1 files changed, 869 insertions, 217 deletions

diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 28528285942c..8af169d3873a 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/cdev.h>
 #include <linux/device.h>
+#include <linux/memremap.h>
 #include <linux/mutex.h>
 #include <linux/rwsem.h>
 #include <linux/sched.h>
@@ -25,18 +26,41 @@
 #include <linux/swapops.h>
 #include <linux/sched/mm.h>
 #include <linux/platform_device.h>
+#include <linux/rmap.h>
+#include <linux/mmu_notifier.h>
+#include <linux/migrate.h>
 
 #include "test_hmm_uapi.h"
 
-#define DMIRROR_NDEVICES		2
+#define DMIRROR_NDEVICES		4
 #define DMIRROR_RANGE_FAULT_TIMEOUT	1000
 #define DEVMEM_CHUNK_SIZE		(256 * 1024 * 1024U)
 #define DEVMEM_CHUNKS_RESERVE		16
 
+/*
+ * For device_private pages, dpage is just a dummy struct page
+ * representing a piece of device memory. dmirror_devmem_alloc_page
+ * allocates a real system memory page as backing storage to fake a
+ * real device. zone_device_data points to that backing page. But
+ * for device_coherent memory, the struct page represents real
+ * physical CPU-accessible memory that we can use directly.
+ */
+#define BACKING_PAGE(page) (is_device_private_page((page)) ? \
+			   (page)->zone_device_data : (page))
+
+static unsigned long spm_addr_dev0;
+module_param(spm_addr_dev0, long, 0644);
+MODULE_PARM_DESC(spm_addr_dev0,
+		"Specify start address for SPM (special purpose memory) used for device 0. By setting this Coherent device type will be used. Make sure spm_addr_dev1 is set too. Minimum SPM size should be DEVMEM_CHUNK_SIZE.");
+
+static unsigned long spm_addr_dev1;
+module_param(spm_addr_dev1, long, 0644);
+MODULE_PARM_DESC(spm_addr_dev1,
+		"Specify start address for SPM (special purpose memory) used for device 1. By setting this Coherent device type will be used. Make sure spm_addr_dev0 is set too. Minimum SPM size should be DEVMEM_CHUNK_SIZE.");
+
 static const struct dev_pagemap_ops dmirror_devmem_ops;
 static const struct mmu_interval_notifier_ops dmirror_min_ops;
 static dev_t dmirror_dev;
-static struct page *dmirror_zero_page;
 
 struct dmirror_device;
 
@@ -47,6 +71,7 @@ struct dmirror_bounce {
 	unsigned long		cpages;
 };
 
+#define DPT_XA_TAG_ATOMIC 1UL
 #define DPT_XA_TAG_WRITE 3UL
 
 /*
@@ -67,6 +92,7 @@ struct dmirror {
 	struct xarray			pt;
 	struct mmu_interval_notifier	notifier;
 	struct mutex			mutex;
+	__u64			flags;
 };
 
 /*
@@ -75,6 +101,7 @@ struct dmirror {
 struct dmirror_chunk {
 	struct dev_pagemap	pagemap;
 	struct dmirror_device	*mdevice;
+	bool remove;
 };
 
 /*
@@ -82,7 +109,8 @@ struct dmirror_chunk {
  */
 struct dmirror_device {
 	struct cdev		cdevice;
-	struct hmm_devmem	*devmem;
+	unsigned int            zone_device_type;
+	struct device		device;
 
 	unsigned int		devmem_capacity;
 	unsigned int		devmem_count;
@@ -92,6 +120,7 @@ struct dmirror_device {
 	unsigned long		calloc;
 	unsigned long		cfree;
 	struct page		*free_pages;
+	struct folio		*free_folios;
 	spinlock_t		lock;		/* protects the above */
 };
 
@@ -110,6 +139,21 @@ static int dmirror_bounce_init(struct dmirror_bounce *bounce,
 	return 0;
 }
 
+static bool dmirror_is_private_zone(struct dmirror_device *mdevice)
+{
+	return (mdevice->zone_device_type ==
+		HMM_DMIRROR_MEMORY_DEVICE_PRIVATE);
+}
+
+static enum migrate_vma_direction
+dmirror_select_device(struct dmirror *dmirror)
+{
+	return (dmirror->mdevice->zone_device_type ==
+		HMM_DMIRROR_MEMORY_DEVICE_PRIVATE) ?
+		MIGRATE_VMA_SELECT_DEVICE_PRIVATE :
+		MIGRATE_VMA_SELECT_DEVICE_COHERENT;
+}
+
 static void dmirror_bounce_fini(struct dmirror_bounce *bounce)
 {
 	vfree(bounce->ptr);
@@ -151,11 +195,16 @@ static int dmirror_fops_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+static struct dmirror_chunk *dmirror_page_to_chunk(struct page *page)
+{
+	return container_of(page_pgmap(page), 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)
@@ -214,6 +263,14 @@ static bool dmirror_interval_invalidate(struct mmu_interval_notifier *mni,
 {
 	struct dmirror *dmirror = container_of(mni, struct dmirror, notifier);
 
+	/*
+	 * Ignore invalidation callbacks for device private pages since
+	 * the invalidation is handled as part of the migration process.
+	 */
+	if (range->event == MMU_NOTIFY_MIGRATE &&
+	    range->owner == dmirror->mdevice)
+		return true;
+
 	if (mmu_notifier_range_blockable(range))
 		mutex_lock(&dmirror->mutex);
 	else if (!mutex_trylock(&dmirror->mutex))
@@ -275,7 +332,7 @@ static int dmirror_fault(struct dmirror *dmirror, unsigned long start,
 {
 	struct mm_struct *mm = dmirror->notifier.mm;
 	unsigned long addr;
-	unsigned long pfns[64];
+	unsigned long pfns[32];
 	struct hmm_range range = {
 		.notifier = &dmirror->notifier,
 		.hmm_pfns = pfns,
@@ -314,16 +371,13 @@ static int dmirror_do_read(struct dmirror *dmirror, unsigned long start,
 	for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) {
 		void *entry;
 		struct page *page;
-		void *tmp;
 
 		entry = xa_load(&dmirror->pt, pfn);
 		page = xa_untag_pointer(entry);
 		if (!page)
 			return -ENOENT;
 
-		tmp = kmap(page);
-		memcpy(ptr, tmp, PAGE_SIZE);
-		kunmap(page);
+		memcpy_from_page(ptr, page, 0, PAGE_SIZE);
 
 		ptr += PAGE_SIZE;
 		bounce->cpages++;
@@ -383,16 +437,13 @@ static int dmirror_do_write(struct dmirror *dmirror, unsigned long start,
 	for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) {
 		void *entry;
 		struct page *page;
-		void *tmp;
 
 		entry = xa_load(&dmirror->pt, pfn);
 		page = xa_untag_pointer(entry);
 		if (!page || xa_pointer_tag(entry) != DPT_XA_TAG_WRITE)
 			return -ENOENT;
 
