Merge tag 'for-usb-next-2014-03-06' of git://git.kernel.org/pub/scm/linux/kernel/git/sarah/xhci into usb-next

Sarah writes:

xhci: Streams and UAS cleanups, misc cleanups for 3.15

Hi Greg,

Here's 76 patches to queue to usb-next for 3.15.

The bulk of this rather large pull request is the UAS driver cleanup, the
xHCI streams fixes, and the new userspace API for usbfs to be able to use
and alloc/free bulk streams.  I've hammered on these changes, and the UAS
driver seems solid.  The performance numbers are pretty spiffy too:

root@xanatos:~# echo 3 > /proc/sys/vm/drop_caches; dd if=/dev/sdb of=/dev/null bs=4k count=1000M iflag=count_bytes
256000+0 records in
256000+0 records out
1048576000 bytes (1.0 GB) copied, 3.28557 s, 319 MB/s

That's about 100 MB/s faster than my fastest Bulk-only-Transport mass
storage drive.

There's a couple of miscellaneous cleanup patches and non-urgent bug fixes
in here as well:

7969943789df xhci: add the meaningful IRQ description if it is empty
bcffae7708eb xhci: Prevent runtime pm from autosuspending during initialization
e587b8b270d3 xhci: make warnings greppable
25cd2882e2fc usb/xhci: Change how we indicate a host supports Link PM.

Sarah Sharp

7 files changed, 303 insertions, 122 deletions

diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 9992fbfec85f..1ad6bc1951c7 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -732,9 +732,11 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		/* Set the U1 and U2 exit latencies. */
 		memcpy(buf, &usb_bos_descriptor,
 				USB_DT_BOS_SIZE + USB_DT_USB_SS_CAP_SIZE);
-		temp = readl(&xhci->cap_regs->hcs_params3);
-		buf[12] = HCS_U1_LATENCY(temp);
-		put_unaligned_le16(HCS_U2_LATENCY(temp), &buf[13]);
+		if ((xhci->quirks & XHCI_LPM_SUPPORT)) {
+			temp = readl(&xhci->cap_regs->hcs_params3);
+			buf[12] = HCS_U1_LATENCY(temp);
+			put_unaligned_le16(HCS_U2_LATENCY(temp), &buf[13]);
+		}
 
 		/* Indicate whether the host has LTM support. */
 		temp = readl(&xhci->cap_regs->hcc_params);
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index bce4391a0e7d..c089668308ad 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -149,14 +149,140 @@ static void xhci_link_rings(struct xhci_hcd *xhci, struct xhci_ring *ring,
 	}
 }
 
