dmaengine: pl330: Improve transfer efficiency for the dregs

Only the unaligned burst transfers have the dregs.
so, still use BURST transfer with a reduced size
for better performance.
Signed-off-by: Sugar Zhang <sugar.zhang@rock-chips.com>
Link: https://lore.kernel.org/r/1593439555-68130-3-git-send-email-sugar.zhang@rock-chips.comSigned-off-by: Vinod Koul <vkoul@kernel.org>

drivers/dma/pl330.c

@@ -1228,8 +1228,9 @@ static int _bursts(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[],
 }
 
 /*
- * transfer dregs with single transfers to peripheral, or a reduced size burst
- * for mem-to-mem.
+ * only the unaligned burst transfers have the dregs.
+ * so, still transfer dregs with a reduced size burst
+ * for mem-to-mem, mem-to-dev or dev-to-mem.
  */
 static int _dregs(struct pl330_dmac *pl330, unsigned int dry_run, u8 buf[],
 		const struct _xfer_spec *pxs, int transfer_length)
@@ -1240,22 +1241,31 @@ static int _dregs(struct pl330_dmac *pl330, unsigned int dry_run, u8 buf[],
 	if (transfer_length == 0)
 		return off;
 
+	/*
+	 * dregs_len = (total bytes - BURST_TO_BYTE(bursts, ccr)) /
+	 *             BRST_SIZE(ccr)
+	 * the dregs len must be smaller than burst len,
+	 * so, for higher efficiency, we can modify CCR
+	 * to use a reduced size burst len for the dregs.
+	 */
+	dregs_ccr = pxs->ccr;
+	dregs_ccr &= ~((0xf << CC_SRCBRSTLEN_SHFT) |
+		(0xf << CC_DSTBRSTLEN_SHFT));
+	dregs_ccr |= (((transfer_length - 1) & 0xf) <<
+		CC_SRCBRSTLEN_SHFT);
+	dregs_ccr |= (((transfer_length - 1) & 0xf) <<
+		CC_DSTBRSTLEN_SHFT);
+
 	switch (pxs->desc->rqtype) {
 	case DMA_MEM_TO_DEV:
 		/* fall through */
 	case DMA_DEV_TO_MEM:
-		off += _ldst_peripheral(pl330, dry_run, &buf[off], pxs,
-			transfer_length, SINGLE);
+		off += _emit_MOV(dry_run, &buf[off], CCR, dregs_ccr);
+		off += _ldst_peripheral(pl330, dry_run, &buf[off], pxs, 1,
+					BURST);
 		break;
 
 	case DMA_MEM_TO_MEM:
-		dregs_ccr = pxs->ccr;
-		dregs_ccr &= ~((0xf << CC_SRCBRSTLEN_SHFT) |
-			(0xf << CC_DSTBRSTLEN_SHFT));
-		dregs_ccr |= (((transfer_length - 1) & 0xf) <<
-			CC_SRCBRSTLEN_SHFT);
-		dregs_ccr |= (((transfer_length - 1) & 0xf) <<
-			CC_DSTBRSTLEN_SHFT);
 		off += _emit_MOV(dry_run, &buf[off], CCR, dregs_ccr);
 		off += _ldst_memtomem(dry_run, &buf[off], pxs, 1);
 		break;