* These are counted as well in @count_transfer_polling and
* @count_transfer_irq
* @count_transfer_dma: count how often dma mode is used
+ * @chip_select: SPI slave currently selected
+ * (used by bcm2835_spi_dma_tx_done() to write @clear_rx_cs)
+ * @tx_dma_active: whether a TX DMA descriptor is in progress
+ * @rx_dma_active: whether a RX DMA descriptor is in progress
+ * (used by bcm2835_spi_dma_tx_done() to handle a race)
+ * @clear_rx_desc: preallocated RX DMA descriptor used for TX-only transfers
+ * (cyclically clears RX FIFO by writing @clear_rx_cs to CS register)
+ * @clear_rx_addr: bus address of @clear_rx_cs
+ * @clear_rx_cs: precalculated CS register value to clear RX FIFO
+ * (uses slave-specific clock polarity and phase settings)
*/
struct bcm2835_spi {
void __iomem *regs;
u64 count_transfer_irq;
u64 count_transfer_irq_after_polling;
u64 count_transfer_dma;
+
+ u8 chip_select;
+ unsigned int tx_dma_active;
+ unsigned int rx_dma_active;
+ struct dma_async_tx_descriptor *clear_rx_desc[BCM2835_SPI_NUM_CS];
+ dma_addr_t clear_rx_addr;
+ u32 clear_rx_cs[BCM2835_SPI_NUM_CS] ____cacheline_aligned;
};
#if defined(CONFIG_DEBUG_FS)
if (!sg_is_last(&tfr->tx_sg.sgl[0]))
bs->tx_prologue = sg_dma_len(&tfr->tx_sg.sgl[0]) & 3;
- if (!sg_is_last(&tfr->rx_sg.sgl[0])) {
+ if (bs->rx_buf && !sg_is_last(&tfr->rx_sg.sgl[0])) {
bs->rx_prologue = sg_dma_len(&tfr->rx_sg.sgl[0]) & 3;
if (bs->rx_prologue > bs->tx_prologue) {
bs->tx_prologue = 0;
}
-static void bcm2835_spi_dma_done(void *data)
+/**
+ * bcm2835_spi_dma_rx_done() - callback for DMA RX channel
+ * @data: SPI master controller
+ *
+ * Used for bidirectional and RX-only transfers.
+ */
+static void bcm2835_spi_dma_rx_done(void *data)
{
struct spi_controller *ctlr = data;
struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
* situation otherwise...
*/
dmaengine_terminate_async(ctlr->dma_tx);
+ bs->tx_dma_active = false;
+ bs->rx_dma_active = false;
bcm2835_spi_undo_prologue(bs);
/* and mark as completed */;
complete(&ctlr->xfer_completion);
}
+/**
+ * bcm2835_spi_dma_tx_done() - callback for DMA TX channel
+ * @data: SPI master controller
+ *
+ * Used for TX-only transfers.
+ */
+static void bcm2835_spi_dma_tx_done(void *data)
+{
+ struct spi_controller *ctlr = data;
+ struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
+
+ /* busy-wait for TX FIFO to empty */
+ while (!(bcm2835_rd(bs, BCM2835_SPI_CS) & BCM2835_SPI_CS_DONE))
+ bcm2835_wr(bs, BCM2835_SPI_CS,
+ bs->clear_rx_cs[bs->chip_select]);
+
+ bs->tx_dma_active = false;
+ smp_wmb();
+
+ /*
+ * In case of a very short transfer, RX DMA may not have been
+ * issued yet. The onus is then on bcm2835_spi_transfer_one_dma()
+ * to terminate it immediately after issuing.
+ */
+ if (cmpxchg(&bs->rx_dma_active, true, false))
+ dmaengine_terminate_async(ctlr->dma_rx);
+
+ bcm2835_spi_undo_prologue(bs);
+ bcm2835_spi_reset_hw(ctlr);
+ complete(&ctlr->xfer_completion);
+}
+
+/**
+ * bcm2835_spi_prepare_sg() - prepare and submit DMA descriptor for sglist
+ * @ctlr: SPI master controller
+ * @spi: SPI slave
+ * @tfr: SPI transfer
+ * @bs: BCM2835 SPI controller
+ * @is_tx: whether to submit DMA descriptor for TX or RX sglist
+ *
+ * Prepare and submit a DMA descriptor for the TX or RX sglist of @tfr.
