#include "gaudi2P.h"
#include "gaudi2_masks.h"
#include "../include/gaudi2/gaudi2_special_blocks.h"
#include "../include/hw_ip/mmu/mmu_general.h"
#include "../include/hw_ip/mmu/mmu_v2_0.h"
#include "../include/gaudi2/gaudi2_packets.h"
#include "../include/gaudi2/gaudi2_reg_map.h"
#include "../include/gaudi2/gaudi2_async_ids_map_extended.h"
#include "../include/gaudi2/arc/gaudi2_arc_common_packets.h"
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/hwmon.h>
#include <linux/iommu.h>
#define GAUDI2_DMA_POOL_BLK_SIZE SZ_256 /* 256 bytes */
#define GAUDI2_RESET_TIMEOUT_MSEC 2000 /* 2000ms */
#define GAUDI2_RESET_POLL_TIMEOUT_USEC 500000 /* 500ms */
#define GAUDI2_PLDM_HRESET_TIMEOUT_MSEC 25000 /* 25s */
#define GAUDI2_PLDM_SRESET_TIMEOUT_MSEC 25000 /* 25s */
#define GAUDI2_PLDM_RESET_POLL_TIMEOUT_USEC 3000000 /* 3s */
#define GAUDI2_RESET_POLL_CNT 3
#define GAUDI2_RESET_WAIT_MSEC 1 /* 1ms */
#define GAUDI2_CPU_RESET_WAIT_MSEC 100 /* 100ms */
#define GAUDI2_PLDM_RESET_WAIT_MSEC 1000 /* 1s */
#define GAUDI2_CB_POOL_CB_CNT 512
#define GAUDI2_CB_POOL_CB_SIZE SZ_128K /* 128KB */
#define GAUDI2_MSG_TO_CPU_TIMEOUT_USEC 4000000 /* 4s */
#define GAUDI2_WAIT_FOR_BL_TIMEOUT_USEC 25000000 /* 25s */
#define GAUDI2_TEST_QUEUE_WAIT_USEC 100000 /* 100ms */
#define GAUDI2_PLDM_TEST_QUEUE_WAIT_USEC 1000000 /* 1s */
#define GAUDI2_ALLOC_CPU_MEM_RETRY_CNT 3
#define MAX_CLUSTER_BINNING_FAULTY_TPCS 1
#define MAX_FAULTY_XBARS 1
#define MAX_FAULTY_EDMAS 1
#define MAX_FAULTY_DECODERS 1
#define GAUDI2_TPC_FULL_MASK 0x1FFFFFF
#define GAUDI2_HIF_HMMU_FULL_MASK 0xFFFF
#define GAUDI2_DECODER_FULL_MASK 0x3FF
#define GAUDI2_NA_EVENT_CAUSE 0xFF
#define GAUDI2_NUM_OF_QM_ERR_CAUSE 18
#define GAUDI2_NUM_OF_LOWER_QM_ERR_CAUSE 25
#define GAUDI2_NUM_OF_QM_ARB_ERR_CAUSE 3
#define GAUDI2_NUM_OF_ARC_SEI_ERR_CAUSE 14
#define GAUDI2_NUM_OF_CPU_SEI_ERR_CAUSE 3
#define GAUDI2_NUM_OF_QM_SEI_ERR_CAUSE 2
#define GAUDI2_NUM_OF_ROT_ERR_CAUSE 22
#define GAUDI2_NUM_OF_TPC_INTR_CAUSE 31
#define GAUDI2_NUM_OF_DEC_ERR_CAUSE 25
#define GAUDI2_NUM_OF_MME_ERR_CAUSE 16
#define GAUDI2_NUM_OF_MME_SBTE_ERR_CAUSE 5
#define GAUDI2_NUM_OF_MME_WAP_ERR_CAUSE 7
#define GAUDI2_NUM_OF_DMA_CORE_INTR_CAUSE 8
#define GAUDI2_NUM_OF_MMU_SPI_SEI_CAUSE 19
#define GAUDI2_NUM_OF_HBM_SEI_CAUSE 9
#define GAUDI2_NUM_OF_SM_SEI_ERR_CAUSE 3
#define GAUDI2_NUM_OF_PCIE_ADDR_DEC_ERR_CAUSE 3
#define GAUDI2_NUM_OF_PMMU_FATAL_ERR_CAUSE 2
#define GAUDI2_NUM_OF_HIF_FATAL_ERR_CAUSE 2
#define GAUDI2_NUM_OF_AXI_DRAIN_ERR_CAUSE 2
#define GAUDI2_NUM_OF_HBM_MC_SPI_CAUSE 5
#define GAUDI2_MMU_CACHE_INV_TIMEOUT_USEC (MMU_CONFIG_TIMEOUT_USEC * 10)
#define GAUDI2_PLDM_MMU_TIMEOUT_USEC (MMU_CONFIG_TIMEOUT_USEC * 200)
#define GAUDI2_ARB_WDT_TIMEOUT (0x1000000)
#define GAUDI2_VDEC_TIMEOUT_USEC 10000 /* 10ms */
#define GAUDI2_PLDM_VDEC_TIMEOUT_USEC (GAUDI2_VDEC_TIMEOUT_USEC * 100)
#define KDMA_TIMEOUT_USEC USEC_PER_SEC
#define IS_DMA_IDLE(dma_core_sts0) \
(!((dma_core_sts0) & (DCORE0_EDMA0_CORE_STS0_BUSY_MASK)))
#define IS_DMA_HALTED(dma_core_sts1) \
((dma_core_sts1) & (DCORE0_EDMA0_CORE_STS1_IS_HALT_MASK))
#define IS_MME_IDLE(mme_arch_sts) (((mme_arch_sts) & MME_ARCH_IDLE_MASK) == MME_ARCH_IDLE_MASK)
#define IS_TPC_IDLE(tpc_cfg_sts) (((tpc_cfg_sts) & (TPC_IDLE_MASK)) == (TPC_IDLE_MASK))
#define IS_QM_IDLE(qm_glbl_sts0, qm_glbl_sts1, qm_cgm_sts) \
((((qm_glbl_sts0) & (QM_IDLE_MASK)) == (QM_IDLE_MASK)) && \
(((qm_glbl_sts1) & (QM_ARC_IDLE_MASK)) == (QM_ARC_IDLE_MASK)) && \
(((qm_cgm_sts) & (CGM_IDLE_MASK)) == (CGM_IDLE_MASK)))
#define PCIE_DEC_EN_MASK 0x300
#define DEC_WORK_STATE_IDLE 0
#define DEC_WORK_STATE_PEND 3
#define IS_DEC_IDLE(dec_swreg15) \
(((dec_swreg15) & DCORE0_DEC0_CMD_SWREG15_SW_WORK_STATE_MASK) == DEC_WORK_STATE_IDLE || \
((dec_swreg15) & DCORE0_DEC0_CMD_SWREG15_SW_WORK_STATE_MASK) == DEC_WORK_STATE_PEND)
#define GAUDI2_HBM_MMU_SCRM_MEM_SIZE SZ_8M
#define GAUDI2_HBM_MMU_SCRM_DIV_SHIFT 26
#define GAUDI2_HBM_MMU_SCRM_MOD_SHIFT 0
#define GAUDI2_HBM_MMU_SCRM_ADDRESS_MASK DRAM_VA_HINT_MASK
#define GAUDI2_COMPENSATE_TLB_PAGE_SIZE_FACTOR 16
#define MMU_RANGE_INV_VA_LSB_SHIFT 12
#define MMU_RANGE_INV_VA_MSB_SHIFT 44
#define MMU_RANGE_INV_EN_SHIFT 0
#define MMU_RANGE_INV_ASID_EN_SHIFT 1
#define MMU_RANGE_INV_ASID_SHIFT 2
#define GAUDI2_PMMU_SPI_SEI_ENABLE_MASK GENMASK(GAUDI2_NUM_OF_MMU_SPI_SEI_CAUSE - 2, 0)
#define GAUDI2_HMMU_SPI_SEI_ENABLE_MASK GENMASK(GAUDI2_NUM_OF_MMU_SPI_SEI_CAUSE - 1, 0)
#define GAUDI2_MAX_STRING_LEN 64
#define GAUDI2_VDEC_MSIX_ENTRIES (GAUDI2_IRQ_NUM_SHARED_DEC1_ABNRM - \
GAUDI2_IRQ_NUM_DCORE0_DEC0_NRM + 1)
#define ENGINE_ID_DCORE_OFFSET (GAUDI2_DCORE1_ENGINE_ID_EDMA_0 - GAUDI2_DCORE0_ENGINE_ID_EDMA_0)
#define RAZWI_GET_AXUSER_XY(x) \
((x & 0xF8001FF0) >> 4)
#define RAZWI_GET_AXUSER_LOW_XY(x) \
((x & 0x00001FF0) >> 4)
#define RAZWI_INITIATOR_AXUER_L_X_SHIFT 0
#define RAZWI_INITIATOR_AXUER_L_X_MASK 0x1F
#define RAZWI_INITIATOR_AXUER_L_Y_SHIFT 5
#define RAZWI_INITIATOR_AXUER_L_Y_MASK 0xF
#define RAZWI_INITIATOR_AXUER_H_X_SHIFT 23
#define RAZWI_INITIATOR_AXUER_H_X_MASK 0x1F
#define RAZWI_INITIATOR_ID_X_Y_LOW(x, y) \
((((y) & RAZWI_INITIATOR_AXUER_L_Y_MASK) << RAZWI_INITIATOR_AXUER_L_Y_SHIFT) | \
(((x) & RAZWI_INITIATOR_AXUER_L_X_MASK) << RAZWI_INITIATOR_AXUER_L_X_SHIFT))
#define RAZWI_INITIATOR_ID_X_HIGH(x) \
(((x) & RAZWI_INITIATOR_AXUER_H_X_MASK) << RAZWI_INITIATOR_AXUER_H_X_SHIFT)
#define RAZWI_INITIATOR_ID_X_Y(xl, yl, xh) \
(RAZWI_INITIATOR_ID_X_Y_LOW(xl, yl) | RAZWI_INITIATOR_ID_X_HIGH(xh))
#define PSOC_RAZWI_ENG_STR_SIZE 128
#define PSOC_RAZWI_MAX_ENG_PER_RTR 5
#define HW_UNSCRAMBLED_BITS_MASK GENMASK_ULL(63, 26)
struct gaudi2_razwi_info {
u32 axuser_xy;
u32 rtr_ctrl;
u16 eng_id;
char *eng_name;
};
static struct gaudi2_razwi_info common_razwi_info[] = {
{RAZWI_INITIATOR_ID_X_Y(2, 4, 0), mmDCORE0_RTR0_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_DEC_0, "DEC0"},
{RAZWI_INITIATOR_ID_X_Y(2, 4, 4), mmDCORE0_RTR0_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_DEC_1, "DEC1"},
{RAZWI_INITIATOR_ID_X_Y(17, 4, 18), mmDCORE1_RTR7_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_DEC_0, "DEC2"},
{RAZWI_INITIATOR_ID_X_Y(17, 4, 14), mmDCORE1_RTR7_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_DEC_1, "DEC3"},
{RAZWI_INITIATOR_ID_X_Y(2, 11, 0), mmDCORE2_RTR0_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_DEC_0, "DEC4"},
{RAZWI_INITIATOR_ID_X_Y(2, 11, 4), mmDCORE2_RTR0_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_DEC_1, "DEC5"},
{RAZWI_INITIATOR_ID_X_Y(17, 11, 18), mmDCORE3_RTR7_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_DEC_0, "DEC6"},
{RAZWI_INITIATOR_ID_X_Y(17, 11, 14), mmDCORE3_RTR7_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_DEC_1, "DEC7"},
{RAZWI_INITIATOR_ID_X_Y(2, 4, 6), mmDCORE0_RTR0_CTRL_BASE,
GAUDI2_PCIE_ENGINE_ID_DEC_0, "DEC8"},
{RAZWI_INITIATOR_ID_X_Y(2, 4, 7), mmDCORE0_RTR0_CTRL_BASE,
GAUDI2_PCIE_ENGINE_ID_DEC_0, "DEC9"},
{RAZWI_INITIATOR_ID_X_Y(3, 4, 2), mmDCORE0_RTR1_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_TPC_0, "TPC0"},
{RAZWI_INITIATOR_ID_X_Y(3, 4, 4), mmDCORE0_RTR1_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_TPC_1, "TPC1"},
{RAZWI_INITIATOR_ID_X_Y(4, 4, 2), mmDCORE0_RTR2_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_TPC_2, "TPC2"},
{RAZWI_INITIATOR_ID_X_Y(4, 4, 4), mmDCORE0_RTR2_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_TPC_3, "TPC3"},
{RAZWI_INITIATOR_ID_X_Y(5, 4, 2), mmDCORE0_RTR3_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_TPC_4, "TPC4"},
{RAZWI_INITIATOR_ID_X_Y(5, 4, 4), mmDCORE0_RTR3_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_TPC_5, "TPC5"},
{RAZWI_INITIATOR_ID_X_Y(16, 4, 14), mmDCORE1_RTR6_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_TPC_0, "TPC6"},
{RAZWI_INITIATOR_ID_X_Y(16, 4, 16), mmDCORE1_RTR6_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_TPC_1, "TPC7"},
{RAZWI_INITIATOR_ID_X_Y(15, 4, 14), mmDCORE1_RTR5_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_TPC_2, "TPC8"},
{RAZWI_INITIATOR_ID_X_Y(15, 4, 16), mmDCORE1_RTR5_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_TPC_3, "TPC9"},
{RAZWI_INITIATOR_ID_X_Y(14, 4, 14), mmDCORE1_RTR4_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_TPC_4, "TPC10"},
{RAZWI_INITIATOR_ID_X_Y(14, 4, 16), mmDCORE1_RTR4_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_TPC_5, "TPC11"},
{RAZWI_INITIATOR_ID_X_Y(5, 11, 2), mmDCORE2_RTR3_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_TPC_0, "TPC12"},
{RAZWI_INITIATOR_ID_X_Y(5, 11, 4), mmDCORE2_RTR3_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_TPC_1, "TPC13"},
{RAZWI_INITIATOR_ID_X_Y(4, 11, 2), mmDCORE2_RTR2_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_TPC_2, "TPC14"},
{RAZWI_INITIATOR_ID_X_Y(4, 11, 4), mmDCORE2_RTR2_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_TPC_3, "TPC15"},
{RAZWI_INITIATOR_ID_X_Y(3, 11, 2), mmDCORE2_RTR1_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_TPC_4, "TPC16"},
{RAZWI_INITIATOR_ID_X_Y(3, 11, 4), mmDCORE2_RTR1_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_TPC_5, "TPC17"},
{RAZWI_INITIATOR_ID_X_Y(14, 11, 14), mmDCORE3_RTR4_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_TPC_0, "TPC18"},
{RAZWI_INITIATOR_ID_X_Y(14, 11, 16), mmDCORE3_RTR4_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_TPC_1, "TPC19"},
{RAZWI_INITIATOR_ID_X_Y(15, 11, 14), mmDCORE3_RTR5_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_TPC_2, "TPC20"},
{RAZWI_INITIATOR_ID_X_Y(15, 11, 16), mmDCORE3_RTR5_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_TPC_3, "TPC21"},
{RAZWI_INITIATOR_ID_X_Y(16, 11, 14), mmDCORE3_RTR6_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_TPC_4, "TPC22"},
{RAZWI_INITIATOR_ID_X_Y(16, 11, 16), mmDCORE3_RTR6_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_TPC_5, "TPC23"},
{RAZWI_INITIATOR_ID_X_Y(2, 4, 2), mmDCORE0_RTR0_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_TPC_5, "TPC24"},
{RAZWI_INITIATOR_ID_X_Y(17, 4, 8), mmDCORE1_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_NIC0_0, "NIC0"},
{RAZWI_INITIATOR_ID_X_Y(17, 4, 10), mmDCORE1_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_NIC0_1, "NIC1"},
{RAZWI_INITIATOR_ID_X_Y(17, 4, 12), mmDCORE1_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_NIC1_0, "NIC2"},
{RAZWI_INITIATOR_ID_X_Y(17, 4, 14), mmDCORE1_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_NIC1_1, "NIC3"},
{RAZWI_INITIATOR_ID_X_Y(17, 4, 15), mmDCORE1_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_NIC2_0, "NIC4"},
{RAZWI_INITIATOR_ID_X_Y(2, 11, 2), mmDCORE2_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_NIC2_1, "NIC5"},
{RAZWI_INITIATOR_ID_X_Y(2, 11, 4), mmDCORE2_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_NIC3_0, "NIC6"},
{RAZWI_INITIATOR_ID_X_Y(2, 11, 6), mmDCORE2_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_NIC3_1, "NIC7"},
{RAZWI_INITIATOR_ID_X_Y(2, 11, 8), mmDCORE2_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_NIC4_0, "NIC8"},
{RAZWI_INITIATOR_ID_X_Y(17, 11, 12), mmDCORE3_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_NIC4_1, "NIC9"},
{RAZWI_INITIATOR_ID_X_Y(17, 11, 14), mmDCORE3_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_NIC5_0, "NIC10"},
{RAZWI_INITIATOR_ID_X_Y(17, 11, 16), mmDCORE3_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_NIC5_1, "NIC11"},
{RAZWI_INITIATOR_ID_X_Y(2, 4, 2), mmDCORE0_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_PDMA_0, "PDMA0"},
{RAZWI_INITIATOR_ID_X_Y(2, 4, 3), mmDCORE0_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_PDMA_1, "PDMA1"},
{RAZWI_INITIATOR_ID_X_Y(2, 4, 4), mmDCORE0_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "PMMU"},
{RAZWI_INITIATOR_ID_X_Y(2, 4, 5), mmDCORE0_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "PCIE"},
{RAZWI_INITIATOR_ID_X_Y(17, 4, 16), mmDCORE1_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_ARC_FARM, "ARC_FARM"},
{RAZWI_INITIATOR_ID_X_Y(17, 4, 17), mmDCORE1_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_KDMA, "KDMA"},
{RAZWI_INITIATOR_ID_X_Y(1, 5, 1), mmSFT0_HBW_RTR_IF1_RTR_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_EDMA_0, "EDMA0"},
{RAZWI_INITIATOR_ID_X_Y(1, 5, 1), mmSFT0_HBW_RTR_IF0_RTR_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_EDMA_1, "EDMA1"},
{RAZWI_INITIATOR_ID_X_Y(18, 5, 18), mmSFT1_HBW_RTR_IF1_RTR_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_EDMA_0, "EDMA2"},
{RAZWI_INITIATOR_ID_X_Y(18, 5, 18), mmSFT1_HBW_RTR_IF0_RTR_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_EDMA_1, "EDMA3"},
{RAZWI_INITIATOR_ID_X_Y(1, 10, 1), mmSFT2_HBW_RTR_IF0_RTR_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_EDMA_0, "EDMA4"},
{RAZWI_INITIATOR_ID_X_Y(1, 10, 1), mmSFT2_HBW_RTR_IF1_RTR_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_EDMA_1, "EDMA5"},
{RAZWI_INITIATOR_ID_X_Y(18, 10, 18), mmSFT2_HBW_RTR_IF0_RTR_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_EDMA_0, "EDMA6"},
{RAZWI_INITIATOR_ID_X_Y(18, 10, 18), mmSFT2_HBW_RTR_IF1_RTR_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_EDMA_1, "EDMA7"},
{RAZWI_INITIATOR_ID_X_Y(1, 5, 0), mmDCORE0_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU0"},
{RAZWI_INITIATOR_ID_X_Y(18, 5, 19), mmDCORE1_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU1"},
{RAZWI_INITIATOR_ID_X_Y(1, 5, 0), mmDCORE0_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU2"},
{RAZWI_INITIATOR_ID_X_Y(18, 5, 19), mmDCORE1_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU3"},
{RAZWI_INITIATOR_ID_X_Y(1, 5, 0), mmDCORE0_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU4"},
{RAZWI_INITIATOR_ID_X_Y(18, 5, 19), mmDCORE1_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU5"},
{RAZWI_INITIATOR_ID_X_Y(1, 5, 0), mmDCORE0_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU6"},
{RAZWI_INITIATOR_ID_X_Y(18, 5, 19), mmDCORE1_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU7"},
{RAZWI_INITIATOR_ID_X_Y(1, 10, 0), mmDCORE2_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU8"},
{RAZWI_INITIATOR_ID_X_Y(18, 10, 19), mmDCORE3_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU9"},
{RAZWI_INITIATOR_ID_X_Y(1, 10, 0), mmDCORE2_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU10"},
{RAZWI_INITIATOR_ID_X_Y(18, 10, 19), mmDCORE3_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU11"},
{RAZWI_INITIATOR_ID_X_Y(1, 10, 0), mmDCORE2_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU12"},
{RAZWI_INITIATOR_ID_X_Y(18, 10, 19), mmDCORE3_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU13"},
{RAZWI_INITIATOR_ID_X_Y(1, 10, 0), mmDCORE2_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU14"},
{RAZWI_INITIATOR_ID_X_Y(18, 10, 19), mmDCORE3_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_SIZE, "HMMU15"},
{RAZWI_INITIATOR_ID_X_Y(2, 11, 2), mmDCORE2_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_ROT_0, "ROT0"},
{RAZWI_INITIATOR_ID_X_Y(17, 11, 16), mmDCORE3_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_ROT_1, "ROT1"},
{RAZWI_INITIATOR_ID_X_Y(2, 11, 2), mmDCORE2_RTR0_CTRL_BASE,
GAUDI2_ENGINE_ID_PSOC, "CPU"},
{RAZWI_INITIATOR_ID_X_Y(17, 11, 11), mmDCORE3_RTR7_CTRL_BASE,
GAUDI2_ENGINE_ID_PSOC, "PSOC"}
};
static struct gaudi2_razwi_info mme_razwi_info[] = {
{RAZWI_INITIATOR_ID_X_Y_LOW(7, 4), mmDCORE0_RTR5_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_MME, "MME0_WAP0"},
{RAZWI_INITIATOR_ID_X_Y_LOW(9, 4), mmDCORE0_RTR7_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_MME, "MME0_WAP1"},
{RAZWI_INITIATOR_ID_X_Y_LOW(8, 4), mmDCORE0_RTR6_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_MME, "MME0_CTRL_WR"},
{RAZWI_INITIATOR_ID_X_Y_LOW(9, 4), mmDCORE0_RTR7_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_MME, "MME0_CTRL_RD"},
{RAZWI_INITIATOR_ID_X_Y_LOW(6, 4), mmDCORE0_RTR4_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_MME, "MME0_SBTE0"},
{RAZWI_INITIATOR_ID_X_Y_LOW(6, 4), mmDCORE0_RTR4_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_MME, "MME0_SBTE1"},
{RAZWI_INITIATOR_ID_X_Y_LOW(7, 4), mmDCORE0_RTR5_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_MME, "MME0_SBTE2"},
{RAZWI_INITIATOR_ID_X_Y_LOW(8, 4), mmDCORE0_RTR6_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_MME, "MME0_SBTE3"},
{RAZWI_INITIATOR_ID_X_Y_LOW(9, 4), mmDCORE0_RTR7_CTRL_BASE,
GAUDI2_DCORE0_ENGINE_ID_MME, "MME0_SBTE4"},
{RAZWI_INITIATOR_ID_X_Y_LOW(12, 4), mmDCORE1_RTR2_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_MME, "MME1_WAP0"},
{RAZWI_INITIATOR_ID_X_Y_LOW(10, 4), mmDCORE1_RTR0_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_MME, "MME1_WAP1"},
{RAZWI_INITIATOR_ID_X_Y_LOW(11, 4), mmDCORE1_RTR1_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_MME, "MME1_CTRL_WR"},
{RAZWI_INITIATOR_ID_X_Y_LOW(10, 4), mmDCORE1_RTR0_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_MME, "MME1_CTRL_RD"},
{RAZWI_INITIATOR_ID_X_Y_LOW(13, 4), mmDCORE1_RTR3_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_MME, "MME1_SBTE0"},
{RAZWI_INITIATOR_ID_X_Y_LOW(13, 4), mmDCORE1_RTR3_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_MME, "MME1_SBTE1"},
{RAZWI_INITIATOR_ID_X_Y_LOW(12, 4), mmDCORE1_RTR2_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_MME, "MME1_SBTE2"},
{RAZWI_INITIATOR_ID_X_Y_LOW(11, 4), mmDCORE1_RTR1_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_MME, "MME1_SBTE3"},
{RAZWI_INITIATOR_ID_X_Y_LOW(10, 4), mmDCORE1_RTR0_CTRL_BASE,
GAUDI2_DCORE1_ENGINE_ID_MME, "MME1_SBTE4"},
{RAZWI_INITIATOR_ID_X_Y_LOW(7, 11), mmDCORE2_RTR5_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_MME, "MME2_WAP0"},
{RAZWI_INITIATOR_ID_X_Y_LOW(9, 11), mmDCORE2_RTR7_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_MME, "MME2_WAP1"},
{RAZWI_INITIATOR_ID_X_Y_LOW(8, 11), mmDCORE2_RTR6_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_MME, "MME2_CTRL_WR"},
{RAZWI_INITIATOR_ID_X_Y_LOW(9, 11), mmDCORE2_RTR7_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_MME, "MME2_CTRL_RD"},
{RAZWI_INITIATOR_ID_X_Y_LOW(6, 11), mmDCORE2_RTR4_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_MME, "MME2_SBTE0"},
{RAZWI_INITIATOR_ID_X_Y_LOW(6, 11), mmDCORE2_RTR4_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_MME, "MME2_SBTE1"},
{RAZWI_INITIATOR_ID_X_Y_LOW(7, 11), mmDCORE2_RTR5_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_MME, "MME2_SBTE2"},
{RAZWI_INITIATOR_ID_X_Y_LOW(8, 11), mmDCORE2_RTR6_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_MME, "MME2_SBTE3"},
{RAZWI_INITIATOR_ID_X_Y_LOW(9, 11), mmDCORE2_RTR7_CTRL_BASE,
GAUDI2_DCORE2_ENGINE_ID_MME, "MME2_SBTE4"},
{RAZWI_INITIATOR_ID_X_Y_LOW(12, 11), mmDCORE3_RTR2_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_MME, "MME3_WAP0"},
{RAZWI_INITIATOR_ID_X_Y_LOW(10, 11), mmDCORE3_RTR0_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_MME, "MME3_WAP1"},
{RAZWI_INITIATOR_ID_X_Y_LOW(11, 11), mmDCORE3_RTR1_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_MME, "MME3_CTRL_WR"},
{RAZWI_INITIATOR_ID_X_Y_LOW(10, 11), mmDCORE3_RTR0_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_MME, "MME3_CTRL_RD"},
{RAZWI_INITIATOR_ID_X_Y_LOW(13, 11), mmDCORE3_RTR3_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_MME, "MME3_SBTE0"},
{RAZWI_INITIATOR_ID_X_Y_LOW(13, 11), mmDCORE3_RTR3_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_MME, "MME3_SBTE1"},
{RAZWI_INITIATOR_ID_X_Y_LOW(12, 11), mmDCORE3_RTR2_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_MME, "MME3_SBTE2"},
{RAZWI_INITIATOR_ID_X_Y_LOW(11, 11), mmDCORE3_RTR1_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_MME, "MME3_SBTE3"},
{RAZWI_INITIATOR_ID_X_Y_LOW(10, 11), mmDCORE3_RTR0_CTRL_BASE,
GAUDI2_DCORE3_ENGINE_ID_MME, "MME3_SBTE4"}
};
enum hl_pmmu_fatal_cause {
LATENCY_RD_OUT_FIFO_OVERRUN,
LATENCY_WR_OUT_FIFO_OVERRUN,
};
enum hl_pcie_drain_ind_cause {
LBW_AXI_DRAIN_IND,
HBW_AXI_DRAIN_IND
};
static const u32 cluster_hmmu_hif_enabled_mask[GAUDI2_HBM_NUM] = {
[HBM_ID0] = 0xFFFC,
[HBM_ID1] = 0xFFCF,
[HBM_ID2] = 0xF7F7,
[HBM_ID3] = 0x7F7F,
[HBM_ID4] = 0xFCFF,
[HBM_ID5] = 0xCFFF,
};
static const u8 xbar_edge_to_hbm_cluster[EDMA_ID_SIZE] = {
[0] = HBM_ID0,
[1] = HBM_ID1,
[2] = HBM_ID4,
[3] = HBM_ID5,
};
static const u8 edma_to_hbm_cluster[EDMA_ID_SIZE] = {
[EDMA_ID_DCORE0_INSTANCE0] = HBM_ID0,
[EDMA_ID_DCORE0_INSTANCE1] = HBM_ID2,
[EDMA_ID_DCORE1_INSTANCE0] = HBM_ID1,
[EDMA_ID_DCORE1_INSTANCE1] = HBM_ID3,
[EDMA_ID_DCORE2_INSTANCE0] = HBM_ID2,
[EDMA_ID_DCORE2_INSTANCE1] = HBM_ID4,
[EDMA_ID_DCORE3_INSTANCE0] = HBM_ID3,
[EDMA_ID_DCORE3_INSTANCE1] = HBM_ID5,
};
static const int gaudi2_qman_async_event_id[] = {
[GAUDI2_QUEUE_ID_PDMA_0_0] = GAUDI2_EVENT_PDMA0_QM,
[GAUDI2_QUEUE_ID_PDMA_0_1] = GAUDI2_EVENT_PDMA0_QM,
[GAUDI2_QUEUE_ID_PDMA_0_2] = GAUDI2_EVENT_PDMA0_QM,
[GAUDI2_QUEUE_ID_PDMA_0_3] = GAUDI2_EVENT_PDMA0_QM,
[GAUDI2_QUEUE_ID_PDMA_1_0] = GAUDI2_EVENT_PDMA1_QM,
[GAUDI2_QUEUE_ID_PDMA_1_1] = GAUDI2_EVENT_PDMA1_QM,
[GAUDI2_QUEUE_ID_PDMA_1_2] = GAUDI2_EVENT_PDMA1_QM,
[GAUDI2_QUEUE_ID_PDMA_1_3] = GAUDI2_EVENT_PDMA1_QM,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_0_0] = GAUDI2_EVENT_HDMA0_QM,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_0_1] = GAUDI2_EVENT_HDMA0_QM,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_0_2] = GAUDI2_EVENT_HDMA0_QM,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_0_3] = GAUDI2_EVENT_HDMA0_QM,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_1_0] = GAUDI2_EVENT_HDMA1_QM,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_1_1] = GAUDI2_EVENT_HDMA1_QM,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_1_2] = GAUDI2_EVENT_HDMA1_QM,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_1_3] = GAUDI2_EVENT_HDMA1_QM,
[GAUDI2_QUEUE_ID_DCORE0_MME_0_0] = GAUDI2_EVENT_MME0_QM,
[GAUDI2_QUEUE_ID_DCORE0_MME_0_1] = GAUDI2_EVENT_MME0_QM,
[GAUDI2_QUEUE_ID_DCORE0_MME_0_2] = GAUDI2_EVENT_MME0_QM,
[GAUDI2_QUEUE_ID_DCORE0_MME_0_3] = GAUDI2_EVENT_MME0_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_0_0] = GAUDI2_EVENT_TPC0_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_0_1] = GAUDI2_EVENT_TPC0_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_0_2] = GAUDI2_EVENT_TPC0_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_0_3] = GAUDI2_EVENT_TPC0_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_1_0] = GAUDI2_EVENT_TPC1_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_1_1] = GAUDI2_EVENT_TPC1_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_1_2] = GAUDI2_EVENT_TPC1_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_1_3] = GAUDI2_EVENT_TPC1_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_2_0] = GAUDI2_EVENT_TPC2_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_2_1] = GAUDI2_EVENT_TPC2_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_2_2] = GAUDI2_EVENT_TPC2_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_2_3] = GAUDI2_EVENT_TPC2_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_3_0] = GAUDI2_EVENT_TPC3_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_3_1] = GAUDI2_EVENT_TPC3_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_3_2] = GAUDI2_EVENT_TPC3_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_3_3] = GAUDI2_EVENT_TPC3_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_4_0] = GAUDI2_EVENT_TPC4_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_4_1] = GAUDI2_EVENT_TPC4_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_4_2] = GAUDI2_EVENT_TPC4_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_4_3] = GAUDI2_EVENT_TPC4_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_5_0] = GAUDI2_EVENT_TPC5_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_5_1] = GAUDI2_EVENT_TPC5_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_5_2] = GAUDI2_EVENT_TPC5_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_5_3] = GAUDI2_EVENT_TPC5_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_6_0] = GAUDI2_EVENT_TPC24_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_6_1] = GAUDI2_EVENT_TPC24_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_6_2] = GAUDI2_EVENT_TPC24_QM,
[GAUDI2_QUEUE_ID_DCORE0_TPC_6_3] = GAUDI2_EVENT_TPC24_QM,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_0_0] = GAUDI2_EVENT_HDMA2_QM,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_0_1] = GAUDI2_EVENT_HDMA2_QM,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_0_2] = GAUDI2_EVENT_HDMA2_QM,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_0_3] = GAUDI2_EVENT_HDMA2_QM,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_1_0] = GAUDI2_EVENT_HDMA3_QM,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_1_1] = GAUDI2_EVENT_HDMA3_QM,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_1_2] = GAUDI2_EVENT_HDMA3_QM,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_1_3] = GAUDI2_EVENT_HDMA3_QM,
[GAUDI2_QUEUE_ID_DCORE1_MME_0_0] = GAUDI2_EVENT_MME1_QM,
[GAUDI2_QUEUE_ID_DCORE1_MME_0_1] = GAUDI2_EVENT_MME1_QM,
[GAUDI2_QUEUE_ID_DCORE1_MME_0_2] = GAUDI2_EVENT_MME1_QM,
[GAUDI2_QUEUE_ID_DCORE1_MME_0_3] = GAUDI2_EVENT_MME1_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_0_0] = GAUDI2_EVENT_TPC6_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_0_1] = GAUDI2_EVENT_TPC6_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_0_2] = GAUDI2_EVENT_TPC6_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_0_3] = GAUDI2_EVENT_TPC6_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_1_0] = GAUDI2_EVENT_TPC7_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_1_1] = GAUDI2_EVENT_TPC7_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_1_2] = GAUDI2_EVENT_TPC7_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_1_3] = GAUDI2_EVENT_TPC7_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_2_0] = GAUDI2_EVENT_TPC8_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_2_1] = GAUDI2_EVENT_TPC8_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_2_2] = GAUDI2_EVENT_TPC8_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_2_3] = GAUDI2_EVENT_TPC8_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_3_0] = GAUDI2_EVENT_TPC9_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_3_1] = GAUDI2_EVENT_TPC9_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_3_2] = GAUDI2_EVENT_TPC9_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_3_3] = GAUDI2_EVENT_TPC9_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_4_0] = GAUDI2_EVENT_TPC10_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_4_1] = GAUDI2_EVENT_TPC10_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_4_2] = GAUDI2_EVENT_TPC10_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_4_3] = GAUDI2_EVENT_TPC10_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_5_0] = GAUDI2_EVENT_TPC11_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_5_1] = GAUDI2_EVENT_TPC11_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_5_2] = GAUDI2_EVENT_TPC11_QM,
[GAUDI2_QUEUE_ID_DCORE1_TPC_5_3] = GAUDI2_EVENT_TPC11_QM,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_0_0] = GAUDI2_EVENT_HDMA4_QM,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_0_1] = GAUDI2_EVENT_HDMA4_QM,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_0_2] = GAUDI2_EVENT_HDMA4_QM,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_0_3] = GAUDI2_EVENT_HDMA4_QM,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_1_0] = GAUDI2_EVENT_HDMA5_QM,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_1_1] = GAUDI2_EVENT_HDMA5_QM,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_1_2] = GAUDI2_EVENT_HDMA5_QM,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_1_3] = GAUDI2_EVENT_HDMA5_QM,
[GAUDI2_QUEUE_ID_DCORE2_MME_0_0] = GAUDI2_EVENT_MME2_QM,
[GAUDI2_QUEUE_ID_DCORE2_MME_0_1] = GAUDI2_EVENT_MME2_QM,
[GAUDI2_QUEUE_ID_DCORE2_MME_0_2] = GAUDI2_EVENT_MME2_QM,
[GAUDI2_QUEUE_ID_DCORE2_MME_0_3] = GAUDI2_EVENT_MME2_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_0_0] = GAUDI2_EVENT_TPC12_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_0_1] = GAUDI2_EVENT_TPC12_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_0_2] = GAUDI2_EVENT_TPC12_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_0_3] = GAUDI2_EVENT_TPC12_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_1_0] = GAUDI2_EVENT_TPC13_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_1_1] = GAUDI2_EVENT_TPC13_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_1_2] = GAUDI2_EVENT_TPC13_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_1_3] = GAUDI2_EVENT_TPC13_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_2_0] = GAUDI2_EVENT_TPC14_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_2_1] = GAUDI2_EVENT_TPC14_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_2_2] = GAUDI2_EVENT_TPC14_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_2_3] = GAUDI2_EVENT_TPC14_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_3_0] = GAUDI2_EVENT_TPC15_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_3_1] = GAUDI2_EVENT_TPC15_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_3_2] = GAUDI2_EVENT_TPC15_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_3_3] = GAUDI2_EVENT_TPC15_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_4_0] = GAUDI2_EVENT_TPC16_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_4_1] = GAUDI2_EVENT_TPC16_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_4_2] = GAUDI2_EVENT_TPC16_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_4_3] = GAUDI2_EVENT_TPC16_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_5_0] = GAUDI2_EVENT_TPC17_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_5_1] = GAUDI2_EVENT_TPC17_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_5_2] = GAUDI2_EVENT_TPC17_QM,
[GAUDI2_QUEUE_ID_DCORE2_TPC_5_3] = GAUDI2_EVENT_TPC17_QM,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_0_0] = GAUDI2_EVENT_HDMA6_QM,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_0_1] = GAUDI2_EVENT_HDMA6_QM,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_0_2] = GAUDI2_EVENT_HDMA6_QM,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_0_3] = GAUDI2_EVENT_HDMA6_QM,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_0] = GAUDI2_EVENT_HDMA7_QM,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_1] = GAUDI2_EVENT_HDMA7_QM,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_2] = GAUDI2_EVENT_HDMA7_QM,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_3] = GAUDI2_EVENT_HDMA7_QM,
[GAUDI2_QUEUE_ID_DCORE3_MME_0_0] = GAUDI2_EVENT_MME3_QM,
[GAUDI2_QUEUE_ID_DCORE3_MME_0_1] = GAUDI2_EVENT_MME3_QM,
[GAUDI2_QUEUE_ID_DCORE3_MME_0_2] = GAUDI2_EVENT_MME3_QM,
[GAUDI2_QUEUE_ID_DCORE3_MME_0_3] = GAUDI2_EVENT_MME3_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_0_0] = GAUDI2_EVENT_TPC18_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_0_1] = GAUDI2_EVENT_TPC18_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_0_2] = GAUDI2_EVENT_TPC18_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_0_3] = GAUDI2_EVENT_TPC18_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_1_0] = GAUDI2_EVENT_TPC19_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_1_1] = GAUDI2_EVENT_TPC19_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_1_2] = GAUDI2_EVENT_TPC19_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_1_3] = GAUDI2_EVENT_TPC19_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_2_0] = GAUDI2_EVENT_TPC20_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_2_1] = GAUDI2_EVENT_TPC20_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_2_2] = GAUDI2_EVENT_TPC20_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_2_3] = GAUDI2_EVENT_TPC20_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_3_0] = GAUDI2_EVENT_TPC21_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_3_1] = GAUDI2_EVENT_TPC21_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_3_2] = GAUDI2_EVENT_TPC21_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_3_3] = GAUDI2_EVENT_TPC21_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_4_0] = GAUDI2_EVENT_TPC22_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_4_1] = GAUDI2_EVENT_TPC22_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_4_2] = GAUDI2_EVENT_TPC22_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_4_3] = GAUDI2_EVENT_TPC22_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_5_0] = GAUDI2_EVENT_TPC23_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_5_1] = GAUDI2_EVENT_TPC23_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_5_2] = GAUDI2_EVENT_TPC23_QM,
[GAUDI2_QUEUE_ID_DCORE3_TPC_5_3] = GAUDI2_EVENT_TPC23_QM,
[GAUDI2_QUEUE_ID_NIC_0_0] = GAUDI2_EVENT_NIC0_QM0,
[GAUDI2_QUEUE_ID_NIC_0_1] = GAUDI2_EVENT_NIC0_QM0,
[GAUDI2_QUEUE_ID_NIC_0_2] = GAUDI2_EVENT_NIC0_QM0,
[GAUDI2_QUEUE_ID_NIC_0_3] = GAUDI2_EVENT_NIC0_QM0,
[GAUDI2_QUEUE_ID_NIC_1_0] = GAUDI2_EVENT_NIC0_QM1,
[GAUDI2_QUEUE_ID_NIC_1_1] = GAUDI2_EVENT_NIC0_QM1,
[GAUDI2_QUEUE_ID_NIC_1_2] = GAUDI2_EVENT_NIC0_QM1,
[GAUDI2_QUEUE_ID_NIC_1_3] = GAUDI2_EVENT_NIC0_QM1,
[GAUDI2_QUEUE_ID_NIC_2_0] = GAUDI2_EVENT_NIC1_QM0,
[GAUDI2_QUEUE_ID_NIC_2_1] = GAUDI2_EVENT_NIC1_QM0,
[GAUDI2_QUEUE_ID_NIC_2_2] = GAUDI2_EVENT_NIC1_QM0,
[GAUDI2_QUEUE_ID_NIC_2_3] = GAUDI2_EVENT_NIC1_QM0,
[GAUDI2_QUEUE_ID_NIC_3_0] = GAUDI2_EVENT_NIC1_QM1,
[GAUDI2_QUEUE_ID_NIC_3_1] = GAUDI2_EVENT_NIC1_QM1,
[GAUDI2_QUEUE_ID_NIC_3_2] = GAUDI2_EVENT_NIC1_QM1,
[GAUDI2_QUEUE_ID_NIC_3_3] = GAUDI2_EVENT_NIC1_QM1,
[GAUDI2_QUEUE_ID_NIC_4_0] = GAUDI2_EVENT_NIC2_QM0,
[GAUDI2_QUEUE_ID_NIC_4_1] = GAUDI2_EVENT_NIC2_QM0,
[GAUDI2_QUEUE_ID_NIC_4_2] = GAUDI2_EVENT_NIC2_QM0,
[GAUDI2_QUEUE_ID_NIC_4_3] = GAUDI2_EVENT_NIC2_QM0,
[GAUDI2_QUEUE_ID_NIC_5_0] = GAUDI2_EVENT_NIC2_QM1,
[GAUDI2_QUEUE_ID_NIC_5_1] = GAUDI2_EVENT_NIC2_QM1,
[GAUDI2_QUEUE_ID_NIC_5_2] = GAUDI2_EVENT_NIC2_QM1,
[GAUDI2_QUEUE_ID_NIC_5_3] = GAUDI2_EVENT_NIC2_QM1,
[GAUDI2_QUEUE_ID_NIC_6_0] = GAUDI2_EVENT_NIC3_QM0,
[GAUDI2_QUEUE_ID_NIC_6_1] = GAUDI2_EVENT_NIC3_QM0,
[GAUDI2_QUEUE_ID_NIC_6_2] = GAUDI2_EVENT_NIC3_QM0,
[GAUDI2_QUEUE_ID_NIC_6_3] = GAUDI2_EVENT_NIC3_QM0,
[GAUDI2_QUEUE_ID_NIC_7_0] = GAUDI2_EVENT_NIC3_QM1,
[GAUDI2_QUEUE_ID_NIC_7_1] = GAUDI2_EVENT_NIC3_QM1,
[GAUDI2_QUEUE_ID_NIC_7_2] = GAUDI2_EVENT_NIC3_QM1,
[GAUDI2_QUEUE_ID_NIC_7_3] = GAUDI2_EVENT_NIC3_QM1,
[GAUDI2_QUEUE_ID_NIC_8_0] = GAUDI2_EVENT_NIC4_QM0,
[GAUDI2_QUEUE_ID_NIC_8_1] = GAUDI2_EVENT_NIC4_QM0,
[GAUDI2_QUEUE_ID_NIC_8_2] = GAUDI2_EVENT_NIC4_QM0,
[GAUDI2_QUEUE_ID_NIC_8_3] = GAUDI2_EVENT_NIC4_QM0,
[GAUDI2_QUEUE_ID_NIC_9_0] = GAUDI2_EVENT_NIC4_QM1,
[GAUDI2_QUEUE_ID_NIC_9_1] = GAUDI2_EVENT_NIC4_QM1,
[GAUDI2_QUEUE_ID_NIC_9_2] = GAUDI2_EVENT_NIC4_QM1,
[GAUDI2_QUEUE_ID_NIC_9_3] = GAUDI2_EVENT_NIC4_QM1,
[GAUDI2_QUEUE_ID_NIC_10_0] = GAUDI2_EVENT_NIC5_QM0,
[GAUDI2_QUEUE_ID_NIC_10_1] = GAUDI2_EVENT_NIC5_QM0,
[GAUDI2_QUEUE_ID_NIC_10_2] = GAUDI2_EVENT_NIC5_QM0,
[GAUDI2_QUEUE_ID_NIC_10_3] = GAUDI2_EVENT_NIC5_QM0,
[GAUDI2_QUEUE_ID_NIC_11_0] = GAUDI2_EVENT_NIC5_QM1,
[GAUDI2_QUEUE_ID_NIC_11_1] = GAUDI2_EVENT_NIC5_QM1,
[GAUDI2_QUEUE_ID_NIC_11_2] = GAUDI2_EVENT_NIC5_QM1,
[GAUDI2_QUEUE_ID_NIC_11_3] = GAUDI2_EVENT_NIC5_QM1,
[GAUDI2_QUEUE_ID_NIC_12_0] = GAUDI2_EVENT_NIC6_QM0,
[GAUDI2_QUEUE_ID_NIC_12_1] = GAUDI2_EVENT_NIC6_QM0,
[GAUDI2_QUEUE_ID_NIC_12_2] = GAUDI2_EVENT_NIC6_QM0,
[GAUDI2_QUEUE_ID_NIC_12_3] = GAUDI2_EVENT_NIC6_QM0,
[GAUDI2_QUEUE_ID_NIC_13_0] = GAUDI2_EVENT_NIC6_QM1,
[GAUDI2_QUEUE_ID_NIC_13_1] = GAUDI2_EVENT_NIC6_QM1,
[GAUDI2_QUEUE_ID_NIC_13_2] = GAUDI2_EVENT_NIC6_QM1,
[GAUDI2_QUEUE_ID_NIC_13_3] = GAUDI2_EVENT_NIC6_QM1,
[GAUDI2_QUEUE_ID_NIC_14_0] = GAUDI2_EVENT_NIC7_QM0,
[GAUDI2_QUEUE_ID_NIC_14_1] = GAUDI2_EVENT_NIC7_QM0,
[GAUDI2_QUEUE_ID_NIC_14_2] = GAUDI2_EVENT_NIC7_QM0,
[GAUDI2_QUEUE_ID_NIC_14_3] = GAUDI2_EVENT_NIC7_QM0,
[GAUDI2_QUEUE_ID_NIC_15_0] = GAUDI2_EVENT_NIC7_QM1,
[GAUDI2_QUEUE_ID_NIC_15_1] = GAUDI2_EVENT_NIC7_QM1,
[GAUDI2_QUEUE_ID_NIC_15_2] = GAUDI2_EVENT_NIC7_QM1,
[GAUDI2_QUEUE_ID_NIC_15_3] = GAUDI2_EVENT_NIC7_QM1,
[GAUDI2_QUEUE_ID_NIC_16_0] = GAUDI2_EVENT_NIC8_QM0,
[GAUDI2_QUEUE_ID_NIC_16_1] = GAUDI2_EVENT_NIC8_QM0,
[GAUDI2_QUEUE_ID_NIC_16_2] = GAUDI2_EVENT_NIC8_QM0,
[GAUDI2_QUEUE_ID_NIC_16_3] = GAUDI2_EVENT_NIC8_QM0,
[GAUDI2_QUEUE_ID_NIC_17_0] = GAUDI2_EVENT_NIC8_QM1,
[GAUDI2_QUEUE_ID_NIC_17_1] = GAUDI2_EVENT_NIC8_QM1,
[GAUDI2_QUEUE_ID_NIC_17_2] = GAUDI2_EVENT_NIC8_QM1,
[GAUDI2_QUEUE_ID_NIC_17_3] = GAUDI2_EVENT_NIC8_QM1,
[GAUDI2_QUEUE_ID_NIC_18_0] = GAUDI2_EVENT_NIC9_QM0,
[GAUDI2_QUEUE_ID_NIC_18_1] = GAUDI2_EVENT_NIC9_QM0,
[GAUDI2_QUEUE_ID_NIC_18_2] = GAUDI2_EVENT_NIC9_QM0,
[GAUDI2_QUEUE_ID_NIC_18_3] = GAUDI2_EVENT_NIC9_QM0,
[GAUDI2_QUEUE_ID_NIC_19_0] = GAUDI2_EVENT_NIC9_QM1,
[GAUDI2_QUEUE_ID_NIC_19_1] = GAUDI2_EVENT_NIC9_QM1,
[GAUDI2_QUEUE_ID_NIC_19_2] = GAUDI2_EVENT_NIC9_QM1,
[GAUDI2_QUEUE_ID_NIC_19_3] = GAUDI2_EVENT_NIC9_QM1,
[GAUDI2_QUEUE_ID_NIC_20_0] = GAUDI2_EVENT_NIC10_QM0,
[GAUDI2_QUEUE_ID_NIC_20_1] = GAUDI2_EVENT_NIC10_QM0,
[GAUDI2_QUEUE_ID_NIC_20_2] = GAUDI2_EVENT_NIC10_QM0,
[GAUDI2_QUEUE_ID_NIC_20_3] = GAUDI2_EVENT_NIC10_QM0,
[GAUDI2_QUEUE_ID_NIC_21_0] = GAUDI2_EVENT_NIC10_QM1,
[GAUDI2_QUEUE_ID_NIC_21_1] = GAUDI2_EVENT_NIC10_QM1,
[GAUDI2_QUEUE_ID_NIC_21_2] = GAUDI2_EVENT_NIC10_QM1,
[GAUDI2_QUEUE_ID_NIC_21_3] = GAUDI2_EVENT_NIC10_QM1,
[GAUDI2_QUEUE_ID_NIC_22_0] = GAUDI2_EVENT_NIC11_QM0,
[GAUDI2_QUEUE_ID_NIC_22_1] = GAUDI2_EVENT_NIC11_QM0,
[GAUDI2_QUEUE_ID_NIC_22_2] = GAUDI2_EVENT_NIC11_QM0,
[GAUDI2_QUEUE_ID_NIC_22_3] = GAUDI2_EVENT_NIC11_QM0,
[GAUDI2_QUEUE_ID_NIC_23_0] = GAUDI2_EVENT_NIC11_QM1,
[GAUDI2_QUEUE_ID_NIC_23_1] = GAUDI2_EVENT_NIC11_QM1,
[GAUDI2_QUEUE_ID_NIC_23_2] = GAUDI2_EVENT_NIC11_QM1,
[GAUDI2_QUEUE_ID_NIC_23_3] = GAUDI2_EVENT_NIC11_QM1,
[GAUDI2_QUEUE_ID_ROT_0_0] = GAUDI2_EVENT_ROTATOR0_ROT0_QM,
[GAUDI2_QUEUE_ID_ROT_0_1] = GAUDI2_EVENT_ROTATOR0_ROT0_QM,
[GAUDI2_QUEUE_ID_ROT_0_2] = GAUDI2_EVENT_ROTATOR0_ROT0_QM,
[GAUDI2_QUEUE_ID_ROT_0_3] = GAUDI2_EVENT_ROTATOR0_ROT0_QM,
[GAUDI2_QUEUE_ID_ROT_1_0] = GAUDI2_EVENT_ROTATOR1_ROT1_QM,
[GAUDI2_QUEUE_ID_ROT_1_1] = GAUDI2_EVENT_ROTATOR1_ROT1_QM,
[GAUDI2_QUEUE_ID_ROT_1_2] = GAUDI2_EVENT_ROTATOR1_ROT1_QM,
[GAUDI2_QUEUE_ID_ROT_1_3] = GAUDI2_EVENT_ROTATOR1_ROT1_QM
};
static const int gaudi2_dma_core_async_event_id[] = {
[DMA_CORE_ID_EDMA0] = GAUDI2_EVENT_HDMA0_CORE,
[DMA_CORE_ID_EDMA1] = GAUDI2_EVENT_HDMA1_CORE,
[DMA_CORE_ID_EDMA2] = GAUDI2_EVENT_HDMA2_CORE,
[DMA_CORE_ID_EDMA3] = GAUDI2_EVENT_HDMA3_CORE,
[DMA_CORE_ID_EDMA4] = GAUDI2_EVENT_HDMA4_CORE,
[DMA_CORE_ID_EDMA5] = GAUDI2_EVENT_HDMA5_CORE,
[DMA_CORE_ID_EDMA6] = GAUDI2_EVENT_HDMA6_CORE,
[DMA_CORE_ID_EDMA7] = GAUDI2_EVENT_HDMA7_CORE,
[DMA_CORE_ID_PDMA0] = GAUDI2_EVENT_PDMA0_CORE,
[DMA_CORE_ID_PDMA1] = GAUDI2_EVENT_PDMA1_CORE,
[DMA_CORE_ID_KDMA] = GAUDI2_EVENT_KDMA0_CORE,
};
static const char * const gaudi2_qm_sei_error_cause[GAUDI2_NUM_OF_QM_SEI_ERR_CAUSE] = {
"qman sei intr",
"arc sei intr"
};
static const char * const gaudi2_cpu_sei_error_cause[GAUDI2_NUM_OF_CPU_SEI_ERR_CAUSE] = {
"AXI_TERMINATOR WR",
"AXI_TERMINATOR RD",
"AXI SPLIT SEI Status"
};
static const char * const gaudi2_arc_sei_error_cause[GAUDI2_NUM_OF_ARC_SEI_ERR_CAUSE] = {
"cbu_bresp_sei_intr_cause",
"cbu_rresp_sei_intr_cause",
"lbu_bresp_sei_intr_cause",
"lbu_rresp_sei_intr_cause",
"cbu_axi_split_intr_cause",
"lbu_axi_split_intr_cause",
"arc_ip_excptn_sei_intr_cause",
"dmi_bresp_sei_intr_cause",
"aux2apb_err_sei_intr_cause",
"cfg_lbw_wr_terminated_intr_cause",
"cfg_lbw_rd_terminated_intr_cause",
"cfg_dccm_wr_terminated_intr_cause",
"cfg_dccm_rd_terminated_intr_cause",
"cfg_hbw_rd_terminated_intr_cause"
};
static const char * const gaudi2_dec_error_cause[GAUDI2_NUM_OF_DEC_ERR_CAUSE] = {
"msix_vcd_hbw_sei",
"msix_l2c_hbw_sei",
"msix_nrm_hbw_sei",
"msix_abnrm_hbw_sei",
"msix_vcd_lbw_sei",
"msix_l2c_lbw_sei",
"msix_nrm_lbw_sei",
"msix_abnrm_lbw_sei",
"apb_vcd_lbw_sei",
"apb_l2c_lbw_sei",
"apb_nrm_lbw_sei",
"apb_abnrm_lbw_sei",
"dec_sei",
"dec_apb_sei",
"trc_apb_sei",
"lbw_mstr_if_sei",
"axi_split_bresp_err_sei",
"hbw_axi_wr_viol_sei",
"hbw_axi_rd_viol_sei",
"lbw_axi_wr_viol_sei",
"lbw_axi_rd_viol_sei",
"vcd_spi",
"l2c_spi",
"nrm_spi",
"abnrm_spi",
};
static const char * const gaudi2_qman_error_cause[GAUDI2_NUM_OF_QM_ERR_CAUSE] = {
"PQ AXI HBW error",
"CQ AXI HBW error",
"CP AXI HBW error",
"CP error due to undefined OPCODE",
"CP encountered STOP OPCODE",
"CP AXI LBW error",
"CP WRREG32 or WRBULK returned error",
"N/A",
"FENCE 0 inc over max value and clipped",
"FENCE 1 inc over max value and clipped",
"FENCE 2 inc over max value and clipped",
"FENCE 3 inc over max value and clipped",
"FENCE 0 dec under min value and clipped",
"FENCE 1 dec under min value and clipped",
"FENCE 2 dec under min value and clipped",
"FENCE 3 dec under min value and clipped",
"CPDMA Up overflow",
"PQC L2H error"
};
