USB: EHCI: work around silicon bug in Intel's EHCI controllers

commit 6402c796d3b4205d3d7296157956c5100a05d7d6 upstream.

This patch (as1660) works around a hardware problem present in some
(if not all) Intel EHCI controllers.  After a QH has been unlinked
from the async schedule and the corresponding IAA interrupt has
occurred, the controller is not supposed access the QH and its qTDs.
There certainly shouldn't be any more DMA writes to those structures.
Nevertheless, Intel's controllers have been observed to perform a
final writeback to the QH's overlay region and to the most recent qTD.
For more information and a test program to determine whether this
problem is present in a particular controller, see

	http://marc.info/?l=linux-usb&m=135492071812265&w=2
	http://marc.info/?l=linux-usb&m=136182570800963&w=2

This patch works around the problem by always waiting for two IAA
cycles when unlinking an async QH.  The extra IAA delay gives the
controller time to perform its final writeback.

Surprisingly enough, the effects of this silicon bug have gone
undetected until quite recently.  More through luck than anything
else, it hasn't caused any apparent problems.  However, it does
interact badly with the path that follows this one, so it needs to be
addressed.

This is the first part of a fix for the regression reported at:

	https://bugs.launchpad.net/bugs/1088733

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Tested-by: Stephen Thirlwall <sdt@dr.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index b416a3fc99594f30afbb15995191313f6c9315a6..5726cb144abfdf425870168589e0d609e12d059a 100644 (file)
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -748,11 +748,9 @@ static irqreturn_t ehci_irq (struct usb_hcd *hcd)
                /* guard against (alleged) silicon errata */
                if (cmd & CMD_IAAD)
                        ehci_dbg(ehci, "IAA with IAAD still set?\n");
-               if (ehci->async_iaa) {
+               if (ehci->async_iaa)
                        COUNT(ehci->stats.iaa);
-                       end_unlink_async(ehci);
-               } else
-                       ehci_dbg(ehci, "IAA with nothing unlinked?\n");
+               end_unlink_async(ehci);
        }
 
        /* remote wakeup [4.3.1] */

diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c
index eda2cf47f9e5f90aa361071542fed28653d7c9f5..5464665f0b6aa7b86b472b080213715dcacfe5f4 100644 (file)
--- a/drivers/usb/host/ehci-q.c
+++ b/drivers/usb/host/ehci-q.c
@@ -1178,7 +1178,7 @@ static void single_unlink_async(struct ehci_hcd *ehci, struct ehci_qh *qh)
        struct ehci_qh          *prev;
 
        /* Add to the end of the list of QHs waiting for the next IAAD */
-       qh->qh_state = QH_STATE_UNLINK;
+       qh->qh_state = QH_STATE_UNLINK_WAIT;
        if (ehci->async_unlink)
                ehci->async_unlink_last->unlink_next = qh;
        else
@@ -1221,9 +1221,19 @@ static void start_iaa_cycle(struct ehci_hcd *ehci, bool nested)
 
                /* Do only the first waiting QH (nVidia bug?) */
                qh = ehci->async_unlink;
-               ehci->async_iaa = qh;
-               ehci->async_unlink = qh->unlink_next;
-               qh->unlink_next = NULL;
+
+               /*
+                * Intel (?) bug: The HC can write back the overlay region
+                * even after the IAA interrupt occurs.  In self-defense,
+                * always go through two IAA cycles for each QH.
+                */
+               if (qh->qh_state == QH_STATE_UNLINK_WAIT) {
+                       qh->qh_state = QH_STATE_UNLINK;
+               } else {
+                       ehci->async_iaa = qh;
+                       ehci->async_unlink = qh->unlink_next;
+                       qh->unlink_next = NULL;
+               }
 
                /* Make sure the unlinks are all visible to the hardware */
                wmb();