+ * Return 0 on success or a negative error number.
+ */
static int bcm2835_spi_prepare_sg(struct spi_controller *ctlr,
+ struct spi_device *spi,
struct spi_transfer *tfr,
+ struct bcm2835_spi *bs,
bool is_tx)
{
struct dma_chan *chan;
chan = ctlr->dma_tx;
nents = tfr->tx_sg.nents;
sgl = tfr->tx_sg.sgl;
- flags = 0 /* no tx interrupt */;
-
+ flags = tfr->rx_buf ? 0 : DMA_PREP_INTERRUPT;
} else {
dir = DMA_DEV_TO_MEM;
chan = ctlr->dma_rx;
if (!desc)
return -EINVAL;
- /* set callback for rx */
+ /*
+ * Completion is signaled by the RX channel for bidirectional and
+ * RX-only transfers; else by the TX channel for TX-only transfers.
+ */
if (!is_tx) {
- desc->callback = bcm2835_spi_dma_done;
+ desc->callback = bcm2835_spi_dma_rx_done;
+ desc->callback_param = ctlr;
+ } else if (!tfr->rx_buf) {
+ desc->callback = bcm2835_spi_dma_tx_done;
desc->callback_param = ctlr;
+ bs->chip_select = spi->chip_select;
}
/* submit it to DMA-engine */
return dma_submit_error(cookie);
}
+/**
+ * bcm2835_spi_transfer_one_dma() - perform SPI transfer using DMA engine
+ * @ctlr: SPI master controller
+ * @spi: SPI slave
+ * @tfr: SPI transfer
+ * @cs: CS register
+ *
+ * For *bidirectional* transfers (both tx_buf and rx_buf are non-%NULL), set up
+ * the TX and RX DMA channel to copy between memory and FIFO register.
+ *
+ * For *TX-only* transfers (rx_buf is %NULL), copying the RX FIFO's contents to
+ * memory is pointless. However not reading the RX FIFO isn't an option either
+ * because transmission is halted once it's full. As a workaround, cyclically
+ * clear the RX FIFO by setting the CLEAR_RX bit in the CS register.
+ *
+ * The CS register value is precalculated in bcm2835_spi_setup(). Normally
+ * this is called only once, on slave registration. A DMA descriptor to write
+ * this value is preallocated in bcm2835_dma_init(). All that's left to do
+ * when performing a TX-only transfer is to submit this descriptor to the RX
+ * DMA channel. Latency is thereby minimized. The descriptor does not
+ * generate any interrupts while running. It must be terminated once the
+ * TX DMA channel is done.
+ *
+ * Clearing the RX FIFO is paced by the DREQ signal. The signal is asserted
+ * when the RX FIFO becomes half full, i.e. 32 bytes. (Tuneable with the DC
+ * register.) Reading 32 bytes from the RX FIFO would normally require 8 bus
+ * accesses, whereas clearing it requires only 1 bus access. So an 8-fold
+ * reduction in bus traffic and thus energy consumption is achieved.
+ */
static int bcm2835_spi_transfer_one_dma(struct spi_controller *ctlr,
struct spi_device *spi,
struct spi_transfer *tfr,
u32 cs)
{
struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
+ dma_cookie_t cookie;
int ret;
/* update usage statistics */
bcm2835_spi_transfer_prologue(ctlr, tfr, bs, cs);
/* setup tx-DMA */
- ret = bcm2835_spi_prepare_sg(ctlr, tfr, true);
+ ret = bcm2835_spi_prepare_sg(ctlr, spi, tfr, bs, true);
if (ret)
goto err_reset_hw;
- /* start TX early */
- dma_async_issue_pending(ctlr->dma_tx);
-
/* set the DMA length */
bcm2835_wr(bs, BCM2835_SPI_DLEN, bs->tx_len);
bcm2835_wr(bs, BCM2835_SPI_CS,
cs | BCM2835_SPI_CS_TA | BCM2835_SPI_CS_DMAEN);
+ bs->tx_dma_active = true;
+ smp_wmb();
+
+ /* start TX early */
+ dma_async_issue_pending(ctlr->dma_tx);
+
/* setup rx-DMA late - to run transfers while
* mapping of the rx buffers still takes place
* this saves 10us or more.
