[PATCH] mm: Add page_cache_readahead_exceed

[Matthew Wilcox (Oracle)]

ext4 and f2fs have duplicated the guts of the readahead code so
they can read past i_size.  Instead, separate out the guts of the
readahead code so they can call it directly.

Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
---
 fs/ext4/verity.c        | 35 ++--------------------
 fs/f2fs/verity.c        | 35 ++--------------------
 include/linux/pagemap.h |  3 ++
 mm/readahead.c          | 66 ++++++++++++++++++++++++++++-------------
 4 files changed, 52 insertions(+), 87 deletions(-)

diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index dc5ec724d889..172ebf860014 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -342,37 +342,6 @@ static int ext4_get_verity_descriptor(struct inode *inode, void *buf,
 	return desc_size;
 }
 
-/*
- * Prefetch some pages from the file's Merkle tree.
- *
- * This is basically a stripped-down version of __do_page_cache_readahead()
- * which works on pages past i_size.
- */
-static void ext4_merkle_tree_readahead(struct address_space *mapping,
-				       pgoff_t start_index, unsigned long count)
-{
-	LIST_HEAD(pages);
-	unsigned int nr_pages = 0;
-	struct page *page;
-	pgoff_t index;
-	struct blk_plug plug;
-
-	for (index = start_index; index < start_index + count; index++) {
-		page = xa_load(&mapping->i_pages, index);
-		if (!page || xa_is_value(page)) {
-			page = __page_cache_alloc(readahead_gfp_mask(mapping));
-			if (!page)
-				break;
-			page->index = index;
-			list_add(&page->lru, &pages);
-			nr_pages++;
-		}
-	}
-	blk_start_plug(&plug);
-	ext4_mpage_readpages(mapping, &pages, NULL, nr_pages, true);
-	blk_finish_plug(&plug);
-}
-
 static struct page *ext4_read_merkle_tree_page(struct inode *inode,
 					       pgoff_t index,
 					       unsigned long num_ra_pages)
@@ -386,8 +355,8 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode,
 		if (page)
 			put_page(page);
 		else if (num_ra_pages > 1)
-			ext4_merkle_tree_readahead(inode->i_mapping, index,
-						   num_ra_pages);
+			page_cache_readahead_exceed(inode->i_mapping, NULL,
+					index, num_ra_pages, 0);
 		page = read_mapping_page(inode->i_mapping, index, NULL);
 	}
 	return page;
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index d7d430a6f130..f240ad087162 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -222,37 +222,6 @@ static int f2fs_get_verity_descriptor(struct inode *inode, void *buf,
 	return size;
 }
 
-/*
- * Prefetch some pages from the file's Merkle tree.
- *
- * This is basically a stripped-down version of __do_page_cache_readahead()
- * which works on pages past i_size.
- */
-static void f2fs_merkle_tree_readahead(struct address_space *mapping,
-				       pgoff_t start_index, unsigned long count)
-{
-	LIST_HEAD(pages);
-	unsigned int nr_pages = 0;
-	struct page *page;
-	pgoff_t index;
-	struct blk_plug plug;
-
-	for (index = start_index; index < start_index + count; index++) {
-		page = xa_load(&mapping->i_pages, index);
-		if (!page || xa_is_value(page)) {
-			page = __page_cache_alloc(readahead_gfp_mask(mapping));
-			if (!page)
-				break;
-			page->index = index;
-			list_add(&page->lru, &pages);
-			nr_pages++;
-		}
-	}
-	blk_start_plug(&plug);
-	f2fs_mpage_readpages(mapping, &pages, NULL, nr_pages, true);
-	blk_finish_plug(&plug);
-}
-
 static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
 					       pgoff_t index,
 					       unsigned long num_ra_pages)
@@ -266,8 +235,8 @@ static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
 		if (page)
 			put_page(page);
 		else if (num_ra_pages > 1)
-			f2fs_merkle_tree_readahead(inode->i_mapping, index,
-						   num_ra_pages);
+			page_cache_readahead_exceed(inode->i_mapping, NULL,
+					index, num_ra_pages, 0);
 		page = read_mapping_page(inode->i_mapping, index, NULL);
 	}
 	return page;
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 48c3bca57df6..1f7964d2b8ca 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -623,6 +623,9 @@ void page_cache_sync_readahead(struct address_space *, struct file_ra_state *,
 void page_cache_async_readahead(struct address_space *, struct file_ra_state *,
 		struct file *, struct page *, pgoff_t index,
 		unsigned long req_count);
+void page_cache_readahead_exceed(struct address_space *, struct file *,
+		pgoff_t index, unsigned long nr_to_read,
+		unsigned long lookahead_count);
 
