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 12/12] mm: add FGP_UNCACHED folio creation flag
Date: Tue, 3 Dec 2024 08:31:48 -0700 [thread overview]
Message-ID: <20241203153232.92224-14-axboe@kernel.dk> (raw)
In-Reply-To: <20241203153232.92224-2-axboe@kernel.dk>
Callers can pass this in for uncached folio creation, in which case if
a folio is newly created it gets marked as uncached. If a folio exists
for this index and lookup succeeds, then it will not get marked as
uncached. If an !uncached lookup finds a cached folio, clear the flag.
For that case, there are competeting uncached and cached users of the
folio, and it should not get pruned.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
include/linux/pagemap.h | 2 ++
mm/filemap.c | 5 +++++
2 files changed, 7 insertions(+)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e49587c40157..374872acbe1d 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -721,6 +721,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
* * %FGP_NOFS - __GFP_FS will get cleared in gfp.
* * %FGP_NOWAIT - Don't block on the folio lock.
* * %FGP_STABLE - Wait for the folio to be stable (finished writeback)
+ * * %FGP_UNCACHED - Uncached buffered IO
* * %FGP_WRITEBEGIN - The flags to use in a filesystem write_begin()
* implementation.
*/
@@ -734,6 +735,7 @@ typedef unsigned int __bitwise fgf_t;
#define FGP_NOWAIT ((__force fgf_t)0x00000020)
#define FGP_FOR_MMAP ((__force fgf_t)0x00000040)
#define FGP_STABLE ((__force fgf_t)0x00000080)
+#define FGP_UNCACHED ((__force fgf_t)0x00000100)
#define FGF_GET_ORDER(fgf) (((__force unsigned)fgf) >> 26) /* top 6 bits */
#define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE)
diff --git a/mm/filemap.c b/mm/filemap.c
index 00f3c6c58629..a03a9b9127b8 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2001,6 +2001,8 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
/* Init accessed so avoid atomic mark_page_accessed later */
if (fgp_flags & FGP_ACCESSED)
__folio_set_referenced(folio);
+ if (fgp_flags & FGP_UNCACHED)
+ __folio_set_uncached(folio);
err = filemap_add_folio(mapping, folio, index, gfp);
if (!err)
@@ -2023,6 +2025,9 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
if (!folio)
return ERR_PTR(-ENOENT);
+ /* not an uncached lookup, clear uncached if set */
+ if (folio_test_uncached(folio) && !(fgp_flags & FGP_UNCACHED))
+ folio_clear_uncached(folio);
return folio;
}
EXPORT_SYMBOL(__filemap_get_folio);
--
2.45.2
next prev parent reply other threads:[~2024-12-03 15:33 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 ` [PATCH 09/12] mm/filemap: drop uncached pages when writeback completes Jens Axboe
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 ` Jens Axboe [this message]
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=20241203153232.92224-14-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox