diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-16 14:02:43 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-16 14:02:43 -0700 |
commit | aa62325dc38de2be8b1c27eb180ad3751b3f58ec (patch) | |
tree | a95691be94ab37128f6aaddcf526d5c9ad2336ff /drivers/spi/spi-bcm2835.c | |
parent | c4d11ccb2b5cec6cdef7aeeb0017473d23031d96 (diff) | |
parent | b769c5ba8aedc395ed04abe6db84a556d28beec1 (diff) |
Merge tag 'spi-v5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi
Pull spi updates from Mark Brown:
"The big theme for this release has been performance, we've had a
series of unrelated overhauls of a few drivers all with a big
peformance component.
Otherwise it's been relatively quiet, highlights include:
- A big overhaul of the spi-fsl-dspi driver improving the code
quality, performance and stability from Vladimir Oltean.
- A big performance enhancement for the bc2835 (Raspberry Pi) driver
for unidirectional transfers from Lukas Wunner.
- Improved performance on small transfers for the uniphier driver
from Keiji Hayashibara.
- Lots of coccinelle generated cleanups from Yue Haibing.
- New device support for Freescale ls2080a and Nuvoton NPCM FIU"
* tag 'spi-v5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi: (102 commits)
spi: mediatek: support large PA
spi: mediatek: add spi support for mt6765 IC
dt-bindings: spi: update bindings for MT6765 SoC
spi: bcm2835: Speed up RX-only DMA transfers by zero-filling TX FIFO
spi: bcm2835: Speed up TX-only DMA transfers by clearing RX FIFO
dmaengine: bcm2835: Avoid accessing memory when copying zeroes
spi: bcm2835: Cache CS register value for ->prepare_message()
dmaengine: bcm2835: Document struct bcm2835_dmadev
spi: Guarantee cacheline alignment of driver-private data
dmaengine: bcm2835: Allow reusable descriptors
dmaengine: bcm2835: Allow cyclic transactions without interrupt
spi: bcm2835: Drop dma_pending flag
spi: bcm2835: Work around DONE bit erratum
spi-gpio: Use PTR_ERR_OR_ZERO() in spi_gpio_request()
spi: Use an abbreviated pointer to ctlr->cur_msg in __spi_pump_messages
spi: npcm-fiu: remove set but not used variable 'retlen'
spi: fsl-spi: use devm_platform_ioremap_resource() to simplify code
spi: zynq-qspi: use devm_platform_ioremap_resource() to simplify code
spi: zynqmp: use devm_platform_ioremap_resource() to simplify code
spi: xlp: use devm_platform_ioremap_resource() to simplify code
...
Diffstat (limited to 'drivers/spi/spi-bcm2835.c')
-rw-r--r-- | drivers/spi/spi-bcm2835.c | 470 |
1 files changed, 382 insertions, 88 deletions
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c index 840b1b8ff3dc..b4070c0de3df 100644 --- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -25,7 +25,9 @@ #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_device.h> -#include <linux/of_gpio.h> +#include <linux/gpio/consumer.h> +#include <linux/gpio/machine.h> /* FIXME: using chip internals */ +#include <linux/gpio/driver.h> /* FIXME: using chip internals */ #include <linux/of_irq.h> #include <linux/spi/spi.h> @@ -66,6 +68,7 @@ #define BCM2835_SPI_FIFO_SIZE 64 #define BCM2835_SPI_FIFO_SIZE_3_4 48 #define BCM2835_SPI_DMA_MIN_LENGTH 96 +#define BCM2835_SPI_NUM_CS 3 /* raise as necessary */ #define BCM2835_SPI_MODE_BITS (SPI_CPOL | SPI_CPHA | SPI_CS_HIGH \ | SPI_NO_CS | SPI_3WIRE) @@ -92,7 +95,8 @@ MODULE_PARM_DESC(polling_limit_us, * @rx_prologue: bytes received without DMA if first RX sglist entry's * length is not a multiple of 4 (to overcome hardware limitation) * @tx_spillover: whether @tx_prologue spills over to second TX sglist entry - * @dma_pending: whether a DMA transfer is in progress + * @prepare_cs: precalculated CS register value for ->prepare_message() + * (uses slave-specific clock polarity