diff options
author | Linus Torvalds <torvalds@ppc970.osdl.org> | 2005-04-16 15:20:36 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@ppc970.osdl.org> | 2005-04-16 15:20:36 -0700 |
commit | 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 (patch) | |
tree | 0bba044c4ce775e45a88a51686b5d9f90697ea9d /fs/eventpoll.c |
Linux-2.6.12-rc2v2.6.12-rc2
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
Diffstat (limited to 'fs/eventpoll.c')
-rw-r--r-- | fs/eventpoll.c | 1639 |
1 files changed, 1639 insertions, 0 deletions
diff --git a/fs/eventpoll.c b/fs/eventpoll.c new file mode 100644 index 00000000000..05b966cd6f7 --- /dev/null +++ b/fs/eventpoll.c @@ -0,0 +1,1639 @@ +/* + * fs/eventpoll.c ( Efficent event polling implementation ) + * Copyright (C) 2001,...,2003 Davide Libenzi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * Davide Libenzi <davidel@xmailserver.org> + * + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/signal.h> +#include <linux/errno.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/poll.h> +#include <linux/smp_lock.h> +#include <linux/string.h> +#include <linux/list.h> +#include <linux/hash.h> +#include <linux/spinlock.h> +#include <linux/syscalls.h> +#include <linux/rwsem.h> +#include <linux/rbtree.h> +#include <linux/wait.h> +#include <linux/eventpoll.h> +#include <linux/mount.h> +#include <linux/bitops.h> +#include <asm/uaccess.h> +#include <asm/system.h> +#include <asm/io.h> +#include <asm/mman.h> +#include <asm/atomic.h> +#include <asm/semaphore.h> + + +/* + * LOCKING: + * There are three level of locking required by epoll : + * + * 1) epsem (semaphore) + * 2) ep->sem (rw_semaphore) + * 3) ep->lock (rw_lock) + * + * The acquire order is the one listed above, from 1 to 3. + * We need a spinlock (ep->lock) because we manipulate objects + * from inside the poll callback, that might be triggered from + * a wake_up() that in turn might be called from IRQ context. + * So we can't sleep inside the poll callback and hence we need + * a spinlock. During the event transfer loop (from kernel to + * user space) we could end up sleeping due a copy_to_user(), so + * we need a lock that will allow us to sleep. This lock is a + * read-write semaphore (ep->sem). It is acquired on read during + * the event transfer loop and in write during epoll_ctl(EPOLL_CTL_DEL) + * and during eventpoll_release_file(). Then we also need a global + * semaphore to serialize eventpoll_release_file() and ep_free(). + * This semaphore is acquired by ep_free() during the epoll file + * cleanup path and it is also acquired by eventpoll_release_file() + * if a file has been pushed inside an epoll set and it is then + * close()d without a previous call toepoll_ctl(EPOLL_CTL_DEL). + * It is possible to drop the "ep->sem" and to use the global + * semaphore "epsem" (together with "ep->lock") to have it working, + * but having "ep->sem" will make the interface more scalable. + * Events that require holding "epsem" are very rare, while for + * normal operations the epoll private "ep->sem" will guarantee + * a greater scalability. + */ + + +#define EVENTPOLLFS_MAGIC 0x03111965 /* My birthday should work for this :) */ + +#define DEBUG_EPOLL 0 + +#if DEBUG_EPOLL > 0 +#define DPRINTK(x) printk x +#define DNPRINTK(n, x) do { if ((n) <= DEBUG_EPOLL) printk x; } while (0) +#else /* #if DEBUG_EPOLL > 0 */ +#define DPRINTK(x) (void) 0 +#define DNPRINTK(n, x) (void) 0 +#endif /* #if DEBUG_EPOLL > 0 */ + +#define DEBUG_EPI 0 + +#if DEBUG_EPI != 0 +#define EPI_SLAB_DEBUG (SLAB_DEBUG_FREE | SLAB_RED_ZONE /* | SLAB_POISON */) +#else /* #if DEBUG_EPI != 0 */ +#define EPI_SLAB_DEBUG 0 +#endif /* #if DEBUG_EPI != 0 */ + +/* Epoll private bits inside the event mask */ +#define EP_PRIVATE_BITS (EPOLLONESHOT | EPOLLET) + +/* Maximum number of poll wake up nests we are allowing */ +#define EP_MAX_POLLWAKE_NESTS 4 + +/* Macro to allocate a "struct epitem" from the slab cache */ +#define EPI_MEM_ALLOC() (struct epitem *) kmem_cache_alloc(epi_cache, SLAB_KERNEL) + +/* Macro to free a "struct epitem" to the slab cache */ +#define EPI_MEM_FREE(p) kmem_cache_free(epi_cache, p) + +/* Macro to allocate a "struct eppoll_entry" from the slab cache */ +#define PWQ_MEM_ALLOC() (struct eppoll_entry *) kmem_cache_alloc(pwq_cache, SLAB_KERNEL) + +/* Macro to free a "struct eppoll_entry" to the slab cache */ +#define PWQ_MEM_FREE(p) kmem_cache_free(pwq_cache, p) + +/* Fast test to see if the file is an evenpoll file */ +#define IS_FILE_EPOLL(f) ((f)->f_op == &eventpoll_fops) + +/* Setup the structure