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

Pull hmm updates from Jason Gunthorpe:
 "This series adds a selftest for hmm_range_fault() and several of the
  DEVICE_PRIVATE migration related actions, and another simplification
  for hmm_range_fault()'s API.

   - Simplify hmm_range_fault() with a simpler return code, no
     HMM_PFN_SPECIAL, and no customizable output PFN format

   - Add a selftest for hmm_range_fault() and DEVICE_PRIVATE related
     functionality"

* tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  MAINTAINERS: add HMM selftests
  mm/hmm/test: add selftests for HMM
  mm/hmm/test: add selftest driver for HMM
  mm/hmm: remove the customizable pfn format from hmm_range_fault
  mm/hmm: remove HMM_PFN_SPECIAL
  drm/amdgpu: remove dead code after hmm_range_fault()
  mm/hmm: make hmm_range_fault return 0 or -1

Documentation/vm/hmm.rst

@@ -161,7 +161,7 @@ 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::
 
-  long hmm_range_fault(struct hmm_range *range);
+  int hmm_range_fault(struct hmm_range *range);
 
 It will trigger a page fault on missing or read-only entries if write access is
 requested (see below). Page faults use the generic mm page fault code path just
@@ -184,10 +184,7 @@ The usage pattern is::
       range.notifier = &interval_sub;
       range.start = ...;
       range.end = ...;
-      range.pfns = ...;
-      range.flags = ...;
-      range.values = ...;
-      range.pfn_shift = ...;
+      range.hmm_pfns = ...;
 
       if (!mmget_not_zero(interval_sub->notifier.mm))
           return -EFAULT;
@@ -229,15 +226,10 @@ The hmm_range struct has 2 fields, default_flags and pfn_flags_mask, that specif
 fault or snapshot policy for the whole range instead of having to set them
 for each entry in the pfns array.
 
-For instance, if the device flags for range.flags are::
+For instance if the device driver wants pages for a range with at least read
+permission, it sets::
 
-    range.flags[HMM_PFN_VALID] = (1 << 63);
-    range.flags[HMM_PFN_WRITE] = (1 << 62);
-
-and the device driver wants pages for a range with at least read permission,
-it sets::
-
-    range->default_flags = (1 << 63);
+    range->default_flags = HMM_PFN_REQ_FAULT;
     range->pfn_flags_mask = 0;
 
 and calls hmm_range_fault() as described above. This will fill fault all pages
@@ -246,18 +238,18 @@ in the range with at least read permission.
 Now let's say the driver wants to do the same except for one page in the range for
 which it wants to have write permission. Now driver set::
 
-    range->default_flags = (1 << 63);
-    range->pfn_flags_mask = (1 << 62);
-    range->pfns[index_of_write] = (1 << 62);
+    range->default_flags = HMM_PFN_REQ_FAULT;
+    range->pfn_flags_mask = HMM_PFN_REQ_WRITE;
+    range->pfns[index_of_write] = HMM_PFN_REQ_WRITE;
 
 With this, HMM will fault in all pages with at least read (i.e., valid) and for the
 address == range->start + (index_of_write << PAGE_SHIFT) it will fault with
 write permission i.e., if the CPU pte does not have write permission set then HMM
 will call handle_mm_fault().
 
-Note that HMM will populate the pfns array with write permission for any page
-that is mapped with CPU write permission no matter what values are set
-in default_flags or pfn_flags_mask.
+After hmm_range_fault completes the flag bits are set to the current state of
+the page tables, ie HMM_PFN_VALID | HMM_PFN_WRITE will be set if the page is
+writable.
 
 
 Represent and manage device memory from core kernel point of view

MAINTAINERS

@@ -7768,7 +7768,9 @@ L:	linux-mm@kvack.org
 S:	Maintained
 F:	Documentation/vm/hmm.rst
 F:	include/linux/hmm*
+F:	lib/test_hmm*
 F:	mm/hmm*
+F:	tools/testing/selftests/vm/*hmm*
 
 HOST AP DRIVER
 M:	Jouni Malinen <j@w1.fi>

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

@@ -766,18 +766,6 @@ struct amdgpu_ttm_tt {
 };
 
 #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 */
-};
-
-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
@@ -816,18 +804,15 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 		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];
+	range->default_flags = HMM_PFN_REQ_FAULT;
 	if (!amdgpu_ttm_tt_is_readonly(ttm))
-		range->default_flags |= range->flags[HMM_PFN_WRITE];
+		range->default_flags |= HMM_PFN_REQ_WRITE;
 
-	range->pfns = kvmalloc_array(ttm->num_pages, sizeof(*range->pfns),
-				     GFP_KERNEL);
-	if (unlikely(!range->pfns)) {
+	range->hmm_pfns = kvmalloc_array(ttm->num_pages,
+					 sizeof(*range->hmm_pfns), GFP_KERNEL);
+	if (unlikely(!range->hmm_pfns)) {
 		r = -ENOMEM;
 		goto out_free_ranges;
 	}
@@ -852,27 +837,23 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 	down_read(&mm->mmap_sem);
 	r = hmm_range_fault(range);
 	up_read(&mm->mmap_sem);
-	if (unlikely(r <= 0)) {
+	if (unlikely(r)) {
 		/*
 		 * FIXME: This timeout should encompass the retry from
 		 * mmu_interval_read_retry() as well.
 		 */
-		if ((r == 0 || r == -EBUSY) && !time_after(jiffies, timeout))
+		if (r == -EBUSY && !time_after(jiffies, timeout))
 			goto retry;
 		goto out_free_pfns;
 	}
 
-	for (i = 0; i < ttm->num_pages; 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, range->pfns[i]);
-			r = -ENOMEM;
-
-			goto out_free_pfns;
-		}
-	}
+	/*
+	 * Due to default_flags, all pages are HMM_PFN_VALID or
+	 * hmm_range_fault() fails. FIXME: The pages cannot be touched outside
+	 * the notifier_lock, and mmu_interval_read_retry() must be done first.
+	 */
+	for (i = 0; i < ttm->num_pages; i++)
+		pages[i] = hmm_pfn_to_page(range->hmm_pfns[i]);
 
 	gtt->range = range;
 	mmput(mm);
@@ -882,7 +863,7 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 out_unlock:
 	up_read(&mm->mmap_sem);
 out_free_pfns:
-	kvfree(range->pfns);
+	kvfree(range->hmm_pfns);
 out_free_ranges:
 	kfree(range);
 out:
@@ -907,7 +888,7 @@ bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm)
 	DRM_DEBUG_DRIVER("user_pages_done 0x%llx pages 0x%lx\n",
 		gtt->userptr, ttm->num_pages);
 
-	WARN_ONCE(!gtt->range || !gtt->range->pfns,
+	WARN_ONCE(!gtt->range || !gtt->range->hmm_pfns,
 		"No user pages to check\n");
 
 	if (gtt->range) {
@@ -917,7 +898,7 @@ bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm)
 		 */
 		r = mmu_interval_read_retry(gtt->range->notifier,
 					 gtt->range->notifier_seq);
-		kvfree(gtt->range->pfns);
+		kvfree(gtt->range->hmm_pfns);
 		kfree(gtt->range);
 		gtt->range = NULL;
 	}
@@ -1008,8 +989,7 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
 
 		for (i = 0; i < ttm->num_pages; i++) {
 			if (ttm->pages[i] !=
-				hmm_device_entry_to_page(gtt->range,
-					      gtt->range->pfns[i]))
+			    hmm_pfn_to_page(gtt->range->hmm_pfns[i]))
 				break;
 		}
 

drivers/gpu/drm/nouveau/nouveau_dmem.c

@@ -85,7 +85,7 @@ static inline struct nouveau_dmem *page_to_dmem(struct page *page)
 	return container_of(page->pgmap, struct nouveau_dmem, pagemap);
 }
 
-static unsigned long nouveau_dmem_page_addr(struct page *page)
+unsigned long nouveau_dmem_page_addr(struct page *page)
 {
 	struct nouveau_dmem_chunk *chunk = page->zone_device_data;
 	unsigned long idx = page_to_pfn(page) - chunk->pfn_first;
@@ -671,28 +671,3 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm,
 out:
 	return ret;
 }
-
-void
-nouveau_dmem_convert_pfn(struct nouveau_drm *drm,
-			 struct hmm_range *range)
-{
-	unsigned long i, npages;
-
-	npages = (range->end - range->start) >> PAGE_SHIFT;
-	for (i = 0; i < npages; ++i) {
-		struct page *page;
-		uint64_t addr;
-
-		page = hmm_device_entry_to_page(range, range->pfns[i]);
-		if (page == NULL)
-			continue;
-
-		if (!is_device_private_page(page))
-			continue;
-
-		addr = nouveau_dmem_page_addr(page);
-		range->pfns[i] &= ((1UL << range->pfn_shift) - 1);
-		range->pfns[i] |= (addr >> PAGE_SHIFT) << range->pfn_shift;
-		range->pfns[i] |= NVIF_VMM_PFNMAP_V0_VRAM;
-	}
-}

drivers/gpu/drm/nouveau/nouveau_dmem.h

@@ -37,9 +37,8 @@ int nouveau_dmem_migrate_vma(struct nouveau_drm *drm,
 			     struct vm_area_struct *vma,
 			     unsigned long start,
 			     unsigned long end);
+unsigned long nouveau_dmem_page_addr(struct page *page);
 
-void nouveau_dmem_convert_pfn(struct nouveau_drm *drm,
-			      struct hmm_range *range);
 #else /* IS_ENABLED(CONFIG_DRM_NOUVEAU_SVM) */
 static inline void nouveau_dmem_init(struct nouveau_drm *drm) {}
 static inline void nouveau_dmem_fini(struct nouveau_drm *drm) {}

drivers/gpu/drm/nouveau/nouveau_svm.c

@@ -369,19 +369,6 @@ nouveau_svmm_init(struct drm_device *dev, void *data,
 	return ret;
 }
 
-static const u64
-nouveau_svm_pfn_flags[HMM_PFN_FLAG_MAX] = {
-	[HMM_PFN_VALID         ] = NVIF_VMM_PFNMAP_V0_V,
-	[HMM_PFN_WRITE         ] = NVIF_VMM_PFNMAP_V0_W,
-};
-
-static const u64
-nouveau_svm_pfn_values[HMM_PFN_VALUE_MAX] = {
-	[HMM_PFN_ERROR  ] = ~NVIF_VMM_PFNMAP_V0_V,
-	[HMM_PFN_NONE   ] =  NVIF_VMM_PFNMAP_V0_NONE,
-	[HMM_PFN_SPECIAL] = ~NVIF_VMM_PFNMAP_V0_V,
-};
-
 /* Issue fault replay for GPU to retry accesses that faulted previously. */
 static void
 nouveau_svm_fault_replay(struct nouveau_svm *svm)
@@ -519,9 +506,45 @@ static const struct mmu_interval_notifier_ops nouveau_svm_mni_ops = {
 	.invalidate = nouveau_svm_range_invalidate,
 };
 
+static void nouveau_hmm_convert_pfn(struct nouveau_drm *drm,
+				    struct hmm_range *range, u64 *ioctl_addr)
+{
+	unsigned long i, npages;
+
+	/*
+	 * The ioctl_addr prepared here is passed through nvif_object_ioctl()
+	 * to an eventual DMA map in something like gp100_vmm_pgt_pfn()
+	 *
+	 * This is all just encoding the internal hmm representation into a
+	 * different nouveau internal representation.
+	 */
+	npages = (range->end - range->start) >> PAGE_SHIFT;
+	for (i = 0; i < npages; ++i) {
+		struct page *page;
+
+		if (!(range->hmm_pfns[i] & HMM_PFN_VALID)) {
+			ioctl_addr[i] = 0;
+			continue;
+		}
+
+		page = hmm_pfn_to_page(range->hmm_pfns[i]);
+		if (is_device_private_page(page))
+			ioctl_addr[i] = nouveau_dmem_page_addr(page) |
+					NVIF_VMM_PFNMAP_V0_V |
+					NVIF_VMM_PFNMAP_V0_VRAM;
+		else
+			ioctl_addr[i] = page_to_phys(page) |
+					NVIF_VMM_PFNMAP_V0_V |
+					NVIF_VMM_PFNMAP_V0_HOST;
+		if (range->hmm_pfns[i] & HMM_PFN_WRITE)
+			ioctl_addr[i] |= NVIF_VMM_PFNMAP_V0_W;
+	}
+}
+
 static int nouveau_range_fault(struct nouveau_svmm *svmm,
 			       struct nouveau_drm *drm, void *data, u32 size,
-			       u64 *pfns, struct svm_notifier *notifier)
+			       unsigned long hmm_pfns[], u64 *ioctl_addr,
+			       struct svm_notifier *notifier)
 {
 	unsigned long timeout =
 		jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
@@ -530,26 +553,27 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm,
 		.notifier = &notifier->notifier,
 		.start = notifier->notifier.interval_tree.start,
 		.end = notifier->notifier.interval_tree.last + 1,
-		.pfns = pfns,
-		.flags = nouveau_svm_pfn_flags,
-		.values = nouveau_svm_pfn_values,
-		.pfn_shift = NVIF_VMM_PFNMAP_V0_ADDR_SHIFT,
+		.pfn_flags_mask = HMM_PFN_REQ_FAULT | HMM_PFN_REQ_WRITE,
+		.hmm_pfns = hmm_pfns,
 	};
 	struct mm_struct *mm = notifier->notifier.mm;
-	long ret;
+	int ret;
 
 	while (true) {
 		if (time_after(jiffies, timeout))
 			return -EBUSY;
 
 		range.notifier_seq = mmu_interval_read_begin(range.notifier);
-		range.default_flags = 0;
-		range.pfn_flags_mask = -1UL;
 		down_read(&mm->mmap_sem);
 		ret = hmm_range_fault(&range);
 		up_read(&mm->mmap_sem);
-		if (ret <= 0) {
-			if (ret == 0 || ret == -EBUSY)
+		if (ret) {
+			/*
+			 * FIXME: the input PFN_REQ flags are destroyed on
+			 * -EBUSY, we need to regenerate them, also for the
+			 * other continue below
+			 */
+			if (ret == -EBUSY)
 				continue;
 			return ret;
 		}
@@ -563,7 +587,7 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm,
 		break;
 	}
 
-	nouveau_dmem_convert_pfn(drm, &range);
+	nouveau_hmm_convert_pfn(drm, &range, ioctl_addr);
 
 	svmm->vmm->vmm.object.client->super = true;
 	ret = nvif_object_ioctl(&svmm->vmm->vmm.object, data, size, NULL);
@@ -590,6 +614,7 @@ nouveau_svm_fault(struct nvif_notify *notify)
 		} i;
 		u64 phys[16];
 	} args;
+	unsigned long hmm_pfns[ARRAY_SIZE(args.phys)];
 	struct vm_area_struct *vma;
 	u64 inst, start, limit;
 	int fi, fn, pi, fill;
@@ -705,12 +730,17 @@ nouveau_svm_fault(struct nvif_notify *notify)
 			 * access flags.
 			 *XXX: atomic?
 			 */
-			if (buffer->fault[fn]->access != 0 /* READ. */ &&
-			    buffer->fault[fn]->access != 3 /* PREFETCH. */) {
-				args.phys[pi++] = NVIF_VMM_PFNMAP_V0_V |
-						  NVIF_VMM_PFNMAP_V0_W;
-			} else {
-				args.phys[pi++] = NVIF_VMM_PFNMAP_V0_V;
+			switch (buffer->fault[fn]->access) {
+			case 0: /* READ. */
+				hmm_pfns[pi++] = HMM_PFN_REQ_FAULT;
+				break;
+			case 3: /* PREFETCH. */
+				hmm_pfns[pi++] = 0;
+				break;
+			default:
+				hmm_pfns[pi++] = HMM_PFN_REQ_FAULT |
+						 HMM_PFN_REQ_WRITE;
+				break;
 			}
 			args.i.p.size = pi << PAGE_SHIFT;
 
@@ -738,7 +768,7 @@ nouveau_svm_fault(struct nvif_notify *notify)
 			fill = (buffer->fault[fn    ]->addr -
 				buffer->fault[fn - 1]->addr) >> PAGE_SHIFT;
 			while (--fill)
-				args.phys[pi++] = NVIF_VMM_PFNMAP_V0_NONE;
+				hmm_pfns[pi++] = 0;
 		}
 
 		SVMM_DBG(svmm, "wndw %016llx-%016llx covering %d fault(s)",
@@ -754,7 +784,7 @@ nouveau_svm_fault(struct nvif_notify *notify)
 			ret = nouveau_range_fault(
 				svmm, svm->drm, &args,
 				sizeof(args.i) + pi * sizeof(args.phys[0]),
-				args.phys, &notifier);
+				hmm_pfns, args.phys, &notifier);
 			mmu_interval_notifier_remove(&notifier.notifier);
 		}
 		mmput(mm);

include/linux/hmm.h

@@ -19,51 +19,47 @@
 #include <linux/mmu_notifier.h>
 
 /*
- * hmm_pfn_flag_e - HMM flag enums
+ * On output:
+ * 0             - The page is faultable and a future call with 
+ *                 HMM_PFN_REQ_FAULT could succeed.
+ * HMM_PFN_VALID - the pfn field points to a valid PFN. This PFN is at
+ *                 least readable. If dev_private_owner is !NULL then this could
+ *                 point at a DEVICE_PRIVATE page.
+ * HMM_PFN_WRITE - if the page memory can be written to (requires HMM_PFN_VALID)
+ * HMM_PFN_ERROR - accessing the pfn is impossible and the device should
+ *                 fail. ie poisoned memory, special pages, no vma, etc
  *
- * Flags:
- * HMM_PFN_VALID: pfn is valid. It has, at least, read permission.
- * HMM_PFN_WRITE: CPU page table has write permission set
- *
- * The driver provides a flags array for mapping page protections to device
- * PTE bits. If the driver valid bit for an entry is bit 3,
- * i.e., (entry & (1 << 3)), then the driver must provide
- * an array in hmm_range.flags with hmm_range.flags[HMM_PFN_VALID] == 1 << 3.
- * Same logic apply to all flags. This is the same idea as vm_page_prot in vma
- * except that this is per device driver rather than per architecture.
+ * On input:
+ * 0                 - Return the current state of the page, do not fault it.
+ * HMM_PFN_REQ_FAULT - The output must have HMM_PFN_VALID or hmm_range_fault()
+ *                     will fail
+ * HMM_PFN_REQ_WRITE - The output must have HMM_PFN_WRITE or hmm_range_fault()
+ *                     will fail. Must be combined with HMM_PFN_REQ_FAULT.
  */
-enum hmm_pfn_flag_e {
-	HMM_PFN_VALID = 0,
-	HMM_PFN_WRITE,
-	HMM_PFN_FLAG_MAX
+enum hmm_pfn_flags {
+	/* Output flags */
+	HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1),
+	HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2),
+	HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3),
+
+	/* Input flags */
+	HMM_PFN_REQ_FAULT = HMM_PFN_VALID,
+	HMM_PFN_REQ_WRITE = HMM_PFN_WRITE,
+
+	HMM_PFN_FLAGS = HMM_PFN_VALID | HMM_PFN_WRITE | HMM_PFN_ERROR,
 };
 
 /*
- * hmm_pfn_value_e - HMM pfn special value
- *
- * Flags:
- * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory
- * HMM_PFN_NONE: corresponding CPU page table entry is pte_none()
- * HMM_PFN_SPECIAL: corresponding CPU page table entry is special; i.e., the
- *      result of vmf_insert_pfn() or vm_insert_page(). Therefore, it should not
- *      be mirrored by a device, because the entry will never have HMM_PFN_VALID
- *      set and the pfn value is undefined.
+ * hmm_pfn_to_page() - return struct page pointed to by a device entry
  *
- * Driver provides values for none entry, error entry, and special entry.
- * Driver can alias (i.e., use same value) error and special, but
- * it should not alias none with error or special.
- *
- * HMM pfn value returned by hmm_vma_get_pfns() or hmm_vma_fault() will be:
- * hmm_range.values[HMM_PFN_ERROR] if CPU page table entry is poisonous,
- * hmm_range.values[HMM_PFN_NONE] if there is no CPU page table entry,
- * hmm_range.values[HMM_PFN_SPECIAL] if CPU page table entry is a special one
+ * This must be called under the caller 'user_lock' after a successful
+ * mmu_interval_read_begin(). The caller must have tested for HMM_PFN_VALID
+ * already.
  */
-enum hmm_pfn_value_e {
-	HMM_PFN_ERROR,
-	HMM_PFN_NONE,
-	HMM_PFN_SPECIAL,
-	HMM_PFN_VALUE_MAX
-};
+static inline struct page *hmm_pfn_to_page(unsigned long hmm_pfn)
+{
+	return pfn_to_page(hmm_pfn & ~HMM_PFN_FLAGS);
+}
 
 /*
  * struct hmm_range - track invalidation lock on virtual address range
@@ -72,12 +68,9 @@ enum hmm_pfn_value_e {
  * @notifier_seq: result of mmu_interval_read_begin()
  * @start: range virtual start address (inclusive)
  * @end: range virtual end address (exclusive)
- * @pfns: array of pfns (big enough for the range)
- * @flags: pfn flags to match device driver page table
- * @values: pfn value for some special case (none, special, error, ...)
+ * @hmm_pfns: array of pfns (big enough for the range)
  * @default_flags: default flags for the range (write, read, ... see hmm doc)
  * @pfn_flags_mask: allows to mask pfn flags so that only default_flags matter
- * @pfn_shift: pfn shift value (should be <= PAGE_SHIFT)
  * @dev_private_owner: owner of device private pages
  */
 struct hmm_range {
@@ -85,42 +78,16 @@ struct hmm_range {
 	unsigned long		notifier_seq;
 	unsigned long		start;
 	unsigned long		end;
-	uint64_t		*pfns;
-	const uint64_t		*flags;
-	const uint64_t		*values;
-	uint64_t		default_flags;
-	uint64_t		pfn_flags_mask;
-	uint8_t			pfn_shift;
+	unsigned long		*hmm_pfns;
+	unsigned long		default_flags;
+	unsigned long		pfn_flags_mask;
 	void			*dev_private_owner;
 };
 
-/*
- * hmm_device_entry_to_page() - return struct page pointed to by a device entry
- * @range: range use to decode device entry value
- * @entry: device entry value to get corresponding struct page from
- * Return: struct page pointer if entry is a valid, NULL otherwise
- *
- * If the device entry is valid (ie valid flag set) then return the struct page
- * matching the entry value. Otherwise return NULL.
- */
-static inline struct page *hmm_device_entry_to_page(const struct hmm_range *range,
-						    uint64_t entry)
-{
-	if (entry == range->values[HMM_PFN_NONE])
-		return NULL;
-	if (entry == range->values[HMM_PFN_ERROR])
-		return NULL;
-	if (entry == range->values[HMM_PFN_SPECIAL])
-		return NULL;
-	if (!(entry & range->flags[HMM_PFN_VALID]))
-		return NULL;
-	return pfn_to_page(entry >> range->pfn_shift);
-}
-
 /*
  * Please see Documentation/vm/hmm.rst for how to use the range API.
  */
-long hmm_range_fault(struct hmm_range *range);
+int hmm_range_fault(struct hmm_range *range);
 
 /*
  * HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range

lib/Kconfig.debug

@@ -2218,6 +2218,19 @@ config TEST_MEMINIT
 
 	  If unsure, say N.
 
+config TEST_HMM
+	tristate "Test HMM (Heterogeneous Memory Management)"
+	depends on TRANSPARENT_HUGEPAGE
+	depends on DEVICE_PRIVATE
+	select HMM_MIRROR
+	select MMU_NOTIFIER
+	help
+	  This is a pseudo device driver solely for testing HMM.
+	  Say M here if you want to build the HMM test module.
+	  Doing so will allow you to run tools/testing/selftest/vm/hmm-tests.
+
+	  If unsure, say N.
+
 endif # RUNTIME_TESTING_MENU
 
 config MEMTEST

lib/Makefile

@@ -92,6 +92,7 @@ obj-$(CONFIG_TEST_STACKINIT) += test_stackinit.o
 obj-$(CONFIG_TEST_BLACKHOLE_DEV) += test_blackhole_dev.o
 obj-$(CONFIG_TEST_MEMINIT) += test_meminit.o
 obj-$(CONFIG_TEST_LOCKUP) += test_lockup.o
+obj-$(CONFIG_TEST_HMM) += test_hmm.o
 
