Merge branch 'for-usb-next' of git+ssh://master.kernel.org/pub/scm/linux/kernel/git/sarah/xhci into usb-next

* 'for-usb-next' of git+ssh://master.kernel.org/pub/scm/linux/kernel/git/sarah/xhci:
  xhci 1.0: Set transfer burst last packet count field.
  xhci 1.0: Set transfer burst count field.
  xhci 1.0: Update TD size field format.
  xhci 1.0: Only interrupt on short packet for IN EPs.
  xhci: Remove sparse warning about cmd_status.
  usbcore: warm reset USB3 port in SS.Inactive state
  usbcore: Refine USB3.0 device suspend and resume
  xHCI: report USB3.0 portstatus comply with USB3.0 specification
  xHCI: Set link state support
  xHCI: Clear link state change support
  xHCI: warm reset support
  usb/ch9: use proper endianess for wBytesPerInterval
  xhci: Remove recursive call to xhci_handle_event
  xhci: Add an assertion to check for virt_dev=0 bug.
  xhci: Add rmb() between reading event validity & event data access.
  xhci: Make xHCI driver endian-safe

6 files changed, 658 insertions, 419 deletions

diff --git a/drivers/usb/host/xhci-dbg.c b/drivers/usb/host/xhci-dbg.c
index 0231814a97a..2e0486178db 100644
--- a/drivers/usb/host/xhci-dbg.c
+++ b/drivers/usb/host/xhci-dbg.c
@@ -147,7 +147,7 @@ static void xhci_print_op_regs(struct xhci_hcd *xhci)
 
 static void xhci_print_ports(struct xhci_hcd *xhci)
 {
-	u32 __iomem *addr;
+	__le32 __iomem *addr;
 	int i, j;
 	int ports;
 	char *names[NUM_PORT_REGS] = {
@@ -253,27 +253,27 @@ void xhci_print_trb_offsets(struct xhci_hcd *xhci, union xhci_trb *trb)
 void xhci_debug_trb(struct xhci_hcd *xhci, union xhci_trb *trb)
 {
 	u64	address;
-	u32	type = xhci_readl(xhci, &trb->link.control) & TRB_TYPE_BITMASK;
+	u32	type = le32_to_cpu(trb->link.control) & TRB_TYPE_BITMASK;
 
 	switch (type) {
 	case TRB_TYPE(TRB_LINK):
 		xhci_dbg(xhci, "Link TRB:\n");
 		xhci_print_trb_offsets(xhci, trb);
 
-		address = trb->link.segment_ptr;
+		address = le64_to_cpu(trb->link.segment_ptr);
 		xhci_dbg(xhci, "Next ring segment DMA address = 0x%llx\n", address);
 
 		xhci_dbg(xhci, "Interrupter target = 0x%x\n",
-				GET_INTR_TARGET(trb->link.intr_target));
+			 GET_INTR_TARGET(le32_to_cpu(trb->link.intr_target)));
 		xhci_dbg(xhci, "Cycle bit = %u\n",
-				(unsigned int) (trb->link.control & TRB_CYCLE));
+			 (unsigned int) (le32_to_cpu(trb->link.control) & TRB_CYCLE));
 		xhci_dbg(xhci, "Toggle cycle bit = %u\n",
-				(unsigned int) (trb->link.control & LINK_TOGGLE));
+			 (unsigned int) (le32_to_cpu(trb->link.control) & LINK_TOGGLE));
 		xhci_dbg(xhci, "No Snoop bit = %u\n",
-				(unsigned int) (trb->link.control & TRB_NO_SNOOP));
+			 (unsigned int) (le32_to_cpu(trb->link.control) & TRB_NO_SNOOP));
 		break;
 	case TRB_TYPE(TRB_TRANSFER):
-		address = trb->trans_event.buffer;
+		address = le64_to_cpu(trb->trans_event.buffer);
 		/*
 		 * FIXME: look at flags to figure out if it's an address or if
 		 * the data is directly in the buffer field.
@@ -281,11 +281,12 @@ void xhci_debug_trb(struct xhci_hcd *xhci, union xhci_trb *trb)
 		xhci_dbg(xhci, "DMA address or buffer contents= %llu\n", address);
 		break;
 	case TRB_TYPE(TRB_COMPLETION):
-		address = trb->event_cmd.cmd_trb;
+		address = le64_to_cpu(trb->event_cmd.cmd_trb);
 		xhci_dbg(xhci, "Command TRB pointer = %llu\n", address);
 		xhci_dbg(xhci, "Completion status = %u\n",
-				(unsigned int) GET_COMP_CODE(trb->event_cmd.status));
-		xhci_dbg(xhci, "Flags = 0x%x\n", (unsigned int) trb->event_cmd.flags);
+			 (unsigned int) GET_COMP_CODE(le32_to_cpu(trb->event_cmd.status)));
+		xhci_dbg(xhci, "Flags = 0x%x\n",
+			 (unsigned int) le32_to_cpu(trb->event_cmd.flags));
 		break;
 	default:
 		xhci_dbg(xhci, "Unknown TRB with TRB type ID %u\n",
@@ -311,16 +312,16 @@ void xhci_debug_trb(struct xhci_hcd *xhci, union xhci_trb *trb)
 void xhci_debug_segment(struct xhci_hcd *xhci, struct xhci_segment *seg)
 {
 	int i;
-	u32 addr = (u32) seg->dma;
+	u64 addr = seg->dma;
 	union xhci_trb *trb = seg->trbs;
 
 	for (i = 0; i < TRBS_PER_SEGMENT; ++i) {
 		trb = &seg->trbs[i];
-		xhci_dbg(xhci, "@%08x %08x %08x %08x %08x\n", addr,
-				lower_32_bits(trb->link.segment_ptr),
-				upper_32_bits(trb->link.segment_ptr),
-				(unsigned int) trb->link.intr_target,
-				(unsigned int) trb->link.control);
+		xhci_dbg(xhci, "@%016llx %08x %08x %08x %08x\n", addr,
+			 (u32)lower_32_bits(le64_to_cpu(trb->link.segment_ptr)),
+			 (u32)upper_32_bits(le64_to_cpu(trb->link.segment_ptr)),
+			 (unsigned int) le32_to_cpu(trb->link.intr_target),
+			 (unsigned int) le32_to_cpu(trb->link.control));
 		addr += sizeof(*trb);
 	}
 }
@@ -391,18 +392,18 @@ void xhci_dbg_ep_rings(struct xhci_hcd *xhci,
 
