Merge tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull hmm updates from Jason Gunthorpe:
"This is another round of bug fixing and cleanup. This time the focus
is on the driver pattern to use mmu notifiers to monitor a VA range.
This code is lifted out of many drivers and hmm_mirror directly into
the mmu_notifier core and written using the best ideas from all the
driver implementations.

This removes many bugs from the drivers and has a very pleasing
diffstat. More drivers can still be converted, but that is for another
cycle.

- A shared branch with RDMA reworking the RDMA ODP implementation

- New mmu_interval_notifier API. This is focused on the use case of
monitoring a VA and simplifies the process for drivers

- A common seq-count locking scheme built into the
mmu_interval_notifier API usable by drivers that call
get_user_pages() or hmm_range_fault() with the VA range

- Conversion of mlx5 ODP, hfi1, radeon, nouveau, AMD GPU, and Xen
GntDev drivers to the new API. This deletes a lot of wonky driver
code.

- Two improvements for hmm_range_fault(), from testing done by Ralph"

* tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
mm/hmm: remove hmm_range_dma_map and hmm_range_dma_unmap
mm/hmm: make full use of walk_page_range()
xen/gntdev: use mmu_interval_notifier_insert
mm/hmm: remove hmm_mirror and related
drm/amdgpu: Use mmu_interval_notifier instead of hmm_mirror
drm/amdgpu: Use mmu_interval_insert instead of hmm_mirror
drm/amdgpu: Call find_vma under mmap_sem
nouveau: use mmu_interval_notifier instead of hmm_mirror
nouveau: use mmu_notifier directly for invalidate_range_start
drm/radeon: use mmu_interval_notifier_insert
RDMA/hfi1: Use mmu_interval_notifier_insert for user_exp_rcv
RDMA/odp: Use mmu_interval_notifier_insert()
mm/hmm: define the pre-processor related parts of hmm.h even if disabled
mm/hmm: allow hmm_range to be used with a mmu_interval_notifier or hmm_mirror
mm/mmu_notifier: add an interval tree notifier
mm/mmu_notifier: define the header pre-processor parts even if disabled
mm/hmm: allow snapshot of the special zero page

Documentation/vm/hmm.rst

···
 Address space mirroring's main objective is to allow duplication of a range of
 CPU page table into a device page table; HMM helps keep both synchronized. A
 device driver that wants to mirror a process address space must start with the
-registration of an hmm_mirror struct::
+registration of a mmu_interval_notifier::
 
- int hmm_mirror_register(struct hmm_mirror *mirror,
-                         struct mm_struct *mm);
+ mni->ops = &driver_ops;
+ int mmu_interval_notifier_insert(struct mmu_interval_notifier *mni,
+			          unsigned long start, unsigned long length,
+			          struct mm_struct *mm);
 
-The mirror struct has a set of callbacks that are used
-to propagate CPU page tables::
-
- struct hmm_mirror_ops {
-     /* release() - release hmm_mirror
-      *
-      * @mirror: pointer to struct hmm_mirror
-      *
-      * This is called when the mm_struct is being released.  The callback
-      * must ensure that all access to any pages obtained from this mirror
-      * is halted before the callback returns. All future access should
-      * fault.
-      */
-     void (*release)(struct hmm_mirror *mirror);
-
-     /* sync_cpu_device_pagetables() - synchronize page tables
-      *
-      * @mirror: pointer to struct hmm_mirror
-      * @update: update information (see struct mmu_notifier_range)
-      * Return: -EAGAIN if update.blockable false and callback need to
-      *         block, 0 otherwise.
-      *
-      * This callback ultimately originates from mmu_notifiers when the CPU
-      * page table is updated. The device driver must update its page table
-      * in response to this callback. The update argument tells what action
-      * to perform.
-      *
-      * The device driver must not return from this callback until the device
-      * page tables are completely updated (TLBs flushed, etc); this is a
-      * synchronous call.
-      */
-     int (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror,
-                                       const struct hmm_update *update);
- };
-
-The device driver must perform the update action to the range (mark range
-read only, or fully unmap, etc.). The device must complete the update before
-the driver callback returns.
+During the driver_ops->invalidate() callback the device driver must perform
+the update action to the range (mark range read only, or fully unmap,
+etc.). The device must complete the update before the driver callback returns.
 
 When the device driver wants to populate a range of virtual addresses, it can
 use::
···
       struct hmm_range range;
       ...
 
+      range.notifier = &mni;
       range.start = ...;
       range.end = ...;
       range.pfns = ...;
       range.flags = ...;
       range.values = ...;
       range.pfn_shift = ...;
-      hmm_range_register(&range, mirror);
 
-      /*
-       * Just wait for range to be valid, safe to ignore return value as we
-       * will use the return value of hmm_range_fault() below under the
-       * mmap_sem to ascertain the validity of the range.
-       */
-      hmm_range_wait_until_valid(&range, TIMEOUT_IN_MSEC);
+      if (!mmget_not_zero(mni->notifier.mm))
+          return -EFAULT;
 
  again:
+      range.notifier_seq = mmu_interval_read_begin(&mni);
       down_read(&mm->mmap_sem);
       ret = hmm_range_fault(&range, HMM_RANGE_SNAPSHOT);
       if (ret) {
           up_read(&mm->mmap_sem);
-          if (ret == -EBUSY) {
-            /*
-             * No need to check hmm_range_wait_until_valid() return value
-             * on retry we will get proper error with hmm_range_fault()
-             */
-            hmm_range_wait_until_valid(&range, TIMEOUT_IN_MSEC);
-            goto again;
-          }
-          hmm_range_unregister(&range);
+          if (ret == -EBUSY)
+                 goto again;
           return ret;
       }
+      up_read(&mm->mmap_sem);
+
       take_lock(driver->update);
-      if (!hmm_range_valid(&range)) {
+      if (mmu_interval_read_retry(&ni, range.notifier_seq) {
           release_lock(driver->update);
-          up_read(&mm->mmap_sem);
           goto again;
       }
 
-      // Use pfns array content to update device page table
+      /* Use pfns array content to update device page table,
+       * under the update lock */
 
-      hmm_range_unregister(&range);
       release_lock(driver->update);
-      up_read(&mm->mmap_sem);
       return 0;
  }
 
 The driver->update lock is the same lock that the driver takes inside its
-sync_cpu_device_pagetables() callback. That lock must be held before calling
-hmm_range_valid() to avoid any race with a concurrent CPU page table update.
-
-HMM implements all this on top of the mmu_notifier API because we wanted a
-simpler API and also to be able to perform optimizations latter on like doing
-concurrent device updates in multi-devices scenario.
-
-HMM also serves as an impedance mismatch between how CPU page table updates
-are done (by CPU write to the page table and TLB flushes) and how devices
-update their own page table. Device updates are a multi-step process. First,
-appropriate commands are written to a buffer, then this buffer is scheduled for
-execution on the device. It is only once the device has executed commands in
-the buffer that the update is done. Creating and scheduling the update command
-buffer can happen concurrently for multiple devices. Waiting for each device to
-report commands as executed is serialized (there is no point in doing this
-concurrently).
-
+invalidate() callback. That lock must be held before calling
+mmu_interval_read_retry() to avoid any race with a concurrent CPU page table
+update.
 
 Leverage default_flags and pfn_flags_mask
 =========================================

drivers/gpu/drm/amd/amdgpu/amdgpu.h

···
 	struct mutex  lock_reset;
 	struct amdgpu_doorbell_index doorbell_index;
 
+	struct mutex			notifier_lock;
+
 	int asic_reset_res;
 	struct work_struct		xgmi_reset_work;
 

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

···
  *
  * Returns 0 for success, negative errno for errors.
  */
-static int init_user_pages(struct kgd_mem *mem, struct mm_struct *mm,
-			   uint64_t user_addr)
+static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr)
 {
 	struct amdkfd_process_info *process_info = mem->process_info;
 	struct amdgpu_bo *bo = mem->bo;
···
 	add_kgd_mem_to_kfd_bo_list(*mem, avm->process_info, user_addr);
 
 	if (user_addr) {
-		ret = init_user_pages(*mem, current->mm, user_addr);
+		ret = init_user_pages(*mem, user_addr);
 		if (ret)
 			goto allocate_init_user_pages_failed;
 	}
···
 			return ret;
 		}
 
+		/*
+		 * FIXME: Cannot ignore the return code, must hold
+		 * notifier_lock
+		 */
 		amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
 
 		/* Mark the BO as valid unless it was invalidated

drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c

···
 		e->tv.num_shared = 2;
 
 	amdgpu_bo_list_get_list(p->bo_list, &p->validated);
-	if (p->bo_list->first_userptr != p->bo_list->num_entries)
-		p->mn = amdgpu_mn_get(p->adev, AMDGPU_MN_TYPE_GFX);
 
 	INIT_LIST_HEAD(&duplicates);
 	amdgpu_vm_get_pd_bo(&fpriv->vm, &p->validated, &p->vm_pd);
···
 	if (r)
 		goto error_unlock;
 
-	/* No memory allocation is allowed while holding the mn lock.
-	 * p->mn is hold until amdgpu_cs_submit is finished and fence is added
-	 * to BOs.
+	/* No memory allocation is allowed while holding the notifier lock.
+	 * The lock is held until amdgpu_cs_submit is finished and fence is
+	 * added to BOs.
 	 */
-	amdgpu_mn_lock(p->mn);
+	mutex_lock(&p->adev->notifier_lock);
 
 	/* If userptr are invalidated after amdgpu_cs_parser_bos(), return
 	 * -EAGAIN, drmIoctl in libdrm will restart the amdgpu_cs_ioctl.
···
 	amdgpu_vm_move_to_lru_tail(p->adev, &fpriv->vm);
 
 	ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence);
-	amdgpu_mn_unlock(p->mn);
+	mutex_unlock(&p->adev->notifier_lock);
 
 	return 0;
 
 error_abort:
 	drm_sched_job_cleanup(&job->base);
-	amdgpu_mn_unlock(p->mn);
+	mutex_unlock(&p->adev->notifier_lock);
 
 error_unlock:
 	amdgpu_job_free(job);

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

···
 	mutex_init(&adev->virt.vf_errors.lock);
 	hash_init(adev->mn_hash);
 	mutex_init(&adev->lock_reset);
+	mutex_init(&adev->notifier_lock);
 	mutex_init(&adev->virt.dpm_mutex);
 	mutex_init(&adev->psp.mutex);
 

drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c

···
 #include "amdgpu_amdkfd.h"
 
 /**
- * struct amdgpu_mn_node
+ * amdgpu_mn_invalidate_gfx - callback to notify about mm change
  *
- * @it: interval node defining start-last of the affected address range
- * @bos: list of all BOs in the affected address range
- *
- * Manages all BOs which are affected of a certain range of address space.
- */
-struct amdgpu_mn_node {
-	struct interval_tree_node	it;
-	struct list_head		bos;
-};
-
-/**
- * amdgpu_mn_destroy - destroy the HMM mirror
- *
- * @work: previously sheduled work item
- *
- * Lazy destroys the notifier from a work item
- */
-static void amdgpu_mn_destroy(struct work_struct *work)
-{
-	struct amdgpu_mn *amn = container_of(work, struct amdgpu_mn, work);
-	struct amdgpu_device *adev = amn->adev;
-	struct amdgpu_mn_node *node, *next_node;
-	struct amdgpu_bo *bo, *next_bo;
-
-	mutex_lock(&adev->mn_lock);
-	down_write(&amn->lock);
-	hash_del(&amn->node);
-	rbtree_postorder_for_each_entry_safe(node, next_node,
-					     &amn->objects.rb_root, it.rb) {
-		list_for_each_entry_safe(bo, next_bo, &node->bos, mn_list) {
-			bo->mn = NULL;
-			list_del_init(&bo->mn_list);
-		}
-		kfree(node);
-	}
-	up_write(&amn->lock);
-	mutex_unlock(&adev->mn_lock);
-
-	hmm_mirror_unregister(&amn->mirror);
-	kfree(amn);
-}
-
-/**
- * amdgpu_hmm_mirror_release - callback to notify about mm destruction
- *
- * @mirror: the HMM mirror (mm) this callback is about
- *
- * Shedule a work item to lazy destroy HMM mirror.
- */
-static void amdgpu_hmm_mirror_release(struct hmm_mirror *mirror)
-{
-	struct amdgpu_mn *amn = container_of(mirror, struct amdgpu_mn, mirror);
-
-	INIT_WORK(&amn->work, amdgpu_mn_destroy);
-	schedule_work(&amn->work);
-}
-
-/**
- * amdgpu_mn_lock - take the write side lock for this notifier
- *
- * @mn: our notifier
- */
-void amdgpu_mn_lock(struct amdgpu_mn *mn)
-{
-	if (mn)
-		down_write(&mn->lock);
-}
-
-/**
- * amdgpu_mn_unlock - drop the write side lock for this notifier
- *
- * @mn: our notifier
- */
-void amdgpu_mn_unlock(struct amdgpu_mn *mn)
-{
-	if (mn)
-		up_write(&mn->lock);
-}
-
-/**
- * amdgpu_mn_read_lock - take the read side lock for this notifier
- *
- * @amn: our notifier
- * @blockable: is the notifier blockable
- */
-static int amdgpu_mn_read_lock(struct amdgpu_mn *amn, bool blockable)
-{
-	if (blockable)
-		down_read(&amn->lock);
-	else if (!down_read_trylock(&amn->lock))
-		return -EAGAIN;
-
-	return 0;
-}
-
-/**
- * amdgpu_mn_read_unlock - drop the read side lock for this notifier
- *
- * @amn: our notifier
- */
-static void amdgpu_mn_read_unlock(struct amdgpu_mn *amn)
-{
-	up_read(&amn->lock);
-}
-
-/**
- * amdgpu_mn_invalidate_node - unmap all BOs of a node
- *
- * @node: the node with the BOs to unmap
- * @start: start of address range affected
- * @end: end of address range affected
+ * @mni: the range (mm) is about to update
+ * @range: details on the invalidation
+ * @cur_seq: Value to pass to mmu_interval_set_seq()
  *
  * Block for operations on BOs to finish and mark pages as accessed and
  * potentially dirty.
  */
-static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node,
-				      unsigned long start,
-				      unsigned long end)
+static bool amdgpu_mn_invalidate_gfx(struct mmu_interval_notifier *mni,
+				     const struct mmu_notifier_range *range,
+				     unsigned long cur_seq)
 {
-	struct amdgpu_bo *bo;
+	struct amdgpu_bo *bo = container_of(mni, struct amdgpu_bo, notifier);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	long r;
 
-	list_for_each_entry(bo, &node->bos, mn_list) {
+	if (!mmu_notifier_range_blockable(range))
+		return false;
 
-		if (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, start, end))
-			continue;
+	mutex_lock(&adev->notifier_lock);
 
-		r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv,
-			true, false, MAX_SCHEDULE_TIMEOUT);
-		if (r <= 0)
-			DRM_ERROR("(%ld) failed to wait for user bo\n", r);
-	}
+	mmu_interval_set_seq(mni, cur_seq);
+
+	r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv, true, false,
+				      MAX_SCHEDULE_TIMEOUT);
+	mutex_unlock(&adev->notifier_lock);
+	if (r <= 0)
+		DRM_ERROR("(%ld) failed to wait for user bo\n", r);
+	return true;
 }
 
-/**
- * amdgpu_mn_sync_pagetables_gfx - callback to notify about mm change
- *
- * @mirror: the hmm_mirror (mm) is about to update
- * @update: the update start, end address
- *
- * Block for operations on BOs to finish and mark pages as accessed and
- * potentially dirty.
- */
-static int
-amdgpu_mn_sync_pagetables_gfx(struct hmm_mirror *mirror,
-			      const struct mmu_notifier_range *update)
-{
-	struct amdgpu_mn *amn = container_of(mirror, struct amdgpu_mn, mirror);
-	unsigned long start = update->start;
-	unsigned long end = update->end;
-	bool blockable = mmu_notifier_range_blockable(update);
-	struct interval_tree_node *it;
-
-	/* notification is exclusive, but interval is inclusive */
-	end -= 1;
-
-	/* TODO we should be able to split locking for interval tree and
-	 * amdgpu_mn_invalidate_node
-	 */
-	if (amdgpu_mn_read_lock(amn, blockable))
-		return -EAGAIN;
-
-	it = interval_tree_iter_first(&amn->objects, start, end);
-	while (it) {
-		struct amdgpu_mn_node *node;
-
-		if (!blockable) {
-			amdgpu_mn_read_unlock(amn);
-			return -EAGAIN;
-		}
-
-		node = container_of(it, struct amdgpu_mn_node, it);
-		it = interval_tree_iter_next(it, start, end);
-
-		amdgpu_mn_invalidate_node(node, start, end);
-	}
-
-	amdgpu_mn_read_unlock(amn);
-
-	return 0;
-}
-
-/**
- * amdgpu_mn_sync_pagetables_hsa - callback to notify about mm change
- *
- * @mirror: the hmm_mirror (mm) is about to update
- * @update: the update start, end address
- *
- * We temporarily evict all BOs between start and end. This
- * necessitates evicting all user-mode queues of the process. The BOs
- * are restorted in amdgpu_mn_invalidate_range_end_hsa.
- */
-static int
-amdgpu_mn_sync_pagetables_hsa(struct hmm_mirror *mirror,
-			      const struct mmu_notifier_range *update)
-{
-	struct amdgpu_mn *amn = container_of(mirror, struct amdgpu_mn, mirror);
-	unsigned long start = update->start;
-	unsigned long end = update->end;
-	bool blockable = mmu_notifier_range_blockable(update);
-	struct interval_tree_node *it;
-
-	/* notification is exclusive, but interval is inclusive */
-	end -= 1;
-
-	if (amdgpu_mn_read_lock(amn, blockable))
-		return -EAGAIN;
-
-	it = interval_tree_iter_first(&amn->objects, start, end);
-	while (it) {
-		struct amdgpu_mn_node *node;
-		struct amdgpu_bo *bo;
-
-		if (!blockable) {
-			amdgpu_mn_read_unlock(amn);
-			return -EAGAIN;
-		}
-
-		node = container_of(it, struct amdgpu_mn_node, it);
-		it = interval_tree_iter_next(it, start, end);
-
-		list_for_each_entry(bo, &node->bos, mn_list) {
-			struct kgd_mem *mem = bo->kfd_bo;
-
-			if (amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm,
-							 start, end))
-				amdgpu_amdkfd_evict_userptr(mem, amn->mm);
-		}
-	}
-
-	amdgpu_mn_read_unlock(amn);
-
-	return 0;
-}
-
-/* Low bits of any reasonable mm pointer will be unused due to struct
- * alignment. Use these bits to make a unique key from the mm pointer
- * and notifier type.
- */
-#define AMDGPU_MN_KEY(mm, type) ((unsigned long)(mm) + (type))
-
-static struct hmm_mirror_ops amdgpu_hmm_mirror_ops[] = {
-	[AMDGPU_MN_TYPE_GFX] = {
-		.sync_cpu_device_pagetables = amdgpu_mn_sync_pagetables_gfx,
-		.release = amdgpu_hmm_mirror_release
-	},
-	[AMDGPU_MN_TYPE_HSA] = {
-		.sync_cpu_device_pagetables = amdgpu_mn_sync_pagetables_hsa,
-		.release = amdgpu_hmm_mirror_release
-	},
+static const struct mmu_interval_notifier_ops amdgpu_mn_gfx_ops = {
+	.invalidate = amdgpu_mn_invalidate_gfx,
 };
 
 /**
- * amdgpu_mn_get - create HMM mirror context
+ * amdgpu_mn_invalidate_hsa - callback to notify about mm change
  *
- * @adev: amdgpu device pointer
- * @type: type of MMU notifier context
+ * @mni: the range (mm) is about to update
+ * @range: details on the invalidation
+ * @cur_seq: Value to pass to mmu_interval_set_seq()
  *
- * Creates a HMM mirror context for current->mm.
+ * We temporarily evict the BO attached to this range. This necessitates
+ * evicting all user-mode queues of the process.
  */
-struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev,
-				enum amdgpu_mn_type type)
+static bool amdgpu_mn_invalidate_hsa(struct mmu_interval_notifier *mni,
+				     const struct mmu_notifier_range *range,
+				     unsigned long cur_seq)
 {
-	struct mm_struct *mm = current->mm;
-	struct amdgpu_mn *amn;
-	unsigned long key = AMDGPU_MN_KEY(mm, type);
-	int r;
+	struct amdgpu_bo *bo = container_of(mni, struct amdgpu_bo, notifier);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 
-	mutex_lock(&adev->mn_lock);
-	if (down_write_killable(&mm->mmap_sem)) {
-		mutex_unlock(&adev->mn_lock);
-		return ERR_PTR(-EINTR);
-	}
+	if (!mmu_notifier_range_blockable(range))
+		return false;
 
-	hash_for_each_possible(adev->mn_hash, amn, node, key)
-		if (AMDGPU_MN_KEY(amn->mm, amn->type) == key)
-			goto release_locks;
+	mutex_lock(&adev->notifier_lock);
 
