[PATCHv5 05/36] thp: try to free page's buffers before attempt split

[Kirill A. Shutemov]

We want page to be isolated from the rest of the system before spliting
it. We rely on page count to be 2 for file pages to make sure nobody
uses the page: one pin to caller, one to radix-tree.

Filesystems with backing storage can have page count increased if it has
buffers.

Let's try to free them, before attempt split. And remove one guarding
VM_BUG_ON_PAGE().

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
---
 include/linux/buffer_head.h |  1 +
 mm/huge_memory.c            | 19 ++++++++++++++++++-
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index d67ab83823ad..fd4134ce9c54 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -400,6 +400,7 @@ extern int __set_page_dirty_buffers(struct page *page);
 #else /* CONFIG_BLOCK */
 
 static inline void buffer_init(void) {}
+static inline int page_has_buffers(struct page *page) { return 0; }
 static inline int try_to_free_buffers(struct page *page) { return 1; }
 static inline int inode_has_buffers(struct inode *inode) { return 0; }
 static inline void invalidate_inode_buffers(struct inode *inode) {}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 91dbab9644be..a15d566b14f6 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -30,6 +30,7 @@
 #include <linux/userfaultfd_k.h>
 #include <linux/page_idle.h>
 #include <linux/shmem_fs.h>
+#include <linux/buffer_head.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -2111,7 +2112,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 
 	VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
 	if (PageAnon(head)) {
@@ -2140,6 +2140,23 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 			goto out;
 		}
 
+		/* Try to free buffers before attempt split */
+		if (!PageSwapBacked(head) && PagePrivate(page)) {
+			/*
+			 * We cannot trigger writeback from here due possible
+			 * recursion if triggered from vmscan, only wait.
+			 *
+			 * Caller can trigger writeback it on its own, if safe.
+			 */
+			wait_on_page_writeback(head);
+
+			if (page_has_buffers(head) && !try_to_release_page(head,
+						GFP_KERNEL)) {
+				ret = -EBUSY;
+				goto out;
+			}
+		}
+
 		/* Addidional pin from radix tree */
 		extra_pins = 1;
 		anon_vma = NULL;
-- 
2.10.2