static const char * const gaudi2_lower_qman_error_cause[GAUDI2_NUM_OF_LOWER_QM_ERR_CAUSE] = {
"RSVD0",
"CQ AXI HBW error",
"CP AXI HBW error",
"CP error due to undefined OPCODE",
"CP encountered STOP OPCODE",
"CP AXI LBW error",
"CP WRREG32 or WRBULK returned error",
"N/A",
"FENCE 0 inc over max value and clipped",
"FENCE 1 inc over max value and clipped",
"FENCE 2 inc over max value and clipped",
"FENCE 3 inc over max value and clipped",
"FENCE 0 dec under min value and clipped",
"FENCE 1 dec under min value and clipped",
"FENCE 2 dec under min value and clipped",
"FENCE 3 dec under min value and clipped",
"CPDMA Up overflow",
"RSVD17",
"CQ_WR_IFIFO_CI_ERR",
"CQ_WR_CTL_CI_ERR",
"ARC_CQF_RD_ERR",
"ARC_CQ_WR_IFIFO_CI_ERR",
"ARC_CQ_WR_CTL_CI_ERR",
"ARC_AXI_ERR",
"CP_SWITCH_WDT_ERR"
};
static const char * const gaudi2_qman_arb_error_cause[GAUDI2_NUM_OF_QM_ARB_ERR_CAUSE] = {
"Choice push while full error",
"Choice Q watchdog error",
"MSG AXI LBW returned with error"
};
static const char * const guadi2_rot_error_cause[GAUDI2_NUM_OF_ROT_ERR_CAUSE] = {
"qm_axi_err",
"qm_trace_fence_events",
"qm_sw_err",
"qm_cp_sw_stop",
"lbw_mstr_rresp_err",
"lbw_mstr_bresp_err",
"lbw_msg_slverr",
"hbw_msg_slverr",
"wbc_slverr",
"hbw_mstr_rresp_err",
"hbw_mstr_bresp_err",
"sb_resp_intr",
"mrsb_resp_intr",
"core_dw_status_0",
"core_dw_status_1",
"core_dw_status_2",
"core_dw_status_3",
"core_dw_status_4",
"core_dw_status_5",
"core_dw_status_6",
"core_dw_status_7",
"async_arc2cpu_sei_intr",
};
static const char * const gaudi2_tpc_interrupts_cause[GAUDI2_NUM_OF_TPC_INTR_CAUSE] = {
"tpc_address_exceed_slm",
"tpc_div_by_0",
"tpc_spu_mac_overflow",
"tpc_spu_addsub_overflow",
"tpc_spu_abs_overflow",
"tpc_spu_fma_fp_dst_nan",
"tpc_spu_fma_fp_dst_inf",
"tpc_spu_convert_fp_dst_nan",
"tpc_spu_convert_fp_dst_inf",
"tpc_spu_fp_dst_denorm",
"tpc_vpu_mac_overflow",
"tpc_vpu_addsub_overflow",
"tpc_vpu_abs_overflow",
"tpc_vpu_convert_fp_dst_nan",
"tpc_vpu_convert_fp_dst_inf",
"tpc_vpu_fma_fp_dst_nan",
"tpc_vpu_fma_fp_dst_inf",
"tpc_vpu_fp_dst_denorm",
"tpc_assertions",
"tpc_illegal_instruction",
"tpc_pc_wrap_around",
"tpc_qm_sw_err",
"tpc_hbw_rresp_err",
"tpc_hbw_bresp_err",
"tpc_lbw_rresp_err",
"tpc_lbw_bresp_err",
"st_unlock_already_locked",
"invalid_lock_access",
"LD_L protection violation",
"ST_L protection violation",
"D$ L0CS mismatch",
};
static const char * const guadi2_mme_error_cause[GAUDI2_NUM_OF_MME_ERR_CAUSE] = {
"agu_resp_intr",
"qman_axi_err",
"wap sei (wbc axi err)",
"arc sei",
"cfg access error",
"qm_sw_err",
"sbte_dbg_intr_0",
"sbte_dbg_intr_1",
"sbte_dbg_intr_2",
"sbte_dbg_intr_3",
"sbte_dbg_intr_4",
"sbte_prtn_intr_0",
"sbte_prtn_intr_1",
"sbte_prtn_intr_2",
"sbte_prtn_intr_3",
"sbte_prtn_intr_4",
};
static const char * const guadi2_mme_sbte_error_cause[GAUDI2_NUM_OF_MME_SBTE_ERR_CAUSE] = {
"i0",
"i1",
"i2",
"i3",
"i4",
};
static const char * const guadi2_mme_wap_error_cause[GAUDI2_NUM_OF_MME_WAP_ERR_CAUSE] = {
"WBC ERR RESP_0",
"WBC ERR RESP_1",
"AP SOURCE POS INF",
"AP SOURCE NEG INF",
"AP SOURCE NAN",
"AP RESULT POS INF",
"AP RESULT NEG INF",
};
static const char * const gaudi2_dma_core_interrupts_cause[GAUDI2_NUM_OF_DMA_CORE_INTR_CAUSE] = {
"HBW Read returned with error RRESP",
"HBW write returned with error BRESP",
"LBW write returned with error BRESP",
"descriptor_fifo_overflow",
"KDMA SB LBW Read returned with error",
"KDMA WBC LBW Write returned with error",
"TRANSPOSE ENGINE DESC FIFO OVERFLOW",
"WRONG CFG FOR COMMIT IN LIN DMA"
};
static const char * const gaudi2_kdma_core_interrupts_cause[GAUDI2_NUM_OF_DMA_CORE_INTR_CAUSE] = {
"HBW/LBW Read returned with error RRESP",
"HBW/LBW write returned with error BRESP",
"LBW write returned with error BRESP",
"descriptor_fifo_overflow",
"KDMA SB LBW Read returned with error",
"KDMA WBC LBW Write returned with error",
"TRANSPOSE ENGINE DESC FIFO OVERFLOW",
"WRONG CFG FOR COMMIT IN LIN DMA"
};
struct gaudi2_sm_sei_cause_data {
const char *cause_name;
const char *log_name;
};
static const struct gaudi2_sm_sei_cause_data
gaudi2_sm_sei_cause[GAUDI2_NUM_OF_SM_SEI_ERR_CAUSE] = {
{"calculated SO value overflow/underflow", "SOB ID"},
{"payload address of monitor is not aligned to 4B", "monitor addr"},
{"armed monitor write got BRESP (SLVERR or DECERR)", "AXI id"},
};
static const char * const
gaudi2_pmmu_fatal_interrupts_cause[GAUDI2_NUM_OF_PMMU_FATAL_ERR_CAUSE] = {
"LATENCY_RD_OUT_FIFO_OVERRUN",
"LATENCY_WR_OUT_FIFO_OVERRUN",
};
static const char * const
gaudi2_hif_fatal_interrupts_cause[GAUDI2_NUM_OF_HIF_FATAL_ERR_CAUSE] = {
"LATENCY_RD_OUT_FIFO_OVERRUN",
"LATENCY_WR_OUT_FIFO_OVERRUN",
};
static const char * const
gaudi2_psoc_axi_drain_interrupts_cause[GAUDI2_NUM_OF_AXI_DRAIN_ERR_CAUSE] = {
"AXI drain HBW",
"AXI drain LBW",
};
static const char * const
gaudi2_pcie_addr_dec_error_cause[GAUDI2_NUM_OF_PCIE_ADDR_DEC_ERR_CAUSE] = {
"HBW error response",
"LBW error response",
"TLP is blocked by RR"
};
const u32 gaudi2_qm_blocks_bases[GAUDI2_QUEUE_ID_SIZE] = {
[GAUDI2_QUEUE_ID_PDMA_0_0] = mmPDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_PDMA_0_1] = mmPDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_PDMA_0_2] = mmPDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_PDMA_0_3] = mmPDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_PDMA_1_0] = mmPDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_PDMA_1_1] = mmPDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_PDMA_1_2] = mmPDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_PDMA_1_3] = mmPDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_0_0] = mmDCORE0_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_0_1] = mmDCORE0_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_0_2] = mmDCORE0_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_0_3] = mmDCORE0_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_1_0] = mmDCORE0_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_1_1] = mmDCORE0_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_1_2] = mmDCORE0_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_1_3] = mmDCORE0_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_MME_0_0] = mmDCORE0_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_MME_0_1] = mmDCORE0_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_MME_0_2] = mmDCORE0_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_MME_0_3] = mmDCORE0_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_0_0] = mmDCORE0_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_0_1] = mmDCORE0_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_0_2] = mmDCORE0_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_0_3] = mmDCORE0_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_1_0] = mmDCORE0_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_1_1] = mmDCORE0_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_1_2] = mmDCORE0_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_1_3] = mmDCORE0_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_2_0] = mmDCORE0_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_2_1] = mmDCORE0_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_2_2] = mmDCORE0_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_2_3] = mmDCORE0_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_3_0] = mmDCORE0_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_3_1] = mmDCORE0_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_3_2] = mmDCORE0_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_3_3] = mmDCORE0_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_4_0] = mmDCORE0_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_4_1] = mmDCORE0_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_4_2] = mmDCORE0_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_4_3] = mmDCORE0_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_5_0] = mmDCORE0_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_5_1] = mmDCORE0_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_5_2] = mmDCORE0_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_5_3] = mmDCORE0_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_6_0] = mmDCORE0_TPC6_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_6_1] = mmDCORE0_TPC6_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_6_2] = mmDCORE0_TPC6_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE0_TPC_6_3] = mmDCORE0_TPC6_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_0_0] = mmDCORE1_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_0_1] = mmDCORE1_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_0_2] = mmDCORE1_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_0_3] = mmDCORE1_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_1_0] = mmDCORE1_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_1_1] = mmDCORE1_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_1_2] = mmDCORE1_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_1_3] = mmDCORE1_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_MME_0_0] = mmDCORE1_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_MME_0_1] = mmDCORE1_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_MME_0_2] = mmDCORE1_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_MME_0_3] = mmDCORE1_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_0_0] = mmDCORE1_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_0_1] = mmDCORE1_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_0_2] = mmDCORE1_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_0_3] = mmDCORE1_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_1_0] = mmDCORE1_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_1_1] = mmDCORE1_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_1_2] = mmDCORE1_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_1_3] = mmDCORE1_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_2_0] = mmDCORE1_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_2_1] = mmDCORE1_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_2_2] = mmDCORE1_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_2_3] = mmDCORE1_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_3_0] = mmDCORE1_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_3_1] = mmDCORE1_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_3_2] = mmDCORE1_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_3_3] = mmDCORE1_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_4_0] = mmDCORE1_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_4_1] = mmDCORE1_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_4_2] = mmDCORE1_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_4_3] = mmDCORE1_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_5_0] = mmDCORE1_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_5_1] = mmDCORE1_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_5_2] = mmDCORE1_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE1_TPC_5_3] = mmDCORE1_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_0_0] = mmDCORE2_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_0_1] = mmDCORE2_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_0_2] = mmDCORE2_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_0_3] = mmDCORE2_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_1_0] = mmDCORE2_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_1_1] = mmDCORE2_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_1_2] = mmDCORE2_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_1_3] = mmDCORE2_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_MME_0_0] = mmDCORE2_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_MME_0_1] = mmDCORE2_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_MME_0_2] = mmDCORE2_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_MME_0_3] = mmDCORE2_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_0_0] = mmDCORE2_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_0_1] = mmDCORE2_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_0_2] = mmDCORE2_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_0_3] = mmDCORE2_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_1_0] = mmDCORE2_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_1_1] = mmDCORE2_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_1_2] = mmDCORE2_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_1_3] = mmDCORE2_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_2_0] = mmDCORE2_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_2_1] = mmDCORE2_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_2_2] = mmDCORE2_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_2_3] = mmDCORE2_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_3_0] = mmDCORE2_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_3_1] = mmDCORE2_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_3_2] = mmDCORE2_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_3_3] = mmDCORE2_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_4_0] = mmDCORE2_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_4_1] = mmDCORE2_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_4_2] = mmDCORE2_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_4_3] = mmDCORE2_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_5_0] = mmDCORE2_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_5_1] = mmDCORE2_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_5_2] = mmDCORE2_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE2_TPC_5_3] = mmDCORE2_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_0_0] = mmDCORE3_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_0_1] = mmDCORE3_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_0_2] = mmDCORE3_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_0_3] = mmDCORE3_EDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_0] = mmDCORE3_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_1] = mmDCORE3_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_2] = mmDCORE3_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_3] = mmDCORE3_EDMA1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_MME_0_0] = mmDCORE3_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_MME_0_1] = mmDCORE3_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_MME_0_2] = mmDCORE3_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_MME_0_3] = mmDCORE3_MME_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_0_0] = mmDCORE3_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_0_1] = mmDCORE3_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_0_2] = mmDCORE3_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_0_3] = mmDCORE3_TPC0_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_1_0] = mmDCORE3_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_1_1] = mmDCORE3_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_1_2] = mmDCORE3_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_1_3] = mmDCORE3_TPC1_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_2_0] = mmDCORE3_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_2_1] = mmDCORE3_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_2_2] = mmDCORE3_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_2_3] = mmDCORE3_TPC2_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_3_0] = mmDCORE3_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_3_1] = mmDCORE3_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_3_2] = mmDCORE3_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_3_3] = mmDCORE3_TPC3_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_4_0] = mmDCORE3_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_4_1] = mmDCORE3_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_4_2] = mmDCORE3_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_4_3] = mmDCORE3_TPC4_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_5_0] = mmDCORE3_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_5_1] = mmDCORE3_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_5_2] = mmDCORE3_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_DCORE3_TPC_5_3] = mmDCORE3_TPC5_QM_BASE,
[GAUDI2_QUEUE_ID_NIC_0_0] = mmNIC0_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_0_1] = mmNIC0_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_0_2] = mmNIC0_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_0_3] = mmNIC0_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_1_0] = mmNIC0_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_1_1] = mmNIC0_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_1_2] = mmNIC0_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_1_3] = mmNIC0_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_2_0] = mmNIC1_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_2_1] = mmNIC1_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_2_2] = mmNIC1_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_2_3] = mmNIC1_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_3_0] = mmNIC1_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_3_1] = mmNIC1_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_3_2] = mmNIC1_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_3_3] = mmNIC1_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_4_0] = mmNIC2_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_4_1] = mmNIC2_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_4_2] = mmNIC2_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_4_3] = mmNIC2_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_5_0] = mmNIC2_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_5_1] = mmNIC2_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_5_2] = mmNIC2_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_5_3] = mmNIC2_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_6_0] = mmNIC3_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_6_1] = mmNIC3_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_6_2] = mmNIC3_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_6_3] = mmNIC3_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_7_0] = mmNIC3_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_7_1] = mmNIC3_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_7_2] = mmNIC3_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_7_3] = mmNIC3_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_8_0] = mmNIC4_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_8_1] = mmNIC4_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_8_2] = mmNIC4_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_8_3] = mmNIC4_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_9_0] = mmNIC4_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_9_1] = mmNIC4_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_9_2] = mmNIC4_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_9_3] = mmNIC4_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_10_0] = mmNIC5_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_10_1] = mmNIC5_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_10_2] = mmNIC5_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_10_3] = mmNIC5_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_11_0] = mmNIC5_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_11_1] = mmNIC5_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_11_2] = mmNIC5_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_11_3] = mmNIC5_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_12_0] = mmNIC6_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_12_1] = mmNIC6_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_12_2] = mmNIC6_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_12_3] = mmNIC6_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_13_0] = mmNIC6_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_13_1] = mmNIC6_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_13_2] = mmNIC6_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_13_3] = mmNIC6_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_14_0] = mmNIC7_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_14_1] = mmNIC7_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_14_2] = mmNIC7_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_14_3] = mmNIC7_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_15_0] = mmNIC7_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_15_1] = mmNIC7_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_15_2] = mmNIC7_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_15_3] = mmNIC7_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_16_0] = mmNIC8_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_16_1] = mmNIC8_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_16_2] = mmNIC8_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_16_3] = mmNIC8_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_17_0] = mmNIC8_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_17_1] = mmNIC8_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_17_2] = mmNIC8_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_17_3] = mmNIC8_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_18_0] = mmNIC9_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_18_1] = mmNIC9_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_18_2] = mmNIC9_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_18_3] = mmNIC9_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_19_0] = mmNIC9_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_19_1] = mmNIC9_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_19_2] = mmNIC9_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_19_3] = mmNIC9_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_20_0] = mmNIC10_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_20_1] = mmNIC10_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_20_2] = mmNIC10_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_20_3] = mmNIC10_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_21_0] = mmNIC10_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_21_1] = mmNIC10_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_21_2] = mmNIC10_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_21_3] = mmNIC10_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_22_0] = mmNIC11_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_22_1] = mmNIC11_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_22_2] = mmNIC11_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_22_3] = mmNIC11_QM0_BASE,
[GAUDI2_QUEUE_ID_NIC_23_0] = mmNIC11_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_23_1] = mmNIC11_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_23_2] = mmNIC11_QM1_BASE,
[GAUDI2_QUEUE_ID_NIC_23_3] = mmNIC11_QM1_BASE,
[GAUDI2_QUEUE_ID_ROT_0_0] = mmROT0_QM_BASE,
[GAUDI2_QUEUE_ID_ROT_0_1] = mmROT0_QM_BASE,
[GAUDI2_QUEUE_ID_ROT_0_2] = mmROT0_QM_BASE,
[GAUDI2_QUEUE_ID_ROT_0_3] = mmROT0_QM_BASE,
[GAUDI2_QUEUE_ID_ROT_1_0] = mmROT1_QM_BASE,
[GAUDI2_QUEUE_ID_ROT_1_1] = mmROT1_QM_BASE,
[GAUDI2_QUEUE_ID_ROT_1_2] = mmROT1_QM_BASE,
[GAUDI2_QUEUE_ID_ROT_1_3] = mmROT1_QM_BASE
};
static const u32 gaudi2_arc_blocks_bases[NUM_ARC_CPUS] = {
[CPU_ID_SCHED_ARC0] = mmARC_FARM_ARC0_AUX_BASE,
[CPU_ID_SCHED_ARC1] = mmARC_FARM_ARC1_AUX_BASE,
[CPU_ID_SCHED_ARC2] = mmARC_FARM_ARC2_AUX_BASE,
[CPU_ID_SCHED_ARC3] = mmARC_FARM_ARC3_AUX_BASE,
[CPU_ID_SCHED_ARC4] = mmDCORE1_MME_QM_ARC_AUX_BASE,
[CPU_ID_SCHED_ARC5] = mmDCORE3_MME_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC0] = mmDCORE0_TPC0_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC1] = mmDCORE0_TPC1_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC2] = mmDCORE0_TPC2_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC3] = mmDCORE0_TPC3_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC4] = mmDCORE0_TPC4_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC5] = mmDCORE0_TPC5_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC6] = mmDCORE1_TPC0_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC7] = mmDCORE1_TPC1_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC8] = mmDCORE1_TPC2_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC9] = mmDCORE1_TPC3_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC10] = mmDCORE1_TPC4_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC11] = mmDCORE1_TPC5_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC12] = mmDCORE2_TPC0_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC13] = mmDCORE2_TPC1_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC14] = mmDCORE2_TPC2_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC15] = mmDCORE2_TPC3_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC16] = mmDCORE2_TPC4_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC17] = mmDCORE2_TPC5_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC18] = mmDCORE3_TPC0_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC19] = mmDCORE3_TPC1_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC20] = mmDCORE3_TPC2_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC21] = mmDCORE3_TPC3_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC22] = mmDCORE3_TPC4_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC23] = mmDCORE3_TPC5_QM_ARC_AUX_BASE,
[CPU_ID_TPC_QMAN_ARC24] = mmDCORE0_TPC6_QM_ARC_AUX_BASE,
[CPU_ID_MME_QMAN_ARC0] = mmDCORE0_MME_QM_ARC_AUX_BASE,
[CPU_ID_MME_QMAN_ARC1] = mmDCORE2_MME_QM_ARC_AUX_BASE,
[CPU_ID_EDMA_QMAN_ARC0] = mmDCORE0_EDMA0_QM_ARC_AUX_BASE,
[CPU_ID_EDMA_QMAN_ARC1] = mmDCORE0_EDMA1_QM_ARC_AUX_BASE,
[CPU_ID_EDMA_QMAN_ARC2] = mmDCORE1_EDMA0_QM_ARC_AUX_BASE,
[CPU_ID_EDMA_QMAN_ARC3] = mmDCORE1_EDMA1_QM_ARC_AUX_BASE,
[CPU_ID_EDMA_QMAN_ARC4] = mmDCORE2_EDMA0_QM_ARC_AUX_BASE,
[CPU_ID_EDMA_QMAN_ARC5] = mmDCORE2_EDMA1_QM_ARC_AUX_BASE,
[CPU_ID_EDMA_QMAN_ARC6] = mmDCORE3_EDMA0_QM_ARC_AUX_BASE,
[CPU_ID_EDMA_QMAN_ARC7] = mmDCORE3_EDMA1_QM_ARC_AUX_BASE,
[CPU_ID_PDMA_QMAN_ARC0] = mmPDMA0_QM_ARC_AUX_BASE,
[CPU_ID_PDMA_QMAN_ARC1] = mmPDMA1_QM_ARC_AUX_BASE,
[CPU_ID_ROT_QMAN_ARC0] = mmROT0_QM_ARC_AUX_BASE,
[CPU_ID_ROT_QMAN_ARC1] = mmROT1_QM_ARC_AUX_BASE,
[CPU_ID_NIC_QMAN_ARC0] = mmNIC0_QM_ARC_AUX0_BASE,
[CPU_ID_NIC_QMAN_ARC1] = mmNIC0_QM_ARC_AUX1_BASE,
[CPU_ID_NIC_QMAN_ARC2] = mmNIC1_QM_ARC_AUX0_BASE,
[CPU_ID_NIC_QMAN_ARC3] = mmNIC1_QM_ARC_AUX1_BASE,
[CPU_ID_NIC_QMAN_ARC4] = mmNIC2_QM_ARC_AUX0_BASE,
[CPU_ID_NIC_QMAN_ARC5] = mmNIC2_QM_ARC_AUX1_BASE,
[CPU_ID_NIC_QMAN_ARC6] = mmNIC3_QM_ARC_AUX0_BASE,
[CPU_ID_NIC_QMAN_ARC7] = mmNIC3_QM_ARC_AUX1_BASE,
[CPU_ID_NIC_QMAN_ARC8] = mmNIC4_QM_ARC_AUX0_BASE,
[CPU_ID_NIC_QMAN_ARC9] = mmNIC4_QM_ARC_AUX1_BASE,
[CPU_ID_NIC_QMAN_ARC10] = mmNIC5_QM_ARC_AUX0_BASE,
[CPU_ID_NIC_QMAN_ARC11] = mmNIC5_QM_ARC_AUX1_BASE,
[CPU_ID_NIC_QMAN_ARC12] = mmNIC6_QM_ARC_AUX0_BASE,
[CPU_ID_NIC_QMAN_ARC13] = mmNIC6_QM_ARC_AUX1_BASE,
[CPU_ID_NIC_QMAN_ARC14] = mmNIC7_QM_ARC_AUX0_BASE,
[CPU_ID_NIC_QMAN_ARC15] = mmNIC7_QM_ARC_AUX1_BASE,
[CPU_ID_NIC_QMAN_ARC16] = mmNIC8_QM_ARC_AUX0_BASE,
[CPU_ID_NIC_QMAN_ARC17] = mmNIC8_QM_ARC_AUX1_BASE,
[CPU_ID_NIC_QMAN_ARC18] = mmNIC9_QM_ARC_AUX0_BASE,
[CPU_ID_NIC_QMAN_ARC19] = mmNIC9_QM_ARC_AUX1_BASE,
[CPU_ID_NIC_QMAN_ARC20] = mmNIC10_QM_ARC_AUX0_BASE,
[CPU_ID_NIC_QMAN_ARC21] = mmNIC10_QM_ARC_AUX1_BASE,
[CPU_ID_NIC_QMAN_ARC22] = mmNIC11_QM_ARC_AUX0_BASE,
[CPU_ID_NIC_QMAN_ARC23] = mmNIC11_QM_ARC_AUX1_BASE,
};
static const u32 gaudi2_arc_dccm_bases[NUM_ARC_CPUS] = {
[CPU_ID_SCHED_ARC0] = mmARC_FARM_ARC0_DCCM0_BASE,
[CPU_ID_SCHED_ARC1] = mmARC_FARM_ARC1_DCCM0_BASE,
[CPU_ID_SCHED_ARC2] = mmARC_FARM_ARC2_DCCM0_BASE,
[CPU_ID_SCHED_ARC3] = mmARC_FARM_ARC3_DCCM0_BASE,
[CPU_ID_SCHED_ARC4] = mmDCORE1_MME_QM_ARC_DCCM_BASE,
[CPU_ID_SCHED_ARC5] = mmDCORE3_MME_QM_ARC_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC0] = mmDCORE0_TPC0_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC1] = mmDCORE0_TPC1_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC2] = mmDCORE0_TPC2_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC3] = mmDCORE0_TPC3_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC4] = mmDCORE0_TPC4_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC5] = mmDCORE0_TPC5_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC6] = mmDCORE1_TPC0_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC7] = mmDCORE1_TPC1_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC8] = mmDCORE1_TPC2_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC9] = mmDCORE1_TPC3_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC10] = mmDCORE1_TPC4_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC11] = mmDCORE1_TPC5_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC12] = mmDCORE2_TPC0_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC13] = mmDCORE2_TPC1_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC14] = mmDCORE2_TPC2_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC15] = mmDCORE2_TPC3_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC16] = mmDCORE2_TPC4_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC17] = mmDCORE2_TPC5_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC18] = mmDCORE3_TPC0_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC19] = mmDCORE3_TPC1_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC20] = mmDCORE3_TPC2_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC21] = mmDCORE3_TPC3_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC22] = mmDCORE3_TPC4_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC23] = mmDCORE3_TPC5_QM_DCCM_BASE,
[CPU_ID_TPC_QMAN_ARC24] = mmDCORE0_TPC6_QM_DCCM_BASE,
[CPU_ID_MME_QMAN_ARC0] = mmDCORE0_MME_QM_ARC_DCCM_BASE,
[CPU_ID_MME_QMAN_ARC1] = mmDCORE2_MME_QM_ARC_DCCM_BASE,
[CPU_ID_EDMA_QMAN_ARC0] = mmDCORE0_EDMA0_QM_DCCM_BASE,
[CPU_ID_EDMA_QMAN_ARC1] = mmDCORE0_EDMA1_QM_DCCM_BASE,
[CPU_ID_EDMA_QMAN_ARC2] = mmDCORE1_EDMA0_QM_DCCM_BASE,
[CPU_ID_EDMA_QMAN_ARC3] = mmDCORE1_EDMA1_QM_DCCM_BASE,
[CPU_ID_EDMA_QMAN_ARC4] = mmDCORE2_EDMA0_QM_DCCM_BASE,
[CPU_ID_EDMA_QMAN_ARC5] = mmDCORE2_EDMA1_QM_DCCM_BASE,
[CPU_ID_EDMA_QMAN_ARC6] = mmDCORE3_EDMA0_QM_DCCM_BASE,
[CPU_ID_EDMA_QMAN_ARC7] = mmDCORE3_EDMA1_QM_DCCM_BASE,
[CPU_ID_PDMA_QMAN_ARC0] = mmPDMA0_QM_ARC_DCCM_BASE,
[CPU_ID_PDMA_QMAN_ARC1] = mmPDMA1_QM_ARC_DCCM_BASE,
[CPU_ID_ROT_QMAN_ARC0] = mmROT0_QM_ARC_DCCM_BASE,
[CPU_ID_ROT_QMAN_ARC1] = mmROT1_QM_ARC_DCCM_BASE,
[CPU_ID_NIC_QMAN_ARC0] = mmNIC0_QM_DCCM0_BASE,
[CPU_ID_NIC_QMAN_ARC1] = mmNIC0_QM_DCCM1_BASE,
[CPU_ID_NIC_QMAN_ARC2] = mmNIC1_QM_DCCM0_BASE,
[CPU_ID_NIC_QMAN_ARC3] = mmNIC1_QM_DCCM1_BASE,
[CPU_ID_NIC_QMAN_ARC4] = mmNIC2_QM_DCCM0_BASE,
[CPU_ID_NIC_QMAN_ARC5] = mmNIC2_QM_DCCM1_BASE,
[CPU_ID_NIC_QMAN_ARC6] = mmNIC3_QM_DCCM0_BASE,
[CPU_ID_NIC_QMAN_ARC7] = mmNIC3_QM_DCCM1_BASE,
[CPU_ID_NIC_QMAN_ARC8] = mmNIC4_QM_DCCM0_BASE,
[CPU_ID_NIC_QMAN_ARC9] = mmNIC4_QM_DCCM1_BASE,
[CPU_ID_NIC_QMAN_ARC10] = mmNIC5_QM_DCCM0_BASE,
[CPU_ID_NIC_QMAN_ARC11] = mmNIC5_QM_DCCM1_BASE,
[CPU_ID_NIC_QMAN_ARC12] = mmNIC6_QM_DCCM0_BASE,
[CPU_ID_NIC_QMAN_ARC13] = mmNIC6_QM_DCCM1_BASE,
[CPU_ID_NIC_QMAN_ARC14] = mmNIC7_QM_DCCM0_BASE,
[CPU_ID_NIC_QMAN_ARC15] = mmNIC7_QM_DCCM1_BASE,
[CPU_ID_NIC_QMAN_ARC16] = mmNIC8_QM_DCCM0_BASE,
[CPU_ID_NIC_QMAN_ARC17] = mmNIC8_QM_DCCM1_BASE,
[CPU_ID_NIC_QMAN_ARC18] = mmNIC9_QM_DCCM0_BASE,
[CPU_ID_NIC_QMAN_ARC19] = mmNIC9_QM_DCCM1_BASE,
[CPU_ID_NIC_QMAN_ARC20] = mmNIC10_QM_DCCM0_BASE,
[CPU_ID_NIC_QMAN_ARC21] = mmNIC10_QM_DCCM1_BASE,
[CPU_ID_NIC_QMAN_ARC22] = mmNIC11_QM_DCCM0_BASE,
[CPU_ID_NIC_QMAN_ARC23] = mmNIC11_QM_DCCM1_BASE,
};
const u32 gaudi2_mme_ctrl_lo_blocks_bases[MME_ID_SIZE] = {
[MME_ID_DCORE0] = mmDCORE0_MME_CTRL_LO_BASE,
[MME_ID_DCORE1] = mmDCORE1_MME_CTRL_LO_BASE,
[MME_ID_DCORE2] = mmDCORE2_MME_CTRL_LO_BASE,
[MME_ID_DCORE3] = mmDCORE3_MME_CTRL_LO_BASE,
};
static const u32 gaudi2_queue_id_to_arc_id[GAUDI2_QUEUE_ID_SIZE] = {
[GAUDI2_QUEUE_ID_PDMA_0_0] = CPU_ID_PDMA_QMAN_ARC0,
[GAUDI2_QUEUE_ID_PDMA_0_1] = CPU_ID_PDMA_QMAN_ARC0,
[GAUDI2_QUEUE_ID_PDMA_0_2] = CPU_ID_PDMA_QMAN_ARC0,
[GAUDI2_QUEUE_ID_PDMA_0_3] = CPU_ID_PDMA_QMAN_ARC0,
[GAUDI2_QUEUE_ID_PDMA_1_0] = CPU_ID_PDMA_QMAN_ARC1,
[GAUDI2_QUEUE_ID_PDMA_1_1] = CPU_ID_PDMA_QMAN_ARC1,
[GAUDI2_QUEUE_ID_PDMA_1_2] = CPU_ID_PDMA_QMAN_ARC1,
[GAUDI2_QUEUE_ID_PDMA_1_3] = CPU_ID_PDMA_QMAN_ARC1,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_0_0] = CPU_ID_EDMA_QMAN_ARC0,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_0_1] = CPU_ID_EDMA_QMAN_ARC0,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_0_2] = CPU_ID_EDMA_QMAN_ARC0,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_0_3] = CPU_ID_EDMA_QMAN_ARC0,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_1_0] = CPU_ID_EDMA_QMAN_ARC1,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_1_1] = CPU_ID_EDMA_QMAN_ARC1,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_1_2] = CPU_ID_EDMA_QMAN_ARC1,
[GAUDI2_QUEUE_ID_DCORE0_EDMA_1_3] = CPU_ID_EDMA_QMAN_ARC1,
[GAUDI2_QUEUE_ID_DCORE0_MME_0_0] = CPU_ID_MME_QMAN_ARC0,
[GAUDI2_QUEUE_ID_DCORE0_MME_0_1] = CPU_ID_MME_QMAN_ARC0,
[GAUDI2_QUEUE_ID_DCORE0_MME_0_2] = CPU_ID_MME_QMAN_ARC0,
[GAUDI2_QUEUE_ID_DCORE0_MME_0_3] = CPU_ID_MME_QMAN_ARC0,
[GAUDI2_QUEUE_ID_DCORE0_TPC_0_0] = CPU_ID_TPC_QMAN_ARC0,
[GAUDI2_QUEUE_ID_DCORE0_TPC_0_1] = CPU_ID_TPC_QMAN_ARC0,
[GAUDI2_QUEUE_ID_DCORE0_TPC_0_2] = CPU_ID_TPC_QMAN_ARC0,
[GAUDI2_QUEUE_ID_DCORE0_TPC_0_3] = CPU_ID_TPC_QMAN_ARC0,
[GAUDI2_QUEUE_ID_DCORE0_TPC_1_0] = CPU_ID_TPC_QMAN_ARC1,
[GAUDI2_QUEUE_ID_DCORE0_TPC_1_1] = CPU_ID_TPC_QMAN_ARC1,
[GAUDI2_QUEUE_ID_DCORE0_TPC_1_2] = CPU_ID_TPC_QMAN_ARC1,
[GAUDI2_QUEUE_ID_DCORE0_TPC_1_3] = CPU_ID_TPC_QMAN_ARC1,
[GAUDI2_QUEUE_ID_DCORE0_TPC_2_0] = CPU_ID_TPC_QMAN_ARC2,
[GAUDI2_QUEUE_ID_DCORE0_TPC_2_1] = CPU_ID_TPC_QMAN_ARC2,
[GAUDI2_QUEUE_ID_DCORE0_TPC_2_2] = CPU_ID_TPC_QMAN_ARC2,
[GAUDI2_QUEUE_ID_DCORE0_TPC_2_3] = CPU_ID_TPC_QMAN_ARC2,
[GAUDI2_QUEUE_ID_DCORE0_TPC_3_0] = CPU_ID_TPC_QMAN_ARC3,
[GAUDI2_QUEUE_ID_DCORE0_TPC_3_1] = CPU_ID_TPC_QMAN_ARC3,
[GAUDI2_QUEUE_ID_DCORE0_TPC_3_2] = CPU_ID_TPC_QMAN_ARC3,
[GAUDI2_QUEUE_ID_DCORE0_TPC_3_3] = CPU_ID_TPC_QMAN_ARC3,
[GAUDI2_QUEUE_ID_DCORE0_TPC_4_0] = CPU_ID_TPC_QMAN_ARC4,
[GAUDI2_QUEUE_ID_DCORE0_TPC_4_1] = CPU_ID_TPC_QMAN_ARC4,
[GAUDI2_QUEUE_ID_DCORE0_TPC_4_2] = CPU_ID_TPC_QMAN_ARC4,
[GAUDI2_QUEUE_ID_DCORE0_TPC_4_3] = CPU_ID_TPC_QMAN_ARC4,
[GAUDI2_QUEUE_ID_DCORE0_TPC_5_0] = CPU_ID_TPC_QMAN_ARC5,
[GAUDI2_QUEUE_ID_DCORE0_TPC_5_1] = CPU_ID_TPC_QMAN_ARC5,
[GAUDI2_QUEUE_ID_DCORE0_TPC_5_2] = CPU_ID_TPC_QMAN_ARC5,
[GAUDI2_QUEUE_ID_DCORE0_TPC_5_3] = CPU_ID_TPC_QMAN_ARC5,
[GAUDI2_QUEUE_ID_DCORE0_TPC_6_0] = CPU_ID_TPC_QMAN_ARC24,
[GAUDI2_QUEUE_ID_DCORE0_TPC_6_1] = CPU_ID_TPC_QMAN_ARC24,
[GAUDI2_QUEUE_ID_DCORE0_TPC_6_2] = CPU_ID_TPC_QMAN_ARC24,
[GAUDI2_QUEUE_ID_DCORE0_TPC_6_3] = CPU_ID_TPC_QMAN_ARC24,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_0_0] = CPU_ID_EDMA_QMAN_ARC2,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_0_1] = CPU_ID_EDMA_QMAN_ARC2,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_0_2] = CPU_ID_EDMA_QMAN_ARC2,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_0_3] = CPU_ID_EDMA_QMAN_ARC2,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_1_0] = CPU_ID_EDMA_QMAN_ARC3,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_1_1] = CPU_ID_EDMA_QMAN_ARC3,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_1_2] = CPU_ID_EDMA_QMAN_ARC3,
[GAUDI2_QUEUE_ID_DCORE1_EDMA_1_3] = CPU_ID_EDMA_QMAN_ARC3,
[GAUDI2_QUEUE_ID_DCORE1_MME_0_0] = CPU_ID_SCHED_ARC4,
[GAUDI2_QUEUE_ID_DCORE1_MME_0_1] = CPU_ID_SCHED_ARC4,
[GAUDI2_QUEUE_ID_DCORE1_MME_0_2] = CPU_ID_SCHED_ARC4,
[GAUDI2_QUEUE_ID_DCORE1_MME_0_3] = CPU_ID_SCHED_ARC4,
[GAUDI2_QUEUE_ID_DCORE1_TPC_0_0] = CPU_ID_TPC_QMAN_ARC6,
[GAUDI2_QUEUE_ID_DCORE1_TPC_0_1] = CPU_ID_TPC_QMAN_ARC6,
[GAUDI2_QUEUE_ID_DCORE1_TPC_0_2] = CPU_ID_TPC_QMAN_ARC6,
[GAUDI2_QUEUE_ID_DCORE1_TPC_0_3] = CPU_ID_TPC_QMAN_ARC6,
[GAUDI2_QUEUE_ID_DCORE1_TPC_1_0] = CPU_ID_TPC_QMAN_ARC7,
[GAUDI2_QUEUE_ID_DCORE1_TPC_1_1] = CPU_ID_TPC_QMAN_ARC7,
[GAUDI2_QUEUE_ID_DCORE1_TPC_1_2] = CPU_ID_TPC_QMAN_ARC7,
[GAUDI2_QUEUE_ID_DCORE1_TPC_1_3] = CPU_ID_TPC_QMAN_ARC7,
[GAUDI2_QUEUE_ID_DCORE1_TPC_2_0] = CPU_ID_TPC_QMAN_ARC8,
[GAUDI2_QUEUE_ID_DCORE1_TPC_2_1] = CPU_ID_TPC_QMAN_ARC8,
[GAUDI2_QUEUE_ID_DCORE1_TPC_2_2] = CPU_ID_TPC_QMAN_ARC8,
[GAUDI2_QUEUE_ID_DCORE1_TPC_2_3] = CPU_ID_TPC_QMAN_ARC8,
[GAUDI2_QUEUE_ID_DCORE1_TPC_3_0] = CPU_ID_TPC_QMAN_ARC9,
[GAUDI2_QUEUE_ID_DCORE1_TPC_3_1] = CPU_ID_TPC_QMAN_ARC9,
[GAUDI2_QUEUE_ID_DCORE1_TPC_3_2] = CPU_ID_TPC_QMAN_ARC9,
[GAUDI2_QUEUE_ID_DCORE1_TPC_3_3] = CPU_ID_TPC_QMAN_ARC9,
[GAUDI2_QUEUE_ID_DCORE1_TPC_4_0] = CPU_ID_TPC_QMAN_ARC10,
[GAUDI2_QUEUE_ID_DCORE1_TPC_4_1] = CPU_ID_TPC_QMAN_ARC10,
[GAUDI2_QUEUE_ID_DCORE1_TPC_4_2] = CPU_ID_TPC_QMAN_ARC10,
[GAUDI2_QUEUE_ID_DCORE1_TPC_4_3] = CPU_ID_TPC_QMAN_ARC10,
[GAUDI2_QUEUE_ID_DCORE1_TPC_5_0] = CPU_ID_TPC_QMAN_ARC11,
[GAUDI2_QUEUE_ID_DCORE1_TPC_5_1] = CPU_ID_TPC_QMAN_ARC11,
[GAUDI2_QUEUE_ID_DCORE1_TPC_5_2] = CPU_ID_TPC_QMAN_ARC11,
[GAUDI2_QUEUE_ID_DCORE1_TPC_5_3] = CPU_ID_TPC_QMAN_ARC11,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_0_0] = CPU_ID_EDMA_QMAN_ARC4,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_0_1] = CPU_ID_EDMA_QMAN_ARC4,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_0_2] = CPU_ID_EDMA_QMAN_ARC4,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_0_3] = CPU_ID_EDMA_QMAN_ARC4,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_1_0] = CPU_ID_EDMA_QMAN_ARC5,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_1_1] = CPU_ID_EDMA_QMAN_ARC5,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_1_2] = CPU_ID_EDMA_QMAN_ARC5,
[GAUDI2_QUEUE_ID_DCORE2_EDMA_1_3] = CPU_ID_EDMA_QMAN_ARC5,
[GAUDI2_QUEUE_ID_DCORE2_MME_0_0] = CPU_ID_MME_QMAN_ARC1,
[GAUDI2_QUEUE_ID_DCORE2_MME_0_1] = CPU_ID_MME_QMAN_ARC1,
[GAUDI2_QUEUE_ID_DCORE2_MME_0_2] = CPU_ID_MME_QMAN_ARC1,
[GAUDI2_QUEUE_ID_DCORE2_MME_0_3] = CPU_ID_MME_QMAN_ARC1,
[GAUDI2_QUEUE_ID_DCORE2_TPC_0_0] = CPU_ID_TPC_QMAN_ARC12,
[GAUDI2_QUEUE_ID_DCORE2_TPC_0_1] = CPU_ID_TPC_QMAN_ARC12,
[GAUDI2_QUEUE_ID_DCORE2_TPC_0_2] = CPU_ID_TPC_QMAN_ARC12,
[GAUDI2_QUEUE_ID_DCORE2_TPC_0_3] = CPU_ID_TPC_QMAN_ARC12,
[GAUDI2_QUEUE_ID_DCORE2_TPC_1_0] = CPU_ID_TPC_QMAN_ARC13,
[GAUDI2_QUEUE_ID_DCORE2_TPC_1_1] = CPU_ID_TPC_QMAN_ARC13,
[GAUDI2_QUEUE_ID_DCORE2_TPC_1_2] = CPU_ID_TPC_QMAN_ARC13,
[GAUDI2_QUEUE_ID_DCORE2_TPC_1_3] = CPU_ID_TPC_QMAN_ARC13,
[GAUDI2_QUEUE_ID_DCORE2_TPC_2_0] = CPU_ID_TPC_QMAN_ARC14,
[GAUDI2_QUEUE_ID_DCORE2_TPC_2_1] = CPU_ID_TPC_QMAN_ARC14,
[GAUDI2_QUEUE_ID_DCORE2_TPC_2_2] = CPU_ID_TPC_QMAN_ARC14,
[GAUDI2_QUEUE_ID_DCORE2_TPC_2_3] = CPU_ID_TPC_QMAN_ARC14,
[GAUDI2_QUEUE_ID_DCORE2_TPC_3_0] = CPU_ID_TPC_QMAN_ARC15,
[GAUDI2_QUEUE_ID_DCORE2_TPC_3_1] = CPU_ID_TPC_QMAN_ARC15,
[GAUDI2_QUEUE_ID_DCORE2_TPC_3_2] = CPU_ID_TPC_QMAN_ARC15,
[GAUDI2_QUEUE_ID_DCORE2_TPC_3_3] = CPU_ID_TPC_QMAN_ARC15,
[GAUDI2_QUEUE_ID_DCORE2_TPC_4_0] = CPU_ID_TPC_QMAN_ARC16,
[GAUDI2_QUEUE_ID_DCORE2_TPC_4_1] = CPU_ID_TPC_QMAN_ARC16,
[GAUDI2_QUEUE_ID_DCORE2_TPC_4_2] = CPU_ID_TPC_QMAN_ARC16,
[GAUDI2_QUEUE_ID_DCORE2_TPC_4_3] = CPU_ID_TPC_QMAN_ARC16,
[GAUDI2_QUEUE_ID_DCORE2_TPC_5_0] = CPU_ID_TPC_QMAN_ARC17,
[GAUDI2_QUEUE_ID_DCORE2_TPC_5_1] = CPU_ID_TPC_QMAN_ARC17,
[GAUDI2_QUEUE_ID_DCORE2_TPC_5_2] = CPU_ID_TPC_QMAN_ARC17,
[GAUDI2_QUEUE_ID_DCORE2_TPC_5_3] = CPU_ID_TPC_QMAN_ARC17,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_0_0] = CPU_ID_EDMA_QMAN_ARC6,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_0_1] = CPU_ID_EDMA_QMAN_ARC6,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_0_2] = CPU_ID_EDMA_QMAN_ARC6,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_0_3] = CPU_ID_EDMA_QMAN_ARC6,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_0] = CPU_ID_EDMA_QMAN_ARC7,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_1] = CPU_ID_EDMA_QMAN_ARC7,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_2] = CPU_ID_EDMA_QMAN_ARC7,
[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_3] = CPU_ID_EDMA_QMAN_ARC7,
[GAUDI2_QUEUE_ID_DCORE3_MME_0_0] = CPU_ID_SCHED_ARC5,
[GAUDI2_QUEUE_ID_DCORE3_MME_0_1] = CPU_ID_SCHED_ARC5,
[GAUDI2_QUEUE_ID_DCORE3_MME_0_2] = CPU_ID_SCHED_ARC5,
[GAUDI2_QUEUE_ID_DCORE3_MME_0_3] = CPU_ID_SCHED_ARC5,
[GAUDI2_QUEUE_ID_DCORE3_TPC_0_0] = CPU_ID_TPC_QMAN_ARC18,
[GAUDI2_QUEUE_ID_DCORE3_TPC_0_1] = CPU_ID_TPC_QMAN_ARC18,
[GAUDI2_QUEUE_ID_DCORE3_TPC_0_2] = CPU_ID_TPC_QMAN_ARC18,
[GAUDI2_QUEUE_ID_DCORE3_TPC_0_3] = CPU_ID_TPC_QMAN_ARC18,
[GAUDI2_QUEUE_ID_DCORE3_TPC_1_0] = CPU_ID_TPC_QMAN_ARC19,
[GAUDI2_QUEUE_ID_DCORE3_TPC_1_1] = CPU_ID_TPC_QMAN_ARC19,
[GAUDI2_QUEUE_ID_DCORE3_TPC_1_2] = CPU_ID_TPC_QMAN_ARC19,
[GAUDI2_QUEUE_ID_DCORE3_TPC_1_3] = CPU_ID_TPC_QMAN_ARC19,
[GAUDI2_QUEUE_ID_DCORE3_TPC_2_0] = CPU_ID_TPC_QMAN_ARC20,
[GAUDI2_QUEUE_ID_DCORE3_TPC_2_1] = CPU_ID_TPC_QMAN_ARC20,
[GAUDI2_QUEUE_ID_DCORE3_TPC_2_2] = CPU_ID_TPC_QMAN_ARC20,
[GAUDI2_QUEUE_ID_DCORE3_TPC_2_3] = CPU_ID_TPC_QMAN_ARC20,
[GAUDI2_QUEUE_ID_DCORE3_TPC_3_0] = CPU_ID_TPC_QMAN_ARC21,
[GAUDI2_QUEUE_ID_DCORE3_TPC_3_1] = CPU_ID_TPC_QMAN_ARC21,
[GAUDI2_QUEUE_ID_DCORE3_TPC_3_2] = CPU_ID_TPC_QMAN_ARC21,
[GAUDI2_QUEUE_ID_DCORE3_TPC_3_3] = CPU_ID_TPC_QMAN_ARC21,
[GAUDI2_QUEUE_ID_DCORE3_TPC_4_0] = CPU_ID_TPC_QMAN_ARC22,
[GAUDI2_QUEUE_ID_DCORE3_TPC_4_1] = CPU_ID_TPC_QMAN_ARC22,
[GAUDI2_QUEUE_ID_DCORE3_TPC_4_2] = CPU_ID_TPC_QMAN_ARC22,
[GAUDI2_QUEUE_ID_DCORE3_TPC_4_3] = CPU_ID_TPC_QMAN_ARC22,
[GAUDI2_QUEUE_ID_DCORE3_TPC_5_0] = CPU_ID_TPC_QMAN_ARC23,
[GAUDI2_QUEUE_ID_DCORE3_TPC_5_1] = CPU_ID_TPC_QMAN_ARC23,
[GAUDI2_QUEUE_ID_DCORE3_TPC_5_2] = CPU_ID_TPC_QMAN_ARC23,
[GAUDI2_QUEUE_ID_DCORE3_TPC_5_3] = CPU_ID_TPC_QMAN_ARC23,
[GAUDI2_QUEUE_ID_NIC_0_0] = CPU_ID_NIC_QMAN_ARC0,
[GAUDI2_QUEUE_ID_NIC_0_1] = CPU_ID_NIC_QMAN_ARC0,
[GAUDI2_QUEUE_ID_NIC_0_2] = CPU_ID_NIC_QMAN_ARC0,
[GAUDI2_QUEUE_ID_NIC_0_3] = CPU_ID_NIC_QMAN_ARC0,
[GAUDI2_QUEUE_ID_NIC_1_0] = CPU_ID_NIC_QMAN_ARC1,
[GAUDI2_QUEUE_ID_NIC_1_1] = CPU_ID_NIC_QMAN_ARC1,
[GAUDI2_QUEUE_ID_NIC_1_2] = CPU_ID_NIC_QMAN_ARC1,
[GAUDI2_QUEUE_ID_NIC_1_3] = CPU_ID_NIC_QMAN_ARC1,
[GAUDI2_QUEUE_ID_NIC_2_0] = CPU_ID_NIC_QMAN_ARC2,
[GAUDI2_QUEUE_ID_NIC_2_1] = CPU_ID_NIC_QMAN_ARC2,
[GAUDI2_QUEUE_ID_NIC_2_2] = CPU_ID_NIC_QMAN_ARC2,
[GAUDI2_QUEUE_ID_NIC_2_3] = CPU_ID_NIC_QMAN_ARC2,
[GAUDI2_QUEUE_ID_NIC_3_0] = CPU_ID_NIC_QMAN_ARC3,
[GAUDI2_QUEUE_ID_NIC_3_1] = CPU_ID_NIC_QMAN_ARC3,
[GAUDI2_QUEUE_ID_NIC_3_2] = CPU_ID_NIC_QMAN_ARC3,
[GAUDI2_QUEUE_ID_NIC_3_3] = CPU_ID_NIC_QMAN_ARC3,
[GAUDI2_QUEUE_ID_NIC_4_0] = CPU_ID_NIC_QMAN_ARC4,
[GAUDI2_QUEUE_ID_NIC_4_1] = CPU_ID_NIC_QMAN_ARC4,
[GAUDI2_QUEUE_ID_NIC_4_2] = CPU_ID_NIC_QMAN_ARC4,
[GAUDI2_QUEUE_ID_NIC_4_3] = CPU_ID_NIC_QMAN_ARC4,
[GAUDI2_QUEUE_ID_NIC_5_0] = CPU_ID_NIC_QMAN_ARC5,
[GAUDI2_QUEUE_ID_NIC_5_1] = CPU_ID_NIC_QMAN_ARC5,
[GAUDI2_QUEUE_ID_NIC_5_2] = CPU_ID_NIC_QMAN_ARC5,
[GAUDI2_QUEUE_ID_NIC_5_3] = CPU_ID_NIC_QMAN_ARC5,
[GAUDI2_QUEUE_ID_NIC_6_0] = CPU_ID_NIC_QMAN_ARC6,
[GAUDI2_QUEUE_ID_NIC_6_1] = CPU_ID_NIC_QMAN_ARC6,
[GAUDI2_QUEUE_ID_NIC_6_2] = CPU_ID_NIC_QMAN_ARC6,
[GAUDI2_QUEUE_ID_NIC_6_3] = CPU_ID_NIC_QMAN_ARC6,
[GAUDI2_QUEUE_ID_NIC_7_0] = CPU_ID_NIC_QMAN_ARC7,
[GAUDI2_QUEUE_ID_NIC_7_1] = CPU_ID_NIC_QMAN_ARC7,
[GAUDI2_QUEUE_ID_NIC_7_2] = CPU_ID_NIC_QMAN_ARC7,
[GAUDI2_QUEUE_ID_NIC_7_3] = CPU_ID_NIC_QMAN_ARC7,
[GAUDI2_QUEUE_ID_NIC_8_0] = CPU_ID_NIC_QMAN_ARC8,
[GAUDI2_QUEUE_ID_NIC_8_1] = CPU_ID_NIC_QMAN_ARC8,
[GAUDI2_QUEUE_ID_NIC_8_2] = CPU_ID_NIC_QMAN_ARC8,
[GAUDI2_QUEUE_ID_NIC_8_3] = CPU_ID_NIC_QMAN_ARC8,
[GAUDI2_QUEUE_ID_NIC_9_0] = CPU_ID_NIC_QMAN_ARC9,
[GAUDI2_QUEUE_ID_NIC_9_1] = CPU_ID_NIC_QMAN_ARC9,
[GAUDI2_QUEUE_ID_NIC_9_2] = CPU_ID_NIC_QMAN_ARC9,
[GAUDI2_QUEUE_ID_NIC_9_3] = CPU_ID_NIC_QMAN_ARC9,
[GAUDI2_QUEUE_ID_NIC_10_0] = CPU_ID_NIC_QMAN_ARC10,
[GAUDI2_QUEUE_ID_NIC_10_1] = CPU_ID_NIC_QMAN_ARC10,
[GAUDI2_QUEUE_ID_NIC_10_2] = CPU_ID_NIC_QMAN_ARC10,
[GAUDI2_QUEUE_ID_NIC_10_3] = CPU_ID_NIC_QMAN_ARC10,
[GAUDI2_QUEUE_ID_NIC_11_0] = CPU_ID_NIC_QMAN_ARC11,
[GAUDI2_QUEUE_ID_NIC_11_1] = CPU_ID_NIC_QMAN_ARC11,
[GAUDI2_QUEUE_ID_NIC_11_2] = CPU_ID_NIC_QMAN_ARC11,
[GAUDI2_QUEUE_ID_NIC_11_3] = CPU_ID_NIC_QMAN_ARC11,
[GAUDI2_QUEUE_ID_NIC_12_0] = CPU_ID_NIC_QMAN_ARC12,
[GAUDI2_QUEUE_ID_NIC_12_1] = CPU_ID_NIC_QMAN_ARC12,
[GAUDI2_QUEUE_ID_NIC_12_2] = CPU_ID_NIC_QMAN_ARC12,
[GAUDI2_QUEUE_ID_NIC_12_3] = CPU_ID_NIC_QMAN_ARC12,
[GAUDI2_QUEUE_ID_NIC_13_0] = CPU_ID_NIC_QMAN_ARC13,
[GAUDI2_QUEUE_ID_NIC_13_1] = CPU_ID_NIC_QMAN_ARC13,
[GAUDI2_QUEUE_ID_NIC_13_2] = CPU_ID_NIC_QMAN_ARC13,
[GAUDI2_QUEUE_ID_NIC_13_3] = CPU_ID_NIC_QMAN_ARC13,
[GAUDI2_QUEUE_ID_NIC_14_0] = CPU_ID_NIC_QMAN_ARC14,
[GAUDI2_QUEUE_ID_NIC_14_1] = CPU_ID_NIC_QMAN_ARC14,
[GAUDI2_QUEUE_ID_NIC_14_2] = CPU_ID_NIC_QMAN_ARC14,
[GAUDI2_QUEUE_ID_NIC_14_3] = CPU_ID_NIC_QMAN_ARC14,
[GAUDI2_QUEUE_ID_NIC_15_0] = CPU_ID_NIC_QMAN_ARC15,
[GAUDI2_QUEUE_ID_NIC_15_1] = CPU_ID_NIC_QMAN_ARC15,
[GAUDI2_QUEUE_ID_NIC_15_2] = CPU_ID_NIC_QMAN_ARC15,
[GAUDI2_QUEUE_ID_NIC_15_3] = CPU_ID_NIC_QMAN_ARC15,
[GAUDI2_QUEUE_ID_NIC_16_0] = CPU_ID_NIC_QMAN_ARC16,
[GAUDI2_QUEUE_ID_NIC_16_1] = CPU_ID_NIC_QMAN_ARC16,
[GAUDI2_QUEUE_ID_NIC_16_2] = CPU_ID_NIC_QMAN_ARC16,
[GAUDI2_QUEUE_ID_NIC_16_3] = CPU_ID_NIC_QMAN_ARC16,
[GAUDI2_QUEUE_ID_NIC_17_0] = CPU_ID_NIC_QMAN_ARC17,
[GAUDI2_QUEUE_ID_NIC_17_1] = CPU_ID_NIC_QMAN_ARC17,
[GAUDI2_QUEUE_ID_NIC_17_2] = CPU_ID_NIC_QMAN_ARC17,
[GAUDI2_QUEUE_ID_NIC_17_3] = CPU_ID_NIC_QMAN_ARC17,
[GAUDI2_QUEUE_ID_NIC_18_0] = CPU_ID_NIC_QMAN_ARC18,
[GAUDI2_QUEUE_ID_NIC_18_1] = CPU_ID_NIC_QMAN_ARC18,
[GAUDI2_QUEUE_ID_NIC_18_2] = CPU_ID_NIC_QMAN_ARC18,
[GAUDI2_QUEUE_ID_NIC_18_3] = CPU_ID_NIC_QMAN_ARC18,
[GAUDI2_QUEUE_ID_NIC_19_0] = CPU_ID_NIC_QMAN_ARC19,
[GAUDI2_QUEUE_ID_NIC_19_1] = CPU_ID_NIC_QMAN_ARC19,
[GAUDI2_QUEUE_ID_NIC_19_2] = CPU_ID_NIC_QMAN_ARC19,
[GAUDI2_QUEUE_ID_NIC_19_3] = CPU_ID_NIC_QMAN_ARC19,
[GAUDI2_QUEUE_ID_NIC_20_0] = CPU_ID_NIC_QMAN_ARC20,
[GAUDI2_QUEUE_ID_NIC_20_1] = CPU_ID_NIC_QMAN_ARC20,
[GAUDI2_QUEUE_ID_NIC_20_2] = CPU_ID_NIC_QMAN_ARC20,
[GAUDI2_QUEUE_ID_NIC_20_3] = CPU_ID_NIC_QMAN_ARC20,
[GAUDI2_QUEUE_ID_NIC_21_0] = CPU_ID_NIC_QMAN_ARC21,
[GAUDI2_QUEUE_ID_NIC_21_1] = CPU_ID_NIC_QMAN_ARC21,
[GAUDI2_QUEUE_ID_NIC_21_2] = CPU_ID_NIC_QMAN_ARC21,
[GAUDI2_QUEUE_ID_NIC_21_3] = CPU_ID_NIC_QMAN_ARC21,
[GAUDI2_QUEUE_ID_NIC_22_0] = CPU_ID_NIC_QMAN_ARC22,
[GAUDI2_QUEUE_ID_NIC_22_1] = CPU_ID_NIC_QMAN_ARC22,
[GAUDI2_QUEUE_ID_NIC_22_2] = CPU_ID_NIC_QMAN_ARC22,
[GAUDI2_QUEUE_ID_NIC_22_3] = CPU_ID_NIC_QMAN_ARC22,
[GAUDI2_QUEUE_ID_NIC_23_0] = CPU_ID_NIC_QMAN_ARC23,
[GAUDI2_QUEUE_ID_NIC_23_1] = CPU_ID_NIC_QMAN_ARC23,
[GAUDI2_QUEUE_ID_NIC_23_2] = CPU_ID_NIC_QMAN_ARC23,
[GAUDI2_QUEUE_ID_NIC_23_3] = CPU_ID_NIC_QMAN_ARC23,
[GAUDI2_QUEUE_ID_ROT_0_0] = CPU_ID_ROT_QMAN_ARC0,
[GAUDI2_QUEUE_ID_ROT_0_1] = CPU_ID_ROT_QMAN_ARC0,
[GAUDI2_QUEUE_ID_ROT_0_2] = CPU_ID_ROT_QMAN_ARC0,
[GAUDI2_QUEUE_ID_ROT_0_3] = CPU_ID_ROT_QMAN_ARC0,
[GAUDI2_QUEUE_ID_ROT_1_0] = CPU_ID_ROT_QMAN_ARC1,
[GAUDI2_QUEUE_ID_ROT_1_1] = CPU_ID_ROT_QMAN_ARC1,
[GAUDI2_QUEUE_ID_ROT_1_2] = CPU_ID_ROT_QMAN_ARC1,
[GAUDI2_QUEUE_ID_ROT_1_3] = CPU_ID_ROT_QMAN_ARC1
};
const u32 gaudi2_dma_core_blocks_bases[DMA_CORE_ID_SIZE] = {
[DMA_CORE_ID_PDMA0] = mmPDMA0_CORE_BASE,
[DMA_CORE_ID_PDMA1] = mmPDMA1_CORE_BASE,
[DMA_CORE_ID_EDMA0] = mmDCORE0_EDMA0_CORE_BASE,
[DMA_CORE_ID_EDMA1] = mmDCORE0_EDMA1_CORE_BASE,
[DMA_CORE_ID_EDMA2] = mmDCORE1_EDMA0_CORE_BASE,
[DMA_CORE_ID_EDMA3] = mmDCORE1_EDMA1_CORE_BASE,
[DMA_CORE_ID_EDMA4] = mmDCORE2_EDMA0_CORE_BASE,
[DMA_CORE_ID_EDMA5] = mmDCORE2_EDMA1_CORE_BASE,
[DMA_CORE_ID_EDMA6] = mmDCORE3_EDMA0_CORE_BASE,
[DMA_CORE_ID_EDMA7] = mmDCORE3_EDMA1_CORE_BASE,
[DMA_CORE_ID_KDMA] = mmARC_FARM_KDMA_BASE
};
const u32 gaudi2_mme_acc_blocks_bases[MME_ID_SIZE] = {
[MME_ID_DCORE0] = mmDCORE0_MME_ACC_BASE,
[MME_ID_DCORE1] = mmDCORE1_MME_ACC_BASE,
[MME_ID_DCORE2] = mmDCORE2_MME_ACC_BASE,
[MME_ID_DCORE3] = mmDCORE3_MME_ACC_BASE
};
static const u32 gaudi2_tpc_cfg_blocks_bases[TPC_ID_SIZE] = {
[TPC_ID_DCORE0_TPC0] = mmDCORE0_TPC0_CFG_BASE,
[TPC_ID_DCORE0_TPC1] = mmDCORE0_TPC1_CFG_BASE,
[TPC_ID_DCORE0_TPC2] = mmDCORE0_TPC2_CFG_BASE,
[TPC_ID_DCORE0_TPC3] = mmDCORE0_TPC3_CFG_BASE,
[TPC_ID_DCORE0_TPC4] = mmDCORE0_TPC4_CFG_BASE,
[TPC_ID_DCORE0_TPC5] = mmDCORE0_TPC5_CFG_BASE,
[TPC_ID_DCORE1_TPC0] = mmDCORE1_TPC0_CFG_BASE,
[TPC_ID_DCORE1_TPC1] = mmDCORE1_TPC1_CFG_BASE,
[TPC_ID_DCORE1_TPC2] = mmDCORE1_TPC2_CFG_BASE,
[TPC_ID_DCORE1_TPC3] = mmDCORE1_TPC3_CFG_BASE,
[TPC_ID_DCORE1_TPC4] = mmDCORE1_TPC4_CFG_BASE,
[TPC_ID_DCORE1_TPC5] = mmDCORE1_TPC5_CFG_BASE,
[TPC_ID_DCORE2_TPC0] = mmDCORE2_TPC0_CFG_BASE,
[TPC_ID_DCORE2_TPC1] = mmDCORE2_TPC1_CFG_BASE,
[TPC_ID_DCORE2_TPC2] = mmDCORE2_TPC2_CFG_BASE,
[TPC_ID_DCORE2_TPC3] = mmDCORE2_TPC3_CFG_BASE,
[TPC_ID_DCORE2_TPC4] = mmDCORE2_TPC4_CFG_BASE,
[TPC_ID_DCORE2_TPC5] = mmDCORE2_TPC5_CFG_BASE,
[TPC_ID_DCORE3_TPC0] = mmDCORE3_TPC0_CFG_BASE,
[TPC_ID_DCORE3_TPC1] = mmDCORE3_TPC1_CFG_BASE,
[TPC_ID_DCORE3_TPC2] = mmDCORE3_TPC2_CFG_BASE,
[TPC_ID_DCORE3_TPC3] = mmDCORE3_TPC3_CFG_BASE,
[TPC_ID_DCORE3_TPC4] = mmDCORE3_TPC4_CFG_BASE,
[TPC_ID_DCORE3_TPC5] = mmDCORE3_TPC5_CFG_BASE,
[TPC_ID_DCORE0_TPC6] = mmDCORE0_TPC6_CFG_BASE,
};
static const u32 gaudi2_tpc_eml_cfg_blocks_bases[TPC_ID_SIZE] = {
[TPC_ID_DCORE0_TPC0] = mmDCORE0_TPC0_EML_CFG_BASE,
[TPC_ID_DCORE0_TPC1] = mmDCORE0_TPC1_EML_CFG_BASE,
[TPC_ID_DCORE0_TPC2] = mmDCORE0_TPC2_EML_CFG_BASE,
[TPC_ID_DCORE0_TPC3] = mmDCORE0_TPC3_EML_CFG_BASE,
[TPC_ID_DCORE0_TPC4] = mmDCORE0_TPC4_EML_CFG_BASE,
[TPC_ID_DCORE0_TPC5] = mmDCORE0_TPC5_EML_CFG_BASE,
[TPC_ID_DCORE1_TPC0] = mmDCORE1_TPC0_EML_CFG_BASE,
[TPC_ID_DCORE1_TPC1] = mmDCORE1_TPC1_EML_CFG_BASE,
[TPC_ID_DCORE1_TPC2] = mmDCORE1_TPC2_EML_CFG_BASE,
[TPC_ID_DCORE1_TPC3] = mmDCORE1_TPC3_EML_CFG_BASE,
[TPC_ID_DCORE1_TPC4] = mmDCORE1_TPC4_EML_CFG_BASE,
[TPC_ID_DCORE1_TPC5] = mmDCORE1_TPC5_EML_CFG_BASE,
[TPC_ID_DCORE2_TPC0] = mmDCORE2_TPC0_EML_CFG_BASE,
[TPC_ID_DCORE2_TPC1] = mmDCORE2_TPC1_EML_CFG_BASE,
[TPC_ID_DCORE2_TPC2] = mmDCORE2_TPC2_EML_CFG_BASE,
[TPC_ID_DCORE2_TPC3] = mmDCORE2_TPC3_EML_CFG_BASE,
[TPC_ID_DCORE2_TPC4] = mmDCORE2_TPC4_EML_CFG_BASE,
[TPC_ID_DCORE2_TPC5] = mmDCORE2_TPC5_EML_CFG_BASE,
[TPC_ID_DCORE3_TPC0] = mmDCORE3_TPC0_EML_CFG_BASE,
[TPC_ID_DCORE3_TPC1] = mmDCORE3_TPC1_EML_CFG_BASE,
[TPC_ID_DCORE3_TPC2] = mmDCORE3_TPC2_EML_CFG_BASE,
[TPC_ID_DCORE3_TPC3] = mmDCORE3_TPC3_EML_CFG_BASE,
[TPC_ID_DCORE3_TPC4] = mmDCORE3_TPC4_EML_CFG_BASE,
[TPC_ID_DCORE3_TPC5] = mmDCORE3_TPC5_EML_CFG_BASE,
[TPC_ID_DCORE0_TPC6] = mmDCORE0_TPC6_EML_CFG_BASE,
};
const u32 gaudi2_rot_blocks_bases[ROTATOR_ID_SIZE] = {
[ROTATOR_ID_0] = mmROT0_BASE,
[ROTATOR_ID_1] = mmROT1_BASE
};
static const u32 gaudi2_tpc_id_to_queue_id[TPC_ID_SIZE] = {
[TPC_ID_DCORE0_TPC0] = GAUDI2_QUEUE_ID_DCORE0_TPC_0_0,
[TPC_ID_DCORE0_TPC1] = GAUDI2_QUEUE_ID_DCORE0_TPC_1_0,
[TPC_ID_DCORE0_TPC2] = GAUDI2_QUEUE_ID_DCORE0_TPC_2_0,
[TPC_ID_DCORE0_TPC3] = GAUDI2_QUEUE_ID_DCORE0_TPC_3_0,
[TPC_ID_DCORE0_TPC4] = GAUDI2_QUEUE_ID_DCORE0_TPC_4_0,
[TPC_ID_DCORE0_TPC5] = GAUDI2_QUEUE_ID_DCORE0_TPC_5_0,
[TPC_ID_DCORE1_TPC0] = GAUDI2_QUEUE_ID_DCORE1_TPC_0_0,
[TPC_ID_DCORE1_TPC1] = GAUDI2_QUEUE_ID_DCORE1_TPC_1_0,
[TPC_ID_DCORE1_TPC2] = GAUDI2_QUEUE_ID_DCORE1_TPC_2_0,
[TPC_ID_DCORE1_TPC3] = GAUDI2_QUEUE_ID_DCORE1_TPC_3_0,
[TPC_ID_DCORE1_TPC4] = GAUDI2_QUEUE_ID_DCORE1_TPC_4_0,
[TPC_ID_DCORE1_TPC5] = GAUDI2_QUEUE_ID_DCORE1_TPC_5_0,
[TPC_ID_DCORE2_TPC0] = GAUDI2_QUEUE_ID_DCORE2_TPC_0_0,
[TPC_ID_DCORE2_TPC1] = GAUDI2_QUEUE_ID_DCORE2_TPC_1_0,
[TPC_ID_DCORE2_TPC2] = GAUDI2_QUEUE_ID_DCORE2_TPC_2_0,
[TPC_ID_DCORE2_TPC3] = GAUDI2_QUEUE_ID_DCORE2_TPC_3_0,
[TPC_ID_DCORE2_TPC4] = GAUDI2_QUEUE_ID_DCORE2_TPC_4_0,
[TPC_ID_DCORE2_TPC5] = GAUDI2_QUEUE_ID_DCORE2_TPC_5_0,
[TPC_ID_DCORE3_TPC0] = GAUDI2_QUEUE_ID_DCORE3_TPC_0_0,
[TPC_ID_DCORE3_TPC1] = GAUDI2_QUEUE_ID_DCORE3_TPC_1_0,
[TPC_ID_DCORE3_TPC2] = GAUDI2_QUEUE_ID_DCORE3_TPC_2_0,
[TPC_ID_DCORE3_TPC3] = GAUDI2_QUEUE_ID_DCORE3_TPC_3_0,
[TPC_ID_DCORE3_TPC4] = GAUDI2_QUEUE_ID_DCORE3_TPC_4_0,
[TPC_ID_DCORE3_TPC5] = GAUDI2_QUEUE_ID_DCORE3_TPC_5_0,
[TPC_ID_DCORE0_TPC6] = GAUDI2_QUEUE_ID_DCORE0_TPC_6_0,
};
static const u32 gaudi2_rot_id_to_queue_id[ROTATOR_ID_SIZE] = {
[ROTATOR_ID_0] = GAUDI2_QUEUE_ID_ROT_0_0,
[ROTATOR_ID_1] = GAUDI2_QUEUE_ID_ROT_1_0,
};
static const u32 gaudi2_tpc_engine_id_to_tpc_id[] = {
[GAUDI2_DCORE0_ENGINE_ID_TPC_0] = TPC_ID_DCORE0_TPC0,
[GAUDI2_DCORE0_ENGINE_ID_TPC_1] = TPC_ID_DCORE0_TPC1,
[GAUDI2_DCORE0_ENGINE_ID_TPC_2] = TPC_ID_DCORE0_TPC2,
[GAUDI2_DCORE0_ENGINE_ID_TPC_3] = TPC_ID_DCORE0_TPC3,
[GAUDI2_DCORE0_ENGINE_ID_TPC_4] = TPC_ID_DCORE0_TPC4,
[GAUDI2_DCORE0_ENGINE_ID_TPC_5] = TPC_ID_DCORE0_TPC5,
[GAUDI2_DCORE1_ENGINE_ID_TPC_0] = TPC_ID_DCORE1_TPC0,
[GAUDI2_DCORE1_ENGINE_ID_TPC_1] = TPC_ID_DCORE1_TPC1,
[GAUDI2_DCORE1_ENGINE_ID_TPC_2] = TPC_ID_DCORE1_TPC2,
[GAUDI2_DCORE1_ENGINE_ID_TPC_3] = TPC_ID_DCORE1_TPC3,
[GAUDI2_DCORE1_ENGINE_ID_TPC_4] = TPC_ID_DCORE1_TPC4,
[GAUDI2_DCORE1_ENGINE_ID_TPC_5] = TPC_ID_DCORE1_TPC5,
[GAUDI2_DCORE2_ENGINE_ID_TPC_0] = TPC_ID_DCORE2_TPC0,
[GAUDI2_DCORE2_ENGINE_ID_TPC_1] = TPC_ID_DCORE2_TPC1,
[GAUDI2_DCORE2_ENGINE_ID_TPC_2] = TPC_ID_DCORE2_TPC2,
[GAUDI2_DCORE2_ENGINE_ID_TPC_3] = TPC_ID_DCORE2_TPC3,
[GAUDI2_DCORE2_ENGINE_ID_TPC_4] = TPC_ID_DCORE2_TPC4,
[GAUDI2_DCORE2_ENGINE_ID_TPC_5] = TPC_ID_DCORE2_TPC5,
[GAUDI2_DCORE3_ENGINE_ID_TPC_0] = TPC_ID_DCORE3_TPC0,
[GAUDI2_DCORE3_ENGINE_ID_TPC_1] = TPC_ID_DCORE3_TPC1,
[GAUDI2_DCORE3_ENGINE_ID_TPC_2] = TPC_ID_DCORE3_TPC2,
[GAUDI2_DCORE3_ENGINE_ID_TPC_3] = TPC_ID_DCORE3_TPC3,
[GAUDI2_DCORE3_ENGINE_ID_TPC_4] = TPC_ID_DCORE3_TPC4,
[GAUDI2_DCORE3_ENGINE_ID_TPC_5] = TPC_ID_DCORE3_TPC5,
[GAUDI2_DCORE0_ENGINE_ID_TPC_6] = TPC_ID_DCORE0_TPC6,
};
static const u32 gaudi2_mme_engine_id_to_mme_id[] = {
[GAUDI2_DCORE0_ENGINE_ID_MME] = MME_ID_DCORE0,
[GAUDI2_DCORE1_ENGINE_ID_MME] = MME_ID_DCORE1,
[GAUDI2_DCORE2_ENGINE_ID_MME] = MME_ID_DCORE2,
[GAUDI2_DCORE3_ENGINE_ID_MME] = MME_ID_DCORE3,
};
static const u32 gaudi2_edma_engine_id_to_edma_id[] = {
[GAUDI2_ENGINE_ID_PDMA_0] = DMA_CORE_ID_PDMA0,
[GAUDI2_ENGINE_ID_PDMA_1] = DMA_CORE_ID_PDMA1,
[GAUDI2_DCORE0_ENGINE_ID_EDMA_0] = DMA_CORE_ID_EDMA0,
[GAUDI2_DCORE0_ENGINE_ID_EDMA_1] = DMA_CORE_ID_EDMA1,
[GAUDI2_DCORE1_ENGINE_ID_EDMA_0] = DMA_CORE_ID_EDMA2,
[GAUDI2_DCORE1_ENGINE_ID_EDMA_1] = DMA_CORE_ID_EDMA3,
[GAUDI2_DCORE2_ENGINE_ID_EDMA_0] = DMA_CORE_ID_EDMA4,
[GAUDI2_DCORE2_ENGINE_ID_EDMA_1] = DMA_CORE_ID_EDMA5,
[GAUDI2_DCORE3_ENGINE_ID_EDMA_0] = DMA_CORE_ID_EDMA6,
[GAUDI2_DCORE3_ENGINE_ID_EDMA_1] = DMA_CORE_ID_EDMA7,
[GAUDI2_ENGINE_ID_KDMA] = DMA_CORE_ID_KDMA,
};
const u32 edma_stream_base[NUM_OF_EDMA_PER_DCORE * NUM_OF_DCORES] = {
GAUDI2_QUEUE_ID_DCORE0_EDMA_0_0,
GAUDI2_QUEUE_ID_DCORE0_EDMA_1_0,
GAUDI2_QUEUE_ID_DCORE1_EDMA_0_0,
GAUDI2_QUEUE_ID_DCORE1_EDMA_1_0,
GAUDI2_QUEUE_ID_DCORE2_EDMA_0_0,
GAUDI2_QUEUE_ID_DCORE2_EDMA_1_0,
GAUDI2_QUEUE_ID_DCORE3_EDMA_0_0,
GAUDI2_QUEUE_ID_DCORE3_EDMA_1_0,
};
static const char gaudi2_vdec_irq_name[GAUDI2_VDEC_MSIX_ENTRIES][GAUDI2_MAX_STRING_LEN] = {
"gaudi2 vdec 0_0", "gaudi2 vdec 0_0 abnormal",
"gaudi2 vdec 0_1", "gaudi2 vdec 0_1 abnormal",
"gaudi2 vdec 1_0", "gaudi2 vdec 1_0 abnormal",
"gaudi2 vdec 1_1", "gaudi2 vdec 1_1 abnormal",
"gaudi2 vdec 2_0", "gaudi2 vdec 2_0 abnormal",
"gaudi2 vdec 2_1", "gaudi2 vdec 2_1 abnormal",
"gaudi2 vdec 3_0", "gaudi2 vdec 3_0 abnormal",
"gaudi2 vdec 3_1", "gaudi2 vdec 3_1 abnormal",
"gaudi2 vdec s_0", "gaudi2 vdec s_0 abnormal",
"gaudi2 vdec s_1", "gaudi2 vdec s_1 abnormal"
};
enum rtr_id {
DCORE0_RTR0,
DCORE0_RTR1,
DCORE0_RTR2,
DCORE0_RTR3,
DCORE0_RTR4,
DCORE0_RTR5,
DCORE0_RTR6,
DCORE0_RTR7,
DCORE1_RTR0,
DCORE1_RTR1,
DCORE1_RTR2,
DCORE1_RTR3,
DCORE1_RTR4,
DCORE1_RTR5,
DCORE1_RTR6,
DCORE1_RTR7,
DCORE2_RTR0,
DCORE2_RTR1,
DCORE2_RTR2,
DCORE2_RTR3,
DCORE2_RTR4,
DCORE2_RTR5,
DCORE2_RTR6,
DCORE2_RTR7,
DCORE3_RTR0,
DCORE3_RTR1,
DCORE3_RTR2,
DCORE3_RTR3,
DCORE3_RTR4,
DCORE3_RTR5,
DCORE3_RTR6,
DCORE3_RTR7,
};
static const u32 gaudi2_tpc_initiator_hbw_rtr_id[NUM_OF_TPC_PER_DCORE * NUM_OF_DCORES + 1] = {
DCORE0_RTR1, DCORE0_RTR1, DCORE0_RTR2, DCORE0_RTR2, DCORE0_RTR3, DCORE0_RTR3,
DCORE1_RTR6, DCORE1_RTR6, DCORE1_RTR5, DCORE1_RTR5, DCORE1_RTR4, DCORE1_RTR4,
DCORE2_RTR3, DCORE2_RTR3, DCORE2_RTR2, DCORE2_RTR2, DCORE2_RTR1, DCORE2_RTR1,
DCORE3_RTR4, DCORE3_RTR4, DCORE3_RTR5, DCORE3_RTR5, DCORE3_RTR6, DCORE3_RTR6,
DCORE0_RTR0
};
static const u32 gaudi2_tpc_initiator_lbw_rtr_id[NUM_OF_TPC_PER_DCORE * NUM_OF_DCORES + 1] = {
DCORE0_RTR1, DCORE0_RTR1, DCORE0_RTR1, DCORE0_RTR1, DCORE0_RTR2, DCORE0_RTR2,
DCORE1_RTR7, DCORE1_RTR7, DCORE1_RTR6, DCORE1_RTR6, DCORE1_RTR5, DCORE1_RTR5,
DCORE2_RTR2, DCORE2_RTR2, DCORE2_RTR1, DCORE2_RTR1, DCORE2_RTR0, DCORE2_RTR0,
DCORE3_RTR5, DCORE3_RTR5, DCORE3_RTR6, DCORE3_RTR6, DCORE3_RTR7, DCORE3_RTR7,
DCORE0_RTR0
};
static const u32 gaudi2_dec_initiator_hbw_rtr_id[NUMBER_OF_DEC] = {
DCORE0_RTR0, DCORE0_RTR0, DCORE1_RTR7, DCORE1_RTR7, DCORE2_RTR0, DCORE2_RTR0,
DCORE3_RTR7, DCORE3_RTR7, DCORE0_RTR0, DCORE0_RTR0
};
static const u32 gaudi2_dec_initiator_lbw_rtr_id[NUMBER_OF_DEC] = {
DCORE0_RTR1, DCORE0_RTR1, DCORE1_RTR6, DCORE1_RTR6, DCORE2_RTR1, DCORE2_RTR1,
DCORE3_RTR6, DCORE3_RTR6, DCORE0_RTR0, DCORE0_RTR0
};
static const u32 gaudi2_nic_initiator_hbw_rtr_id[NIC_NUMBER_OF_MACROS] = {
DCORE1_RTR7, DCORE1_RTR7, DCORE1_RTR7, DCORE1_RTR7, DCORE1_RTR7, DCORE2_RTR0,
DCORE2_RTR0, DCORE2_RTR0, DCORE2_RTR0, DCORE3_RTR7, DCORE3_RTR7, DCORE3_RTR7
};
static const u32 gaudi2_nic_initiator_lbw_rtr_id[NIC_NUMBER_OF_MACROS] = {
DCORE1_RTR7, DCORE1_RTR7, DCORE1_RTR7, DCORE1_RTR7, DCORE1_RTR7, DCORE2_RTR0,
DCORE2_RTR0, DCORE2_RTR0, DCORE2_RTR0, DCORE3_RTR7, DCORE3_RTR7, DCORE3_RTR7
};
static const u32 gaudi2_edma_initiator_hbw_sft[NUM_OF_EDMA_PER_DCORE * NUM_OF_DCORES] = {
mmSFT0_HBW_RTR_IF1_MSTR_IF_RR_SHRD_HBW_BASE,
mmSFT0_HBW_RTR_IF0_MSTR_IF_RR_SHRD_HBW_BASE,
mmSFT1_HBW_RTR_IF1_MSTR_IF_RR_SHRD_HBW_BASE,
mmSFT1_HBW_RTR_IF0_MSTR_IF_RR_SHRD_HBW_BASE,
mmSFT2_HBW_RTR_IF0_MSTR_IF_RR_SHRD_HBW_BASE,
mmSFT2_HBW_RTR_IF1_MSTR_IF_RR_SHRD_HBW_BASE,
mmSFT3_HBW_RTR_IF0_MSTR_IF_RR_SHRD_HBW_BASE,
mmSFT3_HBW_RTR_IF1_MSTR_IF_RR_SHRD_HBW_BASE
};
static const u32 gaudi2_pdma_initiator_hbw_rtr_id[NUM_OF_PDMA] = {
DCORE0_RTR0, DCORE0_RTR0
};
static const u32 gaudi2_pdma_initiator_lbw_rtr_id[NUM_OF_PDMA] = {
DCORE0_RTR2, DCORE0_RTR2
};
static const u32 gaudi2_rot_initiator_hbw_rtr_id[NUM_OF_ROT] = {
DCORE2_RTR0, DCORE3_RTR7
};
static const u32 gaudi2_rot_initiator_lbw_rtr_id[NUM_OF_ROT] = {
DCORE2_RTR2, DCORE3_RTR5
};
struct mme_initiators_rtr_id {
u32 wap0;
u32 wap1;
u32 write;
u32 read;
u32 sbte0;
u32 sbte1;
u32 sbte2;
u32 sbte3;
u32 sbte4;
};
enum mme_initiators {
MME_WAP0 = 0,
MME_WAP1,
MME_WRITE,
MME_READ,
MME_SBTE0,
MME_SBTE1,
MME_SBTE2,
MME_SBTE3,
MME_SBTE4,
MME_INITIATORS_MAX
};
static const struct mme_initiators_rtr_id
gaudi2_mme_initiator_rtr_id[NUM_OF_MME_PER_DCORE * NUM_OF_DCORES] = {
{ .wap0 = 5, .wap1 = 7, .write = 6, .read = 7,
.sbte0 = 7, .sbte1 = 4, .sbte2 = 4, .sbte3 = 5, .sbte4 = 6},
{ .wap0 = 10, .wap1 = 8, .write = 9, .read = 8,
.sbte0 = 11, .sbte1 = 11, .sbte2 = 10, .sbte3 = 9, .sbte4 = 8},
{ .wap0 = 21, .wap1 = 23, .write = 22, .read = 23,
.sbte0 = 20, .sbte1 = 20, .sbte2 = 21, .sbte3 = 22, .sbte4 = 23},
{ .wap0 = 30, .wap1 = 28, .write = 29, .read = 30,
.sbte0 = 31, .sbte1 = 31, .sbte2 = 30, .sbte3 = 29, .sbte4 = 28},
};
enum razwi_event_sources {
RAZWI_TPC,
RAZWI_MME,
RAZWI_EDMA,
RAZWI_PDMA,
RAZWI_NIC,
RAZWI_DEC,
RAZWI_ROT
};
struct hbm_mc_error_causes {
u32 mask;
char cause[50];
};
static struct hl_special_block_info gaudi2_special_blocks[] = GAUDI2_SPECIAL_BLOCKS;
static int gaudi2_iterator_skip_block_types[] = {
GAUDI2_BLOCK_TYPE_PLL,
GAUDI2_BLOCK_TYPE_EU_BIST,
GAUDI2_BLOCK_TYPE_HBM,
GAUDI2_BLOCK_TYPE_XFT
};
static struct range gaudi2_iterator_skip_block_ranges[] = {
{mmPSOC_I2C_M0_BASE, mmPSOC_EFUSE_BASE},
{mmPSOC_BTL_BASE, mmPSOC_MSTR_IF_RR_SHRD_HBW_BASE},
{mmCPU_CA53_CFG_BASE, mmCPU_CA53_CFG_BASE},
{mmCPU_TIMESTAMP_BASE, mmCPU_MSTR_IF_RR_SHRD_HBW_BASE}
};
static struct hbm_mc_error_causes hbm_mc_spi[GAUDI2_NUM_OF_HBM_MC_SPI_CAUSE] = {
{HBM_MC_SPI_TEMP_PIN_CHG_MASK, "temperature pins changed"},
{HBM_MC_SPI_THR_ENG_MASK, "temperature-based throttling engaged"},
{HBM_MC_SPI_THR_DIS_ENG_MASK, "temperature-based throttling disengaged"},
{HBM_MC_SPI_IEEE1500_COMP_MASK, "IEEE1500 op comp"},
{HBM_MC_SPI_IEEE1500_PAUSED_MASK, "IEEE1500 op paused"},
};
static const char * const hbm_mc_sei_cause[GAUDI2_NUM_OF_HBM_SEI_CAUSE] = {
[HBM_SEI_CMD_PARITY_EVEN] = "SEI C/A parity even",
[HBM_SEI_CMD_PARITY_ODD] = "SEI C/A parity odd",
[HBM_SEI_READ_ERR] = "SEI read data error",
[HBM_SEI_WRITE_DATA_PARITY_ERR] = "SEI write data parity error",
[HBM_SEI_CATTRIP] = "SEI CATTRIP asserted",
[HBM_SEI_MEM_BIST_FAIL] = "SEI memory BIST fail",
[HBM_SEI_DFI] = "SEI DFI error",
[HBM_SEI_INV_TEMP_READ_OUT] = "SEI invalid temp read",
[HBM_SEI_BIST_FAIL] = "SEI BIST fail"
};
struct mmu_spi_sei_cause {
char cause[50];
int clear_bit;
};
static const struct mmu_spi_sei_cause gaudi2_mmu_spi_sei[GAUDI2_NUM_OF_MMU_SPI_SEI_CAUSE] = {
{"page fault", 1},
{"page access", 1},
{"bypass ddr", 2},
{"multi hit", 2},
{"mmu rei0", -1},
{"mmu rei1", -1},
{"stlb rei0", -1},
{"stlb rei1", -1},
{"rr privileged write hit", 2},
{"rr privileged read hit", 2},
{"rr secure write hit", 2},
{"rr secure read hit", 2},
{"bist_fail no use", 2},
{"bist_fail no use", 2},
{"bist_fail no use", 2},
{"bist_fail no use", 2},
{"slave error", 16},
{"dec error", 17},
{"burst fifo full", 2}
};
struct gaudi2_cache_invld_params {
u64 start_va;
u64 end_va;
u32 inv_start_val;
u32 flags;
bool range_invalidation;
};
struct gaudi2_tpc_idle_data {
struct engines_data *e;
unsigned long *mask;
bool *is_idle;
const char *tpc_fmt;
};
struct gaudi2_tpc_mmu_data {
u32 rw_asid;
};
static s64 gaudi2_state_dump_specs_props[SP_MAX] = {0};
static int gaudi2_memset_device_memory(struct hl_device *hdev, u64 addr, u64 size, u64 val);
static bool gaudi2_is_queue_enabled(struct hl_device *hdev, u32 hw_queue_id);
static bool gaudi2_is_arc_enabled(struct hl_device *hdev, u64 arc_id);
static void gaudi2_clr_arc_id_cap(struct hl_device *hdev, u64 arc_id);
static void gaudi2_set_arc_id_cap(struct hl_device *hdev, u64 arc_id);
static void gaudi2_memset_device_lbw(struct hl_device *hdev, u32 addr, u32 size, u32 val);
static int gaudi2_send_job_to_kdma(struct hl_device *hdev, u64 src_addr, u64 dst_addr, u32 size,
bool is_memset);
static bool gaudi2_get_tpc_idle_status(struct hl_device *hdev, u64 *mask_arr, u8 mask_len,
struct engines_data *e);
static bool gaudi2_get_mme_idle_status(struct hl_device *hdev, u64 *mask_arr, u8 mask_len,
struct engines_data *e);
static bool gaudi2_get_edma_idle_status(struct hl_device *hdev, u64 *mask_arr, u8 mask_len,
struct engines_data *e);
static u64 gaudi2_mmu_scramble_addr(struct hl_device *hdev, u64 raw_addr);
static u64 gaudi2_mmu_descramble_addr(struct hl_device *hdev, u64 scrambled_addr);
static void gaudi2_init_scrambler_hbm(struct hl_device *hdev)
{
}
static u32 gaudi2_get_signal_cb_size(struct hl_device *hdev)
{
return sizeof(struct packet_msg_short);
}
static u32 gaudi2_get_wait_cb_size(struct hl_device *hdev)
{
return sizeof(struct packet_msg_short) * 4 + sizeof(struct packet_fence);
}
void gaudi2_iterate_tpcs(struct hl_device *hdev, struct iterate_module_ctx *ctx)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
int dcore, inst, tpc_seq;
u32 offset;
ctx->rc = 0;
for (dcore = 0; dcore < NUM_OF_DCORES; dcore++) {
for (inst = 0; inst < NUM_OF_TPC_PER_DCORE; inst++) {
tpc_seq = dcore * NUM_OF_TPC_PER_DCORE + inst;
if (!(prop->tpc_enabled_mask & BIT(tpc_seq)))
continue;
offset = (DCORE_OFFSET * dcore) + (DCORE_TPC_OFFSET * inst);
ctx->fn(hdev, dcore, inst, offset, ctx);
if (ctx->rc) {
dev_err(hdev->dev, "TPC iterator failed for DCORE%d TPC%d\n",
dcore, inst);
return;
}
}
}
if (!(prop->tpc_enabled_mask & BIT(TPC_ID_DCORE0_TPC6)))
return;
offset = DCORE_TPC_OFFSET * (NUM_DCORE0_TPC - 1);
ctx->fn(hdev, 0, NUM_DCORE0_TPC - 1, offset, ctx);
if (ctx->rc)
dev_err(hdev->dev, "TPC iterator failed for DCORE0 TPC6\n");
}
static bool gaudi2_host_phys_addr_valid(u64 addr)
{
if ((addr < HOST_PHYS_BASE_0 + HOST_PHYS_SIZE_0) || (addr >= HOST_PHYS_BASE_1))
return true;
return false;
}
static int set_number_of_functional_hbms(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
u8 faulty_hbms = hweight64(hdev->dram_binning);
if (!faulty_hbms) {
dev_dbg(hdev->dev, "All HBM are in use (no binning)\n");
prop->num_functional_hbms = GAUDI2_HBM_NUM;
return 0;
}
if (faulty_hbms > MAX_FAULTY_HBMS) {
dev_err(hdev->dev,
"HBM binning supports max of %d faulty HBMs, supplied mask 0x%llx.\n",
MAX_FAULTY_HBMS, hdev->dram_binning);
return -EINVAL;
}
prop->num_functional_hbms = GAUDI2_HBM_NUM - faulty_hbms;
return 0;
}
static int gaudi2_set_dram_properties(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
u32 basic_hbm_page_size;
int rc;
rc = set_number_of_functional_hbms(hdev);
if (rc)
return -EINVAL;
basic_hbm_page_size = prop->num_functional_hbms * SZ_8M;
prop->dram_page_size = GAUDI2_COMPENSATE_TLB_PAGE_SIZE_FACTOR * basic_hbm_page_size;
prop->device_mem_alloc_default_page_size = prop->dram_page_size;
prop->dram_size = prop->num_functional_hbms * SZ_16G;
prop->dram_base_address = DRAM_PHYS_BASE;
prop->dram_end_address = prop->dram_base_address + prop->dram_size;
prop->dram_supports_virtual_memory = true;
prop->dram_user_base_address = DRAM_PHYS_BASE + prop->dram_page_size;
prop->dram_hints_align_mask = ~GAUDI2_HBM_MMU_SCRM_ADDRESS_MASK;
prop->hints_dram_reserved_va_range.start_addr = RESERVED_VA_RANGE_FOR_ARC_ON_HBM_START;
prop->hints_dram_reserved_va_range.end_addr = RESERVED_VA_RANGE_FOR_ARC_ON_HBM_END;
prop->dmmu.start_addr = prop->dram_base_address +
(prop->dram_page_size *
DIV_ROUND_UP_SECTOR_T(prop->dram_size, prop->dram_page_size));
prop->dmmu.end_addr = prop->dmmu.start_addr + prop->dram_page_size *
div_u64((VA_HBM_SPACE_END - prop->dmmu.start_addr), prop->dmmu.page_size);
return 0;
}
static int gaudi2_set_fixed_properties(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
struct hw_queue_properties *q_props;
u32 num_sync_stream_queues = 0;
int i;
prop->max_queues = GAUDI2_QUEUE_ID_SIZE;
prop->hw_queues_props = kcalloc(prop->max_queues, sizeof(struct hw_queue_properties),
GFP_KERNEL);
if (!prop->hw_queues_props)
return -ENOMEM;
q_props = prop->hw_queues_props;
for (i = 0 ; i < GAUDI2_QUEUE_ID_CPU_PQ ; i++) {
q_props[i].type = QUEUE_TYPE_HW;
q_props[i].driver_only = 0;
if (i >= GAUDI2_QUEUE_ID_NIC_0_0 && i <= GAUDI2_QUEUE_ID_NIC_23_3) {
q_props[i].supports_sync_stream = 0;
} else {
q_props[i].supports_sync_stream = 1;
num_sync_stream_queues++;
}
q_props[i].cb_alloc_flags = CB_ALLOC_USER;
}
q_props[GAUDI2_QUEUE_ID_CPU_PQ].type = QUEUE_TYPE_CPU;
q_props[GAUDI2_QUEUE_ID_CPU_PQ].driver_only = 1;
q_props[GAUDI2_QUEUE_ID_CPU_PQ].cb_alloc_flags = CB_ALLOC_KERNEL;
prop->cache_line_size = DEVICE_CACHE_LINE_SIZE;
prop->cfg_base_address = CFG_BASE;
prop->device_dma_offset_for_host_access = HOST_PHYS_BASE_0;
prop->host_base_address = HOST_PHYS_BASE_0;
prop->host_end_address = prop->host_base_address + HOST_PHYS_SIZE_0;
prop->max_pending_cs = GAUDI2_MAX_PENDING_CS;
prop->completion_queues_count = GAUDI2_RESERVED_CQ_NUMBER;
prop->user_dec_intr_count = NUMBER_OF_DEC;
prop->user_interrupt_count = GAUDI2_IRQ_NUM_USER_LAST - GAUDI2_IRQ_NUM_USER_FIRST + 1;
prop->completion_mode = HL_COMPLETION_MODE_CS;
prop->sync_stream_first_sob = GAUDI2_RESERVED_SOB_NUMBER;
prop->sync_stream_first_mon = GAUDI2_RESERVED_MON_NUMBER;
prop->sram_base_address = SRAM_BASE_ADDR;
prop->sram_size = SRAM_SIZE;
prop->sram_end_address = prop->sram_base_address + prop->sram_size;
prop->sram_user_base_address = prop->sram_base_address + SRAM_USER_BASE_OFFSET;
prop->hints_range_reservation = true;
prop->rotator_enabled_mask = BIT(NUM_OF_ROT) - 1;
if (hdev->pldm)
prop->mmu_pgt_size = 0x800000;
else
prop->mmu_pgt_size = MMU_PAGE_TABLES_INITIAL_SIZE;
prop->mmu_pte_size = HL_PTE_SIZE;
prop->mmu_hop_table_size = HOP_TABLE_SIZE_512_PTE;
prop->mmu_hop0_tables_total_size = HOP0_512_PTE_TABLES_TOTAL_SIZE;
prop->dmmu.hop_shifts[MMU_HOP0] = DHOP0_SHIFT;
prop->dmmu.hop_shifts[MMU_HOP1] = DHOP1_SHIFT;
prop->dmmu.hop_shifts[MMU_HOP2] = DHOP2_SHIFT;
prop->dmmu.hop_shifts[MMU_HOP3] = DHOP3_SHIFT;
prop->dmmu.hop_shifts[MMU_HOP4] = DHOP4_SHIFT;
prop->dmmu.hop_masks[MMU_HOP0] = DHOP0_MASK;
prop->dmmu.hop_masks[MMU_HOP1] = DHOP1_MASK;
prop->dmmu.hop_masks[MMU_HOP2] = DHOP2_MASK;
prop->dmmu.hop_masks[MMU_HOP3] = DHOP3_MASK;
prop->dmmu.hop_masks[MMU_HOP4] = DHOP4_MASK;
prop->dmmu.page_size = PAGE_SIZE_1GB;
prop->dmmu.num_hops = MMU_ARCH_6_HOPS;
prop->dmmu.last_mask = LAST_MASK;
prop->dmmu.host_resident = 1;
prop->dmmu.hop_table_size = prop->mmu_hop_table_size;
prop->dmmu.hop0_tables_total_size = prop->mmu_hop0_tables_total_size;
prop->dram_size = (GAUDI2_HBM_NUM - 1) * SZ_16G;
hdev->pmmu_huge_range = true;
prop->pmmu.host_resident = 1;
prop->pmmu.num_hops = MMU_ARCH_6_HOPS;
prop->pmmu.last_mask = LAST_MASK;
prop->pmmu.hop_table_size = prop->mmu_hop_table_size;
prop->pmmu.hop0_tables_total_size = prop->mmu_hop0_tables_total_size;
prop->hints_host_reserved_va_range.start_addr = RESERVED_VA_FOR_VIRTUAL_MSIX_DOORBELL_START;
prop->hints_host_reserved_va_range.end_addr = RESERVED_VA_RANGE_FOR_ARC_ON_HOST_END;
prop->hints_host_hpage_reserved_va_range.start_addr =
RESERVED_VA_RANGE_FOR_ARC_ON_HOST_HPAGE_START;
prop->hints_host_hpage_reserved_va_range.end_addr =
RESERVED_VA_RANGE_FOR_ARC_ON_HOST_HPAGE_END;
if (PAGE_SIZE == SZ_64K) {
prop->pmmu.hop_shifts[MMU_HOP0] = HOP0_SHIFT_64K;
prop->pmmu.hop_shifts[MMU_HOP1] = HOP1_SHIFT_64K;
prop->pmmu.hop_shifts[MMU_HOP2] = HOP2_SHIFT_64K;
prop->pmmu.hop_shifts[MMU_HOP3] = HOP3_SHIFT_64K;
prop->pmmu.hop_shifts[MMU_HOP4] = HOP4_SHIFT_64K;
prop->pmmu.hop_shifts[MMU_HOP5] = HOP5_SHIFT_64K;
prop->pmmu.hop_masks[MMU_HOP0] = HOP0_MASK_64K;
prop->pmmu.hop_masks[MMU_HOP1] = HOP1_MASK_64K;
prop->pmmu.hop_masks[MMU_HOP2] = HOP2_MASK_64K;
prop->pmmu.hop_masks[MMU_HOP3] = HOP3_MASK_64K;
prop->pmmu.hop_masks[MMU_HOP4] = HOP4_MASK_64K;
prop->pmmu.hop_masks[MMU_HOP5] = HOP5_MASK_64K;
prop->pmmu.start_addr = VA_HOST_SPACE_PAGE_START;
prop->pmmu.end_addr = VA_HOST_SPACE_PAGE_END;
prop->pmmu.page_size = PAGE_SIZE_64KB;
memcpy(&prop->pmmu_huge, &prop->pmmu, sizeof(prop->pmmu));
prop->pmmu_huge.page_size = PAGE_SIZE_16MB;
prop->pmmu_huge.start_addr = VA_HOST_SPACE_HPAGE_START;
prop->pmmu_huge.end_addr = VA_HOST_SPACE_HPAGE_END;
} else {
prop->pmmu.hop_shifts[MMU_HOP0] = HOP0_SHIFT_4K;
prop->pmmu.hop_shifts[MMU_HOP1] = HOP1_SHIFT_4K;
prop->pmmu.hop_shifts[MMU_HOP2] = HOP2_SHIFT_4K;
prop->pmmu.hop_shifts[MMU_HOP3] = HOP3_SHIFT_4K;
prop->pmmu.hop_shifts[MMU_HOP4] = HOP4_SHIFT_4K;
prop->pmmu.hop_shifts[MMU_HOP5] = HOP5_SHIFT_4K;
prop->pmmu.hop_masks[MMU_HOP0] = HOP0_MASK_4K;
prop->pmmu.hop_masks[MMU_HOP1] = HOP1_MASK_4K;
prop->pmmu.hop_masks[MMU_HOP2] = HOP2_MASK_4K;
prop->pmmu.hop_masks[MMU_HOP3] = HOP3_MASK_4K;
prop->pmmu.hop_masks[MMU_HOP4] = HOP4_MASK_4K;
prop->pmmu.hop_masks[MMU_HOP5] = HOP5_MASK_4K;
prop->pmmu.start_addr = VA_HOST_SPACE_PAGE_START;
prop->pmmu.end_addr = VA_HOST_SPACE_PAGE_END;
prop->pmmu.page_size = PAGE_SIZE_4KB;
memcpy(&prop->pmmu_huge, &prop->pmmu, sizeof(prop->pmmu));
prop->pmmu_huge.page_size = PAGE_SIZE_2MB;
prop->pmmu_huge.start_addr = VA_HOST_SPACE_HPAGE_START;
prop->pmmu_huge.end_addr = VA_HOST_SPACE_HPAGE_END;
}
prop->max_num_of_engines = GAUDI2_ENGINE_ID_SIZE;
prop->num_engine_cores = CPU_ID_MAX;
prop->cfg_size = CFG_SIZE;
prop->max_asid = MAX_ASID;
prop->num_of_events = GAUDI2_EVENT_SIZE;
prop->supports_engine_modes = true;
prop->dc_power_default = DC_POWER_DEFAULT;
prop->cb_pool_cb_cnt = GAUDI2_CB_POOL_CB_CNT;
prop->cb_pool_cb_size = GAUDI2_CB_POOL_CB_SIZE;
prop->pcie_dbi_base_address = CFG_BASE + mmPCIE_DBI_BASE;
prop->pcie_aux_dbi_reg_addr = CFG_BASE + mmPCIE_AUX_DBI;
strncpy(prop->cpucp_info.card_name, GAUDI2_DEFAULT_CARD_NAME, CARD_NAME_MAX_LEN);
prop->mme_master_slave_mode = 1;
prop->first_available_user_sob[0] = GAUDI2_RESERVED_SOB_NUMBER +
(num_sync_stream_queues * HL_RSVD_SOBS);
prop->first_available_user_mon[0] = GAUDI2_RESERVED_MON_NUMBER +
(num_sync_stream_queues * HL_RSVD_MONS);
prop->first_available_user_interrupt = GAUDI2_IRQ_NUM_USER_FIRST;
prop->tpc_interrupt_id = GAUDI2_IRQ_NUM_TPC_ASSERT;
prop->eq_interrupt_id = GAUDI2_IRQ_NUM_EVENT_QUEUE;
prop->first_available_cq[0] = GAUDI2_RESERVED_CQ_NUMBER;
prop->fw_cpu_boot_dev_sts0_valid = false;
prop->fw_cpu_boot_dev_sts1_valid = false;
prop->hard_reset_done_by_fw = false;
prop->gic_interrupts_enable = true;
prop->server_type = HL_SERVER_TYPE_UNKNOWN;
prop->max_dec = NUMBER_OF_DEC;
prop->clk_pll_index = HL_GAUDI2_MME_PLL;
prop->dma_mask = 64;
prop->hbw_flush_reg = mmPCIE_WRAP_SPECIAL_GLBL_SPARE_0;
return 0;
}
static int gaudi2_pci_bars_map(struct hl_device *hdev)
{
static const char * const name[] = {"CFG_SRAM", "MSIX", "DRAM"};
bool is_wc[3] = {false, false, true};
int rc;
rc = hl_pci_bars_map(hdev, name, is_wc);
if (rc)
return rc;
hdev->rmmio = hdev->pcie_bar[SRAM_CFG_BAR_ID] + (CFG_BASE - STM_FLASH_BASE_ADDR);
return 0;
}
static u64 gaudi2_set_hbm_bar_base(struct hl_device *hdev, u64 addr)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
struct hl_inbound_pci_region pci_region;
u64 old_addr = addr;
int rc;
if ((gaudi2) && (gaudi2->dram_bar_cur_addr == addr))
return old_addr;
if (hdev->asic_prop.iatu_done_by_fw)
return U64_MAX;
pci_region.mode = PCI_BAR_MATCH_MODE;
pci_region.bar = DRAM_BAR_ID;
pci_region.addr = addr;
rc = hl_pci_set_inbound_region(hdev, 2, &pci_region);
if (rc)
return U64_MAX;
if (gaudi2) {
old_addr = gaudi2->dram_bar_cur_addr;
gaudi2->dram_bar_cur_addr = addr;
}
return old_addr;
}
static int gaudi2_init_iatu(struct hl_device *hdev)
{
struct hl_inbound_pci_region inbound_region;
struct hl_outbound_pci_region outbound_region;
u32 bar_addr_low, bar_addr_high;
int rc;
if (hdev->asic_prop.iatu_done_by_fw)
return 0;
inbound_region.mode = PCI_BAR_MATCH_MODE;
inbound_region.bar = SRAM_CFG_BAR_ID;
inbound_region.addr = STM_FLASH_BASE_ADDR - STM_FLASH_ALIGNED_OFF;
rc = hl_pci_set_inbound_region(hdev, 0, &inbound_region);
if (rc)
return rc;
bar_addr_high = RREG32(mmPCIE_DBI_BAR1_REG + STM_FLASH_ALIGNED_OFF);
bar_addr_low = RREG32(mmPCIE_DBI_BAR0_REG + STM_FLASH_ALIGNED_OFF) & ~0xF;
hdev->pcie_bar_phys[SRAM_CFG_BAR_ID] = (u64)bar_addr_high << 32 | bar_addr_low;
inbound_region.mode = PCI_ADDRESS_MATCH_MODE;
inbound_region.bar = SRAM_CFG_BAR_ID;
inbound_region.offset_in_bar = 0;
inbound_region.addr = STM_FLASH_BASE_ADDR;
inbound_region.size = CFG_REGION_SIZE;
rc = hl_pci_set_inbound_region(hdev, 0, &inbound_region);
if (rc)
return rc;
inbound_region.mode = PCI_ADDRESS_MATCH_MODE;
inbound_region.bar = SRAM_CFG_BAR_ID;
inbound_region.offset_in_bar = CFG_REGION_SIZE;
inbound_region.addr = BAR0_RSRVD_BASE_ADDR;
inbound_region.size = BAR0_RSRVD_SIZE + SRAM_SIZE;
rc = hl_pci_set_inbound_region(hdev, 1, &inbound_region);
if (rc)
return rc;
inbound_region.mode = PCI_BAR_MATCH_MODE;
inbound_region.bar = DRAM_BAR_ID;
inbound_region.addr = DRAM_PHYS_BASE;
rc = hl_pci_set_inbound_region(hdev, 2, &inbound_region);
if (rc)
return rc;
outbound_region.addr = HOST_PHYS_BASE_0;
outbound_region.size = HOST_PHYS_SIZE_0;
rc = hl_pci_set_outbound_region(hdev, &outbound_region);
return rc;
}
static enum hl_device_hw_state gaudi2_get_hw_state(struct hl_device *hdev)
{
return RREG32(mmHW_STATE);
}
static int gaudi2_tpc_binning_init_prop(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
if (hweight64(hdev->tpc_binning) > MAX_CLUSTER_BINNING_FAULTY_TPCS) {
dev_err(hdev->dev, "TPC binning is supported for max of %d faulty TPCs, provided mask 0x%llx\n",
MAX_CLUSTER_BINNING_FAULTY_TPCS,
hdev->tpc_binning);
return -EINVAL;
}
prop->tpc_binning_mask = hdev->tpc_binning;
prop->tpc_enabled_mask = GAUDI2_TPC_FULL_MASK;
return 0;
}
static int gaudi2_set_tpc_binning_masks(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
struct hw_queue_properties *q_props = prop->hw_queues_props;
u64 tpc_binning_mask;
u8 subst_idx = 0;
int i, rc;
rc = gaudi2_tpc_binning_init_prop(hdev);
if (rc)
return rc;
tpc_binning_mask = prop->tpc_binning_mask;
for (i = 0 ; i < MAX_FAULTY_TPCS ; i++) {
u8 subst_seq, binned, qid_base;
if (tpc_binning_mask == 0)
break;
if (subst_idx == 0) {
subst_seq = TPC_ID_DCORE0_TPC6;
qid_base = GAUDI2_QUEUE_ID_DCORE0_TPC_6_0;
} else {
subst_seq = TPC_ID_DCORE3_TPC5;
qid_base = GAUDI2_QUEUE_ID_DCORE3_TPC_5_0;
}
binned = __ffs(tpc_binning_mask);
if (binned >= TPC_ID_SIZE) {
dev_err(hdev->dev,
"Invalid binned TPC (binning mask: %llx)\n",
tpc_binning_mask);
return -EINVAL;
}
clear_bit(binned, (unsigned long *)&tpc_binning_mask);
clear_bit(subst_seq, (unsigned long *)&prop->tpc_enabled_mask);
q_props[qid_base].binned = 1;
q_props[qid_base + 1].binned = 1;
q_props[qid_base + 2].binned = 1;
q_props[qid_base + 3].binned = 1;
subst_idx++;
}
return 0;
}
static int gaudi2_set_dec_binning_masks(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
u8 num_faulty;
num_faulty = hweight32(hdev->decoder_binning);
if (num_faulty > MAX_FAULTY_DECODERS) {
dev_err(hdev->dev, "decoder binning is supported for max of single faulty decoder, provided mask 0x%x\n",
hdev->decoder_binning);
return -EINVAL;
}
prop->decoder_binning_mask = (hdev->decoder_binning & GAUDI2_DECODER_FULL_MASK);
if (prop->decoder_binning_mask)
prop->decoder_enabled_mask = (GAUDI2_DECODER_FULL_MASK & ~BIT(DEC_ID_PCIE_VDEC1));
else
prop->decoder_enabled_mask = GAUDI2_DECODER_FULL_MASK;
return 0;
}
static void gaudi2_set_dram_binning_masks(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
if (!hdev->dram_binning) {
prop->dram_binning_mask = 0;
prop->dram_enabled_mask = GAUDI2_DRAM_FULL_MASK;
return;
}
prop->faulty_dram_cluster_map |= hdev->dram_binning;
prop->dram_binning_mask = hdev->dram_binning;
prop->dram_enabled_mask = GAUDI2_DRAM_FULL_MASK & ~BIT(HBM_ID5);
}
static int gaudi2_set_edma_binning_masks(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
struct hw_queue_properties *q_props;
u8 seq, num_faulty;
num_faulty = hweight32(hdev->edma_binning);
if (num_faulty > MAX_FAULTY_EDMAS) {
dev_err(hdev->dev,
"EDMA binning is supported for max of single faulty EDMA, provided mask 0x%x\n",
hdev->edma_binning);
return -EINVAL;
}
if (!hdev->edma_binning) {
prop->edma_binning_mask = 0;
prop->edma_enabled_mask = GAUDI2_EDMA_FULL_MASK;
return 0;
}
seq = __ffs((unsigned long)hdev->edma_binning);
prop->faulty_dram_cluster_map |= BIT(edma_to_hbm_cluster[seq]);
prop->edma_binning_mask = hdev->edma_binning;
prop->edma_enabled_mask = GAUDI2_EDMA_FULL_MASK & ~BIT(EDMA_ID_DCORE3_INSTANCE1);
q_props = prop->hw_queues_props;
q_props[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_0].binned = 1;
q_props[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_1].binned = 1;
q_props[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_2].binned = 1;
q_props[GAUDI2_QUEUE_ID_DCORE3_EDMA_1_3].binned = 1;
return 0;
}
static int gaudi2_set_xbar_edge_enable_mask(struct hl_device *hdev, u32 xbar_edge_iso_mask)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
u8 num_faulty, seq;
if (!xbar_edge_iso_mask) {
prop->xbar_edge_enabled_mask = GAUDI2_XBAR_EDGE_FULL_MASK;
return 0;
}
num_faulty = hweight32(xbar_edge_iso_mask);
if (num_faulty > MAX_FAULTY_XBARS) {
dev_err(hdev->dev, "we cannot have more than %d faulty XBAR EDGE\n",
MAX_FAULTY_XBARS);
return -EINVAL;
}
seq = __ffs((unsigned long)xbar_edge_iso_mask);
prop->faulty_dram_cluster_map |= BIT(xbar_edge_to_hbm_cluster[seq]);
prop->xbar_edge_enabled_mask = (~xbar_edge_iso_mask) & GAUDI2_XBAR_EDGE_FULL_MASK;
return 0;
}
static int gaudi2_set_cluster_binning_masks_common(struct hl_device *hdev, u8 xbar_edge_iso_mask)
{
int rc;
hdev->asic_prop.faulty_dram_cluster_map = 0;
gaudi2_set_dram_binning_masks(hdev);
rc = gaudi2_set_edma_binning_masks(hdev);
if (rc)
return rc;
rc = gaudi2_set_xbar_edge_enable_mask(hdev, xbar_edge_iso_mask);
if (rc)
return rc;
hdev->asic_prop.hmmu_hif_enabled_mask = GAUDI2_HIF_HMMU_FULL_MASK;
return 0;
}
static int gaudi2_set_cluster_binning_masks(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
int rc;
rc = gaudi2_set_cluster_binning_masks_common(hdev, prop->cpucp_info.xbar_binning_mask);
if (rc)
return rc;
if (prop->faulty_dram_cluster_map) {
u8 cluster_seq = __ffs((unsigned long)prop->faulty_dram_cluster_map);
prop->hmmu_hif_enabled_mask = cluster_hmmu_hif_enabled_mask[cluster_seq];
}
return 0;
}
static int gaudi2_set_binning_masks(struct hl_device *hdev)
{
int rc;
rc = gaudi2_set_cluster_binning_masks(hdev);
if (rc)
return rc;
rc = gaudi2_set_tpc_binning_masks(hdev);
if (rc)
return rc;
rc = gaudi2_set_dec_binning_masks(hdev);
if (rc)
return rc;
return 0;
}
static int gaudi2_cpucp_info_get(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
struct asic_fixed_properties *prop = &hdev->asic_prop;
long max_power;
u64 dram_size;
int rc;
if (!(gaudi2->hw_cap_initialized & HW_CAP_CPU_Q))
return 0;
if (hdev->reset_info.in_compute_reset)
return 0;
rc = hl_fw_cpucp_handshake(hdev, mmCPU_BOOT_DEV_STS0, mmCPU_BOOT_DEV_STS1, mmCPU_BOOT_ERR0,
mmCPU_BOOT_ERR1);
if (rc)
return rc;
dram_size = le64_to_cpu(prop->cpucp_info.dram_size);
if (dram_size) {
if ((dram_size != ((GAUDI2_HBM_NUM - 1) * SZ_16G)) &&
(dram_size != (GAUDI2_HBM_NUM * SZ_16G))) {
dev_err(hdev->dev,
"F/W reported invalid DRAM size %llu. Trying to use default size %llu\n",
dram_size, prop->dram_size);
dram_size = prop->dram_size;
}
prop->dram_size = dram_size;
prop->dram_end_address = prop->dram_base_address + dram_size;
}
