On Fri, Jul 16, 2021 at 8:19 AM Chengwen Feng <fengchengwen@huawei.com> wrote:
>
> This patch introduce 'dmadevice' which is a generic type of DMA
> device.
>
> The APIs of dmadev library exposes some generic operations which can
> enable configuration and I/O with the DMA devices.
>
> Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
> ---
> v5:
> * add doxy-api-* file modify.
> * use RTE_LOG_REGISTER_DEFAULT.
> * fix typo.
> * resolve some incorrect comments.
> * fix some doxgen problem.
> * fix version.map still hold rte_dmadev_completed_fails.
> v4:
> * replace xxx_complete_fails with xxx_completed_status.
> * add SILENT capability, also a silent_mode in rte_dmadev_conf.
> * add op_flag_llc for performance.
> * rename dmadev_xxx_t to rte_dmadev_xxx_t to avoid namespace conflict.
> * delete filed 'enqueued_count' from rte_dmadev_stats.
> * make rte_dmadev hold 'dev_private' filed.
> * add RTE_DMA_STATUS_NOT_ATTEMPED status code.
> * rename RTE_DMA_STATUS_ACTIVE_DROP to RTE_DMA_STATUS_USER_ABORT.
> * rename rte_dma_sg(e) to rte_dmadev_sg(e) to make sure all struct
> prefix with rte_dmadev.
> * put the comment afterwards.
> * fix some doxgen problem.
> * delete macro RTE_DMADEV_VALID_DEV_ID_OR_RET and
> RTE_DMADEV_PTR_OR_ERR_RET.
> * replace strlcpy with rte_strscpy.
> * other minor modifications from review comment.
> v3:
> * rm reset and fill_sg ops.
> * rm MT-safe capabilities.
> * add submit flag.
> * redefine rte_dma_sg to implement asymmetric copy.
> * delete some reserved field for future use.
> * rearrangement rte_dmadev/rte_dmadev_data struct.
> * refresh rte_dmadev.h copyright.
> * update vchan setup parameter.
> * modified some inappropriate descriptions.
> * arrange version.map alphabetically.
> * other minor modifications from review comment.
> ---
> MAINTAINERS | 4 +
> config/rte_config.h | 3 +
> doc/api/doxy-api-index.md | 1 +
> doc/api/doxy-api.conf.in | 1 +
> lib/dmadev/meson.build | 7 +
> lib/dmadev/rte_dmadev.c | 539 ++++++++++++++++++++++
> lib/dmadev/rte_dmadev.h | 1028 ++++++++++++++++++++++++++++++++++++++++++
> lib/dmadev/rte_dmadev_core.h | 182 ++++++++
> lib/dmadev/rte_dmadev_pmd.h | 72 +++
> lib/dmadev/version.map | 37 ++
> lib/meson.build | 1 +
> 11 files changed, 1875 insertions(+)
> create mode 100644 lib/dmadev/meson.build
> create mode 100644 lib/dmadev/rte_dmadev.c
> create mode 100644 lib/dmadev/rte_dmadev.h
> create mode 100644 lib/dmadev/rte_dmadev_core.h
> create mode 100644 lib/dmadev/rte_dmadev_pmd.h
> create mode 100644 lib/dmadev/version.map
>
> diff --git a/MAINTAINERS b/MAINTAINERS
> index af2a91d..e01a07f 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -495,6 +495,10 @@ F: drivers/raw/skeleton/
> F: app/test/test_rawdev.c
> F: doc/guides/prog_guide/rawdev.rst
>
> +DMA device API - EXPERIMENTAL
> +M: Chengwen Feng <fengchengwen@huawei.com>
> +F: lib/dmadev/
> +
> @@ -0,0 +1,1028 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2021 HiSilicon Limited.
> + * Copyright(c) 2021 Intel Corporation.
> + * Copyright(c) 2021 Marvell International Ltd.
> + * Copyright(c) 2021 SmartShare Systems.
> + */
> +
> +#ifndef _RTE_DMADEV_H_
> +#define _RTE_DMADEV_H_
> +
> +/**
> + * @file rte_dmadev.h
> + *
> + * RTE DMA (Direct Memory Access) device APIs.
> + *
> + * The DMA framework is built on the following model:
> + *
> + * --------------- --------------- ---------------
> + * | virtual DMA | | virtual DMA | | virtual DMA |
> + * | channel | | channel | | channel |
> + * --------------- --------------- ---------------
> + * | | |
> + * ------------------ |
> + * | |
> + * ------------ ------------
> + * | dmadev | | dmadev |
> + * ------------ ------------
> + * | |
> + * ------------------ ------------------
> + * | HW-DMA-channel | | HW-DMA-channel |
> + * ------------------ ------------------
> + * | |
> + * --------------------------------
> + * |
> + * ---------------------
> + * | HW-DMA-Controller |
> + * ---------------------
> + *
> + * The DMA controller could have multiple HW-DMA-channels (aka. HW-DMA-queues),
> + * each HW-DMA-channel should be represented by a dmadev.
> + *
> + * The dmadev could create multiple virtual DMA channel, each virtual DMA
channels?
> + * channel represents a different transfer context. The DMA operation request
> + * must be submitted to the virtual DMA channel. e.g. Application could create
> + * virtual DMA channel 0 for memory-to-memory transfer scenario, and create
> + * virtual DMA channel 1 for memory-to-device transfer scenario.
> + *
> + * The dmadev are dynamically allocated by rte_dmadev_pmd_allocate() during the
> + * PCI/SoC device probing phase performed at EAL initialization time. And could
> + * be released by rte_dmadev_pmd_release() during the PCI/SoC device removing
> + * phase.
> + *
> + * This framework uses 'uint16_t dev_id' as the device identifier of a dmadev,
> + * and 'uint16_t vchan' as the virtual DMA channel identifier in one dmadev.
> + *
> + * The functions exported by the dmadev API to setup a device designated by its
> + * device identifier must be invoked in the following order:
> + * - rte_dmadev_configure()
> + * - rte_dmadev_vchan_setup()
> + * - rte_dmadev_start()
> + *
> + * Then, the application can invoke dataplane APIs to process jobs.
> + *
> + * If the application wants to change the configuration (i.e. invoke
> + * rte_dmadev_configure()), it must invoke rte_dmadev_stop() first to stop the
> + * device and then do the reconfiguration before invoking rte_dmadev_start()
> + * again. The dataplane APIs should not be invoked when the device is stopped.
> + *
> + * Finally, an application can close a dmadev by invoking the
> + * rte_dmadev_close() function.
> + *
> + * The dataplane APIs include two parts:
> + * The first part is the submission of operation requests:
> + * - rte_dmadev_copy()
> + * - rte_dmadev_copy_sg()
> + * - rte_dmadev_fill()
> + * - rte_dmadev_submit()
> + *
> + * These APIs could work with different virtual DMA channels which have
> + * different contexts.
> + *
> + * The first three APIs are used to submit the operation request to the virtual
> + * DMA channel, if the submission is successful, a uint16_t ring_idx is
> + * returned, otherwise a negative number is returned.
> + *
> + * The last API was use to issue doorbell to hardware, and also there are flags
use->used?
> + * (@see RTE_DMA_OP_FLAG_SUBMIT) parameter of the first three APIs could do the
> + * same work.
> + *
> + * The second part is to obtain the result of requests:
> + * - rte_dmadev_completed()
> + * - return the number of operation requests completed successfully.
> + * - rte_dmadev_completed_status()
> + * - return the number of operation requests completed.
> + *
> + * About the ring_idx which enqueue APIs (e.g. rte_dmadev_copy()
> + * rte_dmadev_fill()) returned, the rules are as follows:
> + * - ring_idx for each virtual DMA channel are independent.
> + * - For a virtual DMA channel, the ring_idx is monotonically incremented,
> + * when it reach UINT16_MAX, it wraps back to zero.
> + * - This ring_idx can be used by applications to track per-operation
> + * metadata in an application-defined circular ring.
> + * - The initial ring_idx of a virtual DMA channel is zero, after the
> + * device is stopped, the ring_idx needs to be reset to zero.
> + *
> + * One example:
> + * - step-1: start one dmadev
> + * - step-2: enqueue a copy operation, the ring_idx return is 0
> + * - step-3: enqueue a copy operation again, the ring_idx return is 1
> + * - ...
> + * - step-101: stop the dmadev
> + * - step-102: start the dmadev
> + * - step-103: enqueue a copy operation, the cookie return is 0
> + * - ...
> + * - step-x+0: enqueue a fill operation, the ring_idx return is 65535
> + * - step-x+1: enqueue a copy operation, the ring_idx return is 0
> + * - ...
> + *
> + * By default, all the functions of the dmadev API exported by a PMD are
> + * lock-free functions which assume to not be invoked in parallel on different
> + * logical cores to work on the same target object.
should we add, object like dev_id, vchan_id etc. Upto you.
IMO, We should tell about "silent" mode here and it is the implication
on rte_dmadev_completed_*
as "silent" changes above scheme in the completion side.
> +/**
> + * A structure used to retrieve the information of an DMA device.
a DMA?
> + * A structure used to descript DMA port parameters.
> + */
> +struct rte_dmadev_port_param {
> + enum rte_dmadev_port_type port_type; /**< The device port type. */
> + union {
> + /** For PCIE port:
> + *
> + * The following model show SoC's PCIE module connects to
shows?
> + * multiple PCIE hosts and multiple endpoints. The PCIE module
> + * has an integrate DMA controller.
> + * If the DMA wants to access the memory of host A, it can be
> + * initiated by PF1 in core0, or by VF0 of PF0 in core0.
> + *
> + * System Bus
> + * | ----------PCIE module----------
> + * | Bus
> + * | Interface
> + * | ----- ------------------
> + * | | | | PCIE Core0 |
> + * | | | | | -----------
> + * | | | | PF-0 -- VF-0 | | Host A |
> + * | | |--------| |- VF-1 |--------| Root |
> + * | | | | PF-1 | | Complex |
> + * | | | | PF-2 | -----------
> + * | | | ------------------
> + * | | |
> + * | | | ------------------
> + * | | | | PCIE Core1 |
> + * | | | | | -----------
> + * | | | | PF-0 -- VF-0 | | Host B |
> + * |-----| |--------| PF-1 -- VF-0 |--------| Root |
> + * | | | | |- VF-1 | | Complex |
> + * | | | | PF-2 | -----------
> + * | | | ------------------
> + * | | |
> + * | | | ------------------
> + * | |DMA| | | ------
> + * | | | | |--------| EP |
> + * | | |--------| PCIE Core2 | ------
> + * | | | | | ------
> + * | | | | |--------| EP |
> + * | | | | | ------
> + * | ----- ------------------
> + *
> + * The following structure is used to describe the above access
> + * port.
> + *
> + * @note If some fields are not supported by hardware, set
> + * these fields to zero. And also there are no capabilities
> + * defined for this, it is the duty of the application to set
> + * the correct parameters.
Without getting, capabilities application can not set zero. I would
suggest rewording
something like.
@note If some fields can not be supported by the hardware/driver, then
the driver ignores those
fields. Please check driver-specific documentation for limitations and
capablites.
* @note If some fields are not supported by hardware, set
> + * these fields to zero. And also there are no capabilities
> + * defined for this, it is the duty of the application to set
> + * the correct parameters.