+/*
+ * We need a radix tree for mapping physical addresses of TRBs to which stream
+ * ID they belong to.  We need to do this because the host controller won't tell
+ * us which stream ring the TRB came from.  We could store the stream ID in an
+ * event data TRB, but that doesn't help us for the cancellation case, since the
+ * endpoint may stop before it reaches that event data TRB.
+ *
+ * The radix tree maps the upper portion of the TRB DMA address to a ring
+ * segment that has the same upper portion of DMA addresses.  For example, say I
+ * have segments of size 1KB, that are always 1KB aligned.  A segment may
+ * start at 0x10c91000 and end at 0x10c913f0.  If I use the upper 10 bits, the
+ * key to the stream ID is 0x43244.  I can use the DMA address of the TRB to
+ * pass the radix tree a key to get the right stream ID:
+ *
+ *	0x10c90fff >> 10 = 0x43243
+ *	0x10c912c0 >> 10 = 0x43244
+ *	0x10c91400 >> 10 = 0x43245
+ *
+ * Obviously, only those TRBs with DMA addresses that are within the segment
+ * will make the radix tree return the stream ID for that ring.
+ *
+ * Caveats for the radix tree:
+ *
+ * The radix tree uses an unsigned long as a key pair.  On 32-bit systems, an
+ * unsigned long will be 32-bits; on a 64-bit system an unsigned long will be
+ * 64-bits.  Since we only request 32-bit DMA addresses, we can use that as the
+ * key on 32-bit or 64-bit systems (it would also be fine if we asked for 64-bit
+ * PCI DMA addresses on a 64-bit system).  There might be a problem on 32-bit
+ * extended systems (where the DMA address can be bigger than 32-bits),
+ * if we allow the PCI dma mask to be bigger than 32-bits.  So don't do that.
+ */
+static int xhci_insert_segment_mapping(struct radix_tree_root *trb_address_map,
+		struct xhci_ring *ring,
+		struct xhci_segment *seg,
+		gfp_t mem_flags)
+{
+	unsigned long key;
+	int ret;
+
+	key = (unsigned long)(seg->dma >> TRB_SEGMENT_SHIFT);
+	/* Skip any segments that were already added. */
+	if (radix_tree_lookup(trb_address_map, key))
+		return 0;
+
+	ret = radix_tree_maybe_preload(mem_flags);
+	if (ret)
+		return ret;
+	ret = radix_tree_insert(trb_address_map,
+			key, ring);
+	radix_tree_preload_end();
+	return ret;
+}
+
+static void xhci_remove_segment_mapping(struct radix_tree_root *trb_address_map,
+		struct xhci_segment *seg)
+{
+	unsigned long key;
+
+	key = (unsigned long)(seg->dma >> TRB_SEGMENT_SHIFT);
+	if (radix_tree_lookup(trb_address_map, key))
+		radix_tree_delete(trb_address_map, key);
+}
+
+static int xhci_update_stream_segment_mapping(
+		struct radix_tree_root *trb_address_map,
+		struct xhci_ring *ring,
+		struct xhci_segment *first_seg,
+		struct xhci_segment *last_seg,
+		gfp_t mem_flags)
+{
+	struct xhci_segment *seg;
+	struct xhci_segment *failed_seg;
+	int ret;
+
+	if (WARN_ON_ONCE(trb_address_map == NULL))
+		return 0;
+
+	seg = first_seg;
+	do {
+		ret = xhci_insert_segment_mapping(trb_address_map,
+				ring, seg, mem_flags);
+		if (ret)
+			goto remove_streams;
+		if (seg == last_seg)
+			return 0;
+		seg = seg->next;
+	} while (seg != first_seg);
+
+	return 0;
+
+remove_streams:
+	failed_seg = seg;
+	seg = first_seg;
+	do {
+		xhci_remove_segment_mapping(trb_address_map, seg);
+		if (seg == failed_seg)
+			return ret;
+		seg = seg->next;
+	} while (seg != first_seg);
+
+	return ret;
+}
+
+static void xhci_remove_stream_mapping(struct xhci_ring *ring)
+{
+	struct xhci_segment *seg;
+
+	if (WARN_ON_ONCE(ring->trb_address_map == NULL))
+		return;
+
+	seg = ring->first_seg;
+	do {
+		xhci_remove_segment_mapping(ring->trb_address_map, seg);
+		seg = seg->next;
+	} while (seg != ring->first_seg);
+}
+
+static int xhci_update_stream_mapping(struct xhci_ring *ring, gfp_t mem_flags)
+{
+	return xhci_update_stream_segment_mapping(ring->trb_address_map, ring,
+			ring->first_seg, ring->last_seg, mem_flags);
+}
+
 /* XXX: Do we need the hcd structure in all these functions? */
 void xhci_ring_free(struct xhci_hcd *xhci, struct xhci_ring *ring)
 {
 	if (!ring)
 		return;
 
-	if (ring->first_seg)
+	if (ring->first_seg) {
+		if (ring->type == TYPE_STREAM)
+			xhci_remove_stream_mapping(ring);
 		xhci_free_segments_for_ring(xhci, ring->first_seg);
+	}
 
 	kfree(ring);
 }
@@ -349,6 +475,21 @@ int xhci_ring_expansion(struct xhci_hcd *xhci, struct xhci_ring *ring,
 	if (ret)
 		return -ENOMEM;
 
+	if (ring->type == TYPE_STREAM)
+		ret = xhci_update_stream_segment_mapping(ring->trb_address_map,
+						ring, first, last, flags);
+	if (ret) {
+		struct xhci_segment *next;
+		do {
+			next = first->next;
+			xhci_segment_free(xhci, first);
+			if (first == last)
+				break;
+			first = next;
+		} while (true);
+		return ret;
+	}
+
 	xhci_link_rings(xhci, ring, first, last, num_segs);
 	xhci_dbg_trace(xhci, trace_xhci_dbg_ring_expansion,
 			"ring expansion succeed, now has %d segments",
@@ -434,12 +575,12 @@ static void xhci_free_stream_ctx(struct xhci_hcd *xhci,
 		struct xhci_stream_ctx *stream_ctx, dma_addr_t dma)
 {
 	struct device *dev = xhci_to_hcd(xhci)->self.controller;
+	size_t size = sizeof(struct xhci_stream_ctx) * num_stream_ctxs;
 