and phase settings) * @debugfs_dir: the debugfs directory - neede to remove debugfs when * unloading the module * @count_transfer_polling: count of how often polling mode is used @@ -102,6 +106,19 @@ MODULE_PARM_DESC(polling_limit_us, * 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) + * @fill_tx_desc: preallocated TX DMA descriptor used for RX-only transfers + * (cyclically copies from zero page to TX FIFO) + * @fill_tx_addr: bus address of zero page + * @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; @@ -115,13 +132,22 @@ struct bcm2835_spi { int tx_prologue; int rx_prologue; unsigned int tx_spillover; - unsigned int dma_pending; + u32 prepare_cs[BCM2835_SPI_NUM_CS]; struct dentry *debugfs_dir; u64 count_transfer_polling; 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 *fill_tx_desc; + dma_addr_t fill_tx_addr; + 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) @@ -319,6 +345,13 @@ static void bcm2835_spi_reset_hw(struct spi_controller *ctlr) BCM2835_SPI_CS_INTD | BCM2835_SPI_CS_DMAEN | BCM2835_SPI_CS_TA); + /* + * Transmission sometimes breaks unless the DONE bit is written at the + * end of every transfer. The spec says it's a RO bit. Either the + * spec is wrong and the bit is actually of type RW1C, or it's a + * hardware erratum. + */ + cs |= BCM2835_SPI_CS_DONE; /* and reset RX/TX FIFOS */ cs |= BCM2835_SPI_CS_CLEAR_RX | BCM2835_SPI_CS_CLEAR_TX; @@ -448,14 +481,14 @@ static void bcm2835_spi_transfer_prologue(struct spi_controller *ctlr, bs->rx_prologue = 0; bs->tx_spillover = false; - if (!sg_is_last(&tfr->tx_sg.sgl[0])) + if (bs->tx_buf && !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) { - if (sg_is_last(&tfr->tx_sg.sgl[0])) { + if (!bs->tx_buf || sg_is_last(&tfr->tx_sg.sgl[0])) { bs->tx_prologue = bs->rx_prologue; } else { bs->tx_prologue += 4; @@ -477,7 +510,9 @@ static void bcm2835_spi_transfer_prologue(struct spi_controller *ctlr, bcm2835_wr_fifo_count(bs, bs->rx_prologue); bcm2835_wait_tx_fifo_empty(bs); bcm2835_rd_fifo_count(bs, bs->rx_prologue); - bcm2835_spi_reset_hw(ctlr); + bcm2835_wr(bs, BCM2835_SPI_CS, cs | BCM2835_SPI_CS_CLEAR_RX + | BCM2835_SPI_CS_CLEAR_TX + | BCM2835_SPI_CS_DONE); dma_sync_single_for_device(ctlr->dma_rx->device->dev, sg_dma_address(&tfr->rx_sg.sgl[0]), @@ -487,6 +522,9 @@ static void bcm2835_spi_transfer_prologue(struct spi_controller *ctlr, sg_dma_len(&tfr->rx_sg.sgl[0]) -= bs->rx_prologue; } + if (!bs->tx_buf) + return; + /* * Write remaining TX prologue. Adjust first entry in TX sglist. * Also adjust second entry if prologue spills over to it. @@ -498,7 +536,8 @@ static void bcm2835_spi_transfer_prologue(struct spi_controller *ctlr, | BCM2835_SPI_CS_DMAEN); bcm2835_wr_fifo_count(bs, tx_remaining); bcm2835_wait_tx_fifo_empty(bs); - bcm2835_wr(bs, BCM2835_SPI_CS, cs | BCM2835_SPI_CS_CLEAR_TX); + bcm2835_wr(bs, BCM2835_SPI_CS, cs | BCM2835_SPI_CS_CLEAR_TX + | BCM2835_SPI_CS_DONE); } if (likely(!bs->tx_spillover)) { @@ -531,6 +570,9 @@ static void bcm2835_spi_undo_prologue(struct bcm2835_spi *bs) sg_dma_len(&tfr->rx_sg.sgl[0]) += bs->rx_prologue; } + if (!bs->tx_buf) + goto out; + if (likely(!bs->tx_spillover)) { sg_dma_address(&tfr->tx_sg.sgl[0]) -= bs->tx_prologue; sg_dma_len(&tfr->tx_sg.sgl[0]) += bs->tx_prologue; @@ -539,32 +581,85 @@ static void bcm2835_spi_undo_prologue(struct bcm2835_spi *bs) sg_dma_address(&tfr->tx_sg.sgl[1]) -= 4; sg_dma_len(&tfr->tx_sg.sgl[1]) += 4; } +out: + 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); - /* reset fifo and HW */ - bcm2835_spi_reset_hw(ctlr); - - /* and terminate tx-dma as we do not have an irq for it + /* terminate tx-dma as we do not have an irq for it * because when the rx dma will terminate and this callback * is called