Merge branch 'master' of git://git.denx.de/u-boot-usb

* 'master' of git://git.denx.de/u-boot-usb:
  usb_storage: fix ehci driver max transfer size
  smsc95xx: align buffers to cache line size
  ehci-hcd: change debug() to printf() in case of errors
  usb: check return value of submit_{control, bulk}_msg
  usb: pass cache-aligned buffer to usb_get_descriptor()
  ehci-hcd: fix external buffer cache handling
  ehci-hcd.c, musb_core, usb.h: Add USB_DMA_MINALIGN define for cache alignment
  ehci-hcd: program asynclistaddr before every transfer
  common.h: Introduce DEFINE_CACHE_ALIGN_BUFFER
  ehci-omap: Do not call dcache_off from omap_ehci_hcd_init

Signed-off-by: Wolfgang Denk <wd@denx.de>

8 files changed, 117 insertions, 75 deletions

diff --git a/common/usb.c b/common/usb.c
index c80155c..1b40228 100644
--- a/common/usb.c
+++ b/common/usb.c
@@ -188,7 +188,8 @@ int usb_control_msg(struct usb_device *dev, unsigned int pipe,
 		   request, requesttype, value, index, size);
 	dev->status = USB_ST_NOT_PROC; /*not yet processed */
 
-	submit_control_msg(dev, pipe, data, size, setup_packet);
+	if (submit_control_msg(dev, pipe, data, size, setup_packet) < 0)
+		return -1;
 	if (timeout == 0)
 		return (int)size;
 
@@ -220,7 +221,8 @@ int usb_bulk_msg(struct usb_device *dev, unsigned int pipe,
 	if (len < 0)
 		return -1;
 	dev->status = USB_ST_NOT_PROC; /*not yet processed */
-	submit_bulk_msg(dev, pipe, data, len);
+	if (submit_bulk_msg(dev, pipe, data, len) < 0)
+		return -1;
 	while (timeout--) {
 		if (!((volatile unsigned long)dev->status & USB_ST_NOT_PROC))
 			break;
@@ -799,12 +801,13 @@ int usb_new_device(struct usb_device *dev)
 	dev->epmaxpacketin[0] = 8;
 	dev->epmaxpacketout[0] = 8;
 
-	err = usb_get_descriptor(dev, USB_DT_DEVICE, 0, &dev->descriptor, 8);
+	err = usb_get_descriptor(dev, USB_DT_DEVICE, 0, tmpbuf, 8);
 	if (err < 8) {
 		printf("\n      USB device not responding, " \
 		       "giving up (status=%lX)\n", dev->status);
 		return 1;
 	}
+	memcpy(&dev->descriptor, tmpbuf, 8);
 #else
 	/* This is a Windows scheme of initialization sequence, with double
 	 * reset of the device (Linux uses the same sequence)
@@ -893,7 +896,7 @@ int usb_new_device(struct usb_device *dev)
 	tmp = sizeof(dev->descriptor);
 
 	err = usb_get_descriptor(dev, USB_DT_DEVICE, 0,
-				 &dev->descriptor, sizeof(dev->descriptor));
+				 tmpbuf, sizeof(dev->descriptor));
 	if (err < tmp) {
 		if (err < 0)
 			printf("unable to get device descriptor (error=%d)\n",
@@ -903,6 +906,7 @@ int usb_new_device(struct usb_device *dev)
 				"(expected %i, got %i)\n", tmp, err);
 		return 1;
 	}
+	memcpy(&dev->descriptor, tmpbuf, sizeof(dev->descriptor));
 	/* correct le values */
 	le16_to_cpus(&dev->descriptor.bcdUSB);
 	le16_to_cpus(&dev->descriptor.idVendor);
diff --git a/common/usb_storage.c b/common/usb_storage.c
index faad237..bdc306f 100644
--- a/common/usb_storage.c
+++ b/common/usb_storage.c
@@ -150,12 +150,17 @@ struct us_data {
 	unsigned int	irqpipe;	 	/* pipe for release_irq */
 	unsigned char	irqmaxp;		/* max packed for irq Pipe */
 	unsigned char	irqinterval;		/* Intervall for IRQ Pipe */
-	unsigned long	max_xfer_blk;		/* Max blocks per xfer */
 	ccb		*srb;			/* current srb */
 	trans_reset	transport_reset;	/* reset routine */
 	trans_cmnd	transport;		/* transport routine */
 };
 
+/*
+ * The U-Boot EHCI driver cannot handle more than 5 page aligned buffers
+ * of 4096 bytes in a transfer without running itself out of qt_buffers
+ */
+#define USB_MAX_XFER_BLK(start, blksz)	(((4096 * 5) - (start % 4096)) / blksz)
+
 static struct us_data usb_stor[USB_MAX_STOR_DEV];
 
 
@@ -1041,7 +1046,7 @@ static void usb_bin_fixup(struct usb_device_descriptor descriptor,
 unsigned long usb_stor_read(int device, unsigned long blknr,
 			    unsigned long blkcnt, void *buffer)
 {
-	unsigned long start, blks, buf_addr;
+	unsigned long start, blks, buf_addr, max_xfer_blk;
 	unsigned short smallblks;
 	struct usb_device *dev;
 	struct us_data *ss;
@@ -1083,12 +1088,14 @@ unsigned long usb_stor_read(int device, unsigned long blknr,
 		/* XXX need some comment here */
 		retry = 2;
 		srb->pdata = (unsigned char *)buf_addr;
-		if (blks > ss->max_xfer_blk)
-			smallblks = ss->max_xfer_blk;
+		max_xfer_blk = USB_MAX_XFER_BLK(buf_addr,
+						usb_dev_desc[device].blksz);
+		if (blks > max_xfer_blk)
+			smallblks = (unsigned short) max_xfer_blk;
 		else
 			smallblks = (unsigned short) blks;
 retry_it:
-		if (smallblks == ss->max_xfer_blk)
+		if (smallblks == max_xfer_blk)
 			usb_show_progress();
 		srb->datalen = usb_dev_desc[device].blksz * smallblks;
 		srb->pdata = (unsigned char *)buf_addr;
@@ -1109,7 +1116,7 @@ retry_it:
 			start, smallblks, buf_addr);
 
 	usb_disable_asynch(0); /* asynch transfer allowed */
-	if (blkcnt >= ss->max_xfer_blk)
+	if (blkcnt >= max_xfer_blk)
 		debug("\n");
 	return blkcnt;
 }
@@ -1117,7 +1124,7 @@ retry_it:
 unsigned long usb_stor_write(int device, unsigned long blknr,
 				unsigned long blkcnt, const void *buffer)
 {
-	unsigned long start, blks, buf_addr;
+	unsigned long start, blks, buf_addr, max_xfer_blk;
 	unsigned short smallblks;
 	struct usb_device *dev;
 	struct us_data *ss;
@@ -1162,12 +1169,14 @@ unsigned long usb_stor_write(int device, unsigned long blknr,
 		 */
 		retry = 2;
 		srb->pdata = (unsigned char *)buf_addr;
-		if (blks > ss->max_xfer_blk)
-			smallblks = ss->max_xfer_blk;
+		max_xfer_blk = USB_MAX_XFER_BLK(buf_addr,
+						usb_dev_desc[device].blksz);
+		if (blks > max_xfer_blk)
+			smallblks = (unsigned short) max_xfer_blk;
 		else
 			smallblks = (unsigned short) blks;
 retry_it:
-		if (smallblks == ss->max_xfer_blk)
+		if (smallblks == max_xfer_blk)
 			usb_show_progress();
 		srb->datalen = usb_dev_desc[device].blksz * smallblks;
 		srb->pdata = (unsigned char *)buf_addr;
@@ -1188,7 +1197,7 @@ retry_it:
 			start, smallblks, buf_addr);
 
 	usb_disable_asynch(0); /* asynch transfer allowed */
-	if (blkcnt >= ss->max_xfer_blk)
+	if (blkcnt >= max_xfer_blk)
 		debug("\n");
 	return blkcnt;
 