 obj-$(CONFIG_TEST_LIVEPATCH) += livepatch/
 

lib/test_hmm.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This is a module to test the HMM (Heterogeneous Memory Management)
+ * mirror and zone device private memory migration APIs of the kernel.
+ * Userspace programs can register with the driver to mirror their own address
+ * space and can use the device to read/write any valid virtual address.
+ */
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/highmem.h>
+#include <linux/delay.h>
+#include <linux/pagemap.h>
+#include <linux/hmm.h>
+#include <linux/vmalloc.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/sched/mm.h>
+#include <linux/platform_device.h>
+
+#include "test_hmm_uapi.h"
+
+#define DMIRROR_NDEVICES		2
+#define DMIRROR_RANGE_FAULT_TIMEOUT	1000
+#define DEVMEM_CHUNK_SIZE		(256 * 1024 * 1024U)
+#define DEVMEM_CHUNKS_RESERVE		16
+
+static const struct dev_pagemap_ops dmirror_devmem_ops;
+static const struct mmu_interval_notifier_ops dmirror_min_ops;
+static dev_t dmirror_dev;
+static struct page *dmirror_zero_page;
+
+struct dmirror_device;
+
+struct dmirror_bounce {
+	void			*ptr;
+	unsigned long		size;
+	unsigned long		addr;
+	unsigned long		cpages;
+};
+
+#define DPT_XA_TAG_WRITE 3UL
+
+/*
+ * Data structure to track address ranges and register for mmu interval
+ * notifier updates.
+ */
+struct dmirror_interval {
+	struct mmu_interval_notifier	notifier;
+	struct dmirror			*dmirror;
+};
+
+/*
+ * Data attached to the open device file.
+ * Note that it might be shared after a fork().
+ */
+struct dmirror {
+	struct dmirror_device		*mdevice;
+	struct xarray			pt;
+	struct mmu_interval_notifier	notifier;
+	struct mutex			mutex;
+};
+
+/*
+ * ZONE_DEVICE pages for migration and simulating device memory.
+ */
+struct dmirror_chunk {
+	struct dev_pagemap	pagemap;
+	struct dmirror_device	*mdevice;
+};
+
+/*
+ * Per device data.
+ */
+struct dmirror_device {
+	struct cdev		cdevice;
+	struct hmm_devmem	*devmem;
+
+	unsigned int		devmem_capacity;
+	unsigned int		devmem_count;
+	struct dmirror_chunk	**devmem_chunks;
+	struct mutex		devmem_lock;	/* protects the above */
+
+	unsigned long		calloc;
+	unsigned long		cfree;
+	struct page		*free_pages;
+	spinlock_t		lock;		/* protects the above */
+};
+
+static struct dmirror_device dmirror_devices[DMIRROR_NDEVICES];
+
+static int dmirror_bounce_init(struct dmirror_bounce *bounce,
+			       unsigned long addr,
+			       unsigned long size)
+{
+	bounce->addr = addr;
+	bounce->size = size;
+	bounce->cpages = 0;
+	bounce->ptr = vmalloc(size);
+	if (!bounce->ptr)
+		return -ENOMEM;
+	return 0;
+}
+
+static void dmirror_bounce_fini(struct dmirror_bounce *bounce)
+{
+	vfree(bounce->ptr);
+}
+
+static int dmirror_fops_open(struct inode *inode, struct file *filp)
+{
+	struct cdev *cdev = inode->i_cdev;
+	struct dmirror *dmirror;
+	int ret;
+
+	/* Mirror this process address space */
+	dmirror = kzalloc(sizeof(*dmirror), GFP_KERNEL);
+	if (dmirror == NULL)
+		return -ENOMEM;
+
+	dmirror->mdevice = container_of(cdev, struct dmirror_device, cdevice);
+	mutex_init(&dmirror->mutex);
+	xa_init(&dmirror->pt);
+
+	ret = mmu_interval_notifier_insert(&dmirror->notifier, current->mm,
+				0, ULONG_MAX & PAGE_MASK, &dmirror_min_ops);
+	if (ret) {
+		kfree(dmirror);
+		return ret;
+	}
+
+	filp->private_data = dmirror;
+	return 0;
+}
+
+static int dmirror_fops_release(struct inode *inode, struct file *filp)
+{
+	struct dmirror *dmirror = filp->private_data;
+
+	mmu_interval_notifier_remove(&dmirror->notifier);
+	xa_destroy(&dmirror->pt);
+	kfree(dmirror);
+	return 0;
+}
+
+static struct dmirror_device *dmirror_page_to_device(struct page *page)
+
+{
+	return container_of(page->pgmap, struct dmirror_chunk,
+			    pagemap)->mdevice;
+}
+
+static int dmirror_do_fault(struct dmirror *dmirror, struct hmm_range *range)
+{
+	unsigned long *pfns = range->hmm_pfns;
+	unsigned long pfn;
+
+	for (pfn = (range->start >> PAGE_SHIFT);
+	     pfn < (range->end >> PAGE_SHIFT);
+	     pfn++, pfns++) {
+		struct page *page;
+		void *entry;
+
+		/*
+		 * Since we asked for hmm_range_fault() to populate pages,
+		 * it shouldn't return an error entry on success.
+		 */
+		WARN_ON(*pfns & HMM_PFN_ERROR);
+		WARN_ON(!(*pfns & HMM_PFN_VALID));
+
+		page = hmm_pfn_to_page(*pfns);
+		WARN_ON(!page);
+
+		entry = page;
+		if (*pfns & HMM_PFN_WRITE)
+			entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE);
+		else if (WARN_ON(range->default_flags & HMM_PFN_WRITE))
+			return -EFAULT;
+		entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC);
+		if (xa_is_err(entry))
+			return xa_err(entry);
+	}
+
+	return 0;
+}
+
+static void dmirror_do_update(struct dmirror *dmirror, unsigned long start,
+			      unsigned long end)
+{
+	unsigned long pfn;
+	void *entry;
+
+	/*
+	 * The XArray doesn't hold references to pages since it relies on
+	 * the mmu notifier to clear page pointers when they become stale.
+	 * Therefore, it is OK to just clear the entry.
+	 */
+	xa_for_each_range(&dmirror->pt, pfn, entry, start >> PAGE_SHIFT,
+			  end >> PAGE_SHIFT)
+		xa_erase(&dmirror->pt, pfn);
+}
+
+static bool dmirror_interval_invalidate(struct mmu_interval_notifier *mni,
+				const struct mmu_notifier_range *range,
+				unsigned long cur_seq)
+{
+	struct dmirror *dmirror = container_of(mni, struct dmirror, notifier);
+
+	if (mmu_notifier_range_blockable(range))
+		mutex_lock(&dmirror->mutex);
+	else if (!mutex_trylock(&dmirror->mutex))
+		return false;
+
+	mmu_interval_set_seq(mni, cur_seq);
+	dmirror_do_update(dmirror, range->start, range->end);
+
+	mutex_unlock(&dmirror->mutex);
+	return true;
+}
+
+static const struct mmu_interval_notifier_ops dmirror_min_ops = {
+	.invalidate = dmirror_interval_invalidate,
+};
+
+static int dmirror_range_fault(struct dmirror *dmirror,
+				struct hmm_range *range)
+{
+	struct mm_struct *mm = dmirror->notifier.mm;
+	unsigned long timeout =
+		jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
+	int ret;
+
+	while (true) {
+		if (time_after(jiffies, timeout)) {
+			ret = -EBUSY;
+			goto out;
+		}
+
+		range->notifier_seq = mmu_interval_read_begin(range->notifier);
+		down_read(&mm->mmap_sem);
+		ret = hmm_range_fault(range);
+		up_read(&mm->mmap_sem);
+		if (ret) {
+			if (ret == -EBUSY)
+				continue;
+			goto out;
+		}
+
+		mutex_lock(&dmirror->mutex);
+		if (mmu_interval_read_retry(range->notifier,
+					    range->notifier_seq)) {
+			mutex_unlock(&dmirror->mutex);
+			continue;
+		}
+		break;
+	}
+
+	ret = dmirror_do_fault(dmirror, range);
+
+	mutex_unlock(&dmirror->mutex);
+out:
+	return ret;
+}
+
+static int dmirror_fault(struct dmirror *dmirror, unsigned long start,
+			 unsigned long end, bool write)
+{
+	struct mm_struct *mm = dmirror->notifier.mm;
+	unsigned long addr;
+	unsigned long pfns[64];
+	struct hmm_range range = {
+		.notifier = &dmirror->notifier,
+		.hmm_pfns = pfns,
+		.pfn_flags_mask = 0,
+		.default_flags =
+			HMM_PFN_REQ_FAULT | (write ? HMM_PFN_REQ_WRITE : 0),
+		.dev_private_owner = dmirror->mdevice,
+	};
+	int ret = 0;
+
+	/* Since the mm is for the mirrored process, get a reference first. */
+	if (!mmget_not_zero(mm))
+		return 0;
+
+	for (addr = start; addr < end; addr = range.end) {
+		range.start = addr;
+		range.end = min(addr + (ARRAY_SIZE(pfns) << PAGE_SHIFT), end);
+
+		ret = dmirror_range_fault(dmirror, &range);
+		if (ret)
+			break;
+	}
+
+	mmput(mm);
+	return ret;
+}
+
+static int dmirror_do_read(struct dmirror *dmirror, unsigned long start,
+			   unsigned long end, struct dmirror_bounce *bounce)
+{
+	unsigned long pfn;
+	void *ptr;
+
+	ptr = bounce->ptr + ((start - bounce->addr) & PAGE_MASK);
+
+	for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) {
+		void *entry;
+		struct page *page;
+		void *tmp;
+
+		entry = xa_load(&dmirror->pt, pfn);
+		page = xa_untag_pointer(entry);
+		if (!page)
+			return -ENOENT;
+
+		tmp = kmap(page);
+		memcpy(ptr, tmp, PAGE_SIZE);
+		kunmap(page);
+
+		ptr += PAGE_SIZE;
+		bounce->cpages++;
+	}
+
+	return 0;
+}
+
+static int dmirror_read(struct dmirror *dmirror, struct hmm_dmirror_cmd *cmd)
+{
+	struct dmirror_bounce bounce;
+	unsigned long start, end;
+	unsigned long size = cmd->npages << PAGE_SHIFT;
+	int ret;
+
+	start = cmd->addr;
+	end = start + size;
+	if (end < start)
+		return -EINVAL;
+
+	ret = dmirror_bounce_init(&bounce, start, size);
+	if (ret)
+		return ret;
+
+	while (1) {
+		mutex_lock(&dmirror->mutex);
+		ret = dmirror_do_read(dmirror, start, end, &bounce);
+		mutex_unlock(&dmirror->mutex);
+		if (ret != -ENOENT)
+			break;
+
+		start = cmd->addr + (bounce.cpages << PAGE_SHIFT);
+		ret = dmirror_fault(dmirror, start, end, false);
+		if (ret)
+			break;
+		cmd->faults++;
+	}
+
+	if (ret == 0) {
+		if (copy_to_user(u64_to_user_ptr(cmd->ptr), bounce.ptr,
+				 bounce.size))
+			ret = -EFAULT;
+	}
+	cmd->cpages = bounce.cpages;
+	dmirror_bounce_fini(&bounce);
+	return ret;
+}
+
+static int dmirror_do_write(struct dmirror *dmirror, unsigned long start,
+			    unsigned long end, struct dmirror_bounce *bounce)
+{
+	unsigned long pfn;
+	void *ptr;
+
+	ptr = bounce->ptr + ((start - bounce->addr) & PAGE_MASK);
+
+	for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) {
+		void *entry;
+		struct page *page;
+		void *tmp;
+
+		entry = xa_load(&dmirror->pt, pfn);
+		page = xa_untag_pointer(entry);
+		if (!page || xa_pointer_tag(entry) != DPT_XA_TAG_WRITE)
+			return -ENOENT;
+
+		tmp = kmap(page);
+		memcpy(tmp, ptr, PAGE_SIZE);
+		kunmap(page);
+
+		ptr += PAGE_SIZE;
+		bounce->cpages++;
+	}
+
+	return 0;
+}
+
+static int dmirror_write(struct dmirror *dmirror, struct hmm_dmirror_cmd *cmd)
+{
+	struct dmirror_bounce bounce;
+	unsigned long start, end;
+	unsigned long size = cmd->npages << PAGE_SHIFT;
+	int ret;
+
+	start = cmd->addr;
+	end = start + size;
+	if (end < start)
+		return -EINVAL;
+
+	ret = dmirror_bounce_init(&bounce, start, size);
+	if (ret)
+		return ret;
+	if (copy_from_user(bounce.ptr, u64_to_user_ptr(cmd->ptr),
+			   bounce.size)) {
+		ret = -EFAULT;
+		goto fini;
+	}
+
+	while (1) {
+		mutex_lock(&dmirror->mutex);
+		ret = dmirror_do_write(dmirror, start, end, &bounce);
+		mutex_unlock(&dmirror->mutex);
+		if (ret != -ENOENT)
+			break;
+
+		start = cmd->addr + (bounce.cpages << PAGE_SHIFT);
+		ret = dmirror_fault(dmirror, start, end, true);
+		if (ret)
+			break;
+		cmd->faults++;
+	}
+
+fini:
+	cmd->cpages = bounce.cpages;
+	dmirror_bounce_fini(&bounce);
+	return ret;
+}
+
+static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
+				   struct page **ppage)
+{
+	struct dmirror_chunk *devmem;
+	struct resource *res;
+	unsigned long pfn;
+	unsigned long pfn_first;
+	unsigned long pfn_last;
+	void *ptr;
+
+	mutex_lock(&mdevice->devmem_lock);
+
+	if (mdevice->devmem_count == mdevice->devmem_capacity) {
+		struct dmirror_chunk **new_chunks;
+		unsigned int new_capacity;
+
+		new_capacity = mdevice->devmem_capacity +
+				DEVMEM_CHUNKS_RESERVE;
+		new_chunks = krealloc(mdevice->devmem_chunks,
+				sizeof(new_chunks[0]) * new_capacity,
+				GFP_KERNEL);
+		if (!new_chunks)
+			goto err;
+		mdevice->devmem_capacity = new_capacity;
+		mdevice->devmem_chunks = new_chunks;
+	}
+
+	res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE,
+					"hmm_dmirror");
+	if (IS_ERR(res))
+		goto err;
+
+	devmem = kzalloc(sizeof(*devmem), GFP_KERNEL);
+	if (!devmem)
+		goto err_release;
+
+	devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
+	devmem->pagemap.res = *res;
+	devmem->pagemap.ops = &dmirror_devmem_ops;
+	devmem->pagemap.owner = mdevice;
+
+	ptr = memremap_pages(&devmem->pagemap, numa_node_id());
+	if (IS_ERR(ptr))
+		goto err_free;
+
+	devmem->mdevice = mdevice;
+	pfn_first = devmem->pagemap.res.start >> PAGE_SHIFT;
+	pfn_last = pfn_first +
+		(resource_size(&devmem->pagemap.res) >> PAGE_SHIFT);
+	mdevice->devmem_chunks[mdevice->devmem_count++] = devmem;
+
+	mutex_unlock(&mdevice->devmem_lock);
+
+	pr_info("added new %u MB chunk (total %u chunks, %u MB) PFNs [0x%lx 0x%lx)\n",
+		DEVMEM_CHUNK_SIZE / (1024 * 1024),
+		mdevice->devmem_count,
+		mdevice->devmem_count * (DEVMEM_CHUNK_SIZE / (1024 * 1024)),
+		pfn_first, pfn_last);
+
+	spin_lock(&mdevice->lock);
+	for (pfn = pfn_first; pfn < pfn_last; pfn++) {
+		struct page *page = pfn_to_page(pfn);
+
+		page->zone_device_data = mdevice->free_pages;
+		mdevice->free_pages = page;
+	}
+	if (ppage) {
+		*ppage = mdevice->free_pages;
+		mdevice->free_pages = (*ppage)->zone_device_data;
+		mdevice->calloc++;
+	}
+	spin_unlock(&mdevice->lock);
+
+	return true;
+
+err_free:
+	kfree(devmem);
+err_release:
+	release_mem_region(devmem->pagemap.res.start,
+			   resource_size(&devmem->pagemap.res));
+err:
+	mutex_unlock(&mdevice->devmem_lock);
+	return false;
+}
+
+static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
+{
+	struct page *dpage = NULL;
+	struct page *rpage;
+
+	/*
+	 * This is a fake device so we alloc real system memory to store
+	 * our device memory.
+	 */
+	rpage = alloc_page(GFP_HIGHUSER);
+	if (!rpage)
+		return NULL;
+
+	spin_lock(&mdevice->lock);
+
+	if (mdevice->free_pages) {
+		dpage = mdevice->free_pages;
+		mdevice->free_pages = dpage->zone_device_data;
+		mdevice->calloc++;
+		spin_unlock(&mdevice->lock);
+	} else {
+		spin_unlock(&mdevice->lock);
+		if (!dmirror_allocate_chunk(mdevice, &dpage))
+			goto error;
+	}
+
+	dpage->zone_device_data = rpage;
+	get_page(dpage);
+	lock_page(dpage);
+	return dpage;
+
+error:
+	__free_page(rpage);
+	return NULL;
+}
+
+static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args,
+					   struct dmirror *dmirror)
+{
+	struct dmirror_device *mdevice = dmirror->mdevice;
+	const unsigned long *src = args->src;
+	unsigned long *dst = args->dst;
+	unsigned long addr;
+
+	for (addr = args->start; addr < args->end; addr += PAGE_SIZE,
+						   src++, dst++) {
+		struct page *spage;
+		struct page *dpage;
+		struct page *rpage;
+
+		if (!(*src & MIGRATE_PFN_MIGRATE))
+			continue;
+
+		/*
+		 * Note that spage might be NULL which is OK since it is an
+		 * unallocated pte_none() or read-only zero page.
+		 */
+		spage = migrate_pfn_to_page(*src);
+
+		/*
+		 * Don't migrate device private pages from our own driver or
+		 * others. For our own we would do a device private memory copy
+		 * not a migration and for others, we would need to fault the
