TheRiver | blog

You have reached the world's edge, none but devils play past here

0%

select-poll的源码

Posted on Edited on
Symbols count in article: 14k Reading time ≈ 13 mins.

参考

select/poll/epoll对比分析

Linux进程管理(一)

Linux内核中网络数据包的接收-第二部分 select/poll/epoll

select介绍

man page

1
2
3
#include <sys/select.h>
int select(int nfds, fd_set *readfds, fd_set *writefds,
                  fd_set *exceptfds, struct timeval *timeout);

RETURN VALUE

On success, select() and pselect() return the number of file
descriptors contained in the three returned descriptor sets (that is,
the total number of bits that are set in readfds, writefds,
exceptfds) which may be zero if the timeout expires before anything
interesting happens. On error, -1 is returned, and errno is set to
indicate the error; the file descriptor sets are unmodified, and
timeout becomes undefined.

  • 成功返回三种类型的总的句柄数
  • 超时返回0
  • 异常返回-1

nfds

nfds should be set to the highest-numbered file descriptor in any of
the three sets, plus 1. The indicated file descriptors in each set
are checked, up to this limit (but see BUGS).

timeout

1
2
3
4
struct timeval {
	__kernel_time_t		tv_sec;		/* seconds */
	__kernel_suseconds_t	tv_usec;	/* microseconds 微妙*/
};

timeout = NULL //永久阻塞

timeout.tv_sec = 0 && tv_sec.tv_usec = 0 //不阻塞，直接返回结果

timeout.tv_sec > 0 && tv_sec.tv_usec > 0 //等待超时时间后返回

readfds/writefds/exceptfds

Three independent sets of file descriptors are watched.

The file descriptors listed in readfds will be watched to see if characters
become available for reading (more precisely, to see if a read will
not block; in particular, a file descriptor is also ready on end-of-
file).

The file descriptors in writefds will be watched to see if
space is available for write (though a large write may still block).

The file descriptors in exceptfds will be watched for exceptional
conditions. (For examples of some exceptional conditions, see the
discussion of POLLPRI in poll(2).)

FD_SET

1
2
3
4
5
6
7
#define __FD_SETSIZE	1024

typedef struct {
	unsigned long fds_bits[__FD_SETSIZE / (8 * sizeof(long))];
} __kernel_fd_set;

typedef __kernel_fd_set		fd_set;

64位系统中long是8字节。__FD_SETSIZE表示最大可以监控的句柄数，那么一位可以保存一个，数组大小是多少？__FD_SETSIZE / (8 * sizeof(unsigned long)。

1
2
3
4
void FD_CLR(int fd, fd_set *set);
int  FD_ISSET(int fd, fd_set *set);
void FD_SET(int fd, fd_set *set);
void FD_ZERO(fd_set *set);

引用自这里

FD_CLR(fd, &fdset)

Clears the bit for the file descriptor fd in the file descriptor set fdset.

FD_ISSET(fd, &fdset)

Returns a non-zero value if the bit for the file descriptor fd is set in the file descriptor set pointed to by fdset, and 0 otherwise.

FD_SET(fd, &fdset)

Sets the bit for the file descriptor fd in the file descriptor set fdset.

FD_ZERO(&fdset)

Initializes the file descriptor set fdset to have zero bits for all file descriptors.

select源码

SYSCALL_DEFINE5

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp,
		fd_set __user *, exp, struct timeval __user *, tvp)
{
	struct timespec end_time, *to = NULL;
	struct timeval tv;
	int ret;

	if (tvp) {
		if (copy_from_user(&tv, tvp, sizeof(tv)))
			return -EFAULT;

		to = &end_time;
		if (poll_select_set_timeout(to,
				tv.tv_sec + (tv.tv_usec / USEC_PER_SEC),
				(tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC))
			return -EINVAL;
	}

	ret = core_sys_select(n, inp, outp, exp, to);
	ret = poll_select_copy_remaining(&end_time, tvp, 1, ret);

	return ret;
}

主要把时间格式转换了timeval->timespec

core_sys_select

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
/*
 * We can actually return ERESTARTSYS instead of EINTR, but I'd
 * like to be certain this leads to no problems. So I return
 * EINTR just for safety.
 *
 * Update: ERESTARTSYS breaks at least the xview clock binary, so
 * I'm trying ERESTARTNOHAND which restart only when you want to.
 */
int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
			   fd_set __user *exp, struct timespec *end_time)
{
	fd_set_bits fds;
	void *bits;
	int ret, max_fds;
	unsigned int size;
	struct fdtable *fdt;
	/* Allocate small arguments on the stack to save memory and be faster */
	long stack_fds[SELECT_STACK_ALLOC/sizeof(long)];

