[PATCH v1 1/9] mm: add zone device coherent type memory support

@@ -39,6 +39,13 @@ struct vmem_altmap {
  * A more complete discussion of unaddressable memory may be found in
  * include/linux/hmm.h and Documentation/vm/hmm.rst.
  *
+ * MEMORY_DEVICE_COHERENT:
+ * Device memory that is cache coherent from device and CPU point of view. This
+ * is used on platforms that have an advanced system bus (like CAPI or CXL). A
+ * driver can hotplug the device memory using ZONE_DEVICE and with that memory
+ * type. Any page of a process can be migrated to such memory. However no one
+ * should be allowed to pin such memory so that it can always be evicted.
+ *
  * MEMORY_DEVICE_FS_DAX:
  * Host memory that has similar access semantics as System RAM i.e. DMA
  * coherent and supports page pinning. In support of coordinating page

@@ -59,6 +66,7 @@ struct vmem_altmap {
 enum memory_type {
 	/* 0 is reserved to catch uninitialized type fields */
 	MEMORY_DEVICE_PRIVATE = 1,
+	MEMORY_DEVICE_COHERENT,
 	MEMORY_DEVICE_FS_DAX,
 	MEMORY_DEVICE_GENERIC,
 	MEMORY_DEVICE_PCI_P2PDMA,

@@ -1162,6 +1162,7 @@ static inline bool page_is_devmap_managed(struct page *page)
 		return false;
 	switch (page->pgmap->type) {
 	case MEMORY_DEVICE_PRIVATE:
+	case MEMORY_DEVICE_COHERENT:
 	case MEMORY_DEVICE_FS_DAX:
 		return true;
 	default:

@@ -1191,6 +1192,14 @@ static inline bool is_device_private_page(const struct page *page)
 		page->pgmap->type == MEMORY_DEVICE_PRIVATE;
 }
 
+static inline bool is_device_page(const struct page *page)
+{
+	return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) &&
+		is_zone_device_page(page) &&
+		(page->pgmap->type == MEMORY_DEVICE_PRIVATE ||
+		page->pgmap->type == MEMORY_DEVICE_COHERENT);
+}
+
 static inline bool is_pci_p2pdma_page(const struct page *page)
 {
 	return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) &&

@@ -5695,8 +5695,8 @@ static int mem_cgroup_move_account(struct page *page,
  *   2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
  *     target for charge migration. if @target is not NULL, the entry is stored
  *     in target->ent.
- *   3(MC_TARGET_DEVICE): like MC_TARGET_PAGE  but page is MEMORY_DEVICE_PRIVATE
- *     (so ZONE_DEVICE page and thus not on the lru).
+ *   3(MC_TARGET_DEVICE): like MC_TARGET_PAGE  but page is MEMORY_DEVICE_COHERENT
+ *     or MEMORY_DEVICE_PRIVATE (so ZONE_DEVICE page and thus not on the lru).
  *     For now we such page is charge like a regular page would be as for all
  *     intent and purposes it is just special memory taking the place of a
  *     regular page.

@@ -5730,7 +5730,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 		 */
 		if (page_memcg(page) == mc.from) {
 			ret = MC_TARGET_PAGE;
-			if (is_device_private_page(page))
+			if (is_device_page(page))
 				ret = MC_TARGET_DEVICE;
 			if (target)
 				target->page = page;

@@ -1554,12 +1554,16 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 		goto unlock;
 	}
 
-	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+	switch (pgmap->type) {
+	case MEMORY_DEVICE_PRIVATE:
+	case MEMORY_DEVICE_COHERENT:
 		/*
 		 * TODO: Handle HMM pages which may need coordination
 		 * with device-side memory.
 		 */
 		goto unlock;
+	default:
+		break;
 	}
 
 	/*

@@ -44,6 +44,7 @@ EXPORT_SYMBOL(devmap_managed_key);
 static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
 {
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
+	    pgmap->type == MEMORY_DEVICE_COHERENT ||
 	    pgmap->type == MEMORY_DEVICE_FS_DAX)
 		static_branch_dec(&devmap_managed_key);
 }

@@ -51,6 +52,7 @@ static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
 static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
 {
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
+	    pgmap->type == MEMORY_DEVICE_COHERENT ||
 	    pgmap->type == MEMORY_DEVICE_FS_DAX)
 		static_branch_inc(&devmap_managed_key);
 }

@@ -328,6 +330,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 
 	switch (pgmap->type) {
 	case MEMORY_DEVICE_PRIVATE:
+	case MEMORY_DEVICE_COHERENT:
 		if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) {
 			WARN(1, "Device private memory not supported\n");
 			return ERR_PTR(-EINVAL);

@@ -498,7 +501,7 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap);
 void free_devmap_managed_page(struct page *page)
 {
 	/* notify page idle for dax */
-	if (!is_device_private_page(page)) {
+	if (!is_device_page(page)) {
 		wake_up_var(&page->_refcount);
 		return;
 	}

@@ -362,7 +362,7 @@ static int expected_page_refs(struct address_space *mapping, struct page *page)
 	 * Device private pages have an extra refcount as they are
 	 * ZONE_DEVICE pages.
 	 */
-	expected_count += is_device_private_page(page);
+	expected_count += is_device_page(page);
 	if (mapping)
 		expected_count += thp_nr_pages(page) + page_has_private(page);
 

@@ -2503,7 +2503,7 @@ static bool migrate_vma_check_page(struct page *page)
 		 * FIXME proper solution is to rework migration_entry_wait() so
 		 * it does not need to take a reference on page.
 		 */
-		return is_device_private_page(page);
+		return is_device_page(page);
 	}
 
 	/* For file back page */

@@ -2791,7 +2791,7 @@ EXPORT_SYMBOL(migrate_vma_setup);
  *     handle_pte_fault()
  *       do_anonymous_page()
  * to map in an anonymous zero page but the struct page will be a ZONE_DEVICE
- * private page.
+ * private or coherent page.
  */
 static void migrate_vma_insert_page(struct migrate_vma *migrate,
 				    unsigned long addr,

@@ -2867,10 +2867,15 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 				swp_entry = make_readable_device_private_entry(
 							page_to_pfn(page));
 			entry = swp_entry_to_pte(swp_entry);
+		} else if (is_device_page(page)) {
+			entry = pte_mkold(mk_pte(page,
+						 READ_ONCE(vma->vm_page_prot)));
+			if (vma->vm_flags & VM_WRITE)
+				entry = pte_mkwrite(pte_mkdirty(entry));
 		} else {
 			/*
-			 * For now we only support migrating to un-addressable
-			 * device memory.
+			 * We support migrating to private and coherent types
+			 * for device zone memory.
 			 */
 			pr_warn_once("Unsupported ZONE_DEVICE page type.\n");
 			goto abort;

@@ -2976,10 +2981,10 @@ void migrate_vma_pages(struct migrate_vma *migrate)
 		mapping = page_mapping(page);
 
 		if (is_zone_device_page(newpage)) {
-			if (is_device_private_page(newpage)) {
+			if (is_device_page(newpage)) {
 				/*
-				 * For now only support private anonymous when
-				 * migrating to un-addressable device memory.
+				 * For now only support private and coherent
+				 * anonymous when migrating to device memory.
 				 */
 				if (mapping) {
 					migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;