+		 * other device's page into system memory first.
+		 */
+		if (spage && is_zone_device_page(spage))
+			continue;
+
+		dpage = dmirror_devmem_alloc_page(mdevice);
+		if (!dpage)
+			continue;
+
+		rpage = dpage->zone_device_data;
+		if (spage)
+			copy_highpage(rpage, spage);
+		else
+			clear_highpage(rpage);
+
+		/*
+		 * Normally, a device would use the page->zone_device_data to
+		 * point to the mirror but here we use it to hold the page for
+		 * the simulated device memory and that page holds the pointer
+		 * to the mirror.
+		 */
+		rpage->zone_device_data = dmirror;
+
+		*dst = migrate_pfn(page_to_pfn(dpage)) |
+			    MIGRATE_PFN_LOCKED;
+		if ((*src & MIGRATE_PFN_WRITE) ||
+		    (!spage && args->vma->vm_flags & VM_WRITE))
+			*dst |= MIGRATE_PFN_WRITE;
+	}
+}
+
+static int dmirror_migrate_finalize_and_map(struct migrate_vma *args,
+					    struct dmirror *dmirror)
+{
+	unsigned long start = args->start;
+	unsigned long end = args->end;
+	const unsigned long *src = args->src;
+	const unsigned long *dst = args->dst;
+	unsigned long pfn;
+
+	/* Map the migrated pages into the device's page tables. */
+	mutex_lock(&dmirror->mutex);
+
+	for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++,
+								src++, dst++) {
+		struct page *dpage;
+		void *entry;
+
+		if (!(*src & MIGRATE_PFN_MIGRATE))
+			continue;
+
+		dpage = migrate_pfn_to_page(*dst);
+		if (!dpage)
+			continue;
+
+		/*
+		 * Store the page that holds the data so the page table
+		 * doesn't have to deal with ZONE_DEVICE private pages.
+		 */
+		entry = dpage->zone_device_data;
+		if (*dst & MIGRATE_PFN_WRITE)
+			entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE);
+		entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC);
+		if (xa_is_err(entry)) {
+			mutex_unlock(&dmirror->mutex);
+			return xa_err(entry);
+		}
+	}
+
+	mutex_unlock(&dmirror->mutex);
+	return 0;
+}
+
+static int dmirror_migrate(struct dmirror *dmirror,
+			   struct hmm_dmirror_cmd *cmd)
+{
+	unsigned long start, end, addr;
+	unsigned long size = cmd->npages << PAGE_SHIFT;
+	struct mm_struct *mm = dmirror->notifier.mm;
+	struct vm_area_struct *vma;
+	unsigned long src_pfns[64];
+	unsigned long dst_pfns[64];
+	struct dmirror_bounce bounce;
+	struct migrate_vma args;
+	unsigned long next;
+	int ret;
+
+	start = cmd->addr;
+	end = start + size;
+	if (end < start)
+		return -EINVAL;
+
+	/* Since the mm is for the mirrored process, get a reference first. */
+	if (!mmget_not_zero(mm))
+		return -EINVAL;
+
+	down_read(&mm->mmap_sem);
+	for (addr = start; addr < end; addr = next) {
+		vma = find_vma(mm, addr);
+		if (!vma || addr < vma->vm_start ||
+		    !(vma->vm_flags & VM_READ)) {
+			ret = -EINVAL;
+			goto out;
+		}
+		next = min(end, addr + (ARRAY_SIZE(src_pfns) << PAGE_SHIFT));
+		if (next > vma->vm_end)
+			next = vma->vm_end;
+
+		args.vma = vma;
+		args.src = src_pfns;
+		args.dst = dst_pfns;
+		args.start = addr;
+		args.end = next;
+		args.src_owner = NULL;
+		ret = migrate_vma_setup(&args);
+		if (ret)
+			goto out;
+
+		dmirror_migrate_alloc_and_copy(&args, dmirror);
+		migrate_vma_pages(&args);
+		dmirror_migrate_finalize_and_map(&args, dmirror);
+		migrate_vma_finalize(&args);
+	}
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+
+	/* Return the migrated data for verification. */
+	ret = dmirror_bounce_init(&bounce, start, size);
+	if (ret)
+		return ret;
+	mutex_lock(&dmirror->mutex);
+	ret = dmirror_do_read(dmirror, start, end, &bounce);
+	mutex_unlock(&dmirror->mutex);
+	if (ret == 0) {
+		if (copy_to_user(u64_to_user_ptr(cmd->ptr), bounce.ptr,
+				 bounce.size))
+			ret = -EFAULT;
+	}
+	cmd->cpages = bounce.cpages;
+	dmirror_bounce_fini(&bounce);
+	return ret;
+
+out:
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+	return ret;
+}
+
+static void dmirror_mkentry(struct dmirror *dmirror, struct hmm_range *range,
+			    unsigned char *perm, unsigned long entry)
+{
+	struct page *page;
+
+	if (entry & HMM_PFN_ERROR) {
+		*perm = HMM_DMIRROR_PROT_ERROR;
+		return;
+	}
+	if (!(entry & HMM_PFN_VALID)) {
+		*perm = HMM_DMIRROR_PROT_NONE;
+		return;
+	}
+
+	page = hmm_pfn_to_page(entry);
+	if (is_device_private_page(page)) {
+		/* Is the page migrated to this device or some other? */
+		if (dmirror->mdevice == dmirror_page_to_device(page))
+			*perm = HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL;
+		else
+			*perm = HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE;
+	} else if (is_zero_pfn(page_to_pfn(page)))
+		*perm = HMM_DMIRROR_PROT_ZERO;
+	else
+		*perm = HMM_DMIRROR_PROT_NONE;
+	if (entry & HMM_PFN_WRITE)
+		*perm |= HMM_DMIRROR_PROT_WRITE;
+	else
+		*perm |= HMM_DMIRROR_PROT_READ;
+}
+
+static bool dmirror_snapshot_invalidate(struct mmu_interval_notifier *mni,
+				const struct mmu_notifier_range *range,
+				unsigned long cur_seq)
+{
+	struct dmirror_interval *dmi =
+		container_of(mni, struct dmirror_interval, notifier);
+	struct dmirror *dmirror = dmi->dmirror;
+
+	if (mmu_notifier_range_blockable(range))
+		mutex_lock(&dmirror->mutex);
+	else if (!mutex_trylock(&dmirror->mutex))
+		return false;
+
+	/*
+	 * Snapshots only need to set the sequence number since any
+	 * invalidation in the interval invalidates the whole snapshot.
+	 */
+	mmu_interval_set_seq(mni, cur_seq);
+
+	mutex_unlock(&dmirror->mutex);
+	return true;
+}
+
+static const struct mmu_interval_notifier_ops dmirror_mrn_ops = {
+	.invalidate = dmirror_snapshot_invalidate,
+};
+
+static int dmirror_range_snapshot(struct dmirror *dmirror,
+				  struct hmm_range *range,
+				  unsigned char *perm)
+{
+	struct mm_struct *mm = dmirror->notifier.mm;
+	struct dmirror_interval notifier;
+	unsigned long timeout =
+		jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
+	unsigned long i;
+	unsigned long n;
+	int ret = 0;
+
+	notifier.dmirror = dmirror;
+	range->notifier = &notifier.notifier;
+
+	ret = mmu_interval_notifier_insert(range->notifier, mm,
+			range->start, range->end - range->start,
+			&dmirror_mrn_ops);
+	if (ret)
+		return ret;
+
+	while (true) {
+		if (time_after(jiffies, timeout)) {
+			ret = -EBUSY;
+			goto out;
+		}
+
+		range->notifier_seq = mmu_interval_read_begin(range->notifier);
+
+		down_read(&mm->mmap_sem);
+		ret = hmm_range_fault(range);
+		up_read(&mm->mmap_sem);
+		if (ret) {
+			if (ret == -EBUSY)
+				continue;
+			goto out;
+		}
+
+		mutex_lock(&dmirror->mutex);
+		if (mmu_interval_read_retry(range->notifier,
+					    range->notifier_seq)) {
+			mutex_unlock(&dmirror->mutex);
+			continue;
+		}
+		break;
+	}
+
+	n = (range->end - range->start) >> PAGE_SHIFT;
+	for (i = 0; i < n; i++)
+		dmirror_mkentry(dmirror, range, perm + i, range->hmm_pfns[i]);
+
+	mutex_unlock(&dmirror->mutex);
+out:
+	mmu_interval_notifier_remove(range->notifier);
+	return ret;
+}
+
+static int dmirror_snapshot(struct dmirror *dmirror,
+			    struct hmm_dmirror_cmd *cmd)
+{
+	struct mm_struct *mm = dmirror->notifier.mm;
+	unsigned long start, end;
+	unsigned long size = cmd->npages << PAGE_SHIFT;
+	unsigned long addr;
+	unsigned long next;
+	unsigned long pfns[64];
+	unsigned char perm[64];
+	char __user *uptr;
+	struct hmm_range range = {
+		.hmm_pfns = pfns,
+		.dev_private_owner = dmirror->mdevice,
+	};
+	int ret = 0;
+
+	start = cmd->addr;
+	end = start + size;
+	if (end < start)
+		return -EINVAL;
+
+	/* Since the mm is for the mirrored process, get a reference first. */
+	if (!mmget_not_zero(mm))
+		return -EINVAL;
+
+	/*
+	 * Register a temporary notifier to detect invalidations even if it
+	 * overlaps with other mmu_interval_notifiers.
+	 */
+	uptr = u64_to_user_ptr(cmd->ptr);
+	for (addr = start; addr < end; addr = next) {
+		unsigned long n;
+
+		next = min(addr + (ARRAY_SIZE(pfns) << PAGE_SHIFT), end);
+		range.start = addr;
+		range.end = next;
+
+		ret = dmirror_range_snapshot(dmirror, &range, perm);
+		if (ret)
+			break;
+
+		n = (range.end - range.start) >> PAGE_SHIFT;
+		if (copy_to_user(uptr, perm, n)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		cmd->cpages += n;
+		uptr += n;
+	}
+	mmput(mm);
+
+	return ret;
+}
+
+static long dmirror_fops_unlocked_ioctl(struct file *filp,
+					unsigned int command,
+					unsigned long arg)
+{
+	void __user *uarg = (void __user *)arg;
+	struct hmm_dmirror_cmd cmd;
+	struct dmirror *dmirror;
+	int ret;
+
+	dmirror = filp->private_data;
+	if (!dmirror)
+		return -EINVAL;
+
+	if (copy_from_user(&cmd, uarg, sizeof(cmd)))
+		return -EFAULT;
+
+	if (cmd.addr & ~PAGE_MASK)
+		return -EINVAL;
+	if (cmd.addr >= (cmd.addr + (cmd.npages << PAGE_SHIFT)))
+		return -EINVAL;
+
+	cmd.cpages = 0;
+	cmd.faults = 0;
+
+	switch (command) {
+	case HMM_DMIRROR_READ:
+		ret = dmirror_read(dmirror, &cmd);
+		break;
+
+	case HMM_DMIRROR_WRITE:
+		ret = dmirror_write(dmirror, &cmd);
+		break;
+
+	case HMM_DMIRROR_MIGRATE:
+		ret = dmirror_migrate(dmirror, &cmd);
+		break;
+
+	case HMM_DMIRROR_SNAPSHOT:
+		ret = dmirror_snapshot(dmirror, &cmd);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+	if (ret)
+		return ret;
+
+	if (copy_to_user(uarg, &cmd, sizeof(cmd)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static const struct file_operations dmirror_fops = {
+	.open		= dmirror_fops_open,
+	.release	= dmirror_fops_release,
+	.unlocked_ioctl = dmirror_fops_unlocked_ioctl,
+	.llseek		= default_llseek,
+	.owner		= THIS_MODULE,
+};
+
+static void dmirror_devmem_free(struct page *page)
+{
+	struct page *rpage = page->zone_device_data;
+	struct dmirror_device *mdevice;
+
+	if (rpage)
+		__free_page(rpage);
+
+	mdevice = dmirror_page_to_device(page);
+
+	spin_lock(&mdevice->lock);
+	mdevice->cfree++;
+	page->zone_device_data = mdevice->free_pages;
+	mdevice->free_pages = page;
+	spin_unlock(&mdevice->lock);
+}
+
+static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
+						struct dmirror_device *mdevice)
+{
+	const unsigned long *src = args->src;
+	unsigned long *dst = args->dst;
+	unsigned long start = args->start;
+	unsigned long end = args->end;
+	unsigned long addr;
+
+	for (addr = start; addr < end; addr += PAGE_SIZE,
+				       src++, dst++) {
+		struct page *dpage, *spage;
+
+		spage = migrate_pfn_to_page(*src);
+		if (!spage || !(*src & MIGRATE_PFN_MIGRATE))
+			continue;
+		spage = spage->zone_device_data;
+
+		dpage = alloc_page_vma(GFP_HIGHUSER_MOVABLE, args->vma, addr);
+		if (!dpage)
+			continue;
+
+		lock_page(dpage);
+		copy_highpage(dpage, spage);
+		*dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED;
+		if (*src & MIGRATE_PFN_WRITE)
+			*dst |= MIGRATE_PFN_WRITE;
+	}
+	return 0;
+}
+
+static void dmirror_devmem_fault_finalize_and_map(struct migrate_vma *args,
+						  struct dmirror *dmirror)
+{
+	/* Invalidate the device's page table mapping. */
+	mutex_lock(&dmirror->mutex);
+	dmirror_do_update(dmirror, args->start, args->end);
+	mutex_unlock(&dmirror->mutex);
+}
+
+static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
+{
+	struct migrate_vma args;
+	unsigned long src_pfns;
+	unsigned long dst_pfns;
+	struct page *rpage;
+	struct dmirror *dmirror;
+	vm_fault_t ret;
+
+	/*
+	 * Normally, a device would use the page->zone_device_data to point to
+	 * the mirror but here we use it to hold the page for the simulated
+	 * device memory and that page holds the pointer to the mirror.
+	 */
+	rpage = vmf->page->zone_device_data;
+	dmirror = rpage->zone_device_data;
+
+	/* FIXME demonstrate how we can adjust migrate range */
+	args.vma = vmf->vma;
+	args.start = vmf->address;
+	args.end = args.start + PAGE_SIZE;
+	args.src = &src_pfns;
+	args.dst = &dst_pfns;
+	args.src_owner = dmirror->mdevice;
+
+	if (migrate_vma_setup(&args))
+		return VM_FAULT_SIGBUS;
+
+	ret = dmirror_devmem_fault_alloc_and_copy(&args, dmirror->mdevice);
+	if (ret)
+		return ret;
+	migrate_vma_pages(&args);
+	dmirror_devmem_fault_finalize_and_map(&args, dmirror);
+	migrate_vma_finalize(&args);
+	return 0;
+}
+
+static const struct dev_pagemap_ops dmirror_devmem_ops = {
+	.page_free	= dmirror_devmem_free,
+	.migrate_to_ram	= dmirror_devmem_fault,
+};
+
+static int dmirror_device_init(struct dmirror_device *mdevice, int id)
+{
+	dev_t dev;
+	int ret;
+
+	dev = MKDEV(MAJOR(dmirror_dev), id);
+	mutex_init(&mdevice->devmem_lock);
+	spin_lock_init(&mdevice->lock);
+
+	cdev_init(&mdevice->cdevice, &dmirror_fops);
+	mdevice->cdevice.owner = THIS_MODULE;
+	ret = cdev_add(&mdevice->cdevice, dev, 1);
+	if (ret)
+		return ret;
+
+	/* Build a list of free ZONE_DEVICE private struct pages */
+	dmirror_allocate_chunk(mdevice, NULL);
+
+	return 0;
+}
+
+static void dmirror_device_remove(struct dmirror_device *mdevice)
+{
+	unsigned int i;
+
+	if (mdevice->devmem_chunks) {
+		for (i = 0; i < mdevice->devmem_count; i++) {
+			struct dmirror_chunk *devmem =
+				mdevice->devmem_chunks[i];
+
+			memunmap_pages(&devmem->pagemap);
+			release_mem_region(devmem->pagemap.res.start,
+					   resource_size(&devmem->pagemap.res));
+			kfree(devmem);
+		}
+		kfree(mdevice->devmem_chunks);
+	}
+
+	cdev_del(&mdevice->cdevice);
+}
+
+static int __init hmm_dmirror_init(void)
+{
+	int ret;
+	int id;
+
+	ret = alloc_chrdev_region(&dmirror_dev, 0, DMIRROR_NDEVICES,
+				  "HMM_DMIRROR");
+	if (ret)
+		goto err_unreg;
+
+	for (id = 0; id < DMIRROR_NDEVICES; id++) {
+		ret = dmirror_device_init(dmirror_devices + id, id);
+		if (ret)
+			goto err_chrdev;
+	}
+
+	/*
+	 * Allocate a zero page to simulate a reserved page of device private
+	 * memory which is always zero. The zero_pfn page isn't used just to
+	 * make the code here simpler (i.e., we need a struct page for it).
+	 */
+	dmirror_zero_page = alloc_page(GFP_HIGHUSER | __GFP_ZERO);
+	if (!dmirror_zero_page) {
+		ret = -ENOMEM;
+		goto err_chrdev;
+	}
+
+	pr_info("HMM test module loaded. This is only for testing HMM.\n");
+	return 0;
+
+err_chrdev:
+	while (--id >= 0)
+		dmirror_device_remove(dmirror_devices + id);
+	unregister_chrdev_region(dmirror_dev, DMIRROR_NDEVICES);
+err_unreg:
+	return ret;
+}
+
+static void __exit hmm_dmirror_exit(void)
+{
+	int id;
+
+	if (dmirror_zero_page)
+		__free_page(dmirror_zero_page);
+	for (id = 0; id < DMIRROR_NDEVICES; id++)
+		dmirror_device_remove(dmirror_devices + id);
+	unregister_chrdev_region(dmirror_dev, DMIRROR_NDEVICES);
+}
+
+module_init(hmm_dmirror_init);
+module_exit(hmm_dmirror_exit);
+MODULE_LICENSE("GPL");

