Linux-BTRFS Archive on lore.kernel.org
 help / color / Atom feed
From: Matthew Wilcox <willy@infradead.org>
To: linux-fsdevel@vger.kernel.org
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	linux-btrfs@vger.kernel.org, linux-erofs@lists.ozlabs.org,
	linux-ext4@vger.kernel.org,
	linux-f2fs-devel@lists.sourceforge.net, cluster-devel@redhat.com,
	ocfs2-devel@oss.oracle.com, linux-xfs@vger.kernel.org
Subject: [PATCH v6 08/19] mm: Add readahead address space operation
Date: Mon, 17 Feb 2020 10:45:54 -0800
Message-ID: <20200217184613.19668-14-willy@infradead.org> (raw)
In-Reply-To: <20200217184613.19668-1-willy@infradead.org>

From: "Matthew Wilcox (Oracle)" <willy@infradead.org>

This replaces ->readpages with a saner interface:
 - Return void 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) <willy@infradead.org>
---
 Documentation/filesystems/locking.rst |  6 +++++-
 Documentation/filesystems/vfs.rst     | 13 +++++++++++++
 include/linux/fs.h                    |  2 ++
 include/linux/pagemap.h               | 18 ++++++++++++++++++
 mm/readahead.c                        |  8 +++++++-
 5 files changed, 45 insertions(+), 2 deletions(-)

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index 5057e4d9dcd1..0ebc4491025a 100644
--- a/Documentation/filesystems/locking.rst
+++ b/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 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..81ab30fbe45c 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -706,6 +706,7 @@ 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);
+		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 +782,24 @@ 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 starting 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, the caller will decrement the page
+	refcount and 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.
 	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; implement readahead instead.
 
 ``write_begin``
 	Called by the generic buffered write code to ask the filesystem
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3cd4fe6b845e..d4e2d2964346 100644
--- a/include/linux/fs.h
+++ b/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,
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 3613154e79e4..bd4291f78f41 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -665,6 +665,24 @@ static inline void readahead_next(struct readahead_control *rac)
 #define readahead_for_each(rac, page)					\
 	for (; (page = readahead_page(rac)); readahead_next(rac))
 
+/* The byte offset into the file of this readahead block */
+static inline loff_t readahead_offset(struct readahead_control *rac)
+{
+	return (loff_t)rac->_start * PAGE_SIZE;
+}
+
+/* The number of bytes in this readahead block */
+static inline loff_t readahead_length(struct readahead_control *rac)
+{
+	return (loff_t)rac->_nr_pages * PAGE_SIZE;
+}
+
+/* The index of the first page in this readahead block */
+static inline unsigned int readahead_index(struct readahead_control *rac)
+{
+	return rac->_start;
+}
+
 /* The number of pages in this readahead block */
 static inline unsigned int readahead_count(struct readahead_control *rac)
 {
diff --git a/mm/readahead.c b/mm/readahead.c
index 9e430daae42f..975ff5e387be 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -121,7 +121,13 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages)
 
 	blk_start_plug(&plug);
 
-	if (aops->readpages) {
+	if (aops->readahead) {
+		aops->readahead(rac);
+		readahead_for_each(rac, page) {
+			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 */
-- 
2.25.0


