diff --git a/doc/guides/prog_guide/bbdev.rst b/doc/guides/prog_guide/bbdev.rst index 70fa01ada5..72d14a8aeb 100644 --- a/doc/guides/prog_guide/bbdev.rst +++ b/doc/guides/prog_guide/bbdev.rst @@ -1118,6 +1118,111 @@ Figure :numref:`figure_turbo_tb_decode` above showing the Turbo decoding of CBs using BBDEV interface in TB-mode is also valid for LDPC decode. +BBDEV FFT Operation +~~~~~~~~~~~~~~~~~~~ + +This operation allows to run a combination of DFT and/or IDFT and/or time-domain windowing. +These can be used in a modular fashion (using bypass modes) or as a processing pipeline +which can be used for FFT-based baseband signal processing. + +In more details it allows : + +* to process the data first through an IDFT of adjustable size and padding; +* to perform the windowing as a programmable cyclic shift offset of the data + followed by a pointwise multiplication by a time domain window; +* to process the related data through a DFT of adjustable size and + de-padding for each such cyclic shift output. + +A flexible number of Rx antennas are being processed in parallel with the same configuration. +The API allows more generally for flexibility in what the PMD may support (capability flags) and +flexibility to adjust some of the parameters of the processing. + +The operation/capability flags that can be set for each FFT operation are given below. + + **NOTE:** The actual operation flags that may be used with a specific + bbdev PMD are dependent on the driver capabilities as reported via + ``rte_bbdev_info_get()``, and may be a subset of those below. + ++--------------------------------------------------------------------+ +|Description of FFT capability flags | ++====================================================================+ +|RTE_BBDEV_FFT_WINDOWING | +| Set to enable/support windowing in time domain | ++--------------------------------------------------------------------+ +|RTE_BBDEV_FFT_CS_ADJUSTMENT | +| Set to enable/support the cyclic shift time offset adjustment | ++--------------------------------------------------------------------+ +|RTE_BBDEV_FFT_DFT_BYPASS | +| Set to bypass the DFT and use directly the IDFT as an option | ++--------------------------------------------------------------------+ +|RTE_BBDEV_FFT_IDFT_BYPASS | +| Set to bypass the IDFT and use directly the DFT as an option | ++--------------------------------------------------------------------+ +|RTE_BBDEV_FFT_WINDOWING_BYPASS | +| Set to bypass the time domain windowing as an option | ++--------------------------------------------------------------------+ +|RTE_BBDEV_FFT_POWER_MEAS | +| Set to provide an optional power measurement of the DFT output | ++--------------------------------------------------------------------+ +|RTE_BBDEV_FFT_FP16_INPUT | +| Set if the input data shall use FP16 format instead of INT16 | ++--------------------------------------------------------------------+ +|RTE_BBDEV_FFT_FP16_OUTPUT | +| Set if the output data shall use FP16 format instead of INT16 | ++--------------------------------------------------------------------+ + +The FFT parameters are set out in the table below. + ++-------------------------+--------------------------------------------------------------+ +|Parameter |Description | ++=========================+==============================================================+ +|base_input |input data | ++-------------------------+--------------------------------------------------------------+ +|base_output |output data | ++-------------------------+--------------------------------------------------------------+ +|power_meas_output |optional output data with power measurement on DFT output | ++-------------------------+--------------------------------------------------------------+ +|op_flags |bitmask of all active operation capabilities | ++-------------------------+--------------------------------------------------------------+ +|input_sequence_size |size of the input sequence in 32-bits points per antenna | ++-------------------------+--------------------------------------------------------------+ +|input_leading_padding |number of points padded at the start of input data | ++-------------------------+--------------------------------------------------------------+ +|output_sequence_size |size of the output sequence per antenna and cyclic shift | ++-------------------------+--------------------------------------------------------------+ +|output_leading_depadding |number of points de-padded at the start of output data | ++-------------------------+--------------------------------------------------------------+ +|window_index |optional windowing profile index used for each cyclic shift | ++-------------------------+--------------------------------------------------------------+ +|cs_bitmap |bitmap of the cyclic shift output requested (LSB for index 0) | ++-------------------------+--------------------------------------------------------------+ +|num_antennas_log2 |number of antennas as a log2 (10 maps to 1024...) | ++-------------------------+--------------------------------------------------------------+ +|idft_log2 |IDFT size as a log2 | ++-------------------------+--------------------------------------------------------------+ +|dft_log2 |DFT size as a log2 | ++-------------------------+--------------------------------------------------------------+ +|cs_time_adjustment |adjustment of time position of all the cyclic shift output | ++-------------------------+--------------------------------------------------------------+ +|idft_shift |shift down of signal level post iDFT | ++-------------------------+--------------------------------------------------------------+ +|dft_shift |shift down of signal level post DFT | ++-------------------------+--------------------------------------------------------------+ +|ncs_reciprocal |inverse of max number of CS normalized to 15b (ie. 231 for 12)| ++-------------------------+--------------------------------------------------------------+ +|power_shift |shift down of level of power measurement when enabled | ++-------------------------+--------------------------------------------------------------+ +|fp16_exp_adjust |value added to FP16 exponent at conversion from INT16 | ++-------------------------+--------------------------------------------------------------+ + +The mbuf input ``base_input`` is mandatory for all bbdev PMDs and +is the incoming data for the processing. Its size may not fit into an actual mbuf, +but the structure is used to pass iova address. +The mbuf output ``output`` is mandatory and is output of the FFT processing chain. +Each point is a complex number of 32bits : +either as 2 INT16 or as 2 FP16 based when the option supported. +The data layout is based on contiguous concatenation of output data +first by cyclic shift then by antenna. Sample code ----------- diff --git a/doc/guides/rel_notes/deprecation.rst b/doc/guides/rel_notes/deprecation.rst index 4d4401788d..9e0d451889 100644 --- a/doc/guides/rel_notes/deprecation.rst +++ b/doc/guides/rel_notes/deprecation.rst @@ -94,10 +94,6 @@ Deprecation Notices ``RTE_ETH_EVENT_IPSEC_SA_BYTE_HARD_EXPIRY`` and ``RTE_ETH_EVENT_IPSEC_SA_PKT_HARD_EXPIRY`` in DPDK 22.11. -* bbdev: Will extend API to support new operation type ``RTE_BBDEV_OP_FFT`` as per - this `RFC `__. - This should be updated in DPDK 22.11. - * cryptodev: The function ``rte_cryptodev_cb_fn`` will be updated to have another parameter ``qp_id`` to return the queue pair ID which got error interrupt to the application, diff --git a/doc/guides/rel_notes/release_22_11.rst b/doc/guides/rel_notes/release_22_11.rst index de3379b897..283d956d42 100644 --- a/doc/guides/rel_notes/release_22_11.rst +++ b/doc/guides/rel_notes/release_22_11.rst @@ -168,6 +168,12 @@ New Features * Added AES-CCM support in lookaside protocol (IPsec) for CN9K & CN10K. * Added AES & DES DOCSIS algorithm support in lookaside crypto for CN9K. +* **Added bbdev operation for FFT processing.** + + Added a new operation type in bbdev for FFT processing with new functions + ``rte_bbdev_enqueue_fft_ops``, ``rte_bbdev_dequeue_fft_ops``, + and related structures. + * **Added eventdev adapter instance get API.** * Added ``rte_event_eth_rx_adapter_instance_get`` to get Rx adapter diff --git a/lib/bbdev/rte_bbdev.c b/lib/bbdev/rte_bbdev.c index d74c68377f..d2380ad2a8 100644 --- a/lib/bbdev/rte_bbdev.c +++ b/lib/bbdev/rte_bbdev.c @@ -24,7 +24,7 @@ #define DEV_NAME "BBDEV" /* Number of supported operation types in *rte_bbdev_op_type*. */ -#define BBDEV_OP_TYPE_COUNT 5 +#define BBDEV_OP_TYPE_COUNT 6 /* BBDev library logging ID */ RTE_LOG_REGISTER_DEFAULT(bbdev_logtype, NOTICE); @@ -852,6 +852,9 @@ get_bbdev_op_size(enum rte_bbdev_op_type type) case RTE_BBDEV_OP_LDPC_ENC: result = sizeof(struct rte_bbdev_enc_op); break; + case RTE_BBDEV_OP_FFT: + result = sizeof(struct rte_bbdev_fft_op); + break; default: break; } @@ -875,6 +878,10 @@ bbdev_op_init(struct rte_mempool *mempool, void *arg, void *element, struct rte_bbdev_enc_op *op = element; memset(op, 0, mempool->elt_size); op->mempool = mempool; + } else if (type == RTE_BBDEV_OP_FFT) { + struct rte_bbdev_fft_op *op = element; + memset(op, 0, mempool->elt_size); + op->mempool = mempool; } } @@ -1125,6 +1132,7 @@ rte_bbdev_op_type_str(enum rte_bbdev_op_type op_type) "RTE_BBDEV_OP_TURBO_ENC", "RTE_BBDEV_OP_LDPC_DEC", "RTE_BBDEV_OP_LDPC_ENC", + "RTE_BBDEV_OP_FFT", }; if (op_type < BBDEV_OP_TYPE_COUNT) diff --git a/lib/bbdev/rte_bbdev.h b/lib/bbdev/rte_bbdev.h index a7dae53aac..0fe41ab8ce 100644 --- a/lib/bbdev/rte_bbdev.h +++ b/lib/bbdev/rte_bbdev.h @@ -401,6 +401,12 @@ typedef uint16_t (*rte_bbdev_enqueue_dec_ops_t)( struct rte_bbdev_dec_op **ops, uint16_t num); +/** @internal Enqueue FFT operations for processing on queue of a device. */ +typedef uint16_t (*rte_bbdev_enqueue_fft_ops_t)( + struct rte_bbdev_queue_data *q_data, + struct rte_bbdev_fft_op **ops, + uint16_t num); + /** @internal Dequeue encode operations from a queue of a device. */ typedef uint16_t (*rte_bbdev_dequeue_enc_ops_t)( struct rte_bbdev_queue_data *q_data, @@ -411,6 +417,11 @@ typedef uint16_t (*rte_bbdev_dequeue_dec_ops_t)( struct rte_bbdev_queue_data *q_data, struct rte_bbdev_dec_op **ops, uint16_t num); +/** @internal Dequeue FFT operations from a queue of a device. */ +typedef uint16_t (*rte_bbdev_dequeue_fft_ops_t)( + struct rte_bbdev_queue_data *q_data, + struct rte_bbdev_fft_op **ops, uint16_t num); + #define RTE_BBDEV_NAME_MAX_LEN 64 /**< Max length of device name */ /** @@ -459,6 +470,10 @@ struct __rte_cache_aligned rte_bbdev { rte_bbdev_dequeue_enc_ops_t dequeue_ldpc_enc_ops; /** Dequeue decode function */ rte_bbdev_dequeue_dec_ops_t dequeue_ldpc_dec_ops; + /** Enqueue FFT function */ + rte_bbdev_enqueue_fft_ops_t enqueue_fft_ops; + /** Dequeue FFT function */ + rte_bbdev_dequeue_fft_ops_t dequeue_fft_ops; const struct rte_bbdev_ops *dev_ops; /**< Functions exported by PMD */ struct rte_bbdev_data *data; /**< Pointer to device data */ enum rte_bbdev_state state; /**< If device is currently used or not */ @@ -591,11 +606,10 @@ rte_bbdev_enqueue_ldpc_dec_ops(uint16_t dev_id, uint16_t queue_id, return dev->enqueue_ldpc_dec_ops(q_data, ops, num_ops); } - /** - * Dequeue a burst of processed encode operations from a queue of the device. - * This functions returns only the current contents of the queue, and does not - * block until @ num_ops is available. + * Enqueue a burst of FFT operations to a queue of the device. + * This functions only enqueues as many operations as currently possible and + * does not block until @p num_ops entries in the queue are available. * This function does not provide any error notification to avoid the * corresponding overhead. * @@ -604,15 +618,46 @@ rte_bbdev_enqueue_ldpc_dec_ops(uint16_t dev_id, uint16_t queue_id, * @param queue_id * The index of the queue. * @param ops - * Pointer array where operations will be dequeued to. Must have at least - * @p num_ops entries - * ie. A pointer to a table of void * pointers (ops) that will be filled. + * Pointer array containing operations to be enqueued. + * Must have at least @p num_ops entries. + * @param num_ops + * The maximum number of operations to enqueue. + * + * @return + * The number of operations actually enqueued. + * (This is the number of processed entries in the @p ops array.) + */ +__rte_experimental +static inline uint16_t +rte_bbdev_enqueue_fft_ops(uint16_t dev_id, uint16_t queue_id, + struct rte_bbdev_fft_op **ops, uint16_t num_ops) +{ + struct rte_bbdev *dev = &rte_bbdev_devices[dev_id]; + struct rte_bbdev_queue_data *q_data = &dev->data->queues[queue_id]; + return dev->enqueue_fft_ops(q_data, ops, num_ops); +} + +/** + * Dequeue a burst of processed encode operations from a queue of the device. + * This functions returns only the current contents of the queue, + * and does not block until @ num_ops is available. + * This function does not provide any error notification to avoid the + * corresponding overhead. + * + * @param dev_id + * The identifier of the device. + * @param queue_id + * The index of the queue. + * @param ops + * Pointer array where operations will be dequeued to. + * Must have at least @p num_ops entries, i.e. + * a pointer to a table of void * pointers (ops) that will be filled. * @param num_ops * The maximum number of operations to dequeue. * * @return - * The number of operations actually dequeued (this is the number of entries - * copied into the @p ops array). + * The number of operations actually dequeued. + * (This is the number of entries copied into the @p ops array.) */ static inline uint16_t rte_bbdev_dequeue_enc_ops(uint16_t dev_id, uint16_t queue_id, @@ -716,6 +761,37 @@ rte_bbdev_dequeue_ldpc_dec_ops(uint16_t dev_id, uint16_t queue_id, return dev->dequeue_ldpc_dec_ops(q_data, ops, num_ops); } +/** + * Dequeue a burst of FFT operations from a queue of the device. + * This functions returns only the current contents of the queue, and does not + * block until @ num_ops is available. + * This function does not provide any error notification to avoid the + * corresponding overhead. + * + * @param dev_id + * The identifier of the device. + * @param queue_id + * The index of the queue. + * @param ops + * Pointer array where operations will be dequeued to. Must have at least + * @p num_ops entries + * @param num_ops + * The maximum number of operations to dequeue. + * + * @return + * The number of operations actually dequeued (this is the number of entries + * copied into the @p ops array). + */ +__rte_experimental +static inline uint16_t +rte_bbdev_dequeue_fft_ops(uint16_t dev_id, uint16_t queue_id, + struct rte_bbdev_fft_op **ops, uint16_t num_ops) +{ + struct rte_bbdev *dev = &rte_bbdev_devices[dev_id]; + struct rte_bbdev_queue_data *q_data = &dev->data->queues[queue_id]; + return dev->dequeue_fft_ops(q_data, ops, num_ops); +} + /** Definitions of device event types */ enum rte_bbdev_event_type { RTE_BBDEV_EVENT_UNKNOWN, /**< unknown event type */ diff --git a/lib/bbdev/rte_bbdev_op.h b/lib/bbdev/rte_bbdev_op.h index 99a7552779..3a00ef76ba 100644 --- a/lib/bbdev/rte_bbdev_op.h +++ b/lib/bbdev/rte_bbdev_op.h @@ -47,6 +47,8 @@ extern "C" { #define RTE_BBDEV_TURBO_MAX_CODE_BLOCKS (64) /* LDPC: Maximum number of Code Blocks in Transport Block.*/ #define RTE_BBDEV_LDPC_MAX_CODE_BLOCKS (256) +/* 12 CS maximum */ +#define RTE_BBDEV_MAX_CS_2 (6) /* * Maximum size to be used to manage the enum rte_bbdev_op_type @@ -218,6 +220,26 @@ enum rte_bbdev_op_ldpcenc_flag_bitmasks { RTE_BBDEV_LDPC_ENC_CONCATENATION = (1ULL << 7) }; +/** Flags for FFT operation and capability structure. */ +enum rte_bbdev_op_fft_flag_bitmasks { + /** Flexible windowing capability. */ + RTE_BBDEV_FFT_WINDOWING = (1ULL << 0), + /** Flexible adjustment of Cyclic Shift time offset. */ + RTE_BBDEV_FFT_CS_ADJUSTMENT = (1ULL << 1), + /** Set for bypass the DFT and get directly into iDFT input. */ + RTE_BBDEV_FFT_DFT_BYPASS = (1ULL << 2), + /** Set for bypass the IDFT and get directly the DFT output. */ + RTE_BBDEV_FFT_IDFT_BYPASS = (1ULL << 3), + /** Set for bypass time domain windowing. */ + RTE_BBDEV_FFT_WINDOWING_BYPASS = (1ULL << 4), + /** Set for optional power measurement on DFT output. */ + RTE_BBDEV_FFT_POWER_MEAS = (1ULL << 5), + /** Set if the input data used FP16 format. */ + RTE_BBDEV_FFT_FP16_INPUT = (1ULL << 6), + /** Set if the output data uses FP16 format. */ + RTE_BBDEV_FFT_FP16_OUTPUT = (1ULL << 7) +}; + /** Flags for the Code Block/Transport block mode */ enum rte_bbdev_op_cb_mode { /** One operation is one or fraction of one transport block */ @@ -696,6 +718,55 @@ struct rte_bbdev_op_ldpc_enc { }; }; +/** Operation structure for FFT processing. + * + * The operation processes the data for multiple antennas in a single call + * (i.e. for all the REs belonging to a given SRS sequence for instance). + * + * The output mbuf data structure is expected to be allocated by the + * application with enough room for the output data. + */ +struct rte_bbdev_op_fft { + /** Input data starting from first antenna. */ + struct rte_bbdev_op_data base_input; + /** Output data starting from first antenna and first cyclic shift. */ + struct rte_bbdev_op_data base_output; + /** Optional power measurement output data. */ + struct rte_bbdev_op_data power_meas_output; + /** Flags from rte_bbdev_op_fft_flag_bitmasks. */ + uint32_t op_flags; + /** Input sequence size in 32-bits points. */ + uint16_t input_sequence_size; + /** Padding at the start of the sequence. */ + uint16_t input_leading_padding; + /** Output sequence size in 32-bits points. */ + uint16_t output_sequence_size; + /** Depadding at the start of the DFT output. */ + uint16_t output_leading_depadding; + /** Window index being used for each cyclic shift output. */ + uint8_t window_index[RTE_BBDEV_MAX_CS_2]; + /** Bitmap of the cyclic shift output requested. */ + uint16_t cs_bitmap; + /** Number of antennas as a log2 – 8 to 128. */ + uint8_t num_antennas_log2; + /** iDFT size as a log2 - 32 to 2048. */ + uint8_t idft_log2; + /** DFT size as a log2 - 8 to 2048. */ + uint8_t dft_log2; + /** Adjustment of position of the cyclic shifts - -31 to 31. */ + int8_t cs_time_adjustment; + /** iDFT shift down. */ + int8_t idft_shift; + /** DFT shift down. */ + int8_t dft_shift; + /** NCS reciprocal factor. */ + uint16_t ncs_reciprocal; + /** Power measurement out shift down. */ + uint16_t power_shift; + /** Adjust the FP6 exponent for INT<->FP16 conversion. */ + uint16_t fp16_exp_adjust; +}; + /** List of the capabilities for the Turbo Decoder */ struct rte_bbdev_op_cap_turbo_dec { /** Flags from rte_bbdev_op_td_flag_bitmasks */ @@ -748,6 +819,16 @@ struct rte_bbdev_op_cap_ldpc_enc { uint16_t num_buffers_dst; }; +/** List of the capabilities for the FFT. */ +struct rte_bbdev_op_cap_fft { + /** Flags from *rte_bbdev_op_fft_flag_bitmasks*. */ + uint32_t capability_flags; + /** Number of input code block buffers. */ + uint16_t num_buffers_src; + /** Number of output code block buffers. */ + uint16_t num_buffers_dst; +}; + /** Different operation types supported by the device. * The related macro RTE_BBDEV_OP_TYPE_SIZE_MAX can be used as an absolute maximum for * notably sizing array while allowing for future enumeration insertion. @@ -758,6 +839,7 @@ enum rte_bbdev_op_type { RTE_BBDEV_OP_TURBO_ENC, /**< Turbo encode */ RTE_BBDEV_OP_LDPC_DEC, /**< LDPC decode */ RTE_BBDEV_OP_LDPC_ENC, /**< LDPC encode */ + RTE_BBDEV_OP_FFT, /**< FFT */ /* Note: RTE_BBDEV_OP_TYPE_SIZE_MAX must be larger or equal to maximum enum value */ }; @@ -801,6 +883,18 @@ struct rte_bbdev_dec_op { }; }; +/** Structure specifying a single FFT operation. */ +struct rte_bbdev_fft_op { + /** Status of operation performed. */ + int status; + /** Mempool used for op instance. */ + struct rte_mempool *mempool; + /** Opaque pointer for user data. */ + void *opaque_data; + /** Contains turbo decoder specific parameters. */ + struct rte_bbdev_op_fft fft; +}; + /** Operation capabilities supported by a device */ struct rte_bbdev_op_cap { enum rte_bbdev_op_type type; /**< Type of operation */ @@ -809,6 +903,7 @@ struct rte_bbdev_op_cap { struct rte_bbdev_op_cap_turbo_enc turbo_enc; struct rte_bbdev_op_cap_ldpc_dec ldpc_dec; struct rte_bbdev_op_cap_ldpc_enc ldpc_enc; + struct rte_bbdev_op_cap_fft fft; } cap; /**< Operation-type specific capabilities */ }; @@ -927,6 +1022,41 @@ rte_bbdev_dec_op_alloc_bulk(struct rte_mempool *mempool, return 0; } +/** + * Bulk allocate FFT operations from a mempool with default parameters. + * + * @param mempool + * Operation mempool, created by *rte_bbdev_op_pool_create*. + * @param ops + * Output array to place allocated operations. + * @param num_ops + * Number of operations to allocate. + * + * @returns + * - 0 on success. + * - EINVAL if invalid mempool is provided. + */ +__rte_experimental +static inline int +rte_bbdev_fft_op_alloc_bulk(struct rte_mempool *mempool, + struct rte_bbdev_fft_op **ops, uint16_t num_ops) +{ + struct rte_bbdev_op_pool_private *priv; + int ret; + + /* Check type */ + priv = (struct rte_bbdev_op_pool_private *)rte_mempool_get_priv(mempool); + if (unlikely(priv->type != RTE_BBDEV_OP_FFT)) + return -EINVAL; + + /* Get elements */ + ret = rte_mempool_get_bulk(mempool, (void **)ops, num_ops); + if (unlikely(ret < 0)) + return ret; + + return 0; +} + /** * Free decode operation structures that were allocated by * rte_bbdev_dec_op_alloc_bulk(). @@ -961,6 +1091,24 @@ rte_bbdev_enc_op_free_bulk(struct rte_bbdev_enc_op **ops, unsigned int num_ops) rte_mempool_put_bulk(ops[0]->mempool, (void **)ops, num_ops); } +/** + * Free encode operation structures that were allocated by + * *rte_bbdev_fft_op_alloc_bulk*. + * All structures must belong to the same mempool. + * + * @param ops + * Operation structures. + * @param num_ops + * Number of structures. + */ +__rte_experimental +static inline void +rte_bbdev_fft_op_free_bulk(struct rte_bbdev_fft_op **ops, unsigned int num_ops) +{ + if (num_ops > 0) + rte_mempool_put_bulk(ops[0]->mempool, (void **)ops, num_ops); +} + #ifdef __cplusplus } #endif diff --git a/lib/bbdev/version.map b/lib/bbdev/version.map index addea05f00..db178917e2 100644 --- a/lib/bbdev/version.map +++ b/lib/bbdev/version.map @@ -44,5 +44,9 @@ EXPERIMENTAL { global: # added in 22.11 + rte_bbdev_dequeue_fft_ops; rte_bbdev_device_status_str; + rte_bbdev_enqueue_fft_ops; + rte_bbdev_fft_op_alloc_bulk; + rte_bbdev_fft_op_free_bulk; };