mm: devmap: refactor 1-based refcounting for ZONE_DEVICE pages

An upcoming patch changes and complicates the refcounting and especially
the "put page" aspects of it.  In order to keep everything clean,
refactor the devmap page release routines:

* Rename put_devmap_managed_page() to page_is_devmap_managed(), and
  limit the functionality to "read only": return a bool, with no side
  effects.

* Add a new routine, put_devmap_managed_page(), to handle decrementing
  the refcount for ZONE_DEVICE pages.

* Change callers (just release_pages() and put_page()) to check
  page_is_devmap_managed() before calling the new
  put_devmap_managed_page() routine.  This is a performance point:
  put_page() is a hot path, so we need to avoid non- inline function calls
  where possible.

* Rename __put_devmap_managed_page() to free_devmap_managed_page(), and
  limit the functionality to unconditionally freeing a devmap page.

This is originally based on a separate patch by Ira Weiny, which applied
to an early version of the put_user_page() experiments.  Since then,
Jérôme Glisse suggested the refactoring described above.

Link: http://lkml.kernel.org/r/20200107224558.2362728-5-jhubbard@nvidia.comSigned-off-by: NIra Weiny <ira.weiny@intel.com>
Signed-off-by: NJohn Hubbard <jhubbard@nvidia.com>
Suggested-by: NJérôme Glisse <jglisse@redhat.com>
Reviewed-by: NDan Williams <dan.j.williams@intel.com>
Reviewed-by: NJan Kara <jack@suse.cz>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Björn Töpel <bjorn.topel@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Leon Romanovsky <leonro@mellanox.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

include/linux/mm.h

@@ -947,9 +947,10 @@ static inline bool is_zone_device_page(const struct page *page)
 #endif
 
 #ifdef CONFIG_DEV_PAGEMAP_OPS
-void __put_devmap_managed_page(struct page *page);
+void free_devmap_managed_page(struct page *page);
 DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
-static inline bool put_devmap_managed_page(struct page *page)
+
+static inline bool page_is_devmap_managed(struct page *page)
 {
 	if (!static_branch_unlikely(&devmap_managed_key))
 		return false;
@@ -958,7 +959,6 @@ static inline bool put_devmap_managed_page(struct page *page)
 	switch (page->pgmap->type) {
 	case MEMORY_DEVICE_PRIVATE:
 	case MEMORY_DEVICE_FS_DAX:
-		__put_devmap_managed_page(page);
 		return true;
 	default:
 		break;
@@ -966,11 +966,17 @@ static inline bool put_devmap_managed_page(struct page *page)
 	return false;
 }
 
+void put_devmap_managed_page(struct page *page);
+
 #else /* CONFIG_DEV_PAGEMAP_OPS */
-static inline bool put_devmap_managed_page(struct page *page)
+static inline bool page_is_devmap_managed(struct page *page)
 {
 	return false;
 }
+
+static inline void put_devmap_managed_page(struct page *page)
+{
+}
 #endif /* CONFIG_DEV_PAGEMAP_OPS */
 
 static inline bool is_device_private_page(const struct page *page)
@@ -1023,8 +1029,10 @@ static inline void put_page(struct page *page)
 	 * need to inform the device driver through callback. See
 	 * include/linux/memremap.h and HMM for details.
 	 */
-	if (put_devmap_managed_page(page))
+	if (page_is_devmap_managed(page)) {
+		put_devmap_managed_page(page);
 		return;
+	}
 
 	if (put_page_testzero(page))
 		__put_page(page);

mm/memremap.c

@@ -411,20 +411,8 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 EXPORT_SYMBOL_GPL(get_dev_pagemap);
 
 #ifdef CONFIG_DEV_PAGEMAP_OPS
-void __put_devmap_managed_page(struct page *page)
+void free_devmap_managed_page(struct page *page)
 {
-	int count = page_ref_dec_return(page);
-
-	/* still busy */
-	if (count > 1)
-		return;
-
-	/* only triggered by the dev_pagemap shutdown path */
-	if (count == 0) {
-		__put_page(page);
-		return;
-	}
-
 	/* notify page idle for dax */
 	if (!is_device_private_page(page)) {
 		wake_up_var(&page->_refcount);
@@ -461,5 +449,4 @@ void __put_devmap_managed_page(struct page *page)
 	page->mapping = NULL;
 	page->pgmap->ops->page_free(page);
 }
-EXPORT_SYMBOL(__put_devmap_managed_page);
 #endif /* CONFIG_DEV_PAGEMAP_OPS */

mm/swap.c

@@ -813,8 +813,10 @@ void release_pages(struct page **pages, int nr)
 			 * processing, and instead, expect a call to
 			 * put_page_testzero().
 			 */
-			if (put_devmap_managed_page(page))
+			if (page_is_devmap_managed(page)) {
+				put_devmap_managed_page(page);
 				continue;
+			}
 		}
 
 		page = compound_head(page);
@@ -1102,3 +1104,26 @@ void __init swap_setup(void)
 	 * _really_ don't want to cluster much more
 	 */
 }
+
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+void put_devmap_managed_page(struct page *page)
+{
+	int count;
+
+	if (WARN_ON_ONCE(!page_is_devmap_managed(page)))
+		return;
+
+	count = page_ref_dec_return(page);
+
+	/*
+	 * devmap page refcounts are 1-based, rather than 0-based: if
+	 * refcount is 1, then the page is free and the refcount is
+	 * stable because nobody holds a reference on the page.
+	 */
+	if (count == 1)
+		free_devmap_managed_page(page);
+	else if (!count)
+		__put_page(page);
+}
+EXPORT_SYMBOL(put_devmap_managed_page);
+#endif