Merge tag 'mm-stable-2022-10-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull more MM updates from Andrew Morton:

- fix a race which causes page refcounting errors in ZONE_DEVICE pages
(Alistair Popple)

- fix userfaultfd test harness instability (Peter Xu)

- various other patches in MM, mainly fixes

* tag 'mm-stable-2022-10-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (29 commits)
highmem: fix kmap_to_page() for kmap_local_page() addresses
mm/page_alloc: fix incorrect PGFREE and PGALLOC for high-order page
mm/selftest: uffd: explain the write missing fault check
mm/hugetlb: use hugetlb_pte_stable in migration race check
mm/hugetlb: fix race condition of uffd missing/minor handling
zram: always expose rw_page
LoongArch: update local TLB if PTE entry exists
mm: use update_mmu_tlb() on the second thread
kasan: fix array-bounds warnings in tests
hmm-tests: add test for migrate_device_range()
nouveau/dmem: evict device private memory during release
nouveau/dmem: refactor nouveau_dmem_fault_copy_one()
mm/migrate_device.c: add migrate_device_range()
mm/migrate_device.c: refactor migrate_vma and migrate_deivce_coherent_page()
mm/memremap.c: take a pgmap reference on page allocation
mm: free device private pages have zero refcount
mm/memory.c: fix race when faulting a device private page
mm/damon: use damon_sz_region() in appropriate place
mm/damon: move sz_damon_region to damon_sz_region
lib/test_meminit: add checks for the allocation functions
...

arch/loongarch/include/asm/pgtable.h

···
 	__update_tlb(vma, address, ptep);
 }
 
+#define __HAVE_ARCH_UPDATE_MMU_TLB
+#define update_mmu_tlb	update_mmu_cache
+
 static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
 			unsigned long address, pmd_t *pmdp)
 {

arch/powerpc/kvm/book3s_hv_uvmem.c

···
 static int __kvmppc_svm_page_out(struct vm_area_struct *vma,
 		unsigned long start,
 		unsigned long end, unsigned long page_shift,
-		struct kvm *kvm, unsigned long gpa)
+		struct kvm *kvm, unsigned long gpa, struct page *fault_page)
 {
 	unsigned long src_pfn, dst_pfn = 0;
-	struct migrate_vma mig;
+	struct migrate_vma mig = { 0 };
 	struct page *dpage, *spage;
 	struct kvmppc_uvmem_page_pvt *pvt;
 	unsigned long pfn;
···
 	mig.dst = &dst_pfn;
 	mig.pgmap_owner = &kvmppc_uvmem_pgmap;
 	mig.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
+	mig.fault_page = fault_page;
 
 	/* The requested page is already paged-out, nothing to do */
 	if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL))
···
 static inline int kvmppc_svm_page_out(struct vm_area_struct *vma,
 				      unsigned long start, unsigned long end,
 				      unsigned long page_shift,
-				      struct kvm *kvm, unsigned long gpa)
+				      struct kvm *kvm, unsigned long gpa,
+				      struct page *fault_page)
 {
 	int ret;
 
 	mutex_lock(&kvm->arch.uvmem_lock);
-	ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa);
+	ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa,
+				fault_page);
 	mutex_unlock(&kvm->arch.uvmem_lock);
 
 	return ret;
···
 			pvt->remove_gfn = true;
 
 			if (__kvmppc_svm_page_out(vma, addr, addr + PAGE_SIZE,
-						  PAGE_SHIFT, kvm, pvt->gpa))
+						  PAGE_SHIFT, kvm, pvt->gpa, NULL))
 				pr_err("Can't page out gpa:0x%lx addr:0x%lx\n",
 				       pvt->gpa, addr);
 		} else {
···
 
 	dpage = pfn_to_page(uvmem_pfn);
 	dpage->zone_device_data = pvt;
-	lock_page(dpage);
+	zone_device_page_init(dpage);
 	return dpage;
 out_clear:
 	spin_lock(&kvmppc_uvmem_bitmap_lock);
···
 		bool pagein)
 {
 	unsigned long src_pfn, dst_pfn = 0;
-	struct migrate_vma mig;
+	struct migrate_vma mig = { 0 };
 	struct page *spage;
 	unsigned long pfn;
 	struct page *dpage;
···
 
 	if (kvmppc_svm_page_out(vmf->vma, vmf->address,
 				vmf->address + PAGE_SIZE, PAGE_SHIFT,
-				pvt->kvm, pvt->gpa))
+				pvt->kvm, pvt->gpa, vmf->page))
 		return VM_FAULT_SIGBUS;
 	else
 		return 0;
···
 	if (!vma || vma->vm_start > start || vma->vm_end < end)
 		goto out;
 
-	if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa))
+	if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa, NULL))
 		ret = H_SUCCESS;
 out:
 	mmap_read_unlock(kvm->mm);

drivers/block/zram/zram_drv.c

···
 static size_t huge_class_size;
 
 static const struct block_device_operations zram_devops;
-#ifdef CONFIG_ZRAM_WRITEBACK
-static const struct block_device_operations zram_wb_devops;
-#endif
 
 static void zram_free_page(struct zram *zram, size_t index);
 static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
···
 	zram->backing_dev = backing_dev;
 	zram->bitmap = bitmap;
 	zram->nr_pages = nr_pages;
-	/*
-	 * With writeback feature, zram does asynchronous IO so it's no longer
-	 * synchronous device so let's remove synchronous io flag. Othewise,
-	 * upper layer(e.g., swap) could wait IO completion rather than
-	 * (submit and return), which will cause system sluggish.
-	 * Furthermore, when the IO function returns(e.g., swap_readpage),
-	 * upper layer expects IO was done so it could deallocate the page
-	 * freely but in fact, IO is going on so finally could cause
-	 * use-after-free when the IO is really done.
-	 */
-	zram->disk->fops = &zram_wb_devops;
 	up_write(&zram->init_lock);
 
 	pr_info("setup backing device %s\n", file_name);
···
 		struct bio_vec bvec;
 
 		zram_slot_unlock(zram, index);
+		/* A null bio means rw_page was used, we must fallback to bio */
+		if (!bio)
+			return -EOPNOTSUPP;
 
 		bvec.bv_page = page;
 		bvec.bv_len = PAGE_SIZE;
···
 	.rw_page = zram_rw_page,
 	.owner = THIS_MODULE
 };
-
-#ifdef CONFIG_ZRAM_WRITEBACK
-static const struct block_device_operations zram_wb_devops = {
-	.open = zram_open,
-	.submit_bio = zram_submit_bio,
-	.swap_slot_free_notify = zram_slot_free_notify,
-	.owner = THIS_MODULE
-};
-#endif
 
 static DEVICE_ATTR_WO(compact);
 static DEVICE_ATTR_RW(disksize);

drivers/gpu/drm/amd/amdkfd/kfd_migrate.c

···
 	page = pfn_to_page(pfn);
 	svm_range_bo_ref(prange->svm_bo);
 	page->zone_device_data = prange->svm_bo;
-	lock_page(page);
+	zone_device_page_init(page);
 }
 
 static void
···
 	uint64_t npages = (end - start) >> PAGE_SHIFT;
 	struct kfd_process_device *pdd;
 	struct dma_fence *mfence = NULL;
-	struct migrate_vma migrate;
+	struct migrate_vma migrate = { 0 };
 	unsigned long cpages = 0;
 	dma_addr_t *scratch;
 	void *buf;
···
 static long
 svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 		       struct vm_area_struct *vma, uint64_t start, uint64_t end,
-		       uint32_t trigger)
+		       uint32_t trigger, struct page *fault_page)
 {
 	struct kfd_process *p = container_of(prange->svms, struct kfd_process, svms);
 	uint64_t npages = (end - start) >> PAGE_SHIFT;
···
 	unsigned long cpages = 0;
 	struct kfd_process_device *pdd;
 	struct dma_fence *mfence = NULL;
-	struct migrate_vma migrate;
+	struct migrate_vma migrate = { 0 };
 	dma_addr_t *scratch;
 	void *buf;
 	int r = -ENOMEM;
···
 
 	migrate.src = buf;
 	migrate.dst = migrate.src + npages;
+	migrate.fault_page = fault_page;
 	scratch = (dma_addr_t *)(migrate.dst + npages);
 
 	kfd_smi_event_migration_start(adev->kfd.dev, p->lead_thread->pid,
···
  * 0 - OK, otherwise error code
  */
 int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm,
-			    uint32_t trigger)
+			    uint32_t trigger, struct page *fault_page)
 {
 	struct amdgpu_device *adev;
 	struct vm_area_struct *vma;
···
 		}
 