-	if (num_stream_ctxs > MEDIUM_STREAM_ARRAY_SIZE)
-		dma_free_coherent(dev,
-				sizeof(struct xhci_stream_ctx)*num_stream_ctxs,
+	if (size > MEDIUM_STREAM_ARRAY_SIZE)
+		dma_free_coherent(dev, size,
 				stream_ctx, dma);
-	else if (num_stream_ctxs <= SMALL_STREAM_ARRAY_SIZE)
+	else if (size <= SMALL_STREAM_ARRAY_SIZE)
 		return dma_pool_free(xhci->small_streams_pool,
 				stream_ctx, dma);
 	else
@@ -462,12 +603,12 @@ static struct xhci_stream_ctx *xhci_alloc_stream_ctx(struct xhci_hcd *xhci,
 		gfp_t mem_flags)
 {
 	struct device *dev = xhci_to_hcd(xhci)->self.controller;
+	size_t size = sizeof(struct xhci_stream_ctx) * num_stream_ctxs;
 
-	if (num_stream_ctxs > MEDIUM_STREAM_ARRAY_SIZE)
-		return dma_alloc_coherent(dev,
-				sizeof(struct xhci_stream_ctx)*num_stream_ctxs,
+	if (size > MEDIUM_STREAM_ARRAY_SIZE)
+		return dma_alloc_coherent(dev, size,
 				dma, mem_flags);
-	else if (num_stream_ctxs <= SMALL_STREAM_ARRAY_SIZE)
+	else if (size <= SMALL_STREAM_ARRAY_SIZE)
 		return dma_pool_alloc(xhci->small_streams_pool,
 				mem_flags, dma);
 	else
@@ -510,36 +651,6 @@ struct xhci_ring *xhci_stream_id_to_ring(
  * The number of stream contexts in the stream context array may be bigger than
  * the number of streams the driver wants to use.  This is because the number of
  * stream context array entries must be a power of two.
- *
- * We need a radix tree for mapping physical addresses of TRBs to which stream
- * ID they belong to.  We need to do this because the host controller won't tell
- * us which stream ring the TRB came from.  We could store the stream ID in an
- * event data TRB, but that doesn't help us for the cancellation case, since the
- * endpoint may stop before it reaches that event data TRB.
- *
- * The radix tree maps the upper portion of the TRB DMA address to a ring
- * segment that has the same upper portion of DMA addresses.  For example, say I
- * have segments of size 1KB, that are always 64-byte aligned.  A segment may
- * start at 0x10c91000 and end at 0x10c913f0.  If I use the upper 10 bits, the
- * key to the stream ID is 0x43244.  I can use the DMA address of the TRB to
- * pass the radix tree a key to get the right stream ID:
- *
- * 	0x10c90fff >> 10 = 0x43243
- * 	0x10c912c0 >> 10 = 0x43244
- * 	0x10c91400 >> 10 = 0x43245
- *
- * Obviously, only those TRBs with DMA addresses that are within the segment
- * will make the radix tree return the stream ID for that ring.
- *
- * Caveats for the radix tree:
- *
- * The radix tree uses an unsigned long as a key pair.  On 32-bit systems, an
- * unsigned long will be 32-bits; on a 64-bit system an unsigned long will be
- * 64-bits.  Since we only request 32-bit DMA addresses, we can use that as the
- * key on 32-bit or 64-bit systems (it would also be fine if we asked for 64-bit
- * PCI DMA addresses on a 64-bit system).  There might be a problem on 32-bit
- * extended systems (where the DMA address can be bigger than 32-bits),
- * if we allow the PCI dma mask to be bigger than 32-bits.  So don't do that.
  */
 struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci,
 		unsigned int num_stream_ctxs,
@@ -548,7 +659,6 @@ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci,
 	struct xhci_stream_info *stream_info;
 	u32 cur_stream;
 	struct xhci_ring *cur_ring;
-	unsigned long key;
 	u64 addr;
 	int ret;
 
@@ -603,6 +713,7 @@ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci,
 		if (!cur_ring)
 			goto cleanup_rings;
 		cur_ring->stream_id = cur_stream;
+		cur_ring->trb_address_map = &stream_info->trb_address_map;
 		/* Set deq ptr, cycle bit, and stream context type */
 		addr = cur_ring->first_seg->dma |
 			SCT_FOR_CTX(SCT_PRI_TR) |
@@ -612,10 +723,7 @@ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci,
 		xhci_dbg(xhci, "Setting stream %d ring ptr to 0x%08llx\n",
 				cur_stream, (unsigned long long) addr);
 
