(主要基於Linux-2.6.11.12版本進行分析。)
1. 主要數據結構
struct eventpoll {
/* Protect the this structure access */
rwlock_t lock;
/*
* This semaphore is used to ensure that files are not removed
* while epoll is using them. This is read-held during the event
* collection loop and it is write-held during the file cleanup
* path, the epoll file exit code and the ctl operations.
*/
struct rw_semaphore sem;
/* Wait queue used by sys_epoll_wait() */
wait_queue_head_t wq;
/* Wait queue used by file->poll() */
wait_queue_head_t poll_wait;
/* List of ready file descriptors */
struct list_head rdllist;
/* RB-Tree root used to store monitored fd structs */
struct rb_root rbr;
};
struct epitem {
/* RB-Tree node used to link this structure to the eventpoll rb-tree */
struct rb_node rbn;
/* List header used to link this structure to the eventpoll ready list */
struct list_head rdllink;
/* The file descriptor information this item refers to */
struct epoll_filefd ffd;
/* Number of active wait queue attached to poll operations */
int nwait;
/* List containing poll wait queues */
struct list_head pwqlist;
/* The "container" of this item */
struct eventpoll *ep;
/* The structure that describe the interested events and the source fd */
struct epoll_event event;
/*
* Used to keep track of the usage count of the structure. This avoids
* that the structure will desappear from underneath our processing.
*/
atomic_t usecnt;
/* List header used to link this item to the "struct file" items list */
struct list_head fllink;
/* List header used to link the item to the transfer list */
struct list_head txlink;
/*
* This is used during the collection/transfer of events to userspace
* to pin items empty events set.
*/
unsigned int revents;
};
struct eppoll_entry {
/* List header used to link this structure to the "struct epitem" */
struct list_head llink;
/* The "base" pointer is set to the container "struct epitem" */
void *base;
/*
* Wait queue item that will be linked to the target file wait
* queue head.
*/
wait_queue_t wait;
/* The wait queue head that linked the "wait" wait queue item */
wait_queue_head_t *whead;
};
文件系統結構
/**
* 對內核支持的每一種文件系統,存在一個這樣的結構對其進行描述。
*/
struct file_system_type {
/**
* 文件系統類型的名稱
*/
const char *name;
/**
* 此文件系統類型的屬性
*/
int fs_flags;
/**
* 函數指針,當安裝此類型的文件系統時,就由VFS調用此例程從設備上將此文件系統的superblock讀入內存中
*/
struct super_block *(*get_sb) (struct file_system_type *, int,
const char *, void *);
/**
* 刪除超級塊的方法。
*/
void (*kill_sb) (struct super_block *);
/**
* 指向實現文件系統的模塊的指針。
*/
struct module *owner;
/**
* 下一個文件系統指針。
*/
struct file_system_type * next;
/**
* 具有相同文件系統類型的超級塊對象鏈表的頭。
*/
struct list_head fs_supers;
};
基本數據結構關係
2. eventpoll_init()
epoll開始的準備工作由eventpoll_init完成,
static int __init eventpoll_init(void)
{
int error;
init_MUTEX(&epsem);
/* Initialize the structure used to perform safe poll wait head wake ups */
ep_poll_safewake_init(&psw);
/* Allocates slab cache used to allocate "struct epitem" items */
epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem),
0, SLAB_HWCACHE_ALIGN|EPI_SLAB_DEBUG|SLAB_PANIC,
NULL, NULL);
/* Allocates slab cache used to allocate "struct eppoll_entry" */
pwq_cache = kmem_cache_create("eventpoll_pwq",
sizeof(struct eppoll_entry), 0,
EPI_SLAB_DEBUG|SLAB_PANIC, NULL, NULL);
/*
* Register the virtual file system that will be the source of inodes
* for the eventpoll files
*/
error = register_filesystem(&eventpoll_fs_type);
if (error)
goto epanic;
/* Mount the above commented virtual file system */
eventpoll_mnt = kern_mount(&eventpoll_fs_type);
error = PTR_ERR(eventpoll_mnt);
if (IS_ERR(eventpoll_mnt))
goto epanic;
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: successfully initialized.\n",
current));
return 0;
epanic:
panic("eventpoll_init() failed\n");
}
2.1 kmem_cache_create()
/* Allocates slab cache used to allocate "struct epitem" items */
epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem),
0, SLAB_HWCACHE_ALIGN|EPI_SLAB_DEBUG|SLAB_PANIC,
NULL, NULL);
/* Allocates slab cache used to allocate "struct eppoll_entry" */
pwq_cache = kmem_cache_create("eventpoll_pwq",
sizeof(struct eppoll_entry), 0,
EPI_SLAB_DEBUG|SLAB_PANIC, NULL, NULL);
該函數是slab分配器接口,即創建一個新的高速緩存——內存池。數據結構類型爲struct epitem和struct epoll_entry。
epoll在被內核初始化時(操作系統啓動),同時會開闢出epoll自己的內核告訴cache區,用於安置每一個我們想監控的socket,這些socket會以紅黑樹的形式保存在內核cache張總,以支持快速的查找、插入、刪除。
這個內核高速緩衝區,就是建立連續的物理內存頁,然後在之上建立slab層,簡單地說,就是物理上分配好你想要的size大小的內存對象,每次使用時都是使用空閒的已分配好的對象。
2.2 register_filesystem()
註冊文件系統,將相應的file_system_type加入到鏈表中。
error = register_filesystem(&eventpoll_fs_type);
在內核中,一切皆文件。所以,epoll向內核註冊了一個文件系統,用於存儲上述的被監控socket。
當調用epoll_create時,就會在這個虛擬的epoll文件系統中創建一個file結點。當然這個file不是普通文件,它只服務於epoll。
3. sys_epoll_create()
asmlinkage long sys_epoll_create(int size)
{
int error, fd;
struct inode *inode;
struct file *file;
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d)\n",
current, size));
/* Sanity check on the size parameter */
error = -EINVAL;
if (size <= 0)
goto eexit_1;
/*
* Creates all the items needed to setup an eventpoll file. That is,
* a file structure, and inode and a free file descriptor.
*/
error = ep_getfd(&fd, &inode, &file);
if (error)
goto eexit_1;
/* Setup the file internal data structure ( "struct eventpoll" ) */
error = ep_file_init(file);
if (error)
goto eexit_2;
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
current, size, fd));
return fd;
eexit_2:
sys_close(fd);
eexit_1:
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
current, size, error));
return error;
}
epoll極其高效的原因:
由於在調用epoll_create時,內核除了幫我們在epoll文件系統中創建了個file結點,在內核cache裏建了一個紅黑樹用於存儲以後epoll_ctl傳來的socket外,還會再建立一個list鏈表,用於存儲準備就緒的事件,當epoll_wait調用時,僅僅觀察這個list鏈表有沒有數據即可。有數據就返回,沒有就sleep,等到timeout時間到後,即使鏈表沒有數據也返回。
所以,epoll_wait非常高效。
3.1 ep_getfd()
在第一次調用epoll_create時,是要創建新的inode、新的file、新的fd。
static int ep_getfd(int *efd, struct inode **einode, struct file **efile)
{
struct qstr this;
char name[32];
struct dentry *dentry;
struct inode *inode;
struct file *file;
int error, fd;
/* Get an ready to use file */
error = -ENFILE;
file = get_empty_filp();
if (!file)
goto eexit_1;
/* Allocates an inode from the eventpoll file system */
inode = ep_eventpoll_inode();
error = PTR_ERR(inode);
if (IS_ERR(inode))
goto eexit_2;
/* Allocates a free descriptor to plug the file onto */
error = get_unused_fd();
if (error < 0)
goto eexit_3;
fd = error;
/*
* Link the inode to a directory entry by creating a unique name
* using the inode number.