-	amn = kzalloc(sizeof(*amn), GFP_KERNEL);
-	if (!amn) {
-		amn = ERR_PTR(-ENOMEM);
-		goto release_locks;
-	}
+	mmu_interval_set_seq(mni, cur_seq);
 
-	amn->adev = adev;
-	amn->mm = mm;
-	init_rwsem(&amn->lock);
-	amn->type = type;
-	amn->objects = RB_ROOT_CACHED;
+	amdgpu_amdkfd_evict_userptr(bo->kfd_bo, bo->notifier.mm);
+	mutex_unlock(&adev->notifier_lock);
 
-	amn->mirror.ops = &amdgpu_hmm_mirror_ops[type];
-	r = hmm_mirror_register(&amn->mirror, mm);
-	if (r)
-		goto free_amn;
-
-	hash_add(adev->mn_hash, &amn->node, AMDGPU_MN_KEY(mm, type));
-
-release_locks:
-	up_write(&mm->mmap_sem);
-	mutex_unlock(&adev->mn_lock);
-
-	return amn;
-
-free_amn:
-	up_write(&mm->mmap_sem);
-	mutex_unlock(&adev->mn_lock);
-	kfree(amn);
-
-	return ERR_PTR(r);
+	return true;
 }
+
+static const struct mmu_interval_notifier_ops amdgpu_mn_hsa_ops = {
+	.invalidate = amdgpu_mn_invalidate_hsa,
+};
 
 /**
  * amdgpu_mn_register - register a BO for notifier updates
···
  * @bo: amdgpu buffer object
  * @addr: userptr addr we should monitor
  *
- * Registers an HMM mirror for the given BO at the specified address.
+ * Registers a mmu_notifier for the given BO at the specified address.
  * Returns 0 on success, -ERRNO if anything goes wrong.
  */
 int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
 {
-	unsigned long end = addr + amdgpu_bo_size(bo) - 1;
-	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	enum amdgpu_mn_type type =
-		bo->kfd_bo ? AMDGPU_MN_TYPE_HSA : AMDGPU_MN_TYPE_GFX;
-	struct amdgpu_mn *amn;
-	struct amdgpu_mn_node *node = NULL, *new_node;
-	struct list_head bos;
-	struct interval_tree_node *it;
-
-	amn = amdgpu_mn_get(adev, type);
-	if (IS_ERR(amn))
-		return PTR_ERR(amn);
-
-	new_node = kmalloc(sizeof(*new_node), GFP_KERNEL);
-	if (!new_node)
-		return -ENOMEM;
-
-	INIT_LIST_HEAD(&bos);
-
-	down_write(&amn->lock);
-
-	while ((it = interval_tree_iter_first(&amn->objects, addr, end))) {
-		kfree(node);
-		node = container_of(it, struct amdgpu_mn_node, it);
-		interval_tree_remove(&node->it, &amn->objects);
-		addr = min(it->start, addr);
-		end = max(it->last, end);
-		list_splice(&node->bos, &bos);
-	}
-
-	if (!node)
-		node = new_node;
-	else
-		kfree(new_node);
-
-	bo->mn = amn;
-
-	node->it.start = addr;
-	node->it.last = end;
-	INIT_LIST_HEAD(&node->bos);
-	list_splice(&bos, &node->bos);
-	list_add(&bo->mn_list, &node->bos);
-
-	interval_tree_insert(&node->it, &amn->objects);
-
-	up_write(&amn->lock);
-
-	return 0;
+	if (bo->kfd_bo)
+		return mmu_interval_notifier_insert(&bo->notifier, current->mm,
+						    addr, amdgpu_bo_size(bo),
+						    &amdgpu_mn_hsa_ops);
+	return mmu_interval_notifier_insert(&bo->notifier, current->mm, addr,
+					    amdgpu_bo_size(bo),
+					    &amdgpu_mn_gfx_ops);
 }
 
 /**
- * amdgpu_mn_unregister - unregister a BO for HMM mirror updates
+ * amdgpu_mn_unregister - unregister a BO for notifier updates
  *
  * @bo: amdgpu buffer object
  *
- * Remove any registration of HMM mirror updates from the buffer object.
+ * Remove any registration of mmu notifier updates from the buffer object.
  */
 void amdgpu_mn_unregister(struct amdgpu_bo *bo)
 {
-	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	struct amdgpu_mn *amn;
-	struct list_head *head;
-
-	mutex_lock(&adev->mn_lock);
-
-	amn = bo->mn;
-	if (amn == NULL) {
-		mutex_unlock(&adev->mn_lock);
+	if (!bo->notifier.mm)
 		return;
-	}
-
-	down_write(&amn->lock);
-
-	/* save the next list entry for later */
-	head = bo->mn_list.next;
-
-	bo->mn = NULL;
-	list_del_init(&bo->mn_list);
-
-	if (list_empty(head)) {
-		struct amdgpu_mn_node *node;
-
-		node = container_of(head, struct amdgpu_mn_node, bos);
-		interval_tree_remove(&node->it, &amn->objects);
-		kfree(node);
-	}
-
-	up_write(&amn->lock);
-	mutex_unlock(&adev->mn_lock);
-}
-
-/* flags used by HMM internal, not related to CPU/GPU PTE flags */
-static const uint64_t hmm_range_flags[HMM_PFN_FLAG_MAX] = {
-		(1 << 0), /* HMM_PFN_VALID */
-		(1 << 1), /* HMM_PFN_WRITE */
-		0 /* HMM_PFN_DEVICE_PRIVATE */
-};
-
-static const uint64_t hmm_range_values[HMM_PFN_VALUE_MAX] = {
-		0xfffffffffffffffeUL, /* HMM_PFN_ERROR */
-		0, /* HMM_PFN_NONE */
-		0xfffffffffffffffcUL /* HMM_PFN_SPECIAL */
-};
-
-void amdgpu_hmm_init_range(struct hmm_range *range)
-{
-	if (range) {
-		range->flags = hmm_range_flags;
-		range->values = hmm_range_values;
-		range->pfn_shift = PAGE_SHIFT;
-	}
+	mmu_interval_notifier_remove(&bo->notifier);
+	bo->notifier.mm = NULL;
 }

drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h

···
 #include <linux/workqueue.h>
 #include <linux/interval_tree.h>
 
-enum amdgpu_mn_type {
-	AMDGPU_MN_TYPE_GFX,
-	AMDGPU_MN_TYPE_HSA,
-};
-
-/**
- * struct amdgpu_mn
- *
- * @adev: amdgpu device pointer
- * @mm: process address space
- * @type: type of MMU notifier
- * @work: destruction work item
- * @node: hash table node to find structure by adev and mn
- * @lock: rw semaphore protecting the notifier nodes
- * @objects: interval tree containing amdgpu_mn_nodes
- * @mirror: HMM mirror function support
- *
- * Data for each amdgpu device and process address space.
- */
-struct amdgpu_mn {
-	/* constant after initialisation */
-	struct amdgpu_device	*adev;
-	struct mm_struct	*mm;
-	enum amdgpu_mn_type	type;
-
-	/* only used on destruction */
-	struct work_struct	work;
-
-	/* protected by adev->mn_lock */
-	struct hlist_node	node;
-
-	/* objects protected by lock */
-	struct rw_semaphore	lock;
-	struct rb_root_cached	objects;
-
-#ifdef CONFIG_HMM_MIRROR
-	/* HMM mirror */
-	struct hmm_mirror	mirror;
-#endif
-};
-
 #if defined(CONFIG_HMM_MIRROR)
-void amdgpu_mn_lock(struct amdgpu_mn *mn);
-void amdgpu_mn_unlock(struct amdgpu_mn *mn);
-struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev,
-				enum amdgpu_mn_type type);
 int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr);
 void amdgpu_mn_unregister(struct amdgpu_bo *bo);
-void amdgpu_hmm_init_range(struct hmm_range *range);
 #else
-static inline void amdgpu_mn_lock(struct amdgpu_mn *mn) {}
-static inline void amdgpu_mn_unlock(struct amdgpu_mn *mn) {}
-static inline struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev,
-					      enum amdgpu_mn_type type)
-{
-	return NULL;
-}
 static inline int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
 {
 	DRM_WARN_ONCE("HMM_MIRROR kernel config option is not enabled, "

drivers/gpu/drm/amd/amdgpu/amdgpu_object.h

···
 
 #include <drm/amdgpu_drm.h>
 #include "amdgpu.h"
+#ifdef CONFIG_MMU_NOTIFIER
+#include <linux/mmu_notifier.h>
+#endif
 
 #define AMDGPU_BO_INVALID_OFFSET	LONG_MAX
 #define AMDGPU_BO_MAX_PLACEMENTS	3
···
 	struct ttm_bo_kmap_obj		dma_buf_vmap;
 	struct amdgpu_mn		*mn;
 
-	union {
-		struct list_head	mn_list;
-		struct list_head	shadow_list;
-	};
+
+#ifdef CONFIG_MMU_NOTIFIER
+	struct mmu_interval_notifier	notifier;
+#endif
+
+	struct list_head		shadow_list;
 
 	struct kgd_mem                  *kfd_bo;
 };

drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c

···
 #include <linux/hmm.h>
 #include <linux/pagemap.h>
 #include <linux/sched/task.h>
+#include <linux/sched/mm.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
···
 #endif
 };
 
+#ifdef CONFIG_DRM_AMDGPU_USERPTR
+/* flags used by HMM internal, not related to CPU/GPU PTE flags */
+static const uint64_t hmm_range_flags[HMM_PFN_FLAG_MAX] = {
+	(1 << 0), /* HMM_PFN_VALID */
+	(1 << 1), /* HMM_PFN_WRITE */
+	0 /* HMM_PFN_DEVICE_PRIVATE */
+};
+
+static const uint64_t hmm_range_values[HMM_PFN_VALUE_MAX] = {
+	0xfffffffffffffffeUL, /* HMM_PFN_ERROR */
+	0, /* HMM_PFN_NONE */
+	0xfffffffffffffffcUL /* HMM_PFN_SPECIAL */
+};
+
 /**
  * amdgpu_ttm_tt_get_user_pages - get device accessible pages that back user
  * memory and start HMM tracking CPU page table update
···
  * Calling function must call amdgpu_ttm_tt_userptr_range_done() once and only
  * once afterwards to stop HMM tracking
  */
-#if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR)
-
-#define MAX_RETRY_HMM_RANGE_FAULT	16
-
 int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 {
-	struct hmm_mirror *mirror = bo->mn ? &bo->mn->mirror : NULL;
 	struct ttm_tt *ttm = bo->tbo.ttm;
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
-	struct mm_struct *mm = gtt->usertask->mm;
 	unsigned long start = gtt->userptr;
 	struct vm_area_struct *vma;
 	struct hmm_range *range;
+	unsigned long timeout;
+	struct mm_struct *mm;
 	unsigned long i;
-	uint64_t *pfns;
 	int r = 0;
 
-	if (!mm) /* Happens during process shutdown */
+	mm = bo->notifier.mm;
+	if (unlikely(!mm)) {
+		DRM_DEBUG_DRIVER("BO is not registered?\n");
+		return -EFAULT;
+	}
+
+	/* Another get_user_pages is running at the same time?? */
+	if (WARN_ON(gtt->range))
+		return -EFAULT;
+
+	if (!mmget_not_zero(mm)) /* Happens during process shutdown */
 		return -ESRCH;
-
-	if (unlikely(!mirror)) {
-		DRM_DEBUG_DRIVER("Failed to get hmm_mirror\n");
-		r = -EFAULT;
-		goto out;
-	}
-
-	vma = find_vma(mm, start);
-	if (unlikely(!vma || start < vma->vm_start)) {
-		r = -EFAULT;
-		goto out;
-	}
-	if (unlikely((gtt->userflags & AMDGPU_GEM_USERPTR_ANONONLY) &&
-		vma->vm_file)) {
-		r = -EPERM;
-		goto out;
-	}
 
 	range = kzalloc(sizeof(*range), GFP_KERNEL);
 	if (unlikely(!range)) {
 		r = -ENOMEM;
 		goto out;
 	}
+	range->notifier = &bo->notifier;
+	range->flags = hmm_range_flags;
+	range->values = hmm_range_values;
+	range->pfn_shift = PAGE_SHIFT;
+	range->start = bo->notifier.interval_tree.start;
+	range->end = bo->notifier.interval_tree.last + 1;
+	range->default_flags = hmm_range_flags[HMM_PFN_VALID];
+	if (!amdgpu_ttm_tt_is_readonly(ttm))
+		range->default_flags |= range->flags[HMM_PFN_WRITE];
 
-	pfns = kvmalloc_array(ttm->num_pages, sizeof(*pfns), GFP_KERNEL);
-	if (unlikely(!pfns)) {
+	range->pfns = kvmalloc_array(ttm->num_pages, sizeof(*range->pfns),
+				     GFP_KERNEL);
+	if (unlikely(!range->pfns)) {
 		r = -ENOMEM;
 		goto out_free_ranges;
 	}
 
-	amdgpu_hmm_init_range(range);
-	range->default_flags = range->flags[HMM_PFN_VALID];
-	range->default_flags |= amdgpu_ttm_tt_is_readonly(ttm) ?
-				0 : range->flags[HMM_PFN_WRITE];
-	range->pfn_flags_mask = 0;
-	range->pfns = pfns;
-	range->start = start;
-	range->end = start + ttm->num_pages * PAGE_SIZE;
+	down_read(&mm->mmap_sem);
+	vma = find_vma(mm, start);
+	if (unlikely(!vma || start < vma->vm_start)) {
+		r = -EFAULT;
+		goto out_unlock;
+	}
+	if (unlikely((gtt->userflags & AMDGPU_GEM_USERPTR_ANONONLY) &&
+		vma->vm_file)) {
+		r = -EPERM;
+		goto out_unlock;
+	}
+	up_read(&mm->mmap_sem);
+	timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
 
-	hmm_range_register(range, mirror);
-
-	/*
-	 * Just wait for range to be valid, safe to ignore return value as we
-	 * will use the return value of hmm_range_fault() below under the
-	 * mmap_sem to ascertain the validity of the range.
-	 */
-	hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT);
+retry:
+	range->notifier_seq = mmu_interval_read_begin(&bo->notifier);
 
 	down_read(&mm->mmap_sem);
 	r = hmm_range_fault(range, 0);
 	up_read(&mm->mmap_sem);
-
-	if (unlikely(r < 0))
+	if (unlikely(r <= 0)) {
+		/*
+		 * FIXME: This timeout should encompass the retry from
+		 * mmu_interval_read_retry() as well.
+		 */
+		if ((r == 0 || r == -EBUSY) && !time_after(jiffies, timeout))
+			goto retry;
 		goto out_free_pfns;
+	}
 
 	for (i = 0; i < ttm->num_pages; i++) {
-		pages[i] = hmm_device_entry_to_page(range, pfns[i]);
+		/* FIXME: The pages cannot be touched outside the notifier_lock */
+		pages[i] = hmm_device_entry_to_page(range, range->pfns[i]);
 		if (unlikely(!pages[i])) {
 			pr_err("Page fault failed for pfn[%lu] = 0x%llx\n",
-			       i, pfns[i]);
+			       i, range->pfns[i]);
 			r = -ENOMEM;
 
 			goto out_free_pfns;
···
 	}
 
 	gtt->range = range;
+	mmput(mm);
 
 	return 0;
 
+out_unlock:
+	up_read(&mm->mmap_sem);
 out_free_pfns:
-	hmm_range_unregister(range);
-	kvfree(pfns);
+	kvfree(range->pfns);
 out_free_ranges:
 	kfree(range);
 out:
+	mmput(mm);
 	return r;
 }
 
···
 		"No user pages to check\n");
 
 	if (gtt->range) {
-		r = hmm_range_valid(gtt->range);
-		hmm_range_unregister(gtt->range);
-
+		/*
+		 * FIXME: Must always hold notifier_lock for this, and must
+		 * not ignore the return code.
+		 */
+		r = mmu_interval_read_retry(gtt->range->notifier,
+					 gtt->range->notifier_seq);
 		kvfree(gtt->range->pfns);
 		kfree(gtt->range);
 		gtt->range = NULL;
 	}
 
-	return r;
+	return !r;
 }
 #endif
 
···
 	sg_free_table(ttm->sg);
 
 #if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR)
-	if (gtt->range &&
-	    ttm->pages[0] == hmm_device_entry_to_page(gtt->range,
-						      gtt->range->pfns[0]))
-		WARN_ONCE(1, "Missing get_user_page_done\n");
+	if (gtt->range) {
+		unsigned long i;
+
+		for (i = 0; i < ttm->num_pages; i++) {
+			if (ttm->pages[i] !=
+				hmm_device_entry_to_page(gtt->range,
+					      gtt->range->pfns[i]))
+				break;
+		}
+
+		WARN((i == ttm->num_pages), "Missing get_user_page_done\n");
+	}
 #endif
 }
 

drivers/gpu/drm/nouveau/nouveau_svm.c

···
 }
 
 struct nouveau_svmm {
+	struct mmu_notifier notifier;
 	struct nouveau_vmm *vmm;
 	struct {
 		unsigned long start;
···
 	} unmanaged;
 
 	struct mutex mutex;
-
-	struct mm_struct *mm;
-	struct hmm_mirror mirror;
 };
 
 #define SVMM_DBG(s,f,a...)                                                     \
···
 }
 
 static int
-nouveau_svmm_sync_cpu_device_pagetables(struct hmm_mirror *mirror,
-					const struct mmu_notifier_range *update)
+nouveau_svmm_invalidate_range_start(struct mmu_notifier *mn,
+				    const struct mmu_notifier_range *update)
 {
-	struct nouveau_svmm *svmm = container_of(mirror, typeof(*svmm), mirror);
+	struct nouveau_svmm *svmm =
+		container_of(mn, struct nouveau_svmm, notifier);
 	unsigned long start = update->start;
 	unsigned long limit = update->end;
 
···
 	SVMM_DBG(svmm, "invalidate %016lx-%016lx", start, limit);
 
 	mutex_lock(&svmm->mutex);
+	if (unlikely(!svmm->vmm))
+		goto out;
+
 	if (limit > svmm->unmanaged.start && start < svmm->unmanaged.limit) {
 		if (start < svmm->unmanaged.start) {
 			nouveau_svmm_invalidate(svmm, start,
···
 	}
 
 	nouveau_svmm_invalidate(svmm, start, limit);
+
+out:
 	mutex_unlock(&svmm->mutex);
 	return 0;
 }
 
-static void
-nouveau_svmm_release(struct hmm_mirror *mirror)
+static void nouveau_svmm_free_notifier(struct mmu_notifier *mn)
 {
+	kfree(container_of(mn, struct nouveau_svmm, notifier));
 }
 
-static const struct hmm_mirror_ops
-nouveau_svmm = {
-	.sync_cpu_device_pagetables = nouveau_svmm_sync_cpu_device_pagetables,
-	.release = nouveau_svmm_release,
+static const struct mmu_notifier_ops nouveau_mn_ops = {
+	.invalidate_range_start = nouveau_svmm_invalidate_range_start,
+	.free_notifier = nouveau_svmm_free_notifier,
 };
 
 void
···
 {
 	struct nouveau_svmm *svmm = *psvmm;
 	if (svmm) {
-		hmm_mirror_unregister(&svmm->mirror);
-		kfree(*psvmm);
+		mutex_lock(&svmm->mutex);
+		svmm->vmm = NULL;
+		mutex_unlock(&svmm->mutex);
+		mmu_notifier_put(&svmm->notifier);
 		*psvmm = NULL;
 	}
 }
···
 	mutex_lock(&cli->mutex);
 	if (cli->svm.cli) {
 		ret = -EBUSY;
-		goto done;
+		goto out_free;
 	}
 
 	/* Allocate a new GPU VMM that can support SVM (managed by the
···
 				.fault_replay = true,
 			    }, sizeof(struct gp100_vmm_v0), &cli->svm.vmm);
 	if (ret)
-		goto done;
+		goto out_free;
 
-	/* Enable HMM mirroring of CPU address-space to VMM. */
-	svmm->mm = get_task_mm(current);
-	down_write(&svmm->mm->mmap_sem);
-	svmm->mirror.ops = &nouveau_svmm;
-	ret = hmm_mirror_register(&svmm->mirror, svmm->mm);
-	if (ret == 0) {
-		cli->svm.svmm = svmm;
-		cli->svm.cli = cli;
-	}
-	up_write(&svmm->mm->mmap_sem);
-	mmput(svmm->mm);
-
-done:
+	down_write(&current->mm->mmap_sem);
+	svmm->notifier.ops = &nouveau_mn_ops;
+	ret = __mmu_notifier_register(&svmm->notifier, current->mm);
 	if (ret)
-		nouveau_svmm_fini(&svmm);
+		goto out_mm_unlock;
+	/* Note, ownership of svmm transfers to mmu_notifier */
+
+	cli->svm.svmm = svmm;
+	cli->svm.cli = cli;
+	up_write(&current->mm->mmap_sem);
 	mutex_unlock(&cli->mutex);
+	return 0;
+
+out_mm_unlock:
+	up_write(&current->mm->mmap_sem);
+out_free:
+	mutex_unlock(&cli->mutex);
+	kfree(svmm);
 	return ret;
 }
 
···
 		fault->inst, fault->addr, fault->access);
 }
 
-static inline bool
-nouveau_range_done(struct hmm_range *range)
-{
-	bool ret = hmm_range_valid(range);
+struct svm_notifier {
+	struct mmu_interval_notifier notifier;
+	struct nouveau_svmm *svmm;
+};
 
-	hmm_range_unregister(range);
-	return ret;
+static bool nouveau_svm_range_invalidate(struct mmu_interval_notifier *mni,
+					 const struct mmu_notifier_range *range,
+					 unsigned long cur_seq)
+{
+	struct svm_notifier *sn =
+		container_of(mni, struct svm_notifier, notifier);
+
+	/*
+	 * serializes the update to mni->invalidate_seq done by caller and
+	 * prevents invalidation of the PTE from progressing while HW is being
+	 * programmed. This is very hacky and only works because the normal
+	 * notifier that does invalidation is always called after the range
+	 * notifier.
+	 */
+	if (mmu_notifier_range_blockable(range))
+		mutex_lock(&sn->svmm->mutex);
+	else if (!mutex_trylock(&sn->svmm->mutex))
+		return false;
+	mmu_interval_set_seq(mni, cur_seq);
+	mutex_unlock(&sn->svmm->mutex);
+	return true;
 }
 
-static int
-nouveau_range_fault(struct nouveau_svmm *svmm, struct hmm_range *range)
+static const struct mmu_interval_notifier_ops nouveau_svm_mni_ops = {
+	.invalidate = nouveau_svm_range_invalidate,
+};
+
+static int nouveau_range_fault(struct nouveau_svmm *svmm,
+			       struct nouveau_drm *drm, void *data, u32 size,
+			       u64 *pfns, struct svm_notifier *notifier)
 {
+	unsigned long timeout =
+		jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
+	/* Have HMM fault pages within the fault window to the GPU. */
+	struct hmm_range range = {
+		.notifier = &notifier->notifier,
+		.start = notifier->notifier.interval_tree.start,
+		.end = notifier->notifier.interval_tree.last + 1,
+		.pfns = pfns,
+		.flags = nouveau_svm_pfn_flags,
+		.values = nouveau_svm_pfn_values,
+		.pfn_shift = NVIF_VMM_PFNMAP_V0_ADDR_SHIFT,
+	};
+	struct mm_struct *mm = notifier->notifier.mm;
 	long ret;
 
-	range->default_flags = 0;
-	range->pfn_flags_mask = -1UL;
+	while (true) {
+		if (time_after(jiffies, timeout))
+			return -EBUSY;
 
-	ret = hmm_range_register(range, &svmm->mirror);
-	if (ret) {
-		up_read(&svmm->mm->mmap_sem);
-		return (int)ret;
+		range.notifier_seq = mmu_interval_read_begin(range.notifier);
+		range.default_flags = 0;
+		range.pfn_flags_mask = -1UL;
+		down_read(&mm->mmap_sem);
+		ret = hmm_range_fault(&range, 0);
+		up_read(&mm->mmap_sem);
+		if (ret <= 0) {
+			if (ret == 0 || ret == -EBUSY)
+				continue;
+			return ret;
+		}
+
+		mutex_lock(&svmm->mutex);
+		if (mmu_interval_read_retry(range.notifier,
+					    range.notifier_seq)) {
+			mutex_unlock(&svmm->mutex);
+			continue;
+		}
+		break;
 	}
 
-	if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) {
-		up_read(&svmm->mm->mmap_sem);
-		return -EBUSY;
-	}
+	nouveau_dmem_convert_pfn(drm, &range);
 
-	ret = hmm_range_fault(range, 0);
-	if (ret <= 0) {
-		if (ret == 0)
-			ret = -EBUSY;
-		up_read(&svmm->mm->mmap_sem);
-		hmm_range_unregister(range);
-		return ret;
-	}
-	return 0;
+	svmm->vmm->vmm.object.client->super = true;
+	ret = nvif_object_ioctl(&svmm->vmm->vmm.object, data, size, NULL);
+	svmm->vmm->vmm.object.client->super = false;
+	mutex_unlock(&svmm->mutex);
+
+	return ret;
 }
 
 static int
···
 		} i;
 		u64 phys[16];
 	} args;
-	struct hmm_range range;
 	struct vm_area_struct *vma;
 	u64 inst, start, limit;
 	int fi, fn, pi, fill;
···
 	args.i.p.version = 0;
 
 	for (fi = 0; fn = fi + 1, fi < buffer->fault_nr; fi = fn) {
+		struct svm_notifier notifier;
+		struct mm_struct *mm;
+
 		/* Cancel any faults from non-SVM channels. */
 		if (!(svmm = buffer->fault[fi]->svmm)) {
 			nouveau_svm_fault_cancel_fault(svm, buffer->fault[fi]);
···
 			start = max_t(u64, start, svmm->unmanaged.limit);
 		SVMM_DBG(svmm, "wndw %016llx-%016llx", start, limit);
 
+		mm = svmm->notifier.mm;
+		if (!mmget_not_zero(mm)) {
+			nouveau_svm_fault_cancel_fault(svm, buffer->fault[fi]);
+			continue;
+		}
+
 		/* Intersect fault window with the CPU VMA, cancelling
 		 * the fault if the address is invalid.
 		 */
-		down_read(&svmm->mm->mmap_sem);
-		vma = find_vma_intersection(svmm->mm, start, limit);
+		down_read(&mm->mmap_sem);
+		vma = find_vma_intersection(mm, start, limit);
 		if (!vma) {
 			SVMM_ERR(svmm, "wndw %016llx-%016llx", start, limit);
-			up_read(&svmm->mm->mmap_sem);
+			up_read(&mm->mmap_sem);
+			mmput(mm);
 			nouveau_svm_fault_cancel_fault(svm, buffer->fault[fi]);
 			continue;
 		}
 		start = max_t(u64, start, vma->vm_start);
 		limit = min_t(u64, limit, vma->vm_end);
+		up_read(&mm->mmap_sem);
 		SVMM_DBG(svmm, "wndw %016llx-%016llx", start, limit);
 
 		if (buffer->fault[fi]->addr != start) {
 			SVMM_ERR(svmm, "addr %016llx", buffer->fault[fi]->addr);
-			up_read(&svmm->mm->mmap_sem);
+			mmput(mm);
 			nouveau_svm_fault_cancel_fault(svm, buffer->fault[fi]);
 			continue;
 		}
···
 			 args.i.p.addr,
 			 args.i.p.addr + args.i.p.size, fn - fi);
 
-		/* Have HMM fault pages within the fault window to the GPU. */
-		range.start = args.i.p.addr;
-		range.end = args.i.p.addr + args.i.p.size;
-		range.pfns = args.phys;
-		range.flags = nouveau_svm_pfn_flags;
-		range.values = nouveau_svm_pfn_values;
-		range.pfn_shift = NVIF_VMM_PFNMAP_V0_ADDR_SHIFT;
-again:
-		ret = nouveau_range_fault(svmm, &range);
-		if (ret == 0) {
-			mutex_lock(&svmm->mutex);
-			if (!nouveau_range_done(&range)) {
-				mutex_unlock(&svmm->mutex);
-				goto again;
-			}
-
-			nouveau_dmem_convert_pfn(svm->drm, &range);
-
-			svmm->vmm->vmm.object.client->super = true;
-			ret = nvif_object_ioctl(&svmm->vmm->vmm.object,
-						&args, sizeof(args.i) +
-						pi * sizeof(args.phys[0]),
-						NULL);
-			svmm->vmm->vmm.object.client->super = false;
-			mutex_unlock(&svmm->mutex);
-			up_read(&svmm->mm->mmap_sem);
+		notifier.svmm = svmm;
+		ret = mmu_interval_notifier_insert(&notifier.notifier,
+						   svmm->notifier.mm,
+						   args.i.p.addr, args.i.p.size,
+						   &nouveau_svm_mni_ops);
+		if (!ret) {
+			ret = nouveau_range_fault(
+				svmm, svm->drm, &args,
+				sizeof(args.i) + pi * sizeof(args.phys[0]),
+				args.phys, &notifier);
+			mmu_interval_notifier_remove(&notifier.notifier);
 		}
+		mmput(mm);
 
 		/* Cancel any faults in the window whose pages didn't manage
 		 * to keep their valid bit, or stay writeable when required.
···
 		 */
 		while (fi < fn) {
 			struct nouveau_svm_fault *fault = buffer->fault[fi++];
-			pi = (fault->addr - range.start) >> PAGE_SHIFT;
+			pi = (fault->addr - args.i.p.addr) >> PAGE_SHIFT;
 			if (ret ||
-			     !(range.pfns[pi] & NVIF_VMM_PFNMAP_V0_V) ||
-			    (!(range.pfns[pi] & NVIF_VMM_PFNMAP_V0_W) &&
+			     !(args.phys[pi] & NVIF_VMM_PFNMAP_V0_V) ||
+			    (!(args.phys[pi] & NVIF_VMM_PFNMAP_V0_W) &&
 			     fault->access != 0 && fault->access != 3)) {
 				nouveau_svm_fault_cancel_fault(svm, fault);
 				continue;

drivers/gpu/drm/radeon/radeon.h

···
 #include <linux/hashtable.h>
 #include <linux/dma-fence.h>
 
+#ifdef CONFIG_MMU_NOTIFIER
+#include <linux/mmu_notifier.h>
+#endif
+
 #include <drm/ttm/ttm_bo_api.h>
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_placement.h>
···
 	struct ttm_bo_kmap_obj		dma_buf_vmap;
 	pid_t				pid;
 
-	struct radeon_mn		*mn;
-	struct list_head		mn_list;
+#ifdef CONFIG_MMU_NOTIFIER
+	struct mmu_interval_notifier	notifier;
+#endif
 };
 #define gem_to_radeon_bo(gobj) container_of((gobj), struct radeon_bo, tbo.base)
 

drivers/gpu/drm/radeon/radeon_mn.c

···
 
 #include "radeon.h"
 
-struct radeon_mn {
-	struct mmu_notifier	mn;
-
-	/* objects protected by lock */
-	struct mutex		lock;
-	struct rb_root_cached	objects;
-};
-
-struct radeon_mn_node {
-	struct interval_tree_node	it;
-	struct list_head		bos;
-};
-
 /**
- * radeon_mn_invalidate_range_start - callback to notify about mm change
+ * radeon_mn_invalidate - callback to notify about mm change
  *
  * @mn: our notifier
- * @mn: the mm this callback is about
- * @start: start of updated range
- * @end: end of updated range
+ * @range: the VMA under invalidation
  *
  * We block for all BOs between start and end to be idle and
  * unmap them by move them into system domain again.
  */
-static int radeon_mn_invalidate_range_start(struct mmu_notifier *mn,
-				const struct mmu_notifier_range *range)
+static bool radeon_mn_invalidate(struct mmu_interval_notifier *mn,
+				 const struct mmu_notifier_range *range,
+				 unsigned long cur_seq)
 {
-	struct radeon_mn *rmn = container_of(mn, struct radeon_mn, mn);
+	struct radeon_bo *bo = container_of(mn, struct radeon_bo, notifier);
 	struct ttm_operation_ctx ctx = { false, false };
-	struct interval_tree_node *it;
-	unsigned long end;
-	int ret = 0;
+	long r;
 
-	/* notification is exclusive, but interval is inclusive */
-	end = range->end - 1;
+	if (!bo->tbo.ttm || bo->tbo.ttm->state != tt_bound)
+		return true;
 
-	/* TODO we should be able to split locking for interval tree and
-	 * the tear down.
-	 */
-	if (mmu_notifier_range_blockable(range))
-		mutex_lock(&rmn->lock);
-	else if (!mutex_trylock(&rmn->lock))
-		return -EAGAIN;
+	if (!mmu_notifier_range_blockable(range))
+		return false;
 
-	it = interval_tree_iter_first(&rmn->objects, range->start, end);
-	while (it) {
-		struct radeon_mn_node *node;
-		struct radeon_bo *bo;
-		long r;
-
-		if (!mmu_notifier_range_blockable(range)) {
-			ret = -EAGAIN;
-			goto out_unlock;
-		}
-
-		node = container_of(it, struct radeon_mn_node, it);
-		it = interval_tree_iter_next(it, range->start, end);
-
-		list_for_each_entry(bo, &node->bos, mn_list) {
-
-			if (!bo->tbo.ttm || bo->tbo.ttm->state != tt_bound)
-				continue;
-
-			r = radeon_bo_reserve(bo, true);
-			if (r) {
-				DRM_ERROR("(%ld) failed to reserve user bo\n", r);
-				continue;
-			}
-
-			r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv,
-				true, false, MAX_SCHEDULE_TIMEOUT);
-			if (r <= 0)
-				DRM_ERROR("(%ld) failed to wait for user bo\n", r);
-
-			radeon_ttm_placement_from_domain(bo, RADEON_GEM_DOMAIN_CPU);
-			r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
-			if (r)
-				DRM_ERROR("(%ld) failed to validate user bo\n", r);
-
-			radeon_bo_unreserve(bo);
-		}
+	r = radeon_bo_reserve(bo, true);
+	if (r) {
+		DRM_ERROR("(%ld) failed to reserve user bo\n", r);
+		return true;
 	}
-	
-out_unlock:
-	mutex_unlock(&rmn->lock);
 
-	return ret;
+	r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv, true, false,
+				      MAX_SCHEDULE_TIMEOUT);
+	if (r <= 0)
+		DRM_ERROR("(%ld) failed to wait for user bo\n", r);
+
+	radeon_ttm_placement_from_domain(bo, RADEON_GEM_DOMAIN_CPU);
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+	if (r)
+		DRM_ERROR("(%ld) failed to validate user bo\n", r);
+
+	radeon_bo_unreserve(bo);
+	return true;
 }
 
-static void radeon_mn_release(struct mmu_notifier *mn, struct mm_struct *mm)
-{
-	struct mmu_notifier_range range = {
-		.mm = mm,
-		.start = 0,
-		.end = ULONG_MAX,
-		.flags = 0,
-		.event = MMU_NOTIFY_UNMAP,
-	};
-
-	radeon_mn_invalidate_range_start(mn, &range);
-}
-
-static struct mmu_notifier *radeon_mn_alloc_notifier(struct mm_struct *mm)
-{
-	struct radeon_mn *rmn;
-
-	rmn = kzalloc(sizeof(*rmn), GFP_KERNEL);
-	if (!rmn)
-		return ERR_PTR(-ENOMEM);
-
-	mutex_init(&rmn->lock);
-	rmn->objects = RB_ROOT_CACHED;
-	return &rmn->mn;
-}
-
-static void radeon_mn_free_notifier(struct mmu_notifier *mn)
-{
-	kfree(container_of(mn, struct radeon_mn, mn));
-}
-
-static const struct mmu_notifier_ops radeon_mn_ops = {
-	.release = radeon_mn_release,
-	.invalidate_range_start = radeon_mn_invalidate_range_start,
-	.alloc_notifier = radeon_mn_alloc_notifier,
-	.free_notifier = radeon_mn_free_notifier,
+static const struct mmu_interval_notifier_ops radeon_mn_ops = {
+	.invalidate = radeon_mn_invalidate,
 };
 
 /**
···
  */
 int radeon_mn_register(struct radeon_bo *bo, unsigned long addr)
 {
-	unsigned long end = addr + radeon_bo_size(bo) - 1;
-	struct mmu_notifier *mn;
-	struct radeon_mn *rmn;
-	struct radeon_mn_node *node = NULL;
-	struct list_head bos;
-	struct interval_tree_node *it;
+	int ret;
 
-	mn = mmu_notifier_get(&radeon_mn_ops, current->mm);
-	if (IS_ERR(mn))
-		return PTR_ERR(mn);
-	rmn = container_of(mn, struct radeon_mn, mn);
+	ret = mmu_interval_notifier_insert(&bo->notifier, current->mm, addr,
+					   radeon_bo_size(bo), &radeon_mn_ops);
+	if (ret)
+		return ret;
 
-	INIT_LIST_HEAD(&bos);
-
-	mutex_lock(&rmn->lock);
-
-	while ((it = interval_tree_iter_first(&rmn->objects, addr, end))) {
-		kfree(node);
-		node = container_of(it, struct radeon_mn_node, it);
-		interval_tree_remove(&node->it, &rmn->objects);
-		addr = min(it->start, addr);
-		end = max(it->last, end);
-		list_splice(&node->bos, &bos);
-	}
-
-	if (!node) {
-		node = kmalloc(sizeof(struct radeon_mn_node), GFP_KERNEL);
-		if (!node) {
-			mutex_unlock(&rmn->lock);
-			return -ENOMEM;
-		}
-	}
-
-	bo->mn = rmn;
-
-	node->it.start = addr;
-	node->it.last = end;
-	INIT_LIST_HEAD(&node->bos);
-	list_splice(&bos, &node->bos);
-	list_add(&bo->mn_list, &node->bos);
-
-	interval_tree_insert(&node->it, &rmn->objects);
-
-	mutex_unlock(&rmn->lock);
-
+	/*
+	 * FIXME: radeon appears to allow get_user_pages to run during
+	 * invalidate_range_start/end, which is not a safe way to read the
+	 * PTEs. It should use the mmu_interval_read_begin() scheme around the
+	 * get_user_pages to ensure that the PTEs are read properly
+	 */
+	mmu_interval_read_begin(&bo->notifier);
 	return 0;
 }
 
···
  */
 void radeon_mn_unregister(struct radeon_bo *bo)
 {
-	struct radeon_mn *rmn = bo->mn;
-	struct list_head *head;
-
-	if (!rmn)
+	if (!bo->notifier.mm)
 		return;
-
-	mutex_lock(&rmn->lock);
-	/* save the next list entry for later */
-	head = bo->mn_list.next;
-
-	list_del(&bo->mn_list);
-
-	if (list_empty(head)) {
-		struct radeon_mn_node *node;
-		node = container_of(head, struct radeon_mn_node, bos);
-		interval_tree_remove(&node->it, &rmn->objects);
-		kfree(node);
-	}
-
-	mutex_unlock(&rmn->lock);
-
-	mmu_notifier_put(&rmn->mn);
-	bo->mn = NULL;
+	mmu_interval_notifier_remove(&bo->notifier);
+	bo->notifier.mm = NULL;
 }

drivers/infiniband/core/device.c

···
 	SET_DEVICE_OP(dev_ops, get_vf_guid);
 	SET_DEVICE_OP(dev_ops, get_vf_stats);
 	SET_DEVICE_OP(dev_ops, init_port);
-	SET_DEVICE_OP(dev_ops, invalidate_range);
 	SET_DEVICE_OP(dev_ops, iw_accept);
 	SET_DEVICE_OP(dev_ops, iw_add_ref);
 	SET_DEVICE_OP(dev_ops, iw_connect);

drivers/infiniband/core/umem_odp.c

···
 
 #include "uverbs.h"
 