> + */
> + struct {
> + uint64_t coreid : 4; /**< PCIE core id used. */
> + uint64_t pfid : 8; /**< PF id used. */
> + uint64_t vfen : 1; /**< VF enable bit. */
> + uint64_t vfid : 16; /**< VF id used. */
> + uint64_t pasid : 20;
> + /**< The pasid filed in TLP packet. */
> + uint64_t attr : 3;
> + /**< The attributes filed in TLP packet. */
> + uint64_t ph : 2;
> + /**< The processing hint filed in TLP packet. */
> + uint64_t st : 16;
> + /**< The steering tag filed in TLP packet. */
> + } pcie;
> + };
> + uint64_t reserved[2]; /**< Reserved for future fields. */
> +};
> +
> +/**
> + * A structure used to configure a virtual DMA channel.
> + */
> +struct rte_dmadev_vchan_conf {
> + uint8_t direction;
> + /**< Set of supported transfer directions
Transfer direction
> + * @see RTE_DMA_DIR_MEM_TO_MEM
> + * @see RTE_DMA_DIR_MEM_TO_DEV
> + * @see RTE_DMA_DIR_DEV_TO_MEM
> + * @see RTE_DMA_DIR_DEV_TO_DEV
> + */
> +
> + /** Number of descriptor for the virtual DMA channel */
> + uint16_t nb_desc;
> + /** 1) Used to describes the port parameter in the device-to-memory
> + * transfer scenario.
> + * 2) Used to describes the source port parameter in the
> + * device-to-device transfer scenario.
> + * @see struct rte_dmadev_port_param
> + */
> + struct rte_dmadev_port_param src_port;
> + /** 1) Used to describes the port parameter in the memory-to-device
> + * transfer scenario.
> + * 2) Used to describes the destination port parameter in the
> + * device-to-device transfer scenario.
> + * @see struct rte_dmadev_port_param
> + */
> + struct rte_dmadev_port_param dst_port;
> +};
> +
> +/**
> + * @warning
> + * @b EXPERIMENTAL: this API may change without prior notice.
> + *
> + * Allocate and set up a virtual DMA channel.
> + *
> + * @param dev_id
> + * The identifier of the device.
> + * @param conf
> + * The virtual DMA channel configuration structure encapsulated into
> + * rte_dmadev_vchan_conf object.
> + *
> + * @return
> + * - >=0: Allocate success, it is the virtual DMA channel id. This value must
> + * be less than the field 'max_vchans' of struct rte_dmadev_conf
> + * which configured by rte_dmadev_configure().
> + * - <0: Error code returned by the driver virtual channel setup function.
> + */
> +__rte_experimental
> +int
> +rte_dmadev_vchan_setup(uint16_t dev_id,
> + const struct rte_dmadev_vchan_conf *conf);
> +
> +/**
> + * @warning
> + * @b EXPERIMENTAL: this API may change without prior notice.
> + *
> + * Release a virtual DMA channel.
> + *
> + * @param dev_id
> + * The identifier of the device.
> + * @param vchan
> + * The identifier of virtual DMA channel which return by vchan setup.
> + *
> + * @return
> + * - =0: Successfully release the virtual DMA channel.
> + * - <0: Error code returned by the driver virtual channel release function.
> + */
> +__rte_experimental
> +int
> +rte_dmadev_vchan_release(uint16_t dev_id, uint16_t vchan);
Commented on another thread.
> +
> +/**
> + * rte_dmadev_stats - running statistics.
> + */
> +struct rte_dmadev_stats {
> + uint64_t submitted_count;
> + /**< Count of operations which were submitted to hardware. */
> + uint64_t completed_fail_count;
> + /**< Count of operations which failed to complete. */
> + uint64_t completed_count;
> + /**< Count of operations which successfully complete. */
> +};
> +
> +#define RTE_DMADEV_ALL_VCHAN 0xFFFFu
Commented on another thread. No strong opinion.
> +/**
> + * @warning
> + * @b EXPERIMENTAL: this API may change without prior notice.
> + *
> + * Enqueue a copy operation onto the virtual DMA channel.
> + *
> + * This queues up a copy operation to be performed by hardware, if the 'flags'
> + * parameter contains RTE_DMA_OP_FLAG_SUBMIT then trigger hardware to begin
> + * this operation, otherwise do not trigger hardware.
hardware -> doorbell.
> + *
> + * @param dev_id
> + * The identifier of the device.
> + * @param vchan
> + * The identifier of virtual DMA channel.
> + * @param src
> + * The address of the source buffer.
> + * @param dst
> + * The address of the destination buffer.
> + * @param length
> + * The length of the data to be copied.
> + * @param flags
> + * An flags for this operation.
> + * @see RTE_DMA_OP_FLAG_*
> + *
> + * @return
> + * - 0..UINT16_MAX: index of enqueued copy job.
> + * - <0: Error code returned by the driver copy function.
> + */
> +__rte_experimental
> +static inline int
> +rte_dmadev_copy(uint16_t dev_id, uint16_t vchan, rte_iova_t src, rte_iova_t dst,
> + uint32_t length, uint64_t flags)
> +{
> + struct rte_dmadev *dev = &rte_dmadevices[dev_id];
> +
> +#ifdef RTE_DMADEV_DEBUG
> + if (!rte_dmadev_is_valid_dev(dev_id) ||
> + vchan >= dev->data->dev_conf.max_vchans)
> + return -EINVAL;
> + RTE_FUNC_PTR_OR_ERR_RET(*dev->copy, -ENOTSUP);
> +#endif
> +
> + return (*dev->copy)(dev, vchan, src, dst, length, flags);
> +}
> +
> +/**
> + * @warning
> + * @b EXPERIMENTAL: this API may change without prior notice.
> + *
> + * Enqueue a scatter list copy operation onto the virtual DMA channel.
> + *
> + * This queues up a scatter list copy operation to be performed by hardware, if
> + * the 'flags' parameter contains RTE_DMA_OP_FLAG_SUBMIT then trigger hardware
> + * to begin this operation, otherwise do not trigger hardware.
harware -> doorbell
> + *
> + * @param dev_id
> + * The identifier of the device.
> + * @param vchan
> + * The identifier of virtual DMA channel.
> + * @param sg
> + * The pointer of scatterlist.
> + * @param flags
> + * An flags for this operation.
> + * @see RTE_DMA_OP_FLAG_*
> + *
> + * @return
> + * - 0..UINT16_MAX: index of enqueued copy scatterlist job.
> + * - <0: Error code returned by the driver copy scatterlist function.
> + */
> +__rte_experimental
> +static inline int
> +rte_dmadev_copy_sg(uint16_t dev_id, uint16_t vchan,
> + const struct rte_dmadev_sg *sg,
Sent comment in another thread.
> + uint64_t flags)
> +{
> + struct rte_dmadev *dev = &rte_dmadevices[dev_id];
> +
> +#ifdef RTE_DMADEV_DEBUG
> + if (!rte_dmadev_is_valid_dev(dev_id) ||
> + vchan >= dev->data->dev_conf.max_vchans ||
> + sg == NULL || sg->src == NULL || sg->dst == NULL ||
> + sg->nb_src == 0 || sg->nb_dst == 0)
> + return -EINVAL;
> + RTE_FUNC_PTR_OR_ERR_RET(*dev->copy_sg, -ENOTSUP);
> +#endif
> +
> + return (*dev->copy_sg)(dev, vchan, sg, flags);
> +}
> +
> +/**
> + * @warning
> + * @b EXPERIMENTAL: this API may change without prior notice.
> + *
> + * Enqueue a fill operation onto the virtual DMA channel.
> + *
> + * This queues up a fill operation to be performed by hardware, if the 'flags'
> + * parameter contains RTE_DMA_OP_FLAG_SUBMIT then trigger hardware to begin
> + * this operation, otherwise do not trigger hardware.
hardware -> doorbell.
> + *
> + * @param dev_id
> + * The identifier of the device.
> + * @param vchan
> + * The identifier of virtual DMA channel.
> + * @param pattern
> + * The pattern to populate the destination buffer with.
> + * @param dst
> + * The address of the destination buffer.
> + * @param length
> + * The length of the destination buffer.
> + * @param flags
> + * An flags for this operation.
> + * @see RTE_DMA_OP_FLAG_*
> + *
> + * @return
> + * - 0..UINT16_MAX: index of enqueued fill job.
> + * - <0: Error code returned by the driver fill function.
> + */
> +__rte_experimental
> +static inline int
> +rte_dmadev_fill(uint16_t dev_id, uint16_t vchan, uint64_t pattern,
> + rte_iova_t dst, uint32_t length, uint64_t flags)
> +{
> + struct rte_dmadev *dev = &rte_dmadevices[dev_id];
> +
> +#ifdef RTE_DMADEV_DEBUG
> + if (!rte_dmadev_is_valid_dev(dev_id) ||
> + vchan >= dev->data->dev_conf.max_vchans)
> + return -EINVAL;
> + RTE_FUNC_PTR_OR_ERR_RET(*dev->fill, -ENOTSUP);
> +#endif
> +
> + return (*dev->fill)(dev, vchan, pattern, dst, length, flags);
> +}
> +
> +/**
> + * @warning
> + * @b EXPERIMENTAL: this API may change without prior notice.
> + *
> + * Trigger hardware to begin performing enqueued operations.
> + *
> + * This API is used to write the "doorbell" to the hardware to trigger it
> + * to begin the operations previously enqueued by rte_dmadev_copy/fill().
> + *
> + * @param dev_id
> + * The identifier of the device.
> + * @param vchan
> + * The identifier of virtual DMA channel.
> + *
> + * @return
> + * - =0: Successfully trigger hardware.
> + * - <0: Failure to trigger hardware.
> + */
> +__rte_experimental
> +static inline int
> +rte_dmadev_submit(uint16_t dev_id, uint16_t vchan)
> +{
> + struct rte_dmadev *dev = &rte_dmadevices[dev_id];
> +
> +#ifdef RTE_DMADEV_DEBUG
> + if (!rte_dmadev_is_valid_dev(dev_id) ||
> + vchan >= dev->data->dev_conf.max_vchans)
> + return -EINVAL;
> + RTE_FUNC_PTR_OR_ERR_RET(*dev->submit, -ENOTSUP);
> +#endif
> +
> + return (*dev->submit)(dev, vchan);
> +}
> +
> +/**
> + * @warning
> + * @b EXPERIMENTAL: this API may change without prior notice.
> + *
> + * Returns the number of operations that have been successfully completed.
> + *
> + * @param dev_id
> + * The identifier of the device.
> + * @param vchan
> + * The identifier of virtual DMA channel.
> + * @param nb_cpls
> + * The maximum number of completed operations that can be processed.
> + * @param[out] last_idx
> + * The last completed operation's index.
> + * If not required, NULL can be passed in.
> + * @param[out] has_error
> + * Indicates if there are transfer error.
> + * If not required, NULL can be passed in.
> + *
> + * @return
> + * The number of operations that successfully completed. This return value
> + * must be less than or equal to the value of nb_cpls.
> + */
> +__rte_experimental
> +static inline uint16_t
> +rte_dmadev_completed(uint16_t dev_id, uint16_t vchan, const uint16_t nb_cpls,
> + uint16_t *last_idx, bool *has_error)
> +{
> + struct rte_dmadev *dev = &rte_dmadevices[dev_id];
> + uint16_t idx;
> + bool err;
> +
> +#ifdef RTE_DMADEV_DEBUG
> + if (!rte_dmadev_is_valid_dev(dev_id) ||
> + vchan >= dev->data->dev_conf.max_vchans ||
> + nb_cpls == 0)
> + return 0;
> + RTE_FUNC_PTR_OR_ERR_RET(*dev->completed, 0);
> +#endif
> +
> + /* Ensure the pointer values are non-null to simplify drivers.
> + * In most cases these should be compile time evaluated, since this is
> + * an inline function.
> + * - If NULL is explicitly passed as parameter, then compiler knows the
> + * value is NULL
> + * - If address of local variable is passed as parameter, then compiler
> + * can know it's non-NULL.
> + */
> + if (last_idx == NULL)
> + last_idx = &idx;
> + if (has_error == NULL)
> + has_error = &err;
> +
> + *has_error = false;
> + return (*dev->completed)(dev, vchan, nb_cpls, last_idx, has_error);
> +}
> +
> +/**
> + * @warning
> + * @b EXPERIMENTAL: this API may change without prior notice.
> + *
> + * Returns the number of operations that have been completed, and the
> + * operations result may succeed or fail.
> + *
> + * @param dev_id
> + * The identifier of the device.
> + * @param vchan
> + * The identifier of virtual DMA channel.
> + * @param nb_cpls
> + * Indicates the size of status array.
> + * @param[out] last_idx
> + * The last completed operation's index.
> + * If not required, NULL can be passed in.
> + * @param[out] status
> + * The error code of operations that completed.
> + * @see enum rte_dma_status_code
> + *
> + * @return
> + * The number of operations that completed. This return value must be less
> + * than or equal to the value of nb_cpls.
> + */
> +__rte_experimental
> +static inline uint16_t
> +rte_dmadev_completed_status(uint16_t dev_id, uint16_t vchan,
> + const uint16_t nb_cpls, uint16_t *last_idx,
> + enum rte_dma_status_code *status)
> +{
> + struct rte_dmadev *dev = &rte_dmadevices[dev_id];
> + uint16_t idx;
> +
> +#ifdef RTE_DMADEV_DEBUG
> + if (!rte_dmadev_is_valid_dev(dev_id) ||
> + vchan >= dev->data->dev_conf.max_vchans ||
> + nb_cpls == 0 || status == NULL)
> + return 0;
> + RTE_FUNC_PTR_OR_ERR_RET(*dev->completed_status, 0);
> +#endif
> +
> + if (last_idx == NULL)
> + last_idx = &idx;
> +
> + return (*dev->completed_status)(dev, vchan, nb_cpls, last_idx, status);
> +}
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
Thanks for v5
@@ -495,6 +495,10 @@ F: drivers/raw/skeleton/
F: app/test/test_rawdev.c
F: doc/guides/prog_guide/rawdev.rst
+DMA device API - EXPERIMENTAL
+M: Chengwen Feng <fengchengwen@huawei.com>
+F: lib/dmadev/
+
Memory Pool Drivers
-------------------
@@ -81,6 +81,9 @@
/* rawdev defines */
#define RTE_RAWDEV_MAX_DEVS 64
+/* dmadev defines */
+#define RTE_DMADEV_MAX_DEVS 64
+
/* ip_fragmentation defines */
#define RTE_LIBRTE_IP_FRAG_MAX_FRAG 4
#undef RTE_LIBRTE_IP_FRAG_TBL_STAT
@@ -27,6 +27,7 @@ The public API headers are grouped by topics:
[event_timer_adapter] (@ref rte_event_timer_adapter.h),
[event_crypto_adapter] (@ref rte_event_crypto_adapter.h),
[rawdev] (@ref rte_rawdev.h),
+ [dmadev] (@ref rte_dmadev.h),
[metrics] (@ref rte_metrics.h),
[bitrate] (@ref rte_bitrate.h),
[latency] (@ref rte_latencystats.h),
@@ -35,6 +35,7 @@ INPUT = @TOPDIR@/doc/api/doxy-api-index.md \
@TOPDIR@/lib/compressdev \
@TOPDIR@/lib/cryptodev \
@TOPDIR@/lib/distributor \
+ @TOPDIR@/lib/dmadev \
@TOPDIR@/lib/efd \
@TOPDIR@/lib/ethdev \
@TOPDIR@/lib/eventdev \
new file mode 100644
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2021 HiSilicon Limited.
+
+sources = files('rte_dmadev.c')
+headers = files('rte_dmadev.h')
+indirect_headers += files('rte_dmadev_core.h')
+driver_sdk_headers += files('rte_dmadev_pmd.h')
new file mode 100644
@@ -0,0 +1,539 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2021 HiSilicon Limited.
+ * Copyright(c) 2021 Intel Corporation.
+ */
+
+#include <ctype.h>
+#include <inttypes.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <rte_debug.h>
+#include <rte_dev.h>
+#include <rte_eal.h>
+#include <rte_errno.h>
+#include <rte_lcore.h>
+#include <rte_log.h>
+#include <rte_memory.h>
+#include <rte_memzone.h>
+#include <rte_malloc.h>
+#include <rte_string_fns.h>
+
+#include "rte_dmadev.h"
+#include "rte_dmadev_pmd.h"
+
+struct rte_dmadev rte_dmadevices[RTE_DMADEV_MAX_DEVS];
+
+static const char *MZ_RTE_DMADEV_DATA = "rte_dmadev_data";
+/* Shared memory between primary and secondary processes. */
+static struct {
+ struct rte_dmadev_data data[RTE_DMADEV_MAX_DEVS];
+} *dmadev_shared_data;
+
+RTE_LOG_REGISTER_DEFAULT(rte_dmadev_logtype, INFO);
+#define RTE_DMADEV_LOG(level, ...) \
+ rte_log(RTE_LOG_ ## level, rte_dmadev_logtype, "" __VA_ARGS__)
+
+/* Macros to check for valid device id */
+#define RTE_DMADEV_VALID_DEV_ID_OR_ERR_RET(dev_id, retval) do { \
+ if (!rte_dmadev_is_valid_dev(dev_id)) { \
+ RTE_DMADEV_LOG(ERR, "Invalid dev_id=%u\n", dev_id); \
+ return retval; \
+ } \
+} while (0)
+
+static int
+dmadev_check_name(const char *name)
+{
+ size_t name_len;
+
+ if (name == NULL) {
+ RTE_DMADEV_LOG(ERR, "Name can't be NULL\n");
+ return -EINVAL;
+ }
+
+ name_len = strnlen(name, RTE_DMADEV_NAME_MAX_LEN);
+ if (name_len == 0) {
+ RTE_DMADEV_LOG(ERR, "Zero length DMA device name\n");
+ return -EINVAL;
+ }
+ if (name_len >= RTE_DMADEV_NAME_MAX_LEN) {
+ RTE_DMADEV_LOG(ERR, "DMA device name is too long\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static uint16_t
+dmadev_find_free_dev(void)
+{
+ uint16_t i;
+
+ for (i = 0; i < RTE_DMADEV_MAX_DEVS; i++) {
+ if (dmadev_shared_data->data[i].dev_name[0] == '\0') {
+ RTE_ASSERT(rte_dmadevices[i].state ==
+ RTE_DMADEV_UNUSED);
+ return i;
+ }
+ }
+
+ return RTE_DMADEV_MAX_DEVS;
+}
+
+static struct rte_dmadev*
+dmadev_find(const char *name)
+{
+ uint16_t i;
+
+ for (i = 0; i < RTE_DMADEV_MAX_DEVS; i++) {
+ if ((rte_dmadevices[i].state == RTE_DMADEV_ATTACHED) &&
+ (!strcmp(name, rte_dmadevices[i].data->dev_name)))
+ return &rte_dmadevices[i];
+ }
+
+ return NULL;
+}
+
+static int
+dmadev_shared_data_prepare(void)
+{
+ const struct rte_memzone *mz;
+
+ if (dmadev_shared_data == NULL) {
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+ /* Allocate port data and ownership shared memory. */
+ mz = rte_memzone_reserve(MZ_RTE_DMADEV_DATA,
+ sizeof(*dmadev_shared_data),
+ rte_socket_id(), 0);
+ } else
+ mz = rte_memzone_lookup(MZ_RTE_DMADEV_DATA);
+ if (mz == NULL)
+ return -ENOMEM;
+
+ dmadev_shared_data = mz->addr;
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+ memset(dmadev_shared_data->data, 0,
+ sizeof(dmadev_shared_data->data));
+ }
+
+ return 0;
+}
+
+static struct rte_dmadev *
+dmadev_allocate(const char *name)
+{
+ struct rte_dmadev *dev;
+ uint16_t dev_id;
+
+ dev = dmadev_find(name);
+ if (dev != NULL) {
+ RTE_DMADEV_LOG(ERR, "DMA device already allocated\n");
+ return NULL;
+ }
+
+ dev_id = dmadev_find_free_dev();
+ if (dev_id == RTE_DMADEV_MAX_DEVS) {
+ RTE_DMADEV_LOG(ERR, "Reached maximum number of DMA devices\n");
+ return NULL;
+ }
+
+ if (dmadev_shared_data_prepare() != 0) {
+ RTE_DMADEV_LOG(ERR, "Cannot allocate DMA shared data\n");
+ return NULL;
+ }
+
+ dev = &rte_dmadevices[dev_id];
+ dev->data = &dmadev_shared_data->data[dev_id];
+ dev->data->dev_id = dev_id;
+ rte_strscpy(dev->data->dev_name, name, sizeof(dev->data->dev_name));
+
+ return dev;
+}
+
+static struct rte_dmadev *
+dmadev_attach_secondary(const char *name)
+{
+ struct rte_dmadev *dev;
+ uint16_t i;
+
+ if (dmadev_shared_data_prepare() != 0) {
+ RTE_DMADEV_LOG(ERR, "Cannot allocate DMA shared data\n");
+ return NULL;
+ }
+
+ for (i = 0; i < RTE_DMADEV_MAX_DEVS; i++) {
+ if (!strcmp(dmadev_shared_data->data[i].dev_name, name))
+ break;
+ }
+ if (i == RTE_DMADEV_MAX_DEVS) {
+ RTE_DMADEV_LOG(ERR,
+ "Device %s is not driven by the primary process\n",
+ name);
+ return NULL;
+ }
+
+ dev = &rte_dmadevices[i];
+ dev->data = &dmadev_shared_data->data[i];
+ RTE_ASSERT(dev->data->dev_id == i);
+ dev->dev_private = dev->data->dev_private;
+
+ return dev;
+}
+
+struct rte_dmadev *
+rte_dmadev_pmd_allocate(const char *name)
+{
+ struct rte_dmadev *dev;
+
+ if (dmadev_check_name(name) != 0)
+ return NULL;
+
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+ dev = dmadev_allocate(name);
+ else
+ dev = dmadev_attach_secondary(name);
+
+ if (dev == NULL)
+ return NULL;
+ dev->state = RTE_DMADEV_ATTACHED;
+
+ return dev;
+}
+
+int
+rte_dmadev_pmd_release(struct rte_dmadev *dev)
+{
+ void *dev_private_bak;
+
+ if (dev == NULL)
+ return -EINVAL;
+
+ if (dev->state == RTE_DMADEV_UNUSED)
+ return 0;
+