*/
error = -ENOMEM;
sprintf(name, "[%lu]", inode->i_ino);
this.name = name;
this.len = strlen(name);
this.hash = inode->i_ino;
dentry = d_alloc(eventpoll_mnt->mnt_sb->s_root, &this);
if (!dentry)
goto eexit_4;
dentry->d_op = &eventpollfs_dentry_operations;
d_add(dentry, inode);
file->f_vfsmnt = mntget(eventpoll_mnt);
file->f_dentry = dentry;
file->f_mapping = inode->i_mapping;
file->f_pos = 0;
file->f_flags = O_RDONLY;
file->f_op = &eventpoll_fops;
file->f_mode = FMODE_READ;
file->f_version = 0;
file->private_data = NULL;
/* Install the new setup file into the allocated fd. */
fd_install(fd, file);
*efd = fd;
*einode = inode;
*efile = file;
return 0;
eexit_4:
put_unused_fd(fd);
eexit_3:
iput(inode);
eexit_2:
put_filp(file);
eexit_1:
return error;
}
3.2 ep_file_init()
設置文件內部數據結構,即struct eventpoll。
static int ep_file_init(struct file *file)
{
struct eventpoll *ep;
if (!(ep = kmalloc(sizeof(struct eventpoll), GFP_KERNEL)))
return -ENOMEM;
memset(ep, 0, sizeof(*ep));
rwlock_init(&ep->lock);
init_rwsem(&ep->sem);
init_waitqueue_head(&ep->wq);
init_waitqueue_head(&ep->poll_wait);
INIT_LIST_HEAD(&ep->rdllist);
ep->rbr = RB_ROOT;
file->private_data = ep;
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_file_init() ep=%p\n",
current, ep));
return 0;
}
file->private_data = ep,這裏進行初始化,爲了可以在函數sys_epoll_ctl直接獲取eventpoll文件中的私有數據。4. sys_epoll_ctl()
在函數sys_epoll_ctl中,如果增加socket句柄,則檢查在紅黑樹中是否存在,存在就立即返回;不存在則添加到樹幹上,然後向內核註冊回調函數,用於當中斷事件來臨時向準備就緒鏈表中插入數據。
asmlinkage long
sys_epoll_ctl(int epfd, int op, int fd, struct epoll_event __user *event)
{
int error;
struct file *file, *tfile;
struct eventpoll *ep;
struct epitem *epi;
struct epoll_event epds;
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_ctl(%d, %d, %d, %p)\n",
current, epfd, op, fd, event));
error = -EFAULT;
if (EP_OP_HASH_EVENT(op) &&
copy_from_user(&epds, event, sizeof(struct epoll_event)))
goto eexit_1;
/* Get the "struct file *" for the eventpoll file */
error = -EBADF;
file = fget(epfd);
if (!file)
goto eexit_1;
/* Get the "struct file *" for the target file */
tfile = fget(fd);
if (!tfile)
goto eexit_2;
/* The target file descriptor must support poll */
error = -EPERM;
if (!tfile->f_op || !tfile->f_op->poll)
goto eexit_3;
/*
* We have to check that the file structure underneath the file descriptor
* the user passed to us _is_ an eventpoll file. And also we do not permit
* adding an epoll file descriptor inside itself.
*/
error = -EINVAL;
if (file == tfile || !IS_FILE_EPOLL(file))
goto eexit_3;
/*
* At this point it is safe to assume that the "private_data" contains
* our own data structure.
*/
ep = file->private_data;
down_write(&ep->sem);
/* Try to lookup the file inside our hash table */
epi = ep_find(ep, tfile, fd);
error = -EINVAL;
switch (op) {
case EPOLL_CTL_ADD:
if (!epi) {
epds.events |= POLLERR | POLLHUP;
error = ep_insert(ep, &epds, tfile, fd);
} else
error = -EEXIST;
break;
case EPOLL_CTL_DEL:
if (epi)
error = ep_remove(ep, epi);
else
error = -ENOENT;
break;
case EPOLL_CTL_MOD:
if (epi) {
epds.events |= POLLERR | POLLHUP;
error = ep_modify(ep, epi, &epds);
} else
error = -ENOENT;
break;
}
/*
* The function ep_find() increments the usage count of the structure
* so, if this is not NULL, we need to release it.
