root/drivers/accel/amdxdna/npu4_regs.c
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2023-2024, Advanced Micro Devices, Inc.
 */

#include <drm/amdxdna_accel.h>
#include <drm/drm_device.h>
#include <drm/gpu_scheduler.h>
#include <linux/amd-pmf-io.h>
#include <linux/bits.h>
#include <linux/sizes.h>

#include "aie2_pci.h"
#include "amdxdna_mailbox.h"
#include "amdxdna_pci_drv.h"

/* NPU Public Registers on MpNPUAxiXbar (refer to Diag npu_registers.h) */
#define MPNPU_PWAITMODE                0x301003C
#define MPNPU_PUB_SEC_INTR             0x3010060
#define MPNPU_PUB_PWRMGMT_INTR         0x3010064
#define MPNPU_PUB_SCRATCH0             0x301006C
#define MPNPU_PUB_SCRATCH1             0x3010070
#define MPNPU_PUB_SCRATCH2             0x3010074
#define MPNPU_PUB_SCRATCH3             0x3010078
#define MPNPU_PUB_SCRATCH4             0x301007C
#define MPNPU_PUB_SCRATCH5             0x3010080
#define MPNPU_PUB_SCRATCH6             0x3010084
#define MPNPU_PUB_SCRATCH7             0x3010088
#define MPNPU_PUB_SCRATCH8             0x301008C
#define MPNPU_PUB_SCRATCH9             0x3010090
#define MPNPU_PUB_SCRATCH10            0x3010094
#define MPNPU_PUB_SCRATCH11            0x3010098
#define MPNPU_PUB_SCRATCH12            0x301009C
#define MPNPU_PUB_SCRATCH13            0x30100A0
#define MPNPU_PUB_SCRATCH14            0x30100A4
#define MPNPU_PUB_SCRATCH15            0x30100A8
#define MP0_C2PMSG_73                  0x3810A24
#define MP0_C2PMSG_123                 0x3810AEC

#define MP1_C2PMSG_0                   0x3B10900
#define MP1_C2PMSG_60                  0x3B109F0
#define MP1_C2PMSG_61                  0x3B109F4

#define MPNPU_SRAM_X2I_MAILBOX_0       0x3600000
#define MPNPU_SRAM_X2I_MAILBOX_15      0x361E000
#define MPNPU_SRAM_X2I_MAILBOX_31      0x363E000
#define MPNPU_SRAM_I2X_MAILBOX_31      0x363F000

#define MMNPU_APERTURE0_BASE           0x3000000
#define MMNPU_APERTURE1_BASE           0x3600000
#define MMNPU_APERTURE3_BASE           0x3810000
#define MMNPU_APERTURE4_BASE           0x3B10000

/* PCIe BAR Index for NPU4 */
#define NPU4_REG_BAR_INDEX      0
#define NPU4_MBOX_BAR_INDEX     0
#define NPU4_PSP_BAR_INDEX      4
#define NPU4_SMU_BAR_INDEX      5
#define NPU4_SRAM_BAR_INDEX     2
/* Associated BARs and Apertures */
#define NPU4_REG_BAR_BASE       MMNPU_APERTURE0_BASE
#define NPU4_MBOX_BAR_BASE      MMNPU_APERTURE0_BASE
#define NPU4_PSP_BAR_BASE       MMNPU_APERTURE3_BASE
#define NPU4_SMU_BAR_BASE       MMNPU_APERTURE4_BASE
#define NPU4_SRAM_BAR_BASE      MMNPU_APERTURE1_BASE

