public inbox for [email protected]
 help / color / mirror / Atom feed
From: Pavel Begunkov <[email protected]>
To: Keith Busch <[email protected]>,
	[email protected], [email protected],
	[email protected], [email protected]
Cc: [email protected], Keith Busch <[email protected]>
Subject: Re: [PATCHv2 3/6] io_uring: add support for kernel registered bvecs
Date: Thu, 13 Feb 2025 01:33:21 +0000	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

On 2/11/25 00:56, Keith Busch wrote:
> From: Keith Busch <[email protected]>
> 
> Provide an interface for the kernel to leverage the existing
> pre-registered buffers that io_uring provides. User space can reference
> these later to achieve zero-copy IO.
> 
> User space must register an empty fixed buffer table with io_uring in
> order for the kernel to make use of it.
> 
> Signed-off-by: Keith Busch <[email protected]>
> ---
>   include/linux/io_uring.h       |   1 +
>   include/linux/io_uring_types.h |   4 ++
>   io_uring/rsrc.c                | 100 +++++++++++++++++++++++++++++++--
>   io_uring/rsrc.h                |   1 +
>   4 files changed, 100 insertions(+), 6 deletions(-)
> 
> diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
> index 85fe4e6b275c7..b5637a2aae340 100644
> --- a/include/linux/io_uring.h
> +++ b/include/linux/io_uring.h
> @@ -5,6 +5,7 @@
>   #include <linux/sched.h>
>   #include <linux/xarray.h>
>   #include <uapi/linux/io_uring.h>
> +#include <linux/blk-mq.h>
>   
>   #if defined(CONFIG_IO_URING)
>   void __io_uring_cancel(bool cancel_all);
> diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
> index e2fef264ff8b8..99aac2d52fbae 100644
> --- a/include/linux/io_uring_types.h
> +++ b/include/linux/io_uring_types.h
> @@ -693,4 +693,8 @@ static inline bool io_ctx_cqe32(struct io_ring_ctx *ctx)
>   	return ctx->flags & IORING_SETUP_CQE32;
>   }
>   
> +int io_buffer_register_bvec(struct io_ring_ctx *ctx, struct request *rq,
> +			    void (*release)(void *), unsigned int index);
> +void io_buffer_unregister_bvec(struct io_ring_ctx *ctx, unsigned int tag);
> +
>   #endif
> diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
> index 30f08cf13ef60..14efec8587888 100644
> --- a/io_uring/rsrc.c
> +++ b/io_uring/rsrc.c
> @@ -110,8 +110,9 @@ static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_rsrc_node *node)
>   
>   		if (!refcount_dec_and_test(&imu->refs))
>   			return;
> -		for (i = 0; i < imu->nr_bvecs; i++)
> -			unpin_user_page(imu->bvec[i].bv_page);
> +		if (node->type == IORING_RSRC_BUFFER)
> +			for (i = 0; i < imu->nr_bvecs; i++)
> +				unpin_user_page(imu->bvec[i].bv_page);
>   		if (imu->acct_pages)
>   			io_unaccount_mem(ctx, imu->acct_pages);
>   		kvfree(imu);
> @@ -240,6 +241,13 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
>   		struct io_rsrc_node *node;
>   		u64 tag = 0;
>   
> +		i = array_index_nospec(up->offset + done, ctx->buf_table.nr);
> +		node = io_rsrc_node_lookup(&ctx->buf_table, i);
> +		if (node && node->type != IORING_RSRC_BUFFER) {

Please drop the special rule. It's handled, so if the user wants
to do it, it can be allowed in a generic way.