-static void ib_umem_notifier_start_account(struct ib_umem_odp *umem_odp)
+static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
+				   const struct mmu_interval_notifier_ops *ops)
 {
-	mutex_lock(&umem_odp->umem_mutex);
-	if (umem_odp->notifiers_count++ == 0)
-		/*
-		 * Initialize the completion object for waiting on
-		 * notifiers. Since notifier_count is zero, no one should be
-		 * waiting right now.
-		 */
-		reinit_completion(&umem_odp->notifier_completion);
-	mutex_unlock(&umem_odp->umem_mutex);
-}
-
-static void ib_umem_notifier_end_account(struct ib_umem_odp *umem_odp)
-{
-	mutex_lock(&umem_odp->umem_mutex);
-	/*
-	 * This sequence increase will notify the QP page fault that the page
-	 * that is going to be mapped in the spte could have been freed.
-	 */
-	++umem_odp->notifiers_seq;
-	if (--umem_odp->notifiers_count == 0)
-		complete_all(&umem_odp->notifier_completion);
-	mutex_unlock(&umem_odp->umem_mutex);
-}
-
-static void ib_umem_notifier_release(struct mmu_notifier *mn,
-				     struct mm_struct *mm)
-{
-	struct ib_ucontext_per_mm *per_mm =
-		container_of(mn, struct ib_ucontext_per_mm, mn);
-	struct rb_node *node;
-
-	down_read(&per_mm->umem_rwsem);
-	if (!per_mm->mn.users)
-		goto out;
-
-	for (node = rb_first_cached(&per_mm->umem_tree); node;
-	     node = rb_next(node)) {
-		struct ib_umem_odp *umem_odp =
-			rb_entry(node, struct ib_umem_odp, interval_tree.rb);
-
-		/*
-		 * Increase the number of notifiers running, to prevent any
-		 * further fault handling on this MR.
-		 */
-		ib_umem_notifier_start_account(umem_odp);
-		complete_all(&umem_odp->notifier_completion);
-		umem_odp->umem.ibdev->ops.invalidate_range(
-			umem_odp, ib_umem_start(umem_odp),
-			ib_umem_end(umem_odp));
-	}
-
-out:
-	up_read(&per_mm->umem_rwsem);
-}
-
-static int invalidate_range_start_trampoline(struct ib_umem_odp *item,
-					     u64 start, u64 end, void *cookie)
-{
-	ib_umem_notifier_start_account(item);
-	item->umem.ibdev->ops.invalidate_range(item, start, end);
-	return 0;
-}
-
-static int ib_umem_notifier_invalidate_range_start(struct mmu_notifier *mn,
-				const struct mmu_notifier_range *range)
-{
-	struct ib_ucontext_per_mm *per_mm =
-		container_of(mn, struct ib_ucontext_per_mm, mn);
-	int rc;
-
-	if (mmu_notifier_range_blockable(range))
-		down_read(&per_mm->umem_rwsem);
-	else if (!down_read_trylock(&per_mm->umem_rwsem))
-		return -EAGAIN;
-
-	if (!per_mm->mn.users) {
-		up_read(&per_mm->umem_rwsem);
-		/*
-		 * At this point users is permanently zero and visible to this
-		 * CPU without a lock, that fact is relied on to skip the unlock
-		 * in range_end.
-		 */
-		return 0;
-	}
-
-	rc = rbt_ib_umem_for_each_in_range(&per_mm->umem_tree, range->start,
-					   range->end,
-					   invalidate_range_start_trampoline,
-					   mmu_notifier_range_blockable(range),
-					   NULL);
-	if (rc)
-		up_read(&per_mm->umem_rwsem);
-	return rc;
-}
-
-static int invalidate_range_end_trampoline(struct ib_umem_odp *item, u64 start,
-					   u64 end, void *cookie)
-{
-	ib_umem_notifier_end_account(item);
-	return 0;
-}
-
-static void ib_umem_notifier_invalidate_range_end(struct mmu_notifier *mn,
-				const struct mmu_notifier_range *range)
-{
-	struct ib_ucontext_per_mm *per_mm =
-		container_of(mn, struct ib_ucontext_per_mm, mn);
-
-	if (unlikely(!per_mm->mn.users))
-		return;
-
-	rbt_ib_umem_for_each_in_range(&per_mm->umem_tree, range->start,
-				      range->end,
-				      invalidate_range_end_trampoline, true, NULL);
-	up_read(&per_mm->umem_rwsem);
-}
-
-static struct mmu_notifier *ib_umem_alloc_notifier(struct mm_struct *mm)
-{
-	struct ib_ucontext_per_mm *per_mm;
-
-	per_mm = kzalloc(sizeof(*per_mm), GFP_KERNEL);
-	if (!per_mm)
-		return ERR_PTR(-ENOMEM);
-
-	per_mm->umem_tree = RB_ROOT_CACHED;
-	init_rwsem(&per_mm->umem_rwsem);
-
-	WARN_ON(mm != current->mm);
-	rcu_read_lock();
-	per_mm->tgid = get_task_pid(current->group_leader, PIDTYPE_PID);
-	rcu_read_unlock();
-	return &per_mm->mn;
-}
-
-static void ib_umem_free_notifier(struct mmu_notifier *mn)
-{
-	struct ib_ucontext_per_mm *per_mm =
-		container_of(mn, struct ib_ucontext_per_mm, mn);
-
-	WARN_ON(!RB_EMPTY_ROOT(&per_mm->umem_tree.rb_root));
-
-	put_pid(per_mm->tgid);
-	kfree(per_mm);
-}
-
-static const struct mmu_notifier_ops ib_umem_notifiers = {
-	.release                    = ib_umem_notifier_release,
-	.invalidate_range_start     = ib_umem_notifier_invalidate_range_start,
-	.invalidate_range_end       = ib_umem_notifier_invalidate_range_end,
-	.alloc_notifier		    = ib_umem_alloc_notifier,
-	.free_notifier		    = ib_umem_free_notifier,
-};
-
-static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp)
-{
-	struct ib_ucontext_per_mm *per_mm;
-	struct mmu_notifier *mn;
 	int ret;
 
 	umem_odp->umem.is_odp = 1;
+	mutex_init(&umem_odp->umem_mutex);
+
 	if (!umem_odp->is_implicit_odp) {
 		size_t page_size = 1UL << umem_odp->page_shift;
+		unsigned long start;
+		unsigned long end;
 		size_t pages;
 
-		umem_odp->interval_tree.start =
-			ALIGN_DOWN(umem_odp->umem.address, page_size);
+		start = ALIGN_DOWN(umem_odp->umem.address, page_size);
 		if (check_add_overflow(umem_odp->umem.address,
 				       (unsigned long)umem_odp->umem.length,
-				       &umem_odp->interval_tree.last))
+				       &end))
 			return -EOVERFLOW;
-		umem_odp->interval_tree.last =
-			ALIGN(umem_odp->interval_tree.last, page_size);
-		if (unlikely(umem_odp->interval_tree.last < page_size))
+		end = ALIGN(end, page_size);
+		if (unlikely(end < page_size))
 			return -EOVERFLOW;
 
-		pages = (umem_odp->interval_tree.last -
-			 umem_odp->interval_tree.start) >>
-			umem_odp->page_shift;
+		pages = (end - start) >> umem_odp->page_shift;
 		if (!pages)
 			return -EINVAL;
-
-		/*
-		 * Note that the representation of the intervals in the
-		 * interval tree considers the ending point as contained in
-		 * the interval.
-		 */
-		umem_odp->interval_tree.last--;
 
 		umem_odp->page_list = kvcalloc(
 			pages, sizeof(*umem_odp->page_list), GFP_KERNEL);
···
 			ret = -ENOMEM;
 			goto out_page_list;
 		}
-	}
 
-	mn = mmu_notifier_get(&ib_umem_notifiers, umem_odp->umem.owning_mm);
-	if (IS_ERR(mn)) {
-		ret = PTR_ERR(mn);
-		goto out_dma_list;
+		ret = mmu_interval_notifier_insert(&umem_odp->notifier,
+						   umem_odp->umem.owning_mm,
+						   start, end - start, ops);
+		if (ret)
+			goto out_dma_list;
 	}
-	umem_odp->per_mm = per_mm =
-		container_of(mn, struct ib_ucontext_per_mm, mn);
-
-	mutex_init(&umem_odp->umem_mutex);
-	init_completion(&umem_odp->notifier_completion);
-
-	if (!umem_odp->is_implicit_odp) {
-		down_write(&per_mm->umem_rwsem);
-		interval_tree_insert(&umem_odp->interval_tree,
-				     &per_mm->umem_tree);
-		up_write(&per_mm->umem_rwsem);
-	}
-	mmgrab(umem_odp->umem.owning_mm);
 
 	return 0;
 
···
 
 	if (!context)
 		return ERR_PTR(-EIO);
-	if (WARN_ON_ONCE(!context->device->ops.invalidate_range))
-		return ERR_PTR(-EINVAL);
 
 	umem_odp = kzalloc(sizeof(*umem_odp), GFP_KERNEL);
 	if (!umem_odp)
···
 	umem_odp->is_implicit_odp = 1;
 	umem_odp->page_shift = PAGE_SHIFT;
 
-	ret = ib_init_umem_odp(umem_odp);
+	umem_odp->tgid = get_task_pid(current->group_leader, PIDTYPE_PID);
+	ret = ib_init_umem_odp(umem_odp, NULL);
 	if (ret) {
+		put_pid(umem_odp->tgid);
 		kfree(umem_odp);
 		return ERR_PTR(ret);
 	}
···
  * @addr: The starting userspace VA
  * @size: The length of the userspace VA
  */
-struct ib_umem_odp *ib_umem_odp_alloc_child(struct ib_umem_odp *root,
-					    unsigned long addr, size_t size)
+struct ib_umem_odp *
+ib_umem_odp_alloc_child(struct ib_umem_odp *root, unsigned long addr,
+			size_t size,
+			const struct mmu_interval_notifier_ops *ops)
 {
 	/*
 	 * Caller must ensure that root cannot be freed during the call to
···
 	umem->writable   = root->umem.writable;
 	umem->owning_mm  = root->umem.owning_mm;
 	odp_data->page_shift = PAGE_SHIFT;
+	odp_data->notifier.ops = ops;
 
-	ret = ib_init_umem_odp(odp_data);
+	odp_data->tgid = get_pid(root->tgid);
+	ret = ib_init_umem_odp(odp_data, ops);
 	if (ret) {
+		put_pid(odp_data->tgid);
 		kfree(odp_data);
 		return ERR_PTR(ret);
 	}
···
  * conjunction with MMU notifiers.
  */
 struct ib_umem_odp *ib_umem_odp_get(struct ib_udata *udata, unsigned long addr,
-				    size_t size, int access)
+				    size_t size, int access,
+				    const struct mmu_interval_notifier_ops *ops)
 {
 	struct ib_umem_odp *umem_odp;
 	struct ib_ucontext *context;
···
 	if (!context)
 		return ERR_PTR(-EIO);
 
-	if (WARN_ON_ONCE(!(access & IB_ACCESS_ON_DEMAND)) ||
-	    WARN_ON_ONCE(!context->device->ops.invalidate_range))
+	if (WARN_ON_ONCE(!(access & IB_ACCESS_ON_DEMAND)))
 		return ERR_PTR(-EINVAL);
 
 	umem_odp = kzalloc(sizeof(struct ib_umem_odp), GFP_KERNEL);
···
 	umem_odp->umem.address = addr;
 	umem_odp->umem.writable = ib_access_writable(access);
 	umem_odp->umem.owning_mm = mm = current->mm;
+	umem_odp->notifier.ops = ops;
 
 	umem_odp->page_shift = PAGE_SHIFT;
 	if (access & IB_ACCESS_HUGETLB) {
···
 		up_read(&mm->mmap_sem);
 	}
 
-	ret = ib_init_umem_odp(umem_odp);
+	umem_odp->tgid = get_task_pid(current->group_leader, PIDTYPE_PID);
+	ret = ib_init_umem_odp(umem_odp, ops);
 	if (ret)
-		goto err_free;
+		goto err_put_pid;
 	return umem_odp;
 
+err_put_pid:
+	put_pid(umem_odp->tgid);
 err_free:
 	kfree(umem_odp);
 	return ERR_PTR(ret);
···
 
 void ib_umem_odp_release(struct ib_umem_odp *umem_odp)
 {
-	struct ib_ucontext_per_mm *per_mm = umem_odp->per_mm;
-
 	/*
 	 * Ensure that no more pages are mapped in the umem.
 	 *
···
 		ib_umem_odp_unmap_dma_pages(umem_odp, ib_umem_start(umem_odp),
 					    ib_umem_end(umem_odp));
 		mutex_unlock(&umem_odp->umem_mutex);
+		mmu_interval_notifier_remove(&umem_odp->notifier);
 		kvfree(umem_odp->dma_list);
 		kvfree(umem_odp->page_list);
+		put_pid(umem_odp->tgid);
 	}
-
-	down_write(&per_mm->umem_rwsem);
-	if (!umem_odp->is_implicit_odp) {
-		interval_tree_remove(&umem_odp->interval_tree,
-				     &per_mm->umem_tree);
-		complete_all(&umem_odp->notifier_completion);
-	}
-	/*
-	 * NOTE! mmu_notifier_unregister() can happen between a start/end
-	 * callback, resulting in a missing end, and thus an unbalanced
-	 * lock. This doesn't really matter to us since we are about to kfree
-	 * the memory that holds the lock, however LOCKDEP doesn't like this.
-	 * Thus we call the mmu_notifier_put under the rwsem and test the
-	 * internal users count to reliably see if we are past this point.
-	 */
-	mmu_notifier_put(&per_mm->mn);
-	up_write(&per_mm->umem_rwsem);
-
-	mmdrop(umem_odp->umem.owning_mm);
 	kfree(umem_odp);
 }
 EXPORT_SYMBOL(ib_umem_odp_release);
···
  */
 static int ib_umem_odp_map_dma_single_page(
 		struct ib_umem_odp *umem_odp,
-		int page_index,
+		unsigned int page_index,
 		struct page *page,
 		u64 access_mask,
 		unsigned long current_seq)
···
 	dma_addr_t dma_addr;
 	int ret = 0;
 
-	/*
-	 * Note: we avoid writing if seq is different from the initial seq, to
-	 * handle case of a racing notifier. This check also allows us to bail
-	 * early if we have a notifier running in parallel with us.
-	 */
-	if (ib_umem_mmu_notifier_retry(umem_odp, current_seq)) {
+	if (mmu_interval_check_retry(&umem_odp->notifier, current_seq)) {
 		ret = -EAGAIN;
 		goto out;
 	}
···
 	 * existing beyond the lifetime of the originating process.. Presumably
 	 * mmget_not_zero will fail in this case.
 	 */
-	owning_process = get_pid_task(umem_odp->per_mm->tgid, PIDTYPE_PID);
+	owning_process = get_pid_task(umem_odp->tgid, PIDTYPE_PID);
 	if (!owning_process || !mmget_not_zero(owning_mm)) {
 		ret = -EINVAL;
 		goto out_put_task;
···
 	}
 }
 EXPORT_SYMBOL(ib_umem_odp_unmap_dma_pages);
-
-/* @last is not a part of the interval. See comment for function
- * node_last.
- */
-int rbt_ib_umem_for_each_in_range(struct rb_root_cached *root,
-				  u64 start, u64 last,
-				  umem_call_back cb,
-				  bool blockable,
-				  void *cookie)
-{
-	int ret_val = 0;
-	struct interval_tree_node *node, *next;
-	struct ib_umem_odp *umem;
-
-	if (unlikely(start == last))
-		return ret_val;
-
-	for (node = interval_tree_iter_first(root, start, last - 1);
-			node; node = next) {
-		/* TODO move the blockable decision up to the callback */
-		if (!blockable)
-			return -EAGAIN;
-		next = interval_tree_iter_next(node, start, last - 1);
-		umem = container_of(node, struct ib_umem_odp, interval_tree);
-		ret_val = cb(umem, start, last, cookie) || ret_val;
-	}
-
-	return ret_val;
-}

drivers/infiniband/hw/hfi1/file_ops.c

···
 			HFI1_CAP_UGET_MASK(uctxt->flags, MASK) |
 			HFI1_CAP_KGET_MASK(uctxt->flags, K2U);
 	/* adjust flag if this fd is not able to cache */
-	if (!fd->handler)
+	if (!fd->use_mn)
 		cinfo.runtime_flags |= HFI1_CAP_TID_UNMAP; /* no caching */
 
 	cinfo.num_active = hfi1_count_active_units();

drivers/infiniband/hw/hfi1/hfi.h

···
 	/* for cpu affinity; -1 if none */
 	int rec_cpu_num;
 	u32 tid_n_pinned;
-	struct mmu_rb_handler *handler;
+	bool use_mn;
 	struct tid_rb_node **entry_to_rb;
 	spinlock_t tid_lock; /* protect tid_[limit,used] counters */
 	u32 tid_limit;

drivers/infiniband/hw/hfi1/user_exp_rcv.c

···
 			      struct tid_user_buf *tbuf,
 			      u32 rcventry, struct tid_group *grp,
 			      u16 pageidx, unsigned int npages);
-static int tid_rb_insert(void *arg, struct mmu_rb_node *node);
 static void cacheless_tid_rb_remove(struct hfi1_filedata *fdata,
 				    struct tid_rb_node *tnode);
-static void tid_rb_remove(void *arg, struct mmu_rb_node *node);
-static int tid_rb_invalidate(void *arg, struct mmu_rb_node *mnode);
+static bool tid_rb_invalidate(struct mmu_interval_notifier *mni,
+			      const struct mmu_notifier_range *range,
+			      unsigned long cur_seq);
 static int program_rcvarray(struct hfi1_filedata *fd, struct tid_user_buf *,
 			    struct tid_group *grp,
 			    unsigned int start, u16 count,
···
 			      struct tid_group **grp);
 static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node);
 
-static struct mmu_rb_ops tid_rb_ops = {
-	.insert = tid_rb_insert,
-	.remove = tid_rb_remove,
-	.invalidate = tid_rb_invalidate
+static const struct mmu_interval_notifier_ops tid_mn_ops = {
+	.invalidate = tid_rb_invalidate,
 };
 
 /*
···
 int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd,
 			   struct hfi1_ctxtdata *uctxt)
 {
-	struct hfi1_devdata *dd = uctxt->dd;
 	int ret = 0;
 
 	spin_lock_init(&fd->tid_lock);
···
 			fd->entry_to_rb = NULL;
 			return -ENOMEM;
 		}
-
-		/*
-		 * Register MMU notifier callbacks. If the registration
-		 * fails, continue without TID caching for this context.
-		 */
-		ret = hfi1_mmu_rb_register(fd, fd->mm, &tid_rb_ops,
-					   dd->pport->hfi1_wq,
-					   &fd->handler);
-		if (ret) {
-			dd_dev_info(dd,
-				    "Failed MMU notifier registration %d\n",
-				    ret);
-			ret = 0;
-		}
+		fd->use_mn = true;
 	}
 
 	/*
···
 	 * init.
 	 */
 	spin_lock(&fd->tid_lock);
-	if (uctxt->subctxt_cnt && fd->handler) {
+	if (uctxt->subctxt_cnt && fd->use_mn) {
 		u16 remainder;
 
 		fd->tid_limit = uctxt->expected_count / uctxt->subctxt_cnt;
···
 {
 	struct hfi1_ctxtdata *uctxt = fd->uctxt;
 
-	/*
-	 * The notifier would have been removed when the process'es mm
-	 * was freed.
-	 */
-	if (fd->handler) {
-		hfi1_mmu_rb_unregister(fd->handler);
-	} else {
-		if (!EXP_TID_SET_EMPTY(uctxt->tid_full_list))
-			unlock_exp_tids(uctxt, &uctxt->tid_full_list, fd);
-		if (!EXP_TID_SET_EMPTY(uctxt->tid_used_list))
-			unlock_exp_tids(uctxt, &uctxt->tid_used_list, fd);
-	}
+	if (!EXP_TID_SET_EMPTY(uctxt->tid_full_list))
+		unlock_exp_tids(uctxt, &uctxt->tid_full_list, fd);
+	if (!EXP_TID_SET_EMPTY(uctxt->tid_used_list))
+		unlock_exp_tids(uctxt, &uctxt->tid_used_list, fd);
 
 	kfree(fd->invalid_tids);
 	fd->invalid_tids = NULL;
···
 
 	if (mapped) {
 		pci_unmap_single(dd->pcidev, node->dma_addr,
-				 node->mmu.len, PCI_DMA_FROMDEVICE);
+				 node->npages * PAGE_SIZE, PCI_DMA_FROMDEVICE);
 		pages = &node->pages[idx];
 	} else {
 		pages = &tidbuf->pages[idx];
···
 		return -EFAULT;
 	}
 
-	node->mmu.addr = tbuf->vaddr + (pageidx * PAGE_SIZE);
-	node->mmu.len = npages * PAGE_SIZE;
+	node->fdata = fd;
 	node->phys = page_to_phys(pages[0]);
 	node->npages = npages;
 	node->rcventry = rcventry;
···
 	node->freed = false;
 	memcpy(node->pages, pages, sizeof(struct page *) * npages);
 
-	if (!fd->handler)
-		ret = tid_rb_insert(fd, &node->mmu);
-	else
-		ret = hfi1_mmu_rb_insert(fd->handler, &node->mmu);
-
-	if (ret) {
-		hfi1_cdbg(TID, "Failed to insert RB node %u 0x%lx, 0x%lx %d",
-			  node->rcventry, node->mmu.addr, node->phys, ret);
-		pci_unmap_single(dd->pcidev, phys, npages * PAGE_SIZE,
-				 PCI_DMA_FROMDEVICE);
-		kfree(node);
-		return -EFAULT;
+	if (fd->use_mn) {
+		ret = mmu_interval_notifier_insert(
+			&node->notifier, fd->mm,
+			tbuf->vaddr + (pageidx * PAGE_SIZE), npages * PAGE_SIZE,
+			&tid_mn_ops);
+		if (ret)
+			goto out_unmap;
+		/*
+		 * FIXME: This is in the wrong order, the notifier should be
+		 * established before the pages are pinned by pin_rcv_pages.
+		 */
+		mmu_interval_read_begin(&node->notifier);
 	}
+	fd->entry_to_rb[node->rcventry - uctxt->expected_base] = node;
+
 	hfi1_put_tid(dd, rcventry, PT_EXPECTED, phys, ilog2(npages) + 1);
 	trace_hfi1_exp_tid_reg(uctxt->ctxt, fd->subctxt, rcventry, npages,
-			       node->mmu.addr, node->phys, phys);
+			       node->notifier.interval_tree.start, node->phys,
+			       phys);
 	return 0;
+
+out_unmap:
+	hfi1_cdbg(TID, "Failed to insert RB node %u 0x%lx, 0x%lx %d",
+		  node->rcventry, node->notifier.interval_tree.start,
+		  node->phys, ret);
+	pci_unmap_single(dd->pcidev, phys, npages * PAGE_SIZE,
+			 PCI_DMA_FROMDEVICE);
+	kfree(node);
+	return -EFAULT;
 }
 
 static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
···
 	if (grp)
 		*grp = node->grp;
 
