Linux filesystem development
 help / color / mirror / Atom feed
From: Jeff Layton <jlayton@kernel.org>
To: Joanne Koong <joannelkoong@gmail.com>, miklos@szeredi.hu
Cc: bernd@bsbernd.com, axboe@kernel.dk, linux-fsdevel@vger.kernel.org
Subject: Re: [PATCH v2 12/14] fuse: add pinned payload buffers capability for io-uring buffer rings
Date: Thu, 30 Apr 2026 12:29:24 +0100	[thread overview]
Message-ID: <f27f236a66a58c93c413a5c04d76b646ff7860e5.camel@kernel.org> (raw)
In-Reply-To: <20260402162840.2989717-13-joannelkoong@gmail.com>

On Thu, 2026-04-02 at 09:28 -0700, Joanne Koong wrote:
> Extend the buffer ring pinning capability to payload buffers via the
> FUSE_URING_PINNED_BUFFERS flag. When set alongside FUSE_URING_BUFRING,
> the kernel pins and vmaps the payload buffer region during queue setup.
> 
> With pinned payloads, the kernel uses direct memcpy for all payload
> buffer copies, avoiding the per-request overhead of pinning/unpinning
> user pages and translating virtual addresses. This is particularly
> beneficial for large payload copies.
> 
> As with pinned headers, buffers must be page-aligned. Pinned pages are
> accounted against RLIMIT_MEMLOCK (bypassed with CAP_IPC_LOCK) and
> unpinned in process context during connection abort.
> 
> In benchmarks using passthrough_hp on a high-performance NVMe-backed
> system, pinned headers and pinned payload buffers showed around a 10%
> throughput improvement for direct randreads (~2150 MiB/s to ~2400
> MiB/s), a 4% improvement for direct sequential reads (~2510 MiB/s to
> ~2620 MiB/s), a 8% improvement for buffered randreads (~2100 MiB/s to
> ~2280 MiB/s), and a 6% improvement for buffered sequential reads (~2500
> MiB/s to ~2670 MiB/s).
> 
> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> ---
>  fs/fuse/dev_uring.c       | 54 +++++++++++++++++++++++++++++++++------
>  fs/fuse/dev_uring_i.h     |  4 +++
>  include/uapi/linux/fuse.h |  2 ++
>  3 files changed, 52 insertions(+), 8 deletions(-)
> 
> diff --git a/fs/fuse/dev_uring.c b/fs/fuse/dev_uring.c
> index 79736b02cf9f..06d3d8dc1c82 100644
> --- a/fs/fuse/dev_uring.c
> +++ b/fs/fuse/dev_uring.c
> @@ -52,6 +52,11 @@ static inline bool bufring_pinned_headers(struct fuse_ring_queue *queue)
>  	return queue->bufring->use_pinned_headers;
>  }
>  
> +static inline bool bufring_pinned_buffers(struct fuse_ring_queue *queue)
> +{
> +	return queue->bufring->use_pinned_buffers;
> +}
> +
>  static void uring_cmd_set_ring_ent(struct io_uring_cmd *cmd,
>  				   struct fuse_ring_ent *ring_ent)
>  {
> @@ -235,6 +240,11 @@ static void fuse_uring_bufring_unpin(struct fuse_ring_queue *queue)
>  		fuse_bufring_unpin_mem(&br->pinned_headers);
>  		br->use_pinned_headers = false;
>  	}
> +
> +	if (bufring_pinned_buffers(queue)) {
> +		fuse_bufring_unpin_mem(&br->pinned_bufs);
> +		br->use_pinned_buffers = false;
> +	}
>  }
>  
>  void fuse_uring_destruct(struct fuse_conn *fc)
> @@ -474,6 +484,7 @@ static int fuse_uring_bufring_setup(struct io_uring_cmd *cmd,
>  	unsigned int buf_size = READ_ONCE(cmd_req->init.buf_size);
>  	struct iovec iov[FUSE_URING_IOV_SEGS];
>  	bool pinned_headers = init_flags & FUSE_URING_PINNED_HEADERS;
> +	bool pinned_bufs = init_flags & FUSE_URING_PINNED_BUFFERS;
>  	void __user *payload, *headers;
>  	size_t headers_size, payload_size, ring_size;
>  	struct fuse_bufring *br;
> @@ -523,7 +534,22 @@ static int fuse_uring_bufring_setup(struct io_uring_cmd *cmd,
>  		br->headers = headers;
>  	}
>  
> -	payload_addr = (uintptr_t)payload;
> +	if (pinned_bufs) {
> +		err = fuse_bufring_pin_mem(&br->pinned_bufs, payload,
> +					   payload_size);
> +		if (err) {
> +			if (pinned_headers)
> +				fuse_bufring_unpin_mem(&br->pinned_headers);
> +			kfree(br);
> +			return err;
> +		}
> +		br->use_pinned_buffers = true;
> +	}
> +
> +	if (pinned_bufs)