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

	/* max_fds can increase, so grab it once to avoid race */
	rcu_read_lock();
	fdt = files_fdtable(current->files);
	max_fds = fdt->max_fds;
	rcu_read_unlock();
	if (n > max_fds)
		n = max_fds;

	/*
	 * 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. 
	 */
	size = FDS_BYTES(n);
	bits = stack_fds;
	if (size > sizeof(stack_fds) / 6) {
		/* Not enough space in on-stack array; must use kmalloc */
		ret = -ENOMEM;
		bits = kmalloc(6 * size, GFP_KERNEL);
		if (!bits)
			goto out_nofds;
	}
	fds.in      = bits;
	fds.out     = bits +   size;
	fds.ex      = bits + 2*size;
	fds.res_in  = bits + 3*size;
	fds.res_out = bits + 4*size;
	fds.res_ex  = 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, end_time);

	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:
	if (bits != stack_fds)
		kfree(bits);
out_nofds:
	return ret;
}

do_select

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115

int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
{
	ktime_t expire, *to = NULL;
	struct poll_wqueues table;
	poll_table *wait;
	int retval, i, timed_out = 0;
	unsigned long slack = 0;

	rcu_read_lock();
	retval = max_select_fd(n, fds);
	rcu_read_unlock();

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

	poll_initwait(&table);
	wait = &table.pt;
	if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
		wait->_qproc = NULL;
		timed_out = 1;
	}

	if (end_time && !timed_out)
		slack = select_estimate_accuracy(end_time);

	retval = 0;
	for (;;) {
		unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp;

		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;

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

			for (j = 0; j < BITS_PER_LONG; ++j, ++i, bit <<= 1) {
				struct fd f;
				if (i >= n)
					break;
				if (!(bit & all_bits))
					continue;
				f = fdget(i);
				if (f.file) {
					const struct file_operations *f_op;
					f_op = f.file->f_op;
					mask = DEFAULT_POLLMASK;
					if (f_op && f_op->poll) {
						wait_key_set(wait, in, out, bit);
						//核心函数
						mask = (*f_op->poll)(f.file, wait);
					}
					fdput(f);
					if ((mask & POLLIN_SET) && (in & bit)) {
						res_in |= bit;
						retval++;
						wait->_qproc = NULL;
					}
					if ((mask & POLLOUT_SET) && (out & bit)) {
						res_out |= bit;
						retval++;
						wait->_qproc = NULL;
					}
					if ((mask & POLLEX_SET) && (ex & bit)) {
						res_ex |= bit;
						retval++;
						wait->_qproc = NULL;
					}
				}
			}
			if (res_in)
				*rinp = res_in;
			if (res_out)
				*routp = res_out;
			if (res_ex)
				*rexp = res_ex;
			cond_resched();
		}
		wait->_qproc = NULL;
		if (retval || timed_out || signal_pending(current))
			break;
		if (table.error) {
			retval = table.error;
			break;
		}

		/*
		 * If this is the first loop and we have a timeout
		 * given, then we convert to ktime_t and set the to
		 * pointer to the expiry value.
		 */
		if (end_time && !to) {
			expire = timespec_to_ktime(*end_time);
			to = &expire;
		}

		if (!poll_schedule_timeout(&table, TASK_INTERRUPTIBLE,
					   to, slack))
			timed_out = 1;
	}

	poll_freewait(&table);

