Merge tag 'fixes-for-v4.18-rc5' of...

Merge tag 'fixes-for-v4.18-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb into usb-linus

Felipe writes:

usb: fixes for v4.18-rc5

With a total of 20 non-merge commits, we have accumulated quite a few
fixes. These include lot's of fixes the our audio gadget interface, a
build error fix for PPC64 builds for the frescale PHY driver,
sleep-while-atomic fixes on the r8a66597 UDC driver, 3-stage SETUP fix
for the aspeed-vhub UDC and some other misc fixes.

Documentation/devicetree/bindings/usb/rockchip,dwc3.txt

@@ -16,7 +16,8 @@ A child node must exist to represent the core DWC3 IP block. The name of
 the node is not important. The content of the node is defined in dwc3.txt.
 
 Phy documentation is provided in the following places:
-Documentation/devicetree/bindings/phy/qcom-dwc3-usb-phy.txt
+Documentation/devicetree/bindings/phy/phy-rockchip-inno-usb2.txt - USB2.0 PHY
+Documentation/devicetree/bindings/phy/phy-rockchip-typec.txt     - Type-C PHY
 
 Example device nodes:
 

drivers/usb/dwc2/gadget.c

@@ -3430,7 +3430,7 @@ static void dwc2_gadget_handle_incomplete_isoc_in(struct dwc2_hsotg *hsotg)
 	for (idx = 1; idx < hsotg->num_of_eps; idx++) {
 		hs_ep = hsotg->eps_in[idx];
 		/* Proceed only unmasked ISOC EPs */
-		if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk))
+		if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous)
 			continue;
 
 		epctrl = dwc2_readl(hsotg->regs + DIEPCTL(idx));
@@ -3476,7 +3476,7 @@ static void dwc2_gadget_handle_incomplete_isoc_out(struct dwc2_hsotg *hsotg)
 	for (idx = 1; idx < hsotg->num_of_eps; idx++) {
 		hs_ep = hsotg->eps_out[idx];
 		/* Proceed only unmasked ISOC EPs */
-		if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk))
+		if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous)
 			continue;
 
 		epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx));
@@ -3650,7 +3650,7 @@ static irqreturn_t dwc2_hsotg_irq(int irq, void *pw)
 		for (idx = 1; idx < hsotg->num_of_eps; idx++) {
 			hs_ep = hsotg->eps_out[idx];
 			/* Proceed only unmasked ISOC EPs */
-			if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk))
+			if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous)
 				continue;
 
 			epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx));

drivers/usb/dwc2/hcd.c

@@ -2665,34 +2665,35 @@ static int dwc2_alloc_split_dma_aligned_buf(struct dwc2_hsotg *hsotg,
 
 #define DWC2_USB_DMA_ALIGN 4
 
-struct dma_aligned_buffer {
-	void *kmalloc_ptr;
-	void *old_xfer_buffer;
-	u8 data[0];
-};
-
 static void dwc2_free_dma_aligned_buffer(struct urb *urb)
 {
-	struct dma_aligned_buffer *temp;
+	void *stored_xfer_buffer;
+	size_t length;
 
 	if (!(urb->transfer_flags & URB_ALIGNED_TEMP_BUFFER))
 		return;
 
-	temp = container_of(urb->transfer_buffer,
-			    struct dma_aligned_buffer, data);
+	/* Restore urb->transfer_buffer from the end of the allocated area */
+	memcpy(&stored_xfer_buffer, urb->transfer_buffer +
+	       urb->transfer_buffer_length, sizeof(urb->transfer_buffer));
 
-	if (usb_urb_dir_in(urb))
-		memcpy(temp->old_xfer_buffer, temp->data,
-		       urb->transfer_buffer_length);
-	urb->transfer_buffer = temp->old_xfer_buffer;
-	kfree(temp->kmalloc_ptr);
+	if (usb_urb_dir_in(urb)) {
+		if (usb_pipeisoc(urb->pipe))
+			length = urb->transfer_buffer_length;
+		else
+			length = urb->actual_length;
+
+		memcpy(stored_xfer_buffer, urb->transfer_buffer, length);
+	}
+	kfree(urb->transfer_buffer);
+	urb->transfer_buffer = stored_xfer_buffer;
 
 	urb->transfer_flags &= ~URB_ALIGNED_TEMP_BUFFER;
 }
 
 static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags)
 {
-	struct dma_aligned_buffer *temp, *kmalloc_ptr;
+	void *kmalloc_ptr;
 	size_t kmalloc_size;
 
 	if (urb->num_sgs || urb->sg ||
@@ -2700,22 +2701,29 @@ static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags)
 	    !((uintptr_t)urb->transfer_buffer & (DWC2_USB_DMA_ALIGN - 1)))
 		return 0;
 