if (!strlen(prop->cpucp_info.card_name))
strncpy(prop->cpucp_info.card_name, GAUDI2_DEFAULT_CARD_NAME, CARD_NAME_MAX_LEN);
hdev->dram_binning = prop->cpucp_info.dram_binning_mask;
hdev->edma_binning = prop->cpucp_info.edma_binning_mask;
hdev->tpc_binning = le64_to_cpu(prop->cpucp_info.tpc_binning_mask);
hdev->decoder_binning = lower_32_bits(le64_to_cpu(prop->cpucp_info.decoder_binning_mask));
dev_dbg(hdev->dev, "Read binning masks: tpc: 0x%llx, dram: 0x%llx, edma: 0x%x, dec: 0x%x\n",
hdev->tpc_binning, hdev->dram_binning, hdev->edma_binning,
hdev->decoder_binning);
rc = hdev->asic_funcs->set_dram_properties(hdev);
if (rc)
return rc;
rc = hdev->asic_funcs->set_binning_masks(hdev);
if (rc)
return rc;
max_power = hl_fw_get_max_power(hdev);
if (max_power < 0)
return max_power;
prop->max_power_default = (u64) max_power;
return 0;
}
static int gaudi2_fetch_psoc_frequency(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u16 pll_freq_arr[HL_PLL_NUM_OUTPUTS];
int rc;
if (!(gaudi2->hw_cap_initialized & HW_CAP_CPU_Q))
return 0;
rc = hl_fw_cpucp_pll_info_get(hdev, HL_GAUDI2_CPU_PLL, pll_freq_arr);
if (rc)
return rc;
hdev->asic_prop.psoc_timestamp_frequency = pll_freq_arr[3];
return 0;
}
static int gaudi2_early_init(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
struct pci_dev *pdev = hdev->pdev;
resource_size_t pci_bar_size;
int rc;
rc = gaudi2_set_fixed_properties(hdev);
if (rc)
return rc;
pci_bar_size = pci_resource_len(pdev, SRAM_CFG_BAR_ID);
if (pci_bar_size != CFG_BAR_SIZE) {
dev_err(hdev->dev, "Not " HL_NAME "? BAR %d size %pa, expecting %llu\n",
SRAM_CFG_BAR_ID, &pci_bar_size, CFG_BAR_SIZE);
rc = -ENODEV;
goto free_queue_props;
}
pci_bar_size = pci_resource_len(pdev, MSIX_BAR_ID);
if (pci_bar_size != MSIX_BAR_SIZE) {
dev_err(hdev->dev, "Not " HL_NAME "? BAR %d size %pa, expecting %llu\n",
MSIX_BAR_ID, &pci_bar_size, MSIX_BAR_SIZE);
rc = -ENODEV;
goto free_queue_props;
}
prop->dram_pci_bar_size = pci_resource_len(pdev, DRAM_BAR_ID);
hdev->dram_pci_bar_start = pci_resource_start(pdev, DRAM_BAR_ID);
if (hdev->pldm)
hdev->asic_prop.iatu_done_by_fw = false;
else
hdev->asic_prop.iatu_done_by_fw = true;
rc = hl_pci_init(hdev);
if (rc)
goto free_queue_props;
rc = hl_fw_read_preboot_status(hdev);
if (rc) {
if (hdev->reset_on_preboot_fail)
hdev->asic_funcs->hw_fini(hdev, true, false);
goto pci_fini;
}
if (gaudi2_get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
dev_dbg(hdev->dev, "H/W state is dirty, must reset before initializing\n");
rc = hdev->asic_funcs->hw_fini(hdev, true, false);
if (rc) {
dev_err(hdev->dev, "failed to reset HW in dirty state (%d)\n", rc);
goto pci_fini;
}
}
return 0;
pci_fini:
hl_pci_fini(hdev);
free_queue_props:
kfree(hdev->asic_prop.hw_queues_props);
return rc;
}
static int gaudi2_early_fini(struct hl_device *hdev)
{
kfree(hdev->asic_prop.hw_queues_props);
hl_pci_fini(hdev);
return 0;
}
static bool gaudi2_is_arc_nic_owned(u64 arc_id)
{
switch (arc_id) {
case CPU_ID_NIC_QMAN_ARC0...CPU_ID_NIC_QMAN_ARC23:
return true;
default:
return false;
}
}
static bool gaudi2_is_arc_tpc_owned(u64 arc_id)
{
switch (arc_id) {
case CPU_ID_TPC_QMAN_ARC0...CPU_ID_TPC_QMAN_ARC24:
return true;
default:
return false;
}
}
static void gaudi2_init_arcs(struct hl_device *hdev)
{
struct cpu_dyn_regs *dyn_regs = &hdev->fw_loader.dynamic_loader.comm_desc.cpu_dyn_regs;
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u64 arc_id;
u32 i;
for (i = CPU_ID_SCHED_ARC0 ; i <= CPU_ID_SCHED_ARC3 ; i++) {
if (gaudi2_is_arc_enabled(hdev, i))
continue;
gaudi2_set_arc_id_cap(hdev, i);
}
for (i = GAUDI2_QUEUE_ID_PDMA_0_0 ; i < GAUDI2_QUEUE_ID_CPU_PQ ; i += 4) {
if (!gaudi2_is_queue_enabled(hdev, i))
continue;
arc_id = gaudi2_queue_id_to_arc_id[i];
if (gaudi2_is_arc_enabled(hdev, arc_id))
continue;
if (gaudi2_is_arc_nic_owned(arc_id) &&
!(hdev->nic_ports_mask & BIT_ULL(arc_id - CPU_ID_NIC_QMAN_ARC0)))
continue;
if (gaudi2_is_arc_tpc_owned(arc_id) && !(gaudi2->tpc_hw_cap_initialized &
BIT_ULL(arc_id - CPU_ID_TPC_QMAN_ARC0)))
continue;
gaudi2_set_arc_id_cap(hdev, arc_id);
}
hdev->asic_prop.engine_core_interrupt_reg_addr =
CFG_BASE + le32_to_cpu(dyn_regs->eng_arc_irq_ctrl);
}
static int gaudi2_scrub_arc_dccm(struct hl_device *hdev, u32 cpu_id)
{
u32 reg_base, reg_val;
int rc;
switch (cpu_id) {
case CPU_ID_SCHED_ARC0 ... CPU_ID_SCHED_ARC3:
rc = gaudi2_send_job_to_kdma(hdev, 0, CFG_BASE + gaudi2_arc_dccm_bases[cpu_id],
ARC_DCCM_BLOCK_SIZE * 2, true);
if (rc)
return rc;
break;
case CPU_ID_SCHED_ARC4:
case CPU_ID_SCHED_ARC5:
case CPU_ID_MME_QMAN_ARC0:
case CPU_ID_MME_QMAN_ARC1:
reg_base = gaudi2_arc_blocks_bases[cpu_id];
rc = gaudi2_send_job_to_kdma(hdev, 0, CFG_BASE + gaudi2_arc_dccm_bases[cpu_id],
ARC_DCCM_BLOCK_SIZE, true);
if (rc)
return rc;
reg_val = FIELD_PREP(ARC_FARM_ARC0_AUX_MME_ARC_UPPER_DCCM_EN_VAL_MASK, 1);
WREG32(reg_base + ARC_DCCM_UPPER_EN_OFFSET, reg_val);
rc = gaudi2_send_job_to_kdma(hdev, 0, CFG_BASE + gaudi2_arc_dccm_bases[cpu_id],
ARC_DCCM_BLOCK_SIZE, true);
if (rc)
return rc;
reg_val = FIELD_PREP(ARC_FARM_ARC0_AUX_MME_ARC_UPPER_DCCM_EN_VAL_MASK, 0);
WREG32(reg_base + ARC_DCCM_UPPER_EN_OFFSET, reg_val);
break;
default:
rc = gaudi2_send_job_to_kdma(hdev, 0, CFG_BASE + gaudi2_arc_dccm_bases[cpu_id],
ARC_DCCM_BLOCK_SIZE, true);
if (rc)
return rc;
}
return 0;
}
static int gaudi2_scrub_arcs_dccm(struct hl_device *hdev)
{
u16 arc_id;
int rc;
for (arc_id = CPU_ID_SCHED_ARC0 ; arc_id < CPU_ID_MAX ; arc_id++) {
if (!gaudi2_is_arc_enabled(hdev, arc_id))
continue;
rc = gaudi2_scrub_arc_dccm(hdev, arc_id);
if (rc)
return rc;
}
return 0;
}
static int gaudi2_late_init(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
int rc;
hdev->asic_prop.supports_advanced_cpucp_rc = true;
rc = hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_ENABLE_PCI_ACCESS,
gaudi2->virt_msix_db_dma_addr);
if (rc) {
dev_err(hdev->dev, "Failed to enable PCI access from CPU\n");
return rc;
}
rc = gaudi2_fetch_psoc_frequency(hdev);
if (rc) {
dev_err(hdev->dev, "Failed to fetch psoc frequency\n");
goto disable_pci_access;
}
gaudi2_init_arcs(hdev);
rc = gaudi2_scrub_arcs_dccm(hdev);
if (rc) {
dev_err(hdev->dev, "Failed to scrub arcs DCCM\n");
goto disable_pci_access;
}
gaudi2_init_security(hdev);
return 0;
disable_pci_access:
hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS, 0x0);
return rc;
}
static void gaudi2_late_fini(struct hl_device *hdev)
{
hl_hwmon_release_resources(hdev);
}
static void gaudi2_user_mapped_dec_init(struct gaudi2_device *gaudi2, u32 start_idx)
{
struct user_mapped_block *blocks = gaudi2->mapped_blocks;
HL_USR_MAPPED_BLK_INIT(&blocks[start_idx++], mmDCORE0_DEC0_CMD_BASE, HL_BLOCK_SIZE);
HL_USR_MAPPED_BLK_INIT(&blocks[start_idx++], mmDCORE0_DEC1_CMD_BASE, HL_BLOCK_SIZE);
HL_USR_MAPPED_BLK_INIT(&blocks[start_idx++], mmDCORE1_DEC0_CMD_BASE, HL_BLOCK_SIZE);
HL_USR_MAPPED_BLK_INIT(&blocks[start_idx++], mmDCORE1_DEC1_CMD_BASE, HL_BLOCK_SIZE);
HL_USR_MAPPED_BLK_INIT(&blocks[start_idx++], mmDCORE2_DEC0_CMD_BASE, HL_BLOCK_SIZE);
HL_USR_MAPPED_BLK_INIT(&blocks[start_idx++], mmDCORE2_DEC1_CMD_BASE, HL_BLOCK_SIZE);
HL_USR_MAPPED_BLK_INIT(&blocks[start_idx++], mmDCORE3_DEC0_CMD_BASE, HL_BLOCK_SIZE);
HL_USR_MAPPED_BLK_INIT(&blocks[start_idx++], mmDCORE3_DEC1_CMD_BASE, HL_BLOCK_SIZE);
HL_USR_MAPPED_BLK_INIT(&blocks[start_idx++], mmPCIE_DEC0_CMD_BASE, HL_BLOCK_SIZE);
HL_USR_MAPPED_BLK_INIT(&blocks[start_idx], mmPCIE_DEC1_CMD_BASE, HL_BLOCK_SIZE);
}
static void gaudi2_user_mapped_blocks_init(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
struct user_mapped_block *blocks = gaudi2->mapped_blocks;
u32 block_size, umr_start_idx, num_umr_blocks;
int i;
for (i = 0 ; i < NUM_ARC_CPUS ; i++) {
if (i >= CPU_ID_SCHED_ARC0 && i <= CPU_ID_SCHED_ARC3)
block_size = ARC_DCCM_BLOCK_SIZE * 2;
else
block_size = ARC_DCCM_BLOCK_SIZE;
blocks[i].address = gaudi2_arc_dccm_bases[i];
blocks[i].size = block_size;
}
blocks[NUM_ARC_CPUS].address = mmARC_FARM_ARC0_ACP_ENG_BASE;
blocks[NUM_ARC_CPUS].size = HL_BLOCK_SIZE;
blocks[NUM_ARC_CPUS + 1].address = mmARC_FARM_ARC1_ACP_ENG_BASE;
blocks[NUM_ARC_CPUS + 1].size = HL_BLOCK_SIZE;
blocks[NUM_ARC_CPUS + 2].address = mmARC_FARM_ARC2_ACP_ENG_BASE;
blocks[NUM_ARC_CPUS + 2].size = HL_BLOCK_SIZE;
blocks[NUM_ARC_CPUS + 3].address = mmARC_FARM_ARC3_ACP_ENG_BASE;
blocks[NUM_ARC_CPUS + 3].size = HL_BLOCK_SIZE;
blocks[NUM_ARC_CPUS + 4].address = mmDCORE0_MME_QM_ARC_ACP_ENG_BASE;
blocks[NUM_ARC_CPUS + 4].size = HL_BLOCK_SIZE;
blocks[NUM_ARC_CPUS + 5].address = mmDCORE1_MME_QM_ARC_ACP_ENG_BASE;
blocks[NUM_ARC_CPUS + 5].size = HL_BLOCK_SIZE;
blocks[NUM_ARC_CPUS + 6].address = mmDCORE2_MME_QM_ARC_ACP_ENG_BASE;
blocks[NUM_ARC_CPUS + 6].size = HL_BLOCK_SIZE;
blocks[NUM_ARC_CPUS + 7].address = mmDCORE3_MME_QM_ARC_ACP_ENG_BASE;
blocks[NUM_ARC_CPUS + 7].size = HL_BLOCK_SIZE;
umr_start_idx = NUM_ARC_CPUS + NUM_OF_USER_ACP_BLOCKS;
num_umr_blocks = NIC_NUMBER_OF_ENGINES * NUM_OF_USER_NIC_UMR_BLOCKS;
for (i = 0 ; i < num_umr_blocks ; i++) {
u8 nic_id, umr_block_id;
nic_id = i / NUM_OF_USER_NIC_UMR_BLOCKS;
umr_block_id = i % NUM_OF_USER_NIC_UMR_BLOCKS;
blocks[umr_start_idx + i].address =
mmNIC0_UMR0_0_UNSECURE_DOORBELL0_BASE +
(nic_id / NIC_NUMBER_OF_QM_PER_MACRO) * NIC_OFFSET +
(nic_id % NIC_NUMBER_OF_QM_PER_MACRO) * NIC_QM_OFFSET +
umr_block_id * NIC_UMR_OFFSET;
blocks[umr_start_idx + i].size = HL_BLOCK_SIZE;
}
gaudi2_user_mapped_dec_init(gaudi2, USR_MAPPED_BLK_DEC_START_IDX);
for (i = 1; i < NUM_OF_DCORES; ++i) {
blocks[USR_MAPPED_BLK_SM_START_IDX + 2 * (i - 1)].size = SM_OBJS_BLOCK_SIZE;
blocks[USR_MAPPED_BLK_SM_START_IDX + 2 * (i - 1) + 1].size = HL_BLOCK_SIZE;
blocks[USR_MAPPED_BLK_SM_START_IDX + 2 * (i - 1)].address =
mmDCORE0_SYNC_MNGR_OBJS_BASE + i * DCORE_OFFSET;
blocks[USR_MAPPED_BLK_SM_START_IDX + 2 * (i - 1) + 1].address =
mmDCORE0_SYNC_MNGR_GLBL_BASE + i * DCORE_OFFSET;
}
}
static int gaudi2_alloc_cpu_accessible_dma_mem(struct hl_device *hdev)
{
dma_addr_t dma_addr_arr[GAUDI2_ALLOC_CPU_MEM_RETRY_CNT] = {}, end_addr;
void *virt_addr_arr[GAUDI2_ALLOC_CPU_MEM_RETRY_CNT] = {};
int i, j, rc = 0;
for (i = 0 ; i < GAUDI2_ALLOC_CPU_MEM_RETRY_CNT ; i++) {
virt_addr_arr[i] = hl_asic_dma_alloc_coherent(hdev, HL_CPU_ACCESSIBLE_MEM_SIZE,
&dma_addr_arr[i], GFP_KERNEL | __GFP_ZERO);
if (!virt_addr_arr[i]) {
rc = -ENOMEM;
goto free_dma_mem_arr;
}
end_addr = dma_addr_arr[i] + HL_CPU_ACCESSIBLE_MEM_SIZE - 1;
if (GAUDI2_ARC_PCI_MSB_ADDR(dma_addr_arr[i]) == GAUDI2_ARC_PCI_MSB_ADDR(end_addr))
break;
}
if (i == GAUDI2_ALLOC_CPU_MEM_RETRY_CNT) {
dev_err(hdev->dev,
"MSB of ARC accessible DMA memory are not identical in all range\n");
rc = -EFAULT;
goto free_dma_mem_arr;
}
hdev->cpu_accessible_dma_mem = virt_addr_arr[i];
hdev->cpu_accessible_dma_address = dma_addr_arr[i];
free_dma_mem_arr:
for (j = 0 ; j < i ; j++)
hl_asic_dma_free_coherent(hdev, HL_CPU_ACCESSIBLE_MEM_SIZE, virt_addr_arr[j],
dma_addr_arr[j]);
return rc;
}
static void gaudi2_set_pci_memory_regions(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
struct pci_mem_region *region;
region = &hdev->pci_mem_region[PCI_REGION_CFG];
region->region_base = CFG_BASE;
region->region_size = CFG_SIZE;
region->offset_in_bar = CFG_BASE - STM_FLASH_BASE_ADDR;
region->bar_size = CFG_BAR_SIZE;
region->bar_id = SRAM_CFG_BAR_ID;
region->used = 1;
region = &hdev->pci_mem_region[PCI_REGION_SRAM];
region->region_base = SRAM_BASE_ADDR;
region->region_size = SRAM_SIZE;
region->offset_in_bar = CFG_REGION_SIZE + BAR0_RSRVD_SIZE;
region->bar_size = CFG_BAR_SIZE;
region->bar_id = SRAM_CFG_BAR_ID;
region->used = 1;
region = &hdev->pci_mem_region[PCI_REGION_DRAM];
region->region_base = DRAM_PHYS_BASE;
region->region_size = hdev->asic_prop.dram_size;
region->offset_in_bar = 0;
region->bar_size = prop->dram_pci_bar_size;
region->bar_id = DRAM_BAR_ID;
region->used = 1;
}
static void gaudi2_user_interrupt_setup(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
int i, j, k;
HL_USR_INTR_STRUCT_INIT(hdev->tpc_interrupt, hdev, 0, HL_USR_INTERRUPT_TPC);
HL_USR_INTR_STRUCT_INIT(hdev->unexpected_error_interrupt, hdev, 0,
HL_USR_INTERRUPT_UNEXPECTED);
HL_USR_INTR_STRUCT_INIT(hdev->common_user_cq_interrupt, hdev,
HL_COMMON_USER_CQ_INTERRUPT_ID, HL_USR_INTERRUPT_CQ);
HL_USR_INTR_STRUCT_INIT(hdev->common_decoder_interrupt, hdev,
HL_COMMON_DEC_INTERRUPT_ID, HL_USR_INTERRUPT_DECODER);
for (i = GAUDI2_IRQ_NUM_DCORE0_DEC0_NRM, j = 0 ; i <= GAUDI2_IRQ_NUM_SHARED_DEC1_NRM;
i += 2, j++)
HL_USR_INTR_STRUCT_INIT(hdev->user_interrupt[j], hdev, i,
HL_USR_INTERRUPT_DECODER);
for (i = GAUDI2_IRQ_NUM_USER_FIRST, k = 0 ; k < prop->user_interrupt_count; i++, j++, k++)
HL_USR_INTR_STRUCT_INIT(hdev->user_interrupt[j], hdev, i, HL_USR_INTERRUPT_CQ);
}
static inline int gaudi2_get_non_zero_random_int(void)
{
int rand = get_random_u32();
return rand ? rand : 1;
}
static void gaudi2_special_blocks_free(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
struct hl_skip_blocks_cfg *skip_special_blocks_cfg =
&prop->skip_special_blocks_cfg;
kfree(prop->special_blocks);
kfree(skip_special_blocks_cfg->block_types);
kfree(skip_special_blocks_cfg->block_ranges);
}
static void gaudi2_special_blocks_iterator_free(struct hl_device *hdev)
{
gaudi2_special_blocks_free(hdev);
}
static bool gaudi2_special_block_skip(struct hl_device *hdev,
struct hl_special_blocks_cfg *special_blocks_cfg,
u32 blk_idx, u32 major, u32 minor, u32 sub_minor)
{
return false;
}
static int gaudi2_special_blocks_config(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
int i, rc;
prop->glbl_err_cause_num = GAUDI2_NUM_OF_GLBL_ERR_CAUSE;
prop->num_of_special_blocks = ARRAY_SIZE(gaudi2_special_blocks);
prop->special_blocks = kmalloc_array(prop->num_of_special_blocks,
sizeof(*prop->special_blocks), GFP_KERNEL);
if (!prop->special_blocks)
return -ENOMEM;
for (i = 0 ; i < prop->num_of_special_blocks ; i++)
memcpy(&prop->special_blocks[i], &gaudi2_special_blocks[i],
sizeof(*prop->special_blocks));
memset(&prop->skip_special_blocks_cfg, 0, sizeof(prop->skip_special_blocks_cfg));
prop->skip_special_blocks_cfg.skip_block_hook = gaudi2_special_block_skip;
if (ARRAY_SIZE(gaudi2_iterator_skip_block_types)) {
prop->skip_special_blocks_cfg.block_types =
kmalloc_array(ARRAY_SIZE(gaudi2_iterator_skip_block_types),
sizeof(gaudi2_iterator_skip_block_types[0]), GFP_KERNEL);
if (!prop->skip_special_blocks_cfg.block_types) {
rc = -ENOMEM;
goto free_special_blocks;
}
memcpy(prop->skip_special_blocks_cfg.block_types, gaudi2_iterator_skip_block_types,
sizeof(gaudi2_iterator_skip_block_types));
prop->skip_special_blocks_cfg.block_types_len =
ARRAY_SIZE(gaudi2_iterator_skip_block_types);
}
if (ARRAY_SIZE(gaudi2_iterator_skip_block_ranges)) {
prop->skip_special_blocks_cfg.block_ranges =
kmalloc_array(ARRAY_SIZE(gaudi2_iterator_skip_block_ranges),
sizeof(gaudi2_iterator_skip_block_ranges[0]), GFP_KERNEL);
if (!prop->skip_special_blocks_cfg.block_ranges) {
rc = -ENOMEM;
goto free_skip_special_blocks_types;
}
for (i = 0 ; i < ARRAY_SIZE(gaudi2_iterator_skip_block_ranges) ; i++)
memcpy(&prop->skip_special_blocks_cfg.block_ranges[i],
&gaudi2_iterator_skip_block_ranges[i],
sizeof(struct range));
prop->skip_special_blocks_cfg.block_ranges_len =
ARRAY_SIZE(gaudi2_iterator_skip_block_ranges);
}
return 0;
free_skip_special_blocks_types:
kfree(prop->skip_special_blocks_cfg.block_types);
free_special_blocks:
kfree(prop->special_blocks);
return rc;
}
static int gaudi2_special_blocks_iterator_config(struct hl_device *hdev)
{
return gaudi2_special_blocks_config(hdev);
}
static void gaudi2_test_queues_msgs_free(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
struct gaudi2_queues_test_info *msg_info = gaudi2->queues_test_info;
int i;
for (i = 0 ; i < GAUDI2_NUM_TESTED_QS ; i++) {
if (!msg_info[i].kern_addr)
break;
hl_asic_dma_pool_free(hdev, msg_info[i].kern_addr, msg_info[i].dma_addr);
msg_info[i].kern_addr = NULL;
}
}
static int gaudi2_test_queues_msgs_alloc(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
struct gaudi2_queues_test_info *msg_info = gaudi2->queues_test_info;
int i, rc;
for (i = 0 ; i < GAUDI2_NUM_TESTED_QS ; i++) {
msg_info[i].kern_addr =
(void *)hl_asic_dma_pool_zalloc(hdev, sizeof(struct packet_msg_short),
GFP_KERNEL, &msg_info[i].dma_addr);
if (!msg_info[i].kern_addr) {
dev_err(hdev->dev,
"Failed to allocate dma memory for H/W queue %d testing\n", i);
rc = -ENOMEM;
goto err_exit;
}
}
return 0;
err_exit:
gaudi2_test_queues_msgs_free(hdev);
return rc;
}
static int gaudi2_sw_init(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
struct gaudi2_device *gaudi2;
int i, rc;
gaudi2 = kzalloc(sizeof(*gaudi2), GFP_KERNEL);
if (!gaudi2)
return -ENOMEM;
for (i = 0 ; i < ARRAY_SIZE(gaudi2_irq_map_table) ; i++) {
if (gaudi2_irq_map_table[i].msg || !gaudi2_irq_map_table[i].valid)
continue;
if (gaudi2->num_of_valid_hw_events == GAUDI2_EVENT_SIZE) {
dev_err(hdev->dev, "H/W events array exceeds the limit of %u events\n",
GAUDI2_EVENT_SIZE);
rc = -EINVAL;
goto free_gaudi2_device;
}
gaudi2->hw_events[gaudi2->num_of_valid_hw_events++] = gaudi2_irq_map_table[i].fc_id;
}
for (i = 0 ; i < MME_NUM_OF_LFSR_SEEDS ; i++)
gaudi2->lfsr_rand_seeds[i] = gaudi2_get_non_zero_random_int();
gaudi2->cpucp_info_get = gaudi2_cpucp_info_get;
hdev->asic_specific = gaudi2;
hdev->dma_pool = dma_pool_create(dev_name(hdev->dev), &hdev->pdev->dev,
GAUDI2_DMA_POOL_BLK_SIZE, DEVICE_CACHE_LINE_SIZE, 0);
if (!hdev->dma_pool) {
dev_err(hdev->dev, "failed to create DMA pool\n");
rc = -ENOMEM;
goto free_gaudi2_device;
}
rc = gaudi2_alloc_cpu_accessible_dma_mem(hdev);
if (rc)
goto free_dma_pool;
hdev->cpu_accessible_dma_pool = gen_pool_create(ilog2(32), -1);
if (!hdev->cpu_accessible_dma_pool) {
dev_err(hdev->dev, "Failed to create CPU accessible DMA pool\n");
rc = -ENOMEM;
goto free_cpu_dma_mem;
}
rc = gen_pool_add(hdev->cpu_accessible_dma_pool, (uintptr_t) hdev->cpu_accessible_dma_mem,
HL_CPU_ACCESSIBLE_MEM_SIZE, -1);
if (rc) {
dev_err(hdev->dev, "Failed to add memory to CPU accessible DMA pool\n");
rc = -EFAULT;
goto free_cpu_accessible_dma_pool;
}
gaudi2->virt_msix_db_cpu_addr = hl_cpu_accessible_dma_pool_alloc(hdev, prop->pmmu.page_size,
&gaudi2->virt_msix_db_dma_addr);
if (!gaudi2->virt_msix_db_cpu_addr) {
dev_err(hdev->dev, "Failed to allocate DMA memory for virtual MSI-X doorbell\n");
rc = -ENOMEM;
goto free_cpu_accessible_dma_pool;
}
spin_lock_init(&gaudi2->hw_queues_lock);
gaudi2->scratchpad_kernel_address = hl_asic_dma_alloc_coherent(hdev, PAGE_SIZE,
&gaudi2->scratchpad_bus_address,
GFP_KERNEL | __GFP_ZERO);
if (!gaudi2->scratchpad_kernel_address) {
rc = -ENOMEM;
goto free_virt_msix_db_mem;
}
gaudi2_user_mapped_blocks_init(hdev);
gaudi2_user_interrupt_setup(hdev);
hdev->supports_coresight = true;
hdev->supports_sync_stream = true;
hdev->supports_cb_mapping = true;
hdev->supports_wait_for_multi_cs = false;
prop->supports_compute_reset = true;
if (hl_is_fw_sw_ver_below(hdev, 1, 11))
hdev->event_queue.check_eqe_index = false;
else
hdev->event_queue.check_eqe_index = true;
hdev->asic_funcs->set_pci_memory_regions(hdev);
rc = gaudi2_special_blocks_iterator_config(hdev);
if (rc)
goto free_scratchpad_mem;
rc = gaudi2_test_queues_msgs_alloc(hdev);
if (rc)
goto special_blocks_free;
return 0;
special_blocks_free:
gaudi2_special_blocks_iterator_free(hdev);
free_scratchpad_mem:
hl_asic_dma_free_coherent(hdev, PAGE_SIZE, gaudi2->scratchpad_kernel_address,
gaudi2->scratchpad_bus_address);
free_virt_msix_db_mem:
hl_cpu_accessible_dma_pool_free(hdev, prop->pmmu.page_size, gaudi2->virt_msix_db_cpu_addr);
free_cpu_accessible_dma_pool:
gen_pool_destroy(hdev->cpu_accessible_dma_pool);
free_cpu_dma_mem:
hl_asic_dma_free_coherent(hdev, HL_CPU_ACCESSIBLE_MEM_SIZE, hdev->cpu_accessible_dma_mem,
hdev->cpu_accessible_dma_address);
free_dma_pool:
dma_pool_destroy(hdev->dma_pool);
free_gaudi2_device:
kfree(gaudi2);
return rc;
}
static int gaudi2_sw_fini(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
struct gaudi2_device *gaudi2 = hdev->asic_specific;
gaudi2_test_queues_msgs_free(hdev);
gaudi2_special_blocks_iterator_free(hdev);
hl_cpu_accessible_dma_pool_free(hdev, prop->pmmu.page_size, gaudi2->virt_msix_db_cpu_addr);
gen_pool_destroy(hdev->cpu_accessible_dma_pool);
hl_asic_dma_free_coherent(hdev, HL_CPU_ACCESSIBLE_MEM_SIZE, hdev->cpu_accessible_dma_mem,
hdev->cpu_accessible_dma_address);
hl_asic_dma_free_coherent(hdev, PAGE_SIZE, gaudi2->scratchpad_kernel_address,
gaudi2->scratchpad_bus_address);
dma_pool_destroy(hdev->dma_pool);
kfree(gaudi2);
return 0;
}
static void gaudi2_stop_qman_common(struct hl_device *hdev, u32 reg_base)
{
WREG32(reg_base + QM_GLBL_CFG1_OFFSET, QM_GLBL_CFG1_PQF_STOP |
QM_GLBL_CFG1_CQF_STOP |
QM_GLBL_CFG1_CP_STOP);
WREG32(reg_base + QM_GLBL_CFG2_OFFSET, QM_GLBL_CFG2_ARC_CQF_STOP);
}
static void gaudi2_flush_qman_common(struct hl_device *hdev, u32 reg_base)
{
WREG32(reg_base + QM_GLBL_CFG1_OFFSET, QM_GLBL_CFG1_PQF_FLUSH |
QM_GLBL_CFG1_CQF_FLUSH |
QM_GLBL_CFG1_CP_FLUSH);
}
static void gaudi2_flush_qman_arc_common(struct hl_device *hdev, u32 reg_base)
{
WREG32(reg_base + QM_GLBL_CFG2_OFFSET, QM_GLBL_CFG2_ARC_CQF_FLUSH);
}
static void gaudi2_clear_qm_fence_counters_common(struct hl_device *hdev, u32 queue_id,
bool skip_fence)
{
u32 size, reg_base;
u32 addr, val;
reg_base = gaudi2_qm_blocks_bases[queue_id];
addr = reg_base + QM_CP_FENCE0_CNT_0_OFFSET;
size = mmPDMA0_QM_CP_BARRIER_CFG - mmPDMA0_QM_CP_FENCE0_CNT_0;
val = skip_fence ? U32_MAX : 0;
gaudi2_memset_device_lbw(hdev, addr, size, val);
}
static void gaudi2_qman_manual_flush_common(struct hl_device *hdev, u32 queue_id)
{
u32 reg_base = gaudi2_qm_blocks_bases[queue_id];
gaudi2_clear_qm_fence_counters_common(hdev, queue_id, true);
gaudi2_flush_qman_common(hdev, reg_base);
gaudi2_flush_qman_arc_common(hdev, reg_base);
}
static void gaudi2_stop_dma_qmans(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
int dcore, inst;
if (!(gaudi2->hw_cap_initialized & HW_CAP_PDMA_MASK))
goto stop_edma_qmans;
gaudi2_stop_qman_common(hdev, mmPDMA0_QM_BASE);
gaudi2_stop_qman_common(hdev, mmPDMA1_QM_BASE);
stop_edma_qmans:
if (!(gaudi2->hw_cap_initialized & HW_CAP_EDMA_MASK))
return;
for (dcore = 0 ; dcore < NUM_OF_DCORES ; dcore++) {
for (inst = 0 ; inst < NUM_OF_EDMA_PER_DCORE ; inst++) {
u8 seq = dcore * NUM_OF_EDMA_PER_DCORE + inst;
u32 qm_base;
if (!(gaudi2->hw_cap_initialized & BIT_ULL(HW_CAP_EDMA_SHIFT + seq)))
continue;
qm_base = mmDCORE0_EDMA0_QM_BASE + dcore * DCORE_OFFSET +
inst * DCORE_EDMA_OFFSET;
gaudi2_stop_qman_common(hdev, qm_base);
}
}
}
static void gaudi2_stop_mme_qmans(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 offset, i;
offset = mmDCORE1_MME_QM_BASE - mmDCORE0_MME_QM_BASE;
for (i = 0 ; i < NUM_OF_DCORES ; i++) {
if (!(gaudi2->hw_cap_initialized & BIT_ULL(HW_CAP_MME_SHIFT + i)))
continue;
gaudi2_stop_qman_common(hdev, mmDCORE0_MME_QM_BASE + (i * offset));
}
}
static void gaudi2_stop_tpc_qmans(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 reg_base;
int i;
if (!(gaudi2->tpc_hw_cap_initialized & HW_CAP_TPC_MASK))
return;
for (i = 0 ; i < TPC_ID_SIZE ; i++) {
if (!(gaudi2->tpc_hw_cap_initialized & BIT_ULL(HW_CAP_TPC_SHIFT + i)))
continue;
reg_base = gaudi2_qm_blocks_bases[gaudi2_tpc_id_to_queue_id[i]];
gaudi2_stop_qman_common(hdev, reg_base);
}
}
static void gaudi2_stop_rot_qmans(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 reg_base;
int i;
if (!(gaudi2->hw_cap_initialized & HW_CAP_ROT_MASK))
return;
for (i = 0 ; i < ROTATOR_ID_SIZE ; i++) {
if (!(gaudi2->hw_cap_initialized & BIT_ULL(HW_CAP_ROT_SHIFT + i)))
continue;
reg_base = gaudi2_qm_blocks_bases[gaudi2_rot_id_to_queue_id[i]];
gaudi2_stop_qman_common(hdev, reg_base);
}
}
static void gaudi2_stop_nic_qmans(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 reg_base, queue_id;
int i;
if (!(gaudi2->nic_hw_cap_initialized & HW_CAP_NIC_MASK))
return;
queue_id = GAUDI2_QUEUE_ID_NIC_0_0;
for (i = 0 ; i < NIC_NUMBER_OF_ENGINES ; i++, queue_id += NUM_OF_PQ_PER_QMAN) {
if (!(hdev->nic_ports_mask & BIT(i)))
continue;
reg_base = gaudi2_qm_blocks_bases[queue_id];
gaudi2_stop_qman_common(hdev, reg_base);
}
}
static void gaudi2_stall_dma_common(struct hl_device *hdev, u32 reg_base)
{
u32 reg_val;
reg_val = FIELD_PREP(PDMA0_CORE_CFG_1_HALT_MASK, 0x1);
WREG32(reg_base + DMA_CORE_CFG_1_OFFSET, reg_val);
}
static void gaudi2_dma_stall(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
int dcore, inst;
if (!(gaudi2->hw_cap_initialized & HW_CAP_PDMA_MASK))
goto stall_edma;
gaudi2_stall_dma_common(hdev, mmPDMA0_CORE_BASE);
gaudi2_stall_dma_common(hdev, mmPDMA1_CORE_BASE);
stall_edma:
if (!(gaudi2->hw_cap_initialized & HW_CAP_EDMA_MASK))
return;
for (dcore = 0 ; dcore < NUM_OF_DCORES ; dcore++) {
for (inst = 0 ; inst < NUM_OF_EDMA_PER_DCORE ; inst++) {
u8 seq = dcore * NUM_OF_EDMA_PER_DCORE + inst;
u32 core_base;
if (!(gaudi2->hw_cap_initialized & BIT_ULL(HW_CAP_EDMA_SHIFT + seq)))
continue;
core_base = mmDCORE0_EDMA0_CORE_BASE + dcore * DCORE_OFFSET +
inst * DCORE_EDMA_OFFSET;
gaudi2_stall_dma_common(hdev, core_base);
}
}
}
static void gaudi2_mme_stall(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 offset, i;
offset = mmDCORE1_MME_CTRL_LO_QM_STALL - mmDCORE0_MME_CTRL_LO_QM_STALL;
for (i = 0 ; i < NUM_OF_DCORES ; i++)
if (gaudi2->hw_cap_initialized & BIT_ULL(HW_CAP_MME_SHIFT + i))
WREG32(mmDCORE0_MME_CTRL_LO_QM_STALL + (i * offset), 1);
}
static void gaudi2_tpc_stall(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 reg_base;
int i;
if (!(gaudi2->tpc_hw_cap_initialized & HW_CAP_TPC_MASK))
return;
for (i = 0 ; i < TPC_ID_SIZE ; i++) {
if (!(gaudi2->tpc_hw_cap_initialized & BIT_ULL(HW_CAP_TPC_SHIFT + i)))
continue;
reg_base = gaudi2_tpc_cfg_blocks_bases[i];
WREG32(reg_base + TPC_CFG_STALL_OFFSET, 1);
}
}
static void gaudi2_rotator_stall(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 reg_val;
int i;
if (!(gaudi2->hw_cap_initialized & HW_CAP_ROT_MASK))
return;
reg_val = FIELD_PREP(ROT_MSS_HALT_WBC_MASK, 0x1) |
FIELD_PREP(ROT_MSS_HALT_RSB_MASK, 0x1) |
FIELD_PREP(ROT_MSS_HALT_MRSB_MASK, 0x1);
for (i = 0 ; i < ROTATOR_ID_SIZE ; i++) {
if (!(gaudi2->hw_cap_initialized & BIT_ULL(HW_CAP_ROT_SHIFT + i)))
continue;
WREG32(mmROT0_MSS_HALT + i * ROT_OFFSET, reg_val);
}
}
static void gaudi2_disable_qman_common(struct hl_device *hdev, u32 reg_base)
{
WREG32(reg_base + QM_GLBL_CFG0_OFFSET, 0);
}
static void gaudi2_disable_dma_qmans(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
int dcore, inst;
if (!(gaudi2->hw_cap_initialized & HW_CAP_PDMA_MASK))
goto stop_edma_qmans;
gaudi2_disable_qman_common(hdev, mmPDMA0_QM_BASE);
gaudi2_disable_qman_common(hdev, mmPDMA1_QM_BASE);
stop_edma_qmans:
if (!(gaudi2->hw_cap_initialized & HW_CAP_EDMA_MASK))
return;
for (dcore = 0 ; dcore < NUM_OF_DCORES ; dcore++) {
for (inst = 0 ; inst < NUM_OF_EDMA_PER_DCORE ; inst++) {
u8 seq = dcore * NUM_OF_EDMA_PER_DCORE + inst;
u32 qm_base;
if (!(gaudi2->hw_cap_initialized & BIT_ULL(HW_CAP_EDMA_SHIFT + seq)))
continue;
qm_base = mmDCORE0_EDMA0_QM_BASE + dcore * DCORE_OFFSET +
inst * DCORE_EDMA_OFFSET;
gaudi2_disable_qman_common(hdev, qm_base);
}
}
}
static void gaudi2_disable_mme_qmans(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 offset, i;
offset = mmDCORE1_MME_QM_BASE - mmDCORE0_MME_QM_BASE;
for (i = 0 ; i < NUM_OF_DCORES ; i++)
if (gaudi2->hw_cap_initialized & BIT_ULL(HW_CAP_MME_SHIFT + i))
gaudi2_disable_qman_common(hdev, mmDCORE0_MME_QM_BASE + (i * offset));
}
static void gaudi2_disable_tpc_qmans(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 reg_base;
int i;
if (!(gaudi2->tpc_hw_cap_initialized & HW_CAP_TPC_MASK))
return;
for (i = 0 ; i < TPC_ID_SIZE ; i++) {
if (!(gaudi2->tpc_hw_cap_initialized & BIT_ULL(HW_CAP_TPC_SHIFT + i)))
continue;
reg_base = gaudi2_qm_blocks_bases[gaudi2_tpc_id_to_queue_id[i]];
gaudi2_disable_qman_common(hdev, reg_base);
}
}
static void gaudi2_disable_rot_qmans(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 reg_base;
int i;
if (!(gaudi2->hw_cap_initialized & HW_CAP_ROT_MASK))
return;
for (i = 0 ; i < ROTATOR_ID_SIZE ; i++) {
if (!(gaudi2->hw_cap_initialized & BIT_ULL(HW_CAP_ROT_SHIFT + i)))
continue;
reg_base = gaudi2_qm_blocks_bases[gaudi2_rot_id_to_queue_id[i]];
gaudi2_disable_qman_common(hdev, reg_base);
}
}
static void gaudi2_disable_nic_qmans(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 reg_base, queue_id;
int i;
if (!(gaudi2->nic_hw_cap_initialized & HW_CAP_NIC_MASK))
return;
queue_id = GAUDI2_QUEUE_ID_NIC_0_0;
for (i = 0 ; i < NIC_NUMBER_OF_ENGINES ; i++, queue_id += NUM_OF_PQ_PER_QMAN) {
if (!(hdev->nic_ports_mask & BIT(i)))
continue;
reg_base = gaudi2_qm_blocks_bases[queue_id];
gaudi2_disable_qman_common(hdev, reg_base);
}
}
static void gaudi2_enable_timestamp(struct hl_device *hdev)
{
WREG32(mmPSOC_TIMESTAMP_BASE, 0);
WREG32(mmPSOC_TIMESTAMP_BASE + 0xC, 0);
WREG32(mmPSOC_TIMESTAMP_BASE + 0x8, 0);
WREG32(mmPSOC_TIMESTAMP_BASE, 1);
}
static void gaudi2_disable_timestamp(struct hl_device *hdev)
{
WREG32(mmPSOC_TIMESTAMP_BASE, 0);
}
static const char *gaudi2_irq_name(u16 irq_number)
{
switch (irq_number) {
case GAUDI2_IRQ_NUM_EVENT_QUEUE:
return "gaudi2 cpu eq";
case GAUDI2_IRQ_NUM_COMPLETION:
return "gaudi2 completion";
case GAUDI2_IRQ_NUM_DCORE0_DEC0_NRM ... GAUDI2_IRQ_NUM_SHARED_DEC1_ABNRM:
return gaudi2_vdec_irq_name[irq_number - GAUDI2_IRQ_NUM_DCORE0_DEC0_NRM];
case GAUDI2_IRQ_NUM_TPC_ASSERT:
return "gaudi2 tpc assert";
case GAUDI2_IRQ_NUM_UNEXPECTED_ERROR:
return "gaudi2 unexpected error";
case GAUDI2_IRQ_NUM_USER_FIRST ... GAUDI2_IRQ_NUM_USER_LAST:
return "gaudi2 user completion";
default:
return "invalid";
}
}
static void gaudi2_dec_disable_msix(struct hl_device *hdev, u32 max_irq_num)
{
int i, irq, relative_idx;
struct hl_dec *dec;
for (i = GAUDI2_IRQ_NUM_DCORE0_DEC0_NRM ; i < max_irq_num ; i++) {
irq = pci_irq_vector(hdev->pdev, i);
relative_idx = i - GAUDI2_IRQ_NUM_DCORE0_DEC0_NRM;
dec = hdev->dec + relative_idx / 2;
free_irq(irq, ((relative_idx % 2) ?
(void *) dec :
(void *) &hdev->user_interrupt[dec->core_id]));
}
}
static int gaudi2_dec_enable_msix(struct hl_device *hdev)
{
int rc, i, irq_init_cnt, irq, relative_idx;
struct hl_dec *dec;
for (i = GAUDI2_IRQ_NUM_DCORE0_DEC0_NRM, irq_init_cnt = 0;
i <= GAUDI2_IRQ_NUM_SHARED_DEC1_ABNRM;
i++, irq_init_cnt++) {
irq = pci_irq_vector(hdev->pdev, i);
relative_idx = i - GAUDI2_IRQ_NUM_DCORE0_DEC0_NRM;
dec = hdev->dec + relative_idx / 2;
if (relative_idx % 2) {
rc = request_irq(irq, hl_irq_handler_dec_abnrm, 0,
gaudi2_irq_name(i), (void *) dec);
} else {
rc = request_threaded_irq(irq, hl_irq_handler_user_interrupt,
hl_irq_user_interrupt_thread_handler, IRQF_ONESHOT,
gaudi2_irq_name(i),
(void *) &hdev->user_interrupt[dec->core_id]);
}
if (rc) {
dev_err(hdev->dev, "Failed to request IRQ %d", irq);
goto free_dec_irqs;
}
}
return 0;
free_dec_irqs:
gaudi2_dec_disable_msix(hdev, (GAUDI2_IRQ_NUM_DCORE0_DEC0_NRM + irq_init_cnt));
return rc;
}
static int gaudi2_enable_msix(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
struct gaudi2_device *gaudi2 = hdev->asic_specific;
int rc, irq, i, j, user_irq_init_cnt;
struct hl_cq *cq;
if (gaudi2->hw_cap_initialized & HW_CAP_MSIX)
return 0;
rc = pci_alloc_irq_vectors(hdev->pdev, GAUDI2_MSIX_ENTRIES, GAUDI2_MSIX_ENTRIES,
PCI_IRQ_MSIX);
if (rc < 0) {
dev_err(hdev->dev, "MSI-X: Failed to enable support -- %d/%d\n",
GAUDI2_MSIX_ENTRIES, rc);
return rc;
}
irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_COMPLETION);
cq = &hdev->completion_queue[GAUDI2_RESERVED_CQ_CS_COMPLETION];
rc = request_irq(irq, hl_irq_handler_cq, 0, gaudi2_irq_name(GAUDI2_IRQ_NUM_COMPLETION), cq);
if (rc) {
dev_err(hdev->dev, "Failed to request IRQ %d", irq);
goto free_irq_vectors;
}
irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_EVENT_QUEUE);
rc = request_irq(irq, hl_irq_handler_eq, 0, gaudi2_irq_name(GAUDI2_IRQ_NUM_EVENT_QUEUE),
&hdev->event_queue);
if (rc) {
dev_err(hdev->dev, "Failed to request IRQ %d", irq);
goto free_completion_irq;
}
rc = gaudi2_dec_enable_msix(hdev);
if (rc) {
dev_err(hdev->dev, "Failed to enable decoder IRQ");
goto free_event_irq;
}
irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_TPC_ASSERT);
rc = request_threaded_irq(irq, hl_irq_handler_user_interrupt,
hl_irq_user_interrupt_thread_handler, IRQF_ONESHOT,
gaudi2_irq_name(GAUDI2_IRQ_NUM_TPC_ASSERT), &hdev->tpc_interrupt);
if (rc) {
dev_err(hdev->dev, "Failed to request IRQ %d", irq);
goto free_dec_irq;
}
irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_UNEXPECTED_ERROR);
rc = request_irq(irq, hl_irq_handler_user_interrupt, 0,
gaudi2_irq_name(GAUDI2_IRQ_NUM_UNEXPECTED_ERROR),
&hdev->unexpected_error_interrupt);
if (rc) {
dev_err(hdev->dev, "Failed to request IRQ %d", irq);
goto free_tpc_irq;
}
for (i = GAUDI2_IRQ_NUM_USER_FIRST, j = prop->user_dec_intr_count, user_irq_init_cnt = 0;
user_irq_init_cnt < prop->user_interrupt_count;
i++, j++, user_irq_init_cnt++) {
irq = pci_irq_vector(hdev->pdev, i);
rc = request_threaded_irq(irq, hl_irq_handler_user_interrupt,
hl_irq_user_interrupt_thread_handler, IRQF_ONESHOT,
gaudi2_irq_name(i), &hdev->user_interrupt[j]);
if (rc) {
dev_err(hdev->dev, "Failed to request IRQ %d", irq);
goto free_user_irq;
}
}
gaudi2->hw_cap_initialized |= HW_CAP_MSIX;
return 0;
free_user_irq:
for (i = GAUDI2_IRQ_NUM_USER_FIRST, j = prop->user_dec_intr_count;
i < GAUDI2_IRQ_NUM_USER_FIRST + user_irq_init_cnt ; i++, j++) {
irq = pci_irq_vector(hdev->pdev, i);
free_irq(irq, &hdev->user_interrupt[j]);
}
irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_UNEXPECTED_ERROR);
free_irq(irq, &hdev->unexpected_error_interrupt);
free_tpc_irq:
irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_TPC_ASSERT);
free_irq(irq, &hdev->tpc_interrupt);
free_dec_irq:
gaudi2_dec_disable_msix(hdev, GAUDI2_IRQ_NUM_DEC_LAST + 1);
free_event_irq:
irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_EVENT_QUEUE);
free_irq(irq, cq);
free_completion_irq:
irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_COMPLETION);
free_irq(irq, cq);
free_irq_vectors:
pci_free_irq_vectors(hdev->pdev);
return rc;
}
static void gaudi2_sync_irqs(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
int i, j;
int irq;
if (!(gaudi2->hw_cap_initialized & HW_CAP_MSIX))
return;
synchronize_irq(pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_COMPLETION));
for (i = GAUDI2_IRQ_NUM_DCORE0_DEC0_NRM ; i <= GAUDI2_IRQ_NUM_SHARED_DEC1_ABNRM ; i++) {
irq = pci_irq_vector(hdev->pdev, i);
synchronize_irq(irq);
}
synchronize_irq(pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_TPC_ASSERT));
synchronize_irq(pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_UNEXPECTED_ERROR));
for (i = GAUDI2_IRQ_NUM_USER_FIRST, j = 0 ; j < hdev->asic_prop.user_interrupt_count;
i++, j++) {
irq = pci_irq_vector(hdev->pdev, i);
synchronize_irq(irq);
}
synchronize_irq(pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_EVENT_QUEUE));
}
static void gaudi2_disable_msix(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
struct gaudi2_device *gaudi2 = hdev->asic_specific;
struct hl_cq *cq;
int irq, i, j, k;
if (!(gaudi2->hw_cap_initialized & HW_CAP_MSIX))
return;
gaudi2_sync_irqs(hdev);
irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_EVENT_QUEUE);
free_irq(irq, &hdev->event_queue);
gaudi2_dec_disable_msix(hdev, GAUDI2_IRQ_NUM_SHARED_DEC1_ABNRM + 1);
irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_TPC_ASSERT);
free_irq(irq, &hdev->tpc_interrupt);
irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_UNEXPECTED_ERROR);
free_irq(irq, &hdev->unexpected_error_interrupt);
for (i = GAUDI2_IRQ_NUM_USER_FIRST, j = prop->user_dec_intr_count, k = 0;
k < hdev->asic_prop.user_interrupt_count ; i++, j++, k++) {
irq = pci_irq_vector(hdev->pdev, i);
free_irq(irq, &hdev->user_interrupt[j]);
}
irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_COMPLETION);
cq = &hdev->completion_queue[GAUDI2_RESERVED_CQ_CS_COMPLETION];
free_irq(irq, cq);
pci_free_irq_vectors(hdev->pdev);
gaudi2->hw_cap_initialized &= ~HW_CAP_MSIX;
}
static void gaudi2_stop_dcore_dec(struct hl_device *hdev, int dcore_id)
{
u32 reg_val = FIELD_PREP(DCORE0_VDEC0_BRDG_CTRL_GRACEFUL_STOP_MASK, 0x1);
u32 graceful_pend_mask = DCORE0_VDEC0_BRDG_CTRL_GRACEFUL_PEND_MASK;
u32 timeout_usec, dec_id, dec_bit, offset, graceful;
int rc;
if (hdev->pldm)
timeout_usec = GAUDI2_PLDM_VDEC_TIMEOUT_USEC;
else
timeout_usec = GAUDI2_VDEC_TIMEOUT_USEC;
for (dec_id = 0 ; dec_id < NUM_OF_DEC_PER_DCORE ; dec_id++) {
dec_bit = dcore_id * NUM_OF_DEC_PER_DCORE + dec_id;
if (!(hdev->asic_prop.decoder_enabled_mask & BIT(dec_bit)))
continue;
offset = dcore_id * DCORE_OFFSET + dec_id * DCORE_VDEC_OFFSET;
WREG32(mmDCORE0_DEC0_CMD_SWREG16 + offset, 0);
WREG32(mmDCORE0_VDEC0_BRDG_CTRL_GRACEFUL + offset, reg_val);
rc = hl_poll_timeout(
hdev,
mmDCORE0_VDEC0_BRDG_CTRL_GRACEFUL + offset,
graceful,
(graceful & graceful_pend_mask),
100,
timeout_usec);
if (rc)
dev_err(hdev->dev,
"Failed to stop traffic from DCORE%d Decoder %d\n",
dcore_id, dec_id);
}
}
static void gaudi2_stop_pcie_dec(struct hl_device *hdev)
{
u32 reg_val = FIELD_PREP(DCORE0_VDEC0_BRDG_CTRL_GRACEFUL_STOP_MASK, 0x1);
u32 graceful_pend_mask = PCIE_VDEC0_BRDG_CTRL_GRACEFUL_PEND_MASK;
u32 timeout_usec, dec_id, dec_bit, offset, graceful;
int rc;
if (hdev->pldm)
timeout_usec = GAUDI2_PLDM_VDEC_TIMEOUT_USEC;
else
timeout_usec = GAUDI2_VDEC_TIMEOUT_USEC;
for (dec_id = 0 ; dec_id < NUM_OF_DEC_PER_DCORE ; dec_id++) {
dec_bit = PCIE_DEC_SHIFT + dec_id;
if (!(hdev->asic_prop.decoder_enabled_mask & BIT(dec_bit)))
continue;
offset = dec_id * PCIE_VDEC_OFFSET;
WREG32(mmPCIE_DEC0_CMD_SWREG16 + offset, 0);
WREG32(mmPCIE_VDEC0_BRDG_CTRL_GRACEFUL + offset, reg_val);
rc = hl_poll_timeout(
hdev,
mmPCIE_VDEC0_BRDG_CTRL_GRACEFUL + offset,
graceful,
(graceful & graceful_pend_mask),
100,
timeout_usec);
if (rc)
dev_err(hdev->dev,
"Failed to stop traffic from PCIe Decoder %d\n",
dec_id);
}
}
static void gaudi2_stop_dec(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
int dcore_id;
if ((gaudi2->dec_hw_cap_initialized & HW_CAP_DEC_MASK) == 0)
return;
for (dcore_id = 0 ; dcore_id < NUM_OF_DCORES ; dcore_id++)
gaudi2_stop_dcore_dec(hdev, dcore_id);
gaudi2_stop_pcie_dec(hdev);
}
static void gaudi2_set_arc_running_mode(struct hl_device *hdev, u32 cpu_id, u32 run_mode)
{
u32 reg_base, reg_val;
reg_base = gaudi2_arc_blocks_bases[cpu_id];
if (run_mode == HL_ENGINE_CORE_RUN)
reg_val = FIELD_PREP(ARC_FARM_ARC0_AUX_RUN_HALT_REQ_RUN_REQ_MASK, 1);
else
reg_val = FIELD_PREP(ARC_FARM_ARC0_AUX_RUN_HALT_REQ_HALT_REQ_MASK, 1);
WREG32(reg_base + ARC_HALT_REQ_OFFSET, reg_val);
}
static void gaudi2_halt_arcs(struct hl_device *hdev)
{
u16 arc_id;
for (arc_id = CPU_ID_SCHED_ARC0; arc_id < CPU_ID_MAX; arc_id++) {
if (gaudi2_is_arc_enabled(hdev, arc_id))
gaudi2_set_arc_running_mode(hdev, arc_id, HL_ENGINE_CORE_HALT);
}
}
static int gaudi2_verify_arc_running_mode(struct hl_device *hdev, u32 cpu_id, u32 run_mode)
{
int rc;
u32 reg_base, val, ack_mask, timeout_usec = 100000;
if (hdev->pldm)
timeout_usec *= 100;
reg_base = gaudi2_arc_blocks_bases[cpu_id];
if (run_mode == HL_ENGINE_CORE_RUN)
ack_mask = ARC_FARM_ARC0_AUX_RUN_HALT_ACK_RUN_ACK_MASK;
else
ack_mask = ARC_FARM_ARC0_AUX_RUN_HALT_ACK_HALT_ACK_MASK;
rc = hl_poll_timeout(hdev, reg_base + ARC_HALT_ACK_OFFSET,
val, ((val & ack_mask) == ack_mask),
1000, timeout_usec);
if (!rc) {
val = FIELD_PREP(ARC_FARM_ARC0_AUX_RUN_HALT_REQ_RUN_REQ_MASK, 0);
WREG32(reg_base + ARC_HALT_REQ_OFFSET, val);
}
return rc;
}
static void gaudi2_reset_arcs(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u16 arc_id;
if (!gaudi2)
return;
for (arc_id = CPU_ID_SCHED_ARC0; arc_id < CPU_ID_MAX; arc_id++)
if (gaudi2_is_arc_enabled(hdev, arc_id))
gaudi2_clr_arc_id_cap(hdev, arc_id);
}
static void gaudi2_nic_qmans_manual_flush(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 queue_id;
int i;
if (!(gaudi2->nic_hw_cap_initialized & HW_CAP_NIC_MASK))
return;
queue_id = GAUDI2_QUEUE_ID_NIC_0_0;
for (i = 0 ; i < NIC_NUMBER_OF_ENGINES ; i++, queue_id += NUM_OF_PQ_PER_QMAN) {
if (!(hdev->nic_ports_mask & BIT(i)))
continue;
gaudi2_qman_manual_flush_common(hdev, queue_id);
}
}
static int gaudi2_set_engine_cores(struct hl_device *hdev, u32 *core_ids,
u32 num_cores, u32 core_command)
{
int i, rc;
for (i = 0 ; i < num_cores ; i++) {
if (gaudi2_is_arc_enabled(hdev, core_ids[i]))
gaudi2_set_arc_running_mode(hdev, core_ids[i], core_command);
}
for (i = 0 ; i < num_cores ; i++) {
if (gaudi2_is_arc_enabled(hdev, core_ids[i])) {
rc = gaudi2_verify_arc_running_mode(hdev, core_ids[i], core_command);
if (rc) {
dev_err(hdev->dev, "failed to %s arc: %d\n",
(core_command == HL_ENGINE_CORE_HALT) ?
