多路复用 select 内核实现
附上调试代码 内核调试
/*
* This file contains the procedures for the handling of select and poll
*
* Created for Linux based loosely upon Mathius Lattner's minix
* patches by Peter MacDonald. Heavily edited by Linus.
*
* 4 February 1994
* COFF/ELF binary emulation. If the process has the STICKY_TIMEOUTS
* flag set in its personality we do *not* modify the given timeout
* parameter to reflect time remaining.
*
* 24 January 2000
* Changed sys_poll()/do_poll() to use PAGE_SIZE chunk-based allocation
* of fds to overcome nfds < 16390 descriptors limit (Tigran Aivazian).
*/
#include
#include
#include
#include
#include
#include
#include /* for STICKY_TIMEOUTS */
#include
#include
#include
#include
#include
#include
#include
#include
#include
/*
* Estimate expected accuracy in ns from a timeval.
*
* After quite a bit of churning around, we've settled on
* a simple thing of taking 0.1% of the timeout as the
* slack, with a cap of 100 msec.
* "nice" tasks get a 0.5% slack instead.
*
* Consider this comment an open invitation to come up with even
* better solutions..
*/
#define MAX_SLACK (100 * NSEC_PER_MSEC)
static long __estimate_accuracy(struct timespec *tv)
{
long slack;
int divfactor = 1000;
if (tv->tv_sec < 0)
return 0;
if (task_nice(current) > 0)
divfactor = divfactor / 5;
if (tv->tv_sec > MAX_SLACK / (NSEC_PER_SEC/divfactor))
return MAX_SLACK;
slack = tv->tv_nsec / divfactor;
slack += tv->tv_sec * (NSEC_PER_SEC/divfactor);
if (slack > MAX_SLACK)
return MAX_SLACK;
return slack;
}
long select_estimate_accuracy(struct timespec *tv)
{
unsigned long ret;
struct timespec now;
/*
* Realtime tasks get a slack of 0 for obvious reasons.
*/
if (rt_task(current))
return 0;
ktime_get_ts(&now);
now = timespec_sub(*tv, now);
ret = __estimate_accuracy(&now);
if (ret < current->timer_slack_ns)
return current->timer_slack_ns;
return ret;
}
struct poll_table_page {
struct poll_table_page * next;
struct poll_table_entry * entry;
struct poll_table_entry entries[0];
};
#define POLL_TABLE_FULL(table) \
((unsigned long)((table)->entry+1) > PAGE_SIZE + (unsigned long)(table))
/*
* Ok, Peter made a complicated, but straightforward multiple_wait() function.
* I have rewritten this, taking some shortcuts: This code may not be easy to
* follow, but it should be free of race-conditions, and it's practical. If you
* understand what I'm doing here, then you understand how the linux
* sleep/wakeup mechanism works.
*
* Two very simple procedures, poll_wait() and poll_freewait() make all the
* work. poll_wait() is an inline-function defined in ,
* as all select/poll functions have to call it to add an entry to the
* poll table.
*/
static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
poll_table *p);
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;
}
EXPORT_SYMBOL(poll_initwait);
static void free_poll_entry(struct poll_table_entry *entry)
{
remove_wait_queue(entry->wait_address, &entry->wait);
fput(entry->filp);
}
void poll_freewait(struct poll_wqueues *pwq)
{
struct poll_table_page * p = pwq->table;
int i;
for (i = 0; i < pwq->inline_index; i++)
free_poll_entry(pwq->inline_entries + i);
while (p) {
struct poll_table_entry * entry;
struct poll_table_page *old;
entry = p->entry;
do {
entry--;
free_poll_entry(entry);
} while (entry > p->entries);
old = p;
p = p->next;
free_page((unsigned long) old);
}
}
EXPORT_SYMBOL(poll_freewait);
static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p)
{
struct poll_table_page *table = p->table;
if (p->inline_index < N_INLINE_POLL_ENTRIES)
return p->inline_entries + p->inline_index++;
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;
return NULL;
}
new_table->entry = new_table->entries;
new_table->next = table;
p->table = new_table;
table = new_table;
}
return table->entry++;
}
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();
//有事件触发 标志变量， 避免睡眠
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.