 void xhci_dbg_erst(struct xhci_hcd *xhci, struct xhci_erst *erst)
 {
-	u32 addr = (u32) erst->erst_dma_addr;
+	u64 addr = erst->erst_dma_addr;
 	int i;
 	struct xhci_erst_entry *entry;
 
 	for (i = 0; i < erst->num_entries; ++i) {
 		entry = &erst->entries[i];
-		xhci_dbg(xhci, "@%08x %08x %08x %08x %08x\n",
-				(unsigned int) addr,
-				lower_32_bits(entry->seg_addr),
-				upper_32_bits(entry->seg_addr),
-				(unsigned int) entry->seg_size,
-				(unsigned int) entry->rsvd);
+		xhci_dbg(xhci, "@%016llx %08x %08x %08x %08x\n",
+			 addr,
+			 lower_32_bits(le64_to_cpu(entry->seg_addr)),
+			 upper_32_bits(le64_to_cpu(entry->seg_addr)),
+			 (unsigned int) le32_to_cpu(entry->seg_size),
+			 (unsigned int) le32_to_cpu(entry->rsvd));
 		addr += sizeof(*entry);
 	}
 }
@@ -436,7 +437,7 @@ char *xhci_get_slot_state(struct xhci_hcd *xhci,
 {
 	struct xhci_slot_ctx *slot_ctx = xhci_get_slot_ctx(xhci, ctx);
 
-	switch (GET_SLOT_STATE(slot_ctx->dev_state)) {
+	switch (GET_SLOT_STATE(le32_to_cpu(slot_ctx->dev_state))) {
 	case 0:
 		return "enabled/disabled";
 	case 1:
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index a78f2ebd11b..e3ddc6a95af 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -50,7 +50,7 @@ static void xhci_common_hub_descriptor(struct xhci_hcd *xhci,
 	temp |= 0x0008;
 	/* Bits 6:5 - no TTs in root ports */
 	/* Bit  7 - no port indicators */
-	desc->wHubCharacteristics = (__force __u16) cpu_to_le16(temp);
+	desc->wHubCharacteristics = cpu_to_le16(temp);
 }
 
 /* Fill in the USB 2.0 roothub descriptor */
@@ -314,7 +314,7 @@ void xhci_ring_device(struct xhci_hcd *xhci, int slot_id)
 }
 
 static void xhci_disable_port(struct usb_hcd *hcd, struct xhci_hcd *xhci,
-		u16 wIndex, u32 __iomem *addr, u32 port_status)
+		u16 wIndex, __le32 __iomem *addr, u32 port_status)
 {
 	/* Don't allow the USB core to disable SuperSpeed ports. */
 	if (hcd->speed == HCD_USB3) {
@@ -331,7 +331,7 @@ static void xhci_disable_port(struct usb_hcd *hcd, struct xhci_hcd *xhci,
 }
 
 static void xhci_clear_port_change_bit(struct xhci_hcd *xhci, u16 wValue,
-		u16 wIndex, u32 __iomem *addr, u32 port_status)
+		u16 wIndex, __le32 __iomem *addr, u32 port_status)
 {
 	char *port_change_bit;
 	u32 status;
@@ -341,6 +341,10 @@ static void xhci_clear_port_change_bit(struct xhci_hcd *xhci, u16 wValue,
 		status = PORT_RC;
 		port_change_bit = "reset";
 		break;
+	case USB_PORT_FEAT_C_BH_PORT_RESET:
+		status = PORT_WRC;
+		port_change_bit = "warm(BH) reset";
+		break;
 	case USB_PORT_FEAT_C_CONNECTION:
 		status = PORT_CSC;
 		port_change_bit = "connect";
@@ -357,6 +361,10 @@ static void xhci_clear_port_change_bit(struct xhci_hcd *xhci, u16 wValue,
 		status = PORT_PLC;
 		port_change_bit = "suspend/resume";
 		break;
+	case USB_PORT_FEAT_C_PORT_LINK_STATE:
+		status = PORT_PLC;
+		port_change_bit = "link state";
+		break;
 	default:
 		/* Should never happen */
 		return;
@@ -376,9 +384,10 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 	unsigned long flags;
 	u32 temp, temp1, status;
 	int retval = 0;
-	u32 __iomem **port_array;
+	__le32 __iomem **port_array;
 	int slot_id;
 	struct xhci_bus_state *bus_state;
+	u16 link_state = 0;
 
 	if (hcd->speed == HCD_USB3) {
 		ports = xhci->num_usb3_ports;
@@ -422,9 +431,6 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		}
 		xhci_dbg(xhci, "get port status, actual port %d status  = 0x%x\n", wIndex, temp);
 
-		/* FIXME - should we return a port status value like the USB
-		 * 3.0 external hubs do?
-		 */
 		/* wPortChange bits */
 		if (temp & PORT_CSC)
 			status |= USB_PORT_STAT_C_CONNECTION << 16;
@@ -432,13 +438,21 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			status |= USB_PORT_STAT_C_ENABLE << 16;
 		if ((temp & PORT_OCC))
 			status |= USB_PORT_STAT_C_OVERCURRENT << 16;
-		/*
-		 * FIXME ignoring reset and USB 2.1/3.0 specific
-		 * changes
-		 */
-		if ((temp & PORT_PLS_MASK) == XDEV_U3
-			&& (temp & PORT_POWER))
-			status |= 1 << USB_PORT_FEAT_SUSPEND;
+		if ((temp & PORT_RC))
+			status |= USB_PORT_STAT_C_RESET << 16;
+		/* USB3.0 only */
+		if (hcd->speed == HCD_USB3) {
+			if ((temp & PORT_PLC))
+				status |= USB_PORT_STAT_C_LINK_STATE << 16;
+			if ((temp & PORT_WRC))
+				status |= USB_PORT_STAT_C_BH_RESET << 16;
+		}
+
+		if (hcd->speed != HCD_USB3) {
+			if ((temp & PORT_PLS_MASK) == XDEV_U3
+					&& (temp & PORT_POWER))
+				status |= USB_PORT_STAT_SUSPEND;
+		}
 		if ((temp & PORT_PLS_MASK) == XDEV_RESUME) {
 			if ((temp & PORT_RESET) || !(temp & PORT_PE))
 				goto error;
@@ -469,7 +483,8 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			&& (temp & PORT_POWER)
 			&& (bus_state->suspended_ports & (1 << wIndex))) {
 			bus_state->suspended_ports &= ~(1 << wIndex);
-			bus_state->port_c_suspend |= 1 << wIndex;
+			if (hcd->speed != HCD_USB3)
+				bus_state->port_c_suspend |= 1 << wIndex;
 		}
 		if (temp & PORT_CONNECT) {
 			status |= USB_PORT_STAT_CONNECTION;
@@ -481,14 +496,28 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			status |= USB_PORT_STAT_OVERCURRENT;
 		if (temp & PORT_RESET)
 			status |= USB_PORT_STAT_RESET;
-		if (temp & PORT_POWER)
-			status |= USB_PORT_STAT_POWER;
+		if (temp & PORT_POWER) {
+			if (hcd->speed == HCD_USB3)
+				status |= USB_SS_PORT_STAT_POWER;
+			else
+				status |= USB_PORT_STAT_POWER;
+		}
+		/* Port Link State */
+		if (hcd->speed == HCD_USB3) {
+			/* resume state is a xHCI internal state.
+			 * Do not report it to usb core.
+			 */
+			if ((temp & PORT_PLS_MASK) != XDEV_RESUME)
+				status |= (temp & PORT_PLS_MASK);
+		}
 		if (bus_state->port_c_suspend & (1 << wIndex))
 			status |= 1 << USB_PORT_FEAT_C_SUSPEND;
 		xhci_dbg(xhci, "Get port status returned 0x%x\n", status);
 		put_unaligned(cpu_to_le32(status), (__le32 *) buf);
 		break;
 	case SetPortFeature:
+		if (wValue == USB_PORT_FEAT_LINK_STATE)
+			link_state = (wIndex & 0xff00) >> 3;
 		wIndex &= 0xff;
 		if (!wIndex || wIndex > ports)
 			goto error;
@@ -537,6 +566,44 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			temp = xhci_readl(xhci, port_array[wIndex]);
 			bus_state->suspended_ports |= 1 << wIndex;
 			break;
+		case USB_PORT_FEAT_LINK_STATE:
+			temp = xhci_readl(xhci, port_array[wIndex]);
+			/* Software should not attempt to set
+			 * port link state above '5' (Rx.Detect) and the port
+			 * must be enabled.
+			 */
+			if ((temp & PORT_PE) == 0 ||
+				(link_state > USB_SS_PORT_LS_RX_DETECT)) {
+				xhci_warn(xhci, "Cannot set link state.\n");
+				goto error;
+			}
+
+			if (link_state == USB_SS_PORT_LS_U3) {
+				slot_id = xhci_find_slot_id_by_port(hcd, xhci,
+						wIndex + 1);
+				if (slot_id) {
+					/* unlock to execute stop endpoint
+					 * commands */
+					spin_unlock_irqrestore(&xhci->lock,
+								flags);
+					xhci_stop_device(xhci, slot_id, 1);
+					spin_lock_irqsave(&xhci->lock, flags);
+				}
+			}
+
+			temp = xhci_port_state_to_neutral(temp);
+			temp &= ~PORT_PLS_MASK;
+			temp |= PORT_LINK_STROBE | link_state;
+			xhci_writel(xhci, temp, port_array[wIndex]);
+
+			spin_unlock_irqrestore(&xhci->lock, flags);
+			msleep(20); /* wait device to enter */
+			spin_lock_irqsave(&xhci->lock, flags);
+
+			temp = xhci_readl(xhci, port_array[wIndex]);
+			if (link_state == USB_SS_PORT_LS_U3)
+				bus_state->suspended_ports |= 1 << wIndex;
+			break;
 		case USB_PORT_FEAT_POWER:
 			/*
 			 * Turn on ports, even if there isn't per-port switching.
@@ -557,6 +624,12 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			temp = xhci_readl(xhci, port_array[wIndex]);
 			xhci_dbg(xhci, "set port reset, actual port %d status  = 0x%x\n", wIndex, temp);
 			break;
+		case USB_PORT_FEAT_BH_PORT_RESET:
+			temp |= PORT_WR;
+			xhci_writel(xhci, temp, port_array[wIndex]);
+
+			temp = xhci_readl(xhci, port_array[wIndex]);
+			break;
 		default:
 			goto error;
 		}
@@ -584,35 +657,27 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			if (temp & XDEV_U3) {
 				if ((temp & PORT_PE) == 0)
 					goto error;
-				if (DEV_SUPERSPEED(temp)) {
-					temp = xhci_port_state_to_neutral(temp);
-					temp &= ~PORT_PLS_MASK;
-					temp |= PORT_LINK_STROBE | XDEV_U0;
-					xhci_writel(xhci, temp,
-							port_array[wIndex]);
-					xhci_readl(xhci, port_array[wIndex]);
-				} else {
-					temp = xhci_port_state_to_neutral(temp);
-					temp &= ~PORT_PLS_MASK;
-					temp |= PORT_LINK_STROBE | XDEV_RESUME;
-					xhci_writel(xhci, temp,
-							port_array[wIndex]);
 
