spi: imx: correct wml as the last sg length

Correct wml as the last rx sg length instead of the whole transfer
length. Otherwise, mtd_stresstest will be failed as below:

insmod mtd_stresstest.ko dev=0
=================================================
mtd_stresstest: MTD device: 0
mtd_stresstest: not NAND flash, assume page size is 512 bytes.
mtd_stresstest: MTD device size 4194304, eraseblock size 65536, page size 512, count of eraseblocks 64, pa0
mtd_stresstest: doing operations
mtd_stresstest: 0 operations done
mtd_test: mtd_read from 1ff532, size 880
mtd_test: mtd_read from 20c267, size 64998
spi_master spi0: I/O Error in DMA RX
m25p80 spi0.0: SPI transfer failed: -110
spi_master spi0: failed to transfer one message from queue
mtd_test: error: read failed at 0x20c267
mtd_stresstest: error -110 occurred
=================================================
insmod: ERROR: could not insert module mtd_stresstest.ko: Connection timed out

Signed-off-by: Robin Gong <yibin.gong@nxp.com>
Signed-off-by: Mark Brown <broonie@kernel.org>

drivers/spi/spi-imx.c

@@ -217,22 +217,13 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
 			 struct spi_transfer *transfer)
 {
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(master);
-	unsigned int bytes_per_word, i;
 
 	if (!master->dma_rx)
 		return false;
 
 	if (spi_imx->slave_mode)
 		return false;
 
-	bytes_per_word = spi_imx_bytes_per_word(transfer->bits_per_word);
-
-	for (i = spi_imx->devtype_data->fifo_size / 2; i > 0; i--) {
-		if (!(transfer->len % (i * bytes_per_word)))
-			break;
-	}
-
-	spi_imx->wml = i;
 	spi_imx->dynamic_burst = 0;
 
 	return true;
@@ -594,7 +585,7 @@ static void mx51_setup_wml(struct spi_imx_data *spi_imx)
 	 * and enable DMA request.
 	 */
 
-	writel(MX51_ECSPI_DMA_RX_WML(spi_imx->wml) |
+	writel(MX51_ECSPI_DMA_RX_WML(spi_imx->wml - 1) |
 		MX51_ECSPI_DMA_TX_WML(spi_imx->wml) |
 		MX51_ECSPI_DMA_RXT_WML(spi_imx->wml) |
 		MX51_ECSPI_DMA_TEDEN | MX51_ECSPI_DMA_RXDEN |
@@ -1287,12 +1278,30 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx,
 	unsigned long timeout;
 	struct spi_master *master = spi_imx->bitbang.master;
 	struct sg_table *tx = &transfer->tx_sg, *rx = &transfer->rx_sg;
+	struct scatterlist *last_sg = sg_last(rx->sgl, rx->nents);
+	unsigned int bytes_per_word, i;
 	int ret;
 
+	/* Get the right burst length from the last sg to ensure no tail data */
+	bytes_per_word = spi_imx_bytes_per_word(transfer->bits_per_word);
+	for (i = spi_imx->devtype_data->fifo_size / 2; i > 0; i--) {
+		if (!(sg_dma_len(last_sg) % (i * bytes_per_word)))
+			break;
+	}
+	/* Use 1 as wml in case no available burst length got */
+	if (i == 0)
+		i = 1;
+
+	spi_imx->wml =  i;
+
 	ret = spi_imx_dma_configure(master);
 	if (ret)
 		return ret;
 
+	if (!spi_imx->devtype_data->setup_wml) {
+		dev_err(spi_imx->dev, "No setup_wml()?\n");
+		return -EINVAL;
+	}
 	spi_imx->devtype_data->setup_wml(spi_imx);
 
 	/*