Merge tag 'mm-stable-2025-12-03-21-26' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

  "__vmalloc()/kvmalloc() and no-block support" (Uladzislau Rezki)
     Rework the vmalloc() code to support non-blocking allocations
     (GFP_ATOIC, GFP_NOWAIT)

  "ksm: fix exec/fork inheritance" (xu xin)
     Fix a rare case where the KSM MMF_VM_MERGE_ANY prctl state is not
     inherited across fork/exec

  "mm/zswap: misc cleanup of code and documentations" (SeongJae Park)
     Some light maintenance work on the zswap code

  "mm/page_owner: add debugfs files 'show_handles' and 'show_stacks_handles'" (Mauricio Faria de Oliveira)
     Enhance the /sys/kernel/debug/page_owner debug feature by adding
     unique identifiers to differentiate the various stack traces so
     that userspace monitoring tools can better match stack traces over
     time

  "mm/page_alloc: pcp->batch cleanups" (Joshua Hahn)
     Minor alterations to the page allocator's per-cpu-pages feature

  "Improve UFFDIO_MOVE scalability by removing anon_vma lock" (Lokesh Gidra)
     Address a scalability issue in userfaultfd's UFFDIO_MOVE operation

  "kasan: cleanups for kasan_enabled() checks" (Sabyrzhan Tasbolatov)

  "drivers/base/node: fold node register and unregister functions" (Donet Tom)
     Clean up the NUMA node handling code a little

  "mm: some optimizations for prot numa" (Kefeng Wang)
     Cleanups and small optimizations to the NUMA allocation hinting
     code

  "mm/page_alloc: Batch callers of free_pcppages_bulk" (Joshua Hahn)
     Address long lock hold times at boot on large machines. These were
     causing (harmless) softlockup warnings

  "optimize the logic for handling dirty file folios during reclaim" (Baolin Wang)
     Remove some now-unnecessary work from page reclaim

  "mm/damon: allow DAMOS auto-tuned for per-memcg per-node memory usage" (SeongJae Park)
     Enhance the DAMOS auto-tuning feature

  "mm/damon: fixes for address alignment issues in DAMON_LRU_SORT and DAMON_RECLAIM" (Quanmin Yan)
     Fix DAMON_LRU_SORT and DAMON_RECLAIM with certain userspace
     configuration

  "expand mmap_prepare functionality, port more users" (Lorenzo Stoakes)
     Enhance the new(ish) file_operations.mmap_prepare() method and port
     additional callsites from the old ->mmap() over to ->mmap_prepare()

  "Fix stale IOTLB entries for kernel address space" (Lu Baolu)
     Fix a bug (and possible security issue on non-x86) in the IOMMU
     code. In some situations the IOMMU could be left hanging onto a
     stale kernel pagetable entry

  "mm/huge_memory: cleanup __split_unmapped_folio()" (Wei Yang)
     Clean up and optimize the folio splitting code

  "mm, swap: misc cleanup and bugfix" (Kairui Song)
     Some cleanups and a minor fix in the swap discard code

  "mm/damon: misc documentation fixups" (SeongJae Park)

  "mm/damon: support pin-point targets removal" (SeongJae Park)
     Permit userspace to remove a specific monitoring target in the
     middle of the current targets list

  "mm: MISC follow-up patches for linux/pgalloc.h" (Harry Yoo)
     A couple of cleanups related to mm header file inclusion

  "mm/swapfile.c: select swap devices of default priority round robin" (Baoquan He)
     improve the selection of swap devices for NUMA machines

  "mm: Convert memory block states (MEM_*) macros to enums" (Israel Batista)
     Change the memory block labels from macros to enums so they will
     appear in kernel debug info

  "ksm: perform a range-walk to jump over holes in break_ksm" (Pedro Demarchi Gomes)
     Address an inefficiency when KSM unmerges an address range

  "mm/damon/tests: fix memory bugs in kunit tests" (SeongJae Park)
     Fix leaks and unhandled malloc() failures in DAMON userspace unit
     tests

  "some cleanups for pageout()" (Baolin Wang)
     Clean up a couple of minor things in the page scanner's
     writeback-for-eviction code

  "mm/hugetlb: refactor sysfs/sysctl interfaces" (Hui Zhu)
     Move hugetlb's sysfs/sysctl handling code into a new file