@@ -1415,12 +1424,6 @@ int usb_stor_get_info(struct usb_device *dev, struct us_data *ss,
 	USB_STOR_PRINTF(" address %d\n", dev_desc->target);
 	USB_STOR_PRINTF("partype: %d\n", dev_desc->part_type);
 
-	/*
-	 * The U-Boot EHCI driver cannot handle more than 4096 * 5 bytes in a
-	 * transfer without running itself out of qt_buffers.
-	 */
-	ss->max_xfer_blk = (4096 * 5) / dev_desc->blksz;
-
 	init_part(dev_desc);
 
 	USB_STOR_PRINTF("partype: %d\n", dev_desc->part_type);
diff --git a/drivers/usb/eth/smsc95xx.c b/drivers/usb/eth/smsc95xx.c
index c7aebea..c62a8c1 100644
--- a/drivers/usb/eth/smsc95xx.c
+++ b/drivers/usb/eth/smsc95xx.c
@@ -153,13 +153,15 @@ static int curr_eth_dev; /* index for name of next device detected */
 static int smsc95xx_write_reg(struct ueth_data *dev, u32 index, u32 data)
 {
 	int len;
+	ALLOC_CACHE_ALIGN_BUFFER(u32, tmpbuf, 1);
 
 	cpu_to_le32s(&data);
+	tmpbuf[0] = data;
 
 	len = usb_control_msg(dev->pusb_dev, usb_sndctrlpipe(dev->pusb_dev, 0),
 		USB_VENDOR_REQUEST_WRITE_REGISTER,
 		USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-		00, index, &data, sizeof(data), USB_CTRL_SET_TIMEOUT);
+		00, index, tmpbuf, sizeof(data), USB_CTRL_SET_TIMEOUT);
 	if (len != sizeof(data)) {
 		debug("smsc95xx_write_reg failed: index=%d, data=%d, len=%d",
 		      index, data, len);
@@ -171,11 +173,13 @@ static int smsc95xx_write_reg(struct ueth_data *dev, u32 index, u32 data)
 static int smsc95xx_read_reg(struct ueth_data *dev, u32 index, u32 *data)
 {
 	int len;
+	ALLOC_CACHE_ALIGN_BUFFER(u32, tmpbuf, 1);
 
 	len = usb_control_msg(dev->pusb_dev, usb_rcvctrlpipe(dev->pusb_dev, 0),
 		USB_VENDOR_REQUEST_READ_REGISTER,
 		USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-		00, index, data, sizeof(data), USB_CTRL_GET_TIMEOUT);
+		00, index, tmpbuf, sizeof(data), USB_CTRL_GET_TIMEOUT);
+	*data = tmpbuf[0];
 	if (len != sizeof(data)) {
 		debug("smsc95xx_read_reg failed: index=%d, len=%d",
 		      index, len);
@@ -664,7 +668,8 @@ static int smsc95xx_send(struct eth_device *eth, void* packet, int length)
 	int actual_len;
 	u32 tx_cmd_a;
 	u32 tx_cmd_b;
-	unsigned char msg[PKTSIZE + sizeof(tx_cmd_a) + sizeof(tx_cmd_b)];
+	ALLOC_CACHE_ALIGN_BUFFER(unsigned char, msg,
+				 PKTSIZE + sizeof(tx_cmd_a) + sizeof(tx_cmd_b));
 
 	debug("** %s(), len %d, buf %#x\n", __func__, length, (int)msg);
 	if (length > PKTSIZE)
@@ -695,7 +700,7 @@ static int smsc95xx_send(struct eth_device *eth, void* packet, int length)
 static int smsc95xx_recv(struct eth_device *eth)
 {
 	struct ueth_data *dev = (struct ueth_data *)eth->priv;
-	static unsigned char  recv_buf[AX_RX_URB_SIZE];
+	DEFINE_CACHE_ALIGN_BUFFER(unsigned char, recv_buf, AX_RX_URB_SIZE);
 	unsigned char *buf_ptr;
 	int err;
 	int actual_len;
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 04300be..2a82a29 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -34,7 +34,10 @@ struct ehci_hccr *hccr;	/* R/O registers, not need for volatile */
 volatile struct ehci_hcor *hcor;
 
