Blackfin: fix early_dma_memcpy() handling of busy channels

The early logic to locate a free DMA channel and then set it up was broken
in a few ways that only manifested itself when we needed to set up more
than 2 on chip SRAM regions (most board defaults setup 1 or 2).  First, we
checked the wrong status register (the destination gets updated, not the
source) and second, we did the ssync before rather than after resetting a
DMA config register.

Signed-off-by: Mike Frysinger <vapier@gentoo.org>

arch/blackfin/kernel/bfin_dma_5xx.c

@@ -253,32 +253,31 @@ void __init early_dma_memcpy(void *pdst, const void *psrc, size_t size)
 	BUG_ON(src % 4);
 	BUG_ON(size % 4);
 
-	/* Force a sync in case a previous config reset on this channel
-	 * occurred.  This is needed so subsequent writes to DMA registers
-	 * are not spuriously lost/corrupted.
-	 */
-	__builtin_bfin_ssync();
-
 	src_ch = 0;
 	/* Find an avalible memDMA channel */
 	while (1) {
-		if (!src_ch || src_ch == (struct dma_register *)MDMA_S1_NEXT_DESC_PTR) {
-			dst_ch = (struct dma_register *)MDMA_D0_NEXT_DESC_PTR;
-			src_ch = (struct dma_register *)MDMA_S0_NEXT_DESC_PTR;
-		} else {
+		if (src_ch == (struct dma_register *)MDMA_S0_NEXT_DESC_PTR) {
 			dst_ch = (struct dma_register *)MDMA_D1_NEXT_DESC_PTR;
 			src_ch = (struct dma_register *)MDMA_S1_NEXT_DESC_PTR;
+		} else {
+			dst_ch = (struct dma_register *)MDMA_D0_NEXT_DESC_PTR;
+			src_ch = (struct dma_register *)MDMA_S0_NEXT_DESC_PTR;
 		}
 
-		if (!bfin_read16(&src_ch->cfg)) {
+		if (!bfin_read16(&src_ch->cfg))
+			break;
+		else if (bfin_read16(&dst_ch->irq_status) & DMA_DONE) {
+			bfin_write16(&src_ch->cfg, 0);
 			break;
-		} else {
-			if (bfin_read16(&src_ch->irq_status) & DMA_DONE)
-				bfin_write16(&src_ch->cfg, 0);
 		}
-
 	}
 
+	/* Force a sync in case a previous config reset on this channel
+	 * occurred.  This is needed so subsequent writes to DMA registers
+	 * are not spuriously lost/corrupted.
+	 */
+	__builtin_bfin_ssync();
+
 	/* Destination */
 	bfin_write32(&dst_ch->start_addr, dst);
 	bfin_write16(&dst_ch->x_count, size >> 2);