	return retval;
}

1
2
3
4
5
6
7
8
9
10
11

void poll_initwait(struct poll_wqueues *pwq)
{
	init_poll_funcptr(&pwq->pt, __pollwait);
	pwq->polling_task = current;
	pwq->triggered = 0;
	pwq->error = 0;
	pwq->table = NULL;
	pwq->inline_index = 0;
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
/* Add a new entry */
static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
				poll_table *p)
{
	struct poll_wqueues *pwq = container_of(p, struct poll_wqueues, pt);
	struct poll_table_entry *entry = poll_get_entry(pwq);
	if (!entry)
		return;
	entry->filp = get_file(filp);
	entry->wait_address = wait_address;
	entry->key = p->_key;
	init_waitqueue_func_entry(&entry->wait, pollwake);
	entry->wait.private = pwq;
	add_wait_queue(wait_address, &entry->wait);
}
1
2
3
4
5
6
7
8
9
static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
	struct poll_table_entry *entry;

	entry = container_of(wait, struct poll_table_entry, wait);
	if (key && !((unsigned long)key & entry->key))
		return 0;
	return __pollwake(wait, mode, sync, key);
}
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27

static int __pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
	struct poll_wqueues *pwq = wait->private;
	DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task);

	/*
	 * Although this function is called under waitqueue lock, LOCK
	 * doesn't imply write barrier and the users expect write
	 * barrier semantics on wakeup functions.  The following
	 * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
	 * and is paired with set_mb() in poll_schedule_timeout.
	 */
	smp_wmb();
	pwq->triggered = 1;

	/*
	 * Perform the default wake up operation using a dummy
	 * waitqueue.
	 *
	 * TODO: This is hacky but there currently is no interface to
	 * pass in @sync.  @sync is scheduled to be removed and once
	 * that happens, wake_up_process() can be used directly.
	 */
	return default_wake_function(&dummy_wait, mode, sync, key);
}

图片来自:Linux进程管理(一)
task_struct.jpg

SYSCALL_DEFINE5
    |->core_sys_select
        |->do_select
            |->poll_initwait
                |->init_poll_funcptr(&pwq->pt, __pollwait)
                    |->pollwake
                        |->__pollwake
                            |->default_wake_function
            |->f_op->poll
            |->poll_freewait

poll源码

SYSCALL_DEFINE3

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
		int, timeout_msecs)
{
	struct timespec end_time, *to = NULL;
	int ret;

	if (timeout_msecs >= 0) {
		to = &end_time;
		poll_select_set_timeout(to, timeout_msecs / MSEC_PER_SEC,
			NSEC_PER_MSEC * (timeout_msecs % MSEC_PER_SEC));
	}

	ret = do_sys_poll(ufds, nfds, to);

	if (ret == -EINTR) {
		struct restart_block *restart_block;

		restart_block = &current_thread_info()->restart_block;
		restart_block->fn = do_restart_poll;
		restart_block->poll.ufds = ufds;
		restart_block->poll.nfds = nfds;

		if (timeout_msecs >= 0) {
			restart_block->poll.tv_sec = end_time.tv_sec;
			restart_block->poll.tv_nsec = end_time.tv_nsec;
			restart_block->poll.has_timeout = 1;
		} else
			restart_block->poll.has_timeout = 0;

		ret = -ERESTART_RESTARTBLOCK;
	}
	return ret;
}

do_sys_poll

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66

int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
		struct timespec *end_time)
{
	struct poll_wqueues table;
 	int err = -EFAULT, fdcount, len, size;
	/* Allocate small arguments on the stack to save memory and be
	   faster - use long to make sure the buffer is aligned properly
	   on 64 bit archs to avoid unaligned access */
	long stack_pps[POLL_STACK_ALLOC/sizeof(long)];
	struct poll_list *const head = (struct poll_list *)stack_pps;
 	struct poll_list *walk = head;
 	unsigned long todo = nfds;

	if (nfds > rlimit(RLIMIT_NOFILE))
		return -EINVAL;

	len = min_t(unsigned int, nfds, N_STACK_PPS);
	for (;;) {
		walk->next = NULL;
		walk->len = len;
		if (!len)
			break;

		if (copy_from_user(walk->entries, ufds + nfds-todo,
					sizeof(struct pollfd) * walk->len))
			goto out_fds;

