From: Ojaswin Mujoo <ojaswin@linux.ibm.com>
To: Christian Brauner <brauner@kernel.org>, linux-fsdevel@vger.kernel.org
Cc: "Darrick J . Wong" <djwong@kernel.org>,
Carlos Maiolino <cem@kernel.org>,
Alexander Viro <viro@zeniv.linux.org.uk>, Jan Kara <jack@suse.cz>,
Matthew Wilcox <willy@infradead.org>,
Andrew Morton <akpm@linux-foundation.org>,
Ritesh Harjani <ritesh.list@gmail.com>,
Zhang Yi <yi.zhang@huawei.com>, Christoph Hellwig <hch@lst.de>,
Dave Chinner <dchinner@redhat.com>,
Daniel Gomez <da.gomez@kernel.org>,
Pankaj Raghav <pankaj.raghav@linux.dev>,
Theodore Tso <tytso@mit.edu>,
linux-xfs@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, Andres Freund <andres@anarazel.de>
Subject: [RFC PATCH v4 09/12] fs: Introduce RWF_NOSERIAL flag to indicate parallel reads/writes
Date: Mon, 28 Sep 2026 17:33:10 +0530 [thread overview]
Message-ID: <c097ec4d23324ed223fa29bdb43f64d4dabeb3ff.1790596383.git.ojaswin@linux.ibm.com> (raw)
In-Reply-To: <cover.1790596383.git.ojaswin@linux.ibm.com>
Introduce RWF_NOSERIAL flag to indicate that the application is
okay with its reads and writes going in parallel to other read/writes.
This flag will allow writes and read to go in parallel (for eg, under a
shared lock) increasing performance at the cost of losing the (loosely
implemented) POSIX guarantees wrt to R/W serialization that various
filesystems provide.
In this patch we just introduce the flag and in upcoming patches we will
use it to implement parallel writes to increase performance of
RWF_WRITETHROUGH
Co-developed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Signed-off-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
---
include/linux/fs.h | 10 +++++++++-
include/uapi/linux/fs.h | 6 +++++-
tools/include/uapi/linux/fs.h | 5 ++++-
3 files changed, 18 insertions(+), 3 deletions(-)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index cbaa65e05d9e..6f84bb41f84a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -345,6 +345,7 @@ struct readahead_control;
#define IOCB_DONTCACHE (__force int) RWF_DONTCACHE
#define IOCB_NOSIGNAL (__force int) RWF_NOSIGNAL
#define IOCB_WRITETHROUGH (__force int) RWF_WRITETHROUGH
+#define IOCB_NOSERIAL (__force int) RWF_NOSERIAL
/* non-RWF related bits - start at 16 */
#define IOCB_EVENTFD (1 << 16)
@@ -375,7 +376,8 @@ struct readahead_control;
{ IOCB_NOIO, "NOIO" }, \
{ IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \
{ IOCB_AIO_RW, "AIO_RW" }, \
- { IOCB_HAS_METADATA, "AIO_HAS_METADATA" }
+ { IOCB_HAS_METADATA, "AIO_HAS_METADATA" }, \
+ { IOCB_NOSERIAL, "IOCB_NOSERIAL" }
struct kiocb {
struct file *ki_filp;
@@ -3499,6 +3501,12 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags,
ki->ki_flags &= ~IOCB_APPEND;
}
+ /*
+ * Currently, only writethrough supports noserial IO.
