struct io_uring {
	struct io_uring_sq sq;
	struct io_uring_cq cq;
	unsigned flags;
	int ring_fd;
};
// 其中的两个struct结构如下
struct io_uring_sq {
	unsigned *khead;
	unsigned *ktail;
	unsigned *kring_mask;
	unsigned *kring_entries;
	unsigned *kflags;
	unsigned *kdropped;
	unsigned *array;
	struct io_uring_sqe *sqes;

	unsigned sqe_head;
	unsigned sqe_tail;

	size_t ring_sz;
	void *ring_ptr;
};

struct io_uring_cq {
	unsigned *khead;
	unsigned *ktail;
	unsigned *kring_mask;
	unsigned *kring_entries;
	unsigned *koverflow;
	struct io_uring_cqe *cqes;

	size_t ring_sz;
	void *ring_ptr;
};

extern int io_uring_queue_init(unsigned entries, struct io_uring *ring, unsigned flags);
extern struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring);
void io_uring_prep_readv(struct io_uring_sqe *sqe, int fd,
				       const struct iovec *iovecs, unsigned nr_vecs, off_t offset)；
void io_uring_prep_writev(struct io_uring_sqe *sqe, int fd,
					const struct iovec *iovecs, unsigned nr_vecs, off_t offset);
extern int io_uring_submit(struct io_uring *ring);
extern int io_uring_peek_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr);
extern int io_uring_wait_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr);
/*
 * Must be called after io_uring_{peek,wait}_cqe() after the cqe has
 * been processed by the application.
 */
static inline void io_uring_cqe_seen(struct io_uring *ring, struct io_uring_cqe *cqe);
extern void io_uring_queue_exit(struct io_uring *ring);

int io_uring_setup(unsigned entries, struct io_uring_params *p);
int io_uring_enter(unsigned fd, unsigned to_submit, unsigned min_complete, unsigned flags, sigset_t *sig);
int io_uring_register(int fd, unsigned int opcode, const void *arg, unsigned int nr_args);

#define IORING_OFF_SQ_RING		0ULL
#define IORING_OFF_CQ_RING		0x8000000ULL
#define IORING_OFF_SQES			0x10000000ULL

struct io_uring_params {
	__u32 sq_entries;
	__u32 cq_entries;
	__u32 flags;
	__u32 sq_thread_cpu;
	__u32 sq_thread_idle;
	__u32 resv[5];
	struct io_sqring_offsets sq_off;
	struct io_cqring_offsets cq_off;
};

/*
 * Filled with the offset for mmap(2)
 */
struct io_sqring_offsets {
	__u32 head;
	__u32 tail;
	__u32 ring_mask;
	__u32 ring_entries;
	__u32 flags;
	__u32 dropped;
	__u32 array;
	__u32 resv1;
	__u64 resv2;
};
struct io_cqring_offsets {
	__u32 head;
	__u32 tail;
	__u32 ring_mask;
	__u32 ring_entries;
	__u32 overflow;
	__u32 cqes;
	__u64 resv[2];
};

/*
 * IO submission data structure (Submission Queue Entry)
 */
struct io_uring_sqe {
	__u8	opcode;		/* type of operation for this sqe */
	__u8	flags;		/* IOSQE_ flags */
	__u16	ioprio;		/* ioprio for the request */
	__s32	fd;		/* file descriptor to do IO on */
	__u64	off;		/* offset into file */
	__u64	addr;		/* pointer to buffer or iovecs */
	__u32	len;		/* buffer size or number of iovecs */
	union {
		__kernel_rwf_t	rw_flags;
		__u32		fsync_flags;
		__u16		poll_events;
		__u32		sync_range_flags;
		__u32		msg_flags;
	};
	__u64	user_data;	/* data to be passed back at completion time */
	union {
		__u16	buf_index;	/* index into fixed buffers, if used */
		__u64	__pad2[3];
	};
};
/*
 * IO completion data structure (Completion Queue Entry)
 */
struct io_uring_cqe {
	__u64	user_data;	/* sqe->data submission passed back */
	__s32	res;		/* result code for this event */
	__u32	flags;
};

