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,
	Christoph Hellwig <hch@lst.de>,
	William Kucharski <william.kucharski@oracle.com>,
	Eric Biggers <ebiggers@google.com>
Subject: [PATCH v10 13/25] mm: Add page_cache_readahead_unbounded
Date: Mon, 23 Mar 2020 13:22:47 -0700
Message-ID: <20200323202259.13363-14-willy@infradead.org> (raw)
In-Reply-To: <20200323202259.13363-1-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>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Tested-by: Eric Biggers <ebiggers@google.com>
---
 fs/ext4/verity.c        | 35 ++-------------------
 fs/f2fs/data.c          |  2 +-
 fs/f2fs/f2fs.h          |  3 --
 fs/f2fs/verity.c        | 35 ++-------------------
 include/linux/pagemap.h |  3 ++
 mm/readahead.c          | 68 ++++++++++++++++++++++++++++-------------
 6 files changed, 55 insertions(+), 91 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/data.c b/fs/f2fs/data.c
index dbde309349d0..adc4766782e1 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2148,7 +2148,7 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
  * use ->readpage() or do the necessary surgery to decouple ->readpages()
  * from read-ahead.
  */
-int f2fs_mpage_readpages(struct address_space *mapping,
+static int f2fs_mpage_readpages(struct address_space *mapping,
 			struct list_head *pages, struct page *page,
 			unsigned nr_pages, bool is_readahead)
 {
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 3e727a6af08e..d59b715d7870 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -3369,9 +3369,6 @@ int f2fs_reserve_new_block(struct dnode_of_data *dn);
 int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
 int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from);
 int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
-int f2fs_mpage_readpages(struct address_space *mapping,
-			struct list_head *pages, struct page *page,
-			unsigned nr_pages, bool is_readahead);
 struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
 			int op_flags, bool for_write);
 struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index);
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 89fd6a62bfa5..84e1bd68fda4 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -619,6 +619,9 @@ 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 998fdd23c0b1..ae231a5312cb 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -156,37 +156,34 @@ 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);
 	struct readahead_control rac = {
 		.mapping = mapping,
-		.file = filp,
+		.file = file,
 		._index = index,
 	};
 	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;
-	/* Don't read past the page containing the last byte of the file */
-	if (nr_to_read > end_index - index)
-		nr_to_read = end_index - index + 1;
 
 	/*
 	 * Preallocate as many pages as we will need.
@@ -230,6 +227,35 @@ void __do_page_cache_readahead(struct address_space *mapping,
 	 */
 	read_pages(&rac, &page_pool, false);
 }
+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;
+	/* Don't read past the page containing the last byte of the file */
+	if (nr_to_read > end_index - 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
-- 
2.25.1


  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 ` [PATCH v10 11/25] mm: Add readahead address space operation Matthew Wilcox
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 ` Matthew Wilcox [this message]
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=20200323202259.13363-14-willy@infradead.org \
    --to=willy@infradead.org \
    --cc=akpm@linux-foundation.org \
    --cc=cluster-devel@redhat.com \
    --cc=ebiggers@google.com \
    --cc=hch@lst.de \
    --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