[15/17] userfaultfd: make userfaultfd_write non blocking

Commit Message

Andrea Arcangeli Oct. 3, 2014, 5:08 p.m. UTC

It is generally inefficient to ask the wakeup of userfault ranges
where there's not a single userfault address read through
userfaultfd_read earlier and in turn waiting a wakeup. However it may
come handy to wakeup the same userfault range twice in case of
multiple thread faulting on the same address. But we should still
return an error so if the application thinks this occurrence can never
happen it will know it hit a bug. So just return -ENOENT instead of
blocking.

Signed-off-by: Andrea Arcangeli <[e-mail]>
---
 fs/userfaultfd.c | 34 +++++-----------------------------
 1 file changed, 5 insertions(+), 29 deletions(-)

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

Patch

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 62b827e..2667d0d 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -458,9 +458,7 @@  static ssize_t userfaultfd_write(struct file *file, const char __user *buf,
 				 size_t count, loff_t *ppos)
 {
 	struct userfaultfd_ctx *ctx = file->private_data;
-	ssize_t res;
 	__u64 range[2];
-	DECLARE_WAITQUEUE(wait, current);
 
 	if (ctx->state == USERFAULTFD_STATE_ASK_PROTOCOL) {
 		__u64 protocol;
@@ -488,34 +486,12 @@  static ssize_t userfaultfd_write(struct file *file, const char __user *buf,
 	if (range[0] >= range[1])
 		return -ERANGE;
 
-	spin_lock(&ctx->fd_wqh.lock);
-	__add_wait_queue(&ctx->fd_wqh, &wait);
-	for (;;) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		/* always take the fd_wqh lock before the fault_wqh lock */
-		if (find_userfault(ctx, NULL, POLLOUT)) {
-			if (!wake_userfault(ctx, range)) {
-				res = sizeof(range);
-				break;
-			}
-		}
-		if (signal_pending(current)) {
-			res = -ERESTARTSYS;
-			break;
-		}
-		if (file->f_flags & O_NONBLOCK) {
-			res = -EAGAIN;
-			break;
-		}
-		spin_unlock(&ctx->fd_wqh.lock);
-		schedule();
-		spin_lock(&ctx->fd_wqh.lock);
-	}
-	__remove_wait_queue(&ctx->fd_wqh, &wait);
-	__set_current_state(TASK_RUNNING);
-	spin_unlock(&ctx->fd_wqh.lock);
+	/* always take the fd_wqh lock before the fault_wqh lock */
+	if (find_userfault(ctx, NULL, POLLOUT))
+		if (!wake_userfault(ctx, range))
+			return sizeof(range);
 
-	return res;
+	return -ENOENT;
 }
 
 #ifdef CONFIG_PROC_FS