*/
// 用于唤醒select函数的进程
return default_wake_function(&dummy_wait, mode, sync, key);
}
// table中的某个等待队列被唤醒 执行此函数
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;
printk("wusz %d %s \n", __LINE__, __func__);
return __pollwake(wait, mode, sync, key);
}
/* Add a new entry */
// poll 中调用的poll_wait函数会间接的调用此函数，将poll指定的等待队列(wait_address)添加到table中(p)
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;
//filp对应的驱动中的等待队列被唤醒的时候，会调用此处初始化的pollwake函数
init_waitqueue_func_entry(&entry->wait, pollwake);
entry->wait.private = pwq;
// 将wait_address添加到poll_table中
add_wait_queue(wait_address, &entry->wait); // 把当前进程放到各个驱动的等待队列中
printk("wusz %d %s \n", __LINE__, __func__);
}
int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
ktime_t *expires, unsigned long slack)
{
int rc = -EINTR;
// TASK_INTERRUPTIBLE 设置当前进程位
set_current_state(state);
printk("wusz %d %s \n", __LINE__, __func__);
if (!pwq->triggered) {
// 正式进入睡眠状态，由超时或者被等待队列table唤醒
// 如果等待队列唤醒 会执行回调函数
// (本源文件中的static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key))
rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS);
//超时或者等待队列唤醒睡眠都会执行
printk("wusz %d %s \n", __LINE__, __func__);
}
__set_current_state(TASK_RUNNING);
printk("wusz %d %s \n", __LINE__, __func__);
/*
* Prepare for the next iteration.
*
* The following set_mb() serves two purposes. First, it's
* the counterpart rmb of the wmb in pollwake() such that data
* written before wake up is always visible after wake up.
* Second, the full barrier guarantees that triggered clearing
* doesn't pass event check of the next iteration. Note that
* this problem doesn't exist for the first iteration as
* add_wait_queue() has full barrier semantics.
*/
// 为下一次睡眠做好准备
set_mb(pwq->triggered, 0);
printk("wusz %d %s \n", __LINE__, __func__);
return rc;
}
EXPORT_SYMBOL(poll_schedule_timeout);
/**
* poll_select_set_timeout - helper function to setup the timeout value
* @to: pointer to timespec variable for the final timeout
* @sec: seconds (from user space)
* @nsec: nanoseconds (from user space)
*
* Note, we do not use a timespec for the user space value here, That
* way we can use the function for timeval and compat interfaces as well.
*
* Returns -EINVAL if sec/nsec are not normalized. Otherwise 0.
*/
int poll_select_set_timeout(struct timespec *to, long sec, long nsec)
{
struct timespec ts = {.tv_sec = sec, .tv_nsec = nsec};
if (!timespec_valid(&ts))
return -EINVAL;
/* Optimize for the zero timeout value here */
if (!sec && !nsec) {
to->tv_sec = to->tv_nsec = 0;
} else {
ktime_get_ts(to);
*to = timespec_add_safe(*to, ts);
}
return 0;
}
static int poll_select_copy_remaining(struct timespec *end_time, void __user *p,
int timeval, int ret)
{
struct timespec rts;
struct timeval rtv;
if (!p)
return ret;
if (current->personality & STICKY_TIMEOUTS)
goto sticky;
/* No update for zero timeout */
if (!end_time->tv_sec && !end_time->tv_nsec)
return ret;
ktime_get_ts(&rts);
rts = timespec_sub(*end_time, rts);
if (rts.tv_sec < 0)
rts.tv_sec = rts.tv_nsec = 0;
if (timeval) {
if (sizeof(rtv) > sizeof(rtv.tv_sec) + sizeof(rtv.tv_usec))
memset(&rtv, 0, sizeof(rtv));
rtv.tv_sec = rts.tv_sec;
rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC;
if (!copy_to_user(p, &rtv, sizeof(rtv)))
return ret;
} else if (!copy_to_user(p, &rts, sizeof(rts)))
return ret;
/*
* If an application puts its timeval in read-only memory, we
* don't want the Linux-specific update to the timeval to
* cause a fault after the select has completed
* successfully. However, because we're not updating the
* timeval, we can't restart the system call.
*/
sticky:
if (ret == -ERESTARTNOHAND)
ret = -EINTR;
return ret;
}
#define FDS_IN(fds, n) (fds->in + n)
#define FDS_OUT(fds, n) (fds->out + n)
#define FDS_EX(fds, n) (fds->ex + n)
#define BITS(fds, n) (*FDS_IN(fds, n)|*FDS_OUT(fds, n)|*FDS_EX(fds, n))
static int max_select_fd(unsigned long n, fd_set_bits *fds)
{
unsigned long *open_fds;
unsigned long set;
int max;
struct fdtable *fdt;
/* handle last in-complete long-word first */
set = ~(~0UL << (n & (BITS_PER_LONG-1)));
n /= BITS_PER_LONG;
fdt = files_fdtable(current->files);
open_fds = fdt->open_fds + n;
max = 0;
if (set) {
set &= BITS(fds, n);
if (set) {
if (!(set & ~*open_fds))
goto get_max;
return -EBADF;
}
}
while (n) {
open_fds--;
n--;
set = BITS(fds, n);
if (!set)
continue;
if (set & ~*open_fds)
return -EBADF;
if (max)
continue;
get_max:
do {
max++;
set >>= 1;
} while (set);
max += n * BITS_PER_LONG;
}
return max;
}
#define POLLIN_SET (POLLRDNORM | POLLRDBAND | POLLIN | POLLHUP | POLLERR)
#define POLLOUT_SET (POLLWRBAND | POLLWRNORM | POLLOUT | POLLERR)
#define POLLEX_SET (POLLPRI)
static inline void wait_key_set(poll_table *wait, unsigned long in,
unsigned long out, unsigned long bit,
unsigned int ll_flag)
{
wait->_key = POLLEX_SET | ll_flag;
if (in & bit)
wait->_key |= POLLIN_SET;
if (out & bit)
wait->_key |= POLLOUT_SET;
}
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;
unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
unsigned long busy_end = 0;
rcu_read_lock();
retval = max_select_fd(n, fds);
rcu_read_unlock();
if (retval < 0)
return retval;
n = retval;
// table, 保存所有文件描述符对应file_operations驱动中的 poll 回调函数中的通过poll_wait函数
// 指定的 wait_queue_head_t 等待队列(key_dev->wq_head)
/**
* file_operations 中的 poll 回调函数例子
* unsigned int key_drv_poll(struct file *filp, struct poll_table_struct *pts)
* {
* // 返回一个mask值
* unsigned int mask;
* // 调用poll_wait,将当前到等待队列注册系统中, 注册到 struct poll_wqueues table;中
* // pts 就是 table.pt(wait)
* poll_wait(filp, &key_dev->wq_head, pts);
*
* // 1，当没有数据到时候返回一个0
* if(!key_dev->key_state)
* mask = 0;
*
* // 2，有数据返回一个POLLIN
* if(key_dev->key_state)
* mask |= POLLIN;
*
* return mask;
* }
**/
// 初始化table， 初始化设置poll_wait函数中需要的调用到的__pollwait函数
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);
// 有多少个文件描述符产生事件
retval = 0;
// 死循环 至少要 执行两回，
// 第一回 第一次进入 是遍历所有的文件描述符，调用所有的 poll 回调函数把所有文件描述符对应的poll中指定的等待队列 加入大 table中
// 最后一回 超时或者有文件描述符产生事件 ， 再次调用所有的 poll 回调函数，查看那个得到mask,看那个文件描述符有事件发生保存到res_*中
for (;;) {
unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp;
bool can_busy_loop = false;
inp = fds->in; outp = fds->out; exp = fds->ex;
rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex;
// 遍历所有的文件描述符，按照比特位进行遍历
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;
// 如果 all_bits == 0 说明没有文件描述符 ，所有按照sizeof(unsigned long)*8比特位步长 直接略过
if (all_bits == 0) {
i += BITS_PER_LONG;
continue;
}
// 开始遍历 all_bits 对应的每一个比特位
for (j = 0; j < BITS_PER_LONG; ++j, ++i, bit <<= 1) {
struct fd f;
if (i >= n)
break;
// 对应 bit
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->poll) {
wait_key_set(wait, in, out,
bit, busy_flag);
// 执行 file_operations 驱动中的 poll
mask = (*f_op->poll)(f.file, wait);
printk("wusz %d mask %#x \n", __LINE__, mask);
}
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;
}
/* got something, stop busy polling */
if (retval) {
can_busy_loop = false;
busy_flag = 0;
/*
* only remember a returned