 static uint16_t portreset;
-static struct QH qh_list __attribute__((aligned(32)));
+DEFINE_ALIGN_BUFFER(struct QH, qh_list, 1, USB_DMA_MINALIGN);
+
+#define ALIGN_END_ADDR(type, ptr, size)			\
+	((uint32_t)(ptr) + roundup((size) * sizeof(type), USB_DMA_MINALIGN))
 
 static struct descriptor {
 	struct usb_hub_descriptor hub;
@@ -172,18 +175,15 @@ static int ehci_td_buffer(struct qTD *td, void *buf, size_t sz)
 {
 	uint32_t delta, next;
 	uint32_t addr = (uint32_t)buf;
-	size_t rsz = roundup(sz, 32);
 	int idx;
 
-	if (sz != rsz)
-		debug("EHCI-HCD: Misaligned buffer size (%08x)\n", sz);
-
-	if (addr & 31)
+	if (addr != ALIGN(addr, ARCH_DMA_MINALIGN))
 		debug("EHCI-HCD: Misaligned buffer address (%p)\n", buf);
 
+	flush_dcache_range(addr, ALIGN(addr + sz, ARCH_DMA_MINALIGN));
+
 	idx = 0;
 	while (idx < 5) {
-		flush_dcache_range(addr, addr + rsz);
 		td->qt_buffer[idx] = cpu_to_hc32(addr);
 		td->qt_buffer_hi[idx] = 0;
 		next = (addr + 4096) & ~4095;
@@ -196,7 +196,7 @@ static int ehci_td_buffer(struct qTD *td, void *buf, size_t sz)
 	}
 
 	if (idx == 5) {
-		debug("out of buffer pointers (%u bytes left)\n", sz);
+		printf("out of buffer pointers (%u bytes left)\n", sz);
 		return -1;
 	}
 
@@ -207,8 +207,8 @@ static int
 ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer,
 		   int length, struct devrequest *req)
 {
-	static struct QH qh __attribute__((aligned(32)));
-	static struct qTD qtd[3] __attribute__((aligned (32)));
+	ALLOC_ALIGN_BUFFER(struct QH, qh, 1, USB_DMA_MINALIGN);
+	ALLOC_ALIGN_BUFFER(struct qTD, qtd, 3, USB_DMA_MINALIGN);
 	int qtd_counter = 0;
 
 	volatile struct qTD *vtd;
@@ -229,8 +229,8 @@ ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer,
 		      le16_to_cpu(req->value), le16_to_cpu(req->value),
 		      le16_to_cpu(req->index));
 
-	memset(&qh, 0, sizeof(struct QH));
-	memset(qtd, 0, sizeof(qtd));
+	memset(qh, 0, sizeof(struct QH));
+	memset(qtd, 0, 3 * sizeof(*qtd));
 
 	toggle = usb_gettoggle(dev, usb_pipeendpoint(pipe), usb_pipeout(pipe));
 