the tx-dma must have finished - can't get to this * situation otherwise... */ - if (cmpxchg(&bs->dma_pending, true, false)) { - dmaengine_terminate_async(ctlr->dma_tx); - bcm2835_spi_undo_prologue(bs); - } + dmaengine_terminate_async(ctlr->dma_tx); + bs->tx_dma_active = false; + bs->rx_dma_active = false; + bcm2835_spi_undo_prologue(bs); + + /* reset fifo and HW */ + bcm2835_spi_reset_hw(ctlr); /* 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; @@ -581,8 +676,7 @@ static int bcm2835_spi_prepare_sg(struct spi_controller *ctlr, 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; @@ -595,10 +689,17 @@ static int bcm2835_spi_prepare_sg(struct spi_controller *ctlr, 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 */ @@ -607,12 +708,60 @@ static int bcm2835_spi_prepare_sg(struct spi_controller *ctlr, 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. + * + * For *RX-only* transfers (tx_buf is %NULL), fill the TX FIFO by cyclically + * copying from the zero page. The DMA descriptor to do this is preallocated + * in bcm2835_dma_init(). It must be terminated once the RX DMA channel is + * done and can then be reused. + * + * The BCM2835 DMA driver autodetects when a transaction copies from the zero + * page and utilizes the DMA controller's ability to synthesize zeroes instead + * of copying them from memory. This reduces traffic on the memory bus. The + * feature is not available on so-called "lite" channels, but normally TX DMA + * is backed by a full-featured channel. + * + * Zero-filling the TX FIFO is paced by the DREQ signal. Unfortunately the + * BCM2835 SPI controller continues to assert DREQ even after the DLEN register + * has been counted down to zero (hardware erratum). Thus, when the transfer + * has finished, the DMA engine zero-fills the TX FIFO until it is half full. + * (Tuneable with the DC register.) So up to 9 gratuitous bus accesses are + * performed at the end of an RX-only transfer. + */ 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 */ @@ -625,16 +774,15 @@ static int bcm2835_spi_transfer_one_dma(struct spi_controller *ctlr, bcm2835_spi_transfer_prologue(ctlr, tfr, bs, cs); /* setup tx-DMA */ - ret = bcm2835_spi_prepare_sg(ctlr, tfr, true); + if (bs->tx_buf) { + ret = bcm2835_spi_prepare_sg(ctlr, spi, tfr, bs, true); + } else { + cookie = dmaengine_submit(bs->fill_tx_desc); + ret = dma_submit_error(cookie); + } if (ret) goto err_reset_hw; - /* start TX early */ - dma_async_issue_pending(ctlr->dma_tx); - - /* mark as dma pending */ - bs->dma_pending = 1; - /* set the DMA length */ bcm2835_wr(bs, BCM2835_SPI_DLEN, bs->tx_len); @@ -642,20 +790,43 @@ static int bcm2835_spi_transfer_one_dma(struct spi_controller *ctlr, 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->dma_pending = false; + 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; @@ -678,26 +849,52 @@ static bool bcm2835_spi_can_dma(struct spi_controller *ctlr, 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); + + if (bs->fill_tx_desc) + dmaengine_desc_free(bs->fill_tx_desc); + + if (bs->fill_tx_addr) + dma_unmap_page_attrs(ctlr->dma_tx->device->dev, + bs->fill_tx_addr, sizeof(u32), + DMA_TO_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + 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); @@ -719,7 +916,11 @@ static void bcm2835_dma_init(struct spi_controller *ctlr, struct device *dev) goto err_release; } - /* configure DMAs */ + /* + * The TX DMA channel either copies a transfer's TX buffer to the FIFO + * or, in case of an RX-only transfer, cyclically copies from the zero + * page to the FIFO using a preallocated, reusable descriptor. + */ slave_config.dst_addr = (u32)(dma_reg_base + BCM2835_SPI_FIFO); slave_config.