From: Alan Stern Date: Wed, 17 Sep 2014 15:23:54 +0000 (-0400) Subject: USB: EHCI: unlink QHs even after the controller has stopped X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=375ef46305e47950460390e838ba589101066ae0;p=karo-tx-linux.git USB: EHCI: unlink QHs even after the controller has stopped 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 Reported-by: Joe Lawrence Tested-by: Joe Lawrence Signed-off-by: Greg Kroah-Hartman --- diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 81cda09b47e3..488a30836c36 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -965,8 +965,6 @@ 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));