-		key = (unsigned long)
-			(cur_ring->first_seg->dma >> TRB_SEGMENT_SHIFT);
-		ret = radix_tree_insert(&stream_info->trb_address_map,
-				key, cur_ring);
+		ret = xhci_update_stream_mapping(cur_ring, mem_flags);
 		if (ret) {
 			xhci_ring_free(xhci, cur_ring);
 			stream_info->stream_rings[cur_stream] = NULL;
@@ -635,9 +743,6 @@ cleanup_rings:
 	for (cur_stream = 1; cur_stream < num_streams; cur_stream++) {
 		cur_ring = stream_info->stream_rings[cur_stream];
 		if (cur_ring) {
-			addr = cur_ring->first_seg->dma;
-			radix_tree_delete(&stream_info->trb_address_map,
-					addr >> TRB_SEGMENT_SHIFT);
 			xhci_ring_free(xhci, cur_ring);
 			stream_info->stream_rings[cur_stream] = NULL;
 		}
@@ -698,7 +803,6 @@ void xhci_free_stream_info(struct xhci_hcd *xhci,
 {
 	int cur_stream;
 	struct xhci_ring *cur_ring;
-	dma_addr_t addr;
 
 	if (!stream_info)
 		return;
@@ -707,9 +811,6 @@ void xhci_free_stream_info(struct xhci_hcd *xhci,
 			cur_stream++) {
 		cur_ring = stream_info->stream_rings[cur_stream];
 		if (cur_ring) {
-			addr = cur_ring->first_seg->dma;
-			radix_tree_delete(&stream_info->trb_address_map,
-					addr >> TRB_SEGMENT_SHIFT);
 			xhci_ring_free(xhci, cur_ring);
 			stream_info->stream_rings[cur_stream] = NULL;
 		}
@@ -1711,7 +1812,6 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 
 	if (xhci->lpm_command)
 		xhci_free_command(xhci, xhci->lpm_command);
-	xhci->cmd_ring_reserved_trbs = 0;
 	if (xhci->cmd_ring)
 		xhci_ring_free(xhci, xhci->cmd_ring);
 	xhci->cmd_ring = NULL;
@@ -1776,6 +1876,7 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 	}
 
 no_bw:
+	xhci->cmd_ring_reserved_trbs = 0;
 	xhci->num_usb2_ports = 0;
 	xhci->num_usb3_ports = 0;
 	xhci->num_active_eps = 0;
@@ -2274,11 +2375,12 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	/*
 	 * Initialize the ring segment pool.  The ring must be a contiguous
 	 * structure comprised of TRBs.  The TRBs must be 16 byte aligned,
-	 * however, the command ring segment needs 64-byte aligned segments,
-	 * so we pick the greater alignment need.
+	 * however, the command ring segment needs 64-byte aligned segments
+	 * and our use of dma addresses in the trb_address_map radix tree needs
+	 * TRB_SEGMENT_SIZE alignment, so we pick the greater alignment need.
 	 */
 	xhci->segment_pool = dma_pool_create("xHCI ring segments", dev,
-			TRB_SEGMENT_SIZE, 64, xhci->page_size);
+			TRB_SEGMENT_SIZE, TRB_SEGMENT_SIZE, xhci->page_size);
 
 	/* See Table 46 and Note on Figure 55 */
 	xhci->device_pool = dma_pool_create("xHCI input/output contexts", dev,
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 04f986d9234f..47390e369cd4 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -190,6 +190,10 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	struct usb_hcd *hcd;
 
 	driver = (struct hc_driver *)id->driver_data;
+
+	/* Prevent runtime suspending between USB-2 and USB-3 initialization */
+	pm_runtime_get_noresume(&dev->dev);
+
 	/* Register the USB 2.0 roothub.
 	 * FIXME: USB core must know to register the USB 2.0 roothub first.
 	 * This is sort of silly, because we could just set the HCD driver flags
@@ -199,7 +203,7 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	retval = usb_hcd_pci_probe(dev, id);
 
 	if (retval)
-		return retval;
+		goto put_runtime_pm;
 
 	/* USB 2.0 roothub is stored in the PCI device now. */
 	hcd = dev_get_drvdata(&dev->dev);
@@ -222,11 +226,11 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		goto put_usb3_hcd;
 	/* Roothub already marked as USB 3.0 speed */
 
-	/* We know the LPM timeout algorithms for this host, let the USB core
-	 * enable and disable LPM for devices under the USB 3.0 roothub.
-	 */
-	if (xhci->quirks & XHCI_LPM_SUPPORT)
-		hcd_to_bus(xhci->shared_hcd)->root_hub->lpm_capable = 1;
+	if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
+		xhci->shared_hcd->can_do_streams = 1;
+
+	/* USB-2 and USB-3 roothubs initialized, allow runtime pm suspend */
+	pm_runtime_put_noidle(&dev->dev);
 
 	return 0;
 
@@ -234,6 +238,8 @@ put_usb3_hcd:
 	usb_put_hcd(xhci->shared_hcd);
 dealloc_usb2_hcd:
 	usb_hcd_pci_remove(dev);
+put_runtime_pm:
+	pm_runtime_put_noidle(&dev->dev);
 	return retval;
 }
 