#define IORING_ENTER_GETEVENTS	(1U << 0)

struct io_sq_ring {
	/*
	 * Head and tail offsets into the ring; the offsets need to be
	 * masked to get valid indices.
	 *
	 * The kernel controls head and the application controls tail.
	 */
	struct io_uring		r;
	/*
	 * Bitmask to apply to head and tail offsets (constant, equals
	 * ring_entries - 1)
	 */
	u32			ring_mask;
	/* Ring size (constant, power of 2) */
	u32			ring_entries;
	/*
	 * Number of invalid entries dropped by the kernel due to
	 * invalid index stored in array
	 *
	 * Written by the kernel, shouldn't be modified by the
	 * application (i.e. get number of "new events" by comparing to
	 * cached value).
	 *
	 * After a new SQ head value was read by the application this
	 * counter includes all submissions that were dropped reaching
	 * the new SQ head (and possibly more).
	 */
	u32			dropped;
	/*
	 * Runtime flags
	 *
	 * Written by the kernel, shouldn't be modified by the
	 * application.
	 *
	 * The application needs a full memory barrier before checking
	 * for IORING_SQ_NEED_WAKEUP after updating the sq tail.
	 */
	u32			flags;
	/*
	 * Ring buffer of indices into array of io_uring_sqe, which is
	 * mmapped by the application using the IORING_OFF_SQES offset.
	 *
	 * This indirection could e.g. be used to assign fixed
	 * io_uring_sqe entries to operations and only submit them to
	 * the queue when needed.
	 *
	 * The kernel modifies neither the indices array nor the entries
	 * array.
	 */
	u32			array[];
};

/*
 * This data is shared with the application through the mmap at offset
 * IORING_OFF_CQ_RING.
 *
 * The offsets to the member fields are published through struct
 * io_cqring_offsets when calling io_uring_setup.
 */
struct io_cq_ring {
	/*
	 * Head and tail offsets into the ring; the offsets need to be
	 * masked to get valid indices.
	 *
	 * The application controls head and the kernel tail.
	 */
	struct io_uring		r;
	/*
	 * Bitmask to apply to head and tail offsets (constant, equals
	 * ring_entries - 1)
	 */
	u32			ring_mask;
	/* Ring size (constant, power of 2) */
	u32			ring_entries;
	/*
	 * Number of completion events lost because the queue was full;
	 * this should be avoided by the application by making sure
	 * there are not more requests pending thatn there is space in
	 * the completion queue.
	 *
	 * Written by the kernel, shouldn't be modified by the
	 * application (i.e. get number of "new events" by comparing to
	 * cached value).
	 *
	 * As completion events come in out of order this counter is not
	 * ordered with any other data.
	 */
	u32			overflow;
	/*
	 * Ring buffer of completion events.
	 *
	 * The kernel writes completion events fresh every time they are
	 * produced, so the application is allowed to modify pending
	 * entries.
	 */
	struct io_uring_cqe	cqes[];
};


struct io_ring_ctx {
	struct {
		struct percpu_ref	refs;
	} ____cacheline_aligned_in_smp;

	struct {
		unsigned int		flags;
		bool			compat;
		bool			account_mem;

		/* SQ ring */
		struct io_sq_ring	*sq_ring;
		unsigned		cached_sq_head;
		unsigned		sq_entries;
		unsigned		sq_mask;
		unsigned		sq_thread_idle;
		struct io_uring_sqe	*sq_sqes;

		struct list_head	defer_list;
	} ____cacheline_aligned_in_smp;

	/* IO offload */
	struct workqueue_struct	*sqo_wq;
	struct task_struct	*sqo_thread;	/* if using sq thread polling */
	struct mm_struct	*sqo_mm;
	wait_queue_head_t	sqo_wait;
	struct completion	sqo_thread_started;

	struct {
		/* CQ ring */
		struct io_cq_ring	*cq_ring;
		unsigned		cached_cq_tail;
		unsigned		cq_entries;
		unsigned		cq_mask;
		struct wait_queue_head	cq_wait;
		struct fasync_struct	*cq_fasync;
		struct eventfd_ctx	*cq_ev_fd;
	} ____cacheline_aligned_in_smp;

	/*
	 * If used, fixed file set. Writers must ensure that ->refs is dead,
	 * readers must ensure that ->refs is alive as long as the file* is
	 * used. Only updated through io_uring_register(2).
	 */
	struct file		**user_files;
	unsigned		nr_user_files;