-	if (!fd->handler)
-		cacheless_tid_rb_remove(fd, node);
-	else
-		hfi1_mmu_rb_remove(fd->handler, &node->mmu);
+	if (fd->use_mn)
+		mmu_interval_notifier_remove(&node->notifier);
+	cacheless_tid_rb_remove(fd, node);
 
 	return 0;
 }
···
 	struct hfi1_devdata *dd = uctxt->dd;
 
 	trace_hfi1_exp_tid_unreg(uctxt->ctxt, fd->subctxt, node->rcventry,
-				 node->npages, node->mmu.addr, node->phys,
+				 node->npages,
+				 node->notifier.interval_tree.start, node->phys,
 				 node->dma_addr);
 
 	/*
···
 				if (!node || node->rcventry != rcventry)
 					continue;
 
+				if (fd->use_mn)
+					mmu_interval_notifier_remove(
+						&node->notifier);
 				cacheless_tid_rb_remove(fd, node);
 			}
 		}
 	}
 }
 
-/*
- * Always return 0 from this function.  A non-zero return indicates that the
- * remove operation will be called and that memory should be unpinned.
- * However, the driver cannot unpin out from under PSM.  Instead, retain the
- * memory (by returning 0) and inform PSM that the memory is going away.  PSM
- * will call back later when it has removed the memory from its list.
- */
-static int tid_rb_invalidate(void *arg, struct mmu_rb_node *mnode)
+static bool tid_rb_invalidate(struct mmu_interval_notifier *mni,
+			      const struct mmu_notifier_range *range,
+			      unsigned long cur_seq)
 {
-	struct hfi1_filedata *fdata = arg;
-	struct hfi1_ctxtdata *uctxt = fdata->uctxt;
 	struct tid_rb_node *node =
-		container_of(mnode, struct tid_rb_node, mmu);
+		container_of(mni, struct tid_rb_node, notifier);
+	struct hfi1_filedata *fdata = node->fdata;
+	struct hfi1_ctxtdata *uctxt = fdata->uctxt;
 
 	if (node->freed)
-		return 0;
+		return true;
 
-	trace_hfi1_exp_tid_inval(uctxt->ctxt, fdata->subctxt, node->mmu.addr,
+	trace_hfi1_exp_tid_inval(uctxt->ctxt, fdata->subctxt,
+				 node->notifier.interval_tree.start,
 				 node->rcventry, node->npages, node->dma_addr);
 	node->freed = true;
 
···
 		fdata->invalid_tid_idx++;
 	}
 	spin_unlock(&fdata->invalid_lock);
-	return 0;
-}
-
-static int tid_rb_insert(void *arg, struct mmu_rb_node *node)
-{
-	struct hfi1_filedata *fdata = arg;
-	struct tid_rb_node *tnode =
-		container_of(node, struct tid_rb_node, mmu);
-	u32 base = fdata->uctxt->expected_base;
-
-	fdata->entry_to_rb[tnode->rcventry - base] = tnode;
-	return 0;
+	return true;
 }
 
 static void cacheless_tid_rb_remove(struct hfi1_filedata *fdata,
···
 
 	fdata->entry_to_rb[tnode->rcventry - base] = NULL;
 	clear_tid_node(fdata, tnode);
-}
-
-static void tid_rb_remove(void *arg, struct mmu_rb_node *node)
-{
-	struct hfi1_filedata *fdata = arg;
-	struct tid_rb_node *tnode =
-		container_of(node, struct tid_rb_node, mmu);
-
-	cacheless_tid_rb_remove(fdata, tnode);
 }

drivers/infiniband/hw/hfi1/user_exp_rcv.h

···
 };
 
 struct tid_rb_node {
-	struct mmu_rb_node mmu;
+	struct mmu_interval_notifier notifier;
+	struct hfi1_filedata *fdata;
 	unsigned long phys;
 	struct tid_group *grp;
 	u32 rcventry;

drivers/infiniband/hw/mlx5/mlx5_ib.h

···
 void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *ibdev);
 int __init mlx5_ib_odp_init(void);
 void mlx5_ib_odp_cleanup(void);
-void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
-			      unsigned long end);
 void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent);
 void mlx5_odp_populate_klm(struct mlx5_klm *pklm, size_t offset,
 			   size_t nentries, struct mlx5_ib_mr *mr, int flags);
···
 {
 	return -EOPNOTSUPP;
 }
-static inline void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp,
-					    unsigned long start,
-					    unsigned long end){};
 #endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
+
+extern const struct mmu_interval_notifier_ops mlx5_mn_ops;
 
 /* Needed for rep profile */
 void __mlx5_ib_remove(struct mlx5_ib_dev *dev,

drivers/infiniband/hw/mlx5/mr.c

···
 	if (access_flags & IB_ACCESS_ON_DEMAND) {
 		struct ib_umem_odp *odp;
 
-		odp = ib_umem_odp_get(udata, start, length, access_flags);
+		odp = ib_umem_odp_get(udata, start, length, access_flags,
+				      &mlx5_mn_ops);
 		if (IS_ERR(odp)) {
 			mlx5_ib_dbg(dev, "umem get failed (%ld)\n",
 				    PTR_ERR(odp));

drivers/infiniband/hw/mlx5/odp.c

···
 	xa_unlock(&imr->implicit_children);
 }
 
-void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
-			      unsigned long end)
+static bool mlx5_ib_invalidate_range(struct mmu_interval_notifier *mni,
+				     const struct mmu_notifier_range *range,
+				     unsigned long cur_seq)
 {
+	struct ib_umem_odp *umem_odp =
+		container_of(mni, struct ib_umem_odp, notifier);
 	struct mlx5_ib_mr *mr;
 	const u64 umr_block_mask = (MLX5_UMR_MTT_ALIGNMENT /
 				    sizeof(struct mlx5_mtt)) - 1;
 	u64 idx = 0, blk_start_idx = 0;
 	u64 invalidations = 0;
+	unsigned long start;
+	unsigned long end;
 	int in_block = 0;
 	u64 addr;
 
+	if (!mmu_notifier_range_blockable(range))
+		return false;
+
 	mutex_lock(&umem_odp->umem_mutex);
+	mmu_interval_set_seq(mni, cur_seq);
 	/*
 	 * If npages is zero then umem_odp->private may not be setup yet. This
 	 * does not complete until after the first page is mapped for DMA.
···
 		goto out;
 	mr = umem_odp->private;
 
-	start = max_t(u64, ib_umem_start(umem_odp), start);
-	end = min_t(u64, ib_umem_end(umem_odp), end);
+	start = max_t(u64, ib_umem_start(umem_odp), range->start);
+	end = min_t(u64, ib_umem_end(umem_odp), range->end);
 
 	/*
 	 * Iteration one - zap the HW's MTTs. The notifiers_count ensures that
···
 		destroy_unused_implicit_child_mr(mr);
 out:
 	mutex_unlock(&umem_odp->umem_mutex);
+	return true;
 }
+
+const struct mmu_interval_notifier_ops mlx5_mn_ops = {
+	.invalidate = mlx5_ib_invalidate_range,
+};
 
 void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
 {
···
 
 	odp = ib_umem_odp_alloc_child(to_ib_umem_odp(imr->umem),
 				      idx * MLX5_IMR_MTT_SIZE,
-				      MLX5_IMR_MTT_SIZE);
+				      MLX5_IMR_MTT_SIZE, &mlx5_mn_ops);
 	if (IS_ERR(odp))
 		return ERR_CAST(odp);
 
···
 			     u64 user_va, size_t bcnt, u32 *bytes_mapped,
 			     u32 flags)
 {
-	int current_seq, page_shift, ret, np;
+	int page_shift, ret, np;
 	bool downgrade = flags & MLX5_PF_FLAGS_DOWNGRADE;
+	unsigned long current_seq;
 	u64 access_mask;
 	u64 start_idx, page_mask;
 
···
 	if (odp->umem.writable && !downgrade)
 		access_mask |= ODP_WRITE_ALLOWED_BIT;
 
-	current_seq = READ_ONCE(odp->notifiers_seq);
-	/*
-	 * Ensure the sequence number is valid for some time before we call
-	 * gup.
-	 */
-	smp_rmb();
+	current_seq = mmu_interval_read_begin(&odp->notifier);
 
 	np = ib_umem_odp_map_dma_pages(odp, user_va, bcnt, access_mask,
 				       current_seq);
···
 		return np;
 
 	mutex_lock(&odp->umem_mutex);
-	if (!ib_umem_mmu_notifier_retry(odp, current_seq)) {
+	if (!mmu_interval_read_retry(&odp->notifier, current_seq)) {
 		/*
 		 * No need to check whether the MTTs really belong to
 		 * this MR, since ib_umem_odp_map_dma_pages already
···
 	return np << (page_shift - PAGE_SHIFT);
 
 out:
-	if (ret == -EAGAIN) {
-		unsigned long timeout = msecs_to_jiffies(MMU_NOTIFIER_TIMEOUT);
-
-		if (!wait_for_completion_timeout(&odp->notifier_completion,
-						 timeout)) {
-			mlx5_ib_warn(
-				mr->dev,
-				"timeout waiting for mmu notifier. seq %d against %d. notifiers_count=%d\n",
-				current_seq, odp->notifiers_seq,
-				odp->notifiers_count);
-		}
-	}
-
 	return ret;
 }
 
···
 
 static const struct ib_device_ops mlx5_ib_dev_odp_ops = {
 	.advise_mr = mlx5_ib_advise_mr,
-	.invalidate_range = mlx5_ib_invalidate_range,
 };
 
 int mlx5_ib_odp_init_one(struct mlx5_ib_dev *dev)

drivers/xen/gntdev-common.h

···
 struct gntdev_priv {
 	/* Maps with visible offsets in the file descriptor. */
 	struct list_head maps;
-	/*
-	 * Maps that are not visible; will be freed on munmap.
-	 * Only populated if populate_freeable_maps == 1
-	 */
-	struct list_head freeable_maps;
 	/* lock protects maps and freeable_maps. */
 	struct mutex lock;
-	struct mm_struct *mm;
-	struct mmu_notifier mn;
 
 #ifdef CONFIG_XEN_GRANT_DMA_ALLOC
 	/* Device for which DMA memory is allocated. */
···
 };
 
 struct gntdev_grant_map {
+	struct mmu_interval_notifier notifier;
 	struct list_head next;
 	struct vm_area_struct *vma;
 	int index;

drivers/xen/gntdev.c

···
 static atomic_t pages_mapped = ATOMIC_INIT(0);
 
 static int use_ptemod;
-#define populate_freeable_maps use_ptemod
 
 static int unmap_grant_pages(struct gntdev_grant_map *map,
 			     int offset, int pages);
···
 	if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) {
 		notify_remote_via_evtchn(map->notify.event);
 		evtchn_put(map->notify.event);
-	}
-
-	if (populate_freeable_maps && priv) {
-		mutex_lock(&priv->lock);
-		list_del(&map->next);
-		mutex_unlock(&priv->lock);
 	}
 
 	if (map->pages && !use_ptemod)
···
 
 	pr_debug("gntdev_vma_close %p\n", vma);
 	if (use_ptemod) {
-		/* It is possible that an mmu notifier could be running
-		 * concurrently, so take priv->lock to ensure that the vma won't
-		 * vanishing during the unmap_grant_pages call, since we will
-		 * spin here until that completes. Such a concurrent call will
-		 * not do any unmapping, since that has been done prior to
-		 * closing the vma, but it may still iterate the unmap_ops list.
-		 */
-		mutex_lock(&priv->lock);
+		WARN_ON(map->vma != vma);
+		mmu_interval_notifier_remove(&map->notifier);
 		map->vma = NULL;
-		mutex_unlock(&priv->lock);
 	}
 	vma->vm_private_data = NULL;
 	gntdev_put_map(priv, map);
···
 
 /* ------------------------------------------------------------------ */
 
-static bool in_range(struct gntdev_grant_map *map,
-			      unsigned long start, unsigned long end)
+static bool gntdev_invalidate(struct mmu_interval_notifier *mn,
+			      const struct mmu_notifier_range *range,
+			      unsigned long cur_seq)
 {
-	if (!map->vma)
-		return false;
-	if (map->vma->vm_start >= end)
-		return false;
-	if (map->vma->vm_end <= start)
-		return false;
-
-	return true;
-}
-
-static int unmap_if_in_range(struct gntdev_grant_map *map,
-			      unsigned long start, unsigned long end,
-			      bool blockable)
-{
+	struct gntdev_grant_map *map =
+		container_of(mn, struct gntdev_grant_map, notifier);
 	unsigned long mstart, mend;
 	int err;
 
-	if (!in_range(map, start, end))
-		return 0;
+	if (!mmu_notifier_range_blockable(range))
+		return false;
 
-	if (!blockable)
-		return -EAGAIN;
+	/*
+	 * If the VMA is split or otherwise changed the notifier is not
+	 * updated, but we don't want to process VA's outside the modified
+	 * VMA. FIXME: It would be much more understandable to just prevent
+	 * modifying the VMA in the first place.
+	 */
+	if (map->vma->vm_start >= range->end ||
+	    map->vma->vm_end <= range->start)
+		return true;
 
-	mstart = max(start, map->vma->vm_start);
-	mend   = min(end,   map->vma->vm_end);
+	mstart = max(range->start, map->vma->vm_start);
+	mend = min(range->end, map->vma->vm_end);
 	pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n",
 			map->index, map->count,
 			map->vma->vm_start, map->vma->vm_end,
-			start, end, mstart, mend);
+			range->start, range->end, mstart, mend);
 	err = unmap_grant_pages(map,
 				(mstart - map->vma->vm_start) >> PAGE_SHIFT,
 				(mend - mstart) >> PAGE_SHIFT);
 	WARN_ON(err);
 
-	return 0;
+	return true;
 }
 
-static int mn_invl_range_start(struct mmu_notifier *mn,
-			       const struct mmu_notifier_range *range)
-{
-	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
-	struct gntdev_grant_map *map;
-	int ret = 0;
-
-	if (mmu_notifier_range_blockable(range))
-		mutex_lock(&priv->lock);
-	else if (!mutex_trylock(&priv->lock))
-		return -EAGAIN;
-
-	list_for_each_entry(map, &priv->maps, next) {
-		ret = unmap_if_in_range(map, range->start, range->end,
-					mmu_notifier_range_blockable(range));
-		if (ret)
-			goto out_unlock;
-	}
-	list_for_each_entry(map, &priv->freeable_maps, next) {
-		ret = unmap_if_in_range(map, range->start, range->end,
-					mmu_notifier_range_blockable(range));
-		if (ret)
-			goto out_unlock;
-	}
-
-out_unlock:
-	mutex_unlock(&priv->lock);
-
-	return ret;
-}
-
-static void mn_release(struct mmu_notifier *mn,
-		       struct mm_struct *mm)
-{
-	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
-	struct gntdev_grant_map *map;
-	int err;
-
-	mutex_lock(&priv->lock);
-	list_for_each_entry(map, &priv->maps, next) {
-		if (!map->vma)
-			continue;
-		pr_debug("map %d+%d (%lx %lx)\n",
-				map->index, map->count,
-				map->vma->vm_start, map->vma->vm_end);
-		err = unmap_grant_pages(map, /* offset */ 0, map->count);
-		WARN_ON(err);
-	}
-	list_for_each_entry(map, &priv->freeable_maps, next) {
-		if (!map->vma)
-			continue;
-		pr_debug("map %d+%d (%lx %lx)\n",
-				map->index, map->count,
-				map->vma->vm_start, map->vma->vm_end);
-		err = unmap_grant_pages(map, /* offset */ 0, map->count);
-		WARN_ON(err);
-	}
-	mutex_unlock(&priv->lock);
-}
-
-static const struct mmu_notifier_ops gntdev_mmu_ops = {
-	.release                = mn_release,
-	.invalidate_range_start = mn_invl_range_start,
+static const struct mmu_interval_notifier_ops gntdev_mmu_ops = {
+	.invalidate = gntdev_invalidate,
 };
 
 /* ------------------------------------------------------------------ */
···
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&priv->maps);
-	INIT_LIST_HEAD(&priv->freeable_maps);
 	mutex_init(&priv->lock);
 
 #ifdef CONFIG_XEN_GNTDEV_DMABUF
···
 		return ret;
 	}
 #endif
-
-	if (use_ptemod) {
-		priv->mm = get_task_mm(current);
-		if (!priv->mm) {
-			kfree(priv);
-			return -ENOMEM;
-		}
-		priv->mn.ops = &gntdev_mmu_ops;
-		ret = mmu_notifier_register(&priv->mn, priv->mm);
-		mmput(priv->mm);
-	}
 
 	if (ret) {
 		kfree(priv);
···
 		list_del(&map->next);
 		gntdev_put_map(NULL /* already removed */, map);
 	}
-	WARN_ON(!list_empty(&priv->freeable_maps));
 	mutex_unlock(&priv->lock);
 
 #ifdef CONFIG_XEN_GNTDEV_DMABUF
 	gntdev_dmabuf_fini(priv->dmabuf_priv);
 #endif
-
-	if (use_ptemod)
-		mmu_notifier_unregister(&priv->mn, priv->mm);
 
 	kfree(priv);
 	return 0;
···
 	map = gntdev_find_map_index(priv, op.index >> PAGE_SHIFT, op.count);
 	if (map) {
 		list_del(&map->next);
-		if (populate_freeable_maps)
-			list_add_tail(&map->next, &priv->freeable_maps);
 		err = 0;
 	}
 	mutex_unlock(&priv->lock);
···
 		goto unlock_out;
 	if (use_ptemod && map->vma)
 		goto unlock_out;
-	if (use_ptemod && priv->mm != vma->vm_mm) {
-		pr_warn("Huh? Other mm?\n");
-		goto unlock_out;
-	}
-
 	refcount_inc(&map->users);
 
 	vma->vm_ops = &gntdev_vmops;
···
 		vma->vm_flags |= VM_DONTCOPY;
 
 	vma->vm_private_data = map;
-
-	if (use_ptemod)
-		map->vma = vma;
-
 	if (map->flags) {
 		if ((vma->vm_flags & VM_WRITE) &&
 				(map->flags & GNTMAP_readonly))
···
 			map->flags |= GNTMAP_readonly;
 	}
 
+	if (use_ptemod) {
+		map->vma = vma;
+		err = mmu_interval_notifier_insert_locked(
+			&map->notifier, vma->vm_mm, vma->vm_start,
+			vma->vm_end - vma->vm_start, &gntdev_mmu_ops);
+		if (err)
+			goto out_unlock_put;
+	}
 	mutex_unlock(&priv->lock);
+
+	/*
+	 * gntdev takes the address of the PTE in find_grant_ptes() and passes
+	 * it to the hypervisor in gntdev_map_grant_pages(). The purpose of
+	 * the notifier is to prevent the hypervisor pointer to the PTE from
+	 * going stale.
+	 *
+	 * Since this vma's mappings can't be touched without the mmap_sem,
+	 * and we are holding it now, there is no need for the notifier_range
+	 * locking pattern.
+	 */
+	mmu_interval_read_begin(&map->notifier);
 
 	if (use_ptemod) {
 		map->pages_vm_start = vma->vm_start;
···
 	mutex_unlock(&priv->lock);
 out_put_map:
 	if (use_ptemod) {
-		map->vma = NULL;
 		unmap_grant_pages(map, 0, map->count);
+		if (map->vma) {
+			mmu_interval_notifier_remove(&map->notifier);
+			map->vma = NULL;
+		}
 	}
 	gntdev_put_map(priv, map);
 	return err;

include/linux/hmm.h

···
 #include <linux/kconfig.h>
 #include <asm/pgtable.h>
 
-#ifdef CONFIG_HMM_MIRROR
-
 #include <linux/device.h>
 #include <linux/migrate.h>
 #include <linux/memremap.h>
 #include <linux/completion.h>
 #include <linux/mmu_notifier.h>
-
-
-/*
- * struct hmm - HMM per mm struct
- *
- * @mm: mm struct this HMM struct is bound to
- * @lock: lock protecting ranges list
- * @ranges: list of range being snapshotted
- * @mirrors: list of mirrors for this mm
- * @mmu_notifier: mmu notifier to track updates to CPU page table
- * @mirrors_sem: read/write semaphore protecting the mirrors list
- * @wq: wait queue for user waiting on a range invalidation
- * @notifiers: count of active mmu notifiers
- */
-struct hmm {
-	struct mmu_notifier	mmu_notifier;
-	spinlock_t		ranges_lock;
-	struct list_head	ranges;
-	struct list_head	mirrors;
-	struct rw_semaphore	mirrors_sem;
-	wait_queue_head_t	wq;
-	long			notifiers;
-};
 