* POLL_BUSY_LOOP if we asked for it
*/
} else if (busy_flag & mask)
can_busy_loop = true;
}
}
if (res_in)
*rinp = res_in;
if (res_out)
*routp = res_out;
if (res_ex)
*rexp = res_ex;
printk("wusz %d retval %d \n", __LINE__, retval);
cond_resched();
printk("wusz %d retval %d \n", __LINE__, retval);
}
printk("wusz %d retval %d \n", __LINE__, retval);
wait->_qproc = NULL;
// 如果有事件或者超时跳出 for(;;), 结束从而结束应用层 select 的阻塞状态
if (retval || timed_out || signal_pending(current))
break;
if (table.error) {
retval = table.error;
break;
}
printk("wusz %d retval %d \n", __LINE__, retval);
/* only if found POLL_BUSY_LOOP sockets && not out of time */
if (can_busy_loop && !need_resched()) {
if (!busy_end) {
busy_end = busy_loop_end_time();
continue;
}
if (!busy_loop_timeout(busy_end)) {
printk("wusz %d retval %d \n", __LINE__, retval);
continue;
}
printk("wusz %d retval %d \n", __LINE__, retval);
}
printk("wusz %d retval %d \n", __LINE__, retval);
busy_flag = 0;
/*
* 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;
}
printk("wusz %d retval %d \n", __LINE__, retval);
// 没有事件则进程调度， select对应的进程睡眠状态， 超时也会终止睡眠
// 如果超时则 timed_out = 1; 否则timed_out= 0,
// 终止睡眠之后进行最后一次for(;;), 遍历所有的文件描述符
if (!poll_schedule_timeout(&table, TASK_INTERRUPTIBLE,
to, slack)) {
timed_out = 1; // 超时产生
printk("wusz %d timed_out %d \n", __LINE__, timed_out);
}
printk("wusz %d retval %d \n", __LINE__, retval);
}
poll_freewait(&table);
return retval;
}
/*
* 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 */
// 在内核栈存储空间申请位图，用于保存文件描述符，一个bit位表示一个文件描述符
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.
*/
// 需要使用6个位图，来保存文件描述符
// (in out ex :这三个用来保存从用户空间拷贝过来的；
// res_in res_out res_ex:这三个用来保存有哪些文件描述符有事件)
size = FDS_BYTES(n);
bits = stack_fds;
if (size > sizeof(stack_fds) / 6) {
/* Not enough space in on-stack array; must use kmalloc */
// 如果内核栈的存储空间(stack_fds)不够，就需要在堆中申请内存空间 用于保存文件描述符的位图
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;
// 从用户内存空间(inp, outp, exp)拷贝文件描述符到内核内存空间(fds.in fds.out fds.ex)
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;
// 清空结果内存空间(fds.res_* 这三个保存有哪些文件描述符有事件产生)
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);
printk("wusz %d ret %d n %d \n", __LINE__, ret, n);
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;
}
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;
}
// select 核心函数
ret = core_sys_select(n, inp, outp, exp, to);
ret = poll_select_copy_remaining(&end_time, tvp, 1, ret);
printk("wusz %d %d \n", __LINE__, ret);
return ret;
}
static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp,
fd_set __user *exp, struct timespec __user *tsp,
const sigset_t __user *sigmask, size_t sigsetsize)
{
sigset_t ksigmask, sigsaved;
struct timespec ts, end_time, *to = NULL;
int ret;
if (tsp) {
if (copy_from_user(&ts, tsp, sizeof(ts)))
return -EFAULT;
to = &end_time;
if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
return -EINVAL;
}
if (sigmask) {
/* XXX: Don't preclude handling different sized sigset_t's. */
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
return -EFAULT;
sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
}
ret = core_sys_select(n, inp, outp, exp, to);
ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
if (ret == -ERESTARTNOHAND) {
/*
* Don't restore the signal mask yet. Let do_signal() deliver
* the signal on the way back to userspace, before the signal
* mask is restored.
