#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/compat.h>
+#include <linux/rculist.h>
/*
* LOCKING:
* of these on a server and we do not want this to take another cache line.
*/
struct epitem {
- /* RB tree node used to link this structure to the eventpoll RB tree */
- struct rb_node rbn;
+ union {
+ /* RB tree node links this structure to the eventpoll RB tree */
+ struct rb_node rbn;
+ /* Used to free the struct epitem */
+ struct rcu_head rcu;
+ };
/* List header used to link this structure to the eventpoll ready list */
struct list_head rdllink;
static long zero;
static long long_max = LONG_MAX;
-ctl_table epoll_table[] = {
+struct ctl_table epoll_table[] = {
{
.procname = "max_user_watches",
.data = &max_user_watches,
* @sproc: Pointer to the scan callback.
* @priv: Private opaque data passed to the @sproc callback.
* @depth: The current depth of recursive f_op->poll calls.
+ * @ep_locked: caller already holds ep->mtx
*
* Returns: The same integer error code returned by the @sproc callback.
*/
static int ep_scan_ready_list(struct eventpoll *ep,
int (*sproc)(struct eventpoll *,
struct list_head *, void *),
- void *priv,
- int depth)
+ void *priv, int depth, bool ep_locked)
{
int error, pwake = 0;
unsigned long flags;
* We need to lock this because we could be hit by
* eventpoll_release_file() and epoll_ctl().
*/
- mutex_lock_nested(&ep->mtx, depth);
+
+ if (!ep_locked)
+ mutex_lock_nested(&ep->mtx, depth);
/*
* Steal the ready list, and re-init the original one to the
}
spin_unlock_irqrestore(&ep->lock, flags);
- mutex_unlock(&ep->mtx);
+ if (!ep_locked)
+ mutex_unlock(&ep->mtx);
/* We have to call this outside the lock */
if (pwake)
return error;
}
+static void epi_rcu_free(struct rcu_head *head)
+{
+ struct epitem *epi = container_of(head, struct epitem, rcu);
+ kmem_cache_free(epi_cache, epi);
+}
+
/*
* Removes a "struct epitem" from the eventpoll RB tree and deallocates
* all the associated resources. Must be called with "mtx" held.
/* Remove the current item from the list of epoll hooks */
spin_lock(&file->f_lock);
- if (ep_is_linked(&epi->fllink))
- list_del_init(&epi->fllink);
+ list_del_rcu(&epi->fllink);
spin_unlock(&file->f_lock);
rb_erase(&epi->rbn, &ep->rbr);
spin_unlock_irqrestore(&ep->lock, flags);
wakeup_source_unregister(ep_wakeup_source(epi));
-
- /* At this point it is safe to free the eventpoll item */
- kmem_cache_free(epi_cache, epi);
+ /*
+ * At this point it is safe to free the eventpoll item. Use the union
+ * field epi->rcu, since we are trying to minimize the size of
+ * 'struct epitem'. The 'rbn' field is no longer in use. Protected by
+ * ep->mtx. The rcu read side, reverse_path_check_proc(), does not make
+ * use of the rbn field.
+ */
+ call_rcu(&epi->rcu, epi_rcu_free);
atomic_long_dec(&ep->user->epoll_watches);
epi = rb_entry(rbp, struct epitem, rbn);
ep_unregister_pollwait(ep, epi);
+ cond_resched();
}
/*
while ((rbp = rb_first(&ep->rbr)) != NULL) {
epi = rb_entry(rbp, struct epitem, rbn);
ep_remove(ep, epi);
+ cond_resched();
}
mutex_unlock(&ep->mtx);
return 0;
}
+static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
+ poll_table *pt);
+
+struct readyevents_arg {
+ struct eventpoll *ep;
+ bool locked;
+};
+
static int ep_poll_readyevents_proc(void *priv, void *cookie, int call_nests)
{
- return ep_scan_ready_list(priv, ep_read_events_proc, NULL, call_nests + 1);
+ struct readyevents_arg *arg = priv;
+
+ return ep_scan_ready_list(arg->ep, ep_read_events_proc, NULL,
+ call_nests + 1, arg->locked);
}
static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
{
int pollflags;
struct eventpoll *ep = file->private_data;
+ struct readyevents_arg arg;
+
+ /*
+ * During ep_insert() we already hold the ep->mtx for the tfile.
+ * Prevent re-aquisition.
+ */
+ arg.locked = wait && (wait->_qproc == ep_ptable_queue_proc);
+ arg.ep = ep;
/* Insert inside our poll wait queue */
poll_wait(file, &ep->poll_wait, wait);
* could re-enter here.
