| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CADUfDZoXKATH_nQ0TEqj6BrN+e-Shkd11CUJaJJ_FKbrTrv=GQ@mail.gmail.com>
Date: Mon, 1 Dec 2025 13:16:04 -0800
From: Caleb Sander Mateos <csander@...estorage.com>
To: Ming Lei <ming.lei@...hat.com>
Cc: Jens Axboe <axboe@...nel.dk>, linux-block@...r.kernel.org,
Uday Shankar <ushankar@...estorage.com>, Stefani Seibold <stefani@...bold.net>,
Andrew Morton <akpm@...ux-foundation.org>, linux-kernel@...r.kernel.org
Subject: Re: [PATCH V4 16/27] ublk: add new feature UBLK_F_BATCH_IO
On Thu, Nov 20, 2025 at 6:00 PM Ming Lei <ming.lei@...hat.com> wrote:
>
> Add new feature UBLK_F_BATCH_IO which replaces the following two
> per-io commands:
>
> - UBLK_U_IO_FETCH_REQ
>
> - UBLK_U_IO_COMMIT_AND_FETCH_REQ
>
> with three per-queue batch io uring_cmd:
>
> - UBLK_U_IO_PREP_IO_CMDS
>
> - UBLK_U_IO_COMMIT_IO_CMDS
>
> - UBLK_U_IO_FETCH_IO_CMDS
>
> Then ublk can deliver batch io commands to ublk server in single
> multishort uring_cmd, also allows to prepare & commit multiple
> commands in batch style via single uring_cmd, communication cost is
> reduced a lot.
>
> This feature also doesn't limit task context any more for all supported
> commands, so any allowed uring_cmd can be issued in any task context.
> ublk server implementation becomes much easier.
>
> Meantime load balance becomes much easier to support with this feature.
> The command `UBLK_U_IO_FETCH_IO_CMDS` can be issued from multiple task
> contexts, so each task can adjust this command's buffer length or number
> of inflight commands for controlling how much load is handled by current
> task.
>
> Later, priority parameter will be added to command `UBLK_U_IO_FETCH_IO_CMDS`
> for improving load balance support.
>
> UBLK_U_IO_GET_DATA isn't supported in batch io yet, but it may be
UBLK_U_IO_NEED_GET_DATA?
> enabled in future via its batch pair.
>
> Signed-off-by: Ming Lei <ming.lei@...hat.com>
> ---
> drivers/block/ublk_drv.c | 58 ++++++++++++++++++++++++++++++++---
> include/uapi/linux/ublk_cmd.h | 16 ++++++++++
> 2 files changed, 69 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
> index 849199771f86..90cd1863bc83 100644
> --- a/drivers/block/ublk_drv.c
> +++ b/drivers/block/ublk_drv.c
> @@ -74,7 +74,8 @@
> | UBLK_F_AUTO_BUF_REG \
> | UBLK_F_QUIESCE \
> | UBLK_F_PER_IO_DAEMON \
> - | UBLK_F_BUF_REG_OFF_DAEMON)
> + | UBLK_F_BUF_REG_OFF_DAEMON \
> + | UBLK_F_BATCH_IO)
>
> #define UBLK_F_ALL_RECOVERY_FLAGS (UBLK_F_USER_RECOVERY \
> | UBLK_F_USER_RECOVERY_REISSUE \
> @@ -320,12 +321,12 @@ static void ublk_batch_dispatch(struct ublk_queue *ubq,
>
> static inline bool ublk_dev_support_batch_io(const struct ublk_device *ub)
> {
> - return false;
> + return ub->dev_info.flags & UBLK_F_BATCH_IO;
> }
>
> static inline bool ublk_support_batch_io(const struct ublk_queue *ubq)
> {
> - return false;
> + return ubq->flags & UBLK_F_BATCH_IO;
> }
>
> static inline void ublk_io_lock(struct ublk_io *io)
> @@ -3450,6 +3451,41 @@ static int ublk_validate_batch_fetch_cmd(struct ublk_batch_io_data *data,
> return 0;
> }
>
> +static int ublk_handle_non_batch_cmd(struct io_uring_cmd *cmd,
> + unsigned int issue_flags)
> +{
> + const struct ublksrv_io_cmd *ub_cmd = io_uring_sqe_cmd(cmd->sqe);
> + struct ublk_device *ub = cmd->file->private_data;
> + unsigned tag = READ_ONCE(ub_cmd->tag);
> + unsigned q_id = READ_ONCE(ub_cmd->q_id);
> + unsigned index = READ_ONCE(ub_cmd->addr);
> + struct ublk_queue *ubq;
> + struct ublk_io *io;
> + int ret = -EINVAL;
I think it would be clearer to just return -EINVAL instead of adding
this variable, but up to you
> +
> + if (!ub)
> + return ret;
How is this case possible?