-	/* Allocate a buffer with enough padding for alignment */
+	/*
+	 * Allocate a buffer with enough padding for original transfer_buffer
+	 * pointer. This allocation is guaranteed to be aligned properly for
+	 * DMA
+	 */
 	kmalloc_size = urb->transfer_buffer_length +
-		sizeof(struct dma_aligned_buffer) + DWC2_USB_DMA_ALIGN - 1;
+		sizeof(urb->transfer_buffer);
 
 	kmalloc_ptr = kmalloc(kmalloc_size, mem_flags);
 	if (!kmalloc_ptr)
 		return -ENOMEM;
 
-	/* Position our struct dma_aligned_buffer such that data is aligned */
-	temp = PTR_ALIGN(kmalloc_ptr + 1, DWC2_USB_DMA_ALIGN) - 1;
-	temp->kmalloc_ptr = kmalloc_ptr;
-	temp->old_xfer_buffer = urb->transfer_buffer;
+	/*
+	 * Position value of original urb->transfer_buffer pointer to the end
+	 * of allocation for later referencing
+	 */
+	memcpy(kmalloc_ptr + urb->transfer_buffer_length,
+	       &urb->transfer_buffer, sizeof(urb->transfer_buffer));
+
 	if (usb_urb_dir_out(urb))
-		memcpy(temp->data, urb->transfer_buffer,
+		memcpy(kmalloc_ptr, urb->transfer_buffer,
 		       urb->transfer_buffer_length);
-	urb->transfer_buffer = temp->data;
+	urb->transfer_buffer = kmalloc_ptr;
 
 	urb->transfer_flags |= URB_ALIGNED_TEMP_BUFFER;
 

drivers/usb/dwc2/hcd_intr.c

@@ -1231,7 +1231,10 @@ static void dwc2_hc_nak_intr(struct dwc2_hsotg *hsotg,
 	 * avoid interrupt storms we'll wait before retrying if we've got
 	 * several NAKs. If we didn't do this we'd retry directly from the
 	 * interrupt handler and could end up quickly getting another
-	 * interrupt (another NAK), which we'd retry.
+	 * interrupt (another NAK), which we'd retry. Note that we do not
+	 * delay retries for IN parts of control requests, as those are expected
+	 * to complete fairly quickly, and if we delay them we risk confusing
+	 * the device and cause it issue STALL.
 	 *
 	 * Note that in DMA mode software only gets involved to re-send NAKed
 	 * transfers for split transactions, so we only need to apply this
@@ -1244,7 +1247,9 @@ static void dwc2_hc_nak_intr(struct dwc2_hsotg *hsotg,
 			qtd->error_count = 0;
 		qtd->complete_split = 0;
 		qtd->num_naks++;
-		qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY;
+		qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY &&
+				!(chan->ep_type == USB_ENDPOINT_XFER_CONTROL &&
+				  chan->ep_is_in);
 		dwc2_halt_channel(hsotg, chan, qtd, DWC2_HC_XFER_NAK);
 		goto handle_nak_done;
 	}

drivers/usb/dwc3/ep0.c

@@ -973,15 +973,12 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc,
 		ret = dwc3_ep0_start_trans(dep);
 	} else if (IS_ALIGNED(req->request.length, dep->endpoint.maxpacket) &&
 		   req->request.length && req->request.zero) {
-		u32	maxpacket;
 
 		ret = usb_gadget_map_request_by_dev(dwc->sysdev,
 				&req->request, dep->number);
 		if (ret)
 			return;
 