@@ -244,7 +244,7 @@ ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer,
 	 *   qh_overlay.qt_next ...... 13-10 H
 	 * - qh_overlay.qt_altnext
 	 */
-	qh.qh_link = cpu_to_hc32((uint32_t)&qh_list | QH_LINK_TYPE_QH);
+	qh->qh_link = cpu_to_hc32((uint32_t)qh_list | QH_LINK_TYPE_QH);
 	c = (usb_pipespeed(pipe) != USB_SPEED_HIGH &&
 	     usb_pipeendpoint(pipe) == 0) ? 1 : 0;
 	endpt = (8 << 28) |
@@ -255,14 +255,14 @@ ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer,
 	    (usb_pipespeed(pipe) << 12) |
 	    (usb_pipeendpoint(pipe) << 8) |
 	    (0 << 7) | (usb_pipedevice(pipe) << 0);
-	qh.qh_endpt1 = cpu_to_hc32(endpt);
+	qh->qh_endpt1 = cpu_to_hc32(endpt);
 	endpt = (1 << 30) |
 	    (dev->portnr << 23) |
 	    (dev->parent->devnum << 16) | (0 << 8) | (0 << 0);
-	qh.qh_endpt2 = cpu_to_hc32(endpt);
-	qh.qh_overlay.qt_next = cpu_to_hc32(QT_NEXT_TERMINATE);
+	qh->qh_endpt2 = cpu_to_hc32(endpt);
+	qh->qh_overlay.qt_next = cpu_to_hc32(QT_NEXT_TERMINATE);
 
-	tdp = &qh.qh_overlay.qt_next;
+	tdp = &qh->qh_overlay.qt_next;
 
 	if (req != NULL) {
 		/*
@@ -281,7 +281,7 @@ ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer,
 		    (0 << 15) | (0 << 12) | (3 << 10) | (2 << 8) | (0x80 << 0);
 		qtd[qtd_counter].qt_token = cpu_to_hc32(token);
 		if (ehci_td_buffer(&qtd[qtd_counter], req, sizeof(*req)) != 0) {
-			debug("unable construct SETUP td\n");
+			printf("unable construct SETUP td\n");
 			goto fail;
 		}
 		/* Update previous qTD! */
@@ -310,7 +310,7 @@ ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer,
 		    ((usb_pipein(pipe) ? 1 : 0) << 8) | (0x80 << 0);
 		qtd[qtd_counter].qt_token = cpu_to_hc32(token);
 		if (ehci_td_buffer(&qtd[qtd_counter], buffer, length) != 0) {
-			debug("unable construct DATA td\n");
+			printf("unable construct DATA td\n");
 			goto fail;
 		}
 		/* Update previous qTD! */
@@ -340,13 +340,16 @@ ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer,
 		tdp = &qtd[qtd_counter++].qt_next;
 	}
 
-	qh_list.qh_link = cpu_to_hc32((uint32_t)&qh | QH_LINK_TYPE_QH);
+	qh_list->qh_link = cpu_to_hc32((uint32_t)qh | QH_LINK_TYPE_QH);
 
 	/* Flush dcache */
-	flush_dcache_range((uint32_t)&qh_list,
-		(uint32_t)&qh_list + sizeof(struct QH));
-	flush_dcache_range((uint32_t)&qh, (uint32_t)&qh + sizeof(struct QH));
-	flush_dcache_range((uint32_t)qtd, (uint32_t)qtd + sizeof(qtd));
+	flush_dcache_range((uint32_t)qh_list,
+		ALIGN_END_ADDR(struct QH, qh_list, 1));
+	flush_dcache_range((uint32_t)qh, ALIGN_END_ADDR(struct QH, qh, 1));
+	flush_dcache_range((uint32_t)qtd, ALIGN_END_ADDR(struct qTD, qtd, 3));
+
+	/* Set async. queue head pointer. */
+	ehci_writel(&hcor->or_asynclistaddr, (uint32_t)qh_list);
 
 	usbsts = ehci_readl(&hcor->or_usbsts);
 	ehci_writel(&hcor->or_usbsts, (usbsts & 0x3f));
@@ -369,12 +372,12 @@ ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer,
 	timeout = USB_TIMEOUT_MS(pipe);
 	do {
 		/* Invalidate dcache */
-		invalidate_dcache_range((uint32_t)&qh_list,
-			(uint32_t)&qh_list + sizeof(struct QH));
-		invalidate_dcache_range((uint32_t)&qh,
-			(uint32_t)&qh + sizeof(struct QH));
+		invalidate_dcache_range((uint32_t)qh_list,
+			ALIGN_END_ADDR(struct QH, qh_list, 1));
+		invalidate_dcache_range((uint32_t)qh,
+			ALIGN_END_ADDR(struct QH, qh, 1));
 		invalidate_dcache_range((uint32_t)qtd,
-			(uint32_t)qtd + sizeof(qtd));
+			ALIGN_END_ADDR(struct qTD, qtd, 3));
 
 		token = hc32_to_cpu(vtd->qt_token);
 		if (!(token & 0x80))
@@ -382,9 +385,17 @@ ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer,
 		WATCHDOG_RESET();
 	} while (get_timer(ts) < timeout);
 