	/* if used, fixed mapped user buffers */
	unsigned		nr_user_bufs;
	struct io_mapped_ubuf	*user_bufs;

	struct user_struct	*user;

	struct completion	ctx_done;

	struct {
		struct mutex		uring_lock;
		wait_queue_head_t	wait;
	} ____cacheline_aligned_in_smp;

	struct {
		spinlock_t		completion_lock;
		bool			poll_multi_file;
		/*
		 * ->poll_list is protected by the ctx->uring_lock for
		 * io_uring instances that don't use IORING_SETUP_SQPOLL.
		 * For SQPOLL, only the single threaded io_sq_thread() will
		 * manipulate the list, hence no extra locking is needed there.
		 */
		struct list_head	poll_list;
		struct list_head	cancel_list;
	} ____cacheline_aligned_in_smp;

	struct async_list	pending_async[2];

#if defined(CONFIG_UNIX)
	struct socket		*ring_sock;
#endif
};

int io_uring_queue_init(unsigned entries, struct io_uring *ring, unsigned flags) {
	struct io_uring_params p;
	int fd, ret;

	memset(&p, 0, sizeof(p));
	p.flags = flags;

	fd = io_uring_setup(entries, &p);
	if (fd < 0)
		return -errno;

	ret = io_uring_queue_mmap(fd, &p, ring);
	if (ret)
		close(fd);

	return ret;
}

SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
		u32, min_complete, u32, flags, const sigset_t __user *, sig,
		size_t, sigsz)
{
	struct io_ring_ctx *ctx;
	long ret = -EBADF;
	int submitted = 0;
	struct fd f;
  //...
	/*
	 * For SQ polling, the thread will do all submissions and completions.
	 * Just return the requested submit count, and wake the thread if
	 * we were asked to.
	 */
	if (ctx->flags & IORING_SETUP_SQPOLL) {
		if (flags & IORING_ENTER_SQ_WAKEUP)
			wake_up(&ctx->sqo_wait);
		submitted = to_submit;
		goto out_ctx;
	}

	ret = 0;
	if (to_submit) {
		to_submit = min(to_submit, ctx->sq_entries);
		mutex_lock(&ctx->uring_lock);
		submitted = io_ring_submit(ctx, to_submit);
		mutex_unlock(&ctx->uring_lock);
	}
  
	if (flags & IORING_ENTER_GETEVENTS) {
		unsigned nr_events = 0;
		min_complete = min(min_complete, ctx->cq_entries);
		if (ctx->flags & IORING_SETUP_IOPOLL) {
			ret = io_iopoll_check(ctx, &nr_events, min_complete);
		} else {
			ret = io_cqring_wait(ctx, min_complete, sig, sigsz);
		}
	}

out_ctx:
	io_ring_drop_ctx_refs(ctx, 1);
out_fput:
	fdput(f);
	return submitted ? submitted : ret;
}

static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
			       struct list_head *done)
{
	void *reqs[IO_IOPOLL_BATCH];
	struct io_kiocb *req;
	int to_free;

	to_free = 0;
	while (!list_empty(done)) {
		req = list_first_entry(done, struct io_kiocb, list);
		list_del(&req->list);

		io_cqring_fill_event(ctx, req->user_data, req->result);
		(*nr_events)++;

		if (refcount_dec_and_test(&req->refs)) {
			/* If we're not using fixed files, we have to pair the
			 * completion part with the file put. Use regular
			 * completions for those, only batch free for fixed
			 * file and non-linked commands.
			 */
			if ((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) ==
			    REQ_F_FIXED_FILE) {
				reqs[to_free++] = req;
				if (to_free == ARRAY_SIZE(reqs))
					io_free_req_many(ctx, reqs, &to_free);
			} else {
				io_free_req(req);
			}
		}
	}

	io_commit_cqring(ctx);
	io_free_req_many(ctx, reqs, &to_free);
}

static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
{
	struct io_cq_ring *ring = ctx->cq_ring;
	unsigned tail;

	tail = ctx->cached_cq_tail;
	/*
	 * writes to the cq entry need to come after reading head; the
	 * control dependency is enough as we're using WRITE_ONCE to
	 * fill the cq entry
	 */
	if (tail - READ_ONCE(ring->r.head) == ring->ring_entries)
		return NULL;

	ctx->cached_cq_tail++;
	return &ring->cqes[tail & ctx->cq_mask];
}