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

@@ -147,49 +147,16 @@ Address space mirroring implementation and API
 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,
+ 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::
@@ -216,70 +183,46 @@ The usage pattern is::
       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);
+          if (ret == -EBUSY)
                  goto again;
-          }
-          hmm_range_unregister(&range);
           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

@@ -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;
 

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

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);

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);
 

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, "

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;
+
+#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

@@ -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
 }
 

drivers/gpu/drm/radeon/radeon.h

@@ -68,6 +68,10 @@
 #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>
@@ -509,8 +513,9 @@ struct radeon_bo {
 	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

@@ -36,77 +36,37 @@
 
 #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;
-
-	/* notification is exclusive, but interval is inclusive */
-	end = range->end - 1;
-
-	/* 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;
-
-	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;
+		return true;
+
+	if (!mmu_notifier_range_blockable(range))
+		return false;
 
 	r = radeon_bo_reserve(bo, true);
 	if (r) {
 		DRM_ERROR("(%ld) failed to reserve user bo\n", r);
-				continue;
+		return true;
 	}
 
-			r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv,
-				true, false, MAX_SCHEDULE_TIMEOUT);
+	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);
 
@@ -116,51 +76,11 @@ static int radeon_mn_invalidate_range_start(struct mmu_notifier *mn,
 		DRM_ERROR("(%ld) failed to validate user bo\n", r);
 
 	radeon_bo_unreserve(bo);
-		}
-	}
-	
-out_unlock:
-	mutex_unlock(&rmn->lock);
-
-	return ret;
+	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,
 };
 
 /**
@@ -174,51 +94,20 @@ static const struct mmu_notifier_ops radeon_mn_ops = {
  */
 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;
-
-	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);
-
-	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;
-		}
-	}
+	int ret;
 
-	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);
+	ret = mmu_interval_notifier_insert(&bo->notifier, current->mm, addr,
+					   radeon_bo_size(bo), &radeon_mn_ops);
+	if (ret)
+		return ret;
 
+	/*
+	 * 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;
 }
 
@@ -231,27 +120,8 @@ int radeon_mn_register(struct radeon_bo *bo, unsigned long addr)
  */
 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

@@ -2634,7 +2634,6 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	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/hw/hfi1/file_ops.c

@@ -1138,7 +1138,7 @@ static int get_ctxt_info(struct hfi1_filedata *fd, unsigned long arg, u32 len)
 			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

@@ -1444,7 +1444,7 @@ struct hfi1_filedata {
 	/* 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

@@ -59,11 +59,11 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd,
 			      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,
@@ -73,10 +73,8 @@ static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
 			      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,
 };
 
 /*
@@ -87,7 +85,6 @@ static struct mmu_rb_ops tid_rb_ops = {
 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);
@@ -109,20 +106,7 @@ int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd,
 			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;
 	}
 
 	/*
@@ -139,7 +123,7 @@ int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd,
 	 * 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;
@@ -158,18 +142,10 @@ void hfi1_user_exp_rcv_free(struct hfi1_filedata *fd)
 {
 	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);
-	}
 
 	kfree(fd->invalid_tids);
 	fd->invalid_tids = NULL;
@@ -201,7 +177,7 @@ static void unpin_rcv_pages(struct hfi1_filedata *fd,
 
 	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];
@@ -777,8 +753,7 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd,
 		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;
@@ -787,23 +762,35 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd,
 	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 (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;
 
-	if (ret) {
+	hfi1_put_tid(dd, rcventry, PT_EXPECTED, phys, ilog2(npages) + 1);
+	trace_hfi1_exp_tid_reg(uctxt->ctxt, fd->subctxt, rcventry, npages,
+			       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->mmu.addr, node->phys, ret);
+		  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;
-	}
-	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);
-	return 0;
 }
 
 static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
@@ -833,10 +820,9 @@ static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
 	if (grp)
 		*grp = node->grp;
 
-	if (!fd->handler)
+	if (fd->use_mn)
+		mmu_interval_notifier_remove(&node->notifier);
 	cacheless_tid_rb_remove(fd, node);
-	else
-		hfi1_mmu_rb_remove(fd->handler, &node->mmu);
 
 	return 0;
 }
@@ -847,7 +833,8 @@ static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node)
 	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);
 
 	/*
@@ -894,30 +881,29 @@ static void unlock_exp_tids(struct hfi1_ctxtdata *uctxt,
 				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;
 
@@ -946,18 +932,7 @@ static int tid_rb_invalidate(void *arg, struct mmu_rb_node *mnode)
 		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,
@@ -968,12 +943,3 @@ 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

@@ -65,7 +65,8 @@ struct tid_user_buf {
 };
 
 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

@@ -1258,8 +1258,6 @@ int mlx5_ib_odp_init_one(struct mlx5_ib_dev *ibdev);
 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);
@@ -1289,11 +1287,10 @@ mlx5_ib_advise_mr_prefetch(struct ib_pd *pd,
 {
 	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,
 		      const struct mlx5_ib_profile *profile,

drivers/infiniband/hw/mlx5/mr.c

@@ -749,7 +749,8 @@ static int mr_umem_get(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 	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

@@ -241,18 +241,27 @@ static void destroy_unused_implicit_child_mr(struct mlx5_ib_mr *mr)
 	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.
@@ -261,8 +270,8 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
 		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
@@ -319,8 +328,13 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
 		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)
 {
 	struct ib_odp_caps *caps = &dev->odp_caps;
@@ -419,7 +433,7 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr,
 
