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>
Subject: [PATCH v9 10/25] mm: Put readahead pages in cache earlier
Date: Fri, 20 Mar 2020 07:22:16 -0700
Message-ID: <20200320142231.2402-11-willy@infradead.org> (raw)
In-Reply-To: <20200320142231.2402-1-willy@infradead.org>

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

When populating the page cache for readahead, mappings that use
->readpages must populate the page cache themselves as the pages are
passed on a linked list which would normally be used for the page cache's
LRU.  For mappings that use ->readpage or the upcoming ->readahead method,
we can put the pages into the page cache as soon as they're allocated,
which solves a race between readahead and direct IO.  It also lets us
remove the gfp argument from read_pages().

Use the new readahead_page() API to implement the repeated calls to
->readpage(), just like most filesystems will.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
---
 mm/readahead.c | 46 ++++++++++++++++++++++++++++------------------
 1 file changed, 28 insertions(+), 18 deletions(-)

diff --git a/mm/readahead.c b/mm/readahead.c
index ddc63d3b07b8..e52b3a7b9da5 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -114,14 +114,14 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages,
 EXPORT_SYMBOL(read_cache_pages);
 
 static void read_pages(struct readahead_control *rac, struct list_head *pages,
-		gfp_t gfp)
+		bool skip_page)
 {
 	const struct address_space_operations *aops = rac->mapping->a_ops;
+	struct page *page;
 	struct blk_plug plug;
-	unsigned page_idx;
 
 	if (!readahead_count(rac))
-		return;
+		goto out;
 
 	blk_start_plug(&plug);
 
@@ -130,23 +130,23 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages,
 				readahead_count(rac));
 		/* Clean up the remaining pages */
 		put_pages_list(pages);
-		goto out;
-	}
-
-	for (page_idx = 0; page_idx < readahead_count(rac); page_idx++) {
-		struct page *page = lru_to_page(pages);
-		list_del(&page->lru);
-		if (!add_to_page_cache_lru(page, rac->mapping, page->index,
-				gfp))
+		rac->_index += rac->_nr_pages;
+		rac->_nr_pages = 0;
+	} else {
+		while ((page = readahead_page(rac))) {
 			aops->readpage(rac->file, page);
-		put_page(page);
+			put_page(page);
+		}
 	}
 
-out:
 	blk_finish_plug(&plug);
 
 	BUG_ON(!list_empty(pages));
-	rac->_nr_pages = 0;
+	BUG_ON(readahead_count(rac));
+
+out:
+	if (skip_page)
+		rac->_index++;
 }
 
 /*
@@ -168,6 +168,7 @@ void __do_page_cache_readahead(struct address_space *mapping,
 	struct readahead_control rac = {
 		.mapping = mapping,
 		.file = filp,
+		._index = index,
 	};
 	unsigned long i;
 
@@ -183,6 +184,8 @@ void __do_page_cache_readahead(struct address_space *mapping,
 		if (index + i > end_index)
 			break;
 
+		BUG_ON(index + i != rac._index + rac._nr_pages);
+
 		page = xa_load(&mapping->i_pages, index + i);
 		if (page && !xa_is_value(page)) {
 			/*
@@ -190,15 +193,22 @@ void __do_page_cache_readahead(struct address_space *mapping,
 			 * contiguous pages before continuing with the next
 			 * batch.
 			 */
-			read_pages(&rac, &page_pool, gfp_mask);
+			read_pages(&rac, &page_pool, true);
 			continue;
 		}
 
 		page = __page_cache_alloc(gfp_mask);
 		if (!page)
 			break;
-		page->index = index + i;
-		list_add(&page->lru, &page_pool);
+		if (mapping->a_ops->readpages) {
+			page->index = index + i;
+			list_add(&page->lru, &page_pool);
+		} else if (add_to_page_cache_lru(page, mapping, index + i,
+					gfp_mask) < 0) {
+			put_page(page);
+			read_pages(&rac, &page_pool, true);
+			continue;
+		}
 		if (i == nr_to_read - lookahead_size)
 			SetPageReadahead(page);
 		rac._nr_pages++;
@@ -209,7 +219,7 @@ void __do_page_cache_readahead(struct address_space *mapping,
 	 * uptodate then the caller will launch readpage again, and
 	 * will then handle the error.
 	 */
-	read_pages(&rac, &page_pool, gfp_mask);
+	read_pages(&rac, &page_pool, false);
 }
 