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+ memset(dev->data, 0, sizeof(struct rte_dmadev_data));
+
+ dev_private_bak = dev->dev_private;
+ memset(dev, 0, sizeof(struct rte_dmadev));
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+ dev->dev_private = dev_private_bak;
+ dev->state = RTE_DMADEV_UNUSED;
+
+ return 0;
+}
+
+struct rte_dmadev *
+rte_dmadev_get_device_by_name(const char *name)
+{
+ if (dmadev_check_name(name) != 0)
+ return NULL;
+ return dmadev_find(name);
+}
+
+bool
+rte_dmadev_is_valid_dev(uint16_t dev_id)
+{
+ return (dev_id < RTE_DMADEV_MAX_DEVS) &&
+ rte_dmadevices[dev_id].state == RTE_DMADEV_ATTACHED;
+}
+
+uint16_t
+rte_dmadev_count(void)
+{
+ uint16_t count = 0;
+ uint16_t i;
+
+ for (i = 0; i < RTE_DMADEV_MAX_DEVS; i++) {
+ if (rte_dmadevices[i].state == RTE_DMADEV_ATTACHED)
+ count++;
+ }
+
+ return count;
+}
+
+int
+rte_dmadev_info_get(uint16_t dev_id, struct rte_dmadev_info *dev_info)
+{
+ const struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+ int ret;
+
+ RTE_DMADEV_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
+ if (dev_info == NULL)
+ return -EINVAL;
+
+ RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_info_get, -ENOTSUP);
+ memset(dev_info, 0, sizeof(struct rte_dmadev_info));
+ ret = (*dev->dev_ops->dev_info_get)(dev, dev_info,
+ sizeof(struct rte_dmadev_info));
+ if (ret != 0)
+ return ret;
+
+ dev_info->device = dev->device;
+ dev_info->nb_vchans = dev->data->dev_conf.max_vchans;
+
+ return 0;
+}
+
+int
+rte_dmadev_configure(uint16_t dev_id, const struct rte_dmadev_conf *dev_conf)
+{
+ struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+ struct rte_dmadev_info info;
+ int ret;
+
+ RTE_DMADEV_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
+ if (dev_conf == NULL)
+ return -EINVAL;
+
+ ret = rte_dmadev_info_get(dev_id, &info);
+ if (ret != 0) {
+ RTE_DMADEV_LOG(ERR, "Device %u get device info fail\n", dev_id);
+ return -EINVAL;
+ }
+ if (dev_conf->max_vchans > info.max_vchans) {
+ RTE_DMADEV_LOG(ERR,
+ "Device %u configure too many vchans\n", dev_id);
+ return -EINVAL;
+ }
+
+ if (dev->data->dev_started != 0) {
+ RTE_DMADEV_LOG(ERR,
+ "Device %u must be stopped to allow configuration\n",
+ dev_id);
+ return -EBUSY;
+ }
+
+ RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_configure, -ENOTSUP);
+ ret = (*dev->dev_ops->dev_configure)(dev, dev_conf);
+ if (ret == 0)
+ memcpy(&dev->data->dev_conf, dev_conf, sizeof(*dev_conf));
+
+ return ret;
+}
+
+int
+rte_dmadev_start(uint16_t dev_id)
+{
+ struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+ int ret;
+
+ RTE_DMADEV_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
+
+ if (dev->data->dev_started != 0) {
+ RTE_DMADEV_LOG(WARNING, "Device %u already started\n", dev_id);
+ return 0;
+ }
+
+ if (dev->dev_ops->dev_start == NULL)
+ goto mark_started;
+
+ ret = (*dev->dev_ops->dev_start)(dev);
+ if (ret != 0)
+ return ret;
+
+mark_started:
+ dev->data->dev_started = 1;
+ return 0;
+}
+
+int
+rte_dmadev_stop(uint16_t dev_id)
+{
+ struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+ int ret;
+
+ RTE_DMADEV_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
+
+ if (dev->data->dev_started == 0) {
+ RTE_DMADEV_LOG(WARNING, "Device %u already stopped\n", dev_id);
+ return 0;
+ }
+
+ if (dev->dev_ops->dev_stop == NULL)
+ goto mark_stopped;
+
+ ret = (*dev->dev_ops->dev_stop)(dev);
+ if (ret != 0)
+ return ret;
+
+mark_stopped:
+ dev->data->dev_started = 0;
+ return 0;
+}
+
+int
+rte_dmadev_close(uint16_t dev_id)
+{
+ struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+
+ RTE_DMADEV_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
+
+ /* Device must be stopped before it can be closed */
+ if (dev->data->dev_started == 1) {
+ RTE_DMADEV_LOG(ERR,
+ "Device %u must be stopped before closing\n", dev_id);
+ return -EBUSY;
+ }
+
+ RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_close, -ENOTSUP);
+ return (*dev->dev_ops->dev_close)(dev);
+}
+
+int
+rte_dmadev_vchan_setup(uint16_t dev_id,
+ const struct rte_dmadev_vchan_conf *conf)
+{
+ struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+ struct rte_dmadev_info info;
+ uint8_t dir_all = RTE_DMA_DIR_MEM_TO_MEM | RTE_DMA_DIR_MEM_TO_DEV |
+ RTE_DMA_DIR_DEV_TO_MEM | RTE_DMA_DIR_DEV_TO_DEV;
+ int ret;
+
+ RTE_DMADEV_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
+ if (conf == NULL)
+ return -EINVAL;
+
+ dev = &rte_dmadevices[dev_id];
+
+ ret = rte_dmadev_info_get(dev_id, &info);
+ if (ret != 0) {
+ RTE_DMADEV_LOG(ERR, "Device %u get device info fail\n", dev_id);
+ return -EINVAL;
+ }
+ if (conf->direction == 0 ||
+ conf->direction & ~dir_all) {
+ RTE_DMADEV_LOG(ERR, "Device %u direction invalid!\n", dev_id);
+ return -EINVAL;
+ }
+ if (conf->direction & RTE_DMA_DIR_MEM_TO_MEM &&
+ !(info.dev_capa & RTE_DMA_DEV_CAPA_MEM_TO_MEM)) {
+ RTE_DMADEV_LOG(ERR,
+ "Device %u don't support mem2mem transfer\n", dev_id);
+ return -EINVAL;
+ }
+ if (conf->direction & RTE_DMA_DIR_MEM_TO_DEV &&
+ !(info.dev_capa & RTE_DMA_DEV_CAPA_MEM_TO_DEV)) {
+ RTE_DMADEV_LOG(ERR,
+ "Device %u don't support mem2dev transfer\n", dev_id);
+ return -EINVAL;
+ }
+ if (conf->direction & RTE_DMA_DIR_DEV_TO_MEM &&
+ !(info.dev_capa & RTE_DMA_DEV_CAPA_DEV_TO_MEM)) {
+ RTE_DMADEV_LOG(ERR,
+ "Device %u don't support dev2mem transfer\n", dev_id);
+ return -EINVAL;
+ }
+ if (conf->direction & RTE_DMA_DIR_DEV_TO_DEV &&
+ !(info.dev_capa & RTE_DMA_DEV_CAPA_DEV_TO_DEV)) {
+ RTE_DMADEV_LOG(ERR,
+ "Device %u don't support dev2dev transfer\n", dev_id);
+ return -EINVAL;
+ }
+ if (conf->nb_desc < info.min_desc || conf->nb_desc > info.max_desc) {
+ RTE_DMADEV_LOG(ERR,
+ "Device %u number of descriptors invalid\n", dev_id);
+ return -EINVAL;
+ }
+
+ RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->vchan_setup, -ENOTSUP);
+ return (*dev->dev_ops->vchan_setup)(dev, conf);
+}
+
+int
+rte_dmadev_vchan_release(uint16_t dev_id, uint16_t vchan)
+{
+ struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+
+ RTE_DMADEV_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
+ if (vchan >= dev->data->dev_conf.max_vchans) {
+ RTE_DMADEV_LOG(ERR,
+ "Device %u vchan %u out of range\n", dev_id, vchan);
+ return -EINVAL;
+ }
+
+ RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->vchan_release, -ENOTSUP);
+ return (*dev->dev_ops->vchan_release)(dev, vchan);
+}
+
+int
+rte_dmadev_stats_get(uint16_t dev_id, uint16_t vchan,
+ struct rte_dmadev_stats *stats)
+{
+ const struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+
+ RTE_DMADEV_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
+ if (stats == NULL)
+ return -EINVAL;
+ if (vchan >= dev->data->dev_conf.max_vchans &&
+ vchan != RTE_DMADEV_ALL_VCHAN) {
+ RTE_DMADEV_LOG(ERR,
+ "Device %u vchan %u out of range\n", dev_id, vchan);
+ return -EINVAL;
+ }
+
+ RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->stats_get, -ENOTSUP);
+ return (*dev->dev_ops->stats_get)(dev, vchan, stats,
+ sizeof(struct rte_dmadev_stats));
+}
+
+int
+rte_dmadev_stats_reset(uint16_t dev_id, uint16_t vchan)
+{
+ struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+
+ RTE_DMADEV_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
+ if (vchan >= dev->data->dev_conf.max_vchans &&
+ vchan != RTE_DMADEV_ALL_VCHAN) {
+ RTE_DMADEV_LOG(ERR,
+ "Device %u vchan %u out of range\n", dev_id, vchan);
+ return -EINVAL;
+ }
+
+ RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->stats_reset, -ENOTSUP);
+ return (*dev->dev_ops->stats_reset)(dev, vchan);
+}
+
+int
+rte_dmadev_dump(uint16_t dev_id, FILE *f)
+{
+ const struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+ struct rte_dmadev_info info;
+ int ret;
+
+ RTE_DMADEV_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
+ if (f == NULL)
+ return -EINVAL;
+
+ ret = rte_dmadev_info_get(dev_id, &info);
+ if (ret != 0) {
+ RTE_DMADEV_LOG(ERR, "Device %u get device info fail\n", dev_id);
+ return -EINVAL;
+ }
+
+ fprintf(f, "DMA Dev %u, '%s' [%s]\n",
+ dev->data->dev_id,
+ dev->data->dev_name,
+ dev->data->dev_started ? "started" : "stopped");
+ fprintf(f, " dev_capa: 0x%" PRIx64 "\n", info.dev_capa);
+ fprintf(f, " max_vchans_supported: %u\n", info.max_vchans);
+ fprintf(f, " max_vchans_configured: %u\n", info.nb_vchans);
+
+ if (dev->dev_ops->dev_dump != NULL)
+ return (*dev->dev_ops->dev_dump)(dev, f);
+
+ return 0;
+}
+
+int
+rte_dmadev_selftest(uint16_t dev_id)
+{
+ struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+
+ RTE_DMADEV_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
+ RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_selftest, -ENOTSUP);
+ return (*dev->dev_ops->dev_selftest)(dev_id);
+}
new file mode 100644
@@ -0,0 +1,1028 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2021 HiSilicon Limited.
+ * Copyright(c) 2021 Intel Corporation.
+ * Copyright(c) 2021 Marvell International Ltd.
+ * Copyright(c) 2021 SmartShare Systems.
+ */
+
+#ifndef _RTE_DMADEV_H_
+#define _RTE_DMADEV_H_
+
+/**
+ * @file rte_dmadev.h
+ *
+ * RTE DMA (Direct Memory Access) device APIs.
+ *
+ * The DMA framework is built on the following model:
+ *
+ * --------------- --------------- ---------------
+ * | virtual DMA | | virtual DMA | | virtual DMA |
+ * | channel | | channel | | channel |
+ * --------------- --------------- ---------------
+ * | | |
+ * ------------------ |
+ * | |
+ * ------------ ------------
+ * | dmadev | | dmadev |
+ * ------------ ------------
+ * | |
+ * ------------------ ------------------
+ * | HW-DMA-channel | | HW-DMA-channel |
+ * ------------------ ------------------
+ * | |
+ * --------------------------------
+ * |
+ * ---------------------
+ * | HW-DMA-Controller |
+ * ---------------------
+ *
+ * The DMA controller could have multiple HW-DMA-channels (aka. HW-DMA-queues),
+ * each HW-DMA-channel should be represented by a dmadev.
+ *
+ * The dmadev could create multiple virtual DMA channel, each virtual DMA
+ * channel represents a different transfer context. The DMA operation request
+ * must be submitted to the virtual DMA channel. e.g. Application could create
+ * virtual DMA channel 0 for memory-to-memory transfer scenario, and create
+ * virtual DMA channel 1 for memory-to-device transfer scenario.
+ *
+ * The dmadev are dynamically allocated by rte_dmadev_pmd_allocate() during the
+ * PCI/SoC device probing phase performed at EAL initialization time. And could
+ * be released by rte_dmadev_pmd_release() during the PCI/SoC device removing
+ * phase.
+ *
+ * This framework uses 'uint16_t dev_id' as the device identifier of a dmadev,
+ * and 'uint16_t vchan' as the virtual DMA channel identifier in one dmadev.
+ *
+ * The functions exported by the dmadev API to setup a device designated by its
+ * device identifier must be invoked in the following order:
+ * - rte_dmadev_configure()
+ * - rte_dmadev_vchan_setup()
+ * - rte_dmadev_start()
+ *
+ * Then, the application can invoke dataplane APIs to process jobs.
+ *
+ * If the application wants to change the configuration (i.e. invoke
+ * rte_dmadev_configure()), it must invoke rte_dmadev_stop() first to stop the
+ * device and then do the reconfiguration before invoking rte_dmadev_start()
+ * again. The dataplane APIs should not be invoked when the device is stopped.
+ *
+ * Finally, an application can close a dmadev by invoking the
+ * rte_dmadev_close() function.
+ *
+ * The dataplane APIs include two parts:
+ * The first part is the submission of operation requests:
+ * - rte_dmadev_copy()
+ * - rte_dmadev_copy_sg()
+ * - rte_dmadev_fill()
+ * - rte_dmadev_submit()
+ *
+ * These APIs could work with different virtual DMA channels which have
+ * different contexts.
+ *
+ * The first three APIs are used to submit the operation request to the virtual
+ * DMA channel, if the submission is successful, a uint16_t ring_idx is
+ * returned, otherwise a negative number is returned.
+ *
+ * The last API was use to issue doorbell to hardware, and also there are flags
+ * (@see RTE_DMA_OP_FLAG_SUBMIT) parameter of the first three APIs could do the
+ * same work.
+ *
+ * The second part is to obtain the result of requests:
+ * - rte_dmadev_completed()
+ * - return the number of operation requests completed successfully.
+ * - rte_dmadev_completed_status()
+ * - return the number of operation requests completed.
+ *
+ * About the ring_idx which enqueue APIs (e.g. rte_dmadev_copy()
+ * rte_dmadev_fill()) returned, the rules are as follows:
+ * - ring_idx for each virtual DMA channel are independent.
+ * - For a virtual DMA channel, the ring_idx is monotonically incremented,
+ * when it reach UINT16_MAX, it wraps back to zero.
+ * - This ring_idx can be used by applications to track per-operation
+ * metadata in an application-defined circular ring.
+ * - The initial ring_idx of a virtual DMA channel is zero, after the
+ * device is stopped, the ring_idx needs to be reset to zero.
+ *
+ * One example:
+ * - step-1: start one dmadev
+ * - step-2: enqueue a copy operation, the ring_idx return is 0
+ * - step-3: enqueue a copy operation again, the ring_idx return is 1
+ * - ...
+ * - step-101: stop the dmadev
+ * - step-102: start the dmadev
+ * - step-103: enqueue a copy operation, the cookie return is 0
+ * - ...
+ * - step-x+0: enqueue a fill operation, the ring_idx return is 65535
+ * - step-x+1: enqueue a copy operation, the ring_idx return is 0
+ * - ...
+ *
+ * By default, all the functions of the dmadev API exported by a PMD are
+ * lock-free functions which assume to not be invoked in parallel on different
+ * logical cores to work on the same target object.
+ *
+ */
+
+#include <rte_common.h>
+#include <rte_compat.h>
+#include <rte_dev.h>
+#include <rte_errno.h>
+#include <rte_memory.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#define RTE_DMADEV_NAME_MAX_LEN RTE_DEV_NAME_MAX_LEN
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * @param dev_id
+ * DMA device index.
+ *
+ * @return
+ * - If the device index is valid (true) or not (false).
+ */
+__rte_experimental
+bool
+rte_dmadev_is_valid_dev(uint16_t dev_id);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Get the total number of DMA devices that have been successfully
+ * initialised.
+ *
+ * @return
+ * The total number of usable DMA devices.
+ */
+__rte_experimental
+uint16_t
+rte_dmadev_count(void);
+
+/* Enumerates DMA device capabilities */
+#define RTE_DMA_DEV_CAPA_MEM_TO_MEM (1ull << 0)
+/**< DMA device support memory-to-memory transfer.
+ *
+ * @see struct rte_dmadev_info::dev_capa
+ */
+
+#define RTE_DMA_DEV_CAPA_MEM_TO_DEV (1ull << 1)
+/**< DMA device support memory-to-device transfer.
+ *
+ * @see struct rte_dmadev_info::dev_capa
+ * @see struct rte_dmadev_port_param::port_type
+ */
+
+#define RTE_DMA_DEV_CAPA_DEV_TO_MEM (1ull << 2)
+/**< DMA device support device-to-memory transfer.
+ *
+ * @see struct rte_dmadev_info::dev_capa
+ * @see struct rte_dmadev_port_param::port_type
+ */
+
+#define RTE_DMA_DEV_CAPA_DEV_TO_DEV (1ull << 3)
+/**< DMA device support device-to-device transfer.
+ *
+ * @see struct rte_dmadev_info::dev_capa
+ * @see struct rte_dmadev_port_param::port_type
+ */
+
+#define RTE_DMA_DEV_CAPA_SVA (1ull << 4)
+/**< DMA device support SVA which could use VA as DMA address.
+ * If device support SVA then application could pass any VA address like memory
+ * from rte_malloc(), rte_memzone(), malloc, stack memory.
+ * If device don't support SVA, then application should pass IOVA address which
+ * from rte_malloc(), rte_memzone().
+ *
+ * @see struct rte_dmadev_info::dev_capa
+ */
+
+#define RTE_DMA_DEV_CAPA_SILENT (1ull << 5)
+/**< DMA device support work in silent mode.
+ * In this mode, application don't required to invoke rte_dmadev_completed*()
+ * API.
+ *
+ * @see struct rte_dmadev_conf::silent_mode
+ */
+
+#define RTE_DMA_DEV_CAPA_FENCE (1ull << 6)
+/**< DMA device support fence.
+ * If device support fence, then application could set a fence flags when
+ * enqueue operation by rte_dma_copy/copy_sg/fill().
+ * If a operation has a fence flags, it means the operation must be processed
+ * only after all previous operations are completed.
+ *
+ * @see struct rte_dmadev_info::dev_capa
+ */
+
+#define RTE_DMA_DEV_CAPA_OPS_COPY (1ull << 32)
+/**< DMA device support copy ops.
+ * This capability start with index of 32, so that it could leave gap between
+ * normal capability and ops capability.
+ *
+ * @see struct rte_dmadev_info::dev_capa
+ */
+
+#define RTE_DMA_DEV_CAPA_OPS_COPY_SG (1ull << 33)
+/**< DMA device support scatter-list copy ops.
+ *
+ * @see struct rte_dmadev_info::dev_capa
+ */
+
+#define RTE_DMA_DEV_CAPA_OPS_FILL (1ull << 34)
+/**< DMA device support fill ops.
+ *
+ * @see struct rte_dmadev_info::dev_capa
+ */
+
+/**
+ * A structure used to retrieve the information of an DMA device.
+ */
+struct rte_dmadev_info {
+ struct rte_device *device; /**< Generic Device information. */
+ uint64_t dev_capa; /**< Device capabilities (RTE_DMA_DEV_CAPA_*). */
+ uint16_t max_vchans;
+ /**< Maximum number of virtual DMA channels supported. */
+ uint16_t max_desc;
+ /**< Maximum allowed number of virtual DMA channel descriptors. */
+ uint16_t min_desc;
+ /**< Minimum allowed number of virtual DMA channel descriptors. */
+ uint16_t nb_vchans; /**< Number of virtual DMA channel configured. */
+};
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Retrieve information of a DMA device.
+ *
+ * @param dev_id
+ * The identifier of the device.
+ * @param[out] dev_info
+ * A pointer to a structure of type *rte_dmadev_info* to be filled with the
+ * information of the device.
+ *
+ * @return
+ * - =0: Success, driver updates the information of the DMA device.
+ * - <0: Error code returned by the driver info get function.
+ *
+ */
+__rte_experimental
+int
+rte_dmadev_info_get(uint16_t dev_id, struct rte_dmadev_info *dev_info);
+
+/**
+ * A structure used to configure a DMA device.
+ */
+struct rte_dmadev_conf {
+ uint16_t max_vchans;
+ /**< Maximum number of virtual DMA channel to use.
+ * This value cannot be greater than the field 'max_vchans' of struct
+ * rte_dmadev_info which get from rte_dmadev_info_get().
+ */
+ uint8_t silent_mode;
+ /**< Indicates whether to work in silent mode.
+ * 0-default mode, 1-silent mode.
+ *
+ * @see RTE_DMA_DEV_CAPA_SILENT
+ */
+};
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Configure a DMA device.
+ *
+ * This function must be invoked first before any other function in the
+ * API. This function can also be re-invoked when a device is in the
+ * stopped state.
+ *
+ * @param dev_id
+ * The identifier of the device to configure.
+ * @param dev_conf
+ * The DMA device configuration structure encapsulated into rte_dmadev_conf
+ * object.
+ *
+ * @return
+ * - =0: Success, device configured.
+ * - <0: Error code returned by the driver configuration function.
+ */
+__rte_experimental
+int
+rte_dmadev_configure(uint16_t dev_id, const struct rte_dmadev_conf *dev_conf);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Start a DMA device.