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 8affef910782..151901ce1ba9 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -158,6 +158,9 @@ static int xhci_plat_probe(struct platform_device *pdev)
 	 */
 	*((struct xhci_hcd **) xhci->shared_hcd->hcd_priv) = xhci;
 
+	if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
+		xhci->shared_hcd->can_do_streams = 1;
+
 	ret = usb_add_hcd(xhci->shared_hcd, irq, IRQF_SHARED);
 	if (ret)
 		goto put_usb3_hcd;
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 0ed64eb68e48..5f926bea5ab1 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -546,9 +546,9 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci,
 		struct xhci_dequeue_state *state)
 {
 	struct xhci_virt_device *dev = xhci->devs[slot_id];
+	struct xhci_virt_ep *ep = &dev->eps[ep_index];
 	struct xhci_ring *ep_ring;
 	struct xhci_generic_trb *trb;
-	struct xhci_ep_ctx *ep_ctx;
 	dma_addr_t addr;
 
 	ep_ring = xhci_triad_to_transfer_ring(xhci, slot_id,
@@ -573,8 +573,16 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci,
 	/* Dig out the cycle state saved by the xHC during the stop ep cmd */
 	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
 			"Finding endpoint context");
-	ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, ep_index);
-	state->new_cycle_state = 0x1 & le64_to_cpu(ep_ctx->deq);
+	/* 4.6.9 the css flag is written to the stream context for streams */
+	if (ep->ep_state & EP_HAS_STREAMS) {
+		struct xhci_stream_ctx *ctx =
+			&ep->stream_info->stream_ctx_array[stream_id];
+		state->new_cycle_state = 0x1 & le64_to_cpu(ctx->stream_ring);
+	} else {
+		struct xhci_ep_ctx *ep_ctx
+			= xhci_get_ep_ctx(xhci, dev->out_ctx, ep_index);
+		state->new_cycle_state = 0x1 & le64_to_cpu(ep_ctx->deq);
+	}
 
 	state->new_deq_ptr = cur_td->last_trb;
 	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
@@ -892,6 +900,57 @@ remove_finished_td:
 	/* Return to the event handler with xhci->lock re-acquired */
 }
 
+static void xhci_kill_ring_urbs(struct xhci_hcd *xhci, struct xhci_ring *ring)
+{
+	struct xhci_td *cur_td;
+
+	while (!list_empty(&ring->td_list)) {
+		cur_td = list_first_entry(&ring->td_list,
+				struct xhci_td, td_list);
+		list_del_init(&cur_td->td_list);
+		if (!list_empty(&cur_td->cancelled_td_list))
+			list_del_init(&cur_td->cancelled_td_list);
+		xhci_giveback_urb_in_irq(xhci, cur_td, -ESHUTDOWN);
+	}
+}
+
+static void xhci_kill_endpoint_urbs(struct xhci_hcd *xhci,
+		int slot_id, int ep_index)
+{
+	struct xhci_td *cur_td;
+	struct xhci_virt_ep *ep;
+	struct xhci_ring *ring;
+
+	ep = &xhci->devs[slot_id]->eps[ep_index];
+	if ((ep->ep_state & EP_HAS_STREAMS) ||
+			(ep->ep_state & EP_GETTING_NO_STREAMS)) {
+		int stream_id;
+
+		for (stream_id = 0; stream_id < ep->stream_info->num_streams;
+				stream_id++) {
+			xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
+					"Killing URBs for slot ID %u, ep index %u, stream %u",
+					slot_id, ep_index, stream_id + 1);
+			xhci_kill_ring_urbs(xhci,
+					ep->stream_info->stream_rings[stream_id]);
+		}
+	} else {
+		ring = ep->ring;
+		if (!ring)
+			return;
+		xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
+				"Killing URBs for slot ID %u, ep index %u",
+				slot_id, ep_index);
+		xhci_kill_ring_urbs(xhci, ring);
+	}
+	while (!list_empty(&ep->cancelled_td_list)) {
+		cur_td = list_first_entry(&ep->cancelled_td_list,
+				struct xhci_td, cancelled_td_list);
+		list_del_init(&cur_td->cancelled_td_list);
+		xhci_giveback_urb_in_irq(xhci, cur_td, -ESHUTDOWN);
+	}
+}
+
 /* Watchdog timer function for when a stop endpoint command fails to complete.
  * In this case, we assume the host controller is broken or dying or dead.  The
  * host may still be completing some other events, so we have to be careful to
@@ -915,9 +974,6 @@ void xhci_stop_endpoint_command_watchdog(unsigned long arg)
 {
 	struct xhci_hcd *xhci;
 	struct xhci_virt_ep *ep;
-	struct xhci_virt_ep *temp_ep;
-	struct xhci_ring *ring;
-	struct xhci_td *cur_td;
 	int ret, i, j;
 	unsigned long flags;
 