 /*
  * Like add_to_page_cache_locked, but used to add newly allocated pages:
diff --git a/mm/readahead.c b/mm/readahead.c
index 9dd431fa16c9..cad26287ad8b 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -142,45 +142,43 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages)
 	blk_finish_plug(&plug);
 }
 
-/*
- * __do_page_cache_readahead() actually reads a chunk of disk.  It allocates
- * the pages first, then submits them for I/O. This avoids the very bad
- * behaviour which would occur if page allocations are causing VM writeback.
- * We really don't want to intermingle reads and writes like that.
+/**
+ * page_cache_readahead_exceed - Start unchecked readahead.
+ * @mapping: File address space.
+ * @file: This instance of the open file; used for authentication.
+ * @index: First page index to read.
+ * @nr_to_read: The number of pages to read.
+ * @lookahead_size: Where to start the next readahead.
+ *
+ * This function is for filesystems to call when they want to start
+ * readahead beyond a file's stated i_size.  This is almost certainly
+ * not the function you want to call.  Use page_cache_async_readahead()
+ * or page_cache_sync_readahead() instead.
+ *
+ * Context: File is referenced by caller.  Mutexes may be held by caller.
+ * May sleep, but will not reenter filesystem to reclaim memory.
  */
-void __do_page_cache_readahead(struct address_space *mapping,
-		struct file *filp, pgoff_t index, unsigned long nr_to_read,
+void page_cache_readahead_exceed(struct address_space *mapping,
+		struct file *file, pgoff_t index, unsigned long nr_to_read,
 		unsigned long lookahead_size)
 {
-	struct inode *inode = mapping->host;
-	unsigned long end_index;	/* The last page we want to read */
 	LIST_HEAD(page_pool);
 	unsigned long i;
-	loff_t isize = i_size_read(inode);
 	gfp_t gfp_mask = readahead_gfp_mask(mapping);
 	bool use_list = mapping->a_ops->readpages;
 	struct readahead_control rac = {
 		.mapping = mapping,
-		.file = filp,
+		.file = file,
 		._start = index,
 		._nr_pages = 0,
 	};
 
-	if (isize == 0)
-		return;
-
-	end_index = ((isize - 1) >> PAGE_SHIFT);
-
 	/*
 	 * Preallocate as many pages as we will need.
 	 */
 	for (i = 0; i < nr_to_read; i++) {
-		struct page *page;
-
-		if (index > end_index)
-			break;
+		struct page *page = xa_load(&mapping->i_pages, index);
 
-		page = xa_load(&mapping->i_pages, index);
 		if (page && !xa_is_value(page)) {
 			/*
 			 * Page already present?  Kick off the current batch
@@ -225,6 +223,32 @@ void __do_page_cache_readahead(struct address_space *mapping,
 		read_pages(&rac, &page_pool);
 	BUG_ON(!list_empty(&page_pool));
 }
+EXPORT_SYMBOL_GPL(page_cache_readahead_exceed);
+
+/*
+ * __do_page_cache_readahead() actually reads a chunk of disk.  It allocates
+ * the pages first, then submits them for I/O. This avoids the very bad
+ * behaviour which would occur if page allocations are causing VM writeback.
+ * We really don't want to intermingle reads and writes like that.
+ */
+void __do_page_cache_readahead(struct address_space *mapping,
+		struct file *file, pgoff_t index, unsigned long nr_to_read,
+		unsigned long lookahead_size)
+{
+	struct inode *inode = mapping->host;
+	loff_t isize = i_size_read(inode);
+	pgoff_t end_index;
+
+	if (isize == 0)
+		return;
+
+	end_index = (isize - 1) >> PAGE_SHIFT;
+	if (end_index < index + nr_to_read)
+		nr_to_read = end_index - index;
+
+	page_cache_readahead_exceed(mapping, file, index, nr_to_read,
+			lookahead_size);
+}
 
 /*
  * Chunk the readahead into 2 megabyte units, so that we don't pin too much
-- 
2.25.0