  "introduce VM_MAYBE_GUARD and make it sticky" (Lorenzo Stoakes)
     Make the VMA guard regions available in /proc/pid/smaps and
     improves the mergeability of guarded VMAs

  "mm: perform guard region install/remove under VMA lock" (Lorenzo Stoakes)
     Reduce mmap lock contention for callers performing VMA guard region
     operations

  "vma_start_write_killable" (Matthew Wilcox)
     Start work on permitting applications to be killed when they are
     waiting on a read_lock on the VMA lock

  "mm/damon/tests: add more tests for online parameters commit" (SeongJae Park)
     Add additional userspace testing of DAMON's "commit" feature

  "mm/damon: misc cleanups" (SeongJae Park)

  "make VM_SOFTDIRTY a sticky VMA flag" (Lorenzo Stoakes)
     Address the possible loss of a VMA's VM_SOFTDIRTY flag when that
     VMA is merged with another

  "mm: support device-private THP" (Balbir Singh)
     Introduce support for Transparent Huge Page (THP) migration in zone
     device-private memory

  "Optimize folio split in memory failure" (Zi Yan)

  "mm/huge_memory: Define split_type and consolidate split support checks" (Wei Yang)
     Some more cleanups in the folio splitting code

  "mm: remove is_swap_[pte, pmd]() + non-swap entries, introduce leaf entries" (Lorenzo Stoakes)
     Clean up our handling of pagetable leaf entries by introducing the
     concept of 'software leaf entries', of type softleaf_t

  "reparent the THP split queue" (Muchun Song)
     Reparent the THP split queue to its parent memcg. This is in
     preparation for addressing the long-standing "dying memcg" problem,
     wherein dead memcg's linger for too long, consuming memory
     resources

  "unify PMD scan results and remove redundant cleanup" (Wei Yang)
     A little cleanup in the hugepage collapse code

  "zram: introduce writeback bio batching" (Sergey Senozhatsky)
     Improve zram writeback efficiency by introducing batched bio
     writeback support

  "memcg: cleanup the memcg stats interfaces" (Shakeel Butt)
     Clean up our handling of the interrupt safety of some memcg stats

  "make vmalloc gfp flags usage more apparent" (Vishal Moola)
     Clean up vmalloc's handling of incoming GFP flags

  "mm: Add soft-dirty and uffd-wp support for RISC-V" (Chunyan Zhang)
     Teach soft dirty and userfaultfd write protect tracking to use
     RISC-V's Svrsw60t59b extension

  "mm: swap: small fixes and comment cleanups" (Youngjun Park)
     Fix a small bug and clean up some of the swap code

  "initial work on making VMA flags a bitmap" (Lorenzo Stoakes)
     Start work on converting the vma struct's flags to a bitmap, so we
     stop running out of them, especially on 32-bit

  "mm/swapfile: fix and cleanup swap list iterations" (Youngjun Park)
     Address a possible bug in the swap discard code and clean things
     up a little

[ This merge also reverts commit ebb9aeb980e5 ("vfio/nvgrace-gpu:
  register device memory for poison handling") because it looks
  broken to me, I've asked for clarification   - Linus ]

* tag 'mm-stable-2025-12-03-21-26' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (321 commits)
  mm: fix vma_start_write_killable() signal handling
  mm/swapfile: use plist_for_each_entry in __folio_throttle_swaprate
  mm/swapfile: fix list iteration when next node is removed during discard
  fs/proc/task_mmu.c: fix make_uffd_wp_huge_pte() huge pte handling
  mm/kfence: add reboot notifier to disable KFENCE on shutdown
  memcg: remove inc/dec_lruvec_kmem_state helpers
  selftests/mm/uffd: initialize char variable to Null
  mm: fix DEBUG_RODATA_TEST indentation in Kconfig
  mm: introduce VMA flags bitmap type
  tools/testing/vma: eliminate dependency on vma->__vm_flags
  mm: simplify and rename mm flags function for clarity
  mm: declare VMA flags by bit
  zram: fix a spelling mistake
  mm/page_alloc: optimize lowmem_reserve max lookup using its semantic monotonicity
  mm/vmscan: skip increasing kswapd_failures when reclaim was boosted
  pagemap: update BUDDY flag documentation
  mm: swap: remove scan_swap_map_slots() references from comments
  mm: swap: change swap_alloc_slow() to void
  mm, swap: remove redundant comment for read_swap_cache_async
  mm, swap: use SWP_SOLIDSTATE to determine if swap is rotational
  ...

