Commit f31ecf67 authored by Jens Axboe's avatar Jens Axboe
Browse files

io_uring: add IORING_OP_WAITID support 



This adds support for an async version of waitid(2), in a fully async
version. If an event isn't immediately available, wait for a callback
to trigger a retry.

The format of the sqe is as follows:

sqe->len		The 'which', the idtype being queried/waited for.
sqe->fd			The 'pid' (or id) being waited for.
sqe->file_index		The 'options' being set.
sqe->addr2		A pointer to siginfo_t, if any, being filled in.

buf_index, add3, and waitid_flags are reserved/unused for now.
waitid_flags will be used for options for this request type. One
interesting use case may be to add multi-shot support, so that the
request stays armed and posts a notification every time a monitored
process state change occurs.

Note that this does not support rusage, on Arnd's recommendation.

See the waitid(2) man page for details on the arguments.

Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent 2e521a20

include/linux/io_uring_types.h

+2 −0
Original line number Diff line number Diff line
@@ -313,6 +313,8 @@ struct io_ring_ctx { 
	struct list_head	cq_overflow_list;

	struct io_hash_table	cancel_table;



	struct hlist_head	waitid_list;



	const struct cred	*sq_creds;	/* cred used for __io_sq_thread() */

	struct io_sq_data	*sq_data;	/* if using sq thread polling */

include/uapi/linux/io_uring.h

+2 −0
Original line number Diff line number Diff line
@@ -65,6 +65,7 @@ struct io_uring_sqe { 
		__u32		xattr_flags;

		__u32		msg_ring_flags;

		__u32		uring_cmd_flags;

		__u32		waitid_flags;

	};

	__u64	user_data;	/* data to be passed back at completion time */

	/* pack this to avoid bogus arm OABI complaints */
@@ -241,6 +242,7 @@ enum io_uring_op { 
	IORING_OP_SEND_ZC,

	IORING_OP_SENDMSG_ZC,

	IORING_OP_READ_MULTISHOT,

	IORING_OP_WAITID,



	/* this goes last, obviously */

	IORING_OP_LAST,

io_uring/Makefile

+2 −1
Original line number Diff line number Diff line
@@ -7,5 +7,6 @@ obj-$(CONFIG_IO_URING) += io_uring.o xattr.o nop.o fs.o splice.o \ 
					openclose.o uring_cmd.o epoll.o \

					statx.o net.o msg_ring.o timeout.o \

					sqpoll.o fdinfo.o tctx.o poll.o \

					cancel.o kbuf.o rsrc.o rw.o opdef.o notif.o

					cancel.o kbuf.o rsrc.o rw.o opdef.o \

					notif.o waitid.o

obj-$(CONFIG_IO_WQ)		+= io-wq.o

io_uring/cancel.c

+5 −0
Original line number Diff line number Diff line
@@ -15,6 +15,7 @@ 
#include "tctx.h"

#include "poll.h"

#include "timeout.h"

#include "waitid.h"

#include "cancel.h"



struct io_cancel {
@@ -119,6 +120,10 @@ int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, 
	if (ret != -ENOENT)

		return ret;



	ret = io_waitid_cancel(ctx, cd, issue_flags);

	if (ret != -ENOENT)

		return ret;



	spin_lock(&ctx->completion_lock);

	if (!(cd->flags & IORING_ASYNC_CANCEL_FD))

		ret = io_timeout_cancel(ctx, cd);

io_uring/io_uring.c

+3 −0
Original line number Diff line number Diff line
@@ -92,6 +92,7 @@ 
#include "cancel.h"

#include "net.h"

#include "notif.h"

#include "waitid.h"



#include "timeout.h"

#include "poll.h"
@@ -348,6 +349,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) 
	INIT_LIST_HEAD(&ctx->tctx_list);

	ctx->submit_state.free_list.next = NULL;

	INIT_WQ_LIST(&ctx->locked_free_list);

	INIT_HLIST_HEAD(&ctx->waitid_list);

	INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);

	INIT_WQ_LIST(&ctx->submit_state.compl_reqs);

	return ctx;
@@ -3303,6 +3305,7 @@ static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, 
	ret |= io_cancel_defer_files(ctx, task, cancel_all);

	mutex_lock(&ctx->uring_lock);

	ret |= io_poll_remove_all(ctx, task, cancel_all);

	ret |= io_waitid_remove_all(ctx, task, cancel_all);

	mutex_unlock(&ctx->uring_lock);

	ret |= io_kill_timeouts(ctx, task, cancel_all);

	if (task)