-		tmp = kmap(page);
-		memcpy(tmp, ptr, PAGE_SIZE);
-		kunmap(page);
+		memcpy_to_page(page, 0, ptr, PAGE_SIZE);
 
 		ptr += PAGE_SIZE;
 		bounce->cpages++;
@@ -442,15 +493,47 @@ fini:
 	return ret;
 }
 
-static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
-				   struct page **ppage)
+static int dmirror_allocate_chunk(struct dmirror_device *mdevice,
+				  struct page **ppage, bool is_large)
 {
 	struct dmirror_chunk *devmem;
-	struct resource *res;
+	struct resource *res = NULL;
 	unsigned long pfn;
 	unsigned long pfn_first;
 	unsigned long pfn_last;
 	void *ptr;
+	int ret = -ENOMEM;
+
+	devmem = kzalloc(sizeof(*devmem), GFP_KERNEL);
+	if (!devmem)
+		return ret;
+
+	switch (mdevice->zone_device_type) {
+	case HMM_DMIRROR_MEMORY_DEVICE_PRIVATE:
+		res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE,
+					      "hmm_dmirror");
+		if (IS_ERR_OR_NULL(res))
+			goto err_devmem;
+		devmem->pagemap.range.start = res->start;
+		devmem->pagemap.range.end = res->end;
+		devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
+		break;
+	case HMM_DMIRROR_MEMORY_DEVICE_COHERENT:
+		devmem->pagemap.range.start = (MINOR(mdevice->cdevice.dev) - 2) ?
+							spm_addr_dev0 :
+							spm_addr_dev1;
+		devmem->pagemap.range.end = devmem->pagemap.range.start +
+					    DEVMEM_CHUNK_SIZE - 1;
+		devmem->pagemap.type = MEMORY_DEVICE_COHERENT;
+		break;
+	default:
+		ret = -EINVAL;
+		goto err_devmem;
+	}
+
+	devmem->pagemap.nr_range = 1;
+	devmem->pagemap.ops = &dmirror_devmem_ops;
+	devmem->pagemap.owner = mdevice;
 
 	mutex_lock(&mdevice->devmem_lock);
 
@@ -464,33 +547,22 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
 				sizeof(new_chunks[0]) * new_capacity,
 				GFP_KERNEL);
 		if (!new_chunks)
-			goto err;
+			goto err_release;
 		mdevice->devmem_capacity = new_capacity;
 		mdevice->devmem_chunks = new_chunks;
 	}
-
-	res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE,
-					"hmm_dmirror");
-	if (IS_ERR(res))
-		goto err;
-
-	devmem = kzalloc(sizeof(*devmem), GFP_KERNEL);
-	if (!devmem)
-		goto err_release;
-
-	devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
-	devmem->pagemap.res = *res;
-	devmem->pagemap.ops = &dmirror_devmem_ops;
-	devmem->pagemap.owner = mdevice;
-
 	ptr = memremap_pages(&devmem->pagemap, numa_node_id());
-	if (IS_ERR(ptr))
-		goto err_free;
+	if (IS_ERR_OR_NULL(ptr)) {
+		if (ptr)
+			ret = PTR_ERR(ptr);
+		else
+			ret = -EFAULT;
+		goto err_release;
+	}
 
 	devmem->mdevice = mdevice;
-	pfn_first = devmem->pagemap.res.start >> PAGE_SHIFT;
-	pfn_last = pfn_first +
-		(resource_size(&devmem->pagemap.res) >> PAGE_SHIFT);
+	pfn_first = devmem->pagemap.range.start >> PAGE_SHIFT;
+	pfn_last = pfn_first + (range_len(&devmem->pagemap.range) >> PAGE_SHIFT);
 	mdevice->devmem_chunks[mdevice->devmem_count++] = devmem;
 
 	mutex_unlock(&mdevice->devmem_lock);
@@ -502,108 +574,174 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
 		pfn_first, pfn_last);
 
 	spin_lock(&mdevice->lock);
-	for (pfn = pfn_first; pfn < pfn_last; pfn++) {
+	for (pfn = pfn_first; pfn < pfn_last; ) {
 		struct page *page = pfn_to_page(pfn);
 
+		if (is_large && IS_ALIGNED(pfn, HPAGE_PMD_NR)
+			&& (pfn + HPAGE_PMD_NR <= pfn_last)) {
+			page->zone_device_data = mdevice->free_folios;
+			mdevice->free_folios = page_folio(page);
+			pfn += HPAGE_PMD_NR;
+			continue;
+		}
+
 		page->zone_device_data = mdevice->free_pages;
 		mdevice->free_pages = page;
+		pfn++;
 	}
+
+	ret = 0;
 	if (ppage) {
-		*ppage = mdevice->free_pages;
-		mdevice->free_pages = (*ppage)->zone_device_data;
-		mdevice->calloc++;
+		if (is_large) {
+			if (!mdevice->free_folios) {
+				ret = -ENOMEM;
+				goto err_unlock;
+			}
+			*ppage = folio_page(mdevice->free_folios, 0);
+			mdevice->free_folios = (*ppage)->zone_device_data;
+			mdevice->calloc += HPAGE_PMD_NR;
+		} else if (mdevice->free_pages) {
+			*ppage = mdevice->free_pages;
+			mdevice->free_pages = (*ppage)->zone_device_data;
+			mdevice->calloc++;
+		} else {
+			ret = -ENOMEM;
+			goto err_unlock;
+		}
 	}
+err_unlock:
 	spin_unlock(&mdevice->lock);
 
-	return true;
+	return ret;
 
-err_free:
-	kfree(devmem);
 err_release:
-	release_mem_region(devmem->pagemap.res.start,
-			   resource_size(&devmem->pagemap.res));
-err:
 	mutex_unlock(&mdevice->devmem_lock);
-	return false;
+	if (res && devmem->pagemap.type == MEMORY_DEVICE_PRIVATE)
+		release_mem_region(devmem->pagemap.range.start,
+				   range_len(&devmem->pagemap.range));
+err_devmem:
+	kfree(devmem);
+
+	return ret;
 }
 
-static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
+static struct page *dmirror_devmem_alloc_page(struct dmirror *dmirror,
+					      bool is_large)
 {
 	struct page *dpage = NULL;
-	struct page *rpage;
+	struct page *rpage = NULL;
+	unsigned int order = is_large ? HPAGE_PMD_ORDER : 0;
+	struct dmirror_device *mdevice = dmirror->mdevice;
 
 	/*
-	 * This is a fake device so we alloc real system memory to store
-	 * our device memory.
+	 * For ZONE_DEVICE private type, this is a fake device so we allocate
+	 * real system memory to store our device memory.
+	 * For ZONE_DEVICE coherent type we use the actual dpage to store the
+	 * data and ignore rpage.
 	 */
-	rpage = alloc_page(GFP_HIGHUSER);
-	if (!rpage)
-		return NULL;
-
+	if (dmirror_is_private_zone(mdevice)) {
+		rpage = folio_page(folio_alloc(GFP_HIGHUSER, order), 0);
+		if (!rpage)
+			return NULL;
+	}
 	spin_lock(&mdevice->lock);
 
-	if (mdevice->free_pages) {
+	if (is_large && mdevice->free_folios) {
+		dpage = folio_page(mdevice->free_folios, 0);
+		mdevice->free_folios = dpage->zone_device_data;
+		mdevice->calloc += 1 << order;
+		spin_unlock(&mdevice->lock);
+	} else if (!is_large && mdevice->free_pages) {
 		dpage = mdevice->free_pages;
 		mdevice->free_pages = dpage->zone_device_data;
 		mdevice->calloc++;
 		spin_unlock(&mdevice->lock);
 	} else {
 		spin_unlock(&mdevice->lock);
-		if (!dmirror_allocate_chunk(mdevice, &dpage))
+		if (dmirror_allocate_chunk(mdevice, &dpage, is_large))
 			goto error;
 	}
 
+	zone_device_folio_init(page_folio(dpage), order);
 	dpage->zone_device_data = rpage;
-	get_page(dpage);
-	lock_page(dpage);
 	return dpage;
 
 error:
-	__free_page(rpage);
+	if (rpage)
+		__free_pages(rpage, order);
 	return NULL;
 }
 
 static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args,
 					   struct dmirror *dmirror)
 {
-	struct dmirror_device *mdevice = dmirror->mdevice;
 	const unsigned long *src = args->src;
 	unsigned long *dst = args->dst;
 	unsigned long addr;
 
-	for (addr = args->start; addr < args->end; addr += PAGE_SIZE,
-						   src++, dst++) {
+	for (addr = args->start; addr < args->end; ) {
 		struct page *spage;
 		struct page *dpage;
 		struct page *rpage;
+		bool is_large = *src & MIGRATE_PFN_COMPOUND;
+		int write = (*src & MIGRATE_PFN_WRITE) ? MIGRATE_PFN_WRITE : 0;
+		unsigned long nr = 1;
 
 		if (!(*src & MIGRATE_PFN_MIGRATE))
-			continue;
+			goto next;
 
 		/*
 		 * Note that spage might be NULL which is OK since it is an
 		 * unallocated pte_none() or read-only zero page.
 		 */
 		spage = migrate_pfn_to_page(*src);
-
-		/*
-		 * Don't migrate device private pages from our own driver or
-		 * others. For our own we would do a device private memory copy
-		 * not a migration and for others, we would need to fault the
-		 * other device's page into system memory first.
-		 */
-		if (spage && is_zone_device_page(spage))
+		if (WARN(spage && is_zone_device_page(spage),
+		     "page already in device spage pfn: 0x%lx\n",
+		     page_to_pfn(spage)))
+			goto next;
+
+		if (dmirror->flags & HMM_DMIRROR_FLAG_FAIL_ALLOC) {
+			dmirror->flags &= ~HMM_DMIRROR_FLAG_FAIL_ALLOC;
+			dpage = NULL;
+		} else
+			dpage = dmirror_devmem_alloc_page(dmirror, is_large);
+
+		if (!dpage) {
+			struct folio *folio;
+			unsigned long i;
+			unsigned long spfn = *src >> MIGRATE_PFN_SHIFT;
+			struct page *src_page;
+
+			if (!is_large)
+				goto next;
+
+			if (!spage && is_large) {
+				nr = HPAGE_PMD_NR;
+			} else {
+				folio = page_folio(spage);
+				nr = folio_nr_pages(folio);
+			}
+
+			for (i = 0; i < nr && addr < args->end; i++) {
+				dpage = dmirror_devmem_alloc_page(dmirror, false);
+				rpage = BACKING_PAGE(dpage);
+				rpage->zone_device_data = dmirror;
+
+				*dst = migrate_pfn(page_to_pfn(dpage)) | write;
+				src_page = pfn_to_page(spfn + i);
+
+				if (spage)
+					copy_highpage(rpage, src_page);
+				else
+					clear_highpage(rpage);
+				src++;
+				dst++;
+				addr += PAGE_SIZE;
+			}
 			continue;
+		}
 
-		dpage = dmirror_devmem_alloc_page(mdevice);
-		if (!dpage)
-			continue;
-
-		rpage = dpage->zone_device_data;
-		if (spage)
-			copy_highpage(rpage, spage);
-		else
-			clear_highpage(rpage);
+		rpage = BACKING_PAGE(dpage);
 
 		/*
 		 * Normally, a device would use the page->zone_device_data to
@@ -613,14 +751,82 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args,
 		 */
 		rpage->zone_device_data = dmirror;
 
-		*dst = migrate_pfn(page_to_pfn(dpage)) |
-			    MIGRATE_PFN_LOCKED;
-		if ((*src & MIGRATE_PFN_WRITE) ||
-		    (!spage && args->vma->vm_flags & VM_WRITE))
-			*dst |= MIGRATE_PFN_WRITE;
+		pr_debug("migrating from sys to dev pfn src: 0x%lx pfn dst: 0x%lx\n",
+			 page_to_pfn(spage), page_to_pfn(dpage));
+
+		*dst = migrate_pfn(page_to_pfn(dpage)) | write;
+
+		if (is_large) {
+			int i;
+			struct folio *folio = page_folio(dpage);
+			*dst |= MIGRATE_PFN_COMPOUND;
+
+			if (folio_test_large(folio)) {
+				for (i = 0; i < folio_nr_pages(folio); i++) {
+					struct page *dst_page =
+						pfn_to_page(page_to_pfn(rpage) + i);
+					struct page *src_page =
+						pfn_to_page(page_to_pfn(spage) + i);
+
+					if (spage)
+						copy_highpage(dst_page, src_page);
+					else
+						clear_highpage(dst_page);
+					src++;
+					dst++;
+					addr += PAGE_SIZE;
+				}
+				continue;
+			}
+		}
+
+		if (spage)
+			copy_highpage(rpage, spage);
+		else
+			clear_highpage(rpage);
+
+next:
+		src++;
+		dst++;
+		addr += PAGE_SIZE;
 	}
 }
 