 /*
  * hmm_pfn_flag_e - HMM flag enums
···
 /*
  * struct hmm_range - track invalidation lock on virtual address range
  *
+ * @notifier: a mmu_interval_notifier that includes the start/end
+ * @notifier_seq: result of mmu_interval_read_begin()
  * @hmm: the core HMM structure this range is active against
  * @vma: the vm area struct for the range
  * @list: all range lock are on a list
···
  * @valid: pfns array did not change since it has been fill by an HMM function
  */
 struct hmm_range {
-	struct hmm		*hmm;
-	struct list_head	list;
+	struct mmu_interval_notifier *notifier;
+	unsigned long		notifier_seq;
 	unsigned long		start;
 	unsigned long		end;
 	uint64_t		*pfns;
···
 	uint64_t		default_flags;
 	uint64_t		pfn_flags_mask;
 	uint8_t			pfn_shift;
-	bool			valid;
 };
-
-/*
- * hmm_range_wait_until_valid() - wait for range to be valid
- * @range: range affected by invalidation to wait on
- * @timeout: time out for wait in ms (ie abort wait after that period of time)
- * Return: true if the range is valid, false otherwise.
- */
-static inline bool hmm_range_wait_until_valid(struct hmm_range *range,
-					      unsigned long timeout)
-{
-	return wait_event_timeout(range->hmm->wq, range->valid,
-				  msecs_to_jiffies(timeout)) != 0;
-}
-
-/*
- * hmm_range_valid() - test if a range is valid or not
- * @range: range
- * Return: true if the range is valid, false otherwise.
- */
-static inline bool hmm_range_valid(struct hmm_range *range)
-{
-	return range->valid;
-}
 
 /*
  * hmm_device_entry_to_page() - return struct page pointed to by a device entry
···
 }
 
 /*
- * Mirroring: how to synchronize device page table with CPU page table.
- *
- * A device driver that is participating in HMM mirroring must always
- * synchronize with CPU page table updates. For this, device drivers can either
- * directly use mmu_notifier APIs or they can use the hmm_mirror API. Device
- * drivers can decide to register one mirror per device per process, or just
- * one mirror per process for a group of devices. The pattern is:
- *
- *      int device_bind_address_space(..., struct mm_struct *mm, ...)
- *      {
- *          struct device_address_space *das;
- *
- *          // Device driver specific initialization, and allocation of das
- *          // which contains an hmm_mirror struct as one of its fields.
- *          ...
- *
- *          ret = hmm_mirror_register(&das->mirror, mm, &device_mirror_ops);
- *          if (ret) {
- *              // Cleanup on error
- *              return ret;
- *          }
- *
- *          // Other device driver specific initialization
- *          ...
- *      }
- *
- * Once an hmm_mirror is registered for an address space, the device driver
- * will get callbacks through sync_cpu_device_pagetables() operation (see
- * hmm_mirror_ops struct).
- *
- * Device driver must not free the struct containing the hmm_mirror struct
- * before calling hmm_mirror_unregister(). The expected usage is to do that when
- * the device driver is unbinding from an address space.
- *
- *
- *      void device_unbind_address_space(struct device_address_space *das)
- *      {
- *          // Device driver specific cleanup
- *          ...
- *
- *          hmm_mirror_unregister(&das->mirror);
- *
- *          // Other device driver specific cleanup, and now das can be freed
- *          ...
- *      }
- */
-
-struct hmm_mirror;
-
-/*
- * struct hmm_mirror_ops - HMM mirror device operations callback
- *
- * @update: callback to update range on a device
- */
-struct hmm_mirror_ops {
-	/* release() - release hmm_mirror
-	 *
-	 * @mirror: pointer to struct hmm_mirror
-	 *
-	 * This is called when the mm_struct is being released.  The callback
-	 * must ensure that all access to any pages obtained from this mirror
-	 * is halted before the callback returns. All future access should
-	 * fault.
-	 */
-	void (*release)(struct hmm_mirror *mirror);
-
-	/* sync_cpu_device_pagetables() - synchronize page tables
-	 *
-	 * @mirror: pointer to struct hmm_mirror
-	 * @update: update information (see struct mmu_notifier_range)
-	 * Return: -EAGAIN if mmu_notifier_range_blockable(update) is false
-	 * and callback needs to block, 0 otherwise.
-	 *
-	 * This callback ultimately originates from mmu_notifiers when the CPU
-	 * page table is updated. The device driver must update its page table
-	 * in response to this callback. The update argument tells what action
-	 * to perform.
-	 *
-	 * The device driver must not return from this callback until the device
-	 * page tables are completely updated (TLBs flushed, etc); this is a
-	 * synchronous call.
-	 */
-	int (*sync_cpu_device_pagetables)(
-		struct hmm_mirror *mirror,
-		const struct mmu_notifier_range *update);
-};
-
-/*
- * struct hmm_mirror - mirror struct for a device driver
- *
- * @hmm: pointer to struct hmm (which is unique per mm_struct)
- * @ops: device driver callback for HMM mirror operations
- * @list: for list of mirrors of a given mm
- *
- * Each address space (mm_struct) being mirrored by a device must register one
- * instance of an hmm_mirror struct with HMM. HMM will track the list of all
- * mirrors for each mm_struct.
- */
-struct hmm_mirror {
-	struct hmm			*hmm;
-	const struct hmm_mirror_ops	*ops;
-	struct list_head		list;
-};
-
-int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm);
-void hmm_mirror_unregister(struct hmm_mirror *mirror);
-
-/*
- * Please see Documentation/vm/hmm.rst for how to use the range API.
- */
-int hmm_range_register(struct hmm_range *range, struct hmm_mirror *mirror);
-void hmm_range_unregister(struct hmm_range *range);
-
-/*
  * Retry fault if non-blocking, drop mmap_sem and return -EAGAIN in that case.
  */
 #define HMM_FAULT_ALLOW_RETRY		(1 << 0)
···
 /* Don't fault in missing PTEs, just snapshot the current state. */
 #define HMM_FAULT_SNAPSHOT		(1 << 1)
 
+#ifdef CONFIG_HMM_MIRROR
+/*
+ * Please see Documentation/vm/hmm.rst for how to use the range API.
+ */
 long hmm_range_fault(struct hmm_range *range, unsigned int flags);
-
-long hmm_range_dma_map(struct hmm_range *range,
-		       struct device *device,
-		       dma_addr_t *daddrs,
-		       unsigned int flags);
-long hmm_range_dma_unmap(struct hmm_range *range,
-			 struct device *device,
-			 dma_addr_t *daddrs,
-			 bool dirty);
+#else
+static inline long hmm_range_fault(struct hmm_range *range, unsigned int flags)
+{
+	return -EOPNOTSUPP;
+}
+#endif
 
 /*
  * HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range
···
  * wait already.
  */
 #define HMM_RANGE_DEFAULT_TIMEOUT 1000
-
-#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
 
 #endif /* LINUX_HMM_H */

include/linux/mmu_notifier.h

···
 #include <linux/spinlock.h>
 #include <linux/mm_types.h>
 #include <linux/srcu.h>
+#include <linux/interval_tree.h>
 
+struct mmu_notifier_mm;
 struct mmu_notifier;
-struct mmu_notifier_ops;
+struct mmu_notifier_range;
+struct mmu_interval_notifier;
 
 /**
  * enum mmu_notifier_event - reason for the mmu notifier callback
···
  * access flags). User should soft dirty the page in the end callback to make
  * sure that anyone relying on soft dirtyness catch pages that might be written
  * through non CPU mappings.
+ *
+ * @MMU_NOTIFY_RELEASE: used during mmu_interval_notifier invalidate to signal
+ * that the mm refcount is zero and the range is no longer accessible.
  */
 enum mmu_notifier_event {
 	MMU_NOTIFY_UNMAP = 0,
···
 	MMU_NOTIFY_PROTECTION_VMA,
 	MMU_NOTIFY_PROTECTION_PAGE,
 	MMU_NOTIFY_SOFT_DIRTY,
-};
-
-#ifdef CONFIG_MMU_NOTIFIER
-
-#ifdef CONFIG_LOCKDEP
-extern struct lockdep_map __mmu_notifier_invalidate_range_start_map;
-#endif
-
-/*
- * The mmu notifier_mm structure is allocated and installed in
- * mm->mmu_notifier_mm inside the mm_take_all_locks() protected
- * critical section and it's released only when mm_count reaches zero
- * in mmdrop().
- */
-struct mmu_notifier_mm {
-	/* all mmu notifiers registerd in this mm are queued in this list */
-	struct hlist_head list;
-	/* to serialize the list modifications and hlist_unhashed */
-	spinlock_t lock;
+	MMU_NOTIFY_RELEASE,
 };
 
 #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0)
-
-struct mmu_notifier_range {
-	struct vm_area_struct *vma;
-	struct mm_struct *mm;
-	unsigned long start;
-	unsigned long end;
-	unsigned flags;
-	enum mmu_notifier_event event;
-};
 
 struct mmu_notifier_ops {
 	/*
···
 	unsigned int users;
 };
 
+/**
+ * struct mmu_interval_notifier_ops
+ * @invalidate: Upon return the caller must stop using any SPTEs within this
+ *              range. This function can sleep. Return false only if sleeping
+ *              was required but mmu_notifier_range_blockable(range) is false.
+ */
+struct mmu_interval_notifier_ops {
+	bool (*invalidate)(struct mmu_interval_notifier *mni,
+			   const struct mmu_notifier_range *range,
+			   unsigned long cur_seq);
+};
+
+struct mmu_interval_notifier {
+	struct interval_tree_node interval_tree;
+	const struct mmu_interval_notifier_ops *ops;
+	struct mm_struct *mm;
+	struct hlist_node deferred_item;
+	unsigned long invalidate_seq;
+};
+
+#ifdef CONFIG_MMU_NOTIFIER
+
+#ifdef CONFIG_LOCKDEP
+extern struct lockdep_map __mmu_notifier_invalidate_range_start_map;
+#endif
+
+struct mmu_notifier_range {
+	struct vm_area_struct *vma;
+	struct mm_struct *mm;
+	unsigned long start;
+	unsigned long end;
+	unsigned flags;
+	enum mmu_notifier_event event;
+};
+
 static inline int mm_has_notifiers(struct mm_struct *mm)
 {
 	return unlikely(mm->mmu_notifier_mm);
···
 				   struct mm_struct *mm);
 extern void mmu_notifier_unregister(struct mmu_notifier *mn,
 				    struct mm_struct *mm);
+
+unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *mni);
+int mmu_interval_notifier_insert(struct mmu_interval_notifier *mni,
+				 struct mm_struct *mm, unsigned long start,
+				 unsigned long length,
+				 const struct mmu_interval_notifier_ops *ops);
+int mmu_interval_notifier_insert_locked(
+	struct mmu_interval_notifier *mni, struct mm_struct *mm,
+	unsigned long start, unsigned long length,
+	const struct mmu_interval_notifier_ops *ops);
+void mmu_interval_notifier_remove(struct mmu_interval_notifier *mni);
+
+/**
+ * mmu_interval_set_seq - Save the invalidation sequence
+ * @mni - The mni passed to invalidate
+ * @cur_seq - The cur_seq passed to the invalidate() callback
+ *
+ * This must be called unconditionally from the invalidate callback of a
+ * struct mmu_interval_notifier_ops under the same lock that is used to call
+ * mmu_interval_read_retry(). It updates the sequence number for later use by
+ * mmu_interval_read_retry(). The provided cur_seq will always be odd.
+ *
+ * If the caller does not call mmu_interval_read_begin() or
+ * mmu_interval_read_retry() then this call is not required.
+ */
+static inline void mmu_interval_set_seq(struct mmu_interval_notifier *mni,
+					unsigned long cur_seq)
+{
+	WRITE_ONCE(mni->invalidate_seq, cur_seq);
+}
+
+/**
+ * mmu_interval_read_retry - End a read side critical section against a VA range
+ * mni: The range
+ * seq: The return of the paired mmu_interval_read_begin()
+ *
+ * This MUST be called under a user provided lock that is also held
+ * unconditionally by op->invalidate() when it calls mmu_interval_set_seq().
+ *
+ * Each call should be paired with a single mmu_interval_read_begin() and
+ * should be used to conclude the read side.
+ *
+ * Returns true if an invalidation collided with this critical section, and
+ * the caller should retry.
+ */
+static inline bool mmu_interval_read_retry(struct mmu_interval_notifier *mni,
+					   unsigned long seq)
+{
+	return mni->invalidate_seq != seq;
+}
+
+/**
+ * mmu_interval_check_retry - Test if a collision has occurred
+ * mni: The range
+ * seq: The return of the matching mmu_interval_read_begin()
+ *
+ * This can be used in the critical section between mmu_interval_read_begin()
+ * and mmu_interval_read_retry().  A return of true indicates an invalidation
+ * has collided with this critical region and a future
+ * mmu_interval_read_retry() will return true.
+ *
+ * False is not reliable and only suggests a collision may not have
+ * occured. It can be called many times and does not have to hold the user
+ * provided lock.
+ *
+ * This call can be used as part of loops and other expensive operations to
+ * expedite a retry.
+ */
+static inline bool mmu_interval_check_retry(struct mmu_interval_notifier *mni,
+					    unsigned long seq)
+{
+	/* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */
+	return READ_ONCE(mni->invalidate_seq) != seq;
+}
+
 extern void __mmu_notifier_mm_destroy(struct mm_struct *mm);
 extern void __mmu_notifier_release(struct mm_struct *mm);
 extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm,

include/rdma/ib_umem_odp.h

···
 
 #include <rdma/ib_umem.h>
 #include <rdma/ib_verbs.h>
-#include <linux/interval_tree.h>
 
 struct ib_umem_odp {
 	struct ib_umem umem;
-	struct ib_ucontext_per_mm *per_mm;
+	struct mmu_interval_notifier notifier;
+	struct pid *tgid;
 
 	/*
 	 * An array of the pages included in the on-demand paging umem.
···
 	struct mutex		umem_mutex;
 	void			*private; /* for the HW driver to use. */
 
-	int notifiers_seq;
-	int notifiers_count;
 	int npages;
-
-	/* Tree tracking */
-	struct interval_tree_node interval_tree;
 
 	/*
 	 * An implicit odp umem cannot be DMA mapped, has 0 length, and serves
···
 	 */
 	bool is_implicit_odp;
 
-	struct completion	notifier_completion;
 	unsigned int		page_shift;
 };
 
···
 /* Returns the first page of an ODP umem. */
 static inline unsigned long ib_umem_start(struct ib_umem_odp *umem_odp)
 {
-	return umem_odp->interval_tree.start;
+	return umem_odp->notifier.interval_tree.start;
 }
 
 /* Returns the address of the page after the last one of an ODP umem. */
 static inline unsigned long ib_umem_end(struct ib_umem_odp *umem_odp)
 {
-	return umem_odp->interval_tree.last + 1;
+	return umem_odp->notifier.interval_tree.last + 1;
 }
 
 static inline size_t ib_umem_odp_num_pages(struct ib_umem_odp *umem_odp)
···
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 
-struct ib_ucontext_per_mm {
-	struct mmu_notifier mn;
-	struct pid *tgid;
-
-	struct rb_root_cached umem_tree;
-	/* Protects umem_tree */
-	struct rw_semaphore umem_rwsem;
-};
-
-struct ib_umem_odp *ib_umem_odp_get(struct ib_udata *udata, unsigned long addr,
-				    size_t size, int access);
+struct ib_umem_odp *
+ib_umem_odp_get(struct ib_udata *udata, unsigned long addr, size_t size,
+		int access, const struct mmu_interval_notifier_ops *ops);
 struct ib_umem_odp *ib_umem_odp_alloc_implicit(struct ib_udata *udata,
 					       int access);
-struct ib_umem_odp *ib_umem_odp_alloc_child(struct ib_umem_odp *root_umem,
-					    unsigned long addr, size_t size);
+struct ib_umem_odp *
+ib_umem_odp_alloc_child(struct ib_umem_odp *root_umem, unsigned long addr,
+			size_t size,
+			const struct mmu_interval_notifier_ops *ops);
 void ib_umem_odp_release(struct ib_umem_odp *umem_odp);
 
 int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset,
···
 void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset,
 				 u64 bound);
 
-typedef int (*umem_call_back)(struct ib_umem_odp *item, u64 start, u64 end,
-			      void *cookie);
-/*
- * Call the callback on each ib_umem in the range. Returns the logical or of
- * the return values of the functions called.
- */
-int rbt_ib_umem_for_each_in_range(struct rb_root_cached *root,
-				  u64 start, u64 end,
-				  umem_call_back cb,
-				  bool blockable, void *cookie);
-
-static inline int ib_umem_mmu_notifier_retry(struct ib_umem_odp *umem_odp,
-					     unsigned long mmu_seq)
-{
-	/*
-	 * This code is strongly based on the KVM code from
-	 * mmu_notifier_retry. Should be called with
-	 * the relevant locks taken (umem_odp->umem_mutex
-	 * and the ucontext umem_mutex semaphore locked for read).
-	 */
-
-	if (unlikely(umem_odp->notifiers_count))
-		return 1;
-	if (umem_odp->notifiers_seq != mmu_seq)
-		return 1;
-	return 0;
-}
-
 #else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
-static inline struct ib_umem_odp *ib_umem_odp_get(struct ib_udata *udata,
-						  unsigned long addr,
-						  size_t size, int access)
+static inline struct ib_umem_odp *
+ib_umem_odp_get(struct ib_udata *udata, unsigned long addr, size_t size,
+		int access, const struct mmu_interval_notifier_ops *ops)
 {
 	return ERR_PTR(-EINVAL);
 }

include/rdma/ib_verbs.h

···
 			    u64 iova);
 	int (*unmap_fmr)(struct list_head *fmr_list);
 	int (*dealloc_fmr)(struct ib_fmr *fmr);
-	void (*invalidate_range)(struct ib_umem_odp *umem_odp,
-				 unsigned long start, unsigned long end);
 	int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid);
 	int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid);
 	struct ib_xrcd *(*alloc_xrcd)(struct ib_device *device,

kernel/fork.c

···
 #include <linux/binfmts.h>
 #include <linux/mman.h>
 #include <linux/mmu_notifier.h>
-#include <linux/hmm.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/vmacache.h>

mm/Kconfig

···
 config MMU_NOTIFIER
 	bool
 	select SRCU
+	select INTERVAL_TREE
 
 config KSM
 	bool "Enable KSM for page merging"
···
 config HMM_MIRROR
 	bool
 	depends on MMU
-	depends on MMU_NOTIFIER
 
 config DEVICE_PRIVATE
 	bool "Unaddressable device memory (GPU memory, ...)"