+ *
+ * The device start step is the last one and consists of setting the DMA
+ * to start accepting jobs.
+ *
+ * @param dev_id
+ * The identifier of the device.
+ *
+ * @return
+ * - =0: Success, device started.
+ * - <0: Error code returned by the driver start function.
+ */
+__rte_experimental
+int
+rte_dmadev_start(uint16_t dev_id);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Stop a DMA device.
+ *
+ * The device can be restarted with a call to rte_dmadev_start().
+ *
+ * @param dev_id
+ * The identifier of the device.
+ *
+ * @return
+ * - =0: Success, device stopped.
+ * - <0: Error code returned by the driver stop function.
+ */
+__rte_experimental
+int
+rte_dmadev_stop(uint16_t dev_id);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Close a DMA device.
+ *
+ * The device cannot be restarted after this call.
+ *
+ * @param dev_id
+ * The identifier of the device.
+ *
+ * @return
+ * - =0: Successfully close device
+ * - <0: Failure to close device
+ */
+__rte_experimental
+int
+rte_dmadev_close(uint16_t dev_id);
+
+/* DMA transfer direction defines. */
+#define RTE_DMA_DIR_MEM_TO_MEM (1ull << 0)
+/**< DMA transfer direction - from memory to memory.
+ *
+ * @see struct rte_dmadev_vchan_conf::direction
+ */
+
+#define RTE_DMA_DIR_MEM_TO_DEV (1ull << 1)
+/**< DMA transfer direction - from memory to device.
+ * In a typical scenario, ARM SoCs are installed on x86 servers as iNICs
+ * through the PCIE interface. In this case, the ARM SoCs works in EP(endpoint)
+ * mode, it could initiate a DMA move request from memory (which is ARM memory)
+ * to device (which is x86 host memory).
+ *
+ * @see struct rte_dmadev_vchan_conf::direction
+ */
+
+#define RTE_DMA_DIR_DEV_TO_MEM (1ull << 2)
+/**< DMA transfer direction - from device to memory.
+ * In a typical scenario, ARM SoCs are installed on x86 servers as iNICs
+ * through the PCIE interface. In this case, the ARM SoCs works in EP(endpoint)
+ * mode, it could initiate a DMA move request from device (which is x86 host
+ * memory) to memory (which is ARM memory).
+ *
+ * @see struct rte_dmadev_vchan_conf::direction
+ */
+
+#define RTE_DMA_DIR_DEV_TO_DEV (1ull << 3)
+/**< DMA transfer direction - from device to device.
+ * In a typical scenario, ARM SoCs are installed on x86 servers as iNICs
+ * through the PCIE interface. In this case, the ARM SoCs works in EP(endpoint)
+ * mode, it could initiate a DMA move request from device (which is x86 host
+ * memory) to device (which is another x86 host memory).
+ *
+ * @see struct rte_dmadev_vchan_conf::direction
+ */
+
+/**
+ * enum rte_dmadev_port_type - DMA port type defines
+ * When
+ */
+enum rte_dmadev_port_type {
+ RTE_DMADEV_PORT_PCIE = 1,
+};
+
+/**
+ * A structure used to descript DMA port parameters.
+ */
+struct rte_dmadev_port_param {
+ enum rte_dmadev_port_type port_type; /**< The device port type. */
+ union {
+ /** For PCIE port:
+ *
+ * The following model show SoC's PCIE module connects to
+ * multiple PCIE hosts and multiple endpoints. The PCIE module
+ * has an integrate DMA controller.
+ * If the DMA wants to access the memory of host A, it can be
+ * initiated by PF1 in core0, or by VF0 of PF0 in core0.
+ *
+ * System Bus
+ * | ----------PCIE module----------
+ * | Bus
+ * | Interface
+ * | ----- ------------------
+ * | | | | PCIE Core0 |
+ * | | | | | -----------
+ * | | | | PF-0 -- VF-0 | | Host A |
+ * | | |--------| |- VF-1 |--------| Root |
+ * | | | | PF-1 | | Complex |
+ * | | | | PF-2 | -----------
+ * | | | ------------------
+ * | | |
+ * | | | ------------------
+ * | | | | PCIE Core1 |
+ * | | | | | -----------
+ * | | | | PF-0 -- VF-0 | | Host B |
+ * |-----| |--------| PF-1 -- VF-0 |--------| Root |
+ * | | | | |- VF-1 | | Complex |
+ * | | | | PF-2 | -----------
+ * | | | ------------------
+ * | | |
+ * | | | ------------------
+ * | |DMA| | | ------
+ * | | | | |--------| EP |
+ * | | |--------| PCIE Core2 | ------
+ * | | | | | ------
+ * | | | | |--------| EP |
+ * | | | | | ------
+ * | ----- ------------------
+ *
+ * The following structure is used to describe the above access
+ * port.
+ *
+ * @note If some fields are not supported by hardware, set
+ * these fields to zero. And also there are no capabilities
+ * defined for this, it is the duty of the application to set
+ * the correct parameters.
+ */
+ struct {
+ uint64_t coreid : 4; /**< PCIE core id used. */
+ uint64_t pfid : 8; /**< PF id used. */
+ uint64_t vfen : 1; /**< VF enable bit. */
+ uint64_t vfid : 16; /**< VF id used. */
+ uint64_t pasid : 20;
+ /**< The pasid filed in TLP packet. */
+ uint64_t attr : 3;
+ /**< The attributes filed in TLP packet. */
+ uint64_t ph : 2;
+ /**< The processing hint filed in TLP packet. */
+ uint64_t st : 16;
+ /**< The steering tag filed in TLP packet. */
+ } pcie;
+ };
+ uint64_t reserved[2]; /**< Reserved for future fields. */
+};
+
+/**
+ * A structure used to configure a virtual DMA channel.
+ */
+struct rte_dmadev_vchan_conf {
+ uint8_t direction;
+ /**< Set of supported transfer directions
+ * @see RTE_DMA_DIR_MEM_TO_MEM
+ * @see RTE_DMA_DIR_MEM_TO_DEV
+ * @see RTE_DMA_DIR_DEV_TO_MEM
+ * @see RTE_DMA_DIR_DEV_TO_DEV
+ */
+
+ /** Number of descriptor for the virtual DMA channel */
+ uint16_t nb_desc;
+ /** 1) Used to describes the port parameter in the device-to-memory
+ * transfer scenario.
+ * 2) Used to describes the source port parameter in the
+ * device-to-device transfer scenario.
+ * @see struct rte_dmadev_port_param
+ */
+ struct rte_dmadev_port_param src_port;
+ /** 1) Used to describes the port parameter in the memory-to-device
+ * transfer scenario.
+ * 2) Used to describes the destination port parameter in the
+ * device-to-device transfer scenario.
+ * @see struct rte_dmadev_port_param
+ */
+ struct rte_dmadev_port_param dst_port;
+};
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Allocate and set up a virtual DMA channel.
+ *
+ * @param dev_id
+ * The identifier of the device.
+ * @param conf
+ * The virtual DMA channel configuration structure encapsulated into
+ * rte_dmadev_vchan_conf object.
+ *
+ * @return
+ * - >=0: Allocate success, it is the virtual DMA channel id. This value must
+ * be less than the field 'max_vchans' of struct rte_dmadev_conf
+ * which configured by rte_dmadev_configure().
+ * - <0: Error code returned by the driver virtual channel setup function.
+ */
+__rte_experimental
+int
+rte_dmadev_vchan_setup(uint16_t dev_id,
+ const struct rte_dmadev_vchan_conf *conf);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Release a virtual DMA channel.
+ *
+ * @param dev_id
+ * The identifier of the device.
+ * @param vchan
+ * The identifier of virtual DMA channel which return by vchan setup.
+ *
+ * @return
+ * - =0: Successfully release the virtual DMA channel.
+ * - <0: Error code returned by the driver virtual channel release function.
+ */
+__rte_experimental
+int
+rte_dmadev_vchan_release(uint16_t dev_id, uint16_t vchan);
+
+/**
+ * rte_dmadev_stats - running statistics.
+ */
+struct rte_dmadev_stats {
+ uint64_t submitted_count;
+ /**< Count of operations which were submitted to hardware. */
+ uint64_t completed_fail_count;
+ /**< Count of operations which failed to complete. */
+ uint64_t completed_count;
+ /**< Count of operations which successfully complete. */
+};
+
+#define RTE_DMADEV_ALL_VCHAN 0xFFFFu
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Retrieve basic statistics of a or all virtual DMA channel(s).
+ *
+ * @param dev_id
+ * The identifier of the device.
+ * @param vchan
+ * The identifier of virtual DMA channel.
+ * If equal RTE_DMADEV_ALL_VCHAN means all channels.
+ * @param[out] stats
+ * The basic statistics structure encapsulated into rte_dmadev_stats
+ * object.
+ *
+ * @return
+ * - =0: Successfully retrieve stats.
+ * - <0: Failure to retrieve stats.
+ */
+__rte_experimental
+int
+rte_dmadev_stats_get(uint16_t dev_id, uint16_t vchan,
+ struct rte_dmadev_stats *stats);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Reset basic statistics of a or all virtual DMA channel(s).
+ *
+ * @param dev_id
+ * The identifier of the device.
+ * @param vchan
+ * The identifier of virtual DMA channel.
+ * If equal RTE_DMADEV_ALL_VCHAN means all channels.
+ *
+ * @return
+ * - =0: Successfully reset stats.
+ * - <0: Failure to reset stats.
+ */
+__rte_experimental
+int
+rte_dmadev_stats_reset(uint16_t dev_id, uint16_t vchan);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Dump DMA device info.
+ *
+ * @param dev_id
+ * The identifier of the device.
+ * @param f
+ * The file to write the output to.
+ *
+ * @return
+ * 0 on success. Non-zero otherwise.
+ */
+__rte_experimental
+int
+rte_dmadev_dump(uint16_t dev_id, FILE *f);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Trigger the dmadev self test.
+ *
+ * @param dev_id
+ * The identifier of the device.
+ *
+ * @return
+ * - 0: Selftest successful.
+ * - -ENOTSUP if the device doesn't support selftest
+ * - other values < 0 on failure.
+ */
+__rte_experimental
+int
+rte_dmadev_selftest(uint16_t dev_id);
+
+/**
+ * rte_dma_status_code - DMA transfer result status code defines
+ */
+enum rte_dma_status_code {
+ RTE_DMA_STATUS_SUCCESSFUL = 0,
+ /**< The operation completed successfully. */
+ RTE_DMA_STATUS_USRER_ABORT,
+ /**< The operation failed to complete due abort by user.
+ * This is mainly used when processing dev_stop, user could modidy the
+ * descriptors (e.g. change one bit to tell hardware abort this job),
+ * it allows outstanding requests to be complete as much as possible,
+ * so reduce the time to stop the device.
+ */
+ RTE_DMA_STATUS_NOT_ATTEMPTED,
+ /**< The operation failed to complete due to following scenarios:
+ * The jobs in a particular batch are not attempted because they
+ * appeared after a fence where a previous job failed. In some HW
+ * implementation it's possible for jobs from later batches would be
+ * completed, though, so report the status from the not attempted jobs
+ * before reporting those newer completed jobs.