-		maxpacket = dep->endpoint.maxpacket;
-
 		/* prepare normal TRB */
 		dwc3_ep0_prepare_one_trb(dep, req->request.dma,
 					 req->request.length,

drivers/usb/gadget/composite.c

@@ -1819,7 +1819,6 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
 		if (cdev->use_os_string && cdev->os_desc_config &&
 		    (ctrl->bRequestType & USB_TYPE_VENDOR) &&
 		    ctrl->bRequest == cdev->b_vendor_code) {
-			struct usb_request		*req;
 			struct usb_configuration	*os_desc_cfg;
 			u8				*buf;
 			int				interface;

drivers/usb/gadget/function/f_uac2.c

@@ -438,14 +438,14 @@ static struct usb_descriptor_header *hs_audio_desc[] = {
 };
 
 struct cntrl_cur_lay3 {
-	__u32	dCUR;
+	__le32	dCUR;
 };
 
 struct cntrl_range_lay3 {
-	__u16	wNumSubRanges;
-	__u32	dMIN;
-	__u32	dMAX;
-	__u32	dRES;
+	__le16	wNumSubRanges;
+	__le32	dMIN;
+	__le32	dMAX;
+	__le32	dRES;
 } __packed;
 
 static void set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts,
@@ -559,13 +559,13 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn)
 	agdev->out_ep = usb_ep_autoconfig(gadget, &fs_epout_desc);
 	if (!agdev->out_ep) {
 		dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
-		return ret;
+		return -ENODEV;
 	}
 
 	agdev->in_ep = usb_ep_autoconfig(gadget, &fs_epin_desc);
 	if (!agdev->in_ep) {
 		dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
-		return ret;
+		return -ENODEV;
 	}
 
 	agdev->in_ep_maxpsize = max_t(u16,
@@ -703,9 +703,9 @@ in_rq_cur(struct usb_function *fn, const struct usb_ctrlrequest *cr)
 		memset(&c, 0, sizeof(struct cntrl_cur_lay3));
 
 		if (entity_id == USB_IN_CLK_ID)
-			c.dCUR = p_srate;
+			c.dCUR = cpu_to_le32(p_srate);
 		else if (entity_id == USB_OUT_CLK_ID)
-			c.dCUR = c_srate;
+			c.dCUR = cpu_to_le32(c_srate);
 
 		value = min_t(unsigned, w_length, sizeof c);
 		memcpy(req->buf, &c, value);
@@ -742,15 +742,15 @@ in_rq_range(struct usb_function *fn, const struct usb_ctrlrequest *cr)
 
 	if (control_selector == UAC2_CS_CONTROL_SAM_FREQ) {
 		if (entity_id == USB_IN_CLK_ID)
-			r.dMIN = p_srate;
+			r.dMIN = cpu_to_le32(p_srate);
 		else if (entity_id == USB_OUT_CLK_ID)
-			r.dMIN = c_srate;
+			r.dMIN = cpu_to_le32(c_srate);
 		else
 			return -EOPNOTSUPP;
 
 		r.dMAX = r.dMIN;
 		r.dRES = 0;
-		r.wNumSubRanges = 1;
+		r.wNumSubRanges = cpu_to_le16(1);
 
 		value = min_t(unsigned, w_length, sizeof r);
 		memcpy(req->buf, &r, value);

drivers/usb/gadget/function/u_audio.c

@@ -32,9 +32,6 @@ struct uac_req {
 struct uac_rtd_params {
 	struct snd_uac_chip *uac; /* parent chip */
 	bool ep_enabled; /* if the ep is enabled */
-	/* Size of the ring buffer */
-	size_t dma_bytes;
-	unsigned char *dma_area;
 
 	struct snd_pcm_substream *ss;
 
@@ -43,8 +40,6 @@ struct uac_rtd_params {
 
 	void *rbuf;
 
-	size_t period_size;
-
 	unsigned max_psize;	/* MaxPacketSize of endpoint */
 	struct uac_req *ureq;
 
@@ -84,12 +79,12 @@ static const struct snd_pcm_hardware uac_pcm_hardware = {
 static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req)
 {
 	unsigned pending;
-	unsigned long flags;
+	unsigned long flags, flags2;
 	unsigned int hw_ptr;
-	bool update_alsa = false;
 	int status = req->status;
 	struct uac_req *ur = req->context;
 	struct snd_pcm_substream *substream;
+	struct snd_pcm_runtime *runtime;
 	struct uac_rtd_params *prm = ur->pp;
 	struct snd_uac_chip *uac = prm->uac;
 
@@ -111,6 +106,14 @@ static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req)
 	if (!substream)
 		goto exit;
 
+	snd_pcm_stream_lock_irqsave(substream, flags2);
+
+	runtime = substream->runtime;
+	if (!runtime || !snd_pcm_running(substream)) {
+		snd_pcm_stream_unlock_irqrestore(substream, flags2);
+		goto exit;
+	}
+
 	spin_lock_irqsave(&prm->lock, flags);
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
@@ -137,43 +140,46 @@ static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req)
 		req->actual = req->length;
 	}
 
-	pending = prm->hw_ptr % prm->period_size;
-	pending += req->actual;
-	if (pending >= prm->period_size)
-		update_alsa = true;
-
 	hw_ptr = prm->hw_ptr;
-	prm->hw_ptr = (prm->hw_ptr + req->actual) % prm->dma_bytes;
 
 	spin_unlock_irqrestore(&prm->lock, flags);
 
 	/* Pack USB load in ALSA ring buffer */
-	pending = prm->dma_bytes - hw_ptr;
+	pending = runtime->dma_bytes - hw_ptr;
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
 		if (unlikely(pending < req->actual)) {
-			memcpy(req->buf, prm->dma_area + hw_ptr, pending);
-			memcpy(req->buf + pending, prm->dma_area,
+			memcpy(req->buf, runtime->dma_area + hw_ptr, pending);
+			memcpy(req->buf + pending, runtime->dma_area,
 			       req->actual - pending);
 		} else {
-			memcpy(req->buf, prm->dma_area + hw_ptr, req->actual);
+			memcpy(req->buf, runtime->dma_area + hw_ptr,
+			       req->actual);
 		}
 	} else {
 		if (unlikely(pending < req->actual)) {
-			memcpy(prm->dma_area + hw_ptr, req->buf, pending);
-			memcpy(prm->dma_area, req->buf + pending,
+			memcpy(runtime->dma_area + hw_ptr, req->buf, pending);
+			memcpy(runtime->dma_area, req->buf + pending,
 			       req->actual - pending);
 		} else {
-			memcpy(prm->dma_area + hw_ptr, req->buf, req->actual);
+			memcpy(runtime->dma_area + hw_ptr, req->buf,
+			       req->actual);
 		}
 	}
 
+	spin_lock_irqsave(&prm->lock, flags);
+	/* update hw_ptr after data is copied to memory */
+	prm->hw_ptr = (hw_ptr + req->actual) % runtime->dma_bytes;
+	hw_ptr = prm->hw_ptr;
+	spin_unlock_irqrestore(&prm->lock, flags);
+	snd_pcm_stream_unlock_irqrestore(substream, flags2);
+
+	if ((hw_ptr % snd_pcm_lib_period_bytes(substream)) < req->actual)
+		snd_pcm_period_elapsed(substream);
+
 exit:
 	if (usb_ep_queue(ep, req, GFP_ATOMIC))
 		dev_err(uac->card->dev, "%d Error!\n", __LINE__);
-
-	if (update_alsa)
-		snd_pcm_period_elapsed(substream);
 }
 
 static int uac_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
@@ -236,40 +242,12 @@ static snd_pcm_uframes_t uac_pcm_pointer(struct snd_pcm_substream *substream)
 static int uac_pcm_hw_params(struct snd_pcm_substream *substream,
 			       struct snd_pcm_hw_params *hw_params)
 {
-	struct snd_uac_chip *uac = snd_pcm_substream_chip(substream);
-	struct uac_rtd_params *prm;
-	int err;
-
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		prm = &uac->p_prm;
-	else
-		prm = &uac->c_prm;
-
-	err = snd_pcm_lib_malloc_pages(substream,
+	return snd_pcm_lib_malloc_pages(substream,
 					params_buffer_bytes(hw_params));
-	if (err >= 0) {
-		prm->dma_bytes = substream->runtime->dma_bytes;
-		prm->dma_area = substream->runtime->dma_area;
-		prm->period_size = params_period_bytes(hw_params);
-	}
-
-	return err;
 }
 
 static int uac_pcm_hw_free(struct snd_pcm_substream *substream)
 {
-	struct snd_uac_chip *uac = snd_pcm_substream_chip(substream);
-	struct uac_rtd_params *prm;
-
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		prm = &uac->p_prm;
-	else
-		prm = &uac->c_prm;
-
-	prm->dma_area = NULL;
-	prm->dma_bytes = 0;
-	prm->period_size = 0;
-
 	return snd_pcm_lib_free_pages(substream);
 }
 
@@ -595,15 +573,15 @@ int g_audio_setup(struct g_audio *g_audio, const char *pcm_name,
 	if (err < 0)
 		goto snd_fail;
 
-	strcpy(pcm->name, pcm_name);
+	strlcpy(pcm->name, pcm_name, sizeof(pcm->name));
 	pcm->private_data = uac;
 	uac->pcm = pcm;
 
