Merge branch 'akpm' (patches from Andrew)

Merge third patch-bomb from Andrew Morton:
 "I'm pretty much done for -rc1 now:

   - the rest of MM, basically

   - lib/ updates

   - checkpatch, epoll, hfs, fatfs, ptrace, coredump, exit

   - cpu_mask simplifications

   - kexec, rapidio, MAINTAINERS etc, etc.

   - more dma-mapping cleanups/simplifications from hch"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (109 commits)
  MAINTAINERS: add/fix git URLs for various subsystems
  mm: memcontrol: add "sock" to cgroup2 memory.stat
  mm: memcontrol: basic memory statistics in cgroup2 memory controller
  mm: memcontrol: do not uncharge old page in page cache replacement
  Documentation: cgroup: add memory.swap.{current,max} description
  mm: free swap cache aggressively if memcg swap is full
  mm: vmscan: do not scan anon pages if memcg swap limit is hit
  swap.h: move memcg related stuff to the end of the file
  mm: memcontrol: replace mem_cgroup_lruvec_online with mem_cgroup_online
  mm: vmscan: pass memcg to get_scan_count()
  mm: memcontrol: charge swap to cgroup2
  mm: memcontrol: clean up alloc, online, offline, free functions
  mm: memcontrol: flatten struct cg_proto
  mm: memcontrol: rein in the CONFIG space madness
  net: drop tcp_memcontrol.c
  mm: memcontrol: introduce CONFIG_MEMCG_LEGACY_KMEM
  mm: memcontrol: allow to disable kmem accounting for cgroup2
  mm: memcontrol: account "kmem" consumers in cgroup2 memory controller
  mm: memcontrol: move kmem accounting code to CONFIG_MEMCG
  mm: memcontrol: separate kmem code from legacy tcp accounting code
  ...

1 files changed, 21 insertions, 3 deletions

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 1e009cad8d5c..ae1dbcf47e97 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -92,7 +92,7 @@
  */
 
 /* Epoll private bits inside the event mask */
-#define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET)
+#define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE)
 
 /* Maximum number of nesting allowed inside epoll sets */
 #define EP_MAX_NESTS 4
@@ -1002,6 +1002,7 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 	unsigned long flags;
 	struct epitem *epi = ep_item_from_wait(wait);
 	struct eventpoll *ep = epi->ep;
+	int ewake = 0;
 
 	if ((unsigned long)key & POLLFREE) {
 		ep_pwq_from_wait(wait)->whead = NULL;
@@ -1066,8 +1067,10 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 	 * Wake up ( if active ) both the eventpoll wait list and the ->poll()
 	 * wait list.
 	 */
-	if (waitqueue_active(&ep->wq))
+	if (waitqueue_active(&ep->wq)) {
+		ewake = 1;
 		wake_up_locked(&ep->wq);
+	}
 	if (waitqueue_active(&ep->poll_wait))
 		pwake++;
 
@@ -1078,6 +1081,9 @@ out_unlock:
 	if (pwake)
 		ep_poll_safewake(&ep->poll_wait);
 
+	if (epi->event.events & EPOLLEXCLUSIVE)
+		return ewake;
+
 	return 1;
 }
 
@@ -1095,7 +1101,10 @@ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
 		init_waitqueue_func_entry(&pwq->wait, ep_poll_callback);
 		pwq->whead = whead;
 		pwq->base = epi;
-		add_wait_queue(whead, &pwq->wait);
+		if (epi->event.events & EPOLLEXCLUSIVE)
+			add_wait_queue_exclusive(whead, &pwq->wait);
+		else
+			add_wait_queue(whead, &pwq->wait);
 		list_add_tail(&pwq->llink, &epi->pwqlist);
 		epi->nwait++;
 	} else {
@@ -1862,6 +1871,15 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 		goto error_tgt_fput;
 
 	/*
+	 * epoll adds to the wakeup queue at EPOLL_CTL_ADD time only,
+	 * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation.
+	 * Also, we do not currently supported nested exclusive wakeups.
+	 */
+	if ((epds.events & EPOLLEXCLUSIVE) && (op == EPOLL_CTL_MOD ||
+		(op == EPOLL_CTL_ADD && is_file_epoll(tf.file))))
+		goto error_tgt_fput;
+
+	/*
 	 * At this point it is safe to assume that the "private_data" contains
 	 * our own data structure.
 	 */