5 files changed, 244 insertions, 95 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 46c84fc60af1..af53e796ea1b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -217,7 +217,7 @@ 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;
-	zone_device_page_init(page);
+	zone_device_page_init(page, 0);
 }
 
 static void
@@ -567,8 +567,9 @@ out:
 	return r < 0 ? r : 0;
 }
 
-static void svm_migrate_page_free(struct page *page)
+static void svm_migrate_folio_free(struct folio *folio)
 {
+	struct page *page = &folio->page;
 	struct svm_range_bo *svm_bo = page->zone_device_data;
 
 	if (svm_bo) {
@@ -1008,7 +1009,7 @@ out_mmput:
 }
 
 static const struct dev_pagemap_ops svm_migrate_pgmap_ops = {
-	.page_free		= svm_migrate_page_free,
+	.folio_free		= svm_migrate_folio_free,
 	.migrate_to_ram		= svm_migrate_to_ram,
 };
 
diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c
index 22c44807e3fe..37d7cfbbb3e8 100644
--- a/drivers/gpu/drm/drm_pagemap.c
+++ b/drivers/gpu/drm/drm_pagemap.c
@@ -196,7 +196,7 @@ static void drm_pagemap_get_devmem_page(struct page *page,
 					struct drm_pagemap_zdd *zdd)
 {
 	page->zone_device_data = drm_pagemap_zdd_get(zdd);
-	zone_device_page_init(page);
+	zone_device_page_init(page, 0);
 }
 
 /**
@@ -752,15 +752,15 @@ err_out:
 }
 
 /**
- * drm_pagemap_page_free() - Put GPU SVM zone device data associated with a page
- * @page: Pointer to the page
+ * drm_pagemap_folio_free() - Put GPU SVM zone device data associated with a folio
+ * @folio: Pointer to the folio
  *
  * This function is a callback used to put the GPU SVM zone device data
  * associated with a page when it is being released.
  */
-static void drm_pagemap_page_free(struct page *page)
+static void drm_pagemap_folio_free(struct folio *folio)
 {
-	drm_pagemap_zdd_put(page->zone_device_data);
+	drm_pagemap_zdd_put(folio->page.zone_device_data);
 }
 
 /**
@@ -788,7 +788,7 @@ static vm_fault_t drm_pagemap_migrate_to_ram(struct vm_fault *vmf)
 }
 
 static const struct dev_pagemap_ops drm_pagemap_pagemap_ops = {
-	.page_free = drm_pagemap_page_free,
+	.folio_free = drm_pagemap_folio_free,
 	.migrate_to_ram = drm_pagemap_migrate_to_ram,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index ca4932a150e3..58071652679d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -50,6 +50,7 @@
  */
 #define DMEM_CHUNK_SIZE (2UL << 20)
 #define DMEM_CHUNK_NPAGES (DMEM_CHUNK_SIZE >> PAGE_SHIFT)
+#define NR_CHUNKS (128)
 
 enum nouveau_aper {
 	NOUVEAU_APER_VIRT,
@@ -83,9 +84,15 @@ struct nouveau_dmem {
 	struct list_head chunks;
 	struct mutex mutex;
 	struct page *free_pages;
+	struct folio *free_folios;
 	spinlock_t lock;
 };
 
+struct nouveau_dmem_dma_info {
+	dma_addr_t dma_addr;
+	size_t size;
+};
+
 static struct nouveau_dmem_chunk *nouveau_page_to_chunk(struct page *page)
 {
 	return container_of(page_pgmap(page), struct nouveau_dmem_chunk,
@@ -108,14 +115,20 @@ unsigned long nouveau_dmem_page_addr(struct page *page)
 	return chunk->bo->offset + off;
 }
 
-static void nouveau_dmem_page_free(struct page *page)
+static void nouveau_dmem_folio_free(struct folio *folio)
 {
+	struct page *page = &folio->page;
 	struct nouveau_dmem_chunk *chunk = nouveau_page_to_chunk(page);
 	struct nouveau_dmem *dmem = chunk->drm->dmem;
 
 	spin_lock(&dmem->lock);
-	page->zone_device_data = dmem->free_pages;
-	dmem->free_pages = page;
+	if (folio_order(folio)) {
+		page->zone_device_data = dmem->free_folios;
+		dmem->free_folios = folio;
+	} else {
+		page->zone_device_data = dmem->free_pages;
+		dmem->free_pages = page;
+	}
 
