usb: dwc2: Fix DMA cache alignment issues

Insert a padding between data and the stored_xfer_buffer pointer to
ensure they are not on the same cache line.

Otherwise, the stored_xfer_buffer gets corrupted for IN URBs on
non-cache-coherent systems. (In my case: Lantiq xRX200 MIPS)

Fixes: 3bc04e28 ("usb: dwc2: host: Get aligned DMA in a more supported way")
Fixes: 56406e01 ("usb: dwc2: Fix DMA alignment to start at allocated boundary")
Cc: <stable@vger.kernel.org>
Tested-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Acked-by: Minas Harutyunyan <hminas@synopsys.com>
Signed-off-by: Martin Schiller <ms@dev.tdt.de>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>

drivers/usb/dwc2/hcd.c

@@ -2480,8 +2480,10 @@ static void dwc2_free_dma_aligned_buffer(struct urb *urb)
 		return;
 
 	/* 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));
+	memcpy(&stored_xfer_buffer,
+	       PTR_ALIGN(urb->transfer_buffer + urb->transfer_buffer_length,
+			 dma_get_cache_alignment()),
+	       sizeof(urb->transfer_buffer));
 
 	if (usb_urb_dir_in(urb)) {
 		if (usb_pipeisoc(urb->pipe))
@@ -2513,6 +2515,7 @@ static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags)
 	 * DMA
 	 */
 	kmalloc_size = urb->transfer_buffer_length +
+		(dma_get_cache_alignment() - 1) +
 		sizeof(urb->transfer_buffer);
 
 	kmalloc_ptr = kmalloc(kmalloc_size, mem_flags);
@@ -2523,7 +2526,8 @@ static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags)
 	 * Position value of original urb->transfer_buffer pointer to the end
 	 * of allocation for later referencing
 	 */
-	memcpy(kmalloc_ptr + urb->transfer_buffer_length,
+	memcpy(PTR_ALIGN(kmalloc_ptr + urb->transfer_buffer_length,
+			 dma_get_cache_alignment()),
 	       &urb->transfer_buffer, sizeof(urb->transfer_buffer));
 
 	if (usb_urb_dir_out(urb))