1 files changed, 86 insertions, 18 deletions

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index b1c8e23ddf65..adbe328b957c 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -600,8 +600,13 @@ static void ep_remove_wait_queue(struct eppoll_entry *pwq)
 	wait_queue_head_t *whead;
 
 	rcu_read_lock();
-	/* If it is cleared by POLLFREE, it should be rcu-safe */
-	whead = rcu_dereference(pwq->whead);
+	/*
+	 * If it is cleared by POLLFREE, it should be rcu-safe.
+	 * If we read NULL we need a barrier paired with
+	 * smp_store_release() in ep_poll_callback(), otherwise
+	 * we rely on whead->lock.
+	 */
+	whead = smp_load_acquire(&pwq->whead);
 	if (whead)
 		remove_wait_queue(whead, &pwq->wait);
 	rcu_read_unlock();
@@ -960,10 +965,14 @@ static void ep_show_fdinfo(struct seq_file *m, struct file *f)
 	mutex_lock(&ep->mtx);
 	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
 		struct epitem *epi = rb_entry(rbp, struct epitem, rbn);
+		struct inode *inode = file_inode(epi->ffd.file);
 
-		seq_printf(m, "tfd: %8d events: %8x data: %16llx\n",
+		seq_printf(m, "tfd: %8d events: %8x data: %16llx "
+			   " pos:%lli ino:%lx sdev:%x\n",
 			   epi->ffd.fd, epi->event.events,
-			   (long long)epi->event.data);
+			   (long long)epi->event.data,
+			   (long long)epi->ffd.file->f_pos,
+			   inode->i_ino, inode->i_sb->s_dev);
 		if (seq_has_overflowed(m))
 			break;
 	}
@@ -1073,6 +1082,50 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
 	return epir;
 }
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff)
+{
+	struct rb_node *rbp;
+	struct epitem *epi;
+
+	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+		epi = rb_entry(rbp, struct epitem, rbn);
+		if (epi->ffd.fd == tfd) {
+			if (toff == 0)
+				return epi;
+			else
+				toff--;
+		}
+		cond_resched();
+	}
+
+	return NULL;
+}
+
+struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
+				     unsigned long toff)
+{
+	struct file *file_raw;
+	struct eventpoll *ep;
+	struct epitem *epi;
+
+	if (!is_file_epoll(file))
+		return ERR_PTR(-EINVAL);
+
+	ep = file->private_data;
+
+	mutex_lock(&ep->mtx);
+	epi = ep_find_tfd(ep, tfd, toff);
+	if (epi)
+		file_raw = epi->ffd.file;
+	else
+		file_raw = ERR_PTR(-ENOENT);
+	mutex_unlock(&ep->mtx);
+
+	return file_raw;
+}
+#endif /* CONFIG_CHECKPOINT_RESTORE */
+
 /*
  * This is the callback that is passed to the wait queue wakeup
  * mechanism. It is called by the stored file descriptors when they
@@ -1086,17 +1139,6 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
 	struct eventpoll *ep = epi->ep;
 	int ewake = 0;
 
-	if ((unsigned long)key & POLLFREE) {
-		ep_pwq_from_wait(wait)->whead = NULL;
-		/*
-		 * whead = NULL above can race with ep_remove_wait_queue()
-		 * which can do another remove_wait_queue() after us, so we
-		 * can't use __remove_wait_queue(). whead->lock is held by
-		 * the caller.
-		 */
-		list_del_init(&wait->entry);
-	}
-
 	spin_lock_irqsave(&ep->lock, flags);
 
 	ep_set_busy_poll_napi_id(epi);
@@ -1180,10 +1222,26 @@ out_unlock:
 	if (pwake)
 		ep_poll_safewake(&ep->poll_wait);
 
-	if (epi->event.events & EPOLLEXCLUSIVE)
-		return ewake;
+	if (!(epi->event.events & EPOLLEXCLUSIVE))
+		ewake = 1;
+
+	if ((unsigned long)key & POLLFREE) {
+		/*
+		 * If we race with ep_remove_wait_queue() it can miss
+		 * ->whead = NULL and do another remove_wait_queue() after
+		 * us, so we can't use __remove_wait_queue().
+		 */
+		list_del_init(&wait->entry);
+		/*
+		 * ->whead != NULL protects us from the race with ep_free()
+		 * or ep_remove(), ep_remove_wait_queue() takes whead->lock
+		 * held by the caller. Once we nullify it, nothing protects
+		 * ep/epi or even wait.
+		 */
+		smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL);
+	}
 
-	return 1;
+	return ewake;
 }
 
 /*
@@ -1748,6 +1806,16 @@ fetch_events:
 			 * to TASK_INTERRUPTIBLE before doing the checks.
 			 */
 			set_current_state(TASK_INTERRUPTIBLE);
+			/*
+			 * Always short-circuit for fatal signals to allow
+			 * threads to make a timely exit without the chance of
+			 * finding more events available and fetching
+			 * repeatedly.
+			 */
+			if (fatal_signal_pending(current)) {
+				res = -EINTR;
+				break;
+			}
 			if (ep_events_available(ep) || timed_out)
 				break;
 			if (signal_pending(current)) {