+static int dmirror_check_atomic(struct dmirror *dmirror, unsigned long start,
+			     unsigned long end)
+{
+	unsigned long pfn;
+
+	for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) {
+		void *entry;
+
+		entry = xa_load(&dmirror->pt, pfn);
+		if (xa_pointer_tag(entry) == DPT_XA_TAG_ATOMIC)
+			return -EPERM;
+	}
+
+	return 0;
+}
+
+static int dmirror_atomic_map(unsigned long addr, struct page *page,
+		struct dmirror *dmirror)
+{
+	void *entry;
+
+	/* Map the migrated pages into the device's page tables. */
+	mutex_lock(&dmirror->mutex);
+
+	entry = xa_tag_pointer(page, DPT_XA_TAG_ATOMIC);
+	entry = xa_store(&dmirror->pt, addr >> PAGE_SHIFT, entry, GFP_ATOMIC);
+	if (xa_is_err(entry)) {
+		mutex_unlock(&dmirror->mutex);
+		return xa_err(entry);
+	}
+
+	mutex_unlock(&dmirror->mutex);
+	return 0;
+}
+
 static int dmirror_migrate_finalize_and_map(struct migrate_vma *args,
 					    struct dmirror *dmirror)
 {
@@ -629,14 +835,17 @@ static int dmirror_migrate_finalize_and_map(struct migrate_vma *args,
 	const unsigned long *src = args->src;
 	const unsigned long *dst = args->dst;
 	unsigned long pfn;
+	const unsigned long start_pfn = start >> PAGE_SHIFT;
+	const unsigned long end_pfn = end >> PAGE_SHIFT;
 
 	/* Map the migrated pages into the device's page tables. */
 	mutex_lock(&dmirror->mutex);
 
-	for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++,
-								src++, dst++) {
+	for (pfn = start_pfn; pfn < end_pfn; pfn++, src++, dst++) {
 		struct page *dpage;
 		void *entry;
+		int nr, i;
+		struct page *rpage;
 
 		if (!(*src & MIGRATE_PFN_MIGRATE))
 			continue;
@@ -645,17 +854,25 @@ static int dmirror_migrate_finalize_and_map(struct migrate_vma *args,
 		if (!dpage)
 			continue;
 
-		/*
-		 * Store the page that holds the data so the page table
-		 * doesn't have to deal with ZONE_DEVICE private pages.
-		 */
-		entry = dpage->zone_device_data;
-		if (*dst & MIGRATE_PFN_WRITE)
-			entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE);
-		entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC);
-		if (xa_is_err(entry)) {
-			mutex_unlock(&dmirror->mutex);
-			return xa_err(entry);
+		if (*dst & MIGRATE_PFN_COMPOUND)
+			nr = folio_nr_pages(page_folio(dpage));
+		else
+			nr = 1;
+
+		WARN_ON_ONCE(end_pfn < start_pfn + nr);
+
+		rpage = BACKING_PAGE(dpage);
+		VM_WARN_ON(folio_nr_pages(page_folio(rpage)) != nr);
+
+		for (i = 0; i < nr; i++) {
+			entry = folio_page(page_folio(rpage), i);
+			if (*dst & MIGRATE_PFN_WRITE)
+				entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE);
+			entry = xa_store(&dmirror->pt, pfn + i, entry, GFP_ATOMIC);
+			if (xa_is_err(entry)) {
+				mutex_unlock(&dmirror->mutex);
+				return xa_err(entry);
+			}
 		}
 	}
 
@@ -663,19 +880,238 @@ static int dmirror_migrate_finalize_and_map(struct migrate_vma *args,
 	return 0;
 }
 