> +		payload_addr = (uintptr_t)br->pinned_bufs.addr;
> +	else
> +		payload_addr = (uintptr_t)payload;
>  
>  	/* populate the ring buffer */
>  	for (i = 0; i < nr_bufs; i++, payload_addr += buf_size) {
> @@ -553,6 +579,7 @@ static bool queue_init_flags_consistent(struct fuse_ring_queue *queue,
>  {
>  	bool bufring = init_flags & FUSE_URING_BUFRING;
>  	bool pinned_headers = init_flags & FUSE_URING_PINNED_HEADERS;
> +	bool pinned_bufs = init_flags & FUSE_URING_PINNED_BUFFERS;
>  
>  	if (bufring_enabled(queue) != bufring)
>  		return false;
> @@ -560,7 +587,8 @@ static bool queue_init_flags_consistent(struct fuse_ring_queue *queue,
>  	if (!bufring)
>  		return true;
>  
> -	return bufring_pinned_headers(queue) == pinned_headers;
> +	return bufring_pinned_headers(queue) == pinned_headers &&
> +		bufring_pinned_buffers(queue) == pinned_bufs;
>  }
>  
>  static struct fuse_ring_queue *
> @@ -1011,13 +1039,15 @@ static int setup_fuse_copy_state(struct fuse_copy_state *cs,
>  				 struct fuse_ring_ent *ent, int dir,
>  				 struct iov_iter *iter)
>  {
> -	void __user *payload;
> +	void __user *payload = NULL;
> +	bool use_bufring = bufring_enabled(ent->queue);
> +	bool pinned_buffers = use_bufring && bufring_pinned_buffers(ent->queue);
>  	int err;
>  
> -	if (bufring_enabled(ent->queue))
> -		payload = (void __user *)ent->payload_buf.addr;
> -	else
> +	if (!use_bufring)
>  		payload = ent->payload;
> +	else if (!pinned_buffers)
> +		payload = (void __user *)ent->payload_buf.addr;
>  
>  	if (payload) {
>  		err = import_ubuf(dir, payload, ring->max_payload_sz, iter);
> @@ -1029,6 +1059,12 @@ static int setup_fuse_copy_state(struct fuse_copy_state *cs,
>  
>  	fuse_copy_init(cs, dir == ITER_DEST, iter);
>  
> +	if (pinned_buffers) {
> +		cs->is_kaddr = true;
> +		cs->kaddr = (void *)ent->payload_buf.addr;
> +		cs->len = ent->payload_buf.len;
> +	}
> +
>  	cs->is_uring = true;
>  	cs->req = req;
>  
> @@ -1608,11 +1644,13 @@ fuse_uring_create_ring_ent(struct io_uring_cmd *cmd,
>  static bool init_flags_valid(u64 init_flags)
>  {
>  	u64 valid_flags =
> -		FUSE_URING_BUFRING | FUSE_URING_PINNED_HEADERS;
> +		FUSE_URING_BUFRING | FUSE_URING_PINNED_HEADERS |
> +		FUSE_URING_PINNED_BUFFERS;
>  	bool bufring = init_flags & FUSE_URING_BUFRING;
>  	bool pinned_headers = init_flags & FUSE_URING_PINNED_HEADERS;
> +	bool pinned_buffers = init_flags & FUSE_URING_PINNED_BUFFERS;
>  
> -	if (pinned_headers && !bufring)
> +	if (!bufring && (pinned_headers || pinned_buffers))
>  		return false;
>  
>  	return !(init_flags & ~valid_flags);
> diff --git a/fs/fuse/dev_uring_i.h b/fs/fuse/dev_uring_i.h
> index 05c0f061a882..859ee4e6ba03 100644
> --- a/fs/fuse/dev_uring_i.h
> +++ b/fs/fuse/dev_uring_i.h
> @@ -57,6 +57,7 @@ struct fuse_bufring_pinned {
>  
>  struct fuse_bufring {
>  	bool use_pinned_headers: 1;
> +	bool use_pinned_buffers: 1;
>  	unsigned int queue_depth;
>  
>  	union {
> @@ -65,6 +66,9 @@ struct fuse_bufring {
>  		struct fuse_bufring_pinned pinned_headers;
>  	};
>  
> +	/* only used if the buffers are pinned */
> +	struct fuse_bufring_pinned pinned_bufs;
> +
>  	/* metadata tracking state of the bufring */
>  	unsigned int nbufs;
>  	unsigned int head;
> diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
> index e57244c03d42..51ecb66dd6eb 100644
> --- a/include/uapi/linux/fuse.h
> +++ b/include/uapi/linux/fuse.h
> @@ -245,6 +245,7 @@
>   *  - add FUSE_URING_BUFRING flag
>   *  - add fuse_uring_cmd_req init struct
>   *  - add FUSE_URING_PINNED_HEADERS flag
> + *  - add FUSE_URING_PINNED_BUFFERS flag
>   */
>  
>  #ifndef _LINUX_FUSE_H
> @@ -1308,6 +1309,7 @@ enum fuse_uring_cmd {
>  /* fuse_uring_cmd_req flags */
>  #define FUSE_URING_BUFRING		(1 << 0)
>  #define FUSE_URING_PINNED_HEADERS	(1 << 1)
> +#define FUSE_URING_PINNED_BUFFERS	(1 << 2)
>  
>  /**
>   * In the 80B command area of the SQE.

Reviewed-by: Jeff Layton <jlayton@kernel.org>

  reply	other threads:[~2026-04-30 11:29 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-02 16:28 [PATCH v2 00/14] fuse: add io-uring buffer rings and zero-copy Joanne Koong
2026-04-02 16:28 ` [PATCH v2 01/14] fuse: separate next request fetching from sending logic Joanne Koong
2026-04-29 11:52   ` Jeff Layton
2026-04-02 16:28 ` [PATCH v2 02/14] fuse: refactor io-uring header copying to ring Joanne Koong
2026-04-29 12:05   ` Jeff Layton
2026-04-02 16:28 ` [PATCH v2 03/14] fuse: refactor io-uring header copying from ring Joanne Koong
2026-04-29 12:06   ` Jeff Layton
2026-04-02 16:28 ` [PATCH v2 04/14] fuse: use enum types for header copying Joanne Koong
2026-04-30  8:04   ` Jeff Layton
2026-04-02 16:28 ` [PATCH v2 05/14] fuse: refactor setting up copy state for payload copying Joanne Koong
2026-04-30  8:06   ` Jeff Layton
2026-04-02 16:28 ` [PATCH v2 06/14] fuse: support buffer copying for kernel addresses Joanne Koong
2026-04-30  8:19   ` Jeff Layton
2026-04-02 16:28 ` [PATCH v2 07/14] fuse: use named constants for io-uring iovec indices Joanne Koong
2026-04-15  9:36   ` Bernd Schubert
2026-04-30  8:20   ` Jeff Layton
2026-04-02 16:28 ` [PATCH v2 08/14] fuse: move fuse_uring_abort() from header to dev_uring.c Joanne Koong
2026-04-15  9:40   ` Bernd Schubert
2026-04-30  8:21   ` Jeff Layton
2026-04-02 16:28 ` [PATCH v2 09/14] fuse: rearrange io-uring iovec and ent allocation logic Joanne Koong
2026-04-15  9:45   ` Bernd Schubert
2026-04-30  8:24   ` Jeff Layton
2026-04-02 16:28 ` [PATCH v2 10/14] fuse: add io-uring buffer rings Joanne Koong
2026-04-15  9:48   ` Bernd Schubert
2026-04-15 21:40     ` Joanne Koong
2026-04-30 11:08   ` Jeff Layton
2026-04-30 12:44     ` Joanne Koong
2026-05-05 22:47   ` Bernd Schubert
2026-04-02 16:28 ` [PATCH v2 11/14] fuse: add pinned headers capability for " Joanne Koong
2026-04-14 12:47   ` Bernd Schubert
2026-04-15  0:48     ` Joanne Koong
2026-05-05 22:51       ` Bernd Schubert
2026-04-30 11:22   ` Jeff Layton
2026-04-02 16:28 ` [PATCH v2 12/14] fuse: add pinned payload buffers " Joanne Koong
2026-04-30 11:29   ` Jeff Layton [this message]
2026-04-02 16:28 ` [PATCH v2 13/14] fuse: add zero-copy over io-uring Joanne Koong
2026-04-30 11:42   ` Jeff Layton
2026-04-30 12:35     ` Joanne Koong
2026-04-30 12:55       ` Jeff Layton
2026-05-05 22:55         ` Bernd Schubert
2026-04-30 12:56   ` Jeff Layton
2026-05-05 23:45   ` Bernd Schubert
2026-04-02 16:28 ` [PATCH v2 14/14] docs: fuse: add io-uring bufring and zero-copy documentation Joanne Koong
2026-04-14 21:05   ` Bernd Schubert
2026-04-15  1:10     ` Joanne Koong
2026-04-15 10:55       ` Bernd Schubert
2026-04-15 22:40         ` Joanne Koong
2026-04-30 12:57   ` Jeff Layton
2026-04-30 12:59 ` [PATCH v2 00/14] fuse: add io-uring buffer rings and zero-copy Jeff Layton

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=f27f236a66a58c93c413a5c04d76b646ff7860e5.camel@kernel.org \
    --to=jlayton@kernel.org \
    --cc=axboe@kernel.dk \
    --cc=bernd@bsbernd.com \
    --cc=joannelkoong@gmail.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=miklos@szeredi.hu \
    /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