that is used as key for the rb-tree */ +#define EP_SET_FFD(p, f, d) do { (p)->file = (f); (p)->fd = (d); } while (0) + +/* Compare rb-tree keys */ +#define EP_CMP_FFD(p1, p2) ((p1)->file > (p2)->file ? +1: \ + ((p1)->file < (p2)->file ? -1: (p1)->fd - (p2)->fd)) + +/* Special initialization for the rb-tree node to detect linkage */ +#define EP_RB_INITNODE(n) (n)->rb_parent = (n) + +/* Removes a node from the rb-tree and marks it for a fast is-linked check */ +#define EP_RB_ERASE(n, r) do { rb_erase(n, r); (n)->rb_parent = (n); } while (0) + +/* Fast check to verify that the item is linked to the main rb-tree */ +#define EP_RB_LINKED(n) ((n)->rb_parent != (n)) + +/* + * Remove the item from the list and perform its initialization. + * This is useful for us because we can test if the item is linked + * using "EP_IS_LINKED(p)". + */ +#define EP_LIST_DEL(p) do { list_del(p); INIT_LIST_HEAD(p); } while (0) + +/* Tells us if the item is currently linked */ +#define EP_IS_LINKED(p) (!list_empty(p)) + +/* Get the "struct epitem" from a wait queue pointer */ +#define EP_ITEM_FROM_WAIT(p) ((struct epitem *) container_of(p, struct eppoll_entry, wait)->base) + +/* Get the "struct epitem" from an epoll queue wrapper */ +#define EP_ITEM_FROM_EPQUEUE(p) (container_of(p, struct ep_pqueue, pt)->epi) + +/* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ +#define EP_OP_HASH_EVENT(op) ((op) != EPOLL_CTL_DEL) + + +struct epoll_filefd { + struct file *file; + int fd; +}; + +/* + * Node that is linked into the "wake_task_list" member of the "struct poll_safewake". + * It is used to keep track on all tasks that are currently inside the wake_up() code + * to 1) short-circuit the one coming from the same task and same wait queue head + * ( loop ) 2) allow a maximum number of epoll descriptors inclusion nesting + * 3) let go the ones coming from other tasks. + */ +struct wake_task_node { + struct list_head llink; + task_t *task; + wait_queue_head_t *wq; +}; + +/* + * This is used to implement the safe poll wake up avoiding to reenter + * the poll callback from inside wake_up(). + */ +struct poll_safewake { + struct list_head wake_task_list; + spinlock_t lock; +}; + +/* + * This structure is stored inside the "private_data" member of the file + * structure and rapresent the main data sructure for the eventpoll + * interface. + */ +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; +}; + +/* Wait structure used by the poll hooks */ +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; +}; + +/* + * Each file descriptor added to the eventpoll interface will + * have an entry of this type linked to the hash. + */ +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; +}; + +/* Wrapper struct used by poll queueing */ +struct ep_pqueue { + poll_table pt; + struct epitem *epi; +}; + + + +static void ep_poll_safewake_init(struct poll_safewake *psw); +static void ep_poll_safewake(struct poll_safewake *psw, wait_queue_head_t *wq); +static int ep_getfd(int *efd, struct inode **einode, struct file **efile); +static int ep_file_init(struct file *file); +static void ep_free(struct eventpoll *ep); +static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd); +static void ep_use_epitem(struct epitem *epi); +static void ep_release_epitem(struct epitem *epi); +static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead, + poll_table *pt); +static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi); +static int ep_insert(struct eventpoll *ep, struct epoll_event *event, + struct file *tfile, int fd); +static int ep_modify(struct eventpoll *ep, struct epitem *epi, + struct epoll_event *event); +static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi); +static int ep_unlink(struct eventpoll *ep, struct epitem *epi); +static int ep_remove(struct eventpoll *ep, struct epitem *epi); +static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key); +static int ep_eventpoll_close(struct inode *inode, struct file *file); +static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait); +static int ep_collect_ready_items(struct eventpoll *ep, + struct list_head *txlist, int maxevents); +static int ep_send_events(struct eventpoll *ep, struct list_head *txlist, + struct epoll_event __user *events); +static void ep_reinject_items(struct eventpoll *ep, struct list_head *txlist); +static int ep_events_transfer(struct eventpoll *ep, + struct epoll_event __user *events, + int maxevents); +static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, + int maxevents, long timeout); +static int