All of lore.kernel.org
 help / color / mirror / Atom feed
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, bfoster@redhat.com,
	Jens Axboe <axboe@kernel.dk>
Subject: [PATCH 09/12] mm/filemap: drop uncached pages when writeback completes
Date: Tue,  3 Dec 2024 08:31:45 -0700	[thread overview]
Message-ID: <20241203153232.92224-11-axboe@kernel.dk> (raw)
In-Reply-To: <20241203153232.92224-2-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 139d1db79ff8..eb6a8d39f9d0 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1599,6 +1599,27 @@ 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.
@@ -1609,6 +1630,8 @@ 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);
 
 	/*
@@ -1630,9 +1653,14 @@ void folio_end_writeback(struct folio *folio)
 	 * reused before the folio_wake_bit().
 	 */
 	folio_get(folio);
+	if (!folio_test_dirty(folio))
+		folio_uncached = folio_test_clear_uncached(folio);
 	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


  parent reply	other threads:[~2024-12-03 15:32 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-12-03 15:31 [PATCHSET v6 0/12] Uncached buffered IO Jens Axboe
2024-12-03 15:31 ` [PATCH 01/12] mm/filemap: change filemap_create_folio() to take a struct kiocb Jens Axboe
2024-12-10 11:13   ` Christoph Hellwig
2024-12-12 15:49     ` Jens Axboe
2024-12-03 15:31 ` [PATCH 02/12] mm/readahead: add folio allocation helper Jens Axboe
2024-12-03 15:31 ` [PATCH 03/12] mm: add PG_uncached page flag Jens Axboe
2024-12-03 15:31 ` [PATCH 04/12] mm/readahead: add readahead_control->uncached member Jens Axboe
2024-12-03 15:31 ` [PATCH 05/12] mm/filemap: use page_cache_sync_ra() to kick off read-ahead Jens Axboe
2024-12-10 11:15   ` Christoph Hellwig
2024-12-03 15:31 ` [PATCH 06/12] mm/truncate: add folio_unmap_invalidate() helper Jens Axboe
2024-12-10 11:21   ` Christoph Hellwig
2024-12-12 20:19     ` Jens Axboe
2024-12-03 15:31 ` [PATCH 07/12] fs: add RWF_UNCACHED iocb and FOP_UNCACHED file_operations flag Jens Axboe
2024-12-06 17:35   ` Darrick J. Wong
2024-12-10 11:22   ` Christoph Hellwig
2024-12-12 19:42     ` Jens Axboe
2024-12-03 15:31 ` [PATCH 08/12] mm/filemap: add read support for RWF_UNCACHED Jens Axboe
2024-12-03 15:31 ` Jens Axboe [this message]
2024-12-03 15:31 ` [PATCH 10/12] mm/filemap: add filemap_fdatawrite_range_kick() helper Jens Axboe
2024-12-03 15:31 ` [PATCH 11/12] mm/filemap: make buffered writes work with RWF_UNCACHED Jens Axboe
2024-12-06 17:17   ` Darrick J. Wong
2024-12-06 18:22     ` Jens Axboe
2024-12-10 11:31       ` Christoph Hellwig
2024-12-12 15:51         ` Jens Axboe
2024-12-03 15:31 ` [PATCH 12/12] mm: add FGP_UNCACHED folio creation flag Jens Axboe
2024-12-03 18:23 ` [PATCHSET v6 0/12] Uncached buffered IO Christoph Lameter (Ampere)
2024-12-03 21:06   ` Jens Axboe
2024-12-03 22:16     ` Christoph Lameter (Ampere)
2024-12-03 22:41       ` Jens Axboe
2024-12-04  5:52         ` Darrick J. Wong
2024-12-04 16:36           ` Jens Axboe
2024-12-10 11:11           ` Christoph Hellwig
2024-12-12 15:48             ` Jens Axboe
2024-12-12 16:59               ` Christoph Lameter (Ampere)
2024-12-12 19:14                 ` Jens Axboe
2024-12-12 19:35                   ` Matthew Wilcox
2024-12-12 19:36                     ` Jens Axboe
2024-12-12 20:06                     ` Christoph Lameter (Ampere)
2024-12-13  5:04                     ` Johannes Weiner
2024-12-13 14:49                       ` Jens Axboe
2024-12-06 17:37 ` Darrick J. Wong
2024-12-10  9:48 ` Bharata B Rao
2024-12-12 15:46   ` 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=20241203153232.92224-11-axboe@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=bfoster@redhat.com \
    --cc=clm@meta.com \
    --cc=hannes@cmpxchg.org \
    --cc=kirill@shutemov.name \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.