mm/hmm.c

···
 #include <linux/mmu_notifier.h>
 #include <linux/memory_hotplug.h>
 
-static struct mmu_notifier *hmm_alloc_notifier(struct mm_struct *mm)
-{
-	struct hmm *hmm;
-
-	hmm = kzalloc(sizeof(*hmm), GFP_KERNEL);
-	if (!hmm)
-		return ERR_PTR(-ENOMEM);
-
-	init_waitqueue_head(&hmm->wq);
-	INIT_LIST_HEAD(&hmm->mirrors);
-	init_rwsem(&hmm->mirrors_sem);
-	INIT_LIST_HEAD(&hmm->ranges);
-	spin_lock_init(&hmm->ranges_lock);
-	hmm->notifiers = 0;
-	return &hmm->mmu_notifier;
-}
-
-static void hmm_free_notifier(struct mmu_notifier *mn)
-{
-	struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
-
-	WARN_ON(!list_empty(&hmm->ranges));
-	WARN_ON(!list_empty(&hmm->mirrors));
-	kfree(hmm);
-}
-
-static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
-{
-	struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
-	struct hmm_mirror *mirror;
-
-	/*
-	 * Since hmm_range_register() holds the mmget() lock hmm_release() is
-	 * prevented as long as a range exists.
-	 */
-	WARN_ON(!list_empty_careful(&hmm->ranges));
-
-	down_read(&hmm->mirrors_sem);
-	list_for_each_entry(mirror, &hmm->mirrors, list) {
-		/*
-		 * Note: The driver is not allowed to trigger
-		 * hmm_mirror_unregister() from this thread.
-		 */
-		if (mirror->ops->release)
-			mirror->ops->release(mirror);
-	}
-	up_read(&hmm->mirrors_sem);
-}
-
-static void notifiers_decrement(struct hmm *hmm)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&hmm->ranges_lock, flags);
-	hmm->notifiers--;
-	if (!hmm->notifiers) {
-		struct hmm_range *range;
-
-		list_for_each_entry(range, &hmm->ranges, list) {
-			if (range->valid)
-				continue;
-			range->valid = true;
-		}
-		wake_up_all(&hmm->wq);
-	}
-	spin_unlock_irqrestore(&hmm->ranges_lock, flags);
-}
-
-static int hmm_invalidate_range_start(struct mmu_notifier *mn,
-			const struct mmu_notifier_range *nrange)
-{
-	struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
-	struct hmm_mirror *mirror;
-	struct hmm_range *range;
-	unsigned long flags;
-	int ret = 0;
-
-	spin_lock_irqsave(&hmm->ranges_lock, flags);
-	hmm->notifiers++;
-	list_for_each_entry(range, &hmm->ranges, list) {
-		if (nrange->end < range->start || nrange->start >= range->end)
-			continue;
-
-		range->valid = false;
-	}
-	spin_unlock_irqrestore(&hmm->ranges_lock, flags);
-
-	if (mmu_notifier_range_blockable(nrange))
-		down_read(&hmm->mirrors_sem);
-	else if (!down_read_trylock(&hmm->mirrors_sem)) {
-		ret = -EAGAIN;
-		goto out;
-	}
-
-	list_for_each_entry(mirror, &hmm->mirrors, list) {
-		int rc;
-
-		rc = mirror->ops->sync_cpu_device_pagetables(mirror, nrange);
-		if (rc) {
-			if (WARN_ON(mmu_notifier_range_blockable(nrange) ||
-			    rc != -EAGAIN))
-				continue;
-			ret = -EAGAIN;
-			break;
-		}
-	}
-	up_read(&hmm->mirrors_sem);
-
-out:
-	if (ret)
-		notifiers_decrement(hmm);
-	return ret;
-}
-
-static void hmm_invalidate_range_end(struct mmu_notifier *mn,
-			const struct mmu_notifier_range *nrange)
-{
-	struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
-
-	notifiers_decrement(hmm);
-}
-
-static const struct mmu_notifier_ops hmm_mmu_notifier_ops = {
-	.release		= hmm_release,
-	.invalidate_range_start	= hmm_invalidate_range_start,
-	.invalidate_range_end	= hmm_invalidate_range_end,
-	.alloc_notifier		= hmm_alloc_notifier,
-	.free_notifier		= hmm_free_notifier,
-};
-
-/*
- * hmm_mirror_register() - register a mirror against an mm
- *
- * @mirror: new mirror struct to register
- * @mm: mm to register against
- * Return: 0 on success, -ENOMEM if no memory, -EINVAL if invalid arguments
- *
- * To start mirroring a process address space, the device driver must register
- * an HMM mirror struct.
- *
- * The caller cannot unregister the hmm_mirror while any ranges are
- * registered.
- *
- * Callers using this function must put a call to mmu_notifier_synchronize()
- * in their module exit functions.
- */
-int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm)
-{
-	struct mmu_notifier *mn;
-
-	lockdep_assert_held_write(&mm->mmap_sem);
-
-	/* Sanity check */
-	if (!mm || !mirror || !mirror->ops)
-		return -EINVAL;
-
-	mn = mmu_notifier_get_locked(&hmm_mmu_notifier_ops, mm);
-	if (IS_ERR(mn))
-		return PTR_ERR(mn);
-	mirror->hmm = container_of(mn, struct hmm, mmu_notifier);
-
-	down_write(&mirror->hmm->mirrors_sem);
-	list_add(&mirror->list, &mirror->hmm->mirrors);
-	up_write(&mirror->hmm->mirrors_sem);
-
-	return 0;
-}
-EXPORT_SYMBOL(hmm_mirror_register);
-
-/*
- * hmm_mirror_unregister() - unregister a mirror
- *
- * @mirror: mirror struct to unregister
- *
- * Stop mirroring a process address space, and cleanup.
- */
-void hmm_mirror_unregister(struct hmm_mirror *mirror)
-{
-	struct hmm *hmm = mirror->hmm;
-
-	down_write(&hmm->mirrors_sem);
-	list_del(&mirror->list);
-	up_write(&hmm->mirrors_sem);
-	mmu_notifier_put(&hmm->mmu_notifier);
-}
-EXPORT_SYMBOL(hmm_mirror_unregister);
-
 struct hmm_vma_walk {
 	struct hmm_range	*range;
 	struct dev_pagemap	*pgmap;
···
 	return -EFAULT;
 }
 
-static int hmm_pfns_bad(unsigned long addr,
-			unsigned long end,
-			struct mm_walk *walk)
+static int hmm_pfns_fill(unsigned long addr, unsigned long end,
+		struct hmm_range *range, enum hmm_pfn_value_e value)
 {
-	struct hmm_vma_walk *hmm_vma_walk = walk->private;
-	struct hmm_range *range = hmm_vma_walk->range;
 	uint64_t *pfns = range->pfns;
 	unsigned long i;
 
 	i = (addr - range->start) >> PAGE_SHIFT;
 	for (; addr < end; addr += PAGE_SIZE, i++)
-		pfns[i] = range->values[HMM_PFN_ERROR];
+		pfns[i] = range->values[value];
 
 	return 0;
 }
···
 		if (unlikely(!hmm_vma_walk->pgmap))
 			return -EBUSY;
 	} else if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && pte_special(pte)) {
-		*pfn = range->values[HMM_PFN_SPECIAL];
-		return -EFAULT;
+		if (!is_zero_pfn(pte_pfn(pte))) {
+			*pfn = range->values[HMM_PFN_SPECIAL];
+			return -EFAULT;
+		}
+		/*
+		 * Since each architecture defines a struct page for the zero
+		 * page, just fall through and treat it like a normal page.
+		 */
 	}
 
 	*pfn = hmm_device_entry_from_pfn(range, pte_pfn(pte)) | cpu_flags;
···
 		}
 		return 0;
 	} else if (!pmd_present(pmd))
-		return hmm_pfns_bad(start, end, walk);
+		return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
 
 	if (pmd_devmap(pmd) || pmd_trans_huge(pmd)) {
 		/*
···
 	 * recover.
 	 */
 	if (pmd_bad(pmd))
-		return hmm_pfns_bad(start, end, walk);
+		return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
 
 	ptep = pte_offset_map(pmdp, addr);
 	i = (addr - range->start) >> PAGE_SHIFT;
···
 #define hmm_vma_walk_hugetlb_entry NULL
 #endif /* CONFIG_HUGETLB_PAGE */
 
-static void hmm_pfns_clear(struct hmm_range *range,
-			   uint64_t *pfns,
-			   unsigned long addr,
-			   unsigned long end)
+static int hmm_vma_walk_test(unsigned long start, unsigned long end,
+			     struct mm_walk *walk)
 {
-	for (; addr < end; addr += PAGE_SIZE, pfns++)
-		*pfns = range->values[HMM_PFN_NONE];
-}
-
-/*
- * hmm_range_register() - start tracking change to CPU page table over a range
- * @range: range
- * @mm: the mm struct for the range of virtual address
- *
- * Return: 0 on success, -EFAULT if the address space is no longer valid
- *
- * Track updates to the CPU page table see include/linux/hmm.h
- */
-int hmm_range_register(struct hmm_range *range, struct hmm_mirror *mirror)
-{
-	struct hmm *hmm = mirror->hmm;
-	unsigned long flags;
-
-	range->valid = false;
-	range->hmm = NULL;
-
-	if ((range->start & (PAGE_SIZE - 1)) || (range->end & (PAGE_SIZE - 1)))
-		return -EINVAL;
-	if (range->start >= range->end)
-		return -EINVAL;
-
-	/* Prevent hmm_release() from running while the range is valid */
-	if (!mmget_not_zero(hmm->mmu_notifier.mm))
-		return -EFAULT;
-
-	/* Initialize range to track CPU page table updates. */
-	spin_lock_irqsave(&hmm->ranges_lock, flags);
-
-	range->hmm = hmm;
-	list_add(&range->list, &hmm->ranges);
+	struct hmm_vma_walk *hmm_vma_walk = walk->private;
+	struct hmm_range *range = hmm_vma_walk->range;
+	struct vm_area_struct *vma = walk->vma;
 
 	/*
-	 * If there are any concurrent notifiers we have to wait for them for
-	 * the range to be valid (see hmm_range_wait_until_valid()).
+	 * Skip vma ranges that don't have struct page backing them or
+	 * map I/O devices directly.
 	 */
-	if (!hmm->notifiers)
-		range->valid = true;
-	spin_unlock_irqrestore(&hmm->ranges_lock, flags);
+	if (vma->vm_flags & (VM_IO | VM_PFNMAP | VM_MIXEDMAP))
+		return -EFAULT;
+
+	/*
+	 * If the vma does not allow read access, then assume that it does not
+	 * allow write access either. HMM does not support architectures
+	 * that allow write without read.
+	 */
+	if (!(vma->vm_flags & VM_READ)) {
+		bool fault, write_fault;
+
+		/*
+		 * Check to see if a fault is requested for any page in the
+		 * range.
+		 */
+		hmm_range_need_fault(hmm_vma_walk, range->pfns +
+					((start - range->start) >> PAGE_SHIFT),
+					(end - start) >> PAGE_SHIFT,
+					0, &fault, &write_fault);
+		if (fault || write_fault)
+			return -EFAULT;
+
+		hmm_pfns_fill(start, end, range, HMM_PFN_NONE);
+		hmm_vma_walk->last = end;
+
+		/* Skip this vma and continue processing the next vma. */
+		return 1;
+	}
 
 	return 0;
 }
-EXPORT_SYMBOL(hmm_range_register);
-
-/*
- * hmm_range_unregister() - stop tracking change to CPU page table over a range
- * @range: range
- *
- * Range struct is used to track updates to the CPU page table after a call to
- * hmm_range_register(). See include/linux/hmm.h for how to use it.
- */
-void hmm_range_unregister(struct hmm_range *range)
-{
-	struct hmm *hmm = range->hmm;
-	unsigned long flags;
-
-	spin_lock_irqsave(&hmm->ranges_lock, flags);
-	list_del_init(&range->list);
-	spin_unlock_irqrestore(&hmm->ranges_lock, flags);
-
-	/* Drop reference taken by hmm_range_register() */
-	mmput(hmm->mmu_notifier.mm);
-
-	/*
-	 * The range is now invalid and the ref on the hmm is dropped, so
-	 * poison the pointer.  Leave other fields in place, for the caller's
-	 * use.
-	 */
-	range->valid = false;
-	memset(&range->hmm, POISON_INUSE, sizeof(range->hmm));
-}
-EXPORT_SYMBOL(hmm_range_unregister);
 
 static const struct mm_walk_ops hmm_walk_ops = {
 	.pud_entry	= hmm_vma_walk_pud,
 	.pmd_entry	= hmm_vma_walk_pmd,
 	.pte_hole	= hmm_vma_walk_hole,
 	.hugetlb_entry	= hmm_vma_walk_hugetlb_entry,
+	.test_walk	= hmm_vma_walk_test,
 };
 
 /**
···
  */
 long hmm_range_fault(struct hmm_range *range, unsigned int flags)
 {
-	const unsigned long device_vma = VM_IO | VM_PFNMAP | VM_MIXEDMAP;
-	unsigned long start = range->start, end;
-	struct hmm_vma_walk hmm_vma_walk;
-	struct hmm *hmm = range->hmm;
-	struct vm_area_struct *vma;
+	struct hmm_vma_walk hmm_vma_walk = {
+		.range = range,
+		.last = range->start,
+		.flags = flags,
+	};
+	struct mm_struct *mm = range->notifier->mm;
 	int ret;
 
-	lockdep_assert_held(&hmm->mmu_notifier.mm->mmap_sem);
+	lockdep_assert_held(&mm->mmap_sem);
 
 	do {
 		/* If range is no longer valid force retry. */
-		if (!range->valid)
+		if (mmu_interval_check_retry(range->notifier,
+					     range->notifier_seq))
 			return -EBUSY;
+		ret = walk_page_range(mm, hmm_vma_walk.last, range->end,
+				      &hmm_walk_ops, &hmm_vma_walk);
+	} while (ret == -EBUSY);
 
-		vma = find_vma(hmm->mmu_notifier.mm, start);
-		if (vma == NULL || (vma->vm_flags & device_vma))
-			return -EFAULT;
-
-		if (!(vma->vm_flags & VM_READ)) {
-			/*
-			 * If vma do not allow read access, then assume that it
-			 * does not allow write access, either. HMM does not
-			 * support architecture that allow write without read.
-			 */
-			hmm_pfns_clear(range, range->pfns,
-				range->start, range->end);
-			return -EPERM;
-		}
-
-		hmm_vma_walk.pgmap = NULL;
-		hmm_vma_walk.last = start;
-		hmm_vma_walk.flags = flags;
-		hmm_vma_walk.range = range;
-		end = min(range->end, vma->vm_end);
-
-		walk_page_range(vma->vm_mm, start, end, &hmm_walk_ops,
-				&hmm_vma_walk);
-
-		do {
-			ret = walk_page_range(vma->vm_mm, start, end,
-					&hmm_walk_ops, &hmm_vma_walk);
-			start = hmm_vma_walk.last;
-
-			/* Keep trying while the range is valid. */
-		} while (ret == -EBUSY && range->valid);
-
-		if (ret) {
-			unsigned long i;
-
-			i = (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
-			hmm_pfns_clear(range, &range->pfns[i],
-				hmm_vma_walk.last, range->end);
-			return ret;
-		}
-		start = end;
-
-	} while (start < range->end);
-
+	if (ret)
+		return ret;
 	return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
 }
 EXPORT_SYMBOL(hmm_range_fault);
-
-/**
- * hmm_range_dma_map - hmm_range_fault() and dma map page all in one.
- * @range:	range being faulted
- * @device:	device to map page to
- * @daddrs:	array of dma addresses for the mapped pages
- * @flags:	HMM_FAULT_*
- *
- * Return: the number of pages mapped on success (including zero), or any
- * status return from hmm_range_fault() otherwise.
- */
-long hmm_range_dma_map(struct hmm_range *range, struct device *device,
-		dma_addr_t *daddrs, unsigned int flags)
-{
-	unsigned long i, npages, mapped;
-	long ret;
-
-	ret = hmm_range_fault(range, flags);
-	if (ret <= 0)
-		return ret ? ret : -EBUSY;
-
-	npages = (range->end - range->start) >> PAGE_SHIFT;
-	for (i = 0, mapped = 0; i < npages; ++i) {
-		enum dma_data_direction dir = DMA_TO_DEVICE;
-		struct page *page;
-
-		/*
-		 * FIXME need to update DMA API to provide invalid DMA address
-		 * value instead of a function to test dma address value. This
-		 * would remove lot of dumb code duplicated accross many arch.
-		 *
-		 * For now setting it to 0 here is good enough as the pfns[]
-		 * value is what is use to check what is valid and what isn't.
-		 */
-		daddrs[i] = 0;
-
-		page = hmm_device_entry_to_page(range, range->pfns[i]);
-		if (page == NULL)
-			continue;
-
-		/* Check if range is being invalidated */
-		if (!range->valid) {
-			ret = -EBUSY;
-			goto unmap;
-		}
-
-		/* If it is read and write than map bi-directional. */
-		if (range->pfns[i] & range->flags[HMM_PFN_WRITE])
-			dir = DMA_BIDIRECTIONAL;
-
-		daddrs[i] = dma_map_page(device, page, 0, PAGE_SIZE, dir);
-		if (dma_mapping_error(device, daddrs[i])) {
-			ret = -EFAULT;
-			goto unmap;
-		}
-
-		mapped++;
-	}
-
-	return mapped;
-
-unmap:
-	for (npages = i, i = 0; (i < npages) && mapped; ++i) {
-		enum dma_data_direction dir = DMA_TO_DEVICE;
-		struct page *page;
-
-		page = hmm_device_entry_to_page(range, range->pfns[i]);
-		if (page == NULL)
-			continue;
-
-		if (dma_mapping_error(device, daddrs[i]))
-			continue;
-
-		/* If it is read and write than map bi-directional. */
-		if (range->pfns[i] & range->flags[HMM_PFN_WRITE])
-			dir = DMA_BIDIRECTIONAL;
-
-		dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir);
-		mapped--;
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL(hmm_range_dma_map);
-
-/**
- * hmm_range_dma_unmap() - unmap range of that was map with hmm_range_dma_map()
- * @range: range being unmapped
- * @device: device against which dma map was done
- * @daddrs: dma address of mapped pages
- * @dirty: dirty page if it had the write flag set
- * Return: number of page unmapped on success, -EINVAL otherwise
- *
- * Note that caller MUST abide by mmu notifier or use HMM mirror and abide
- * to the sync_cpu_device_pagetables() callback so that it is safe here to
- * call set_page_dirty(). Caller must also take appropriate locks to avoid
- * concurrent mmu notifier or sync_cpu_device_pagetables() to make progress.
- */
-long hmm_range_dma_unmap(struct hmm_range *range,
-			 struct device *device,
-			 dma_addr_t *daddrs,
-			 bool dirty)
-{
-	unsigned long i, npages;
-	long cpages = 0;
-
-	/* Sanity check. */
-	if (range->end <= range->start)
-		return -EINVAL;
-	if (!daddrs)
-		return -EINVAL;
-	if (!range->pfns)
-		return -EINVAL;
-
-	npages = (range->end - range->start) >> PAGE_SHIFT;
-	for (i = 0; i < npages; ++i) {
-		enum dma_data_direction dir = DMA_TO_DEVICE;
-		struct page *page;
-
-		page = hmm_device_entry_to_page(range, range->pfns[i]);
-		if (page == NULL)
-			continue;
-
-		/* If it is read and write than map bi-directional. */
-		if (range->pfns[i] & range->flags[HMM_PFN_WRITE]) {
-			dir = DMA_BIDIRECTIONAL;
-
-			/*
-			 * See comments in function description on why it is
-			 * safe here to call set_page_dirty()
-			 */
-			if (dirty)
-				set_page_dirty(page);
-		}
-
-		/* Unmap and clear pfns/dma address */
-		dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir);
-		range->pfns[i] = range->values[HMM_PFN_NONE];
-		/* FIXME see comments in hmm_vma_dma_map() */
-		daddrs[i] = 0;
-		cpages++;
-	}
-
-	return cpages;
-}
-EXPORT_SYMBOL(hmm_range_dma_unmap);

mm/mmu_notifier.c

···
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/err.h>
+#include <linux/interval_tree.h>
 #include <linux/srcu.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
···
 #endif
 
