USB: EHCI: go back to using the system clock for QH unlinks

This patch (as1477) fixes a problem affecting a few types of EHCI
controller.  Contrary to what one might expect, these controllers
automatically stop their internal frame counter when no ports are
enabled.  Since ehci-hcd currently relies on the frame counter for
determining when it should unlink QHs from the async schedule, those
controllers run into trouble: The frame counter stops and the QHs
never get unlinked.

Some systems have also experienced other problems traced back to
commit b963801164618e25fbdc0cd452ce49c3628b46c8 (USB: ehci-hcd unlink
speedups), which made the original switch from using the system clock
to using the frame counter.  It never became clear what the reason was
for these problems, but evidently it is related to use of the frame
counter.

To fix all these problems, this patch more or less reverts that commit
and goes back to using the system clock.  But this can't be done
cleanly because other changes have since been made to the scan_async()
subroutine.  One of these changes involved the tricky logic that tries
to avoid rescanning QHs that have already been seen when the scanning
loop is restarted, which happens whenever an URB is given back.
Switching back to clock-based unlinks would make this logic even more
complicated.

Therefore the new code doesn't rescan the entire async list whenever a
giveback occurs.  Instead it rescans only the current QH and continues
on from there.  This requires the use of a separate pointer to keep
track of the next QH to scan, since the current QH may be unlinked
while the scanning is in progress.  That new pointer must be global,
so that it can be adjusted forward whenever the _next_ QH gets
unlinked.  (uhci-hcd uses this same trick.)

Simplification of the scanning loop removes a level of indentation,
which accounts for the size of the patch.  The amount of code changed
is relatively small, and it isn't exactly a reversion of the
b963801164 commit.

This fixes Bugzilla #32432.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
CC: <stable@kernel.org>
Tested-by: Matej Kenda <matejken@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

1 files changed, 40 insertions, 42 deletions

diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c
index 5d6bc624c96..9bf3c0d983c 100644
--- a/drivers/usb/host/ehci-q.c
+++ b/drivers/usb/host/ehci-q.c
@@ -1231,6 +1231,8 @@ static void start_unlink_async (struct ehci_hcd *ehci, struct ehci_qh *qh)
 
 	prev->hw->hw_next = qh->hw->hw_next;
 	prev->qh_next = qh->qh_next;
+	if (ehci->qh_scan_next == qh)
+		ehci->qh_scan_next = qh->qh_next.qh;
 	wmb ();
 
 	/* If the controller isn't running, we don't have to wait for it */
@@ -1256,53 +1258,49 @@ static void scan_async (struct ehci_hcd *ehci)
 	struct ehci_qh		*qh;
 	enum ehci_timer_action	action = TIMER_IO_WATCHDOG;
 
-	ehci->stamp = ehci_readl(ehci, &ehci->regs->frame_index);
 	timer_action_done (ehci, TIMER_ASYNC_SHRINK);
-rescan:
 	stopped = !HC_IS_RUNNING(ehci_to_hcd(ehci)->state);
-	qh = ehci->async->qh_next.qh;
-	if (likely (qh != NULL)) {
-		do {
-			/* clean any finished work for this qh */
-			if (!list_empty(&qh->qtd_list) && (stopped ||
-					qh->stamp != ehci->stamp)) {
-				int temp;
-
-				/* unlinks could happen here; completion
-				 * reporting drops the lock.  rescan using
-				 * the latest schedule, but don't rescan
-				 * qhs we already finished (no looping)
-				 * unless the controller is stopped.
-				 */
-				qh = qh_get (qh);
-				qh->stamp = ehci->stamp;
-				temp = qh_completions (ehci, qh);
-				if (qh->needs_rescan)
-					unlink_async(ehci, qh);
-				qh_put (qh);
-				if (temp != 0) {
-					goto rescan;
-				}
-			}
 
-			/* unlink idle entries, reducing DMA usage as well
-			 * as HCD schedule-scanning costs.  delay for any qh
-			 * we just scanned, there's a not-unusual case that it
-			 * doesn't stay idle for long.
-			 * (plus, avoids some kind of re-activation race.)
+	ehci->qh_scan_next = ehci->async->qh_next.qh;
+	while (ehci->qh_scan_next) {
+		qh = ehci->qh_scan_next;
+		ehci->qh_scan_next = qh->qh_next.qh;
+ rescan:
+		/* clean any finished work for this qh */
+		if (!list_empty(&qh->qtd_list)) {
+			int temp;
+
+			/*
+			 * Unlinks could happen here; completion reporting
+			 * drops the lock.  That's why ehci->qh_scan_next
+			 * always holds the next qh to scan; if the next qh
+			 * gets unlinked then ehci->qh_scan_next is adjusted
+			 * in start_unlink_async().
 			 */
-			if (list_empty(&qh->qtd_list)
-					&& qh->qh_state == QH_STATE_LINKED) {
-				if (!ehci->reclaim && (stopped ||
-					((ehci->stamp - qh->stamp) & 0x1fff)
-						>= EHCI_SHRINK_FRAMES * 8))
-					start_unlink_async(ehci, qh);
-				else
-					action = TIMER_ASYNC_SHRINK;
-			}
+			qh = qh_get(qh);
+			temp = qh_completions(ehci, qh);
+			if (qh->needs_rescan)
+				unlink_async(ehci, qh);
+			qh->unlink_time = jiffies + EHCI_SHRINK_JIFFIES;
+			qh_put(qh);
+			if (temp != 0)
+				goto rescan;
+		}
 
-			qh = qh->qh_next.qh;
-		} while (qh);
+		/* unlink idle entries, reducing DMA usage as well
+		 * as HCD schedule-scanning costs.  delay for any qh
+		 * we just scanned, there's a not-unusual case that it
+		 * doesn't stay idle for long.
+		 * (plus, avoids some kind of re-activation race.)
+		 */
+		if (list_empty(&qh->qtd_list)
+				&& qh->qh_state == QH_STATE_LINKED) {
+			if (!ehci->reclaim && (stopped ||
+					time_after_eq(jiffies, qh->unlink_time)))
+				start_unlink_async(ehci, qh);
+			else
+				action = TIMER_ASYNC_SHRINK;
+		}
 	}
 	if (action == TIMER_ASYNC_SHRINK)
 		timer_action (ehci, TIMER_ASYNC_SHRINK);