size of iova range */
+	struct vfio_bitmap bitmap;
+};
+
+#define VFIO_IOMMU_DIRTY_PAGES             _IO(VFIO_TYPE, VFIO_BASE + 17)
+
 /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
 
 /*