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; @@ -727,17 +928,74 @@ static void bcm2835_dma_init(struct spi_controller *ctlr, struct device *dev) if (ret) goto err_config; + bs->fill_tx_addr = dma_map_page_attrs(ctlr->dma_tx->device->dev, + ZERO_PAGE(0), 0, sizeof(u32), + DMA_TO_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + if (dma_mapping_error(ctlr->dma_tx->device->dev, bs->fill_tx_addr)) { + dev_err(dev, "cannot map zero page - not using DMA mode\n"); + bs->fill_tx_addr = 0; + goto err_release; + } + + bs->fill_tx_desc = dmaengine_prep_dma_cyclic(ctlr->dma_tx, + bs->fill_tx_addr, + sizeof(u32), 0, + DMA_MEM_TO_DEV, 0); + if (!bs->fill_tx_desc) { + dev_err(dev, "cannot prepare fill_tx_desc - not using DMA mode\n"); + goto err_release; + } + + ret = dmaengine_desc_set_reuse(bs->fill_tx_desc); + if (ret) { + dev_err(dev, "cannot reuse fill_tx_desc - not using DMA mode\n"); + goto err_release; + } + + /* + * 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; return; @@ -745,7 +1003,7 @@ err_config: 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; } @@ -812,7 +1070,7 @@ static int bcm2835_spi_transfer_one(struct spi_controller *ctlr, struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr); unsigned long spi_hz, clk_hz, cdiv, spi_used_hz; unsigned long hz_per_byte, byte_limit; - u32 cs = bcm2835_rd(bs, BCM2835_SPI_CS); + u32 cs = bs->prepare_cs[spi->chip_select]; /* set clock */ spi_hz = tfr->speed_hz; @@ -834,18 +1092,8 @@ static int bcm2835_spi_transfer_one(struct spi_controller *ctlr, 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; - else - cs &= ~BCM2835_SPI_CS_REN; - - /* - * The driver always uses software-controlled GPIO Chip Select. - * Set the hardware-controlled native Chip Select to an invalid - * value to prevent it from interfering. - */ - cs |= BCM2835_SPI_CS_CS_10 | BCM2835_SPI_CS_CS_01; /* set transmit buffers and length */ bs->tx_buf = tfr->tx_buf; @@ -882,7 +1130,6 @@ static int bcm2835_spi_prepare_message(struct spi_controller *ctlr, { struct spi_device *spi = msg->spi; struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr); - u32 cs = bcm2835_rd(bs, BCM2835_SPI_CS); int ret; if (ctlr->can_dma) { @@ -897,14 +1144,11 @@ static int bcm2835_spi_prepare_message(struct spi_controller *ctlr, return ret; } - cs &= ~(BCM2835_SPI_CS_CPOL | BCM2835_SPI_CS_CPHA); - - if (spi->mode & SPI_CPOL) - cs |= BCM2835_SPI_CS_CPOL; - if (spi->mode & SPI_CPHA) - cs |= BCM2835_SPI_CS_CPHA; - - bcm2835_wr(bs, BCM2835_SPI_CS, cs); + /* + * Set up clock polarity before spi_transfer_one_message() asserts + * chip select to avoid a gratuitous clock signal edge. + */ + bcm2835_wr(bs, BCM2835_SPI_CS, bs->prepare_cs[spi->chip_select]); return 0; } @@ -915,11 +1159,12 @@ static void bcm2835_spi_handle_err(struct spi_controller *ctlr, struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr); /* if an error occurred and we have an active dma, then terminate */ - if (cmpxchg(&bs->dma_pending, true, false)) { - dmaengine_terminate_sync(ctlr->dma_tx); - dmaengine_terminate_sync(ctlr->dma_rx); - bcm2835_spi_undo_prologue(bs); - } + 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 */ bcm2835_spi_reset_hw(ctlr); } @@ -931,14 +1176,50 @@ static int chip_match_name(struct gpio_chip *chip, void *data) static int bcm2835_spi_setup(struct spi_device *spi) { - int err; + 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; + + /* + * Precalculate SPI slave's CS register value for ->prepare_message(): + * The driver always uses software-controlled GPIO chip select, hence + * set the hardware-controlled native chip select to an invalid value + * to prevent it from interfering. + */ + cs = BCM2835_SPI_CS_CS_10 | BCM2835_SPI_CS_CS_01; + if (spi->mode & SPI_CPOL) + cs |= BCM2835_SPI_CS_CPOL; + if (spi->mode & SPI_CPHA) + 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 */ if (spi->mode & SPI_NO_CS) return 0; - if (gpio_is_valid(spi->cs_gpio)) + /* + * The SPI core has successfully requested the CS GPIO line from the + * device tree, so we are done. + */ + if (spi->cs_gpiod) return 0; if (spi->chip_select > 1) { /* error in the case of native CS requested with CS > 1 @@ -949,29 +1230,43 @@ static int bcm2835_spi_setup(struct spi_device *spi) "setup: only two native chip-selects are supported\n"); return -EINVAL; } - /* now translate native cs to GPIO */ + + /* + * Translate native CS to GPIO + * + * FIXME: poking around in the gpiolib internals like this is + * not very good practice. Find a way to locate the real problem + * and fix it. Why is the GPIO descriptor in spi->cs_gpiod + * sometimes not assigned correctly? Erroneous device trees? + */ /* get the gpio chip for the base */ chip = gpiochip_find("pinctrl-bcm2835", chip_match_name); if (!chip) return 0; - /* and calculate the real CS */ - spi->cs_gpio = chip->base + 8 - spi->chip_select; + /* + * Retrieve the corresponding GPIO line used for CS. + * The inversion semantics will be handled by the GPIO core + * code, so we pass GPIOS_OUT_LOW for "unasserted" and + * the correct flag for inversion semantics. The SPI_CS_HIGH + * on spi->mode cannot be checked for polarity in this case + * as the flag use_gpio_descriptors enforces SPI_CS_HIGH. + */ + if (of_property_read_bool(spi->dev.of_node, "spi-cs-high")) + lflags = GPIO_ACTIVE_HIGH; + else + lflags = GPIO_ACTIVE_LOW; + spi->cs_gpiod = gpiochip_request_own_desc(chip, 8 - spi->chip_select, + DRV_NAME, + lflags, + GPIOD_OUT_LOW); + if (IS_ERR(spi->cs_gpiod)) + return PTR_ERR(spi->cs_gpiod); /* and set up the "mode" and level */ - dev_info(&spi->dev, "setting up native-CS%i as GPIO %i\n", - spi->chip_select, spi->cs_gpio); - - /* set up GPIO as output and pull to the correct level */ - err = gpio_direction_output(spi->cs_gpio, - (spi->mode & SPI_CS_HIGH) ? 0 : 1); - if (err) { - dev_err(&spi->dev, - "could not set CS%i gpio %i as output: %i", - spi->chip_select, spi->cs_gpio, err); - return err; - } + dev_info(&spi->dev, "setting up native-CS%i to use GPIO\n", + spi->chip_select); return 0; } @@ -980,18 +1275,19 @@ static int bcm2835_spi_probe(struct platform_device *pdev) { struct spi_controller *ctlr; struct bcm2835_spi *bs; - struct resource *res; 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; platform_set_drvdata(pdev, ctlr); + ctlr->use_gpio_descriptors = true; ctlr->mode_bits = BCM2835_SPI_MODE_BITS; ctlr->bits_per_word_mask = SPI_BPW_MASK(8); - ctlr->num_chipselect = 3; + ctlr->num_chipselect = BCM2835_SPI_NUM_CS; ctlr->setup = bcm2835_spi_setup; ctlr->transfer_one = bcm2835_spi_transfer_one; ctlr->handle_err = bcm2835_spi_handle_err; @@ -1000,8 +1296,7 @@ static int bcm2835_spi_probe(struct platform_device *pdev) bs = spi_controller_get_devdata(ctlr); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - bs->regs = devm_ioremap_resource(&pdev->dev, res); + bs->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(bs->regs)) { err = PTR_ERR(bs->regs); goto out_controller_put; @@ -1016,14 +1311,13 @@ static int bcm2835_spi_probe(struct platform_device *pdev) bs->irq = platform_get_irq(pdev, 0); if (bs->irq <= 0) { - dev_err(&pdev->dev, "could not get IRQ: %d\n", bs->irq); err = bs->irq ? bs->irq : -ENODEV; goto out_controller_put; } 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, @@ -1067,7 +1361,7 @@ static int bcm2835_spi_remove(struct platform_device *pdev) clk_disable_unprepare(bs->clk); - bcm2835_dma_release(ctlr); + bcm2835_dma_release(ctlr, bs); return 0; } |