*/
if (epi)
ep_release_epitem(epi);
up_write(&ep->sem);
eexit_3:
fput(tfile);
eexit_2:
fput(file);
eexit_1:
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_ctl(%d, %d, %d, %p) = %d\n",
current, epfd, op, fd, event, error));
return error;
}
4.1 ep = file->private_data;
獲取eventpoll文件中的私有數據,該數據在event_create中創建。
4.2 ep_find()
在eventpoll中存儲文件描述符信息的紅黑樹中查找指定fd對應的epitem實例。
一個新創建的epoll文件帶有一個struct eventpoll結構,這個結構再掛一個紅黑樹,而這個紅黑樹就是每次epoll_ctl時fd存放的地方。
ep_find的實現,是struct eventpoll的rbr成員(strut rb_root),原來就是一個紅黑樹的根。而紅黑樹上掛的是struct epitem。
4.3 ep_insert()
首先,進行ep_find,
如果找到了struct epitem而用戶操作是ADD,那麼返回-EEXIST;
如果是DEL,則ep_remove;
如果找不到struct epitem而用戶操作是ADD,就ep_insert創建並插入一個。
static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
struct file *tfile, int fd)
{
int error, revents, pwake = 0;
unsigned long flags;
struct epitem *epi;
struct ep_pqueue epq;
error = -ENOMEM;
if (!(epi = EPI_MEM_ALLOC()))
goto eexit_1;
/* Item initialization follow here ... */
EP_RB_INITNODE(&epi->rbn);
INIT_LIST_HEAD(&epi->rdllink);
INIT_LIST_HEAD(&epi->fllink);
INIT_LIST_HEAD(&epi->txlink);
INIT_LIST_HEAD(&epi->pwqlist);
epi->ep = ep;
EP_SET_FFD(&epi->ffd, tfile, fd);
epi->event = *event;
atomic_set(&epi->usecnt, 1);
epi->nwait = 0;
/* 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.
*/
revents = tfile->f_op->poll(tfile, &epq.pt);/////
........
}
4.3.1 EPI_MEM_ALLOC()
首先,申請一個epi空間。
2.3.2 進行初始化
EP_RB_INITNODE(&epi->rbn);
INIT_LIST_HEAD(&epi->rdllink);
INIT_LIST_HEAD(&epi->fllink);
INIT_LIST_HEAD(&epi->txlink);
INIT_LIST_HEAD(&epi->pwqlist);
epi->ep = ep;
2.3.3 ep_ptable_queue_proc()
static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
poll_table *pt)
{
struct epitem *epi = EP_ITEM_FROM_EPQUEUE(pt);
struct eppoll_entry *pwq;
if (epi->nwait >= 0 && (pwq = PWQ_MEM_ALLOC())) {
init_waitqueue_func_entry(&pwq->wait, ep_poll_callback);
pwq->whead = whead;
pwq->base = epi;
add_wait_queue(whead, &pwq->wait);
list_add_tail(&pwq->llink, &epi->pwqlist);
epi->nwait++;
} else {
/* We have to signal that an error occurred */
epi->nwait = -1;
}
}
函數init_waitqueue_func_entry()中定義等待隊列上的喚醒函數爲ep_poll_callback,並對等待隊列進行初始化。
ep_poll_callback()
把紅黑樹上收到event的epitem(代表每個fd)插入ep->rdlist中,
這樣,當epoll_wait返回時,rdlist裏就都是就緒的fd了。
static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
int pwake = 0;
unsigned long flags;
struct epitem *epi = EP_ITEM_FROM_WAIT(wait);
struct eventpoll *ep = epi->ep;
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: poll_callback(%p) epi=%p ep=%p\n",
current, epi->file, epi, ep));
write_lock_irqsave(&ep->lock, flags);
/*
* If the event mask does not contain any poll(2) event, we consider the
* descriptor to be disabled. This condition is likely the effect of the
* EPOLLONESHOT bit that disables the descriptor when an event is received,
* until the next EPOLL_CTL_MOD will be issued.
