mirror of
https://github.com/torvalds/linux.git
synced 2026-06-05 04:56:13 +02:00
033af2b3eb
The io_uring_enter() has a fixed order of execution: it submits requests, waits for completions, and returns to the user. Allow to optionally replace it with a custom loop driven by a callback called loop_step. The basic requirements to the callback is that it should be able to submit requests, wait for completions, parse them and repeat. Most of the communication including parameter passing can be implemented via shared memory. The callback should return IOU_LOOP_CONTINUE to continue execution or IOU_LOOP_STOP to return to the user space. Note that the kernel may decide to prematurely terminate it as well, e.g. in case the process was signalled or killed. The hook takes a structure with parameters. It can be used to ask the kernel to wait for CQEs by setting cq_wait_idx to the CQE index it wants to wait for. Spurious wake ups are possible and even likely, the callback is expected to handle it. There will be more parameters in the future like timeout. It can be used with kernel callbacks, for example, as a slow path deprecation mechanism overwiting SQEs and emulating the wanted behaviour, however it's more useful together with BPF programs implemented in following patches. Note that keeping it separately from the normal io_uring wait loop makes things much simpler and cleaner. It keeps it in one place instead of spreading a bunch of checks in different places including disabling the submission path. It holds the lock by default, which is a better fit for BPF synchronisation and the loop execution model. It nicely avoids existing quirks like forced wake ups on timeout request completion. And it should be easier to implement new features. Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Link: https://patch.msgid.link/a2d369aa1c9dd23ad7edac9220cffc563abcaed6.1772109579.git.asml.silence@gmail.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
51 lines
1.3 KiB
C
51 lines
1.3 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#ifndef IOU_WAIT_H
|
|
#define IOU_WAIT_H
|
|
|
|
#include <linux/io_uring_types.h>
|
|
|
|
/*
|
|
* No waiters. It's larger than any valid value of the tw counter
|
|
* so that tests against ->cq_wait_nr would fail and skip wake_up().
|
|
*/
|
|
#define IO_CQ_WAKE_INIT (-1U)
|
|
/* Forced wake up if there is a waiter regardless of ->cq_wait_nr */
|
|
#define IO_CQ_WAKE_FORCE (IO_CQ_WAKE_INIT >> 1)
|
|
|
|
struct ext_arg {
|
|
size_t argsz;
|
|
struct timespec64 ts;
|
|
const sigset_t __user *sig;
|
|
ktime_t min_time;
|
|
bool ts_set;
|
|
bool iowait;
|
|
};
|
|
|
|
int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags,
|
|
struct ext_arg *ext_arg);
|
|
int io_run_task_work_sig(struct io_ring_ctx *ctx);
|
|
void io_cqring_do_overflow_flush(struct io_ring_ctx *ctx);
|
|
void io_cqring_overflow_flush_locked(struct io_ring_ctx *ctx);
|
|
|
|
static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx)
|
|
{
|
|
return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head);
|
|
}
|
|
|
|
static inline unsigned int __io_cqring_events_user(struct io_ring_ctx *ctx)
|
|
{
|
|
return READ_ONCE(ctx->rings->cq.tail) - READ_ONCE(ctx->rings->cq.head);
|
|
}
|
|
|
|
/*
|
|
* Reads the tail/head of the CQ ring while providing an acquire ordering,
|
|
* see comment at top of io_uring.c.
|
|
*/
|
|
static inline unsigned io_cqring_events(struct io_ring_ctx *ctx)
|
|
{
|
|
smp_rmb();
|
|
return __io_cqring_events(ctx);
|
|
}
|
|
|
|
#endif
|