*/
- ret = bcm2835_spi_prepare_sg(ctlr, tfr, false);
+ if (bs->rx_buf) {
+ ret = bcm2835_spi_prepare_sg(ctlr, spi, tfr, bs, false);
+ } else {
+ cookie = dmaengine_submit(bs->clear_rx_desc[spi->chip_select]);
+ ret = dma_submit_error(cookie);
+ }
if (ret) {
/* need to reset on errors */
dmaengine_terminate_sync(ctlr->dma_tx);
+ bs->tx_dma_active = false;
goto err_reset_hw;
}
/* start rx dma late */
dma_async_issue_pending(ctlr->dma_rx);
+ bs->rx_dma_active = true;
+ smp_mb();
+
+ /*
+ * In case of a very short TX-only transfer, bcm2835_spi_dma_tx_done()
+ * may run before RX DMA is issued. Terminate RX DMA if so.
+ */
+ if (!bs->rx_buf && !bs->tx_dma_active &&
+ cmpxchg(&bs->rx_dma_active, true, false)) {
+ dmaengine_terminate_async(ctlr->dma_rx);
+ bcm2835_spi_reset_hw(ctlr);
+ }
/* wait for wakeup in framework */
return 1;
return true;
}
-static void bcm2835_dma_release(struct spi_controller *ctlr)
+static void bcm2835_dma_release(struct spi_controller *ctlr,
+ struct bcm2835_spi *bs)
{
+ int i;
+
if (ctlr->dma_tx) {
dmaengine_terminate_sync(ctlr->dma_tx);
dma_release_channel(ctlr->dma_tx);
ctlr->dma_tx = NULL;
}
+
if (ctlr->dma_rx) {
dmaengine_terminate_sync(ctlr->dma_rx);
+
+ for (i = 0; i < BCM2835_SPI_NUM_CS; i++)
+ if (bs->clear_rx_desc[i])
+ dmaengine_desc_free(bs->clear_rx_desc[i]);
+
+ if (bs->clear_rx_addr)
+ dma_unmap_single(ctlr->dma_rx->device->dev,
+ bs->clear_rx_addr,
+ sizeof(bs->clear_rx_cs),
+ DMA_TO_DEVICE);
+
dma_release_channel(ctlr->dma_rx);
ctlr->dma_rx = NULL;
}
}
-static void bcm2835_dma_init(struct spi_controller *ctlr, struct device *dev)
+static void bcm2835_dma_init(struct spi_controller *ctlr, struct device *dev,
+ struct bcm2835_spi *bs)
{
struct dma_slave_config slave_config;
const __be32 *addr;
dma_addr_t dma_reg_base;
- int ret;
+ int ret, i;
/* base address in dma-space */
addr = of_get_address(ctlr->dev.of_node, 0, NULL, NULL);
if (ret)
goto err_config;
+ /*
+ * The RX DMA channel is used bidirectionally: It either reads the
+ * RX FIFO or, in case of a TX-only transfer, cyclically writes a
+ * precalculated value to the CS register to clear the RX FIFO.