"HALT" : "RUN", core_ids[i]);
return -1;
}
}
}
return 0;
}
static int gaudi2_set_tpc_engine_mode(struct hl_device *hdev, u32 engine_id, u32 engine_command)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 reg_base, reg_addr, reg_val, tpc_id;
if (!(gaudi2->tpc_hw_cap_initialized & HW_CAP_TPC_MASK))
return 0;
tpc_id = gaudi2_tpc_engine_id_to_tpc_id[engine_id];
if (!(gaudi2->tpc_hw_cap_initialized & BIT_ULL(HW_CAP_TPC_SHIFT + tpc_id)))
return 0;
reg_base = gaudi2_tpc_cfg_blocks_bases[tpc_id];
reg_addr = reg_base + TPC_CFG_STALL_OFFSET;
reg_val = FIELD_PREP(DCORE0_TPC0_CFG_TPC_STALL_V_MASK,
(engine_command == HL_ENGINE_STALL) ? 1 : 0);
WREG32(reg_addr, reg_val);
if (engine_command == HL_ENGINE_RESUME) {
reg_base = gaudi2_tpc_eml_cfg_blocks_bases[tpc_id];
reg_addr = reg_base + TPC_EML_CFG_DBG_CNT_OFFSET;
RMWREG32(reg_addr, 0x1, DCORE0_TPC0_EML_CFG_DBG_CNT_DBG_EXIT_MASK);
}
return 0;
}
static int gaudi2_set_mme_engine_mode(struct hl_device *hdev, u32 engine_id, u32 engine_command)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 reg_base, reg_addr, reg_val, mme_id;
mme_id = gaudi2_mme_engine_id_to_mme_id[engine_id];
if (!(gaudi2->hw_cap_initialized & BIT_ULL(HW_CAP_MME_SHIFT + mme_id)))
return 0;
reg_base = gaudi2_mme_ctrl_lo_blocks_bases[mme_id];
reg_addr = reg_base + MME_CTRL_LO_QM_STALL_OFFSET;
reg_val = FIELD_PREP(DCORE0_MME_CTRL_LO_QM_STALL_V_MASK,
(engine_command == HL_ENGINE_STALL) ? 1 : 0);
WREG32(reg_addr, reg_val);
return 0;
}
static int gaudi2_set_edma_engine_mode(struct hl_device *hdev, u32 engine_id, u32 engine_command)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 reg_base, reg_addr, reg_val, edma_id;
if (!(gaudi2->hw_cap_initialized & HW_CAP_EDMA_MASK))
return 0;
edma_id = gaudi2_edma_engine_id_to_edma_id[engine_id];
if (!(gaudi2->hw_cap_initialized & BIT_ULL(HW_CAP_EDMA_SHIFT + edma_id)))
return 0;
reg_base = gaudi2_dma_core_blocks_bases[edma_id];
reg_addr = reg_base + EDMA_CORE_CFG_STALL_OFFSET;
reg_val = FIELD_PREP(DCORE0_EDMA0_CORE_CFG_1_HALT_MASK,
(engine_command == HL_ENGINE_STALL) ? 1 : 0);
WREG32(reg_addr, reg_val);
if (engine_command == HL_ENGINE_STALL) {
reg_val = FIELD_PREP(DCORE0_EDMA0_CORE_CFG_1_HALT_MASK, 0x1) |
FIELD_PREP(DCORE0_EDMA0_CORE_CFG_1_FLUSH_MASK, 0x1);
WREG32(reg_addr, reg_val);
}
return 0;
}
static int gaudi2_set_engine_modes(struct hl_device *hdev,
u32 *engine_ids, u32 num_engines, u32 engine_command)
{
int i, rc;
for (i = 0 ; i < num_engines ; ++i) {
switch (engine_ids[i]) {
case GAUDI2_DCORE0_ENGINE_ID_TPC_0 ... GAUDI2_DCORE0_ENGINE_ID_TPC_5:
case GAUDI2_DCORE1_ENGINE_ID_TPC_0 ... GAUDI2_DCORE1_ENGINE_ID_TPC_5:
case GAUDI2_DCORE2_ENGINE_ID_TPC_0 ... GAUDI2_DCORE2_ENGINE_ID_TPC_5:
case GAUDI2_DCORE3_ENGINE_ID_TPC_0 ... GAUDI2_DCORE3_ENGINE_ID_TPC_5:
rc = gaudi2_set_tpc_engine_mode(hdev, engine_ids[i], engine_command);
if (rc)
return rc;
break;
case GAUDI2_DCORE0_ENGINE_ID_MME:
case GAUDI2_DCORE1_ENGINE_ID_MME:
case GAUDI2_DCORE2_ENGINE_ID_MME:
case GAUDI2_DCORE3_ENGINE_ID_MME:
rc = gaudi2_set_mme_engine_mode(hdev, engine_ids[i], engine_command);
if (rc)
return rc;
break;
case GAUDI2_DCORE0_ENGINE_ID_EDMA_0 ... GAUDI2_DCORE0_ENGINE_ID_EDMA_1:
case GAUDI2_DCORE1_ENGINE_ID_EDMA_0 ... GAUDI2_DCORE1_ENGINE_ID_EDMA_1:
case GAUDI2_DCORE2_ENGINE_ID_EDMA_0 ... GAUDI2_DCORE2_ENGINE_ID_EDMA_1:
case GAUDI2_DCORE3_ENGINE_ID_EDMA_0 ... GAUDI2_DCORE3_ENGINE_ID_EDMA_1:
rc = gaudi2_set_edma_engine_mode(hdev, engine_ids[i], engine_command);
if (rc)
return rc;
break;
default:
dev_err(hdev->dev, "Invalid engine ID %u\n", engine_ids[i]);
return -EINVAL;
}
}
return 0;
}
static int gaudi2_set_engines(struct hl_device *hdev, u32 *engine_ids,
u32 num_engines, u32 engine_command)
{
switch (engine_command) {
case HL_ENGINE_CORE_HALT:
case HL_ENGINE_CORE_RUN:
return gaudi2_set_engine_cores(hdev, engine_ids, num_engines, engine_command);
case HL_ENGINE_STALL:
case HL_ENGINE_RESUME:
return gaudi2_set_engine_modes(hdev, engine_ids, num_engines, engine_command);
default:
dev_err(hdev->dev, "failed to execute command id %u\n", engine_command);
return -EINVAL;
}
}
static void gaudi2_halt_engines(struct hl_device *hdev, bool hard_reset, bool fw_reset)
{
u32 wait_timeout_ms;
if (hdev->pldm)
wait_timeout_ms = GAUDI2_PLDM_RESET_WAIT_MSEC;
else
wait_timeout_ms = GAUDI2_RESET_WAIT_MSEC;
if (fw_reset)
goto skip_engines;
gaudi2_stop_dma_qmans(hdev);
gaudi2_stop_mme_qmans(hdev);
gaudi2_stop_tpc_qmans(hdev);
gaudi2_stop_rot_qmans(hdev);
gaudi2_stop_nic_qmans(hdev);
msleep(wait_timeout_ms);
gaudi2_halt_arcs(hdev);
gaudi2_dma_stall(hdev);
gaudi2_mme_stall(hdev);
gaudi2_tpc_stall(hdev);
gaudi2_rotator_stall(hdev);
msleep(wait_timeout_ms);
gaudi2_stop_dec(hdev);
if (!hard_reset)
gaudi2_nic_qmans_manual_flush(hdev);
gaudi2_disable_dma_qmans(hdev);
gaudi2_disable_mme_qmans(hdev);
gaudi2_disable_tpc_qmans(hdev);
gaudi2_disable_rot_qmans(hdev);
gaudi2_disable_nic_qmans(hdev);
gaudi2_disable_timestamp(hdev);
skip_engines:
if (hard_reset) {
gaudi2_disable_msix(hdev);
return;
}
gaudi2_sync_irqs(hdev);
}
static void gaudi2_init_firmware_preload_params(struct hl_device *hdev)
{
struct pre_fw_load_props *pre_fw_load = &hdev->fw_loader.pre_fw_load;
pre_fw_load->cpu_boot_status_reg = mmPSOC_GLOBAL_CONF_CPU_BOOT_STATUS;
pre_fw_load->sts_boot_dev_sts0_reg = mmCPU_BOOT_DEV_STS0;
pre_fw_load->sts_boot_dev_sts1_reg = mmCPU_BOOT_DEV_STS1;
pre_fw_load->boot_err0_reg = mmCPU_BOOT_ERR0;
pre_fw_load->boot_err1_reg = mmCPU_BOOT_ERR1;
pre_fw_load->wait_for_preboot_timeout = GAUDI2_PREBOOT_REQ_TIMEOUT_USEC;
}
static void gaudi2_init_firmware_loader(struct hl_device *hdev)
{
struct fw_load_mgr *fw_loader = &hdev->fw_loader;
struct dynamic_fw_load_mgr *dynamic_loader;
struct cpu_dyn_regs *dyn_regs;
fw_loader->fw_comp_loaded = FW_TYPE_NONE;
fw_loader->boot_fit_img.image_name = GAUDI2_BOOT_FIT_FILE;
fw_loader->linux_img.image_name = GAUDI2_LINUX_FW_FILE;
fw_loader->boot_fit_timeout = GAUDI2_BOOT_FIT_REQ_TIMEOUT_USEC;
fw_loader->skip_bmc = false;
fw_loader->sram_bar_id = SRAM_CFG_BAR_ID;
fw_loader->dram_bar_id = DRAM_BAR_ID;
fw_loader->cpu_timeout = GAUDI2_CPU_TIMEOUT_USEC;
dynamic_loader = &hdev->fw_loader.dynamic_loader;
dyn_regs = &dynamic_loader->comm_desc.cpu_dyn_regs;
dyn_regs->kmd_msg_to_cpu = cpu_to_le32(mmPSOC_GLOBAL_CONF_KMD_MSG_TO_CPU);
dyn_regs->cpu_cmd_status_to_host = cpu_to_le32(mmCPU_CMD_STATUS_TO_HOST);
dynamic_loader->wait_for_bl_timeout = GAUDI2_WAIT_FOR_BL_TIMEOUT_USEC;
}
static int gaudi2_init_cpu(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
int rc;
if (!(hdev->fw_components & FW_TYPE_PREBOOT_CPU))
return 0;
if (gaudi2->hw_cap_initialized & HW_CAP_CPU)
return 0;
rc = hl_fw_init_cpu(hdev);
if (rc)
return rc;
gaudi2->hw_cap_initialized |= HW_CAP_CPU;
return 0;
}
static int gaudi2_init_cpu_queues(struct hl_device *hdev, u32 cpu_timeout)
{
struct hl_hw_queue *cpu_pq = &hdev->kernel_queues[GAUDI2_QUEUE_ID_CPU_PQ];
struct asic_fixed_properties *prop = &hdev->asic_prop;
struct gaudi2_device *gaudi2 = hdev->asic_specific;
struct cpu_dyn_regs *dyn_regs;
struct hl_eq *eq;
u32 status;
int err;
if (!hdev->cpu_queues_enable)
return 0;
if (gaudi2->hw_cap_initialized & HW_CAP_CPU_Q)
return 0;
eq = &hdev->event_queue;
dyn_regs = &hdev->fw_loader.dynamic_loader.comm_desc.cpu_dyn_regs;
WREG32(mmCPU_IF_PQ_BASE_ADDR_LOW, lower_32_bits(cpu_pq->bus_address));
WREG32(mmCPU_IF_PQ_BASE_ADDR_HIGH, upper_32_bits(cpu_pq->bus_address));
WREG32(mmCPU_IF_EQ_BASE_ADDR_LOW, lower_32_bits(eq->bus_address));
WREG32(mmCPU_IF_EQ_BASE_ADDR_HIGH, upper_32_bits(eq->bus_address));
WREG32(mmCPU_IF_CQ_BASE_ADDR_LOW, lower_32_bits(hdev->cpu_accessible_dma_address));
WREG32(mmCPU_IF_CQ_BASE_ADDR_HIGH, upper_32_bits(hdev->cpu_accessible_dma_address));
WREG32(mmCPU_IF_PQ_LENGTH, HL_QUEUE_SIZE_IN_BYTES);
WREG32(mmCPU_IF_EQ_LENGTH, HL_EQ_SIZE_IN_BYTES);
WREG32(mmCPU_IF_CQ_LENGTH, HL_CPU_ACCESSIBLE_MEM_SIZE);
WREG32(mmCPU_IF_EQ_RD_OFFS, 0);
WREG32(mmCPU_IF_PF_PQ_PI, 0);
WREG32(mmCPU_IF_QUEUE_INIT, PQ_INIT_STATUS_READY_FOR_CP);
WREG32(le32_to_cpu(dyn_regs->gic_host_pi_upd_irq),
gaudi2_irq_map_table[GAUDI2_EVENT_CPU_PI_UPDATE].cpu_id);
err = hl_poll_timeout(
hdev,
mmCPU_IF_QUEUE_INIT,
status,
(status == PQ_INIT_STATUS_READY_FOR_HOST),
1000,
cpu_timeout);
if (err) {
dev_err(hdev->dev, "Failed to communicate with device CPU (timeout)\n");
return -EIO;
}
if (prop->fw_cpu_boot_dev_sts0_valid)
prop->fw_app_cpu_boot_dev_sts0 = RREG32(mmCPU_BOOT_DEV_STS0);
if (prop->fw_cpu_boot_dev_sts1_valid)
prop->fw_app_cpu_boot_dev_sts1 = RREG32(mmCPU_BOOT_DEV_STS1);
gaudi2->hw_cap_initialized |= HW_CAP_CPU_Q;
return 0;
}
static void gaudi2_init_qman_pq(struct hl_device *hdev, u32 reg_base,
u32 queue_id_base)
{
struct hl_hw_queue *q;
u32 pq_id, pq_offset;
for (pq_id = 0 ; pq_id < NUM_OF_PQ_PER_QMAN ; pq_id++) {
q = &hdev->kernel_queues[queue_id_base + pq_id];
pq_offset = pq_id * 4;
WREG32(reg_base + QM_PQ_BASE_LO_0_OFFSET + pq_offset,
lower_32_bits(q->bus_address));
WREG32(reg_base + QM_PQ_BASE_HI_0_OFFSET + pq_offset,
upper_32_bits(q->bus_address));
WREG32(reg_base + QM_PQ_SIZE_0_OFFSET + pq_offset, ilog2(HL_QUEUE_LENGTH));
WREG32(reg_base + QM_PQ_PI_0_OFFSET + pq_offset, 0);
WREG32(reg_base + QM_PQ_CI_0_OFFSET + pq_offset, 0);
}
}
static void gaudi2_init_qman_cp(struct hl_device *hdev, u32 reg_base)
{
u32 cp_id, cp_offset, mtr_base_lo, mtr_base_hi, so_base_lo, so_base_hi;
mtr_base_lo = lower_32_bits(CFG_BASE + mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0);
mtr_base_hi = upper_32_bits(CFG_BASE + mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0);
so_base_lo = lower_32_bits(CFG_BASE + mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0);
so_base_hi = upper_32_bits(CFG_BASE + mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0);
for (cp_id = 0 ; cp_id < NUM_OF_CP_PER_QMAN; cp_id++) {
cp_offset = cp_id * 4;
WREG32(reg_base + QM_CP_MSG_BASE0_ADDR_LO_0_OFFSET + cp_offset, mtr_base_lo);
WREG32(reg_base + QM_CP_MSG_BASE0_ADDR_HI_0_OFFSET + cp_offset, mtr_base_hi);
WREG32(reg_base + QM_CP_MSG_BASE1_ADDR_LO_0_OFFSET + cp_offset, so_base_lo);
WREG32(reg_base + QM_CP_MSG_BASE1_ADDR_HI_0_OFFSET + cp_offset, so_base_hi);
}
WREG32(reg_base + QM_CP_CFG_OFFSET, FIELD_PREP(PDMA0_QM_CP_CFG_SWITCH_EN_MASK, 0x1));
}
static void gaudi2_init_qman_pqc(struct hl_device *hdev, u32 reg_base,
u32 queue_id_base)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 pq_id, pq_offset, so_base_lo, so_base_hi;
so_base_lo = lower_32_bits(CFG_BASE + mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0);
so_base_hi = upper_32_bits(CFG_BASE + mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0);
for (pq_id = 0 ; pq_id < NUM_OF_PQ_PER_QMAN ; pq_id++) {
pq_offset = pq_id * 4;
WREG32(reg_base + QM_PQC_HBW_BASE_LO_0_OFFSET + pq_offset,
lower_32_bits(gaudi2->scratchpad_bus_address));
WREG32(reg_base + QM_PQC_HBW_BASE_HI_0_OFFSET + pq_offset,
upper_32_bits(gaudi2->scratchpad_bus_address));
WREG32(reg_base + QM_PQC_SIZE_0_OFFSET + pq_offset,
ilog2(PAGE_SIZE / sizeof(struct hl_cq_entry)));
WREG32(reg_base + QM_PQC_PI_0_OFFSET + pq_offset, 0);
WREG32(reg_base + QM_PQC_LBW_WDATA_0_OFFSET + pq_offset, QM_PQC_LBW_WDATA);
WREG32(reg_base + QM_PQC_LBW_BASE_LO_0_OFFSET + pq_offset, so_base_lo);
WREG32(reg_base + QM_PQC_LBW_BASE_HI_0_OFFSET + pq_offset, so_base_hi);
}
WREG32(reg_base + QM_PQC_CFG_OFFSET, 1 << PDMA0_QM_PQC_CFG_EN_SHIFT);
}
static u32 gaudi2_get_dyn_sp_reg(struct hl_device *hdev, u32 queue_id_base)
{
struct cpu_dyn_regs *dyn_regs = &hdev->fw_loader.dynamic_loader.comm_desc.cpu_dyn_regs;
u32 sp_reg_addr;
switch (queue_id_base) {
case GAUDI2_QUEUE_ID_PDMA_0_0...GAUDI2_QUEUE_ID_PDMA_1_3:
fallthrough;
case GAUDI2_QUEUE_ID_DCORE0_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE0_EDMA_1_3:
fallthrough;
case GAUDI2_QUEUE_ID_DCORE1_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE1_EDMA_1_3:
fallthrough;
case GAUDI2_QUEUE_ID_DCORE2_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE2_EDMA_1_3:
fallthrough;
case GAUDI2_QUEUE_ID_DCORE3_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE3_EDMA_1_3:
sp_reg_addr = le32_to_cpu(dyn_regs->gic_dma_qm_irq_ctrl);
break;
case GAUDI2_QUEUE_ID_DCORE0_MME_0_0...GAUDI2_QUEUE_ID_DCORE0_MME_0_3:
fallthrough;
case GAUDI2_QUEUE_ID_DCORE1_MME_0_0...GAUDI2_QUEUE_ID_DCORE1_MME_0_3:
fallthrough;
case GAUDI2_QUEUE_ID_DCORE2_MME_0_0...GAUDI2_QUEUE_ID_DCORE2_MME_0_3:
fallthrough;
case GAUDI2_QUEUE_ID_DCORE3_MME_0_0...GAUDI2_QUEUE_ID_DCORE3_MME_0_3:
sp_reg_addr = le32_to_cpu(dyn_regs->gic_mme_qm_irq_ctrl);
break;
case GAUDI2_QUEUE_ID_DCORE0_TPC_0_0 ... GAUDI2_QUEUE_ID_DCORE0_TPC_6_3:
fallthrough;
case GAUDI2_QUEUE_ID_DCORE1_TPC_0_0 ... GAUDI2_QUEUE_ID_DCORE1_TPC_5_3:
fallthrough;
case GAUDI2_QUEUE_ID_DCORE2_TPC_0_0 ... GAUDI2_QUEUE_ID_DCORE2_TPC_5_3:
fallthrough;
case GAUDI2_QUEUE_ID_DCORE3_TPC_0_0 ... GAUDI2_QUEUE_ID_DCORE3_TPC_5_3:
sp_reg_addr = le32_to_cpu(dyn_regs->gic_tpc_qm_irq_ctrl);
break;
case GAUDI2_QUEUE_ID_ROT_0_0...GAUDI2_QUEUE_ID_ROT_1_3:
sp_reg_addr = le32_to_cpu(dyn_regs->gic_rot_qm_irq_ctrl);
break;
case GAUDI2_QUEUE_ID_NIC_0_0...GAUDI2_QUEUE_ID_NIC_23_3:
sp_reg_addr = le32_to_cpu(dyn_regs->gic_nic_qm_irq_ctrl);
break;
default:
dev_err(hdev->dev, "Unexpected h/w queue %d\n", queue_id_base);
return 0;
}
return sp_reg_addr;
}
static void gaudi2_init_qman_common(struct hl_device *hdev, u32 reg_base,
u32 queue_id_base)
{
u32 glbl_prot = QMAN_MAKE_TRUSTED, irq_handler_offset;
int map_table_entry;
WREG32(reg_base + QM_GLBL_PROT_OFFSET, glbl_prot);
irq_handler_offset = gaudi2_get_dyn_sp_reg(hdev, queue_id_base);
WREG32(reg_base + QM_GLBL_ERR_ADDR_LO_OFFSET, lower_32_bits(CFG_BASE + irq_handler_offset));
WREG32(reg_base + QM_GLBL_ERR_ADDR_HI_OFFSET, upper_32_bits(CFG_BASE + irq_handler_offset));
map_table_entry = gaudi2_qman_async_event_id[queue_id_base];
WREG32(reg_base + QM_GLBL_ERR_WDATA_OFFSET,
gaudi2_irq_map_table[map_table_entry].cpu_id);
WREG32(reg_base + QM_ARB_ERR_MSG_EN_OFFSET, QM_ARB_ERR_MSG_EN_MASK);
WREG32(reg_base + QM_ARB_SLV_CHOISE_WDT_OFFSET, GAUDI2_ARB_WDT_TIMEOUT);
WREG32(reg_base + QM_GLBL_CFG1_OFFSET, 0);
WREG32(reg_base + QM_GLBL_CFG2_OFFSET, 0);
if (reg_base == gaudi2_qm_blocks_bases[GAUDI2_QUEUE_ID_PDMA_1_0])
WREG32(reg_base + QM_GLBL_CFG0_OFFSET, PDMA1_QMAN_ENABLE);
else if (reg_base == gaudi2_qm_blocks_bases[GAUDI2_QUEUE_ID_PDMA_0_0])
WREG32(reg_base + QM_GLBL_CFG0_OFFSET, PDMA0_QMAN_ENABLE);
else
WREG32(reg_base + QM_GLBL_CFG0_OFFSET, QMAN_ENABLE);
}
static void gaudi2_init_qman(struct hl_device *hdev, u32 reg_base,
u32 queue_id_base)
{
u32 pq_id;
for (pq_id = 0 ; pq_id < NUM_OF_PQ_PER_QMAN ; pq_id++)
hdev->kernel_queues[queue_id_base + pq_id].cq_id = GAUDI2_RESERVED_CQ_CS_COMPLETION;
gaudi2_init_qman_pq(hdev, reg_base, queue_id_base);
gaudi2_init_qman_cp(hdev, reg_base);
gaudi2_init_qman_pqc(hdev, reg_base, queue_id_base);
gaudi2_init_qman_common(hdev, reg_base, queue_id_base);
}
static void gaudi2_init_dma_core(struct hl_device *hdev, u32 reg_base,
u32 dma_core_id, bool is_secure)
{
u32 prot, irq_handler_offset;
struct cpu_dyn_regs *dyn_regs;
int map_table_entry;
prot = 1 << ARC_FARM_KDMA_PROT_ERR_VAL_SHIFT;
if (is_secure)
prot |= 1 << ARC_FARM_KDMA_PROT_VAL_SHIFT;
WREG32(reg_base + DMA_CORE_PROT_OFFSET, prot);
dyn_regs = &hdev->fw_loader.dynamic_loader.comm_desc.cpu_dyn_regs;
irq_handler_offset = le32_to_cpu(dyn_regs->gic_dma_core_irq_ctrl);
WREG32(reg_base + DMA_CORE_ERRMSG_ADDR_LO_OFFSET,
lower_32_bits(CFG_BASE + irq_handler_offset));
WREG32(reg_base + DMA_CORE_ERRMSG_ADDR_HI_OFFSET,
upper_32_bits(CFG_BASE + irq_handler_offset));
map_table_entry = gaudi2_dma_core_async_event_id[dma_core_id];
WREG32(reg_base + DMA_CORE_ERRMSG_WDATA_OFFSET,
gaudi2_irq_map_table[map_table_entry].cpu_id);
WREG32(reg_base + DMA_CORE_CFG_0_OFFSET, 1 << ARC_FARM_KDMA_CFG_0_EN_SHIFT);
}
static void gaudi2_init_kdma(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 reg_base;
if ((gaudi2->hw_cap_initialized & HW_CAP_KDMA) == HW_CAP_KDMA)
return;
reg_base = gaudi2_dma_core_blocks_bases[DMA_CORE_ID_KDMA];
gaudi2_init_dma_core(hdev, reg_base, DMA_CORE_ID_KDMA, true);
gaudi2->hw_cap_initialized |= HW_CAP_KDMA;
}
static void gaudi2_init_pdma(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 reg_base;
if ((gaudi2->hw_cap_initialized & HW_CAP_PDMA_MASK) == HW_CAP_PDMA_MASK)
return;
reg_base = gaudi2_dma_core_blocks_bases[DMA_CORE_ID_PDMA0];
gaudi2_init_dma_core(hdev, reg_base, DMA_CORE_ID_PDMA0, false);
reg_base = gaudi2_qm_blocks_bases[GAUDI2_QUEUE_ID_PDMA_0_0];
gaudi2_init_qman(hdev, reg_base, GAUDI2_QUEUE_ID_PDMA_0_0);
reg_base = gaudi2_dma_core_blocks_bases[DMA_CORE_ID_PDMA1];
gaudi2_init_dma_core(hdev, reg_base, DMA_CORE_ID_PDMA1, false);
reg_base = gaudi2_qm_blocks_bases[GAUDI2_QUEUE_ID_PDMA_1_0];
gaudi2_init_qman(hdev, reg_base, GAUDI2_QUEUE_ID_PDMA_1_0);
gaudi2->hw_cap_initialized |= HW_CAP_PDMA_MASK;
}
static void gaudi2_init_edma_instance(struct hl_device *hdev, u8 seq)
{
u32 reg_base, base_edma_core_id, base_edma_qman_id;
base_edma_core_id = DMA_CORE_ID_EDMA0 + seq;
base_edma_qman_id = edma_stream_base[seq];
reg_base = gaudi2_dma_core_blocks_bases[base_edma_core_id];
gaudi2_init_dma_core(hdev, reg_base, base_edma_core_id, false);
reg_base = gaudi2_qm_blocks_bases[base_edma_qman_id];
gaudi2_init_qman(hdev, reg_base, base_edma_qman_id);
}
static void gaudi2_init_edma(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
struct gaudi2_device *gaudi2 = hdev->asic_specific;
int dcore, inst;
if ((gaudi2->hw_cap_initialized & HW_CAP_EDMA_MASK) == HW_CAP_EDMA_MASK)
return;
for (dcore = 0 ; dcore < NUM_OF_DCORES ; dcore++) {
for (inst = 0 ; inst < NUM_OF_EDMA_PER_DCORE ; inst++) {
u8 seq = dcore * NUM_OF_EDMA_PER_DCORE + inst;
if (!(prop->edma_enabled_mask & BIT(seq)))
continue;
gaudi2_init_edma_instance(hdev, seq);
gaudi2->hw_cap_initialized |= BIT_ULL(HW_CAP_EDMA_SHIFT + seq);
}
}
}
static void gaudi2_arm_monitors_for_virt_msix_db(struct hl_device *hdev, u32 sob_id,
u32 first_mon_id, u32 interrupt_id)
{
u32 sob_offset, first_mon_offset, mon_offset, payload, sob_group, mode, arm, config;
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u64 addr;
u8 mask;
sob_offset = sob_id * sizeof(u32);
WREG32(mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0 + sob_offset, 0);
first_mon_offset = first_mon_id * sizeof(u32);
mon_offset = first_mon_offset + sizeof(u32);
addr = CFG_BASE + mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0 + sob_offset;
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0 + mon_offset, lower_32_bits(addr));
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_ADDRH_0 + mon_offset, upper_32_bits(addr));
payload = FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_SOB_OBJ_VAL_MASK, 0x7FFF) |
FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_SOB_OBJ_SIGN_MASK, 1) |
FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_SOB_OBJ_INC_MASK, 1);
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_DATA_0 + mon_offset, payload);
mon_offset = first_mon_offset + 2 * sizeof(u32);
addr = CFG_BASE + mmDCORE0_SYNC_MNGR_OBJS_MON_ARM_0 + first_mon_offset;
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0 + mon_offset, lower_32_bits(addr));
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_ADDRH_0 + mon_offset, upper_32_bits(addr));
sob_group = sob_id / 8;
mask = ~BIT(sob_id & 0x7);
mode = 0;
arm = FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_MON_ARM_SID_MASK, sob_group) |
FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_MON_ARM_MASK_MASK, mask) |
FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_MON_ARM_SOP_MASK, mode) |
FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_MON_ARM_SOD_MASK, 1);
payload = arm;
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_DATA_0 + mon_offset, payload);
mon_offset = first_mon_offset;
config = FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_MON_CONFIG_WR_NUM_MASK, 2);
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_CONFIG_0 + mon_offset, config);
addr = gaudi2->virt_msix_db_dma_addr;
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0 + mon_offset, lower_32_bits(addr));
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_ADDRH_0 + mon_offset, upper_32_bits(addr));
payload = interrupt_id;
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_DATA_0 + mon_offset, payload);
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_ARM_0 + mon_offset, arm);
}
static void gaudi2_prepare_sm_for_virt_msix_db(struct hl_device *hdev)
{
u32 decoder_id, sob_id, first_mon_id, interrupt_id;
struct asic_fixed_properties *prop = &hdev->asic_prop;
for (decoder_id = 0 ; decoder_id < NUMBER_OF_DEC ; ++decoder_id) {
if (!(prop->decoder_enabled_mask & BIT(decoder_id)))
continue;
sob_id = GAUDI2_RESERVED_SOB_DEC_NRM_FIRST + decoder_id;
first_mon_id = GAUDI2_RESERVED_MON_DEC_NRM_FIRST + 3 * decoder_id;
interrupt_id = GAUDI2_IRQ_NUM_DCORE0_DEC0_NRM + 2 * decoder_id;
gaudi2_arm_monitors_for_virt_msix_db(hdev, sob_id, first_mon_id, interrupt_id);
sob_id = GAUDI2_RESERVED_SOB_DEC_ABNRM_FIRST + decoder_id;
first_mon_id = GAUDI2_RESERVED_MON_DEC_ABNRM_FIRST + 3 * decoder_id;
interrupt_id += 1;
gaudi2_arm_monitors_for_virt_msix_db(hdev, sob_id, first_mon_id, interrupt_id);
}
}
static void gaudi2_init_sm(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u64 cq_address;
u32 reg_val;
int i;
reg_val = FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_MON_CONFIG_CQ_EN_MASK, 1);
reg_val |= FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_MON_CONFIG_LBW_EN_MASK, 1);
for (i = 0 ; i < GAUDI2_MAX_PENDING_CS ; i++)
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_CONFIG_0 + (4 * i), reg_val);
reg_val = FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_MON_CONFIG_CQ_EN_MASK, 1);
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_CONFIG_0 + (4 * i), reg_val);
WREG32(mmDCORE0_SYNC_MNGR_GLBL_LBW_ADDR_L_0, lower_32_bits(gaudi2->virt_msix_db_dma_addr));
WREG32(mmDCORE0_SYNC_MNGR_GLBL_LBW_ADDR_H_0, upper_32_bits(gaudi2->virt_msix_db_dma_addr));
WREG32(mmDCORE0_SYNC_MNGR_GLBL_LBW_DATA_0, GAUDI2_IRQ_NUM_COMPLETION);
for (i = 0 ; i < GAUDI2_RESERVED_CQ_NUMBER ; i++) {
cq_address =
hdev->completion_queue[i].bus_address;
WREG32(mmDCORE0_SYNC_MNGR_GLBL_CQ_BASE_ADDR_L_0 + (4 * i),
lower_32_bits(cq_address));
WREG32(mmDCORE0_SYNC_MNGR_GLBL_CQ_BASE_ADDR_H_0 + (4 * i),
upper_32_bits(cq_address));
WREG32(mmDCORE0_SYNC_MNGR_GLBL_CQ_SIZE_LOG2_0 + (4 * i),
ilog2(HL_CQ_SIZE_IN_BYTES));
}
WREG32(mmDCORE0_SYNC_MNGR_GLBL_ASID_SEC, 0x10000);
WREG32(mmDCORE0_SYNC_MNGR_GLBL_ASID_NONE_SEC_PRIV, 0);
gaudi2_prepare_sm_for_virt_msix_db(hdev);
}
static void gaudi2_init_mme_acc(struct hl_device *hdev, u32 reg_base)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 reg_val;
int i;
reg_val = FIELD_PREP(MME_ACC_INTR_MASK_WBC_ERR_RESP_MASK, 0);
reg_val |= FIELD_PREP(MME_ACC_INTR_MASK_AP_SRC_POS_INF_MASK, 1);
reg_val |= FIELD_PREP(MME_ACC_INTR_MASK_AP_SRC_NEG_INF_MASK, 1);
reg_val |= FIELD_PREP(MME_ACC_INTR_MASK_AP_SRC_NAN_MASK, 1);
reg_val |= FIELD_PREP(MME_ACC_INTR_MASK_AP_RESULT_POS_INF_MASK, 1);
reg_val |= FIELD_PREP(MME_ACC_INTR_MASK_AP_RESULT_NEG_INF_MASK, 1);
WREG32(reg_base + MME_ACC_INTR_MASK_OFFSET, reg_val);
WREG32(reg_base + MME_ACC_AP_LFSR_POLY_OFFSET, 0x80DEADAF);
for (i = 0 ; i < MME_NUM_OF_LFSR_SEEDS ; i++) {
WREG32(reg_base + MME_ACC_AP_LFSR_SEED_SEL_OFFSET, i);
WREG32(reg_base + MME_ACC_AP_LFSR_SEED_WDATA_OFFSET, gaudi2->lfsr_rand_seeds[i]);
}
}
static void gaudi2_init_dcore_mme(struct hl_device *hdev, int dcore_id,
bool config_qman_only)
{
u32 queue_id_base, reg_base;
switch (dcore_id) {
case 0:
queue_id_base = GAUDI2_QUEUE_ID_DCORE0_MME_0_0;
break;
case 1:
queue_id_base = GAUDI2_QUEUE_ID_DCORE1_MME_0_0;
break;
case 2:
queue_id_base = GAUDI2_QUEUE_ID_DCORE2_MME_0_0;
break;
case 3:
queue_id_base = GAUDI2_QUEUE_ID_DCORE3_MME_0_0;
break;
default:
dev_err(hdev->dev, "Invalid dcore id %u\n", dcore_id);
return;
}
if (!config_qman_only) {
reg_base = gaudi2_mme_acc_blocks_bases[dcore_id];
gaudi2_init_mme_acc(hdev, reg_base);
}
reg_base = gaudi2_qm_blocks_bases[queue_id_base];
gaudi2_init_qman(hdev, reg_base, queue_id_base);
}
static void gaudi2_init_mme(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
int i;
if ((gaudi2->hw_cap_initialized & HW_CAP_MME_MASK) == HW_CAP_MME_MASK)
return;
for (i = 0 ; i < NUM_OF_DCORES ; i++) {
gaudi2_init_dcore_mme(hdev, i, false);
gaudi2->hw_cap_initialized |= BIT_ULL(HW_CAP_MME_SHIFT + i);
}
}
static void gaudi2_init_tpc_cfg(struct hl_device *hdev, u32 reg_base)
{
WREG32(reg_base + TPC_CFG_TPC_INTR_MASK_OFFSET, 0x23FFFE);
WREG32(reg_base + TPC_CFG_MSS_CONFIG_OFFSET,
2 << DCORE0_TPC0_CFG_MSS_CONFIG_ICACHE_FETCH_LINE_NUM_SHIFT);
}
struct gaudi2_tpc_init_cfg_data {
enum gaudi2_queue_id dcore_tpc_qid_base[NUM_OF_DCORES];
};
static void gaudi2_init_tpc_config(struct hl_device *hdev, int dcore, int inst,
u32 offset, struct iterate_module_ctx *ctx)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
struct gaudi2_tpc_init_cfg_data *cfg_data = ctx->data;
u32 queue_id_base;
u8 seq;
queue_id_base = cfg_data->dcore_tpc_qid_base[dcore] + (inst * NUM_OF_PQ_PER_QMAN);
if (dcore == 0 && inst == (NUM_DCORE0_TPC - 1))
seq = NUM_OF_DCORES * NUM_OF_TPC_PER_DCORE;
else
seq = dcore * NUM_OF_TPC_PER_DCORE + inst;
gaudi2_init_tpc_cfg(hdev, mmDCORE0_TPC0_CFG_BASE + offset);
gaudi2_init_qman(hdev, mmDCORE0_TPC0_QM_BASE + offset, queue_id_base);
gaudi2->tpc_hw_cap_initialized |= BIT_ULL(HW_CAP_TPC_SHIFT + seq);
}
static void gaudi2_init_tpc(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
struct gaudi2_tpc_init_cfg_data init_cfg_data;
struct iterate_module_ctx tpc_iter;
if (!hdev->asic_prop.tpc_enabled_mask)
return;
if ((gaudi2->tpc_hw_cap_initialized & HW_CAP_TPC_MASK) == HW_CAP_TPC_MASK)
return;
init_cfg_data.dcore_tpc_qid_base[0] = GAUDI2_QUEUE_ID_DCORE0_TPC_0_0;
init_cfg_data.dcore_tpc_qid_base[1] = GAUDI2_QUEUE_ID_DCORE1_TPC_0_0;
init_cfg_data.dcore_tpc_qid_base[2] = GAUDI2_QUEUE_ID_DCORE2_TPC_0_0;
init_cfg_data.dcore_tpc_qid_base[3] = GAUDI2_QUEUE_ID_DCORE3_TPC_0_0;
tpc_iter.fn = &gaudi2_init_tpc_config;
tpc_iter.data = &init_cfg_data;
gaudi2_iterate_tpcs(hdev, &tpc_iter);
}
static void gaudi2_init_rotator(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 i, reg_base, queue_id;
queue_id = GAUDI2_QUEUE_ID_ROT_0_0;
for (i = 0 ; i < NUM_OF_ROT ; i++, queue_id += NUM_OF_PQ_PER_QMAN) {
reg_base = gaudi2_qm_blocks_bases[queue_id];
gaudi2_init_qman(hdev, reg_base, queue_id);
gaudi2->hw_cap_initialized |= BIT_ULL(HW_CAP_ROT_SHIFT + i);
}
}
static void gaudi2_init_vdec_brdg_ctrl(struct hl_device *hdev, u64 base_addr, u32 decoder_id)
{
u32 sob_id;
sob_id = GAUDI2_RESERVED_SOB_DEC_NRM_FIRST + decoder_id;
WREG32(base_addr + BRDG_CTRL_NRM_MSIX_LBW_AWADDR,
mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0 + sob_id * sizeof(u32));
WREG32(base_addr + BRDG_CTRL_NRM_MSIX_LBW_WDATA, GAUDI2_SOB_INCREMENT_BY_ONE);
sob_id = GAUDI2_RESERVED_SOB_DEC_ABNRM_FIRST + decoder_id;
WREG32(base_addr + BRDG_CTRL_ABNRM_MSIX_LBW_AWADDR,
mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0 + sob_id * sizeof(u32));
WREG32(base_addr + BRDG_CTRL_ABNRM_MSIX_LBW_WDATA, GAUDI2_SOB_INCREMENT_BY_ONE);
}
static void gaudi2_init_dec(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 dcore_id, dec_id, dec_bit;
u64 base_addr;
if (!hdev->asic_prop.decoder_enabled_mask)
return;
if ((gaudi2->dec_hw_cap_initialized & HW_CAP_DEC_MASK) == HW_CAP_DEC_MASK)
return;
for (dcore_id = 0 ; dcore_id < NUM_OF_DCORES ; dcore_id++)
for (dec_id = 0 ; dec_id < NUM_OF_DEC_PER_DCORE ; dec_id++) {
dec_bit = dcore_id * NUM_OF_DEC_PER_DCORE + dec_id;
if (!(hdev->asic_prop.decoder_enabled_mask & BIT(dec_bit)))
continue;
base_addr = mmDCORE0_DEC0_CMD_BASE +
BRDG_CTRL_BLOCK_OFFSET +
dcore_id * DCORE_OFFSET +
dec_id * DCORE_VDEC_OFFSET;
gaudi2_init_vdec_brdg_ctrl(hdev, base_addr, dec_bit);
gaudi2->dec_hw_cap_initialized |= BIT_ULL(HW_CAP_DEC_SHIFT + dec_bit);
}
for (dec_id = 0 ; dec_id < NUM_OF_PCIE_VDEC ; dec_id++) {
dec_bit = PCIE_DEC_SHIFT + dec_id;
if (!(hdev->asic_prop.decoder_enabled_mask & BIT(dec_bit)))
continue;
base_addr = mmPCIE_DEC0_CMD_BASE + BRDG_CTRL_BLOCK_OFFSET +
dec_id * DCORE_VDEC_OFFSET;
gaudi2_init_vdec_brdg_ctrl(hdev, base_addr, dec_bit);
gaudi2->dec_hw_cap_initialized |= BIT_ULL(HW_CAP_DEC_SHIFT + dec_bit);
}
}
static int gaudi2_mmu_update_asid_hop0_addr(struct hl_device *hdev,
u32 stlb_base, u32 asid, u64 phys_addr)
{
u32 status, timeout_usec;
int rc;
if (hdev->pldm || !hdev->pdev)
timeout_usec = GAUDI2_PLDM_MMU_TIMEOUT_USEC;
else
timeout_usec = MMU_CONFIG_TIMEOUT_USEC;
WREG32(stlb_base + STLB_ASID_OFFSET, asid);
WREG32(stlb_base + STLB_HOP0_PA43_12_OFFSET, phys_addr >> MMU_HOP0_PA43_12_SHIFT);
WREG32(stlb_base + STLB_HOP0_PA63_44_OFFSET, phys_addr >> MMU_HOP0_PA63_44_SHIFT);
WREG32(stlb_base + STLB_BUSY_OFFSET, 0x80000000);
rc = hl_poll_timeout(
hdev,
stlb_base + STLB_BUSY_OFFSET,
status,
!(status & 0x80000000),
1000,
timeout_usec);
if (rc) {
dev_err(hdev->dev, "Timeout during MMU hop0 config of asid %d\n", asid);
return rc;
}
return 0;
}
static void gaudi2_mmu_send_invalidate_cache_cmd(struct hl_device *hdev, u32 stlb_base,
u32 start_offset, u32 inv_start_val,
u32 flags)
{
if (flags & MMU_OP_CLEAR_MEMCACHE)
WREG32(mmPMMU_HBW_STLB_MEM_CACHE_INVALIDATION, 0x1);
if (flags & MMU_OP_SKIP_LOW_CACHE_INV)
return;
WREG32(stlb_base + start_offset, inv_start_val);
}
static int gaudi2_mmu_invalidate_cache_status_poll(struct hl_device *hdev, u32 stlb_base,
struct gaudi2_cache_invld_params *inv_params)
{
u32 status, timeout_usec, start_offset;
int rc;
timeout_usec = (hdev->pldm) ? GAUDI2_PLDM_MMU_TIMEOUT_USEC :
GAUDI2_MMU_CACHE_INV_TIMEOUT_USEC;
if (inv_params->flags & MMU_OP_CLEAR_MEMCACHE) {
rc = hl_poll_timeout(
hdev,
mmPMMU_HBW_STLB_MEM_CACHE_INV_STATUS,
status,
status & 0x1,
1000,
timeout_usec);
if (rc)
return rc;
WREG32(mmPMMU_HBW_STLB_MEM_CACHE_INV_STATUS, 0x0);
}
if (inv_params->flags & MMU_OP_SKIP_LOW_CACHE_INV)
return 0;
start_offset = inv_params->range_invalidation ?
STLB_RANGE_CACHE_INVALIDATION_OFFSET : STLB_INV_ALL_START_OFFSET;
rc = hl_poll_timeout(
hdev,
stlb_base + start_offset,
status,
!(status & 0x1),
1000,
timeout_usec);
return rc;
}
bool gaudi2_is_hmmu_enabled(struct hl_device *hdev, int dcore_id, int hmmu_id)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 hw_cap;
hw_cap = HW_CAP_DCORE0_DMMU0 << (NUM_OF_HMMU_PER_DCORE * dcore_id + hmmu_id);
if (gaudi2->hw_cap_initialized & hw_cap)
return true;
return false;
}
static inline u32 get_hmmu_stlb_base(int dcore_id, int hmmu_id)
{
u32 offset;
offset = (u32) (dcore_id * DCORE_OFFSET + hmmu_id * DCORE_HMMU_OFFSET);
return (u32)(mmDCORE0_HMMU0_STLB_BASE + offset);
}
static void gaudi2_mmu_invalidate_cache_trigger(struct hl_device *hdev, u32 stlb_base,
struct gaudi2_cache_invld_params *inv_params)
{
u32 start_offset;
if (inv_params->range_invalidation) {
u64 start = inv_params->start_va - 1;
start_offset = STLB_RANGE_CACHE_INVALIDATION_OFFSET;
WREG32(stlb_base + STLB_RANGE_INV_START_LSB_OFFSET,
start >> MMU_RANGE_INV_VA_LSB_SHIFT);
WREG32(stlb_base + STLB_RANGE_INV_START_MSB_OFFSET,
start >> MMU_RANGE_INV_VA_MSB_SHIFT);
WREG32(stlb_base + STLB_RANGE_INV_END_LSB_OFFSET,
inv_params->end_va >> MMU_RANGE_INV_VA_LSB_SHIFT);
WREG32(stlb_base + STLB_RANGE_INV_END_MSB_OFFSET,
inv_params->end_va >> MMU_RANGE_INV_VA_MSB_SHIFT);
} else {
start_offset = STLB_INV_ALL_START_OFFSET;
}
gaudi2_mmu_send_invalidate_cache_cmd(hdev, stlb_base, start_offset,
inv_params->inv_start_val, inv_params->flags);
}
static inline void gaudi2_hmmu_invalidate_cache_trigger(struct hl_device *hdev,
int dcore_id, int hmmu_id,
struct gaudi2_cache_invld_params *inv_params)
{
u32 stlb_base = get_hmmu_stlb_base(dcore_id, hmmu_id);
gaudi2_mmu_invalidate_cache_trigger(hdev, stlb_base, inv_params);
}
static inline int gaudi2_hmmu_invalidate_cache_status_poll(struct hl_device *hdev,
int dcore_id, int hmmu_id,
struct gaudi2_cache_invld_params *inv_params)
{
u32 stlb_base = get_hmmu_stlb_base(dcore_id, hmmu_id);
return gaudi2_mmu_invalidate_cache_status_poll(hdev, stlb_base, inv_params);
}
static int gaudi2_hmmus_invalidate_cache(struct hl_device *hdev,
struct gaudi2_cache_invld_params *inv_params)
{
int dcore_id, hmmu_id;
for (dcore_id = 0 ; dcore_id < NUM_OF_DCORES ; dcore_id++) {
for (hmmu_id = 0 ; hmmu_id < NUM_OF_HMMU_PER_DCORE ; hmmu_id++) {
if (!gaudi2_is_hmmu_enabled(hdev, dcore_id, hmmu_id))
continue;
gaudi2_hmmu_invalidate_cache_trigger(hdev, dcore_id, hmmu_id, inv_params);
}
}
for (dcore_id = 0 ; dcore_id < NUM_OF_DCORES ; dcore_id++) {
for (hmmu_id = 0 ; hmmu_id < NUM_OF_HMMU_PER_DCORE ; hmmu_id++) {
int rc;
if (!gaudi2_is_hmmu_enabled(hdev, dcore_id, hmmu_id))
continue;
rc = gaudi2_hmmu_invalidate_cache_status_poll(hdev, dcore_id, hmmu_id,
inv_params);
if (rc)
return rc;
}
}
return 0;
}
static int gaudi2_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard, u32 flags)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
struct gaudi2_cache_invld_params invld_params;
int rc = 0;
if (hdev->reset_info.hard_reset_pending)
return rc;
invld_params.range_invalidation = false;
invld_params.inv_start_val = 1;
if ((flags & MMU_OP_USERPTR) && (gaudi2->hw_cap_initialized & HW_CAP_PMMU)) {
invld_params.flags = flags;
gaudi2_mmu_invalidate_cache_trigger(hdev, mmPMMU_HBW_STLB_BASE, &invld_params);
rc = gaudi2_mmu_invalidate_cache_status_poll(hdev, mmPMMU_HBW_STLB_BASE,
&invld_params);
} else if (flags & MMU_OP_PHYS_PACK) {
invld_params.flags = 0;
rc = gaudi2_hmmus_invalidate_cache(hdev, &invld_params);
}
return rc;
}
static int gaudi2_mmu_invalidate_cache_range(struct hl_device *hdev, bool is_hard,
u32 flags, u32 asid, u64 va, u64 size)
{
struct gaudi2_cache_invld_params invld_params = {0};
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u64 start_va, end_va;
u32 inv_start_val;
int rc = 0;
if (hdev->reset_info.hard_reset_pending)
return 0;
inv_start_val = (1 << MMU_RANGE_INV_EN_SHIFT |
1 << MMU_RANGE_INV_ASID_EN_SHIFT |
asid << MMU_RANGE_INV_ASID_SHIFT);
start_va = va;
end_va = start_va + size;
if ((flags & MMU_OP_USERPTR) && (gaudi2->hw_cap_initialized & HW_CAP_PMMU)) {
if (start_va) {
invld_params.range_invalidation = true;
invld_params.start_va = start_va;
invld_params.end_va = end_va;
invld_params.inv_start_val = inv_start_val;
invld_params.flags = flags | MMU_OP_CLEAR_MEMCACHE;
} else {
invld_params.range_invalidation = false;
invld_params.inv_start_val = 1;
invld_params.flags = flags;
}
gaudi2_mmu_invalidate_cache_trigger(hdev, mmPMMU_HBW_STLB_BASE, &invld_params);
rc = gaudi2_mmu_invalidate_cache_status_poll(hdev, mmPMMU_HBW_STLB_BASE,
&invld_params);
if (rc)
return rc;
} else if (flags & MMU_OP_PHYS_PACK) {
invld_params.start_va = gaudi2_mmu_scramble_addr(hdev, start_va);
invld_params.end_va = gaudi2_mmu_scramble_addr(hdev, end_va);
invld_params.inv_start_val = inv_start_val;
invld_params.flags = flags;
rc = gaudi2_hmmus_invalidate_cache(hdev, &invld_params);
}
return rc;
}
static int gaudi2_mmu_update_hop0_addr(struct hl_device *hdev, u32 stlb_base)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
u64 hop0_addr;
u32 asid, max_asid = prop->max_asid;
int rc;
if (hdev->pldm)
max_asid = min((u32) 8, max_asid);
for (asid = 0 ; asid < max_asid ; asid++) {
hop0_addr = hdev->mmu_priv.hr.mmu_asid_hop0[asid].phys_addr;
rc = gaudi2_mmu_update_asid_hop0_addr(hdev, stlb_base, asid, hop0_addr);
if (rc) {
dev_err(hdev->dev, "failed to set hop0 addr for asid %d\n", asid);
return rc;
}
}
return 0;
}
static int gaudi2_mmu_init_common(struct hl_device *hdev, u32 mmu_base, u32 stlb_base)
{
u32 status, timeout_usec;
int rc;
if (hdev->pldm || !hdev->pdev)
timeout_usec = GAUDI2_PLDM_MMU_TIMEOUT_USEC;
else
timeout_usec = GAUDI2_MMU_CACHE_INV_TIMEOUT_USEC;
WREG32(stlb_base + STLB_INV_ALL_START_OFFSET, 1);
rc = hl_poll_timeout(
hdev,
stlb_base + STLB_SRAM_INIT_OFFSET,
status,
!status,
1000,
timeout_usec);
if (rc)
dev_notice_ratelimited(hdev->dev, "Timeout when waiting for MMU SRAM init\n");
rc = gaudi2_mmu_update_hop0_addr(hdev, stlb_base);
if (rc)
return rc;
WREG32(mmu_base + MMU_BYPASS_OFFSET, 0);
rc = hl_poll_timeout(
hdev,
stlb_base + STLB_INV_ALL_START_OFFSET,
status,
!status,
1000,
timeout_usec);
if (rc)
dev_notice_ratelimited(hdev->dev, "Timeout when waiting for MMU invalidate all\n");
WREG32(mmu_base + MMU_ENABLE_OFFSET, 1);
return rc;
}
static int gaudi2_pci_mmu_init(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 mmu_base, stlb_base;
int rc;
if (gaudi2->hw_cap_initialized & HW_CAP_PMMU)
return 0;
mmu_base = mmPMMU_HBW_MMU_BASE;
stlb_base = mmPMMU_HBW_STLB_BASE;
RMWREG32_SHIFTED(stlb_base + STLB_HOP_CONFIGURATION_OFFSET,
(0 << PMMU_HBW_STLB_HOP_CONFIGURATION_FIRST_HOP_SHIFT) |
(5 << PMMU_HBW_STLB_HOP_CONFIGURATION_FIRST_LOOKUP_HOP_SMALL_P_SHIFT) |
(4 << PMMU_HBW_STLB_HOP_CONFIGURATION_FIRST_LOOKUP_HOP_LARGE_P_SHIFT) |
(5 << PMMU_HBW_STLB_HOP_CONFIGURATION_LAST_HOP_SHIFT) |
(5 << PMMU_HBW_STLB_HOP_CONFIGURATION_FOLLOWER_HOP_SHIFT),
PMMU_HBW_STLB_HOP_CONFIGURATION_FIRST_HOP_MASK |
PMMU_HBW_STLB_HOP_CONFIGURATION_FIRST_LOOKUP_HOP_SMALL_P_MASK |
PMMU_HBW_STLB_HOP_CONFIGURATION_FIRST_LOOKUP_HOP_LARGE_P_MASK |
PMMU_HBW_STLB_HOP_CONFIGURATION_LAST_HOP_MASK |
PMMU_HBW_STLB_HOP_CONFIGURATION_FOLLOWER_HOP_MASK);
WREG32(stlb_base + STLB_LL_LOOKUP_MASK_63_32_OFFSET, 0);
if (PAGE_SIZE == SZ_64K) {
RMWREG32_SHIFTED(mmu_base + MMU_STATIC_MULTI_PAGE_SIZE_OFFSET,
FIELD_PREP(DCORE0_HMMU0_MMU_STATIC_MULTI_PAGE_SIZE_HOP5_PAGE_SIZE_MASK, 4) |
FIELD_PREP(DCORE0_HMMU0_MMU_STATIC_MULTI_PAGE_SIZE_HOP4_PAGE_SIZE_MASK, 3) |
FIELD_PREP(
DCORE0_HMMU0_MMU_STATIC_MULTI_PAGE_SIZE_CFG_8_BITS_HOP_MODE_EN_MASK,
1),
DCORE0_HMMU0_MMU_STATIC_MULTI_PAGE_SIZE_HOP5_PAGE_SIZE_MASK |
DCORE0_HMMU0_MMU_STATIC_MULTI_PAGE_SIZE_HOP4_PAGE_SIZE_MASK |
DCORE0_HMMU0_MMU_STATIC_MULTI_PAGE_SIZE_CFG_8_BITS_HOP_MODE_EN_MASK);
}
WREG32(mmu_base + MMU_SPI_SEI_MASK_OFFSET, GAUDI2_PMMU_SPI_SEI_ENABLE_MASK);
rc = gaudi2_mmu_init_common(hdev, mmu_base, stlb_base);
if (rc)
return rc;
gaudi2->hw_cap_initialized |= HW_CAP_PMMU;
return 0;
}
static int gaudi2_dcore_hmmu_init(struct hl_device *hdev, int dcore_id,
int hmmu_id)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 offset, mmu_base, stlb_base, hw_cap;
u8 dmmu_seq;
int rc;
dmmu_seq = NUM_OF_HMMU_PER_DCORE * dcore_id + hmmu_id;
hw_cap = HW_CAP_DCORE0_DMMU0 << dmmu_seq;
if ((gaudi2->hw_cap_initialized & hw_cap) || !(prop->hmmu_hif_enabled_mask & BIT(dmmu_seq)))
return 0;
offset = (u32) (dcore_id * DCORE_OFFSET + hmmu_id * DCORE_HMMU_OFFSET);
mmu_base = mmDCORE0_HMMU0_MMU_BASE + offset;
stlb_base = mmDCORE0_HMMU0_STLB_BASE + offset;
RMWREG32(mmu_base + MMU_STATIC_MULTI_PAGE_SIZE_OFFSET, 5 ,
MMU_STATIC_MULTI_PAGE_SIZE_HOP4_PAGE_SIZE_MASK);
RMWREG32_SHIFTED(stlb_base + STLB_HOP_CONFIGURATION_OFFSET,
FIELD_PREP(DCORE0_HMMU0_STLB_HOP_CONFIGURATION_FIRST_HOP_MASK, 0) |
FIELD_PREP(DCORE0_HMMU0_STLB_HOP_CONFIGURATION_FIRST_LOOKUP_HOP_SMALL_P_MASK, 3) |
FIELD_PREP(DCORE0_HMMU0_STLB_HOP_CONFIGURATION_FIRST_LOOKUP_HOP_LARGE_P_MASK, 3) |
FIELD_PREP(DCORE0_HMMU0_STLB_HOP_CONFIGURATION_LAST_HOP_MASK, 3) |
FIELD_PREP(DCORE0_HMMU0_STLB_HOP_CONFIGURATION_FOLLOWER_HOP_MASK, 3),
DCORE0_HMMU0_STLB_HOP_CONFIGURATION_FIRST_HOP_MASK |
DCORE0_HMMU0_STLB_HOP_CONFIGURATION_FIRST_LOOKUP_HOP_SMALL_P_MASK |
DCORE0_HMMU0_STLB_HOP_CONFIGURATION_FIRST_LOOKUP_HOP_LARGE_P_MASK |
DCORE0_HMMU0_STLB_HOP_CONFIGURATION_LAST_HOP_MASK |
DCORE0_HMMU0_STLB_HOP_CONFIGURATION_FOLLOWER_HOP_MASK);
RMWREG32(stlb_base + STLB_HOP_CONFIGURATION_OFFSET, 1,
STLB_HOP_CONFIGURATION_ONLY_LARGE_PAGE_MASK);
WREG32(mmu_base + MMU_SPI_SEI_MASK_OFFSET, GAUDI2_HMMU_SPI_SEI_ENABLE_MASK);
rc = gaudi2_mmu_init_common(hdev, mmu_base, stlb_base);
if (rc)
return rc;
gaudi2->hw_cap_initialized |= hw_cap;
return 0;
}
static int gaudi2_hbm_mmu_init(struct hl_device *hdev)
{
int rc, dcore_id, hmmu_id;
for (dcore_id = 0 ; dcore_id < NUM_OF_DCORES ; dcore_id++)
for (hmmu_id = 0 ; hmmu_id < NUM_OF_HMMU_PER_DCORE; hmmu_id++) {
rc = gaudi2_dcore_hmmu_init(hdev, dcore_id, hmmu_id);
if (rc)
return rc;
}
return 0;
}
static int gaudi2_mmu_init(struct hl_device *hdev)
{
int rc;
rc = gaudi2_pci_mmu_init(hdev);
if (rc)
return rc;
rc = gaudi2_hbm_mmu_init(hdev);
if (rc)
return rc;
return 0;
}
static int gaudi2_hw_init(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
int rc;
WREG32(mmHW_STATE, HL_DEVICE_HW_STATE_DIRTY);
RREG32(mmHW_STATE);
if (hdev->asic_prop.iatu_done_by_fw)
gaudi2->dram_bar_cur_addr = DRAM_PHYS_BASE;
if (gaudi2_set_hbm_bar_base(hdev, DRAM_PHYS_BASE) == U64_MAX) {
dev_err(hdev->dev, "failed to map HBM bar to DRAM base address\n");
return -EIO;
}
rc = gaudi2_init_cpu(hdev);
if (rc) {
dev_err(hdev->dev, "failed to initialize CPU\n");
return rc;
}
gaudi2_init_scrambler_hbm(hdev);
gaudi2_init_kdma(hdev);
rc = gaudi2_init_cpu_queues(hdev, GAUDI2_CPU_TIMEOUT_USEC);
if (rc) {
dev_err(hdev->dev, "failed to initialize CPU H/W queues %d\n", rc);
return rc;
}
rc = gaudi2->cpucp_info_get(hdev);
if (rc) {
dev_err(hdev->dev, "Failed to get cpucp info\n");
return rc;
}
rc = gaudi2_mmu_init(hdev);
if (rc)
return rc;
gaudi2_init_pdma(hdev);
gaudi2_init_edma(hdev);
gaudi2_init_sm(hdev);
gaudi2_init_tpc(hdev);
gaudi2_init_mme(hdev);
gaudi2_init_rotator(hdev);
gaudi2_init_dec(hdev);
gaudi2_enable_timestamp(hdev);
rc = gaudi2_coresight_init(hdev);
if (rc)
goto disable_queues;
rc = gaudi2_enable_msix(hdev);
if (rc)
goto disable_queues;
RREG32(mmHW_STATE);
return 0;
disable_queues:
gaudi2_disable_dma_qmans(hdev);
gaudi2_disable_mme_qmans(hdev);
gaudi2_disable_tpc_qmans(hdev);
gaudi2_disable_rot_qmans(hdev);
gaudi2_disable_nic_qmans(hdev);
gaudi2_disable_timestamp(hdev);
return rc;
}
static void gaudi2_send_hard_reset_cmd(struct hl_device *hdev)
{
struct cpu_dyn_regs *dyn_regs = &hdev->fw_loader.dynamic_loader.comm_desc.cpu_dyn_regs;
bool heartbeat_reset, preboot_only, cpu_initialized = false;
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 cpu_boot_status;
preboot_only = (hdev->fw_loader.fw_comp_loaded == FW_TYPE_PREBOOT_CPU);
heartbeat_reset = (hdev->reset_info.curr_reset_cause == HL_RESET_CAUSE_HEARTBEAT);
cpu_boot_status = RREG32(mmPSOC_GLOBAL_CONF_CPU_BOOT_STATUS);
if (gaudi2 && (gaudi2->hw_cap_initialized & HW_CAP_CPU) &&
(cpu_boot_status == CPU_BOOT_STATUS_SRAM_AVAIL))
cpu_initialized = true;
if (!preboot_only && cpu_initialized) {
WREG32(le32_to_cpu(dyn_regs->gic_host_halt_irq),
gaudi2_irq_map_table[GAUDI2_EVENT_CPU_HALT_MACHINE].cpu_id);
msleep(GAUDI2_CPU_RESET_WAIT_MSEC);
}
if (heartbeat_reset || preboot_only || !cpu_initialized) {
if (hdev->asic_prop.hard_reset_done_by_fw)
hl_fw_ask_hard_reset_without_linux(hdev);
else
hl_fw_ask_halt_machine_without_linux(hdev);
}
}
static void gaudi2_execute_hard_reset(struct hl_device *hdev)
{
if (hdev->asic_prop.hard_reset_done_by_fw) {
gaudi2_send_hard_reset_cmd(hdev);
return;
}
WREG32(mmPCIE_AUX_FLR_CTRL,
(PCIE_AUX_FLR_CTRL_HW_CTRL_MASK | PCIE_AUX_FLR_CTRL_INT_MASK_MASK));
gaudi2_send_hard_reset_cmd(hdev);
WREG32(mmPSOC_RESET_CONF_SW_ALL_RST, 1);
}
static int gaudi2_get_soft_rst_done_indication(struct hl_device *hdev, u32 poll_timeout_us)
{
int i, rc = 0;
u32 reg_val;
for (i = 0 ; i < GAUDI2_RESET_POLL_CNT ; i++)
rc = hl_poll_timeout(
hdev,
mmCPU_RST_STATUS_TO_HOST,
reg_val,
reg_val == CPU_RST_STATUS_SOFT_RST_DONE,
1000,
poll_timeout_us);
if (rc)
