From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
To: linux-fsdevel@vger.kernel.org, linux-mm@kvack.org
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: [PATCH 04/10] mm/truncate: Replace page_mapped() call in invalidate_inode_page()
Date: Mon, 14 Feb 2022 20:00:11 +0000 [thread overview]
Message-ID: <20220214200017.3150590-5-willy@infradead.org> (raw)
In-Reply-To: <20220214200017.3150590-1-willy@infradead.org>
folio_mapped() is expensive because it has to check each page's mapcount
field. A cheaper check is whether there are any extra references to
the page, other than the one we own and the ones held by the page cache.
The call to remove_mapping() will fail in any case if it cannot freeze
the refcount, but failing here avoids cycling the i_pages spinlock.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
mm/truncate.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/truncate.c b/mm/truncate.c
index b73c30c95cd0..d67fa8871b75 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -287,7 +287,7 @@ int invalidate_inode_page(struct page *page)
return 0;
if (folio_test_dirty(folio) || folio_test_writeback(folio))
return 0;
- if (page_mapped(page))
+ if (folio_ref_count(folio) > folio_nr_pages(folio) + 1)
return 0;
if (folio_has_private(folio) && !filemap_release_folio(folio, 0))
return 0;
--
2.34.1
next prev parent reply other threads:[~2022-02-14 20:00 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-14 20:00 [PATCH 00/10] Various fixes around invalidate_page() Matthew Wilcox (Oracle)
2022-02-14 20:00 ` [PATCH 01/10] splice: Use a folio in page_cache_pipe_buf_try_steal() Matthew Wilcox (Oracle)
2022-02-15 7:15 ` Christoph Hellwig
2022-02-15 8:32 ` Miaohe Lin
2022-02-14 20:00 ` [PATCH 02/10] mm/truncate: Inline invalidate_complete_page() into its one caller Matthew Wilcox (Oracle)
2022-02-14 23:09 ` John Hubbard
2022-02-14 23:32 ` Matthew Wilcox
2022-02-14 23:51 ` John Hubbard
2022-02-15 7:17 ` Christoph Hellwig
2022-02-15 7:45 ` Miaohe Lin
2022-02-15 20:09 ` Matthew Wilcox
2022-02-16 2:36 ` Miaohe Lin
2022-02-16 2:45 ` Miaohe Lin
2022-02-14 20:00 ` [PATCH 03/10] mm/truncate: Convert invalidate_inode_page() to use a folio Matthew Wilcox (Oracle)
2022-02-15 7:18 ` Christoph Hellwig
2022-02-15 8:32 ` Miaohe Lin
2022-02-14 20:00 ` Matthew Wilcox (Oracle) [this message]
2022-02-15 7:19 ` [PATCH 04/10] mm/truncate: Replace page_mapped() call in invalidate_inode_page() Christoph Hellwig
2022-02-15 20:12 ` Matthew Wilcox
2022-02-15 8:32 ` Miaohe Lin
2022-02-25 1:31 ` Matthew Wilcox
2022-02-25 3:27 ` Matthew Wilcox
2022-02-14 20:00 ` [PATCH 05/10] mm: Convert remove_mapping() to take a folio Matthew Wilcox (Oracle)
2022-02-15 7:21 ` Christoph Hellwig
2022-02-15 8:33 ` Miaohe Lin
2022-02-14 20:00 ` [PATCH 06/10] mm/truncate: Split invalidate_inode_page() into mapping_shrink_folio() Matthew Wilcox (Oracle)
2022-02-15 7:23 ` Christoph Hellwig
2022-02-15 9:37 ` Miaohe Lin
2022-02-14 20:00 ` [PATCH 07/10] mm/truncate: Convert __invalidate_mapping_pages() to use a folio Matthew Wilcox (Oracle)
2022-02-15 7:24 ` Christoph Hellwig
2022-02-15 9:37 ` Miaohe Lin
2022-02-14 20:00 ` [PATCH 08/10] mm: Turn deactivate_file_page() into deactivate_file_folio() Matthew Wilcox (Oracle)
2022-02-15 7:25 ` Christoph Hellwig
2022-02-15 8:26 ` Miaohe Lin
2022-02-15 20:33 ` Matthew Wilcox
2022-02-16 2:45 ` Miaohe Lin
2022-02-14 20:00 ` [PATCH 09/10] mm/truncate: Combine invalidate_mapping_pagevec() and __invalidate_mapping_pages() Matthew Wilcox (Oracle)
2022-02-15 7:26 ` Christoph Hellwig
2022-02-15 9:37 ` Miaohe Lin
2022-02-14 20:00 ` [PATCH 10/10] fs: Move many prototypes to pagemap.h Matthew Wilcox (Oracle)
2022-02-15 7:27 ` Christoph Hellwig
2022-02-15 9:38 ` Miaohe Lin
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=20220214200017.3150590-5-willy@infradead.org \
--to=willy@infradead.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-mm@kvack.org \
/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).