From: Jens Axboe <[email protected]>
To: Jiufei Xue <[email protected]>, [email protected]
Cc: [email protected]
Subject: Re: [PATCH v4 1/2] io_uring: change the poll type to be 32-bits
Date: Wed, 17 Jun 2020 09:15:36 -0600 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
On 6/17/20 3:53 AM, Jiufei Xue wrote:
> poll events should be 32-bits to cover EPOLLEXCLUSIVE.
>
> Explicit word-swap the poll32_events for big endian to make sure the ABI
> is not changed. We call this feature IORING_FEAT_POLL_32BITS,
> applications who want to use EPOLLEXCLUSIVE should check the feature bit
> first.
>
> Signed-off-by: Jiufei Xue <[email protected]>
> ---
> fs/io_uring.c | 13 +++++++++----
> include/uapi/linux/io_uring.h | 4 +++-
> tools/io_uring/liburing.h | 6 +++++-
> 3 files changed, 17 insertions(+), 6 deletions(-)
>
> diff --git a/fs/io_uring.c b/fs/io_uring.c
> index 155f3d8..fe935cf 100644
> --- a/fs/io_uring.c
> +++ b/fs/io_uring.c
> @@ -4543,7 +4543,7 @@ static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
> static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
> {
> struct io_poll_iocb *poll = &req->poll;
> - u16 events;
> + u32 events;
>
> if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
> return -EINVAL;
> @@ -4552,7 +4552,10 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe
> if (!poll->file)
> return -EBADF;
>
> - events = READ_ONCE(sqe->poll_events);
> + events = READ_ONCE(sqe->poll32_events);
> +#ifdef __BIG_ENDIAN
> + events = swahw32(events);
> +#endif
> poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP;
>
> get_task_struct(current);
> @@ -7865,7 +7868,8 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
>
> p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
> IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
> - IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
> + IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL |
> + IORING_FEAT_POLL_32BITS;
>
> if (copy_to_user(params, p, sizeof(*p))) {
> ret = -EFAULT;
> @@ -8154,7 +8158,8 @@ static int __init io_uring_init(void)
> BUILD_BUG_SQE_ELEM(28, /* compat */ int, rw_flags);
> BUILD_BUG_SQE_ELEM(28, /* compat */ __u32, rw_flags);
> BUILD_BUG_SQE_ELEM(28, __u32, fsync_flags);
> - BUILD_BUG_SQE_ELEM(28, __u16, poll_events);
> + BUILD_BUG_SQE_ELEM(28, /* compat */ __u16, poll_events);
> + BUILD_BUG_SQE_ELEM(28, __u32, poll32_events);
> BUILD_BUG_SQE_ELEM(28, __u32, sync_range_flags);
> BUILD_BUG_SQE_ELEM(28, __u32, msg_flags);
> BUILD_BUG_SQE_ELEM(28, __u32, timeout_flags);
> diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
> index 92c2269..8d03396 100644
> --- a/include/uapi/linux/io_uring.h
> +++ b/include/uapi/linux/io_uring.h
> @@ -31,7 +31,8 @@ struct io_uring_sqe {
> union {
> __kernel_rwf_t rw_flags;
> __u32 fsync_flags;
> - __u16 poll_events;
> + __u16 poll_events; /* compatibility */
> + __u32 poll32_events; /* word-reversed for BE */
> __u32 sync_range_flags;
> __u32 msg_flags;
> __u32 timeout_flags;
> @@ -248,6 +249,7 @@ struct io_uring_params {
> #define IORING_FEAT_RW_CUR_POS (1U << 3)
> #define IORING_FEAT_CUR_PERSONALITY (1U << 4)
> #define IORING_FEAT_FAST_POLL (1U << 5)
> +#define IORING_FEAT_POLL_32BITS (1U << 6)
>
> /*
> * io_uring_register(2) opcodes and arguments
> diff --git a/tools/io_uring/liburing.h b/tools/io_uring/liburing.h
> index 5f305c8..28a837b 100644
> --- a/tools/io_uring/liburing.h
> +++ b/tools/io_uring/liburing.h
> @@ -10,6 +10,7 @@
> #include <string.h>
> #include "../../include/uapi/linux/io_uring.h"
> #include <inttypes.h>
> +#include <linux/swab.h>
> #include "barrier.h"
>
> /*
> @@ -145,11 +146,14 @@ static inline void io_uring_prep_write_fixed(struct io_uring_sqe *sqe, int fd,
> }
>
> static inline void io_uring_prep_poll_add(struct io_uring_sqe *sqe, int fd,
> - short poll_mask)
> + unsigned poll_mask)
> {
> memset(sqe, 0, sizeof(*sqe));
> sqe->opcode = IORING_OP_POLL_ADD;
> sqe->fd = fd;
> +#if __BYTE_ORDER == __BIG_ENDIAN
> + poll_mask = __swahw32(poll_mask);
> +#endif
> sqe->poll_events = poll_mask;
This looks good to me now, but this one need not use the __ version, it
should just use the regular one as that's the one defined in the
non-uapi header. But I'll just make that change, won't functionally do
anything.
--
Jens Axboe
next prev parent reply other threads:[~2020-06-17 15:15 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-17 9:53 [PATCH v4 0/2] io_uring: add EPOLLEXCLUSIVE flag for POLL_ADD operation Jiufei Xue
2020-06-17 9:53 ` [PATCH v4 1/2] io_uring: change the poll type to be 32-bits Jiufei Xue
2020-06-17 15:15 ` Jens Axboe [this message]
2020-06-17 9:53 ` [PATCH v4 2/2] io_uring: use EPOLLEXCLUSIVE flag to aoid thundering herd type behavior Jiufei Xue
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] \
/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