*/
pollflags = ep_call_nested(&poll_readywalk_ncalls, EP_MAX_NESTS,
- ep_poll_readyevents_proc, ep, ep, current);
+ ep_poll_readyevents_proc, &arg, ep, current);
return pollflags != -1 ? pollflags : 0;
}
#ifdef CONFIG_PROC_FS
-static int ep_show_fdinfo(struct seq_file *m, struct file *f)
+static void ep_show_fdinfo(struct seq_file *m, struct file *f)
{
struct eventpoll *ep = f->private_data;
struct rb_node *rbp;
- int ret = 0;
mutex_lock(&ep->mtx);
for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
struct epitem *epi = rb_entry(rbp, struct epitem, rbn);
- ret = seq_printf(m, "tfd: %8d events: %8x data: %16llx\n",
- epi->ffd.fd, epi->event.events,
- (long long)epi->event.data);
- if (ret)
+ seq_printf(m, "tfd: %8d events: %8x data: %16llx\n",
+ epi->ffd.fd, epi->event.events,
+ (long long)epi->event.data);
+ if (seq_has_overflowed(m))
break;
}
mutex_unlock(&ep->mtx);
-
- return ret;
}
#endif
*/
void eventpoll_release_file(struct file *file)
{
- struct list_head *lsthead = &file->f_ep_links;
struct eventpoll *ep;
- struct epitem *epi;
+ struct epitem *epi, *next;
/*
* We don't want to get "file->f_lock" because it is not
* Besides, ep_remove() acquires the lock, so we can't hold it here.
*/
mutex_lock(&epmutex);
-
- while (!list_empty(lsthead)) {
- epi = list_first_entry(lsthead, struct epitem, fllink);
-
+ list_for_each_entry_safe(epi, next, &file->f_ep_links, fllink) {
ep = epi->ep;
- list_del_init(&epi->fllink);
mutex_lock_nested(&ep->mtx, 0);
ep_remove(ep, epi);
mutex_unlock(&ep->mtx);
}
-
mutex_unlock(&epmutex);
}
struct file *child_file;
struct epitem *epi;
- list_for_each_entry(epi, &file->f_ep_links, fllink) {
+ /* CTL_DEL can remove links here, but that can't increase our count */
+ rcu_read_lock();
+ list_for_each_entry_rcu(epi, &file->f_ep_links, fllink) {
child_file = epi->ep->file;
if (is_file_epoll(child_file)) {
if (list_empty(&child_file->f_ep_links)) {
"file is not an ep!\n");
}
}
+ rcu_read_unlock();
return error;
}
* Must be called with "mtx" held.
*/
static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
- struct file *tfile, int fd)
+ struct file *tfile, int fd, int full_check)
{
int error, revents, pwake = 0;
unsigned long flags;
/* Add the current item to the list of active epoll hook for this file */
spin_lock(&tfile->f_lock);
- list_add_tail(&epi->fllink, &tfile->f_ep_links);
+ list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links);
spin_unlock(&tfile->f_lock);
/*
/* now check if we've created too many backpaths */
error = -EINVAL;
- if (reverse_path_check())
+ if (full_check && reverse_path_check())
goto error_remove_epi;
/* We have to drop the new item inside our item list to keep track of it */
error_remove_epi:
spin_lock(&tfile->f_lock);
- if (ep_is_linked(&epi->fllink))
- list_del_init(&epi->fllink);
+ list_del_rcu(&epi->fllink);
spin_unlock(&tfile->f_lock);
rb_erase(&epi->rbn, &ep->rbr);
esed.maxevents = maxevents;
esed.events = events;
- return ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0);
+ return ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0, false);
}
static inline struct timespec ep_set_mstimeout(long ms)
{
int res = 0, eavail, timed_out = 0;
unsigned long flags;
- long slack = 0;
+ u64 slack = 0;
wait_queue_t wait;
ktime_t expires, *to = NULL;
spin_lock_irqsave(&ep->lock, flags);
}
- __remove_wait_queue(&ep->wq, &wait);
- set_current_state(TASK_RUNNING);
+ __remove_wait_queue(&ep->wq, &wait);
+ __set_current_state(TASK_RUNNING);
}
check_events:
/* Is it worth to try to dig for events ? */
struct epoll_event __user *, event)
{
int error;
- int did_lock_epmutex = 0;
- struct file *file, *tfile;
+ int full_check = 0;
+ struct fd f, tf;
struct eventpoll *ep;
struct epitem *epi;
struct epoll_event epds;
+ struct eventpoll *tep = NULL;
error = -EFAULT;
if (ep_op_has_event(op) &&
copy_from_user(&epds, event, sizeof(struct epoll_event)))
goto error_return;
- /* Get the "struct file *" for the eventpoll file */
error = -EBADF;
- file = fget(epfd);
- if (!file)
+ f = fdget(epfd);
+ if (!f.file)
goto error_return;
/* Get the "struct file *" for the target file */
- tfile = fget(fd);
- if (!tfile)
+ tf = fdget(fd);
+ if (!tf.file)
goto error_fput;
/* The target file descriptor must support poll */
error = -EPERM;
- if (!tfile->f_op || !tfile->f_op->poll)
+ if (!tf.file->f_op->poll)
goto error_tgt_fput;
/* Check if EPOLLWAKEUP is allowed */
- ep_take_care_of_epollwakeup(&epds);
+ if (ep_op_has_event(op))
+ ep_take_care_of_epollwakeup(&epds);
/*
* We have to check that the file structure underneath the file descriptor
* adding an epoll file descriptor inside itself.