*/
if (!(epi->event.events & ~EP_PRIVATE_BITS))
goto is_disabled;
/* If this file is already in the ready list we exit soon */
if (EP_IS_LINKED(&epi->rdllink))
goto is_linked;
list_add_tail(&epi->rdllink, &ep->rdllist);
is_linked:
/*
* Wake up ( if active ) both the eventpoll wait list and the ->poll()
* wait list.
*/
if (waitqueue_active(&ep->wq))
wake_up(&ep->wq);
if (waitqueue_active(&ep->poll_wait))
pwake++;
is_disabled:
write_unlock_irqrestore(&ep->lock, flags);
/* We have to call this outside the lock */
if (pwake)
ep_poll_safewake(&psw, &ep->poll_wait);
return 1;
}
EP_PRIVATE_BITS,即宏替換爲(EPOLLONESHOT | EPOLLET).
list_add_tail(&epi->rdlink, &ep->rdlist);
epi->rdlink插入到ep->rdlist之前; struct epitem放到放到struct eventpoll的rdlist中去。
4. sys_epoll_wait()
asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events,
int maxevents, int timeout)
{
int error;
struct file *file;
struct eventpoll *ep;
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_wait(%d, %p, %d, %d)\n",
current, epfd, events, maxevents, timeout));
/* The maximum number of event must be greater than zero */
if (maxevents <= 0)
return -EINVAL;
/* Verify that the area passed by the user is writeable */
if ((error = verify_area(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event))))
goto eexit_1;
/* Get the "struct file *" for the eventpoll file */
error = -EBADF;
file = fget(epfd);
if (!file)
goto eexit_1;
/*
* We have to check that the file structure underneath the fd
* the user passed to us _is_ an eventpoll file.
*/
error = -EINVAL;
if (!IS_FILE_EPOLL(file))
goto eexit_2;
/*
* At this point it is safe to assume that the "private_data" contains
* our own data structure.
*/
ep = file->private_data;
/* Time to fish for events ... */
error = ep_poll(ep, events, maxevents, timeout);
eexit_2:
fput(file);
eexit_1:
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_wait(%d, %p, %d, %d) = %d\n",
current, epfd, events, maxevents, timeout, error));
return error;
}
4.1 maxevents
事件個數一定大於0,否則返回-EINVAL。
4.2 verify_area()
/**
* 函數verify_area執行與access_ok宏類似的檢查,雖然它被認爲是陳舊過時的
* 但是在源代碼中仍然被廣泛使用。
*/
static inline int verify_area(int type, const void __user * addr, unsigned long size)
{
return access_ok(type,addr,size) ? 0 : -EFAULT;
}
對系統調用所傳遞地址的檢查是通過access_ok宏實現的。
· 它由兩個分別爲addr和size的參數。
· 該宏檢查addr到addr+size-1之間的地址區間。
4.3 file = fget(epfd)
獲取epfd對應的file實例。
然後接着調用IS_FILE_EPOLL(file),判斷是否爲eventpoll的file,
即(f)->f_op == &eventpoll_fops.
4.4 ep_poll
這個函數是epoll的核心函數,接下來進行分析。
static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
int maxevents, long timeout)
{
int res, eavail;
unsigned long flags;
long jtimeout;
wait_queue_t wait;
/*
* Calculate the timeout by checking for the "infinite" value ( -1 )
* and the overflow condition. The passed timeout is in milliseconds,
* that why (t * HZ) / 1000.