 	WARN_ON(!chunk->callocated);
 	chunk->callocated--;
@@ -139,20 +152,28 @@ static void nouveau_dmem_fence_done(struct nouveau_fence **fence)
 	}
 }
 
-static int nouveau_dmem_copy_one(struct nouveau_drm *drm, struct page *spage,
-				struct page *dpage, dma_addr_t *dma_addr)
+static int nouveau_dmem_copy_folio(struct nouveau_drm *drm,
+				   struct folio *sfolio, struct folio *dfolio,
+				   struct nouveau_dmem_dma_info *dma_info)
 {
 	struct device *dev = drm->dev->dev;
+	struct page *dpage = folio_page(dfolio, 0);
+	struct page *spage = folio_page(sfolio, 0);
 
-	lock_page(dpage);
+	folio_lock(dfolio);
 
-	*dma_addr = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(dev, *dma_addr))
+	dma_info->dma_addr = dma_map_page(dev, dpage, 0, page_size(dpage),
+					DMA_BIDIRECTIONAL);
+	dma_info->size = page_size(dpage);
+	if (dma_mapping_error(dev, dma_info->dma_addr))
 		return -EIO;
 
-	if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_HOST, *dma_addr,
-					 NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage))) {
-		dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
+	if (drm->dmem->migrate.copy_func(drm, folio_nr_pages(sfolio),
+					 NOUVEAU_APER_HOST, dma_info->dma_addr,
+					 NOUVEAU_APER_VRAM,
+					 nouveau_dmem_page_addr(spage))) {
+		dma_unmap_page(dev, dma_info->dma_addr, page_size(dpage),
+					DMA_BIDIRECTIONAL);
 		return -EIO;
 	}
 
@@ -165,21 +186,48 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf)
 	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;
+	struct page *dpage;
 	vm_fault_t ret = 0;
+	int err;
 	struct migrate_vma args = {
 		.vma		= vmf->vma,
-		.start		= vmf->address,
-		.end		= vmf->address + PAGE_SIZE,
-		.src		= &src,
-		.dst		= &dst,
 		.pgmap_owner	= drm->dev,
 		.fault_page	= vmf->page,
-		.flags		= MIGRATE_VMA_SELECT_DEVICE_PRIVATE,
+		.flags		= MIGRATE_VMA_SELECT_DEVICE_PRIVATE |
+				  MIGRATE_VMA_SELECT_COMPOUND,
+		.src = NULL,
+		.dst = NULL,
 	};
+	unsigned int order, nr;
+	struct folio *sfolio, *dfolio;
+	struct nouveau_dmem_dma_info dma_info;
+
+	sfolio = page_folio(vmf->page);
+	order = folio_order(sfolio);
+	nr = 1 << order;
+
+	/*
+	 * Handle partial unmap faults, where the folio is large, but
+	 * the pmd is split.
+	 */
+	if (vmf->pte) {
+		order = 0;
+		nr = 1;
+	}
+
+	if (order)
+		args.flags |= MIGRATE_VMA_SELECT_COMPOUND;
 
+	args.start = ALIGN_DOWN(vmf->address, (PAGE_SIZE << order));
+	args.vma = vmf->vma;
+	args.end = args.start + (PAGE_SIZE << order);
+	args.src = kcalloc(nr, sizeof(*args.src), GFP_KERNEL);
+	args.dst = kcalloc(nr, sizeof(*args.dst), GFP_KERNEL);
+
+	if (!args.src || !args.dst) {
+		ret = VM_FAULT_OOM;
+		goto err;
+	}
 	/*
 	 * FIXME what we really want is to find some heuristic to migrate more
 	 * than just one page on CPU fault. When such fault happens it is very
@@ -190,22 +238,28 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf)
 	if (!args.cpages)
 		return 0;
 
-	spage = migrate_pfn_to_page(src);
-	if (!spage || !(src & MIGRATE_PFN_MIGRATE))
-		goto done;
-
-	dpage = alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vmf->vma, vmf->address);
-	if (!dpage)
+	if (order)
+		dpage = folio_page(vma_alloc_folio(GFP_HIGHUSER | __GFP_ZERO,
+					order, vmf->vma, vmf->address), 0);
+	else
+		dpage = alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vmf->vma,
+					vmf->address);
+	if (!dpage) {
+		ret = VM_FAULT_OOM;
 		goto done;
+	}
 