dev_err(hdev->dev, "Timeout while waiting for FW to complete soft reset (0x%x)\n",
reg_val);
return rc;
}
static int gaudi2_execute_soft_reset(struct hl_device *hdev, bool driver_performs_reset,
u32 poll_timeout_us)
{
struct cpu_dyn_regs *dyn_regs = &hdev->fw_loader.dynamic_loader.comm_desc.cpu_dyn_regs;
int rc = 0;
if (!driver_performs_reset) {
if (hl_is_fw_sw_ver_below(hdev, 1, 10)) {
if (dyn_regs->cpu_rst_status)
WREG32(le32_to_cpu(dyn_regs->cpu_rst_status), CPU_RST_STATUS_NA);
else
WREG32(mmCPU_RST_STATUS_TO_HOST, CPU_RST_STATUS_NA);
WREG32(le32_to_cpu(dyn_regs->gic_host_soft_rst_irq),
gaudi2_irq_map_table[GAUDI2_EVENT_CPU_SOFT_RESET].cpu_id);
rc = gaudi2_get_soft_rst_done_indication(hdev, poll_timeout_us);
} else {
rc = hl_fw_send_soft_reset(hdev);
}
return rc;
}
gaudi2_write_rr_to_all_lbw_rtrs(hdev, RR_TYPE_LONG, NUM_LONG_LBW_RR - 1,
mmDCORE0_TPC0_QM_DCCM_BASE, mmPCIE_MSIX_BASE);
gaudi2_write_rr_to_all_lbw_rtrs(hdev, RR_TYPE_LONG, NUM_LONG_LBW_RR - 2,
mmPCIE_MSIX_BASE + HL_BLOCK_SIZE,
mmPCIE_VDEC1_MSTR_IF_RR_SHRD_HBW_BASE + HL_BLOCK_SIZE);
WREG32(mmPSOC_RESET_CONF_SOFT_RST, 1);
return 0;
}
static void gaudi2_poll_btm_indication(struct hl_device *hdev, u32 poll_timeout_us)
{
int i, rc = 0;
u32 reg_val;
for (i = 0 ; i < GAUDI2_RESET_POLL_CNT ; i++)
rc = hl_poll_timeout(
hdev,
mmPSOC_GLOBAL_CONF_BTM_FSM,
reg_val,
reg_val == 0,
1000,
poll_timeout_us);
if (rc)
dev_err(hdev->dev, "Timeout while waiting for device to reset 0x%x\n", reg_val);
}
static int gaudi2_hw_fini(struct hl_device *hdev, bool hard_reset, bool fw_reset)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 poll_timeout_us, reset_sleep_ms;
bool driver_performs_reset = false;
int rc;
if (hdev->pldm) {
reset_sleep_ms = hard_reset ? GAUDI2_PLDM_HRESET_TIMEOUT_MSEC :
GAUDI2_PLDM_SRESET_TIMEOUT_MSEC;
poll_timeout_us = GAUDI2_PLDM_RESET_POLL_TIMEOUT_USEC;
} else {
reset_sleep_ms = GAUDI2_RESET_TIMEOUT_MSEC;
poll_timeout_us = GAUDI2_RESET_POLL_TIMEOUT_USEC;
}
if (fw_reset)
goto skip_reset;
gaudi2_reset_arcs(hdev);
if (hard_reset) {
driver_performs_reset = !hdev->asic_prop.hard_reset_done_by_fw;
gaudi2_execute_hard_reset(hdev);
} else {
driver_performs_reset = (hdev->fw_components == FW_TYPE_PREBOOT_CPU &&
!hdev->asic_prop.fw_security_enabled);
rc = gaudi2_execute_soft_reset(hdev, driver_performs_reset, poll_timeout_us);
if (rc)
return rc;
}
skip_reset:
if (driver_performs_reset || hard_reset) {
msleep(reset_sleep_ms);
if (hdev->fw_components & FW_TYPE_PREBOOT_CPU)
hl_fw_wait_preboot_ready(hdev);
else
gaudi2_poll_btm_indication(hdev, poll_timeout_us);
}
if (!gaudi2)
return 0;
gaudi2->dec_hw_cap_initialized &= ~(HW_CAP_DEC_MASK);
gaudi2->tpc_hw_cap_initialized &= ~(HW_CAP_TPC_MASK);
gaudi2->nic_hw_cap_initialized &= ~(HW_CAP_NIC_MASK);
if (hard_reset) {
gaudi2->hw_cap_initialized &=
~(HW_CAP_DRAM | HW_CAP_CLK_GATE | HW_CAP_HBM_SCRAMBLER_MASK |
HW_CAP_PMMU | HW_CAP_CPU | HW_CAP_CPU_Q |
HW_CAP_SRAM_SCRAMBLER | HW_CAP_DMMU_MASK |
HW_CAP_PDMA_MASK | HW_CAP_EDMA_MASK | HW_CAP_KDMA |
HW_CAP_MME_MASK | HW_CAP_ROT_MASK);
memset(gaudi2->events_stat, 0, sizeof(gaudi2->events_stat));
} else {
gaudi2->hw_cap_initialized &=
~(HW_CAP_CLK_GATE | HW_CAP_HBM_SCRAMBLER_SW_RESET |
HW_CAP_PDMA_MASK | HW_CAP_EDMA_MASK | HW_CAP_MME_MASK |
HW_CAP_ROT_MASK);
}
return 0;
}
static int gaudi2_suspend(struct hl_device *hdev)
{
int rc;
rc = hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS, 0x0);
if (rc)
dev_err(hdev->dev, "Failed to disable PCI access from CPU\n");
return rc;
}
static int gaudi2_resume(struct hl_device *hdev)
{
return gaudi2_init_iatu(hdev);
}
static int gaudi2_mmap(struct hl_device *hdev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t dma_addr, size_t size)
{
int rc;
vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP |
VM_DONTCOPY | VM_NORESERVE);
#ifdef _HAS_DMA_MMAP_COHERENT
rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, dma_addr, size);
if (rc)
dev_err(hdev->dev, "dma_mmap_coherent error %d", rc);
#else
rc = remap_pfn_range(vma, vma->vm_start,
virt_to_phys(cpu_addr) >> PAGE_SHIFT,
size, vma->vm_page_prot);
if (rc)
dev_err(hdev->dev, "remap_pfn_range error %d", rc);
#endif
return rc;
}
static bool gaudi2_is_queue_enabled(struct hl_device *hdev, u32 hw_queue_id)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u64 hw_cap_mask = 0;
u64 hw_tpc_cap_bit = 0;
u64 hw_nic_cap_bit = 0;
u64 hw_test_cap_bit = 0;
switch (hw_queue_id) {
case GAUDI2_QUEUE_ID_PDMA_0_0:
case GAUDI2_QUEUE_ID_PDMA_0_1:
case GAUDI2_QUEUE_ID_PDMA_1_0:
hw_cap_mask = HW_CAP_PDMA_MASK;
break;
case GAUDI2_QUEUE_ID_DCORE0_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE0_EDMA_1_3:
hw_test_cap_bit = HW_CAP_EDMA_SHIFT +
((hw_queue_id - GAUDI2_QUEUE_ID_DCORE0_EDMA_0_0) >> 2);
break;
case GAUDI2_QUEUE_ID_DCORE1_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE1_EDMA_1_3:
hw_test_cap_bit = HW_CAP_EDMA_SHIFT + NUM_OF_EDMA_PER_DCORE +
((hw_queue_id - GAUDI2_QUEUE_ID_DCORE1_EDMA_0_0) >> 2);
break;
case GAUDI2_QUEUE_ID_DCORE2_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE2_EDMA_1_3:
hw_test_cap_bit = HW_CAP_EDMA_SHIFT + 2 * NUM_OF_EDMA_PER_DCORE +
((hw_queue_id - GAUDI2_QUEUE_ID_DCORE2_EDMA_0_0) >> 2);
break;
case GAUDI2_QUEUE_ID_DCORE3_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE3_EDMA_1_3:
hw_test_cap_bit = HW_CAP_EDMA_SHIFT + 3 * NUM_OF_EDMA_PER_DCORE +
((hw_queue_id - GAUDI2_QUEUE_ID_DCORE3_EDMA_0_0) >> 2);
break;
case GAUDI2_QUEUE_ID_DCORE0_MME_0_0 ... GAUDI2_QUEUE_ID_DCORE0_MME_0_3:
hw_test_cap_bit = HW_CAP_MME_SHIFT;
break;
case GAUDI2_QUEUE_ID_DCORE1_MME_0_0 ... GAUDI2_QUEUE_ID_DCORE1_MME_0_3:
hw_test_cap_bit = HW_CAP_MME_SHIFT + 1;
break;
case GAUDI2_QUEUE_ID_DCORE2_MME_0_0 ... GAUDI2_QUEUE_ID_DCORE2_MME_0_3:
hw_test_cap_bit = HW_CAP_MME_SHIFT + 2;
break;
case GAUDI2_QUEUE_ID_DCORE3_MME_0_0 ... GAUDI2_QUEUE_ID_DCORE3_MME_0_3:
hw_test_cap_bit = HW_CAP_MME_SHIFT + 3;
break;
case GAUDI2_QUEUE_ID_DCORE0_TPC_0_0 ... GAUDI2_QUEUE_ID_DCORE0_TPC_5_3:
hw_tpc_cap_bit = HW_CAP_TPC_SHIFT +
((hw_queue_id - GAUDI2_QUEUE_ID_DCORE0_TPC_0_0) >> 2);
if (!hw_tpc_cap_bit)
return !!(gaudi2->tpc_hw_cap_initialized & BIT_ULL(0));
break;
case GAUDI2_QUEUE_ID_DCORE1_TPC_0_0 ... GAUDI2_QUEUE_ID_DCORE1_TPC_5_3:
hw_tpc_cap_bit = HW_CAP_TPC_SHIFT + NUM_OF_TPC_PER_DCORE +
((hw_queue_id - GAUDI2_QUEUE_ID_DCORE1_TPC_0_0) >> 2);
break;
case GAUDI2_QUEUE_ID_DCORE2_TPC_0_0 ... GAUDI2_QUEUE_ID_DCORE2_TPC_5_3:
hw_tpc_cap_bit = HW_CAP_TPC_SHIFT + (2 * NUM_OF_TPC_PER_DCORE) +
((hw_queue_id - GAUDI2_QUEUE_ID_DCORE2_TPC_0_0) >> 2);
break;
case GAUDI2_QUEUE_ID_DCORE3_TPC_0_0 ... GAUDI2_QUEUE_ID_DCORE3_TPC_5_3:
hw_tpc_cap_bit = HW_CAP_TPC_SHIFT + (3 * NUM_OF_TPC_PER_DCORE) +
((hw_queue_id - GAUDI2_QUEUE_ID_DCORE3_TPC_0_0) >> 2);
break;
case GAUDI2_QUEUE_ID_DCORE0_TPC_6_0 ... GAUDI2_QUEUE_ID_DCORE0_TPC_6_3:
hw_tpc_cap_bit = HW_CAP_TPC_SHIFT + (4 * NUM_OF_TPC_PER_DCORE);
break;
case GAUDI2_QUEUE_ID_ROT_0_0 ... GAUDI2_QUEUE_ID_ROT_1_3:
hw_test_cap_bit = HW_CAP_ROT_SHIFT + ((hw_queue_id - GAUDI2_QUEUE_ID_ROT_0_0) >> 2);
break;
case GAUDI2_QUEUE_ID_NIC_0_0 ... GAUDI2_QUEUE_ID_NIC_23_3:
hw_nic_cap_bit = HW_CAP_NIC_SHIFT + ((hw_queue_id - GAUDI2_QUEUE_ID_NIC_0_0) >> 2);
if (!hw_nic_cap_bit)
return !!(gaudi2->nic_hw_cap_initialized & BIT_ULL(0));
break;
case GAUDI2_QUEUE_ID_CPU_PQ:
return !!(gaudi2->hw_cap_initialized & HW_CAP_CPU_Q);
default:
return false;
}
if (hw_tpc_cap_bit)
return !!(gaudi2->tpc_hw_cap_initialized & BIT_ULL(hw_tpc_cap_bit));
if (hw_nic_cap_bit)
return !!(gaudi2->nic_hw_cap_initialized & BIT_ULL(hw_nic_cap_bit));
if (hw_test_cap_bit)
hw_cap_mask = BIT_ULL(hw_test_cap_bit);
return !!(gaudi2->hw_cap_initialized & hw_cap_mask);
}
static bool gaudi2_is_arc_enabled(struct hl_device *hdev, u64 arc_id)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
switch (arc_id) {
case CPU_ID_SCHED_ARC0 ... CPU_ID_SCHED_ARC5:
case CPU_ID_MME_QMAN_ARC0...CPU_ID_ROT_QMAN_ARC1:
return !!(gaudi2->active_hw_arc & BIT_ULL(arc_id));
case CPU_ID_TPC_QMAN_ARC0...CPU_ID_TPC_QMAN_ARC24:
return !!(gaudi2->active_tpc_arc & BIT_ULL(arc_id - CPU_ID_TPC_QMAN_ARC0));
case CPU_ID_NIC_QMAN_ARC0...CPU_ID_NIC_QMAN_ARC23:
return !!(gaudi2->active_nic_arc & BIT_ULL(arc_id - CPU_ID_NIC_QMAN_ARC0));
default:
return false;
}
}
static void gaudi2_clr_arc_id_cap(struct hl_device *hdev, u64 arc_id)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
switch (arc_id) {
case CPU_ID_SCHED_ARC0 ... CPU_ID_SCHED_ARC5:
case CPU_ID_MME_QMAN_ARC0...CPU_ID_ROT_QMAN_ARC1:
gaudi2->active_hw_arc &= ~(BIT_ULL(arc_id));
break;
case CPU_ID_TPC_QMAN_ARC0...CPU_ID_TPC_QMAN_ARC24:
gaudi2->active_tpc_arc &= ~(BIT_ULL(arc_id - CPU_ID_TPC_QMAN_ARC0));
break;
case CPU_ID_NIC_QMAN_ARC0...CPU_ID_NIC_QMAN_ARC23:
gaudi2->active_nic_arc &= ~(BIT_ULL(arc_id - CPU_ID_NIC_QMAN_ARC0));
break;
default:
return;
}
}
static void gaudi2_set_arc_id_cap(struct hl_device *hdev, u64 arc_id)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
switch (arc_id) {
case CPU_ID_SCHED_ARC0 ... CPU_ID_SCHED_ARC5:
case CPU_ID_MME_QMAN_ARC0...CPU_ID_ROT_QMAN_ARC1:
gaudi2->active_hw_arc |= BIT_ULL(arc_id);
break;
case CPU_ID_TPC_QMAN_ARC0...CPU_ID_TPC_QMAN_ARC24:
gaudi2->active_tpc_arc |= BIT_ULL(arc_id - CPU_ID_TPC_QMAN_ARC0);
break;
case CPU_ID_NIC_QMAN_ARC0...CPU_ID_NIC_QMAN_ARC23:
gaudi2->active_nic_arc |= BIT_ULL(arc_id - CPU_ID_NIC_QMAN_ARC0);
break;
default:
return;
}
}
static void gaudi2_ring_doorbell(struct hl_device *hdev, u32 hw_queue_id, u32 pi)
{
struct cpu_dyn_regs *dyn_regs = &hdev->fw_loader.dynamic_loader.comm_desc.cpu_dyn_regs;
u32 pq_offset, reg_base, db_reg_offset, db_value;
if (hw_queue_id != GAUDI2_QUEUE_ID_CPU_PQ) {
pq_offset = (hw_queue_id & 0x3) * 4;
reg_base = gaudi2_qm_blocks_bases[hw_queue_id];
db_reg_offset = reg_base + QM_PQ_PI_0_OFFSET + pq_offset;
} else {
db_reg_offset = mmCPU_IF_PF_PQ_PI;
}
db_value = pi;
WREG32(db_reg_offset, db_value);
if (hw_queue_id == GAUDI2_QUEUE_ID_CPU_PQ) {
mb();
WREG32(le32_to_cpu(dyn_regs->gic_host_pi_upd_irq),
gaudi2_irq_map_table[GAUDI2_EVENT_CPU_PI_UPDATE].cpu_id);
}
}
static void gaudi2_pqe_write(struct hl_device *hdev, __le64 *pqe, struct hl_bd *bd)
{
__le64 *pbd = (__le64 *) bd;
pqe[0] = pbd[0];
pqe[1] = pbd[1];
}
static void *gaudi2_dma_alloc_coherent(struct hl_device *hdev, size_t size,
dma_addr_t *dma_handle, gfp_t flags)
{
return dma_alloc_coherent(&hdev->pdev->dev, size, dma_handle, flags);
}
static void gaudi2_dma_free_coherent(struct hl_device *hdev, size_t size,
void *cpu_addr, dma_addr_t dma_handle)
{
dma_free_coherent(&hdev->pdev->dev, size, cpu_addr, dma_handle);
}
static int gaudi2_send_cpu_message(struct hl_device *hdev, u32 *msg, u16 len,
u32 timeout, u64 *result)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
if (!(gaudi2->hw_cap_initialized & HW_CAP_CPU_Q)) {
if (result)
*result = 0;
return 0;
}
if (!timeout)
timeout = GAUDI2_MSG_TO_CPU_TIMEOUT_USEC;
return hl_fw_send_cpu_message(hdev, GAUDI2_QUEUE_ID_CPU_PQ, msg, len, timeout, result);
}
static void *gaudi2_dma_pool_zalloc(struct hl_device *hdev, size_t size,
gfp_t mem_flags, dma_addr_t *dma_handle)
{
if (size > GAUDI2_DMA_POOL_BLK_SIZE)
return NULL;
return dma_pool_zalloc(hdev->dma_pool, mem_flags, dma_handle);
}
static void gaudi2_dma_pool_free(struct hl_device *hdev, void *vaddr, dma_addr_t dma_addr)
{
dma_pool_free(hdev->dma_pool, vaddr, dma_addr);
}
static void *gaudi2_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size,
dma_addr_t *dma_handle)
{
return hl_fw_cpu_accessible_dma_pool_alloc(hdev, size, dma_handle);
}
static void gaudi2_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size, void *vaddr)
{
hl_fw_cpu_accessible_dma_pool_free(hdev, size, vaddr);
}
static dma_addr_t gaudi2_dma_map_single(struct hl_device *hdev, void *addr, int len,
enum dma_data_direction dir)
{
dma_addr_t dma_addr;
dma_addr = dma_map_single(&hdev->pdev->dev, addr, len, dir);
if (unlikely(dma_mapping_error(&hdev->pdev->dev, dma_addr)))
return 0;
return dma_addr;
}
static void gaudi2_dma_unmap_single(struct hl_device *hdev, dma_addr_t addr, int len,
enum dma_data_direction dir)
{
dma_unmap_single(&hdev->pdev->dev, addr, len, dir);
}
static int gaudi2_validate_cb_address(struct hl_device *hdev, struct hl_cs_parser *parser)
{
struct asic_fixed_properties *asic_prop = &hdev->asic_prop;
struct gaudi2_device *gaudi2 = hdev->asic_specific;
if (!gaudi2_is_queue_enabled(hdev, parser->hw_queue_id)) {
dev_err(hdev->dev, "h/w queue %d is disabled\n", parser->hw_queue_id);
return -EINVAL;
}
if (hl_mem_area_inside_range((u64) (uintptr_t) parser->user_cb,
parser->user_cb_size,
asic_prop->sram_user_base_address,
asic_prop->sram_end_address))
return 0;
if (hl_mem_area_inside_range((u64) (uintptr_t) parser->user_cb,
parser->user_cb_size,
asic_prop->dram_user_base_address,
asic_prop->dram_end_address))
return 0;
if ((gaudi2->hw_cap_initialized & HW_CAP_DMMU_MASK) &&
hl_mem_area_inside_range((u64) (uintptr_t) parser->user_cb,
parser->user_cb_size,
asic_prop->dmmu.start_addr,
asic_prop->dmmu.end_addr))
return 0;
if (gaudi2->hw_cap_initialized & HW_CAP_PMMU) {
if (hl_mem_area_inside_range((u64) (uintptr_t) parser->user_cb,
parser->user_cb_size,
asic_prop->pmmu.start_addr,
asic_prop->pmmu.end_addr) ||
hl_mem_area_inside_range(
(u64) (uintptr_t) parser->user_cb,
parser->user_cb_size,
asic_prop->pmmu_huge.start_addr,
asic_prop->pmmu_huge.end_addr))
return 0;
} else if (gaudi2_host_phys_addr_valid((u64) (uintptr_t) parser->user_cb)) {
if (!hdev->pdev)
return 0;
if (!device_iommu_mapped(&hdev->pdev->dev))
return 0;
}
dev_err(hdev->dev, "CB address %p + 0x%x for internal QMAN is not valid\n",
parser->user_cb, parser->user_cb_size);
return -EFAULT;
}
static int gaudi2_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
if (!parser->is_kernel_allocated_cb)
return gaudi2_validate_cb_address(hdev, parser);
if (!(gaudi2->hw_cap_initialized & HW_CAP_PMMU)) {
dev_err(hdev->dev, "PMMU not initialized - Unsupported mode in Gaudi2\n");
return -EINVAL;
}
return 0;
}
static int gaudi2_send_heartbeat(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
if (!(gaudi2->hw_cap_initialized & HW_CAP_CPU_Q))
return 0;
return hl_fw_send_heartbeat(hdev);
}
static void gaudi2_kdma_set_mmbp_asid(struct hl_device *hdev,
bool mmu_bypass, u32 asid)
{
u32 rw_asid, rw_mmu_bp;
rw_asid = (asid << ARC_FARM_KDMA_CTX_AXUSER_HB_ASID_RD_SHIFT) |
(asid << ARC_FARM_KDMA_CTX_AXUSER_HB_ASID_WR_SHIFT);
rw_mmu_bp = (!!mmu_bypass << ARC_FARM_KDMA_CTX_AXUSER_HB_MMU_BP_RD_SHIFT) |
(!!mmu_bypass << ARC_FARM_KDMA_CTX_AXUSER_HB_MMU_BP_WR_SHIFT);
WREG32(mmARC_FARM_KDMA_CTX_AXUSER_HB_ASID, rw_asid);
WREG32(mmARC_FARM_KDMA_CTX_AXUSER_HB_MMU_BP, rw_mmu_bp);
}
static void gaudi2_arm_cq_monitor(struct hl_device *hdev, u32 sob_id, u32 mon_id, u32 cq_id,
u32 mon_payload, u32 sync_value)
{
u32 sob_offset, mon_offset, sync_group_id, mode, mon_arm;
u8 mask;
sob_offset = sob_id * 4;
mon_offset = mon_id * 4;
WREG32(mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0 + sob_offset, 0);
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0 + mon_offset, cq_id);
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_DATA_0 + mon_offset, mon_payload);
sync_group_id = sob_id / 8;
mask = ~(1 << (sob_id & 0x7));
mode = 1;
mon_arm = FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_MON_ARM_SOD_MASK, sync_value);
mon_arm |= FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_MON_ARM_SOP_MASK, mode);
mon_arm |= FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_MON_ARM_MASK_MASK, mask);
mon_arm |= FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_MON_ARM_SID_MASK, sync_group_id);
WREG32(mmDCORE0_SYNC_MNGR_OBJS_MON_ARM_0 + mon_offset, mon_arm);
}
static int gaudi2_send_job_to_kdma(struct hl_device *hdev,
u64 src_addr, u64 dst_addr,
u32 size, bool is_memset)
{
u32 comp_val, commit_mask, *polling_addr, timeout, status = 0;
struct hl_cq_entry *cq_base;
struct hl_cq *cq;
u64 comp_addr;
int rc;
gaudi2_arm_cq_monitor(hdev, GAUDI2_RESERVED_SOB_KDMA_COMPLETION,
GAUDI2_RESERVED_MON_KDMA_COMPLETION,
GAUDI2_RESERVED_CQ_KDMA_COMPLETION, 1, 1);
comp_addr = CFG_BASE + mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0 +
(GAUDI2_RESERVED_SOB_KDMA_COMPLETION * sizeof(u32));
comp_val = FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_SOB_OBJ_INC_MASK, 1) |
FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_SOB_OBJ_VAL_MASK, 1);
WREG32(mmARC_FARM_KDMA_CTX_SRC_BASE_LO, lower_32_bits(src_addr));
WREG32(mmARC_FARM_KDMA_CTX_SRC_BASE_HI, upper_32_bits(src_addr));
WREG32(mmARC_FARM_KDMA_CTX_DST_BASE_LO, lower_32_bits(dst_addr));
WREG32(mmARC_FARM_KDMA_CTX_DST_BASE_HI, upper_32_bits(dst_addr));
WREG32(mmARC_FARM_KDMA_CTX_WR_COMP_ADDR_LO, lower_32_bits(comp_addr));
WREG32(mmARC_FARM_KDMA_CTX_WR_COMP_ADDR_HI, upper_32_bits(comp_addr));
WREG32(mmARC_FARM_KDMA_CTX_WR_COMP_WDATA, comp_val);
WREG32(mmARC_FARM_KDMA_CTX_DST_TSIZE_0, size);
commit_mask = FIELD_PREP(ARC_FARM_KDMA_CTX_COMMIT_LIN_MASK, 1) |
FIELD_PREP(ARC_FARM_KDMA_CTX_COMMIT_WR_COMP_EN_MASK, 1);
if (is_memset)
commit_mask |= FIELD_PREP(ARC_FARM_KDMA_CTX_COMMIT_MEM_SET_MASK, 1);
WREG32(mmARC_FARM_KDMA_CTX_COMMIT, commit_mask);
cq = &hdev->completion_queue[GAUDI2_RESERVED_CQ_KDMA_COMPLETION];
cq_base = cq->kernel_address;
polling_addr = (u32 *)&cq_base[cq->ci];
if (hdev->pldm)
timeout = ((size / SZ_1M) + 1) * USEC_PER_SEC * 20;
else
timeout = KDMA_TIMEOUT_USEC;
rc = hl_poll_timeout_memory(
hdev,
polling_addr,
status,
(status == 1),
1000,
timeout,
true);
*polling_addr = 0;
if (rc) {
dev_err(hdev->dev, "Timeout while waiting for KDMA to be idle\n");
WREG32(mmARC_FARM_KDMA_CFG_1, 1 << ARC_FARM_KDMA_CFG_1_HALT_SHIFT);
return rc;
}
cq->ci = hl_cq_inc_ptr(cq->ci);
return 0;
}
static void gaudi2_memset_device_lbw(struct hl_device *hdev, u32 addr, u32 size, u32 val)
{
u32 i;
for (i = 0 ; i < size ; i += sizeof(u32))
WREG32(addr + i, val);
}
static void gaudi2_qman_set_test_mode(struct hl_device *hdev, u32 hw_queue_id, bool enable)
{
u32 reg_base = gaudi2_qm_blocks_bases[hw_queue_id];
if (enable) {
WREG32(reg_base + QM_GLBL_PROT_OFFSET, QMAN_MAKE_TRUSTED_TEST_MODE);
WREG32(reg_base + QM_PQC_CFG_OFFSET, 0);
} else {
WREG32(reg_base + QM_GLBL_PROT_OFFSET, QMAN_MAKE_TRUSTED);
WREG32(reg_base + QM_PQC_CFG_OFFSET, 1 << PDMA0_QM_PQC_CFG_EN_SHIFT);
}
}
static inline u32 gaudi2_test_queue_hw_queue_id_to_sob_id(struct hl_device *hdev, u32 hw_queue_id)
{
return hdev->asic_prop.first_available_user_sob[0] +
hw_queue_id - GAUDI2_QUEUE_ID_PDMA_0_0;
}
static void gaudi2_test_queue_clear(struct hl_device *hdev, u32 hw_queue_id)
{
u32 sob_offset = gaudi2_test_queue_hw_queue_id_to_sob_id(hdev, hw_queue_id) * 4;
u32 sob_addr = mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0 + sob_offset;
WREG32(sob_addr, 0);
}
static int gaudi2_test_queue_send_msg_short(struct hl_device *hdev, u32 hw_queue_id, u32 sob_val,
struct gaudi2_queues_test_info *msg_info)
{
u32 sob_offset = gaudi2_test_queue_hw_queue_id_to_sob_id(hdev, hw_queue_id) * 4;
u32 tmp, sob_base = 1;
struct packet_msg_short *msg_short_pkt = msg_info->kern_addr;
size_t pkt_size = sizeof(struct packet_msg_short);
int rc;
tmp = (PACKET_MSG_SHORT << GAUDI2_PKT_CTL_OPCODE_SHIFT) |
(1 << GAUDI2_PKT_CTL_EB_SHIFT) |
(1 << GAUDI2_PKT_CTL_MB_SHIFT) |
(sob_base << GAUDI2_PKT_SHORT_CTL_BASE_SHIFT) |
(sob_offset << GAUDI2_PKT_SHORT_CTL_ADDR_SHIFT);
msg_short_pkt->value = cpu_to_le32(sob_val);
msg_short_pkt->ctl = cpu_to_le32(tmp);
rc = hl_hw_queue_send_cb_no_cmpl(hdev, hw_queue_id, pkt_size, msg_info->dma_addr);
if (rc)
dev_err(hdev->dev,
"Failed to send msg_short packet to H/W queue %d\n", hw_queue_id);
return rc;
}
static int gaudi2_test_queue_wait_completion(struct hl_device *hdev, u32 hw_queue_id, u32 sob_val)
{
u32 sob_offset = gaudi2_test_queue_hw_queue_id_to_sob_id(hdev, hw_queue_id) * 4;
u32 sob_addr = mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0 + sob_offset;
u32 timeout_usec, tmp;
int rc;
if (hdev->pldm)
timeout_usec = GAUDI2_PLDM_TEST_QUEUE_WAIT_USEC;
else
timeout_usec = GAUDI2_TEST_QUEUE_WAIT_USEC;
rc = hl_poll_timeout(
hdev,
sob_addr,
tmp,
(tmp == sob_val),
1000,
timeout_usec);
if (rc == -ETIMEDOUT) {
dev_err(hdev->dev, "H/W queue %d test failed (SOB_OBJ_0 == 0x%x)\n",
hw_queue_id, tmp);
rc = -EIO;
}
return rc;
}
static int gaudi2_test_cpu_queue(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
if (!(gaudi2->hw_cap_initialized & HW_CAP_CPU_Q))
return 0;
return hl_fw_test_cpu_queue(hdev);
}
static int gaudi2_test_queues(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
struct gaudi2_queues_test_info *msg_info;
u32 sob_val = 0x5a5a;
int i, rc;
for (i = GAUDI2_QUEUE_ID_PDMA_0_0 ; i < GAUDI2_QUEUE_ID_CPU_PQ; i++) {
if (!gaudi2_is_queue_enabled(hdev, i))
continue;
msg_info = &gaudi2->queues_test_info[i - GAUDI2_QUEUE_ID_PDMA_0_0];
gaudi2_qman_set_test_mode(hdev, i, true);
gaudi2_test_queue_clear(hdev, i);
rc = gaudi2_test_queue_send_msg_short(hdev, i, sob_val, msg_info);
if (rc)
goto done;
}
rc = gaudi2_test_cpu_queue(hdev);
if (rc)
goto done;
for (i = GAUDI2_QUEUE_ID_PDMA_0_0 ; i < GAUDI2_QUEUE_ID_CPU_PQ; i++) {
if (!gaudi2_is_queue_enabled(hdev, i))
continue;
rc = gaudi2_test_queue_wait_completion(hdev, i, sob_val);
if (rc)
goto done;
gaudi2_test_queue_clear(hdev, i);
gaudi2_qman_set_test_mode(hdev, i, false);
}
done:
return rc;
}
static int gaudi2_compute_reset_late_init(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
size_t irq_arr_size;
int rc;
gaudi2_init_arcs(hdev);
rc = gaudi2_scrub_arcs_dccm(hdev);
if (rc) {
dev_err(hdev->dev, "Failed to scrub arcs DCCM\n");
return rc;
}
gaudi2_init_security(hdev);
irq_arr_size = gaudi2->num_of_valid_hw_events * sizeof(gaudi2->hw_events[0]);
return hl_fw_unmask_irq_arr(hdev, gaudi2->hw_events, irq_arr_size);
}
static bool gaudi2_get_edma_idle_status(struct hl_device *hdev, u64 *mask_arr, u8 mask_len,
struct engines_data *e)
{
u32 qm_glbl_sts0, qm_glbl_sts1, qm_cgm_sts, dma_core_sts0, dma_core_sts1;
struct asic_fixed_properties *prop = &hdev->asic_prop;
unsigned long *mask = (unsigned long *) mask_arr;
const char *edma_fmt = "%-6d%-6d%-9s%#-14x%#-15x%#x\n";
bool is_idle = true, is_eng_idle;
int engine_idx, i, j;
u64 offset;
if (e)
hl_engine_data_sprintf(e,
"\nCORE EDMA is_idle QM_GLBL_STS0 DMA_CORE_STS0 DMA_CORE_STS1\n"
"---- ---- ------- ------------ ------------- -------------\n");
for (i = 0; i < NUM_OF_DCORES; i++) {
for (j = 0 ; j < NUM_OF_EDMA_PER_DCORE ; j++) {
int seq = i * NUM_OF_EDMA_PER_DCORE + j;
if (!(prop->edma_enabled_mask & BIT(seq)))
continue;
engine_idx = GAUDI2_DCORE0_ENGINE_ID_EDMA_0 +
i * GAUDI2_ENGINE_ID_DCORE_OFFSET + j;
offset = i * DCORE_OFFSET + j * DCORE_EDMA_OFFSET;
dma_core_sts0 = RREG32(mmDCORE0_EDMA0_CORE_STS0 + offset);
dma_core_sts1 = RREG32(mmDCORE0_EDMA0_CORE_STS1 + offset);
qm_glbl_sts0 = RREG32(mmDCORE0_EDMA0_QM_GLBL_STS0 + offset);
qm_glbl_sts1 = RREG32(mmDCORE0_EDMA0_QM_GLBL_STS1 + offset);
qm_cgm_sts = RREG32(mmDCORE0_EDMA0_QM_CGM_STS + offset);
is_eng_idle = IS_QM_IDLE(qm_glbl_sts0, qm_glbl_sts1, qm_cgm_sts) &&
IS_DMA_IDLE(dma_core_sts0) && !IS_DMA_HALTED(dma_core_sts1);
is_idle &= is_eng_idle;
if (mask && !is_eng_idle)
set_bit(engine_idx, mask);
if (e)
hl_engine_data_sprintf(e, edma_fmt, i, j, is_eng_idle ? "Y" : "N",
qm_glbl_sts0, dma_core_sts0, dma_core_sts1);
}
}
return is_idle;
}
static bool gaudi2_get_pdma_idle_status(struct hl_device *hdev, u64 *mask_arr, u8 mask_len,
struct engines_data *e)
{
u32 qm_glbl_sts0, qm_glbl_sts1, qm_cgm_sts, dma_core_sts0, dma_core_sts1;
unsigned long *mask = (unsigned long *) mask_arr;
const char *pdma_fmt = "%-6d%-9s%#-14x%#-15x%#x\n";
bool is_idle = true, is_eng_idle;
int engine_idx, i;
u64 offset;
if (e)
hl_engine_data_sprintf(e,
"\nPDMA is_idle QM_GLBL_STS0 DMA_CORE_STS0 DMA_CORE_STS1\n"
"---- ------- ------------ ------------- -------------\n");
for (i = 0 ; i < NUM_OF_PDMA ; i++) {
engine_idx = GAUDI2_ENGINE_ID_PDMA_0 + i;
offset = i * PDMA_OFFSET;
dma_core_sts0 = RREG32(mmPDMA0_CORE_STS0 + offset);
dma_core_sts1 = RREG32(mmPDMA0_CORE_STS1 + offset);
qm_glbl_sts0 = RREG32(mmPDMA0_QM_GLBL_STS0 + offset);
qm_glbl_sts1 = RREG32(mmPDMA0_QM_GLBL_STS1 + offset);
qm_cgm_sts = RREG32(mmPDMA0_QM_CGM_STS + offset);
is_eng_idle = IS_QM_IDLE(qm_glbl_sts0, qm_glbl_sts1, qm_cgm_sts) &&
IS_DMA_IDLE(dma_core_sts0) && !IS_DMA_HALTED(dma_core_sts1);
is_idle &= is_eng_idle;
if (mask && !is_eng_idle)
set_bit(engine_idx, mask);
if (e)
hl_engine_data_sprintf(e, pdma_fmt, i, is_eng_idle ? "Y" : "N",
qm_glbl_sts0, dma_core_sts0, dma_core_sts1);
}
return is_idle;
}
static bool gaudi2_get_nic_idle_status(struct hl_device *hdev, u64 *mask_arr, u8 mask_len,
struct engines_data *e)
{
unsigned long *mask = (unsigned long *) mask_arr;
const char *nic_fmt = "%-5d%-9s%#-14x%#-12x\n";
u32 qm_glbl_sts0, qm_glbl_sts1, qm_cgm_sts;
bool is_idle = true, is_eng_idle;
int engine_idx, i;
u64 offset = 0;
if (e && hdev->nic_ports_mask)
hl_engine_data_sprintf(e,
"\nNIC is_idle QM_GLBL_STS0 QM_CGM_STS\n"
"--- ------- ------------ ----------\n");
for (i = 0 ; i < NIC_NUMBER_OF_ENGINES ; i++) {
if (!(i & 1))
offset = i / 2 * NIC_OFFSET;
else
offset += NIC_QM_OFFSET;
if (!(hdev->nic_ports_mask & BIT(i)))
continue;
engine_idx = GAUDI2_ENGINE_ID_NIC0_0 + i;
qm_glbl_sts0 = RREG32(mmNIC0_QM0_GLBL_STS0 + offset);
qm_glbl_sts1 = RREG32(mmNIC0_QM0_GLBL_STS1 + offset);
qm_cgm_sts = RREG32(mmNIC0_QM0_CGM_STS + offset);
is_eng_idle = IS_QM_IDLE(qm_glbl_sts0, qm_glbl_sts1, qm_cgm_sts);
is_idle &= is_eng_idle;
if (mask && !is_eng_idle)
set_bit(engine_idx, mask);
if (e)
hl_engine_data_sprintf(e, nic_fmt, i, is_eng_idle ? "Y" : "N",
qm_glbl_sts0, qm_cgm_sts);
}
return is_idle;
}
static bool gaudi2_get_mme_idle_status(struct hl_device *hdev, u64 *mask_arr, u8 mask_len,
struct engines_data *e)
{
u32 qm_glbl_sts0, qm_glbl_sts1, qm_cgm_sts, mme_arch_sts;
unsigned long *mask = (unsigned long *) mask_arr;
const char *mme_fmt = "%-5d%-6s%-9s%#-14x%#x\n";
bool is_idle = true, is_eng_idle;
int engine_idx, i;
u64 offset;
if (e)
hl_engine_data_sprintf(e,
"\nMME Stub is_idle QM_GLBL_STS0 MME_ARCH_STATUS\n"
"--- ---- ------- ------------ ---------------\n");
for (i = 0 ; i < NUM_OF_DCORES ; i++) {
engine_idx = GAUDI2_DCORE0_ENGINE_ID_MME + i * GAUDI2_ENGINE_ID_DCORE_OFFSET;
offset = i * DCORE_OFFSET;
qm_glbl_sts0 = RREG32(mmDCORE0_MME_QM_GLBL_STS0 + offset);
qm_glbl_sts1 = RREG32(mmDCORE0_MME_QM_GLBL_STS1 + offset);
qm_cgm_sts = RREG32(mmDCORE0_MME_QM_CGM_STS + offset);
is_eng_idle = IS_QM_IDLE(qm_glbl_sts0, qm_glbl_sts1, qm_cgm_sts);
is_idle &= is_eng_idle;
mme_arch_sts = RREG32(mmDCORE0_MME_CTRL_LO_ARCH_STATUS + offset);
is_eng_idle &= IS_MME_IDLE(mme_arch_sts);
is_idle &= is_eng_idle;
if (e)
hl_engine_data_sprintf(e, mme_fmt, i, "N",
is_eng_idle ? "Y" : "N",
qm_glbl_sts0,
mme_arch_sts);
if (mask && !is_eng_idle)
set_bit(engine_idx, mask);
}
return is_idle;
}
static void gaudi2_is_tpc_engine_idle(struct hl_device *hdev, int dcore, int inst, u32 offset,
struct iterate_module_ctx *ctx)
{
struct gaudi2_tpc_idle_data *idle_data = ctx->data;
u32 tpc_cfg_sts, qm_glbl_sts0, qm_glbl_sts1, qm_cgm_sts;
bool is_eng_idle;
int engine_idx;
if ((dcore == 0) && (inst == (NUM_DCORE0_TPC - 1)))
engine_idx = GAUDI2_DCORE0_ENGINE_ID_TPC_6;
else
engine_idx = GAUDI2_DCORE0_ENGINE_ID_TPC_0 +
dcore * GAUDI2_ENGINE_ID_DCORE_OFFSET + inst;
tpc_cfg_sts = RREG32(mmDCORE0_TPC0_CFG_STATUS + offset);
qm_glbl_sts0 = RREG32(mmDCORE0_TPC0_QM_GLBL_STS0 + offset);
qm_glbl_sts1 = RREG32(mmDCORE0_TPC0_QM_GLBL_STS1 + offset);
qm_cgm_sts = RREG32(mmDCORE0_TPC0_QM_CGM_STS + offset);
is_eng_idle = IS_QM_IDLE(qm_glbl_sts0, qm_glbl_sts1, qm_cgm_sts) &&
IS_TPC_IDLE(tpc_cfg_sts);
*(idle_data->is_idle) &= is_eng_idle;
if (idle_data->mask && !is_eng_idle)
set_bit(engine_idx, idle_data->mask);
if (idle_data->e)
hl_engine_data_sprintf(idle_data->e,
idle_data->tpc_fmt, dcore, inst,
is_eng_idle ? "Y" : "N",
qm_glbl_sts0, qm_cgm_sts, tpc_cfg_sts);
}
static bool gaudi2_get_tpc_idle_status(struct hl_device *hdev, u64 *mask_arr, u8 mask_len,
struct engines_data *e)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
unsigned long *mask = (unsigned long *) mask_arr;
bool is_idle = true;
struct gaudi2_tpc_idle_data tpc_idle_data = {
.tpc_fmt = "%-6d%-5d%-9s%#-14x%#-12x%#x\n",
.e = e,
.mask = mask,
.is_idle = &is_idle,
};
struct iterate_module_ctx tpc_iter = {
.fn = &gaudi2_is_tpc_engine_idle,
.data = &tpc_idle_data,
};
if (e && prop->tpc_enabled_mask)
hl_engine_data_sprintf(e,
"\nCORE TPC is_idle QM_GLBL_STS0 QM_CGM_STS STATUS\n"
"---- --- ------- ------------ ---------- ------\n");
gaudi2_iterate_tpcs(hdev, &tpc_iter);
return *tpc_idle_data.is_idle;
}
static bool gaudi2_get_decoder_idle_status(struct hl_device *hdev, u64 *mask_arr, u8 mask_len,
struct engines_data *e)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
unsigned long *mask = (unsigned long *) mask_arr;
const char *pcie_dec_fmt = "%-10d%-9s%#x\n";
const char *dec_fmt = "%-6d%-5d%-9s%#x\n";
bool is_idle = true, is_eng_idle;
u32 dec_swreg15, dec_enabled_bit;
int engine_idx, i, j;
u64 offset;
if (e && (prop->decoder_enabled_mask & (~PCIE_DEC_EN_MASK)))
hl_engine_data_sprintf(e,
"\nCORE DEC is_idle VSI_CMD_SWREG15\n"
"---- --- ------- ---------------\n");
for (i = 0 ; i < NUM_OF_DCORES ; i++) {
for (j = 0 ; j < NUM_OF_DEC_PER_DCORE ; j++) {
dec_enabled_bit = 1 << (i * NUM_OF_DEC_PER_DCORE + j);
if (!(prop->decoder_enabled_mask & dec_enabled_bit))
continue;
engine_idx = GAUDI2_DCORE0_ENGINE_ID_DEC_0 +
i * GAUDI2_ENGINE_ID_DCORE_OFFSET + j;
offset = i * DCORE_OFFSET + j * DCORE_DEC_OFFSET;
dec_swreg15 = RREG32(mmDCORE0_DEC0_CMD_SWREG15 + offset);
is_eng_idle = IS_DEC_IDLE(dec_swreg15);
is_idle &= is_eng_idle;
if (mask && !is_eng_idle)
set_bit(engine_idx, mask);
if (e)
hl_engine_data_sprintf(e, dec_fmt, i, j,
is_eng_idle ? "Y" : "N", dec_swreg15);
}
}
if (e && (prop->decoder_enabled_mask & PCIE_DEC_EN_MASK))
hl_engine_data_sprintf(e,
"\nPCIe DEC is_idle VSI_CMD_SWREG15\n"
"-------- ------- ---------------\n");
for (i = 0 ; i < NUM_OF_DEC_PER_DCORE ; i++) {
dec_enabled_bit = PCIE_DEC_SHIFT + i;
if (!(prop->decoder_enabled_mask & BIT(dec_enabled_bit)))
continue;
engine_idx = GAUDI2_PCIE_ENGINE_ID_DEC_0 + i;
offset = i * DCORE_DEC_OFFSET;
dec_swreg15 = RREG32(mmPCIE_DEC0_CMD_SWREG15 + offset);
is_eng_idle = IS_DEC_IDLE(dec_swreg15);
is_idle &= is_eng_idle;
if (mask && !is_eng_idle)
set_bit(engine_idx, mask);
if (e)
hl_engine_data_sprintf(e, pcie_dec_fmt, i,
is_eng_idle ? "Y" : "N", dec_swreg15);
}
return is_idle;
}
static bool gaudi2_get_rotator_idle_status(struct hl_device *hdev, u64 *mask_arr, u8 mask_len,
struct engines_data *e)
{
const char *rot_fmt = "%-6d%-5d%-9s%#-14x%#-14x%#x\n";
unsigned long *mask = (unsigned long *) mask_arr;
u32 qm_glbl_sts0, qm_glbl_sts1, qm_cgm_sts;
bool is_idle = true, is_eng_idle;
int engine_idx, i;
u64 offset;
if (e)
hl_engine_data_sprintf(e,
"\nCORE ROT is_idle QM_GLBL_STS0 QM_GLBL_STS1 QM_CGM_STS\n"
"---- --- ------- ------------ ------------ ----------\n");
for (i = 0 ; i < NUM_OF_ROT ; i++) {
engine_idx = GAUDI2_ENGINE_ID_ROT_0 + i;
offset = i * ROT_OFFSET;
qm_glbl_sts0 = RREG32(mmROT0_QM_GLBL_STS0 + offset);
qm_glbl_sts1 = RREG32(mmROT0_QM_GLBL_STS1 + offset);
qm_cgm_sts = RREG32(mmROT0_QM_CGM_STS + offset);
is_eng_idle = IS_QM_IDLE(qm_glbl_sts0, qm_glbl_sts1, qm_cgm_sts);
is_idle &= is_eng_idle;
if (mask && !is_eng_idle)
set_bit(engine_idx, mask);
if (e)
hl_engine_data_sprintf(e, rot_fmt, i, 0, is_eng_idle ? "Y" : "N",
qm_glbl_sts0, qm_glbl_sts1, qm_cgm_sts);
}
return is_idle;
}
static bool gaudi2_is_device_idle(struct hl_device *hdev, u64 *mask_arr, u8 mask_len,
struct engines_data *e)
{
bool is_idle = true;
is_idle &= gaudi2_get_edma_idle_status(hdev, mask_arr, mask_len, e);
is_idle &= gaudi2_get_pdma_idle_status(hdev, mask_arr, mask_len, e);
is_idle &= gaudi2_get_nic_idle_status(hdev, mask_arr, mask_len, e);
is_idle &= gaudi2_get_mme_idle_status(hdev, mask_arr, mask_len, e);
is_idle &= gaudi2_get_tpc_idle_status(hdev, mask_arr, mask_len, e);
is_idle &= gaudi2_get_decoder_idle_status(hdev, mask_arr, mask_len, e);
is_idle &= gaudi2_get_rotator_idle_status(hdev, mask_arr, mask_len, e);
return is_idle;
}
static void gaudi2_hw_queues_lock(struct hl_device *hdev)
__acquires(&gaudi2->hw_queues_lock)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
spin_lock(&gaudi2->hw_queues_lock);
}
static void gaudi2_hw_queues_unlock(struct hl_device *hdev)
__releases(&gaudi2->hw_queues_lock)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
spin_unlock(&gaudi2->hw_queues_lock);
}
static u32 gaudi2_get_pci_id(struct hl_device *hdev)
{
return hdev->pdev->device;
}
static int gaudi2_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
if (!(gaudi2->hw_cap_initialized & HW_CAP_CPU_Q))
return 0;
return hl_fw_get_eeprom_data(hdev, data, max_size);
}
static void gaudi2_update_eq_ci(struct hl_device *hdev, u32 val)
{
WREG32(mmCPU_IF_EQ_RD_OFFS, val);
}
static void *gaudi2_get_events_stat(struct hl_device *hdev, bool aggregate, u32 *size)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
if (aggregate) {
*size = (u32) sizeof(gaudi2->events_stat_aggregate);
return gaudi2->events_stat_aggregate;
}
*size = (u32) sizeof(gaudi2->events_stat);
return gaudi2->events_stat;
}
static void gaudi2_mmu_vdec_dcore_prepare(struct hl_device *hdev, int dcore_id,
int dcore_vdec_id, u32 rw_asid, u32 rw_mmu_bp)
{
u32 offset = (mmDCORE0_VDEC1_BRDG_CTRL_BASE - mmDCORE0_VDEC0_BRDG_CTRL_BASE) *
dcore_vdec_id + DCORE_OFFSET * dcore_id;
WREG32(mmDCORE0_VDEC0_BRDG_CTRL_AXUSER_DEC_HB_MMU_BP + offset, rw_mmu_bp);
WREG32(mmDCORE0_VDEC0_BRDG_CTRL_AXUSER_DEC_HB_ASID + offset, rw_asid);
WREG32(mmDCORE0_VDEC0_BRDG_CTRL_AXUSER_MSIX_ABNRM_HB_MMU_BP + offset, rw_mmu_bp);
WREG32(mmDCORE0_VDEC0_BRDG_CTRL_AXUSER_MSIX_ABNRM_HB_ASID + offset, rw_asid);
WREG32(mmDCORE0_VDEC0_BRDG_CTRL_AXUSER_MSIX_L2C_HB_MMU_BP + offset, rw_mmu_bp);
WREG32(mmDCORE0_VDEC0_BRDG_CTRL_AXUSER_MSIX_L2C_HB_ASID + offset, rw_asid);
WREG32(mmDCORE0_VDEC0_BRDG_CTRL_AXUSER_MSIX_NRM_HB_MMU_BP + offset, rw_mmu_bp);
WREG32(mmDCORE0_VDEC0_BRDG_CTRL_AXUSER_MSIX_NRM_HB_ASID + offset, rw_asid);
WREG32(mmDCORE0_VDEC0_BRDG_CTRL_AXUSER_MSIX_VCD_HB_MMU_BP + offset, rw_mmu_bp);
WREG32(mmDCORE0_VDEC0_BRDG_CTRL_AXUSER_MSIX_VCD_HB_ASID + offset, rw_asid);
}
static void gaudi2_mmu_dcore_prepare(struct hl_device *hdev, int dcore_id, u32 asid)
{
u32 rw_asid = (asid << ARC_FARM_KDMA_CTX_AXUSER_HB_ASID_RD_SHIFT) |
(asid << ARC_FARM_KDMA_CTX_AXUSER_HB_ASID_WR_SHIFT);
struct asic_fixed_properties *prop = &hdev->asic_prop;
u32 dcore_offset = dcore_id * DCORE_OFFSET;
u32 vdec_id, i, ports_offset, reg_val;
u8 edma_seq_base;
edma_seq_base = dcore_id * NUM_OF_EDMA_PER_DCORE;
if (prop->edma_enabled_mask & BIT(edma_seq_base)) {
WREG32(mmDCORE0_EDMA0_QM_AXUSER_NONSECURED_HB_MMU_BP + dcore_offset, 0);
WREG32(mmDCORE0_EDMA0_QM_AXUSER_NONSECURED_HB_ASID + dcore_offset, rw_asid);
WREG32(mmDCORE0_EDMA0_CORE_CTX_AXUSER_HB_MMU_BP + dcore_offset, 0);
WREG32(mmDCORE0_EDMA0_CORE_CTX_AXUSER_HB_ASID + dcore_offset, rw_asid);
}
if (prop->edma_enabled_mask & BIT(edma_seq_base + 1)) {
WREG32(mmDCORE0_EDMA1_QM_AXUSER_NONSECURED_HB_MMU_BP + dcore_offset, 0);
WREG32(mmDCORE0_EDMA1_QM_AXUSER_NONSECURED_HB_ASID + dcore_offset, rw_asid);
WREG32(mmDCORE0_EDMA1_CORE_CTX_AXUSER_HB_ASID + dcore_offset, rw_asid);
WREG32(mmDCORE0_EDMA1_CORE_CTX_AXUSER_HB_MMU_BP + dcore_offset, 0);
}
WREG32(mmDCORE0_SYNC_MNGR_GLBL_ASID_NONE_SEC_PRIV + dcore_offset, asid);
if (dcore_id > 0) {
reg_val = (asid << DCORE0_SYNC_MNGR_MSTR_IF_AXUSER_HB_ASID_RD_SHIFT) |
(asid << DCORE0_SYNC_MNGR_MSTR_IF_AXUSER_HB_ASID_WR_SHIFT);
WREG32(mmDCORE0_SYNC_MNGR_MSTR_IF_AXUSER_HB_ASID + dcore_offset, reg_val);
WREG32(mmDCORE0_SYNC_MNGR_MSTR_IF_AXUSER_HB_MMU_BP + dcore_offset, 0);
}
WREG32(mmDCORE0_MME_CTRL_LO_MME_AXUSER_HB_MMU_BP + dcore_offset, 0);
WREG32(mmDCORE0_MME_CTRL_LO_MME_AXUSER_HB_ASID + dcore_offset, rw_asid);
for (i = 0 ; i < NUM_OF_MME_SBTE_PORTS ; i++) {
ports_offset = i * DCORE_MME_SBTE_OFFSET;
WREG32(mmDCORE0_MME_SBTE0_MSTR_IF_AXUSER_HB_MMU_BP +
dcore_offset + ports_offset, 0);
WREG32(mmDCORE0_MME_SBTE0_MSTR_IF_AXUSER_HB_ASID +
dcore_offset + ports_offset, rw_asid);
}
for (i = 0 ; i < NUM_OF_MME_WB_PORTS ; i++) {
ports_offset = i * DCORE_MME_WB_OFFSET;
WREG32(mmDCORE0_MME_WB0_MSTR_IF_AXUSER_HB_MMU_BP +
dcore_offset + ports_offset, 0);
WREG32(mmDCORE0_MME_WB0_MSTR_IF_AXUSER_HB_ASID +
dcore_offset + ports_offset, rw_asid);
}
WREG32(mmDCORE0_MME_QM_AXUSER_NONSECURED_HB_MMU_BP + dcore_offset, 0);
WREG32(mmDCORE0_MME_QM_AXUSER_NONSECURED_HB_ASID + dcore_offset, rw_asid);
for (vdec_id = 0 ; vdec_id < NUM_OF_DEC_PER_DCORE ; vdec_id++) {
if (prop->decoder_enabled_mask & BIT(dcore_id * NUM_OF_DEC_PER_DCORE + vdec_id))
gaudi2_mmu_vdec_dcore_prepare(hdev, dcore_id, vdec_id, rw_asid, 0);
}
}
static void gudi2_mmu_vdec_shared_prepare(struct hl_device *hdev,
int shared_vdec_id, u32 rw_asid, u32 rw_mmu_bp)
{
u32 offset = (mmPCIE_VDEC1_BRDG_CTRL_BASE - mmPCIE_VDEC0_BRDG_CTRL_BASE) * shared_vdec_id;
WREG32(mmPCIE_VDEC0_BRDG_CTRL_AXUSER_DEC_HB_MMU_BP + offset, rw_mmu_bp);
WREG32(mmPCIE_VDEC0_BRDG_CTRL_AXUSER_DEC_HB_ASID + offset, rw_asid);
WREG32(mmPCIE_VDEC0_BRDG_CTRL_AXUSER_MSIX_ABNRM_HB_MMU_BP + offset, rw_mmu_bp);
WREG32(mmPCIE_VDEC0_BRDG_CTRL_AXUSER_MSIX_ABNRM_HB_ASID + offset, rw_asid);
WREG32(mmPCIE_VDEC0_BRDG_CTRL_AXUSER_MSIX_L2C_HB_MMU_BP + offset, rw_mmu_bp);
WREG32(mmPCIE_VDEC0_BRDG_CTRL_AXUSER_MSIX_L2C_HB_ASID + offset, rw_asid);
WREG32(mmPCIE_VDEC0_BRDG_CTRL_AXUSER_MSIX_NRM_HB_MMU_BP + offset, rw_mmu_bp);
WREG32(mmPCIE_VDEC0_BRDG_CTRL_AXUSER_MSIX_NRM_HB_ASID + offset, rw_asid);
WREG32(mmPCIE_VDEC0_BRDG_CTRL_AXUSER_MSIX_VCD_HB_MMU_BP + offset, rw_mmu_bp);
WREG32(mmPCIE_VDEC0_BRDG_CTRL_AXUSER_MSIX_VCD_HB_ASID + offset, rw_asid);
}
static void gudi2_mmu_arc_farm_arc_dup_eng_prepare(struct hl_device *hdev, int arc_farm_id,
u32 rw_asid, u32 rw_mmu_bp)
{
u32 offset = (mmARC_FARM_ARC1_DUP_ENG_BASE - mmARC_FARM_ARC0_DUP_ENG_BASE) * arc_farm_id;
WREG32(mmARC_FARM_ARC0_DUP_ENG_AXUSER_HB_MMU_BP + offset, rw_mmu_bp);
WREG32(mmARC_FARM_ARC0_DUP_ENG_AXUSER_HB_ASID + offset, rw_asid);
}
static void gaudi2_arc_mmu_prepare(struct hl_device *hdev, u32 cpu_id, u32 asid)
{
u32 reg_base, reg_offset, reg_val = 0;
reg_base = gaudi2_arc_blocks_bases[cpu_id];
reg_val = FIELD_PREP(ARC_FARM_ARC0_AUX_ARC_REGION_CFG_MMU_BP_MASK, 0);
reg_val |= FIELD_PREP(ARC_FARM_ARC0_AUX_ARC_REGION_CFG_0_ASID_MASK, asid);
reg_offset = ARC_REGION_CFG_OFFSET(ARC_REGION3_GENERAL);
WREG32(reg_base + reg_offset, reg_val);
reg_offset = ARC_REGION_CFG_OFFSET(ARC_REGION4_HBM0_FW);
WREG32(reg_base + reg_offset, reg_val);
reg_offset = ARC_REGION_CFG_OFFSET(ARC_REGION5_HBM1_GC_DATA);
WREG32(reg_base + reg_offset, reg_val);
reg_offset = ARC_REGION_CFG_OFFSET(ARC_REGION6_HBM2_GC_DATA);
WREG32(reg_base + reg_offset, reg_val);
reg_offset = ARC_REGION_CFG_OFFSET(ARC_REGION7_HBM3_GC_DATA);
WREG32(reg_base + reg_offset, reg_val);
reg_offset = ARC_REGION_CFG_OFFSET(ARC_REGION9_PCIE);
WREG32(reg_base + reg_offset, reg_val);
reg_offset = ARC_REGION_CFG_OFFSET(ARC_REGION10_GENERAL);
WREG32(reg_base + reg_offset, reg_val);
reg_offset = ARC_REGION_CFG_OFFSET(ARC_REGION11_GENERAL);
WREG32(reg_base + reg_offset, reg_val);
reg_offset = ARC_REGION_CFG_OFFSET(ARC_REGION12_GENERAL);
WREG32(reg_base + reg_offset, reg_val);
reg_offset = ARC_REGION_CFG_OFFSET(ARC_REGION13_GENERAL);
WREG32(reg_base + reg_offset, reg_val);
reg_offset = ARC_REGION_CFG_OFFSET(ARC_REGION14_GENERAL);
WREG32(reg_base + reg_offset, reg_val);
}
static int gaudi2_arc_mmu_prepare_all(struct hl_device *hdev, u32 asid)
{
int i;
if (hdev->fw_components & FW_TYPE_BOOT_CPU)
return hl_fw_cpucp_engine_core_asid_set(hdev, asid);
for (i = CPU_ID_SCHED_ARC0 ; i < NUM_OF_ARC_FARMS_ARC ; i++)
gaudi2_arc_mmu_prepare(hdev, i, asid);
for (i = GAUDI2_QUEUE_ID_PDMA_0_0 ; i < GAUDI2_QUEUE_ID_CPU_PQ ; i += 4) {
if (!gaudi2_is_queue_enabled(hdev, i))
continue;
gaudi2_arc_mmu_prepare(hdev, gaudi2_queue_id_to_arc_id[i], asid);
}
return 0;
}
static int gaudi2_mmu_shared_prepare(struct hl_device *hdev, u32 asid)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
u32 rw_asid, offset;
int rc, i;
rw_asid = FIELD_PREP(ARC_FARM_KDMA_CTX_AXUSER_HB_ASID_RD_MASK, asid) |
FIELD_PREP(ARC_FARM_KDMA_CTX_AXUSER_HB_ASID_WR_MASK, asid);
WREG32(mmPDMA0_QM_AXUSER_NONSECURED_HB_ASID, rw_asid);
WREG32(mmPDMA0_QM_AXUSER_NONSECURED_HB_MMU_BP, 0);
WREG32(mmPDMA0_CORE_CTX_AXUSER_HB_ASID, rw_asid);
WREG32(mmPDMA0_CORE_CTX_AXUSER_HB_MMU_BP, 0);
WREG32(mmPDMA1_QM_AXUSER_NONSECURED_HB_ASID, rw_asid);
WREG32(mmPDMA1_QM_AXUSER_NONSECURED_HB_MMU_BP, 0);
WREG32(mmPDMA1_CORE_CTX_AXUSER_HB_ASID, rw_asid);
WREG32(mmPDMA1_CORE_CTX_AXUSER_HB_MMU_BP, 0);
for (i = 0 ; i < NUM_OF_ROT ; i++) {
offset = i * ROT_OFFSET;
WREG32(mmROT0_QM_AXUSER_NONSECURED_HB_ASID + offset, rw_asid);
WREG32(mmROT0_QM_AXUSER_NONSECURED_HB_MMU_BP + offset, 0);
RMWREG32(mmROT0_CPL_QUEUE_AWUSER + offset, asid, MMUBP_ASID_MASK);
RMWREG32(mmROT0_DESC_HBW_ARUSER_LO + offset, asid, MMUBP_ASID_MASK);
RMWREG32(mmROT0_DESC_HBW_AWUSER_LO + offset, asid, MMUBP_ASID_MASK);
}
if (prop->decoder_enabled_mask & BIT(NUM_OF_DCORES * NUM_OF_DEC_PER_DCORE + 0))
gudi2_mmu_vdec_shared_prepare(hdev, 0, rw_asid, 0);
if (prop->decoder_enabled_mask & BIT(NUM_OF_DCORES * NUM_OF_DEC_PER_DCORE + 1))
gudi2_mmu_vdec_shared_prepare(hdev, 1, rw_asid, 0);
for (i = 0 ; i < NUM_OF_ARC_FARMS_ARC ; i++)
gudi2_mmu_arc_farm_arc_dup_eng_prepare(hdev, i, rw_asid, 0);
rc = gaudi2_arc_mmu_prepare_all(hdev, asid);
if (rc)
return rc;
return 0;
}
static void gaudi2_tpc_mmu_prepare(struct hl_device *hdev, int dcore, int inst, u32 offset,
struct iterate_module_ctx *ctx)
{
struct gaudi2_tpc_mmu_data *mmu_data = ctx->data;
WREG32(mmDCORE0_TPC0_CFG_AXUSER_HB_MMU_BP + offset, 0);
WREG32(mmDCORE0_TPC0_CFG_AXUSER_HB_ASID + offset, mmu_data->rw_asid);
WREG32(mmDCORE0_TPC0_QM_AXUSER_NONSECURED_HB_MMU_BP + offset, 0);
WREG32(mmDCORE0_TPC0_QM_AXUSER_NONSECURED_HB_ASID + offset, mmu_data->rw_asid);
}
static int gaudi2_mmu_prepare(struct hl_device *hdev, u32 asid)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
struct gaudi2_tpc_mmu_data tpc_mmu_data;
struct iterate_module_ctx tpc_iter = {
.fn = &gaudi2_tpc_mmu_prepare,
.data = &tpc_mmu_data,
};
int rc, i;
if (asid & ~DCORE0_HMMU0_STLB_ASID_ASID_MASK) {
dev_crit(hdev->dev, "asid %u is too big\n", asid);
return -EINVAL;
}
if (!(gaudi2->hw_cap_initialized & HW_CAP_MMU_MASK))
return 0;
rc = gaudi2_mmu_shared_prepare(hdev, asid);
if (rc)
return rc;
tpc_mmu_data.rw_asid = (asid << ARC_FARM_KDMA_CTX_AXUSER_HB_ASID_RD_SHIFT) |
(asid << ARC_FARM_KDMA_CTX_AXUSER_HB_ASID_WR_SHIFT);
gaudi2_iterate_tpcs(hdev, &tpc_iter);
for (i = 0 ; i < NUM_OF_DCORES ; i++)
gaudi2_mmu_dcore_prepare(hdev, i, asid);
return 0;
}
static inline bool is_info_event(u32 event)
{
switch (event) {
case GAUDI2_EVENT_CPU_CPLD_SHUTDOWN_CAUSE:
case GAUDI2_EVENT_CPU_FIX_POWER_ENV_S ... GAUDI2_EVENT_CPU_FIX_THERMAL_ENV_E:
case GAUDI2_EVENT_CPU0_STATUS_NIC0_ENG0 ... GAUDI2_EVENT_CPU11_STATUS_NIC11_ENG1:
return true;
default:
return false;
}
}
static void gaudi2_print_event(struct hl_device *hdev, u16 event_type,
bool ratelimited, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
if (ratelimited)
dev_err_ratelimited(hdev->dev, "%s: %pV\n",
gaudi2_irq_map_table[event_type].valid ?
