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:
parent
2d23d8ba31
commit
7312b5ddd4
@ -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));
|
||||
|
Loading…
Reference in New Issue
Block a user