userfaultfd: avoid missing wakeups during refile in userfaultfd_read

aagit · torvalds · commit 2c5b7e1be74f · 2015-09-04T16:54:41.000-07:00
During the refile in userfaultfd_read both waitqueues could look empty to
the lockless wake_userfault().  Use a seqcount to prevent this false
negative that could leave an userfault blocked.

Signed-off-by: Andrea Arcangeli &lt;aarcange@redhat.com&gt;
Cc: Pavel Emelyanov &lt;xemul@parallels.com&gt;
Cc: Dave Hansen &lt;dave.hansen@intel.com&gt;
Cc: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
@@ -45,6 +45,8 @@ struct userfaultfd_ctx {
 	wait_queue_head_t fault_wqh;
 	/* waitqueue head for the pseudo fd to wakeup poll/read */
 	wait_queue_head_t fd_wqh;
+	/* a refile sequence protected by fault_pending_wqh lock */
+	struct seqcount refile_seq;
 	/* pseudo fd refcounting */
 	atomic_t refcount;
 	/* userfaultfd syscall flags */
@@ -546,6 +548,15 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 		spin_lock(&ctx->fault_pending_wqh.lock);
 		uwq = find_userfault(ctx);
 		if (uwq) {
+			/*
+			 * Use a seqcount to repeat the lockless check
+			 * in wake_userfault() to avoid missing
+			 * wakeups because during the refile both
+			 * waitqueue could become empty if this is the
+			 * only userfault.
+			 */
+			write_seqcount_begin(&ctx->refile_seq);
+
 			/*
 			 * The fault_pending_wqh.lock prevents the uwq
 			 * to disappear from under us.
@@ -570,6 +581,8 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 			list_del(&uwq->wq.task_list);
 			__add_wait_queue(&ctx->fault_wqh, &uwq->wq);
 
+			write_seqcount_end(&ctx->refile_seq);
+
 			/* careful to always initialize msg if ret == 0 */
 			*msg = uwq->msg;
 			spin_unlock(&ctx->fault_pending_wqh.lock);
@@ -647,6 +660,9 @@ static void __wake_userfault(struct userfaultfd_ctx *ctx,
 static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
 					   struct userfaultfd_wake_range *range)
 {
+	unsigned seq;
+	bool need_wakeup;
+
 	/*
 	 * To be sure waitqueue_active() is not reordered by the CPU
 	 * before the pagetable update, use an explicit SMP memory
@@ -662,8 +678,13 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
 	 * userfaults yet. So we take the spinlock only when we're
 	 * sure we've userfaults to wake.
 	 */
-	if (waitqueue_active(&ctx->fault_pending_wqh) ||
-	    waitqueue_active(&ctx->fault_wqh))
+	do {
+		seq = read_seqcount_begin(&ctx->refile_seq);
+		need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) ||
+			waitqueue_active(&ctx->fault_wqh);
+		cond_resched();
+	} while (read_seqcount_retry(&ctx->refile_seq, seq));
+	if (need_wakeup)
 		__wake_userfault(ctx, range);
 }
 
@@ -1219,6 +1240,7 @@ static void init_once_userfaultfd_ctx(void *mem)
 	init_waitqueue_head(&ctx->fault_pending_wqh);
 	init_waitqueue_head(&ctx->fault_wqh);
 	init_waitqueue_head(&ctx->fd_wqh);
+	seqcount_init(&ctx->refile_seq);
 }
 
 /**
