1 files changed, 52 insertions, 28 deletions

diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 1732dea030b2..6fefb09af7c3 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -17,6 +17,7 @@ struct device;
  */
 struct vmem_altmap {
 	const unsigned long base_pfn;
+	const unsigned long end_pfn;
 	const unsigned long reserve;
 	unsigned long free;
 	unsigned long align;
@@ -37,13 +38,6 @@ 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_PUBLIC:
- * Device memory that is cache coherent from device and CPU point of view. This
- * is use on platform that have an advance system bus (like CAPI or CCIX). 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 allow 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
@@ -52,55 +46,85 @@ struct vmem_altmap {
  * wakeup is used to coordinate physical address space management (ex:
  * fs truncate/hole punch) vs pinned pages (ex: device dma).
  *
+ * MEMORY_DEVICE_DEVDAX:
+ * Host memory that has similar access semantics as System RAM i.e. DMA
+ * coherent and supports page pinning. In contrast to
+ * MEMORY_DEVICE_FS_DAX, this memory is access via a device-dax
+ * character device.
+ *
  * MEMORY_DEVICE_PCI_P2PDMA:
  * Device memory residing in a PCI BAR intended for use with Peer-to-Peer
  * transactions.
  */
 enum memory_type {
+	/* 0 is reserved to catch uninitialized type fields */
 	MEMORY_DEVICE_PRIVATE = 1,
-	MEMORY_DEVICE_PUBLIC,
 	MEMORY_DEVICE_FS_DAX,
+	MEMORY_DEVICE_DEVDAX,
 	MEMORY_DEVICE_PCI_P2PDMA,
 };
 
-/*
- * Additional notes about MEMORY_DEVICE_PRIVATE may be found in
- * include/linux/hmm.h and Documentation/vm/hmm.rst. There is also a brief
- * explanation in include/linux/memory_hotplug.h.
- *
- * The page_free() callback is called once the page refcount reaches 1
- * (ZONE_DEVICE pages never reach 0 refcount unless there is a refcount bug.
- * This allows the device driver to implement its own memory management.)
- */
-typedef void (*dev_page_free_t)(struct page *page, void *data);
+struct dev_pagemap_ops {
+	/*
+	 * Called once the page refcount reaches 1.  (ZONE_DEVICE pages never
+	 * reach 0 refcount unless there is a refcount bug. This allows the
+	 * device driver to implement its own memory management.)
+	 */
+	void (*page_free)(struct page *page);
+
+	/*
+	 * Transition the refcount in struct dev_pagemap to the dead state.
+	 */
+	void (*kill)(struct dev_pagemap *pgmap);
+
+	/*
+	 * Wait for refcount in struct dev_pagemap to be idle and reap it.
+	 */
+	void (*cleanup)(struct dev_pagemap *pgmap);
+
+	/*
+	 * Used for private (un-addressable) device memory only.  Must migrate
+	 * the page back to a CPU accessible page.
+	 */
+	vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf);
+};
+
+#define PGMAP_ALTMAP_VALID	(1 << 0)
 
 /**
  * struct dev_pagemap - metadata for ZONE_DEVICE mappings
- * @page_free: free page callback when page refcount reaches 1
  * @altmap: pre-allocated/reserved memory for vmemmap allocations
  * @res: physical address range covered by @ref
  * @ref: reference count that pins the devm_memremap_pages() mapping
- * @kill: callback to transition @ref to the dead state
- * @cleanup: callback to wait for @ref to be idle and reap it
+ * @internal_ref: internal reference if @ref is not provided by the caller
+ * @done: completion for @internal_ref
  * @dev: host device of the mapping for debug
  * @data: private data pointer for page_free()
  * @type: memory type: see MEMORY_* in memory_hotplug.h
+ * @flags: PGMAP_* flags to specify defailed behavior
+ * @ops: method table
  */
 struct dev_pagemap {
-	dev_page_free_t page_free;
 	struct vmem_altmap altmap;
-	bool altmap_valid;
 	struct resource res;
 	struct percpu_ref *ref;
-	void (*kill)(struct percpu_ref *ref);
-	void (*cleanup)(struct percpu_ref *ref);
-	struct device *dev;
-	void *data;
+	struct percpu_ref internal_ref;
+	struct completion done;
 	enum memory_type type;
-	u64 pci_p2pdma_bus_offset;
+	unsigned int flags;
+	const struct dev_pagemap_ops *ops;
 };
 
+static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap)
+{
+	if (pgmap->flags & PGMAP_ALTMAP_VALID)
+		return &pgmap->altmap;
+	return NULL;
+}
+
 #ifdef CONFIG_ZONE_DEVICE
+void *memremap_pages(struct dev_pagemap *pgmap, int nid);
+void memunmap_pages(struct dev_pagemap *pgmap);
 void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap);
 void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap);
 struct dev_pagemap *get_dev_pagemap(unsigned long pfn,