iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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 committed by Greg Kroah-Hartman
parent 2d23d8ba31
commit 7312b5ddd4
1 changed files with 0 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
drivers/usb/host/ehci-hcd.c
View File

@ -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));