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &uac_pcm_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &uac_pcm_ops);
 
-	strcpy(card->driver, card_name);
-	strcpy(card->shortname, card_name);
+	strlcpy(card->driver, card_name, sizeof(card->driver));
+	strlcpy(card->shortname, card_name, sizeof(card->shortname));
 	sprintf(card->longname, "%s %i", card_name, card->dev->id);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,

drivers/usb/gadget/udc/aspeed-vhub/ep0.c

@@ -108,6 +108,13 @@ void ast_vhub_ep0_handle_setup(struct ast_vhub_ep *ep)
 	/* Check our state, cancel pending requests if needed */
 	if (ep->ep0.state != ep0_state_token) {
 		EPDBG(ep, "wrong state\n");
+		ast_vhub_nuke(ep, -EIO);
+
+		/*
+		 * Accept the packet regardless, this seems to happen
+		 * when stalling a SETUP packet that has an OUT data
+		 * phase.
+		 */
 		ast_vhub_nuke(ep, 0);
 		goto stall;
 	}
@@ -212,6 +219,8 @@ static void ast_vhub_ep0_do_send(struct ast_vhub_ep *ep,
 	if (chunk && req->req.buf)
 		memcpy(ep->buf, req->req.buf + req->req.actual, chunk);
 
+	vhub_dma_workaround(ep->buf);
+
 	/* Remember chunk size and trigger send */
 	reg = VHUB_EP0_SET_TX_LEN(chunk);
 	writel(reg, ep->ep0.ctlstat);
@@ -224,7 +233,7 @@ static void ast_vhub_ep0_rx_prime(struct ast_vhub_ep *ep)
 	EPVDBG(ep, "rx prime\n");
 
 	/* Prime endpoint for receiving data */
-	writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat + AST_VHUB_EP0_CTRL);
+	writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat);
 }
 
 static void ast_vhub_ep0_do_receive(struct ast_vhub_ep *ep, struct ast_vhub_req *req,

drivers/usb/gadget/udc/aspeed-vhub/epn.c

@@ -66,11 +66,16 @@ static void ast_vhub_epn_kick(struct ast_vhub_ep *ep, struct ast_vhub_req *req)
 	if (!req->req.dma) {
 
 		/* For IN transfers, copy data over first */
-		if (ep->epn.is_in)
+		if (ep->epn.is_in) {
 			memcpy(ep->buf, req->req.buf + act, chunk);
+			vhub_dma_workaround(ep->buf);
+		}
 		writel(ep->buf_dma, ep->epn.regs + AST_VHUB_EP_DESC_BASE);
-	} else
+	} else {
+		if (ep->epn.is_in)
+			vhub_dma_workaround(req->req.buf);
 		writel(req->req.dma + act, ep->epn.regs + AST_VHUB_EP_DESC_BASE);
+	}
 
 	/* Start DMA */
 	req->active = true;
@@ -161,6 +166,7 @@ static inline unsigned int ast_vhub_count_free_descs(struct ast_vhub_ep *ep)
 static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep,
 				   struct ast_vhub_req *req)
 {
+	struct ast_vhub_desc *desc = NULL;
 	unsigned int act = req->act_count;
 	unsigned int len = req->req.length;
 	unsigned int chunk;
@@ -177,7 +183,6 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep,
 
 	/* While we can create descriptors */
 	while (ast_vhub_count_free_descs(ep) && req->last_desc < 0) {
-		struct ast_vhub_desc *desc;
 		unsigned int d_num;
 
 		/* Grab next free descriptor */
@@ -227,6 +232,9 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep,
 		req->act_count = act = act + chunk;
 	}
 
+	if (likely(desc))
+		vhub_dma_workaround(desc);
+
 	/* Tell HW about new descriptors */
 	writel(VHUB_EP_DMA_SET_CPU_WPTR(ep->epn.d_next),
 	       ep->epn.regs + AST_VHUB_EP_DESC_STATUS);

drivers/usb/gadget/udc/aspeed-vhub/vhub.h

@@ -462,6 +462,39 @@ enum std_req_rc {
 #define DDBG(d, fmt, ...)	do { } while(0)
 #endif
 
