mm/device-public-memory: device memory cache coherent with CPU v5

Platform with advance system bus (like CAPI or CCIX) allow device
memory to be accessible from CPU in a cache coherent fashion. Add
a new type of ZONE_DEVICE to represent such memory. The use case
are the same as for the un-addressable device memory but without
all the corners cases.

Changed since v4:
  - added memory cgroup change to this patch
Changed since v3:
  - s/public/public (going back)
Changed since v2:
  - s/public/public
  - add proper include in migrate.c and drop useless #if/#endif
Changed since v1:
  - Kconfig and #if/#else cleanup

Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>

1 files changed, 21 insertions, 0 deletions

diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 8aa6b82679e2..f8ee1c73ad2d 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -57,10 +57,18 @@ static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
  *
  * A more complete discussion of unaddressable memory may be found in
  * include/linux/hmm.h and Documentation/vm/hmm.txt.
+ *
+ * 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.
  */
 enum memory_type {
 	MEMORY_DEVICE_HOST = 0,
 	MEMORY_DEVICE_PRIVATE,
+	MEMORY_DEVICE_PUBLIC,
 };
 
 /*
@@ -92,6 +100,8 @@ enum memory_type {
  * 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.)
+ *
+ * For MEMORY_DEVICE_PUBLIC only the page_free() callback matter.
  */
 typedef int (*dev_page_fault_t)(struct vm_area_struct *vma,
 				unsigned long addr,
@@ -134,6 +144,12 @@ static inline bool is_device_private_page(const struct page *page)
 	return is_zone_device_page(page) &&
 		page->pgmap->type == MEMORY_DEVICE_PRIVATE;
 }
+
+static inline bool is_device_public_page(const struct page *page)
+{
+	return is_zone_device_page(page) &&
+		page->pgmap->type == MEMORY_DEVICE_PUBLIC;
+}
 #else
 static inline void *devm_memremap_pages(struct device *dev,
 		struct resource *res, struct percpu_ref *ref,
@@ -157,6 +173,11 @@ static inline bool is_device_private_page(const struct page *page)
 {
 	return false;
 }
+
+static inline bool is_device_public_page(const struct page *page)
+{
+	return false;
+}
 #endif
 
 /**