-static int dmirror_migrate(struct dmirror *dmirror,
-			   struct hmm_dmirror_cmd *cmd)
+static int dmirror_exclusive(struct dmirror *dmirror,
+			     struct hmm_dmirror_cmd *cmd)
+{
+	unsigned long start, end, addr;
+	unsigned long size = cmd->npages << PAGE_SHIFT;
+	struct mm_struct *mm = dmirror->notifier.mm;
+	struct dmirror_bounce bounce;
+	int ret = 0;
+
+	start = cmd->addr;
+	end = start + size;
+	if (end < start)
+		return -EINVAL;
+
+	/* Since the mm is for the mirrored process, get a reference first. */
+	if (!mmget_not_zero(mm))
+		return -EINVAL;
+
+	mmap_read_lock(mm);
+	for (addr = start; !ret && addr < end; addr += PAGE_SIZE) {
+		struct folio *folio;
+		struct page *page;
+
+		page = make_device_exclusive(mm, addr, NULL, &folio);
+		if (IS_ERR(page)) {
+			ret = PTR_ERR(page);
+			break;
+		}
+
+		ret = dmirror_atomic_map(addr, page, dmirror);
+		folio_unlock(folio);
+		folio_put(folio);
+	}
+	mmap_read_unlock(mm);
+	mmput(mm);
+
+	if (ret)
+		return ret;
+
+	/* Return the migrated data for verification. */
+	ret = dmirror_bounce_init(&bounce, start, size);
+	if (ret)
+		return ret;
+	mutex_lock(&dmirror->mutex);
+	ret = dmirror_do_read(dmirror, start, end, &bounce);
+	mutex_unlock(&dmirror->mutex);
+	if (ret == 0) {
+		if (copy_to_user(u64_to_user_ptr(cmd->ptr), bounce.ptr,
+				 bounce.size))
+			ret = -EFAULT;
+	}
+
+	cmd->cpages = bounce.cpages;
+	dmirror_bounce_fini(&bounce);
+	return ret;
+}
+
+static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
+						      struct dmirror *dmirror)
+{
+	const unsigned long *src = args->src;
+	unsigned long *dst = args->dst;
+	unsigned long start = args->start;
+	unsigned long end = args->end;
+	unsigned long addr;
+	unsigned int order = 0;
+	int i;
+
+	for (addr = start; addr < end; ) {
+		struct page *dpage, *spage;
+
+		spage = migrate_pfn_to_page(*src);
+		if (!spage || !(*src & MIGRATE_PFN_MIGRATE)) {
+			addr += PAGE_SIZE;
+			goto next;
+		}
+
+		if (WARN_ON(!is_device_private_page(spage) &&
+			    !is_device_coherent_page(spage))) {
+			addr += PAGE_SIZE;
+			goto next;
+		}
+
+		spage = BACKING_PAGE(spage);
+		order = folio_order(page_folio(spage));
+		if (order)
+			*dst = MIGRATE_PFN_COMPOUND;
+		if (*src & MIGRATE_PFN_WRITE)
+			*dst |= MIGRATE_PFN_WRITE;
+
+		if (dmirror->flags & HMM_DMIRROR_FLAG_FAIL_ALLOC) {
+			dmirror->flags &= ~HMM_DMIRROR_FLAG_FAIL_ALLOC;
+			*dst &= ~MIGRATE_PFN_COMPOUND;
+			dpage = NULL;
+		} else if (order) {
+			dpage = folio_page(vma_alloc_folio(GFP_HIGHUSER_MOVABLE,
+						order, args->vma, addr), 0);
+		} else {
+			dpage = alloc_page_vma(GFP_HIGHUSER_MOVABLE, args->vma, addr);
+		}
+
+		if (!dpage && !order)
+			return VM_FAULT_OOM;
+
+		pr_debug("migrating from sys to dev pfn src: 0x%lx pfn dst: 0x%lx\n",
+				page_to_pfn(spage), page_to_pfn(dpage));
+
+		if (dpage) {
+			lock_page(dpage);
+			*dst |= migrate_pfn(page_to_pfn(dpage));
+		}
+
+		for (i = 0; i < (1 << order); i++) {
+			struct page *src_page;
+			struct page *dst_page;
+
+			/* Try with smaller pages if large allocation fails */
+			if (!dpage && order) {
+				dpage = alloc_page_vma(GFP_HIGHUSER_MOVABLE, args->vma, addr);
+				lock_page(dpage);
+				dst[i] = migrate_pfn(page_to_pfn(dpage));
+				dst_page = pfn_to_page(page_to_pfn(dpage));
+				dpage = NULL; /* For the next iteration */
+			} else {
+				dst_page = pfn_to_page(page_to_pfn(dpage) + i);
+			}
+
+			src_page = pfn_to_page(page_to_pfn(spage) + i);
+
+			xa_erase(&dmirror->pt, addr >> PAGE_SHIFT);
+			addr += PAGE_SIZE;
+			copy_highpage(dst_page, src_page);
+		}
+next:
+		src += 1 << order;
+		dst += 1 << order;
+	}
+	return 0;
+}
+
+static unsigned long
+dmirror_successful_migrated_pages(struct migrate_vma *migrate)
+{
+	unsigned long cpages = 0;
+	unsigned long i;
+
+	for (i = 0; i < migrate->npages; i++) {
+		if (migrate->src[i] & MIGRATE_PFN_VALID &&
+		    migrate->src[i] & MIGRATE_PFN_MIGRATE)
+			cpages++;
+	}
+	return cpages;
+}
+
+static int dmirror_migrate_to_system(struct dmirror *dmirror,
+				     struct hmm_dmirror_cmd *cmd)
+{
+	unsigned long start, end, addr;
+	unsigned long size = cmd->npages << PAGE_SHIFT;
+	struct mm_struct *mm = dmirror->notifier.mm;
+	struct vm_area_struct *vma;
+	struct migrate_vma args = { 0 };
+	unsigned long next;
+	int ret;
+	unsigned long *src_pfns;
+	unsigned long *dst_pfns;
+
+	src_pfns = kvcalloc(PTRS_PER_PTE, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL);
+	dst_pfns = kvcalloc(PTRS_PER_PTE, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL);
+
+	start = cmd->addr;
+	end = start + size;
+	if (end < start)
+		return -EINVAL;
+
+	/* Since the mm is for the mirrored process, get a reference first. */
+	if (!mmget_not_zero(mm))
+		return -EINVAL;
+
+	cmd->cpages = 0;
+	mmap_read_lock(mm);
+	for (addr = start; addr < end; addr = next) {
+		vma = vma_lookup(mm, addr);
+		if (!vma || !(vma->vm_flags & VM_READ)) {
+			ret = -EINVAL;
+			goto out;
+		}
+		next = min(end, addr + (PTRS_PER_PTE << PAGE_SHIFT));
+		if (next > vma->vm_end)
+			next = vma->vm_end;
+
+		args.vma = vma;
+		args.src = src_pfns;
+		args.dst = dst_pfns;
+		args.start = addr;
+		args.end = next;
+		args.pgmap_owner = dmirror->mdevice;
+		args.flags = dmirror_select_device(dmirror) | MIGRATE_VMA_SELECT_COMPOUND;
+
+		ret = migrate_vma_setup(&args);
+		if (ret)
+			goto out;
+
+		pr_debug("Migrating from device mem to sys mem\n");
+		dmirror_devmem_fault_alloc_and_copy(&args, dmirror);
+
+		migrate_vma_pages(&args);
+		cmd->cpages += dmirror_successful_migrated_pages(&args);
+		migrate_vma_finalize(&args);
+	}
+out:
+	mmap_read_unlock(mm);
+	mmput(mm);
+	kvfree(src_pfns);
+	kvfree(dst_pfns);
+
+	return ret;
+}
+
+static int dmirror_migrate_to_device(struct dmirror *dmirror,
+				struct hmm_dmirror_cmd *cmd)
 {
 	unsigned long start, end, addr;
 	unsigned long size = cmd->npages << PAGE_SHIFT;
 	struct mm_struct *mm = dmirror->notifier.mm;
 	struct vm_area_struct *vma;
-	unsigned long src_pfns[64];
-	unsigned long dst_pfns[64];
 	struct dmirror_bounce bounce;
-	struct migrate_vma args;
+	struct migrate_vma args = { 0 };
 	unsigned long next;
 	int ret;
+	unsigned long *src_pfns = NULL;
+	unsigned long *dst_pfns = NULL;
 
 	start = cmd->addr;
 	end = start + size;
@@ -686,15 +1122,26 @@ static int dmirror_migrate(struct dmirror *dmirror,
 	if (!mmget_not_zero(mm))
 		return -EINVAL;
 
+	ret = -ENOMEM;
+	src_pfns = kvcalloc(PTRS_PER_PTE, sizeof(*src_pfns),
+			  GFP_KERNEL | __GFP_NOFAIL);
+	if (!src_pfns)
+		goto free_mem;
+
+	dst_pfns = kvcalloc(PTRS_PER_PTE, sizeof(*dst_pfns),
+			  GFP_KERNEL | __GFP_NOFAIL);
+	if (!dst_pfns)
+		goto free_mem;
+
+	ret = 0;
 	mmap_read_lock(mm);
 	for (addr = start; addr < end; addr = next) {
-		vma = find_vma(mm, addr);
-		if (!vma || addr < vma->vm_start ||
-		    !(vma->vm_flags & VM_READ)) {
+		vma = vma_lookup(mm, addr);
+		if (!vma || !(vma->vm_flags & VM_READ)) {
 			ret = -EINVAL;
 			goto out;
 		}
-		next = min(end, addr + (ARRAY_SIZE(src_pfns) << PAGE_SHIFT));
+		next = min(end, addr + (PTRS_PER_PTE << PAGE_SHIFT));
 		if (next > vma->vm_end)
 			next = vma->vm_end;
 
