- /*
- * 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, ep);
- if (error)
- goto eexit_2;
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
- current, size, fd));
-
- return fd;
-
-eexit_2:
- ep_free(ep);
- kfree(ep);
-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_has_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 RB tree */
- 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;
-}
-
-
-/*
- * 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 > EP_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;
-}
-
-
-#ifdef TIF_RESTORE_SIGMASK
-
-/*
- * Implement the event wait interface for the eventpoll file. It is the kernel
- * part of the user space epoll_pwait(2).
- */
-asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events,
- int maxevents, int timeout, const sigset_t __user *sigmask,
- size_t sigsetsize)
-{
- int error;
- sigset_t ksigmask, sigsaved;
-
- /*
- * If the caller wants a certain signal mask to be set during the wait,
- * we apply it here.
- */
- if (sigmask) {
- 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);
- }
-
- error = sys_epoll_wait(epfd, events, maxevents, timeout);
-
- /*
- * If we changed the signal mask, we need to restore the original one.
- * In case we've got a signal while waiting, we do not restore the
- * signal mask yet, and we allow do_signal() to deliver the signal on
- * the way back to userspace, before the signal mask is restored.
- */
- if (sigmask) {
- if (error == -EINTR) {
- memcpy(¤t->saved_sigmask, &sigsaved,
- sizeof(sigsaved));
- set_thread_flag(TIF_RESTORE_SIGMASK);
- } else
- sigprocmask(SIG_SETMASK, &sigsaved, NULL);
- }
-
- return error;
-}
-
-#endif /* #ifdef TIF_RESTORE_SIGMASK */
-
-
-/*
- * Creates the file descriptor to be used by the epoll interface.
- */
-static int ep_getfd(int *efd, struct inode **einode, struct file **efile,
- struct eventpoll *ep)
-{
- 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();
- if (IS_ERR(inode)) {
- error = PTR_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_path.mnt = mntget(eventpoll_mnt);
- file->f_path.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 = ep;
-
- /* 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_alloc(struct eventpoll **pep)
-{
- struct eventpoll *ep = kzalloc(sizeof(*ep), GFP_KERNEL);
-
- if (!ep)
- return -ENOMEM;
-
- 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;
-
- *pep = ep;
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_alloc() 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 "epmutex" is sufficent here.
- */
- mutex_lock(&epmutex);
-
- /*
- * 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 tree 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);
- }