*/
jtimeout = timeout == -1 || timeout > (MAX_SCHEDULE_TIMEOUT - 1000) / HZ ?
MAX_SCHEDULE_TIMEOUT: (timeout * HZ + 999) / 1000;
retry:
write_lock_irqsave(&ep->lock, flags);
res = 0;
if (list_empty(&ep->rdllist)) {
/*
* We don't have any available event to return to the caller.
* We need to sleep here, and we will be wake up by
* ep_poll_callback() when events will become available.
*/
init_waitqueue_entry(&wait, current);
add_wait_queue(&ep->wq, &wait);
for (;;) {
/*
* We don't want to sleep if the ep_poll_callback() sends us
* a wakeup in between. That's why we set the task state
* to TASK_INTERRUPTIBLE before doing the checks.
*/
set_current_state(TASK_INTERRUPTIBLE);
if (!list_empty(&ep->rdllist) || !jtimeout)
break;
if (signal_pending(current)) {
res = -EINTR;
break;
}
write_unlock_irqrestore(&ep->lock, flags);
jtimeout = schedule_timeout(jtimeout);
write_lock_irqsave(&ep->lock, flags);
}
remove_wait_queue(&ep->wq, &wait);
set_current_state(TASK_RUNNING);
}
/* Is it worth to try to dig for events ? */
eavail = !list_empty(&ep->rdllist);
write_unlock_irqrestore(&ep->lock, flags);
/*
* Try to transfer events to user space. In case we get 0 events and
* there's still timeout left over, we go trying again in search of
* more luck.
*/
if (!res && eavail &&
!(res = ep_events_transfer(ep, events, maxevents)) && jtimeout)
goto retry;
return res;
}
首先,調用list_empty(&ep->rdlist),判斷ep->rdlist是否爲NULL。
eventpoll下的struct list_head rdlist,雙鏈表中存放着將要通過epoll_wait返回給用戶的滿足條件的事件。
而struct rb_root rbr,是紅黑樹的根結點,樹中存儲所有添加到epoll中的需要監控的事件。
如果沒有事件到來,不會返回給調用方;
一直在這裏睡眠,直到事件發生,被ep_poll_callback()喚醒。
init_waitqueue_entry()
初始化wait_queue_t結構的變量。
add_wait_queue()
將wait進程插入等待隊列鏈表的第一個位置。
4.4.1 set_current_state()
for循環中,設置TASK_INTERRUPTIBLE狀態,其原因是:如果ep_poll_callback()發生喚醒,不會去休眠。
4.4.2 signal_pending()
如果進程描述符所表示的進程有非阻塞的掛起信號,就返回1。否則返回0。
該函數只是通過檢查進程的TIF_SIGPENDING標誌。
static inline int signal_pending(struct task_struct *p)
{
return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
}
4.4.3 remove_wait_queue()
將wait進程從等待隊列鏈表中刪除。
4.4.4 ep_event_transfer()
把rdlist中的fd拷貝到用戶空間。
static int ep_events_transfer(struct eventpoll *ep,
struct epoll_event __user *events, int maxevents)
{
int eventcnt = 0;
struct list_head txlist;
INIT_LIST_HEAD(&txlist);
/*
* We need to lock this because we could be hit by
* eventpoll_release_file() and epoll_ctl(EPOLL_CTL_DEL).
*/
down_read(&ep->sem);
/* Collect/extract ready items */
if (ep_collect_ready_items(ep, &txlist, maxevents) > 0) {
/* Build result set in userspace */
eventcnt = ep_send_events(ep, &txlist, events);
/* Reinject ready items into the ready list */
ep_reinject_items(ep, &txlist);
}
up_read(&ep->sem);
return eventcnt;
}
4.4.4.1 ep_collect_ready_items()
把rdlist裏的fd挪到txlist中(挪完後rdlist就空了)。
static int ep_collect_ready_items(struct eventpoll *ep, struct list_head *txlist, int maxevents)
{
int nepi;
unsigned long flags;
struct list_head *lsthead = &ep->rdllist, *lnk;
struct epitem *epi;
write_lock_irqsave(&ep->lock, flags);
for (nepi = 0, lnk = lsthead->next; lnk != lsthead && nepi < maxevents;) {
epi = list_entry(lnk, struct epitem, rdllink);
lnk = lnk->next;
/* If this file is already in the ready list we exit soon */
if (!EP_IS_LINKED(&epi->txlink)) {
/*
* This is initialized in this way so that the default
* behaviour of the reinjecting code will be to push back
* the item inside the ready list.