> +
> + if (q_id >= ub->dev_info.nr_hw_queues)
> + return ret;
> +
> + ubq = ublk_get_queue(ub, q_id);
> + if (tag >= ubq->q_depth)
Can avoid the likely cache miss here by using ub->dev_info.queue_depth
instead, analogous to ublk_ch_uring_cmd_local()
> + return ret;
> +
> + io = &ubq->ios[tag];
> +
> + switch (cmd->cmd_op) {
> + case UBLK_U_IO_REGISTER_IO_BUF:
> + return ublk_register_io_buf(cmd, ub, q_id, tag, io, index,
> + issue_flags);
> + case UBLK_U_IO_UNREGISTER_IO_BUF:
> + return ublk_unregister_io_buf(cmd, ub, index, issue_flags);
> + default:
> + return -EOPNOTSUPP;
> + }
> +}
> +
> static int ublk_ch_batch_io_uring_cmd(struct io_uring_cmd *cmd,
> unsigned int issue_flags)
> {
> @@ -3497,7 +3533,8 @@ static int ublk_ch_batch_io_uring_cmd(struct io_uring_cmd *cmd,
> ret = ublk_handle_batch_fetch_cmd(&data);
> break;
> default:
> - ret = -EOPNOTSUPP;
> + ret = ublk_handle_non_batch_cmd(cmd, issue_flags);
We should probably skip the if (data.header.q_id >=
ub->dev_info.nr_hw_queues) check for a non-batch command?
> + break;
> }
> out:
> return ret;
> @@ -4163,9 +4200,13 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header)
>
> ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE |
> UBLK_F_URING_CMD_COMP_IN_TASK |
> - UBLK_F_PER_IO_DAEMON |
> + (ublk_dev_support_batch_io(ub) ? 0 : UBLK_F_PER_IO_DAEMON) |
Seems redundant with the logic below to clear UBLK_F_PER_IO_DAEMON if
(ublk_dev_support_batch_io(ub))?
> UBLK_F_BUF_REG_OFF_DAEMON;
>
> + /* So far, UBLK_F_PER_IO_DAEMON won't be exposed for BATCH_IO */
> + if (ublk_dev_support_batch_io(ub))
> + ub->dev_info.flags &= ~UBLK_F_PER_IO_DAEMON;
> +
> /* GET_DATA isn't needed any more with USER_COPY or ZERO COPY */
> if (ub->dev_info.flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY |
> UBLK_F_AUTO_BUF_REG))
> @@ -4518,6 +4559,13 @@ static int ublk_wait_for_idle_io(struct ublk_device *ub,
> unsigned int elapsed = 0;
> int ret;
>
> + /*
> + * For UBLK_F_BATCH_IO ublk server can get notified with existing
> + * or new fetch command, so needn't wait any more
> + */
> + if (ublk_dev_support_batch_io(ub))
> + return 0;
> +
> while (elapsed < timeout_ms && !signal_pending(current)) {
> unsigned int queues_cancelable = 0;
> int i;
> diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
> index cd894c1d188e..5e8b1211b7f4 100644
> --- a/include/uapi/linux/ublk_cmd.h
> +++ b/include/uapi/linux/ublk_cmd.h
> @@ -335,6 +335,22 @@
> */
> #define UBLK_F_BUF_REG_OFF_DAEMON (1ULL << 14)
>
> +
> +/*
> + * Support the following commands for delivering & committing io command
> + * in batch.
> + *
> + * - UBLK_U_IO_PREP_IO_CMDS
> + * - UBLK_U_IO_COMMIT_IO_CMDS
> + * - UBLK_U_IO_FETCH_IO_CMDS
> + * - UBLK_U_IO_REGISTER_IO_BUF
> + * - UBLK_U_IO_UNREGISTER_IO_BUF
Seems like it might make sense to provided batched versions of
UBLK_U_IO_REGISTER_IO_BUF and UBLK_U_IO_UNREGISTER_IO_BUF. That could
be done in the future, I guess, but it might simplify
ublk_ch_batch_io_uring_cmd() to only have to handle struct
ublk_batch_io.
> + *
> + * The existing UBLK_U_IO_FETCH_REQ, UBLK_U_IO_COMMIT_AND_FETCH_REQ and
> + * UBLK_U_IO_GET_DATA uring_cmd are not supported for this feature.
UBLK_U_IO_NEED_GET_DATA?
Best,
Caleb
> + */
> +#define UBLK_F_BATCH_IO (1ULL << 15)
> +
> /* device state */
> #define UBLK_S_DEV_DEAD 0
> #define UBLK_S_DEV_LIVE 1
> --
> 2.47.0
>
Powered by blists - more mailing lists