[v6,3/5] baseband/acc100: introduce PMD for ACC101
Checks
Commit Message
Support for ACC101 as a derivative of ACC100.
Integrated in unified driver and reusing existing code when possible.
Signed-off-by: Nicolas Chautru <nicolas.chautru@intel.com>
---
MAINTAINERS | 1 +
doc/guides/bbdevs/acc100.rst | 37 +++++---
doc/guides/bbdevs/features/acc101.ini | 13 +++
doc/guides/rel_notes/release_22_07.rst | 3 +
drivers/baseband/acc100/rte_acc100_pmd.c | 153 +++++++++++++++++++++++++++++--
drivers/baseband/acc100/rte_acc100_pmd.h | 11 +++
drivers/baseband/acc100/rte_acc101_pmd.h | 55 +++++++++++
7 files changed, 254 insertions(+), 19 deletions(-)
create mode 100644 doc/guides/bbdevs/features/acc101.ini
create mode 100644 drivers/baseband/acc100/rte_acc101_pmd.h
Comments
>
>
> Enable Virtual Functions
> @@ -167,14 +172,14 @@ queues, priorities, load balance, bandwidth and other
> settings necessary for the
> device to perform FEC functions.
>
> This configuration needs to be executed at least once after reboot or PCI FLR
> and can
> -be achieved by using the function ``acc100_configure()``, which sets up the
> -parameters defined in ``acc100_conf`` structure.
> +be achieved by using the functions ``acc100_configure()`` or
> ``acc101_configure()``,
I believe the API for user is common now. Right? So why to have two references?
> +which sets up the parameters defined in the compatible ``acc100_conf``
> structure.
>
> Test Application
> ----------------
>
> BBDEV provides a test application, ``test-bbdev.py`` and range of test data for
> testing
> -the functionality of ACC100 5G/4G FEC encode and decode, depending on the
> device's
> +the functionality of the device 5G/4G FEC encode and decode, depending on
> the device's
> capabilities. The test application is located under app->test-bbdev folder and
> has the
> following options:
>
> @@ -212,7 +217,7 @@ Test Vectors
>
> In addition to the simple LDPC decoder and LDPC encoder tests, bbdev also
> provides
> a range of additional tests under the test_vectors folder, which may be useful.
> The results
> -of these tests will depend on the ACC100 5G/4G FEC capabilities which may
> cause some
> +of these tests will depend on the device 5G/4G FEC capabilities which may
> cause some
> testcases to be skipped, but no failure should be reported.
>
>
> @@ -233,3 +238,11 @@ Specifically for the BBDEV ACC100 PMD, the command
> below can be used:
>
> ./pf_bb_config ACC100 -c acc100/acc100_config_vf_5g.cfg
> ./test-bbdev.py -e="-c 0xff0 -a${VF_PCI_ADDR}" -c validation -n 64 -b 32 -l 1 -v
> ./ldpc_dec_default.data
> +
> +Specifically for the BBDEV ACC101 PMD, the command below can be used:
> +
> +.. code-block:: console
> +
> + ./pf_bb_config ACC101 -c acc101/acc101_config_2vf_4g5g.cfg
> + ./test-bbdev.py -e="-c 0xff0 -a${VF_PCI_ADDR}" -c validation -n 64 -b 32 -l 1 -
> v ./ldpc_dec_default.data
> +
> diff --git a/doc/guides/bbdevs/features/acc101.ini
> b/doc/guides/bbdevs/features/acc101.ini
> new file mode 100644
> index 0000000..0e2c21a
> --- /dev/null
> +++ b/doc/guides/bbdevs/features/acc101.ini
> @@ -0,0 +1,13 @@
> +;
> +; Supported features of the 'acc101' bbdev driver.
> +;
> +; Refer to default.ini for the full list of available PMD features.
> +;
> +[Features]
> +Turbo Decoder (4G) = Y
> +Turbo Encoder (4G) = Y
> +LDPC Decoder (5G) = Y
> +LDPC Encoder (5G) = Y
> +LLR/HARQ Compression = Y
> +External DDR Access = Y
> +HW Accelerated = Y
> diff --git a/doc/guides/rel_notes/release_22_07.rst
> b/doc/guides/rel_notes/release_22_07.rst
> index e49cace..1803947 100644
> --- a/doc/guides/rel_notes/release_22_07.rst
> +++ b/doc/guides/rel_notes/release_22_07.rst
> @@ -104,6 +104,9 @@ New Features
> * ``RTE_EVENT_QUEUE_ATTR_WEIGHT``
> * ``RTE_EVENT_QUEUE_ATTR_AFFINITY``
>
> +* **Added Intel ACC101 baseband PMD.**
> +
> + * Added a new baseband PMD for Intel ACC101 device.
>
> Removed Items
> -------------
> diff --git a/drivers/baseband/acc100/rte_acc100_pmd.c
> b/drivers/baseband/acc100/rte_acc100_pmd.c
> index 3fdf17d..6a2123b 100644
> --- a/drivers/baseband/acc100/rte_acc100_pmd.c
> +++ b/drivers/baseband/acc100/rte_acc100_pmd.c
> @@ -22,6 +22,7 @@
> #include <rte_bbdev.h>
> #include <rte_bbdev_pmd.h>
> #include "rte_acc100_pmd.h"
> +#include "rte_acc101_pmd.h"
>
> #ifdef RTE_LIBRTE_BBDEV_DEBUG
> RTE_LOG_REGISTER_DEFAULT(acc100_logtype, DEBUG);
> @@ -1133,7 +1134,10 @@
> /* ACC100 PCI PF address map */
> static struct rte_pci_id pci_id_acc100_pf_map[] = {
> {
> - RTE_PCI_DEVICE(RTE_ACC100_VENDOR_ID,
> RTE_ACC100_PF_DEVICE_ID)
> + RTE_PCI_DEVICE(RTE_ACC100_VENDOR_ID,
> RTE_ACC100_PF_DEVICE_ID),
> + },
> + {
> + RTE_PCI_DEVICE(RTE_ACC101_VENDOR_ID,
> RTE_ACC101_PF_DEVICE_ID),
> },
> {.device_id = 0},
> };
> @@ -1141,7 +1145,10 @@
> /* ACC100 PCI VF address map */
> static struct rte_pci_id pci_id_acc100_vf_map[] = {
> {
> - RTE_PCI_DEVICE(RTE_ACC100_VENDOR_ID,
> RTE_ACC100_VF_DEVICE_ID)
> + RTE_PCI_DEVICE(RTE_ACC100_VENDOR_ID,
> RTE_ACC100_VF_DEVICE_ID),
> + },
> + {
> + RTE_PCI_DEVICE(RTE_ACC101_VENDOR_ID,
> RTE_ACC101_VF_DEVICE_ID),
> },
> {.device_id = 0},
> };
> @@ -1290,7 +1297,7 @@
>
> /* Fill in a frame control word for LDPC decoding. */
> static inline void
> -acc100_fcw_ld_fill(const struct rte_bbdev_dec_op *op, struct acc100_fcw_ld
> *fcw,
> +acc100_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
> union acc100_harq_layout_data *harq_layout)
> {
> uint16_t harq_out_length, harq_in_length, ncb_p, k0_p, parity_offset;
> @@ -1414,6 +1421,128 @@
> }
> }
>
> +/* Convert offset to harq index for harq_layout structure */
> +static inline uint32_t hq_index(uint32_t offset)
> +{
> + return (offset >> ACC100_HARQ_OFFSET_SHIFT) &
> ACC100_HARQ_OFFSET_MASK;
> +}
> +
> +/* Fill in a frame control word for LDPC decoding for ACC101 */
> +static inline void
> +acc101_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
> + union acc100_harq_layout_data *harq_layout)
> +{
> + uint16_t harq_out_length, harq_in_length, ncb_p, k0_p, parity_offset;
> + uint32_t harq_index;
> + uint32_t l;
> +
> + fcw->qm = op->ldpc_dec.q_m;
> + fcw->nfiller = op->ldpc_dec.n_filler;
> + fcw->BG = (op->ldpc_dec.basegraph - 1);
> + fcw->Zc = op->ldpc_dec.z_c;
> + fcw->ncb = op->ldpc_dec.n_cb;
> + fcw->k0 = get_k0(fcw->ncb, fcw->Zc, op->ldpc_dec.basegraph,
> + op->ldpc_dec.rv_index);
> + if (op->ldpc_dec.code_block_mode == RTE_BBDEV_CODE_BLOCK)
> + fcw->rm_e = op->ldpc_dec.cb_params.e;
> + else
> + fcw->rm_e = (op->ldpc_dec.tb_params.r <
> + op->ldpc_dec.tb_params.cab) ?
> + op->ldpc_dec.tb_params.ea :
> + op->ldpc_dec.tb_params.eb;
> +
> + if (unlikely(check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE) &&
> + (op->ldpc_dec.harq_combined_input.length == 0))) {
> + rte_bbdev_log(WARNING, "Null HARQ input size provided");
> + /* Disable HARQ input in that case to carry forward */
> + op->ldpc_dec.op_flags ^=
> RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE;
> + }
> +
> + fcw->hcin_en = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE);
> + fcw->hcout_en = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_HQ_COMBINE_OUT_ENABLE);
> + fcw->crc_select = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_CRC_TYPE_24B_CHECK);
> + fcw->bypass_dec = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_DECODE_BYPASS);
> + fcw->bypass_intlv = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_DEINTERLEAVER_BYPASS);
> + if (op->ldpc_dec.q_m == 1) {
> + fcw->bypass_intlv = 1;
> + fcw->qm = 2;
> + }
> + fcw->hcin_decomp_mode = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION);
> + fcw->hcout_comp_mode = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION);
> + fcw->llr_pack_mode = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_LLR_COMPRESSION);
> + harq_index = hq_index(op->ldpc_dec.harq_combined_output.offset);
> + if (fcw->hcin_en > 0) {
> + harq_in_length = op->ldpc_dec.harq_combined_input.length;
> + if (fcw->hcin_decomp_mode > 0)
> + harq_in_length = harq_in_length * 8 / 6;
> + harq_in_length = RTE_MIN(harq_in_length, op->ldpc_dec.n_cb
> + - op->ldpc_dec.n_filler);
> + /* Alignment on next 64B - Already enforced from HC output */
> + harq_in_length = RTE_ALIGN_FLOOR(harq_in_length, 64);
> + fcw->hcin_size0 = harq_in_length;
> + fcw->hcin_offset = 0;
> + fcw->hcin_size1 = 0;
> + } else {
> + fcw->hcin_size0 = 0;
> + fcw->hcin_offset = 0;
> + fcw->hcin_size1 = 0;
> + }
> +
> + fcw->itmax = op->ldpc_dec.iter_max;
> + fcw->itstop = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_ITERATION_STOP_ENABLE);
> + fcw->synd_precoder = fcw->itstop;
> + /*
> + * These are all implicitly set
> + * fcw->synd_post = 0;
> + * fcw->so_en = 0;
> + * fcw->so_bypass_rm = 0;
> + * fcw->so_bypass_intlv = 0;
> + * fcw->dec_convllr = 0;
> + * fcw->hcout_convllr = 0;
> + * fcw->hcout_size1 = 0;
> + * fcw->so_it = 0;
> + * fcw->hcout_offset = 0;
> + * fcw->negstop_th = 0;
> + * fcw->negstop_it = 0;
> + * fcw->negstop_en = 0;
> + * fcw->gain_i = 1;
> + * fcw->gain_h = 1;
> + */
> + if (fcw->hcout_en > 0) {
> + parity_offset = (op->ldpc_dec.basegraph == 1 ? 20 : 8)
> + * op->ldpc_dec.z_c - op->ldpc_dec.n_filler;
> + k0_p = (fcw->k0 > parity_offset) ?
> + fcw->k0 - op->ldpc_dec.n_filler : fcw->k0;
> + ncb_p = fcw->ncb - op->ldpc_dec.n_filler;
> + l = RTE_MIN(k0_p + fcw->rm_e, INT16_MAX);
> + harq_out_length = (uint16_t) fcw->hcin_size0;
> + harq_out_length = RTE_MAX(harq_out_length, l);
> + /* Cannot exceed the pruned Ncb circular buffer */
> + harq_out_length = RTE_MIN(harq_out_length, ncb_p);
> + /* Alignment on next 64B */
> + harq_out_length = RTE_ALIGN_CEIL(harq_out_length, 64);
> + fcw->hcout_size0 = harq_out_length;
> + fcw->hcout_size1 = 0;
> + fcw->hcout_offset = 0;
> + harq_layout[harq_index].offset = fcw->hcout_offset;
> + harq_layout[harq_index].size0 = fcw->hcout_size0;
> + } else {
> + fcw->hcout_size0 = 0;
> + fcw->hcout_size1 = 0;
> + fcw->hcout_offset = 0;
> + }
> +}
> +
> /**
> * Fills descriptor with data pointers of one block type.
> *
> @@ -2966,7 +3095,7 @@
> struct acc100_fcw_ld *fcw;
> uint32_t seg_total_left;
> fcw = &desc->req.fcw_ld;
> - acc100_fcw_ld_fill(op, fcw, harq_layout);
> + q->d->fcw_ld_fill(op, fcw, harq_layout);
>
> /* Special handling when overusing mbuf */
> if (fcw->rm_e < ACC100_MAX_E_MBUF)
> @@ -3033,7 +3162,7 @@
> desc = q->ring_addr + desc_idx;
> uint64_t fcw_offset = (desc_idx << 8) + ACC100_DESC_FCW_OFFSET;
> union acc100_harq_layout_data *harq_layout = q->d->harq_layout;
> - acc100_fcw_ld_fill(op, &desc->req.fcw_ld, harq_layout);
> + q->d->fcw_ld_fill(op, &desc->req.fcw_ld, harq_layout);
>
> input = op->ldpc_dec.input.data;
> h_output_head = h_output = op->ldpc_dec.hard_output.data;
> @@ -4145,9 +4274,19 @@
> dev->dequeue_ldpc_enc_ops = acc100_dequeue_ldpc_enc;
> dev->dequeue_ldpc_dec_ops = acc100_dequeue_ldpc_dec;
>
> + /* Device variant specific handling */
> + if ((pci_dev->id.device_id == RTE_ACC100_PF_DEVICE_ID) ||
> + (pci_dev->id.device_id == RTE_ACC100_VF_DEVICE_ID))
> {
> + ((struct acc100_device *) dev->data->dev_private)-
> >device_variant = ACC100_VARIANT;
> + ((struct acc100_device *) dev->data->dev_private)->fcw_ld_fill
> = acc100_fcw_ld_fill;
> + } else {
> + ((struct acc100_device *) dev->data->dev_private)-
> >device_variant = ACC101_VARIANT;
> + ((struct acc100_device *) dev->data->dev_private)->fcw_ld_fill
> = acc101_fcw_ld_fill;
> + }
> +
> ((struct acc100_device *) dev->data->dev_private)->pf_device =
> - !strcmp(drv->driver.name,
> - RTE_STR(ACC100PF_DRIVER_NAME));
> + !strcmp(drv->driver.name,
> RTE_STR(ACC100PF_DRIVER_NAME));
> +
> ((struct acc100_device *) dev->data->dev_private)->mmio_base =
> pci_dev->mem_resource[0].addr;
>
> diff --git a/drivers/baseband/acc100/rte_acc100_pmd.h
> b/drivers/baseband/acc100/rte_acc100_pmd.h
> index 8fea322..39d5f22 100644
> --- a/drivers/baseband/acc100/rte_acc100_pmd.h
> +++ b/drivers/baseband/acc100/rte_acc100_pmd.h
> @@ -22,6 +22,9 @@
> #define rte_bbdev_log_debug(fmt, ...)
> #endif
>
> +#define ACC100_VARIANT 0
> +#define ACC101_VARIANT 1
Since you are using PCI dev id for identifying the device. Do we still need above defines?
> +
> /* ACC100 PF and VF driver names */
> #define ACC100PF_DRIVER_NAME intel_acc100_pf
> #define ACC100VF_DRIVER_NAME intel_acc100_vf
> @@ -67,6 +70,8 @@
> #define ACC100_HARQ_LAYOUT (64*1024*1024)
> /* Assume offset for HARQ in memory */
> #define ACC100_HARQ_OFFSET (32*1024)
> +#define ACC100_HARQ_OFFSET_SHIFT 15
> +#define ACC100_HARQ_OFFSET_MASK 0x7ffffff
> /* Mask used to calculate an index in an Info Ring array (not a byte offset) */
> #define ACC100_INFO_RING_MASK (ACC100_INFO_RING_NUM_ENTRIES-
> 1)
> /* Number of Virtual Functions ACC100 supports */
> @@ -574,6 +579,10 @@ struct __rte_cache_aligned acc100_queue {
> struct acc100_device *d;
> };
>
> +typedef void (*acc10x_fcw_ld_fill_fun_t)(struct rte_bbdev_dec_op *op,
> + struct acc100_fcw_ld *fcw,
> + union acc100_harq_layout_data *harq_layout);
> +
> /* Private data structure for each ACC100 device */
> struct acc100_device {
> void *mmio_base; /**< Base address of MMIO registers (BAR0) */
> @@ -605,6 +614,8 @@ struct acc100_device {
> uint16_t q_assigned_bit_map[ACC100_NUM_QGRPS];
> bool pf_device; /**< True if this is a PF ACC100 device */
> bool configured; /**< True if this ACC100 device is configured */
> + uint16_t device_variant; /**< Device variant */
> + acc10x_fcw_ld_fill_fun_t fcw_ld_fill; /**< 5GUL FCW generation
> function */
> };
>
> /**
> diff --git a/drivers/baseband/acc100/rte_acc101_pmd.h
> b/drivers/baseband/acc100/rte_acc101_pmd.h
> new file mode 100644
> index 0000000..8f1f4ab
> --- /dev/null
> +++ b/drivers/baseband/acc100/rte_acc101_pmd.h
This file is internal, shouldn't we drop the rte?
> @@ -0,0 +1,55 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2022 Intel Corporation
> + */
> +
> +/* ACC101 PCI vendor & device IDs */
> +#define RTE_ACC101_VENDOR_ID (0x8086)
> +#define RTE_ACC101_PF_DEVICE_ID (0x57c4)
> +#define RTE_ACC101_VF_DEVICE_ID (0x57c5)
> +
> +/* Define as 1 to use only a single FEC engine */
> +#ifndef RTE_ACC101_SINGLE_FEC
> +#define RTE_ACC101_SINGLE_FEC 0
> +#endif
Also the above defines should drop RTE if they are internal symbols.
> +
> +/* Number of Virtual Functions ACC101 supports */
> +#define ACC101_NUM_VFS 16
> +#define ACC101_NUM_QGRPS 8
> +#define ACC101_NUM_AQS 16
> +/* All ACC101 Registers alignment are 32bits = 4B */
> +#define ACC101_BYTES_IN_WORD 4
> +
> +#define ACC101_TMPL_PRI_0 0x03020100
> +#define ACC101_TMPL_PRI_1 0x07060504
> +#define ACC101_TMPL_PRI_2 0x0b0a0908
> +#define ACC101_TMPL_PRI_3 0x0f0e0d0c
> +#define ACC101_WORDS_IN_ARAM_SIZE (128 * 1024 / 4)
> +
> +#define ACC101_NUM_TMPL 32
> +/* Mapping of signals for the available engines */
> +#define ACC101_SIG_UL_5G 0
> +#define ACC101_SIG_UL_5G_LAST 8
> +#define ACC101_SIG_DL_5G 13
> +#define ACC101_SIG_DL_5G_LAST 15
> +#define ACC101_SIG_UL_4G 16
> +#define ACC101_SIG_UL_4G_LAST 19
> +#define ACC101_SIG_DL_4G 27
> +#define ACC101_SIG_DL_4G_LAST 31
> +#define ACC101_NUM_ACCS 5
> +#define ACC101_PF_VAL 2
> +
> +/* ACC101 Configuration */
> +#define ACC101_CFG_DMA_ERROR 0x3D7
> +#define ACC101_CFG_AXI_CACHE 0x11
> +#define ACC101_CFG_QMGR_HI_P 0x0F0F
> +#define ACC101_CFG_PCI_AXI 0xC003
> +#define ACC101_CFG_PCI_BRIDGE 0x40006033
> +#define ACC101_ENGINE_OFFSET 0x1000
> +#define ACC101_LONG_WAIT 1000
> +#define ACC101_GPEX_AXIMAP_NUM 17
> +#define ACC101_CLOCK_GATING_EN 0x30000
> +#define ACC101_DMA_INBOUND 0x104
> +/* DDR Size per VF - 512MB by default
> + * Can be increased up to 4 GB with single PF/VF
> + */
> +#define ACC101_HARQ_DDR (512 * 1)
> --
> 1.8.3.1
Hi Akhil,
> -----Original Message-----
> From: Akhil Goyal <gakhil@marvell.com>
> Sent: Monday, May 30, 2022 12:40 AM
> To: Chautru, Nicolas <nicolas.chautru@intel.com>; dev@dpdk.org;
> trix@redhat.com; maxime.coquelin@redhat.com
> Cc: thomas@monjalon.net; Kinsella, Ray <ray.kinsella@intel.com>;
> Richardson, Bruce <bruce.richardson@intel.com>;
> hemant.agrawal@nxp.com; Vargas, Hernan <hernan.vargas@intel.com>;
> david.marchand@redhat.com
> Subject: RE: [EXT] [PATCH v6 3/5] baseband/acc100: introduce PMD for
> ACC101
>
> >
> >
> > Enable Virtual Functions
> > @@ -167,14 +172,14 @@ queues, priorities, load balance, bandwidth and
> > other settings necessary for the device to perform FEC functions.
> >
> > This configuration needs to be executed at least once after reboot or
> > PCI FLR and can -be achieved by using the function
> > ``acc100_configure()``, which sets up the -parameters defined in
> > ``acc100_conf`` structure.
> > +be achieved by using the functions ``acc100_configure()`` or
> > ``acc101_configure()``,
>
> I believe the API for user is common now. Right? So why to have two
> references?
Thanks, I will amend the documentation now.
>
> > +which sets up the parameters defined in the compatible
> > +``acc100_conf``
> > structure.
> >
> > Test Application
> > ----------------
> >
> > BBDEV provides a test application, ``test-bbdev.py`` and range of
> > test data for testing -the functionality of ACC100 5G/4G FEC encode
> > and decode, depending on the device's
> > +the functionality of the device 5G/4G FEC encode and decode,
> > +depending on
> > the device's
> > capabilities. The test application is located under app->test-bbdev
> > folder and has the following options:
> >
> > @@ -212,7 +217,7 @@ Test Vectors
> >
> > In addition to the simple LDPC decoder and LDPC encoder tests, bbdev
> > also provides a range of additional tests under the test_vectors
> > folder, which may be useful.
> > The results
> > -of these tests will depend on the ACC100 5G/4G FEC capabilities which
> > may cause some
> > +of these tests will depend on the device 5G/4G FEC capabilities which
> > +may
> > cause some
> > testcases to be skipped, but no failure should be reported.
> >
> >
> > @@ -233,3 +238,11 @@ Specifically for the BBDEV ACC100 PMD, the
> > command below can be used:
> >
> > ./pf_bb_config ACC100 -c acc100/acc100_config_vf_5g.cfg
> > ./test-bbdev.py -e="-c 0xff0 -a${VF_PCI_ADDR}" -c validation -n 64
> > -b 32 -l 1 -v ./ldpc_dec_default.data
> > +
> > +Specifically for the BBDEV ACC101 PMD, the command below can be used:
> > +
> > +.. code-block:: console
> > +
> > + ./pf_bb_config ACC101 -c acc101/acc101_config_2vf_4g5g.cfg
> > + ./test-bbdev.py -e="-c 0xff0 -a${VF_PCI_ADDR}" -c validation -n 64
> > + -b 32 -l 1 -
> > v ./ldpc_dec_default.data
> > +
> > diff --git a/doc/guides/bbdevs/features/acc101.ini
> > b/doc/guides/bbdevs/features/acc101.ini
> > new file mode 100644
> > index 0000000..0e2c21a
> > --- /dev/null
> > +++ b/doc/guides/bbdevs/features/acc101.ini
> > @@ -0,0 +1,13 @@
> > +;
> > +; Supported features of the 'acc101' bbdev driver.
