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 v7 12/24] mm: Add page_cache_readahead_unbounded
Date: Wed, 19 Feb 2020 13:00:51 -0800 [thread overview]
Message-ID: <20200219210103.32400-13-willy@infradead.org> (raw)
In-Reply-To: <20200219210103.32400-1-willy@infradead.org>
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
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@infradead.org>
---
fs/ext4/verity.c | 35 ++-------------------
fs/f2fs/verity.c | 35 ++-------------------
include/linux/pagemap.h | 3 ++
mm/readahead.c | 70 ++++++++++++++++++++++++++++-------------
4 files changed, 55 insertions(+), 88 deletions(-)
diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index dc5ec724d889..dec1244dd062 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_unbounded(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..865c9fb774fb 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_unbounded(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 b3008605fd1b..60f9b8d4da6c 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -621,6 +621,9 @@ 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_unbounded(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 ace611f4bf05..453ef146de83 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -155,40 +155,36 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages)
rac->_index++;
}
-/*
- * __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_unbounded - 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_unbounded(struct address_space *mapping,
+ struct file *file, pgoff_t index, unsigned long nr_to_read,
unsigned long lookahead_size)
{
- struct inode *inode = mapping->host;
LIST_HEAD(page_pool);
- 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,
._index = index,
._nr_pages = 0,
};
unsigned long i;
- pgoff_t end_index; /* The last page we want to read */
-
- if (isize == 0)
- return;
-
- end_index = (isize - 1) >> PAGE_SHIFT;
- if (index > end_index)
- return;
- if (index + nr_to_read < index)
- nr_to_read = ULONG_MAX - index + 1;
- if (index + nr_to_read >= end_index)
- nr_to_read = end_index - index + 1;
/*
* Preallocate as many pages as we will need.
@@ -232,6 +228,36 @@ void __do_page_cache_readahead(struct address_space *mapping,
*/
read_pages(&rac, &page_pool);
}
+EXPORT_SYMBOL_GPL(page_cache_readahead_unbounded);
+
+/*
+ * __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; /* The last page we want to read */
+
+ if (isize == 0)
+ return;
+
+ end_index = (isize - 1) >> PAGE_SHIFT;
+ if (index > end_index)
+ return;
+ if (index + nr_to_read < index)
+ nr_to_read = ULONG_MAX - index + 1;
+ if (index + nr_to_read >= end_index)
+ nr_to_read = end_index - index + 1;
+
+ page_cache_readahead_unbounded(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
next prev parent reply other threads:[~2020-02-19 21:01 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-19 21:00 [PATCH v7 00/23] Change readahead API Matthew Wilcox
2020-02-19 21:00 ` [PATCH v7 01/24] mm: Move readahead prototypes from mm.h Matthew Wilcox
2020-02-21 2:43 ` John Hubbard
2020-02-21 21:48 ` Matthew Wilcox
2020-02-22 0:15 ` John Hubbard
2020-02-24 21:32 ` Christoph Hellwig
2020-02-19 21:00 ` [PATCH v7 02/24] mm: Return void from various readahead functions Matthew Wilcox
2020-02-24 21:33 ` Christoph Hellwig
2020-02-19 21:00 ` [PATCH v7 03/24] mm: Ignore return value of ->readpages Matthew Wilcox
2020-02-19 21:00 ` [PATCH v7 04/24] mm: Move readahead nr_pages check into read_pages Matthew Wilcox
2020-02-20 14:36 ` Zi Yan
2020-02-21 4:24 ` John Hubbard