*/
if (sigmask) {
memcpy(¤t->saved_sigmask, &sigsaved,
sizeof(sigsaved));
set_restore_sigmask();
}
} else if (sigmask)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
return ret;
}
/*
* Most architectures can't handle 7-argument syscalls. So we provide a
* 6-argument version where the sixth argument is a pointer to a structure
* which has a pointer to the sigset_t itself followed by a size_t containing
* the sigset size.
*/
SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp,
fd_set __user *, exp, struct timespec __user *, tsp,
void __user *, sig)
{
size_t sigsetsize = 0;
sigset_t __user *up = NULL;
if (sig) {
if (!access_ok(VERIFY_READ, sig, sizeof(void *)+sizeof(size_t))
|| __get_user(up, (sigset_t __user * __user *)sig)
|| __get_user(sigsetsize,
(size_t __user *)(sig+sizeof(void *))))
return -EFAULT;
}
return do_pselect(n, inp, outp, exp, tsp, up, sigsetsize);
}
#ifdef __ARCH_WANT_SYS_OLD_SELECT
struct sel_arg_struct {
unsigned long n;
fd_set __user *inp, *outp, *exp;
struct timeval __user *tvp;
};
SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg)
{
struct sel_arg_struct a;
if (copy_from_user(&a, arg, sizeof(a)))
return -EFAULT;
return sys_select(a.n, a.inp, a.outp, a.exp, a.tvp);
}
#endif
struct poll_list {
struct poll_list *next;
int len;
struct pollfd entries[0];
};
#define POLLFD_PER_PAGE ((PAGE_SIZE-sizeof(struct poll_list)) / sizeof(struct pollfd))
/*
* 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,
bool *can_busy_poll,
unsigned int busy_flag)
{
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->poll) {
pwait->_key = pollfd->events|POLLERR|POLLHUP;
pwait->_key |= busy_flag;
mask = f.file->f_op->poll(f.file, pwait);
if (mask & busy_flag)
*can_busy_poll = true;
}
/* Mask out unneeded events. */
mask &= pollfd->events | POLLERR | POLLHUP;
fdput(f);
}
}
pollfd->revents = mask;
return mask;
}
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;
unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
unsigned long busy_end = 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;
bool can_busy_loop = false;
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, &can_busy_loop,
busy_flag)) {
count++;
pt->_qproc = NULL;
/* found something, stop busy polling */
busy_flag = 0;
can_busy_loop = false;
}
}
}
/*
* 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;
/* only if found POLL_BUSY_LOOP sockets && not out of time */
if (can_busy_loop && !need_resched()) {
if (!busy_end) {
busy_end = busy_loop_end_time();
continue;
}
if (!busy_loop_timeout(busy_end))
continue;
}
busy_flag = 0;
/*
* 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;
}
#define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list)) / \
sizeof(struct pollfd))
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;
}
static long do_restart_poll(struct restart_block *restart_block)
{
struct pollfd __user *ufds = restart_block->poll.ufds;
int nfds = restart_block->poll.nfds;
struct timespec *to = NULL, end_time;
int ret;
if (restart_block->poll.has_timeout) {
end_time.tv_sec = restart_block->poll.tv_sec;
end_time.tv_nsec = restart_block->poll.tv_nsec;
to = &end_time;
}
ret = do_sys_poll(ufds, nfds, to);
if (ret == -EINTR) {
restart_block->fn = do_restart_poll;
ret = -ERESTART_RESTARTBLOCK;
}
return ret;
}
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 = ¤t_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;
}
SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds,
struct timespec __user *, tsp, const sigset_t __user *, sigmask,
size_t, sigsetsize)
{
sigset_t ksigmask, sigsaved;
struct timespec ts, end_time, *to = NULL;
int ret;
if (tsp) {
if (copy_from_user(&ts, tsp, sizeof(ts)))
return -EFAULT;
to = &end_time;
if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
return -EINVAL;
}
if (sigmask) {
/* XXX: Don't preclude handling different sized sigset_t's. */
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
return -EFAULT;
sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
}
ret = do_sys_poll(ufds, nfds, to);
/* We can restart this syscall, usually */
if (ret == -EINTR) {
/*
* Don't restore the signal mask yet. Let do_signal() deliver
* the signal on the way back to userspace, before the signal
* mask is restored.