gaudi2_irq_map_table[event_type].name : "N/A Event", &vaf);
else
dev_err(hdev->dev, "%s: %pV\n",
gaudi2_irq_map_table[event_type].valid ?
gaudi2_irq_map_table[event_type].name : "N/A Event", &vaf);
va_end(args);
}
static bool gaudi2_handle_ecc_event(struct hl_device *hdev, u16 event_type,
struct hl_eq_ecc_data *ecc_data)
{
u64 ecc_address = 0, ecc_syndrom = 0;
u8 memory_wrapper_idx = 0;
ecc_address = le64_to_cpu(ecc_data->ecc_address);
ecc_syndrom = le64_to_cpu(ecc_data->ecc_syndrom);
memory_wrapper_idx = ecc_data->memory_wrapper_idx;
gaudi2_print_event(hdev, event_type, !ecc_data->is_critical,
"ECC error detected. address: %#llx. Syndrom: %#llx. block id %u. critical %u.",
ecc_address, ecc_syndrom, memory_wrapper_idx, ecc_data->is_critical);
return !!ecc_data->is_critical;
}
static void print_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base)
{
u32 lo, hi, cq_ptr_size, arc_cq_ptr_size;
u64 cq_ptr, arc_cq_ptr, cp_current_inst;
lo = RREG32(qman_base + QM_CQ_PTR_LO_4_OFFSET);
hi = RREG32(qman_base + QM_CQ_PTR_HI_4_OFFSET);
cq_ptr = ((u64) hi) << 32 | lo;
cq_ptr_size = RREG32(qman_base + QM_CQ_TSIZE_4_OFFSET);
lo = RREG32(qman_base + QM_ARC_CQ_PTR_LO_OFFSET);
hi = RREG32(qman_base + QM_ARC_CQ_PTR_HI_OFFSET);
arc_cq_ptr = ((u64) hi) << 32 | lo;
arc_cq_ptr_size = RREG32(qman_base + QM_ARC_CQ_TSIZE_OFFSET);
lo = RREG32(qman_base + QM_CP_CURRENT_INST_LO_4_OFFSET);
hi = RREG32(qman_base + QM_CP_CURRENT_INST_HI_4_OFFSET);
cp_current_inst = ((u64) hi) << 32 | lo;
dev_info(hdev->dev,
"LowerQM. CQ: {ptr %#llx, size %u}, ARC_CQ: {ptr %#llx, size %u}, CP: {instruction %#llx}\n",
cq_ptr, cq_ptr_size, arc_cq_ptr, arc_cq_ptr_size, cp_current_inst);
}
static int gaudi2_handle_qman_err_generic(struct hl_device *hdev, u16 event_type,
u64 qman_base, u32 qid_base)
{
u32 i, j, glbl_sts_val, arb_err_val, num_error_causes, error_count = 0;
u64 glbl_sts_addr, arb_err_addr;
char reg_desc[32];
glbl_sts_addr = qman_base + (mmDCORE0_TPC0_QM_GLBL_ERR_STS_0 - mmDCORE0_TPC0_QM_BASE);
arb_err_addr = qman_base + (mmDCORE0_TPC0_QM_ARB_ERR_CAUSE - mmDCORE0_TPC0_QM_BASE);
for (i = 0 ; i < QMAN_STREAMS + 1 ; i++) {
glbl_sts_val = RREG32(glbl_sts_addr + 4 * i);
if (!glbl_sts_val)
continue;
if (i == QMAN_STREAMS) {
snprintf(reg_desc, ARRAY_SIZE(reg_desc), "LowerQM");
num_error_causes = GAUDI2_NUM_OF_LOWER_QM_ERR_CAUSE;
} else {
snprintf(reg_desc, ARRAY_SIZE(reg_desc), "stream%u", i);
num_error_causes = GAUDI2_NUM_OF_QM_ERR_CAUSE;
}
for (j = 0 ; j < num_error_causes ; j++)
if (glbl_sts_val & BIT(j)) {
gaudi2_print_event(hdev, event_type, true,
"%s. err cause: %s", reg_desc,
i == QMAN_STREAMS ?
gaudi2_lower_qman_error_cause[j] :
gaudi2_qman_error_cause[j]);
error_count++;
}
if (i == QMAN_STREAMS)
print_lower_qman_data_on_err(hdev, qman_base);
}
arb_err_val = RREG32(arb_err_addr);
if (!arb_err_val)
goto out;
for (j = 0 ; j < GAUDI2_NUM_OF_QM_ARB_ERR_CAUSE ; j++) {
if (arb_err_val & BIT(j)) {
gaudi2_print_event(hdev, event_type, true,
"ARB_ERR. err cause: %s",
gaudi2_qman_arb_error_cause[j]);
error_count++;
}
}
out:
return error_count;
}
static void gaudi2_razwi_rr_hbw_shared_printf_info(struct hl_device *hdev,
u64 rtr_mstr_if_base_addr, bool is_write, char *name,
enum gaudi2_engine_id id, u64 *event_mask)
{
u32 razwi_hi, razwi_lo, razwi_xy;
u16 eng_id = id;
u8 rd_wr_flag;
if (is_write) {
razwi_hi = RREG32(rtr_mstr_if_base_addr + RR_SHRD_HBW_AW_RAZWI_HI);
razwi_lo = RREG32(rtr_mstr_if_base_addr + RR_SHRD_HBW_AW_RAZWI_LO);
razwi_xy = RREG32(rtr_mstr_if_base_addr + RR_SHRD_HBW_AW_RAZWI_XY);
rd_wr_flag = HL_RAZWI_WRITE;
} else {
razwi_hi = RREG32(rtr_mstr_if_base_addr + RR_SHRD_HBW_AR_RAZWI_HI);
razwi_lo = RREG32(rtr_mstr_if_base_addr + RR_SHRD_HBW_AR_RAZWI_LO);
razwi_xy = RREG32(rtr_mstr_if_base_addr + RR_SHRD_HBW_AR_RAZWI_XY);
rd_wr_flag = HL_RAZWI_READ;
}
hl_handle_razwi(hdev, (u64)razwi_hi << 32 | razwi_lo, &eng_id, 1,
rd_wr_flag | HL_RAZWI_HBW, event_mask);
dev_err_ratelimited(hdev->dev,
"%s-RAZWI SHARED RR HBW %s error, address %#llx, Initiator coordinates 0x%x\n",
name, is_write ? "WR" : "RD", (u64)razwi_hi << 32 | razwi_lo, razwi_xy);
}
static void gaudi2_razwi_rr_lbw_shared_printf_info(struct hl_device *hdev,
u64 rtr_mstr_if_base_addr, bool is_write, char *name,
enum gaudi2_engine_id id, u64 *event_mask)
{
u64 razwi_addr = CFG_BASE;
u32 razwi_xy;
u16 eng_id = id;
u8 rd_wr_flag;
if (is_write) {
razwi_addr += RREG32(rtr_mstr_if_base_addr + RR_SHRD_LBW_AW_RAZWI);
razwi_xy = RREG32(rtr_mstr_if_base_addr + RR_SHRD_LBW_AW_RAZWI_XY);
rd_wr_flag = HL_RAZWI_WRITE;
} else {
razwi_addr += RREG32(rtr_mstr_if_base_addr + RR_SHRD_LBW_AR_RAZWI);
razwi_xy = RREG32(rtr_mstr_if_base_addr + RR_SHRD_LBW_AR_RAZWI_XY);
rd_wr_flag = HL_RAZWI_READ;
}
hl_handle_razwi(hdev, razwi_addr, &eng_id, 1, rd_wr_flag | HL_RAZWI_LBW, event_mask);
dev_err_ratelimited(hdev->dev,
"%s-RAZWI SHARED RR LBW %s error, mstr_if 0x%llx, captured address 0x%llX Initiator coordinates 0x%x\n",
name, is_write ? "WR" : "RD", rtr_mstr_if_base_addr, razwi_addr,
razwi_xy);
}
static enum gaudi2_engine_id gaudi2_razwi_calc_engine_id(struct hl_device *hdev,
enum razwi_event_sources module, u8 module_idx)
{
switch (module) {
case RAZWI_TPC:
if (module_idx == (NUM_OF_TPC_PER_DCORE * NUM_OF_DCORES))
return GAUDI2_DCORE0_ENGINE_ID_TPC_6;
return (((module_idx / NUM_OF_TPC_PER_DCORE) * ENGINE_ID_DCORE_OFFSET) +
(module_idx % NUM_OF_TPC_PER_DCORE) +
(GAUDI2_DCORE0_ENGINE_ID_TPC_0 - GAUDI2_DCORE0_ENGINE_ID_EDMA_0));
case RAZWI_MME:
return ((GAUDI2_DCORE0_ENGINE_ID_MME - GAUDI2_DCORE0_ENGINE_ID_EDMA_0) +
(module_idx * ENGINE_ID_DCORE_OFFSET));
case RAZWI_EDMA:
return (((module_idx / NUM_OF_EDMA_PER_DCORE) * ENGINE_ID_DCORE_OFFSET) +
(module_idx % NUM_OF_EDMA_PER_DCORE));
case RAZWI_PDMA:
return (GAUDI2_ENGINE_ID_PDMA_0 + module_idx);
case RAZWI_NIC:
return (GAUDI2_ENGINE_ID_NIC0_0 + (NIC_NUMBER_OF_QM_PER_MACRO * module_idx));
case RAZWI_DEC:
if (module_idx == 8)
return GAUDI2_PCIE_ENGINE_ID_DEC_0;
if (module_idx == 9)
return GAUDI2_PCIE_ENGINE_ID_DEC_1;
;
return (((module_idx / NUM_OF_DEC_PER_DCORE) * ENGINE_ID_DCORE_OFFSET) +
(module_idx % NUM_OF_DEC_PER_DCORE) +
(GAUDI2_DCORE0_ENGINE_ID_DEC_0 - GAUDI2_DCORE0_ENGINE_ID_EDMA_0));
case RAZWI_ROT:
return GAUDI2_ENGINE_ID_ROT_0 + module_idx;
default:
return GAUDI2_ENGINE_ID_SIZE;
}
}
static void gaudi2_ack_module_razwi_event_handler(struct hl_device *hdev,
enum razwi_event_sources module, u8 module_idx,
u8 module_sub_idx, u64 *event_mask)
{
bool via_sft = false;
u32 hbw_rtr_id, lbw_rtr_id, dcore_id, dcore_rtr_id, eng_id, binned_idx;
u64 hbw_rtr_mstr_if_base_addr, lbw_rtr_mstr_if_base_addr;
u32 hbw_shrd_aw = 0, hbw_shrd_ar = 0;
u32 lbw_shrd_aw = 0, lbw_shrd_ar = 0;
char initiator_name[64];
switch (module) {
case RAZWI_TPC:
sprintf(initiator_name, "TPC_%u", module_idx);
if (hdev->tpc_binning) {
binned_idx = __ffs(hdev->tpc_binning);
if (binned_idx == module_idx)
module_idx = TPC_ID_DCORE0_TPC6;
}
hbw_rtr_id = gaudi2_tpc_initiator_hbw_rtr_id[module_idx];
if (hl_is_fw_sw_ver_below(hdev, 1, 9) &&
!hdev->asic_prop.fw_security_enabled &&
((module_idx == 0) || (module_idx == 1)))
lbw_rtr_id = DCORE0_RTR0;
else
lbw_rtr_id = gaudi2_tpc_initiator_lbw_rtr_id[module_idx];
break;
case RAZWI_MME:
sprintf(initiator_name, "MME_%u", module_idx);
switch (module_sub_idx) {
case MME_WAP0:
hbw_rtr_id = gaudi2_mme_initiator_rtr_id[module_idx].wap0;
break;
case MME_WAP1:
hbw_rtr_id = gaudi2_mme_initiator_rtr_id[module_idx].wap1;
break;
case MME_WRITE:
hbw_rtr_id = gaudi2_mme_initiator_rtr_id[module_idx].write;
break;
case MME_READ:
hbw_rtr_id = gaudi2_mme_initiator_rtr_id[module_idx].read;
break;
case MME_SBTE0:
hbw_rtr_id = gaudi2_mme_initiator_rtr_id[module_idx].sbte0;
break;
case MME_SBTE1:
hbw_rtr_id = gaudi2_mme_initiator_rtr_id[module_idx].sbte1;
break;
case MME_SBTE2:
hbw_rtr_id = gaudi2_mme_initiator_rtr_id[module_idx].sbte2;
break;
case MME_SBTE3:
hbw_rtr_id = gaudi2_mme_initiator_rtr_id[module_idx].sbte3;
break;
case MME_SBTE4:
hbw_rtr_id = gaudi2_mme_initiator_rtr_id[module_idx].sbte4;
break;
default:
return;
}
lbw_rtr_id = hbw_rtr_id;
break;
case RAZWI_EDMA:
hbw_rtr_mstr_if_base_addr = gaudi2_edma_initiator_hbw_sft[module_idx];
dcore_id = module_idx / NUM_OF_EDMA_PER_DCORE;
lbw_rtr_mstr_if_base_addr = mmSFT0_LBW_RTR_IF_MSTR_IF_RR_SHRD_HBW_BASE +
dcore_id * SFT_DCORE_OFFSET;
via_sft = true;
sprintf(initiator_name, "EDMA_%u", module_idx);
break;
case RAZWI_PDMA:
hbw_rtr_id = gaudi2_pdma_initiator_hbw_rtr_id[module_idx];
lbw_rtr_id = gaudi2_pdma_initiator_lbw_rtr_id[module_idx];
sprintf(initiator_name, "PDMA_%u", module_idx);
break;
case RAZWI_NIC:
hbw_rtr_id = gaudi2_nic_initiator_hbw_rtr_id[module_idx];
lbw_rtr_id = gaudi2_nic_initiator_lbw_rtr_id[module_idx];
sprintf(initiator_name, "NIC_%u", module_idx);
break;
case RAZWI_DEC:
sprintf(initiator_name, "DEC_%u", module_idx);
if (hdev->decoder_binning) {
binned_idx = __ffs(hdev->decoder_binning);
if (binned_idx == module_idx)
module_idx = DEC_ID_PCIE_VDEC1;
}
hbw_rtr_id = gaudi2_dec_initiator_hbw_rtr_id[module_idx];
lbw_rtr_id = gaudi2_dec_initiator_lbw_rtr_id[module_idx];
break;
case RAZWI_ROT:
hbw_rtr_id = gaudi2_rot_initiator_hbw_rtr_id[module_idx];
lbw_rtr_id = gaudi2_rot_initiator_lbw_rtr_id[module_idx];
sprintf(initiator_name, "ROT_%u", module_idx);
break;
default:
return;
}
if (!via_sft) {
dcore_id = hbw_rtr_id / NUM_OF_RTR_PER_DCORE;
dcore_rtr_id = hbw_rtr_id % NUM_OF_RTR_PER_DCORE;
hbw_rtr_mstr_if_base_addr = mmDCORE0_RTR0_CTRL_BASE +
dcore_id * DCORE_OFFSET +
dcore_rtr_id * DCORE_RTR_OFFSET +
RTR_MSTR_IF_OFFSET;
lbw_rtr_mstr_if_base_addr = hbw_rtr_mstr_if_base_addr +
(((s32)lbw_rtr_id - hbw_rtr_id) * DCORE_RTR_OFFSET);
}
hbw_shrd_aw = RREG32(hbw_rtr_mstr_if_base_addr + RR_SHRD_HBW_AW_RAZWI_HAPPENED);
hbw_shrd_ar = RREG32(hbw_rtr_mstr_if_base_addr + RR_SHRD_HBW_AR_RAZWI_HAPPENED);
lbw_shrd_aw = RREG32(lbw_rtr_mstr_if_base_addr + RR_SHRD_LBW_AW_RAZWI_HAPPENED);
lbw_shrd_ar = RREG32(lbw_rtr_mstr_if_base_addr + RR_SHRD_LBW_AR_RAZWI_HAPPENED);
eng_id = gaudi2_razwi_calc_engine_id(hdev, module, module_idx);
if (hbw_shrd_aw) {
gaudi2_razwi_rr_hbw_shared_printf_info(hdev, hbw_rtr_mstr_if_base_addr, true,
initiator_name, eng_id, event_mask);
WREG32(hbw_rtr_mstr_if_base_addr + RR_SHRD_HBW_AW_RAZWI_HAPPENED, hbw_shrd_aw);
}
if (hbw_shrd_ar) {
gaudi2_razwi_rr_hbw_shared_printf_info(hdev, hbw_rtr_mstr_if_base_addr, false,
initiator_name, eng_id, event_mask);
WREG32(hbw_rtr_mstr_if_base_addr + RR_SHRD_HBW_AR_RAZWI_HAPPENED, hbw_shrd_ar);
}
if (lbw_shrd_aw) {
gaudi2_razwi_rr_lbw_shared_printf_info(hdev, lbw_rtr_mstr_if_base_addr, true,
initiator_name, eng_id, event_mask);
WREG32(lbw_rtr_mstr_if_base_addr + RR_SHRD_LBW_AW_RAZWI_HAPPENED, lbw_shrd_aw);
}
if (lbw_shrd_ar) {
gaudi2_razwi_rr_lbw_shared_printf_info(hdev, lbw_rtr_mstr_if_base_addr, false,
initiator_name, eng_id, event_mask);
WREG32(lbw_rtr_mstr_if_base_addr + RR_SHRD_LBW_AR_RAZWI_HAPPENED, lbw_shrd_ar);
}
}
static void gaudi2_check_if_razwi_happened(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
u8 mod_idx, sub_mod;
for (mod_idx = 0 ; mod_idx < (NUM_OF_TPC_PER_DCORE * NUM_OF_DCORES + 1) ; mod_idx++) {
if (prop->tpc_enabled_mask & BIT(mod_idx))
gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_TPC, mod_idx, 0, NULL);
}
for (mod_idx = 0 ; mod_idx < (NUM_OF_MME_PER_DCORE * NUM_OF_DCORES) ; mod_idx++)
for (sub_mod = MME_WAP0 ; sub_mod < MME_INITIATORS_MAX ; sub_mod++)
gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_MME, mod_idx,
sub_mod, NULL);
for (mod_idx = 0 ; mod_idx < (NUM_OF_EDMA_PER_DCORE * NUM_OF_DCORES) ; mod_idx++)
if (prop->edma_enabled_mask & BIT(mod_idx))
gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_EDMA, mod_idx, 0, NULL);
for (mod_idx = 0 ; mod_idx < NUM_OF_PDMA ; mod_idx++)
gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_PDMA, mod_idx, 0, NULL);
for (mod_idx = 0 ; mod_idx < NIC_NUMBER_OF_PORTS ; mod_idx++)
if (hdev->nic_ports_mask & BIT(mod_idx))
gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_NIC, mod_idx >> 1, 0,
NULL);
for (mod_idx = 0 ; mod_idx < NUMBER_OF_DEC ; mod_idx++)
if (prop->decoder_enabled_mask & BIT(mod_idx))
gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_DEC, mod_idx, 0, NULL);
for (mod_idx = 0 ; mod_idx < NUM_OF_ROT ; mod_idx++)
gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_ROT, mod_idx, 0, NULL);
}
static int gaudi2_psoc_razwi_get_engines(struct gaudi2_razwi_info *razwi_info, u32 array_size,
u32 axuser_xy, u32 *base, u16 *eng_id,
char *eng_name)
{
int i, num_of_eng = 0;
u16 str_size = 0;
for (i = 0 ; i < array_size ; i++) {
if (axuser_xy != razwi_info[i].axuser_xy)
continue;
eng_id[num_of_eng] = razwi_info[i].eng_id;
base[num_of_eng] = razwi_info[i].rtr_ctrl;
if (!num_of_eng)
str_size += snprintf(eng_name + str_size,
PSOC_RAZWI_ENG_STR_SIZE - str_size, "%s",
razwi_info[i].eng_name);
else
str_size += snprintf(eng_name + str_size,
PSOC_RAZWI_ENG_STR_SIZE - str_size, " or %s",
razwi_info[i].eng_name);
num_of_eng++;
}
return num_of_eng;
}
static bool gaudi2_handle_psoc_razwi_happened(struct hl_device *hdev, u32 razwi_reg,
u64 *event_mask)
{
u32 axuser_xy = RAZWI_GET_AXUSER_XY(razwi_reg), addr_hi = 0, addr_lo = 0;
u32 base[PSOC_RAZWI_MAX_ENG_PER_RTR];
u16 num_of_eng, eng_id[PSOC_RAZWI_MAX_ENG_PER_RTR];
char eng_name_str[PSOC_RAZWI_ENG_STR_SIZE];
bool razwi_happened = false;
u64 addr;
int i;
num_of_eng = gaudi2_psoc_razwi_get_engines(common_razwi_info, ARRAY_SIZE(common_razwi_info),
axuser_xy, base, eng_id, eng_name_str);
if (!num_of_eng) {
axuser_xy = RAZWI_GET_AXUSER_LOW_XY(razwi_reg);
num_of_eng = gaudi2_psoc_razwi_get_engines(mme_razwi_info,
ARRAY_SIZE(mme_razwi_info),
axuser_xy, base, eng_id,
eng_name_str);
}
for (i = 0 ; i < num_of_eng ; i++) {
if (RREG32(base[i] + DEC_RAZWI_HBW_AW_SET)) {
addr_hi = RREG32(base[i] + DEC_RAZWI_HBW_AW_ADDR_HI);
addr_lo = RREG32(base[i] + DEC_RAZWI_HBW_AW_ADDR_LO);
addr = ((u64)addr_hi << 32) + addr_lo;
if (addr) {
dev_err(hdev->dev,
"PSOC HBW AW RAZWI: %s, address (aligned to 128 byte): 0x%llX\n",
eng_name_str, addr);
hl_handle_razwi(hdev, addr, &eng_id[0],
num_of_eng, HL_RAZWI_HBW | HL_RAZWI_WRITE, event_mask);
razwi_happened = true;
}
}
if (RREG32(base[i] + DEC_RAZWI_HBW_AR_SET)) {
addr_hi = RREG32(base[i] + DEC_RAZWI_HBW_AR_ADDR_HI);
addr_lo = RREG32(base[i] + DEC_RAZWI_HBW_AR_ADDR_LO);
addr = ((u64)addr_hi << 32) + addr_lo;
if (addr) {
dev_err(hdev->dev,
"PSOC HBW AR RAZWI: %s, address (aligned to 128 byte): 0x%llX\n",
eng_name_str, addr);
hl_handle_razwi(hdev, addr, &eng_id[0],
num_of_eng, HL_RAZWI_HBW | HL_RAZWI_READ, event_mask);
razwi_happened = true;
}
}
if (RREG32(base[i] + DEC_RAZWI_LBW_AW_SET)) {
addr_lo = RREG32(base[i] + DEC_RAZWI_LBW_AW_ADDR);
if (addr_lo) {
dev_err(hdev->dev,
"PSOC LBW AW RAZWI: %s, address (aligned to 128 byte): 0x%X\n",
eng_name_str, addr_lo);
hl_handle_razwi(hdev, addr_lo, &eng_id[0],
num_of_eng, HL_RAZWI_LBW | HL_RAZWI_WRITE, event_mask);
razwi_happened = true;
}
}
if (RREG32(base[i] + DEC_RAZWI_LBW_AR_SET)) {
addr_lo = RREG32(base[i] + DEC_RAZWI_LBW_AR_ADDR);
if (addr_lo) {
dev_err(hdev->dev,
"PSOC LBW AR RAZWI: %s, address (aligned to 128 byte): 0x%X\n",
eng_name_str, addr_lo);
hl_handle_razwi(hdev, addr_lo, &eng_id[0],
num_of_eng, HL_RAZWI_LBW | HL_RAZWI_READ, event_mask);
razwi_happened = true;
}
}
if (razwi_happened)
break;
}
return razwi_happened;
}
static int gaudi2_ack_psoc_razwi_event_handler(struct hl_device *hdev, u64 *event_mask)
{
u32 razwi_mask_info, razwi_intr = 0, error_count = 0;
if (hdev->pldm || !(hdev->fw_components & FW_TYPE_LINUX)) {
razwi_intr = RREG32(mmPSOC_GLOBAL_CONF_RAZWI_INTERRUPT);
if (!razwi_intr)
return 0;
}
razwi_mask_info = RREG32(mmPSOC_GLOBAL_CONF_RAZWI_MASK_INFO);
dev_err_ratelimited(hdev->dev,
"PSOC RAZWI interrupt: Mask %d, AR %d, AW %d, AXUSER_L 0x%x AXUSER_H 0x%x\n",
FIELD_GET(PSOC_GLOBAL_CONF_RAZWI_MASK_INFO_MASK_MASK, razwi_mask_info),
FIELD_GET(PSOC_GLOBAL_CONF_RAZWI_MASK_INFO_WAS_AR_MASK, razwi_mask_info),
FIELD_GET(PSOC_GLOBAL_CONF_RAZWI_MASK_INFO_WAS_AW_MASK, razwi_mask_info),
FIELD_GET(PSOC_GLOBAL_CONF_RAZWI_MASK_INFO_AXUSER_L_MASK, razwi_mask_info),
FIELD_GET(PSOC_GLOBAL_CONF_RAZWI_MASK_INFO_AXUSER_H_MASK, razwi_mask_info));
if (gaudi2_handle_psoc_razwi_happened(hdev, razwi_mask_info, event_mask))
error_count++;
else
dev_err_ratelimited(hdev->dev,
"PSOC RAZWI interrupt: invalid razwi info (0x%x)\n",
razwi_mask_info);
if (hdev->pldm || !(hdev->fw_components & FW_TYPE_LINUX))
WREG32(mmPSOC_GLOBAL_CONF_RAZWI_INTERRUPT, razwi_intr);
return error_count;
}
static int _gaudi2_handle_qm_sei_err(struct hl_device *hdev, u64 qman_base, u16 event_type)
{
u32 i, sts_val, sts_clr_val = 0, error_count = 0;
sts_val = RREG32(qman_base + QM_SEI_STATUS_OFFSET);
for (i = 0 ; i < GAUDI2_NUM_OF_QM_SEI_ERR_CAUSE ; i++) {
if (sts_val & BIT(i)) {
gaudi2_print_event(hdev, event_type, true,
"err cause: %s", gaudi2_qm_sei_error_cause[i]);
sts_clr_val |= BIT(i);
error_count++;
}
}
WREG32(qman_base + QM_SEI_STATUS_OFFSET, sts_clr_val);
return error_count;
}
static int gaudi2_handle_qm_sei_err(struct hl_device *hdev, u16 event_type,
bool extended_err_check, u64 *event_mask)
{
enum razwi_event_sources module;
u32 error_count = 0;
u64 qman_base;
u8 index;
switch (event_type) {
case GAUDI2_EVENT_TPC0_AXI_ERR_RSP ... GAUDI2_EVENT_TPC23_AXI_ERR_RSP:
index = event_type - GAUDI2_EVENT_TPC0_AXI_ERR_RSP;
qman_base = mmDCORE0_TPC0_QM_BASE +
(index / NUM_OF_TPC_PER_DCORE) * DCORE_OFFSET +
(index % NUM_OF_TPC_PER_DCORE) * DCORE_TPC_OFFSET;
module = RAZWI_TPC;
break;
case GAUDI2_EVENT_TPC24_AXI_ERR_RSP:
qman_base = mmDCORE0_TPC6_QM_BASE;
module = RAZWI_TPC;
break;
case GAUDI2_EVENT_MME0_CTRL_AXI_ERROR_RESPONSE:
case GAUDI2_EVENT_MME1_CTRL_AXI_ERROR_RESPONSE:
case GAUDI2_EVENT_MME2_CTRL_AXI_ERROR_RESPONSE:
case GAUDI2_EVENT_MME3_CTRL_AXI_ERROR_RESPONSE:
index = (event_type - GAUDI2_EVENT_MME0_CTRL_AXI_ERROR_RESPONSE) /
(GAUDI2_EVENT_MME1_CTRL_AXI_ERROR_RESPONSE -
GAUDI2_EVENT_MME0_CTRL_AXI_ERROR_RESPONSE);
qman_base = mmDCORE0_MME_QM_BASE + index * DCORE_OFFSET;
module = RAZWI_MME;
break;
case GAUDI2_EVENT_PDMA_CH0_AXI_ERR_RSP:
case GAUDI2_EVENT_PDMA_CH1_AXI_ERR_RSP:
index = event_type - GAUDI2_EVENT_PDMA_CH0_AXI_ERR_RSP;
qman_base = mmPDMA0_QM_BASE + index * PDMA_OFFSET;
module = RAZWI_PDMA;
break;
case GAUDI2_EVENT_ROTATOR0_AXI_ERROR_RESPONSE:
case GAUDI2_EVENT_ROTATOR1_AXI_ERROR_RESPONSE:
index = event_type - GAUDI2_EVENT_ROTATOR0_AXI_ERROR_RESPONSE;
qman_base = mmROT0_QM_BASE + index * ROT_OFFSET;
module = RAZWI_ROT;
break;
default:
return 0;
}
error_count = _gaudi2_handle_qm_sei_err(hdev, qman_base, event_type);
if (event_type >= GAUDI2_EVENT_NIC0_AXI_ERROR_RESPONSE &&
event_type <= GAUDI2_EVENT_NIC11_AXI_ERROR_RESPONSE)
error_count += _gaudi2_handle_qm_sei_err(hdev,
qman_base + NIC_QM_OFFSET, event_type);
if (extended_err_check) {
gaudi2_ack_module_razwi_event_handler(hdev, module, 0, 0, event_mask);
hl_check_for_glbl_errors(hdev);
}
return error_count;
}
static int gaudi2_handle_qman_err(struct hl_device *hdev, u16 event_type, u64 *event_mask)
{
u32 qid_base, error_count = 0;
u64 qman_base;
u8 index = 0;
switch (event_type) {
case GAUDI2_EVENT_TPC0_QM ... GAUDI2_EVENT_TPC5_QM:
index = event_type - GAUDI2_EVENT_TPC0_QM;
qid_base = GAUDI2_QUEUE_ID_DCORE0_TPC_0_0 + index * QMAN_STREAMS;
qman_base = mmDCORE0_TPC0_QM_BASE + index * DCORE_TPC_OFFSET;
break;
case GAUDI2_EVENT_TPC6_QM ... GAUDI2_EVENT_TPC11_QM:
index = event_type - GAUDI2_EVENT_TPC6_QM;
qid_base = GAUDI2_QUEUE_ID_DCORE1_TPC_0_0 + index * QMAN_STREAMS;
qman_base = mmDCORE1_TPC0_QM_BASE + index * DCORE_TPC_OFFSET;
break;
case GAUDI2_EVENT_TPC12_QM ... GAUDI2_EVENT_TPC17_QM:
index = event_type - GAUDI2_EVENT_TPC12_QM;
qid_base = GAUDI2_QUEUE_ID_DCORE2_TPC_0_0 + index * QMAN_STREAMS;
qman_base = mmDCORE2_TPC0_QM_BASE + index * DCORE_TPC_OFFSET;
break;
case GAUDI2_EVENT_TPC18_QM ... GAUDI2_EVENT_TPC23_QM:
index = event_type - GAUDI2_EVENT_TPC18_QM;
qid_base = GAUDI2_QUEUE_ID_DCORE3_TPC_0_0 + index * QMAN_STREAMS;
qman_base = mmDCORE3_TPC0_QM_BASE + index * DCORE_TPC_OFFSET;
break;
case GAUDI2_EVENT_TPC24_QM:
qid_base = GAUDI2_QUEUE_ID_DCORE0_TPC_6_0;
qman_base = mmDCORE0_TPC6_QM_BASE;
break;
case GAUDI2_EVENT_MME0_QM:
qid_base = GAUDI2_QUEUE_ID_DCORE0_MME_0_0;
qman_base = mmDCORE0_MME_QM_BASE;
break;
case GAUDI2_EVENT_MME1_QM:
qid_base = GAUDI2_QUEUE_ID_DCORE1_MME_0_0;
qman_base = mmDCORE1_MME_QM_BASE;
break;
case GAUDI2_EVENT_MME2_QM:
qid_base = GAUDI2_QUEUE_ID_DCORE2_MME_0_0;
qman_base = mmDCORE2_MME_QM_BASE;
break;
case GAUDI2_EVENT_MME3_QM:
qid_base = GAUDI2_QUEUE_ID_DCORE3_MME_0_0;
qman_base = mmDCORE3_MME_QM_BASE;
break;
case GAUDI2_EVENT_HDMA0_QM:
index = 0;
qid_base = GAUDI2_QUEUE_ID_DCORE0_EDMA_0_0;
qman_base = mmDCORE0_EDMA0_QM_BASE;
break;
case GAUDI2_EVENT_HDMA1_QM:
index = 1;
qid_base = GAUDI2_QUEUE_ID_DCORE0_EDMA_1_0;
qman_base = mmDCORE0_EDMA1_QM_BASE;
break;
case GAUDI2_EVENT_HDMA2_QM:
index = 2;
qid_base = GAUDI2_QUEUE_ID_DCORE1_EDMA_0_0;
qman_base = mmDCORE1_EDMA0_QM_BASE;
break;
case GAUDI2_EVENT_HDMA3_QM:
index = 3;
qid_base = GAUDI2_QUEUE_ID_DCORE1_EDMA_1_0;
qman_base = mmDCORE1_EDMA1_QM_BASE;
break;
case GAUDI2_EVENT_HDMA4_QM:
index = 4;
qid_base = GAUDI2_QUEUE_ID_DCORE2_EDMA_0_0;
qman_base = mmDCORE2_EDMA0_QM_BASE;
break;
case GAUDI2_EVENT_HDMA5_QM:
index = 5;
qid_base = GAUDI2_QUEUE_ID_DCORE2_EDMA_1_0;
qman_base = mmDCORE2_EDMA1_QM_BASE;
break;
case GAUDI2_EVENT_HDMA6_QM:
index = 6;
qid_base = GAUDI2_QUEUE_ID_DCORE3_EDMA_0_0;
qman_base = mmDCORE3_EDMA0_QM_BASE;
break;
case GAUDI2_EVENT_HDMA7_QM:
index = 7;
qid_base = GAUDI2_QUEUE_ID_DCORE3_EDMA_1_0;
qman_base = mmDCORE3_EDMA1_QM_BASE;
break;
case GAUDI2_EVENT_PDMA0_QM:
qid_base = GAUDI2_QUEUE_ID_PDMA_0_0;
qman_base = mmPDMA0_QM_BASE;
break;
case GAUDI2_EVENT_PDMA1_QM:
qid_base = GAUDI2_QUEUE_ID_PDMA_1_0;
qman_base = mmPDMA1_QM_BASE;
break;
case GAUDI2_EVENT_ROTATOR0_ROT0_QM:
qid_base = GAUDI2_QUEUE_ID_ROT_0_0;
qman_base = mmROT0_QM_BASE;
break;
case GAUDI2_EVENT_ROTATOR1_ROT1_QM:
qid_base = GAUDI2_QUEUE_ID_ROT_1_0;
qman_base = mmROT1_QM_BASE;
break;
default:
return 0;
}
error_count = gaudi2_handle_qman_err_generic(hdev, event_type, qman_base, qid_base);
if (event_type >= GAUDI2_EVENT_HDMA2_QM && event_type <= GAUDI2_EVENT_HDMA5_QM) {
error_count += _gaudi2_handle_qm_sei_err(hdev, qman_base, event_type);
gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_EDMA, index, 0, event_mask);
}
hl_check_for_glbl_errors(hdev);
return error_count;
}
static int gaudi2_handle_arc_farm_sei_err(struct hl_device *hdev, u16 event_type)
{
u32 i, sts_val, sts_clr_val, error_count = 0, arc_farm;
for (arc_farm = 0 ; arc_farm < NUM_OF_ARC_FARMS_ARC ; arc_farm++) {
sts_clr_val = 0;
sts_val = RREG32(mmARC_FARM_ARC0_AUX_ARC_SEI_INTR_STS +
(arc_farm * ARC_FARM_OFFSET));
for (i = 0 ; i < GAUDI2_NUM_OF_ARC_SEI_ERR_CAUSE ; i++) {
if (sts_val & BIT(i)) {
gaudi2_print_event(hdev, event_type, true,
"ARC FARM ARC %u err cause: %s",
arc_farm, gaudi2_arc_sei_error_cause[i]);
sts_clr_val |= BIT(i);
error_count++;
}
}
WREG32(mmARC_FARM_ARC0_AUX_ARC_SEI_INTR_CLR + (arc_farm * ARC_FARM_OFFSET),
sts_clr_val);
}
hl_check_for_glbl_errors(hdev);
return error_count;
}
static int gaudi2_handle_cpu_sei_err(struct hl_device *hdev, u16 event_type)
{
u32 i, sts_val, sts_clr_val = 0, error_count = 0;
sts_val = RREG32(mmCPU_IF_CPU_SEI_INTR_STS);
for (i = 0 ; i < GAUDI2_NUM_OF_CPU_SEI_ERR_CAUSE ; i++) {
if (sts_val & BIT(i)) {
gaudi2_print_event(hdev, event_type, true,
"err cause: %s", gaudi2_cpu_sei_error_cause[i]);
sts_clr_val |= BIT(i);
error_count++;
}
}
hl_check_for_glbl_errors(hdev);
WREG32(mmCPU_IF_CPU_SEI_INTR_CLR, sts_clr_val);
return error_count;
}
static int gaudi2_handle_rot_err(struct hl_device *hdev, u8 rot_index, u16 event_type,
struct hl_eq_razwi_with_intr_cause *razwi_with_intr_cause,
u64 *event_mask)
{
u64 intr_cause_data = le64_to_cpu(razwi_with_intr_cause->intr_cause.intr_cause_data);
u32 error_count = 0;
int i;
for (i = 0 ; i < GAUDI2_NUM_OF_ROT_ERR_CAUSE ; i++)
if (intr_cause_data & BIT(i)) {
gaudi2_print_event(hdev, event_type, true,
"err cause: %s", guadi2_rot_error_cause[i]);
error_count++;
}
gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_ROT, rot_index, 0, event_mask);
hl_check_for_glbl_errors(hdev);
return error_count;
}
static int gaudi2_tpc_ack_interrupts(struct hl_device *hdev, u8 tpc_index, u16 event_type,
struct hl_eq_razwi_with_intr_cause *razwi_with_intr_cause,
u64 *event_mask)
{
u64 intr_cause_data = le64_to_cpu(razwi_with_intr_cause->intr_cause.intr_cause_data);
u32 error_count = 0;
int i;
for (i = 0 ; i < GAUDI2_NUM_OF_TPC_INTR_CAUSE ; i++)
if (intr_cause_data & BIT(i)) {
gaudi2_print_event(hdev, event_type, true,
"interrupt cause: %s", gaudi2_tpc_interrupts_cause[i]);
error_count++;
}
gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_TPC, tpc_index, 0, event_mask);
hl_check_for_glbl_errors(hdev);
return error_count;
}
static int gaudi2_handle_dec_err(struct hl_device *hdev, u8 dec_index, u16 event_type,
u64 *event_mask)
{
u32 sts_addr, sts_val, sts_clr_val = 0, error_count = 0;
int i;
if (dec_index < NUM_OF_VDEC_PER_DCORE * NUM_OF_DCORES)
sts_addr = mmDCORE0_VDEC0_BRDG_CTRL_CAUSE_INTR +
DCORE_OFFSET * (dec_index / NUM_OF_DEC_PER_DCORE) +
DCORE_VDEC_OFFSET * (dec_index % NUM_OF_DEC_PER_DCORE);
else
sts_addr = mmPCIE_VDEC0_BRDG_CTRL_CAUSE_INTR + PCIE_VDEC_OFFSET *
(dec_index - NUM_OF_VDEC_PER_DCORE * NUM_OF_DCORES);
sts_val = RREG32(sts_addr);
for (i = 0 ; i < GAUDI2_NUM_OF_DEC_ERR_CAUSE ; i++) {
if (sts_val & BIT(i)) {
gaudi2_print_event(hdev, event_type, true,
"err cause: %s", gaudi2_dec_error_cause[i]);
sts_clr_val |= BIT(i);
error_count++;
}
}
gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_DEC, dec_index, 0, event_mask);
hl_check_for_glbl_errors(hdev);
WREG32(sts_addr, sts_clr_val);
return error_count;
}
static int gaudi2_handle_mme_err(struct hl_device *hdev, u8 mme_index, u16 event_type,
u64 *event_mask)
{
u32 sts_addr, sts_val, sts_clr_addr, sts_clr_val = 0, error_count = 0;
int i;
sts_addr = mmDCORE0_MME_CTRL_LO_INTR_CAUSE + DCORE_OFFSET * mme_index;
sts_clr_addr = mmDCORE0_MME_CTRL_LO_INTR_CLEAR + DCORE_OFFSET * mme_index;
sts_val = RREG32(sts_addr);
for (i = 0 ; i < GAUDI2_NUM_OF_MME_ERR_CAUSE ; i++) {
if (sts_val & BIT(i)) {
gaudi2_print_event(hdev, event_type, true,
"err cause: %s", guadi2_mme_error_cause[i]);
sts_clr_val |= BIT(i);
error_count++;
}
}
for (i = MME_WRITE ; i < MME_INITIATORS_MAX ; i++)
gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_MME, mme_index, i, event_mask);
hl_check_for_glbl_errors(hdev);
WREG32(sts_clr_addr, sts_clr_val);
return error_count;
}
static int gaudi2_handle_mme_sbte_err(struct hl_device *hdev, u16 event_type,
u64 intr_cause_data)
{
int i, error_count = 0;
for (i = 0 ; i < GAUDI2_NUM_OF_MME_SBTE_ERR_CAUSE ; i++)
if (intr_cause_data & BIT(i)) {
gaudi2_print_event(hdev, event_type, true,
"err cause: %s", guadi2_mme_sbte_error_cause[i]);
error_count++;
}
hl_check_for_glbl_errors(hdev);
return error_count;
}
static int gaudi2_handle_mme_wap_err(struct hl_device *hdev, u8 mme_index, u16 event_type,
u64 *event_mask)
{
u32 sts_addr, sts_val, sts_clr_addr, sts_clr_val = 0, error_count = 0;
int i;
sts_addr = mmDCORE0_MME_ACC_INTR_CAUSE + DCORE_OFFSET * mme_index;
sts_clr_addr = mmDCORE0_MME_ACC_INTR_CLEAR + DCORE_OFFSET * mme_index;
sts_val = RREG32(sts_addr);
for (i = 0 ; i < GAUDI2_NUM_OF_MME_WAP_ERR_CAUSE ; i++) {
if (sts_val & BIT(i)) {
gaudi2_print_event(hdev, event_type, true,
"err cause: %s", guadi2_mme_wap_error_cause[i]);
sts_clr_val |= BIT(i);
error_count++;
}
}
gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_MME, mme_index, MME_WAP0, event_mask);
gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_MME, mme_index, MME_WAP1, event_mask);
hl_check_for_glbl_errors(hdev);
WREG32(sts_clr_addr, sts_clr_val);
return error_count;
}
static int gaudi2_handle_kdma_core_event(struct hl_device *hdev, u16 event_type,
u64 intr_cause_data)
{
u32 error_count = 0;
int i;
for (i = 0 ; i < GAUDI2_NUM_OF_DMA_CORE_INTR_CAUSE ; i++)
if (intr_cause_data & BIT(i)) {
gaudi2_print_event(hdev, event_type, true,
"err cause: %s", gaudi2_kdma_core_interrupts_cause[i]);
error_count++;
}
hl_check_for_glbl_errors(hdev);
return error_count;
}
static int gaudi2_handle_dma_core_event(struct hl_device *hdev, u16 event_type, u64 intr_cause)
{
u32 error_count = 0;
int i;
for (i = 0 ; i < GAUDI2_NUM_OF_DMA_CORE_INTR_CAUSE ; i++)
if (intr_cause & BIT(i)) {
gaudi2_print_event(hdev, event_type, true,
"err cause: %s", gaudi2_dma_core_interrupts_cause[i]);
error_count++;
}
hl_check_for_glbl_errors(hdev);
return error_count;
}
static void gaudi2_print_pcie_mstr_rr_mstr_if_razwi_info(struct hl_device *hdev, u64 *event_mask)
{
u32 mstr_if_base_addr = mmPCIE_MSTR_RR_MSTR_IF_RR_SHRD_HBW_BASE, razwi_happened_addr;
razwi_happened_addr = mstr_if_base_addr + RR_SHRD_HBW_AW_RAZWI_HAPPENED;
if (RREG32(razwi_happened_addr)) {
gaudi2_razwi_rr_hbw_shared_printf_info(hdev, mstr_if_base_addr, true, "PCIE",
GAUDI2_ENGINE_ID_PCIE, event_mask);
WREG32(razwi_happened_addr, 0x1);
}
razwi_happened_addr = mstr_if_base_addr + RR_SHRD_HBW_AR_RAZWI_HAPPENED;
if (RREG32(razwi_happened_addr)) {
gaudi2_razwi_rr_hbw_shared_printf_info(hdev, mstr_if_base_addr, false, "PCIE",
GAUDI2_ENGINE_ID_PCIE, event_mask);
WREG32(razwi_happened_addr, 0x1);
}
razwi_happened_addr = mstr_if_base_addr + RR_SHRD_LBW_AW_RAZWI_HAPPENED;
if (RREG32(razwi_happened_addr)) {
gaudi2_razwi_rr_lbw_shared_printf_info(hdev, mstr_if_base_addr, true, "PCIE",
GAUDI2_ENGINE_ID_PCIE, event_mask);
WREG32(razwi_happened_addr, 0x1);
}
razwi_happened_addr = mstr_if_base_addr + RR_SHRD_LBW_AR_RAZWI_HAPPENED;
if (RREG32(razwi_happened_addr)) {
gaudi2_razwi_rr_lbw_shared_printf_info(hdev, mstr_if_base_addr, false, "PCIE",
GAUDI2_ENGINE_ID_PCIE, event_mask);
WREG32(razwi_happened_addr, 0x1);
}
}
static int gaudi2_print_pcie_addr_dec_info(struct hl_device *hdev, u16 event_type,
u64 intr_cause_data, u64 *event_mask)
{
u32 error_count = 0;
int i;
gaudi2_print_event(hdev, event_type, true,
"intr_cause_data: %#llx", intr_cause_data);
for (i = 0 ; i < GAUDI2_NUM_OF_PCIE_ADDR_DEC_ERR_CAUSE ; i++) {
if (!(intr_cause_data & BIT_ULL(i)))
continue;
gaudi2_print_event(hdev, event_type, true,
"err cause: %s", gaudi2_pcie_addr_dec_error_cause[i]);
error_count++;
}
hl_check_for_glbl_errors(hdev);
gaudi2_print_pcie_mstr_rr_mstr_if_razwi_info(hdev, event_mask);
return error_count;
}
static int gaudi2_handle_pif_fatal(struct hl_device *hdev, u16 event_type,
u64 intr_cause_data)
{
u32 error_count = 0;
int i;
for (i = 0 ; i < GAUDI2_NUM_OF_PMMU_FATAL_ERR_CAUSE ; i++) {
if (intr_cause_data & BIT_ULL(i)) {
gaudi2_print_event(hdev, event_type, true,
"err cause: %s", gaudi2_pmmu_fatal_interrupts_cause[i]);
error_count++;
}
}
return error_count;
}
static int gaudi2_handle_hif_fatal(struct hl_device *hdev, u16 event_type, u64 intr_cause_data)
{
u32 error_count = 0;
int i;
for (i = 0 ; i < GAUDI2_NUM_OF_HIF_FATAL_ERR_CAUSE ; i++) {
if (intr_cause_data & BIT_ULL(i)) {
gaudi2_print_event(hdev, event_type, true,
"err cause: %s", gaudi2_hif_fatal_interrupts_cause[i]);
error_count++;
}
}
return error_count;
}
static void gaudi2_handle_page_error(struct hl_device *hdev, u64 mmu_base, bool is_pmmu,
u64 *event_mask)
{
u32 valid, val;
u64 addr;
valid = RREG32(mmu_base + MMU_OFFSET(mmDCORE0_HMMU0_MMU_ACCESS_PAGE_ERROR_VALID));
if (!(valid & DCORE0_HMMU0_MMU_ACCESS_PAGE_ERROR_VALID_PAGE_ERR_VALID_ENTRY_MASK))
return;
val = RREG32(mmu_base + MMU_OFFSET(mmDCORE0_HMMU0_MMU_PAGE_ERROR_CAPTURE));
addr = val & DCORE0_HMMU0_MMU_PAGE_ERROR_CAPTURE_VA_63_32_MASK;
addr <<= 32;
addr |= RREG32(mmu_base + MMU_OFFSET(mmDCORE0_HMMU0_MMU_PAGE_ERROR_CAPTURE_VA));
if (is_pmmu) {
dev_err_ratelimited(hdev->dev, "PMMU page fault on va 0x%llx\n", addr);
} else {
addr = gaudi2_mmu_descramble_addr(hdev, addr);
addr &= HW_UNSCRAMBLED_BITS_MASK;
dev_err_ratelimited(hdev->dev, "HMMU page fault on va range 0x%llx - 0x%llx\n",
addr, addr + ~HW_UNSCRAMBLED_BITS_MASK);
}
hl_handle_page_fault(hdev, addr, 0, is_pmmu, event_mask);
WREG32(mmu_base + MMU_OFFSET(mmDCORE0_HMMU0_MMU_ACCESS_PAGE_ERROR_VALID), 0);
}
static void gaudi2_handle_access_error(struct hl_device *hdev, u64 mmu_base, bool is_pmmu)
{
u32 valid, val;
u64 addr;
valid = RREG32(mmu_base + MMU_OFFSET(mmDCORE0_HMMU0_MMU_ACCESS_PAGE_ERROR_VALID));
if (!(valid & DCORE0_HMMU0_MMU_ACCESS_PAGE_ERROR_VALID_ACCESS_ERR_VALID_ENTRY_MASK))
return;
val = RREG32(mmu_base + MMU_OFFSET(mmDCORE0_HMMU0_MMU_ACCESS_ERROR_CAPTURE));
addr = val & DCORE0_HMMU0_MMU_ACCESS_ERROR_CAPTURE_VA_63_32_MASK;
addr <<= 32;
addr |= RREG32(mmu_base + MMU_OFFSET(mmDCORE0_HMMU0_MMU_ACCESS_ERROR_CAPTURE_VA));
if (!is_pmmu)
addr = gaudi2_mmu_descramble_addr(hdev, addr);
dev_err_ratelimited(hdev->dev, "%s access error on va 0x%llx\n",
is_pmmu ? "PMMU" : "HMMU", addr);
WREG32(mmu_base + MMU_OFFSET(mmDCORE0_HMMU0_MMU_ACCESS_PAGE_ERROR_VALID), 0);
}
static int gaudi2_handle_mmu_spi_sei_generic(struct hl_device *hdev, u16 event_type,
u64 mmu_base, bool is_pmmu, u64 *event_mask)
{
u32 spi_sei_cause, interrupt_clr = 0x0, error_count = 0;
int i;
spi_sei_cause = RREG32(mmu_base + MMU_SPI_SEI_CAUSE_OFFSET);
for (i = 0 ; i < GAUDI2_NUM_OF_MMU_SPI_SEI_CAUSE ; i++) {
if (spi_sei_cause & BIT(i)) {
gaudi2_print_event(hdev, event_type, true,
"err cause: %s", gaudi2_mmu_spi_sei[i].cause);
if (i == 0)
gaudi2_handle_page_error(hdev, mmu_base, is_pmmu, event_mask);
else if (i == 1)
gaudi2_handle_access_error(hdev, mmu_base, is_pmmu);
if (gaudi2_mmu_spi_sei[i].clear_bit >= 0)
interrupt_clr |= BIT(gaudi2_mmu_spi_sei[i].clear_bit);
error_count++;
}
}
WREG32_AND(mmu_base + MMU_SPI_SEI_CAUSE_OFFSET, ~spi_sei_cause);
WREG32(mmu_base + MMU_INTERRUPT_CLR_OFFSET, interrupt_clr);
return error_count;
}
static int gaudi2_handle_sm_err(struct hl_device *hdev, u16 event_type, u8 sm_index)
{
u32 sei_cause_addr, sei_cause_val, sei_cause_cause, sei_cause_log,
cq_intr_addr, cq_intr_val, cq_intr_queue_index, error_count = 0;
int i;
sei_cause_addr = mmDCORE0_SYNC_MNGR_GLBL_SM_SEI_CAUSE + DCORE_OFFSET * sm_index;
cq_intr_addr = mmDCORE0_SYNC_MNGR_GLBL_CQ_INTR + DCORE_OFFSET * sm_index;
sei_cause_val = RREG32(sei_cause_addr);
sei_cause_cause = FIELD_GET(DCORE0_SYNC_MNGR_GLBL_SM_SEI_CAUSE_CAUSE_MASK, sei_cause_val);
cq_intr_val = RREG32(cq_intr_addr);
if (sei_cause_cause) {
sei_cause_log = FIELD_GET(DCORE0_SYNC_MNGR_GLBL_SM_SEI_CAUSE_LOG_MASK,
sei_cause_val);
for (i = 0 ; i < GAUDI2_NUM_OF_SM_SEI_ERR_CAUSE ; i++) {
if (!(sei_cause_cause & BIT(i)))
continue;
gaudi2_print_event(hdev, event_type, true,
"err cause: %s. %s: 0x%X",
gaudi2_sm_sei_cause[i].cause_name,
gaudi2_sm_sei_cause[i].log_name,
sei_cause_log);
error_count++;
break;
}
WREG32(sei_cause_addr, 0);
}
if (cq_intr_val & DCORE0_SYNC_MNGR_GLBL_CQ_INTR_CQ_SEC_INTR_MASK) {
cq_intr_queue_index =
FIELD_GET(DCORE0_SYNC_MNGR_GLBL_CQ_INTR_CQ_INTR_QUEUE_INDEX_MASK,
cq_intr_val);
dev_err_ratelimited(hdev->dev, "SM%u err. err cause: CQ_INTR. queue index: %u\n",
sm_index, cq_intr_queue_index);
error_count++;
WREG32(cq_intr_addr, 0);
}
hl_check_for_glbl_errors(hdev);
return error_count;
}
static u64 get_hmmu_base(u16 event_type)
{
u8 dcore, index_in_dcore;
switch (event_type) {
case GAUDI2_EVENT_HMMU_0_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU0_SPI_BASE ... GAUDI2_EVENT_HMMU0_SECURITY_ERROR:
dcore = 0;
index_in_dcore = 0;
break;
case GAUDI2_EVENT_HMMU_1_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU1_SPI_BASE ... GAUDI2_EVENT_HMMU1_SECURITY_ERROR:
dcore = 1;
index_in_dcore = 0;
break;
case GAUDI2_EVENT_HMMU_2_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU2_SPI_BASE ... GAUDI2_EVENT_HMMU2_SECURITY_ERROR:
dcore = 0;
index_in_dcore = 1;
break;
case GAUDI2_EVENT_HMMU_3_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU3_SPI_BASE ... GAUDI2_EVENT_HMMU3_SECURITY_ERROR:
dcore = 1;
index_in_dcore = 1;
break;
case GAUDI2_EVENT_HMMU_4_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU4_SPI_BASE ... GAUDI2_EVENT_HMMU4_SECURITY_ERROR:
dcore = 3;
index_in_dcore = 2;
break;
case GAUDI2_EVENT_HMMU_5_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU5_SPI_BASE ... GAUDI2_EVENT_HMMU5_SECURITY_ERROR:
dcore = 2;
index_in_dcore = 2;
break;
case GAUDI2_EVENT_HMMU_6_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU6_SPI_BASE ... GAUDI2_EVENT_HMMU6_SECURITY_ERROR:
dcore = 3;
index_in_dcore = 3;
break;
case GAUDI2_EVENT_HMMU_7_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU7_SPI_BASE ... GAUDI2_EVENT_HMMU7_SECURITY_ERROR:
dcore = 2;
index_in_dcore = 3;
break;
case GAUDI2_EVENT_HMMU_8_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU8_SPI_BASE ... GAUDI2_EVENT_HMMU8_SECURITY_ERROR:
dcore = 0;
index_in_dcore = 2;
break;
case GAUDI2_EVENT_HMMU_9_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU9_SPI_BASE ... GAUDI2_EVENT_HMMU9_SECURITY_ERROR:
dcore = 1;
index_in_dcore = 2;
break;
case GAUDI2_EVENT_HMMU_10_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU10_SPI_BASE ... GAUDI2_EVENT_HMMU10_SECURITY_ERROR:
dcore = 0;
index_in_dcore = 3;
break;
case GAUDI2_EVENT_HMMU_11_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU11_SPI_BASE ... GAUDI2_EVENT_HMMU11_SECURITY_ERROR:
dcore = 1;
index_in_dcore = 3;
break;
case GAUDI2_EVENT_HMMU_12_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU12_SPI_BASE ... GAUDI2_EVENT_HMMU12_SECURITY_ERROR:
dcore = 3;
index_in_dcore = 0;
break;
case GAUDI2_EVENT_HMMU_13_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU13_SPI_BASE ... GAUDI2_EVENT_HMMU13_SECURITY_ERROR:
dcore = 2;
index_in_dcore = 0;
break;
case GAUDI2_EVENT_HMMU_14_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU14_SPI_BASE ... GAUDI2_EVENT_HMMU14_SECURITY_ERROR:
dcore = 3;
index_in_dcore = 1;
break;
case GAUDI2_EVENT_HMMU_15_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU15_SPI_BASE ... GAUDI2_EVENT_HMMU15_SECURITY_ERROR:
dcore = 2;