 		next = min(vma->vm_end, end);
-		r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next, trigger);
+		r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next, trigger,
+			fault_page);
 		if (r < 0) {
 			pr_debug("failed %ld to migrate prange %p\n", r, prange);
 			break;
···
 	pr_debug("from gpu 0x%x to gpu 0x%x\n", prange->actual_loc, best_loc);
 
 	do {
-		r = svm_migrate_vram_to_ram(prange, mm, trigger);
+		r = svm_migrate_vram_to_ram(prange, mm, trigger, NULL);
 		if (r)
 			return r;
 	} while (prange->actual_loc && --retries);
···
 	}
 
 	r = svm_migrate_vram_to_ram(prange, vmf->vma->vm_mm,
-				    KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU);
+				    KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU,
+				    vmf->page);
 	if (r)
 		pr_debug("failed %d migrate svms 0x%p range 0x%p [0x%lx 0x%lx]\n",
 			 r, prange->svms, prange, prange->start, prange->last);

drivers/gpu/drm/amd/amdkfd/kfd_migrate.h

···
 int svm_migrate_to_vram(struct svm_range *prange,  uint32_t best_loc,
 			struct mm_struct *mm, uint32_t trigger);
 int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm,
-			    uint32_t trigger);
+			    uint32_t trigger, struct page *fault_page);
 unsigned long
 svm_migrate_addr_to_pfn(struct amdgpu_device *adev, unsigned long addr);
 

drivers/gpu/drm/amd/amdkfd/kfd_svm.c

···
 				 */
 				if (prange->actual_loc)
 					r = svm_migrate_vram_to_ram(prange, mm,
-					   KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU);
+					   KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU,
+					   NULL);
 				else
 					r = 0;
 			}
 		} else {
 			r = svm_migrate_vram_to_ram(prange, mm,
-					KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU);
+					KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU,
+					NULL);
 		}
 		if (r) {
 			pr_debug("failed %d to migrate svms %p [0x%lx 0x%lx]\n",
···
 		return 0;
 
 	if (!best_loc) {
-		r = svm_migrate_vram_to_ram(prange, mm, KFD_MIGRATE_TRIGGER_PREFETCH);
+		r = svm_migrate_vram_to_ram(prange, mm,
+					KFD_MIGRATE_TRIGGER_PREFETCH, NULL);
 		*migrated = !r;
 		return r;
 	}
···
 		mutex_lock(&prange->migrate_mutex);
 		do {
 			r = svm_migrate_vram_to_ram(prange, mm,
-						KFD_MIGRATE_TRIGGER_TTM_EVICTION);
+					KFD_MIGRATE_TRIGGER_TTM_EVICTION, NULL);
 		} while (!r && prange->actual_loc && --retries);
 
 		if (!r && prange->actual_loc)

drivers/gpu/drm/nouveau/nouveau_dmem.c

···
 	}
 }
 
-static vm_fault_t nouveau_dmem_fault_copy_one(struct nouveau_drm *drm,
-		struct vm_fault *vmf, struct migrate_vma *args,
-		dma_addr_t *dma_addr)
+static int nouveau_dmem_copy_one(struct nouveau_drm *drm, struct page *spage,
+				struct page *dpage, dma_addr_t *dma_addr)
 {
 	struct device *dev = drm->dev->dev;
-	struct page *dpage, *spage;
-	struct nouveau_svmm *svmm;
 
-	spage = migrate_pfn_to_page(args->src[0]);
-	if (!spage || !(args->src[0] & MIGRATE_PFN_MIGRATE))
-		return 0;
-
-	dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address);
-	if (!dpage)
-		return VM_FAULT_SIGBUS;
 	lock_page(dpage);
 
 	*dma_addr = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_BIDIRECTIONAL);
 	if (dma_mapping_error(dev, *dma_addr))
-		goto error_free_page;
+		return -EIO;
 
-	svmm = spage->zone_device_data;
-	mutex_lock(&svmm->mutex);
-	nouveau_svmm_invalidate(svmm, args->start, args->end);
 	if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_HOST, *dma_addr,
-			NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage)))
-		goto error_dma_unmap;
-	mutex_unlock(&svmm->mutex);
+					 NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage))) {
+		dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
+		return -EIO;
+	}
 
-	args->dst[0] = migrate_pfn(page_to_pfn(dpage));
 	return 0;
-
-error_dma_unmap:
-	mutex_unlock(&svmm->mutex);
-	dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
-error_free_page:
-	__free_page(dpage);
-	return VM_FAULT_SIGBUS;
 }
 
 static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf)
···
 	struct nouveau_drm *drm = page_to_drm(vmf->page);
 	struct nouveau_dmem *dmem = drm->dmem;
 	struct nouveau_fence *fence;
+	struct nouveau_svmm *svmm;
+	struct page *spage, *dpage;
 	unsigned long src = 0, dst = 0;
 	dma_addr_t dma_addr = 0;
-	vm_fault_t ret;
+	vm_fault_t ret = 0;
 	struct migrate_vma args = {
 		.vma		= vmf->vma,
 		.start		= vmf->address,
···
 	if (!args.cpages)
 		return 0;
 
-	ret = nouveau_dmem_fault_copy_one(drm, vmf, &args, &dma_addr);
-	if (ret || dst == 0)
+	spage = migrate_pfn_to_page(src);
+	if (!spage || !(src & MIGRATE_PFN_MIGRATE))
 		goto done;
+
+	dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address);
+	if (!dpage)
+		goto done;
+
+	dst = migrate_pfn(page_to_pfn(dpage));
+
+	svmm = spage->zone_device_data;
+	mutex_lock(&svmm->mutex);
+	nouveau_svmm_invalidate(svmm, args.start, args.end);
+	ret = nouveau_dmem_copy_one(drm, spage, dpage, &dma_addr);
+	mutex_unlock(&svmm->mutex);
+	if (ret) {
+		ret = VM_FAULT_SIGBUS;
+		goto done;
+	}
 
 	nouveau_fence_new(dmem->migrate.chan, false, &fence);
 	migrate_vma_pages(&args);
···
 			return NULL;
 	}
 
-	lock_page(page);
+	zone_device_page_init(page);
 	return page;
 }
 
···
 	mutex_unlock(&drm->dmem->mutex);
 }
 
+/*
+ * Evict all pages mapping a chunk.
+ */
+static void
+nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk)
+{
+	unsigned long i, npages = range_len(&chunk->pagemap.range) >> PAGE_SHIFT;
+	unsigned long *src_pfns, *dst_pfns;
+	dma_addr_t *dma_addrs;
+	struct nouveau_fence *fence;
+
+	src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL);
+	dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL);
+	dma_addrs = kcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL);
+
+	migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT,
+			npages);
+
+	for (i = 0; i < npages; i++) {
+		if (src_pfns[i] & MIGRATE_PFN_MIGRATE) {
+			struct page *dpage;
+
+			/*
+			 * _GFP_NOFAIL because the GPU is going away and there
+			 * is nothing sensible we can do if we can't copy the
+			 * data back.
+			 */
+			dpage = alloc_page(GFP_HIGHUSER | __GFP_NOFAIL);
+			dst_pfns[i] = migrate_pfn(page_to_pfn(dpage));
+			nouveau_dmem_copy_one(chunk->drm,
+					migrate_pfn_to_page(src_pfns[i]), dpage,
+					&dma_addrs[i]);
+		}
+	}
+
+	nouveau_fence_new(chunk->drm->dmem->migrate.chan, false, &fence);
+	migrate_device_pages(src_pfns, dst_pfns, npages);
+	nouveau_dmem_fence_done(&fence);
+	migrate_device_finalize(src_pfns, dst_pfns, npages);
+	kfree(src_pfns);
+	kfree(dst_pfns);
+	for (i = 0; i < npages; i++)
+		dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL);
+	kfree(dma_addrs);
+}
+
 void
 nouveau_dmem_fini(struct nouveau_drm *drm)
 {
···
 	mutex_lock(&drm->dmem->mutex);
 
 	list_for_each_entry_safe(chunk, tmp, &drm->dmem->chunks, list) {
+		nouveau_dmem_evict_chunk(chunk);
 		nouveau_bo_unpin(chunk->bo);
 		nouveau_bo_ref(NULL, &chunk->bo);
+		WARN_ON(chunk->callocated);
 		list_del(&chunk->list);
 		memunmap_pages(&chunk->pagemap);
 		release_mem_region(chunk->pagemap.range.start,

fs/ext4/verity.c

···
 					       pgoff_t index,
 					       unsigned long num_ra_pages)
 {
-	DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index);
 	struct page *page;
 
 	index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT;
 
 	page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED);
 	if (!page || !PageUptodate(page)) {
+		DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index);
+
 		if (page)
 			put_page(page);
 		else if (num_ra_pages > 1)

fs/f2fs/verity.c

···
 					       pgoff_t index,
 					       unsigned long num_ra_pages)
 {
-	DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index);
 	struct page *page;
 
 	index += f2fs_verity_metadata_pos(inode) >> PAGE_SHIFT;
 
 	page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED);
 	if (!page || !PageUptodate(page)) {
+		DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index);
+
 		if (page)
 			put_page(page);
 		else if (num_ra_pages > 1)

include/linux/damon.h

···
 	return list_first_entry(&t->regions_list, struct damon_region, list);
 }
 
+static inline unsigned long damon_sz_region(struct damon_region *r)
+{
+	return r->ar.end - r->ar.start;
+}
+
+
 #define damon_for_each_region(r, t) \
 	list_for_each_entry(r, &t->regions_list, list)
 

include/linux/memremap.h

···
 }
 
 #ifdef CONFIG_ZONE_DEVICE
+void zone_device_page_init(struct page *page);
 void *memremap_pages(struct dev_pagemap *pgmap, int nid);
 void memunmap_pages(struct dev_pagemap *pgmap);
 void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap);

include/linux/migrate.h

···
 #ifdef CONFIG_MIGRATION
 
 extern void putback_movable_pages(struct list_head *l);
+int migrate_folio_extra(struct address_space *mapping, struct folio *dst,
+		struct folio *src, enum migrate_mode mode, int extra_count);
 int migrate_folio(struct address_space *mapping, struct folio *dst,
 		struct folio *src, enum migrate_mode mode);
 extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
···
 	 */
 	void			*pgmap_owner;
 	unsigned long		flags;
+
+	/*
+	 * Set to vmf->page if this is being called to migrate a page as part of
+	 * a migrate_to_ram() callback.
+	 */
+	struct page		*fault_page;
 };
 
 int migrate_vma_setup(struct migrate_vma *args);
 void migrate_vma_pages(struct migrate_vma *migrate);
 void migrate_vma_finalize(struct migrate_vma *migrate);
+int migrate_device_range(unsigned long *src_pfns, unsigned long start,
+			unsigned long npages);
+void migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns,
+			unsigned long npages);
+void migrate_device_finalize(unsigned long *src_pfns,
+			unsigned long *dst_pfns, unsigned long npages);
+
 #endif /* CONFIG_MIGRATION */
 
 #endif /* _LINUX_MIGRATE_H */

include/linux/sched.h

···
 	struct mm_struct		*mm;
 	struct mm_struct		*active_mm;
 
-	/* Per-thread vma caching: */
-
 #ifdef SPLIT_RSS_COUNTING
 	struct task_rss_stat		rss_stat;
 #endif

lib/test_hmm.c

···
 struct dmirror_chunk {
 	struct dev_pagemap	pagemap;
 	struct dmirror_device	*mdevice;
+	bool remove;
 };
 
 /*
···
 	return 0;
 }
 
+static struct dmirror_chunk *dmirror_page_to_chunk(struct page *page)
+{
+	return container_of(page->pgmap, struct dmirror_chunk, pagemap);
+}
+
 static struct dmirror_device *dmirror_page_to_device(struct page *page)
 
 {
-	return container_of(page->pgmap, struct dmirror_chunk,
-			    pagemap)->mdevice;
+	return dmirror_page_to_chunk(page)->mdevice;
 }
 
 static int dmirror_do_fault(struct dmirror *dmirror, struct hmm_range *range)
···
 			goto error;
 	}
 
+	zone_device_page_init(dpage);
 	dpage->zone_device_data = rpage;
-	lock_page(dpage);
 	return dpage;
 
 error:
···
 	struct vm_area_struct *vma;
 	unsigned long src_pfns[64] = { 0 };
 	unsigned long dst_pfns[64] = { 0 };
-	struct migrate_vma args;
+	struct migrate_vma args = { 0 };
 	unsigned long next;
 	int ret;
 
···
 	unsigned long src_pfns[64] = { 0 };
 	unsigned long dst_pfns[64] = { 0 };
 	struct dmirror_bounce bounce;
-	struct migrate_vma args;
+	struct migrate_vma args = { 0 };
 	unsigned long next;
 	int ret;
 
···
 	return ret;
 }
 
+static void dmirror_device_evict_chunk(struct dmirror_chunk *chunk)
+{
+	unsigned long start_pfn = chunk->pagemap.range.start >> PAGE_SHIFT;
+	unsigned long end_pfn = chunk->pagemap.range.end >> PAGE_SHIFT;
+	unsigned long npages = end_pfn - start_pfn + 1;
+	unsigned long i;
+	unsigned long *src_pfns;
+	unsigned long *dst_pfns;
+
+	src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL);
+	dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL);
+
+	migrate_device_range(src_pfns, start_pfn, npages);
+	for (i = 0; i < npages; i++) {
+		struct page *dpage, *spage;
+
+		spage = migrate_pfn_to_page(src_pfns[i]);
+		if (!spage || !(src_pfns[i] & MIGRATE_PFN_MIGRATE))
+			continue;
+
+		if (WARN_ON(!is_device_private_page(spage) &&
+			    !is_device_coherent_page(spage)))
+			continue;
+		spage = BACKING_PAGE(spage);
+		dpage = alloc_page(GFP_HIGHUSER_MOVABLE | __GFP_NOFAIL);
+		lock_page(dpage);
+		copy_highpage(dpage, spage);
+		dst_pfns[i] = migrate_pfn(page_to_pfn(dpage));
+		if (src_pfns[i] & MIGRATE_PFN_WRITE)
+			dst_pfns[i] |= MIGRATE_PFN_WRITE;
+	}
+	migrate_device_pages(src_pfns, dst_pfns, npages);
+	migrate_device_finalize(src_pfns, dst_pfns, npages);
+	kfree(src_pfns);
+	kfree(dst_pfns);
+}
+
+/* Removes free pages from the free list so they can't be re-allocated */
+static void dmirror_remove_free_pages(struct dmirror_chunk *devmem)
+{
+	struct dmirror_device *mdevice = devmem->mdevice;
+	struct page *page;
+
+	for (page = mdevice->free_pages; page; page = page->zone_device_data)
+		if (dmirror_page_to_chunk(page) == devmem)
+			mdevice->free_pages = page->zone_device_data;
+}
+
+static void dmirror_device_remove_chunks(struct dmirror_device *mdevice)
+{
+	unsigned int i;
+
+	mutex_lock(&mdevice->devmem_lock);
+	if (mdevice->devmem_chunks) {
+		for (i = 0; i < mdevice->devmem_count; i++) {
+			struct dmirror_chunk *devmem =
+				mdevice->devmem_chunks[i];
+
+			spin_lock(&mdevice->lock);
+			devmem->remove = true;
+			dmirror_remove_free_pages(devmem);
+			spin_unlock(&mdevice->lock);
+
+			dmirror_device_evict_chunk(devmem);
+			memunmap_pages(&devmem->pagemap);
+			if (devmem->pagemap.type == MEMORY_DEVICE_PRIVATE)
+				release_mem_region(devmem->pagemap.range.start,
+						   range_len(&devmem->pagemap.range));
+			kfree(devmem);
+		}
+		mdevice->devmem_count = 0;
+		mdevice->devmem_capacity = 0;
+		mdevice->free_pages = NULL;
+		kfree(mdevice->devmem_chunks);
+		mdevice->devmem_chunks = NULL;
+	}
+	mutex_unlock(&mdevice->devmem_lock);
+}
+
 static long dmirror_fops_unlocked_ioctl(struct file *filp,
 					unsigned int command,
 					unsigned long arg)
···
 
 	case HMM_DMIRROR_SNAPSHOT:
 		ret = dmirror_snapshot(dmirror, &cmd);
+		break;
+
+	case HMM_DMIRROR_RELEASE:
+		dmirror_device_remove_chunks(dmirror->mdevice);
+		ret = 0;
 		break;
 
