[v5,3/5] raw/afu_mf: add HE-LBK AFU driver

Message ID 1653629824-4535-4-git-send-email-wei.huang@intel.com (mailing list archive)
State Superseded, archived
Delegated to: Thomas Monjalon
Headers
Series introduce afu_mf raw device driver |

Checks

Context Check Description
ci/checkpatch success coding style OK

Commit Message

Wei Huang May 27, 2022, 5:37 a.m. UTC
  HE-LBK and HE-MEM-LBK are host exerciser modules in OFS FPGA,
HE-LBK is used to test PCI bus and HE-MEM-LBK is used to test
local memory.
This driver initialize the modules and report test result.

Signed-off-by: Wei Huang <wei.huang@intel.com>
---
 drivers/raw/afu_mf/afu_mf_rawdev.c |   5 +
 drivers/raw/afu_mf/he_lbk.c        | 427 +++++++++++++++++++++++++++++++++++++
 drivers/raw/afu_mf/he_lbk.h        | 121 +++++++++++
 drivers/raw/afu_mf/meson.build     |   2 +-
 drivers/raw/afu_mf/rte_pmd_afu.h   |  14 ++
 5 files changed, 568 insertions(+), 1 deletion(-)
 create mode 100644 drivers/raw/afu_mf/he_lbk.c
 create mode 100644 drivers/raw/afu_mf/he_lbk.h
  

Comments

Zhang, Tianfei June 6, 2022, 1:41 a.m. UTC | #1
> -----Original Message-----
> From: Huang, Wei <wei.huang@intel.com>
> Sent: Friday, May 27, 2022 1:37 PM
> To: dev@dpdk.org; thomas@monjalon.net; nipun.gupta@nxp.com;
> hemant.agrawal@nxp.com
> Cc: stable@dpdk.org; Xu, Rosen <rosen.xu@intel.com>; Zhang, Tianfei
> <tianfei.zhang@intel.com>; Zhang, Qi Z <qi.z.zhang@intel.com>; Huang, Wei
> <wei.huang@intel.com>
> Subject: [PATCH v5 3/5] raw/afu_mf: add HE-LBK AFU driver
> 
> HE-LBK and HE-MEM-LBK are host exerciser modules in OFS FPGA, HE-LBK is
> used to test PCI bus and HE-MEM-LBK is used to test local memory.
> This driver initialize the modules and report test result.
> 
> Signed-off-by: Wei Huang <wei.huang@intel.com>
> ---
>  drivers/raw/afu_mf/afu_mf_rawdev.c |   5 +
>  drivers/raw/afu_mf/he_lbk.c        | 427
> +++++++++++++++++++++++++++++++++++++
>  drivers/raw/afu_mf/he_lbk.h        | 121 +++++++++++
>  drivers/raw/afu_mf/meson.build     |   2 +-
>  drivers/raw/afu_mf/rte_pmd_afu.h   |  14 ++
>  5 files changed, 568 insertions(+), 1 deletion(-)  create mode 100644
> drivers/raw/afu_mf/he_lbk.c  create mode 100644 drivers/raw/afu_mf/he_lbk.h
> 
> diff --git a/drivers/raw/afu_mf/afu_mf_rawdev.c
> b/drivers/raw/afu_mf/afu_mf_rawdev.c
> index 7c18f3b..e91eb21 100644
> --- a/drivers/raw/afu_mf/afu_mf_rawdev.c
> +++ b/drivers/raw/afu_mf/afu_mf_rawdev.c
> @@ -20,16 +20,21 @@
>  #include "rte_pmd_afu.h"
>  #include "afu_mf_rawdev.h"
>  #include "n3000_afu.h"
> +#include "he_lbk.h"
> 
>  #define AFU_MF_PMD_RAWDEV_NAME rawdev_afu_mf
> 
>  static const struct rte_afu_uuid afu_uuid_map[] = {
>  	{ N3000_AFU_UUID_L, N3000_AFU_UUID_H },
> +	{ HE_LBK_UUID_L, HE_LBK_UUID_H },
> +	{ HE_MEM_LBK_UUID_L, HE_MEM_LBK_UUID_H },
>  	{ 0, 0 /* sentinel */ }
>  };
> 
>  static struct afu_mf_drv *afu_table[] = {
>  	&n3000_afu_drv,
> +	&he_lbk_drv,
> +	&he_mem_lbk_drv,
>  	NULL
>  };
> 
> diff --git a/drivers/raw/afu_mf/he_lbk.c b/drivers/raw/afu_mf/he_lbk.c new file
> mode 100644 index 0000000..8735647
> --- /dev/null
> +++ b/drivers/raw/afu_mf/he_lbk.c
> @@ -0,0 +1,427 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2022 Intel Corporation
> + */
> +
> +#include <errno.h>
> +#include <stdio.h>
> +#include <stdint.h>
> +#include <stdlib.h>
> +#include <inttypes.h>
> +#include <unistd.h>
> +#include <fcntl.h>
> +#include <poll.h>
> +#include <sys/eventfd.h>
> +#include <sys/ioctl.h>
> +
> +#include <rte_eal.h>
> +#include <rte_malloc.h>
> +#include <rte_memcpy.h>
> +#include <rte_io.h>
> +#include <rte_vfio.h>
> +#include <rte_bus_pci.h>
> +#include <rte_bus_ifpga.h>
> +#include <rte_rawdev.h>
> +
> +#include "afu_mf_rawdev.h"
> +#include "he_lbk.h"
> +
> +static int he_lbk_afu_config(struct afu_mf_rawdev *dev) {
> +	struct he_lbk_priv *priv = NULL;
> +	struct rte_pmd_afu_he_lbk_cfg *cfg = NULL;
> +	struct he_lbk_csr_cfg v;
> +
> +	if (!dev)
> +		return -EINVAL;
> +
> +	priv = (struct he_lbk_priv *)dev->priv;
> +	if (!priv)
> +		return -ENOENT;
> +
> +	cfg = &priv->he_lbk_cfg;
> +
> +	v.csr = 0;
> +
> +	if (cfg->cont)
> +		v.cont = 1;
> +
> +	v.mode = cfg->mode;
> +	v.trput_interleave = cfg->trput_interleave;
> +	if (cfg->multi_cl == 4)
> +		v.multicl_len = 2;
> +	else
> +		v.multicl_len = cfg->multi_cl - 1;
> +
> +	AFU_MF_PMD_DEBUG("cfg: 0x%08x", v.csr);
> +	rte_write32(v.csr, priv->he_lbk_ctx.addr + CSR_CFG);
> +
> +	return 0;
> +}
> +
> +static void he_lbk_report(struct afu_mf_rawdev *dev, uint32_t cl) {
> +	struct he_lbk_priv *priv = NULL;
> +	struct rte_pmd_afu_he_lbk_cfg *cfg = NULL;
> +	struct he_lbk_ctx *ctx = NULL;
> +	struct he_lbk_dsm_status *stat = NULL;
> +	struct he_lbk_status0 stat0;
> +	struct he_lbk_status1 stat1;
> +	uint64_t swtest_msg = 0;
> +	uint64_t ticks = 0;
> +	uint64_t info = 0;
> +	double num, rd_bw, wr_bw;
> +
> +	if (!dev || !dev->priv)
> +		return;
> +
> +	priv = (struct he_lbk_priv *)dev->priv;
> +	cfg = &priv->he_lbk_cfg;
> +	ctx = &priv->he_lbk_ctx;
> +
> +	stat = ctx->status_ptr;
> +
> +	swtest_msg = rte_read64(ctx->addr + CSR_SWTEST_MSG);
> +	stat0.csr = rte_read64(ctx->addr + CSR_STATUS0);
> +	stat1.csr = rte_read64(ctx->addr + CSR_STATUS1);
> +
> +	if (cfg->cont)
> +		ticks = stat->num_clocks - stat->start_overhead;
> +	else
> +		ticks = stat->num_clocks -
> +			(stat->start_overhead + stat->end_overhead);
> +
> +	if (cfg->freq_mhz == 0) {
> +		info = rte_read64(ctx->addr + CSR_HE_INFO0);
> +		AFU_MF_PMD_INFO("API version: %"PRIx64, info >> 16);
> +		cfg->freq_mhz = info & 0xffff;
> +		if (cfg->freq_mhz == 0) {
> +			AFU_MF_PMD_INFO("Frequency of AFU clock is
> unknown."
> +				" Assuming 350 MHz.");
> +			cfg->freq_mhz = 350;
> +		}
> +	}
> +
> +	num = (double)stat0.num_reads;
> +	rd_bw = (num * CLS_TO_SIZE(1) * MHZ(cfg->freq_mhz)) / ticks;
> +	num = (double)stat0.num_writes;
> +	wr_bw = (num * CLS_TO_SIZE(1) * MHZ(cfg->freq_mhz)) / ticks;
> +
> +	printf("Cachelines  Read_Count Write_Count Pend_Read Pend_Write "
> +		"Clocks@%uMHz   Rd_Bandwidth   Wr_Bandwidth\n",
> +		cfg->freq_mhz);
> +	printf("%10u  %10u %10u %10u %10u  %12"PRIu64
> +		"   %7.3f GB/s   %7.3f GB/s\n",
> +		cl, stat0.num_reads, stat0.num_writes,
> +		stat1.num_pend_reads, stat1.num_pend_writes,
> +		ticks, rd_bw / 1e9, wr_bw / 1e9);
> +	printf("Test Message: 0x%"PRIx64"\n", swtest_msg); }
> +
> +static int he_lbk_test(struct afu_mf_rawdev *dev) {
> +	struct he_lbk_priv *priv = NULL;
> +	struct rte_pmd_afu_he_lbk_cfg *cfg = NULL;
> +	struct he_lbk_ctx *ctx = NULL;
> +	struct he_lbk_csr_ctl ctl;
> +	uint32_t *ptr = NULL;
> +	uint32_t i, j, cl, val = 0;
> +	uint64_t sval = 0;
> +	int ret = 0;
> +
> +	if (!dev)
> +		return -EINVAL;
> +
> +	priv = (struct he_lbk_priv *)dev->priv;
> +	if (!priv)
> +		return -ENOENT;
> +
> +	cfg = &priv->he_lbk_cfg;
> +	ctx = &priv->he_lbk_ctx;
> +
> +	ctl.csr = 0;
> +	rte_write32(ctl.csr, ctx->addr + CSR_CTL);
> +	rte_delay_us(1000);
> +	ctl.reset = 1;
> +	rte_write32(ctl.csr, ctx->addr + CSR_CTL);
> +
> +	/* initialize DMA addresses */
> +	AFU_MF_PMD_DEBUG("src_addr: 0x%"PRIx64, ctx->src_iova);
> +	rte_write64(SIZE_TO_CLS(ctx->src_iova), ctx->addr + CSR_SRC_ADDR);
> +
> +	AFU_MF_PMD_DEBUG("dst_addr: 0x%"PRIx64, ctx->dest_iova);
> +	rte_write64(SIZE_TO_CLS(ctx->dest_iova), ctx->addr + CSR_DST_ADDR);
> +
> +	AFU_MF_PMD_DEBUG("dsm_addr: 0x%"PRIx64, ctx->dsm_iova);
> +	rte_write32(SIZE_TO_CLS(ctx->dsm_iova), ctx->addr +
> CSR_AFU_DSM_BASEL);
> +	rte_write32(SIZE_TO_CLS(ctx->dsm_iova) >> 32,
> +		ctx->addr + CSR_AFU_DSM_BASEH);
> +
> +	ret = he_lbk_afu_config(dev);
> +	if (ret)
> +		return ret;
> +
> +	/* initialize src data */
> +	ptr = (uint32_t *)ctx->src_ptr;
> +	j = CLS_TO_SIZE(cfg->end) >> 2;
> +	for (i = 0; i < j; i++)
> +		*ptr++ = i;
> +
> +	/* start test */
> +	for (cl = cfg->begin; cl <= cfg->end; cl += cfg->multi_cl) {
> +		memset(ctx->dest_ptr, 0, CLS_TO_SIZE(cl));
> +		memset(ctx->dsm_ptr, 0, DSM_SIZE);
> +
> +		ctl.csr = 0;
> +		rte_write32(ctl.csr, ctx->addr + CSR_CTL);
> +		rte_delay_us(1000);
> +		ctl.reset = 1;
> +		rte_write32(ctl.csr, ctx->addr + CSR_CTL);
> +
> +		rte_write32(cl - 1, ctx->addr + CSR_NUM_LINES);
> +
> +		ctl.start = 1;
> +		rte_write32(ctl.csr, ctx->addr + CSR_CTL);
> +
> +		if (cfg->cont) {
> +			rte_delay_ms(cfg->timeout * 1000);
> +			ctl.force_completion = 1;
> +			rte_write32(ctl.csr, ctx->addr + CSR_CTL);
> +			ret = dsm_poll_timeout(&ctx->status_ptr-
> >test_complete,
> +				val, (val & 0x1) == 1, DSM_POLL_INTERVAL,
> +				DSM_TIMEOUT);
> +			if (ret) {
> +				printf("DSM poll timeout\n");
> +				goto end;
> +			}
> +		} else {
> +			ret = dsm_poll_timeout(&ctx->status_ptr-
> >test_complete,
> +				val, (val & 0x1) == 1, DSM_POLL_INTERVAL,
> +				DSM_TIMEOUT);
> +			if (ret) {
> +				printf("DSM poll timeout\n");
> +				goto end;
> +			}
> +			ctl.force_completion = 1;
> +			rte_write32(ctl.csr, ctx->addr + CSR_CTL);
> +		}
> +
> +		he_lbk_report(dev, cl);
> +
> +		i = 0;
> +		while (i++ < 100) {
> +			sval = rte_read64(ctx->addr + CSR_STATUS1);
> +			if (sval == 0)
> +				break;
> +			rte_delay_us(1000);
> +		}
> +
> +		if (cfg->mode == NLB_MODE_LPBK) {
> +			ptr = (uint32_t *)ctx->dest_ptr;
> +			j = CLS_TO_SIZE(cl) >> 2;
> +			for (i = 0; i < j; i++) {
> +				if (*ptr++ != i) {
> +					AFU_MF_PMD_ERR("Data mismatch @
> %u", i);
> +					break;
> +				}
> +			}
> +		}
> +	}
> +
> +end:
> +	return 0;
> +}
> +
> +static int he_lbk_ctx_release(struct afu_mf_rawdev *dev) {
> +	struct he_lbk_priv *priv = NULL;
> +	struct he_lbk_ctx *ctx = NULL;
> +
> +	if (!dev)
> +		return -EINVAL;
> +
> +	priv = (struct he_lbk_priv *)dev->priv;
> +	if (!priv)
> +		return -ENOENT;
> +
> +	ctx = &priv->he_lbk_ctx;
> +
> +	rte_free(ctx->dsm_ptr);
> +	ctx->dsm_ptr = NULL;
> +	ctx->status_ptr = NULL;
> +
> +	rte_free(ctx->src_ptr);
> +	ctx->src_ptr = NULL;
> +
> +	rte_free(ctx->dest_ptr);
> +	ctx->dest_ptr = NULL;
> +
> +	return 0;
> +}
> +
> +static int he_lbk_ctx_init(struct afu_mf_rawdev *dev) {
> +	struct he_lbk_priv *priv = NULL;
> +	struct he_lbk_ctx *ctx = NULL;
> +	int ret = 0;
> +
> +	if (!dev)
> +		return -EINVAL;
> +
> +	priv = (struct he_lbk_priv *)dev->priv;
> +	if (!priv)
> +		return -ENOENT;
> +
> +	ctx = &priv->he_lbk_ctx;
> +	ctx->addr = (uint8_t *)dev->addr;
> +
> +	ctx->dsm_ptr = (uint8_t *)rte_zmalloc(NULL, DSM_SIZE,
> TEST_MEM_ALIGN);
> +	if (!ctx->dsm_ptr) {
> +		ret = -ENOMEM;
> +		goto release;
> +	}
> +	ctx->dsm_iova = rte_malloc_virt2iova(ctx->dsm_ptr);
> +	if (ctx->dsm_iova == RTE_BAD_IOVA) {
> +		ret = -ENOMEM;
> +		goto release;
> +	}
> +
> +	ctx->src_ptr = (uint8_t *)rte_zmalloc(NULL, NLB_BUF_SIZE,
> +		TEST_MEM_ALIGN);
> +	if (!ctx->src_ptr) {
> +		ret = -ENOMEM;
> +		goto release;

If ctx->src_ptr alloc fail, he_lbk_ctx_release() can work?

> +	}
> +	ctx->src_iova = rte_malloc_virt2iova(ctx->src_ptr);
> +	if (ctx->src_iova == RTE_BAD_IOVA) {
> +		ret = -ENOMEM;
> +		goto release;
> +	}
> +
> +	ctx->dest_ptr = (uint8_t *)rte_zmalloc(NULL, NLB_BUF_SIZE,
> +		TEST_MEM_ALIGN);
> +	if (!ctx->dest_ptr) {
> +		ret = -ENOMEM;
> +		goto release;
> +	}
> +	ctx->dest_iova = rte_malloc_virt2iova(ctx->dest_ptr);
> +	if (ctx->dest_iova == RTE_BAD_IOVA) {
> +		ret = -ENOMEM;
> +		goto release;
> +	}
> +
> +	ctx->status_ptr = (struct he_lbk_dsm_status *)ctx->dsm_ptr;
> +	return 0;
> +
> +release:
> +	he_lbk_ctx_release(dev);
> +	return ret;
> +}
> +
> +static int he_lbk_init(struct afu_mf_rawdev *dev) {
> +	if (!dev)
> +		return -EINVAL;
> +
> +	if (!dev->priv) {
> +		dev->priv = rte_zmalloc(NULL, sizeof(struct he_lbk_priv), 0);
> +		if (!dev->priv)
> +			return -ENOMEM;
> +	}
> +
> +	return he_lbk_ctx_init(dev);
> +}
> +
> +static int he_lbk_config(struct afu_mf_rawdev *dev, void *config,
> +	size_t config_size)
> +{
> +	struct he_lbk_priv *priv = NULL;
> +	struct rte_pmd_afu_he_lbk_cfg *cfg = NULL;
> +
> +	if (!dev || !config || !config_size)
> +		return -EINVAL;
> +
> +	priv = (struct he_lbk_priv *)dev->priv;
> +	if (!priv)
> +		return -ENOENT;
> +
> +	if (config_size != sizeof(struct rte_pmd_afu_he_lbk_cfg))
> +		return -EINVAL;
> +
> +	cfg = (struct rte_pmd_afu_he_lbk_cfg *)config;
> +	if (cfg->mode > NLB_MODE_TRPUT)
> +		return -EINVAL;
> +	if ((cfg->multi_cl != 1) && (cfg->multi_cl != 2) &&
> +		(cfg->multi_cl != 4))
> +		return -EINVAL;
> +	if ((cfg->begin < MIN_CACHE_LINES) || (cfg->begin >
> MAX_CACHE_LINES))
> +		return -EINVAL;
> +	if ((cfg->end < cfg->begin) || (cfg->end > MAX_CACHE_LINES))
> +		return -EINVAL;
> +
> +	rte_memcpy(&priv->he_lbk_cfg, cfg, sizeof(priv->he_lbk_cfg));
> +
> +	return 0;
> +}
> +
> +static int he_lbk_close(struct afu_mf_rawdev *dev) {
> +	if (!dev)
> +		return -EINVAL;
> +
> +	he_lbk_ctx_release(dev);
> +
> +	rte_free(dev->priv);
> +	dev->priv = NULL;
> +
> +	return 0;
> +}
> +
> +static int he_lbk_dump(struct afu_mf_rawdev *dev, FILE *f) {
> +	struct he_lbk_priv *priv = NULL;
> +	struct he_lbk_ctx *ctx = NULL;
> +
> +	if (!dev)
> +		return -EINVAL;
> +
> +	priv = (struct he_lbk_priv *)dev->priv;
> +	if (!priv)
> +		return -ENOENT;
> +
> +	if (!f)
> +		f = stdout;
> +
> +	ctx = &priv->he_lbk_ctx;
> +
> +	fprintf(f, "addr:\t\t%p\n", (void *)ctx->addr);
> +	fprintf(f, "dsm_ptr:\t%p\n", (void *)ctx->dsm_ptr);
> +	fprintf(f, "dsm_iova:\t0x%"PRIx64"\n", ctx->dsm_iova);
> +	fprintf(f, "src_ptr:\t%p\n", (void *)ctx->src_ptr);
> +	fprintf(f, "src_iova:\t0x%"PRIx64"\n", ctx->src_iova);
> +	fprintf(f, "dest_ptr:\t%p\n", (void *)ctx->dest_ptr);
> +	fprintf(f, "dest_iova:\t0x%"PRIx64"\n", ctx->dest_iova);
> +	fprintf(f, "status_ptr:\t%p\n", (void *)ctx->status_ptr);
> +
> +	return 0;
> +}
> +
> +static struct afu_mf_ops he_lbk_ops = {
> +	.init = he_lbk_init,
> +	.config = he_lbk_config,
> +	.start = NULL,
> +	.stop = NULL,
> +	.test = he_lbk_test,
> +	.close = he_lbk_close,
> +	.dump = he_lbk_dump,
> +	.reset = NULL
> +};
> +
> +struct afu_mf_drv he_lbk_drv = {
> +	.uuid = { HE_LBK_UUID_L, HE_LBK_UUID_H },
> +	.ops = &he_lbk_ops
> +};
> +
> +struct afu_mf_drv he_mem_lbk_drv = {
> +	.uuid = { HE_MEM_LBK_UUID_L, HE_MEM_LBK_UUID_H },
> +	.ops = &he_lbk_ops
> +};
> diff --git a/drivers/raw/afu_mf/he_lbk.h b/drivers/raw/afu_mf/he_lbk.h new file
> mode 100644 index 0000000..c2e8a29
> --- /dev/null
> +++ b/drivers/raw/afu_mf/he_lbk.h
> @@ -0,0 +1,121 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2022 Intel Corporation
> + */
> +
> +#ifndef _HE_LBK_H_
> +#define _HE_LBK_H_
> +
> +#include "afu_mf_rawdev.h"
> +#include "rte_pmd_afu.h"
> +
> +#define HE_LBK_UUID_L      0xb94b12284c31e02b
> +#define HE_LBK_UUID_H      0x56e203e9864f49a7
> +#define HE_MEM_LBK_UUID_L  0xbb652a578330a8eb #define
> HE_MEM_LBK_UUID_H
> +0x8568ab4e6ba54616
> +
> +extern struct afu_mf_drv he_lbk_drv;
> +extern struct afu_mf_drv he_mem_lbk_drv;
> +
> +/* HE-LBK & HE-MEM-LBK registers definition */
> +#define CSR_SCRATCHPAD0    0x100
> +#define CSR_SCRATCHPAD1    0x108
> +#define CSR_AFU_DSM_BASEL  0x110
> +#define CSR_AFU_DSM_BASEH  0x114
> +#define CSR_SRC_ADDR       0x120
> +#define CSR_DST_ADDR       0x128
> +#define CSR_NUM_LINES      0x130
> +#define CSR_CTL            0x138
> +#define CSR_CFG            0x140
> +#define CSR_INACT_THRESH   0x148
> +#define CSR_INTERRUPT0     0x150
> +#define CSR_SWTEST_MSG     0x158
> +#define CSR_STATUS0        0x160
> +#define CSR_STATUS1        0x168
> +#define CSR_ERROR          0x170
> +#define CSR_STRIDE         0x178
> +#define CSR_HE_INFO0       0x180
> +
> +#define DSM_SIZE           0x200000
> +#define DSM_POLL_INTERVAL  5  /* ms */
> +#define DSM_TIMEOUT        1000  /* ms */
> +
> +#define NLB_BUF_SIZE  0x400000
> +#define TEST_MEM_ALIGN  1024
> +
> +struct he_lbk_csr_ctl {
> +	union {
> +		uint32_t csr;
> +		struct {
> +			uint32_t reset:1;
> +			uint32_t start:1;
> +			uint32_t force_completion:1;
> +			uint32_t reserved:29;
> +		};
> +	};
> +};
> +
> +struct he_lbk_csr_cfg {
> +	union {
> +		uint32_t csr;
> +		struct {
> +			uint32_t rsvd1:1;
> +			uint32_t cont:1;
> +			uint32_t mode:3;
> +			uint32_t multicl_len:2;
> +			uint32_t rsvd2:13;
> +			uint32_t trput_interleave:3;
> +			uint32_t test_cfg:5;
> +			uint32_t interrupt_on_error:1;
> +			uint32_t interrupt_testmode:1;
> +			uint32_t rsvd3:2;
> +		};
> +	};
> +};
> +
> +struct he_lbk_status0 {
> +	union {
> +		uint64_t csr;
> +		struct {
> +			uint32_t num_writes;
> +			uint32_t num_reads;
> +		};
> +	};
> +};
> +
> +struct he_lbk_status1 {
> +	union {
> +		uint64_t csr;
> +		struct {
> +			uint32_t num_pend_writes;
> +			uint32_t num_pend_reads;
> +		};
> +	};
> +};
> +
> +struct he_lbk_dsm_status {
> +	uint32_t test_complete;
> +	uint32_t test_error;
> +	uint64_t num_clocks;
> +	uint32_t num_reads;
> +	uint32_t num_writes;
> +	uint32_t start_overhead;
> +	uint32_t end_overhead;
> +};
> +
> +struct he_lbk_ctx {
> +	uint8_t *addr;
> +	uint8_t *dsm_ptr;
> +	uint64_t dsm_iova;
> +	uint8_t *src_ptr;
> +	uint64_t src_iova;
> +	uint8_t *dest_ptr;
> +	uint64_t dest_iova;
> +	struct he_lbk_dsm_status *status_ptr;
> +};
> +
> +struct he_lbk_priv {
> +	struct rte_pmd_afu_he_lbk_cfg he_lbk_cfg;
> +	struct he_lbk_ctx he_lbk_ctx;
> +};
> +
> +#endif /* _HE_LBK_H_ */
> diff --git a/drivers/raw/afu_mf/meson.build b/drivers/raw/afu_mf/meson.build
> index 8a989e3..a983f53 100644
> --- a/drivers/raw/afu_mf/meson.build
> +++ b/drivers/raw/afu_mf/meson.build
> @@ -2,6 +2,6 @@
>  # Copyright 2022 Intel Corporation
> 
>  deps += ['rawdev', 'bus_pci', 'bus_ifpga'] -sources = files('afu_mf_rawdev.c',
> 'n3000_afu.c')
> +sources = files('afu_mf_rawdev.c', 'n3000_afu.c', 'he_lbk.c')
> 
>  headers = files('rte_pmd_afu.h')
> diff --git a/drivers/raw/afu_mf/rte_pmd_afu.h
> b/drivers/raw/afu_mf/rte_pmd_afu.h
> index f14a053..658df55 100644
> --- a/drivers/raw/afu_mf/rte_pmd_afu.h
> +++ b/drivers/raw/afu_mf/rte_pmd_afu.h
> @@ -90,6 +90,20 @@ struct rte_pmd_afu_n3000_cfg {
>  	};
>  };
> 
> +/**
> + * HE-LBK & HE-MEM-LBK AFU configuration data structure.
> + */
> +struct rte_pmd_afu_he_lbk_cfg {
> +	uint32_t mode;
> +	uint32_t begin;
> +	uint32_t end;
> +	uint32_t multi_cl;
> +	uint32_t cont;
> +	uint32_t timeout;
> +	uint32_t trput_interleave;
> +	uint32_t freq_mhz;
> +};
> +
>  #ifdef __cplusplus
>  }
>  #endif
> --
> 1.8.3.1
  
Wei Huang June 7, 2022, 2:42 a.m. UTC | #2
> -----Original Message-----
> From: Zhang, Tianfei <tianfei.zhang@intel.com>
> Sent: Monday, June 6, 2022 09:41
> To: Huang, Wei <wei.huang@intel.com>; dev@dpdk.org;
> thomas@monjalon.net; nipun.gupta@nxp.com; hemant.agrawal@nxp.com
> Cc: stable@dpdk.org; Xu, Rosen <rosen.xu@intel.com>; Zhang, Qi Z
> <qi.z.zhang@intel.com>
> Subject: RE: [PATCH v5 3/5] raw/afu_mf: add HE-LBK AFU driver
> 
> 
> 
> > -----Original Message-----
> > From: Huang, Wei <wei.huang@intel.com>
> > Sent: Friday, May 27, 2022 1:37 PM
> > To: dev@dpdk.org; thomas@monjalon.net; nipun.gupta@nxp.com;
> > hemant.agrawal@nxp.com
> > Cc: stable@dpdk.org; Xu, Rosen <rosen.xu@intel.com>; Zhang, Tianfei
> > <tianfei.zhang@intel.com>; Zhang, Qi Z <qi.z.zhang@intel.com>; Huang,
> > Wei <wei.huang@intel.com>
> > Subject: [PATCH v5 3/5] raw/afu_mf: add HE-LBK AFU driver
> >
> > HE-LBK and HE-MEM-LBK are host exerciser modules in OFS FPGA, HE-LBK
> > is used to test PCI bus and HE-MEM-LBK is used to test local memory.
> > This driver initialize the modules and report test result.
> >
> > Signed-off-by: Wei Huang <wei.huang@intel.com>
> > ---
> >  drivers/raw/afu_mf/afu_mf_rawdev.c |   5 +
> >  drivers/raw/afu_mf/he_lbk.c        | 427
> > +++++++++++++++++++++++++++++++++++++
> >  drivers/raw/afu_mf/he_lbk.h        | 121 +++++++++++
> >  drivers/raw/afu_mf/meson.build     |   2 +-
> >  drivers/raw/afu_mf/rte_pmd_afu.h   |  14 ++
> >  5 files changed, 568 insertions(+), 1 deletion(-)  create mode 100644
> > drivers/raw/afu_mf/he_lbk.c  create mode 100644
> > drivers/raw/afu_mf/he_lbk.h
> >
> > diff --git a/drivers/raw/afu_mf/afu_mf_rawdev.c
> > b/drivers/raw/afu_mf/afu_mf_rawdev.c
> > index 7c18f3b..e91eb21 100644
> > --- a/drivers/raw/afu_mf/afu_mf_rawdev.c
> > +++ b/drivers/raw/afu_mf/afu_mf_rawdev.c
> > @@ -20,16 +20,21 @@
> >  #include "rte_pmd_afu.h"
> >  #include "afu_mf_rawdev.h"
> >  #include "n3000_afu.h"
> > +#include "he_lbk.h"
> >
> >  #define AFU_MF_PMD_RAWDEV_NAME rawdev_afu_mf
> >
> >  static const struct rte_afu_uuid afu_uuid_map[] = {
> >  	{ N3000_AFU_UUID_L, N3000_AFU_UUID_H },
> > +	{ HE_LBK_UUID_L, HE_LBK_UUID_H },
> > +	{ HE_MEM_LBK_UUID_L, HE_MEM_LBK_UUID_H },
> >  	{ 0, 0 /* sentinel */ }
> >  };
> >
> >  static struct afu_mf_drv *afu_table[] = {
> >  	&n3000_afu_drv,
> > +	&he_lbk_drv,
> > +	&he_mem_lbk_drv,
> >  	NULL
> >  };
> >
> > diff --git a/drivers/raw/afu_mf/he_lbk.c b/drivers/raw/afu_mf/he_lbk.c
> > new file mode 100644 index 0000000..8735647
> > --- /dev/null
> > +++ b/drivers/raw/afu_mf/he_lbk.c
> > @@ -0,0 +1,427 @@
> > +/* SPDX-License-Identifier: BSD-3-Clause
> > + * Copyright(c) 2022 Intel Corporation  */
> > +
> > +#include <errno.h>
> > +#include <stdio.h>
> > +#include <stdint.h>
> > +#include <stdlib.h>
> > +#include <inttypes.h>
> > +#include <unistd.h>
> > +#include <fcntl.h>
> > +#include <poll.h>
> > +#include <sys/eventfd.h>
> > +#include <sys/ioctl.h>
> > +
> > +#include <rte_eal.h>
> > +#include <rte_malloc.h>
> > +#include <rte_memcpy.h>
> > +#include <rte_io.h>
> > +#include <rte_vfio.h>
> > +#include <rte_bus_pci.h>
> > +#include <rte_bus_ifpga.h>
> > +#include <rte_rawdev.h>
> > +
> > +#include "afu_mf_rawdev.h"
> > +#include "he_lbk.h"
> > +
> > +static int he_lbk_afu_config(struct afu_mf_rawdev *dev) {
> > +	struct he_lbk_priv *priv = NULL;
> > +	struct rte_pmd_afu_he_lbk_cfg *cfg = NULL;
> > +	struct he_lbk_csr_cfg v;
> > +
> > +	if (!dev)
> > +		return -EINVAL;
> > +
> > +	priv = (struct he_lbk_priv *)dev->priv;
> > +	if (!priv)
> > +		return -ENOENT;
> > +
> > +	cfg = &priv->he_lbk_cfg;
> > +
> > +	v.csr = 0;
> > +
> > +	if (cfg->cont)
> > +		v.cont = 1;
> > +
> > +	v.mode = cfg->mode;
> > +	v.trput_interleave = cfg->trput_interleave;
> > +	if (cfg->multi_cl == 4)
> > +		v.multicl_len = 2;
> > +	else
> > +		v.multicl_len = cfg->multi_cl - 1;
> > +
> > +	AFU_MF_PMD_DEBUG("cfg: 0x%08x", v.csr);
> > +	rte_write32(v.csr, priv->he_lbk_ctx.addr + CSR_CFG);
> > +
> > +	return 0;
> > +}
> > +
> > +static void he_lbk_report(struct afu_mf_rawdev *dev, uint32_t cl) {
> > +	struct he_lbk_priv *priv = NULL;
> > +	struct rte_pmd_afu_he_lbk_cfg *cfg = NULL;
> > +	struct he_lbk_ctx *ctx = NULL;
> > +	struct he_lbk_dsm_status *stat = NULL;
> > +	struct he_lbk_status0 stat0;
> > +	struct he_lbk_status1 stat1;
> > +	uint64_t swtest_msg = 0;
> > +	uint64_t ticks = 0;
> > +	uint64_t info = 0;
> > +	double num, rd_bw, wr_bw;
> > +
> > +	if (!dev || !dev->priv)
> > +		return;
> > +
> > +	priv = (struct he_lbk_priv *)dev->priv;
> > +	cfg = &priv->he_lbk_cfg;
> > +	ctx = &priv->he_lbk_ctx;
> > +
> > +	stat = ctx->status_ptr;
> > +
> > +	swtest_msg = rte_read64(ctx->addr + CSR_SWTEST_MSG);
> > +	stat0.csr = rte_read64(ctx->addr + CSR_STATUS0);
> > +	stat1.csr = rte_read64(ctx->addr + CSR_STATUS1);
> > +
> > +	if (cfg->cont)
> > +		ticks = stat->num_clocks - stat->start_overhead;
> > +	else
> > +		ticks = stat->num_clocks -
> > +			(stat->start_overhead + stat->end_overhead);
> > +
> > +	if (cfg->freq_mhz == 0) {
> > +		info = rte_read64(ctx->addr + CSR_HE_INFO0);
> > +		AFU_MF_PMD_INFO("API version: %"PRIx64, info >> 16);
> > +		cfg->freq_mhz = info & 0xffff;
> > +		if (cfg->freq_mhz == 0) {
> > +			AFU_MF_PMD_INFO("Frequency of AFU clock is
> > unknown."
> > +				" Assuming 350 MHz.");
> > +			cfg->freq_mhz = 350;
> > +		}
> > +	}
> > +
> > +	num = (double)stat0.num_reads;
> > +	rd_bw = (num * CLS_TO_SIZE(1) * MHZ(cfg->freq_mhz)) / ticks;
> > +	num = (double)stat0.num_writes;
> > +	wr_bw = (num * CLS_TO_SIZE(1) * MHZ(cfg->freq_mhz)) / ticks;
> > +
> > +	printf("Cachelines  Read_Count Write_Count Pend_Read
> Pend_Write "
> > +		"Clocks@%uMHz   Rd_Bandwidth   Wr_Bandwidth\n",
> > +		cfg->freq_mhz);
> > +	printf("%10u  %10u %10u %10u %10u  %12"PRIu64
> > +		"   %7.3f GB/s   %7.3f GB/s\n",
> > +		cl, stat0.num_reads, stat0.num_writes,
> > +		stat1.num_pend_reads, stat1.num_pend_writes,
> > +		ticks, rd_bw / 1e9, wr_bw / 1e9);
> > +	printf("Test Message: 0x%"PRIx64"\n", swtest_msg); }
> > +
> > +static int he_lbk_test(struct afu_mf_rawdev *dev) {
> > +	struct he_lbk_priv *priv = NULL;
> > +	struct rte_pmd_afu_he_lbk_cfg *cfg = NULL;
> > +	struct he_lbk_ctx *ctx = NULL;
> > +	struct he_lbk_csr_ctl ctl;
> > +	uint32_t *ptr = NULL;
> > +	uint32_t i, j, cl, val = 0;
> > +	uint64_t sval = 0;
> > +	int ret = 0;
> > +
> > +	if (!dev)
> > +		return -EINVAL;
> > +
> > +	priv = (struct he_lbk_priv *)dev->priv;
> > +	if (!priv)
> > +		return -ENOENT;
> > +
> > +	cfg = &priv->he_lbk_cfg;
> > +	ctx = &priv->he_lbk_ctx;
> > +
> > +	ctl.csr = 0;
> > +	rte_write32(ctl.csr, ctx->addr + CSR_CTL);
> > +	rte_delay_us(1000);
> > +	ctl.reset = 1;
> > +	rte_write32(ctl.csr, ctx->addr + CSR_CTL);
> > +
> > +	/* initialize DMA addresses */
> > +	AFU_MF_PMD_DEBUG("src_addr: 0x%"PRIx64, ctx->src_iova);
> > +	rte_write64(SIZE_TO_CLS(ctx->src_iova), ctx->addr +
> CSR_SRC_ADDR);
> > +
> > +	AFU_MF_PMD_DEBUG("dst_addr: 0x%"PRIx64, ctx->dest_iova);
> > +	rte_write64(SIZE_TO_CLS(ctx->dest_iova), ctx->addr +
> CSR_DST_ADDR);
> > +
> > +	AFU_MF_PMD_DEBUG("dsm_addr: 0x%"PRIx64, ctx->dsm_iova);
> > +	rte_write32(SIZE_TO_CLS(ctx->dsm_iova), ctx->addr +
> > CSR_AFU_DSM_BASEL);
> > +	rte_write32(SIZE_TO_CLS(ctx->dsm_iova) >> 32,
> > +		ctx->addr + CSR_AFU_DSM_BASEH);
> > +
> > +	ret = he_lbk_afu_config(dev);
> > +	if (ret)
> > +		return ret;
> > +
> > +	/* initialize src data */
> > +	ptr = (uint32_t *)ctx->src_ptr;
> > +	j = CLS_TO_SIZE(cfg->end) >> 2;
> > +	for (i = 0; i < j; i++)
> > +		*ptr++ = i;
> > +
> > +	/* start test */
> > +	for (cl = cfg->begin; cl <= cfg->end; cl += cfg->multi_cl) {
> > +		memset(ctx->dest_ptr, 0, CLS_TO_SIZE(cl));
> > +		memset(ctx->dsm_ptr, 0, DSM_SIZE);
> > +
> > +		ctl.csr = 0;
> > +		rte_write32(ctl.csr, ctx->addr + CSR_CTL);
> > +		rte_delay_us(1000);
> > +		ctl.reset = 1;
> > +		rte_write32(ctl.csr, ctx->addr + CSR_CTL);
> > +
> > +		rte_write32(cl - 1, ctx->addr + CSR_NUM_LINES);
> > +
> > +		ctl.start = 1;
> > +		rte_write32(ctl.csr, ctx->addr + CSR_CTL);
> > +
> > +		if (cfg->cont) {
> > +			rte_delay_ms(cfg->timeout * 1000);
> > +			ctl.force_completion = 1;
> > +			rte_write32(ctl.csr, ctx->addr + CSR_CTL);
> > +			ret = dsm_poll_timeout(&ctx->status_ptr-
> > >test_complete,
> > +				val, (val & 0x1) == 1, DSM_POLL_INTERVAL,
> > +				DSM_TIMEOUT);
> > +			if (ret) {
> > +				printf("DSM poll timeout\n");
> > +				goto end;
> > +			}
> > +		} else {
> > +			ret = dsm_poll_timeout(&ctx->status_ptr-
> > >test_complete,
> > +				val, (val & 0x1) == 1, DSM_POLL_INTERVAL,
> > +				DSM_TIMEOUT);
> > +			if (ret) {
> > +				printf("DSM poll timeout\n");
> > +				goto end;
> > +			}
> > +			ctl.force_completion = 1;
> > +			rte_write32(ctl.csr, ctx->addr + CSR_CTL);
> > +		}
> > +
> > +		he_lbk_report(dev, cl);
> > +
> > +		i = 0;
> > +		while (i++ < 100) {
> > +			sval = rte_read64(ctx->addr + CSR_STATUS1);
> > +			if (sval == 0)
> > +				break;
> > +			rte_delay_us(1000);
> > +		}
> > +
> > +		if (cfg->mode == NLB_MODE_LPBK) {
> > +			ptr = (uint32_t *)ctx->dest_ptr;
> > +			j = CLS_TO_SIZE(cl) >> 2;
> > +			for (i = 0; i < j; i++) {
> > +				if (*ptr++ != i) {
> > +					AFU_MF_PMD_ERR("Data mismatch
> @
> > %u", i);
> > +					break;
> > +				}
> > +			}
> > +		}
> > +	}
> > +
> > +end:
> > +	return 0;
> > +}
> > +
> > +static int he_lbk_ctx_release(struct afu_mf_rawdev *dev) {
> > +	struct he_lbk_priv *priv = NULL;
> > +	struct he_lbk_ctx *ctx = NULL;
> > +
> > +	if (!dev)
> > +		return -EINVAL;
> > +
> > +	priv = (struct he_lbk_priv *)dev->priv;
> > +	if (!priv)
> > +		return -ENOENT;
> > +
> > +	ctx = &priv->he_lbk_ctx;
> > +
> > +	rte_free(ctx->dsm_ptr);
> > +	ctx->dsm_ptr = NULL;
> > +	ctx->status_ptr = NULL;
> > +
> > +	rte_free(ctx->src_ptr);
> > +	ctx->src_ptr = NULL;
> > +
> > +	rte_free(ctx->dest_ptr);
> > +	ctx->dest_ptr = NULL;
> > +
> > +	return 0;
> > +}
> > +
> > +static int he_lbk_ctx_init(struct afu_mf_rawdev *dev) {
> > +	struct he_lbk_priv *priv = NULL;
> > +	struct he_lbk_ctx *ctx = NULL;
> > +	int ret = 0;
> > +
> > +	if (!dev)
> > +		return -EINVAL;
> > +
> > +	priv = (struct he_lbk_priv *)dev->priv;
> > +	if (!priv)
> > +		return -ENOENT;
> > +
> > +	ctx = &priv->he_lbk_ctx;
> > +	ctx->addr = (uint8_t *)dev->addr;
> > +
> > +	ctx->dsm_ptr = (uint8_t *)rte_zmalloc(NULL, DSM_SIZE,
> > TEST_MEM_ALIGN);
> > +	if (!ctx->dsm_ptr) {
> > +		ret = -ENOMEM;
> > +		goto release;
> > +	}
> > +	ctx->dsm_iova = rte_malloc_virt2iova(ctx->dsm_ptr);
> > +	if (ctx->dsm_iova == RTE_BAD_IOVA) {
> > +		ret = -ENOMEM;
> > +		goto release;
> > +	}
> > +
> > +	ctx->src_ptr = (uint8_t *)rte_zmalloc(NULL, NLB_BUF_SIZE,
> > +		TEST_MEM_ALIGN);
> > +	if (!ctx->src_ptr) {
> > +		ret = -ENOMEM;
> > +		goto release;
> 
> If ctx->src_ptr alloc fail, he_lbk_ctx_release() can work?
> 
He_lbk_ctx_release() can work correct in failure situation, but it's not standard exception handle, I will change it.
> > +	}
> > +	ctx->src_iova = rte_malloc_virt2iova(ctx->src_ptr);
> > +	if (ctx->src_iova == RTE_BAD_IOVA) {
> > +		ret = -ENOMEM;
> > +		goto release;
> > +	}
> > +
> > +	ctx->dest_ptr = (uint8_t *)rte_zmalloc(NULL, NLB_BUF_SIZE,
> > +		TEST_MEM_ALIGN);
> > +	if (!ctx->dest_ptr) {
> > +		ret = -ENOMEM;
> > +		goto release;
> > +	}
> > +	ctx->dest_iova = rte_malloc_virt2iova(ctx->dest_ptr);
> > +	if (ctx->dest_iova == RTE_BAD_IOVA) {
> > +		ret = -ENOMEM;
> > +		goto release;
> > +	}
> > +
> > +	ctx->status_ptr = (struct he_lbk_dsm_status *)ctx->dsm_ptr;
> > +	return 0;
> > +
> > +release:
> > +	he_lbk_ctx_release(dev);
> > +	return ret;
> > +}
> > +
> > +static int he_lbk_init(struct afu_mf_rawdev *dev) {
> > +	if (!dev)
> > +		return -EINVAL;
> > +
> > +	if (!dev->priv) {
> > +		dev->priv = rte_zmalloc(NULL, sizeof(struct he_lbk_priv), 0);
> > +		if (!dev->priv)
> > +			return -ENOMEM;
> > +	}
> > +
> > +	return he_lbk_ctx_init(dev);
> > +}
> > +
> > +static int he_lbk_config(struct afu_mf_rawdev *dev, void *config,
> > +	size_t config_size)
> > +{
> > +	struct he_lbk_priv *priv = NULL;
> > +	struct rte_pmd_afu_he_lbk_cfg *cfg = NULL;
> > +
> > +	if (!dev || !config || !config_size)
> > +		return -EINVAL;
> > +
> > +	priv = (struct he_lbk_priv *)dev->priv;
> > +	if (!priv)
> > +		return -ENOENT;
> > +
> > +	if (config_size != sizeof(struct rte_pmd_afu_he_lbk_cfg))
> > +		return -EINVAL;
> > +
> > +	cfg = (struct rte_pmd_afu_he_lbk_cfg *)config;
> > +	if (cfg->mode > NLB_MODE_TRPUT)
> > +		return -EINVAL;
> > +	if ((cfg->multi_cl != 1) && (cfg->multi_cl != 2) &&
> > +		(cfg->multi_cl != 4))
> > +		return -EINVAL;
> > +	if ((cfg->begin < MIN_CACHE_LINES) || (cfg->begin >
> > MAX_CACHE_LINES))
> > +		return -EINVAL;
> > +	if ((cfg->end < cfg->begin) || (cfg->end > MAX_CACHE_LINES))
> > +		return -EINVAL;
> > +
> > +	rte_memcpy(&priv->he_lbk_cfg, cfg, sizeof(priv->he_lbk_cfg));
> > +
> > +	return 0;
> > +}
> > +
> > +static int he_lbk_close(struct afu_mf_rawdev *dev) {
> > +	if (!dev)
> > +		return -EINVAL;
> > +
> > +	he_lbk_ctx_release(dev);
> > +
> > +	rte_free(dev->priv);
> > +	dev->priv = NULL;
> > +
> > +	return 0;
> > +}
> > +
> > +static int he_lbk_dump(struct afu_mf_rawdev *dev, FILE *f) {
> > +	struct he_lbk_priv *priv = NULL;
> > +	struct he_lbk_ctx *ctx = NULL;
> > +
> > +	if (!dev)
> > +		return -EINVAL;
> > +
> > +	priv = (struct he_lbk_priv *)dev->priv;
> > +	if (!priv)
> > +		return -ENOENT;
> > +
> > +	if (!f)
> > +		f = stdout;
> > +
> > +	ctx = &priv->he_lbk_ctx;
> > +
> > +	fprintf(f, "addr:\t\t%p\n", (void *)ctx->addr);
> > +	fprintf(f, "dsm_ptr:\t%p\n", (void *)ctx->dsm_ptr);
> > +	fprintf(f, "dsm_iova:\t0x%"PRIx64"\n", ctx->dsm_iova);
> > +	fprintf(f, "src_ptr:\t%p\n", (void *)ctx->src_ptr);
> > +	fprintf(f, "src_iova:\t0x%"PRIx64"\n", ctx->src_iova);
> > +	fprintf(f, "dest_ptr:\t%p\n", (void *)ctx->dest_ptr);
> > +	fprintf(f, "dest_iova:\t0x%"PRIx64"\n", ctx->dest_iova);
> > +	fprintf(f, "status_ptr:\t%p\n", (void *)ctx->status_ptr);
> > +
> > +	return 0;
> > +}
> > +
> > +static struct afu_mf_ops he_lbk_ops = {
> > +	.init = he_lbk_init,
> > +	.config = he_lbk_config,
> > +	.start = NULL,
> > +	.stop = NULL,
> > +	.test = he_lbk_test,
> > +	.close = he_lbk_close,
> > +	.dump = he_lbk_dump,
> > +	.reset = NULL
> > +};
> > +
> > +struct afu_mf_drv he_lbk_drv = {
> > +	.uuid = { HE_LBK_UUID_L, HE_LBK_UUID_H },
> > +	.ops = &he_lbk_ops
> > +};
> > +
> > +struct afu_mf_drv he_mem_lbk_drv = {
> > +	.uuid = { HE_MEM_LBK_UUID_L, HE_MEM_LBK_UUID_H },
> > +	.ops = &he_lbk_ops
> > +};
> > diff --git a/drivers/raw/afu_mf/he_lbk.h b/drivers/raw/afu_mf/he_lbk.h
> > new file mode 100644 index 0000000..c2e8a29
> > --- /dev/null
> > +++ b/drivers/raw/afu_mf/he_lbk.h
> > @@ -0,0 +1,121 @@
> > +/* SPDX-License-Identifier: BSD-3-Clause
> > + * Copyright(c) 2022 Intel Corporation  */
> > +
> > +#ifndef _HE_LBK_H_
> > +#define _HE_LBK_H_
> > +
> > +#include "afu_mf_rawdev.h"
> > +#include "rte_pmd_afu.h"
> > +
> > +#define HE_LBK_UUID_L      0xb94b12284c31e02b
> > +#define HE_LBK_UUID_H      0x56e203e9864f49a7
> > +#define HE_MEM_LBK_UUID_L  0xbb652a578330a8eb #define
> > HE_MEM_LBK_UUID_H
> > +0x8568ab4e6ba54616
> > +
> > +extern struct afu_mf_drv he_lbk_drv;
> > +extern struct afu_mf_drv he_mem_lbk_drv;
> > +
> > +/* HE-LBK & HE-MEM-LBK registers definition */
> > +#define CSR_SCRATCHPAD0    0x100
> > +#define CSR_SCRATCHPAD1    0x108
> > +#define CSR_AFU_DSM_BASEL  0x110
> > +#define CSR_AFU_DSM_BASEH  0x114
> > +#define CSR_SRC_ADDR       0x120
> > +#define CSR_DST_ADDR       0x128
> > +#define CSR_NUM_LINES      0x130
> > +#define CSR_CTL            0x138
> > +#define CSR_CFG            0x140
> > +#define CSR_INACT_THRESH   0x148
> > +#define CSR_INTERRUPT0     0x150
> > +#define CSR_SWTEST_MSG     0x158
> > +#define CSR_STATUS0        0x160
> > +#define CSR_STATUS1        0x168
> > +#define CSR_ERROR          0x170
> > +#define CSR_STRIDE         0x178
> > +#define CSR_HE_INFO0       0x180
> > +
> > +#define DSM_SIZE           0x200000
> > +#define DSM_POLL_INTERVAL  5  /* ms */
> > +#define DSM_TIMEOUT        1000  /* ms */
> > +
> > +#define NLB_BUF_SIZE  0x400000
> > +#define TEST_MEM_ALIGN  1024
> > +
> > +struct he_lbk_csr_ctl {
> > +	union {
> > +		uint32_t csr;
> > +		struct {
> > +			uint32_t reset:1;
> > +			uint32_t start:1;
> > +			uint32_t force_completion:1;
> > +			uint32_t reserved:29;
> > +		};
> > +	};
> > +};
> > +
> > +struct he_lbk_csr_cfg {
> > +	union {
> > +		uint32_t csr;
> > +		struct {
> > +			uint32_t rsvd1:1;
> > +			uint32_t cont:1;
> > +			uint32_t mode:3;
> > +			uint32_t multicl_len:2;
> > +			uint32_t rsvd2:13;
> > +			uint32_t trput_interleave:3;
> > +			uint32_t test_cfg:5;
> > +			uint32_t interrupt_on_error:1;
> > +			uint32_t interrupt_testmode:1;
> > +			uint32_t rsvd3:2;
> > +		};
> > +	};
> > +};
> > +
> > +struct he_lbk_status0 {
> > +	union {
> > +		uint64_t csr;
> > +		struct {
> > +			uint32_t num_writes;
> > +			uint32_t num_reads;
> > +		};
> > +	};
> > +};
> > +
> > +struct he_lbk_status1 {
> > +	union {
> > +		uint64_t csr;
> > +		struct {
> > +			uint32_t num_pend_writes;
> > +			uint32_t num_pend_reads;
> > +		};
> > +	};
> > +};
> > +
> > +struct he_lbk_dsm_status {
> > +	uint32_t test_complete;
> > +	uint32_t test_error;
> > +	uint64_t num_clocks;
> > +	uint32_t num_reads;
> > +	uint32_t num_writes;
> > +	uint32_t start_overhead;
> > +	uint32_t end_overhead;
> > +};
> > +
> > +struct he_lbk_ctx {
> > +	uint8_t *addr;
> > +	uint8_t *dsm_ptr;
> > +	uint64_t dsm_iova;
> > +	uint8_t *src_ptr;
> > +	uint64_t src_iova;
> > +	uint8_t *dest_ptr;
> > +	uint64_t dest_iova;
> > +	struct he_lbk_dsm_status *status_ptr; };
> > +
> > +struct he_lbk_priv {
> > +	struct rte_pmd_afu_he_lbk_cfg he_lbk_cfg;
> > +	struct he_lbk_ctx he_lbk_ctx;
> > +};
> > +
> > +#endif /* _HE_LBK_H_ */
> > diff --git a/drivers/raw/afu_mf/meson.build
> > b/drivers/raw/afu_mf/meson.build index 8a989e3..a983f53 100644
> > --- a/drivers/raw/afu_mf/meson.build
> > +++ b/drivers/raw/afu_mf/meson.build
> > @@ -2,6 +2,6 @@
> >  # Copyright 2022 Intel Corporation
> >
> >  deps += ['rawdev', 'bus_pci', 'bus_ifpga'] -sources =
> > files('afu_mf_rawdev.c',
> > 'n3000_afu.c')
> > +sources = files('afu_mf_rawdev.c', 'n3000_afu.c', 'he_lbk.c')
> >
> >  headers = files('rte_pmd_afu.h')
> > diff --git a/drivers/raw/afu_mf/rte_pmd_afu.h
> > b/drivers/raw/afu_mf/rte_pmd_afu.h
> > index f14a053..658df55 100644
> > --- a/drivers/raw/afu_mf/rte_pmd_afu.h
> > +++ b/drivers/raw/afu_mf/rte_pmd_afu.h
> > @@ -90,6 +90,20 @@ struct rte_pmd_afu_n3000_cfg {
> >  	};
> >  };
> >
> > +/**
> > + * HE-LBK & HE-MEM-LBK AFU configuration data structure.
> > + */
> > +struct rte_pmd_afu_he_lbk_cfg {
> > +	uint32_t mode;
> > +	uint32_t begin;
> > +	uint32_t end;
> > +	uint32_t multi_cl;
> > +	uint32_t cont;
> > +	uint32_t timeout;
> > +	uint32_t trput_interleave;
> > +	uint32_t freq_mhz;
> > +};
> > +
> >  #ifdef __cplusplus
> >  }
> >  #endif
> > --
> > 1.8.3.1
  

Patch

diff --git a/drivers/raw/afu_mf/afu_mf_rawdev.c b/drivers/raw/afu_mf/afu_mf_rawdev.c
index 7c18f3b..e91eb21 100644
--- a/drivers/raw/afu_mf/afu_mf_rawdev.c
+++ b/drivers/raw/afu_mf/afu_mf_rawdev.c
@@ -20,16 +20,21 @@ 
 #include "rte_pmd_afu.h"
 #include "afu_mf_rawdev.h"
 #include "n3000_afu.h"
+#include "he_lbk.h"
 
 #define AFU_MF_PMD_RAWDEV_NAME rawdev_afu_mf
 
 static const struct rte_afu_uuid afu_uuid_map[] = {
 	{ N3000_AFU_UUID_L, N3000_AFU_UUID_H },
+	{ HE_LBK_UUID_L, HE_LBK_UUID_H },
+	{ HE_MEM_LBK_UUID_L, HE_MEM_LBK_UUID_H },
 	{ 0, 0 /* sentinel */ }
 };
 
 static struct afu_mf_drv *afu_table[] = {
 	&n3000_afu_drv,
+	&he_lbk_drv,
+	&he_mem_lbk_drv,
 	NULL
 };
 
diff --git a/drivers/raw/afu_mf/he_lbk.c b/drivers/raw/afu_mf/he_lbk.c
new file mode 100644
index 0000000..8735647
--- /dev/null
+++ b/drivers/raw/afu_mf/he_lbk.c
@@ -0,0 +1,427 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Intel Corporation
+ */
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <inttypes.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <sys/eventfd.h>
+#include <sys/ioctl.h>
+
+#include <rte_eal.h>
+#include <rte_malloc.h>
+#include <rte_memcpy.h>
+#include <rte_io.h>
+#include <rte_vfio.h>
+#include <rte_bus_pci.h>
+#include <rte_bus_ifpga.h>
+#include <rte_rawdev.h>
+
+#include "afu_mf_rawdev.h"
+#include "he_lbk.h"
+
+static int he_lbk_afu_config(struct afu_mf_rawdev *dev)
+{
+	struct he_lbk_priv *priv = NULL;
+	struct rte_pmd_afu_he_lbk_cfg *cfg = NULL;
+	struct he_lbk_csr_cfg v;
+
+	if (!dev)
+		return -EINVAL;
+
+	priv = (struct he_lbk_priv *)dev->priv;
+	if (!priv)
+		return -ENOENT;
+
+	cfg = &priv->he_lbk_cfg;
+
+	v.csr = 0;
+
+	if (cfg->cont)
+		v.cont = 1;
+
+	v.mode = cfg->mode;
+	v.trput_interleave = cfg->trput_interleave;
+	if (cfg->multi_cl == 4)
+		v.multicl_len = 2;
+	else
+		v.multicl_len = cfg->multi_cl - 1;
+
+	AFU_MF_PMD_DEBUG("cfg: 0x%08x", v.csr);
+	rte_write32(v.csr, priv->he_lbk_ctx.addr + CSR_CFG);
+
+	return 0;
+}
+
+static void he_lbk_report(struct afu_mf_rawdev *dev, uint32_t cl)
+{
+	struct he_lbk_priv *priv = NULL;
+	struct rte_pmd_afu_he_lbk_cfg *cfg = NULL;
+	struct he_lbk_ctx *ctx = NULL;
+	struct he_lbk_dsm_status *stat = NULL;
+	struct he_lbk_status0 stat0;
+	struct he_lbk_status1 stat1;
+	uint64_t swtest_msg = 0;
+	uint64_t ticks = 0;
+	uint64_t info = 0;
+	double num, rd_bw, wr_bw;
+
+	if (!dev || !dev->priv)
+		return;
+
+	priv = (struct he_lbk_priv *)dev->priv;
+	cfg = &priv->he_lbk_cfg;
+	ctx = &priv->he_lbk_ctx;
+
+	stat = ctx->status_ptr;
+
+	swtest_msg = rte_read64(ctx->addr + CSR_SWTEST_MSG);
+	stat0.csr = rte_read64(ctx->addr + CSR_STATUS0);
+	stat1.csr = rte_read64(ctx->addr + CSR_STATUS1);
+
+	if (cfg->cont)
+		ticks = stat->num_clocks - stat->start_overhead;
+	else
+		ticks = stat->num_clocks -
+			(stat->start_overhead + stat->end_overhead);
+
+	if (cfg->freq_mhz == 0) {
+		info = rte_read64(ctx->addr + CSR_HE_INFO0);
+		AFU_MF_PMD_INFO("API version: %"PRIx64, info >> 16);
+		cfg->freq_mhz = info & 0xffff;
+		if (cfg->freq_mhz == 0) {
+			AFU_MF_PMD_INFO("Frequency of AFU clock is unknown."
+				" Assuming 350 MHz.");
+			cfg->freq_mhz = 350;
+		}
+	}
+
+	num = (double)stat0.num_reads;
+	rd_bw = (num * CLS_TO_SIZE(1) * MHZ(cfg->freq_mhz)) / ticks;
+	num = (double)stat0.num_writes;
+	wr_bw = (num * CLS_TO_SIZE(1) * MHZ(cfg->freq_mhz)) / ticks;
+
+	printf("Cachelines  Read_Count Write_Count Pend_Read Pend_Write "
+		"Clocks@%uMHz   Rd_Bandwidth   Wr_Bandwidth\n",
+		cfg->freq_mhz);
+	printf("%10u  %10u %10u %10u %10u  %12"PRIu64
+		"   %7.3f GB/s   %7.3f GB/s\n",
+		cl, stat0.num_reads, stat0.num_writes,
+		stat1.num_pend_reads, stat1.num_pend_writes,
+		ticks, rd_bw / 1e9, wr_bw / 1e9);
+	printf("Test Message: 0x%"PRIx64"\n", swtest_msg);
+}
+
+static int he_lbk_test(struct afu_mf_rawdev *dev)
+{
+	struct he_lbk_priv *priv = NULL;
+	struct rte_pmd_afu_he_lbk_cfg *cfg = NULL;
+	struct he_lbk_ctx *ctx = NULL;
+	struct he_lbk_csr_ctl ctl;
+	uint32_t *ptr = NULL;
+	uint32_t i, j, cl, val = 0;
+	uint64_t sval = 0;
+	int ret = 0;
+
+	if (!dev)
+		return -EINVAL;
+
+	priv = (struct he_lbk_priv *)dev->priv;
+	if (!priv)
+		return -ENOENT;
+
+	cfg = &priv->he_lbk_cfg;
+	ctx = &priv->he_lbk_ctx;
+
+	ctl.csr = 0;
+	rte_write32(ctl.csr, ctx->addr + CSR_CTL);
+	rte_delay_us(1000);
+	ctl.reset = 1;
+	rte_write32(ctl.csr, ctx->addr + CSR_CTL);
+
+	/* initialize DMA addresses */
+	AFU_MF_PMD_DEBUG("src_addr: 0x%"PRIx64, ctx->src_iova);
+	rte_write64(SIZE_TO_CLS(ctx->src_iova), ctx->addr + CSR_SRC_ADDR);
+
+	AFU_MF_PMD_DEBUG("dst_addr: 0x%"PRIx64, ctx->dest_iova);
+	rte_write64(SIZE_TO_CLS(ctx->dest_iova), ctx->addr + CSR_DST_ADDR);
+
+	AFU_MF_PMD_DEBUG("dsm_addr: 0x%"PRIx64, ctx->dsm_iova);
+	rte_write32(SIZE_TO_CLS(ctx->dsm_iova), ctx->addr + CSR_AFU_DSM_BASEL);
+	rte_write32(SIZE_TO_CLS(ctx->dsm_iova) >> 32,
+		ctx->addr + CSR_AFU_DSM_BASEH);
+
+	ret = he_lbk_afu_config(dev);
+	if (ret)
+		return ret;
+
+	/* initialize src data */
+	ptr = (uint32_t *)ctx->src_ptr;
+	j = CLS_TO_SIZE(cfg->end) >> 2;
+	for (i = 0; i < j; i++)
+		*ptr++ = i;
+
+	/* start test */
+	for (cl = cfg->begin; cl <= cfg->end; cl += cfg->multi_cl) {
+		memset(ctx->dest_ptr, 0, CLS_TO_SIZE(cl));
+		memset(ctx->dsm_ptr, 0, DSM_SIZE);
+
+		ctl.csr = 0;
+		rte_write32(ctl.csr, ctx->addr + CSR_CTL);
+		rte_delay_us(1000);
+		ctl.reset = 1;
+		rte_write32(ctl.csr, ctx->addr + CSR_CTL);
+
+		rte_write32(cl - 1, ctx->addr + CSR_NUM_LINES);
+
+		ctl.start = 1;
+		rte_write32(ctl.csr, ctx->addr + CSR_CTL);
+
+		if (cfg->cont) {
+			rte_delay_ms(cfg->timeout * 1000);
+			ctl.force_completion = 1;
+			rte_write32(ctl.csr, ctx->addr + CSR_CTL);
+			ret = dsm_poll_timeout(&ctx->status_ptr->test_complete,
+				val, (val & 0x1) == 1, DSM_POLL_INTERVAL,
+				DSM_TIMEOUT);
+			if (ret) {
+				printf("DSM poll timeout\n");
+				goto end;
+			}
+		} else {
+			ret = dsm_poll_timeout(&ctx->status_ptr->test_complete,
+				val, (val & 0x1) == 1, DSM_POLL_INTERVAL,
+				DSM_TIMEOUT);
+			if (ret) {
+				printf("DSM poll timeout\n");
+				goto end;
+			}
+			ctl.force_completion = 1;
+			rte_write32(ctl.csr, ctx->addr + CSR_CTL);
+		}
+
+		he_lbk_report(dev, cl);
+
+		i = 0;
+		while (i++ < 100) {
+			sval = rte_read64(ctx->addr + CSR_STATUS1);
+			if (sval == 0)
+				break;
+			rte_delay_us(1000);
+		}
+
+		if (cfg->mode == NLB_MODE_LPBK) {
+			ptr = (uint32_t *)ctx->dest_ptr;
+			j = CLS_TO_SIZE(cl) >> 2;
+			for (i = 0; i < j; i++) {
+				if (*ptr++ != i) {
+					AFU_MF_PMD_ERR("Data mismatch @ %u", i);
+					break;
+				}
+			}
+		}
+	}
+
+end:
+	return 0;
+}
+
+static int he_lbk_ctx_release(struct afu_mf_rawdev *dev)
+{
+	struct he_lbk_priv *priv = NULL;
+	struct he_lbk_ctx *ctx = NULL;
+
+	if (!dev)
+		return -EINVAL;
+
+	priv = (struct he_lbk_priv *)dev->priv;
+	if (!priv)
+		return -ENOENT;
+
+	ctx = &priv->he_lbk_ctx;
+
+	rte_free(ctx->dsm_ptr);
+	ctx->dsm_ptr = NULL;
+	ctx->status_ptr = NULL;
+
+	rte_free(ctx->src_ptr);
+	ctx->src_ptr = NULL;
+
+	rte_free(ctx->dest_ptr);
+	ctx->dest_ptr = NULL;
+
+	return 0;
+}
+
+static int he_lbk_ctx_init(struct afu_mf_rawdev *dev)
+{
+	struct he_lbk_priv *priv = NULL;
+	struct he_lbk_ctx *ctx = NULL;
+	int ret = 0;
+
+	if (!dev)
+		return -EINVAL;
+
+	priv = (struct he_lbk_priv *)dev->priv;
+	if (!priv)
+		return -ENOENT;
+
+	ctx = &priv->he_lbk_ctx;
+	ctx->addr = (uint8_t *)dev->addr;
+
+	ctx->dsm_ptr = (uint8_t *)rte_zmalloc(NULL, DSM_SIZE, TEST_MEM_ALIGN);
+	if (!ctx->dsm_ptr) {
+		ret = -ENOMEM;
+		goto release;
+	}
+	ctx->dsm_iova = rte_malloc_virt2iova(ctx->dsm_ptr);
+	if (ctx->dsm_iova == RTE_BAD_IOVA) {
+		ret = -ENOMEM;
+		goto release;
+	}
+
+	ctx->src_ptr = (uint8_t *)rte_zmalloc(NULL, NLB_BUF_SIZE,
+		TEST_MEM_ALIGN);
+	if (!ctx->src_ptr) {
+		ret = -ENOMEM;
+		goto release;
+	}
+	ctx->src_iova = rte_malloc_virt2iova(ctx->src_ptr);
+	if (ctx->src_iova == RTE_BAD_IOVA) {
+		ret = -ENOMEM;
+		goto release;
+	}
+
+	ctx->dest_ptr = (uint8_t *)rte_zmalloc(NULL, NLB_BUF_SIZE,
+		TEST_MEM_ALIGN);
+	if (!ctx->dest_ptr) {
+		ret = -ENOMEM;
+		goto release;
+	}
+	ctx->dest_iova = rte_malloc_virt2iova(ctx->dest_ptr);
+	if (ctx->dest_iova == RTE_BAD_IOVA) {
+		ret = -ENOMEM;
+		goto release;
+	}
+
+	ctx->status_ptr = (struct he_lbk_dsm_status *)ctx->dsm_ptr;
+	return 0;
+
+release:
+	he_lbk_ctx_release(dev);
+	return ret;
+}
+
+static int he_lbk_init(struct afu_mf_rawdev *dev)
+{
+	if (!dev)
+		return -EINVAL;
+
+	if (!dev->priv) {
+		dev->priv = rte_zmalloc(NULL, sizeof(struct he_lbk_priv), 0);
+		if (!dev->priv)
+			return -ENOMEM;
+	}
+
+	return he_lbk_ctx_init(dev);
+}
+
+static int he_lbk_config(struct afu_mf_rawdev *dev, void *config,
+	size_t config_size)
+{
+	struct he_lbk_priv *priv = NULL;
+	struct rte_pmd_afu_he_lbk_cfg *cfg = NULL;
+
+	if (!dev || !config || !config_size)
+		return -EINVAL;
+
+	priv = (struct he_lbk_priv *)dev->priv;
+	if (!priv)
+		return -ENOENT;
+
+	if (config_size != sizeof(struct rte_pmd_afu_he_lbk_cfg))
+		return -EINVAL;
+
+	cfg = (struct rte_pmd_afu_he_lbk_cfg *)config;
+	if (cfg->mode > NLB_MODE_TRPUT)
+		return -EINVAL;
+	if ((cfg->multi_cl != 1) && (cfg->multi_cl != 2) &&
+		(cfg->multi_cl != 4))
+		return -EINVAL;
+	if ((cfg->begin < MIN_CACHE_LINES) || (cfg->begin > MAX_CACHE_LINES))
+		return -EINVAL;
+	if ((cfg->end < cfg->begin) || (cfg->end > MAX_CACHE_LINES))
+		return -EINVAL;
+
+	rte_memcpy(&priv->he_lbk_cfg, cfg, sizeof(priv->he_lbk_cfg));
+
+	return 0;
+}
+
+static int he_lbk_close(struct afu_mf_rawdev *dev)
+{
+	if (!dev)
+		return -EINVAL;
+
+	he_lbk_ctx_release(dev);
+
+	rte_free(dev->priv);
+	dev->priv = NULL;
+
+	return 0;
+}
+
+static int he_lbk_dump(struct afu_mf_rawdev *dev, FILE *f)
+{
+	struct he_lbk_priv *priv = NULL;
+	struct he_lbk_ctx *ctx = NULL;
+
+	if (!dev)
+		return -EINVAL;
+
+	priv = (struct he_lbk_priv *)dev->priv;
+	if (!priv)
+		return -ENOENT;
+
+	if (!f)
+		f = stdout;
+
+	ctx = &priv->he_lbk_ctx;
+
+	fprintf(f, "addr:\t\t%p\n", (void *)ctx->addr);
+	fprintf(f, "dsm_ptr:\t%p\n", (void *)ctx->dsm_ptr);
+	fprintf(f, "dsm_iova:\t0x%"PRIx64"\n", ctx->dsm_iova);
+	fprintf(f, "src_ptr:\t%p\n", (void *)ctx->src_ptr);
+	fprintf(f, "src_iova:\t0x%"PRIx64"\n", ctx->src_iova);
+	fprintf(f, "dest_ptr:\t%p\n", (void *)ctx->dest_ptr);
+	fprintf(f, "dest_iova:\t0x%"PRIx64"\n", ctx->dest_iova);
+	fprintf(f, "status_ptr:\t%p\n", (void *)ctx->status_ptr);
+
+	return 0;
+}
+
+static struct afu_mf_ops he_lbk_ops = {
+	.init = he_lbk_init,
+	.config = he_lbk_config,
+	.start = NULL,
+	.stop = NULL,
+	.test = he_lbk_test,
+	.close = he_lbk_close,
+	.dump = he_lbk_dump,
+	.reset = NULL
+};
+
+struct afu_mf_drv he_lbk_drv = {
+	.uuid = { HE_LBK_UUID_L, HE_LBK_UUID_H },
+	.ops = &he_lbk_ops
+};
+
+struct afu_mf_drv he_mem_lbk_drv = {
+	.uuid = { HE_MEM_LBK_UUID_L, HE_MEM_LBK_UUID_H },
+	.ops = &he_lbk_ops
+};
diff --git a/drivers/raw/afu_mf/he_lbk.h b/drivers/raw/afu_mf/he_lbk.h
new file mode 100644
index 0000000..c2e8a29
--- /dev/null
+++ b/drivers/raw/afu_mf/he_lbk.h
@@ -0,0 +1,121 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Intel Corporation
+ */
+
+#ifndef _HE_LBK_H_
+#define _HE_LBK_H_
+
+#include "afu_mf_rawdev.h"
+#include "rte_pmd_afu.h"
+
+#define HE_LBK_UUID_L      0xb94b12284c31e02b
+#define HE_LBK_UUID_H      0x56e203e9864f49a7
+#define HE_MEM_LBK_UUID_L  0xbb652a578330a8eb
+#define HE_MEM_LBK_UUID_H  0x8568ab4e6ba54616
+
+extern struct afu_mf_drv he_lbk_drv;
+extern struct afu_mf_drv he_mem_lbk_drv;
+
+/* HE-LBK & HE-MEM-LBK registers definition */
+#define CSR_SCRATCHPAD0    0x100
+#define CSR_SCRATCHPAD1    0x108
+#define CSR_AFU_DSM_BASEL  0x110
+#define CSR_AFU_DSM_BASEH  0x114
+#define CSR_SRC_ADDR       0x120
+#define CSR_DST_ADDR       0x128
+#define CSR_NUM_LINES      0x130
+#define CSR_CTL            0x138
+#define CSR_CFG            0x140
+#define CSR_INACT_THRESH   0x148
+#define CSR_INTERRUPT0     0x150
+#define CSR_SWTEST_MSG     0x158
+#define CSR_STATUS0        0x160
+#define CSR_STATUS1        0x168
+#define CSR_ERROR          0x170
+#define CSR_STRIDE         0x178
+#define CSR_HE_INFO0       0x180
+
+#define DSM_SIZE           0x200000
+#define DSM_POLL_INTERVAL  5  /* ms */
+#define DSM_TIMEOUT        1000  /* ms */
+
+#define NLB_BUF_SIZE  0x400000
+#define TEST_MEM_ALIGN  1024
+
+struct he_lbk_csr_ctl {
+	union {
+		uint32_t csr;
+		struct {
+			uint32_t reset:1;
+			uint32_t start:1;
+			uint32_t force_completion:1;
+			uint32_t reserved:29;
+		};
+	};
+};
+
+struct he_lbk_csr_cfg {
+	union {
+		uint32_t csr;
+		struct {
+			uint32_t rsvd1:1;
+			uint32_t cont:1;
+			uint32_t mode:3;
+			uint32_t multicl_len:2;
+			uint32_t rsvd2:13;
+			uint32_t trput_interleave:3;
+			uint32_t test_cfg:5;
+			uint32_t interrupt_on_error:1;
+			uint32_t interrupt_testmode:1;
+			uint32_t rsvd3:2;
+		};
+	};
+};
+
+struct he_lbk_status0 {
+	union {
+		uint64_t csr;
+		struct {
+			uint32_t num_writes;
+			uint32_t num_reads;
+		};
+	};
+};
+
+struct he_lbk_status1 {
+	union {
+		uint64_t csr;
+		struct {
+			uint32_t num_pend_writes;
+			uint32_t num_pend_reads;
+		};
+	};
+};
+
+struct he_lbk_dsm_status {
+	uint32_t test_complete;
+	uint32_t test_error;
+	uint64_t num_clocks;
+	uint32_t num_reads;
+	uint32_t num_writes;
+	uint32_t start_overhead;
+	uint32_t end_overhead;
+};
+
+struct he_lbk_ctx {
+	uint8_t *addr;
+	uint8_t *dsm_ptr;
+	uint64_t dsm_iova;
+	uint8_t *src_ptr;
+	uint64_t src_iova;
+	uint8_t *dest_ptr;
+	uint64_t dest_iova;
+	struct he_lbk_dsm_status *status_ptr;
+};
+
+struct he_lbk_priv {
+	struct rte_pmd_afu_he_lbk_cfg he_lbk_cfg;
+	struct he_lbk_ctx he_lbk_ctx;
+};
+
+#endif /* _HE_LBK_H_ */
diff --git a/drivers/raw/afu_mf/meson.build b/drivers/raw/afu_mf/meson.build
index 8a989e3..a983f53 100644
--- a/drivers/raw/afu_mf/meson.build
+++ b/drivers/raw/afu_mf/meson.build
@@ -2,6 +2,6 @@ 
 # Copyright 2022 Intel Corporation
 
 deps += ['rawdev', 'bus_pci', 'bus_ifpga']
-sources = files('afu_mf_rawdev.c', 'n3000_afu.c')
+sources = files('afu_mf_rawdev.c', 'n3000_afu.c', 'he_lbk.c')
 
 headers = files('rte_pmd_afu.h')
diff --git a/drivers/raw/afu_mf/rte_pmd_afu.h b/drivers/raw/afu_mf/rte_pmd_afu.h
index f14a053..658df55 100644
--- a/drivers/raw/afu_mf/rte_pmd_afu.h
+++ b/drivers/raw/afu_mf/rte_pmd_afu.h
@@ -90,6 +90,20 @@  struct rte_pmd_afu_n3000_cfg {
 	};
 };
 
+/**
+ * HE-LBK & HE-MEM-LBK AFU configuration data structure.
+ */
+struct rte_pmd_afu_he_lbk_cfg {
+	uint32_t mode;
+	uint32_t begin;
+	uint32_t end;
+	uint32_t multi_cl;
+	uint32_t cont;
+	uint32_t timeout;
+	uint32_t trput_interleave;
+	uint32_t freq_mhz;
+};
+
 #ifdef __cplusplus
 }
 #endif