-					spin_unlock_irqrestore(&xhci->lock,
-							       flags);
-					msleep(20);
-					spin_lock_irqsave(&xhci->lock, flags);
+				temp = xhci_port_state_to_neutral(temp);
+				temp &= ~PORT_PLS_MASK;
+				temp |= PORT_LINK_STROBE | XDEV_RESUME;
+				xhci_writel(xhci, temp,
+						port_array[wIndex]);
 
-					temp = xhci_readl(xhci,
-							port_array[wIndex]);
-					temp = xhci_port_state_to_neutral(temp);
-					temp &= ~PORT_PLS_MASK;
-					temp |= PORT_LINK_STROBE | XDEV_U0;
-					xhci_writel(xhci, temp,
-							port_array[wIndex]);
-				}
-				bus_state->port_c_suspend |= 1 << wIndex;
+				spin_unlock_irqrestore(&xhci->lock,
+						       flags);
+				msleep(20);
+				spin_lock_irqsave(&xhci->lock, flags);
+
+				temp = xhci_readl(xhci,
+						port_array[wIndex]);
+				temp = xhci_port_state_to_neutral(temp);
+				temp &= ~PORT_PLS_MASK;
+				temp |= PORT_LINK_STROBE | XDEV_U0;
+				xhci_writel(xhci, temp,
+						port_array[wIndex]);
 			}
+			bus_state->port_c_suspend |= 1 << wIndex;
 
 			slot_id = xhci_find_slot_id_by_port(hcd, xhci,
 					wIndex + 1);
@@ -625,9 +690,11 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		case USB_PORT_FEAT_C_SUSPEND:
 			bus_state->port_c_suspend &= ~(1 << wIndex);
 		case USB_PORT_FEAT_C_RESET:
+		case USB_PORT_FEAT_C_BH_PORT_RESET:
 		case USB_PORT_FEAT_C_CONNECTION:
 		case USB_PORT_FEAT_C_OVER_CURRENT:
 		case USB_PORT_FEAT_C_ENABLE:
+		case USB_PORT_FEAT_C_PORT_LINK_STATE:
 			xhci_clear_port_change_bit(xhci, wValue, wIndex,
 					port_array[wIndex], temp);
 			break;
@@ -664,7 +731,7 @@ int xhci_hub_status_data(struct usb_hcd *hcd, char *buf)
 	int i, retval;
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
 	int ports;
-	u32 __iomem **port_array;
+	__le32 __iomem **port_array;
 	struct xhci_bus_state *bus_state;
 
 	if (hcd->speed == HCD_USB3) {
@@ -681,7 +748,7 @@ int xhci_hub_status_data(struct usb_hcd *hcd, char *buf)
 	memset(buf, 0, retval);
 	status = 0;
 
-	mask = PORT_CSC | PORT_PEC | PORT_OCC;
+	mask = PORT_CSC | PORT_PEC | PORT_OCC | PORT_PLC;
 
 	spin_lock_irqsave(&xhci->lock, flags);
 	/* For each port, did anything change?  If so, set that bit in buf. */
@@ -709,7 +776,7 @@ int xhci_bus_suspend(struct usb_hcd *hcd)
 {
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
 	int max_ports, port_index;
-	u32 __iomem **port_array;
+	__le32 __iomem **port_array;
 	struct xhci_bus_state *bus_state;
 	unsigned long flags;
 
@@ -779,7 +846,7 @@ int xhci_bus_suspend(struct usb_hcd *hcd)
 
 		if (DEV_HIGHSPEED(t1)) {
 			/* enable remote wake up for USB 2.0 */
-			u32 __iomem *addr;
+			__le32 __iomem *addr;
 			u32 tmp;
 
 			/* Add one to the port status register address to get
@@ -801,7 +868,7 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 {
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
 	int max_ports, port_index;
-	u32 __iomem **port_array;
+	__le32 __iomem **port_array;
 	struct xhci_bus_state *bus_state;
 	u32 temp;
 	unsigned long flags;
@@ -875,7 +942,7 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 
 		if (DEV_HIGHSPEED(temp)) {
 			/* disable remote wake up for USB 2.0 */
-			u32 __iomem *addr;
+			__le32 __iomem *addr;
 			u32 tmp;
 
 			/* Add one to the port status register address to get
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 627f3438028..a4fc4d92938 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -89,16 +89,17 @@ static void xhci_link_segments(struct xhci_hcd *xhci, struct xhci_segment *prev,
 		return;
 	prev->next = next;
 	if (link_trbs) {
-		prev->trbs[TRBS_PER_SEGMENT-1].link.segment_ptr = next->dma;
+		prev->trbs[TRBS_PER_SEGMENT-1].link.
+			segment_ptr = cpu_to_le64(next->dma);
 
 		/* Set the last TRB in the segment to have a TRB type ID of Link TRB */
-		val = prev->trbs[TRBS_PER_SEGMENT-1].link.control;
+		val = le32_to_cpu(prev->trbs[TRBS_PER_SEGMENT-1].link.control);
 		val &= ~TRB_TYPE_BITMASK;
 		val |= TRB_TYPE(TRB_LINK);
 		/* Always set the chain bit with 0.95 hardware */
 		if (xhci_link_trb_quirk(xhci))
 			val |= TRB_CHAIN;
-		prev->trbs[TRBS_PER_SEGMENT-1].link.control = val;
+		prev->trbs[TRBS_PER_SEGMENT-1].link.control = cpu_to_le32(val);
 	}
 	xhci_dbg(xhci, "Linking segment 0x%llx to segment 0x%llx (DMA)\n",
 			(unsigned long long)prev->dma,
@@ -186,7 +187,8 @@ static struct xhci_ring *xhci_ring_alloc(struct xhci_hcd *xhci,
 
 	if (link_trbs) {
 		/* See section 4.9.2.1 and 6.4.4.1 */
-		prev->trbs[TRBS_PER_SEGMENT-1].link.control |= (LINK_TOGGLE);
+		prev->trbs[TRBS_PER_SEGMENT-1].link.
+			control |= cpu_to_le32(LINK_TOGGLE);
 		xhci_dbg(xhci, "Wrote link toggle flag to"
 				" segment %p (virtual), 0x%llx (DMA)\n",
 				prev, (unsigned long long)prev->dma);
@@ -548,7 +550,8 @@ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci,
 		addr = cur_ring->first_seg->dma |
 			SCT_FOR_CTX(SCT_PRI_TR) |
 			cur_ring->cycle_state;
-		stream_info->stream_ctx_array[cur_stream].stream_ring = addr;
+		stream_info->stream_ctx_array[cur_stream].
+			stream_ring = cpu_to_le64(addr);
 		xhci_dbg(xhci, "Setting stream %d ring ptr to 0x%08llx\n",
 				cur_stream, (unsigned long long) addr);
 