-	dst = migrate_pfn(page_to_pfn(dpage));
+	args.dst[0] = migrate_pfn(page_to_pfn(dpage));
+	if (order)
+		args.dst[0] |= MIGRATE_PFN_COMPOUND;
+	dfolio = page_folio(dpage);
 
-	svmm = spage->zone_device_data;
+	svmm = folio_zone_device_data(sfolio);
 	mutex_lock(&svmm->mutex);
 	nouveau_svmm_invalidate(svmm, args.start, args.end);
-	ret = nouveau_dmem_copy_one(drm, spage, dpage, &dma_addr);
+	err = nouveau_dmem_copy_folio(drm, sfolio, dfolio, &dma_info);
 	mutex_unlock(&svmm->mutex);
-	if (ret) {
+	if (err) {
 		ret = VM_FAULT_SIGBUS;
 		goto done;
 	}
@@ -213,25 +267,40 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf)
 	nouveau_fence_new(&fence, dmem->migrate.chan);
 	migrate_vma_pages(&args);
 	nouveau_dmem_fence_done(&fence);
-	dma_unmap_page(drm->dev->dev, dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
+	dma_unmap_page(drm->dev->dev, dma_info.dma_addr, PAGE_SIZE,
+				DMA_BIDIRECTIONAL);
 done:
 	migrate_vma_finalize(&args);
+err:
+	kfree(args.src);
+	kfree(args.dst);
 	return ret;
 }
 
+static void nouveau_dmem_folio_split(struct folio *head, struct folio *tail)
+{
+	if (tail == NULL)
+		return;
+	tail->pgmap = head->pgmap;
+	tail->mapping = head->mapping;
+	folio_set_zone_device_data(tail, folio_zone_device_data(head));
+}
+
 static const struct dev_pagemap_ops nouveau_dmem_pagemap_ops = {
-	.page_free		= nouveau_dmem_page_free,
+	.folio_free		= nouveau_dmem_folio_free,
 	.migrate_to_ram		= nouveau_dmem_migrate_to_ram,
+	.folio_split		= nouveau_dmem_folio_split,
 };
 
 static int
-nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage)
+nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage,
+			 bool is_large)
 {
 	struct nouveau_dmem_chunk *chunk;
 	struct resource *res;
 	struct page *page;
 	void *ptr;
-	unsigned long i, pfn_first;
+	unsigned long i, pfn_first, pfn;
 	int ret;
 
 	chunk = kzalloc(sizeof(*chunk), GFP_KERNEL);
@@ -241,7 +310,7 @@ nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage)
 	}
 
 	/* Allocate unused physical address space for device private pages. */
-	res = request_free_mem_region(&iomem_resource, DMEM_CHUNK_SIZE,
+	res = request_free_mem_region(&iomem_resource, DMEM_CHUNK_SIZE * NR_CHUNKS,
 				      "nouveau_dmem");
 	if (IS_ERR(res)) {
 		ret = PTR_ERR(res);
@@ -274,16 +343,40 @@ nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage)
 	pfn_first = chunk->pagemap.range.start >> PAGE_SHIFT;
 	page = pfn_to_page(pfn_first);
 	spin_lock(&drm->dmem->lock);
-	for (i = 0; i < DMEM_CHUNK_NPAGES - 1; ++i, ++page) {
-		page->zone_device_data = drm->dmem->free_pages;
-		drm->dmem->free_pages = page;
+
+	pfn = pfn_first;
+	for (i = 0; i < NR_CHUNKS; i++) {
+		int j;
+
+		if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) || !is_large) {
+			for (j = 0; j < DMEM_CHUNK_NPAGES - 1; j++, pfn++) {
+				page = pfn_to_page(pfn);
+				page->zone_device_data = drm->dmem->free_pages;
+				drm->dmem->free_pages = page;
+			}
+		} else {
+			page = pfn_to_page(pfn);
+			page->zone_device_data = drm->dmem->free_folios;
+			drm->dmem->free_folios = page_folio(page);
+			pfn += DMEM_CHUNK_NPAGES;
+		}
+	}
+
+	/* Move to next page */
+	if (is_large) {
+		*ppage = &drm->dmem->free_folios->page;
+		drm->dmem->free_folios = (*ppage)->zone_device_data;
+	} else {
+		*ppage = drm->dmem->free_pages;
+		drm->dmem->free_pages = (*ppage)->zone_device_data;
 	}
-	*ppage = page;
+
 	chunk->callocated++;
 	spin_unlock(&drm->dmem->lock);
 