 /*
+ * The mmu notifier_mm structure is allocated and installed in
+ * mm->mmu_notifier_mm inside the mm_take_all_locks() protected
+ * critical section and it's released only when mm_count reaches zero
+ * in mmdrop().
+ */
+struct mmu_notifier_mm {
+	/* all mmu notifiers registered in this mm are queued in this list */
+	struct hlist_head list;
+	bool has_itree;
+	/* to serialize the list modifications and hlist_unhashed */
+	spinlock_t lock;
+	unsigned long invalidate_seq;
+	unsigned long active_invalidate_ranges;
+	struct rb_root_cached itree;
+	wait_queue_head_t wq;
+	struct hlist_head deferred_list;
+};
+
+/*
+ * This is a collision-retry read-side/write-side 'lock', a lot like a
+ * seqcount, however this allows multiple write-sides to hold it at
+ * once. Conceptually the write side is protecting the values of the PTEs in
+ * this mm, such that PTES cannot be read into SPTEs (shadow PTEs) while any
+ * writer exists.
+ *
+ * Note that the core mm creates nested invalidate_range_start()/end() regions
+ * within the same thread, and runs invalidate_range_start()/end() in parallel
+ * on multiple CPUs. This is designed to not reduce concurrency or block
+ * progress on the mm side.
+ *
+ * As a secondary function, holding the full write side also serves to prevent
+ * writers for the itree, this is an optimization to avoid extra locking
+ * during invalidate_range_start/end notifiers.
+ *
+ * The write side has two states, fully excluded:
+ *  - mm->active_invalidate_ranges != 0
+ *  - mnn->invalidate_seq & 1 == True (odd)
+ *  - some range on the mm_struct is being invalidated
+ *  - the itree is not allowed to change
+ *
+ * And partially excluded:
+ *  - mm->active_invalidate_ranges != 0
+ *  - mnn->invalidate_seq & 1 == False (even)
+ *  - some range on the mm_struct is being invalidated
+ *  - the itree is allowed to change
+ *
+ * Operations on mmu_notifier_mm->invalidate_seq (under spinlock):
+ *    seq |= 1  # Begin writing
+ *    seq++     # Release the writing state
+ *    seq & 1   # True if a writer exists
+ *
+ * The later state avoids some expensive work on inv_end in the common case of
+ * no mni monitoring the VA.
+ */
+static bool mn_itree_is_invalidating(struct mmu_notifier_mm *mmn_mm)
+{
+	lockdep_assert_held(&mmn_mm->lock);
+	return mmn_mm->invalidate_seq & 1;
+}
+
+static struct mmu_interval_notifier *
+mn_itree_inv_start_range(struct mmu_notifier_mm *mmn_mm,
+			 const struct mmu_notifier_range *range,
+			 unsigned long *seq)
+{
+	struct interval_tree_node *node;
+	struct mmu_interval_notifier *res = NULL;
+
+	spin_lock(&mmn_mm->lock);
+	mmn_mm->active_invalidate_ranges++;
+	node = interval_tree_iter_first(&mmn_mm->itree, range->start,
+					range->end - 1);
+	if (node) {
+		mmn_mm->invalidate_seq |= 1;
+		res = container_of(node, struct mmu_interval_notifier,
+				   interval_tree);
+	}
+
+	*seq = mmn_mm->invalidate_seq;
+	spin_unlock(&mmn_mm->lock);
+	return res;
+}
+
+static struct mmu_interval_notifier *
+mn_itree_inv_next(struct mmu_interval_notifier *mni,
+		  const struct mmu_notifier_range *range)
+{
+	struct interval_tree_node *node;
+
+	node = interval_tree_iter_next(&mni->interval_tree, range->start,
+				       range->end - 1);
+	if (!node)
+		return NULL;
+	return container_of(node, struct mmu_interval_notifier, interval_tree);
+}
+
+static void mn_itree_inv_end(struct mmu_notifier_mm *mmn_mm)
+{
+	struct mmu_interval_notifier *mni;
+	struct hlist_node *next;
+
+	spin_lock(&mmn_mm->lock);
+	if (--mmn_mm->active_invalidate_ranges ||
+	    !mn_itree_is_invalidating(mmn_mm)) {
+		spin_unlock(&mmn_mm->lock);
+		return;
+	}
+
+	/* Make invalidate_seq even */
+	mmn_mm->invalidate_seq++;
+
+	/*
+	 * The inv_end incorporates a deferred mechanism like rtnl_unlock().
+	 * Adds and removes are queued until the final inv_end happens then
+	 * they are progressed. This arrangement for tree updates is used to
+	 * avoid using a blocking lock during invalidate_range_start.
+	 */
+	hlist_for_each_entry_safe(mni, next, &mmn_mm->deferred_list,
+				  deferred_item) {
+		if (RB_EMPTY_NODE(&mni->interval_tree.rb))
+			interval_tree_insert(&mni->interval_tree,
+					     &mmn_mm->itree);
+		else
+			interval_tree_remove(&mni->interval_tree,
+					     &mmn_mm->itree);
+		hlist_del(&mni->deferred_item);
+	}
+	spin_unlock(&mmn_mm->lock);
+
+	wake_up_all(&mmn_mm->wq);
+}
+
+/**
+ * mmu_interval_read_begin - Begin a read side critical section against a VA
+ *                           range
+ * mni: The range to use
+ *
+ * mmu_iterval_read_begin()/mmu_iterval_read_retry() implement a
+ * collision-retry scheme similar to seqcount for the VA range under mni. If
+ * the mm invokes invalidation during the critical section then
+ * mmu_interval_read_retry() will return true.
+ *
+ * This is useful to obtain shadow PTEs where teardown or setup of the SPTEs
+ * require a blocking context.  The critical region formed by this can sleep,
+ * and the required 'user_lock' can also be a sleeping lock.
+ *
+ * The caller is required to provide a 'user_lock' to serialize both teardown
+ * and setup.
+ *
+ * The return value should be passed to mmu_interval_read_retry().
+ */
+unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *mni)
+{
+	struct mmu_notifier_mm *mmn_mm = mni->mm->mmu_notifier_mm;
+	unsigned long seq;
+	bool is_invalidating;
+
+	/*
+	 * If the mni has a different seq value under the user_lock than we
+	 * started with then it has collided.
+	 *
+	 * If the mni currently has the same seq value as the mmn_mm seq, then
+	 * it is currently between invalidate_start/end and is colliding.
+	 *
+	 * The locking looks broadly like this:
+	 *   mn_tree_invalidate_start():          mmu_interval_read_begin():
+	 *                                         spin_lock
+	 *                                          seq = READ_ONCE(mni->invalidate_seq);
+	 *                                          seq == mmn_mm->invalidate_seq
+	 *                                         spin_unlock
+	 *    spin_lock
+	 *     seq = ++mmn_mm->invalidate_seq
+	 *    spin_unlock
+	 *     op->invalidate_range():
+	 *       user_lock
+	 *        mmu_interval_set_seq()
+	 *         mni->invalidate_seq = seq
+	 *       user_unlock
+	 *
+	 *                          [Required: mmu_interval_read_retry() == true]
+	 *
+	 *   mn_itree_inv_end():
+	 *    spin_lock
+	 *     seq = ++mmn_mm->invalidate_seq
+	 *    spin_unlock
+	 *
+	 *                                        user_lock
+	 *                                         mmu_interval_read_retry():
+	 *                                          mni->invalidate_seq != seq
+	 *                                        user_unlock
+	 *
+	 * Barriers are not needed here as any races here are closed by an
+	 * eventual mmu_interval_read_retry(), which provides a barrier via the
+	 * user_lock.
+	 */
+	spin_lock(&mmn_mm->lock);
+	/* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */
+	seq = READ_ONCE(mni->invalidate_seq);
+	is_invalidating = seq == mmn_mm->invalidate_seq;
+	spin_unlock(&mmn_mm->lock);
+
+	/*
+	 * mni->invalidate_seq must always be set to an odd value via
+	 * mmu_interval_set_seq() using the provided cur_seq from
+	 * mn_itree_inv_start_range(). This ensures that if seq does wrap we
+	 * will always clear the below sleep in some reasonable time as
+	 * mmn_mm->invalidate_seq is even in the idle state.
+	 */
+	lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
+	lock_map_release(&__mmu_notifier_invalidate_range_start_map);
+	if (is_invalidating)
+		wait_event(mmn_mm->wq,
+			   READ_ONCE(mmn_mm->invalidate_seq) != seq);
+
+	/*
+	 * Notice that mmu_interval_read_retry() can already be true at this
+	 * point, avoiding loops here allows the caller to provide a global
+	 * time bound.
+	 */
+
+	return seq;
+}
+EXPORT_SYMBOL_GPL(mmu_interval_read_begin);
+
+static void mn_itree_release(struct mmu_notifier_mm *mmn_mm,
+			     struct mm_struct *mm)
+{
+	struct mmu_notifier_range range = {
+		.flags = MMU_NOTIFIER_RANGE_BLOCKABLE,
+		.event = MMU_NOTIFY_RELEASE,
+		.mm = mm,
+		.start = 0,
+		.end = ULONG_MAX,
+	};
+	struct mmu_interval_notifier *mni;
+	unsigned long cur_seq;
+	bool ret;
+
+	for (mni = mn_itree_inv_start_range(mmn_mm, &range, &cur_seq); mni;
+	     mni = mn_itree_inv_next(mni, &range)) {
+		ret = mni->ops->invalidate(mni, &range, cur_seq);
+		WARN_ON(!ret);
+	}
+
+	mn_itree_inv_end(mmn_mm);
+}
+
+/*
  * This function can't run concurrently against mmu_notifier_register
  * because mm->mm_users > 0 during mmu_notifier_register and exit_mmap
  * runs with mm_users == 0. Other tasks may still invoke mmu notifiers
···
  * can't go away from under us as exit_mmap holds an mm_count pin
  * itself.
  */
-void __mmu_notifier_release(struct mm_struct *mm)
+static void mn_hlist_release(struct mmu_notifier_mm *mmn_mm,
+			     struct mm_struct *mm)
 {
 	struct mmu_notifier *mn;
 	int id;
···
 	 * ->release returns.
 	 */
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist)
+	hlist_for_each_entry_rcu(mn, &mmn_mm->list, hlist)
 		/*
 		 * If ->release runs before mmu_notifier_unregister it must be
 		 * handled, as it's the only way for the driver to flush all
···
 		if (mn->ops->release)
 			mn->ops->release(mn, mm);
 
-	spin_lock(&mm->mmu_notifier_mm->lock);
-	while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) {
-		mn = hlist_entry(mm->mmu_notifier_mm->list.first,
-				 struct mmu_notifier,
+	spin_lock(&mmn_mm->lock);
+	while (unlikely(!hlist_empty(&mmn_mm->list))) {
+		mn = hlist_entry(mmn_mm->list.first, struct mmu_notifier,
 				 hlist);
 		/*
 		 * We arrived before mmu_notifier_unregister so
···
 		 */
 		hlist_del_init_rcu(&mn->hlist);
 	}
-	spin_unlock(&mm->mmu_notifier_mm->lock);
+	spin_unlock(&mmn_mm->lock);
 	srcu_read_unlock(&srcu, id);
 
 	/*
···
 	 * is held by exit_mmap.
 	 */
 	synchronize_srcu(&srcu);
+}
+
+void __mmu_notifier_release(struct mm_struct *mm)
+{
+	struct mmu_notifier_mm *mmn_mm = mm->mmu_notifier_mm;
+
+	if (mmn_mm->has_itree)
+		mn_itree_release(mmn_mm, mm);
+
+	if (!hlist_empty(&mmn_mm->list))
+		mn_hlist_release(mmn_mm, mm);
 }
 
 /*
···
 	srcu_read_unlock(&srcu, id);
 }
 
-int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range)
+static int mn_itree_invalidate(struct mmu_notifier_mm *mmn_mm,
+			       const struct mmu_notifier_range *range)
+{
+	struct mmu_interval_notifier *mni;
+	unsigned long cur_seq;
+
+	for (mni = mn_itree_inv_start_range(mmn_mm, range, &cur_seq); mni;
+	     mni = mn_itree_inv_next(mni, range)) {
+		bool ret;
+
+		ret = mni->ops->invalidate(mni, range, cur_seq);
+		if (!ret) {
+			if (WARN_ON(mmu_notifier_range_blockable(range)))
+				continue;
+			goto out_would_block;
+		}
+	}
+	return 0;
+
+out_would_block:
+	/*
+	 * On -EAGAIN the non-blocking caller is not allowed to call
+	 * invalidate_range_end()
+	 */
+	mn_itree_inv_end(mmn_mm);
+	return -EAGAIN;
+}
+
+static int mn_hlist_invalidate_range_start(struct mmu_notifier_mm *mmn_mm,
+					   struct mmu_notifier_range *range)
 {
 	struct mmu_notifier *mn;
 	int ret = 0;
 	int id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, &range->mm->mmu_notifier_mm->list, hlist) {
+	hlist_for_each_entry_rcu(mn, &mmn_mm->list, hlist) {
 		if (mn->ops->invalidate_range_start) {
 			int _ret;
 
···
 	return ret;
 }
 
-void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range,
-					 bool only_end)
+int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range)
+{
+	struct mmu_notifier_mm *mmn_mm = range->mm->mmu_notifier_mm;
+	int ret;
+
+	if (mmn_mm->has_itree) {
+		ret = mn_itree_invalidate(mmn_mm, range);
+		if (ret)
+			return ret;
+	}
+	if (!hlist_empty(&mmn_mm->list))
+		return mn_hlist_invalidate_range_start(mmn_mm, range);
+	return 0;
+}
+
+static void mn_hlist_invalidate_end(struct mmu_notifier_mm *mmn_mm,
+				    struct mmu_notifier_range *range,
+				    bool only_end)
 {
 	struct mmu_notifier *mn;
 	int id;
 
-	lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, &range->mm->mmu_notifier_mm->list, hlist) {
+	hlist_for_each_entry_rcu(mn, &mmn_mm->list, hlist) {
 		/*
 		 * Call invalidate_range here too to avoid the need for the
 		 * subsystem of having to register an invalidate_range_end
···
 		}
 	}
 	srcu_read_unlock(&srcu, id);
+}
+
+void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range,
+					 bool only_end)
+{
+	struct mmu_notifier_mm *mmn_mm = range->mm->mmu_notifier_mm;
+
+	lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
+	if (mmn_mm->has_itree)
+		mn_itree_inv_end(mmn_mm);
+
+	if (!hlist_empty(&mmn_mm->list))
+		mn_hlist_invalidate_end(mmn_mm, range, only_end);
 	lock_map_release(&__mmu_notifier_invalidate_range_start_map);
 }
 
···
 }
 
 /*
- * Same as mmu_notifier_register but here the caller must hold the
- * mmap_sem in write mode.
+ * Same as mmu_notifier_register but here the caller must hold the mmap_sem in
+ * write mode. A NULL mn signals the notifier is being registered for itree
+ * mode.
  */
 int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm)
 {
···
 		fs_reclaim_release(GFP_KERNEL);
 	}
 
-	mn->mm = mm;
-	mn->users = 1;
-
 	if (!mm->mmu_notifier_mm) {
 		/*
 		 * kmalloc cannot be called under mm_take_all_locks(), but we
···
 		 * the write side of the mmap_sem.
 		 */
 		mmu_notifier_mm =
-			kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL);
+			kzalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL);
 		if (!mmu_notifier_mm)
 			return -ENOMEM;
 
 		INIT_HLIST_HEAD(&mmu_notifier_mm->list);
 		spin_lock_init(&mmu_notifier_mm->lock);
+		mmu_notifier_mm->invalidate_seq = 2;
+		mmu_notifier_mm->itree = RB_ROOT_CACHED;
+		init_waitqueue_head(&mmu_notifier_mm->wq);
+		INIT_HLIST_HEAD(&mmu_notifier_mm->deferred_list);
 	}
 
 	ret = mm_take_all_locks(mm);
 	if (unlikely(ret))
 		goto out_clean;
-
-	/* Pairs with the mmdrop in mmu_notifier_unregister_* */
-	mmgrab(mm);
 
 	/*
 	 * Serialize the update against mmu_notifier_unregister. A
···
 	 * current->mm or explicitly with get_task_mm() or similar).
 	 * We can't race against any other mmu notifier method either
 	 * thanks to mm_take_all_locks().
+	 *
+	 * release semantics on the initialization of the mmu_notifier_mm's
+	 * contents are provided for unlocked readers.  acquire can only be
+	 * used while holding the mmgrab or mmget, and is safe because once
+	 * created the mmu_notififer_mm is not freed until the mm is
+	 * destroyed.  As above, users holding the mmap_sem or one of the
+	 * mm_take_all_locks() do not need to use acquire semantics.
 	 */
 	if (mmu_notifier_mm)
-		mm->mmu_notifier_mm = mmu_notifier_mm;
+		smp_store_release(&mm->mmu_notifier_mm, mmu_notifier_mm);
 
-	spin_lock(&mm->mmu_notifier_mm->lock);
-	hlist_add_head_rcu(&mn->hlist, &mm->mmu_notifier_mm->list);
-	spin_unlock(&mm->mmu_notifier_mm->lock);
+	if (mn) {
+		/* Pairs with the mmdrop in mmu_notifier_unregister_* */
+		mmgrab(mm);
+		mn->mm = mm;
+		mn->users = 1;
+
+		spin_lock(&mm->mmu_notifier_mm->lock);
+		hlist_add_head_rcu(&mn->hlist, &mm->mmu_notifier_mm->list);
+		spin_unlock(&mm->mmu_notifier_mm->lock);
+	} else
+		mm->mmu_notifier_mm->has_itree = true;
 
 	mm_drop_all_locks(mm);
 	BUG_ON(atomic_read(&mm->mm_users) <= 0);
···
 	spin_unlock(&mm->mmu_notifier_mm->lock);
 }
 EXPORT_SYMBOL_GPL(mmu_notifier_put);
+
+static int __mmu_interval_notifier_insert(
+	struct mmu_interval_notifier *mni, struct mm_struct *mm,
+	struct mmu_notifier_mm *mmn_mm, unsigned long start,
+	unsigned long length, const struct mmu_interval_notifier_ops *ops)
+{
+	mni->mm = mm;
+	mni->ops = ops;
+	RB_CLEAR_NODE(&mni->interval_tree.rb);
+	mni->interval_tree.start = start;
+	/*
+	 * Note that the representation of the intervals in the interval tree
+	 * considers the ending point as contained in the interval.
+	 */
+	if (length == 0 ||
+	    check_add_overflow(start, length - 1, &mni->interval_tree.last))
+		return -EOVERFLOW;
+
+	/* Must call with a mmget() held */
+	if (WARN_ON(atomic_read(&mm->mm_count) <= 0))
+		return -EINVAL;
+
+	/* pairs with mmdrop in mmu_interval_notifier_remove() */
+	mmgrab(mm);
+
+	/*
+	 * If some invalidate_range_start/end region is going on in parallel
+	 * we don't know what VA ranges are affected, so we must assume this
+	 * new range is included.
+	 *
+	 * If the itree is invalidating then we are not allowed to change
+	 * it. Retrying until invalidation is done is tricky due to the
+	 * possibility for live lock, instead defer the add to
+	 * mn_itree_inv_end() so this algorithm is deterministic.
+	 *
+	 * In all cases the value for the mni->invalidate_seq should be
+	 * odd, see mmu_interval_read_begin()
+	 */
+	spin_lock(&mmn_mm->lock);
+	if (mmn_mm->active_invalidate_ranges) {
+		if (mn_itree_is_invalidating(mmn_mm))
+			hlist_add_head(&mni->deferred_item,
+				       &mmn_mm->deferred_list);
+		else {
+			mmn_mm->invalidate_seq |= 1;
+			interval_tree_insert(&mni->interval_tree,
+					     &mmn_mm->itree);
+		}
+		mni->invalidate_seq = mmn_mm->invalidate_seq;
+	} else {
+		WARN_ON(mn_itree_is_invalidating(mmn_mm));
+		/*
+		 * The starting seq for a mni not under invalidation should be
+		 * odd, not equal to the current invalidate_seq and
+		 * invalidate_seq should not 'wrap' to the new seq any time
+		 * soon.
+		 */
+		mni->invalidate_seq = mmn_mm->invalidate_seq - 1;
+		interval_tree_insert(&mni->interval_tree, &mmn_mm->itree);
+	}
+	spin_unlock(&mmn_mm->lock);
+	return 0;
+}
+
+/**
+ * mmu_interval_notifier_insert - Insert an interval notifier
+ * @mni: Interval notifier to register
+ * @start: Starting virtual address to monitor
+ * @length: Length of the range to monitor
+ * @mm : mm_struct to attach to
+ *
+ * This function subscribes the interval notifier for notifications from the
+ * mm.  Upon return the ops related to mmu_interval_notifier will be called
+ * whenever an event that intersects with the given range occurs.
+ *
+ * Upon return the range_notifier may not be present in the interval tree yet.
+ * The caller must use the normal interval notifier read flow via
+ * mmu_interval_read_begin() to establish SPTEs for this range.
+ */
+int mmu_interval_notifier_insert(struct mmu_interval_notifier *mni,
+				 struct mm_struct *mm, unsigned long start,
+				 unsigned long length,
+				 const struct mmu_interval_notifier_ops *ops)
+{
+	struct mmu_notifier_mm *mmn_mm;
+	int ret;
+
+	might_lock(&mm->mmap_sem);
+
+	mmn_mm = smp_load_acquire(&mm->mmu_notifier_mm);
+	if (!mmn_mm || !mmn_mm->has_itree) {
+		ret = mmu_notifier_register(NULL, mm);
+		if (ret)
+			return ret;
+		mmn_mm = mm->mmu_notifier_mm;
+	}
+	return __mmu_interval_notifier_insert(mni, mm, mmn_mm, start, length,
+					      ops);
+}
+EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert);
+
+int mmu_interval_notifier_insert_locked(
+	struct mmu_interval_notifier *mni, struct mm_struct *mm,
+	unsigned long start, unsigned long length,
+	const struct mmu_interval_notifier_ops *ops)
+{
+	struct mmu_notifier_mm *mmn_mm;
+	int ret;
+
+	lockdep_assert_held_write(&mm->mmap_sem);
+
+	mmn_mm = mm->mmu_notifier_mm;
+	if (!mmn_mm || !mmn_mm->has_itree) {
+		ret = __mmu_notifier_register(NULL, mm);
+		if (ret)
+			return ret;
+		mmn_mm = mm->mmu_notifier_mm;
+	}
+	return __mmu_interval_notifier_insert(mni, mm, mmn_mm, start, length,
+					      ops);
+}
+EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert_locked);
+
+/**
+ * mmu_interval_notifier_remove - Remove a interval notifier
+ * @mni: Interval notifier to unregister
+ *
+ * This function must be paired with mmu_interval_notifier_insert(). It cannot
+ * be called from any ops callback.
+ *
+ * Once this returns ops callbacks are no longer running on other CPUs and
+ * will not be called in future.
+ */
+void mmu_interval_notifier_remove(struct mmu_interval_notifier *mni)
+{
+	struct mm_struct *mm = mni->mm;
+	struct mmu_notifier_mm *mmn_mm = mm->mmu_notifier_mm;
+	unsigned long seq = 0;
+
+	might_sleep();
+
+	spin_lock(&mmn_mm->lock);
+	if (mn_itree_is_invalidating(mmn_mm)) {
+		/*
+		 * remove is being called after insert put this on the
+		 * deferred list, but before the deferred list was processed.
+		 */
+		if (RB_EMPTY_NODE(&mni->interval_tree.rb)) {
+			hlist_del(&mni->deferred_item);
+		} else {
+			hlist_add_head(&mni->deferred_item,
+				       &mmn_mm->deferred_list);
+			seq = mmn_mm->invalidate_seq;
+		}
+	} else {
+		WARN_ON(RB_EMPTY_NODE(&mni->interval_tree.rb));
+		interval_tree_remove(&mni->interval_tree, &mmn_mm->itree);
+	}
+	spin_unlock(&mmn_mm->lock);
+
+	/*
+	 * The possible sleep on progress in the invalidation requires the
+	 * caller not hold any locks held by invalidation callbacks.
+	 */
+	lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
+	lock_map_release(&__mmu_notifier_invalidate_range_start_map);
+	if (seq)
+		wait_event(mmn_mm->wq,
+			   READ_ONCE(mmn_mm->invalidate_seq) != seq);
+
+	/* pairs with mmgrab in mmu_interval_notifier_insert() */
+	mmdrop(mm);
+}
+EXPORT_SYMBOL_GPL(mmu_interval_notifier_remove);
 
 /**
  * mmu_notifier_synchronize - Ensure all mmu_notifiers are freed