+ */
slave_config.src_addr = (u32)(dma_reg_base + BCM2835_SPI_FIFO);
slave_config.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+ slave_config.dst_addr = (u32)(dma_reg_base + BCM2835_SPI_CS);
+ slave_config.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
ret = dmaengine_slave_config(ctlr->dma_rx, &slave_config);
if (ret)
goto err_config;
+ bs->clear_rx_addr = dma_map_single(ctlr->dma_rx->device->dev,
+ bs->clear_rx_cs,
+ sizeof(bs->clear_rx_cs),
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(ctlr->dma_rx->device->dev, bs->clear_rx_addr)) {
+ dev_err(dev, "cannot map clear_rx_cs - not using DMA mode\n");
+ bs->clear_rx_addr = 0;
+ goto err_release;
+ }
+
+ for (i = 0; i < BCM2835_SPI_NUM_CS; i++) {
+ bs->clear_rx_desc[i] = dmaengine_prep_dma_cyclic(ctlr->dma_rx,
+ bs->clear_rx_addr + i * sizeof(u32),
+ sizeof(u32), 0,
+ DMA_MEM_TO_DEV, 0);
+ if (!bs->clear_rx_desc[i]) {
+ dev_err(dev, "cannot prepare clear_rx_desc - not using DMA mode\n");
+ goto err_release;
+ }
+
+ ret = dmaengine_desc_set_reuse(bs->clear_rx_desc[i]);
+ if (ret) {
+ dev_err(dev, "cannot reuse clear_rx_desc - not using DMA mode\n");
+ goto err_release;
+ }
+ }
+
/* all went well, so set can_dma */
ctlr->can_dma = bcm2835_spi_can_dma;
- /* need to do TX AND RX DMA, so we need dummy buffers */
- ctlr->flags = SPI_CONTROLLER_MUST_RX | SPI_CONTROLLER_MUST_TX;
+ /* need to do TX DMA, so we need a dummy buffer */
+ ctlr->flags = SPI_CONTROLLER_MUST_TX;
return;
dev_err(dev, "issue configuring dma: %d - not using DMA mode\n",
ret);
err_release:
- bcm2835_dma_release(ctlr);
+ bcm2835_dma_release(ctlr, bs);
err:
return;
}
bcm2835_wr(bs, BCM2835_SPI_CLK, cdiv);
/* handle all the 3-wire mode */
- if (spi->mode & SPI_3WIRE && tfr->rx_buf &&
- tfr->rx_buf != ctlr->dummy_rx)
+ if (spi->mode & SPI_3WIRE && tfr->rx_buf)
cs |= BCM2835_SPI_CS_REN;
/* set transmit buffers and length */
/* if an error occurred and we have an active dma, then terminate */
dmaengine_terminate_sync(ctlr->dma_tx);
+ bs->tx_dma_active = false;
dmaengine_terminate_sync(ctlr->dma_rx);
+ bs->rx_dma_active = false;
bcm2835_spi_undo_prologue(bs);
/* and reset */
static int bcm2835_spi_setup(struct spi_device *spi)
{
- struct bcm2835_spi *bs = spi_controller_get_devdata(spi->controller);
+ struct spi_controller *ctlr = spi->controller;
+ struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
struct gpio_chip *chip;
enum gpio_lookup_flags lflags;
u32 cs;
cs |= BCM2835_SPI_CS_CPHA;
bs->prepare_cs[spi->chip_select] = cs;
+ /*
+ * Precalculate SPI slave's CS register value to clear RX FIFO
+ * in case of a TX-only DMA transfer.
+ */
+ if (ctlr->dma_rx) {
+ bs->clear_rx_cs[spi->chip_select] = cs |
+ BCM2835_SPI_CS_TA |
+ BCM2835_SPI_CS_DMAEN |
+ BCM2835_SPI_CS_CLEAR_RX;
+ dma_sync_single_for_device(ctlr->dma_rx->device->dev,
+ bs->clear_rx_addr,
+ sizeof(bs->clear_rx_cs),
+ DMA_TO_DEVICE);
+ }
+
/*
* sanity checking the native-chipselects
*/
struct bcm2835_spi *bs;
int err;
- ctlr = spi_alloc_master(&pdev->dev, sizeof(*bs));
+ ctlr = spi_alloc_master(&pdev->dev, ALIGN(sizeof(*bs),
+ dma_get_cache_alignment()));
if (!ctlr)
return -ENOMEM;
clk_prepare_enable(bs->clk);
- bcm2835_dma_init(ctlr, &pdev->dev);
+ bcm2835_dma_init(ctlr, &pdev->dev, bs);
/* initialise the hardware with the default polarities */
bcm2835_wr(bs, BCM2835_SPI_CS,
clk_disable_unprepare(bs->clk);
- bcm2835_dma_release(ctlr);
+ bcm2835_dma_release(ctlr, bs);
return 0;
}