+ */
+ RTE_DMA_STATUS_INVALID_SRC_ADDR,
+ /**< The operation failed to complete due invalid source address. */
+ RTE_DMA_STATUS_INVALID_DST_ADDR,
+ /**< The operation failed to complete due invalid destination
+ * address.
+ */
+ RTE_DMA_STATUS_INVALID_LENGTH,
+ /**< The operation failed to complete due invalid length. */
+ RTE_DMA_STATUS_INVALID_OPCODE,
+ /**< The operation failed to complete due invalid opcode.
+ * The DMA descriptor could have multiple format, which are
+ * distinguished by the opcode field.
+ */
+ RTE_DMA_STATUS_BUS_ERROR,
+ /**< The operation failed to complete due bus err. */
+ RTE_DMA_STATUS_DATA_POISION,
+ /**< The operation failed to complete due data poison. */
+ RTE_DMA_STATUS_DESCRIPTOR_READ_ERROR,
+ /**< The operation failed to complete due descriptor read error. */
+ RTE_DMA_STATUS_DEV_LINK_ERROR,
+ /**< The operation failed to complete due device link error.
+ * Used to indicates that the link error in the memory-to-device/
+ * device-to-memory/device-to-device transfer scenario.
+ */
+ RTE_DMA_STATUS_UNKNOWN = 0x100,
+ /**< The operation failed to complete due unknown reason.
+ * The initial value is 256, which reserves space for future errors.
+ */
+};
+
+/**
+ * rte_dmadev_sge - can hold scatter DMA operation request entry
+ */
+struct rte_dmadev_sge {
+ rte_iova_t addr;
+ uint32_t length;
+};
+
+/**
+ * rte_dmadev_sg - can hold scatter DMA operation request
+ */
+struct rte_dmadev_sg {
+ struct rte_dmadev_sge *src;
+ struct rte_dmadev_sge *dst;
+ uint16_t nb_src; /**< The number of src entry */
+ uint16_t nb_dst; /**< The number of dst entry */
+};
+
+#include "rte_dmadev_core.h"
+
+/* DMA flags to augment operation preparation. */
+#define RTE_DMA_OP_FLAG_FENCE (1ull << 0)
+/**< DMA fence flag.
+ * It means the operation with this flag must be processed only after all
+ * previous operations are completed.
+ *
+ * @see rte_dmadev_copy()
+ * @see rte_dmadev_copy_sg()
+ * @see rte_dmadev_fill()
+ */
+
+#define RTE_DMA_OP_FLAG_SUBMIT (1ull << 1)
+/**< DMA submit flag.
+ * It means the operation with this flag must issue doorbell to hardware after
+ * enqueued jobs.
+ */
+
+#define RTE_DMA_OP_FLAG_LLC (1ull << 2)
+/**< DMA write data to low level cache hint.
+ * This just a hint, and there is no capability bit for this, driver should not
+ * return error if this flag was set.
+ */
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Enqueue a copy operation onto the virtual DMA channel.
+ *
+ * This queues up a copy operation to be performed by hardware, if the 'flags'
+ * parameter contains RTE_DMA_OP_FLAG_SUBMIT then trigger hardware to begin
+ * this operation, otherwise do not trigger hardware.
+ *
+ * @param dev_id
+ * The identifier of the device.
+ * @param vchan
+ * The identifier of virtual DMA channel.
+ * @param src
+ * The address of the source buffer.
+ * @param dst
+ * The address of the destination buffer.
+ * @param length
+ * The length of the data to be copied.
+ * @param flags
+ * An flags for this operation.
+ * @see RTE_DMA_OP_FLAG_*
+ *
+ * @return
+ * - 0..UINT16_MAX: index of enqueued copy job.
+ * - <0: Error code returned by the driver copy function.
+ */
+__rte_experimental
+static inline int
+rte_dmadev_copy(uint16_t dev_id, uint16_t vchan, rte_iova_t src, rte_iova_t dst,
+ uint32_t length, uint64_t flags)
+{
+ struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+
+#ifdef RTE_DMADEV_DEBUG
+ if (!rte_dmadev_is_valid_dev(dev_id) ||
+ vchan >= dev->data->dev_conf.max_vchans)
+ return -EINVAL;
+ RTE_FUNC_PTR_OR_ERR_RET(*dev->copy, -ENOTSUP);
+#endif
+
+ return (*dev->copy)(dev, vchan, src, dst, length, flags);
+}
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Enqueue a scatter list copy operation onto the virtual DMA channel.
+ *
+ * This queues up a scatter list copy operation to be performed by hardware, if
+ * the 'flags' parameter contains RTE_DMA_OP_FLAG_SUBMIT then trigger hardware
+ * to begin this operation, otherwise do not trigger hardware.
+ *
+ * @param dev_id
+ * The identifier of the device.
+ * @param vchan
+ * The identifier of virtual DMA channel.
+ * @param sg
+ * The pointer of scatterlist.
+ * @param flags
+ * An flags for this operation.
+ * @see RTE_DMA_OP_FLAG_*
+ *
+ * @return
+ * - 0..UINT16_MAX: index of enqueued copy scatterlist job.
+ * - <0: Error code returned by the driver copy scatterlist function.
+ */
+__rte_experimental
+static inline int
+rte_dmadev_copy_sg(uint16_t dev_id, uint16_t vchan,
+ const struct rte_dmadev_sg *sg,
+ uint64_t flags)
+{
+ struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+
+#ifdef RTE_DMADEV_DEBUG
+ if (!rte_dmadev_is_valid_dev(dev_id) ||
+ vchan >= dev->data->dev_conf.max_vchans ||
+ sg == NULL || sg->src == NULL || sg->dst == NULL ||
+ sg->nb_src == 0 || sg->nb_dst == 0)
+ return -EINVAL;
+ RTE_FUNC_PTR_OR_ERR_RET(*dev->copy_sg, -ENOTSUP);
+#endif
+
+ return (*dev->copy_sg)(dev, vchan, sg, flags);
+}
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Enqueue a fill operation onto the virtual DMA channel.
+ *
+ * This queues up a fill operation to be performed by hardware, if the 'flags'
+ * parameter contains RTE_DMA_OP_FLAG_SUBMIT then trigger hardware to begin
+ * this operation, otherwise do not trigger hardware.
+ *
+ * @param dev_id
+ * The identifier of the device.
+ * @param vchan
+ * The identifier of virtual DMA channel.
+ * @param pattern
+ * The pattern to populate the destination buffer with.
+ * @param dst
+ * The address of the destination buffer.
+ * @param length
+ * The length of the destination buffer.
+ * @param flags
+ * An flags for this operation.
+ * @see RTE_DMA_OP_FLAG_*
+ *
+ * @return
+ * - 0..UINT16_MAX: index of enqueued fill job.
+ * - <0: Error code returned by the driver fill function.
+ */
+__rte_experimental
+static inline int
+rte_dmadev_fill(uint16_t dev_id, uint16_t vchan, uint64_t pattern,
+ rte_iova_t dst, uint32_t length, uint64_t flags)
+{
+ struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+
+#ifdef RTE_DMADEV_DEBUG
+ if (!rte_dmadev_is_valid_dev(dev_id) ||
+ vchan >= dev->data->dev_conf.max_vchans)
+ return -EINVAL;
+ RTE_FUNC_PTR_OR_ERR_RET(*dev->fill, -ENOTSUP);
+#endif
+
+ return (*dev->fill)(dev, vchan, pattern, dst, length, flags);
+}
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Trigger hardware to begin performing enqueued operations.
+ *
+ * This API is used to write the "doorbell" to the hardware to trigger it
+ * to begin the operations previously enqueued by rte_dmadev_copy/fill().
+ *
+ * @param dev_id
+ * The identifier of the device.
+ * @param vchan
+ * The identifier of virtual DMA channel.
+ *
+ * @return
+ * - =0: Successfully trigger hardware.
+ * - <0: Failure to trigger hardware.
+ */
+__rte_experimental
+static inline int
+rte_dmadev_submit(uint16_t dev_id, uint16_t vchan)
+{
+ struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+
+#ifdef RTE_DMADEV_DEBUG
+ if (!rte_dmadev_is_valid_dev(dev_id) ||
+ vchan >= dev->data->dev_conf.max_vchans)
+ return -EINVAL;
+ RTE_FUNC_PTR_OR_ERR_RET(*dev->submit, -ENOTSUP);
+#endif
+
+ return (*dev->submit)(dev, vchan);
+}
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Returns the number of operations that have been successfully completed.
+ *
+ * @param dev_id
+ * The identifier of the device.
+ * @param vchan
+ * The identifier of virtual DMA channel.
+ * @param nb_cpls
+ * The maximum number of completed operations that can be processed.
+ * @param[out] last_idx
+ * The last completed operation's index.
+ * If not required, NULL can be passed in.
+ * @param[out] has_error
+ * Indicates if there are transfer error.
+ * If not required, NULL can be passed in.
+ *
+ * @return
+ * The number of operations that successfully completed. This return value
+ * must be less than or equal to the value of nb_cpls.
+ */
+__rte_experimental
+static inline uint16_t
+rte_dmadev_completed(uint16_t dev_id, uint16_t vchan, const uint16_t nb_cpls,
+ uint16_t *last_idx, bool *has_error)
+{
+ struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+ uint16_t idx;
+ bool err;
+
+#ifdef RTE_DMADEV_DEBUG
+ if (!rte_dmadev_is_valid_dev(dev_id) ||
+ vchan >= dev->data->dev_conf.max_vchans ||
+ nb_cpls == 0)
+ return 0;
+ RTE_FUNC_PTR_OR_ERR_RET(*dev->completed, 0);
+#endif
+
+ /* Ensure the pointer values are non-null to simplify drivers.
+ * In most cases these should be compile time evaluated, since this is
+ * an inline function.
+ * - If NULL is explicitly passed as parameter, then compiler knows the
+ * value is NULL
+ * - If address of local variable is passed as parameter, then compiler
+ * can know it's non-NULL.
+ */
+ if (last_idx == NULL)
+ last_idx = &idx;
+ if (has_error == NULL)
+ has_error = &err;
+
+ *has_error = false;
+ return (*dev->completed)(dev, vchan, nb_cpls, last_idx, has_error);
+}
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Returns the number of operations that have been completed, and the
+ * operations result may succeed or fail.
+ *
+ * @param dev_id
+ * The identifier of the device.
+ * @param vchan
+ * The identifier of virtual DMA channel.
+ * @param nb_cpls
+ * Indicates the size of status array.
+ * @param[out] last_idx
+ * The last completed operation's index.
+ * If not required, NULL can be passed in.
+ * @param[out] status
+ * The error code of operations that completed.
+ * @see enum rte_dma_status_code
+ *
+ * @return
+ * The number of operations that completed. This return value must be less
+ * than or equal to the value of nb_cpls.
