Linux-ext4 Archive on lore.kernel.org
 help / color / Atom feed
From: Matthew Wilcox <willy@infradead.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>,
	linux-fsdevel@vger.kernel.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,
	John Hubbard <jhubbard@nvidia.com>,
	Christoph Hellwig <hch@lst.de>,
	William Kucharski <william.kucharski@oracle.com>
Subject: [PATCH v10 11/25] mm: Add readahead address space operation
Date: Mon, 23 Mar 2020 13:22:45 -0700
Message-ID: <20200323202259.13363-12-willy@infradead.org> (raw)
In-Reply-To: <20200323202259.13363-1-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.
 - 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().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
---
 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(-)

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index 5057e4d9dcd1..0af2e0e11461 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 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.
 
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index 7d4d09dd5e6d..ed17771c212b 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 +782,26 @@ 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 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
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2c097c0793f3..3b505aabebde 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/mm/readahead.c b/mm/readahead.c
index e52b3a7b9da5..d01531ef9f3c 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -125,7 +125,14 @@ 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);
+		/* 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 address_space *mapping,
 	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;
 
 	/*
-- 
2.25.1


  parent reply index

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-23 20:22 [PATCH v10 00/25] Change readahead API Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 01/25] mm: Move readahead prototypes from mm.h Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 02/25] mm: Return void from various readahead functions Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 03/25] mm: Ignore return value of ->readpages Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 04/25] mm: Move readahead nr_pages check into read_pages Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 05/25] mm: Add new readahead_control API Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 06/25] mm: Use readahead_control to pass arguments Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 07/25] mm: Rename various 'offset' parameters to 'index' Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 08/25] mm: rename readahead loop variable to 'i' Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 09/25] mm: Remove 'page_offset' from readahead loop Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 10/25] mm: Put readahead pages in cache earlier Matthew Wilcox
2020-03-23 20:22 ` Matthew Wilcox [this message]
2020-03-23 20:22 ` [PATCH v10 12/25] mm: Move end_index check out of readahead loop Matthew Wilcox
2020-03-23 20:49   ` Eric Biggers
2020-03-24  8:40   ` Christoph Hellwig
2020-03-23 20:22 ` [PATCH v10 13/25] mm: Add page_cache_readahead_unbounded Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 14/25] mm: Document why we don't set PageReadahead Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 15/25] mm: Use memalloc_nofs_save in readahead path Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 16/25] fs: Convert mpage_readpages to mpage_readahead Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 17/25] btrfs: Convert from readpages to readahead Matthew Wilcox
2020-03-26 16:53   ` David Sterba
2020-03-23 20:22 ` [PATCH v10 18/25] erofs: Convert uncompressed files " Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 19/25] erofs: Convert compressed " Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 20/25] ext4: Convert " Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 21/25] ext4: Pass the inode to ext4_mpage_readpages Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 22/25] f2fs: Convert from readpages to readahead Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 23/25] f2fs: Pass the inode to f2fs_mpage_readpages Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 24/25] fuse: Convert from readpages to readahead Matthew Wilcox
2020-03-25  9:42   ` Miklos Szeredi
2020-03-25 12:02     ` Matthew Wilcox
2020-03-25 14:43       ` Miklos Szeredi
2020-03-25 15:32         ` Matthew Wilcox
2020-03-25 15:54           ` Miklos Szeredi
2020-03-23 20:22 ` [PATCH v10 25/25] iomap: " Matthew Wilcox

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=20200323202259.13363-12-willy@infradead.org \
    --to=willy@infradead.org \
    --cc=akpm@linux-foundation.org \
    --cc=cluster-devel@redhat.com \
    --cc=hch@lst.de \
    --cc=jhubbard@nvidia.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 \
    --cc=william.kucharski@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-ext4 Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-ext4/0 linux-ext4/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-ext4 linux-ext4/ https://lore.kernel.org/linux-ext4 \
		linux-ext4@vger.kernel.org
	public-inbox-index linux-ext4

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-ext4


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