		todo -= walk->len;
		if (!todo)
			break;

		len = min(todo, POLLFD_PER_PAGE);
		size = sizeof(struct poll_list) + sizeof(struct pollfd) * len;
		walk = walk->next = kmalloc(size, GFP_KERNEL);
		if (!walk) {
			err = -ENOMEM;
			goto out_fds;
		}
	}

	poll_initwait(&table);
	fdcount = do_poll(nfds, head, &table, end_time);
	poll_freewait(&table);

	for (walk = head; walk; walk = walk->next) {
		struct pollfd *fds = walk->entries;
		int j;

		for (j = 0; j < walk->len; j++, ufds++)
			if (__put_user(fds[j].revents, &ufds->revents))
				goto out_fds;
  	}

	err = fdcount;
out_fds:
	walk = head->next;
	while (walk) {
		struct poll_list *pos = walk;
		walk = walk->next;
		kfree(pos);
	}

	return err;
}

do_poll

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69

static int do_poll(unsigned int nfds,  struct poll_list *list,
		   struct poll_wqueues *wait, struct timespec *end_time)
{
	poll_table* pt = &wait->pt;
	ktime_t expire, *to = NULL;
	int timed_out = 0, count = 0;
	unsigned long slack = 0;

	/* Optimise the no-wait case */
	if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
		pt->_qproc = NULL;
		timed_out = 1;
	}

	if (end_time && !timed_out)
		slack = select_estimate_accuracy(end_time);

	for (;;) {
		struct poll_list *walk;

		for (walk = list; walk != NULL; walk = walk->next) {
			struct pollfd * pfd, * pfd_end;

			pfd = walk->entries;
			pfd_end = pfd + walk->len;
			for (; pfd != pfd_end; pfd++) {
				/*
				 * Fish for events. If we found one, record it
				 * and kill poll_table->_qproc, so we don't
				 * needlessly register any other waiters after
				 * this. They'll get immediately deregistered
				 * when we break out and return.
				 */
				if (do_pollfd(pfd, pt)) {
					count++;
					pt->_qproc = NULL;
				}
			}
		}
		/*
		 * All waiters have already been registered, so don't provide
		 * a poll_table->_qproc to them on the next loop iteration.
		 */
		pt->_qproc = NULL;
		if (!count) {
			count = wait->error;
			if (signal_pending(current))
				count = -EINTR;
		}
		if (count || timed_out)
			break;

		/*
		 * If this is the first loop and we have a timeout
		 * given, then we convert to ktime_t and set the to
		 * pointer to the expiry value.
		 */
		if (end_time && !to) {
			expire = timespec_to_ktime(*end_time);
			to = &expire;
		}

		if (!poll_schedule_timeout(wait, TASK_INTERRUPTIBLE, to, slack))
			timed_out = 1;
	}
	return count;
}

do_pollfd

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34

/*
 * Fish for pollable events on the pollfd->fd file descriptor. We're only
 * interested in events matching the pollfd->events mask, and the result
 * matching that mask is both recorded in pollfd->revents and returned. The
 * pwait poll_table will be used by the fd-provided poll handler for waiting,
 * if pwait->_qproc is non-NULL.
 */
static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait)
{
	unsigned int mask;
	int fd;

	mask = 0;
	fd = pollfd->fd;
	if (fd >= 0) {
		struct fd f = fdget(fd);
		mask = POLLNVAL;
		if (f.file) {
			mask = DEFAULT_POLLMASK;
			if (f.file->f_op && f.file->f_op->poll) {
				pwait->_key = pollfd->events|POLLERR|POLLHUP;
				mask = f.file->f_op->poll(f.file, pwait);
			}
			/* Mask out unneeded events. */
			mask &= pollfd->events | POLLERR | POLLHUP;
			fdput(f);
		}
	}
	pollfd->revents = mask;

	return mask;
}

SYSCALL_DEFINE3
|->do_sys_poll
    |->poll_initwait
    |->do_poll
        |->do_pollfd
            |->f.file->f_op->poll
1
unsigned int (*poll) (struct file *, struct poll_table_struct *);

ending

59069747_p0_master1200.jpg

----------- ending -----------