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
  ...

5 files changed, 99 insertions, 67 deletions

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 7c74d8cba44f..966aab902d19 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -52,9 +52,6 @@ static unsigned int num_devices = 1;
 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,
@@ -546,17 +543,6 @@ static ssize_t backing_dev_store(struct device *dev,
 	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);
@@ -1270,6 +1256,9 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
 		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;
@@ -1856,15 +1845,6 @@ static const struct block_device_operations zram_devops = {
 	.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);
 static DEVICE_ATTR_RO(initstate);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index c70c026c9a93..2797029bd500 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -223,7 +223,7 @@ svm_migrate_get_vram_page(struct svm_range *prange, unsigned long pfn)
 	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
@@ -410,7 +410,7 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 	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;
@@ -666,7 +666,7 @@ out_oom:
 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;
@@ -674,7 +674,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 	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;
@@ -697,6 +697,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 
 	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,
@@ -764,7 +765,7 @@ out:
  * 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;
@@ -805,7 +806,8 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm,
 		}
 
 		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;
@@ -849,7 +851,7 @@ svm_migrate_vram_to_vram(struct svm_range *prange, uint32_t best_loc,
 	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);
@@ -950,7 +952,8 @@ static vm_fault_t svm_migrate_to_ram(struct vm_fault *vmf)
 	}
 
 	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);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h
index b3f0754b32fa..a5d7e6d22264 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h
@@ -43,7 +43,7 @@ enum MIGRATION_COPY_DIR {
 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);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index f5913ba22174..64fdf63093a0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -2913,13 +2913,15 @@ retry_write_locked:
 				 */
 				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",
@@ -3278,7 +3280,8 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange,
 		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;
 	}
@@ -3339,7 +3342,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 		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)
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 16356611b5b9..5fe209107246 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -139,44 +139,24 @@ static void nouveau_dmem_fence_done(struct nouveau_fence **fence)
 	}
 }
 
-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)
@@ -184,9 +164,11 @@ 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,
@@ -207,9 +189,25 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf)
 	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);
@@ -326,7 +324,7 @@ nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm)
 			return NULL;
 	}
 
-	lock_page(page);
+	zone_device_page_init(page);
 	return page;
 }
 
@@ -369,6 +367,52 @@ nouveau_dmem_suspend(struct nouveau_drm *drm)
 	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)
 {
@@ -380,8 +424,10 @@ 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,