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 09/24] mm: Put readahead pages in cache earlier
Date: Wed, 19 Feb 2020 13:00:48 -0800 [thread overview]
Message-ID: <20200219210103.32400-10-willy@infradead.org> (raw)
In-Reply-To: <20200219210103.32400-1-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. This iterator also
supports huge pages, even though none of the filesystems have been
converted to use them yet.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
include/linux/pagemap.h | 20 +++++++++++++++++
mm/readahead.c | 48 +++++++++++++++++++++++++----------------
2 files changed, 49 insertions(+), 19 deletions(-)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 55fcea0249e6..4989d330fada 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -647,8 +647,28 @@ struct readahead_control {
/* private: use the readahead_* accessors instead */
pgoff_t _index;
unsigned int _nr_pages;
+ unsigned int _batch_count;
};
+static inline struct page *readahead_page(struct readahead_control *rac)
+{
+ struct page *page;
+
+ BUG_ON(rac->_batch_count > rac->_nr_pages);
+ rac->_nr_pages -= rac->_batch_count;
+ rac->_index += rac->_batch_count;
+ rac->_batch_count = 0;
+
+ if (!rac->_nr_pages)
+ return NULL;
+
+ page = xa_load(&rac->mapping->i_pages, rac->_index);
+ VM_BUG_ON_PAGE(!PageLocked(page), page);
+ rac->_batch_count = hpage_nr_pages(page);
+
+ return page;
+}
+
/* The number of pages in this readahead block */
static inline unsigned int readahead_count(struct readahead_control *rac)
{
diff --git a/mm/readahead.c b/mm/readahead.c
index 83df5c061d33..aaa209559ba2 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -113,15 +113,14 @@ 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)
+static void read_pages(struct readahead_control *rac, struct list_head *pages)
{
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 +129,23 @@ 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 we were called due to a conflicting page, skip over it */
+ rac->_index++;
}
/*
@@ -165,9 +164,11 @@ void __do_page_cache_readahead(struct address_space *mapping,
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,
+ ._index = index,
._nr_pages = 0,
};
unsigned long i;
@@ -184,6 +185,8 @@ 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)) {
/*
@@ -191,15 +194,22 @@ 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);
continue;
}
page = __page_cache_alloc(gfp_mask);
if (!page)
break;
- page->index = index + i;
- list_add(&page->lru, &page_pool);
+ if (use_list) {
+ 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);
+ continue;
+ }
if (i == nr_to_read - lookahead_size)
SetPageReadahead(page);
rac._nr_pages++;
@@ -210,7 +220,7 @@ 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);
}
/*
--
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 ` Matthew Wilcox [this message]
2020-02-21 3:19 ` [PATCH v7 09/24] mm: Put readahead pages in cache earlier 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 ` [PATCH v7 12/24] mm: Add page_cache_readahead_unbounded Matthew Wilcox
2020-02-24 21:53 ` [Cluster-devel] " 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=20200219210103.32400-10-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).