Commit 7312b5dd authored by Alan Stern's avatar Alan Stern Committed by Greg Kroah-Hartman

USB: EHCI: unlink QHs even after the controller has stopped

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: default avatarAlan Stern <stern@rowland.harvard.edu>
Reported-by: default avatarJoe Lawrence <joe.lawrence@stratus.com>
Tested-by: default avatarJoe Lawrence <joe.lawrence@stratus.com>
CC: <stable@vger.kernel.org>
Signed-off-by: default avatarGreg Kroah-Hartman <gregkh@linuxfoundation.org>
parent 2d23d8ba
...@@ -965,8 +965,6 @@ ehci_endpoint_disable (struct usb_hcd *hcd, struct usb_host_endpoint *ep) ...@@ -965,8 +965,6 @@ ehci_endpoint_disable (struct usb_hcd *hcd, struct usb_host_endpoint *ep)
} }
qh->exception = 1; qh->exception = 1;
if (ehci->rh_state < EHCI_RH_RUNNING)
qh->qh_state = QH_STATE_IDLE;
switch (qh->qh_state) { switch (qh->qh_state) {
case QH_STATE_LINKED: case QH_STATE_LINKED:
WARN_ON(!list_empty(&qh->qtd_list)); WARN_ON(!list_empty(&qh->qtd_list));
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment