spi: imx: allow only WML aligned transfers to use DMA

RX DMA tail data handling doesn't work correctly in many cases with current
implementation. It happens because SPI core was setup to generates both RX
and RX TAIL events. And RX TAIL event does not work correctly.
This can be easily verified by sending SPI transaction with size modulus
WML(32 in our case) not equal 0.

Also removing change introduced in f6ee9b58
since this change only fix usecases with transfer size from 33 to 128 bytes
and doesn't fix 129 bytes and bigger.

This is output from transaction with len 138 bytes in loopback mode at 10Mhz:
TX0000: a3 97 a2 55 53 be f1 fc f9 79 6b 52 14 13 e9 e2
TX0010: 2d 51 8e 1f 56 08 57 27 a7 05 d4 d0 52 82 77 75
TX0020: 1b 99 4a ed 58 3d 6a 52 36 d5 24 4a 68 8e ad 95
TX0030: 5f 3c 35 b5 c4 8c dd 6c 11 32 3d e2 b4 b4 59 cf
TX0040: ce 23 3d 27 df a7 f9 96 fc 1e e0 66 2c 0e 7b 8c
TX0050: ca 30 42 8f bc 9f 7b ce d1 b8 b1 87 ec 8a d6 bb
TX0060: 2e 15 63 0e 3c dc a4 3a 7a 06 20 a7 93 1b 34 dd
TX0070: 4c f5 ec 88 96 68 d6 68 a0 09 6f 8e 93 47 c9 41
TX0080: db ac cf 97 89 f3 51 05 79 71

RX0000: a3 97 a2 55 53 be f1 fc f9 79 6b 52 14 13 e9 e2
RX0010: 2d 51 8e 1f 56 08 57 27 a7 05 d4 d0 52 82 77 75
RX0020: 1b 99 4a ed 58 3d 6a 52 36 d5 24 4a 68 8e ad 95
RX0030: 5f 3c 35 00 00 b5 00 00 00 c4 00 00 8c 00 00 dd
RX0040: 6c 11 32 3d e2 b4 b4 59 cf ce 23 3d 27 df a7 f9
RX0050: 96 fc 1e e0 66 2c 0e 7b 8c ca 30 42 8f 1f 1f bc
RX0060: 9f 7b ce d1 b8 b1 87 ec 8a d6 bb 2e 15 63 0e ed
RX0070: ed 3c 58 58 58 dc 3d 3d a4 6a 6a 3a 52 52 7a 36
RX0080: 06 20 a7 93 1b 34 dd 4c f5 ec

Zeros at offset 33 and 34 caused by reading empty RX FIFO which not possible
if DMA RX read was triggered by RX event. This mean DMA was triggered
by RX TAIL event.
Signed-off-by: Anton Bondarenko <anton.bondarenko.sama@gmail.com>
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Mark Brown <broonie@kernel.org>

drivers/spi/spi-imx.c

@@ -204,8 +204,8 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
 {
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(master);
 
-	if (spi_imx->dma_is_inited &&
-	    transfer->len > spi_imx->wml * sizeof(u32))
+	if (spi_imx->dma_is_inited && transfer->len >= spi_imx->wml &&
+	    (transfer->len % spi_imx->wml) == 0)
 		return true;
 	return false;
 }
@@ -919,8 +919,6 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx,
 	struct dma_async_tx_descriptor *desc_tx = NULL, *desc_rx = NULL;
 	int ret;
 	unsigned long timeout;
-	u32 dma;
-	int left;
 	struct spi_master *master = spi_imx->bitbang.master;
 	struct sg_table *tx = &transfer->tx_sg, *rx = &transfer->rx_sg;
 
@@ -954,13 +952,6 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx,
 	/* Trigger the cspi module. */
 	spi_imx->dma_finished = 0;
 
-	dma = readl(spi_imx->base + MX51_ECSPI_DMA);
-	dma = dma & (~MX51_ECSPI_DMA_RXT_WML_MASK);
-	/* Change RX_DMA_LENGTH trigger dma fetch tail data */
-	left = transfer->len % spi_imx->wml;
-	if (left)
-		writel(dma | (left << MX51_ECSPI_DMA_RXT_WML_OFFSET),
-				spi_imx->base + MX51_ECSPI_DMA);
 	/*
 	 * Set these order to avoid potential RX overflow. The overflow may
 	 * happen if we enable SPI HW before starting RX DMA due to rescheduling
@@ -992,10 +983,6 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx,
 			spi_imx->devtype_data->reset(spi_imx);
 			dmaengine_terminate_all(master->dma_rx);
 		}
-		dma &= ~MX51_ECSPI_DMA_RXT_WML_MASK;
-		writel(dma |
-		       spi_imx->wml << MX51_ECSPI_DMA_RXT_WML_OFFSET,
-		       spi_imx->base + MX51_ECSPI_DMA);
 	}
 
 	spi_imx->dma_finished = 1;