lib/test_hmm_uapi.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * This is a module to test the HMM (Heterogeneous Memory Management) API
+ * of the kernel. It allows a userspace program to expose its entire address
+ * space through the HMM test module device file.
+ */
+#ifndef _LIB_TEST_HMM_UAPI_H
+#define _LIB_TEST_HMM_UAPI_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/*
+ * Structure to pass to the HMM test driver to mimic a device accessing
+ * system memory and ZONE_DEVICE private memory through device page tables.
+ *
+ * @addr: (in) user address the device will read/write
+ * @ptr: (in) user address where device data is copied to/from
+ * @npages: (in) number of pages to read/write
+ * @cpages: (out) number of pages copied
+ * @faults: (out) number of device page faults seen
+ */
+struct hmm_dmirror_cmd {
+	__u64		addr;
+	__u64		ptr;
+	__u64		npages;
+	__u64		cpages;
+	__u64		faults;
+};
+
+/* Expose the address space of the calling process through hmm device file */
+#define HMM_DMIRROR_READ		_IOWR('H', 0x00, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_WRITE		_IOWR('H', 0x01, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_MIGRATE		_IOWR('H', 0x02, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_SNAPSHOT		_IOWR('H', 0x03, struct hmm_dmirror_cmd)
+
+/*
+ * Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT.
+ * HMM_DMIRROR_PROT_ERROR: no valid mirror PTE for this page
+ * HMM_DMIRROR_PROT_NONE: unpopulated PTE or PTE with no access
+ * HMM_DMIRROR_PROT_READ: read-only PTE
+ * HMM_DMIRROR_PROT_WRITE: read/write PTE
+ * HMM_DMIRROR_PROT_ZERO: special read-only zero page
+ * HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL: Migrated device private page on the
+ *					device the ioctl() is made
+ * HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE: Migrated device private page on some
+ *					other device
+ */
+enum {
+	HMM_DMIRROR_PROT_ERROR			= 0xFF,
+	HMM_DMIRROR_PROT_NONE			= 0x00,
+	HMM_DMIRROR_PROT_READ			= 0x01,
+	HMM_DMIRROR_PROT_WRITE			= 0x02,
+	HMM_DMIRROR_PROT_ZERO			= 0x10,
+	HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL	= 0x20,
+	HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE	= 0x30,
+};
+
+#endif /* _LIB_TEST_HMM_UAPI_H */

mm/hmm.c

@@ -37,28 +37,13 @@ enum {
 	HMM_NEED_ALL_BITS = HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT,
 };
 
-/*
- * hmm_device_entry_from_pfn() - create a valid device entry value from pfn
- * @range: range use to encode HMM pfn value
- * @pfn: pfn value for which to create the device entry
- * Return: valid device entry for the pfn
- */
-static uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range,
-					  unsigned long pfn)
-{
-	return (pfn << range->pfn_shift) | range->flags[HMM_PFN_VALID];
-}
-
 static int hmm_pfns_fill(unsigned long addr, unsigned long end,
-		struct hmm_range *range, enum hmm_pfn_value_e value)
+			 struct hmm_range *range, unsigned long cpu_flags)
 {
-	uint64_t *pfns = range->pfns;
-	unsigned long i;
+	unsigned long i = (addr - range->start) >> PAGE_SHIFT;
 
-	i = (addr - range->start) >> PAGE_SHIFT;
 	for (; addr < end; addr += PAGE_SIZE, i++)
-		pfns[i] = range->values[value];
-
+		range->hmm_pfns[i] = cpu_flags;
 	return 0;
 }
 
@@ -96,7 +81,8 @@ static int hmm_vma_fault(unsigned long addr, unsigned long end,
 }
 
 static unsigned int hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
-				       uint64_t pfns, uint64_t cpu_flags)
+				       unsigned long pfn_req_flags,
+				       unsigned long cpu_flags)
 {
 	struct hmm_range *range = hmm_vma_walk->range;
 
@@ -110,27 +96,28 @@ static unsigned int hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
 	 * waste to have the user pre-fill the pfn arrays with a default
 	 * flags value.
 	 */
-	pfns = (pfns & range->pfn_flags_mask) | range->default_flags;
+	pfn_req_flags &= range->pfn_flags_mask;
+	pfn_req_flags |= range->default_flags;
 
 	/* We aren't ask to do anything ... */
-	if (!(pfns & range->flags[HMM_PFN_VALID]))
+	if (!(pfn_req_flags & HMM_PFN_REQ_FAULT))
 		return 0;
 
 	/* Need to write fault ? */
-	if ((pfns & range->flags[HMM_PFN_WRITE]) &&
-	    !(cpu_flags & range->flags[HMM_PFN_WRITE]))
+	if ((pfn_req_flags & HMM_PFN_REQ_WRITE) &&
+	    !(cpu_flags & HMM_PFN_WRITE))
 		return HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT;
 
 	/* If CPU page table is not valid then we need to fault */
-	if (!(cpu_flags & range->flags[HMM_PFN_VALID]))
+	if (!(cpu_flags & HMM_PFN_VALID))
 		return HMM_NEED_FAULT;
 	return 0;
 }
 
 static unsigned int
 hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
-		     const uint64_t *pfns, unsigned long npages,
-		     uint64_t cpu_flags)
+		     const unsigned long hmm_pfns[], unsigned long npages,
+		     unsigned long cpu_flags)
 {
 	struct hmm_range *range = hmm_vma_walk->range;
 	unsigned int required_fault = 0;
@@ -142,12 +129,12 @@ hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
 	 * hmm_pte_need_fault() will always return 0.
 	 */
 	if (!((range->default_flags | range->pfn_flags_mask) &
-	      range->flags[HMM_PFN_VALID]))
+	      HMM_PFN_REQ_FAULT))
 		return 0;
 
 	for (i = 0; i < npages; ++i) {
-		required_fault |=
-			hmm_pte_need_fault(hmm_vma_walk, pfns[i], cpu_flags);
+		required_fault |= hmm_pte_need_fault(hmm_vma_walk, hmm_pfns[i],
+						     cpu_flags);
 		if (required_fault == HMM_NEED_ALL_BITS)
 			return required_fault;
 	}
@@ -161,12 +148,13 @@ static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
 	struct hmm_range *range = hmm_vma_walk->range;
 	unsigned int required_fault;
 	unsigned long i, npages;
-	uint64_t *pfns;
+	unsigned long *hmm_pfns;
 
 	i = (addr - range->start) >> PAGE_SHIFT;
 	npages = (end - addr) >> PAGE_SHIFT;
-	pfns = &range->pfns[i];
-	required_fault = hmm_range_need_fault(hmm_vma_walk, pfns, npages, 0);
+	hmm_pfns = &range->hmm_pfns[i];
+	required_fault =
+		hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0);
 	if (!walk->vma) {
 		if (required_fault)
 			return -EFAULT;
@@ -174,46 +162,44 @@ static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
 	}
 	if (required_fault)
 		return hmm_vma_fault(addr, end, required_fault, walk);
-	hmm_vma_walk->last = addr;
-	return hmm_pfns_fill(addr, end, range, HMM_PFN_NONE);
+	return hmm_pfns_fill(addr, end, range, 0);
 }
 
-static inline uint64_t pmd_to_hmm_pfn_flags(struct hmm_range *range, pmd_t pmd)
+static inline unsigned long pmd_to_hmm_pfn_flags(struct hmm_range *range,
+						 pmd_t pmd)
 {
 	if (pmd_protnone(pmd))
 		return 0;
-	return pmd_write(pmd) ? range->flags[HMM_PFN_VALID] |
-				range->flags[HMM_PFN_WRITE] :
-				range->flags[HMM_PFN_VALID];
+	return pmd_write(pmd) ? (HMM_PFN_VALID | HMM_PFN_WRITE) : HMM_PFN_VALID;
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
-		unsigned long end, uint64_t *pfns, pmd_t pmd)
+			      unsigned long end, unsigned long hmm_pfns[],
+			      pmd_t pmd)
 {
 	struct hmm_vma_walk *hmm_vma_walk = walk->private;
 	struct hmm_range *range = hmm_vma_walk->range;
 	unsigned long pfn, npages, i;
 	unsigned int required_fault;
-	uint64_t cpu_flags;
+	unsigned long cpu_flags;
 
 	npages = (end - addr) >> PAGE_SHIFT;
 	cpu_flags = pmd_to_hmm_pfn_flags(range, pmd);
 	required_fault =
-		hmm_range_need_fault(hmm_vma_walk, pfns, npages, cpu_flags);
+		hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, cpu_flags);
 	if (required_fault)
 		return hmm_vma_fault(addr, end, required_fault, walk);
 
 	pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
 	for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++)
-		pfns[i] = hmm_device_entry_from_pfn(range, pfn) | cpu_flags;
-	hmm_vma_walk->last = end;
+		hmm_pfns[i] = pfn | cpu_flags;
 	return 0;
 }
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 /* stub to allow the code below to compile */
 int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
-		unsigned long end, uint64_t *pfns, pmd_t pmd);
+		unsigned long end, unsigned long hmm_pfns[], pmd_t pmd);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 static inline bool hmm_is_device_private_entry(struct hmm_range *range,
@@ -224,31 +210,31 @@ static inline bool hmm_is_device_private_entry(struct hmm_range *range,
 		range->dev_private_owner;
 }
 