@@ -614,10 +617,10 @@ void xhci_setup_streams_ep_input_ctx(struct xhci_hcd *xhci,
 	max_primary_streams = fls(stream_info->num_stream_ctxs) - 2;
 	xhci_dbg(xhci, "Setting number of stream ctx array entries to %u\n",
 			1 << (max_primary_streams + 1));
-	ep_ctx->ep_info &= ~EP_MAXPSTREAMS_MASK;
-	ep_ctx->ep_info |= EP_MAXPSTREAMS(max_primary_streams);
-	ep_ctx->ep_info |= EP_HAS_LSA;
-	ep_ctx->deq  = stream_info->ctx_array_dma;
+	ep_ctx->ep_info &= cpu_to_le32(~EP_MAXPSTREAMS_MASK);
+	ep_ctx->ep_info |= cpu_to_le32(EP_MAXPSTREAMS(max_primary_streams)
+				       | EP_HAS_LSA);
+	ep_ctx->deq  = cpu_to_le64(stream_info->ctx_array_dma);
 }
 
 /*
@@ -630,10 +633,9 @@ void xhci_setup_no_streams_ep_input_ctx(struct xhci_hcd *xhci,
 		struct xhci_virt_ep *ep)
 {
 	dma_addr_t addr;
-	ep_ctx->ep_info &= ~EP_MAXPSTREAMS_MASK;
-	ep_ctx->ep_info &= ~EP_HAS_LSA;
+	ep_ctx->ep_info &= cpu_to_le32(~(EP_MAXPSTREAMS_MASK | EP_HAS_LSA));
 	addr = xhci_trb_virt_to_dma(ep->ring->deq_seg, ep->ring->dequeue);
-	ep_ctx->deq  = addr | ep->ring->cycle_state;
+	ep_ctx->deq  = cpu_to_le64(addr | ep->ring->cycle_state);
 }
 
 /* Frees all stream contexts associated with the endpoint,
@@ -781,11 +783,11 @@ int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id,
 	dev->udev = udev;
 
 	/* Point to output device context in dcbaa. */
-	xhci->dcbaa->dev_context_ptrs[slot_id] = dev->out_ctx->dma;
+	xhci->dcbaa->dev_context_ptrs[slot_id] = cpu_to_le64(dev->out_ctx->dma);
 	xhci_dbg(xhci, "Set slot id %d dcbaa entry %p to 0x%llx\n",
-			slot_id,
-			&xhci->dcbaa->dev_context_ptrs[slot_id],
-			(unsigned long long) xhci->dcbaa->dev_context_ptrs[slot_id]);
+		 slot_id,
+		 &xhci->dcbaa->dev_context_ptrs[slot_id],
+		 (unsigned long long) le64_to_cpu(xhci->dcbaa->dev_context_ptrs[slot_id]));
 
 	return 1;
 fail:
@@ -810,8 +812,9 @@ void xhci_copy_ep0_dequeue_into_input_ctx(struct xhci_hcd *xhci,
 	 * configured device has reset, so all control transfers should have
 	 * been completed or cancelled before the reset.
 	 */
-	ep0_ctx->deq = xhci_trb_virt_to_dma(ep_ring->enq_seg, ep_ring->enqueue);
-	ep0_ctx->deq |= ep_ring->cycle_state;
+	ep0_ctx->deq = cpu_to_le64(xhci_trb_virt_to_dma(ep_ring->enq_seg,
+							ep_ring->enqueue)
+				   | ep_ring->cycle_state);
 }
 
 /*
@@ -885,24 +888,22 @@ int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *ud
 	slot_ctx = xhci_get_slot_ctx(xhci, dev->in_ctx);
 
 	/* 2) New slot context and endpoint 0 context are valid*/
-	ctrl_ctx->add_flags = SLOT_FLAG | EP0_FLAG;
+	ctrl_ctx->add_flags = cpu_to_le32(SLOT_FLAG | EP0_FLAG);
 
 	/* 3) Only the control endpoint is valid - one endpoint context */
-	slot_ctx->dev_info |= LAST_CTX(1);
-
-	slot_ctx->dev_info |= (u32) udev->route;
+	slot_ctx->dev_info |= cpu_to_le32(LAST_CTX(1) | (u32) udev->route);
 	switch (udev->speed) {
 	case USB_SPEED_SUPER:
-		slot_ctx->dev_info |= (u32) SLOT_SPEED_SS;
+		slot_ctx->dev_info |= cpu_to_le32((u32) SLOT_SPEED_SS);
 		break;
 	case USB_SPEED_HIGH:
-		slot_ctx->dev_info |= (u32) SLOT_SPEED_HS;
+		slot_ctx->dev_info |= cpu_to_le32((u32) SLOT_SPEED_HS);
 		break;
 	case USB_SPEED_FULL:
-		slot_ctx->dev_info |= (u32) SLOT_SPEED_FS;
+		slot_ctx->dev_info |= cpu_to_le32((u32) SLOT_SPEED_FS);
 		break;
 	case USB_SPEED_LOW:
-		slot_ctx->dev_info |= (u32) SLOT_SPEED_LS;
+		slot_ctx->dev_info |= cpu_to_le32((u32) SLOT_SPEED_LS);
 		break;
 	case USB_SPEED_WIRELESS:
 		xhci_dbg(xhci, "FIXME xHCI doesn't support wireless speeds\n");
@@ -916,7 +917,7 @@ int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *ud
 	port_num = xhci_find_real_port_number(xhci, udev);
 	if (!port_num)
 		return -EINVAL;
-	slot_ctx->dev_info2 |= (u32) ROOT_HUB_PORT(port_num);
+	slot_ctx->dev_info2 |= cpu_to_le32((u32) ROOT_HUB_PORT(port_num));
 	/* Set the port number in the virtual_device to the faked port number */
 	for (top_dev = udev; top_dev->parent && top_dev->parent->parent;
 			top_dev = top_dev->parent)
@@ -927,31 +928,31 @@ int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *ud
 
 	/* Is this a LS/FS device under an external HS hub? */
 	if (udev->tt && udev->tt->hub->parent) {
-		slot_ctx->tt_info = udev->tt->hub->slot_id;
-		slot_ctx->tt_info |= udev->ttport << 8;
+		slot_ctx->tt_info = cpu_to_le32(udev->tt->hub->slot_id |
+						(udev->ttport << 8));
 		if (udev->tt->multi)
-			slot_ctx->dev_info |= DEV_MTT;
+			slot_ctx->dev_info |= cpu_to_le32(DEV_MTT);
 	}
 	xhci_dbg(xhci, "udev->tt = %p\n", udev->tt);
 	xhci_dbg(xhci, "udev->ttport = 0x%x\n", udev->ttport);
 
 	/* Step 4 - ring already allocated */
 	/* Step 5 */
-	ep0_ctx->ep_info2 = EP_TYPE(CTRL_EP);
+	ep0_ctx->ep_info2 = cpu_to_le32(EP_TYPE(CTRL_EP));
 	/*
 	 * XXX: Not sure about wireless USB devices.
 	 */
 	switch (udev->speed) {
 	case USB_SPEED_SUPER:
-		ep0_ctx->ep_info2 |= MAX_PACKET(512);
+		ep0_ctx->ep_info2 |= cpu_to_le32(MAX_PACKET(512));
 		break;
 	case USB_SPEED_HIGH:
 	/* USB core guesses at a 64-byte max packet first for FS devices */
 	case USB_SPEED_FULL:
-		ep0_ctx->ep_info2 |= MAX_PACKET(64);
+		ep0_ctx->ep_info2 |= cpu_to_le32(MAX_PACKET(64));
 		break;
 	case USB_SPEED_LOW:
-		ep0_ctx->ep_info2 |= MAX_PACKET(8);
+		ep0_ctx->ep_info2 |= cpu_to_le32(MAX_PACKET(8));
 		break;
 	case USB_SPEED_WIRELESS:
 		xhci_dbg(xhci, "FIXME xHCI doesn't support wireless speeds\n");
@@ -962,12 +963,10 @@ int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *ud
 		BUG();
 	}
 	/* EP 0 can handle "burst" sizes of 1, so Max Burst Size field is 0 */
-	ep0_ctx->ep_info2 |= MAX_BURST(0);
-	ep0_ctx->ep_info2 |= ERROR_COUNT(3);
+	ep0_ctx->ep_info2 |= cpu_to_le32(MAX_BURST(0) | ERROR_COUNT(3));
 
-	ep0_ctx->deq =
-		dev->eps[0].ring->first_seg->dma;
-	ep0_ctx->deq |= dev->eps[0].ring->cycle_state;
+	ep0_ctx->deq = cpu_to_le64(dev->eps[0].ring->first_seg->dma |
+				   dev->eps[0].ring->cycle_state);
 
 	/* Steps 7 and 8 were done in xhci_alloc_virt_device() */
 
@@ -1131,10 +1130,10 @@ static u32 xhci_get_max_esit_payload(struct xhci_hcd *xhci,
 		return 0;
 
 	if (udev->speed == USB_SPEED_SUPER)
-		return ep->ss_ep_comp.wBytesPerInterval;
+		return le16_to_cpu(ep->ss_ep_comp.wBytesPerInterval);
 
-	max_packet = GET_MAX_PACKET(ep->desc.wMaxPacketSize);
-	max_burst = (ep->desc.wMaxPacketSize & 0x1800) >> 11;
+	max_packet = GET_MAX_PACKET(le16_to_cpu(ep->desc.wMaxPacketSize));
+	max_burst = (le16_to_cpu(ep->desc.wMaxPacketSize) & 0x1800) >> 11;
 	/* A 0 in max burst means 1 transfer per ESIT */
 	return max_packet * (max_burst + 1);
 }
@@ -1183,10 +1182,10 @@ int xhci_endpoint_init(struct xhci_hcd *xhci,
 	}
 	virt_dev->eps[ep_index].skip = false;
 	ep_ring = virt_dev->eps[ep_index].new_ring;
-	ep_ctx->deq = ep_ring->first_seg->dma | ep_ring->cycle_state;
+	ep_ctx->deq = cpu_to_le64(ep_ring->first_seg->dma | ep_ring->cycle_state);
 
-	ep_ctx->ep_info = xhci_get_endpoint_interval(udev, ep);
-	ep_ctx->ep_info |= EP_MULT(xhci_get_endpoint_mult(udev, ep));
+	ep_ctx->ep_info = cpu_to_le32(xhci_get_endpoint_interval(udev, ep)
+				      | EP_MULT(xhci_get_endpoint_mult(udev, ep)));
 
 	/* FIXME dig Mult and streams info out of ep companion desc */
 
@@ -1194,22 +1193,22 @@ int xhci_endpoint_init(struct xhci_hcd *xhci,
 	 * error count = 0 means infinite retries.
 	 */
 	if (!usb_endpoint_xfer_isoc(&ep->desc))
-		ep_ctx->ep_info2 = ERROR_COUNT(3);
+		ep_ctx->ep_info2 = cpu_to_le32(ERROR_COUNT(3));
 	else
-		ep_ctx->ep_info2 = ERROR_COUNT(1);
+		ep_ctx->ep_info2 = cpu_to_le32(ERROR_COUNT(1));
 
-	ep_ctx->ep_info2 |= xhci_get_endpoint_type(udev, ep);
+	ep_ctx->ep_info2 |= cpu_to_le32(xhci_get_endpoint_type(udev, ep));
 
 	/* Set the max packet size and max burst */
 	switch (udev->speed) {
 	case USB_SPEED_SUPER:
-		max_packet = ep->desc.wMaxPacketSize;
-		ep_ctx->ep_info2 |= MAX_PACKET(max_packet);
+		max_packet = le16_to_cpu(ep->desc.wMaxPacketSize);
+		ep_ctx->ep_info2 |= cpu_to_le32(MAX_PACKET(max_packet));
 		/* dig out max burst from ep companion desc */
 		max_packet = ep->ss_ep_comp.bMaxBurst;
 		if (!max_packet)
 			xhci_warn(xhci, "WARN no SS endpoint bMaxBurst\n");
-		ep_ctx->ep_info2 |= MAX_BURST(max_packet);
+		ep_ctx->ep_info2 |= cpu_to_le32(MAX_BURST(max_packet));
 		break;
 	case USB_SPEED_HIGH:
 		/* bits 11:12 specify the number of additional transaction
@@ -1217,20 +1216,21 @@ int xhci_endpoint_init(struct xhci_hcd *xhci,
 		 */
 		if (usb_endpoint_xfer_isoc(&ep->desc) ||
 				usb_endpoint_xfer_int(&ep->desc)) {
-			max_burst = (ep->desc.wMaxPacketSize & 0x1800) >> 11;
-			ep_ctx->ep_info2 |= MAX_BURST(max_burst);
+			max_burst = (le16_to_cpu(ep->desc.wMaxPacketSize)
+				     & 0x1800) >> 11;
+			ep_ctx->ep_info2 |= cpu_to_le32(MAX_BURST(max_burst));
 		}
 		/* Fall through */
 	case USB_SPEED_FULL:
 	case USB_SPEED_LOW:
-		max_packet = GET_MAX_PACKET(ep->desc.wMaxPacketSize);
-		ep_ctx->ep_info2 |= MAX_PACKET(max_packet);
+		max_packet = GET_MAX_PACKET(le16_to_cpu(ep->desc.wMaxPacketSize));
+		ep_ctx->ep_info2 |= cpu_to_le32(MAX_PACKET(max_packet));
 		break;
 	default:
 		BUG();
 	}
 	max_esit_payload = xhci_get_max_esit_payload(xhci, udev, ep);
-	ep_ctx->tx_info = MAX_ESIT_PAYLOAD_FOR_EP(max_esit_payload);
+	ep_ctx->tx_info = cpu_to_le32(MAX_ESIT_PAYLOAD_FOR_EP(max_esit_payload));
 
 	/*
 	 * XXX no idea how to calculate the average TRB buffer length for bulk
@@ -1247,7 +1247,7 @@ int xhci_endpoint_init(struct xhci_hcd *xhci,
 	 * use Event Data TRBs, and we don't chain in a link TRB on short
 	 * transfers, we're basically dividing by 1.
 	 */
-	ep_ctx->tx_info |= AVG_TRB_LENGTH_FOR_EP(max_esit_payload);
+	ep_ctx->tx_info |= cpu_to_le32(AVG_TRB_LENGTH_FOR_EP(max_esit_payload));
 
 	/* FIXME Debug endpoint context */
 	return 0;
@@ -1347,7 +1347,7 @@ static int scratchpad_alloc(struct xhci_hcd *xhci, gfp_t flags)
 	if (!xhci->scratchpad->sp_dma_buffers)
 		goto fail_sp4;
 
-	xhci->dcbaa->dev_context_ptrs[0] = xhci->scratchpad->sp_dma;
+	xhci->dcbaa->dev_context_ptrs[0] = cpu_to_le64(xhci->scratchpad->sp_dma);
 	for (i = 0; i < num_sp; i++) {
 		dma_addr_t dma;
 		void *buf = pci_alloc_consistent(to_pci_dev(dev),
@@ -1724,7 +1724,7 @@ static void xhci_set_hc_event_deq(struct xhci_hcd *xhci)
 }
 
 static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports,
-		u32 __iomem *addr, u8 major_revision)
+		__le32 __iomem *addr, u8 major_revision)
 {
 	u32 temp, port_offset, port_count;
 	int i;
@@ -1789,7 +1789,7 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports,
  */
 static int xhci_setup_port_arrays(struct xhci_hcd *xhci, gfp_t flags)
 {
-	u32 __iomem *addr;
+	__le32 __iomem *addr;
 	u32 offset;
 	unsigned int num_ports;
 	int i, port_index;
@@ -2042,8 +2042,8 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	/* set ring base address and size for each segment table entry */
 	for (val = 0, seg = xhci->event_ring->first_seg; val < ERST_NUM_SEGS; val++) {
 		struct xhci_erst_entry *entry = &xhci->erst.entries[val];
-		entry->seg_addr = seg->dma;
-		entry->seg_size = TRBS_PER_SEGMENT;
+		entry->seg_addr = cpu_to_le64(seg->dma);
+		entry->seg_size = cpu_to_le32(TRBS_PER_SEGMENT);
 		entry->rsvd = 0;
 		seg = seg->next;
 	}
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 7437386a9a5..396f8d2a2e8 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -100,7 +100,7 @@ static bool last_trb_on_last_seg(struct xhci_hcd *xhci, struct xhci_ring *ring,
 		return (trb == &seg->trbs[TRBS_PER_SEGMENT]) &&
 			(seg->next == xhci->event_ring->first_seg);
 	else
-		return trb->link.control & LINK_TOGGLE;
+		return le32_to_cpu(trb->link.control) & LINK_TOGGLE;
 }
 
