1 files changed, 28 insertions, 31 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index bd8543c6508f..ad7242043bdb 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -211,7 +211,7 @@ void __delete_from_page_cache(struct page *page, void *shadow)
 	 */
 	if (PageDirty(page) && mapping_cap_account_dirty(mapping)) {
 		dec_zone_page_state(page, NR_FILE_DIRTY);
-		dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
+		dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE);
 	}
 }
 
@@ -1046,8 +1046,7 @@ EXPORT_SYMBOL(find_lock_entry);
  * @mapping: the address_space to search
  * @offset: the page index
  * @fgp_flags: PCG flags
- * @cache_gfp_mask: gfp mask to use for the page cache data page allocation
- * @radix_gfp_mask: gfp mask to use for radix tree node allocation
+ * @gfp_mask: gfp mask to use for the page cache data page allocation
  *
  * Looks up the page cache slot at @mapping & @offset.
  *
@@ -1056,11 +1055,9 @@ EXPORT_SYMBOL(find_lock_entry);
  * FGP_ACCESSED: the page will be marked accessed
  * FGP_LOCK: Page is return locked
  * FGP_CREAT: If page is not present then a new page is allocated using
- *		@cache_gfp_mask and added to the page cache and the VM's LRU
- *		list. If radix tree nodes are allocated during page cache
- *		insertion then @radix_gfp_mask is used. The page is returned
- *		locked and with an increased refcount. Otherwise, %NULL is
- *		returned.
+ *		@gfp_mask and added to the page cache and the VM's LRU
+ *		list. The page is returned locked and with an increased
+ *		refcount. Otherwise, %NULL is returned.
  *
  * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even
  * if the GFP flags specified for FGP_CREAT are atomic.
@@ -1068,7 +1065,7 @@ EXPORT_SYMBOL(find_lock_entry);
  * If there is a page cache page, it is returned with an increased refcount.
  */
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
-	int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask)
+	int fgp_flags, gfp_t gfp_mask)
 {
 	struct page *page;
 
@@ -1105,13 +1102,11 @@ no_page:
 	if (!page && (fgp_flags & FGP_CREAT)) {
 		int err;
 		if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))
-			cache_gfp_mask |= __GFP_WRITE;
-		if (fgp_flags & FGP_NOFS) {
-			cache_gfp_mask &= ~__GFP_FS;
-			radix_gfp_mask &= ~__GFP_FS;
-		}
+			gfp_mask |= __GFP_WRITE;
+		if (fgp_flags & FGP_NOFS)
+			gfp_mask &= ~__GFP_FS;
 
-		page = __page_cache_alloc(cache_gfp_mask);
+		page = __page_cache_alloc(gfp_mask);
 		if (!page)
 			return NULL;
 
@@ -1122,7 +1117,8 @@ no_page:
 		if (fgp_flags & FGP_ACCESSED)
 			__SetPageReferenced(page);
 
-		err = add_to_page_cache_lru(page, mapping, offset, radix_gfp_mask);
+		err = add_to_page_cache_lru(page, mapping, offset,
+				gfp_mask & GFP_RECLAIM_MASK);
 		if (unlikely(err)) {
 			page_cache_release(page);
 			page = NULL;
@@ -1699,8 +1695,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 	loff_t *ppos = &iocb->ki_pos;
 	loff_t pos = *ppos;
 
-	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
-	if (file->f_flags & O_DIRECT) {
+	if (io_is_direct(file)) {
 		struct address_space *mapping = file->f_mapping;
 		struct inode *inode = mapping->host;
 		size_t count = iov_iter_count(iter);
@@ -1727,9 +1722,11 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 		 * we've already read everything we wanted to, or if
 		 * there was a short read because we hit EOF, go ahead
 		 * and return.  Otherwise fallthrough to buffered io for
-		 * the rest of the read.
+		 * the rest of the read.  Buffered reads will not work for
+		 * DAX files, so don't bother trying.
 		 */
-		if (retval < 0 || !iov_iter_count(iter) || *ppos >= size) {
+		if (retval < 0 || !iov_iter_count(iter) || *ppos >= size ||
+		    IS_DAX(inode)) {
 			file_accessed(file);
 			goto out;
 		}
@@ -2091,7 +2088,6 @@ const struct vm_operations_struct generic_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= filemap_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 /* This is used for a general mmap of a disk file */
@@ -2443,8 +2439,7 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
 		fgp_flags |= FGP_NOFS;
 
 	page = pagecache_get_page(mapping, index, fgp_flags,
-			mapping_gfp_mask(mapping),
-			GFP_KERNEL);
+			mapping_gfp_mask(mapping));
 	if (page)
 		wait_for_stable_page(page);
 
@@ -2570,7 +2565,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	size_t		count = iov_iter_count(from);
 
 	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err)
 		goto out;
@@ -2588,18 +2583,20 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (err)
 		goto out;
 
-	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
-	if (unlikely(file->f_flags & O_DIRECT)) {
+	if (io_is_direct(file)) {
 		loff_t endbyte;
 
 		written = generic_file_direct_write(iocb, from, pos);
-		if (written < 0 || written == count)
-			goto out;
-
 		/*
-		 * direct-io write to a hole: fall through to buffered I/O
-		 * for completing the rest of the request.
+		 * If the write stopped short of completing, fall back to
+		 * buffered writes.  Some filesystems do this for writes to
+		 * holes, for example.  For DAX files, a buffered write will
+		 * not succeed (even if it did, DAX does not handle dirty
+		 * page-cache pages correctly).
 		 */
+		if (written < 0 || written == count || IS_DAX(inode))
+			goto out;
+
 		pos += written;
 		count -= written;