linux sys_select 系统调用

---

几个结构体

struct poll_wqueues {
	poll_table pt;
	struct poll_table_page * table;
	int error;
};

struct poll_table_page {
	struct poll_table_page * next;
	struct poll_table_entry * entry;
	struct poll_table_entry entries[0];
};

struct poll_table_entry {
	struct file * filp;
	wait_queue_t wait;
	wait_queue_head_t * wait_address;
};


typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *);

typedef struct poll_table_struct {
	poll_queue_proc qproc;
} poll_table;

核心调用逻辑

asmlinkage long
sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp)
{
	fd_set_bits fds;
	char *bits;
	long timeout;
	int ret, size, max_fdset;

	timeout = MAX_SCHEDULE_TIMEOUT;
	if (tvp) {
		time_t sec, usec;

		if ((ret = verify_area(VERIFY_READ, tvp, sizeof(*tvp)))
		    || (ret = __get_user(sec, &tvp->tv_sec))
		    || (ret = __get_user(usec, &tvp->tv_usec)))
			goto out_nofds;

		ret = -EINVAL;
		if (sec < 0 || usec < 0)
			goto out_nofds;

		if ((unsigned long) sec < MAX_SELECT_SECONDS) {
			timeout = ROUND_UP(usec, 1000000/HZ);
			timeout += sec * (unsigned long) HZ;
		}
	}

	ret = -EINVAL;
	if (n < 0)
		goto out_nofds;

	/* max_fdset can increase, so grab it once to avoid race */
	max_fdset = current->files->max_fdset;
	if (n > max_fdset)
		n = max_fdset;

	/*
	 * We need 6 bitmaps (in/out/ex for both incoming and outgoing),
	 * since we used fdset we need to allocate memory in units of
	 * long-words. 
	 */
	ret = -ENOMEM;
	size = FDS_BYTES(n);
	bits = select_bits_alloc(size);
	if (!bits)
		goto out_nofds;
	fds.in      = (unsigned long *)  bits;
	fds.out     = (unsigned long *) (bits +   size);
	fds.ex      = (unsigned long *) (bits + 2*size);
	fds.res_in  = (unsigned long *) (bits + 3*size);
	fds.res_out = (unsigned long *) (bits + 4*size);
	fds.res_ex  = (unsigned long *) (bits + 5*size);

	if ((ret = get_fd_set(n, inp, fds.in)) ||
	    (ret = get_fd_set(n, outp, fds.out)) ||
	    (ret = get_fd_set(n, exp, fds.ex)))
		goto out;
	zero_fd_set(n, fds.res_in);
	zero_fd_set(n, fds.res_out);
	zero_fd_set(n, fds.res_ex);

	ret = do_select(n, &fds, &timeout);

	if (tvp && !(current->personality & STICKY_TIMEOUTS)) {
		time_t sec = 0, usec = 0;
		if (timeout) {
			sec = timeout / HZ;
			usec = timeout % HZ;
			usec *= (1000000/HZ);
		}
		put_user(sec, &tvp->tv_sec);
		put_user(usec, &tvp->tv_usec);
	}

	if (ret < 0)
		goto out;
	if (!ret) {
		ret = -ERESTARTNOHAND;
		if (signal_pending(current))
			goto out;
		ret = 0;
	}

	if (set_fd_set(n, inp, fds.res_in) ||
	    set_fd_set(n, outp, fds.res_out) ||
	    set_fd_set(n, exp, fds.res_ex))
		ret = -EFAULT;

out:
	select_bits_free(bits, size);
out_nofds:
	return ret;
}


int do_select(int n, fd_set_bits *fds, long *timeout)
{
	struct poll_wqueues table;
	poll_table *wait;
	int retval, i;
	long __timeout = *timeout;

 	spin_lock(&current->files->file_lock);
	retval = max_select_fd(n, fds);
	spin_unlock(&current->files->file_lock);

	if (retval < 0)
		return retval;
	n = retval;

	poll_initwait(&table);
	wait = &table.pt;
	if (!__timeout)
		wait = NULL;
	retval = 0;
	for (;;) {
		unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp;

		set_current_state(TASK_INTERRUPTIBLE);

		inp = fds->in; outp = fds->out; exp = fds->ex;
		rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex;

		for (i = 0; i < n; ++rinp, ++routp, ++rexp) {
			unsigned long in, out, ex, all_bits, bit = 1, mask, j;
			unsigned long res_in = 0, res_out = 0, res_ex = 0;
			struct file_operations *f_op = NULL;
			struct file *file = NULL;

			in = *inp++; out = *outp++; ex = *exp++;
			all_bits = in | out | ex;
			if (all_bits == 0) {
				i += __NFDBITS;
				continue;
			}

			for (j = 0; j < __NFDBITS; ++j, ++i, bit <<= 1) {
				if (i >= n)
					break;
				if (!(bit & all_bits))
					continue;
				file = fget(i);
				if (file) {
					f_op = file->f_op;
					mask = DEFAULT_POLLMASK;
					if (f_op && f_op->poll)
						mask = (*f_op->poll)(file, retval ? NULL : wait);
					fput(file);
					if ((mask & POLLIN_SET) && (in & bit)) {
						res_in |= bit;
						retval++;
					}
					if ((mask & POLLOUT_SET) && (out & bit)) {
						res_out |= bit;
						retval++;
					}
					if ((mask & POLLEX_SET) && (ex & bit)) {
						res_ex |= bit;
						retval++;
					}
				}
				cond_resched();
			}
			if (res_in)
				*rinp = res_in;
			if (res_out)
				*routp = res_out;
			if (res_ex)
				*rexp = res_ex;
		}
		wait = NULL;
		if (retval || !__timeout || signal_pending(current))
			break;
		if(table.error) {
			retval = table.error;
			break;
		}
		__timeout = schedule_timeout(__timeout);
	}
	__set_current_state(TASK_RUNNING);

	poll_freewait(&table);

	/*
	 * Up-to-date the caller timeout.
	 */
	*timeout = __timeout;
	return retval;
}

static unsigned int sock_poll(struct file *file, poll_table * wait)
{
	struct socket *sock;

	/*
	 *	We can't return errors to poll, so it's either yes or no. 
	 */
	sock = SOCKET_I(file->f_dentry->d_inode);
	return sock->ops->poll(file, sock, wait);
}


unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
{
	unsigned int mask;
	struct sock *sk = sock->sk;
	struct tcp_sock *tp = tcp_sk(sk);

	poll_wait(file, sk->sk_sleep, wait);
	if (sk->sk_state == TCP_LISTEN)
		return tcp_listen_poll(sk, wait);
...		
}

void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *_p)
{
	struct poll_wqueues *p = container_of(_p, struct poll_wqueues, pt);
	struct poll_table_page *table = p->table;

	if (!table || POLL_TABLE_FULL(table)) {
		struct poll_table_page *new_table;

		new_table = (struct poll_table_page *) __get_free_page(GFP_KERNEL);
		if (!new_table) {
			p->error = -ENOMEM;
			__set_current_state(TASK_RUNNING);
			return;
		}
		new_table->entry = new_table->entries;
		new_table->next = table;
		p->table = new_table;
		table = new_table;
	}

	/* Add a new entry */
	{
		struct poll_table_entry * entry = table->entry;
		table->entry = entry+1;
	 	get_file(filp);
	 	entry->filp = filp;
		entry->wait_address = wait_address;
		init_waitqueue_entry(&entry->wait, current);
		add_wait_queue(wait_address,&entry->wait);
	}
}

图