Re: [PATCH RFC v4 09/15] spi: axi-spi-engine: implement offload support

[Nuno Sá <noname.nuno@xxxxxxxxx>]

On Wed, 2024-10-23 at 15:59 -0500, David Lechner wrote:
> Implement SPI offload support for the AXI SPI Engine. Currently, the
> hardware only supports triggering offload transfers with a hardware
> trigger so attempting to use an offload message in the regular SPI
> message queue will fail. Also, only allows streaming rx data to an
> external sink, so attempts to use a rx_buf in the offload message will
> fail.
> 
> Signed-off-by: David Lechner <dlechner@xxxxxxxxxxxx>
> ---
> 
> v4 changes:
> * Adapted to changes in other patches in the series.
> * Moved trigger enable/disable to same function as offload
>   enable/disable.
> 
> v3 changes:
> * Added clk and dma_chan getter callbacks.
> * Fixed some bugs.
> 
> v2 changes:
> 
> This patch has been reworked to accommodate the changes described in all
> of the other patches.
> ---
>  drivers/spi/Kconfig              |   1 +
>  drivers/spi/spi-axi-spi-engine.c | 273 ++++++++++++++++++++++++++++++++++++++-
>  2 files changed, 268 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
> index 50d04fa317b7..af3143ec5245 100644
> --- a/drivers/spi/Kconfig
> +++ b/drivers/spi/Kconfig
> @@ -168,6 +168,7 @@ config SPI_AU1550
>  config SPI_AXI_SPI_ENGINE
>  	tristate "Analog Devices AXI SPI Engine controller"
>  	depends on HAS_IOMEM
> +	select SPI_OFFLOAD
>  	help
>  	  This enables support for the Analog Devices AXI SPI Engine SPI
> controller.
>  	  It is part of the SPI Engine framework that is used in some Analog
> Devices
> diff --git a/drivers/spi/spi-axi-spi-engine.c b/drivers/spi/spi-axi-spi-engine.c
> index 2d24d762b5bd..1710847d81a1 100644
> --- a/drivers/spi/spi-axi-spi-engine.c
> +++ b/drivers/spi/spi-axi-spi-engine.c
> @@ -2,11 +2,14 @@
>  /*
>   * SPI-Engine SPI controller driver
>   * Copyright 2015 Analog Devices Inc.
> + * Copyright 2024 BayLibre, SAS
>   *  Author: Lars-Peter Clausen <lars@xxxxxxxxxx>
>   */
>  
> +#include <linux/bitops.h>
>  #include <linux/clk.h>
>  #include <linux/completion.h>
> +#include <linux/dmaengine.h>
>  #include <linux/fpga/adi-axi-common.h>
>  #include <linux/interrupt.h>
>  #include <linux/io.h>
> @@ -14,8 +17,10 @@
>  #include <linux/module.h>
>  #include <linux/overflow.h>
>  #include <linux/platform_device.h>
> +#include <linux/spi/spi-offload.h>
>  #include <linux/spi/spi.h>
>  

...

> +#define SPI_ENGINE_REG_OFFLOAD_MEM_ADDR_WIDTH	0x10
>  #define SPI_ENGINE_REG_RESET			0x40
>  
>  #define SPI_ENGINE_REG_INT_ENABLE		0x80
> @@ -23,6 +28,7 @@
>  #define SPI_ENGINE_REG_INT_SOURCE		0x88
>  
>  #define SPI_ENGINE_REG_SYNC_ID			0xc0
> +#define SPI_ENGINE_REG_OFFLOAD_SYNC_ID		0xc4
>  
>  #define SPI_ENGINE_REG_CMD_FIFO_ROOM		0xd0
>  #define SPI_ENGINE_REG_SDO_FIFO_ROOM		0xd4
> @@ -33,10 +39,24 @@
>  #define SPI_ENGINE_REG_SDI_DATA_FIFO		0xe8
>  #define SPI_ENGINE_REG_SDI_DATA_FIFO_PEEK	0xec
>  
> +#define SPI_ENGINE_MAX_NUM_OFFLOADS		32
> +
> +#define SPI_ENGINE_REG_OFFLOAD_CTRL(x)		(0x100 +
> SPI_ENGINE_MAX_NUM_OFFLOADS * (x))
> +#define SPI_ENGINE_REG_OFFLOAD_STATUS(x)	(0x104 +
> SPI_ENGINE_MAX_NUM_OFFLOADS * (x))
> +#define SPI_ENGINE_REG_OFFLOAD_RESET(x)		(0x108 +
> SPI_ENGINE_MAX_NUM_OFFLOADS * (x))
> +#define SPI_ENGINE_REG_OFFLOAD_CMD_FIFO(x)	(0x110 +
> SPI_ENGINE_MAX_NUM_OFFLOADS * (x))
> +#define SPI_ENGINE_REG_OFFLOAD_SDO_FIFO(x)	(0x114 +
> SPI_ENGINE_MAX_NUM_OFFLOADS * (x))
> +
> +#define SPI_ENGINE_SPI_OFFLOAD_MEM_WIDTH_SDO	GENMASK(15, 8)
> +#define SPI_ENGINE_SPI_OFFLOAD_MEM_WIDTH_CMD	GENMASK(7, 0)
> +
>  #define SPI_ENGINE_INT_CMD_ALMOST_EMPTY		BIT(0)
>  #define SPI_ENGINE_INT_SDO_ALMOST_EMPTY		BIT(1)
>  #define SPI_ENGINE_INT_SDI_ALMOST_FULL		BIT(2)
>  #define SPI_ENGINE_INT_SYNC			BIT(3)
> +#define SPI_ENGINE_INT_OFFLOAD_SYNC		BIT(4)
> +
> +#define SPI_ENGINE_OFFLOAD_CTRL_ENABLE		BIT(0)
>  
>  #define SPI_ENGINE_CONFIG_CPHA			BIT(0)
>  #define SPI_ENGINE_CONFIG_CPOL			BIT(1)
> @@ -78,6 +98,14 @@
>  #define SPI_ENGINE_CMD_CS_INV(flags) \
>  	SPI_ENGINE_CMD(SPI_ENGINE_INST_CS_INV, 0, (flags))
>  
> +/* default sizes - can be changed when SPI Engine firmware is compiled */
> +#define SPI_ENGINE_OFFLOAD_CMD_FIFO_SIZE	16
> +#define SPI_ENGINE_OFFLOAD_SDO_FIFO_SIZE	16
> +
> +#define SPI_ENGINE_OFFLOAD_CAPS (SPI_OFFLOAD_CAP_TRIGGER | \
> +				 SPI_OFFLOAD_CAP_TX_STATIC_DATA | \
> +				 SPI_OFFLOAD_CAP_RX_STREAM_DMA)
> +
>  struct spi_engine_program {
>  	unsigned int length;
>  	uint16_t instructions[] __counted_by(length);
> @@ -105,6 +133,16 @@ struct spi_engine_message_state {
>  	uint8_t *rx_buf;
>  };
>  
> +enum {
> +	SPI_ENGINE_OFFLOAD_FLAG_PREPARED,
> +};
> +
> +struct spi_engine_offload {
> +	struct spi_engine *spi_engine;
> +	unsigned long flags;
> +	unsigned int offload_num;
> +};
> +
>  struct spi_engine {
>  	struct clk *clk;
>  	struct clk *ref_clk;
> @@ -117,6 +155,11 @@ struct spi_engine {
>  	unsigned int int_enable;
>  	/* shadows hardware CS inversion flag state */
>  	u8 cs_inv;
> +
> +	unsigned int offload_ctrl_mem_size;
> +	unsigned int offload_sdo_mem_size;
> +	struct spi_offload *offloads;
> +	unsigned int num_offloads;
>  };
>  
>  static void spi_engine_program_add_cmd(struct spi_engine_program *p,
> @@ -164,7 +207,7 @@ static void spi_engine_gen_xfer(struct spi_engine_program *p,
> bool dry,
>  
>  		if (xfer->tx_buf)
>  			flags |= SPI_ENGINE_TRANSFER_WRITE;
> -		if (xfer->rx_buf)
> +		if (xfer->rx_buf || (xfer->offload_flags &
> SPI_OFFLOAD_XFER_RX_STREAM))
>  			flags |= SPI_ENGINE_TRANSFER_READ;
>  
>  		spi_engine_program_add_cmd(p, dry,
> @@ -220,16 +263,24 @@ static void spi_engine_gen_cs(struct spi_engine_program *p,
> bool dry,
>   *
>   * NB: This is separate from spi_engine_compile_message() because the latter
>   * is called twice and would otherwise result in double-evaluation.
> + *
> + * Returns 0 on success, -EINVAL on failure.
>   */
> -static void spi_engine_precompile_message(struct spi_message *msg)
> +static int spi_engine_precompile_message(struct spi_message *msg)
>  {
>  	unsigned int clk_div, max_hz = msg->spi->controller->max_speed_hz;
>  	struct spi_transfer *xfer;
>  
>  	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
> +		/* If we have an offload transfer, we can't rx to buffer */
> +		if (msg->offload && xfer->rx_buf)
> +			return -EINVAL;
> +
>  		clk_div = DIV_ROUND_UP(max_hz, xfer->speed_hz);
>  		xfer->effective_speed_hz = max_hz / min(clk_div, 256U);
>  	}
> +
> +	return 0;
>  }
>  
>  static void spi_engine_compile_message(struct spi_message *msg, bool dry,
> @@ -544,11 +595,94 @@ static irqreturn_t spi_engine_irq(int irq, void *devid)
>  	return IRQ_HANDLED;
>  }
>  
> +static int spi_engine_offload_prepare(struct spi_message *msg)
> +{
> +	struct spi_controller *host = msg->spi->controller;
> +	struct spi_engine *spi_engine = spi_controller_get_devdata(host);
> +	struct spi_engine_program *p = msg->opt_state;
> +	struct spi_engine_offload *priv = msg->offload->priv;
> +	struct spi_transfer *xfer;
> +	void __iomem *cmd_addr;
> +	void __iomem *sdo_addr;
> +	size_t tx_word_count = 0;
> +	unsigned int i;
> +
> +	if (p->length > spi_engine->offload_ctrl_mem_size)
> +		return -EINVAL;
> +
> +	/* count total number of tx words in message */
> +	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
> +		if (!xfer->tx_buf)
> +			continue;
> +
> +		if (xfer->bits_per_word <= 8)
> +			tx_word_count += xfer->len;
> +		else if (xfer->bits_per_word <= 16)
> +			tx_word_count += xfer->len / 2;
> +		else
> +			tx_word_count += xfer->len / 4;
> +	}
> +
> +	if (tx_word_count > spi_engine->offload_sdo_mem_size)
> +		return -EINVAL;
> +
> +	if (test_and_set_bit_lock(SPI_ENGINE_OFFLOAD_FLAG_PREPARED, &priv->flags))
> +		return -EBUSY;
> +

This is odd. Any special reason for using this with aquire - release semantics? Can
optimize() and unoptimize() run concurrently? Because if they can this does not give
us mutual exclusion and we really need to do what we're doing with kind of stuff :)

- Nuno Sá