@@ -974,34 +1030,8 @@ void xhci_stop_endpoint_command_watchdog(unsigned long arg)
 	for (i = 0; i < MAX_HC_SLOTS; i++) {
 		if (!xhci->devs[i])
 			continue;
-		for (j = 0; j < 31; j++) {
-			temp_ep = &xhci->devs[i]->eps[j];
-			ring = temp_ep->ring;
-			if (!ring)
-				continue;
-			xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
-					"Killing URBs for slot ID %u, "
-					"ep index %u", i, j);
-			while (!list_empty(&ring->td_list)) {
-				cur_td = list_first_entry(&ring->td_list,
-						struct xhci_td,
-						td_list);
-				list_del_init(&cur_td->td_list);
-				if (!list_empty(&cur_td->cancelled_td_list))
-					list_del_init(&cur_td->cancelled_td_list);
-				xhci_giveback_urb_in_irq(xhci, cur_td,
-						-ESHUTDOWN);
-			}
-			while (!list_empty(&temp_ep->cancelled_td_list)) {
-				cur_td = list_first_entry(
-						&temp_ep->cancelled_td_list,
-						struct xhci_td,
-						cancelled_td_list);
-				list_del_init(&cur_td->cancelled_td_list);
-				xhci_giveback_urb_in_irq(xhci, cur_td,
-						-ESHUTDOWN);
-			}
-		}
+		for (j = 0; j < 31; j++)
+			xhci_kill_endpoint_urbs(xhci, i, j);
 	}
 	spin_unlock_irqrestore(&xhci->lock, flags);
 	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
@@ -1073,17 +1103,18 @@ static void xhci_handle_cmd_set_deq(struct xhci_hcd *xhci, int slot_id,
 	unsigned int stream_id;
 	struct xhci_ring *ep_ring;
 	struct xhci_virt_device *dev;
+	struct xhci_virt_ep *ep;
 	struct xhci_ep_ctx *ep_ctx;
 	struct xhci_slot_ctx *slot_ctx;
 
 	ep_index = TRB_TO_EP_INDEX(le32_to_cpu(trb->generic.field[3]));
 	stream_id = TRB_TO_STREAM_ID(le32_to_cpu(trb->generic.field[2]));
 	dev = xhci->devs[slot_id];
+	ep = &dev->eps[ep_index];
 
 	ep_ring = xhci_stream_id_to_ring(dev, ep_index, stream_id);
 	if (!ep_ring) {
-		xhci_warn(xhci, "WARN Set TR deq ptr command for "
-				"freed stream ID %u\n",
+		xhci_warn(xhci, "WARN Set TR deq ptr command for freed stream ID %u\n",
 				stream_id);
 		/* XXX: Harmless??? */
 		dev->eps[ep_index].ep_state &= ~SET_DEQ_PENDING;
@@ -1099,12 +1130,10 @@ static void xhci_handle_cmd_set_deq(struct xhci_hcd *xhci, int slot_id,
 
