From: Keith Busch <[email protected]>
To: Ming Lei <[email protected]>
Cc: Keith Busch <[email protected]>,
[email protected], [email protected],
[email protected], [email protected],
[email protected], [email protected]
Subject: Re: [PATCHv5 09/11] ublk: zc register/unregister bvec
Date: Tue, 25 Feb 2025 09:35:30 -0700 [thread overview]
Message-ID: <Z73xUhaRezPMy_Dz@kbusch-mbp> (raw)
In-Reply-To: <Z72itckfQq5p6xC2@fedora>
On Tue, Feb 25, 2025 at 07:00:05PM +0800, Ming Lei wrote:
> On Mon, Feb 24, 2025 at 01:31:14PM -0800, Keith Busch wrote:
> > static inline bool ublk_dev_is_user_copy(const struct ublk_device *ub)
> > {
> > - return ub->dev_info.flags & UBLK_F_USER_COPY;
> > + return ub->dev_info.flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY);
> > }
>
> I'd suggest to set UBLK_F_USER_COPY explicitly either from userspace or
> kernel side.
>
> One reason is that UBLK_F_UNPRIVILEGED_DEV mode can't work for both.
In my reference implementation using ublksrv, I had the userspace
explicitly setting F_USER_COPY automatically if zero copy was requested.
Is that what you mean? Or do you need the kernel side to set both flags
if zero copy is requested too?
I actually have a newer diff for ublksrv making use of the SQE links.
I'll send that out with the next update since it looks like there will
need to be at least one more version.
Relevant part from the cover letter,
https://lore.kernel.org/io-uring/[email protected]/
diff --git a/ublksrv_tgt.cpp b/ublksrv_tgt.cpp
index 8f9cf28..f3ebe14 100644
--- a/ublksrv_tgt.cpp
+++ b/ublksrv_tgt.cpp
@@ -723,7 +723,7 @@ static int cmd_dev_add(int argc, char *argv[])
data.tgt_type = optarg;
break;
case 'z':
- data.flags |= UBLK_F_SUPPORT_ZERO_COPY;
+ data.flags |= UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_USER_COPY;
break;
case 'q':
data.nr_hw_queues = strtol(optarg, NULL, 10);
next prev parent reply other threads:[~2025-02-25 16:35 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-24 21:31 [PATCHv5 00/11] ublk zero copy support Keith Busch
2025-02-24 21:31 ` [PATCHv5 01/11] io_uring/rsrc: remove redundant check for valid imu Keith Busch
2025-02-25 8:37 ` Ming Lei
2025-02-25 13:13 ` Pavel Begunkov
2025-02-24 21:31 ` [PATCHv5 02/11] io_uring/nop: reuse req->buf_index Keith Busch
2025-02-24 23:30 ` Jens Axboe
2025-02-25 0:02 ` Keith Busch
2025-02-25 8:43 ` Ming Lei
2025-02-25 13:13 ` Pavel Begunkov
2025-02-24 21:31 ` [PATCHv5 03/11] io_uring/net: reuse req->buf_index for sendzc Keith Busch
2025-02-25 8:44 ` Ming Lei
2025-02-25 13:14 ` Pavel Begunkov
2025-02-24 21:31 ` [PATCHv5 04/11] io_uring/nvme: pass issue_flags to io_uring_cmd_import_fixed() Keith Busch
2025-02-25 8:52 ` Ming Lei
2025-02-24 21:31 ` [PATCHv5 05/11] io_uring: combine buffer lookup and import Keith Busch
2025-02-25 8:55 ` Ming Lei
2025-02-24 21:31 ` [PATCHv5 06/11] io_uring/rw: move fixed buffer import to issue path Keith Busch
2025-02-25 9:26 ` Ming Lei
2025-02-25 13:57 ` Pavel Begunkov
2025-02-25 20:57 ` Caleb Sander Mateos
2025-02-25 21:16 ` Keith Busch
2025-02-24 21:31 ` [PATCHv5 07/11] io_uring: add support for kernel registered bvecs Keith Busch
2025-02-25 9:40 ` Ming Lei
2025-02-25 17:32 ` Keith Busch
2025-02-25 22:47 ` Ming Lei
2025-02-25 22:55 ` Keith Busch
2025-02-25 14:00 ` Pavel Begunkov
2025-02-25 14:05 ` Pavel Begunkov
2025-02-25 20:58 ` Caleb Sander Mateos
2025-02-24 21:31 ` [PATCHv5 08/11] nvme: map uring_cmd data even if address is 0 Keith Busch
2025-02-25 9:41 ` Ming Lei
2025-02-24 21:31 ` [PATCHv5 09/11] ublk: zc register/unregister bvec Keith Busch
2025-02-25 11:00 ` Ming Lei
2025-02-25 16:35 ` Keith Busch [this message]
2025-02-25 22:56 ` Ming Lei
2025-02-25 16:19 ` Pavel Begunkov
2025-02-25 16:27 ` Keith Busch
2025-02-25 16:42 ` Pavel Begunkov
2025-02-25 16:52 ` Keith Busch
2025-02-27 4:16 ` Ming Lei
2025-02-25 21:14 ` Caleb Sander Mateos
2025-02-26 8:15 ` Ming Lei
2025-02-26 17:10 ` Keith Busch
2025-02-27 4:19 ` Ming Lei
2025-02-24 21:31 ` [PATCHv5 10/11] io_uring: add abstraction for buf_table rsrc data Keith Busch
2025-02-25 16:04 ` Pavel Begunkov
2025-02-24 21:31 ` [PATCHv5 11/11] io_uring: cache nodes and mapped buffers Keith Busch
2025-02-25 13:11 ` Pavel Begunkov
2025-02-25 14:10 ` [PATCHv5 00/11] ublk zero copy support Pavel Begunkov
2025-02-25 14:47 ` Jens Axboe
2025-02-25 15:07 ` (subset) " 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=Z73xUhaRezPMy_Dz@kbusch-mbp \
[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