  parent reply index

Thread overview: 111+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-17 18:45 [PATCH v6 00/19] Change readahead API Matthew Wilcox
2020-02-17 18:45 ` [PATCH v6 01/19] mm: Return void from various readahead functions Matthew Wilcox
2020-02-18  4:47   ` Dave Chinner
2020-02-18 21:05   ` John Hubbard
2020-02-18 21:21     ` Matthew Wilcox
2020-02-18 21:52       ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 02/19] mm: Ignore return value of ->readpages Matthew Wilcox
2020-02-18  4:48   ` Dave Chinner
2020-02-18 21:33   ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 03/19] mm: Use readahead_control to pass arguments Matthew Wilcox
2020-02-18  5:03   ` Dave Chinner
2020-02-18 13:56     ` Matthew Wilcox
2020-02-18 22:46       ` Dave Chinner
2020-02-18 22:52         ` Matthew Wilcox
2020-02-18 22:22   ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 04/19] mm: Rearrange readahead loop Matthew Wilcox
2020-02-18  5:08   ` Dave Chinner
2020-02-18 13:57     ` Matthew Wilcox
2020-02-18 22:48       ` Dave Chinner
2020-02-18 22:33   ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 04/16] mm: Tweak readahead loop slightly Matthew Wilcox
2020-02-18 22:57   ` John Hubbard
2020-02-18 23:00     ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 05/16] mm: Put readahead pages in cache earlier Matthew Wilcox
2020-02-17 18:45 ` [PATCH v6 05/19] mm: Remove 'page_offset' from readahead loop Matthew Wilcox
2020-02-18  5:14   ` Dave Chinner
2020-02-18 23:08   ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 06/16] mm: Add readahead address space operation Matthew Wilcox
2020-02-17 18:45 ` [PATCH v6 06/19] mm: rename readahead loop variable to 'i' Matthew Wilcox
2020-02-18  5:33   ` Dave Chinner
2020-02-18 23:11   ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 07/16] mm: Add page_cache_readahead_limit Matthew Wilcox
2020-02-17 18:45 ` [PATCH v6 07/19] mm: Put readahead pages in cache earlier Matthew Wilcox
2020-02-18  6:14   ` Dave Chinner
2020-02-18 15:42     ` Matthew Wilcox
2020-02-19  0:59       ` Dave Chinner
2020-02-19  0:01   ` John Hubbard
2020-02-19  1:02     ` Matthew Wilcox
2020-02-19  1:13       ` John Hubbard
2020-02-19  3:24       ` John Hubbard
2020-02-19 14:41     ` Matthew Wilcox
2020-02-19 14:52       ` Christoph Hellwig
2020-02-19 15:01         ` Matthew Wilcox
2020-02-19 20:24           ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 08/16] fs: Convert mpage_readpages to mpage_readahead Matthew Wilcox
2020-02-17 18:45 ` Matthew Wilcox [this message]
2020-02-18  6:21   ` [PATCH v6 08/19] mm: Add readahead address space operation Dave Chinner
2020-02-18 16:10     ` Matthew Wilcox
2020-02-19  1:04       ` Dave Chinner
2020-02-19  0:12   ` John Hubbard
2020-02-19  3:10   ` Eric Biggers
2020-02-19  3:35     ` Eric Biggers
2020-02-19 16:52     ` Matthew Wilcox
2020-02-17 18:45 ` [PATCH v6 09/16] btrfs: Convert from readpages to readahead Matthew Wilcox
2020-02-17 18:45 ` [PATCH v6 09/19] mm: Add page_cache_readahead_limit Matthew Wilcox
2020-02-18  6:31   ` Dave Chinner
2020-02-18 19:54     ` Matthew Wilcox
2020-02-19  1:08       ` Dave Chinner
2020-02-19  1:32   ` John Hubbard
2020-02-19  2:23     ` Matthew Wilcox
2020-02-19  2:46       ` John Hubbard
2020-02-17 18:45 ` [PATCH v6 10/16] erofs: Convert uncompressed files from readpages to readahead Matthew Wilcox
2020-02-17 18:45 ` [PATCH v6 10/19] fs: Convert mpage_readpages to mpage_readahead Matthew Wilcox
2020-02-18  1:51   ` [Ocfs2-devel] " Joseph Qi
2020-02-18  6:37   ` Dave Chinner
2020-02-19  2:48   ` John Hubbard
2020-02-19  3:28   ` Eric Biggers
2020-02-19  3:47     ` Matthew Wilcox
2020-02-19  3:55       ` Eric Biggers
2020-02-17 18:45 ` [PATCH v6 11/19] btrfs: Convert from readpages to readahead Matthew Wilcox
2020-02-18  6:57   ` Dave Chinner
2020-02-18 21:12     ` Matthew Wilcox
2020-02-19  1:23       ` Dave Chinner
2020-02-17 18:46 ` [PATCH v6 11/16] erofs: Convert compressed files " Matthew Wilcox
2020-02-19  2:34   ` Gao Xiang
2020-02-17 18:46 ` [PATCH v6 12/19] erofs: Convert uncompressed " Matthew Wilcox
2020-02-19  2:39   ` Gao Xiang
2020-02-19  3:04   ` Dave Chinner
2020-02-17 18:46 ` [PATCH v6 12/16] ext4: Convert " Matthew Wilcox
2020-02-17 18:46 ` [PATCH v6 13/19] erofs: Convert compressed files " Matthew Wilcox
2020-02-19  3:08   ` Dave Chinner
2020-02-17 18:46 ` [PATCH v6 13/16] f2fs: Convert " Matthew Wilcox
2020-02-17 18:46 ` [PATCH v6 14/19] ext4: " Matthew Wilcox
2020-02-19  3:16   ` Dave Chinner
2020-02-19  3:29   ` Eric Biggers
2020-02-17 18:46 ` [PATCH v6 14/16] fuse: " Matthew Wilcox
2020-02-17 18:46 ` [PATCH v6 15/19] f2fs: " Matthew Wilcox
2020-02-17 18:46 ` [PATCH v6 15/16] iomap: " Matthew Wilcox
2020-02-17 18:46 ` [PATCH v6 16/19] fuse: " Matthew Wilcox
2020-02-19  3:22   ` Dave Chinner
2020-02-17 18:46 ` [PATCH v6 16/16] mm: Use memalloc_nofs_save in readahead path Matthew Wilcox
2020-02-17 18:46 ` [PATCH v6 17/19] iomap: Restructure iomap_readpages_actor Matthew Wilcox
2020-02-19  3:17   ` John Hubbard
2020-02-19  5:35     ` Matthew Wilcox
2020-02-19  3:29   ` Dave Chinner
2020-02-19  6:04     ` Matthew Wilcox
2020-02-19  6:40       ` Dave Chinner
2020-02-19 17:06         ` Matthew Wilcox
2020-02-17 18:46 ` [PATCH v6 18/19] iomap: Convert from readpages to readahead Matthew Wilcox
2020-02-19  3:40   ` Dave Chinner
2020-02-17 18:46 ` [PATCH v6 19/19] mm: Use memalloc_nofs_save in readahead path Matthew Wilcox
2020-02-19  3:43   ` Dave Chinner
2020-02-19  5:22     ` Matthew Wilcox
2020-02-17 18:48 ` [PATCH v6 00/19] Change readahead API Matthew Wilcox
2020-02-18  4:56 ` Dave Chinner
2020-02-18 13:42   ` Matthew Wilcox
2020-02-18 21:26     ` Dave Chinner
2020-02-19  3:45       ` Dave Chinner
2020-02-19  3:48         ` Matthew Wilcox
2020-02-19  3:57           ` Dave Chinner
2020-02-18 20:49 ` John Hubbard

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200217184613.19668-14-willy@infradead.org \
    --to=willy@infradead.org \
    --cc=cluster-devel@redhat.com \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-erofs@lists.ozlabs.org \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-f2fs-devel@lists.sourceforge.net \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=ocfs2-devel@oss.oracle.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-BTRFS Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-btrfs/0 linux-btrfs/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-btrfs linux-btrfs/ https://lore.kernel.org/linux-btrfs \
		linux-btrfs@vger.kernel.org
	public-inbox-index linux-btrfs

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-btrfs


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git