All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: io-uring@vger.kernel.org
Cc: asml.silence@gmail.com, Jens Axboe <axboe@kernel.dk>
Subject: [PATCH 12/16] io_uring: eliminate the need to track provided buffer ID separately
Date: Sun,  1 May 2022 14:56:49 -0600	[thread overview]
Message-ID: <20220501205653.15775-13-axboe@kernel.dk> (raw)
In-Reply-To: <20220501205653.15775-1-axboe@kernel.dk>

We have io_kiocb->buf_index which is used for either fixed buffers, or
for provided buffers. For the latter, it's used to hold the buffer group
ID for buffer selection. Post selection, req->kbuf->bid is used to get
the buffer ID.

Store the buffer ID, when selected, in req->buf_index. If we do end up
recycling the buffer, reset it back to the buffer group ID.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 23de92f5934f..ff3b803cf749 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -968,6 +968,11 @@ struct io_kiocb {
 	u8				opcode;
 	/* polled IO has completed */
 	u8				iopoll_completed;
+	/*
+	 * Can be either a fixed buffer index, or used with provided buffers.
+	 * For the latter, before issue it points to the buffer group ID,
+	 * and after selection it points to the buffer ID itself.
+	 */
 	u16				buf_index;
 	unsigned int			flags;
 
@@ -1562,14 +1567,11 @@ static inline void io_req_set_rsrc_node(struct io_kiocb *req,
 
 static unsigned int __io_put_kbuf(struct io_kiocb *req, struct list_head *list)
 {
-	struct io_buffer *kbuf = req->kbuf;
-	unsigned int cflags;
-
-	cflags = IORING_CQE_F_BUFFER | (kbuf->bid << IORING_CQE_BUFFER_SHIFT);
 	req->flags &= ~REQ_F_BUFFER_SELECTED;
-	list_add(&kbuf->list, list);
+	list_add(&req->kbuf->list, list);
 	req->kbuf = NULL;
-	return cflags;
+
+	return IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
 }
 
 static inline unsigned int io_put_kbuf_comp(struct io_kiocb *req)
@@ -1643,6 +1645,7 @@ static void io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
 	bl = io_buffer_get_list(ctx, buf->bgid);
 	list_add(&buf->list, &bl->buf_list);
 	req->flags &= ~REQ_F_BUFFER_SELECTED;
+	req->buf_index = buf->bgid;
 	req->kbuf = NULL;
 
 	io_ring_submit_unlock(ctx, issue_flags);
@@ -3582,6 +3585,7 @@ static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len,
 		*len = kbuf->len;
 	req->flags |= REQ_F_BUFFER_SELECTED;
 	req->kbuf = kbuf;
+	req->buf_index = kbuf->bid;
 	io_ring_submit_unlock(req->ctx, issue_flags);
 	return u64_to_user_ptr(kbuf->addr);
 }
-- 
2.35.1


  parent reply	other threads:[~2022-05-01 20:57 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-05-01 20:56 [PATCHSET v4 0/16] Add support for ring mapped provided buffers Jens Axboe
2022-05-01 20:56 ` [PATCH 01/16] io_uring: kill io_recv_buffer_select() wrapper Jens Axboe
2022-05-01 20:56 ` [PATCH 02/16] io_uring: use 'sr' vs 'req->sr_msg' consistently Jens Axboe
2022-05-01 20:56 ` [PATCH 03/16] io_uring: make io_buffer_select() return the user address directly Jens Axboe
2022-05-09 12:06   ` Dylan Yudaken
2022-05-09 12:12     ` Dylan Yudaken
2022-05-09 12:28       ` Jens Axboe
2022-05-09 12:43         ` Dylan Yudaken
2022-05-09 12:46           ` Jens Axboe
2022-05-09 12:21     ` Jens Axboe
2022-05-01 20:56 ` [PATCH 04/16] io_uring: kill io_rw_buffer_select() wrapper Jens Axboe
2022-05-01 20:56 ` [PATCH 05/16] io_uring: ignore ->buf_index if REQ_F_BUFFER_SELECT isn't set Jens Axboe
2022-05-01 20:56 ` [PATCH 06/16] io_uring: always use req->buf_index for the provided buffer group Jens Axboe
2022-05-01 20:56 ` [PATCH 07/16] io_uring: get rid of hashed provided buffer groups Jens Axboe
2022-05-01 20:56 ` [PATCH 08/16] io_uring: never call io_buffer_select() for a buffer re-select Jens Axboe
2022-05-01 20:56 ` [PATCH 09/16] io_uring: abstract out provided buffer list selection Jens Axboe
2022-05-01 20:56 ` [PATCH 10/16] io_uring: move provided and fixed buffers into the same io_kiocb area Jens Axboe
2022-05-01 20:56 ` [PATCH 11/16] io_uring: move provided buffer state closer to submit state Jens Axboe
2022-05-01 20:56 ` Jens Axboe [this message]
2022-05-01 20:56 ` [PATCH 13/16] io_uring: don't clear req->kbuf when buffer selection is done Jens Axboe
2022-05-01 20:56 ` [PATCH 14/16] io_uring: add buffer selection support to IORING_OP_NOP Jens Axboe
2022-05-01 20:56 ` [PATCH 15/16] io_uring: add io_pin_pages() helper Jens Axboe
2022-05-01 20:56 ` [PATCH 16/16] io_uring: add support for ring mapped supplied buffers 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=20220501205653.15775-13-axboe@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=asml.silence@gmail.com \
    --cc=io-uring@vger.kernel.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.