 	default:
···
 
 	mdevice = dmirror_page_to_device(page);
 	spin_lock(&mdevice->lock);
-	mdevice->cfree++;
-	page->zone_device_data = mdevice->free_pages;
-	mdevice->free_pages = page;
+
+	/* Return page to our allocator if not freeing the chunk */
+	if (!dmirror_page_to_chunk(page)->remove) {
+		mdevice->cfree++;
+		page->zone_device_data = mdevice->free_pages;
+		mdevice->free_pages = page;
+	}
 	spin_unlock(&mdevice->lock);
 }
 
 static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 {
-	struct migrate_vma args;
+	struct migrate_vma args = { 0 };
 	unsigned long src_pfns = 0;
 	unsigned long dst_pfns = 0;
 	struct page *rpage;
···
 	args.dst = &dst_pfns;
 	args.pgmap_owner = dmirror->mdevice;
 	args.flags = dmirror_select_device(dmirror);
+	args.fault_page = vmf->page;
 
 	if (migrate_vma_setup(&args))
 		return VM_FAULT_SIGBUS;
···
 
 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);
-			if (devmem->pagemap.type == MEMORY_DEVICE_PRIVATE)
-				release_mem_region(devmem->pagemap.range.start,
-						   range_len(&devmem->pagemap.range));
-			kfree(devmem);
-		}
-		kfree(mdevice->devmem_chunks);
-	}
-
+	dmirror_device_remove_chunks(mdevice);
 	cdev_device_del(&mdevice->cdevice, &mdevice->device);
 }
 

lib/test_hmm_uapi.h

···
 #define HMM_DMIRROR_SNAPSHOT		_IOWR('H', 0x04, struct hmm_dmirror_cmd)
 #define HMM_DMIRROR_EXCLUSIVE		_IOWR('H', 0x05, struct hmm_dmirror_cmd)
 #define HMM_DMIRROR_CHECK_EXCLUSIVE	_IOWR('H', 0x06, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_RELEASE		_IOWR('H', 0x07, struct hmm_dmirror_cmd)
 
 /*
  * Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT.

lib/test_meminit.c

···
 	size_t size = PAGE_SIZE << order;
 
 	page = alloc_pages(GFP_KERNEL, order);
+	if (!page)
+		goto err;
 	buf = page_address(page);
 	fill_with_garbage(buf, size);
 	__free_pages(page, order);
 
 	page = alloc_pages(GFP_KERNEL, order);
+	if (!page)
+		goto err;
 	buf = page_address(page);
 	if (count_nonzero_bytes(buf, size))
 		(*total_failures)++;
 	fill_with_garbage(buf, size);
 	__free_pages(page, order);
+	return 1;
+err:
+	(*total_failures)++;
 	return 1;
 }
 
···
 	void *buf;
 
 	buf = kmalloc(size, GFP_KERNEL);
+	if (!buf)
+		goto err;
 	fill_with_garbage(buf, size);
 	kfree(buf);
 
 	buf = kmalloc(size, GFP_KERNEL);
+	if (!buf)
+		goto err;
 	if (count_nonzero_bytes(buf, size))
 		(*total_failures)++;
 	fill_with_garbage(buf, size);
 	kfree(buf);
+	return 1;
+err:
+	(*total_failures)++;
 	return 1;
 }
 
···
 	void *buf;
 
 	buf = vmalloc(size);
+	if (!buf)
+		goto err;
 	fill_with_garbage(buf, size);
 	vfree(buf);
 
 	buf = vmalloc(size);
+	if (!buf)
+		goto err;
 	if (count_nonzero_bytes(buf, size))
 		(*total_failures)++;
 	fill_with_garbage(buf, size);
 	vfree(buf);
+	return 1;
+err:
+	(*total_failures)++;
 	return 1;
 }
 

mm/compaction.c

···
 					pfn = cc->zone->zone_start_pfn;
 				cc->fast_search_fail = 0;
 				found_block = true;
-				set_pageblock_skip(freepage);
 				break;
 			}
 		}

mm/damon/core.c

···
 
 	damon_for_each_target(t, ctx) {
 		damon_for_each_region(r, t)
-			sz += r->ar.end - r->ar.start;
+			sz += damon_sz_region(r);
 	}
 
 	if (ctx->attrs.min_nr_regions)
···
 {
 	unsigned long sz;
 
-	sz = r->ar.end - r->ar.start;
+	sz = damon_sz_region(r);
 	return s->pattern.min_sz_region <= sz &&
 		sz <= s->pattern.max_sz_region &&
 		s->pattern.min_nr_accesses <= r->nr_accesses &&
···
 
 	damon_for_each_scheme(s, c) {
 		struct damos_quota *quota = &s->quota;
-		unsigned long sz = r->ar.end - r->ar.start;
+		unsigned long sz = damon_sz_region(r);
 		struct timespec64 begin, end;
 		unsigned long sz_applied = 0;
 
···
 				sz = ALIGN_DOWN(quota->charge_addr_from -
 						r->ar.start, DAMON_MIN_REGION);
 				if (!sz) {
-					if (r->ar.end - r->ar.start <=
-							DAMON_MIN_REGION)
+					if (damon_sz_region(r) <=
+					    DAMON_MIN_REGION)
 						continue;
 					sz = DAMON_MIN_REGION;
 				}
 				damon_split_region_at(t, r, sz);
 				r = damon_next_region(r);
-				sz = r->ar.end - r->ar.start;
+				sz = damon_sz_region(r);
 			}
 			quota->charge_target_from = NULL;
 			quota->charge_addr_from = 0;
···
 					continue;
 				score = c->ops.get_scheme_score(
 						c, t, r, s);
-				quota->histogram[score] +=
-					r->ar.end - r->ar.start;
+				quota->histogram[score] += damon_sz_region(r);
 				if (score > max_score)
 					max_score = score;
 			}
···
 	}
 }
 
-static inline unsigned long sz_damon_region(struct damon_region *r)
-{
-	return r->ar.end - r->ar.start;
-}
-
 /*
  * Merge two adjacent regions into one region
  */
 static void damon_merge_two_regions(struct damon_target *t,
 		struct damon_region *l, struct damon_region *r)
 {
-	unsigned long sz_l = sz_damon_region(l), sz_r = sz_damon_region(r);
+	unsigned long sz_l = damon_sz_region(l), sz_r = damon_sz_region(r);
 
 	l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) /
 			(sz_l + sz_r);
···
 
 		if (prev && prev->ar.end == r->ar.start &&
 		    abs(prev->nr_accesses - r->nr_accesses) <= thres &&
-		    sz_damon_region(prev) + sz_damon_region(r) <= sz_limit)
+		    damon_sz_region(prev) + damon_sz_region(r) <= sz_limit)
 			damon_merge_two_regions(t, prev, r);
 		else
 			prev = r;
···
 	int i;
 
 	damon_for_each_region_safe(r, next, t) {
-		sz_region = r->ar.end - r->ar.start;
+		sz_region = damon_sz_region(r);
 
 		for (i = 0; i < nr_subs - 1 &&
 				sz_region > 2 * DAMON_MIN_REGION; i++) {

mm/damon/vaddr.c

···
 		return -EINVAL;
 
 	orig_end = r->ar.end;
-	sz_orig = r->ar.end - r->ar.start;
+	sz_orig = damon_sz_region(r);
 	sz_piece = ALIGN_DOWN(sz_orig / nr_pieces, DAMON_MIN_REGION);
 
 	if (!sz_piece)
···
 {
 	struct mm_struct *mm;
 	unsigned long start = PAGE_ALIGN(r->ar.start);
-	unsigned long len = PAGE_ALIGN(r->ar.end - r->ar.start);
+	unsigned long len = PAGE_ALIGN(damon_sz_region(r));
 	unsigned long applied;
 
 	mm = damon_get_mm(target);

mm/highmem.c

···
 #include <asm/tlbflush.h>
 #include <linux/vmalloc.h>
 
+#ifdef CONFIG_KMAP_LOCAL
+static inline int kmap_local_calc_idx(int idx)
+{
+	return idx + KM_MAX_IDX * smp_processor_id();
+}
+
+#ifndef arch_kmap_local_map_idx
+#define arch_kmap_local_map_idx(idx, pfn)	kmap_local_calc_idx(idx)
+#endif
+#endif /* CONFIG_KMAP_LOCAL */
+
 /*
  * Virtual_count is not a pure "count".
  *  0 means that it is not mapped, and has not been mapped
···
 
 struct page *__kmap_to_page(void *vaddr)
 {
+	unsigned long base = (unsigned long) vaddr & PAGE_MASK;
+	struct kmap_ctrl *kctrl = &current->kmap_ctrl;
 	unsigned long addr = (unsigned long)vaddr;
+	int i;
 
