[dpdk-dev] [PATCH v4 06/11] dma/ioat: add data path job submission functions

[fengchengwen]

Reviewed-by: Chengwen Feng <fengchengwen at huawei.com>

On 2021/9/17 23:42, Conor Walsh wrote:
> Add data path functions for enqueuing and submitting operations to
> IOAT devices.
> 
> Signed-off-by: Conor Walsh <conor.walsh at intel.com>
> Reviewed-by: Kevin Laatz <kevin.laatz at intel.com>
> ---
>  doc/guides/dmadevs/ioat.rst    | 54 ++++++++++++++++++++
>  drivers/dma/ioat/ioat_dmadev.c | 92 ++++++++++++++++++++++++++++++++++
>  2 files changed, 146 insertions(+)
> 
> diff --git a/doc/guides/dmadevs/ioat.rst b/doc/guides/dmadevs/ioat.rst
> index a64d67bf89..2464207e20 100644
> --- a/doc/guides/dmadevs/ioat.rst
> +++ b/doc/guides/dmadevs/ioat.rst
> @@ -89,3 +89,57 @@ The following code shows how the device is configured in ``test_dmadev.c``:
>  
>  Once configured, the device can then be made ready for use by calling the
>  ``rte_dma_start()`` API.
> +
> +Performing Data Copies
> +~~~~~~~~~~~~~~~~~~~~~~~
> +
> +To perform data copies using IOAT dmadev devices, the functions
> +``rte_dma_copy()`` and ``rte_dma_submit()`` should be used. Alternatively
> +``rte_dma_copy()`` can be called with the ``RTE_DMA_OP_FLAG_SUBMIT`` flag
> +set.
> +
> +The ``rte_dma_copy()`` function enqueues a single copy to the
> +device ring for copying at a later point. The parameters to the function
> +include the device ID of the desired device, the virtual DMA channel required
> +(always 0 for IOAT), the IOVA addresses of both the source and destination
> +buffers, the length of the data to be copied and any operation flags. The
> +function will return the index of the enqueued job which can be use to
> +track that operation.
> +
> +While the ``rte_dma_copy()`` function enqueues a copy operation on the device
> +ring, the copy will not actually be performed until after the application calls
> +the ``rte_dma_submit()`` function. This function informs the device hardware
> +of the elements enqueued on the ring, and the device will begin to process them.
> +It is expected that, for efficiency reasons, a burst of operations will be
> +enqueued to the device via multiple enqueue calls between calls to the
> +``rte_dma_submit()`` function. If desired you can pass the
> +``RTE_DMA_OP_FLAG_SUBMIT`` flag when calling ``rte_dma_copy()`` and this will
> +tell the device to perform the enqueued operation and any unperformed operations
> +before it. The ``RTE_DMA_OP_FLAG_SUBMIT`` flag can be passed instead of calling
> +the ``rte_dma_submit()`` function for example on the last enqueue of the burst.
> +
> +The following code from demonstrates how to enqueue a burst of copies to the
> +device and start the hardware processing of them:
> +
> +.. code-block:: C
> +
> +   for (i = 0; i < BURST_SIZE; i++) {
> +      if (rte_dma_copy(dev_id, vchan, rte_mbuf_data_iova(srcs[i]),
> +            rte_mbuf_data_iova(dsts[i]), COPY_LEN, 0) < 0) {
> +         PRINT_ERR("Error with rte_dma_copy for buffer %u\n", i);
> +         return -1;
> +      }
> +   }
> +   if (rte_dma_submit(dev_id, vchan) < 0) {
> +      PRINT_ERR("Error with performing operations\n", i);
> +      return -1;
> +   }
> +
> +Filling an Area of Memory
> +~~~~~~~~~~~~~~~~~~~~~~~~~~
> +
> +The driver also has support for the ``fill`` operation, where an area
> +of memory is overwritten, or filled, with a short pattern of data.
> +Fill operations can be performed in much the same was as copy operations
> +described above, just using the ``rte_dma_fill()`` function rather
> +than the ``rte_dma_copy()`` function.
> diff --git a/drivers/dma/ioat/ioat_dmadev.c b/drivers/dma/ioat/ioat_dmadev.c
> index a47567ca66..edcc882d63 100644
> --- a/drivers/dma/ioat/ioat_dmadev.c
> +++ b/drivers/dma/ioat/ioat_dmadev.c
> @@ -5,6 +5,7 @@
>  #include <rte_bus_pci.h>
>  #include <rte_dmadev_pmd.h>
>  #include <rte_malloc.h>
> +#include <rte_prefetch.h>
>  
>  #include "ioat_internal.h"
>  
> @@ -17,6 +18,12 @@ RTE_LOG_REGISTER_DEFAULT(ioat_pmd_logtype, INFO);
>  #define IOAT_PMD_NAME dmadev_ioat
>  #define IOAT_PMD_NAME_STR RTE_STR(IOAT_PMD_NAME)
>  
> +/* IOAT operations. */
> +enum rte_ioat_ops {
> +	ioat_op_copy = 0,	/* Standard DMA Operation */
> +	ioat_op_fill		/* Block Fill */
> +};
> +
>  /* Configure a device. */
>  static int
>  ioat_dev_configure(struct rte_dma_dev *dev __rte_unused, const struct rte_dma_conf *dev_conf,
> @@ -194,6 +201,87 @@ ioat_dev_close(struct rte_dma_dev *dev)
>  	return 0;
>  }
>  
> +/* Trigger hardware to begin performing enqueued operations. */
> +static inline void
> +__submit(struct ioat_dmadev *ioat)
> +{
> +	*ioat->doorbell = ioat->next_write - ioat->offset;
> +
> +	ioat->last_write = ioat->next_write;
> +}
> +
> +/* External submit function wrapper. */
> +static int
> +ioat_submit(struct rte_dma_dev *dev, uint16_t qid __rte_unused)
> +{
> +	struct ioat_dmadev *ioat = (struct ioat_dmadev *)dev->dev_private;
> +
> +	__submit(ioat);
> +
> +	return 0;
> +}
> +
> +/* Write descriptor for enqueue. */
> +static inline int
> +__write_desc(struct rte_dma_dev *dev, uint32_t op, uint64_t src, phys_addr_t dst,
> +		unsigned int length, uint64_t flags)
> +{
> +	struct ioat_dmadev *ioat = dev->dev_private;
> +	uint16_t ret;
> +	const unsigned short mask = ioat->qcfg.nb_desc - 1;
> +	const unsigned short read = ioat->next_read;
> +	unsigned short write = ioat->next_write;
> +	const unsigned short space = mask + read - write;
> +	struct ioat_dma_hw_desc *desc;
> +
> +	if (space == 0)
> +		return -ENOSPC;
> +
> +	ioat->next_write = write + 1;
> +	write &= mask;
> +
> +	desc = &ioat->desc_ring[write];
> +	desc->size = length;
> +	desc->u.control_raw = (uint32_t)((op << IOAT_CMD_OP_SHIFT) |
> +			(1 << IOAT_COMP_UPDATE_SHIFT));
> +
> +	/* In IOAT the fence ensures that all operations including the current one
> +	 * are completed before moving on, DMAdev assumes that the fence ensures
> +	 * all operations before the current one are completed before starting
> +	 * the current one, so in IOAT we set the fence for the previous descriptor.
> +	 */
> +	if (flags & RTE_DMA_OP_FLAG_FENCE)
> +		ioat->desc_ring[(write - 1) & mask].u.control.fence = 1;
> +
> +	desc->src_addr = src;
> +	desc->dest_addr = dst;
> +
> +	rte_prefetch0(&ioat->desc_ring[ioat->next_write & mask]);
> +
> +	ret = (uint16_t)(ioat->next_write - 1);
> +
> +	if (flags & RTE_DMA_OP_FLAG_SUBMIT)
> +		__submit(ioat);
> +
> +	return ret;
> +}
> +
> +/* Enqueue a fill operation onto the ioat device. */
> +static int
> +ioat_enqueue_fill(struct rte_dma_dev *dev, uint16_t qid __rte_unused, uint64_t pattern,
> +		rte_iova_t dst, unsigned int length, uint64_t flags)
> +{
> +	return __write_desc(dev, ioat_op_fill, pattern, dst, length, flags);
> +}
> +
> +/* Enqueue a copy operation onto the ioat device. */
> +static int
> +ioat_enqueue_copy(struct rte_dma_dev *dev, uint16_t qid __rte_unused, rte_iova_t src,
> +		rte_iova_t dst, unsigned int length, uint64_t flags)
> +{
> +	return __write_desc(dev, ioat_op_copy, src, dst, length, flags);
> +}
> +
>  /* Dump DMA device info. */
>  static int
>  ioat_dev_dump(const struct rte_dma_dev *dev, FILE *f)
> @@ -290,6 +378,10 @@ ioat_dmadev_create(const char *name, struct rte_pci_device *dev)
>  
>  	dmadev->dev_ops = &ioat_dmadev_ops;
>  
> +	dmadev->copy = ioat_enqueue_copy;
> +	dmadev->fill = ioat_enqueue_fill;
> +	dmadev->submit = ioat_submit;
> +
>  	ioat = dmadev->data->dev_private;
>  	ioat->dmadev = dmadev;
>  	ioat->regs = dev->mem_resource[0].addr;
>