+ */
+ if ((flags & RWF_NOSERIAL) && !(flags & RWF_WRITETHROUGH))
+ return -EOPNOTSUPP;
+
ki->ki_flags |= kiocb_flags;
return 0;
}
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 67d8987b343d..b2ad2d8548ac 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -454,10 +454,14 @@ typedef int __bitwise __kernel_rwf_t;
/* buffered IO that is asynchronously written through to disk after write */
#define RWF_WRITETHROUGH ((__force __kernel_rwf_t)0x00000200)
+/* buffered IO writes that are non sequential because they use a shared lock */
+#define RWF_NOSERIAL ((__force __kernel_rwf_t)0x00000400)
+
/* mask of flags supported by the kernel */
#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC |\
- RWF_DONTCACHE | RWF_NOSIGNAL | RWF_WRITETHROUGH)
+ RWF_DONTCACHE | RWF_NOSIGNAL | RWF_WRITETHROUGH |\
+ RWF_NOSERIAL)
#define PROCFS_IOCTL_MAGIC 'f'
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index 63ef6b126b8b..c7a1a1d238f0 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -347,10 +347,13 @@ typedef int __bitwise __kernel_rwf_t;
/* buffered IO that is asynchronously written through to disk after write */
#define RWF_WRITETHROUGH ((__force __kernel_rwf_t)0x00000200)
+/* buffered IO writes that are non sequential because they use a shared lock */
+#define RWF_NOSERIAL ((__force __kernel_rwf_t)0x00000400)
+
/* mask of flags supported by the kernel */
#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC |\
- RWF_DONTCACHE | RWF_WRITETHROUGH)
+ RWF_DONTCACHE | RWF_WRITETHROUGH | RWF_NOSERIAL)
#define PROCFS_IOCTL_MAGIC 'f'
--
2.55.0
next prev parent reply other threads:[~2026-09-28 12:04 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-28 12:03 [RFC PATCH v4 00/13] Add RWF_WRITETHROUGH support to iomap & xfs Ojaswin Mujoo
2026-09-28 12:03 ` [RFC PATCH v4 01/12] xfs: reexpand iter to original count when upgrading to excl ILOCK Ojaswin Mujoo
2026-09-28 12:03 ` [RFC PATCH v4 02/12] fs: Add counter to track inflight writes that need stable pages Ojaswin Mujoo
2026-09-28 12:03 ` [RFC PATCH v4 03/12] mm: Refactor folio_clear_dirty_for_io() Ojaswin Mujoo
2026-09-28 12:03 ` [RFC PATCH v4 04/12] iomap: Add helper to revert iomap iter Ojaswin Mujoo
2026-09-28 12:03 ` [RFC PATCH v4 05/12] iomap: Add initial support for buffered RWF_WRITETHROUGH Ojaswin Mujoo
2026-09-28 12:03 ` [RFC PATCH v4 06/12] xfs: Add RWF_WRITETHROUGH support to xfs Ojaswin Mujoo
2026-09-28 12:03 ` [RFC PATCH v4 07/12] iomap: Add aio support to RWF_WRITETHROUGH Ojaswin Mujoo
2026-09-28 12:03 ` [RFC PATCH v4 08/12] iomap: Add DSYNC " Ojaswin Mujoo
2026-09-28 12:03 ` Ojaswin Mujoo [this message]
2026-09-28 12:03 ` [RFC PATCH v4 10/12] xfs: Implement RWF_NOSERIAL to parallelize RWF_WRITETHROUGH writes Ojaswin Mujoo
2026-09-28 12:03 ` [RFC PATCH v4 11/12] iomap: Avoid folio dirtying in case of RWF_WRITETHROUGH Ojaswin Mujoo
2026-09-28 12:03 ` [RFC PATCH v4 12/12] iomap: Handle deadlock due to repeating folios in RWF_WRITETHROUGH Ojaswin Mujoo
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=c097ec4d23324ed223fa29bdb43f64d4dabeb3ff.1790596383.git.ojaswin@linux.ibm.com \
--to=ojaswin@linux.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=andres@anarazel.de \
--cc=brauner@kernel.org \
--cc=cem@kernel.org \
--cc=da.gomez@kernel.org \
--cc=dchinner@redhat.com \
--cc=djwong@kernel.org \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-xfs@vger.kernel.org \
--cc=pankaj.raghav@linux.dev \
--cc=ritesh.list@gmail.com \
--cc=tytso@mit.edu \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@infradead.org \
--cc=yi.zhang@huawei.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
all inboxes | Powered by JetHome®