-	if (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) {
-		int i = PKMAP_NR(addr);
+	/* kmap() mappings */
+	if (WARN_ON_ONCE(addr >= PKMAP_ADDR(0) &&
+			 addr < PKMAP_ADDR(LAST_PKMAP)))
+		return pte_page(pkmap_page_table[PKMAP_NR(addr)]);
 
-		return pte_page(pkmap_page_table[i]);
+	/* kmap_local_page() mappings */
+	if (WARN_ON_ONCE(base >= __fix_to_virt(FIX_KMAP_END) &&
+			 base < __fix_to_virt(FIX_KMAP_BEGIN))) {
+		for (i = 0; i < kctrl->idx; i++) {
+			unsigned long base_addr;
+			int idx;
+
+			idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
+			base_addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+
+			if (base_addr == base)
+				return pte_page(kctrl->pteval[i]);
+		}
 	}
 
 	return virt_to_page(vaddr);
···
 # define arch_kmap_local_post_unmap(vaddr)		do { } while (0)
 #endif
 
-#ifndef arch_kmap_local_map_idx
-#define arch_kmap_local_map_idx(idx, pfn)	kmap_local_calc_idx(idx)
-#endif
-
 #ifndef arch_kmap_local_unmap_idx
 #define arch_kmap_local_unmap_idx(idx, vaddr)	kmap_local_calc_idx(idx)
 #endif
···
 	}
 #endif
 	return false;
-}
-
-static inline int kmap_local_calc_idx(int idx)
-{
-	return idx + KM_MAX_IDX * smp_processor_id();
 }
 
 static pte_t *__kmap_pte;

mm/hugetlb.c

···
 		 * unmapped and its refcount is dropped, so just clear pte here.
 		 */
 		if (unlikely(!pte_present(pte))) {
+#ifdef CONFIG_PTE_MARKER_UFFD_WP
 			/*
 			 * If the pte was wr-protected by uffd-wp in any of the
 			 * swap forms, meanwhile the caller does not want to
···
 				set_huge_pte_at(mm, address, ptep,
 						make_pte_marker(PTE_MARKER_UFFD_WP));
 			else
+#endif
 				huge_pte_clear(mm, address, ptep, sz);
 			spin_unlock(ptl);
 			continue;
···
 		tlb_remove_huge_tlb_entry(h, tlb, ptep, address);
 		if (huge_pte_dirty(pte))
 			set_page_dirty(page);
+#ifdef CONFIG_PTE_MARKER_UFFD_WP
 		/* Leave a uffd-wp pte marker if needed */
 		if (huge_pte_uffd_wp(pte) &&
 		    !(zap_flags & ZAP_FLAG_DROP_MARKER))
 			set_huge_pte_at(mm, address, ptep,
 					make_pte_marker(PTE_MARKER_UFFD_WP));
+#endif
 		hugetlb_count_sub(pages_per_huge_page(h), mm);
 		page_remove_rmap(page, vma, true);
 
···
 	return handle_userfault(&vmf, reason);
 }
 
+/*
+ * Recheck pte with pgtable lock.  Returns true if pte didn't change, or
+ * false if pte changed or is changing.
+ */
+static bool hugetlb_pte_stable(struct hstate *h, struct mm_struct *mm,
+			       pte_t *ptep, pte_t old_pte)
+{
+	spinlock_t *ptl;
+	bool same;
+
+	ptl = huge_pte_lock(h, mm, ptep);
+	same = pte_same(huge_ptep_get(ptep), old_pte);
+	spin_unlock(ptl);
+
+	return same;
+}
+
 static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 			struct vm_area_struct *vma,
 			struct address_space *mapping, pgoff_t idx,
···
 		if (idx >= size)
 			goto out;
 		/* Check for page in userfault range */
-		if (userfaultfd_missing(vma))
-			return hugetlb_handle_userfault(vma, mapping, idx,
-						       flags, haddr, address,
-						       VM_UFFD_MISSING);
+		if (userfaultfd_missing(vma)) {
+			/*
+			 * Since hugetlb_no_page() was examining pte
+			 * without pgtable lock, we need to re-test under
+			 * lock because the pte may not be stable and could
+			 * have changed from under us.  Try to detect
+			 * either changed or during-changing ptes and retry
+			 * properly when needed.
+			 *
+			 * Note that userfaultfd is actually fine with
+			 * false positives (e.g. caused by pte changed),
+			 * but not wrong logical events (e.g. caused by
+			 * reading a pte during changing).  The latter can
+			 * confuse the userspace, so the strictness is very
+			 * much preferred.  E.g., MISSING event should
+			 * never happen on the page after UFFDIO_COPY has
+			 * correctly installed the page and returned.
+			 */
+			if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) {
+				ret = 0;
+				goto out;
+			}
+
+			return hugetlb_handle_userfault(vma, mapping, idx, flags,
+							haddr, address,
+							VM_UFFD_MISSING);
+		}
 
 		page = alloc_huge_page(vma, haddr, 0);
 		if (IS_ERR(page)) {
···
 			 * here.  Before returning error, get ptl and make
 			 * sure there really is no pte entry.
 			 */
-			ptl = huge_pte_lock(h, mm, ptep);
-			ret = 0;
-			if (huge_pte_none(huge_ptep_get(ptep)))
+			if (hugetlb_pte_stable(h, mm, ptep, old_pte))
 				ret = vmf_error(PTR_ERR(page));
-			spin_unlock(ptl);
+			else
+				ret = 0;
 			goto out;
 		}
 		clear_huge_page(page, address, pages_per_huge_page(h));
···
 		if (userfaultfd_minor(vma)) {
 			unlock_page(page);
 			put_page(page);
-			return hugetlb_handle_userfault(vma, mapping, idx,
-						       flags, haddr, address,
-						       VM_UFFD_MINOR);
+			/* See comment in userfaultfd_missing() block above */
+			if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) {
+				ret = 0;
+				goto out;
+			}
+			return hugetlb_handle_userfault(vma, mapping, idx, flags,
+							haddr, address,
+							VM_UFFD_MINOR);
 		}
 	}
 
···
 	kfree(vma_lock);
 }
 
-void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock)
+static void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock)
 {
 	struct vm_area_struct *vma = vma_lock->vma;
 

mm/kasan/kasan_test.c

···
 	ptr2 = krealloc(ptr1, size2, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2);
 
+	/* Suppress -Warray-bounds warnings. */
+	OPTIMIZER_HIDE_VAR(ptr2);
+
 	/* All offsets up to size2 must be accessible. */
 	ptr2[size1 - 1] = 'x';
 	ptr2[size1] = 'x';
···
 
 	ptr2 = krealloc(ptr1, size2, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2);
+
+	/* Suppress -Warray-bounds warnings. */
+	OPTIMIZER_HIDE_VAR(ptr2);
 
 	/* Must be accessible for all modes. */
 	ptr2[size2 - 1] = 'x';
···
 {
 	char *ptr;
 	size_t size = 64;
-	volatile size_t invalid_size = size;
+	size_t invalid_size = size;
 
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
 	memset((char *)ptr, 0, 64);
 	OPTIMIZER_HIDE_VAR(ptr);
+	OPTIMIZER_HIDE_VAR(invalid_size);
 	KUNIT_EXPECT_KASAN_FAIL(test,
 		memmove((char *)ptr, (char *)ptr + 4, invalid_size));
 	kfree(ptr);

mm/memory.c

···
 			      unsigned long addr, pte_t *pte,
 			      struct zap_details *details, pte_t pteval)
 {
+#ifdef CONFIG_PTE_MARKER_UFFD_WP
 	if (zap_drop_file_uffd_wp(details))
 		return;
 
 	pte_install_uffd_wp_if_needed(vma, addr, pte, pteval);
+#endif
 }
 
 static unsigned long zap_pte_range(struct mmu_gather *tlb,
···
 			ret = remove_device_exclusive_entry(vmf);
 		} else if (is_device_private_entry(entry)) {
 			vmf->page = pfn_swap_entry_to_page(entry);
-			ret = vmf->page->pgmap->ops->migrate_to_ram(vmf);
+			vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
+					vmf->address, &vmf->ptl);
+			if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) {
+				spin_unlock(vmf->ptl);
+				goto out;
+			}
+
+			/*
+			 * Get a page reference while we know the page can't be
+			 * freed.
+			 */
+			get_page(vmf->page);
+			pte_unmap_unlock(vmf->pte, vmf->ptl);
+			vmf->page->pgmap->ops->migrate_to_ram(vmf);
+			put_page(vmf->page);
 		} else if (is_hwpoison_entry(entry)) {
 			ret = VM_FAULT_HWPOISON;
 		} else if (is_swapin_error_entry(entry)) {
···
 	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
 			&vmf->ptl);
 	if (!pte_none(*vmf->pte)) {
-		update_mmu_cache(vma, vmf->address, vmf->pte);
+		update_mmu_tlb(vma, vmf->address, vmf->pte);
 		goto release;
 	}
 

mm/memremap.c

···
 	int i;
 
 	percpu_ref_kill(&pgmap->ref);
-	for (i = 0; i < pgmap->nr_range; i++)
-		percpu_ref_put_many(&pgmap->ref, pfn_len(pgmap, i));
+	if (pgmap->type != MEMORY_DEVICE_PRIVATE &&
+	    pgmap->type != MEMORY_DEVICE_COHERENT)
+		for (i = 0; i < pgmap->nr_range; i++)
+			percpu_ref_put_many(&pgmap->ref, pfn_len(pgmap, i));
+
 	wait_for_completion(&pgmap->done);
 
 	for (i = 0; i < pgmap->nr_range; i++)
···
 	memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
 				PHYS_PFN(range->start),
 				PHYS_PFN(range_len(range)), pgmap);
-	percpu_ref_get_many(&pgmap->ref, pfn_len(pgmap, range_id));
+	if (pgmap->type != MEMORY_DEVICE_PRIVATE &&
+	    pgmap->type != MEMORY_DEVICE_COHERENT)
+		percpu_ref_get_many(&pgmap->ref, pfn_len(pgmap, range_id));
 	return 0;
 
 err_add_memory:
···
 	page->mapping = NULL;
 	page->pgmap->ops->page_free(page);
 
-	/*
-	 * Reset the page count to 1 to prepare for handing out the page again.
-	 */
-	set_page_count(page, 1);
+	if (page->pgmap->type != MEMORY_DEVICE_PRIVATE &&
+	    page->pgmap->type != MEMORY_DEVICE_COHERENT)
+		/*
+		 * Reset the page count to 1 to prepare for handing out the page
+		 * again.
+		 */
+		set_page_count(page, 1);
+	else
+		put_dev_pagemap(page->pgmap);
 }
+
+void zone_device_page_init(struct page *page)
+{
+	/*
+	 * Drivers shouldn't be allocating pages after calling
+	 * memunmap_pages().
+	 */
+	WARN_ON_ONCE(!percpu_ref_tryget_live(&page->pgmap->ref));
+	set_page_count(page, 1);
+	lock_page(page);
+}
+EXPORT_SYMBOL_GPL(zone_device_page_init);
 
 #ifdef CONFIG_FS_DAX
 bool __put_devmap_managed_page_refs(struct page *page, int refs)

mm/migrate.c

···
  *                    Migration functions
  ***********************************************************/
 
+int migrate_folio_extra(struct address_space *mapping, struct folio *dst,
+		struct folio *src, enum migrate_mode mode, int extra_count)
+{
+	int rc;
+
+	BUG_ON(folio_test_writeback(src));	/* Writeback must be complete */
+
+	rc = folio_migrate_mapping(mapping, dst, src, extra_count);
+
+	if (rc != MIGRATEPAGE_SUCCESS)
+		return rc;
+
+	if (mode != MIGRATE_SYNC_NO_COPY)
+		folio_migrate_copy(dst, src);
+	else
+		folio_migrate_flags(dst, src);
+	return MIGRATEPAGE_SUCCESS;
+}
+
 /**
  * migrate_folio() - Simple folio migration.
  * @mapping: The address_space containing the folio.
···
 int migrate_folio(struct address_space *mapping, struct folio *dst,
 		struct folio *src, enum migrate_mode mode)
 {
-	int rc;
-
-	BUG_ON(folio_test_writeback(src));	/* Writeback must be complete */
-
-	rc = folio_migrate_mapping(mapping, dst, src, 0);
-
-	if (rc != MIGRATEPAGE_SUCCESS)
-		return rc;
-
-	if (mode != MIGRATE_SYNC_NO_COPY)
-		folio_migrate_copy(dst, src);
-	else
-		folio_migrate_flags(dst, src);
-	return MIGRATEPAGE_SUCCESS;
+	return migrate_folio_extra(mapping, dst, src, mode, 0);
 }
 EXPORT_SYMBOL(migrate_folio);
 

mm/migrate_device.c

···
  * folio_migrate_mapping(), except that here we allow migration of a
  * ZONE_DEVICE page.
  */
-static bool migrate_vma_check_page(struct page *page)
+static bool migrate_vma_check_page(struct page *page, struct page *fault_page)
 {
 	/*
 	 * One extra ref because caller holds an extra reference, either from
 	 * isolate_lru_page() for a regular page, or migrate_vma_collect() for
 	 * a device page.
 	 */
-	int extra = 1;
+	int extra = 1 + (page == fault_page);
 
 	/*
 	 * FIXME support THP (transparent huge page), it is bit more complex to
···
 }
 
 /*
- * migrate_vma_unmap() - replace page mapping with special migration pte entry
- * @migrate: migrate struct containing all migration information
- *
- * Isolate pages from the LRU and replace mappings (CPU page table pte) with a
- * special migration pte entry and check if it has been pinned. Pinned pages are
- * restored because we cannot migrate them.
- *
- * This is the last step before we call the device driver callback to allocate
- * destination memory and copy contents of original page over to new page.
+ * Unmaps pages for migration. Returns number of unmapped pages.
  */
-static void migrate_vma_unmap(struct migrate_vma *migrate)
+static unsigned long migrate_device_unmap(unsigned long *src_pfns,
+					  unsigned long npages,
+					  struct page *fault_page)
 {
-	const unsigned long npages = migrate->npages;
 	unsigned long i, restore = 0;
 	bool allow_drain = true;
+	unsigned long unmapped = 0;
 
 	lru_add_drain();
 
 	for (i = 0; i < npages; i++) {
-		struct page *page = migrate_pfn_to_page(migrate->src[i]);
+		struct page *page = migrate_pfn_to_page(src_pfns[i]);
 		struct folio *folio;
 
 		if (!page)
···
 			}
 
 			if (isolate_lru_page(page)) {
-				migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
-				migrate->cpages--;
+				src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
 				restore++;
 				continue;
 			}
···
 		if (folio_mapped(folio))
 			try_to_migrate(folio, 0);
 
-		if (page_mapped(page) || !migrate_vma_check_page(page)) {
+		if (page_mapped(page) ||
+		    !migrate_vma_check_page(page, fault_page)) {
 			if (!is_zone_device_page(page)) {
 				get_page(page);
 				putback_lru_page(page);
 			}
 
-			migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
-			migrate->cpages--;
+			src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
 			restore++;
 			continue;
 		}
+
+		unmapped++;
 	}
 
 	for (i = 0; i < npages && restore; i++) {
-		struct page *page = migrate_pfn_to_page(migrate->src[i]);
+		struct page *page = migrate_pfn_to_page(src_pfns[i]);
 		struct folio *folio;
 
-		if (!page || (migrate->src[i] & MIGRATE_PFN_MIGRATE))
+		if (!page || (src_pfns[i] & MIGRATE_PFN_MIGRATE))
 			continue;
 
 		folio = page_folio(page);
 		remove_migration_ptes(folio, folio, false);
 
-		migrate->src[i] = 0;
+		src_pfns[i] = 0;
 		folio_unlock(folio);
 		folio_put(folio);
 		restore--;
 	}
+
+	return unmapped;
+}
+
+/*
+ * migrate_vma_unmap() - replace page mapping with special migration pte entry
+ * @migrate: migrate struct containing all migration information
+ *
+ * Isolate pages from the LRU and replace mappings (CPU page table pte) with a
+ * special migration pte entry and check if it has been pinned. Pinned pages are
+ * restored because we cannot migrate them.
+ *
+ * This is the last step before we call the device driver callback to allocate
+ * destination memory and copy contents of original page over to new page.
+ */
+static void migrate_vma_unmap(struct migrate_vma *migrate)
+{
+	migrate->cpages = migrate_device_unmap(migrate->src, migrate->npages,
+					migrate->fault_page);
 }
 