+ */
+__rte_experimental
+static inline uint16_t
+rte_dmadev_completed_status(uint16_t dev_id, uint16_t vchan,
+ const uint16_t nb_cpls, uint16_t *last_idx,
+ enum rte_dma_status_code *status)
+{
+ struct rte_dmadev *dev = &rte_dmadevices[dev_id];
+ uint16_t idx;
+
+#ifdef RTE_DMADEV_DEBUG
+ if (!rte_dmadev_is_valid_dev(dev_id) ||
+ vchan >= dev->data->dev_conf.max_vchans ||
+ nb_cpls == 0 || status == NULL)
+ return 0;
+ RTE_FUNC_PTR_OR_ERR_RET(*dev->completed_status, 0);
+#endif
+
+ if (last_idx == NULL)
+ last_idx = &idx;
+
+ return (*dev->completed_status)(dev, vchan, nb_cpls, last_idx, status);
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_DMADEV_H_ */
new file mode 100644
@@ -0,0 +1,182 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2021 HiSilicon Limited.
+ * Copyright(c) 2021 Intel Corporation.
+ */
+
+#ifndef _RTE_DMADEV_CORE_H_
+#define _RTE_DMADEV_CORE_H_
+
+/**
+ * @file
+ *
+ * RTE DMA Device internal header.
+ *
+ * This header contains internal data types, that are used by the DMA devices
+ * in order to expose their ops to the class.
+ *
+ * Applications should not use these API directly.
+ *
+ */
+
+struct rte_dmadev;
+
+typedef int (*rte_dmadev_info_get_t)(const struct rte_dmadev *dev,
+ struct rte_dmadev_info *dev_info,
+ uint32_t info_sz);
+/** @internal Used to get device information of a device. */
+
+typedef int (*rte_dmadev_configure_t)(struct rte_dmadev *dev,
+ const struct rte_dmadev_conf *dev_conf);
+/** @internal Used to configure a device. */
+
+typedef int (*rte_dmadev_start_t)(struct rte_dmadev *dev);
+/** @internal Used to start a configured device. */
+
+typedef int (*rte_dmadev_stop_t)(struct rte_dmadev *dev);
+/** @internal Used to stop a configured device. */
+
+typedef int (*rte_dmadev_close_t)(struct rte_dmadev *dev);
+/** @internal Used to close a configured device. */
+
+typedef int (*rte_dmadev_vchan_setup_t)(struct rte_dmadev *dev,
+ const struct rte_dmadev_vchan_conf *conf);
+/** @internal Used to allocate and set up a virtual DMA channel. */
+
+typedef int (*rte_dmadev_vchan_release_t)(struct rte_dmadev *dev,
+ uint16_t vchan);
+/** @internal Used to release a virtual DMA channel. */
+
+typedef int (*rte_dmadev_stats_get_t)(const struct rte_dmadev *dev,
+ uint16_t vchan, struct rte_dmadev_stats *stats,
+ uint32_t stats_sz);
+/** @internal Used to retrieve basic statistics. */
+
+typedef int (*rte_dmadev_stats_reset_t)(struct rte_dmadev *dev, uint16_t vchan);
+/** @internal Used to reset basic statistics. */
+
+typedef int (*rte_dmadev_dump_t)(const struct rte_dmadev *dev, FILE *f);
+/** @internal Used to dump internal information. */
+
+typedef int (*rte_dmadev_selftest_t)(uint16_t dev_id);
+/** @internal Used to start dmadev selftest. */
+
+typedef int (*rte_dmadev_copy_t)(struct rte_dmadev *dev, uint16_t vchan,
+ rte_iova_t src, rte_iova_t dst,
+ uint32_t length, uint64_t flags);
+/** @internal Used to enqueue a copy operation. */
+
+typedef int (*rte_dmadev_copy_sg_t)(struct rte_dmadev *dev, uint16_t vchan,
+ const struct rte_dmadev_sg *sg,
+ uint64_t flags);
+/** @internal Used to enqueue a scatter list copy operation. */
+
+typedef int (*rte_dmadev_fill_t)(struct rte_dmadev *dev, uint16_t vchan,
+ uint64_t pattern, rte_iova_t dst,
+ uint32_t length, uint64_t flags);
+/** @internal Used to enqueue a fill operation. */
+
+typedef int (*rte_dmadev_submit_t)(struct rte_dmadev *dev, uint16_t vchan);
+/** @internal Used to trigger hardware to begin working. */
+
+typedef uint16_t (*rte_dmadev_completed_t)(struct rte_dmadev *dev,
+ uint16_t vchan, const uint16_t nb_cpls,
+ uint16_t *last_idx, bool *has_error);
+/** @internal Used to return number of successful completed operations. */
+
+typedef uint16_t (*rte_dmadev_completed_status_t)(struct rte_dmadev *dev,
+ uint16_t vchan, const uint16_t nb_cpls,
+ uint16_t *last_idx, enum rte_dma_status_code *status);
+/** @internal Used to return number of completed operations. */
+
+/**
+ * Possible states of a DMA device.
+ */
+enum rte_dmadev_state {
+ RTE_DMADEV_UNUSED = 0,
+ /**< Device is unused before being probed. */
+ RTE_DMADEV_ATTACHED,
+ /**< Device is attached when allocated in probing. */
+};
+
+/**
+ * DMA device operations function pointer table
+ */
+struct rte_dmadev_ops {
+ rte_dmadev_info_get_t dev_info_get;
+ rte_dmadev_configure_t dev_configure;
+ rte_dmadev_start_t dev_start;
+ rte_dmadev_stop_t dev_stop;
+ rte_dmadev_close_t dev_close;
+ rte_dmadev_vchan_setup_t vchan_setup;
+ rte_dmadev_vchan_release_t vchan_release;
+ rte_dmadev_stats_get_t stats_get;
+ rte_dmadev_stats_reset_t stats_reset;
+ rte_dmadev_dump_t dev_dump;
+ rte_dmadev_selftest_t dev_selftest;
+};
+
+/**
+ * @internal
+ * The data part, with no function pointers, associated with each DMA device.
+ *
+ * This structure is safe to place in shared memory to be common among different
+ * processes in a multi-process configuration.
+ */
+struct rte_dmadev_data {
+ void *dev_private;
+ /**< PMD-specific private data.
+ * This is a copy of the 'dev_private' field in the 'struct rte_dmadev'
+ * from primary process, it is used by the secondary process to get
+ * dev_private information.
+ */
+ uint16_t dev_id; /**< Device [external] identifier. */
+ char dev_name[RTE_DMADEV_NAME_MAX_LEN]; /**< Unique identifier name */
+ struct rte_dmadev_conf dev_conf; /**< DMA device configuration. */
+ uint8_t dev_started : 1; /**< Device state: STARTED(1)/STOPPED(0). */
+ uint64_t reserved[2]; /**< Reserved for future fields */
+} __rte_cache_aligned;
+
+/**
+ * @internal
+ * The generic data structure associated with each DMA device.
+ *
+ * The dataplane APIs are located at the beginning of the structure, along
+ * with the pointer to where all the data elements for the particular device
+ * are stored in shared memory. This split scheme allows the function pointer
+ * and driver data to be per-process, while the actual configuration data for
+ * the device is shared.
+ * And the 'dev_private' field was placed in the first cache line to optimize
+ * performance because the PMD driver mainly depends on this field.
+ */
+struct rte_dmadev {
+ rte_dmadev_copy_t copy;
+ rte_dmadev_copy_sg_t copy_sg;
+ rte_dmadev_fill_t fill;
+ rte_dmadev_submit_t submit;
+ rte_dmadev_completed_t completed;
+ rte_dmadev_completed_status_t completed_status;
+ void *reserved_ptr; /**< Reserved for future IO function. */
+ void *dev_private;
+ /**< PMD-specific private data.
+ * If is the primary process, after dmadev allocated by
+ * rte_dmadev_pmd_allocate(), the PCI/SoC device probing should
+ * initialize this field, and copy it's value to the 'dev_private'
+ * field of 'struct rte_dmadev_data' which pointer by 'data' filed.
+ * If is the secondary process, dmadev framework will initialize this
+ * field by copy from 'dev_private' field of 'struct rte_dmadev_data'
+ * which initialized by primary process.
+ * It's the primary process responsibility to deinitialize this field
+ * after invoke rte_dmadev_pmd_release() in the PCI/SoC device removing
+ * stage.
+ */
+ struct rte_dmadev_data *data; /**< Pointer to device data. */
+ const struct rte_dmadev_ops *dev_ops; /**< Functions exported by PMD. */
+ struct rte_device *device;
+ /**< Device info which supplied during device initialization. */
+ enum rte_dmadev_state state; /**< Flag indicating the device state. */
+ uint64_t reserved[2]; /**< Reserved for future fields. */
+} __rte_cache_aligned;
+
+extern struct rte_dmadev rte_dmadevices[];
+
+#endif /* _RTE_DMADEV_CORE_H_ */
new file mode 100644
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2021 HiSilicon Limited.
+ */
+
+#ifndef _RTE_DMADEV_PMD_H_
+#define _RTE_DMADEV_PMD_H_
+
+/**
+ * @file
+ *
+ * RTE DMA Device PMD APIs
+ *
+ * Driver facing APIs for a DMA device. These are not to be called directly by
+ * any application.
+ */
+
+#include "rte_dmadev.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/**
+ * @internal
+ * Allocates a new dmadev slot for an DMA device and returns the pointer
+ * to that slot for the driver to use.
+ *
+ * @param name
+ * DMA device name.
+ *
+ * @return
+ * A pointer to the DMA device slot case of success,
+ * NULL otherwise.
+ */
+__rte_internal
+struct rte_dmadev *
+rte_dmadev_pmd_allocate(const char *name);
+
+/**
+ * @internal
+ * Release the specified dmadev.
+ *
+ * @param dev
+ * Device to be released.
+ *
+ * @return
+ * - 0 on success, negative on error
+ */
+__rte_internal
+int
+rte_dmadev_pmd_release(struct rte_dmadev *dev);
+
+/**
+ * @internal
+ * Return the DMA device based on the device name.
+ *
+ * @param name
+ * DMA device name.
+ *
+ * @return
+ * A pointer to the DMA device slot case of success,
+ * NULL otherwise.
+ */
+__rte_internal
+struct rte_dmadev *
+rte_dmadev_get_device_by_name(const char *name);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_DMADEV_PMD_H_ */
new file mode 100644
@@ -0,0 +1,37 @@
+EXPERIMENTAL {
+ global:
+
+ rte_dmadev_close;
+ rte_dmadev_completed;
+ rte_dmadev_completed_status;
+ rte_dmadev_configure;
+ rte_dmadev_copy;
+ rte_dmadev_copy_sg;
+ rte_dmadev_count;
+ rte_dmadev_dump;
+ rte_dmadev_fill;
+ rte_dmadev_info_get;
+ rte_dmadev_is_valid_dev;
+ rte_dmadev_selftest;
+ rte_dmadev_start;
+ rte_dmadev_stats_get;
+ rte_dmadev_stats_reset;
+ rte_dmadev_stop;
+ rte_dmadev_submit;
+ rte_dmadev_vchan_release;
+ rte_dmadev_vchan_setup;
+
+ local: *;
+};
+
+INTERNAL {
+ global:
+
+ rte_dmadevices;
+ rte_dmadev_get_device_by_name;
+ rte_dmadev_pmd_allocate;
+ rte_dmadev_pmd_release;
+
+ local: *;
+};
+
@@ -60,6 +60,7 @@ libraries = [
'bpf',
'graph',
'node',
+ 'dmadev',
]
if is_windows