为什么80%的码农都做不了架构师？>>> 
结论
- 两者都基于struct poll_wqueues（poll机制），调用file.f_op->poll获得事件mask；
- select以事件类型为切入点，poll以fd为切入点；
- 磁盘文件不可以poll。
核心代码
struct poll_table_struct;
/*
* structures and helpers for f_op->poll implementations
*/
typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *);
/*
* Do not touch the structure directly, use the access functions
* poll_does_not_wait() and poll_requested_events() instead.
*/
typedef struct poll_table_struct {
poll_queue_proc _qproc;
__poll_t _key;
} poll_table;
static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p)
{
if (p && p->_qproc && wait_address)
p->_qproc(filp, wait_address, p);
}
static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
{
pt->_qproc = qproc;
pt->_key = ~(__poll_t)0; /* all events enabled */
}
static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
{
if (unlikely(!file->f_op->poll))
return DEFAULT_POLLMASK;
return file->f_op->poll(file, pt);
}
struct wait_queue_head {
spinlock_t lock;
struct list_head head;
};
typedef struct wait_queue_head wait_queue_head_t;
struct wait_queue_entry {
unsigned int flags;
void *private;
wait_queue_func_t func;
struct list_head entry;
};
typedef struct wait_queue_entry wait_queue_entry_t;
struct poll_table_entry {
struct file *filp;
__poll_t key;
wait_queue_entry_t wait;
wait_queue_head_t *wait_address;
};
struct poll_table_page {
struct poll_table_page * next;
struct poll_table_entry * entry;
struct poll_table_entry entries[0];
};
/*
* Structures and helpers for select/poll syscall
*/
struct poll_wqueues {
poll_table pt;
struct poll_table_page *table;
struct task_struct *polling_task;
int triggered;
int error;
int inline_index;
struct poll_table_entry inline_entries[N_INLINE_POLL_ENTRIES];
};
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 inline void
init_waitqueue_func_entry(struct wait_queue_entry *wq_entry, wait_queue_func_t func)
{
wq_entry->flags = 0;
wq_entry->private = NULL;
wq_entry->func = func;
}
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))
static int __pollwake(wait_queue_entry_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 smp_store_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);
}
static int pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
{
struct poll_table_entry *entry;
entry = container_of(wait, struct poll_table_entry, wait);
if (key && !(key_to_poll(key) & entry->key))
return 0;
return __pollwake(wait, mode, sync, key);
}
/* 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);
}
static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p)
{
if (p && p->_qproc && wait_address)
p->_qproc(filp, wait_address, p);
}poll流程机制
struct poll_wqueues table;
poll_table *wait;
poll_initwait(&table);
wait = &table.pt;
// 对于每一个file
mask = vfs_poll(f.file, wait);
// 一个具体的f_op->poll
static __poll_t
rpc_pipe_poll(struct file *filp, struct poll_table_struct *wait)
{
struct inode *inode = file_inode(filp);
struct rpc_inode *rpci = RPC_I(inode);
__poll_t mask = EPOLLOUT | EPOLLWRNORM;
poll_wait(filp, &rpci->waitq, wait);
inode_lock(inode);
if (rpci->pipe == NULL)
mask |= EPOLLERR | EPOLLHUP;
else if (filp->private_data || !list_empty(&rpci->pipe->pipe))
mask |= EPOLLIN | EPOLLRDNORM;
inode_unlock(inode);
return mask;
}- vfs_poll调用file->f_op->poll(file, pt)
- 通过f_op->pll调用poll_wait(file, wait_address, pt)
- 再调用_qproc，即__pollwait(file, wait_address, pt)，__pollwait设置waitqueue回调函数并加入到当前file的wait queue
- 如果所有的fd都没有感兴趣的事件发生，则通过poll_schedule_timeout请求一次调度。此时线程阻塞，等待事件发生
- 如果事件发生或超时，线程被唤醒，再次轮询fd获得事件并返回。
poll代码
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 __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait,
bool *can_busy_poll,
__poll_t busy_flag)
{
int fd = pollfd->fd;
__poll_t mask = 0, filter;
struct fd f;
if (fd < 0)
goto out;
mask = EPOLLNVAL;
f = fdget(fd);
if (!f.file)
goto out;
/* userland u16 ->events contains POLL... bitmap */
filter = demangle_poll(pollfd->events) | EPOLLERR | EPOLLHUP;
pwait->_key = filter | busy_flag;
mask = vfs_poll(f.file, pwait);
if (mask & busy_flag)
*can_busy_poll = true;
mask &= filter; /* Mask out unneeded events. */
fdput(f);
out:
/* ... and so does ->revents */
pollfd->revents = mangle_poll(mask);
return mask;
}
static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
struct timespec64 *end_time)
{
poll_table* pt = &wait->pt;
ktime_t expire, *to = NULL;
int timed_out = 0, count = 0;
u64 slack = 0;
__poll_t busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
unsigned long busy_start = 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_start) {
busy_start = busy_loop_current_time();
continue;
}
if (!busy_loop_timeout(busy_start))
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 = timespec64_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))
static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
struct timespec64 *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(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 timespec64 *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 timespec64 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->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;
}poll按需求封装实现poll机制。在第一次轮询完毕后设置_qproc = NULL，后续再次调用vfs_poll（f_op->poll）时就是直接返回事件mask。其中使用poll_table_page和poll_list实现分页数组链表优化是亮点。
select代码就不贴了。