+static inline void vhub_dma_workaround(void *addr)
+{
+	/*
+	 * This works around a confirmed HW issue with the Aspeed chip.
+	 *
+	 * The core uses a different bus to memory than the AHB going to
+	 * the USB device controller. Due to the latter having a higher
+	 * priority than the core for arbitration on that bus, it's
+	 * possible for an MMIO to the device, followed by a DMA by the
+	 * device from memory to all be performed and services before
+	 * a previous store to memory gets completed.
+	 *
+	 * This the following scenario can happen:
+	 *
+	 *    - Driver writes to a DMA descriptor (Mbus)
+	 *    - Driver writes to the MMIO register to start the DMA (AHB)
+	 *    - The gadget sees the second write and sends a read of the
+	 *      descriptor to the memory controller (Mbus)
+	 *    - The gadget hits memory before the descriptor write
+	 *      causing it to read an obsolete value.
+	 *
+	 * Thankfully the problem is limited to the USB gadget device, other
+	 * masters in the SoC all have a lower priority than the core, thus
+	 * ensuring that the store by the core arrives first.
+	 *
+	 * The workaround consists of using a dummy read of the memory before
+	 * doing the MMIO writes. This will ensure that the previous writes
+	 * have been "pushed out".
+	 */
+	mb();
+	(void)__raw_readl((void __iomem *)addr);
+}
+
 /* core.c */
 void ast_vhub_done(struct ast_vhub_ep *ep, struct ast_vhub_req *req,
 		   int status);

drivers/usb/gadget/udc/r8a66597-udc.c

@@ -832,11 +832,11 @@ static void init_controller(struct r8a66597 *r8a66597)
 
 		r8a66597_bset(r8a66597, XCKE, SYSCFG0);
 
-		msleep(3);
+		mdelay(3);
 
 		r8a66597_bset(r8a66597, PLLC, SYSCFG0);
 
-		msleep(1);
+		mdelay(1);
 
 		r8a66597_bset(r8a66597, SCKE, SYSCFG0);
 
@@ -1190,7 +1190,7 @@ __acquires(r8a66597->lock)
 	r8a66597->ep0_req->length = 2;
 	/* AV: what happens if we get called again before that gets through? */
 	spin_unlock(&r8a66597->lock);
-	r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_KERNEL);
+	r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_ATOMIC);
 	spin_lock(&r8a66597->lock);
 }
 

drivers/usb/phy/phy-fsl-usb.c

@@ -861,6 +861,7 @@ int usb_otg_start(struct platform_device *pdev)
 	if (pdata->init && pdata->init(pdev) != 0)
 		return -EINVAL;
 
+#ifdef CONFIG_PPC32
 	if (pdata->big_endian_mmio) {
 		_fsl_readl = _fsl_readl_be;
 		_fsl_writel = _fsl_writel_be;
@@ -868,6 +869,7 @@ int usb_otg_start(struct platform_device *pdev)
 		_fsl_readl = _fsl_readl_le;
 		_fsl_writel = _fsl_writel_le;
 	}
+#endif
 
 	/* request irq */
 	p_otg->irq = platform_get_irq(pdev, 0);
@@ -958,7 +960,7 @@ int usb_otg_start(struct platform_device *pdev)
 /*
  * state file in sysfs
  */
-static int show_fsl_usb2_otg_state(struct device *dev,
+static ssize_t show_fsl_usb2_otg_state(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
 	struct otg_fsm *fsm = &fsl_otg_dev->fsm;

tools/usb/ffs-test.c

@@ -44,12 +44,25 @@
 
 /******************** Little Endian Handling ********************************/
 
-#define cpu_to_le16(x)  htole16(x)
-#define cpu_to_le32(x)  htole32(x)
+/*
+ * cpu_to_le16/32 are used when initializing structures, a context where a
+ * function call is not allowed. To solve this, we code cpu_to_le16/32 in a way
+ * that allows them to be used when initializing structures.
+ */
+
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+#define cpu_to_le16(x)  (x)
+#define cpu_to_le32(x)  (x)
+#else
+#define cpu_to_le16(x)  ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8))
+#define cpu_to_le32(x)  \
+	((((x) & 0xff000000u) >> 24) | (((x) & 0x00ff0000u) >>  8) | \
+	(((x) & 0x0000ff00u) <<  8) | (((x) & 0x000000ffu) << 24))
+#endif
+
 #define le32_to_cpu(x)  le32toh(x)
 #define le16_to_cpu(x)  le16toh(x)
 
-
 /******************** Messages and Errors ***********************************/
 
 static const char argv0[] = "ffs-test";