2020-02-24 21:34 ` Christoph Hellwig
2020-02-19 21:00 ` [PATCH v7 05/24] mm: Use readahead_control to pass arguments Matthew Wilcox
2020-02-24 21:36 ` Christoph Hellwig
2020-02-19 21:00 ` [PATCH v7 06/24] mm: Rename various 'offset' parameters to 'index' Matthew Wilcox
2020-02-21 2:21 ` John Hubbard
2020-02-21 3:27 ` John Hubbard
2020-02-19 21:00 ` [PATCH v7 07/24] mm: rename readahead loop variable to 'i' Matthew Wilcox
2020-02-19 21:00 ` [PATCH v7 08/24] mm: Remove 'page_offset' from readahead loop Matthew Wilcox
2020-02-21 2:48 ` John Hubbard
2020-02-24 21:37 ` Christoph Hellwig
2020-02-19 21:00 ` [PATCH v7 09/24] mm: Put readahead pages in cache earlier Matthew Wilcox
2020-02-21 3:19 ` John Hubbard
2020-02-21 3:43 ` Matthew Wilcox
2020-02-21 4:19 ` John Hubbard
2020-02-24 21:40 ` Christoph Hellwig
2020-02-19 21:00 ` [PATCH v7 10/24] mm: Add readahead address space operation Matthew Wilcox
2020-02-20 15:00 ` Zi Yan
2020-02-20 15:10 ` Matthew Wilcox
2020-02-21 4:30 ` John Hubbard
2020-02-24 21:41 ` Christoph Hellwig
2020-02-19 21:00 ` [PATCH v7 11/24] mm: Move end_index check out of readahead loop Matthew Wilcox
2020-02-21 3:50 ` John Hubbard
2020-02-21 15:35 ` Matthew Wilcox
2020-02-21 19:41 ` John Hubbard
2020-02-19 21:00 ` Matthew Wilcox [this message]
2020-02-24 21:53 ` [Cluster-devel] [PATCH v7 12/24] mm: Add page_cache_readahead_unbounded Christoph Hellwig
2020-02-19 21:00 ` [PATCH v7 13/24] fs: Convert mpage_readpages to mpage_readahead Matthew Wilcox
2020-02-24 21:54 ` [Cluster-devel] " Christoph Hellwig
2020-02-19 21:00 ` [PATCH v7 14/24] btrfs: Convert from readpages to readahead Matthew Wilcox
2020-02-20 9:42 ` Johannes Thumshirn
2020-02-20 13:48 ` Matthew Wilcox
2020-02-20 15:46 ` Christoph Hellwig
2020-02-20 15:54 ` Matthew Wilcox
2020-02-20 15:57 ` Christoph Hellwig
2020-02-24 21:43 ` Christoph Hellwig
2020-02-24 21:54 ` Matthew Wilcox
2020-02-24 21:57 ` Christoph Hellwig
2020-02-19 21:00 ` [PATCH v7 15/24] erofs: Convert uncompressed files " Matthew Wilcox
2020-02-19 21:00 ` [PATCH v7 16/24] erofs: Convert compressed " Matthew Wilcox
2020-02-19 21:00 ` [PATCH v7 17/24] ext4: Convert " Matthew Wilcox
2020-02-19 21:00 ` [PATCH v7 18/24] ext4: Pass the inode to ext4_mpage_readpages Matthew Wilcox
2020-02-19 21:00 ` [PATCH v7 19/24] f2fs: Convert from readpages to readahead Matthew Wilcox
2020-02-19 21:00 ` [PATCH v7 20/24] fuse: " Matthew Wilcox
2020-02-19 21:01 ` [PATCH v7 21/24] iomap: Restructure iomap_readpages_actor Matthew Wilcox
2020-02-20 15:47 ` Christoph Hellwig
2020-02-20 16:24 ` Matthew Wilcox
2020-02-24 22:17 ` Christoph Hellwig
2020-02-25 1:49 ` Matthew Wilcox
2020-02-22 0:44 ` Darrick J. Wong
2020-02-22 1:54 ` Matthew Wilcox
2020-02-23 17:55 ` Darrick J. Wong
2020-02-19 21:01 ` [PATCH v7 22/24] iomap: Convert from readpages to readahead Matthew Wilcox
2020-02-20 15:49 ` Christoph Hellwig
2020-02-20 16:57 ` Matthew Wilcox
2020-02-22 1:00 ` Darrick J. Wong
2020-02-24 4:33 ` Matthew Wilcox
2020-02-24 16:52 ` Darrick J. Wong
2020-02-22 1:03 ` Darrick J. Wong
2020-02-22 1:09 ` Matthew Wilcox
2020-02-19 21:01 ` [PATCH v7 23/24] mm: Document why we don't set PageReadahead Matthew Wilcox
2020-02-19 21:01 ` [PATCH v7 24/24] mm: Use memalloc_nofs_save in readahead path Matthew Wilcox
2020-02-20 17:54 ` [PATCH v7 00/23] Change readahead API David Sterba
2020-02-20 22:39 ` Matthew Wilcox
2020-02-21 11:59 ` David Sterba
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=20200219210103.32400-13-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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).