Re: [PATCH for-next 2/4] io_uring: introduce fixed buffer support for io_uring_cmd
From: Pavel Begunkov <asml.silence@gmail.com>
Date: 2022-08-22 11:02:29
Also in:
io-uring, linux-nvme
On 8/19/22 11:30, Kanchan Joshi wrote:
quoted hunk ↗ jump to hunk
From: Anuj Gupta <redacted> Add IORING_OP_URING_CMD_FIXED opcode that enables sending io_uring command with previously registered buffers. User-space passes the buffer index in sqe->buf_index, same as done in read/write variants that uses fixed buffers. Signed-off-by: Anuj Gupta <redacted> Signed-off-by: Kanchan Joshi <redacted> --- include/linux/io_uring.h | 5 ++++- include/uapi/linux/io_uring.h | 1 + io_uring/opdef.c | 10 ++++++++++ io_uring/rw.c | 3 ++- io_uring/uring_cmd.c | 18 +++++++++++++++++- 5 files changed, 34 insertions(+), 3 deletions(-)diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 60aba10468fc..40961d7c3827 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h@@ -5,6 +5,8 @@ #include <linux/sched.h> #include <linux/xarray.h> +#include<uapi/linux/io_uring.h> + enum io_uring_cmd_flags { IO_URING_F_COMPLETE_DEFER = 1, IO_URING_F_UNLOCKED = 2,@@ -15,6 +17,7 @@ enum io_uring_cmd_flags { IO_URING_F_SQE128 = 4, IO_URING_F_CQE32 = 8, IO_URING_F_IOPOLL = 16, + IO_URING_F_FIXEDBUFS = 32, }; struct io_uring_cmd {@@ -33,7 +36,7 @@ struct io_uring_cmd { #if defined(CONFIG_IO_URING) int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, - struct iov_iter *iter, void *ioucmd) + struct iov_iter *iter, void *ioucmd);
Please try to compile the first patch separately
quoted hunk ↗ jump to hunk
void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2); void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, void (*task_work_cb)(struct io_uring_cmd *));diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 1463cfecb56b..80ea35d1ed5c 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h@@ -203,6 +203,7 @@ enum io_uring_op { IORING_OP_SOCKET, IORING_OP_URING_CMD, IORING_OP_SENDZC_NOTIF, + IORING_OP_URING_CMD_FIXED,
I don't think it should be another opcode, is there any control flags we can fit it in?
quoted hunk ↗ jump to hunk
/* this goes last, obviously */ IORING_OP_LAST,diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 9a0df19306fe..7d5731b84c92 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c@@ -472,6 +472,16 @@ const struct io_op_def io_op_defs[] = { .issue = io_uring_cmd, .prep_async = io_uring_cmd_prep_async, }, + [IORING_OP_URING_CMD_FIXED] = { + .needs_file = 1, + .plug = 1, + .name = "URING_CMD_FIXED", + .iopoll = 1, + .async_size = uring_cmd_pdu_size(1), + .prep = io_uring_cmd_prep, + .issue = io_uring_cmd, + .prep_async = io_uring_cmd_prep_async, + }, [IORING_OP_SENDZC_NOTIF] = { .name = "SENDZC_NOTIF", .needs_file = 1,diff --git a/io_uring/rw.c b/io_uring/rw.c index 1a4fb8a44b9a..3c7b94bffa62 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c@@ -1005,7 +1005,8 @@ int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin) if (READ_ONCE(req->iopoll_completed)) break; - if (req->opcode == IORING_OP_URING_CMD) { + if (req->opcode == IORING_OP_URING_CMD || + req->opcode == IORING_OP_URING_CMD_FIXED) {
I don't see the changed chunk upstream
struct io_uring_cmd *ioucmd = (struct io_uring_cmd *)rw; ret = req->file->f_op->uring_cmd_iopoll(ioucmd);
[...] -- Pavel Begunkov