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

8 files changed, 169 insertions, 512 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index bcc5d40a8d5f..0c229a92a24b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -967,6 +967,8 @@ struct amdgpu_device {
 	struct mutex  lock_reset;
 	struct amdgpu_doorbell_index doorbell_index;
 
+	struct mutex			notifier_lock;
+
 	int asic_reset_res;
 	struct work_struct		xgmi_reset_work;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index ae6f5446262c..7d35b5b66229 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -505,8 +505,7 @@ static void remove_kgd_mem_from_kfd_bo_list(struct kgd_mem *mem,
  *
  * 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;
@@ -1199,7 +1198,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	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;
 	}
@@ -1744,6 +1743,10 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
 			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
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index a169ff16277f..5ca905b4a0fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -538,8 +538,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 		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);
@@ -1219,11 +1217,11 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	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.
@@ -1266,13 +1264,13 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	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);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 4f76beafb2fa..c17505fba988 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2794,6 +2794,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	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);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index 392300f77b13..828b5167ff12 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -51,439 +51,107 @@
 #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 (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, start, end))
-			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);
-	}
-}
-
-/**
- * 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;
+	if (!mmu_notifier_range_blockable(range))
+		return false;
 
-	/* notification is exclusive, but interval is inclusive */
-	end -= 1;
+	mutex_lock(&adev->notifier_lock);
 
-	/* 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;
+	mmu_interval_set_seq(mni, cur_seq);
 
-	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;
+	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;
 }
 
-/* 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;
-
-	mutex_lock(&adev->mn_lock);
-	if (down_write_killable(&mm->mmap_sem)) {
-		mutex_unlock(&adev->mn_lock);
-		return ERR_PTR(-EINTR);
-	}
-
-	hash_for_each_possible(adev->mn_hash, amn, node, key)
-		if (AMDGPU_MN_KEY(amn->mm, amn->type) == key)
-			goto release_locks;
-
-	amn = kzalloc(sizeof(*amn), GFP_KERNEL);
-	if (!amn) {
-		amn = ERR_PTR(-ENOMEM);
-		goto release_locks;
-	}
-
-	amn->adev = adev;
-	amn->mm = mm;
-	init_rwsem(&amn->lock);
-	amn->type = type;
-	amn->objects = RB_ROOT_CACHED;
-
-	amn->mirror.ops = &amdgpu_hmm_mirror_ops[type];
-	r = hmm_mirror_register(&amn->mirror, mm);
-	if (r)
-		goto free_amn;
+	struct amdgpu_bo *bo = container_of(mni, struct amdgpu_bo, notifier);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 
-	hash_add(adev->mn_hash, &amn->node, AMDGPU_MN_KEY(mm, type));
+	if (!mmu_notifier_range_blockable(range))
+		return false;
 
-release_locks:
-	up_write(&mm->mmap_sem);
-	mutex_unlock(&adev->mn_lock);
+	mutex_lock(&adev->notifier_lock);
 
-	return amn;
+	mmu_interval_set_seq(mni, cur_seq);
 
-free_amn:
-	up_write(&mm->mmap_sem);
-	mutex_unlock(&adev->mn_lock);
-	kfree(amn);
+	amdgpu_amdkfd_evict_userptr(bo->kfd_bo, bo->notifier.mm);
+	mutex_unlock(&adev->notifier_lock);
 
-	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;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
index b8ed68943625..a292238f75eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
@@ -30,63 +30,10 @@
 #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, "
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 7e99f6c58c48..36dec51d1ef1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -30,6 +30,9 @@
 
 #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
@@ -101,10 +104,12 @@ struct amdgpu_bo {
 	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;
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 61d9b7774d42..2616e2eafdeb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -35,6 +35,7 @@
 #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>
@@ -769,6 +770,20 @@ struct amdgpu_ttm_tt {
 #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
@@ -776,85 +791,89 @@ struct amdgpu_ttm_tt {
  * 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 */
-		return -ESRCH;
-
-	if (unlikely(!mirror)) {
-		DRM_DEBUG_DRIVER("Failed to get hmm_mirror\n");
-		r = -EFAULT;
-		goto out;
+	mm = bo->notifier.mm;
+	if (unlikely(!mm)) {
+		DRM_DEBUG_DRIVER("BO is not registered?\n");
+		return -EFAULT;
 	}
 
-	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;
-	}
+	/* 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;
 
 	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;
-
-	hmm_range_register(range, mirror);
+	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);
 
-	/*
-	 * 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;
@@ -862,15 +881,18 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 	}
 
 	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;
 }
 
@@ -895,15 +917,18 @@ bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm)
 		"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
 
@@ -984,10 +1009,18 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
 	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
 }