-	/* Invalidate the memory area occupied by buffer */
-	invalidate_dcache_range(((uint32_t)buffer & ~31),
-		((uint32_t)buffer & ~31) + roundup(length, 32));
+	/*
+	 * Invalidate the memory area occupied by buffer
+	 * Don't try to fix the buffer alignment, if it isn't properly
+	 * aligned it's upper layer's fault so let invalidate_dcache_range()
+	 * vow about it. But we have to fix the length as it's actual
+	 * transfer length and can be unaligned. This is potentially
+	 * dangerous operation, it's responsibility of the calling
+	 * code to make sure enough space is reserved.
+	 */
+	invalidate_dcache_range((uint32_t)buffer,
+		ALIGN((uint32_t)buffer + length, ARCH_DMA_MINALIGN));
 
 	/* Check that the TD processing happened */
 	if (token & 0x80) {
@@ -403,9 +414,7 @@ ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer,
 		goto fail;
 	}
 
-	qh_list.qh_link = cpu_to_hc32((uint32_t)&qh_list | QH_LINK_TYPE_QH);
-
-	token = hc32_to_cpu(qh.qh_overlay.qt_token);
+	token = hc32_to_cpu(qh->qh_overlay.qt_token);
 	if (!(token & 0x80)) {
 		debug("TOKEN=%#x\n", token);
 		switch (token & 0xfc) {
@@ -733,16 +742,13 @@ int usb_lowlevel_init(void)
 #endif
 
 	/* Set head of reclaim list */
-	memset(&qh_list, 0, sizeof(qh_list));
-	qh_list.qh_link = cpu_to_hc32((uint32_t)&qh_list | QH_LINK_TYPE_QH);
-	qh_list.qh_endpt1 = cpu_to_hc32((1 << 15) | (USB_SPEED_HIGH << 12));
-	qh_list.qh_curtd = cpu_to_hc32(QT_NEXT_TERMINATE);
-	qh_list.qh_overlay.qt_next = cpu_to_hc32(QT_NEXT_TERMINATE);
-	qh_list.qh_overlay.qt_altnext = cpu_to_hc32(QT_NEXT_TERMINATE);
-	qh_list.qh_overlay.qt_token = cpu_to_hc32(0x40);
-
-	/* Set async. queue head pointer. */
-	ehci_writel(&hcor->or_asynclistaddr, (uint32_t)&qh_list);
+	memset(qh_list, 0, sizeof(*qh_list));
+	qh_list->qh_link = cpu_to_hc32((uint32_t)qh_list | QH_LINK_TYPE_QH);
+	qh_list->qh_endpt1 = cpu_to_hc32((1 << 15) | (USB_SPEED_HIGH << 12));
+	qh_list->qh_curtd = cpu_to_hc32(QT_NEXT_TERMINATE);
+	qh_list->qh_overlay.qt_next = cpu_to_hc32(QT_NEXT_TERMINATE);
+	qh_list->qh_overlay.qt_altnext = cpu_to_hc32(QT_NEXT_TERMINATE);
+	qh_list->qh_overlay.qt_token = cpu_to_hc32(0x40);
 
 	reg = ehci_readl(&hccr->cr_hcsparams);
 	descriptor.hub.bNbrPorts = HCS_N_PORTS(reg);
diff --git a/drivers/usb/host/ehci-omap.c b/drivers/usb/host/ehci-omap.c
index 1ed7710..292673b 100644
--- a/drivers/usb/host/ehci-omap.c
+++ b/drivers/usb/host/ehci-omap.c
@@ -246,7 +246,6 @@ int omap_ehci_hcd_init(struct omap_usbhs_board_data *usbhs_pdata)
 		if (is_ehci_phy_mode(usbhs_pdata->port_mode[i]))
 			omap_ehci_soft_phy_reset(i);
 