eventpollfs_delete_dentry(struct dentry *dentry); +static struct inode *ep_eventpoll_inode(void); +static struct super_block *eventpollfs_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, + void *data); + +/* + * This semaphore is used to serialize ep_free() and eventpoll_release_file(). + */ +struct semaphore epsem; + +/* Safe wake up implementation */ +static struct poll_safewake psw; + +/* Slab cache used to allocate "struct epitem" */ +static kmem_cache_t *epi_cache; + +/* Slab cache used to allocate "struct eppoll_entry" */ +static kmem_cache_t *pwq_cache; + +/* Virtual fs used to allocate inodes for eventpoll files */ +static struct vfsmount *eventpoll_mnt; + +/* File callbacks that implement the eventpoll file behaviour */ +static struct file_operations eventpoll_fops = { + .release = ep_eventpoll_close, + .poll = ep_eventpoll_poll +}; + +/* + * This is used to register the virtual file system from where + * eventpoll inodes are allocated. + */ +static struct file_system_type eventpoll_fs_type = { + .name = "eventpollfs", + .get_sb = eventpollfs_get_sb, + .kill_sb = kill_anon_super, +}; + +/* Very basic directory entry operations for the eventpoll virtual file system */ +static struct dentry_operations eventpollfs_dentry_operations = { + .d_delete = eventpollfs_delete_dentry, +}; + + + +/* Initialize the poll safe wake up structure */ +static void ep_poll_safewake_init(struct poll_safewake *psw) +{ + + INIT_LIST_HEAD(&psw->wake_task_list); + spin_lock_init(&psw->lock); +} + + +/* + * Perform a safe wake up of the poll wait list. The problem is that + * with the new callback'd wake up system, it is possible that the + * poll callback is reentered from inside the call to wake_up() done + * on the poll wait queue head. The rule is that we cannot reenter the + * wake up code from the same task more than EP_MAX_POLLWAKE_NESTS times, + * and we cannot reenter the same wait queue head at all. This will + * enable to have a hierarchy of epoll file descriptor of no more than + * EP_MAX_POLLWAKE_NESTS deep. We need the irq version of the spin lock + * because this one gets called by the poll callback, that in turn is called + * from inside a wake_up(), that might be called from irq context. + */ +static void ep_poll_safewake(struct poll_safewake *psw, wait_queue_head_t *wq) +{ + int wake_nests = 0; + unsigned long flags; + task_t *this_task = current; + struct list_head *lsthead = &psw->wake_task_list, *lnk; + struct wake_task_node *tncur; + struct wake_task_node tnode; + + spin_lock_irqsave(&psw->lock, flags); + + /* Try to see if the current task is already inside this wakeup call */ + list_for_each(lnk, lsthead) { + tncur = list_entry(lnk, struct wake_task_node, llink); + + if (tncur->wq == wq || + (tncur->task == this_task && ++wake_nests > EP_MAX_POLLWAKE_NESTS)) { + /* + * Ops ... loop detected or maximum nest level reached. + * We abort this wake by breaking the cycle itself. + */ + spin_unlock_irqrestore(&psw->lock, flags); + return; + } + } + + /* Add the current task to the list */ + tnode.task = this_task; + tnode.wq = wq; + list_add(&tnode.llink, lsthead); + + spin_unlock_irqrestore(&psw->lock, flags); + + /* Do really wake up now */ + wake_up(wq); + + /* Remove the current task from the list */ + spin_lock_irqsave(&psw->lock, flags); + list_del(&tnode.llink); + spin_unlock_irqrestore(&psw->lock, flags); +} + + +/* Used to initialize the epoll bits inside the "struct file" */ +void eventpoll_init_file(struct file *file) +{ + + INIT_LIST_HEAD(&file->f_ep_links); + spin_lock_init(&file->f_ep_lock); +} + + +/* + * This is called from eventpoll_release() to unlink files from the eventpoll + * interface. We need to have this facility to cleanup correctly files that are + * closed without being removed from the eventpoll interface. + */ +void eventpoll_release_file(struct file *file) +{ + struct list_head *lsthead = &file->f_ep_links; + struct eventpoll *ep; + struct epitem *epi; + + /* + * We don't want to get "file->f_ep_lock" because it is not + * necessary. It is not necessary because we're in the "struct file" + * cleanup path, and this means that noone is using this file anymore. + * The only hit might come from ep_free() but by holding the semaphore + * will correctly serialize the operation. We do need to acquire + * "ep->sem" after "epsem" because ep_remove() requires it when called + * from anywhere but ep_free(). + */ + down(&epsem); + + while (!list_empty(lsthead)) { + epi = list_entry(lsthead->next, struct epitem, fllink); + + ep = epi->ep; + EP_LIST_DEL(&epi->fllink); + down_write(&ep->sem); + ep_remove(ep, epi); + up_write(&ep->sem); + } + + up(&epsem); +} + + +/* + * It opens an eventpoll file descriptor by suggesting a storage of "size" + * file descriptors. The size parameter is just an hint about how to size + * data structures. It won't prevent the user to store more than "size" + * file descriptors inside the epoll interface. It is the kernel part of + * the userspace epoll_create(2). + */ +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; +} + + +/* + * The following function implements the controller interface for + * the eventpoll file that enables the insertion/removal/change of + * file descriptors inside the interest set. It represents + * the kernel part of the user space epoll_ctl(2). + */ +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; +} + +#define MAX_EVENTS (INT_MAX / sizeof(struct epoll_event)) + +/* + * Implement the event wait interface for the eventpoll file. It is the kernel + * part of the user space epoll_wait(2). + */ +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 || maxevents > MAX_EVENTS) + return -EINVAL; + + /* Verify that the area passed by the user is writeable */ + if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event))) { + error = -EFAULT; + 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; +} + + +/* + * Creates the file descriptor to be used by the epoll interface. + */ +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; +} + + +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; +} + + +static void ep_free(struct eventpoll *ep) +{ + struct rb_node *rbp; + struct epitem *epi; + + /* We need to release all tasks waiting for these file */ + if (waitqueue_active(&ep->poll_wait)) + ep_poll_safewake(&psw, &ep->poll_wait); + + /* + * We need to lock this because we could be hit by + * eventpoll_release_file() while we're freeing the "struct eventpoll". + * We do not need to hold "ep->sem" here because the epoll file + * is on the way to be removed and no one has references to it + * anymore. The only hit might come from eventpoll_release_file() but + * holding "epsem" is sufficent here. + */ + down(&epsem); + + /* + * Walks through the whole tree by unregistering poll callbacks. + */ + for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) { + epi = rb_entry(rbp, struct epitem, rbn); + + ep_unregister_pollwait(ep, epi); + } + + /* + * Walks through the whole hash by freeing each "struct epitem". At this + * point we are sure no poll callbacks will be lingering around, and also by + * write-holding "sem" we can be sure that no file cleanup code will hit + * us during this operation. So we can avoid the lock on "ep->lock". + */ + while ((rbp = rb_first(&ep->rbr)) != 0) { + epi = rb_entry(rbp, struct epitem, rbn); + ep_remove(ep, epi); + } + + up(&epsem); +} + + +/* + * Search the file inside the eventpoll hash. It add usage count to + * the returned item, so the caller must call ep_release_epitem() + * after finished using the "struct epitem". + */ +static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd) +{ + int kcmp; + unsigned long flags; + struct rb_node *rbp; + struct epitem *epi, *epir = NULL; + struct epoll_filefd ffd; + + EP_SET_FFD(&ffd, file, fd); + read_lock_irqsave(&ep->lock, flags); + for (rbp = ep->rbr.rb_node; rbp; ) { + epi = rb_entry(rbp, struct epitem, rbn); + kcmp = EP_CMP_FFD(&ffd, &epi->ffd); + if (kcmp > 0) + rbp = rbp->rb_right; + else if (kcmp < 0) + rbp = rbp->rb_left; + else { + ep_use_epitem(epi); + epir = epi; + break; + } + } + read_unlock_irqrestore(&ep->lock, flags); + + DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_find(%p) -> %p\n", + current, file, epir)); + + return epir; +} + + +/* + * Increment the usage count of the "struct epitem" making it sure + * that the user will have a valid pointer to reference. + */ +static void ep_use_epitem(struct epitem *epi) +{ + + atomic_inc(&epi->usecnt); +} + + +/* + * Decrement ( release ) the usage count by signaling that the user + * has finished using the structure. It might lead to freeing the + * structure itself if the count goes to zero. + */ +static void ep_release_epitem(struct epitem *epi) +{ + + if (atomic_dec_and_test(&epi->usecnt)) + EPI_MEM_FREE(epi); +} + + +/* + * This is the callback that is used to add our wait queue to the + * target file wakeup lists. + */ +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; + } +} + + +static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) +{ + int kcmp; + struct rb_node **p = &ep->rbr.rb_node, *parent = NULL; + struct epitem *epic; + + while (*p) { + parent = *p; + epic = rb_entry(parent, struct epitem, rbn); + kcmp = EP_CMP_FFD(&epi->ffd, &epic->ffd); + if (kcmp > 0) + p = &parent->rb_right; + else + p = &parent->rb_left; + } + rb_link_node(&epi->rbn, parent, p); + rb_insert_color(&epi->rbn, &ep->rbr); +} + + +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); + + /* + * We have to check if something went wrong during the poll wait queue + * install process. Namely an allocation for a wait queue failed due + * high memory pressure. + */ + if (epi->nwait < 0) + goto eexit_2; + + /* Add the current item to the list of active epoll hook for this file */ + spin_lock(&tfile->f_ep_lock); + list_add_tail(&epi->fllink, &tfile->f_ep_links); + spin_unlock(&tfile->f_ep_lock); + + /* We have to drop the new item inside our item list to keep track of it */ + write_lock_irqsave(&ep->lock, flags); + + /* Add the current item to the rb-tree */ + ep_rbtree_insert(ep, epi); + + /* If the file is already "ready" we drop it inside the ready list */ + if ((revents & event->events) && !EP_IS_LINKED(&epi->rdllink)) { + list_add_tail(&epi->rdllink, &ep->rdllist); + + /* Notify waiting tasks that events are available */ + 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); + + DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_insert(%p, %p, %d)\n", + current, ep, tfile, fd)); + + return 0; + +eexit_2: + ep_unregister_pollwait(ep, epi); + + /* + * We need to do this because an event could have been arrived on some + * allocated wait queue. + */ + write_lock_irqsave(&ep->lock, flags); + if (EP_IS_LINKED(&epi->rdllink)) + EP_LIST_DEL(&epi->rdllink); + write_unlock_irqrestore(&ep->lock, flags); + + EPI_MEM_FREE(epi); +eexit_1: + return error; +} + + +/* + * Modify the interest event mask by dropping an event if the new mask + * has a match in the current file status. + */ +static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_event *event) +{ + int pwake = 0; + unsigned int revents; + unsigned long flags; + + /* + * Set the new event interest mask before calling f_op->poll(), otherwise + * a potential race might occur. In fact if we do this operation inside + * the lock, an event might happen between the f_op->poll() call and the + * new event set registering. + */ + epi->event.events = event->events; + + /* + * 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 = epi->ffd.file->f_op->poll(epi->ffd.file, NULL); + + write_lock_irqsave(&ep->lock, flags); + + /* Copy the data member from inside the lock */ + epi->event.data = event->data; + + /* + * If the item is not linked to the hash it means that it's on its + * way toward the removal. Do nothing in this case. + */ + if (EP_RB_LINKED(&epi->rbn)) { + /* + * If the item is "hot" and it is not registered inside the ready + * list, push it inside. If the item is not "hot" and it is currently + * registered inside the ready list, unlink it. + */ + if (revents & event->events) { + if (!EP_IS_LINKED(&epi->rdllink)) { + list_add_tail(&epi->rdllink, &ep->rdllist); + + /* Notify waiting tasks that events are available */ + 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); + + return 0; +} + + +/* + * This function unregister poll callbacks from the associated file descriptor. + * Since this must be called without holding "ep->lock" the atomic exchange trick + * will protect us from multiple unregister. + */ +static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi) +{ + int nwait; + struct list_head *lsthead = &epi->pwqlist; + struct eppoll_entry *pwq; + + /* This is called without locks, so we need the atomic exchange */ + nwait = xchg(&epi->nwait, 0); + + if (nwait) { + while (!list_empty(lsthead)) { + pwq = list_entry(lsthead->next, struct eppoll_entry, llink); + + EP_LIST_DEL(&pwq->llink); + remove_wait_queue(pwq->whead, &pwq->wait); + PWQ_MEM_FREE(pwq); + } + } +} + + +/* + * Unlink the "struct epitem" from all places it might have been hooked up. + * This function must be called with write IRQ lock on "ep->lock". + */ +static int ep_unlink(struct eventpoll *ep, struct epitem *epi) +{ + int error; + + /* + * It can happen that this one is called for an item already unlinked. + * The check protect us from doing a double unlink ( crash ). + */ + error = -ENOENT; + if (!EP_RB_LINKED(&epi->rbn)) + goto eexit_1; + + /* + * Clear the event mask for the unlinked item. This will avoid item + * notifications to be sent after the unlink operation from inside + * the kernel->userspace event transfer |