#include <sys/epoll.h>

int epoll_ctl(int epfd, int op, int fd, struct epoll_event *event);

/*
 * This is the callback that is passed to the wait queue wakeup
 * mechanism. It is called by the stored file descriptors when they
 * have events to report.
 *
 * This callback takes a read lock in order not to contend with concurrent
 * events from another file descriptor, thus all modifications to ->rdllist
 * or ->ovflist are lockless.  Read lock is paired with the write lock from
 * ep_start/done_scan(), which stops all list modifications and guarantees
 * that lists state is seen correctly.
 *
 * Another thing worth to mention is that ep_poll_callback() can be called
 * concurrently for the same @epi from different CPUs if poll table was inited
 * with several wait queues entries.  Plural wakeup from different CPUs of a
 * single wait queue is serialized by wq.lock, but the case when multiple wait
 * queues are used should be detected accordingly.  This is detected using
 * cmpxchg() operation.
 */
static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key

/* No kernel lock held - perfect */
static __poll_t sock_poll(struct file *file, poll_table *wait)
{
	struct socket *sock = file->private_data;
	const struct proto_ops *ops = READ_ONCE(sock->ops);
	__poll_t events = poll_requested_events(wait), flag = 0;

	if (!ops->poll)
		return 0;

	if (sk_can_busy_loop(sock->sk)) {
		/* poll once if requested by the syscall */
		if (events & POLL_BUSY_LOOP)
			sk_busy_loop(sock->sk, 1);

		/* if this socket can poll_ll, tell the system call */
		flag = POLL_BUSY_LOOP;
	}

	return ops->poll(file, sock, wait) | flag;
}

/*
 * This is the callback that is used to add our wait queue to the
 * target file wakeup lists.
 */
static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
				 poll_table *pt)
{
	struct ep_pqueue *epq = container_of(pt, struct ep_pqueue, pt);
	struct epitem *epi = epq->epi;
	struct eppoll_entry *pwq;

	if (unlikely(!epi))	// an earlier allocation has failed
		return;

	pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL);
	if (unlikely(!pwq)) {
		epq->epi = NULL;
		return;
	}

	init_waitqueue_func_entry(&pwq->wait, ep_poll_callback);
	pwq->whead = whead;
	pwq->base = epi;
	if (epi->event.events & EPOLLEXCLUSIVE)
		add_wait_queue_exclusive(whead, &pwq->wait);
	else
		add_wait_queue(whead, &pwq->wait);
	pwq->next = epi->pwqlist;
	epi->pwqlist = pwq;
}

   /* Initialize the poll table using the queue callback */
	epq.epi = epi;
	init_poll_funcptr(&epq.pt, ep_ptable_queue_proc);

	/*
	 * Attach the item to the poll hooks and get current event bits.
	 * We can safely use the file* here because its usage count has
	 * been increased by the caller of this function. Note that after
	 * this operation completes, the poll callback can start hitting
	 * the new item.
	 */
	revents = ep_item_poll(epi, &epq.pt, 1);

	/*
	 * We have to check if something went wrong during the poll wait queue
	 * install process. Namely an allocation for a wait queue failed due
	 * high memory pressure.
	 */
	if (unlikely(!epq.epi)) {
		ep_remove_safe(ep, epi);
		return -ENOMEM;
	}

	/* We have to drop the new item inside our item list to keep track of it */
	write_lock_irq(&ep->lock);

	/* record NAPI ID of new item if present */
	ep_set_busy_poll_napi_id(epi);

/*
 * Open an eventpoll file descriptor.
 */
static int do_epoll_create(int flags)
{
	int error, fd;
	struct eventpoll *ep = NULL;
	struct file *file;

	/* Check the EPOLL_* constant for consistency.  */
	BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);

	if (flags & ~EPOLL_CLOEXEC)
		return -EINVAL;
	/*
	 * Create the internal data structure ("struct eventpoll").
	 */
	error = ep_alloc(&ep);
	if (error < 0)
		return error;
	/*
	 * Creates all the items needed to setup an eventpoll file. That is,
	 * a file structure and a free file descriptor.
	 */
	fd = get_unused_fd_flags(O_RDWR | (flags & O_CLOEXEC));
	if (fd < 0) {
		error = fd;
		goto out_free_ep;
	}
	file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep,
				 O_RDWR | (flags & O_CLOEXEC));
	if (IS_ERR(file)) {
		error = PTR_ERR(file);
		goto out_free_fd;
	}
	ep->file = file;
	fd_install(fd, file);
	return fd;

out_free_fd:
	put_unused_fd(fd);
out_free_ep:
	ep_clear_and_put(ep);
	return error;
}

/*
 * Implement the event wait interface for the eventpoll file. It is the kernel
 * part of the user space epoll_wait(2).
 */
static int do_epoll_wait(int epfd, struct epoll_event __user *events,
			 int maxevents, struct timespec64 *to)
{
	struct eventpoll *ep;

	/* The maximum number of event must be greater than zero */
	if (maxevents <= 0 || maxevents > EP_MAX_EVENTS)
		return -EINVAL;

	/* Verify that the area passed by the user is writeable */
	if (!access_ok(events, maxevents * sizeof(struct epoll_event)))
		return -EFAULT;

	/* Get the "struct file *" for the eventpoll file */
	CLASS(fd, f)(epfd);
	if (fd_empty(f))
		return -EBADF;

	/*
	 * We have to check that the file structure underneath the fd
	 * the user passed to us _is_ an eventpoll file.
	 */
	if (!is_file_epoll(fd_file(f)))
		return -EINVAL;

	/*
	 * At this point it is safe to assume that the "private_data" contains
	 * our own data structure.
	 */
	ep = fd_file(f)->private_data;

	/* Time to fish for events ... */
	return ep_poll(ep, events, maxevents, to);
}

SYSCALL_DEFINE4 Macro in the Linux Kernel
The SYSCALL_DEFINE4 macro is used in the Linux kernel to define system calls that take four arguments.
It helps streamline the declaration of system call functions, ensuring they are properly registered in the syscall table.

SYSCALL_DEFINE4(name, type1, arg1, type2, arg2, type3, arg3, type4, arg4)

static int __init eventpoll_init(void)
{
	struct sysinfo si;

	si_meminfo(&si);
	/*
	 * Allows top 4% of lomem to be allocated for epoll watches (per user).
	 */
	max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) /
		EP_ITEM_COST;
	BUG_ON(max_user_watches < 0);

	/*
	 * We can have many thousands of epitems, so prevent this from
	 * using an extra cache line on 64-bit (and smaller) CPUs
	 */
	BUILD_BUG_ON(sizeof(void *) <= 8 && sizeof(struct epitem) > 128);

	/* Allocates slab cache used to allocate "struct epitem" items */
	epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem),
			0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL);

	/* Allocates slab cache used to allocate "struct eppoll_entry" */
	pwq_cache = kmem_cache_create("eventpoll_pwq",
		sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL);
	epoll_sysctls_init();

	ephead_cache = kmem_cache_create("ep_head",
		sizeof(struct epitems_head), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL);

	return 0;
}
fs_initcall(eventpoll_init);

 #define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
/**
 * BUILD_BUG_ON - break compile if a condition is true.
 * @condition: the condition which the compiler should know is false.
 *
 * If you have some code which relies on certain constants being equal, or
 * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to
 * detect if someone changes it.
 */
#define BUILD_BUG_ON(condition) \
	BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition)