Linux-ext4 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 v5 05/13] mm: Add page_cache_readahead_limit
Date: Mon, 10 Feb 2020 17:03:40 -0800
Message-ID: <20200211010348.6872-6-willy@infradead.org> (raw)
In-Reply-To: <20200211010348.6872-1-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 |  4 ++++
 mm/readahead.c          | 51 ++++++++++++++++++++++++-----------------
 4 files changed, 38 insertions(+), 87 deletions(-)

diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index dc5ec724d889..f6e0bf05933e 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_limit(inode->i_mapping, NULL,
+					index, LONG_MAX, 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..71a3e36721fa 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_limit(inode->i_mapping, NULL,
+					index, LONG_MAX, 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 13efafaf7e1f..ddb2d1b43212 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -389,6 +389,10 @@ extern struct page * read_cache_page_gfp(struct address_space *mapping,
 				pgoff_t index, gfp_t gfp_mask);
 extern int read_cache_pages(struct address_space *mapping,
 		struct list_head *pages, filler_t *filler, void *data);
+unsigned long page_cache_readahead_limit(struct address_space *mapping,
+		struct file *file, pgoff_t start, pgoff_t end_index,
+		unsigned long nr_to_read, unsigned long lookahead_size);
+
 
 static inline struct page *read_mapping_page(struct address_space *mapping,
 				pgoff_t index, void *data)
diff --git a/mm/readahead.c b/mm/readahead.c
index 933b32e0c90a..29ca25c8f01e 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -144,38 +144,22 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages)
 	blk_finish_plug(&plug);
 }
 
-/*
- * __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.
- *
- * Returns the number of pages requested, or the maximum amount of I/O allowed.
- */
-unsigned long __do_page_cache_readahead(struct address_space *mapping,
-		struct file *filp, pgoff_t start, unsigned long nr_to_read,
-		unsigned long lookahead_size)
+unsigned long page_cache_readahead_limit(struct address_space *mapping,
+		struct file *file, pgoff_t start, pgoff_t end_index,
+		unsigned long nr_to_read, unsigned long lookahead_size)
 {
-	struct inode *inode = mapping->host;
-	unsigned long end_index;	/* The last page we want to read */
 	LIST_HEAD(page_pool);
 	int page_idx;
 	pgoff_t page_offset = start;
-	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,
 		.start = start,
 		.nr_pages = 0,
 	};
 
-	if (isize == 0)
-		goto out;
-
-	end_index = ((isize - 1) >> PAGE_SHIFT);
-
 	/*
 	 * Preallocate as many pages as we will need.
 	 */
@@ -233,9 +217,34 @@ unsigned long __do_page_cache_readahead(struct address_space *mapping,
 	 */
 	read_pages(&rac, &page_pool);
 	BUG_ON(!list_empty(&page_pool));
-out:
 	return rac.nr_pages;
 }
+EXPORT_SYMBOL_GPL(page_cache_readahead_limit);
+
+/*
+ * __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.
+ *
+ * Returns the number of pages requested, or the maximum amount of I/O allowed.
+ */
+unsigned long __do_page_cache_readahead(struct address_space *mapping,
+		struct file *file, pgoff_t start, unsigned long nr_to_read,
+		unsigned long lookahead_size)
+{
+	struct inode *inode = mapping->host;
+	unsigned long end_index;	/* The last page we want to read */
+	loff_t isize = i_size_read(inode);
+
+	if (isize == 0)
+		return 0;
+
+	end_index = ((isize - 1) >> PAGE_SHIFT);
+
+	return page_cache_readahead_limit(mapping, file, start, end_index,
+			nr_to_read, lookahead_size);
+}
 
 /*
  * Chunk the readahead into 2 megabyte units, so that we don't pin too much
-- 
2.25.0


  parent reply index

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-11  1:03 [PATCH v5 00/13] Change readahead API Matthew Wilcox
2020-02-11  1:03 ` [PATCH v5 01/13] mm: Fix the return type of __do_page_cache_readahead Matthew Wilcox
2020-02-11  8:19   ` Johannes Thumshirn
2020-02-11 12:34     ` Matthew Wilcox
2020-02-12 18:13   ` Christoph Hellwig
2020-02-14  3:19   ` John Hubbard
2020-02-14  4:21     ` Matthew Wilcox
2020-02-14  4:33       ` John Hubbard
2020-02-14 19:50   ` Matthew Wilcox
2020-02-11  1:03 ` [PATCH v5 02/13] mm: Ignore return value of ->readpages Matthew Wilcox
2020-02-12 18:13   ` Christoph Hellwig
2020-02-11  1:03 ` [PATCH v5 03/13] mm: Put readahead pages in cache earlier Matthew Wilcox
2020-02-14  3:36   ` John Hubbard
2020-02-15  1:15     ` Matthew Wilcox
2020-02-11  1:03 ` [PATCH v5 04/13] mm: Add readahead address space operation Matthew Wilcox
2020-02-11  4:52   ` Dave Chinner
2020-02-11 12:54     ` Matthew Wilcox
2020-02-11 20:08       ` Dave Chinner
2020-02-12 18:18   ` Christoph Hellwig
2020-02-14  5:36   ` John Hubbard
2020-02-15  1:15     ` Matthew Wilcox
2020-02-11  1:03 ` Matthew Wilcox [this message]
2020-02-11  1:03 ` [PATCH v5 06/13] fs: Convert mpage_readpages to mpage_readahead Matthew Wilcox
2020-02-13 22:09   ` Junxiao Bi
2020-02-11  1:03 ` [PATCH v5 07/13] btrfs: Convert from readpages to readahead Matthew Wilcox
2020-02-11  1:03 ` [PATCH v5 08/13] erofs: Convert uncompressed files " Matthew Wilcox
2020-02-11  1:03 ` [PATCH v5 09/13] erofs: Convert compressed " Matthew Wilcox
2020-02-11  1:03 ` [PATCH v5 10/13] ext4: Convert " Matthew Wilcox
2020-02-11  1:03 ` [PATCH v5 11/13] f2fs: " Matthew Wilcox
2020-02-11  1:03 ` [PATCH v5 12/13] fuse: " Matthew Wilcox
2020-02-11  1:03 ` [PATCH v5 13/13] 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=20200211010348.6872-6-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-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