 /**
···
 	if (args->end <= args->vma->vm_start || args->end > args->vma->vm_end)
 		return -EINVAL;
 	if (!args->src || !args->dst)
+		return -EINVAL;
+	if (args->fault_page && !is_device_private_page(args->fault_page))
 		return -EINVAL;
 
 	memset(args->src, 0, sizeof(*args->src) * nr_pages);
···
 	*src &= ~MIGRATE_PFN_MIGRATE;
 }
 
-/**
- * migrate_vma_pages() - migrate meta-data from src page to dst page
- * @migrate: migrate struct containing all migration information
- *
- * This migrates struct page meta-data from source struct page to destination
- * struct page. This effectively finishes the migration from source page to the
- * destination page.
- */
-void migrate_vma_pages(struct migrate_vma *migrate)
+static void __migrate_device_pages(unsigned long *src_pfns,
+				unsigned long *dst_pfns, unsigned long npages,
+				struct migrate_vma *migrate)
 {
-	const unsigned long npages = migrate->npages;
-	const unsigned long start = migrate->start;
 	struct mmu_notifier_range range;
-	unsigned long addr, i;
+	unsigned long i;
 	bool notified = false;
 
-	for (i = 0, addr = start; i < npages; addr += PAGE_SIZE, i++) {
-		struct page *newpage = migrate_pfn_to_page(migrate->dst[i]);
-		struct page *page = migrate_pfn_to_page(migrate->src[i]);
+	for (i = 0; i < npages; i++) {
+		struct page *newpage = migrate_pfn_to_page(dst_pfns[i]);
+		struct page *page = migrate_pfn_to_page(src_pfns[i]);
 		struct address_space *mapping;
 		int r;
 
 		if (!newpage) {
-			migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
+			src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
 			continue;
 		}
 
 		if (!page) {
+			unsigned long addr;
+
+			if (!(src_pfns[i] & MIGRATE_PFN_MIGRATE))
+				continue;
+
 			/*
 			 * The only time there is no vma is when called from
 			 * migrate_device_coherent_page(). However this isn't
 			 * called if the page could not be unmapped.
 			 */
-			VM_BUG_ON(!migrate->vma);
-			if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE))
-				continue;
+			VM_BUG_ON(!migrate);
+			addr = migrate->start + i*PAGE_SIZE;
 			if (!notified) {
 				notified = true;
 
···
 				mmu_notifier_invalidate_range_start(&range);
 			}
 			migrate_vma_insert_page(migrate, addr, newpage,
-						&migrate->src[i]);
+						&src_pfns[i]);
 			continue;
 		}
 
···
 			 * device private or coherent memory.
 			 */
 			if (mapping) {
-				migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
+				src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
 				continue;
 			}
 		} else if (is_zone_device_page(newpage)) {
 			/*
 			 * Other types of ZONE_DEVICE page are not supported.
 			 */
-			migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
+			src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
 			continue;
 		}
 
-		r = migrate_folio(mapping, page_folio(newpage),
-				page_folio(page), MIGRATE_SYNC_NO_COPY);
+		if (migrate && migrate->fault_page == page)
+			r = migrate_folio_extra(mapping, page_folio(newpage),
+						page_folio(page),
+						MIGRATE_SYNC_NO_COPY, 1);
+		else
+			r = migrate_folio(mapping, page_folio(newpage),
+					page_folio(page), MIGRATE_SYNC_NO_COPY);
 		if (r != MIGRATEPAGE_SUCCESS)
-			migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
+			src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
 	}
 
 	/*
···
 	if (notified)
 		mmu_notifier_invalidate_range_only_end(&range);
 }
-EXPORT_SYMBOL(migrate_vma_pages);
 
 /**
- * migrate_vma_finalize() - restore CPU page table entry
+ * migrate_device_pages() - migrate meta-data from src page to dst page
+ * @src_pfns: src_pfns returned from migrate_device_range()
+ * @dst_pfns: array of pfns allocated by the driver to migrate memory to
+ * @npages: number of pages in the range
+ *
+ * Equivalent to migrate_vma_pages(). This is called to migrate struct page
+ * meta-data from source struct page to destination.
+ */
+void migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns,
+			unsigned long npages)
+{
+	__migrate_device_pages(src_pfns, dst_pfns, npages, NULL);
+}
+EXPORT_SYMBOL(migrate_device_pages);
+
+/**
+ * migrate_vma_pages() - migrate meta-data from src page to dst page
  * @migrate: migrate struct containing all migration information
  *
- * This replaces the special migration pte entry with either a mapping to the
- * new page if migration was successful for that page, or to the original page
- * otherwise.
- *
- * This also unlocks the pages and puts them back on the lru, or drops the extra
- * refcount, for device pages.
+ * This migrates struct page meta-data from source struct page to destination
+ * struct page. This effectively finishes the migration from source page to the
+ * destination page.
  */
-void migrate_vma_finalize(struct migrate_vma *migrate)
+void migrate_vma_pages(struct migrate_vma *migrate)
 {
-	const unsigned long npages = migrate->npages;
+	__migrate_device_pages(migrate->src, migrate->dst, migrate->npages, migrate);
+}
+EXPORT_SYMBOL(migrate_vma_pages);
+
+/*
+ * migrate_device_finalize() - complete page migration
+ * @src_pfns: src_pfns returned from migrate_device_range()
+ * @dst_pfns: array of pfns allocated by the driver to migrate memory to
+ * @npages: number of pages in the range
+ *
+ * Completes migration of the page by removing special migration entries.
+ * Drivers must ensure copying of page data is complete and visible to the CPU
+ * before calling this.
+ */
+void migrate_device_finalize(unsigned long *src_pfns,
+			unsigned long *dst_pfns, unsigned long npages)
+{
 	unsigned long i;
 
 	for (i = 0; i < npages; i++) {
 		struct folio *dst, *src;
-		struct page *newpage = migrate_pfn_to_page(migrate->dst[i]);
-		struct page *page = migrate_pfn_to_page(migrate->src[i]);
+		struct page *newpage = migrate_pfn_to_page(dst_pfns[i]);
+		struct page *page = migrate_pfn_to_page(src_pfns[i]);
 
 		if (!page) {
 			if (newpage) {
···
 			continue;
 		}
 
-		if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE) || !newpage) {
+		if (!(src_pfns[i] & MIGRATE_PFN_MIGRATE) || !newpage) {
 			if (newpage) {
 				unlock_page(newpage);
 				put_page(newpage);
···
 		}
 	}
 }
+EXPORT_SYMBOL(migrate_device_finalize);
+
+/**
+ * migrate_vma_finalize() - restore CPU page table entry
+ * @migrate: migrate struct containing all migration information
+ *
+ * This replaces the special migration pte entry with either a mapping to the
+ * new page if migration was successful for that page, or to the original page
+ * otherwise.
+ *
+ * This also unlocks the pages and puts them back on the lru, or drops the extra
+ * refcount, for device pages.
+ */
+void migrate_vma_finalize(struct migrate_vma *migrate)
+{
+	migrate_device_finalize(migrate->src, migrate->dst, migrate->npages);
+}
 EXPORT_SYMBOL(migrate_vma_finalize);
+
+/**
+ * migrate_device_range() - migrate device private pfns to normal memory.
+ * @src_pfns: array large enough to hold migrating source device private pfns.
+ * @start: starting pfn in the range to migrate.
+ * @npages: number of pages to migrate.
+ *
+ * migrate_vma_setup() is similar in concept to migrate_vma_setup() except that
+ * instead of looking up pages based on virtual address mappings a range of
+ * device pfns that should be migrated to system memory is used instead.
+ *
+ * This is useful when a driver needs to free device memory but doesn't know the
+ * virtual mappings of every page that may be in device memory. For example this
+ * is often the case when a driver is being unloaded or unbound from a device.
+ *
+ * Like migrate_vma_setup() this function will take a reference and lock any
+ * migrating pages that aren't free before unmapping them. Drivers may then
+ * allocate destination pages and start copying data from the device to CPU
+ * memory before calling migrate_device_pages().
+ */
+int migrate_device_range(unsigned long *src_pfns, unsigned long start,
+			unsigned long npages)
+{
+	unsigned long i, pfn;
+
+	for (pfn = start, i = 0; i < npages; pfn++, i++) {
+		struct page *page = pfn_to_page(pfn);
+
+		if (!get_page_unless_zero(page)) {
+			src_pfns[i] = 0;
+			continue;
+		}
+
+		if (!trylock_page(page)) {
+			src_pfns[i] = 0;
+			put_page(page);
+			continue;
+		}
+
+		src_pfns[i] = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE;
+	}
+
+	migrate_device_unmap(src_pfns, npages, NULL);
+
+	return 0;
+}
+EXPORT_SYMBOL(migrate_device_range);
 
