[v4,04/12] mm: Add readahead address space operation

Commit Message

Matthew Wilcox (Oracle) Feb. 1, 2020, 3:12 p.m. UTC

From: "Matthew Wilcox (Oracle)" <[e-mail]>

This replaces ->readpages with a saner interface:
 - Return the number of pages not read instead of an ignored error code.
 - Pages are already in the page cache when ->readahead is called.
 - Implementation looks up the pages in the page cache instead of
   having them passed in a linked list.

Signed-off-by: Matthew Wilcox (Oracle) <[e-mail]>
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
---
 Documentation/filesystems/locking.rst |  7 ++++++-
 Documentation/filesystems/vfs.rst     | 14 ++++++++++++++
 include/linux/fs.h                    |  2 ++
 include/linux/pagemap.h               | 12 ++++++++++++
 mm/readahead.c                        | 13 ++++++++++++-
 5 files changed, 46 insertions(+), 2 deletions(-)

Patch

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index 5057e4d9dcd1..3d10729caf44 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -239,6 +239,8 @@  prototypes::
 	int (*readpage)(struct file *, struct page *);
 	int (*writepages)(struct address_space *, struct writeback_control *);
 	int (*set_page_dirty)(struct page *page);
+	unsigned (*readahead)(struct file *, struct address_space *,
+				 pgoff_t start, unsigned nr_pages);
 	int (*readpages)(struct file *filp, struct address_space *mapping,
 			struct list_head *pages, unsigned nr_pages);
 	int (*write_begin)(struct file *, struct address_space *mapping,
@@ -271,7 +273,8 @@  writepage:		yes, unlocks (see below)
 readpage:		yes, unlocks
 writepages:
 set_page_dirty		no
-readpages:
+readahead:		yes, unlocks
+readpages:		no
 write_begin:		locks the page		 exclusive
 write_end:		yes, unlocks		 exclusive
 bmap:
@@ -295,6 +298,8 @@  the request handler (/dev/loop).
 ->readpage() unlocks the page, either synchronously or via I/O
 completion.
 
+->readahead() unlocks the pages like ->readpage().
+
 ->readpages() populates the pagecache with the passed pages and starts
 I/O against them.  They come unlocked upon I/O completion.
 
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index 7d4d09dd5e6d..c2bc345f2169 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -706,6 +706,8 @@  cache in your filesystem.  The following members are defined:
 		int (*readpage)(struct file *, struct page *);
 		int (*writepages)(struct address_space *, struct writeback_control *);
 		int (*set_page_dirty)(struct page *page);
+		unsigned (*readahead)(struct file *filp, struct address_space *mapping,
+				 pgoff_t start, unsigned nr_pages);
 		int (*readpages)(struct file *filp, struct address_space *mapping,
 				 struct list_head *pages, unsigned nr_pages);
 		int (*write_begin)(struct file *, struct address_space *mapping,
@@ -781,6 +783,18 @@  cache in your filesystem.  The following members are defined:
 	If defined, it should set the PageDirty flag, and the
 	PAGECACHE_TAG_DIRTY tag in the radix tree.
 
+``readahead``
+	Called by the VM to read pages associated with the address_space
+	object.  The pages are consecutive in the page cache and
+	are locked.  The implementation should decrement the page
+	refcount after attempting I/O on each page.  Usually the
+	page will be unlocked by the I/O completion handler.  If the
+	function does not attempt I/O on some pages, return the number
+	of pages which were not read so the caller can unlock the pages
+	for you.  Set PageUptodate if the I/O completes successfully.
+	Setting PageError on any page will be ignored; simply unlock
+	the page if an I/O error occurs.
+
 ``readpages``
 	called by the VM to read pages associated with the address_space
 	object.  This is essentially just a vector version of readpage.
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 41584f50af0d..3bfc142e7d10 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -375,6 +375,8 @@  struct address_space_operations {
 	 */
 	int (*readpages)(struct file *filp, struct address_space *mapping,
 			struct list_head *pages, unsigned nr_pages);
+	unsigned (*readahead)(struct file *, struct address_space *,
+			pgoff_t start, unsigned nr_pages);
 
 	int (*write_begin)(struct file *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned flags,
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index ccb14b6a16b5..a2cf007826f2 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -630,6 +630,18 @@  static inline int add_to_page_cache(struct page *page,
 	return error;
 }
 
+/*
+ * Only call this from a ->readahead implementation.
+ */
+static inline
+struct page *readahead_page(struct address_space *mapping, pgoff_t index)
+{
+	struct page *page = xa_load(&mapping->i_pages, index);
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+
+	return page;
+}
+
 static inline unsigned long dir_pages(struct inode *inode)
 {
 	return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >>
diff --git a/mm/readahead.c b/mm/readahead.c
index 7daef0038b14..b2ed0baf3a5d 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -121,7 +121,18 @@  static void read_pages(struct address_space *mapping, struct file *filp,
 
 	blk_start_plug(&plug);
 
-	if (mapping->a_ops->readpages) {
+	if (mapping->a_ops->readahead) {
+		unsigned left = mapping->a_ops->readahead(filp, mapping,
+				start, nr_pages);
+
+		while (left) {
+			struct page *page = readahead_page(mapping,
+					start + nr_pages - left);
+			unlock_page(page);
+			put_page(page);
+			left--;
+		}
+	} else if (mapping->a_ops->readpages) {
 		mapping->a_ops->readpages(filp, mapping, pages, nr_pages);
 		/* Clean up the remaining pages */
 		put_pages_list(pages);