diff mbox

[4/7] userfaultfd: avoid missing wakeups during refile in userfaultfd_read

Message ID 1434388931-24487-5-git-send-email-aarcange@redhat.com (mailing list archive)
State New, archived
Headers show

Commit Message

Andrea Arcangeli June 15, 2015, 5:22 p.m. UTC
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 <aarcange@redhat.com>
---
 fs/userfaultfd.c | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 8286ec8..f9e11ec 100644
--- 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 */
@@ -547,6 +549,15 @@  static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 		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);
@@ -648,6 +661,9 @@  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
@@ -663,8 +679,13 @@  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);
 }
 
@@ -1223,6 +1244,7 @@  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);
 }
 
 /**