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

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.

Link: http://lkml.kernel.org/r/20170817000548.32038-19-jglisse@redhat.com
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>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: David Nellans <dnellans@nvidia.com>
Cc: Evgeny Baskakov <ebaskakov@nvidia.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mark Hairgrove <mhairgrove@nvidia.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Sherry Cheung <SCheung@nvidia.com>
Cc: Subhash Gutti <sgutti@nvidia.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Bob Liu <liubo95@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 36 insertions, 10 deletions

diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 67a03b20a2db..6d3b0b4fed4e 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -327,7 +327,7 @@ int hmm_vma_fault(struct vm_area_struct *vma,
 #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
 
 
-#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
+#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) ||  IS_ENABLED(CONFIG_DEVICE_PUBLIC)
 struct hmm_devmem;
 
 struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma,
@@ -494,7 +494,7 @@ struct hmm_device {
  */
 struct hmm_device *hmm_device_new(void *drvdata);
 void hmm_device_put(struct hmm_device *hmm_device);
-#endif /* IS_ENABLED(CONFIG_DEVICE_PRIVATE) */
+#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
 
 
 /* Below are for HMM internal use only! Not to be used by device driver! */
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 3a4f69137bc2..f5cf32e80041 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -131,6 +131,7 @@ enum {
 	IORES_DESC_PERSISTENT_MEMORY		= 4,
 	IORES_DESC_PERSISTENT_MEMORY_LEGACY	= 5,
 	IORES_DESC_DEVICE_PRIVATE_MEMORY	= 6,
+	IORES_DESC_DEVICE_PUBLIC_MEMORY		= 7,
 };
 
 /* helpers to define resources */
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
 
 /**
diff --git a/include/linux/mm.h b/include/linux/mm.h
index eccdab4bb44a..de66a1127db4 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -800,15 +800,16 @@ static inline bool is_zone_device_page(const struct page *page)
 }
 #endif
 
-#ifdef CONFIG_DEVICE_PRIVATE
-void put_zone_device_private_page(struct page *page);
+#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) ||  IS_ENABLED(CONFIG_DEVICE_PUBLIC)
+void put_zone_device_private_or_public_page(struct page *page);
 #else
-static inline void put_zone_device_private_page(struct page *page)
+static inline void put_zone_device_private_or_public_page(struct page *page)
 {
 }
-#endif
+#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
 
 static inline bool is_device_private_page(const struct page *page);
+static inline bool is_device_public_page(const struct page *page);
 
 DECLARE_STATIC_KEY_FALSE(device_private_key);
 
@@ -834,8 +835,9 @@ static inline void put_page(struct page *page)
 	 * include/linux/memremap.h and HMM for details.
 	 */
 	if (static_branch_unlikely(&device_private_key) &&
-	    unlikely(is_device_private_page(page))) {
-		put_zone_device_private_page(page);
+	    unlikely(is_device_private_page(page) ||
+		     is_device_public_page(page))) {
+		put_zone_device_private_or_public_page(page);
 		return;
 	}
 
@@ -1224,8 +1226,10 @@ struct zap_details {
 	pgoff_t last_index;			/* Highest page->index to unmap */
 };
 
-struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
-		pte_t pte);
+struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t pte, bool with_public_device);
+#define vm_normal_page(vma, addr, pte) _vm_normal_page(vma, addr, pte, false)
+
 struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
 				pmd_t pmd);