#define NPU4_DPM_TOPS(ndev, hclk) (4096 * (ndev)->total_col * (hclk) / 1000000)

const struct rt_config npu4_default_rt_cfg[] = {
        { 5, 1, AIE2_RT_CFG_INIT }, /* PDI APP LOAD MODE */
        { 10, 1, AIE2_RT_CFG_INIT }, /* DEBUG BUF */
        { 14, 0, AIE2_RT_CFG_INIT, BIT_U64(AIE2_PREEMPT) }, /* Frame boundary preemption */
        { 1, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */
        { 2, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */
        { 3, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */
        { 4, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */
        { 13, 0, AIE2_RT_CFG_FORCE_PREEMPT },
        { 14, 0, AIE2_RT_CFG_FRAME_BOUNDARY_PREEMPT },
        { 0 },
};

const struct dpm_clk_freq npu4_dpm_clk_table[] = {
        {396, 792},
        {600, 1056},
        {792, 1152},
        {975, 1267},
        {975, 1267},
        {1056, 1408},
        {1152, 1584},
        {1267, 1800},
        { 0 }
};

const struct amdxdna_fw_feature_tbl npu4_fw_feature_table[] = {
        { .major = 6, .min_minor = 12 },
        { .features = BIT_U64(AIE2_PREEMPT), .major = 6, .min_minor = 12 },
        { .features = BIT_U64(AIE2_TEMPORAL_ONLY), .major = 6, .min_minor = 12 },
        { .features = BIT_U64(AIE2_NPU_COMMAND), .major = 6, .min_minor = 15 },
        { .features = BIT_U64(AIE2_UPDATE_PROPERTY), .major = 6, .min_minor = 15 },
        { .features = BIT_U64(AIE2_APP_HEALTH), .major = 6, .min_minor = 18 },
        { .features = BIT_U64(AIE2_ADD_HOST_BUFFER), .major = 6, .min_minor = 18 },
        { .features = BIT_U64(AIE2_GET_DEV_REVISION), .major = 6, .min_minor = 24 },
        { .features = AIE2_ALL_FEATURES, .major = 7 },
        { 0 }
};

static int npu4_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level)
{
        int ret;

        ret = aie_smu_set_dpm(ndev->aie.smu_hdl, dpm_level);
        if (ret)
                return ret;

        ndev->npuclk_freq = ndev->priv->dpm_clk_tbl[dpm_level].npuclk;
        ndev->hclk_freq = ndev->priv->dpm_clk_tbl[dpm_level].hclk;
        ndev->max_tops = NPU4_DPM_TOPS(ndev, ndev->priv->dpm_clk_tbl[ndev->max_dpm_level].hclk);
        ndev->curr_tops = NPU4_DPM_TOPS(ndev, ndev->hclk_freq);

        XDNA_DBG(ndev->aie.xdna, "MP-NPU clock %d, H clock %d\n",
                 ndev->npuclk_freq, ndev->hclk_freq);

        return 0;
}

static int npu4_update_counters(struct amdxdna_dev_hdl *ndev)
{
        struct amd_pmf_npu_metrics npu_metrics;
        int ret;

        ret = AIE2_GET_PMF_NPU_METRICS(&npu_metrics);
        if (ret)
                return ret;

        ndev->npuclk_freq = npu_metrics.mpnpuclk_freq;
        ndev->hclk_freq = npu_metrics.npuclk_freq;
        ndev->curr_tops = NPU4_DPM_TOPS(ndev, ndev->hclk_freq);

        return 0;
}

const struct aie2_hw_ops npu4_hw_ops = {
        .set_dpm = npu4_set_dpm,
        .update_counters = npu4_update_counters,
};

const struct amdxdna_rev_vbnv npu4_rev_vbnv_tbl[] = {
        { AIE2_DEV_REVISION_STXA, "NPU Strix" },
        { AIE2_DEV_REVISION_STXB, "NPU Strix" },
        { AIE2_DEV_REVISION_KRK1, "NPU Krackan 1" },
        { AIE2_DEV_REVISION_KRK2, "NPU Krackan 2" },
        { AIE2_DEV_REVISION_HALO, "NPU Strix Halo" },
        { AIE2_DEV_REVISION_GPT1, "NPU Gorgon Point 1" },
        { AIE2_DEV_REVISION_GPT2, "NPU Gorgon Point 2" },
        { AIE2_DEV_REVISION_GPT3, "NPU Gorgon Point 3" },
        { 0 }
};

static const struct amdxdna_dev_priv npu4_dev_priv = {
        .fw_path        = "amdnpu/17f0_10/",
        .rt_config      = npu4_default_rt_cfg,
        .dpm_clk_tbl    = npu4_dpm_clk_table,
        .col_align      = COL_ALIGN_NATURE,
        .col_opc        = 4096,
        .mbox_dev_addr  = NPU4_MBOX_BAR_BASE,
        .mbox_size      = 0, /* Use BAR size */
        .sram_dev_addr  = NPU4_SRAM_BAR_BASE,
        .hwctx_limit    = 16,
        .sram_offs      = {
                DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU4_SRAM, MPNPU_SRAM_X2I_MAILBOX_0),
                DEFINE_BAR_OFFSET(FW_ALIVE_OFF,   NPU4_SRAM, MPNPU_SRAM_X2I_MAILBOX_15),
        },
        .psp_regs_off   = {
                DEFINE_BAR_OFFSET(PSP_CMD_REG,    NPU4_PSP, MP0_C2PMSG_123),
                DEFINE_BAR_OFFSET(PSP_ARG0_REG,   NPU4_REG, MPNPU_PUB_SCRATCH3),
                DEFINE_BAR_OFFSET(PSP_ARG1_REG,   NPU4_REG, MPNPU_PUB_SCRATCH4),
                DEFINE_BAR_OFFSET(PSP_ARG2_REG,   NPU4_REG, MPNPU_PUB_SCRATCH9),
                DEFINE_BAR_OFFSET(PSP_INTR_REG,   NPU4_PSP, MP0_C2PMSG_73),
                DEFINE_BAR_OFFSET(PSP_STATUS_REG, NPU4_PSP, MP0_C2PMSG_123),
                DEFINE_BAR_OFFSET(PSP_RESP_REG,   NPU4_REG, MPNPU_PUB_SCRATCH3),
                DEFINE_BAR_OFFSET(PSP_PWAITMODE_REG, NPU4_REG, MPNPU_PWAITMODE),
        },
        .smu_regs_off   = {
                DEFINE_BAR_OFFSET(SMU_CMD_REG,  NPU4_SMU, MP1_C2PMSG_0),
                DEFINE_BAR_OFFSET(SMU_ARG_REG,  NPU4_SMU, MP1_C2PMSG_60),
                DEFINE_BAR_OFFSET(SMU_INTR_REG, NPU4_SMU, MMNPU_APERTURE4_BASE),
                DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU4_SMU, MP1_C2PMSG_61),
                DEFINE_BAR_OFFSET(SMU_OUT_REG,  NPU4_SMU, MP1_C2PMSG_60),
        },
        .hw_ops         = &npu4_hw_ops
};

const struct amdxdna_dev_info dev_npu4_info = {
        .reg_bar           = NPU4_REG_BAR_INDEX,
        .mbox_bar          = NPU4_MBOX_BAR_INDEX,
        .sram_bar          = NPU4_SRAM_BAR_INDEX,
        .psp_bar           = NPU4_PSP_BAR_INDEX,
        .smu_bar           = NPU4_SMU_BAR_INDEX,
        .first_col         = 0,
        .dev_mem_buf_shift = 15, /* 32 KiB aligned */
        .dev_mem_base      = AIE2_DEVM_BASE,
        .dev_mem_size      = AIE2_DEVM_SIZE,
        .default_vbnv      = "RyzenAI-npu4",
        .dev_heap_max_size = AIE2_DEVM_MAX_SIZE,
        .device_type       = AMDXDNA_DEV_TYPE_KMQ,
        .rev_vbnv_tbl      = npu4_rev_vbnv_tbl,
        .dev_priv          = &npu4_dev_priv,
        .fw_feature_tbl    = npu4_fw_feature_table,
        .ops               = &aie2_ops, /* NPU4 can share NPU1's callback */
};