-	dcache_disable();
 	hccr = (struct ehci_hccr *)(OMAP_EHCI_BASE);
 	hcor = (struct ehci_hcor *)(OMAP_EHCI_BASE + 0x10);
 
diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h
index a8adcce..e914369 100644
--- a/drivers/usb/musb/musb_core.h
+++ b/drivers/usb/musb/musb_core.h
@@ -145,7 +145,7 @@ struct musb_regs {
 		struct musb_epN_regs epN;
 	} ep[16];
 
-} __attribute__((packed, aligned(32)));
+} __attribute__((packed, aligned(USB_DMA_MINALIGN)));
 #endif
 
 /*
diff --git a/include/common.h b/include/common.h
index d1dd65a..be9c278 100644
--- a/include/common.h
+++ b/include/common.h
@@ -39,6 +39,7 @@ typedef volatile unsigned char	vu_char;
 #include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/string.h>
+#include <linux/compiler.h>
 #include <asm/ptrace.h>
 #include <stdarg.h>
 #if defined(CONFIG_PCI) && (defined(CONFIG_4xx) && !defined(CONFIG_AP1000))
@@ -944,11 +945,25 @@ int cpu_release(int nr, int argc, char * const argv[]);
  * of a function scoped static buffer.  It can not be used to create a cache
  * line aligned global buffer.
  */
+#define ALLOC_ALIGN_BUFFER(type, name, size, align)			\
+	char __##name[ROUND(size * sizeof(type), align) + (align - 1)];	\
+									\
+	type *name = (type *) ALIGN((uintptr_t)__##name, align)
 #define ALLOC_CACHE_ALIGN_BUFFER(type, name, size)			\
-	char __##name[ROUND(size * sizeof(type), ARCH_DMA_MINALIGN) +	\
-		      ARCH_DMA_MINALIGN - 1];				\
+	ALLOC_ALIGN_BUFFER(type, name, size, ARCH_DMA_MINALIGN)
+
+/*
+ * DEFINE_CACHE_ALIGN_BUFFER() is similar to ALLOC_CACHE_ALIGN_BUFFER, but it's
+ * purpose is to allow allocating aligned buffers outside of function scope.
+ * Usage of this macro shall be avoided or used with extreme care!
+ */
+#define DEFINE_ALIGN_BUFFER(type, name, size, align)			\
+	static char __##name[roundup(size * sizeof(type), align)]	\
+			__aligned(align);				\
 									\
-	type *name = (type *) ALIGN((uintptr_t)__##name, ARCH_DMA_MINALIGN)
+	static type *name = (type *)__##name
+#define DEFINE_CACHE_ALIGN_BUFFER(type, name, size)			\
+	DEFINE_ALIGN_BUFFER(type, name, size, ARCH_DMA_MINALIGN)
 
 /* Pull in stuff for the build system */
 #ifdef DO_DEPS_ONLY
diff --git a/include/usb.h b/include/usb.h
index 6da91e7..ba3d169 100644
--- a/include/usb.h
+++ b/include/usb.h
@@ -29,6 +29,16 @@
 #include <usb_defs.h>
 #include <usbdescriptors.h>
 
+/*
+ * The EHCI spec says that we must align to at least 32 bytes.  However,
+ * some platforms require larger alignment.
+ */
+#if ARCH_DMA_MINALIGN > 32
+#define USB_DMA_MINALIGN	ARCH_DMA_MINALIGN
+#else
+#define USB_DMA_MINALIGN	32
+#endif
+
 /* Everything is aribtrary */
 #define USB_ALTSETTINGALLOC		4
 #define USB_MAXALTSETTING		128	/* Hard limit */