xhci: Fix failure to give back some cached cancelled URBs.

Only TDs with status TD_CLEARING_CACHE will be given back after
cache is cleared with a set TR deq command.

xhci_invalidate_cached_td() failed to set the TD_CLEARING_CACHE status
for some cancelled TDs as it assumed an endpoint only needs to clear the
TD it stopped on.

This isn't always true. For example with streams enabled an endpoint may
have several stream rings, each stopping on a different TDs.

Note that if an endpoint has several stream rings, the current code
will still only clear the cache of the stream pointed to by the last
cancelled TD in the cancel list.

This patch only focus on making sure all canceled TDs are given back,
avoiding hung task after device removal.
Another fix to solve clearing the caches of all stream rings with
cancelled TDs is needed, but not as urgent.

This issue was simultanously discovered and debugged by
by Tao Wang, with a slightly different fix proposal.

Fixes: 674f843 ("xhci: split handling halted endpoints into two steps")
Cc: <[email protected]> #5.12
Reported-by: Tao Wang <[email protected]>
Signed-off-by: Mathias Nyman <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Greg Kroah-Hartman <[email protected]>

Author: matnyman

drivers/usb/host/xhci-ring.c

@@ -942,17 +942,21 @@ static int xhci_invalidate_cancelled_tds(struct xhci_virt_ep *ep)
 					 td->urb->stream_id);
 		hw_deq &= ~0xf;
 
-		if (td->cancel_status == TD_HALTED) {
-			cached_td = td;
-		} else if (trb_in_td(xhci, td->start_seg, td->first_trb,
-			      td->last_trb, hw_deq, false)) {
+		if (td->cancel_status == TD_HALTED ||
+		    trb_in_td(xhci, td->start_seg, td->first_trb, td->last_trb, hw_deq, false)) {
 			switch (td->cancel_status) {
 			case TD_CLEARED: /* TD is already no-op */
 			case TD_CLEARING_CACHE: /* set TR deq command already queued */
 				break;
 			case TD_DIRTY: /* TD is cached, clear it */
 			case TD_HALTED:
-				/* FIXME  stream case, several stopped rings */
+				td->cancel_status = TD_CLEARING_CACHE;
+				if (cached_td)
+					/* FIXME  stream case, several stopped rings */
+					xhci_dbg(xhci,
+						 "Move dq past stream %u URB %p instead of stream %u URB %p\n",
+						 td->urb->stream_id, td->urb,
+						 cached_td->urb->stream_id, cached_td->urb);
 				cached_td = td;
 				break;
 			}
@@ -961,18 +965,24 @@ static int xhci_invalidate_cancelled_tds(struct xhci_virt_ep *ep)
 			td->cancel_status = TD_CLEARED;
 		}
 	}
-	if (cached_td) {
-		cached_td->cancel_status = TD_CLEARING_CACHE;
 
-		err = xhci_move_dequeue_past_td(xhci, slot_id, ep->ep_index,
-						cached_td->urb->stream_id,
-						cached_td);
-		/* Failed to move past cached td, try just setting it noop */
-		if (err) {
-			td_to_noop(xhci, ring, cached_td, false);
-			cached_td->cancel_status = TD_CLEARED;
+	/* If there's no need to move the dequeue pointer then we're done */
+	if (!cached_td)
+		return 0;
+
+	err = xhci_move_dequeue_past_td(xhci, slot_id, ep->ep_index,
+					cached_td->urb->stream_id,
+					cached_td);
+	if (err) {
+		/* Failed to move past cached td, just set cached TDs to no-op */
+		list_for_each_entry_safe(td, tmp_td, &ep->cancelled_td_list, cancelled_td_list) {
+			if (td->cancel_status != TD_CLEARING_CACHE)
+				continue;
+			xhci_dbg(xhci, "Failed to clear cancelled cached URB %p, mark clear anyway\n",
+				 td->urb);
+			td_to_noop(xhci, ring, td, false);
+			td->cancel_status = TD_CLEARED;
 		}
-		cached_td = NULL;
 	}
 	return 0;
 }