@@ -703,11 +1150,14 @@ static int dmirror_migrate(struct dmirror *dmirror,
 		args.dst = dst_pfns;
 		args.start = addr;
 		args.end = next;
-		args.src_owner = NULL;
+		args.pgmap_owner = dmirror->mdevice;
+		args.flags = MIGRATE_VMA_SELECT_SYSTEM |
+				MIGRATE_VMA_SELECT_COMPOUND;
 		ret = migrate_vma_setup(&args);
 		if (ret)
 			goto out;
 
+		pr_debug("Migrating from sys mem to device mem\n");
 		dmirror_migrate_alloc_and_copy(&args, dmirror);
 		migrate_vma_pages(&args);
 		dmirror_migrate_finalize_and_map(&args, dmirror);
@@ -716,10 +1166,13 @@ static int dmirror_migrate(struct dmirror *dmirror,
 	mmap_read_unlock(mm);
 	mmput(mm);
 
-	/* Return the migrated data for verification. */
+	/*
+	 * Return the migrated data for verification.
+	 * Only for pages in device zone
+	 */
 	ret = dmirror_bounce_init(&bounce, start, size);
 	if (ret)
-		return ret;
+		goto free_mem;
 	mutex_lock(&dmirror->mutex);
 	ret = dmirror_do_read(dmirror, start, end, &bounce);
 	mutex_unlock(&dmirror->mutex);
@@ -730,11 +1183,14 @@ static int dmirror_migrate(struct dmirror *dmirror,
 	}
 	cmd->cpages = bounce.cpages;
 	dmirror_bounce_fini(&bounce);
-	return ret;
+	goto free_mem;
 
 out:
 	mmap_read_unlock(mm);
 	mmput(mm);
+free_mem:
+	kfree(src_pfns);
+	kfree(dst_pfns);
 	return ret;
 }
 
@@ -759,6 +1215,12 @@ static void dmirror_mkentry(struct dmirror *dmirror, struct hmm_range *range,
 			*perm = HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL;
 		else
 			*perm = HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE;
+	} else if (is_device_coherent_page(page)) {
+		/* Is the page migrated to this device or some other? */
+		if (dmirror->mdevice == dmirror_page_to_device(page))
+			*perm = HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL;
+		else
+			*perm = HMM_DMIRROR_PROT_DEV_COHERENT_REMOTE;
 	} else if (is_zero_pfn(page_to_pfn(page)))
 		*perm = HMM_DMIRROR_PROT_ZERO;
 	else
@@ -767,6 +1229,10 @@ static void dmirror_mkentry(struct dmirror *dmirror, struct hmm_range *range,
 		*perm |= HMM_DMIRROR_PROT_WRITE;
 	else
 		*perm |= HMM_DMIRROR_PROT_READ;
+	if (hmm_pfn_to_map_order(entry) + PAGE_SHIFT == PMD_SHIFT)
+		*perm |= HMM_DMIRROR_PROT_PMD;
+	else if (hmm_pfn_to_map_order(entry) + PAGE_SHIFT == PUD_SHIFT)
+		*perm |= HMM_DMIRROR_PROT_PUD;
 }
 
 static bool dmirror_snapshot_invalidate(struct mmu_interval_notifier *mni,
@@ -861,8 +1327,8 @@ static int dmirror_snapshot(struct dmirror *dmirror,
 	unsigned long size = cmd->npages << PAGE_SHIFT;
 	unsigned long addr;
 	unsigned long next;
-	unsigned long pfns[64];
-	unsigned char perm[64];
+	unsigned long pfns[32];
+	unsigned char perm[32];
 	char __user *uptr;
 	struct hmm_range range = {
 		.hmm_pfns = pfns,
@@ -909,6 +1375,104 @@ static int dmirror_snapshot(struct dmirror *dmirror,
 	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;
+	unsigned int order = 0;
+
+	src_pfns = kvcalloc(npages, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL);
+	dst_pfns = kvcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL);
+
+	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;
+
+		order = folio_order(page_folio(spage));
+		spage = BACKING_PAGE(spage);
+		if (src_pfns[i] & MIGRATE_PFN_COMPOUND) {
+			dpage = folio_page(folio_alloc(GFP_HIGHUSER_MOVABLE,
+					      order), 0);
+		} else {
+			dpage = alloc_page(GFP_HIGHUSER_MOVABLE | __GFP_NOFAIL);
+			order = 0;
+		}
+
+		/* TODO Support splitting here */
+		lock_page(dpage);
+		dst_pfns[i] = migrate_pfn(page_to_pfn(dpage));
+		if (src_pfns[i] & MIGRATE_PFN_WRITE)
+			dst_pfns[i] |= MIGRATE_PFN_WRITE;
+		if (order)
+			dst_pfns[i] |= MIGRATE_PFN_COMPOUND;
+		folio_copy(page_folio(dpage), page_folio(spage));
+	}
+	migrate_device_pages(src_pfns, dst_pfns, npages);
+	migrate_device_finalize(src_pfns, dst_pfns, npages);
+	kvfree(src_pfns);
+	kvfree(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;
+	struct folio *folio;
+
+
+	for (folio = mdevice->free_folios; folio; folio = folio_zone_device_data(folio))
+		if (dmirror_page_to_chunk(folio_page(folio, 0)) == devmem)
+			mdevice->free_folios = folio_zone_device_data(folio);
+	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;
+		mdevice->free_folios = 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)
@@ -942,14 +1506,36 @@ static long dmirror_fops_unlocked_ioctl(struct file *filp,
 		ret = dmirror_write(dmirror, &cmd);
 		break;
 
-	case HMM_DMIRROR_MIGRATE:
-		ret = dmirror_migrate(dmirror, &cmd);
+	case HMM_DMIRROR_MIGRATE_TO_DEV:
+		ret = dmirror_migrate_to_device(dmirror, &cmd);
+		break;
+
+	case HMM_DMIRROR_MIGRATE_TO_SYS:
+		ret = dmirror_migrate_to_system(dmirror, &cmd);
+		break;
+
+	case HMM_DMIRROR_EXCLUSIVE:
+		ret = dmirror_exclusive(dmirror, &cmd);
+		break;
+
+	case HMM_DMIRROR_CHECK_EXCLUSIVE:
+		ret = dmirror_check_atomic(dmirror, cmd.addr,
+					cmd.addr + (cmd.npages << PAGE_SHIFT));
 		break;
 
 	case HMM_DMIRROR_SNAPSHOT:
 		ret = dmirror_snapshot(dmirror, &cmd);
 		break;
 