> > +;
> > +; Refer to default.ini for the full list of available PMD features.
> > +;
> > +[Features]
> > +Turbo Decoder (4G) = Y
> > +Turbo Encoder (4G) = Y
> > +LDPC Decoder (5G) = Y
> > +LDPC Encoder (5G) = Y
> > +LLR/HARQ Compression = Y
> > +External DDR Access = Y
> > +HW Accelerated = Y
> > diff --git a/doc/guides/rel_notes/release_22_07.rst
> > b/doc/guides/rel_notes/release_22_07.rst
> > index e49cace..1803947 100644
> > --- a/doc/guides/rel_notes/release_22_07.rst
> > +++ b/doc/guides/rel_notes/release_22_07.rst
> > @@ -104,6 +104,9 @@ New Features
> > * ``RTE_EVENT_QUEUE_ATTR_WEIGHT``
> > * ``RTE_EVENT_QUEUE_ATTR_AFFINITY``
> >
> > +* **Added Intel ACC101 baseband PMD.**
> > +
> > + * Added a new baseband PMD for Intel ACC101 device.
> >
> > Removed Items
> > -------------
> > diff --git a/drivers/baseband/acc100/rte_acc100_pmd.c
> > b/drivers/baseband/acc100/rte_acc100_pmd.c
> > index 3fdf17d..6a2123b 100644
> > --- a/drivers/baseband/acc100/rte_acc100_pmd.c
> > +++ b/drivers/baseband/acc100/rte_acc100_pmd.c
> > @@ -22,6 +22,7 @@
> > #include <rte_bbdev.h>
> > #include <rte_bbdev_pmd.h>
> > #include "rte_acc100_pmd.h"
> > +#include "rte_acc101_pmd.h"
> >
> > #ifdef RTE_LIBRTE_BBDEV_DEBUG
> > RTE_LOG_REGISTER_DEFAULT(acc100_logtype, DEBUG); @@ -1133,7
> +1134,10
> > @@
> > /* ACC100 PCI PF address map */
> > static struct rte_pci_id pci_id_acc100_pf_map[] = {
> > {
> > - RTE_PCI_DEVICE(RTE_ACC100_VENDOR_ID,
> > RTE_ACC100_PF_DEVICE_ID)
> > + RTE_PCI_DEVICE(RTE_ACC100_VENDOR_ID,
> > RTE_ACC100_PF_DEVICE_ID),
> > + },
> > + {
> > + RTE_PCI_DEVICE(RTE_ACC101_VENDOR_ID,
> > RTE_ACC101_PF_DEVICE_ID),
> > },
> > {.device_id = 0},
> > };
> > @@ -1141,7 +1145,10 @@
> > /* ACC100 PCI VF address map */
> > static struct rte_pci_id pci_id_acc100_vf_map[] = {
> > {
> > - RTE_PCI_DEVICE(RTE_ACC100_VENDOR_ID,
> > RTE_ACC100_VF_DEVICE_ID)
> > + RTE_PCI_DEVICE(RTE_ACC100_VENDOR_ID,
> > RTE_ACC100_VF_DEVICE_ID),
> > + },
> > + {
> > + RTE_PCI_DEVICE(RTE_ACC101_VENDOR_ID,
> > RTE_ACC101_VF_DEVICE_ID),
> > },
> > {.device_id = 0},
> > };
> > @@ -1290,7 +1297,7 @@
> >
> > /* Fill in a frame control word for LDPC decoding. */ static inline
> > void -acc100_fcw_ld_fill(const struct rte_bbdev_dec_op *op, struct
> > acc100_fcw_ld *fcw,
> > +acc100_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld
> > +*fcw,
> > union acc100_harq_layout_data *harq_layout) {
> > uint16_t harq_out_length, harq_in_length, ncb_p, k0_p,
> > parity_offset; @@ -1414,6 +1421,128 @@
> > }
> > }
> >
> > +/* Convert offset to harq index for harq_layout structure */ static
> > +inline uint32_t hq_index(uint32_t offset) {
> > + return (offset >> ACC100_HARQ_OFFSET_SHIFT) &
> > ACC100_HARQ_OFFSET_MASK;
> > +}
> > +
> > +/* Fill in a frame control word for LDPC decoding for ACC101 */
> > +static inline void acc101_fcw_ld_fill(struct rte_bbdev_dec_op *op,
> > +struct acc100_fcw_ld *fcw,
> > + union acc100_harq_layout_data *harq_layout) {
> > + uint16_t harq_out_length, harq_in_length, ncb_p, k0_p,
> parity_offset;
> > + uint32_t harq_index;
> > + uint32_t l;
> > +
> > + fcw->qm = op->ldpc_dec.q_m;
> > + fcw->nfiller = op->ldpc_dec.n_filler;
> > + fcw->BG = (op->ldpc_dec.basegraph - 1);
> > + fcw->Zc = op->ldpc_dec.z_c;
> > + fcw->ncb = op->ldpc_dec.n_cb;
> > + fcw->k0 = get_k0(fcw->ncb, fcw->Zc, op->ldpc_dec.basegraph,
> > + op->ldpc_dec.rv_index);
> > + if (op->ldpc_dec.code_block_mode == RTE_BBDEV_CODE_BLOCK)
> > + fcw->rm_e = op->ldpc_dec.cb_params.e;
> > + else
> > + fcw->rm_e = (op->ldpc_dec.tb_params.r <
> > + op->ldpc_dec.tb_params.cab) ?
> > + op->ldpc_dec.tb_params.ea :
> > + op->ldpc_dec.tb_params.eb;
> > +
> > + if (unlikely(check_bit(op->ldpc_dec.op_flags,
> > + RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE) &&
> > + (op->ldpc_dec.harq_combined_input.length == 0))) {
> > + rte_bbdev_log(WARNING, "Null HARQ input size provided");
> > + /* Disable HARQ input in that case to carry forward */
> > + op->ldpc_dec.op_flags ^=
> > RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE;
> > + }
> > +
> > + fcw->hcin_en = check_bit(op->ldpc_dec.op_flags,
> > + RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE);
> > + fcw->hcout_en = check_bit(op->ldpc_dec.op_flags,
> > + RTE_BBDEV_LDPC_HQ_COMBINE_OUT_ENABLE);
> > + fcw->crc_select = check_bit(op->ldpc_dec.op_flags,
> > + RTE_BBDEV_LDPC_CRC_TYPE_24B_CHECK);
> > + fcw->bypass_dec = check_bit(op->ldpc_dec.op_flags,
> > + RTE_BBDEV_LDPC_DECODE_BYPASS);
> > + fcw->bypass_intlv = check_bit(op->ldpc_dec.op_flags,
> > + RTE_BBDEV_LDPC_DEINTERLEAVER_BYPASS);
> > + if (op->ldpc_dec.q_m == 1) {
> > + fcw->bypass_intlv = 1;
> > + fcw->qm = 2;
> > + }
> > + fcw->hcin_decomp_mode = check_bit(op->ldpc_dec.op_flags,
> > + RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION);
> > + fcw->hcout_comp_mode = check_bit(op->ldpc_dec.op_flags,
> > + RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION);
> > + fcw->llr_pack_mode = check_bit(op->ldpc_dec.op_flags,
> > + RTE_BBDEV_LDPC_LLR_COMPRESSION);
> > + harq_index = hq_index(op-
> >ldpc_dec.harq_combined_output.offset);
> > + if (fcw->hcin_en > 0) {
> > + harq_in_length = op-
> >ldpc_dec.harq_combined_input.length;
> > + if (fcw->hcin_decomp_mode > 0)
> > + harq_in_length = harq_in_length * 8 / 6;
> > + harq_in_length = RTE_MIN(harq_in_length, op-
> >ldpc_dec.n_cb
> > + - op->ldpc_dec.n_filler);
> > + /* Alignment on next 64B - Already enforced from HC output
> */
> > + harq_in_length = RTE_ALIGN_FLOOR(harq_in_length, 64);
> > + fcw->hcin_size0 = harq_in_length;
> > + fcw->hcin_offset = 0;
> > + fcw->hcin_size1 = 0;
> > + } else {
> > + fcw->hcin_size0 = 0;
> > + fcw->hcin_offset = 0;
> > + fcw->hcin_size1 = 0;
> > + }
> > +
> > + fcw->itmax = op->ldpc_dec.iter_max;
> > + fcw->itstop = check_bit(op->ldpc_dec.op_flags,
> > + RTE_BBDEV_LDPC_ITERATION_STOP_ENABLE);
> > + fcw->synd_precoder = fcw->itstop;
> > + /*
> > + * These are all implicitly set
> > + * fcw->synd_post = 0;
> > + * fcw->so_en = 0;
> > + * fcw->so_bypass_rm = 0;
> > + * fcw->so_bypass_intlv = 0;
> > + * fcw->dec_convllr = 0;
> > + * fcw->hcout_convllr = 0;
> > + * fcw->hcout_size1 = 0;
> > + * fcw->so_it = 0;
> > + * fcw->hcout_offset = 0;
> > + * fcw->negstop_th = 0;
> > + * fcw->negstop_it = 0;
> > + * fcw->negstop_en = 0;
> > + * fcw->gain_i = 1;
> > + * fcw->gain_h = 1;
> > + */
> > + if (fcw->hcout_en > 0) {
> > + parity_offset = (op->ldpc_dec.basegraph == 1 ? 20 : 8)
> > + * op->ldpc_dec.z_c - op->ldpc_dec.n_filler;
> > + k0_p = (fcw->k0 > parity_offset) ?
> > + fcw->k0 - op->ldpc_dec.n_filler : fcw->k0;
> > + ncb_p = fcw->ncb - op->ldpc_dec.n_filler;
> > + l = RTE_MIN(k0_p + fcw->rm_e, INT16_MAX);
> > + harq_out_length = (uint16_t) fcw->hcin_size0;
> > + harq_out_length = RTE_MAX(harq_out_length, l);
> > + /* Cannot exceed the pruned Ncb circular buffer */
> > + harq_out_length = RTE_MIN(harq_out_length, ncb_p);
> > + /* Alignment on next 64B */
> > + harq_out_length = RTE_ALIGN_CEIL(harq_out_length, 64);
> > + fcw->hcout_size0 = harq_out_length;
> > + fcw->hcout_size1 = 0;
> > + fcw->hcout_offset = 0;
> > + harq_layout[harq_index].offset = fcw->hcout_offset;
> > + harq_layout[harq_index].size0 = fcw->hcout_size0;
> > + } else {
> > + fcw->hcout_size0 = 0;
> > + fcw->hcout_size1 = 0;
> > + fcw->hcout_offset = 0;
> > + }
> > +}
> > +
> > /**
> > * Fills descriptor with data pointers of one block type.
> > *
> > @@ -2966,7 +3095,7 @@
> > struct acc100_fcw_ld *fcw;
> > uint32_t seg_total_left;
> > fcw = &desc->req.fcw_ld;
> > - acc100_fcw_ld_fill(op, fcw, harq_layout);
> > + q->d->fcw_ld_fill(op, fcw, harq_layout);
> >
> > /* Special handling when overusing mbuf */
> > if (fcw->rm_e < ACC100_MAX_E_MBUF)
> > @@ -3033,7 +3162,7 @@
> > desc = q->ring_addr + desc_idx;
> > uint64_t fcw_offset = (desc_idx << 8) + ACC100_DESC_FCW_OFFSET;
> > union acc100_harq_layout_data *harq_layout = q->d->harq_layout;
> > - acc100_fcw_ld_fill(op, &desc->req.fcw_ld, harq_layout);
> > + q->d->fcw_ld_fill(op, &desc->req.fcw_ld, harq_layout);
> >
> > input = op->ldpc_dec.input.data;
> > h_output_head = h_output = op->ldpc_dec.hard_output.data; @@ -
> 4145,9
> > +4274,19 @@
> > dev->dequeue_ldpc_enc_ops = acc100_dequeue_ldpc_enc;
> > dev->dequeue_ldpc_dec_ops = acc100_dequeue_ldpc_dec;
> >
> > + /* Device variant specific handling */
> > + if ((pci_dev->id.device_id == RTE_ACC100_PF_DEVICE_ID) ||
> > + (pci_dev->id.device_id ==
> RTE_ACC100_VF_DEVICE_ID))
> > {
> > + ((struct acc100_device *) dev->data->dev_private)-
> > >device_variant = ACC100_VARIANT;
> > + ((struct acc100_device *) dev->data->dev_private)-
> >fcw_ld_fill
> > = acc100_fcw_ld_fill;
> > + } else {
> > + ((struct acc100_device *) dev->data->dev_private)-
> > >device_variant = ACC101_VARIANT;
> > + ((struct acc100_device *) dev->data->dev_private)-
> >fcw_ld_fill
> > = acc101_fcw_ld_fill;
> > + }
> > +
> > ((struct acc100_device *) dev->data->dev_private)->pf_device =
> > - !strcmp(drv->driver.name,
> > - RTE_STR(ACC100PF_DRIVER_NAME));
> > + !strcmp(drv->driver.name,
> > RTE_STR(ACC100PF_DRIVER_NAME));
> > +
> > ((struct acc100_device *) dev->data->dev_private)->mmio_base =
> > pci_dev->mem_resource[0].addr;
> >
> > diff --git a/drivers/baseband/acc100/rte_acc100_pmd.h
> > b/drivers/baseband/acc100/rte_acc100_pmd.h
> > index 8fea322..39d5f22 100644
> > --- a/drivers/baseband/acc100/rte_acc100_pmd.h
> > +++ b/drivers/baseband/acc100/rte_acc100_pmd.h
> > @@ -22,6 +22,9 @@
> > #define rte_bbdev_log_debug(fmt, ...) #endif
> >
> > +#define ACC100_VARIANT 0
> > +#define ACC101_VARIANT 1
>
> Since you are using PCI dev id for identifying the device. Do we still need
> above defines?
The implementation is_acc100() is based on checking that enum
(q->d->device_variant == ACC100_VARIANT);
> > +
> > /* ACC100 PF and VF driver names */
> > #define ACC100PF_DRIVER_NAME intel_acc100_pf
> > #define ACC100VF_DRIVER_NAME intel_acc100_vf
> > @@ -67,6 +70,8 @@
> > #define ACC100_HARQ_LAYOUT (64*1024*1024)
> > /* Assume offset for HARQ in memory */
> > #define ACC100_HARQ_OFFSET (32*1024)
> > +#define ACC100_HARQ_OFFSET_SHIFT 15
> > +#define ACC100_HARQ_OFFSET_MASK 0x7ffffff
> > /* Mask used to calculate an index in an Info Ring array (not a byte offset)
> */
> > #define ACC100_INFO_RING_MASK
> (ACC100_INFO_RING_NUM_ENTRIES-
> > 1)
> > /* Number of Virtual Functions ACC100 supports */ @@ -574,6 +579,10
> > @@ struct __rte_cache_aligned acc100_queue {
> > struct acc100_device *d;
> > };
> >
> > +typedef void (*acc10x_fcw_ld_fill_fun_t)(struct rte_bbdev_dec_op *op,
> > + struct acc100_fcw_ld *fcw,
> > + union acc100_harq_layout_data *harq_layout);
> > +
> > /* Private data structure for each ACC100 device */ struct
> > acc100_device {
> > void *mmio_base; /**< Base address of MMIO registers (BAR0) */
> @@
> > -605,6 +614,8 @@ struct acc100_device {
> > uint16_t q_assigned_bit_map[ACC100_NUM_QGRPS];
> > bool pf_device; /**< True if this is a PF ACC100 device */
> > bool configured; /**< True if this ACC100 device is configured */
> > + uint16_t device_variant; /**< Device variant */
> > + acc10x_fcw_ld_fill_fun_t fcw_ld_fill; /**< 5GUL FCW generation
> > function */
> > };
> >
> > /**
> > diff --git a/drivers/baseband/acc100/rte_acc101_pmd.h
> > b/drivers/baseband/acc100/rte_acc101_pmd.h
> > new file mode 100644
> > index 0000000..8f1f4ab
> > --- /dev/null
> > +++ b/drivers/baseband/acc100/rte_acc101_pmd.h
>
> This file is internal, shouldn't we drop the rte?
There is lack of consistency on the filenaming really historically, still will update the new file. Thanks
>
>
> > @@ -0,0 +1,55 @@
> > +/* SPDX-License-Identifier: BSD-3-Clause
> > + * Copyright(c) 2022 Intel Corporation */
> > +
> > +/* ACC101 PCI vendor & device IDs */
> > +#define RTE_ACC101_VENDOR_ID (0x8086)
> > +#define RTE_ACC101_PF_DEVICE_ID (0x57c4)
> > +#define RTE_ACC101_VF_DEVICE_ID (0x57c5)
> > +
> > +/* Define as 1 to use only a single FEC engine */ #ifndef
> > +RTE_ACC101_SINGLE_FEC #define RTE_ACC101_SINGLE_FEC 0 #endif
>
> Also the above defines should drop RTE if they are internal symbols.
This is historical as well but will update on current code first with additional commit.
Thanks
>
> > +
> > +/* Number of Virtual Functions ACC101 supports */
> > +#define ACC101_NUM_VFS 16
> > +#define ACC101_NUM_QGRPS 8
> > +#define ACC101_NUM_AQS 16
> > +/* All ACC101 Registers alignment are 32bits = 4B */
> > +#define ACC101_BYTES_IN_WORD 4
> > +
> > +#define ACC101_TMPL_PRI_0 0x03020100
> > +#define ACC101_TMPL_PRI_1 0x07060504
> > +#define ACC101_TMPL_PRI_2 0x0b0a0908
> > +#define ACC101_TMPL_PRI_3 0x0f0e0d0c
> > +#define ACC101_WORDS_IN_ARAM_SIZE (128 * 1024 / 4)
> > +
> > +#define ACC101_NUM_TMPL 32
> > +/* Mapping of signals for the available engines */
> > +#define ACC101_SIG_UL_5G 0
> > +#define ACC101_SIG_UL_5G_LAST 8
> > +#define ACC101_SIG_DL_5G 13
> > +#define ACC101_SIG_DL_5G_LAST 15
> > +#define ACC101_SIG_UL_4G 16
> > +#define ACC101_SIG_UL_4G_LAST 19
> > +#define ACC101_SIG_DL_4G 27
> > +#define ACC101_SIG_DL_4G_LAST 31
> > +#define ACC101_NUM_ACCS 5
> > +#define ACC101_PF_VAL 2
> > +
> > +/* ACC101 Configuration */
> > +#define ACC101_CFG_DMA_ERROR 0x3D7
> > +#define ACC101_CFG_AXI_CACHE 0x11
> > +#define ACC101_CFG_QMGR_HI_P 0x0F0F
> > +#define ACC101_CFG_PCI_AXI 0xC003
> > +#define ACC101_CFG_PCI_BRIDGE 0x40006033
> > +#define ACC101_ENGINE_OFFSET 0x1000
> > +#define ACC101_LONG_WAIT 1000
> > +#define ACC101_GPEX_AXIMAP_NUM 17
> > +#define ACC101_CLOCK_GATING_EN 0x30000
> > +#define ACC101_DMA_INBOUND 0x104
> > +/* DDR Size per VF - 512MB by default
> > + * Can be increased up to 4 GB with single PF/VF */
> > +#define ACC101_HARQ_DDR (512 * 1)
> > --
> > 1.8.3.1
@@ -1318,6 +1318,7 @@ F: doc/guides/bbdevs/features/fpga_5gnr_fec.ini
F: drivers/baseband/acc100/
F: doc/guides/bbdevs/acc100.rst
F: doc/guides/bbdevs/features/acc100.ini
+F: doc/guides/bbdevs/features/acc101.ini
Null baseband
M: Nicolas Chautru <nicolas.chautru@intel.com>
@@ -1,17 +1,19 @@
.. SPDX-License-Identifier: BSD-3-Clause
Copyright(c) 2020 Intel Corporation
-Intel(R) ACC100 5G/4G FEC Poll Mode Driver
-==========================================
+Intel(R) ACC100 and ACC101 5G/4G FEC Poll Mode Drivers
+======================================================
The BBDEV ACC100 5G/4G FEC poll mode driver (PMD) supports an
implementation of a VRAN FEC wireless acceleration function.
This device is also known as Mount Bryce.
+The BBDEV ACC101, also known as Mount Cirrus, is a derivative device from Mount Bryce
+with functional and capacity improvements but still with the same exposed BBDEV capabilities.
Features
--------
-ACC100 5G/4G FEC PMD supports the following features:
+ACC100 and ACC101 5G/4G FEC PMDs support the following features:
- LDPC Encode in the DL (5GNR)
- LDPC Decode in the UL (5GNR)
@@ -23,7 +25,7 @@ ACC100 5G/4G FEC PMD supports the following features:
- MSI
- SR-IOV
-ACC100 5G/4G FEC PMD supports the following BBDEV capabilities:
+ACC100 and ACC101 5G/4G FEC PMDs support the following BBDEV capabilities:
* For the LDPC encode operation:
- ``RTE_BBDEV_LDPC_CRC_24B_ATTACH`` : set to attach CRC24B to CB(s)
@@ -80,14 +82,16 @@ hugepage configuration of a server may be examined using:
Initialization
--------------
-When the device first powers up, its PCI Physical Functions (PF) can be listed through this command:
+When the device first powers up, its PCI Physical Functions (PF) can be listed through these
+commands for ACC100 and ACC101 respectively:
.. code-block:: console
sudo lspci -vd8086:0d5c
+ sudo lspci -vd8086:57c4
The physical and virtual functions are compatible with Linux UIO drivers:
-``vfio`` and ``igb_uio``. However, in order to work the ACC100 5G/4G
+``vfio`` and ``igb_uio``. However, in order to work the 5G/4G
FEC device first needs to be bound to one of these linux drivers through DPDK.
@@ -97,7 +101,8 @@ Bind PF UIO driver(s)
Install the DPDK igb_uio driver, bind it with the PF PCI device ID and use
``lspci`` to confirm the PF device is under use by ``igb_uio`` DPDK UIO driver.
-The igb_uio driver may be bound to the PF PCI device using one of two methods:
+The igb_uio driver may be bound to the PF PCI device using one of two methods for ACC100
+(for ACC101 the device id ``57c4`` should be used in lieu of ``0d5c``):
1. PCI functions (physical or virtual, depending on the use case) can be bound to
@@ -121,7 +126,7 @@ the UIO driver by repeating this command for every function.
where the PCI device ID (example: 0000:06:00.0) is obtained using lspci -vd8086:0d5c
-In a similar way the ACC100 5G/4G FEC PF may be bound with vfio-pci as any PCIe device.
+In a similar way the 5G/4G FEC PF may be bound with vfio-pci as any PCIe device.
Enable Virtual Functions
@@ -167,14 +172,14 @@ queues, priorities, load balance, bandwidth and other settings necessary for the
device to perform FEC functions.
This configuration needs to be executed at least once after reboot or PCI FLR and can
-be achieved by using the function ``acc100_configure()``, which sets up the
-parameters defined in ``acc100_conf`` structure.
+be achieved by using the functions ``acc100_configure()`` or ``acc101_configure()``,
+which sets up the parameters defined in the compatible ``acc100_conf`` structure.
Test Application
----------------
BBDEV provides a test application, ``test-bbdev.py`` and range of test data for testing
-the functionality of ACC100 5G/4G FEC encode and decode, depending on the device's
+the functionality of the device 5G/4G FEC encode and decode, depending on the device's
capabilities. The test application is located under app->test-bbdev folder and has the
following options:
@@ -212,7 +217,7 @@ Test Vectors
In addition to the simple LDPC decoder and LDPC encoder tests, bbdev also provides
a range of additional tests under the test_vectors folder, which may be useful. The results
-of these tests will depend on the ACC100 5G/4G FEC capabilities which may cause some
+of these tests will depend on the device 5G/4G FEC capabilities which may cause some
testcases to be skipped, but no failure should be reported.
@@ -233,3 +238,11 @@ Specifically for the BBDEV ACC100 PMD, the command below can be used:
./pf_bb_config ACC100 -c acc100/acc100_config_vf_5g.cfg
./test-bbdev.py -e="-c 0xff0 -a${VF_PCI_ADDR}" -c validation -n 64 -b 32 -l 1 -v ./ldpc_dec_default.data
+
+Specifically for the BBDEV ACC101 PMD, the command below can be used:
+
+.. code-block:: console
+
+ ./pf_bb_config ACC101 -c acc101/acc101_config_2vf_4g5g.cfg
+ ./test-bbdev.py -e="-c 0xff0 -a${VF_PCI_ADDR}" -c validation -n 64 -b 32 -l 1 -v ./ldpc_dec_default.data
+
new file mode 100644
@@ -0,0 +1,13 @@
+;
+; Supported features of the 'acc101' bbdev driver.
+;
+; Refer to default.ini for the full list of available PMD features.
+;
+[Features]
+Turbo Decoder (4G) = Y
+Turbo Encoder (4G) = Y
+LDPC Decoder (5G) = Y
+LDPC Encoder (5G) = Y
+LLR/HARQ Compression = Y
+External DDR Access = Y
+HW Accelerated = Y
@@ -104,6 +104,9 @@ New Features
* ``RTE_EVENT_QUEUE_ATTR_WEIGHT``
* ``RTE_EVENT_QUEUE_ATTR_AFFINITY``
+* **Added Intel ACC101 baseband PMD.**
+
+ * Added a new baseband PMD for Intel ACC101 device.
Removed Items
-------------
@@ -22,6 +22,7 @@
#include <rte_bbdev.h>
#include <rte_bbdev_pmd.h>
#include "rte_acc100_pmd.h"
+#include "rte_acc101_pmd.h"
#ifdef RTE_LIBRTE_BBDEV_DEBUG
RTE_LOG_REGISTER_DEFAULT(acc100_logtype, DEBUG);
@@ -1133,7 +1134,10 @@
/* ACC100 PCI PF address map */
static struct rte_pci_id pci_id_acc100_pf_map[] = {
{
- RTE_PCI_DEVICE(RTE_ACC100_VENDOR_ID, RTE_ACC100_PF_DEVICE_ID)
+ RTE_PCI_DEVICE(RTE_ACC100_VENDOR_ID, RTE_ACC100_PF_DEVICE_ID),
+ },
+ {
+ RTE_PCI_DEVICE(RTE_ACC101_VENDOR_ID, RTE_ACC101_PF_DEVICE_ID),
},
{.device_id = 0},
};
@@ -1141,7 +1145,10 @@
/* ACC100 PCI VF address map */
static struct rte_pci_id pci_id_acc100_vf_map[] = {
{
- RTE_PCI_DEVICE(RTE_ACC100_VENDOR_ID, RTE_ACC100_VF_DEVICE_ID)
+ RTE_PCI_DEVICE(RTE_ACC100_VENDOR_ID, RTE_ACC100_VF_DEVICE_ID),
+ },
+ {
+ RTE_PCI_DEVICE(RTE_ACC101_VENDOR_ID, RTE_ACC101_VF_DEVICE_ID),
},
{.device_id = 0},
};
@@ -1290,7 +1297,7 @@
/* Fill in a frame control word for LDPC decoding. */
static inline void
-acc100_fcw_ld_fill(const struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
+acc100_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
union acc100_harq_layout_data *harq_layout)
{
uint16_t harq_out_length, harq_in_length, ncb_p, k0_p, parity_offset;
@@ -1414,6 +1421,128 @@
}
}
+/* Convert offset to harq index for harq_layout structure */
+static inline uint32_t hq_index(uint32_t offset)
+{
+ return (offset >> ACC100_HARQ_OFFSET_SHIFT) & ACC100_HARQ_OFFSET_MASK;
+}
+
+/* Fill in a frame control word for LDPC decoding for ACC101 */
+static inline void
+acc101_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
+ union acc100_harq_layout_data *harq_layout)
+{
+ uint16_t harq_out_length, harq_in_length, ncb_p, k0_p, parity_offset;
+ uint32_t harq_index;
+ uint32_t l;
+
+ fcw->qm = op->ldpc_dec.q_m;
+ fcw->nfiller = op->ldpc_dec.n_filler;
+ fcw->BG = (op->ldpc_dec.basegraph - 1);
+ fcw->Zc = op->ldpc_dec.z_c;
+ fcw->ncb = op->ldpc_dec.n_cb;
+ fcw->k0 = get_k0(fcw->ncb, fcw->Zc, op->ldpc_dec.basegraph,
+ op->ldpc_dec.rv_index);
+ if (op->ldpc_dec.code_block_mode == RTE_BBDEV_CODE_BLOCK)
+ fcw->rm_e = op->ldpc_dec.cb_params.e;
+ else
+ fcw->rm_e = (op->ldpc_dec.tb_params.r <
+ op->ldpc_dec.tb_params.cab) ?
+ op->ldpc_dec.tb_params.ea :
+ op->ldpc_dec.tb_params.eb;
+
+ if (unlikely(check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE) &&
+ (op->ldpc_dec.harq_combined_input.length == 0))) {
+ rte_bbdev_log(WARNING, "Null HARQ input size provided");
+ /* Disable HARQ input in that case to carry forward */
+ op->ldpc_dec.op_flags ^= RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE;
+ }
+
+ fcw->hcin_en = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE);
+ fcw->hcout_en = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_HQ_COMBINE_OUT_ENABLE);
+ fcw->crc_select = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_CRC_TYPE_24B_CHECK);
+ fcw->bypass_dec = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_DECODE_BYPASS);
+ fcw->bypass_intlv = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_DEINTERLEAVER_BYPASS);
+ if (op->ldpc_dec.q_m == 1) {
+ fcw->bypass_intlv = 1;
+ fcw->qm = 2;
+ }
+ fcw->hcin_decomp_mode = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION);
+ fcw->hcout_comp_mode = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION);
+ fcw->llr_pack_mode = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_LLR_COMPRESSION);
+ harq_index = hq_index(op->ldpc_dec.harq_combined_output.offset);
+ if (fcw->hcin_en > 0) {
+ harq_in_length = op->ldpc_dec.harq_combined_input.length;
+ if (fcw->hcin_decomp_mode > 0)
+ harq_in_length = harq_in_length * 8 / 6;
+ harq_in_length = RTE_MIN(harq_in_length, op->ldpc_dec.n_cb
+ - op->ldpc_dec.n_filler);
+ /* Alignment on next 64B - Already enforced from HC output */
+ harq_in_length = RTE_ALIGN_FLOOR(harq_in_length, 64);
+ fcw->hcin_size0 = harq_in_length;
+ fcw->hcin_offset = 0;
+ fcw->hcin_size1 = 0;
+ } else {
+ fcw->hcin_size0 = 0;
+ fcw->hcin_offset = 0;
+ fcw->hcin_size1 = 0;
+ }
+
+ fcw->itmax = op->ldpc_dec.iter_max;
+ fcw->itstop = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_ITERATION_STOP_ENABLE);
+ fcw->synd_precoder = fcw->itstop;
+ /*
+ * These are all implicitly set
+ * fcw->synd_post = 0;
+ * fcw->so_en = 0;
+ * fcw->so_bypass_rm = 0;
+ * fcw->so_bypass_intlv = 0;
+ * fcw->dec_convllr = 0;
+ * fcw->hcout_convllr = 0;
+ * fcw->hcout_size1 = 0;
+ * fcw->so_it = 0;
+ * fcw->hcout_offset = 0;
+ * fcw->negstop_th = 0;
+ * fcw->negstop_it = 0;
+ * fcw->negstop_en = 0;
+ * fcw->gain_i = 1;
+ * fcw->gain_h = 1;
+ */
+ if (fcw->hcout_en > 0) {
+ parity_offset = (op->ldpc_dec.basegraph == 1 ? 20 : 8)
+ * op->ldpc_dec.z_c - op->ldpc_dec.n_filler;
+ k0_p = (fcw->k0 > parity_offset) ?