-	NV_INFO(drm, "DMEM: registered %ldMB of device memory\n",
-		DMEM_CHUNK_SIZE >> 20);
+	NV_INFO(drm, "DMEM: registered %ldMB of %sdevice memory %lx %lx\n",
+		NR_CHUNKS * DMEM_CHUNK_SIZE >> 20, is_large ? "THP " : "", pfn_first,
+		nouveau_dmem_page_addr(page));
 
 	return 0;
 
@@ -298,27 +391,41 @@ out:
 }
 
 static struct page *
-nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm)
+nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm, bool is_large)
 {
 	struct nouveau_dmem_chunk *chunk;
 	struct page *page = NULL;
+	struct folio *folio = NULL;
 	int ret;
+	unsigned int order = 0;
 
 	spin_lock(&drm->dmem->lock);
-	if (drm->dmem->free_pages) {
+	if (is_large && drm->dmem->free_folios) {
+		folio = drm->dmem->free_folios;
+		page = &folio->page;
+		drm->dmem->free_folios = page->zone_device_data;
+		chunk = nouveau_page_to_chunk(&folio->page);
+		chunk->callocated++;
+		spin_unlock(&drm->dmem->lock);
+		order = ilog2(DMEM_CHUNK_NPAGES);
+	} else if (!is_large && drm->dmem->free_pages) {
 		page = drm->dmem->free_pages;
 		drm->dmem->free_pages = page->zone_device_data;
 		chunk = nouveau_page_to_chunk(page);
 		chunk->callocated++;
 		spin_unlock(&drm->dmem->lock);
+		folio = page_folio(page);
 	} else {
 		spin_unlock(&drm->dmem->lock);
-		ret = nouveau_dmem_chunk_alloc(drm, &page);
+		ret = nouveau_dmem_chunk_alloc(drm, &page, is_large);
 		if (ret)
 			return NULL;
+		folio = page_folio(page);
+		if (is_large)
+			order = ilog2(DMEM_CHUNK_NPAGES);
 	}
 
-	zone_device_page_init(page);
+	zone_device_folio_init(folio, order);
 	return page;
 }
 
@@ -369,12 +476,12 @@ 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_dmem_dma_info *dma_info;
 	struct nouveau_fence *fence;
 
 	src_pfns = kvcalloc(npages, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL);
 	dst_pfns = kvcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL);
-	dma_addrs = kvcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL | __GFP_NOFAIL);
+	dma_info = kvcalloc(npages, sizeof(*dma_info), GFP_KERNEL | __GFP_NOFAIL);
 
 	migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT,
 			npages);
@@ -382,17 +489,28 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk)
 	for (i = 0; i < npages; i++) {
 		if (src_pfns[i] & MIGRATE_PFN_MIGRATE) {
 			struct page *dpage;
+			struct folio *folio = page_folio(
+				migrate_pfn_to_page(src_pfns[i]));
+			unsigned int order = folio_order(folio);
+
+			if (src_pfns[i] & MIGRATE_PFN_COMPOUND) {
+				dpage = folio_page(
+						folio_alloc(
+						GFP_HIGHUSER_MOVABLE, order), 0);
+			} else {
+				/*
+				 * _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);
+			}
 
-			/*
-			 * _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_dmem_copy_folio(chunk->drm,
+				page_folio(migrate_pfn_to_page(src_pfns[i])),
+				page_folio(dpage),
+				&dma_info[i]);
 		}
 	}
 
@@ -403,8 +521,9 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk)
 	kvfree(src_pfns);
 	kvfree(dst_pfns);
 	for (i = 0; i < npages; i++)
-		dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL);
-	kvfree(dma_addrs);
+		dma_unmap_page(chunk->drm->dev->dev, dma_info[i].dma_addr,
+				dma_info[i].size, DMA_BIDIRECTIONAL);
+	kvfree(dma_info);
 }
 
 void
@@ -607,31 +726,36 @@ nouveau_dmem_init(struct nouveau_drm *drm)
 
 static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm,
 		struct nouveau_svmm *svmm, unsigned long src,
-		dma_addr_t *dma_addr, u64 *pfn)
+		struct nouveau_dmem_dma_info *dma_info, u64 *pfn)
 {
 	struct device *dev = drm->dev->dev;
 	struct page *dpage, *spage;
 	unsigned long paddr;
+	bool is_large = false;
+	unsigned long mpfn;
 
 	spage = migrate_pfn_to_page(src);
 	if (!(src & MIGRATE_PFN_MIGRATE))
 		goto out;
 