 	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);
 
@@ -606,8 +620,9 @@ static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *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;
 
@@ -619,12 +634,7 @@ static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *odp,
 	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);
@@ -632,7 +642,7 @@ static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *odp,
 		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
@@ -662,19 +672,6 @@ static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *odp,
 	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;
 }
 
@@ -1622,7 +1619,6 @@ void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent)
 
 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

@@ -21,15 +21,8 @@ struct gntdev_dmabuf_priv;
 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. */
@@ -49,6 +42,7 @@ struct gntdev_unmap_notify {
 };
 
 struct gntdev_grant_map {
+	struct mmu_interval_notifier notifier;
 	struct list_head next;
 	struct vm_area_struct *vma;
 	int index;

drivers/xen/gntdev.c

@@ -63,7 +63,6 @@ MODULE_PARM_DESC(limit, "Maximum number of grants that may be mapped by "
 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);
@@ -249,12 +248,6 @@ void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map)
 		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)
 		unmap_grant_pages(map, 0, map->count);
 	gntdev_free_map(map);
@@ -444,16 +437,9 @@ static void gntdev_vma_close(struct vm_area_struct *vma)
 
 	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);
@@ -475,109 +461,44 @@ static const struct vm_operations_struct gntdev_vmops = {
 
 /* ------------------------------------------------------------------ */
 
-static bool in_range(struct gntdev_grant_map *map,
-			      unsigned long start, unsigned long end)
-{
-	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)
+static bool gntdev_invalidate(struct mmu_interval_notifier *mn,
+			      const struct mmu_notifier_range *range,
+			      unsigned long cur_seq)
 {
+	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;
-}
-
-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);
+	return true;
 }
 
-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,
 };
 
 /* ------------------------------------------------------------------ */
@@ -592,7 +513,6 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&priv->maps);
-	INIT_LIST_HEAD(&priv->freeable_maps);
 	mutex_init(&priv->lock);
 
 #ifdef CONFIG_XEN_GNTDEV_DMABUF
@@ -604,17 +524,6 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 	}
 #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);
 		return ret;
@@ -644,16 +553,12 @@ static int gntdev_release(struct inode *inode, struct file *flip)
 		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;
 }
@@ -714,8 +619,6 @@ static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv,
 	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);
@@ -1087,11 +990,6 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 		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;
@@ -1102,10 +1000,6 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 		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))
@@ -1116,8 +1010,28 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 			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;
 		err = apply_to_page_range(vma->vm_mm, vma->vm_start,
@@ -1166,8 +1080,11 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 	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

@@ -62,37 +62,12 @@
 #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
  *
@@ -145,6 +120,8 @@ enum hmm_pfn_value_e {
 /*
  * 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
@@ -159,8 +136,8 @@ enum hmm_pfn_value_e {
  * @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;
@@ -169,32 +146,8 @@ struct hmm_range {
 	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
  * @range: range use to decode device entry value
@@ -264,120 +217,6 @@ static inline uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range,
 		range->flags[HMM_PFN_VALID];
 }
 
-/*
- * 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.
  */
@@ -386,16 +225,17 @@ void hmm_range_unregister(struct hmm_range *range);
 /* 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
@@ -406,6 +246,4 @@ long hmm_range_dma_unmap(struct hmm_range *range,
  */
 #define HMM_RANGE_DEFAULT_TIMEOUT 1000
 
-#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
-
 #endif /* LINUX_HMM_H */

include/linux/mmu_notifier.h

@@ -6,9 +6,12 @@
 #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
@@ -31,6 +34,9 @@ struct mmu_notifier_ops;
  * 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,
@@ -38,38 +44,11 @@ enum mmu_notifier_event {
 	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 {
 	/*
 	 * Called either by mmu_notifier_unregister or when the mm is
@@ -249,6 +228,41 @@ struct mmu_notifier {
 	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);
@@ -275,6 +289,81 @@ extern int __mmu_notifier_register(struct mmu_notifier *mn,
 				   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

@@ -35,11 +35,11 @@
 
 #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.
@@ -62,13 +62,8 @@ struct ib_umem_odp {
 	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
 	 * only as an anchor for the driver to hold onto the per_mm. FIXME:
@@ -77,7 +72,6 @@ struct ib_umem_odp {
 	 */
 	bool is_implicit_odp;
 
-	struct completion	notifier_completion;
 	unsigned int		page_shift;
 };
 
@@ -89,13 +83,13 @@ static inline struct ib_umem_odp *to_ib_umem_odp(struct ib_umem *umem)
 /* 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)
@@ -119,21 +113,15 @@ 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,
@@ -143,39 +131,11 @@ 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

@@ -2451,8 +2451,6 @@ struct ib_device_ops {
 			    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

@@ -40,7 +40,6 @@
 #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

@@ -284,6 +284,7 @@ config VIRT_TO_BUS
 config MMU_NOTIFIER
 	bool
 	select SRCU
+	select INTERVAL_TREE
 
 config KSM
 	bool "Enable KSM for page merging"
@@ -674,7 +675,6 @@ config DEV_PAGEMAP_OPS
 config HMM_MIRROR
 	bool
 	depends on MMU
-	depends on MMU_NOTIFIER
 
 config DEVICE_PRIVATE
 	bool "Unaddressable device memory (GPU memory, ...)"