 		switch (cmd_comp_code) {
 		case COMP_TRB_ERR:
-			xhci_warn(xhci, "WARN Set TR Deq Ptr cmd invalid because "
-					"of stream ID configuration\n");
+			xhci_warn(xhci, "WARN Set TR Deq Ptr cmd invalid because of stream ID configuration\n");
 			break;
 		case COMP_CTX_STATE:
-			xhci_warn(xhci, "WARN Set TR Deq Ptr cmd failed due "
-					"to incorrect slot or ep state.\n");
+			xhci_warn(xhci, "WARN Set TR Deq Ptr cmd failed due to incorrect slot or ep state.\n");
 			ep_state = le32_to_cpu(ep_ctx->ep_info);
 			ep_state &= EP_STATE_MASK;
 			slot_state = le32_to_cpu(slot_ctx->dev_state);
@@ -1114,13 +1143,12 @@ static void xhci_handle_cmd_set_deq(struct xhci_hcd *xhci, int slot_id,
 					slot_state, ep_state);
 			break;
 		case COMP_EBADSLT:
-			xhci_warn(xhci, "WARN Set TR Deq Ptr cmd failed because "
-					"slot %u was not enabled.\n", slot_id);
+			xhci_warn(xhci, "WARN Set TR Deq Ptr cmd failed because slot %u was not enabled.\n",
+					slot_id);
 			break;
 		default:
-			xhci_warn(xhci, "WARN Set TR Deq Ptr cmd with unknown "
-					"completion code of %u.\n",
-				  cmd_comp_code);
+			xhci_warn(xhci, "WARN Set TR Deq Ptr cmd with unknown completion code of %u.\n",
+					cmd_comp_code);
 			break;
 		}
 		/* OK what do we do now?  The endpoint state is hosed, and we
@@ -1130,23 +1158,28 @@ static void xhci_handle_cmd_set_deq(struct xhci_hcd *xhci, int slot_id,
 		 * cancelling URBs, which might not be an error...
 		 */
 	} else {
+		u64 deq;
+		/* 4.6.10 deq ptr is written to the stream ctx for streams */
+		if (ep->ep_state & EP_HAS_STREAMS) {
+			struct xhci_stream_ctx *ctx =
+				&ep->stream_info->stream_ctx_array[stream_id];
+			deq = le64_to_cpu(ctx->stream_ring) & SCTX_DEQ_MASK;
+		} else {
+			deq = le64_to_cpu(ep_ctx->deq) & ~EP_CTX_CYCLE_MASK;
+		}
 		xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
-			"Successful Set TR Deq Ptr cmd, deq = @%08llx",
-			 le64_to_cpu(ep_ctx->deq));
-		if (xhci_trb_virt_to_dma(dev->eps[ep_index].queued_deq_seg,
-					 dev->eps[ep_index].queued_deq_ptr) ==
-		    (le64_to_cpu(ep_ctx->deq) & ~(EP_CTX_CYCLE_MASK))) {
+			"Successful Set TR Deq Ptr cmd, deq = @%08llx", deq);
+		if (xhci_trb_virt_to_dma(ep->queued_deq_seg,
+					 ep->queued_deq_ptr) == deq) {
 			/* Update the ring's dequeue segment and dequeue pointer
 			 * to reflect the new position.
 			 */
 			update_ring_for_set_deq_completion(xhci, dev,
 				ep_ring, ep_index);
 		} else {
-			xhci_warn(xhci, "Mismatch between completed Set TR Deq "
-					"Ptr command & xHCI internal state.\n");
+			xhci_warn(xhci, "Mismatch between completed Set TR Deq Ptr command & xHCI internal state.\n");
 			xhci_warn(xhci, "ep deq seg = %p, deq ptr = %p\n",
-					dev->eps[ep_index].queued_deq_seg,
-					dev->eps[ep_index].queued_deq_ptr);
+				  ep->queued_deq_seg, ep->queued_deq_ptr);
 		}
 	}
 
@@ -4070,6 +4103,7 @@ static int queue_set_tr_deq(struct xhci_hcd *xhci, int slot_id,
 	u32 trb_slot_id = SLOT_ID_FOR_TRB(slot_id);
 	u32 trb_ep_index = EP_ID_FOR_TRB(ep_index);
 	u32 trb_stream_id = STREAM_ID_FOR_TRB(stream_id);
+	u32 trb_sct = 0;
 	u32 type = TRB_TYPE(TRB_SET_DEQ);
 	struct xhci_virt_ep *ep;
 
@@ -4088,7 +4122,9 @@ static int queue_set_tr_deq(struct xhci_hcd *xhci, int slot_id,
 	}
 	ep->queued_deq_seg = deq_seg;
 	ep->queued_deq_ptr = deq_ptr;
-	return queue_command(xhci, lower_32_bits(addr) | cycle_state,
+	if (stream_id)
+		trb_sct = SCT_FOR_TRB(SCT_PRI_TR);
+	return queue_command(xhci, lower_32_bits(addr) | trb_sct | cycle_state,
 			upper_32_bits(addr), trb_stream_id,
 			trb_slot_id | trb_ep_index | type, false);
 }
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 6fe577d46fa2..652be2138b4b 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -390,6 +390,10 @@ static int xhci_try_enable_msi(struct usb_hcd *hcd)
 	}
 
  legacy_irq:
+	if (!strlen(hcd->irq_descr))
+		snprintf(hcd->irq_descr, sizeof(hcd->irq_descr), "%s:usb%d",
+			 hcd->driver->description, hcd->self.busnum);
+
 	/* fall back to legacy interrupt*/
 	ret = request_irq(pdev->irq, &usb_hcd_irq, IRQF_SHARED,
 			hcd->irq_descr, hcd);
@@ -2678,6 +2682,20 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
 	return ret;
 }
 