> +			err = -EBUSY;
> +			break;
> +		}
> +
...
> +int io_buffer_register_bvec(struct io_ring_ctx *ctx, struct request *rq,
> +			    void (*release)(void *), unsigned int index)
> +{
> +	struct io_rsrc_data *data = &ctx->buf_table;
> +	struct req_iterator rq_iter;
> +	struct io_mapped_ubuf *imu;
> +	struct io_rsrc_node *node;
> +	struct bio_vec bv;
> +	u16 nr_bvecs;
> +	int i = 0;
> +
> +	lockdep_assert_held(&ctx->uring_lock);
> +
> +	if (!data->nr)
> +		return -EINVAL;
> +	if (index >= data->nr)
> +		return -EINVAL;

array_index_nospec

> +
> +	node = data->nodes[index];
> +	if (node)
> +		return -EBUSY;
...> +void io_buffer_unregister_bvec(struct io_ring_ctx *ctx, unsigned int index)
> +{
> +	struct io_rsrc_data *data = &ctx->buf_table;
> +	struct io_rsrc_node *node;
> +
> +	lockdep_assert_held(&ctx->uring_lock);
> +
> +	if (!data->nr)
> +		return;
> +	if (index >= data->nr)
> +		return;

array_index_nospec

> +
> +	node = data->nodes[index];
> +	if (!node || !node->buf)

How can node->buf be NULL?

> +		return;
> +	if (node->type != IORING_RSRC_KBUFFER)
> +		return;
> +	io_reset_rsrc_node(ctx, data, index);
> +}
> +EXPORT_SYMBOL_GPL(io_buffer_unregister_bvec);
...> diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
> index a3826ab84e666..8147dfc26f737 100644
> --- a/io_uring/rsrc.h
> +++ b/io_uring/rsrc.h
> @@ -13,6 +13,7 @@
>   enum {
>   	IORING_RSRC_FILE		= 0,
>   	IORING_RSRC_BUFFER		= 1,
> +	IORING_RSRC_KBUFFER		= 2,

nit: you don't even need it, just check for presence of the
callback in io_buffer_unmap()

-- 
Pavel Begunkov


  reply	other threads:[~2025-02-13  1:32 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-02-11  0:56 [PATCHv2 0/6] ublk zero-copy support Keith Busch
2025-02-11  0:56 ` [PATCHv2 1/6] io_uring: use node for import Keith Busch
2025-02-11  0:56 ` [PATCHv2 2/6] io_uring: create resource release callback Keith Busch
2025-02-13  1:31   ` Pavel Begunkov
2025-02-13  1:58     ` Keith Busch
2025-02-13 13:06       ` Pavel Begunkov
2025-02-11  0:56 ` [PATCHv2 3/6] io_uring: add support for kernel registered bvecs Keith Busch
2025-02-13  1:33   ` Pavel Begunkov [this message]
2025-02-14  3:30   ` Ming Lei
2025-02-14 15:26     ` Keith Busch
2025-02-15  1:34       ` Ming Lei
2025-02-18 20:34         ` Keith Busch
2025-02-11  0:56 ` [PATCHv2 4/6] ublk: zc register/unregister bvec Keith Busch
2025-02-12  2:49   ` Ming Lei
2025-02-12  4:11     ` Keith Busch
2025-02-12  9:24       ` Ming Lei
2025-02-12 14:59         ` Keith Busch
2025-02-13  2:12   ` Pavel Begunkov
2025-02-11  0:56 ` [PATCHv2 5/6] io_uring: add abstraction for buf_table rsrc data Keith Busch
2025-02-11  0:56 ` [PATCHv2 6/6] io_uring: cache nodes and mapped buffers Keith Busch
2025-02-11 16:47   ` Keith Busch
2025-02-12  2:29 ` [PATCHv2 0/6] ublk zero-copy support Ming Lei
2025-02-12 15:28   ` Keith Busch
2025-02-12 16:06     ` Pavel Begunkov
2025-02-13  1:52       ` Ming Lei
2025-02-13 15:12 ` lizetao
2025-02-13 16:06   ` Keith Busch
2025-02-14  3:39     ` lizetao
2025-02-14  2:41   ` Ming Lei
2025-02-14  4:21     ` lizetao

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 \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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