diff mbox series

[v6,04/14] baseband/acc: introduce PMD for ACC200

Message ID 20220924005048.20302-5-nicolas.chautru@intel.com (mailing list archive)
State Superseded, archived
Delegated to: akhil goyal
Headers show
Series [v6,01/14] baseband/acc100: remove unused registers | expand

Checks

Context Check Description
ci/checkpatch success coding style OK

Commit Message

Chautru, Nicolas Sept. 24, 2022, 12:50 a.m. UTC
This patch introduces stubs for device driver for the ACC200
integrated VRAN accelerator on SPR-EEC

Signed-off-by: Nicolas Chautru <nicolas.chautru@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
 MAINTAINERS                           |   3 +
 doc/guides/bbdevs/acc200.rst          | 244 ++++++++++++++++++++++++++
 doc/guides/bbdevs/index.rst           |   1 +
 drivers/baseband/acc/acc200_pmd.h     |  32 ++++
 drivers/baseband/acc/meson.build      |   2 +-
 drivers/baseband/acc/rte_acc200_pmd.c | 144 +++++++++++++++
 6 files changed, 425 insertions(+), 1 deletion(-)
 create mode 100644 doc/guides/bbdevs/acc200.rst
 create mode 100644 drivers/baseband/acc/acc200_pmd.h
 create mode 100644 drivers/baseband/acc/rte_acc200_pmd.c
diff mbox series

Patch

diff --git a/MAINTAINERS b/MAINTAINERS
index 52afd5d2e0..909c855048 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1340,6 +1340,9 @@  F: drivers/baseband/acc/
 F: doc/guides/bbdevs/acc100.rst
 F: doc/guides/bbdevs/features/acc100.ini
 F: doc/guides/bbdevs/features/acc101.ini
+F: drivers/baseband/acc200/
+F: doc/guides/bbdevs/acc200.rst
+F: doc/guides/bbdevs/features/acc200.ini
 
 Null baseband
 M: Nicolas Chautru <nicolas.chautru@intel.com>
diff --git a/doc/guides/bbdevs/acc200.rst b/doc/guides/bbdevs/acc200.rst
new file mode 100644
index 0000000000..c5e1bd7890
--- /dev/null
+++ b/doc/guides/bbdevs/acc200.rst
@@ -0,0 +1,244 @@ 
+..  SPDX-License-Identifier: BSD-3-Clause
+    Copyright(c) 2022 Intel Corporation
+
+Intel(R) ACC200 vRAN Dedicated Accelerator Poll Mode Driver
+===========================================================
+
+The Intel® vRAN Dedicated Accelerator ACC200 peripheral enables cost-effective 4G
+and 5G next-generation virtualized Radio Access Network (vRAN) solutions integrated on
+Sapphire Rapids EEC Intel(R)7 based Xeon(R) multi-core Serverprocessor.
+
+Features
+--------
+
+The ACC200 includes a 5G Low Density Parity Check (LDPC) encoder/decoder, rate match/dematch,
+Hybrid Automatic Repeat Request (HARQ) with access to DDR memory for buffer management, a 4G
+Turbo encoder/decoder, a Fast Fourier Transform (FFT) block providing DFT/iDFT processing offload
+for the 5G Sounding Reference Signal (SRS), a Queue Manager (QMGR), and a DMA subsystem.
+There is no dedicated on-card memory for HARQ, this is using coherent memory on the CPU side.
+
+These correspond to the following features exposed by the PMD:
+
+- LDPC Encode in the Downlink (5GNR)
+- LDPC Decode in the Uplink (5GNR)
+- Turbo Encode in the Downlink (4G)
+- Turbo Decode in the Uplink (4G)
+- FFT processing
+- SR-IOV with 16 VFs per PF
+- Maximum of 256 queues per VF
+- MSI
+
+ACC200 PMD supports the following BBDEV capabilities:
+
+* For the LDPC encode operation:
+   - ``RTE_BBDEV_LDPC_CRC_24B_ATTACH`` :  set to attach CRC24B to CB(s)
+   - ``RTE_BBDEV_LDPC_RATE_MATCH`` :  if set then do not do Rate Match bypass
+   - ``RTE_BBDEV_LDPC_INTERLEAVER_BYPASS`` : if set then bypass interleaver
+
+* For the LDPC decode operation:
+   - ``RTE_BBDEV_LDPC_CRC_TYPE_24B_CHECK`` :  check CRC24B from CB(s)
+   - ``RTE_BBDEV_LDPC_CRC_TYPE_24B_DROP`` :  drops CRC24B bits appended while decoding
+   - ``RTE_BBDEV_LDPC_CRC_TYPE_24A_CHECK`` :  check CRC24A from CB(s)
+   - ``RTE_BBDEV_LDPC_CRC_TYPE_16_CHECK`` :  check CRC16 from CB(s)
+   - ``RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE`` :  provides an input for HARQ combining
+   - ``RTE_BBDEV_LDPC_HQ_COMBINE_OUT_ENABLE`` :  provides an input for HARQ combining
+   - ``RTE_BBDEV_LDPC_ITERATION_STOP_ENABLE`` :  disable early termination
+   - ``RTE_BBDEV_LDPC_DEC_SCATTER_GATHER`` :  supports scatter-gather for input/output data
+   - ``RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION`` :  supports compression of the HARQ input/output
+   - ``RTE_BBDEV_LDPC_LLR_COMPRESSION`` :  supports LLR input compression
+
+* For the turbo encode operation:
+   - ``RTE_BBDEV_TURBO_CRC_24B_ATTACH`` :  set to attach CRC24B to CB(s)
+   - ``RTE_BBDEV_TURBO_RATE_MATCH`` :  if set then do not do Rate Match bypass
+   - ``RTE_BBDEV_TURBO_ENC_INTERRUPTS`` :  set for encoder dequeue interrupts
+   - ``RTE_BBDEV_TURBO_RV_INDEX_BYPASS`` :  set to bypass RV index
+   - ``RTE_BBDEV_TURBO_ENC_SCATTER_GATHER`` :  supports scatter-gather for input/output data
+
+* For the turbo decode operation:
+   - ``RTE_BBDEV_TURBO_CRC_TYPE_24B`` :  check CRC24B from CB(s)
+   - ``RTE_BBDEV_TURBO_SUBBLOCK_DEINTERLEAVE`` :  perform subblock de-interleave
+   - ``RTE_BBDEV_TURBO_DEC_INTERRUPTS`` :  set for decoder dequeue interrupts
+   - ``RTE_BBDEV_TURBO_NEG_LLR_1_BIT_IN`` :  set if negative LLR input is supported
+   - ``RTE_BBDEV_TURBO_DEC_TB_CRC_24B_KEEP`` :  keep CRC24B bits appended while decoding
+   - ``RTE_BBDEV_TURBO_DEC_CRC_24B_DROP`` : option to drop the code block CRC after decoding
+   - ``RTE_BBDEV_TURBO_EARLY_TERMINATION`` :  set early termination feature
+   - ``RTE_BBDEV_TURBO_DEC_SCATTER_GATHER`` :  supports scatter-gather for input/output data
+   - ``RTE_BBDEV_TURBO_HALF_ITERATION_EVEN`` :  set half iteration granularity
+   - ``RTE_BBDEV_TURBO_SOFT_OUTPUT`` :  set the APP LLR soft output
+   - ``RTE_BBDEV_TURBO_EQUALIZER`` :  set the turbo equalizer feature
+   - ``RTE_BBDEV_TURBO_SOFT_OUT_SATURATE`` :  set the soft output saturation
+   - ``RTE_BBDEV_TURBO_CONTINUE_CRC_MATCH`` :  set to run an extra odd iteration after CRC match
+   - ``RTE_BBDEV_TURBO_NEG_LLR_1_BIT_SOFT_OUT`` :  set if negative APP LLR output supported
+   - ``RTE_BBDEV_TURBO_MAP_DEC`` :  supports flexible parallel MAP engine decoding
+
+Installation
+------------
+
+Section 3 of the DPDK manual provides instructions on installing and compiling DPDK.
+
+DPDK requires hugepages to be configured as detailed in section 2 of the DPDK manual.
+The bbdev test application has been tested with a configuration 40 x 1GB hugepages. The
+hugepage configuration of a server may be examined using:
+
+.. code-block:: console
+
+   grep Huge* /proc/meminfo
+
+
+Initialization
+--------------
+
+When the device first powers up, its PCI Physical Functions (PF) can be listed through these
+commands for ACC200:
+
+.. code-block:: console
+
+  sudo lspci -vd8086:57c0
+
+The physical and virtual functions are compatible with Linux UIO drivers:
+``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.
+
+
+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 for ACC200:
+
+
+1. PCI functions (physical or virtual, depending on the use case) can be bound to
+the UIO driver by repeating this command for every function.
+
+.. code-block:: console
+
+  cd <dpdk-top-level-directory>
+  insmod ./build/kmod/igb_uio.ko
+  echo "8086 57c0" > /sys/bus/pci/drivers/igb_uio/new_id
+  lspci -vd8086:57c0
+
+
+2. Another way to bind PF with DPDK UIO driver is by using the ``dpdk-devbind.py`` tool
+
+.. code-block:: console
+
+  cd <dpdk-top-level-directory>
+  ./usertools/dpdk-devbind.py -b igb_uio 0000:f7:00.0
+
+where the PCI device ID (example: 0000:f7:00.0) is obtained using lspci -vd8086:57c0
+
+
+In a similar way the PF may be bound with vfio-pci as any PCIe device.
+
+
+Enable Virtual Functions
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+Now, it should be visible in the printouts that PCI PF is under igb_uio control
+"``Kernel driver in use: igb_uio``"
+
+To show the number of available VFs on the device, read ``sriov_totalvfs`` file..
+
+.. code-block:: console
+
+  cat /sys/bus/pci/devices/0000\:<b>\:<d>.<f>/sriov_totalvfs
+
+  where 0000\:<b>\:<d>.<f> is the PCI device ID
+
+
+To enable VFs via igb_uio, echo the number of virtual functions intended to
+enable to ``max_vfs`` file..
+
+.. code-block:: console
+
+  echo <num-of-vfs> > /sys/bus/pci/devices/0000\:<b>\:<d>.<f>/max_vfs
+
+
+Afterwards, all VFs must be bound to appropriate UIO drivers as required, same
+way it was done with the physical function previously.
+
+Enabling SR-IOV via vfio driver is pretty much the same, except that the file
+name is different:
+
+.. code-block:: console
+
+  echo <num-of-vfs> > /sys/bus/pci/devices/0000\:<b>\:<d>.<f>/sriov_numvfs
+
+
+Configure the VFs through PF
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The PCI virtual functions must be configured before working or getting assigned
+to VMs/Containers. The configuration involves allocating the number of hardware
+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 functions ``rte_acc200_configure()``,
+which sets up the parameters defined in the compatible ``acc200_conf`` structure.
+
+Test Application
+----------------
+
+BBDEV provides a test application, ``test-bbdev.py`` and range of test data for testing
+the functionality of the device, depending on the device's
+capabilities. The test application is located under app->test-bbdev folder and has the
+following options:
+
+.. code-block:: console
+
+  "-p", "--testapp-path": specifies path to the bbdev test app.
+  "-e", "--eal-params"	: EAL arguments which are passed to the test app.
+  "-t", "--timeout"	: Timeout in seconds (default=300).
+  "-c", "--test-cases"	: Defines test cases to run. Run all if not specified.
+  "-v", "--test-vector"	: Test vector path (default=dpdk_path+/app/test-bbdev/test_vectors/bbdev_null.data).
+  "-n", "--num-ops"	: Number of operations to process on device (default=32).
+  "-b", "--burst-size"	: Operations enqueue/dequeue burst size (default=32).
+  "-s", "--snr"		: SNR in dB used when generating LLRs for bler tests.
+  "-s", "--iter_max"	: Number of iterations for LDPC decoder.
+  "-l", "--num-lcores"	: Number of lcores to run (default=16).
+  "-i", "--init-device" : Initialise PF device with default values.
+
+
+To execute the test application tool using simple decode or encode data,
+type one of the following:
+
+.. code-block:: console
+
+  ./test-bbdev.py -c validation -n 64 -b 1 -v ./ldpc_dec_default.data
+  ./test-bbdev.py -c validation -n 64 -b 1 -v ./ldpc_enc_default.data
+
+
+The test application ``test-bbdev.py``, supports the ability to configure the PF device with
+a default set of values, if the "-i" or "- -init-device" option is included. The default values
+are defined in test_bbdev_perf.c.
+
+
+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 device capabilities which may cause some
+testcases to be skipped, but no failure should be reported.
+
+
+Alternate Baseband Device configuration tool
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+On top of the embedded configuration feature supported in test-bbdev using "- -init-device"
+option mentioned above, there is also a tool available to perform that device configuration
+using a companion application.
+The ``pf_bb_config`` application notably enables then to run bbdev-test from the VF
+and not only limited to the PF as captured above.
+
+See for more details: https://github.com/intel/pf-bb-config
+
+Specifically for the BBDEV ACC200 PMD, the command below can be used:
+
+.. code-block:: console
+
+  ./pf_bb_config ACC200 -c ./acc200/acc200_config_vf_5g.cfg
+  ./test-bbdev.py -e="-c 0xff0 -a${VF_PCI_ADDR}" -c validation -n 64 -b 64 -l 1 -v ./ldpc_dec_default.data
diff --git a/doc/guides/bbdevs/index.rst b/doc/guides/bbdevs/index.rst
index cedd706fa6..4e9dea8e4c 100644
--- a/doc/guides/bbdevs/index.rst
+++ b/doc/guides/bbdevs/index.rst
@@ -14,4 +14,5 @@  Baseband Device Drivers
     fpga_lte_fec
     fpga_5gnr_fec
     acc100
+    acc200
     la12xx
diff --git a/drivers/baseband/acc/acc200_pmd.h b/drivers/baseband/acc/acc200_pmd.h
new file mode 100644
index 0000000000..aaa6b7753c
--- /dev/null
+++ b/drivers/baseband/acc/acc200_pmd.h
@@ -0,0 +1,32 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Intel Corporation
+ */
+
+#ifndef _RTE_ACC200_PMD_H_
+#define _RTE_ACC200_PMD_H_
+
+#include "acc_common.h"
+
+/* Helper macro for logging */
+#define rte_bbdev_log(level, fmt, ...) \
+	rte_log(RTE_LOG_ ## level, acc200_logtype, fmt "\n", \
+		##__VA_ARGS__)
+
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+#define rte_bbdev_log_debug(fmt, ...) \
+		rte_bbdev_log(DEBUG, "acc200_pmd: " fmt, \
+		##__VA_ARGS__)
+#else
+#define rte_bbdev_log_debug(fmt, ...)
+#endif
+
+/* ACC200 PF and VF driver names */
+#define ACC200PF_DRIVER_NAME           intel_acc200_pf
+#define ACC200VF_DRIVER_NAME           intel_acc200_vf
+
+/* ACC200 PCI vendor & device IDs */
+#define RTE_ACC200_VENDOR_ID           (0x8086)
+#define RTE_ACC200_PF_DEVICE_ID        (0x57C0)
+#define RTE_ACC200_VF_DEVICE_ID        (0x57C1)
+
+#endif /* _RTE_ACC200_PMD_H_ */
diff --git a/drivers/baseband/acc/meson.build b/drivers/baseband/acc/meson.build
index 9a1a3b8b07..63912f0621 100644
--- a/drivers/baseband/acc/meson.build
+++ b/drivers/baseband/acc/meson.build
@@ -3,6 +3,6 @@ 
 
 deps += ['bbdev', 'bus_vdev', 'ring', 'pci', 'bus_pci']
 
-sources = files('rte_acc100_pmd.c')
+sources = files('rte_acc100_pmd.c', 'rte_acc200_pmd.c')
 
 headers = files('rte_acc100_cfg.h')
diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
new file mode 100644
index 0000000000..5554488280
--- /dev/null
+++ b/drivers/baseband/acc/rte_acc200_pmd.c
@@ -0,0 +1,144 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Intel Corporation
+ */
+
+#include <unistd.h>
+
+#include <rte_common.h>
+#include <rte_log.h>
+#include <rte_dev.h>
+#include <rte_malloc.h>
+#include <rte_mempool.h>
+#include <rte_byteorder.h>
+#include <rte_errno.h>
+#include <rte_branch_prediction.h>
+#include <rte_hexdump.h>
+#include <rte_pci.h>
+#include <rte_bus_pci.h>
+#ifdef RTE_BBDEV_OFFLOAD_COST
+#include <rte_cycles.h>
+#endif
+
+#include <rte_bbdev.h>
+#include <rte_bbdev_pmd.h>
+#include "acc200_pmd.h"
+
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+RTE_LOG_REGISTER_DEFAULT(acc200_logtype, DEBUG);
+#else
+RTE_LOG_REGISTER_DEFAULT(acc200_logtype, NOTICE);
+#endif
+
+/* Free memory used for software rings */
+static int
+acc200_dev_close(struct rte_bbdev *dev)
+{
+	RTE_SET_USED(dev);
+	/* Ensure all in flight HW transactions are completed */
+	usleep(ACC_LONG_WAIT);
+	return 0;
+}
+
+
+static const struct rte_bbdev_ops acc200_bbdev_ops = {
+	.close = acc200_dev_close,
+};
+
+/* ACC200 PCI PF address map */
+static struct rte_pci_id pci_id_acc200_pf_map[] = {
+	{
+		RTE_PCI_DEVICE(RTE_ACC200_VENDOR_ID, RTE_ACC200_PF_DEVICE_ID)
+	},
+	{.device_id = 0},
+};
+
+/* ACC200 PCI VF address map */
+static struct rte_pci_id pci_id_acc200_vf_map[] = {
+	{
+		RTE_PCI_DEVICE(RTE_ACC200_VENDOR_ID, RTE_ACC200_VF_DEVICE_ID)
+	},
+	{.device_id = 0},
+};
+
+/* Initialization Function */
+static void
+acc200_bbdev_init(struct rte_bbdev *dev, struct rte_pci_driver *drv)
+{
+	struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(dev->device);
+
+	dev->dev_ops = &acc200_bbdev_ops;
+
+	((struct acc_device *) dev->data->dev_private)->pf_device =
+			!strcmp(drv->driver.name,
+					RTE_STR(ACC200PF_DRIVER_NAME));
+	((struct acc_device *) dev->data->dev_private)->mmio_base =
+			pci_dev->mem_resource[0].addr;
+
+	rte_bbdev_log_debug("Init device %s [%s] @ vaddr %p paddr %#"PRIx64"",
+			drv->driver.name, dev->data->name,
+			(void *)pci_dev->mem_resource[0].addr,
+			pci_dev->mem_resource[0].phys_addr);
+}
+
+static int acc200_pci_probe(struct rte_pci_driver *pci_drv,
+	struct rte_pci_device *pci_dev)
+{
+	struct rte_bbdev *bbdev = NULL;
+	char dev_name[RTE_BBDEV_NAME_MAX_LEN];
+
+	if (pci_dev == NULL) {
+		rte_bbdev_log(ERR, "NULL PCI device");
+		return -EINVAL;
+	}
+
+	rte_pci_device_name(&pci_dev->addr, dev_name, sizeof(dev_name));
+
+	/* Allocate memory to be used privately by drivers */
+	bbdev = rte_bbdev_allocate(pci_dev->device.name);
+	if (bbdev == NULL)
+		return -ENODEV;
+
+	/* allocate device private memory */
+	bbdev->data->dev_private = rte_zmalloc_socket(dev_name,
+			sizeof(struct acc_device), RTE_CACHE_LINE_SIZE,
+			pci_dev->device.numa_node);
+
+	if (bbdev->data->dev_private == NULL) {
+		rte_bbdev_log(CRIT,
+				"Allocate of %zu bytes for device \"%s\" failed",
+				sizeof(struct acc_device), dev_name);
+				rte_bbdev_release(bbdev);
+			return -ENOMEM;
+	}
+
+	/* Fill HW specific part of device structure */
+	bbdev->device = &pci_dev->device;
+	bbdev->intr_handle = pci_dev->intr_handle;
+	bbdev->data->socket_id = pci_dev->device.numa_node;
+
+	/* Invoke ACC200 device initialization function */
+	acc200_bbdev_init(bbdev, pci_drv);
+
+	rte_bbdev_log_debug("Initialised bbdev %s (id = %u)",
+			dev_name, bbdev->data->dev_id);
+	return 0;
+}
+
+static struct rte_pci_driver acc200_pci_pf_driver = {
+		.probe = acc200_pci_probe,
+		.remove = acc_pci_remove,
+		.id_table = pci_id_acc200_pf_map,
+		.drv_flags = RTE_PCI_DRV_NEED_MAPPING
+};
+
+static struct rte_pci_driver acc200_pci_vf_driver = {
+		.probe = acc200_pci_probe,
+		.remove = acc_pci_remove,
+		.id_table = pci_id_acc200_vf_map,
+		.drv_flags = RTE_PCI_DRV_NEED_MAPPING
+};
+
+RTE_PMD_REGISTER_PCI(ACC200PF_DRIVER_NAME, acc200_pci_pf_driver);
+RTE_PMD_REGISTER_PCI_TABLE(ACC200PF_DRIVER_NAME, pci_id_acc200_pf_map);
+RTE_PMD_REGISTER_PCI(ACC200VF_DRIVER_NAME, acc200_pci_vf_driver);
+RTE_PMD_REGISTER_PCI_TABLE(ACC200VF_DRIVER_NAME, pci_id_acc200_vf_map);