From: Jens Axboe <axboe@kernel.dk>
To: linux-mm@kvack.org, linux-fsdevel@vger.kernel.org
Cc: hannes@cmpxchg.org, clm@meta.com, linux-kernel@vger.kernel.org,
willy@infradead.org, kirill@shutemov.name,
linux-btrfs@vger.kernel.org, linux-ext4@vger.kernel.org,
linux-xfs@vger.kernel.org, Jens Axboe <axboe@kernel.dk>
Subject: [PATCH 09/16] mm/filemap: drop uncached pages when writeback completes
Date: Mon, 11 Nov 2024 16:37:36 -0700 [thread overview]
Message-ID: <20241111234842.2024180-10-axboe@kernel.dk> (raw)
In-Reply-To: <20241111234842.2024180-1-axboe@kernel.dk>
If the folio is marked as uncached, drop pages when writeback completes.
Intended to be used with RWF_UNCACHED, to avoid needing sync writes for
uncached IO.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
mm/filemap.c | 28 ++++++++++++++++++++++++++++
1 file changed, 28 insertions(+)
diff --git a/mm/filemap.c b/mm/filemap.c
index 3d0614ea5f59..40debe742abe 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1600,6 +1600,27 @@ int folio_wait_private_2_killable(struct folio *folio)
}
EXPORT_SYMBOL(folio_wait_private_2_killable);
+/*
+ * If folio was marked as uncached, then pages should be dropped when writeback
+ * completes. Do that now. If we fail, it's likely because of a big folio -
+ * just reset uncached for that case and latter completions should invalidate.
+ */
+static void folio_end_uncached(struct folio *folio)
+{
+ /*
+ * Hitting !in_task() should not happen off RWF_UNCACHED writeback, but
+ * can happen if normal writeback just happens to find dirty folios
+ * that were created as part of uncached writeback, and that writeback
+ * would otherwise not need non-IRQ handling. Just skip the
+ * invalidation in that case.
+ */
+ if (in_task() && folio_trylock(folio)) {
+ if (folio->mapping)
+ folio_unmap_invalidate(folio->mapping, folio, 0);
+ folio_unlock(folio);
+ }
+}
+
/**
* folio_end_writeback - End writeback against a folio.
* @folio: The folio.
@@ -1610,6 +1631,8 @@ EXPORT_SYMBOL(folio_wait_private_2_killable);
*/
void folio_end_writeback(struct folio *folio)
{
+ bool folio_uncached = false;
+
VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio);
/*
@@ -1631,9 +1654,14 @@ void folio_end_writeback(struct folio *folio)
* reused before the folio_wake_bit().
*/
folio_get(folio);
+ if (folio_test_uncached(folio) && folio_test_clear_uncached(folio))
+ folio_uncached = true;
if (__folio_end_writeback(folio))
folio_wake_bit(folio, PG_writeback);
acct_reclaim_writeback(folio);
+
+ if (folio_uncached)
+ folio_end_uncached(folio);
folio_put(folio);
}
EXPORT_SYMBOL(folio_end_writeback);
--
2.45.2
next prev parent reply other threads:[~2024-11-11 23:49 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-11 23:37 [PATCHSET v3 0/16] Uncached buffered IO Jens Axboe
2024-11-11 23:37 ` [PATCH 01/16] mm/filemap: change filemap_create_folio() to take a struct kiocb Jens Axboe
2024-11-11 23:37 ` [PATCH 02/16] mm/readahead: add folio allocation helper Jens Axboe
2024-11-11 23:37 ` [PATCH 03/16] mm: add PG_uncached page flag Jens Axboe
2024-11-12 9:12 ` Kirill A. Shutemov
2024-11-12 14:07 ` Jens Axboe
2024-11-11 23:37 ` [PATCH 04/16] mm/readahead: add readahead_control->uncached member Jens Axboe
2024-11-11 23:37 ` [PATCH 05/16] mm/filemap: use page_cache_sync_ra() to kick off read-ahead Jens Axboe
2024-11-11 23:37 ` [PATCH 06/16] mm/truncate: add folio_unmap_invalidate() helper Jens Axboe
2024-11-11 23:37 ` [PATCH 07/16] fs: add RWF_UNCACHED iocb and FOP_UNCACHED file_operations flag Jens Axboe
2024-11-11 23:37 ` [PATCH 08/16] mm/filemap: add read support for RWF_UNCACHED Jens Axboe
2024-11-11 23:37 ` Jens Axboe [this message]
2024-11-12 9:31 ` [PATCH 09/16] mm/filemap: drop uncached pages when writeback completes Kirill A. Shutemov
2024-11-12 14:09 ` Jens Axboe
2024-11-11 23:37 ` [PATCH 10/16] mm/filemap: make buffered writes work with RWF_UNCACHED Jens Axboe
2024-11-12 0:57 ` Dave Chinner
2024-11-12 1:27 ` Jens Axboe
2024-11-12 8:02 ` Dave Chinner
2024-11-12 9:50 ` Kirill A. Shutemov
2024-11-12 13:36 ` Dave Chinner
2024-11-12 14:51 ` Jens Axboe
2024-11-11 23:37 ` [PATCH 11/16] mm: add FGP_UNCACHED folio creation flag Jens Axboe
2024-11-11 23:37 ` [PATCH 12/16] ext4: add RWF_UNCACHED write support Jens Axboe
2024-11-12 16:36 ` Brian Foster
2024-11-12 17:13 ` Jens Axboe
2024-11-12 18:11 ` Brian Foster
2024-11-12 18:47 ` Jens Axboe
2024-11-11 23:37 ` [PATCH 13/16] iomap: make buffered writes work with RWF_UNCACHED Jens Axboe
2024-11-12 1:01 ` Darrick J. Wong
2024-11-12 1:30 ` Jens Axboe
2024-11-12 16:37 ` Brian Foster
2024-11-12 17:16 ` Jens Axboe
2024-11-12 18:15 ` Brian Foster
2024-11-11 23:37 ` [PATCH 14/16] xfs: punt uncached write completions to the completion wq Jens Axboe
2024-11-11 23:37 ` [PATCH 15/16] xfs: flag as supporting FOP_UNCACHED Jens Axboe
2024-11-11 23:37 ` [PATCH 16/16] btrfs: add support for uncached writes Jens Axboe
2024-11-12 1:31 ` [PATCHSET v3 0/16] Uncached buffered IO Jens Axboe
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=20241111234842.2024180-10-axboe@kernel.dk \
--to=axboe@kernel.dk \
--cc=clm@meta.com \
--cc=hannes@cmpxchg.org \
--cc=kirill@shutemov.name \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-xfs@vger.kernel.org \
--cc=willy@infradead.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).