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: Alan Stern <stern@rowland.harvard.edu>
Reported-by: Joe Lawrence <joe.lawrence@stratus.com>
Tested-by: Joe Lawrence <joe.lawrence@stratus.com>
CC: <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Alan Stern 2014-09-17 11:23:54 -04:00 коммит произвёл Greg Kroah-Hartman
Родитель 2d23d8ba31
Коммит 7312b5ddd4
1 изменённых файлов: 0 добавлений и 2 удалений

Просмотреть файл

@ -965,8 +965,6 @@ rescan:
} }
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));