*/
epi->revents = epi->event.events;
/* Link the ready item into the transfer list */
list_add(&epi->txlink, txlist);
nepi++;
/*
* Unlink the item from the ready list.
*/
EP_LIST_DEL(&epi->rdllink);
}
}
write_unlock_irqrestore(&ep->lock, flags);
return nepi;
}
4.4.4.2 ep_send_events()
把txlist中的fd拷貝到用戶空間。
static int ep_send_events(struct eventpoll *ep, struct list_head *txlist,
struct epoll_event __user *events)
{
int eventcnt = 0;
unsigned int revents;
struct list_head *lnk;
struct epitem *epi;
/*
* We can loop without lock because this is a task private list.
* The test done during the collection loop will guarantee us that
* another task will not try to collect this file. Also, items
* cannot vanish during the loop because we are holding "sem".
*/
list_for_each(lnk, txlist) {
epi = list_entry(lnk, struct epitem, txlink);
/*
* Get the ready file event set. We can safely use the file
* because we are holding the "sem" in read and this will
* guarantee that both the file and the item will not vanish.
*/
revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL);
/*
* Set the return event set for the current file descriptor.
* Note that only the task task was successfully able to link
* the item to its "txlist" will write this field.
*/
epi->revents = revents & epi->event.events;
if (epi->revents) {
if (__put_user(epi->revents,
&events[eventcnt].events) ||
__put_user(epi->event.data,
&events[eventcnt].data))
return -EFAULT;
if (epi->event.events & EPOLLONESHOT)
epi->event.events &= EP_PRIVATE_BITS;
eventcnt++;
}
}
return eventcnt;
}
在ep_send_events()中,
revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL);
調用函數scull_p_poll,也就是其中的poll_wait()函數,
POLL方法是poll、epoll和select這三個系統調用的後端實現。可用來查詢某個或多個文件描述符上的讀取或寫入是否會被阻塞。
poll方式返回一個位掩碼mask,用來指出非阻塞的讀取或寫入是否可能。並且會向內核提供將調用進程置於休眠狀態直到IO變爲可能時的信息,並且驅動程序中將POLL方法定義爲NULL,則設備會被認爲既可讀也可寫,並且不會阻塞。
設備先要把current(當前進程)掛在inq和outq兩個隊列上(這個“掛”操作是wait回調函數指針做的),然後等設備喚醒,喚醒後就能通過mask拿到事件掩碼了。
這裏的mask參數就是負責事件掩碼。
4.4.4.3 ep_reinject_items()
把一部分fd從txlist裏“返還”給rdlist以便下次還能從rdlist裏發現它。
static void ep_reinject_items(struct eventpoll *ep, struct list_head *txlist)
{
int ricnt = 0, pwake = 0;
unsigned long flags;
struct epitem *epi;
write_lock_irqsave(&ep->lock, flags);
while (!list_empty(txlist)) {
epi = list_entry(txlist->next, struct epitem, txlink);
/* Unlink the current item from the transfer list */
EP_LIST_DEL(&epi->txlink);
/*
* If the item is no more linked to the interest set, we don't
* have to push it inside the ready list because the following
* ep_release_epitem() is going to drop it. Also, if the current
* item is set to have an Edge Triggered behaviour, we don't have
* to push it back either.
*/
if (EP_RB_LINKED(&epi->rbn) && !(epi->event.events & EPOLLET) &&
(epi->revents & epi->event.events) && !EP_IS_LINKED(&epi->rdllink)) {
list_add_tail(&epi->rdllink, &ep->rdllist);
ricnt++;
}
}
if (ricnt) {
/*
* Wake up ( if active ) both the eventpoll wait list and the ->poll()
* wait list.
*/
if (waitqueue_active(&ep->wq))
wake_up(&ep->wq);
if (waitqueue_active(&ep->poll_wait))
pwake++;
}
write_unlock_irqrestore(&ep->lock, flags);
/* We have to call this outside the lock */
if (pwake)
ep_poll_safewake(&psw, &ep->poll_wait);
}
函數中進行判斷時,
EP_RB_LINKED(epi->rbn) && !(epi->event.events & EPOLLET) && (epi->revents & epi->event.events) && IEP_IS_LINKED(&epi->rdlink),
是哪些“沒有標上EPOLLET”(標紅代碼)且“事件被關注”(標藍代碼)的fd重新被放回了rdlist。
LT模式下,只要一個句柄上事件一次沒有處理完,會在以後調用epoll_wait時此次返回這個句柄,從txlist拷貝到用戶空間後,會返還給rdlist。
而ET模式下,僅在第一次返回。
--------------------------------------------------------------------
總結
1. select和poll每次調用這些函數的時候都需要將監控的fd和需要監控的事件從用戶空間拷貝到內核空間,非常影響效率。而epoll就是自己保存用戶空間拷入的fd和需要監控的事件,只需在調用epoll_ctl的時候就把所有的fd和需要監控的事件只進行一次從用戶空間到內核空間的拷貝。
2. poll和select類似,每次調用都返回整個用戶註冊的事件集合(包括就緒的和未就緒的),應用程序索引就緒文件描述符的時間複雜度爲O(n)。而epoll是在內核中維護一個事件表,epoll_wait的events參數返回就緒的事件,時間複雜度爲O(1).
3. poll和epoll_wait分別用nfds和maxevents參數指定最多監聽多少個文件描述符和事件個數,即65535(cat/proc/sys/fs/file-max)。而select允許監聽的最大文件描述符個數爲1024.
併發支持完美,不會隨着socket的增加而降低效率,也不用在內核空間和用戶空間之間做無效的copy操作。
4. poll只能工作在相對低效的LT模式(電平觸發),而epoll支持LT和ET模式。
ET 邊沿觸發:只觸發一次,無論緩衝區中是否還有剩餘數據,直到有新的數據到達纔會被觸發,再去讀取緩衝區裏面的數據。
LT 水平觸發(默認): LT(level triggered)是缺省的工作方式,並且同時支持block和no-block socket,每次緩衝區都有數據都要觸發。
epoll可以監控管道文件,任意文件,不僅僅是socket文件.
5. poll採用輪詢方式,即每次調用都要掃描整個註冊文件描述符集合,並將其中就緒的文件描述符返回個用戶,因此檢測就緒事件的時間複雜度是O(n)。epoll則採用回調方式。內核檢測到就緒的文件描述符,將觸發回調函數,回調函數將該文件描述符上對應的事件插入內核就緒事件隊列。內核最後將該就緒事件隊列的內容拷貝到用戶空間。時間複雜度爲O(1).
6. 能處理EPOLLONESHOT事件
----------------------------------
應用場景
1. epoll_wait適用於I/O密集型,即連接數量多,但活動連接較少的情況。因爲epoll則採用回調方式。內核檢測到就緒的文件描述符,將觸發回調函數,回調函數將該文件描述符上對應的事件插入內核就緒事件隊列。內核最後將該就緒事件隊列的內容拷貝到用戶空間。
但是,當活動連接較多時,epoll_wait的效率未必比select和poll高,因爲此時回調函數被觸發的過於頻繁。
2. 併發支持完美,不會隨着socket的增加而降低效率,也不用在內核空間和用戶空間之間做無效的copy操作。