-	dpage = nouveau_dmem_page_alloc_locked(drm);
+	is_large = src & MIGRATE_PFN_COMPOUND;
+	dpage = nouveau_dmem_page_alloc_locked(drm, is_large);
 	if (!dpage)
 		goto out;
 
 	paddr = nouveau_dmem_page_addr(dpage);
 	if (spage) {
-		*dma_addr = dma_map_page(dev, spage, 0, page_size(spage),
+		dma_info->dma_addr = dma_map_page(dev, spage, 0, page_size(spage),
 					 DMA_BIDIRECTIONAL);
-		if (dma_mapping_error(dev, *dma_addr))
+		dma_info->size = page_size(spage);
+		if (dma_mapping_error(dev, dma_info->dma_addr))
 			goto out_free_page;
-		if (drm->dmem->migrate.copy_func(drm, 1,
-			NOUVEAU_APER_VRAM, paddr, NOUVEAU_APER_HOST, *dma_addr))
+		if (drm->dmem->migrate.copy_func(drm, folio_nr_pages(page_folio(spage)),
+			NOUVEAU_APER_VRAM, paddr, NOUVEAU_APER_HOST,
+			dma_info->dma_addr))
 			goto out_dma_unmap;
 	} else {
-		*dma_addr = DMA_MAPPING_ERROR;
+		dma_info->dma_addr = DMA_MAPPING_ERROR;
 		if (drm->dmem->migrate.clear_func(drm, page_size(dpage),
 			NOUVEAU_APER_VRAM, paddr))
 			goto out_free_page;
@@ -642,10 +766,13 @@ static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm,
 		((paddr >> PAGE_SHIFT) << NVIF_VMM_PFNMAP_V0_ADDR_SHIFT);
 	if (src & MIGRATE_PFN_WRITE)
 		*pfn |= NVIF_VMM_PFNMAP_V0_W;
-	return migrate_pfn(page_to_pfn(dpage));
+	mpfn = migrate_pfn(page_to_pfn(dpage));
+	if (folio_order(page_folio(dpage)))
+		mpfn |= MIGRATE_PFN_COMPOUND;
+	return mpfn;
 
 out_dma_unmap:
-	dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
+	dma_unmap_page(dev, dma_info->dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
 out_free_page:
 	nouveau_dmem_page_free_locked(drm, dpage);
 out:
@@ -655,27 +782,38 @@ out:
 
 static void nouveau_dmem_migrate_chunk(struct nouveau_drm *drm,
 		struct nouveau_svmm *svmm, struct migrate_vma *args,
-		dma_addr_t *dma_addrs, u64 *pfns)
+		struct nouveau_dmem_dma_info *dma_info, u64 *pfns)
 {
 	struct nouveau_fence *fence;
 	unsigned long addr = args->start, nr_dma = 0, i;
+	unsigned long order = 0;
+
+	for (i = 0; addr < args->end; ) {
+		struct folio *folio;
 
-	for (i = 0; addr < args->end; i++) {
 		args->dst[i] = nouveau_dmem_migrate_copy_one(drm, svmm,
-				args->src[i], dma_addrs + nr_dma, pfns + i);
-		if (!dma_mapping_error(drm->dev->dev, dma_addrs[nr_dma]))
+				args->src[i], dma_info + nr_dma, pfns + i);
+		if (!args->dst[i]) {
+			i++;
+			addr += PAGE_SIZE;
+			continue;
+		}
+		if (!dma_mapping_error(drm->dev->dev, dma_info[nr_dma].dma_addr))
 			nr_dma++;
-		addr += PAGE_SIZE;
+		folio = page_folio(migrate_pfn_to_page(args->dst[i]));
+		order = folio_order(folio);
+		i += 1 << order;
+		addr += (1 << order) * PAGE_SIZE;
 	}
 
 	nouveau_fence_new(&fence, drm->dmem->migrate.chan);
 	migrate_vma_pages(args);
 	nouveau_dmem_fence_done(&fence);
-	nouveau_pfns_map(svmm, args->vma->vm_mm, args->start, pfns, i);
+	nouveau_pfns_map(svmm, args->vma->vm_mm, args->start, pfns, i, order);
 