 /*
-- 
2.25.1


  parent reply index

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-20 14:22 [PATCH v9 00/25] Change readahead API Matthew Wilcox
2020-03-20 14:22 ` [PATCH v9 01/25] mm: Move readahead prototypes from mm.h Matthew Wilcox
2020-03-20 14:22 ` [PATCH v9 02/25] mm: Return void from various readahead functions Matthew Wilcox
2020-03-20 14:22 ` [PATCH v9 03/25] mm: Ignore return value of ->readpages Matthew Wilcox
2020-03-20 14:22 ` [PATCH v9 04/25] mm: Move readahead nr_pages check into read_pages Matthew Wilcox
2020-03-20 14:22 ` [PATCH v9 05/25] mm: Add new readahead_control API Matthew Wilcox
2020-03-20 14:22 ` [PATCH v9 06/25] mm: Use readahead_control to pass arguments Matthew Wilcox
2020-03-20 14:22 ` [PATCH v9 07/25] mm: Rename various 'offset' parameters to 'index' Matthew Wilcox
2020-03-20 14:22 ` [PATCH v9 08/25] mm: rename readahead loop variable to 'i' Matthew Wilcox
2020-03-20 14:22 ` [PATCH v9 09/25] mm: Remove 'page_offset' from readahead loop Matthew Wilcox
2020-03-20 14:22 ` Matthew Wilcox [this message]
2020-03-20 14:22 ` [PATCH v9 11/25] mm: Add readahead address space operation Matthew Wilcox
2020-03-20 14:22 ` [PATCH v9 12/25] mm: Move end_index check out of readahead loop Matthew Wilcox
2020-03-20 16:58   ` Eric Biggers
2020-03-20 17:30     ` Matthew Wilcox
2020-03-20 18:00       ` Eric Biggers
2020-03-20 18:11         ` Matthew Wilcox
2020-03-20 18:24           ` Eric Biggers
2020-03-22 16:28             ` Matthew Wilcox
2020-03-20 14:22 ` [PATCH v9 13/25] mm: Add page_cache_readahead_unbounded Matthew Wilcox
2020-03-20 17:27   ` Eric Biggers
2020-03-20 14:22 ` [PATCH v9 14/25] mm: Document why we don't set PageReadahead Matthew Wilcox
2020-03-20 14:22 ` [PATCH v9 15/25] mm: Use memalloc_nofs_save in readahead path Matthew Wilcox
2020-03-20 14:22 ` [PATCH v9 16/25] fs: Convert mpage_readpages to mpage_readahead Matthew Wilcox
2020-03-20 23:24   ` Namjae Jeon
2020-03-20 14:22 ` [PATCH v9 17/25] btrfs: Convert from readpages to readahead Matthew Wilcox
2020-03-20 14:22 ` [PATCH v9 18/25] erofs: Convert uncompressed files " Matthew Wilcox
2020-03-21 12:38   ` [f2fs-dev] " Chao Yu
2020-03-20 14:22 ` [PATCH v9 19/25] erofs: Convert compressed " Matthew Wilcox
2020-03-21 12:41   ` [f2fs-dev] " Chao Yu
2020-03-20 14:22 ` [PATCH v9 20/25] ext4: Convert " Matthew Wilcox
2020-03-20 17:37   ` Eric Biggers
2020-03-20 17:48     ` Matthew Wilcox
2020-03-20 18:40       ` Eric Biggers
2020-03-20 14:22 ` [PATCH v9 21/25] ext4: Pass the inode to ext4_mpage_readpages Matthew Wilcox
2020-03-20 18:44   ` Eric Biggers
2020-03-20 14:22 ` [PATCH v9 22/25] f2fs: Convert from readpages to readahead Matthew Wilcox
2020-03-20 18:51   ` Eric Biggers
2020-03-21 12:34   ` [f2fs-dev] " Chao Yu
2020-03-23  3:55   ` Jaegeuk Kim
2020-03-20 14:22 ` [PATCH v9 23/25] f2fs: Pass the inode to f2fs_mpage_readpages Matthew Wilcox
2020-03-20 18:52   ` Eric Biggers
2020-03-21 12:35   ` [f2fs-dev] " Chao Yu
2020-03-23  3:53   ` Jaegeuk Kim
2020-03-20 14:22 ` [PATCH v9 24/25] fuse: Convert from readpages to readahead Matthew Wilcox
2020-03-20 14:22 ` [PATCH v9 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=20200320142231.2402-11-willy@infradead.org \
    --to=willy@infradead.org \
    --cc=akpm@linux-foundation.org \
    --cc=cluster-devel@redhat.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