 /* Is this TRB a link TRB or was the last TRB the last TRB in this event ring
@@ -113,13 +113,15 @@ static int last_trb(struct xhci_hcd *xhci, struct xhci_ring *ring,
 	if (ring == xhci->event_ring)
 		return trb == &seg->trbs[TRBS_PER_SEGMENT];
 	else
-		return (trb->link.control & TRB_TYPE_BITMASK) == TRB_TYPE(TRB_LINK);
+		return (le32_to_cpu(trb->link.control) & TRB_TYPE_BITMASK)
+			== TRB_TYPE(TRB_LINK);
 }
 
 static int enqueue_is_link_trb(struct xhci_ring *ring)
 {
 	struct xhci_link_trb *link = &ring->enqueue->link;
-	return ((link->control & TRB_TYPE_BITMASK) == TRB_TYPE(TRB_LINK));
+	return ((le32_to_cpu(link->control) & TRB_TYPE_BITMASK) ==
+		TRB_TYPE(TRB_LINK));
 }
 
 /* Updates trb to point to the next TRB in the ring, and updates seg if the next
@@ -197,7 +199,7 @@ static void inc_enq(struct xhci_hcd *xhci, struct xhci_ring *ring,
 	union xhci_trb *next;
 	unsigned long long addr;
 
-	chain = ring->enqueue->generic.field[3] & TRB_CHAIN;
+	chain = le32_to_cpu(ring->enqueue->generic.field[3]) & TRB_CHAIN;
 	next = ++(ring->enqueue);
 
 	ring->enq_updates++;
@@ -223,12 +225,14 @@ static void inc_enq(struct xhci_hcd *xhci, struct xhci_ring *ring,
 				 * (which may mean the chain bit is cleared).
 				 */
 				if (!xhci_link_trb_quirk(xhci)) {
-					next->link.control &= ~TRB_CHAIN;
-					next->link.control |= chain;
+					next->link.control &=
+						cpu_to_le32(~TRB_CHAIN);
+					next->link.control |=
+						cpu_to_le32(chain);
 				}
 				/* Give this link TRB to the hardware */
 				wmb();
-				next->link.control ^= TRB_CYCLE;
+				next->link.control ^= cpu_to_le32(TRB_CYCLE);
 			}
 			/* Toggle the cycle bit after the last ring segment. */
 			if (last_trb_on_last_seg(xhci, ring, ring->enq_seg, next)) {
@@ -319,7 +323,7 @@ void xhci_ring_ep_doorbell(struct xhci_hcd *xhci,
 		unsigned int ep_index,
 		unsigned int stream_id)
 {
-	__u32 __iomem *db_addr = &xhci->dba->doorbell[slot_id];
+	__le32 __iomem *db_addr = &xhci->dba->doorbell[slot_id];
 	struct xhci_virt_ep *ep = &xhci->devs[slot_id]->eps[ep_index];
 	unsigned int ep_state = ep->ep_state;
 
@@ -380,7 +384,7 @@ static struct xhci_segment *find_trb_seg(
 	while (cur_seg->trbs > trb ||
 			&cur_seg->trbs[TRBS_PER_SEGMENT - 1] < trb) {
 		generic_trb = &cur_seg->trbs[TRBS_PER_SEGMENT - 1].generic;
-		if (generic_trb->field[3] & LINK_TOGGLE)
+		if (le32_to_cpu(generic_trb->field[3]) & LINK_TOGGLE)
 			*cycle_state ^= 0x1;
 		cur_seg = cur_seg->next;
 		if (cur_seg == start_seg)
@@ -447,6 +451,10 @@ static struct xhci_ring *xhci_urb_to_transfer_ring(struct xhci_hcd *xhci,
  *    any link TRBs with the toggle cycle bit set.
  *  - Finally we move the dequeue state one TRB further, toggling the cycle bit
  *    if we've moved it past a link TRB with the toggle cycle bit set.
+ *
+ * Some of the uses of xhci_generic_trb are grotty, but if they're done
+ * with correct __le32 accesses they should work fine.  Only users of this are
+ * in here.
  */
 void xhci_find_new_dequeue_state(struct xhci_hcd *xhci,
 		unsigned int slot_id, unsigned int ep_index,
@@ -480,7 +488,7 @@ 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(xhci, "Finding endpoint context\n");
 	ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, ep_index);
-	state->new_cycle_state = 0x1 & ep_ctx->deq;
+	state->new_cycle_state = 0x1 & le64_to_cpu(ep_ctx->deq);
 
 	state->new_deq_ptr = cur_td->last_trb;
 	xhci_dbg(xhci, "Finding segment containing last TRB in TD.\n");
@@ -493,8 +501,8 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci,
 	}
 
 	trb = &state->new_deq_ptr->generic;
-	if ((trb->field[3] & TRB_TYPE_BITMASK) == TRB_TYPE(TRB_LINK) &&
-				(trb->field[3] & LINK_TOGGLE))
+	if ((le32_to_cpu(trb->field[3]) & TRB_TYPE_BITMASK) ==
+	    TRB_TYPE(TRB_LINK) && (le32_to_cpu(trb->field[3]) & LINK_TOGGLE))
 		state->new_cycle_state ^= 0x1;
 	next_trb(xhci, ep_ring, &state->new_deq_seg, &state->new_deq_ptr);
 
@@ -529,12 +537,12 @@ static void td_to_noop(struct xhci_hcd *xhci, struct xhci_ring *ep_ring,
 	for (cur_seg = cur_td->start_seg, cur_trb = cur_td->first_trb;
 			true;
 			next_trb(xhci, ep_ring, &cur_seg, &cur_trb)) {
-		if ((cur_trb->generic.field[3] & TRB_TYPE_BITMASK) ==
-				TRB_TYPE(TRB_LINK)) {
+		if ((le32_to_cpu(cur_trb->generic.field[3]) & TRB_TYPE_BITMASK)
+		    == TRB_TYPE(TRB_LINK)) {
 			/* Unchain any chained Link TRBs, but
 			 * leave the pointers intact.
 			 */
-			cur_trb->generic.field[3] &= ~TRB_CHAIN;