 	while (nr_dma--) {
-		dma_unmap_page(drm->dev->dev, dma_addrs[nr_dma], PAGE_SIZE,
-				DMA_BIDIRECTIONAL);
+		dma_unmap_page(drm->dev->dev, dma_info[nr_dma].dma_addr,
+				dma_info[nr_dma].size, DMA_BIDIRECTIONAL);
 	}
 	migrate_vma_finalize(args);
 }
@@ -688,20 +826,27 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm,
 			 unsigned long end)
 {
 	unsigned long npages = (end - start) >> PAGE_SHIFT;
-	unsigned long max = min(SG_MAX_SINGLE_ALLOC, npages);
-	dma_addr_t *dma_addrs;
+	unsigned long max = npages;
 	struct migrate_vma args = {
 		.vma		= vma,
 		.start		= start,
 		.pgmap_owner	= drm->dev,
-		.flags		= MIGRATE_VMA_SELECT_SYSTEM,
+		.flags		= MIGRATE_VMA_SELECT_SYSTEM
+				  | MIGRATE_VMA_SELECT_COMPOUND,
 	};
 	unsigned long i;
 	u64 *pfns;
 	int ret = -ENOMEM;
+	struct nouveau_dmem_dma_info *dma_info;
 
-	if (drm->dmem == NULL)
-		return -ENODEV;
+	if (drm->dmem == NULL) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		if (max > (unsigned long)HPAGE_PMD_NR)
+			max = (unsigned long)HPAGE_PMD_NR;
 
 	args.src = kcalloc(max, sizeof(*args.src), GFP_KERNEL);
 	if (!args.src)
@@ -710,8 +855,8 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm,
 	if (!args.dst)
 		goto out_free_src;
 
-	dma_addrs = kmalloc_array(max, sizeof(*dma_addrs), GFP_KERNEL);
-	if (!dma_addrs)
+	dma_info = kmalloc_array(max, sizeof(*dma_info), GFP_KERNEL);
+	if (!dma_info)
 		goto out_free_dst;
 
 	pfns = nouveau_pfns_alloc(max);
@@ -729,7 +874,7 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm,
 			goto out_free_pfns;
 
 		if (args.cpages)
-			nouveau_dmem_migrate_chunk(drm, svmm, &args, dma_addrs,
+			nouveau_dmem_migrate_chunk(drm, svmm, &args, dma_info,
 						   pfns);
 		args.start = args.end;
 	}
@@ -738,7 +883,7 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm,
 out_free_pfns:
 	nouveau_pfns_free(pfns);
 out_free_dma:
-	kfree(dma_addrs);
+	kfree(dma_info);
 out_free_dst:
 	kfree(args.dst);
 out_free_src:
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index 6fa387da0637..b8a3378154d5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -921,12 +921,14 @@ nouveau_pfns_free(u64 *pfns)
 
 void
 nouveau_pfns_map(struct nouveau_svmm *svmm, struct mm_struct *mm,
-		 unsigned long addr, u64 *pfns, unsigned long npages)
+		 unsigned long addr, u64 *pfns, unsigned long npages,
+		 unsigned int page_shift)
 {
 	struct nouveau_pfnmap_args *args = nouveau_pfns_to_args(pfns);
 
 	args->p.addr = addr;
-	args->p.size = npages << PAGE_SHIFT;
+	args->p.size = npages << page_shift;
+	args->p.page = page_shift;
 
 	mutex_lock(&svmm->mutex);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.h b/drivers/gpu/drm/nouveau/nouveau_svm.h
index e7d63d7f0c2d..3fd78662f17e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.h
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.h
@@ -33,7 +33,8 @@ void nouveau_svmm_invalidate(struct nouveau_svmm *svmm, u64 start, u64 limit);
 u64 *nouveau_pfns_alloc(unsigned long npages);
 void nouveau_pfns_free(u64 *pfns);
 void nouveau_pfns_map(struct nouveau_svmm *svmm, struct mm_struct *mm,
-		      unsigned long addr, u64 *pfns, unsigned long npages);
+		      unsigned long addr, u64 *pfns, unsigned long npages,
+		      unsigned int page_shift);
 #else /* IS_ENABLED(CONFIG_DRM_NOUVEAU_SVM) */
 static inline void nouveau_svm_init(struct nouveau_drm *drm) {}
 static inline void nouveau_svm_fini(struct nouveau_drm *drm) {}