+static void xhci_check_bw_drop_ep_streams(struct xhci_hcd *xhci,
+	struct xhci_virt_device *vdev, int i)
+{
+	struct xhci_virt_ep *ep = &vdev->eps[i];
+
+	if (ep->ep_state & EP_HAS_STREAMS) {
+		xhci_warn(xhci, "WARN: endpoint 0x%02x has streams on set_interface, freeing streams.\n",
+				xhci_get_endpoint_address(i));
+		xhci_free_stream_info(xhci, ep->stream_info);
+		ep->stream_info = NULL;
+		ep->ep_state &= ~EP_HAS_STREAMS;
+	}
+}
+
 /* Called after one or more calls to xhci_add_endpoint() or
  * xhci_drop_endpoint().  If this call fails, the USB core is expected
  * to call xhci_reset_bandwidth().
@@ -2742,8 +2760,10 @@ int xhci_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev)
 	/* Free any rings that were dropped, but not changed. */
 	for (i = 1; i < 31; ++i) {
 		if ((le32_to_cpu(ctrl_ctx->drop_flags) & (1 << (i + 1))) &&
-		    !(le32_to_cpu(ctrl_ctx->add_flags) & (1 << (i + 1))))
+		    !(le32_to_cpu(ctrl_ctx->add_flags) & (1 << (i + 1)))) {
 			xhci_free_or_cache_endpoint_ring(xhci, virt_dev, i);
+			xhci_check_bw_drop_ep_streams(xhci, virt_dev, i);
+		}
 	}
 	xhci_zero_in_ctx(xhci, virt_dev);
 	/*
@@ -2759,6 +2779,7 @@ int xhci_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev)
 		if (virt_dev->eps[i].ring) {
 			xhci_free_or_cache_endpoint_ring(xhci, virt_dev, i);
 		}
+		xhci_check_bw_drop_ep_streams(xhci, virt_dev, i);
 		virt_dev->eps[i].ring = virt_dev->eps[i].new_ring;
 		virt_dev->eps[i].new_ring = NULL;
 	}
@@ -2954,7 +2975,7 @@ static int xhci_check_streams_endpoint(struct xhci_hcd *xhci,
 	ret = xhci_check_args(xhci_to_hcd(xhci), udev, ep, 1, true, __func__);
 	if (ret <= 0)
 		return -EINVAL;
-	if (ep->ss_ep_comp.bmAttributes == 0) {
+	if (usb_ss_max_streams(&ep->ss_ep_comp) == 0) {
 		xhci_warn(xhci, "WARN: SuperSpeed Endpoint Companion"
 				" descriptor for ep 0x%x does not support streams\n",
 				ep->desc.bEndpointAddress);
@@ -3121,6 +3142,12 @@ int xhci_alloc_streams(struct usb_hcd *hcd, struct usb_device *udev,
 	xhci_dbg(xhci, "Driver wants %u stream IDs (including stream 0).\n",
 			num_streams);
 
+	/* MaxPSASize value 0 (2 streams) means streams are not supported */
+	if (HCC_MAX_PSA(xhci->hcc_params) < 4) {
+		xhci_dbg(xhci, "xHCI controller does not support streams.\n");
+		return -ENOSYS;
+	}
+
 	config_cmd = xhci_alloc_command(xhci, true, true, mem_flags);
 	if (!config_cmd) {
 		xhci_dbg(xhci, "Could not allocate xHCI command structure.\n");
@@ -3519,6 +3546,8 @@ int xhci_discover_or_reset_device(struct usb_hcd *hcd, struct usb_device *udev)
 		struct xhci_virt_ep *ep = &virt_dev->eps[i];
 
 		if (ep->ep_state & EP_HAS_STREAMS) {
+			xhci_warn(xhci, "WARN: endpoint 0x%02x has streams on device reset, freeing streams.\n",
+					xhci_get_endpoint_address(i));
 			xhci_free_stream_info(xhci, ep->stream_info);
 			ep->stream_info = NULL;
 			ep->ep_state &= ~EP_HAS_STREAMS;
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 58ed9d088e63..d280e9213d08 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -703,6 +703,7 @@ struct xhci_ep_ctx {
 
 /* deq bitmasks */
 #define EP_CTX_CYCLE_MASK		(1 << 0)
+#define SCTX_DEQ_MASK			(~0xfL)
 
 
 /**
@@ -1118,9 +1119,10 @@ enum xhci_setup_dev {
 #define TRB_TO_SUSPEND_PORT(p)		(((p) & (1 << 23)) >> 23)
 #define LAST_EP_INDEX			30
 
-/* Set TR Dequeue Pointer command TRB fields */
+/* Set TR Dequeue Pointer command TRB fields, 6.4.3.9 */
 #define TRB_TO_STREAM_ID(p)		((((p) & (0xffff << 16)) >> 16))
 #define STREAM_ID_FOR_TRB(p)		((((p)) & 0xffff) << 16)
+#define SCT_FOR_TRB(p)			(((p) << 1) & 0x7)
 
 
 /* Port Status Change Event TRB fields */
@@ -1341,6 +1343,7 @@ struct xhci_ring {
 	unsigned int		num_trbs_free_temp;
 	enum xhci_ring_type	type;
 	bool			last_td_was_short;
+	struct radix_tree_root	*trb_address_map;
 };
 
 struct xhci_erst_entry {