-static inline uint64_t pte_to_hmm_pfn_flags(struct hmm_range *range, pte_t pte)
+static inline unsigned long pte_to_hmm_pfn_flags(struct hmm_range *range,
+						 pte_t pte)
 {
 	if (pte_none(pte) || !pte_present(pte) || pte_protnone(pte))
 		return 0;
-	return pte_write(pte) ? range->flags[HMM_PFN_VALID] |
-				range->flags[HMM_PFN_WRITE] :
-				range->flags[HMM_PFN_VALID];
+	return pte_write(pte) ? (HMM_PFN_VALID | HMM_PFN_WRITE) : HMM_PFN_VALID;
 }
 
 static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 			      unsigned long end, pmd_t *pmdp, pte_t *ptep,
-			      uint64_t *pfn)
+			      unsigned long *hmm_pfn)
 {
 	struct hmm_vma_walk *hmm_vma_walk = walk->private;
 	struct hmm_range *range = hmm_vma_walk->range;
 	unsigned int required_fault;
-	uint64_t cpu_flags;
+	unsigned long cpu_flags;
 	pte_t pte = *ptep;
-	uint64_t orig_pfn = *pfn;
+	uint64_t pfn_req_flags = *hmm_pfn;
 
 	if (pte_none(pte)) {
-		required_fault = hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0);
+		required_fault =
+			hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0);
 		if (required_fault)
 			goto fault;
-		*pfn = range->values[HMM_PFN_NONE];
+		*hmm_pfn = 0;
 		return 0;
 	}
 
@@ -260,17 +246,18 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 		 * the PFN even if not present.
 		 */
 		if (hmm_is_device_private_entry(range, entry)) {
-			*pfn = hmm_device_entry_from_pfn(range,
-				device_private_entry_to_pfn(entry));
-			*pfn |= range->flags[HMM_PFN_VALID];
+			cpu_flags = HMM_PFN_VALID;
 			if (is_write_device_private_entry(entry))
-				*pfn |= range->flags[HMM_PFN_WRITE];
+				cpu_flags |= HMM_PFN_WRITE;
+			*hmm_pfn = device_private_entry_to_pfn(entry) |
+					cpu_flags;
 			return 0;
 		}
 
-		required_fault = hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0);
+		required_fault =
+			hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0);
 		if (!required_fault) {
-			*pfn = range->values[HMM_PFN_NONE];
+			*hmm_pfn = 0;
 			return 0;
 		}
 
@@ -290,7 +277,8 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 	}
 
 	cpu_flags = pte_to_hmm_pfn_flags(range, pte);
-	required_fault = hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags);
+	required_fault =
+		hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags);
 	if (required_fault)
 		goto fault;
 
@@ -299,15 +287,15 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 	 * fall through and treat it like a normal page.
 	 */
 	if (pte_special(pte) && !is_zero_pfn(pte_pfn(pte))) {
-		if (hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0)) {
+		if (hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0)) {
 			pte_unmap(ptep);
 			return -EFAULT;
 		}
-		*pfn = range->values[HMM_PFN_SPECIAL];
+		*hmm_pfn = HMM_PFN_ERROR;
 		return 0;
 	}
 
-	*pfn = hmm_device_entry_from_pfn(range, pte_pfn(pte)) | cpu_flags;
+	*hmm_pfn = pte_pfn(pte) | cpu_flags;
 	return 0;
 
 fault:
@@ -323,7 +311,8 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
 {
 	struct hmm_vma_walk *hmm_vma_walk = walk->private;
 	struct hmm_range *range = hmm_vma_walk->range;
-	uint64_t *pfns = &range->pfns[(start - range->start) >> PAGE_SHIFT];
+	unsigned long *hmm_pfns =
+		&range->hmm_pfns[(start - range->start) >> PAGE_SHIFT];
 	unsigned long npages = (end - start) >> PAGE_SHIFT;
 	unsigned long addr = start;
 	pte_t *ptep;
@@ -335,16 +324,16 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
 		return hmm_vma_walk_hole(start, end, -1, walk);
 
 	if (thp_migration_supported() && is_pmd_migration_entry(pmd)) {
-		if (hmm_range_need_fault(hmm_vma_walk, pfns, npages, 0)) {
+		if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0)) {
 			hmm_vma_walk->last = addr;
 			pmd_migration_entry_wait(walk->mm, pmdp);
 			return -EBUSY;
 		}
-		return hmm_pfns_fill(start, end, range, HMM_PFN_NONE);
+		return hmm_pfns_fill(start, end, range, 0);
 	}
 
 	if (!pmd_present(pmd)) {
-		if (hmm_range_need_fault(hmm_vma_walk, pfns, npages, 0))
+		if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0))
 			return -EFAULT;
 		return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
 	}
@@ -364,7 +353,7 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
 		if (!pmd_devmap(pmd) && !pmd_trans_huge(pmd))
 			goto again;
 
-		return hmm_vma_handle_pmd(walk, addr, end, pfns, pmd);
+		return hmm_vma_handle_pmd(walk, addr, end, hmm_pfns, pmd);
 	}
 
 	/*
@@ -374,37 +363,33 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
 	 * recover.
 	 */
 	if (pmd_bad(pmd)) {
-		if (hmm_range_need_fault(hmm_vma_walk, pfns, npages, 0))
+		if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0))
 			return -EFAULT;
 		return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
 	}
 
 	ptep = pte_offset_map(pmdp, addr);
-	for (; addr < end; addr += PAGE_SIZE, ptep++, pfns++) {
+	for (; addr < end; addr += PAGE_SIZE, ptep++, hmm_pfns++) {
 		int r;
 
-		r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, pfns);
+		r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, hmm_pfns);
 		if (r) {
 			/* hmm_vma_handle_pte() did pte_unmap() */
-			hmm_vma_walk->last = addr;
 			return r;
 		}
 	}
 	pte_unmap(ptep - 1);
-
-	hmm_vma_walk->last = addr;
 	return 0;
 }
 
 #if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && \
     defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
-static inline uint64_t pud_to_hmm_pfn_flags(struct hmm_range *range, pud_t pud)
+static inline unsigned long pud_to_hmm_pfn_flags(struct hmm_range *range,
+						 pud_t pud)
 {
 	if (!pud_present(pud))
 		return 0;
-	return pud_write(pud) ? range->flags[HMM_PFN_VALID] |
-				range->flags[HMM_PFN_WRITE] :
-				range->flags[HMM_PFN_VALID];
+	return pud_write(pud) ? (HMM_PFN_VALID | HMM_PFN_WRITE) : HMM_PFN_VALID;
 }
 
 static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
@@ -432,7 +417,8 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
 	if (pud_huge(pud) && pud_devmap(pud)) {
 		unsigned long i, npages, pfn;
 		unsigned int required_fault;
-		uint64_t *pfns, cpu_flags;
+		unsigned long *hmm_pfns;
+		unsigned long cpu_flags;
 
 		if (!pud_present(pud)) {
 			spin_unlock(ptl);
@@ -441,10 +427,10 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
 
 		i = (addr - range->start) >> PAGE_SHIFT;
 		npages = (end - addr) >> PAGE_SHIFT;
-		pfns = &range->pfns[i];
+		hmm_pfns = &range->hmm_pfns[i];
 
 		cpu_flags = pud_to_hmm_pfn_flags(range, pud);
-		required_fault = hmm_range_need_fault(hmm_vma_walk, pfns,
+		required_fault = hmm_range_need_fault(hmm_vma_walk, hmm_pfns,
 						      npages, cpu_flags);
 		if (required_fault) {
 			spin_unlock(ptl);
@@ -453,9 +439,7 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
 
 		pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
 		for (i = 0; i < npages; ++i, ++pfn)
-			pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
-				  cpu_flags;
-		hmm_vma_walk->last = end;
+			hmm_pfns[i] = pfn | cpu_flags;
 		goto out_unlock;
 	}
 
@@ -479,8 +463,9 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
 	struct hmm_vma_walk *hmm_vma_walk = walk->private;
 	struct hmm_range *range = hmm_vma_walk->range;
 	struct vm_area_struct *vma = walk->vma;
-	uint64_t orig_pfn, cpu_flags;
 	unsigned int required_fault;
+	unsigned long pfn_req_flags;
+	unsigned long cpu_flags;
 	spinlock_t *ptl;
 	pte_t entry;
 
@@ -488,9 +473,10 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
 	entry = huge_ptep_get(pte);
 
 	i = (start - range->start) >> PAGE_SHIFT;
-	orig_pfn = range->pfns[i];
+	pfn_req_flags = range->hmm_pfns[i];
 	cpu_flags = pte_to_hmm_pfn_flags(range, entry);
-	required_fault = hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags);
+	required_fault =
+		hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags);
 	if (required_fault) {
 		spin_unlock(ptl);
 		return hmm_vma_fault(addr, end, required_fault, walk);
@@ -498,9 +484,8 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
 
 	pfn = pte_pfn(entry) + ((start & ~hmask) >> PAGE_SHIFT);
 	for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
-		range->pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
-				 cpu_flags;
-	hmm_vma_walk->last = end;
+		range->hmm_pfns[i] = pfn | cpu_flags;
+
 	spin_unlock(ptl);
 	return 0;
 }
@@ -531,13 +516,12 @@ static int hmm_vma_walk_test(unsigned long start, unsigned long end,
 	 * failure.
 	 */
 	if (hmm_range_need_fault(hmm_vma_walk,
-				 range->pfns +
+				 range->hmm_pfns +
 					 ((start - range->start) >> PAGE_SHIFT),
 				 (end - start) >> PAGE_SHIFT, 0))
 		return -EFAULT;
 
 	hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
-	hmm_vma_walk->last = end;
 
 	/* Skip this vma and continue processing the next vma. */
 	return 1;
@@ -555,9 +539,7 @@ static const struct mm_walk_ops hmm_walk_ops = {
  * hmm_range_fault - try to fault some address in a virtual address range
  * @range:	argument structure
  *
- * Return: the number of valid pages in range->pfns[] (from range start
- * address), which may be zero.  On error one of the following status codes
- * can be returned:
+ * Returns 0 on success or one of the following error codes:
  *
  * -EINVAL:	Invalid arguments or mm or virtual address is in an invalid vma
  *		(e.g., device file vma).
@@ -572,7 +554,7 @@ static const struct mm_walk_ops hmm_walk_ops = {
  * This is similar to get_user_pages(), except that it can read the page tables
  * without mutating them (ie causing faults).
  */
-long hmm_range_fault(struct hmm_range *range)
+int hmm_range_fault(struct hmm_range *range)
 {
 	struct hmm_vma_walk hmm_vma_walk = {
 		.range = range,
@@ -590,10 +572,13 @@ long hmm_range_fault(struct hmm_range *range)
 			return -EBUSY;
 		ret = walk_page_range(mm, hmm_vma_walk.last, range->end,
 				      &hmm_walk_ops, &hmm_vma_walk);
+		/*
+		 * When -EBUSY is returned the loop restarts with
+		 * hmm_vma_walk.last set to an address that has not been stored
+		 * in pfns. All entries < last in the pfn array are set to their
+		 * output, and all >= are still at their input values.
+		 */
 	} while (ret == -EBUSY);
-
-	if (ret)
-		return ret;
-	return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
+	return ret;
 }
 EXPORT_SYMBOL(hmm_range_fault);

tools/testing/selftests/vm/.gitignore

@@ -17,3 +17,4 @@ gup_benchmark
 va_128TBswitch
 map_fixed_noreplace
 write_to_hugetlbfs
+hmm-tests

tools/testing/selftests/vm/Makefile

@@ -7,6 +7,7 @@ CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
 LDLIBS = -lrt
 TEST_GEN_FILES = compaction_test
 TEST_GEN_FILES += gup_benchmark
+TEST_GEN_FILES += hmm-tests
 TEST_GEN_FILES += hugepage-mmap
 TEST_GEN_FILES += hugepage-shm
 TEST_GEN_FILES += map_hugetlb
@@ -33,6 +34,8 @@ TEST_FILES := test_vmalloc.sh
 KSFT_KHDR_INSTALL := 1
 include ../lib.mk
 
+$(OUTPUT)/hmm-tests: LDLIBS += -lhugetlbfs -lpthread
+
 $(OUTPUT)/userfaultfd: LDLIBS += -lpthread
 
 $(OUTPUT)/mlock-random-test: LDLIBS += -lcap

tools/testing/selftests/vm/config

 CONFIG_SYSVIPC=y
 CONFIG_USERFAULTFD=y
 CONFIG_TEST_VMALLOC=m
+CONFIG_DEVICE_PRIVATE=y
+CONFIG_TEST_HMM=m

tools/testing/selftests/vm/hmm-tests.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * HMM stands for Heterogeneous Memory Management, it is a helper layer inside
+ * the linux kernel to help device drivers mirror a process address space in
+ * the device. This allows the device to use the same address space which
+ * makes communication and data exchange a lot easier.
+ *
+ * This framework's sole purpose is to exercise various code paths inside
+ * the kernel to make sure that HMM performs as expected and to flush out any
+ * bugs.
+ */
+
+#include "../kselftest_harness.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <strings.h>
+#include <time.h>
+#include <pthread.h>
+#include <hugetlbfs.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <sys/ioctl.h>
+
+/*
+ * This is a private UAPI to the kernel test module so it isn't exported
+ * in the usual include/uapi/... directory.
+ */
+#include "../../../../lib/test_hmm_uapi.h"
+
+struct hmm_buffer {
+	void		*ptr;
+	void		*mirror;
+	unsigned long	size;
+	int		fd;
+	uint64_t	cpages;
+	uint64_t	faults;
+};
+
+#define TWOMEG		(1 << 21)
+#define HMM_BUFFER_SIZE (1024 << 12)
+#define HMM_PATH_MAX    64
+#define NTIMES		256
+
+#define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1)))
+
+FIXTURE(hmm)
+{
+	int		fd;
+	unsigned int	page_size;
+	unsigned int	page_shift;
+};
+
+FIXTURE(hmm2)
+{
+	int		fd0;
+	int		fd1;
+	unsigned int	page_size;
+	unsigned int	page_shift;
+};
+
+static int hmm_open(int unit)
+{
+	char pathname[HMM_PATH_MAX];
+	int fd;
+
+	snprintf(pathname, sizeof(pathname), "/dev/hmm_dmirror%d", unit);
+	fd = open(pathname, O_RDWR, 0);
+	if (fd < 0)
+		fprintf(stderr, "could not open hmm dmirror driver (%s)\n",
+			pathname);
+	return fd;
+}
+
+FIXTURE_SETUP(hmm)
+{
+	self->page_size = sysconf(_SC_PAGE_SIZE);
+	self->page_shift = ffs(self->page_size) - 1;
+
+	self->fd = hmm_open(0);
+	ASSERT_GE(self->fd, 0);
+}
+
+FIXTURE_SETUP(hmm2)
+{
+	self->page_size = sysconf(_SC_PAGE_SIZE);
+	self->page_shift = ffs(self->page_size) - 1;
+
+	self->fd0 = hmm_open(0);
+	ASSERT_GE(self->fd0, 0);
+	self->fd1 = hmm_open(1);
+	ASSERT_GE(self->fd1, 0);
+}
+
+FIXTURE_TEARDOWN(hmm)
+{
+	int ret = close(self->fd);
+
+	ASSERT_EQ(ret, 0);
+	self->fd = -1;
+}
+
+FIXTURE_TEARDOWN(hmm2)
+{
+	int ret = close(self->fd0);
+
+	ASSERT_EQ(ret, 0);
+	self->fd0 = -1;
+
+	ret = close(self->fd1);
+	ASSERT_EQ(ret, 0);
+	self->fd1 = -1;
+}
+
+static int hmm_dmirror_cmd(int fd,
+			   unsigned long request,
+			   struct hmm_buffer *buffer,
+			   unsigned long npages)
+{
+	struct hmm_dmirror_cmd cmd;
+	int ret;
+
+	/* Simulate a device reading system memory. */
+	cmd.addr = (__u64)buffer->ptr;
+	cmd.ptr = (__u64)buffer->mirror;
+	cmd.npages = npages;
+
+	for (;;) {
+		ret = ioctl(fd, request, &cmd);
+		if (ret == 0)
+			break;
+		if (errno == EINTR)
+			continue;
+		return -errno;
+	}
+	buffer->cpages = cmd.cpages;
+	buffer->faults = cmd.faults;
+
+	return 0;
+}
+
+static void hmm_buffer_free(struct hmm_buffer *buffer)
+{
+	if (buffer == NULL)
+		return;
+
+	if (buffer->ptr)
+		munmap(buffer->ptr, buffer->size);
+	free(buffer->mirror);
+	free(buffer);
+}
+
+/*
+ * Create a temporary file that will be deleted on close.
+ */
+static int hmm_create_file(unsigned long size)
+{
+	char path[HMM_PATH_MAX];
+	int fd;
+
+	strcpy(path, "/tmp");
+	fd = open(path, O_TMPFILE | O_EXCL | O_RDWR, 0600);
+	if (fd >= 0) {
+		int r;
+
+		do {
+			r = ftruncate(fd, size);
+		} while (r == -1 && errno == EINTR);
+		if (!r)
+			return fd;
+		close(fd);
+	}
+	return -1;
+}
+
+/*
+ * Return a random unsigned number.
+ */
+static unsigned int hmm_random(void)
+{
+	static int fd = -1;
+	unsigned int r;
+
+	if (fd < 0) {
+		fd = open("/dev/urandom", O_RDONLY);
+		if (fd < 0) {
+			fprintf(stderr, "%s:%d failed to open /dev/urandom\n",
+					__FILE__, __LINE__);
+			return ~0U;
+		}
+	}
+	read(fd, &r, sizeof(r));
+	return r;
+}
+
+static void hmm_nanosleep(unsigned int n)
+{
+	struct timespec t;
+
+	t.tv_sec = 0;
+	t.tv_nsec = n;
+	nanosleep(&t, NULL);
+}
+
+/*
+ * Simple NULL test of device open/close.
+ */
+TEST_F(hmm, open_close)
+{
+}
+
+/*
+ * Read private anonymous memory.
+ */
+TEST_F(hmm, anon_read)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	int ret;
+	int val;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/*
+	 * Initialize buffer in system memory but leave the first two pages
+	 * zero (pte_none and pfn_zero).
+	 */
+	i = 2 * self->page_size / sizeof(*ptr);
+	for (ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Set buffer permission to read-only. */
+	ret = mprotect(buffer->ptr, size, PROT_READ);
+	ASSERT_EQ(ret, 0);
+
+	/* Populate the CPU page table with a special zero page. */
+	val = *(int *)(buffer->ptr + self->page_size);
+	ASSERT_EQ(val, 0);
+
+	/* Simulate a device reading system memory. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_READ, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+	ASSERT_EQ(buffer->faults, 1);
+
+	/* Check what the device read. */
+	ptr = buffer->mirror;
+	for (i = 0; i < 2 * self->page_size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], 0);
+	for (; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	hmm_buffer_free(buffer);
+}
+
+/*
+ * Read private anonymous memory which has been protected with
+ * mprotect() PROT_NONE.
+ */
+TEST_F(hmm, anon_read_prot)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	int ret;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Initialize buffer in system memory. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Initialize mirror buffer so we can verify it isn't written. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ptr[i] = -i;
+
+	/* Protect buffer from reading. */
+	ret = mprotect(buffer->ptr, size, PROT_NONE);
+	ASSERT_EQ(ret, 0);
+
+	/* Simulate a device reading system memory. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_READ, buffer, npages);
+	ASSERT_EQ(ret, -EFAULT);
+
+	/* Allow CPU to read the buffer so we can check it. */
+	ret = mprotect(buffer->ptr, size, PROT_READ);
+	ASSERT_EQ(ret, 0);
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	/* Check what the device read. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], -i);
+
+	hmm_buffer_free(buffer);
+}
+
+/*
+ * Write private anonymous memory.
+ */
+TEST_F(hmm, anon_write)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	int ret;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Initialize data that the device will write to buffer->ptr. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Simulate a device writing system memory. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_WRITE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+	ASSERT_EQ(buffer->faults, 1);
+
+	/* Check what the device wrote. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	hmm_buffer_free(buffer);
+}
+
+/*
+ * Write private anonymous memory which has been protected with
+ * mprotect() PROT_READ.
+ */
+TEST_F(hmm, anon_write_prot)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	int ret;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ,
+			   MAP_PRIVATE | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Simulate a device reading a zero page of memory. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_READ, buffer, 1);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, 1);
+	ASSERT_EQ(buffer->faults, 1);
+
+	/* Initialize data that the device will write to buffer->ptr. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Simulate a device writing system memory. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_WRITE, buffer, npages);
+	ASSERT_EQ(ret, -EPERM);
+
+	/* Check what the device wrote. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], 0);
+
+	/* Now allow writing and see that the zero page is replaced. */
+	ret = mprotect(buffer->ptr, size, PROT_WRITE | PROT_READ);
+	ASSERT_EQ(ret, 0);
+
+	/* Simulate a device writing system memory. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_WRITE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+	ASSERT_EQ(buffer->faults, 1);
+
+	/* Check what the device wrote. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	hmm_buffer_free(buffer);
+}
+
+/*
+ * Check that a device writing an anonymous private mapping
+ * will copy-on-write if a child process inherits the mapping.
+ */
+TEST_F(hmm, anon_write_child)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	pid_t pid;
+	int child_fd;
+	int ret;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Initialize buffer->ptr so we can tell if it is written. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Initialize data that the device will write to buffer->ptr. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ptr[i] = -i;
+
+	pid = fork();
+	if (pid == -1)
+		ASSERT_EQ(pid, 0);
+	if (pid != 0) {
+		waitpid(pid, &ret, 0);
+		ASSERT_EQ(WIFEXITED(ret), 1);
+
+		/* Check that the parent's buffer did not change. */
+		for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+			ASSERT_EQ(ptr[i], i);
+		return;
+	}
+
+	/* Check that we see the parent's values. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], -i);
+
+	/* The child process needs its own mirror to its own mm. */
+	child_fd = hmm_open(0);
+	ASSERT_GE(child_fd, 0);
+
+	/* Simulate a device writing system memory. */
+	ret = hmm_dmirror_cmd(child_fd, HMM_DMIRROR_WRITE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+	ASSERT_EQ(buffer->faults, 1);
+
+	/* Check what the device wrote. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], -i);
+
+	close(child_fd);
+	exit(0);
+}
+
+/*
+ * Check that a device writing an anonymous shared mapping
+ * will not copy-on-write if a child process inherits the mapping.
+ */
+TEST_F(hmm, anon_write_child_shared)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	pid_t pid;
+	int child_fd;
+	int ret;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_SHARED | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Initialize buffer->ptr so we can tell if it is written. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Initialize data that the device will write to buffer->ptr. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ptr[i] = -i;
+
+	pid = fork();
+	if (pid == -1)
+		ASSERT_EQ(pid, 0);
+	if (pid != 0) {
+		waitpid(pid, &ret, 0);
+		ASSERT_EQ(WIFEXITED(ret), 1);
+
+		/* Check that the parent's buffer did change. */
+		for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+			ASSERT_EQ(ptr[i], -i);
+		return;
+	}
+
+	/* Check that we see the parent's values. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], -i);
+
+	/* The child process needs its own mirror to its own mm. */
+	child_fd = hmm_open(0);
+	ASSERT_GE(child_fd, 0);
+
+	/* Simulate a device writing system memory. */
+	ret = hmm_dmirror_cmd(child_fd, HMM_DMIRROR_WRITE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+	ASSERT_EQ(buffer->faults, 1);
+
+	/* Check what the device wrote. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], -i);
+
+	close(child_fd);
+	exit(0);
+}
+
+/*
+ * Write private anonymous huge page.
+ */
+TEST_F(hmm, anon_write_huge)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	void *old_ptr;
+	void *map;
+	int *ptr;
+	int ret;
+
+	size = 2 * TWOMEG;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	size = TWOMEG;
+	npages = size >> self->page_shift;
+	map = (void *)ALIGN((uintptr_t)buffer->ptr, size);
+	ret = madvise(map, size, MADV_HUGEPAGE);
+	ASSERT_EQ(ret, 0);
+	old_ptr = buffer->ptr;
+	buffer->ptr = map;
+
+	/* Initialize data that the device will write to buffer->ptr. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Simulate a device writing system memory. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_WRITE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+	ASSERT_EQ(buffer->faults, 1);
+
+	/* Check what the device wrote. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	buffer->ptr = old_ptr;
+	hmm_buffer_free(buffer);
+}
+
+/*
+ * Write huge TLBFS page.
+ */
+TEST_F(hmm, anon_write_hugetlbfs)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	int ret;
+	long pagesizes[4];
+	int n, idx;
+
+	/* Skip test if we can't allocate a hugetlbfs page. */
+
+	n = gethugepagesizes(pagesizes, 4);
+	if (n <= 0)
+		return;
+	for (idx = 0; --n > 0; ) {
+		if (pagesizes[n] < pagesizes[idx])
+			idx = n;
+	}
+	size = ALIGN(TWOMEG, pagesizes[idx]);
+	npages = size >> self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->ptr = get_hugepage_region(size, GHR_STRICT);
+	if (buffer->ptr == NULL) {
+		free(buffer);
+		return;
+	}
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	/* Initialize data that the device will write to buffer->ptr. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Simulate a device writing system memory. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_WRITE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+	ASSERT_EQ(buffer->faults, 1);
+
+	/* Check what the device wrote. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	free_hugepage_region(buffer->ptr);
+	buffer->ptr = NULL;
+	hmm_buffer_free(buffer);
+}
+
+/*
+ * Read mmap'ed file memory.
+ */
+TEST_F(hmm, file_read)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	int ret;
+	int fd;
+	ssize_t len;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	fd = hmm_create_file(size);
+	ASSERT_GE(fd, 0);
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = fd;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	/* Write initial contents of the file. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+	len = pwrite(fd, buffer->mirror, size, 0);
+	ASSERT_EQ(len, size);
+	memset(buffer->mirror, 0, size);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ,
+			   MAP_SHARED,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Simulate a device reading system memory. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_READ, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+	ASSERT_EQ(buffer->faults, 1);
+
+	/* Check what the device read. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	hmm_buffer_free(buffer);
+}
+
+/*
+ * Write mmap'ed file memory.
+ */
+TEST_F(hmm, file_write)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	int ret;
+	int fd;
+	ssize_t len;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	fd = hmm_create_file(size);
+	ASSERT_GE(fd, 0);
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = fd;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_SHARED,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Initialize data that the device will write to buffer->ptr. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Simulate a device writing system memory. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_WRITE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+	ASSERT_EQ(buffer->faults, 1);
+
+	/* Check what the device wrote. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	/* Check that the device also wrote the file. */
+	len = pread(fd, buffer->mirror, size, 0);
+	ASSERT_EQ(len, size);
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	hmm_buffer_free(buffer);
+}
+
+/*
+ * Migrate anonymous memory to device private memory.
+ */
+TEST_F(hmm, migrate)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	int ret;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Initialize buffer in system memory. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Migrate memory to device. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+
+	/* Check what the device read. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	hmm_buffer_free(buffer);
+}
+
+/*
+ * Migrate anonymous memory to device private memory and fault it back to system
+ * memory.
+ */
+TEST_F(hmm, migrate_fault)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	int ret;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Initialize buffer in system memory. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Migrate memory to device. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+
+	/* Check what the device read. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	/* Fault pages back to system memory and check them. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	hmm_buffer_free(buffer);
+}
+
+/*
+ * Try to migrate various memory types to device private memory.
+ */
+TEST_F(hmm2, migrate_mixed)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	int *ptr;
+	unsigned char *p;
+	int ret;
+	int val;
+
+	npages = 6;
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	/* Reserve a range of addresses. */
+	buffer->ptr = mmap(NULL, size,
+			   PROT_NONE,
+			   MAP_PRIVATE | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+	p = buffer->ptr;
+
+	/* Migrating a protected area should be an error. */
+	ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, npages);
+	ASSERT_EQ(ret, -EINVAL);
+
+	/* Punch a hole after the first page address. */
+	ret = munmap(buffer->ptr + self->page_size, self->page_size);
+	ASSERT_EQ(ret, 0);
+
+	/* We expect an error if the vma doesn't cover the range. */
+	ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 3);
+	ASSERT_EQ(ret, -EINVAL);
+
+	/* Page 2 will be a read-only zero page. */
+	ret = mprotect(buffer->ptr + 2 * self->page_size, self->page_size,
+				PROT_READ);
+	ASSERT_EQ(ret, 0);
+	ptr = (int *)(buffer->ptr + 2 * self->page_size);
+	val = *ptr + 3;
+	ASSERT_EQ(val, 3);
+
+	/* Page 3 will be read-only. */
+	ret = mprotect(buffer->ptr + 3 * self->page_size, self->page_size,
+				PROT_READ | PROT_WRITE);
+	ASSERT_EQ(ret, 0);
+	ptr = (int *)(buffer->ptr + 3 * self->page_size);
+	*ptr = val;
+	ret = mprotect(buffer->ptr + 3 * self->page_size, self->page_size,
+				PROT_READ);
+	ASSERT_EQ(ret, 0);
+
+	/* Page 4-5 will be read-write. */
+	ret = mprotect(buffer->ptr + 4 * self->page_size, 2 * self->page_size,
+				PROT_READ | PROT_WRITE);
+	ASSERT_EQ(ret, 0);
+	ptr = (int *)(buffer->ptr + 4 * self->page_size);
+	*ptr = val;
+	ptr = (int *)(buffer->ptr + 5 * self->page_size);
+	*ptr = val;
+
+	/* Now try to migrate pages 2-5 to device 1. */
+	buffer->ptr = p + 2 * self->page_size;
+	ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 4);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, 4);
+
+	/* Page 5 won't be migrated to device 0 because it's on device 1. */
+	buffer->ptr = p + 5 * self->page_size;
+	ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_MIGRATE, buffer, 1);
+	ASSERT_EQ(ret, -ENOENT);
+	buffer->ptr = p;
+
+	buffer->ptr = p;
+	hmm_buffer_free(buffer);
+}
+
+/*
+ * Migrate anonymous memory to device private memory and fault it back to system
+ * memory multiple times.
+ */
+TEST_F(hmm, migrate_multiple)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	unsigned long c;
+	int *ptr;
+	int ret;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	for (c = 0; c < NTIMES; c++) {
+		buffer = malloc(sizeof(*buffer));
+		ASSERT_NE(buffer, NULL);
+
+		buffer->fd = -1;
+		buffer->size = size;
+		buffer->mirror = malloc(size);
+		ASSERT_NE(buffer->mirror, NULL);
+
+		buffer->ptr = mmap(NULL, size,
+				   PROT_READ | PROT_WRITE,
+				   MAP_PRIVATE | MAP_ANONYMOUS,
+				   buffer->fd, 0);
+		ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+		/* Initialize buffer in system memory. */
+		for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+			ptr[i] = i;
+
+		/* Migrate memory to device. */
+		ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer,
+				      npages);
+		ASSERT_EQ(ret, 0);
+		ASSERT_EQ(buffer->cpages, npages);
+
+		/* Check what the device read. */
+		for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+			ASSERT_EQ(ptr[i], i);
+
+		/* Fault pages back to system memory and check them. */
+		for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+			ASSERT_EQ(ptr[i], i);
+
+		hmm_buffer_free(buffer);
+	}
+}
+
+/*
+ * Read anonymous memory multiple times.
+ */
+TEST_F(hmm, anon_read_multiple)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	unsigned long c;
+	int *ptr;
+	int ret;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	for (c = 0; c < NTIMES; c++) {
+		buffer = malloc(sizeof(*buffer));
+		ASSERT_NE(buffer, NULL);
+
+		buffer->fd = -1;
+		buffer->size = size;
+		buffer->mirror = malloc(size);
+		ASSERT_NE(buffer->mirror, NULL);
+
+		buffer->ptr = mmap(NULL, size,
+				   PROT_READ | PROT_WRITE,
+				   MAP_PRIVATE | MAP_ANONYMOUS,
+				   buffer->fd, 0);
+		ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+		/* Initialize buffer in system memory. */
+		for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+			ptr[i] = i + c;
+
+		/* Simulate a device reading system memory. */
+		ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_READ, buffer,
+				      npages);
+		ASSERT_EQ(ret, 0);
+		ASSERT_EQ(buffer->cpages, npages);
+		ASSERT_EQ(buffer->faults, 1);
+
+		/* Check what the device read. */
+		for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+			ASSERT_EQ(ptr[i], i + c);
+
+		hmm_buffer_free(buffer);
+	}
+}
+
+void *unmap_buffer(void *p)
+{
+	struct hmm_buffer *buffer = p;
+
+	/* Delay for a bit and then unmap buffer while it is being read. */
+	hmm_nanosleep(hmm_random() % 32000);
+	munmap(buffer->ptr + buffer->size / 2, buffer->size / 2);
+	buffer->ptr = NULL;
+
+	return NULL;
+}
+
+/*
+ * Try reading anonymous memory while it is being unmapped.
+ */
+TEST_F(hmm, anon_teardown)
+{
+	unsigned long npages;
+	unsigned long size;
+	unsigned long c;
+	void *ret;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	for (c = 0; c < NTIMES; ++c) {
+		pthread_t thread;
+		struct hmm_buffer *buffer;
+		unsigned long i;
+		int *ptr;
+		int rc;
+
+		buffer = malloc(sizeof(*buffer));
+		ASSERT_NE(buffer, NULL);
+
+		buffer->fd = -1;
+		buffer->size = size;
+		buffer->mirror = malloc(size);
+		ASSERT_NE(buffer->mirror, NULL);
+
+		buffer->ptr = mmap(NULL, size,
+				   PROT_READ | PROT_WRITE,
+				   MAP_PRIVATE | MAP_ANONYMOUS,
+				   buffer->fd, 0);
+		ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+		/* Initialize buffer in system memory. */
+		for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+			ptr[i] = i + c;
+
+		rc = pthread_create(&thread, NULL, unmap_buffer, buffer);
+		ASSERT_EQ(rc, 0);
+
+		/* Simulate a device reading system memory. */
+		rc = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_READ, buffer,
+				     npages);
+		if (rc == 0) {
+			ASSERT_EQ(buffer->cpages, npages);
+			ASSERT_EQ(buffer->faults, 1);
+
+			/* Check what the device read. */
+			for (i = 0, ptr = buffer->mirror;
+			     i < size / sizeof(*ptr);
+			     ++i)
+				ASSERT_EQ(ptr[i], i + c);
+		}
+
+		pthread_join(thread, &ret);
+		hmm_buffer_free(buffer);
+	}
+}
+
+/*
+ * Test memory snapshot without faulting in pages accessed by the device.
+ */
+TEST_F(hmm2, snapshot)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	int *ptr;
+	unsigned char *p;
+	unsigned char *m;
+	int ret;
+	int val;
+
+	npages = 7;
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(npages);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	/* Reserve a range of addresses. */
+	buffer->ptr = mmap(NULL, size,
+			   PROT_NONE,
+			   MAP_PRIVATE | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+	p = buffer->ptr;
+
+	/* Punch a hole after the first page address. */
+	ret = munmap(buffer->ptr + self->page_size, self->page_size);
+	ASSERT_EQ(ret, 0);
+
+	/* Page 2 will be read-only zero page. */
+	ret = mprotect(buffer->ptr + 2 * self->page_size, self->page_size,
+				PROT_READ);
+	ASSERT_EQ(ret, 0);
+	ptr = (int *)(buffer->ptr + 2 * self->page_size);
+	val = *ptr + 3;
+	ASSERT_EQ(val, 3);
+
+	/* Page 3 will be read-only. */
+	ret = mprotect(buffer->ptr + 3 * self->page_size, self->page_size,
+				PROT_READ | PROT_WRITE);
+	ASSERT_EQ(ret, 0);
+	ptr = (int *)(buffer->ptr + 3 * self->page_size);
+	*ptr = val;
+	ret = mprotect(buffer->ptr + 3 * self->page_size, self->page_size,
+				PROT_READ);
+	ASSERT_EQ(ret, 0);
+
+	/* Page 4-6 will be read-write. */
+	ret = mprotect(buffer->ptr + 4 * self->page_size, 3 * self->page_size,
+				PROT_READ | PROT_WRITE);
+	ASSERT_EQ(ret, 0);
+	ptr = (int *)(buffer->ptr + 4 * self->page_size);
+	*ptr = val;
+
+	/* Page 5 will be migrated to device 0. */
+	buffer->ptr = p + 5 * self->page_size;
+	ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_MIGRATE, buffer, 1);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, 1);
+
+	/* Page 6 will be migrated to device 1. */
+	buffer->ptr = p + 6 * self->page_size;
+	ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 1);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, 1);
+
+	/* Simulate a device snapshotting CPU pagetables. */
+	buffer->ptr = p;
+	ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_SNAPSHOT, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+
+	/* Check what the device saw. */
+	m = buffer->mirror;
+	ASSERT_EQ(m[0], HMM_DMIRROR_PROT_ERROR);
+	ASSERT_EQ(m[1], HMM_DMIRROR_PROT_ERROR);
+	ASSERT_EQ(m[2], HMM_DMIRROR_PROT_ZERO | HMM_DMIRROR_PROT_READ);
+	ASSERT_EQ(m[3], HMM_DMIRROR_PROT_READ);
+	ASSERT_EQ(m[4], HMM_DMIRROR_PROT_WRITE);
+	ASSERT_EQ(m[5], HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL |
+			HMM_DMIRROR_PROT_WRITE);
+	ASSERT_EQ(m[6], HMM_DMIRROR_PROT_NONE);
+
+	hmm_buffer_free(buffer);
+}
+
+/*
+ * Test two devices reading the same memory (double mapped).
+ */
+TEST_F(hmm2, double_map)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	int ret;
+
+	npages = 6;
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(npages);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	/* Reserve a range of addresses. */
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Initialize buffer in system memory. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Make region read-only. */
+	ret = mprotect(buffer->ptr, size, PROT_READ);
+	ASSERT_EQ(ret, 0);
+
+	/* Simulate device 0 reading system memory. */
+	ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_READ, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+	ASSERT_EQ(buffer->faults, 1);
+
+	/* Check what the device read. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	/* Simulate device 1 reading system memory. */
+	ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_READ, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+	ASSERT_EQ(buffer->faults, 1);
+
+	/* Check what the device read. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	/* Punch a hole after the first page address. */
+	ret = munmap(buffer->ptr + self->page_size, self->page_size);
+	ASSERT_EQ(ret, 0);
+
+	hmm_buffer_free(buffer);
+}
+
+TEST_HARNESS_MAIN

