From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 18 Mar 2020 02:15:54 +0200
Subject: spi: spi-fsl-dspi: Fix bits-per-word acceleration in DMA mode
Git-commit: a957499bd437720d082d92657b7eb5cf5a62e893
Patch-mainline: v5.7-rc1
References: bsc#1167260
In DMA mode, dspi_setup_accel does not get called, which results in the
dspi->oper_word_size variable (which is used by dspi_dma_xfer) to not be
initialized properly.
Because oper_word_size is zero, a few calculations end up being
incorrect, and the DMA transfer eventually times out instead of sending
anything on the wire.
Set up native transfers (or 8-on-16 acceleration) using dspi_setup_accel
for DMA mode too.
Also take the opportunity and simplify the DMA buffer handling a little
bit.
Fixes: 6c1c26ecd9a3 ("spi: spi-fsl-dspi: Accelerate transfers using larger word size if possible")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Michael Walle <michael@walle.cc>
Link: https://lore.kernel.org/r/20200318001603.9650-4-olteanv@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Mian Yousaf Kaukab <ykaukab@suse.de>
---
drivers/spi/spi-fsl-dspi.c | 86 ++++++++++++++++-----------------------------
1 file changed, 32 insertions(+), 54 deletions(-)
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -119,7 +119,6 @@ struct fsl_dspi_devtype_data {
enum dspi_trans_mode trans_mode;
u8 max_clock_factor;
int fifo_size;
- int dma_bufsize;
};
enum {
@@ -138,7 +137,6 @@ static const struct fsl_dspi_devtype_dat
[VF610] = {
.trans_mode = DSPI_DMA_MODE,
.max_clock_factor = 2,
- .dma_bufsize = 4096,
.fifo_size = 4,
},
[LS1021A] = {
@@ -167,19 +165,16 @@ static const struct fsl_dspi_devtype_dat
},
[LS2080A] = {
.trans_mode = DSPI_DMA_MODE,
- .dma_bufsize = 8,
.max_clock_factor = 8,
.fifo_size = 4,
},
[LS2085A] = {
.trans_mode = DSPI_DMA_MODE,
- .dma_bufsize = 8,
.max_clock_factor = 8,
.fifo_size = 4,
},
[LX2160A] = {
.trans_mode = DSPI_DMA_MODE,
- .dma_bufsize = 8,
.max_clock_factor = 8,
.fifo_size = 4,
},
@@ -191,9 +186,6 @@ static const struct fsl_dspi_devtype_dat
};
struct fsl_dspi_dma {
- /* Length of transfer in words of dspi->fifo_size */
- u32 curr_xfer_len;
-
u32 *tx_dma_buf;
struct dma_chan *chan_tx;
dma_addr_t tx_dma_phys;
@@ -351,7 +343,7 @@ static void dspi_rx_dma_callback(void *a
int i;
if (dspi->rx) {
- for (i = 0; i < dma->curr_xfer_len; i++)
+ for (i = 0; i < dspi->words_in_flight; i++)
dspi_push_rx(dspi, dspi->dma->rx_dma_buf[i]);
}
@@ -365,12 +357,12 @@ static int dspi_next_xfer_dma_submit(str
int time_left;
int i;
- for (i = 0; i < dma->curr_xfer_len; i++)
+ for (i = 0; i < dspi->words_in_flight; i++)
dspi->dma->tx_dma_buf[i] = dspi_pop_tx_pushr(dspi);
dma->tx_desc = dmaengine_prep_slave_single(dma->chan_tx,
dma->tx_dma_phys,
- dma->curr_xfer_len *
+ dspi->words_in_flight *
DMA_SLAVE_BUSWIDTH_4_BYTES,
DMA_MEM_TO_DEV,
DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
@@ -388,7 +380,7 @@ static int dspi_next_xfer_dma_submit(str
dma->rx_desc = dmaengine_prep_slave_single(dma->chan_rx,
dma->rx_dma_phys,
- dma->curr_xfer_len *
+ dspi->words_in_flight *
DMA_SLAVE_BUSWIDTH_4_BYTES,
DMA_DEV_TO_MEM,
DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
@@ -436,46 +428,42 @@ static int dspi_next_xfer_dma_submit(str
return 0;
}
+static void dspi_setup_accel(struct fsl_dspi *dspi);
+
static int dspi_dma_xfer(struct fsl_dspi *dspi)
{
struct spi_message *message = dspi->cur_msg;
struct device *dev = &dspi->pdev->dev;
- struct fsl_dspi_dma *dma = dspi->dma;
- int curr_remaining_bytes;
- int bytes_per_buffer;
int ret = 0;
- curr_remaining_bytes = dspi->len;
- bytes_per_buffer = dspi->devtype_data->dma_bufsize /
- dspi->devtype_data->fifo_size;
- while (curr_remaining_bytes) {
- /* Check if current transfer fits the DMA buffer */
- dma->curr_xfer_len = curr_remaining_bytes /
- dspi->oper_word_size;
- if (dma->curr_xfer_len > bytes_per_buffer)
- dma->curr_xfer_len = bytes_per_buffer;
+ /*
+ * dspi->len gets decremented by dspi_pop_tx_pushr in
+ * dspi_next_xfer_dma_submit
+ */
+ while (dspi->len) {
+ /* Figure out operational bits-per-word for this chunk */
+ dspi_setup_accel(dspi);
+
+ dspi->words_in_flight = dspi->len / dspi->oper_word_size;
+ if (dspi->words_in_flight > dspi->devtype_data->fifo_size)
+ dspi->words_in_flight = dspi->devtype_data->fifo_size;
+
+ message->actual_length += dspi->words_in_flight *
+ dspi->oper_word_size;
ret = dspi_next_xfer_dma_submit(dspi);
if (ret) {
dev_err(dev, "DMA transfer failed\n");
- goto exit;
-
- } else {
- const int len = dma->curr_xfer_len *
- dspi->oper_word_size;
- curr_remaining_bytes -= len;
- message->actual_length += len;
- if (curr_remaining_bytes < 0)
- curr_remaining_bytes = 0;
+ break;
}
}
-exit:
return ret;
}
static int dspi_request_dma(struct fsl_dspi *dspi, phys_addr_t phy_addr)
{
+ int dma_bufsize = dspi->devtype_data->fifo_size * 2;
struct device *dev = &dspi->pdev->dev;
struct dma_slave_config cfg;
struct fsl_dspi_dma *dma;
@@ -500,16 +488,16 @@ static int dspi_request_dma(struct fsl_d
}
dma->tx_dma_buf = dma_alloc_coherent(dma->chan_tx->device->dev,
- dspi->devtype_data->dma_bufsize,
- &dma->tx_dma_phys, GFP_KERNEL);
+ dma_bufsize, &dma->tx_dma_phys,
+ GFP_KERNEL);
if (!dma->tx_dma_buf) {
ret = -ENOMEM;
goto err_tx_dma_buf;
}
dma->rx_dma_buf = dma_alloc_coherent(dma->chan_rx->device->dev,
- dspi->devtype_data->dma_bufsize,
- &dma->rx_dma_phys, GFP_KERNEL);
+ dma_bufsize, &dma->rx_dma_phys,
+ GFP_KERNEL);
if (!dma->rx_dma_buf) {
ret = -ENOMEM;
goto err_rx_dma_buf;
@@ -546,12 +534,10 @@ static int dspi_request_dma(struct fsl_d
err_slave_config:
dma_free_coherent(dma->chan_rx->device->dev,
- dspi->devtype_data->dma_bufsize,
- dma->rx_dma_buf, dma->rx_dma_phys);
+ dma_bufsize, dma->rx_dma_buf, dma->rx_dma_phys);
err_rx_dma_buf:
dma_free_coherent(dma->chan_tx->device->dev,
- dspi->devtype_data->dma_bufsize,
- dma->tx_dma_buf, dma->tx_dma_phys);
+ dma_bufsize, dma->tx_dma_buf, dma->tx_dma_phys);
err_tx_dma_buf:
dma_release_channel(dma->chan_tx);
err_tx_channel:
@@ -565,6 +551,7 @@ err_tx_channel:
static void dspi_release_dma(struct fsl_dspi *dspi)
{
+ int dma_bufsize = dspi->devtype_data->fifo_size * 2;
struct fsl_dspi_dma *dma = dspi->dma;
if (!dma)
@@ -572,15 +559,13 @@ static void dspi_release_dma(struct fsl_
if (dma->chan_tx) {
dma_unmap_single(dma->chan_tx->device->dev, dma->tx_dma_phys,
- dspi->devtype_data->dma_bufsize,
- DMA_TO_DEVICE);
+ dma_bufsize, DMA_TO_DEVICE);
dma_release_channel(dma->chan_tx);
}
if (dma->chan_rx) {
dma_unmap_single(dma->chan_rx->device->dev, dma->rx_dma_phys,
- dspi->devtype_data->dma_bufsize,
- DMA_FROM_DEVICE);
+ dma_bufsize, DMA_FROM_DEVICE);
dma_release_channel(dma->chan_rx);
}
}
@@ -832,7 +817,7 @@ no_accel:
dspi->oper_word_size = DIV_ROUND_UP(dspi->oper_bits_per_word, 8);
/*
- * Update CTAR here (code is common for both EOQ and XSPI modes).
+ * Update CTAR here (code is common for EOQ, XSPI and DMA modes).
* We will update CTARE in the portion specific to XSPI, when we
* also know the preload value (DTCP).
*/
@@ -952,13 +937,6 @@ static int dspi_transfer_one_message(str
regmap_update_bits(dspi->regmap, SPI_MCR,
SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF,
SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF);
- /*
- * Static CTAR setup for modes that don't dynamically adjust it
- * via dspi_setup_accel (aka for DMA)
- */
- regmap_write(dspi->regmap, SPI_CTAR(0),
- dspi->cur_chip->ctar_val |
- SPI_FRAME_BITS(transfer->bits_per_word));
trans_mode = dspi->devtype_data->trans_mode;
switch (trans_mode) {