epoll: Add a flag, EPOLLWAKEUP, to prevent suspend while epoll events are ready

When an epoll_event, that has the EPOLLWAKEUP flag set, is ready, a
wakeup_source will be active to prevent suspend. This can be used to
handle wakeup events from a driver that support poll, e.g. input, if
that driver wakes up the waitqueue passed to epoll before allowing
suspend.

Signed-off-by: Arve Hjønnevåg <[e-mail]>
Reviewed-by: NeilBrown <[e-mail]>
Signed-off-by: Rafael J. Wysocki <[e-mail]>

fs/eventpoll.c

···
 #include <linux/bitops.h>
 #include <linux/mutex.h>
 #include <linux/anon_inodes.h>
+#include <linux/device.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/mman.h>
···
  */
 
 /* Epoll private bits inside the event mask */
-#define EP_PRIVATE_BITS (EPOLLONESHOT | EPOLLET)
+#define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET)
 
 /* Maximum number of nesting allowed inside epoll sets */
 #define EP_MAX_NESTS 4
···
 	/* List header used to link this item to the "struct file" items list */
 	struct list_head fllink;
 
+	/* wakeup_source used when EPOLLWAKEUP is set */
+	struct wakeup_source *ws;
+
 	/* The structure that describe the interested events and the source fd */
 	struct epoll_event event;
 };
···
 	 * holding ->lock.
 	 */
 	struct epitem *ovflist;
+
+	/* wakeup_source used when ep_scan_ready_list is running */
+	struct wakeup_source *ws;
 
 	/* The user that created the eventpoll descriptor */
 	struct user_struct *user;
···
 		 * queued into ->ovflist but the "txlist" might already
 		 * contain them, and the list_splice() below takes care of them.
 		 */
-		if (!ep_is_linked(&epi->rdllink))
+		if (!ep_is_linked(&epi->rdllink)) {
 			list_add_tail(&epi->rdllink, &ep->rdllist);
+			__pm_stay_awake(epi->ws);
+		}
 	}
 	/*
 	 * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after
···
 	 * Quickly re-inject items left on "txlist".
 	 */
 	list_splice(&txlist, &ep->rdllist);
+	__pm_relax(ep->ws);
 
 	if (!list_empty(&ep->rdllist)) {
 		/*
···
 		list_del_init(&epi->rdllink);
 	spin_unlock_irqrestore(&ep->lock, flags);
 
+	wakeup_source_unregister(epi->ws);
+
 	/* At this point it is safe to free the eventpoll item */
 	kmem_cache_free(epi_cache, epi);
 
···
 	mutex_unlock(&epmutex);
 	mutex_destroy(&ep->mtx);
 	free_uid(ep->user);
+	wakeup_source_unregister(ep->ws);
 	kfree(ep);
 }
 
···
 			 * callback, but it's not actually ready, as far as
 			 * caller requested events goes. We can remove it here.
 			 */
+			__pm_relax(epi->ws);
 			list_del_init(&epi->rdllink);
 		}
 	}
···
 		if (epi->next == EP_UNACTIVE_PTR) {
 			epi->next = ep->ovflist;
 			ep->ovflist = epi;
+			if (epi->ws) {
+				/*
+				 * Activate ep->ws since epi->ws may get
+				 * deactivated at any time.
+				 */
+				__pm_stay_awake(ep->ws);
+			}
+
 		}
 		goto out_unlock;
 	}
 
 	/* If this file is already in the ready list we exit soon */
-	if (!ep_is_linked(&epi->rdllink))
+	if (!ep_is_linked(&epi->rdllink)) {
 		list_add_tail(&epi->rdllink, &ep->rdllist);
+		__pm_stay_awake(epi->ws);
+	}
 
 	/*
 	 * Wake up ( if active ) both the eventpoll wait list and the ->poll()
···
 	return error;
 }
 
+static int ep_create_wakeup_source(struct epitem *epi)
+{
+	const char *name;
+
+	if (!epi->ep->ws) {
+		epi->ep->ws = wakeup_source_register("eventpoll");
+		if (!epi->ep->ws)
+			return -ENOMEM;
+	}
+
+	name = epi->ffd.file->f_path.dentry->d_name.name;
+	epi->ws = wakeup_source_register(name);
+	if (!epi->ws)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void ep_destroy_wakeup_source(struct epitem *epi)
+{
+	wakeup_source_unregister(epi->ws);
+	epi->ws = NULL;
+}
+
 /*
  * Must be called with "mtx" held.
  */
···
 	epi->event = *event;
 	epi->nwait = 0;
 	epi->next = EP_UNACTIVE_PTR;
+	if (epi->event.events & EPOLLWAKEUP) {
+		error = ep_create_wakeup_source(epi);
+		if (error)
+			goto error_create_wakeup_source;
+	} else {
+		epi->ws = NULL;
+	}
 