+	case HMM_DMIRROR_RELEASE:
+		dmirror_device_remove_chunks(dmirror->mdevice);
+		ret = 0;
+		break;
+	case HMM_DMIRROR_FLAGS:
+		dmirror->flags = cmd.npages;
+		ret = 0;
+		break;
+
 	default:
 		return -EINVAL;
 	}
@@ -962,111 +1548,180 @@ static long dmirror_fops_unlocked_ioctl(struct file *filp,
 	return 0;
 }
 
+static int dmirror_fops_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	unsigned long addr;
+
+	for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) {
+		struct page *page;
+		int ret;
+
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!page)
+			return -ENOMEM;
+
+		ret = vm_insert_page(vma, addr, page);
+		if (ret) {
+			__free_page(page);
+			return ret;
+		}
+		put_page(page);
+	}
+
+	return 0;
+}
+
 static const struct file_operations dmirror_fops = {
 	.open		= dmirror_fops_open,
 	.release	= dmirror_fops_release,
+	.mmap		= dmirror_fops_mmap,
 	.unlocked_ioctl = dmirror_fops_unlocked_ioctl,
 	.llseek		= default_llseek,
 	.owner		= THIS_MODULE,
 };
 
-static void dmirror_devmem_free(struct page *page)
+static void dmirror_devmem_free(struct folio *folio)
 {
-	struct page *rpage = page->zone_device_data;
+	struct page *page = &folio->page;
+	struct page *rpage = BACKING_PAGE(page);
 	struct dmirror_device *mdevice;
+	struct folio *rfolio = page_folio(rpage);
+	unsigned int order = folio_order(rfolio);
 
-	if (rpage)
-		__free_page(rpage);
+	if (rpage != page) {
+		if (order)
+			__free_pages(rpage, order);
+		else
+			__free_page(rpage);
+		rpage = NULL;
+	}
 
 	mdevice = dmirror_page_to_device(page);
-
 	spin_lock(&mdevice->lock);
-	mdevice->cfree++;
-	page->zone_device_data = mdevice->free_pages;
-	mdevice->free_pages = page;
-	spin_unlock(&mdevice->lock);
-}
 
-static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
-						struct dmirror_device *mdevice)
-{
-	const unsigned long *src = args->src;
-	unsigned long *dst = args->dst;
-	unsigned long start = args->start;
-	unsigned long end = args->end;
-	unsigned long addr;
-
-	for (addr = start; addr < end; addr += PAGE_SIZE,
-				       src++, dst++) {
-		struct page *dpage, *spage;
-
-		spage = migrate_pfn_to_page(*src);
-		if (!spage || !(*src & MIGRATE_PFN_MIGRATE))
-			continue;
-		spage = spage->zone_device_data;
-
-		dpage = alloc_page_vma(GFP_HIGHUSER_MOVABLE, args->vma, addr);
-		if (!dpage)
-			continue;
-
-		lock_page(dpage);
-		copy_highpage(dpage, spage);
-		*dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED;
-		if (*src & MIGRATE_PFN_WRITE)
-			*dst |= MIGRATE_PFN_WRITE;
+	/* Return page to our allocator if not freeing the chunk */
+	if (!dmirror_page_to_chunk(page)->remove) {
+		mdevice->cfree += 1 << order;
+		if (order) {
+			page->zone_device_data = mdevice->free_folios;
+			mdevice->free_folios = page_folio(page);
+		} else {
+			page->zone_device_data = mdevice->free_pages;
+			mdevice->free_pages = page;
+		}
 	}
-	return 0;
-}
-
-static void dmirror_devmem_fault_finalize_and_map(struct migrate_vma *args,
-						  struct dmirror *dmirror)
-{
-	/* Invalidate the device's page table mapping. */
-	mutex_lock(&dmirror->mutex);
-	dmirror_do_update(dmirror, args->start, args->end);
-	mutex_unlock(&dmirror->mutex);
+	spin_unlock(&mdevice->lock);
 }
 
 static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 {
-	struct migrate_vma args;
-	unsigned long src_pfns;
-	unsigned long dst_pfns;
+	struct migrate_vma args = { 0 };
 	struct page *rpage;
 	struct dmirror *dmirror;
-	vm_fault_t ret;
+	vm_fault_t ret = 0;
+	unsigned int order, nr;
 
 	/*
 	 * Normally, a device would use the page->zone_device_data to point to
 	 * the mirror but here we use it to hold the page for the simulated
 	 * device memory and that page holds the pointer to the mirror.
 	 */
-	rpage = vmf->page->zone_device_data;
+	rpage = folio_zone_device_data(page_folio(vmf->page));
 	dmirror = rpage->zone_device_data;
 
 	/* FIXME demonstrate how we can adjust migrate range */
+	order = folio_order(page_folio(vmf->page));
+	nr = 1 << order;
+
+	/*
+	 * When folios are partially mapped, we can't rely on the folio
+	 * order of vmf->page as the folio might not be fully split yet
+	 */
+	if (vmf->pte) {
+		order = 0;
+		nr = 1;
+	}
+
+	/*
+	 * Consider a per-cpu cache of src and dst pfns, but with
+	 * large number of cpus that might not scale well.
+	 */
+	args.start = ALIGN_DOWN(vmf->address, (PAGE_SIZE << order));
 	args.vma = vmf->vma;
-	args.start = vmf->address;
-	args.end = args.start + PAGE_SIZE;
-	args.src = &src_pfns;
-	args.dst = &dst_pfns;
-	args.src_owner = dmirror->mdevice;
+	args.end = args.start + (PAGE_SIZE << order);
+
+	nr = (args.end - args.start) >> PAGE_SHIFT;
+	args.src = kcalloc(nr, sizeof(unsigned long), GFP_KERNEL);
+	args.dst = kcalloc(nr, sizeof(unsigned long), GFP_KERNEL);
+	args.pgmap_owner = dmirror->mdevice;
+	args.flags = dmirror_select_device(dmirror);
+	args.fault_page = vmf->page;
+
+	if (!args.src || !args.dst) {
+		ret = VM_FAULT_OOM;
+		goto err;
+	}
+
+	if (order)
+		args.flags |= MIGRATE_VMA_SELECT_COMPOUND;
 
 	if (migrate_vma_setup(&args))
 		return VM_FAULT_SIGBUS;
 
-	ret = dmirror_devmem_fault_alloc_and_copy(&args, dmirror->mdevice);
+	ret = dmirror_devmem_fault_alloc_and_copy(&args, dmirror);
 	if (ret)
-		return ret;
+		goto err;
 	migrate_vma_pages(&args);
-	dmirror_devmem_fault_finalize_and_map(&args, dmirror);
+	/*
+	 * No device finalize step is needed since
+	 * dmirror_devmem_fault_alloc_and_copy() will have already
+	 * invalidated the device page table.
+	 */
 	migrate_vma_finalize(&args);
-	return 0;
+err:
+	kfree(args.src);
+	kfree(args.dst);
+	return ret;
+}
+
+static void dmirror_devmem_folio_split(struct folio *head, struct folio *tail)
+{
+	struct page *rpage = BACKING_PAGE(folio_page(head, 0));
+	struct page *rpage_tail;
+	struct folio *rfolio;
+	unsigned long offset = 0;
+
+	if (!rpage) {
+		tail->page.zone_device_data = NULL;
+		return;
+	}
+
+	rfolio = page_folio(rpage);
+
+	if (tail == NULL) {
+		folio_reset_order(rfolio);
+		rfolio->mapping = NULL;
+		folio_set_count(rfolio, 1);
+		return;
+	}
+
+	offset = folio_pfn(tail) - folio_pfn(head);
+
+	rpage_tail = folio_page(rfolio, offset);
+	tail->page.zone_device_data = rpage_tail;
+	rpage_tail->zone_device_data = rpage->zone_device_data;
+	clear_compound_head(rpage_tail);
+	rpage_tail->mapping = NULL;
+
+	folio_page(tail, 0)->mapping = folio_page(head, 0)->mapping;
+	tail->pgmap = head->pgmap;
+	folio_set_count(page_folio(rpage_tail), 1);
 }
 
 static const struct dev_pagemap_ops dmirror_devmem_ops = {
-	.page_free	= dmirror_devmem_free,
+	.folio_free	= dmirror_devmem_free,
 	.migrate_to_ram	= dmirror_devmem_fault,
+	.folio_split	= dmirror_devmem_folio_split,
 };
 
 static int dmirror_device_init(struct dmirror_device *mdevice, int id)
@@ -1080,63 +1735,60 @@ static int dmirror_device_init(struct dmirror_device *mdevice, int id)
 
 	cdev_init(&mdevice->cdevice, &dmirror_fops);
 	mdevice->cdevice.owner = THIS_MODULE;
-	ret = cdev_add(&mdevice->cdevice, dev, 1);
+	device_initialize(&mdevice->device);
+	mdevice->device.devt = dev;
+
+	ret = dev_set_name(&mdevice->device, "hmm_dmirror%u", id);
 	if (ret)
-		return ret;
+		goto put_device;
+
+	ret = cdev_device_add(&mdevice->cdevice, &mdevice->device);
+	if (ret)
+		goto put_device;
 
-	/* Build a list of free ZONE_DEVICE private struct pages */
-	dmirror_allocate_chunk(mdevice, NULL);
+	/* Build a list of free ZONE_DEVICE struct pages */
+	return dmirror_allocate_chunk(mdevice, NULL, false);
 
-	return 0;
+put_device:
+	put_device(&mdevice->device);
+	return ret;
 }
 
 static void dmirror_device_remove(struct dmirror_device *mdevice)
 {
-	unsigned int i;
-
-	if (mdevice->devmem_chunks) {
-		for (i = 0; i < mdevice->devmem_count; i++) {
-			struct dmirror_chunk *devmem =
-				mdevice->devmem_chunks[i];
-
-			memunmap_pages(&devmem->pagemap);
-			release_mem_region(devmem->pagemap.res.start,
-					   resource_size(&devmem->pagemap.res));
-			kfree(devmem);
-		}
-		kfree(mdevice->devmem_chunks);
-	}
-
-	cdev_del(&mdevice->cdevice);
+	dmirror_device_remove_chunks(mdevice);
+	cdev_device_del(&mdevice->cdevice, &mdevice->device);
+	put_device(&mdevice->device);
 }
 
 static int __init hmm_dmirror_init(void)
 {
 	int ret;
-	int id;
+	int id = 0;
+	int ndevices = 0;
 
 	ret = alloc_chrdev_region(&dmirror_dev, 0, DMIRROR_NDEVICES,
 				  "HMM_DMIRROR");
 	if (ret)
 		goto err_unreg;
 
-	for (id = 0; id < DMIRROR_NDEVICES; id++) {
+	memset(dmirror_devices, 0, DMIRROR_NDEVICES * sizeof(dmirror_devices[0]));
+	dmirror_devices[ndevices++].zone_device_type =
+				HMM_DMIRROR_MEMORY_DEVICE_PRIVATE;
+	dmirror_devices[ndevices++].zone_device_type =
+				HMM_DMIRROR_MEMORY_DEVICE_PRIVATE;
+	if (spm_addr_dev0 && spm_addr_dev1) {
+		dmirror_devices[ndevices++].zone_device_type =
+					HMM_DMIRROR_MEMORY_DEVICE_COHERENT;
+		dmirror_devices[ndevices++].zone_device_type =
+					HMM_DMIRROR_MEMORY_DEVICE_COHERENT;
+	}
+	for (id = 0; id < ndevices; id++) {
 		ret = dmirror_device_init(dmirror_devices + id, id);
 		if (ret)
 			goto err_chrdev;
 	}
 
-	/*
-	 * Allocate a zero page to simulate a reserved page of device private
-	 * memory which is always zero. The zero_pfn page isn't used just to
-	 * make the code here simpler (i.e., we need a struct page for it).
-	 */
-	dmirror_zero_page = alloc_page(GFP_HIGHUSER | __GFP_ZERO);
-	if (!dmirror_zero_page) {
-		ret = -ENOMEM;
-		goto err_chrdev;
-	}
-
 	pr_info("HMM test module loaded. This is only for testing HMM.\n");
 	return 0;
 
@@ -1152,13 +1804,13 @@ static void __exit hmm_dmirror_exit(void)
 {
 	int id;
 
-	if (dmirror_zero_page)
-		__free_page(dmirror_zero_page);
 	for (id = 0; id < DMIRROR_NDEVICES; id++)
-		dmirror_device_remove(dmirror_devices + id);
+		if (dmirror_devices[id].zone_device_type)
+			dmirror_device_remove(dmirror_devices + id);
 	unregister_chrdev_region(dmirror_dev, DMIRROR_NDEVICES);
 }
 
 module_init(hmm_dmirror_init);
 module_exit(hmm_dmirror_exit);
+MODULE_DESCRIPTION("HMM (Heterogeneous Memory Management) test module");
 MODULE_LICENSE("GPL");