*/
error = -EINVAL;
- if (file == tfile || !is_file_epoll(file))
+ if (f.file == tf.file || !is_file_epoll(f.file))
goto error_tgt_fput;
/*
* At this point it is safe to assume that the "private_data" contains
* our own data structure.
*/
- ep = file->private_data;
+ ep = f.file->private_data;
/*
* When we insert an epoll file descriptor, inside another epoll file
* and hang them on the tfile_check_list, so we can check that we
* haven't created too many possible wakeup paths.
*
- * We need to hold the epmutex across both ep_insert and ep_remove
- * b/c we want to make sure we are looking at a coherent view of
- * epoll network.
+ * We do not need to take the global 'epumutex' on EPOLL_CTL_ADD when
+ * the epoll file descriptor is attaching directly to a wakeup source,
+ * unless the epoll file descriptor is nested. The purpose of taking the
+ * 'epmutex' on add is to prevent complex toplogies such as loops and
+ * deep wakeup paths from forming in parallel through multiple
+ * EPOLL_CTL_ADD operations.
*/
- if (op == EPOLL_CTL_ADD || op == EPOLL_CTL_DEL) {
- mutex_lock(&epmutex);
- did_lock_epmutex = 1;
- }
+ mutex_lock_nested(&ep->mtx, 0);
if (op == EPOLL_CTL_ADD) {
- if (is_file_epoll(tfile)) {
- error = -ELOOP;
- if (ep_loop_check(ep, tfile) != 0) {
- clear_tfile_check_list();
- goto error_tgt_fput;
+ if (!list_empty(&f.file->f_ep_links) ||
+ is_file_epoll(tf.file)) {
+ full_check = 1;
+ mutex_unlock(&ep->mtx);
+ mutex_lock(&epmutex);
+ if (is_file_epoll(tf.file)) {
+ error = -ELOOP;
+ if (ep_loop_check(ep, tf.file) != 0) {
+ clear_tfile_check_list();
+ goto error_tgt_fput;
+ }
+ } else
+ list_add(&tf.file->f_tfile_llink,
+ &tfile_check_list);
+ mutex_lock_nested(&ep->mtx, 0);
+ if (is_file_epoll(tf.file)) {
+ tep = tf.file->private_data;
+ mutex_lock_nested(&tep->mtx, 1);
}
- } else
- list_add(&tfile->f_tfile_llink, &tfile_check_list);
+ }
}
- mutex_lock_nested(&ep->mtx, 0);
-
/*
* Try to lookup the file inside our RB tree, Since we grabbed "mtx"
* above, we can be sure to be able to use the item looked up by
* ep_find() till we release the mutex.
*/
- epi = ep_find(ep, tfile, fd);
+ epi = ep_find(ep, tf.file, fd);
error = -EINVAL;
switch (op) {
case EPOLL_CTL_ADD:
if (!epi) {
epds.events |= POLLERR | POLLHUP;
- error = ep_insert(ep, &epds, tfile, fd);
+ error = ep_insert(ep, &epds, tf.file, fd, full_check);
} else
error = -EEXIST;
- clear_tfile_check_list();
+ if (full_check)
+ clear_tfile_check_list();
break;
case EPOLL_CTL_DEL:
if (epi)
error = -ENOENT;
break;
}
+ if (tep != NULL)
+ mutex_unlock(&tep->mtx);
mutex_unlock(&ep->mtx);
error_tgt_fput:
- if (did_lock_epmutex)
+ if (full_check)
mutex_unlock(&epmutex);
- fput(tfile);
+ fdput(tf);
error_fput:
- fput(file);
+ fdput(f);
error_return:
return error;
return -EINVAL;
if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
return -EFAULT;
- sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
- sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+ sigsaved = current->blocked;
+ set_current_blocked(&ksigmask);
}
error = sys_epoll_wait(epfd, events, maxevents, timeout);
sizeof(sigsaved));
set_restore_sigmask();
} else
- sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ set_current_blocked(&sigsaved);
}
return error;
if (copy_from_user(&csigmask, sigmask, sizeof(csigmask)))
return -EFAULT;
sigset_from_compat(&ksigmask, &csigmask);
- sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
- sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+ sigsaved = current->blocked;
+ set_current_blocked(&ksigmask);
}
err = sys_epoll_wait(epfd, events, maxevents, timeout);
sizeof(sigsaved));
set_restore_sigmask();
} else
- sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ set_current_blocked(&sigsaved);
}
return err;