 	/* Initialize the poll table using the queue callback */
 	epq.epi = 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);
+		__pm_stay_awake(epi->ws);
 
 		/* Notify waiting tasks that events are available */
 		if (waitqueue_active(&ep->wq))
···
 		list_del_init(&epi->rdllink);
 	spin_unlock_irqrestore(&ep->lock, flags);
 
+	wakeup_source_unregister(epi->ws);
+
+error_create_wakeup_source:
 	kmem_cache_free(epi_cache, epi);
 
 	return error;
···
 	epi->event.events = event->events;
 	pt._key = event->events;
 	epi->event.data = event->data; /* protected by mtx */
+	if (epi->event.events & EPOLLWAKEUP) {
+		if (!epi->ws)
+			ep_create_wakeup_source(epi);
+	} else if (epi->ws) {
+		ep_destroy_wakeup_source(epi);
+	}
 
 	/*
 	 * Get current event bits. We can safely use the file* here because
···
 		spin_lock_irq(&ep->lock);
 		if (!ep_is_linked(&epi->rdllink)) {
 			list_add_tail(&epi->rdllink, &ep->rdllist);
+			__pm_stay_awake(epi->ws);
 
 			/* Notify waiting tasks that events are available */
 			if (waitqueue_active(&ep->wq))
···
 	     !list_empty(head) && eventcnt < esed->maxevents;) {
 		epi = list_first_entry(head, struct epitem, rdllink);
 
+		/*
+		 * Activate ep->ws before deactivating epi->ws to prevent
+		 * triggering auto-suspend here (in case we reactive epi->ws
+		 * below).
+		 *
+		 * This could be rearranged to delay the deactivation of epi->ws
+		 * instead, but then epi->ws would temporarily be out of sync
+		 * with ep_is_linked().
+		 */
+		if (epi->ws && epi->ws->active)
+			__pm_stay_awake(ep->ws);
+		__pm_relax(epi->ws);
 		list_del_init(&epi->rdllink);
 
 		pt._key = epi->event.events;
···
 			if (__put_user(revents, &uevent->events) ||
 			    __put_user(epi->event.data, &uevent->data)) {
 				list_add(&epi->rdllink, head);
+				__pm_stay_awake(epi->ws);
 				return eventcnt ? eventcnt : -EFAULT;
 			}
 			eventcnt++;
···
 				 * poll callback will queue them in ep->ovflist.
 				 */
 				list_add_tail(&epi->rdllink, &ep->rdllist);
+				__pm_stay_awake(epi->ws);
 			}
 		}
 	}
···
 	/* The target file descriptor must support poll */
 	error = -EPERM;
 	if (!tfile->f_op || !tfile->f_op->poll)
+		goto error_tgt_fput;
+
+	/* Check if EPOLLWAKEUP is allowed */
+	if ((epds.events & EPOLLWAKEUP) && !capable(CAP_EPOLLWAKEUP))
 		goto error_tgt_fput;
 
 	/*

include/linux/capability.h

···
 
 #define CAP_WAKE_ALARM            35
 
+/* Allow preventing system suspends while epoll events are pending */
 
-#define CAP_LAST_CAP         CAP_WAKE_ALARM
+#define CAP_EPOLLWAKEUP      36
+
+#define CAP_LAST_CAP         CAP_EPOLLWAKEUP
 
 #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
 

include/linux/eventpoll.h

···
 #define EPOLL_CTL_DEL 2
 #define EPOLL_CTL_MOD 3
 
+/*
+ * Request the handling of system wakeup events so as to prevent system suspends
+ * from happening while those events are being processed.
+ *
+ * Assuming neither EPOLLET nor EPOLLONESHOT is set, system suspends will not be
+ * re-allowed until epoll_wait is called again after consuming the wakeup
+ * event(s).
+ *
+ * Requires CAP_EPOLLWAKEUP
+ */
+#define EPOLLWAKEUP (1 << 29)
+
 /* Set the One Shot behaviour for the target file descriptor */
 #define EPOLLONESHOT (1 << 30)