#include <unistd.h>
#include <stdio.h>
#include <assert.h>
#include <string.h>
#include <sys/mman.h>
#include <sys/syscall.h>
#include <linux/io_uring.h>

int io_uring_setup(unsigned entries, io_uring_params*params) { return syscall(__NR_io_uring_setup, entries, params); }
int io_uring_enter(int ring_fd, unsigned int to_submit, unsigned int min_complete, unsigned int flags, void*sig) { return (int) syscall(__NR_io_uring_enter, ring_fd, to_submit, min_complete, flags, 0); }

typedef int* IntPtr;
#define X(NAME) NAME = (int*)(p+params.sq_off.NAME)
struct sqinfo
{
	IntPtr head, tail, ring_mask, ring_entries, flags, dropped;
	int*array;
	void set(char*p, io_uring_params&params) { X(head); X(tail); X(ring_mask); X(ring_entries); X(flags); X(dropped); array = (int*)(p+params.sq_off.array); }
};
#undef X
#define X(NAME) NAME = (int*)(p+params.cq_off.NAME)
struct cqinfo
{
	IntPtr head, tail, ring_mask, ring_entries, overflow, flags;
	io_uring_cqe*cqes;
	void set(char*p, io_uring_params&params) { X(head); X(tail); X(ring_mask); X(ring_entries); X(overflow); X(flags); cqes = (io_uring_cqe*)(p+params.cq_off.cqes); }
};
#undef X


int main(int argc, char*argv[])
{
	int queue_size = 256;
	io_uring_params param{}; // zero init
	param.flags = IORING_SETUP_SQPOLL;
	int ringFD = io_uring_setup(queue_size, &param);
	assert(ringFD>0);
	assert(param.features & IORING_FEAT_SINGLE_MMAP);
	auto base_length = param.sq_off.array + param.sq_entries*4;
	char *base = (char*) mmap(0, base_length, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, ringFD, IORING_OFF_SQ_RING);
	assert(base != MAP_FAILED);
	auto sqes = (io_uring_sqe*)mmap(0, param.sq_entries * sizeof(io_uring_sqe), PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, ringFD, IORING_OFF_SQES);
	assert(sqes != MAP_FAILED);

	cqinfo cq;
	sqinfo sq;

	cq.set(base, param);
	sq.set(base, param);
	for(int i=0; i<*sq.ring_entries; i++) {
		memset(sqes+i, -1, sizeof(io_uring_sqe));
	}
	for(int i=0; i<*cq.ring_entries; i++) {
		memset(cq.cqes+i, -1, sizeof(io_uring_cqe));
	}


	// Take 10 items
	assert(*sq.tail == 0);
	auto p = &sqes[0];
	memset(p, 0, sizeof(io_uring_sqe)*10);
	for(int i=0; i<10; i++) {
		sqes[i].opcode = IORING_OP_NOP;
		sqes[i].user_data = 0x1234+i;
	}

	__atomic_store_n(sq.tail, 10, __ATOMIC_RELEASE);

	//int res = io_uring_enter(ringFD, 10, 10, IORING_ENTER_SQ_WAIT, 0);
	int res = io_uring_enter(ringFD, 10, 10, IORING_ENTER_SQ_WAKEUP, 0);

	sleep(1);
	printf("cq tail is %d enter result was %d\n", __atomic_load_n(cq.tail, __ATOMIC_ACQUIRE), res);

	for(int i=0; i<11; i++) {
		printf("%X %d\n", cq.cqes[i].user_data, cq.cqes[i].res);
	}
	return 0;
}