[PATCH 3.13 111/163] USB: EHCI: unlink QHs even after the controller has stopped

[Kamal Mostafa]

3.13.11.9 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Alan Stern <stern at rowland.harvard.edu>

commit 7312b5ddd47fee2356baa78c5516ef8e04eed452 upstream.

Old code in ehci-hcd tries to expedite disabling endpoints after the
controller has stopped, by destroying the endpoint's associated QH
without first unlinking the QH.  This was necessary back when the
driver wasn't so careful about keeping track of the controller's
state.

But now we are careful about it, and the driver knows that when the
controller isn't running, no unlinking delay is needed.  Furthermore,
skipping the unlink step will trigger a BUG() in qh_destroy() when the
preceding QH is released, because the link pointer will be non-NULL.

Removing the lines that skip the unlinking step and go directly to
QH_STATE_IDLE fixes the problem.

Signed-off-by: Alan Stern <stern at rowland.harvard.edu>
Reported-by: Joe Lawrence <joe.lawrence at stratus.com>
Tested-by: Joe Lawrence <joe.lawrence at stratus.com>
Signed-off-by: Greg Kroah-Hartman <gregkh at linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal at canonical.com>
---
 drivers/usb/host/ehci-hcd.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 4dfd6fb..86e6d39 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -973,8 +973,6 @@ rescan:
 	}
 
 	qh->exception = 1;
-	if (ehci->rh_state < EHCI_RH_RUNNING)
-		qh->qh_state = QH_STATE_IDLE;
 	switch (qh->qh_state) {
 	case QH_STATE_LINKED:
 		WARN_ON(!list_empty(&qh->qtd_list));
-- 
1.9.1