+ fcw->k0 - op->ldpc_dec.n_filler : fcw->k0;
+ ncb_p = fcw->ncb - op->ldpc_dec.n_filler;
+ l = RTE_MIN(k0_p + fcw->rm_e, INT16_MAX);
+ harq_out_length = (uint16_t) fcw->hcin_size0;
+ harq_out_length = RTE_MAX(harq_out_length, l);
+ /* Cannot exceed the pruned Ncb circular buffer */
+ harq_out_length = RTE_MIN(harq_out_length, ncb_p);
+ /* Alignment on next 64B */
+ harq_out_length = RTE_ALIGN_CEIL(harq_out_length, 64);
+ fcw->hcout_size0 = harq_out_length;
+ fcw->hcout_size1 = 0;
+ fcw->hcout_offset = 0;
+ harq_layout[harq_index].offset = fcw->hcout_offset;
+ harq_layout[harq_index].size0 = fcw->hcout_size0;
+ } else {
+ fcw->hcout_size0 = 0;
+ fcw->hcout_size1 = 0;
+ fcw->hcout_offset = 0;
+ }
+}
+
/**
* Fills descriptor with data pointers of one block type.
*
@@ -2966,7 +3095,7 @@
struct acc100_fcw_ld *fcw;
uint32_t seg_total_left;
fcw = &desc->req.fcw_ld;
- acc100_fcw_ld_fill(op, fcw, harq_layout);
+ q->d->fcw_ld_fill(op, fcw, harq_layout);
/* Special handling when overusing mbuf */
if (fcw->rm_e < ACC100_MAX_E_MBUF)
@@ -3033,7 +3162,7 @@
desc = q->ring_addr + desc_idx;
uint64_t fcw_offset = (desc_idx << 8) + ACC100_DESC_FCW_OFFSET;
union acc100_harq_layout_data *harq_layout = q->d->harq_layout;
- acc100_fcw_ld_fill(op, &desc->req.fcw_ld, harq_layout);
+ q->d->fcw_ld_fill(op, &desc->req.fcw_ld, harq_layout);
input = op->ldpc_dec.input.data;
h_output_head = h_output = op->ldpc_dec.hard_output.data;
@@ -4145,9 +4274,19 @@
dev->dequeue_ldpc_enc_ops = acc100_dequeue_ldpc_enc;
dev->dequeue_ldpc_dec_ops = acc100_dequeue_ldpc_dec;
+ /* Device variant specific handling */
+ if ((pci_dev->id.device_id == RTE_ACC100_PF_DEVICE_ID) ||
+ (pci_dev->id.device_id == RTE_ACC100_VF_DEVICE_ID)) {
+ ((struct acc100_device *) dev->data->dev_private)->device_variant = ACC100_VARIANT;
+ ((struct acc100_device *) dev->data->dev_private)->fcw_ld_fill = acc100_fcw_ld_fill;
+ } else {
+ ((struct acc100_device *) dev->data->dev_private)->device_variant = ACC101_VARIANT;
+ ((struct acc100_device *) dev->data->dev_private)->fcw_ld_fill = acc101_fcw_ld_fill;
+ }
+
((struct acc100_device *) dev->data->dev_private)->pf_device =
- !strcmp(drv->driver.name,
- RTE_STR(ACC100PF_DRIVER_NAME));
+ !strcmp(drv->driver.name, RTE_STR(ACC100PF_DRIVER_NAME));
+
((struct acc100_device *) dev->data->dev_private)->mmio_base =
pci_dev->mem_resource[0].addr;
@@ -22,6 +22,9 @@
#define rte_bbdev_log_debug(fmt, ...)
#endif
+#define ACC100_VARIANT 0
+#define ACC101_VARIANT 1
+
/* ACC100 PF and VF driver names */
#define ACC100PF_DRIVER_NAME intel_acc100_pf
#define ACC100VF_DRIVER_NAME intel_acc100_vf
@@ -67,6 +70,8 @@
#define ACC100_HARQ_LAYOUT (64*1024*1024)
/* Assume offset for HARQ in memory */
#define ACC100_HARQ_OFFSET (32*1024)
+#define ACC100_HARQ_OFFSET_SHIFT 15
+#define ACC100_HARQ_OFFSET_MASK 0x7ffffff
/* Mask used to calculate an index in an Info Ring array (not a byte offset) */
#define ACC100_INFO_RING_MASK (ACC100_INFO_RING_NUM_ENTRIES-1)
/* Number of Virtual Functions ACC100 supports */
@@ -574,6 +579,10 @@ struct __rte_cache_aligned acc100_queue {
struct acc100_device *d;
};
+typedef void (*acc10x_fcw_ld_fill_fun_t)(struct rte_bbdev_dec_op *op,
+ struct acc100_fcw_ld *fcw,
+ union acc100_harq_layout_data *harq_layout);
+
/* Private data structure for each ACC100 device */
struct acc100_device {
void *mmio_base; /**< Base address of MMIO registers (BAR0) */
@@ -605,6 +614,8 @@ struct acc100_device {
uint16_t q_assigned_bit_map[ACC100_NUM_QGRPS];
bool pf_device; /**< True if this is a PF ACC100 device */
bool configured; /**< True if this ACC100 device is configured */
+ uint16_t device_variant; /**< Device variant */
+ acc10x_fcw_ld_fill_fun_t fcw_ld_fill; /**< 5GUL FCW generation function */
};
/**
new file mode 100644
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Intel Corporation
+ */
+
+/* ACC101 PCI vendor & device IDs */
+#define RTE_ACC101_VENDOR_ID (0x8086)
+#define RTE_ACC101_PF_DEVICE_ID (0x57c4)
+#define RTE_ACC101_VF_DEVICE_ID (0x57c5)
+
+/* Define as 1 to use only a single FEC engine */
+#ifndef RTE_ACC101_SINGLE_FEC
+#define RTE_ACC101_SINGLE_FEC 0
+#endif
+
+/* Number of Virtual Functions ACC101 supports */
+#define ACC101_NUM_VFS 16
+#define ACC101_NUM_QGRPS 8
+#define ACC101_NUM_AQS 16
+/* All ACC101 Registers alignment are 32bits = 4B */
+#define ACC101_BYTES_IN_WORD 4
+
+#define ACC101_TMPL_PRI_0 0x03020100
+#define ACC101_TMPL_PRI_1 0x07060504
+#define ACC101_TMPL_PRI_2 0x0b0a0908
+#define ACC101_TMPL_PRI_3 0x0f0e0d0c
+#define ACC101_WORDS_IN_ARAM_SIZE (128 * 1024 / 4)
+
+#define ACC101_NUM_TMPL 32
+/* Mapping of signals for the available engines */
+#define ACC101_SIG_UL_5G 0
+#define ACC101_SIG_UL_5G_LAST 8
+#define ACC101_SIG_DL_5G 13
+#define ACC101_SIG_DL_5G_LAST 15
+#define ACC101_SIG_UL_4G 16
+#define ACC101_SIG_UL_4G_LAST 19
+#define ACC101_SIG_DL_4G 27
+#define ACC101_SIG_DL_4G_LAST 31
+#define ACC101_NUM_ACCS 5
+#define ACC101_PF_VAL 2
+
+/* ACC101 Configuration */
+#define ACC101_CFG_DMA_ERROR 0x3D7
+#define ACC101_CFG_AXI_CACHE 0x11
+#define ACC101_CFG_QMGR_HI_P 0x0F0F
+#define ACC101_CFG_PCI_AXI 0xC003
+#define ACC101_CFG_PCI_BRIDGE 0x40006033
+#define ACC101_ENGINE_OFFSET 0x1000
+#define ACC101_LONG_WAIT 1000
+#define ACC101_GPEX_AXIMAP_NUM 17
+#define ACC101_CLOCK_GATING_EN 0x30000
+#define ACC101_DMA_INBOUND 0x104
+/* DDR Size per VF - 512MB by default
+ * Can be increased up to 4 GB with single PF/VF
+ */
+#define ACC101_HARQ_DDR (512 * 1)