The patch titled
Subject: mm: add readahead address space operation
has been added to the -mm tree. Its filename is
mm-add-readahead-address-space-operation.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-add-readahead-address-space-operation.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-add-readahead-address-space-operation.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>
Subject: mm: add readahead address space operation
This replaces ->readpages with a saner interface:
- Return void instead of an ignored error code.
- Page cache is already populated with locked pages when ->readahead
is called.
- New arguments can be passed to the implementation without changing
all the filesystems that use a common helper function like
mpage_readahead().
Link: http://lkml.kernel.org/r/20200414150233.24495-12-willy@xxxxxxxxxxxxx
Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Reviewed-by: John Hubbard <jhubbard@xxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: William Kucharski <william.kucharski@xxxxxxxxxx>
Cc: Chao Yu <yuchao0@xxxxxxxxxx>
Cc: Cong Wang <xiyou.wangcong@xxxxxxxxx>
Cc: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
Cc: Dave Chinner <dchinner@xxxxxxxxxx>
Cc: Eric Biggers <ebiggers@xxxxxxxxxx>
Cc: Gao Xiang <gaoxiang25@xxxxxxxxxx>
Cc: Jaegeuk Kim <jaegeuk@xxxxxxxxxx>
Cc: Joseph Qi <joseph.qi@xxxxxxxxxxxxxxxxx>
Cc: Junxiao Bi <junxiao.bi@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Zi Yan <ziy@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
Documentation/filesystems/locking.rst | 6 +++++-
Documentation/filesystems/vfs.rst | 15 +++++++++++++++
include/linux/fs.h | 2 ++
mm/readahead.c | 12 ++++++++++--
4 files changed, 32 insertions(+), 3 deletions(-)
--- a/Documentation/filesystems/locking.rst~mm-add-readahead-address-space-operation
+++ a/Documentation/filesystems/locking.rst
@@ -239,6 +239,7 @@ prototypes::
int (*readpage)(struct file *, struct page *);
int (*writepages)(struct address_space *, struct writeback_control *);
int (*set_page_dirty)(struct page *page);
+ void (*readahead)(struct readahead_control *);
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 +272,8 @@ 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 +297,8 @@ the request handler (/dev/loop).
->readpage() unlocks the page, either synchronously or via I/O
completion.
+->readahead() unlocks the pages that I/O is attempted on like ->readpage().
+
->readpages() populates the pagecache with the passed pages and starts
I/O against them. They come unlocked upon I/O completion.
--- a/Documentation/filesystems/vfs.rst~mm-add-readahead-address-space-operation
+++ a/Documentation/filesystems/vfs.rst
@@ -706,6 +706,7 @@ cache in your filesystem. The following
int (*readpage)(struct file *, struct page *);
int (*writepages)(struct address_space *, struct writeback_control *);
int (*set_page_dirty)(struct page *page);
+ void (*readahead)(struct readahead_control *);
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,
@@ -781,12 +782,26 @@ cache in your filesystem. The following
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 starting I/O on each page. Usually the page will be
+ unlocked by the I/O completion handler. If the filesystem decides
+ to stop attempting I/O before reaching the end of the readahead
+ window, it can simply return. The caller will decrement the page
+ refcount and unlock the remaining 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.
Instead of just one page, several pages are requested.
readpages is only used for read-ahead, so read errors are
ignored. If anything goes wrong, feel free to give up.
+ This interface is deprecated and will be removed by the end of
+ 2020; implement readahead instead.
``write_begin``
Called by the generic buffered write code to ask the filesystem
--- a/include/linux/fs.h~mm-add-readahead-address-space-operation
+++ a/include/linux/fs.h
@@ -292,6 +292,7 @@ enum positive_aop_returns {
struct page;
struct address_space;
struct writeback_control;
+struct readahead_control;
/*
* Write life time hint values.
@@ -375,6 +376,7 @@ struct address_space_operations {
*/
int (*readpages)(struct file *filp, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages);
+ void (*readahead)(struct readahead_control *);
int (*write_begin)(struct file *, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
--- a/mm/readahead.c~mm-add-readahead-address-space-operation
+++ a/mm/readahead.c
@@ -125,7 +125,14 @@ static void read_pages(struct readahead_
blk_start_plug(&plug);
- if (aops->readpages) {
+ if (aops->readahead) {
+ aops->readahead(rac);
+ /* Clean up the remaining pages */
+ while ((page = readahead_page(rac))) {
+ unlock_page(page);
+ put_page(page);
+ }
+ } else if (aops->readpages) {
aops->readpages(rac->file, rac->mapping, pages,
readahead_count(rac));
/* Clean up the remaining pages */
@@ -233,7 +240,8 @@ void force_page_cache_readahead(struct a
struct file_ra_state *ra = &filp->f_ra;
unsigned long max_pages;
- if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages))
+ if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages &&
+ !mapping->a_ops->readahead))
return;
/*
_
Patches currently in -mm which might be from willy@xxxxxxxxxxxxx are
mm-move-readahead-prototypes-from-mmh.patch
mm-return-void-from-various-readahead-functions.patch
mm-ignore-return-value-of-readpages.patch
mm-move-readahead-nr_pages-check-into-read_pages.patch
mm-add-new-readahead_control-api.patch
mm-use-readahead_control-to-pass-arguments.patch
mm-rename-various-offset-parameters-to-index.patch
mm-rename-readahead-loop-variable-to-i.patch
mm-remove-page_offset-from-readahead-loop.patch
mm-put-readahead-pages-in-cache-earlier.patch
mm-add-readahead-address-space-operation.patch
mm-move-end_index-check-out-of-readahead-loop.patch
mm-add-page_cache_readahead_unbounded.patch
mm-document-why-we-dont-set-pagereadahead.patch
mm-use-memalloc_nofs_save-in-readahead-path.patch
fs-convert-mpage_readpages-to-mpage_readahead.patch
btrfs-convert-from-readpages-to-readahead.patch
erofs-convert-uncompressed-files-from-readpages-to-readahead.patch
erofs-convert-compressed-files-from-readpages-to-readahead.patch
ext4-convert-from-readpages-to-readahead.patch
ext4-pass-the-inode-to-ext4_mpage_readpages.patch
f2fs-convert-from-readpages-to-readahead.patch
f2fs-pass-the-inode-to-f2fs_mpage_readpages.patch
fuse-convert-from-readpages-to-readahead.patch
iomap-convert-from-readpages-to-readahead.patch