*/
if (sigmask) {
memcpy(¤t->saved_sigmask, &sigsaved,
sizeof(sigsaved));
set_restore_sigmask();
}
ret = -ERESTARTNOHAND;
} else if (sigmask)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
return ret;
}
应用层调试代码
#include
#include
#include
#include
#include
#include
#include
int main(int argc, const char *argv[])
{
int retval = 0, fd = 0;
char buf[100] = "";
fd_set readset;
struct timeval tv;
// fd = open("/dev/input/mouse0", O_RDWR);
// if (fd < 0)
// perror("open()");
// while(1) {
tv.tv_sec = 10;
tv.tv_usec = 0;
FD_ZERO(&readset);
FD_SET(0, &readset);
// FD_SET(fd, &readset);
retval = select(3, &readset, NULL, NULL, &tv);
printf("retval %d \n", retval);
if(retval == -1) {
perror("select()");
} else if(retval) {
printf("Data if available now.\n");
if(FD_ISSET(0, &readset)) {
read(0, buf, 100);
printf("%s %d\n", buf, __LINE__);
}
// if(FD_ISSET(fd, &readset)) {
// read(fd, buf, 100);
// printf("%s %d\n", buf, __LINE__);
// }
memset(buf, 0, sizeof(buf));
} else {
printf("No data within five seconds. %d \n",
FD_ISSET(0, &readset));
}
// }
return 0;
} 调试结果
有数据执行结果
[ 155.385000] wusz 239 __pollwait
[ 155.390000] wusz 239 __pollwait
[ 155.390000] wusz 512 mask 0x104
[ 155.395000] wusz 550 retval 0
[ 155.400000] wusz 552 retval 0
[ 155.400000] wusz 554 retval 0
[ 155.405000] wusz 564 retval 0
[ 155.410000] wusz 577 retval 0
[ 155.410000] wusz 590 retval 0
[ 155.415000] wusz 248 poll_schedule_timeout
a[ 158.990000] wusz 218 pollwake
[ 158.990000] wusz 255 poll_schedule_timeout
[ 158.995000] wusz 258 poll_schedule_timeout
[ 159.000000] wusz 273 poll_schedule_timeout
[ 159.005000] wusz 599 retval 0
[ 159.010000] wusz 512 mask 0x145
[ 159.010000] wusz 550 retval 1
[ 159.015000] wusz 552 retval 1
[ 159.015000] wusz 554 retval 1
[ 159.020000] wusz 676 ret 1 n 3
[ 159.025000] wusz 719 1
[ 159.025000] wusz 239 __pollwait
[ 159.030000] wusz 239 __pollwait
[ 159.030000] wusz 248 poll_schedule_timeout
retval 1
Data if available now.
a
35
无数据执行结果
[ 99.310000] wusz 239 __pollwait
[ 99.310000] wusz 239 __pollwait
[ 99.315000] wusz 512 mask 0x104
[ 99.315000] wusz 550 retval 0
[ 99.320000] wusz 552 retval 0
[ 99.325000] wusz 554 retval 0
[ 99.325000] wusz 564 retval 0
[ 99.330000] wusz 577 retval 0
[ 99.335000] wusz 590 retval 0
[ 99.335000] wusz 248 poll_schedule_timeout
[ 109.320000] wusz 255 poll_schedule_timeout
[ 109.320000] wusz 258 poll_schedule_timeout
[ 109.325000] wusz 273 poll_schedule_timeout
[ 109.330000] wusz 597 timed_out 1
[ 109.335000] wusz 599 retval 0
[ 109.335000] wusz 512 mask 0x104
[ 109.340000] wusz 550 retval 0
[ 109.345000] wusz 552 retval 0
[ 109.345000] wusz 554 retval 0
[ 109.350000] wusz 676 ret 0 n 3
[ 109.355000] wusz 719 0
retval 0
No data within five seconds. 0