 /*
  * Migrate a device coherent page back to normal memory. The caller should have
···
 int migrate_device_coherent_page(struct page *page)
 {
 	unsigned long src_pfn, dst_pfn = 0;
-	struct migrate_vma args;
 	struct page *dpage;
 
 	WARN_ON_ONCE(PageCompound(page));
 
 	lock_page(page);
 	src_pfn = migrate_pfn(page_to_pfn(page)) | MIGRATE_PFN_MIGRATE;
-	args.src = &src_pfn;
-	args.dst = &dst_pfn;
-	args.cpages = 1;
-	args.npages = 1;
-	args.vma = NULL;
 
 	/*
 	 * We don't have a VMA and don't need to walk the page tables to find
 	 * the source page. So call migrate_vma_unmap() directly to unmap the
 	 * page as migrate_vma_setup() will fail if args.vma == NULL.
 	 */
-	migrate_vma_unmap(&args);
+	migrate_device_unmap(&src_pfn, 1, NULL);
 	if (!(src_pfn & MIGRATE_PFN_MIGRATE))
 		return -EBUSY;
 
···
 		dst_pfn = migrate_pfn(page_to_pfn(dpage));
 	}
 
-	migrate_vma_pages(&args);
+	migrate_device_pages(&src_pfn, &dst_pfn, 1);
 	if (src_pfn & MIGRATE_PFN_MIGRATE)
 		copy_highpage(dpage, page);
-	migrate_vma_finalize(&args);
+	migrate_device_finalize(&src_pfn, &dst_pfn, 1);
 
 	if (src_pfn & MIGRATE_PFN_MIGRATE)
 		return 0;

mm/mmap.c

···
 	if (!arch_validate_flags(vma->vm_flags)) {
 		error = -EINVAL;
 		if (file)
-			goto unmap_and_free_vma;
+			goto close_and_free_vma;
 		else
 			goto free_vma;
 	}
···
 	validate_mm(mm);
 	return addr;
 
+close_and_free_vma:
+	if (vma->vm_ops && vma->vm_ops->close)
+		vma->vm_ops->close(vma);
 unmap_and_free_vma:
 	fput(vma->vm_file);
 	vma->vm_file = NULL;
···
 	if (vma &&
 	    (!vma->anon_vma || list_is_singular(&vma->anon_vma_chain)) &&
 	    ((vma->vm_flags & ~VM_SOFTDIRTY) == flags)) {
-		mas->index = vma->vm_start;
-		mas->last = addr + len - 1;
-		vma_adjust_trans_huge(vma, addr, addr + len, 0);
+		mas_set_range(mas, vma->vm_start, addr + len - 1);
+		if (mas_preallocate(mas, vma, GFP_KERNEL))
+			return -ENOMEM;
+
+		vma_adjust_trans_huge(vma, vma->vm_start, addr + len, 0);
 		if (vma->anon_vma) {
 			anon_vma_lock_write(vma->anon_vma);
 			anon_vma_interval_tree_pre_update_vma(vma);
 		}
 		vma->vm_end = addr + len;
 		vma->vm_flags |= VM_SOFTDIRTY;
-		if (mas_store_gfp(mas, vma, GFP_KERNEL))
-			goto mas_expand_failed;
+		mas_store_prealloc(mas, vma);
 
 		if (vma->anon_vma) {
 			anon_vma_interval_tree_post_update_vma(vma);
···
 	vm_area_free(vma);
 vma_alloc_fail:
 	vm_unacct_memory(len >> PAGE_SHIFT);
-	return -ENOMEM;
-
-mas_expand_failed:
-	if (vma->anon_vma) {
-		anon_vma_interval_tree_post_update_vma(vma);
-		anon_vma_unlock_write(vma->anon_vma);
-	}
 	return -ENOMEM;
 }
 
···
 out_vma_link:
 	if (new_vma->vm_ops && new_vma->vm_ops->close)
 		new_vma->vm_ops->close(new_vma);
+
+	if (new_vma->vm_file)
+		fput(new_vma->vm_file);
+
+	unlink_anon_vmas(new_vma);
 out_free_mempol:
 	mpol_put(vma_policy(new_vma));
 out_free_vma:

mm/mmu_gather.c

···
 #include <linux/gfp.h>
 #include <linux/highmem.h>
 #include <linux/kernel.h>
+#include <linux/kmsan-checks.h>
 #include <linux/mmdebug.h>
 #include <linux/mm_types.h>
 #include <linux/mm_inline.h>
···
 static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 			     bool fullmm)
 {
+	/*
+	 * struct mmu_gather contains 7 1-bit fields packed into a 32-bit
+	 * unsigned int value. The remaining 25 bits remain uninitialized
+	 * and are never used, but KMSAN updates the origin for them in
+	 * zap_pXX_range() in mm/memory.c, thus creating very long origin
+	 * chains. This is technically correct, but consumes too much memory.
+	 * Unpoisoning the whole structure will prevent creating such chains.
+	 */
+	kmsan_unpoison_memory(tlb, sizeof(*tlb));
 	tlb->mm = mm;
 	tlb->fullmm = fullmm;
 

mm/mprotect.c

···
 		} else {
 			/* It must be an none page, or what else?.. */
 			WARN_ON_ONCE(!pte_none(oldpte));
+#ifdef CONFIG_PTE_MARKER_UFFD_WP
 			if (unlikely(uffd_wp && !vma_is_anonymous(vma))) {
 				/*
 				 * For file-backed mem, we need to be able to
···
 					   make_pte_marker(PTE_MARKER_UFFD_WP));
 				pages++;
 			}
+#endif
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();

mm/page_alloc.c

···
 	int pindex;
 	bool free_high;
 
-	__count_vm_event(PGFREE);
+	__count_vm_events(PGFREE, 1 << order);
 	pindex = order_to_pindex(migratetype, order);
 	list_add(&page->pcp_list, &pcp->lists[pindex]);
 	pcp->count += 1 << order;
···
 	pcp_spin_unlock_irqrestore(pcp, flags);
 	pcp_trylock_finish(UP_flags);
 	if (page) {
-		__count_zid_vm_events(PGALLOC, page_zonenum(page), 1);
+		__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
 		zone_statistics(preferred_zone, zone, 1);
 	}
 	return page;
···
 		set_pageblock_migratetype(page, MIGRATE_MOVABLE);
 		cond_resched();
 	}
+
+	/*
+	 * ZONE_DEVICE pages are released directly to the driver page allocator
+	 * which will set the page count to 1 when allocating the page.
+	 */
+	if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
+	    pgmap->type == MEMORY_DEVICE_COHERENT)
+		set_page_count(page, 0);
 }
 
 /*

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

···
 	hmm_buffer_free(buffer);
 }
 
+TEST_F(hmm, migrate_release)
+{
+	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_migrate_sys_to_dev(self->fd, 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);
+
+	/* Release device memory. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_RELEASE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+
+	/* Fault pages back to system memory and check them. */
+	for (i = 0, ptr = buffer->ptr; i < size / (2 * sizeof(*ptr)); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	hmm_buffer_free(buffer);
+}
+
 /*
  * Migrate anonymous shared memory to device private memory.
  */

tools/testing/selftests/vm/userfaultfd.c

···
 		continue_range(uffd, msg->arg.pagefault.address, page_size);
 		stats->minor_faults++;
 	} else {
-		/* Missing page faults */
+		/*
+		 * Missing page faults.
+		 *
+		 * Here we force a write check for each of the missing mode
+		 * faults.  It's guaranteed because the only threads that
+		 * will trigger uffd faults are the locking threads, and
+		 * their first instruction to touch the missing page will
+		 * always be pthread_mutex_lock().
+		 *
+		 * Note that here we relied on an NPTL glibc impl detail to
+		 * always read the lock type at the entry of the lock op
+		 * (pthread_mutex_t.__data.__type, offset 0x10) before
+		 * doing any locking operations to guarantee that.  It's
+		 * actually not good to rely on this impl detail because
+		 * logically a pthread-compatible lib can implement the
+		 * locks without types and we can fail when linking with
+		 * them.  However since we used to find bugs with this
+		 * strict check we still keep it around.  Hopefully this
+		 * could be a good hint when it fails again.  If one day
+		 * it'll break on some other impl of glibc we'll revisit.
+		 */
 		if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
 			err("unexpected write fault");