spi: dw: Add SPI Tx-done wait method to DMA-based transfer

Since DMA transfers are performed asynchronously with actual SPI bus
transfers, then even if DMA transactions are finished it doesn't mean
all data is actually pushed to the SPI bus. Some data might still be
in the controller FIFO. This is specifically true for Tx-only transfers.
In this case if the next SPI transfer is recharged while a tail of the
previous one is still in FIFO, we'll loose that tail data. In order to
fix that problem let's add the wait procedure of the Tx SPI transfer
completion after the DMA transactions are finished.

Fixes: 7063c0d942 ("spi/dw_spi: add DMA support")
Co-developed-by: Georgy Vlasov <Georgy.Vlasov@baikalelectronics.ru>
Signed-off-by: Georgy Vlasov <Georgy.Vlasov@baikalelectronics.ru>
Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Cc: Ramil Zaripov <Ramil.Zaripov@baikalelectronics.ru>
Cc: Alexey Malahov <Alexey.Malahov@baikalelectronics.ru>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: linux-mips@vger.kernel.org
Cc: devicetree@vger.kernel.org
Link: https://lore.kernel.org/r/20200529131205.31838-5-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Mark Brown <broonie@kernel.org>

drivers/spi/spi-dw-mid.c

@@ -19,6 +19,7 @@
 #include <linux/pci.h>
 #include <linux/platform_data/dma-dw.h>
 
+#define WAIT_RETRIES	5
 #define RX_BUSY		0
 #define TX_BUSY		1
 
@@ -171,6 +172,33 @@ static int dw_spi_dma_wait(struct dw_spi *dws, struct spi_transfer *xfer)
 	return 0;
 }
 
+static inline bool dw_spi_dma_tx_busy(struct dw_spi *dws)
+{
+	return !(dw_readl(dws, DW_SPI_SR) & SR_TF_EMPT);
+}
+
+static int dw_spi_dma_wait_tx_done(struct dw_spi *dws,
+				   struct spi_transfer *xfer)
+{
+	int retry = WAIT_RETRIES;
+	struct spi_delay delay;
+	u32 nents;
+
+	nents = dw_readl(dws, DW_SPI_TXFLR);
+	delay.unit = SPI_DELAY_UNIT_SCK;
+	delay.value = nents * dws->n_bytes * BITS_PER_BYTE;
+
+	while (dw_spi_dma_tx_busy(dws) && retry--)
+		spi_delay_exec(&delay, xfer);
+
+	if (retry < 0) {
+		dev_err(&dws->master->dev, "Tx hanged up\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
 /*
  * dws->dma_chan_busy is set before the dma transfer starts, callback for tx
  * channel will clear a corresponding bit.
@@ -324,6 +352,12 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, struct spi_transfer *xfer)
 	if (ret)
 		return ret;
 
+	if (txdesc && dws->master->cur_msg->status == -EINPROGRESS) {
+		ret = dw_spi_dma_wait_tx_done(dws, xfer);
+		if (ret)
+			return ret;
+	}
+
 	return 0;
 }