tools/testing/selftests/vm/run_vmtests

@@ -307,4 +307,20 @@ else
 	echo "[FAIL]"
 	exitcode=1
 fi
+
+echo "running HMM smoke test"
+echo "------------------------------------"
+./test_hmm.sh smoke
+ret_val=$?
+
+if [ $ret_val -eq 0 ]; then
+	echo "[PASS]"
+elif [ $ret_val -eq $ksft_skip ]; then
+	echo "[SKIP]"
+	exitcode=$ksft_skip
+else
+	echo "[FAIL]"
+	exitcode=1
+fi
+
 exit $exitcode

tools/testing/selftests/vm/test_hmm.sh

+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2018 Uladzislau Rezki (Sony) <urezki@gmail.com>
+#
+# This is a test script for the kernel test driver to analyse vmalloc
+# allocator. Therefore it is just a kernel module loader. You can specify
+# and pass different parameters in order to:
+#     a) analyse performance of vmalloc allocations;
+#     b) stressing and stability check of vmalloc subsystem.
+
+TEST_NAME="test_hmm"
+DRIVER="test_hmm"
+
+# 1 if fails
+exitcode=1
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+check_test_requirements()
+{
+	uid=$(id -u)
+	if [ $uid -ne 0 ]; then
+		echo "$0: Must be run as root"
+		exit $ksft_skip
+	fi
+
+	if ! which modprobe > /dev/null 2>&1; then
+		echo "$0: You need modprobe installed"
+		exit $ksft_skip
+	fi
+
+	if ! modinfo $DRIVER > /dev/null 2>&1; then
+		echo "$0: You must have the following enabled in your kernel:"
+		echo "CONFIG_TEST_HMM=m"
+		exit $ksft_skip
+	fi
+}
+
+load_driver()
+{
+	modprobe $DRIVER > /dev/null 2>&1
+	if [ $? == 0 ]; then
+		major=$(awk "\$2==\"HMM_DMIRROR\" {print \$1}" /proc/devices)
+		mknod /dev/hmm_dmirror0 c $major 0
+		mknod /dev/hmm_dmirror1 c $major 1
+	fi
+}
+
+unload_driver()
+{
+	modprobe -r $DRIVER > /dev/null 2>&1
+	rm -f /dev/hmm_dmirror?
+}
+
+run_smoke()
+{
+	echo "Running smoke test. Note, this test provides basic coverage."
+
+	load_driver
+	$(dirname "${BASH_SOURCE[0]}")/hmm-tests
+	unload_driver
+}
+
+usage()
+{
+	echo -n "Usage: $0"
+	echo
+	echo "Example usage:"
+	echo
+	echo "# Shows help message"
+	echo "./${TEST_NAME}.sh"
+	echo
+	echo "# Smoke testing"
+	echo "./${TEST_NAME}.sh smoke"
+	echo
+	exit 0
+}
+
+function run_test()
+{
+	if [ $# -eq 0 ]; then
+		usage
+	else
+		if [ "$1" = "smoke" ]; then
+			run_smoke
+		else
+			usage
+		fi
+	fi
+}
+
+check_test_requirements
+run_test $@
+
+exit 0