index_in_dcore = 1;
break;
default:
return ULONG_MAX;
}
return mmDCORE0_HMMU0_MMU_BASE + dcore * DCORE_OFFSET + index_in_dcore * DCORE_HMMU_OFFSET;
}
static int gaudi2_handle_mmu_spi_sei_err(struct hl_device *hdev, u16 event_type, u64 *event_mask)
{
bool is_pmmu = false;
u32 error_count = 0;
u64 mmu_base;
switch (event_type) {
case GAUDI2_EVENT_HMMU_0_AXI_ERR_RSP ... GAUDI2_EVENT_HMMU_12_AXI_ERR_RSP:
case GAUDI2_EVENT_HMMU0_SPI_BASE ... GAUDI2_EVENT_HMMU12_SECURITY_ERROR:
mmu_base = get_hmmu_base(event_type);
break;
case GAUDI2_EVENT_PMMU0_PAGE_FAULT_WR_PERM ... GAUDI2_EVENT_PMMU0_SECURITY_ERROR:
case GAUDI2_EVENT_PMMU_AXI_ERR_RSP_0:
is_pmmu = true;
mmu_base = mmPMMU_HBW_MMU_BASE;
break;
default:
return 0;
}
if (mmu_base == ULONG_MAX)
return 0;
error_count = gaudi2_handle_mmu_spi_sei_generic(hdev, event_type, mmu_base,
is_pmmu, event_mask);
hl_check_for_glbl_errors(hdev);
return error_count;
}
static bool gaudi2_hbm_sei_handle_read_err(struct hl_device *hdev,
struct hl_eq_hbm_sei_read_err_intr_info *rd_err_data, u32 err_cnt)
{
u32 addr, beat, beat_shift;
bool rc = false;
dev_err_ratelimited(hdev->dev,
"READ ERROR count: ECC SERR: %d, ECC DERR: %d, RD_PARITY: %d\n",
FIELD_GET(HBM_ECC_SERR_CNTR_MASK, err_cnt),
FIELD_GET(HBM_ECC_DERR_CNTR_MASK, err_cnt),
FIELD_GET(HBM_RD_PARITY_CNTR_MASK, err_cnt));
addr = le32_to_cpu(rd_err_data->dbg_rd_err_addr.rd_addr_val);
dev_err_ratelimited(hdev->dev,
"READ ERROR address: sid(%u), bg(%u), ba(%u), col(%u), row(%u)\n",
FIELD_GET(HBM_RD_ADDR_SID_MASK, addr),
FIELD_GET(HBM_RD_ADDR_BG_MASK, addr),
FIELD_GET(HBM_RD_ADDR_BA_MASK, addr),
FIELD_GET(HBM_RD_ADDR_COL_MASK, addr),
FIELD_GET(HBM_RD_ADDR_ROW_MASK, addr));
for (beat = 0 ; beat < 4 ; beat++) {
if (le32_to_cpu(rd_err_data->dbg_rd_err_misc) &
(HBM_RD_ERR_SERR_BEAT0_MASK << beat))
dev_err_ratelimited(hdev->dev, "Beat%d ECC SERR: DM: %#x, Syndrome: %#x\n",
beat,
le32_to_cpu(rd_err_data->dbg_rd_err_dm),
le32_to_cpu(rd_err_data->dbg_rd_err_syndrome));
if (le32_to_cpu(rd_err_data->dbg_rd_err_misc) &
(HBM_RD_ERR_DERR_BEAT0_MASK << beat)) {
dev_err_ratelimited(hdev->dev, "Beat%d ECC DERR: DM: %#x, Syndrome: %#x\n",
beat,
le32_to_cpu(rd_err_data->dbg_rd_err_dm),
le32_to_cpu(rd_err_data->dbg_rd_err_syndrome));
rc |= true;
}
beat_shift = beat * HBM_RD_ERR_BEAT_SHIFT;
if (le32_to_cpu(rd_err_data->dbg_rd_err_misc) &
(HBM_RD_ERR_PAR_ERR_BEAT0_MASK << beat_shift)) {
dev_err_ratelimited(hdev->dev,
"Beat%d read PARITY: DM: %#x, PAR data: %#x\n",
beat,
le32_to_cpu(rd_err_data->dbg_rd_err_dm),
(le32_to_cpu(rd_err_data->dbg_rd_err_misc) &
(HBM_RD_ERR_PAR_DATA_BEAT0_MASK << beat_shift)) >>
(HBM_RD_ERR_PAR_DATA_BEAT0_SHIFT + beat_shift));
rc |= true;
}
dev_err_ratelimited(hdev->dev, "Beat%d DQ data:\n", beat);
dev_err_ratelimited(hdev->dev, "\t0x%08x\n",
le32_to_cpu(rd_err_data->dbg_rd_err_data[beat * 2]));
dev_err_ratelimited(hdev->dev, "\t0x%08x\n",
le32_to_cpu(rd_err_data->dbg_rd_err_data[beat * 2 + 1]));
}
return rc;
}
static void gaudi2_hbm_sei_print_wr_par_info(struct hl_device *hdev,
struct hl_eq_hbm_sei_wr_par_intr_info *wr_par_err_data, u32 err_cnt)
{
struct hbm_sei_wr_cmd_address *wr_cmd_addr = wr_par_err_data->dbg_last_wr_cmds;
u32 i, curr_addr, derr = wr_par_err_data->dbg_derr;
dev_err_ratelimited(hdev->dev, "WRITE PARITY ERROR count: %d\n", err_cnt);
dev_err_ratelimited(hdev->dev, "CK-0 DERR: 0x%02x, CK-1 DERR: 0x%02x\n",
derr & 0x3, derr & 0xc);
dev_err_ratelimited(hdev->dev, "Last latched write commands addresses:\n");
for (i = 0 ; i < HBM_WR_PAR_CMD_LIFO_LEN ; i++) {
curr_addr = le32_to_cpu(wr_cmd_addr[i].dbg_wr_cmd_addr);
dev_err_ratelimited(hdev->dev,
"\twrite cmd[%u]: Address: SID(%u) BG(%u) BA(%u) COL(%u).\n",
i,
FIELD_GET(WR_PAR_LAST_CMD_SID_MASK, curr_addr),
FIELD_GET(WR_PAR_LAST_CMD_BG_MASK, curr_addr),
FIELD_GET(WR_PAR_LAST_CMD_BA_MASK, curr_addr),
FIELD_GET(WR_PAR_LAST_CMD_COL_MASK, curr_addr));
}
}
static void gaudi2_hbm_sei_print_ca_par_info(struct hl_device *hdev,
struct hl_eq_hbm_sei_ca_par_intr_info *ca_par_err_data, u32 err_cnt)
{
__le32 *col_cmd = ca_par_err_data->dbg_col;
__le16 *row_cmd = ca_par_err_data->dbg_row;
u32 i;
dev_err_ratelimited(hdev->dev, "CA ERROR count: %d\n", err_cnt);
dev_err_ratelimited(hdev->dev, "Last latched C&R bus commands:\n");
for (i = 0 ; i < HBM_CA_ERR_CMD_LIFO_LEN ; i++)
dev_err_ratelimited(hdev->dev, "cmd%u: ROW(0x%04x) COL(0x%05x)\n", i,
le16_to_cpu(row_cmd[i]) & (u16)GENMASK(13, 0),
le32_to_cpu(col_cmd[i]) & (u32)GENMASK(17, 0));
}
static bool gaudi2_handle_hbm_mc_sei_err(struct hl_device *hdev, u16 event_type,
struct hl_eq_hbm_sei_data *sei_data)
{
bool require_hard_reset = false;
u32 hbm_id, mc_id, cause_idx;
hbm_id = (event_type - GAUDI2_EVENT_HBM0_MC0_SEI_SEVERE) / 4;
mc_id = ((event_type - GAUDI2_EVENT_HBM0_MC0_SEI_SEVERE) / 2) % 2;
cause_idx = sei_data->hdr.sei_cause;
if (cause_idx > GAUDI2_NUM_OF_HBM_SEI_CAUSE - 1) {
gaudi2_print_event(hdev, event_type, true,
"err cause: %s",
"Invalid HBM SEI event cause (%d) provided by FW", cause_idx);
return true;
}
gaudi2_print_event(hdev, event_type, !sei_data->hdr.is_critical,
"System %s Error Interrupt - HBM(%u) MC(%u) MC_CH(%u) MC_PC(%u). Error cause: %s",
sei_data->hdr.is_critical ? "Critical" : "Non-critical",
hbm_id, mc_id, sei_data->hdr.mc_channel, sei_data->hdr.mc_pseudo_channel,
hbm_mc_sei_cause[cause_idx]);
switch (cause_idx) {
case HBM_SEI_CATTRIP:
require_hard_reset = true;
break;
case HBM_SEI_CMD_PARITY_EVEN:
gaudi2_hbm_sei_print_ca_par_info(hdev, &sei_data->ca_parity_even_info,
le32_to_cpu(sei_data->hdr.cnt));
require_hard_reset = true;
break;
case HBM_SEI_CMD_PARITY_ODD:
gaudi2_hbm_sei_print_ca_par_info(hdev, &sei_data->ca_parity_odd_info,
le32_to_cpu(sei_data->hdr.cnt));
require_hard_reset = true;
break;
case HBM_SEI_WRITE_DATA_PARITY_ERR:
gaudi2_hbm_sei_print_wr_par_info(hdev, &sei_data->wr_parity_info,
le32_to_cpu(sei_data->hdr.cnt));
require_hard_reset = true;
break;
case HBM_SEI_READ_ERR:
require_hard_reset = gaudi2_hbm_sei_handle_read_err(hdev,
&sei_data->read_err_info,
le32_to_cpu(sei_data->hdr.cnt));
break;
default:
break;
}
require_hard_reset |= !!sei_data->hdr.is_critical;
return require_hard_reset;
}
static int gaudi2_handle_hbm_cattrip(struct hl_device *hdev, u16 event_type,
u64 intr_cause_data)
{
if (intr_cause_data) {
gaudi2_print_event(hdev, event_type, true,
"temperature error cause: %#llx", intr_cause_data);
return 1;
}
return 0;
}
static int gaudi2_handle_hbm_mc_spi(struct hl_device *hdev, u64 intr_cause_data)
{
u32 i, error_count = 0;
for (i = 0 ; i < GAUDI2_NUM_OF_HBM_MC_SPI_CAUSE ; i++)
if (intr_cause_data & hbm_mc_spi[i].mask) {
dev_dbg(hdev->dev, "HBM spi event: notification cause(%s)\n",
hbm_mc_spi[i].cause);
error_count++;
}
return error_count;
}
static void gaudi2_print_clk_change_info(struct hl_device *hdev, u16 event_type, u64 *event_mask)
{
ktime_t zero_time = ktime_set(0, 0);
mutex_lock(&hdev->clk_throttling.lock);
switch (event_type) {
case GAUDI2_EVENT_CPU_FIX_POWER_ENV_S:
hdev->clk_throttling.current_reason |= HL_CLK_THROTTLE_POWER;
hdev->clk_throttling.aggregated_reason |= HL_CLK_THROTTLE_POWER;
hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_POWER].start = ktime_get();
hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_POWER].end = zero_time;
dev_dbg_ratelimited(hdev->dev, "Clock throttling due to power consumption\n");
break;
case GAUDI2_EVENT_CPU_FIX_POWER_ENV_E:
hdev->clk_throttling.current_reason &= ~HL_CLK_THROTTLE_POWER;
hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_POWER].end = ktime_get();
dev_dbg_ratelimited(hdev->dev, "Power envelop is safe, back to optimal clock\n");
break;
case GAUDI2_EVENT_CPU_FIX_THERMAL_ENV_S:
hdev->clk_throttling.current_reason |= HL_CLK_THROTTLE_THERMAL;
hdev->clk_throttling.aggregated_reason |= HL_CLK_THROTTLE_THERMAL;
hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].start = ktime_get();
hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].end = zero_time;
*event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
dev_info_ratelimited(hdev->dev, "Clock throttling due to overheating\n");
break;
case GAUDI2_EVENT_CPU_FIX_THERMAL_ENV_E:
hdev->clk_throttling.current_reason &= ~HL_CLK_THROTTLE_THERMAL;
hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].end = ktime_get();
*event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
dev_info_ratelimited(hdev->dev, "Thermal envelop is safe, back to optimal clock\n");
break;
default:
dev_err(hdev->dev, "Received invalid clock change event %d\n", event_type);
break;
}
mutex_unlock(&hdev->clk_throttling.lock);
}
static void gaudi2_print_out_of_sync_info(struct hl_device *hdev, u16 event_type,
struct cpucp_pkt_sync_err *sync_err)
{
struct hl_hw_queue *q = &hdev->kernel_queues[GAUDI2_QUEUE_ID_CPU_PQ];
gaudi2_print_event(hdev, event_type, false,
"FW: pi=%u, ci=%u, LKD: pi=%u, ci=%d",
le32_to_cpu(sync_err->pi), le32_to_cpu(sync_err->ci),
q->pi, atomic_read(&q->ci));
}
static int gaudi2_handle_pcie_p2p_msix(struct hl_device *hdev, u16 event_type)
{
u32 p2p_intr, msix_gw_intr, error_count = 0;
p2p_intr = RREG32(mmPCIE_WRAP_P2P_INTR);
msix_gw_intr = RREG32(mmPCIE_WRAP_MSIX_GW_INTR);
if (p2p_intr) {
gaudi2_print_event(hdev, event_type, true,
"pcie p2p transaction terminated due to security, req_id(0x%x)",
RREG32(mmPCIE_WRAP_P2P_REQ_ID));
WREG32(mmPCIE_WRAP_P2P_INTR, 0x1);
error_count++;
}
if (msix_gw_intr) {
gaudi2_print_event(hdev, event_type, true,
"pcie msi-x gen denied due to vector num check failure, vec(0x%X)",
RREG32(mmPCIE_WRAP_MSIX_GW_VEC));
WREG32(mmPCIE_WRAP_MSIX_GW_INTR, 0x1);
error_count++;
}
return error_count;
}
static int gaudi2_handle_pcie_drain(struct hl_device *hdev,
struct hl_eq_pcie_drain_ind_data *drain_data)
{
u64 lbw_rd, lbw_wr, hbw_rd, hbw_wr, cause, error_count = 0;
cause = le64_to_cpu(drain_data->intr_cause.intr_cause_data);
lbw_rd = le64_to_cpu(drain_data->drain_rd_addr_lbw);
lbw_wr = le64_to_cpu(drain_data->drain_wr_addr_lbw);
hbw_rd = le64_to_cpu(drain_data->drain_rd_addr_hbw);
hbw_wr = le64_to_cpu(drain_data->drain_wr_addr_hbw);
if (cause & BIT_ULL(0)) {
dev_err_ratelimited(hdev->dev,
"PCIE AXI drain LBW completed, read_err %u, write_err %u\n",
!!lbw_rd, !!lbw_wr);
error_count++;
}
if (cause & BIT_ULL(1)) {
dev_err_ratelimited(hdev->dev,
"PCIE AXI drain HBW completed, raddr %#llx, waddr %#llx\n",
hbw_rd, hbw_wr);
error_count++;
}
return error_count;
}
static int gaudi2_handle_psoc_drain(struct hl_device *hdev, u64 intr_cause_data)
{
u32 error_count = 0;
int i;
for (i = 0 ; i < GAUDI2_NUM_OF_AXI_DRAIN_ERR_CAUSE ; i++) {
if (intr_cause_data & BIT_ULL(i)) {
dev_err_ratelimited(hdev->dev, "PSOC %s completed\n",
gaudi2_psoc_axi_drain_interrupts_cause[i]);
error_count++;
}
}
hl_check_for_glbl_errors(hdev);
return error_count;
}
static void gaudi2_print_cpu_pkt_failure_info(struct hl_device *hdev, u16 event_type,
struct cpucp_pkt_sync_err *sync_err)
{
struct hl_hw_queue *q = &hdev->kernel_queues[GAUDI2_QUEUE_ID_CPU_PQ];
gaudi2_print_event(hdev, event_type, false,
"FW reported sanity check failure, FW: pi=%u, ci=%u, LKD: pi=%u, ci=%d",
le32_to_cpu(sync_err->pi), le32_to_cpu(sync_err->ci), q->pi, atomic_read(&q->ci));
}
static int hl_arc_event_handle(struct hl_device *hdev, u16 event_type,
struct hl_eq_engine_arc_intr_data *data)
{
struct hl_engine_arc_dccm_queue_full_irq *q;
u32 intr_type, engine_id;
u64 payload;
intr_type = le32_to_cpu(data->intr_type);
engine_id = le32_to_cpu(data->engine_id);
payload = le64_to_cpu(data->payload);
switch (intr_type) {
case ENGINE_ARC_DCCM_QUEUE_FULL_IRQ:
q = (struct hl_engine_arc_dccm_queue_full_irq *) &payload;
gaudi2_print_event(hdev, event_type, true,
"ARC DCCM Full event: EngId: %u, Intr_type: %u, Qidx: %u",
engine_id, intr_type, q->queue_index);
return 1;
default:
gaudi2_print_event(hdev, event_type, true, "Unknown ARC event type");
return 0;
}
}
static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
bool reset_required = false, is_critical = false;
u32 index, ctl, reset_flags = 0, error_count = 0;
u64 event_mask = 0;
u16 event_type;
ctl = le32_to_cpu(eq_entry->hdr.ctl);
event_type = ((ctl & EQ_CTL_EVENT_TYPE_MASK) >> EQ_CTL_EVENT_TYPE_SHIFT);
if (event_type >= GAUDI2_EVENT_SIZE) {
dev_err(hdev->dev, "Event type %u exceeds maximum of %u",
event_type, GAUDI2_EVENT_SIZE - 1);
return;
}
gaudi2->events_stat[event_type]++;
gaudi2->events_stat_aggregate[event_type]++;
switch (event_type) {
case GAUDI2_EVENT_PCIE_CORE_SERR ... GAUDI2_EVENT_ARC0_ECC_DERR:
fallthrough;
case GAUDI2_EVENT_ROTATOR0_SERR ... GAUDI2_EVENT_ROTATOR1_DERR:
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
reset_required = gaudi2_handle_ecc_event(hdev, event_type, &eq_entry->ecc_data);
is_critical = eq_entry->ecc_data.is_critical;
error_count++;
break;
case GAUDI2_EVENT_TPC0_QM ... GAUDI2_EVENT_PDMA1_QM:
fallthrough;
case GAUDI2_EVENT_ROTATOR0_ROT0_QM ... GAUDI2_EVENT_ROTATOR1_ROT1_QM:
fallthrough;
case GAUDI2_EVENT_NIC0_QM0 ... GAUDI2_EVENT_NIC11_QM1:
error_count = gaudi2_handle_qman_err(hdev, event_type, &event_mask);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_ARC_AXI_ERROR_RESPONSE_0:
error_count = gaudi2_handle_arc_farm_sei_err(hdev, event_type);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_CPU_AXI_ERR_RSP:
error_count = gaudi2_handle_cpu_sei_err(hdev, event_type);
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_CRITICL_FW_ERR;
break;
case GAUDI2_EVENT_PDMA_CH0_AXI_ERR_RSP:
case GAUDI2_EVENT_PDMA_CH1_AXI_ERR_RSP:
error_count = gaudi2_handle_qm_sei_err(hdev, event_type, true, &event_mask);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_ROTATOR0_AXI_ERROR_RESPONSE:
case GAUDI2_EVENT_ROTATOR1_AXI_ERROR_RESPONSE:
index = event_type - GAUDI2_EVENT_ROTATOR0_AXI_ERROR_RESPONSE;
error_count = gaudi2_handle_rot_err(hdev, index, event_type,
&eq_entry->razwi_with_intr_cause, &event_mask);
error_count += gaudi2_handle_qm_sei_err(hdev, event_type, false, &event_mask);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_TPC0_AXI_ERR_RSP ... GAUDI2_EVENT_TPC24_AXI_ERR_RSP:
index = event_type - GAUDI2_EVENT_TPC0_AXI_ERR_RSP;
error_count = gaudi2_tpc_ack_interrupts(hdev, index, event_type,
&eq_entry->razwi_with_intr_cause, &event_mask);
error_count += gaudi2_handle_qm_sei_err(hdev, event_type, false, &event_mask);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_DEC0_AXI_ERR_RSPONSE ... GAUDI2_EVENT_DEC9_AXI_ERR_RSPONSE:
index = event_type - GAUDI2_EVENT_DEC0_AXI_ERR_RSPONSE;
error_count = gaudi2_handle_dec_err(hdev, index, event_type, &event_mask);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_TPC0_KERNEL_ERR:
case GAUDI2_EVENT_TPC1_KERNEL_ERR:
case GAUDI2_EVENT_TPC2_KERNEL_ERR:
case GAUDI2_EVENT_TPC3_KERNEL_ERR:
case GAUDI2_EVENT_TPC4_KERNEL_ERR:
case GAUDI2_EVENT_TPC5_KERNEL_ERR:
case GAUDI2_EVENT_TPC6_KERNEL_ERR:
case GAUDI2_EVENT_TPC7_KERNEL_ERR:
case GAUDI2_EVENT_TPC8_KERNEL_ERR:
case GAUDI2_EVENT_TPC9_KERNEL_ERR:
case GAUDI2_EVENT_TPC10_KERNEL_ERR:
case GAUDI2_EVENT_TPC11_KERNEL_ERR:
case GAUDI2_EVENT_TPC12_KERNEL_ERR:
case GAUDI2_EVENT_TPC13_KERNEL_ERR:
case GAUDI2_EVENT_TPC14_KERNEL_ERR:
case GAUDI2_EVENT_TPC15_KERNEL_ERR:
case GAUDI2_EVENT_TPC16_KERNEL_ERR:
case GAUDI2_EVENT_TPC17_KERNEL_ERR:
case GAUDI2_EVENT_TPC18_KERNEL_ERR:
case GAUDI2_EVENT_TPC19_KERNEL_ERR:
case GAUDI2_EVENT_TPC20_KERNEL_ERR:
case GAUDI2_EVENT_TPC21_KERNEL_ERR:
case GAUDI2_EVENT_TPC22_KERNEL_ERR:
case GAUDI2_EVENT_TPC23_KERNEL_ERR:
case GAUDI2_EVENT_TPC24_KERNEL_ERR:
index = (event_type - GAUDI2_EVENT_TPC0_KERNEL_ERR) /
(GAUDI2_EVENT_TPC1_KERNEL_ERR - GAUDI2_EVENT_TPC0_KERNEL_ERR);
error_count = gaudi2_tpc_ack_interrupts(hdev, index, event_type,
&eq_entry->razwi_with_intr_cause, &event_mask);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_DEC0_SPI:
case GAUDI2_EVENT_DEC1_SPI:
case GAUDI2_EVENT_DEC2_SPI:
case GAUDI2_EVENT_DEC3_SPI:
case GAUDI2_EVENT_DEC4_SPI:
case GAUDI2_EVENT_DEC5_SPI:
case GAUDI2_EVENT_DEC6_SPI:
case GAUDI2_EVENT_DEC7_SPI:
case GAUDI2_EVENT_DEC8_SPI:
case GAUDI2_EVENT_DEC9_SPI:
index = (event_type - GAUDI2_EVENT_DEC0_SPI) /
(GAUDI2_EVENT_DEC1_SPI - GAUDI2_EVENT_DEC0_SPI);
error_count = gaudi2_handle_dec_err(hdev, index, event_type, &event_mask);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_MME0_CTRL_AXI_ERROR_RESPONSE:
case GAUDI2_EVENT_MME1_CTRL_AXI_ERROR_RESPONSE:
case GAUDI2_EVENT_MME2_CTRL_AXI_ERROR_RESPONSE:
case GAUDI2_EVENT_MME3_CTRL_AXI_ERROR_RESPONSE:
index = (event_type - GAUDI2_EVENT_MME0_CTRL_AXI_ERROR_RESPONSE) /
(GAUDI2_EVENT_MME1_CTRL_AXI_ERROR_RESPONSE -
GAUDI2_EVENT_MME0_CTRL_AXI_ERROR_RESPONSE);
error_count = gaudi2_handle_mme_err(hdev, index, event_type, &event_mask);
error_count += gaudi2_handle_qm_sei_err(hdev, event_type, false, &event_mask);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_MME0_QMAN_SW_ERROR:
case GAUDI2_EVENT_MME1_QMAN_SW_ERROR:
case GAUDI2_EVENT_MME2_QMAN_SW_ERROR:
case GAUDI2_EVENT_MME3_QMAN_SW_ERROR:
index = (event_type - GAUDI2_EVENT_MME0_QMAN_SW_ERROR) /
(GAUDI2_EVENT_MME1_QMAN_SW_ERROR -
GAUDI2_EVENT_MME0_QMAN_SW_ERROR);
error_count = gaudi2_handle_mme_err(hdev, index, event_type, &event_mask);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_MME0_WAP_SOURCE_RESULT_INVALID:
case GAUDI2_EVENT_MME1_WAP_SOURCE_RESULT_INVALID:
case GAUDI2_EVENT_MME2_WAP_SOURCE_RESULT_INVALID:
case GAUDI2_EVENT_MME3_WAP_SOURCE_RESULT_INVALID:
index = (event_type - GAUDI2_EVENT_MME0_WAP_SOURCE_RESULT_INVALID) /
(GAUDI2_EVENT_MME1_WAP_SOURCE_RESULT_INVALID -
GAUDI2_EVENT_MME0_WAP_SOURCE_RESULT_INVALID);
error_count = gaudi2_handle_mme_wap_err(hdev, index, event_type, &event_mask);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_KDMA_CH0_AXI_ERR_RSP:
case GAUDI2_EVENT_KDMA0_CORE:
error_count = gaudi2_handle_kdma_core_event(hdev, event_type,
le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_HDMA2_CORE ... GAUDI2_EVENT_HDMA5_CORE:
error_count = gaudi2_handle_dma_core_event(hdev, event_type,
le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_PDMA0_CORE ... GAUDI2_EVENT_PDMA1_CORE:
error_count = gaudi2_handle_dma_core_event(hdev, event_type,
le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_PCIE_ADDR_DEC_ERR:
error_count = gaudi2_print_pcie_addr_dec_info(hdev, event_type,
le64_to_cpu(eq_entry->intr_cause.intr_cause_data), &event_mask);
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_HMMU0_PAGE_FAULT_OR_WR_PERM ... GAUDI2_EVENT_HMMU12_SECURITY_ERROR:
case GAUDI2_EVENT_HMMU_0_AXI_ERR_RSP ... GAUDI2_EVENT_HMMU_12_AXI_ERR_RSP:
case GAUDI2_EVENT_PMMU0_PAGE_FAULT_WR_PERM ... GAUDI2_EVENT_PMMU0_SECURITY_ERROR:
case GAUDI2_EVENT_PMMU_AXI_ERR_RSP_0:
error_count = gaudi2_handle_mmu_spi_sei_err(hdev, event_type, &event_mask);
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_HIF0_FATAL ... GAUDI2_EVENT_HIF12_FATAL:
error_count = gaudi2_handle_hif_fatal(hdev, event_type,
le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_PMMU_FATAL_0:
error_count = gaudi2_handle_pif_fatal(hdev, event_type,
le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_PSOC63_RAZWI_OR_PID_MIN_MAX_INTERRUPT:
error_count = gaudi2_ack_psoc_razwi_event_handler(hdev, &event_mask);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_HBM0_MC0_SEI_SEVERE ... GAUDI2_EVENT_HBM5_MC1_SEI_NON_SEVERE:
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
if (gaudi2_handle_hbm_mc_sei_err(hdev, event_type, &eq_entry->sei_data)) {
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
reset_required = true;
}
error_count++;
break;
case GAUDI2_EVENT_HBM_CATTRIP_0 ... GAUDI2_EVENT_HBM_CATTRIP_5:
error_count = gaudi2_handle_hbm_cattrip(hdev, event_type,
le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_HBM0_MC0_SPI ... GAUDI2_EVENT_HBM5_MC1_SPI:
error_count = gaudi2_handle_hbm_mc_spi(hdev,
le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_PCIE_DRAIN_COMPLETE:
error_count = gaudi2_handle_pcie_drain(hdev, &eq_entry->pcie_drain_ind_data);
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_PSOC59_RPM_ERROR_OR_DRAIN:
error_count = gaudi2_handle_psoc_drain(hdev,
le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_CPU_AXI_ECC:
error_count = GAUDI2_NA_EVENT_CAUSE;
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_CPU_L2_RAM_ECC:
error_count = GAUDI2_NA_EVENT_CAUSE;
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_MME0_SBTE0_AXI_ERR_RSP ... GAUDI2_EVENT_MME0_SBTE4_AXI_ERR_RSP:
case GAUDI2_EVENT_MME1_SBTE0_AXI_ERR_RSP ... GAUDI2_EVENT_MME1_SBTE4_AXI_ERR_RSP:
case GAUDI2_EVENT_MME2_SBTE0_AXI_ERR_RSP ... GAUDI2_EVENT_MME2_SBTE4_AXI_ERR_RSP:
case GAUDI2_EVENT_MME3_SBTE0_AXI_ERR_RSP ... GAUDI2_EVENT_MME3_SBTE4_AXI_ERR_RSP:
error_count = gaudi2_handle_mme_sbte_err(hdev, event_type,
le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_VM0_ALARM_A ... GAUDI2_EVENT_VM3_ALARM_B:
error_count = GAUDI2_NA_EVENT_CAUSE;
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_PSOC_AXI_ERR_RSP:
error_count = GAUDI2_NA_EVENT_CAUSE;
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_PSOC_PRSTN_FALL:
error_count = GAUDI2_NA_EVENT_CAUSE;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_PCIE_APB_TIMEOUT:
error_count = GAUDI2_NA_EVENT_CAUSE;
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_PCIE_FATAL_ERR:
error_count = GAUDI2_NA_EVENT_CAUSE;
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_TPC0_BMON_SPMU:
case GAUDI2_EVENT_TPC1_BMON_SPMU:
case GAUDI2_EVENT_TPC2_BMON_SPMU:
case GAUDI2_EVENT_TPC3_BMON_SPMU:
case GAUDI2_EVENT_TPC4_BMON_SPMU:
case GAUDI2_EVENT_TPC5_BMON_SPMU:
case GAUDI2_EVENT_TPC6_BMON_SPMU:
case GAUDI2_EVENT_TPC7_BMON_SPMU:
case GAUDI2_EVENT_TPC8_BMON_SPMU:
case GAUDI2_EVENT_TPC9_BMON_SPMU:
case GAUDI2_EVENT_TPC10_BMON_SPMU:
case GAUDI2_EVENT_TPC11_BMON_SPMU:
case GAUDI2_EVENT_TPC12_BMON_SPMU:
case GAUDI2_EVENT_TPC13_BMON_SPMU:
case GAUDI2_EVENT_TPC14_BMON_SPMU:
case GAUDI2_EVENT_TPC15_BMON_SPMU:
case GAUDI2_EVENT_TPC16_BMON_SPMU:
case GAUDI2_EVENT_TPC17_BMON_SPMU:
case GAUDI2_EVENT_TPC18_BMON_SPMU:
case GAUDI2_EVENT_TPC19_BMON_SPMU:
case GAUDI2_EVENT_TPC20_BMON_SPMU:
case GAUDI2_EVENT_TPC21_BMON_SPMU:
case GAUDI2_EVENT_TPC22_BMON_SPMU:
case GAUDI2_EVENT_TPC23_BMON_SPMU:
case GAUDI2_EVENT_TPC24_BMON_SPMU:
case GAUDI2_EVENT_MME0_CTRL_BMON_SPMU:
case GAUDI2_EVENT_MME0_SBTE_BMON_SPMU:
case GAUDI2_EVENT_MME0_WAP_BMON_SPMU:
case GAUDI2_EVENT_MME1_CTRL_BMON_SPMU:
case GAUDI2_EVENT_MME1_SBTE_BMON_SPMU:
case GAUDI2_EVENT_MME1_WAP_BMON_SPMU:
case GAUDI2_EVENT_MME2_CTRL_BMON_SPMU:
case GAUDI2_EVENT_MME2_SBTE_BMON_SPMU:
case GAUDI2_EVENT_MME2_WAP_BMON_SPMU:
case GAUDI2_EVENT_MME3_CTRL_BMON_SPMU:
case GAUDI2_EVENT_MME3_SBTE_BMON_SPMU:
case GAUDI2_EVENT_MME3_WAP_BMON_SPMU:
case GAUDI2_EVENT_HDMA2_BM_SPMU ... GAUDI2_EVENT_PDMA1_BM_SPMU:
fallthrough;
case GAUDI2_EVENT_DEC0_BMON_SPMU:
case GAUDI2_EVENT_DEC1_BMON_SPMU:
case GAUDI2_EVENT_DEC2_BMON_SPMU:
case GAUDI2_EVENT_DEC3_BMON_SPMU:
case GAUDI2_EVENT_DEC4_BMON_SPMU:
case GAUDI2_EVENT_DEC5_BMON_SPMU:
case GAUDI2_EVENT_DEC6_BMON_SPMU:
case GAUDI2_EVENT_DEC7_BMON_SPMU:
case GAUDI2_EVENT_DEC8_BMON_SPMU:
case GAUDI2_EVENT_DEC9_BMON_SPMU:
case GAUDI2_EVENT_ROTATOR0_BMON_SPMU ... GAUDI2_EVENT_SM3_BMON_SPMU:
error_count = GAUDI2_NA_EVENT_CAUSE;
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_CPU_FIX_POWER_ENV_S:
case GAUDI2_EVENT_CPU_FIX_POWER_ENV_E:
case GAUDI2_EVENT_CPU_FIX_THERMAL_ENV_S:
case GAUDI2_EVENT_CPU_FIX_THERMAL_ENV_E:
gaudi2_print_clk_change_info(hdev, event_type, &event_mask);
error_count = GAUDI2_NA_EVENT_CAUSE;
break;
case GAUDI2_EVENT_CPU_PKT_QUEUE_OUT_SYNC:
gaudi2_print_out_of_sync_info(hdev, event_type, &eq_entry->pkt_sync_err);
error_count = GAUDI2_NA_EVENT_CAUSE;
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_PCIE_FLR_REQUESTED:
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
error_count = GAUDI2_NA_EVENT_CAUSE;
break;
case GAUDI2_EVENT_PCIE_P2P_MSIX:
error_count = gaudi2_handle_pcie_p2p_msix(hdev, event_type);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_SM0_AXI_ERROR_RESPONSE ... GAUDI2_EVENT_SM3_AXI_ERROR_RESPONSE:
index = event_type - GAUDI2_EVENT_SM0_AXI_ERROR_RESPONSE;
error_count = gaudi2_handle_sm_err(hdev, event_type, index);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_PSOC_MME_PLL_LOCK_ERR ... GAUDI2_EVENT_DCORE2_HBM_PLL_LOCK_ERR:
error_count = GAUDI2_NA_EVENT_CAUSE;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_CPU_CPLD_SHUTDOWN_CAUSE:
dev_info(hdev->dev, "CPLD shutdown cause, reset reason: 0x%llx\n",
le64_to_cpu(eq_entry->data[0]));
error_count = GAUDI2_NA_EVENT_CAUSE;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_CPU_CPLD_SHUTDOWN_EVENT:
dev_err(hdev->dev, "CPLD shutdown event, reset reason: 0x%llx\n",
le64_to_cpu(eq_entry->data[0]));
error_count = GAUDI2_NA_EVENT_CAUSE;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_CPU_PKT_SANITY_FAILED:
gaudi2_print_cpu_pkt_failure_info(hdev, event_type, &eq_entry->pkt_sync_err);
error_count = GAUDI2_NA_EVENT_CAUSE;
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
break;
case GAUDI2_EVENT_ARC_DCCM_FULL:
error_count = hl_arc_event_handle(hdev, event_type, &eq_entry->arc_data);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_CPU_FP32_NOT_SUPPORTED:
case GAUDI2_EVENT_CPU_DEV_RESET_REQ:
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
error_count = GAUDI2_NA_EVENT_CAUSE;
is_critical = true;
break;
default:
if (gaudi2_irq_map_table[event_type].valid) {
dev_err_ratelimited(hdev->dev, "Cannot find handler for event %d\n",
event_type);
error_count = GAUDI2_NA_EVENT_CAUSE;
}
}
if (error_count == GAUDI2_NA_EVENT_CAUSE && !is_info_event(event_type))
gaudi2_print_event(hdev, event_type, true, "%d", event_type);
else if (error_count == 0)
gaudi2_print_event(hdev, event_type, true,
"No error cause for H/W event %u", event_type);
if ((gaudi2_irq_map_table[event_type].reset != EVENT_RESET_TYPE_NONE) ||
reset_required) {
if (reset_required ||
(gaudi2_irq_map_table[event_type].reset == EVENT_RESET_TYPE_HARD))
reset_flags |= HL_DRV_RESET_HARD;
if (hdev->hard_reset_on_fw_events ||
(hdev->asic_prop.fw_security_enabled && is_critical))
goto reset_device;
}
if (!gaudi2_irq_map_table[event_type].msg)
hl_fw_unmask_irq(hdev, event_type);
if (event_mask)
hl_notifier_event_send_all(hdev, event_mask);
return;
reset_device:
if (hdev->asic_prop.fw_security_enabled && is_critical) {
reset_flags |= HL_DRV_RESET_BYPASS_REQ_TO_FW;
event_mask |= HL_NOTIFIER_EVENT_DEVICE_UNAVAILABLE;
} else {
reset_flags |= HL_DRV_RESET_DELAY;
}
if (event_mask & HL_NOTIFIER_EVENT_GENERAL_HW_ERR)
hl_handle_critical_hw_err(hdev, event_type, &event_mask);
event_mask |= HL_NOTIFIER_EVENT_DEVICE_RESET;
hl_device_cond_reset(hdev, reset_flags, event_mask);
}
static int gaudi2_memset_memory_chunk_using_edma_qm(struct hl_device *hdev,
struct packet_lin_dma *lin_dma_pkt, dma_addr_t pkt_dma_addr,
u32 hw_queue_id, u32 size, u64 addr, u32 val)
{
u32 ctl, pkt_size;
int rc = 0;
ctl = FIELD_PREP(GAUDI2_PKT_CTL_OPCODE_MASK, PACKET_LIN_DMA);
ctl |= FIELD_PREP(GAUDI2_PKT_LIN_DMA_CTL_MEMSET_MASK, 1);
ctl |= FIELD_PREP(GAUDI2_PKT_LIN_DMA_CTL_WRCOMP_MASK, 1);
ctl |= FIELD_PREP(GAUDI2_PKT_CTL_EB_MASK, 1);
lin_dma_pkt->ctl = cpu_to_le32(ctl);
lin_dma_pkt->src_addr = cpu_to_le64(val);
lin_dma_pkt->dst_addr = cpu_to_le64(addr);
lin_dma_pkt->tsize = cpu_to_le32(size);
pkt_size = sizeof(struct packet_lin_dma);
rc = hl_hw_queue_send_cb_no_cmpl(hdev, hw_queue_id, pkt_size, pkt_dma_addr);
if (rc)
dev_err(hdev->dev, "Failed to send lin dma packet to H/W queue %d\n",
hw_queue_id);
return rc;
}
static int gaudi2_memset_device_memory(struct hl_device *hdev, u64 addr, u64 size, u64 val)
{
u32 edma_queues_id[] = {GAUDI2_QUEUE_ID_DCORE0_EDMA_0_0,
GAUDI2_QUEUE_ID_DCORE1_EDMA_0_0,
GAUDI2_QUEUE_ID_DCORE2_EDMA_0_0,
GAUDI2_QUEUE_ID_DCORE3_EDMA_0_0};
u32 chunk_size, dcore, edma_idx, sob_offset, sob_addr, comp_val,
old_mmubp, mmubp, num_of_pkts, busy, pkt_size;
u64 comp_addr, cur_addr = addr, end_addr = addr + size;
struct asic_fixed_properties *prop = &hdev->asic_prop;
void *lin_dma_pkts_arr;
dma_addr_t pkt_dma_addr;
int rc = 0, dma_num = 0;
if (prop->edma_enabled_mask == 0) {
dev_info(hdev->dev, "non of the EDMA engines is enabled - skip dram scrubbing\n");
return -EIO;
}
sob_offset = hdev->asic_prop.first_available_user_sob[0] * 4;
sob_addr = mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0 + sob_offset;
comp_addr = CFG_BASE + sob_addr;
comp_val = FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_SOB_OBJ_INC_MASK, 1) |
FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_SOB_OBJ_VAL_MASK, 1);
mmubp = FIELD_PREP(ARC_FARM_KDMA_CTX_AXUSER_HB_MMU_BP_WR_MASK, 1) |
FIELD_PREP(ARC_FARM_KDMA_CTX_AXUSER_HB_MMU_BP_RD_MASK, 1);
num_of_pkts = div64_u64(round_up(size, SZ_2G), SZ_2G);
pkt_size = sizeof(struct packet_lin_dma);
lin_dma_pkts_arr = hl_asic_dma_alloc_coherent(hdev, pkt_size * num_of_pkts,
&pkt_dma_addr, GFP_KERNEL);
if (!lin_dma_pkts_arr)
return -ENOMEM;
old_mmubp = RREG32(mmDCORE0_EDMA0_CORE_CTX_AXUSER_HB_MMU_BP);
for (dcore = 0 ; dcore < NUM_OF_DCORES ; dcore++) {
for (edma_idx = 0 ; edma_idx < NUM_OF_EDMA_PER_DCORE ; edma_idx++) {
u32 edma_offset = dcore * DCORE_OFFSET + edma_idx * DCORE_EDMA_OFFSET;
u32 edma_bit = dcore * NUM_OF_EDMA_PER_DCORE + edma_idx;
if (!(prop->edma_enabled_mask & BIT(edma_bit)))
continue;
WREG32(mmDCORE0_EDMA0_CORE_CTX_AXUSER_HB_MMU_BP +
edma_offset, mmubp);
WREG32(mmDCORE0_EDMA0_CORE_CTX_WR_COMP_ADDR_LO + edma_offset,
lower_32_bits(comp_addr));
WREG32(mmDCORE0_EDMA0_CORE_CTX_WR_COMP_ADDR_HI + edma_offset,
upper_32_bits(comp_addr));
WREG32(mmDCORE0_EDMA0_CORE_CTX_WR_COMP_WDATA + edma_offset,
comp_val);
gaudi2_qman_set_test_mode(hdev,
edma_queues_id[dcore] + 4 * edma_idx, true);
}
}
WREG32(sob_addr, 0);
while (cur_addr < end_addr) {
for (dcore = 0 ; dcore < NUM_OF_DCORES ; dcore++) {
for (edma_idx = 0 ; edma_idx < NUM_OF_EDMA_PER_DCORE ; edma_idx++) {
u32 edma_bit = dcore * NUM_OF_EDMA_PER_DCORE + edma_idx;
if (!(prop->edma_enabled_mask & BIT(edma_bit)))
continue;
chunk_size = min_t(u64, SZ_2G, end_addr - cur_addr);
rc = gaudi2_memset_memory_chunk_using_edma_qm(hdev,
(struct packet_lin_dma *)lin_dma_pkts_arr + dma_num,
pkt_dma_addr + dma_num * pkt_size,
edma_queues_id[dcore] + edma_idx * 4,
chunk_size, cur_addr, val);
if (rc)
goto end;
dma_num++;
cur_addr += chunk_size;
if (cur_addr == end_addr)
break;
}
}
}
rc = hl_poll_timeout(hdev, sob_addr, busy, (busy == dma_num), 1000, 1000000);
if (rc) {
dev_err(hdev->dev, "DMA Timeout during HBM scrubbing\n");
goto end;
}
end:
for (dcore = 0 ; dcore < NUM_OF_DCORES ; dcore++) {
for (edma_idx = 0 ; edma_idx < NUM_OF_EDMA_PER_DCORE ; edma_idx++) {
u32 edma_offset = dcore * DCORE_OFFSET + edma_idx * DCORE_EDMA_OFFSET;
u32 edma_bit = dcore * NUM_OF_EDMA_PER_DCORE + edma_idx;
if (!(prop->edma_enabled_mask & BIT(edma_bit)))
continue;
WREG32(mmDCORE0_EDMA0_CORE_CTX_AXUSER_HB_MMU_BP + edma_offset, old_mmubp);
WREG32(mmDCORE0_EDMA0_CORE_CTX_WR_COMP_ADDR_LO + edma_offset, 0);
WREG32(mmDCORE0_EDMA0_CORE_CTX_WR_COMP_ADDR_HI + edma_offset, 0);
WREG32(mmDCORE0_EDMA0_CORE_CTX_WR_COMP_WDATA + edma_offset, 0);
gaudi2_qman_set_test_mode(hdev,
edma_queues_id[dcore] + 4 * edma_idx, false);
}
}
WREG32(sob_addr, 0);
hl_asic_dma_free_coherent(hdev, pkt_size * num_of_pkts, lin_dma_pkts_arr, pkt_dma_addr);
return rc;
}
static int gaudi2_scrub_device_dram(struct hl_device *hdev, u64 val)
{
int rc;
struct asic_fixed_properties *prop = &hdev->asic_prop;
u64 size = prop->dram_end_address - prop->dram_user_base_address;
rc = gaudi2_memset_device_memory(hdev, prop->dram_user_base_address, size, val);
if (rc)
dev_err(hdev->dev, "Failed to scrub dram, address: 0x%llx size: %llu\n",
prop->dram_user_base_address, size);
return rc;
}
static int gaudi2_scrub_device_mem(struct hl_device *hdev)
{
int rc;
struct asic_fixed_properties *prop = &hdev->asic_prop;
u64 val = hdev->memory_scrub_val;
u64 addr, size;
if (!hdev->memory_scrub)
return 0;
addr = prop->sram_user_base_address;
size = hdev->pldm ? 0x10000 : (prop->sram_size - SRAM_USER_BASE_OFFSET);
dev_dbg(hdev->dev, "Scrubbing SRAM: 0x%09llx - 0x%09llx, val: 0x%llx\n",
addr, addr + size, val);
rc = gaudi2_memset_device_memory(hdev, addr, size, val);
if (rc) {
dev_err(hdev->dev, "scrubbing SRAM failed (%d)\n", rc);
return rc;
}
rc = gaudi2_scrub_device_dram(hdev, val);
if (rc) {
dev_err(hdev->dev, "scrubbing DRAM failed (%d)\n", rc);
return rc;
}
return 0;
}
static void gaudi2_restore_user_sm_registers(struct hl_device *hdev)
{
u64 addr, mon_sts_addr, mon_cfg_addr, cq_lbw_l_addr, cq_lbw_h_addr,
cq_lbw_data_addr, cq_base_l_addr, cq_base_h_addr, cq_size_addr;
u32 val, size, offset;
int dcore_id;
offset = hdev->asic_prop.first_available_cq[0] * 4;
cq_lbw_l_addr = mmDCORE0_SYNC_MNGR_GLBL_LBW_ADDR_L_0 + offset;
cq_lbw_h_addr = mmDCORE0_SYNC_MNGR_GLBL_LBW_ADDR_H_0 + offset;
cq_lbw_data_addr = mmDCORE0_SYNC_MNGR_GLBL_LBW_DATA_0 + offset;
cq_base_l_addr = mmDCORE0_SYNC_MNGR_GLBL_CQ_BASE_ADDR_L_0 + offset;
cq_base_h_addr = mmDCORE0_SYNC_MNGR_GLBL_CQ_BASE_ADDR_H_0 + offset;
cq_size_addr = mmDCORE0_SYNC_MNGR_GLBL_CQ_SIZE_LOG2_0 + offset;
size = mmDCORE0_SYNC_MNGR_GLBL_LBW_ADDR_H_0 -
(mmDCORE0_SYNC_MNGR_GLBL_LBW_ADDR_L_0 + offset);
gaudi2_memset_device_lbw(hdev, cq_lbw_l_addr, size, 0);
gaudi2_memset_device_lbw(hdev, cq_lbw_h_addr, size, 0);
gaudi2_memset_device_lbw(hdev, cq_lbw_data_addr, size, 0);
gaudi2_memset_device_lbw(hdev, cq_base_l_addr, size, 0);
gaudi2_memset_device_lbw(hdev, cq_base_h_addr, size, 0);
gaudi2_memset_device_lbw(hdev, cq_size_addr, size, 0);
cq_lbw_l_addr = mmDCORE0_SYNC_MNGR_GLBL_LBW_ADDR_L_0 + DCORE_OFFSET;
cq_lbw_h_addr = mmDCORE0_SYNC_MNGR_GLBL_LBW_ADDR_H_0 + DCORE_OFFSET;
cq_lbw_data_addr = mmDCORE0_SYNC_MNGR_GLBL_LBW_DATA_0 + DCORE_OFFSET;
cq_base_l_addr = mmDCORE0_SYNC_MNGR_GLBL_CQ_BASE_ADDR_L_0 + DCORE_OFFSET;
cq_base_h_addr = mmDCORE0_SYNC_MNGR_GLBL_CQ_BASE_ADDR_H_0 + DCORE_OFFSET;
cq_size_addr = mmDCORE0_SYNC_MNGR_GLBL_CQ_SIZE_LOG2_0 + DCORE_OFFSET;
size = mmDCORE0_SYNC_MNGR_GLBL_LBW_ADDR_H_0 - mmDCORE0_SYNC_MNGR_GLBL_LBW_ADDR_L_0;
for (dcore_id = 1 ; dcore_id < NUM_OF_DCORES ; dcore_id++) {
gaudi2_memset_device_lbw(hdev, cq_lbw_l_addr, size, 0);
gaudi2_memset_device_lbw(hdev, cq_lbw_h_addr, size, 0);
gaudi2_memset_device_lbw(hdev, cq_lbw_data_addr, size, 0);
gaudi2_memset_device_lbw(hdev, cq_base_l_addr, size, 0);
gaudi2_memset_device_lbw(hdev, cq_base_h_addr, size, 0);
gaudi2_memset_device_lbw(hdev, cq_size_addr, size, 0);
cq_lbw_l_addr += DCORE_OFFSET;
cq_lbw_h_addr += DCORE_OFFSET;
cq_lbw_data_addr += DCORE_OFFSET;
cq_base_l_addr += DCORE_OFFSET;
cq_base_h_addr += DCORE_OFFSET;
cq_size_addr += DCORE_OFFSET;
}
offset = hdev->asic_prop.first_available_user_mon[0] * 4;
addr = mmDCORE0_SYNC_MNGR_OBJS_MON_STATUS_0 + offset;
val = 1 << DCORE0_SYNC_MNGR_OBJS_MON_STATUS_PROT_SHIFT;
size = mmDCORE0_SYNC_MNGR_OBJS_SM_SEC_0 - (mmDCORE0_SYNC_MNGR_OBJS_MON_STATUS_0 + offset);
gaudi2_memset_device_lbw(hdev, addr, size, val);
addr = mmDCORE0_SYNC_MNGR_OBJS_MON_CONFIG_0 + offset;
gaudi2_memset_device_lbw(hdev, addr, size, 0);
mon_sts_addr = mmDCORE0_SYNC_MNGR_OBJS_MON_STATUS_0 + DCORE_OFFSET;
mon_cfg_addr = mmDCORE0_SYNC_MNGR_OBJS_MON_CONFIG_0 + DCORE_OFFSET;
size = mmDCORE0_SYNC_MNGR_OBJS_SM_SEC_0 - mmDCORE0_SYNC_MNGR_OBJS_MON_STATUS_0;
for (dcore_id = 1 ; dcore_id < NUM_OF_DCORES ; dcore_id++) {
gaudi2_memset_device_lbw(hdev, mon_sts_addr, size, val);
gaudi2_memset_device_lbw(hdev, mon_cfg_addr, size, 0);
mon_sts_addr += DCORE_OFFSET;
mon_cfg_addr += DCORE_OFFSET;
}
offset = hdev->asic_prop.first_available_user_sob[0] * 4;
addr = mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0 + offset;
val = 0;
size = mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0 -
(mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0 + offset);
gaudi2_memset_device_lbw(hdev, addr, size, val);
addr = mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0 + DCORE_OFFSET;
size = mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0 - mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0;
for (dcore_id = 1 ; dcore_id < NUM_OF_DCORES ; dcore_id++) {
gaudi2_memset_device_lbw(hdev, addr, size, val);
addr += DCORE_OFFSET;
}
val = RREG32(mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0 + offset);
}
static void gaudi2_restore_user_qm_registers(struct hl_device *hdev)
{
u32 reg_base, hw_queue_id;
for (hw_queue_id = GAUDI2_QUEUE_ID_PDMA_0_0 ; hw_queue_id <= GAUDI2_QUEUE_ID_ROT_1_0;
hw_queue_id += NUM_OF_PQ_PER_QMAN) {
if (!gaudi2_is_queue_enabled(hdev, hw_queue_id))
continue;
gaudi2_clear_qm_fence_counters_common(hdev, hw_queue_id, false);
reg_base = gaudi2_qm_blocks_bases[hw_queue_id];
WREG32(reg_base + QM_ARB_CFG_0_OFFSET, 0);
}
RREG32(mmPDMA0_QM_ARB_CFG_0);
}
static void gaudi2_restore_nic_qm_registers(struct hl_device *hdev)
{
u32 reg_base, hw_queue_id;
for (hw_queue_id = GAUDI2_QUEUE_ID_NIC_0_0 ; hw_queue_id <= GAUDI2_QUEUE_ID_NIC_23_3;
hw_queue_id += NUM_OF_PQ_PER_QMAN) {
if (!gaudi2_is_queue_enabled(hdev, hw_queue_id))
continue;
gaudi2_clear_qm_fence_counters_common(hdev, hw_queue_id, false);
reg_base = gaudi2_qm_blocks_bases[hw_queue_id];
WREG32(reg_base + QM_ARB_CFG_0_OFFSET, 0);
}
RREG32(mmPDMA0_QM_ARB_CFG_0);
}
static int gaudi2_context_switch(struct hl_device *hdev, u32 asid)
{
return 0;
}
static void gaudi2_restore_phase_topology(struct hl_device *hdev)
{
}
static void gaudi2_init_block_instances(struct hl_device *hdev, u32 block_idx,
struct dup_block_ctx *cfg_ctx)
{
u64 block_base = cfg_ctx->base + block_idx * cfg_ctx->block_off;
u8 seq;
int i;
for (i = 0 ; i < cfg_ctx->instances ; i++) {
seq = block_idx * cfg_ctx->instances + i;
if (!(cfg_ctx->enabled_mask & BIT_ULL(seq)))
continue;
cfg_ctx->instance_cfg_fn(hdev, block_base + i * cfg_ctx->instance_off,
cfg_ctx->data);
}
}
static void gaudi2_init_blocks_with_mask(struct hl_device *hdev, struct dup_block_ctx *cfg_ctx,
u64 mask)
{
int i;
cfg_ctx->enabled_mask = mask;
for (i = 0 ; i < cfg_ctx->blocks ; i++)
gaudi2_init_block_instances(hdev, i, cfg_ctx);
}
void gaudi2_init_blocks(struct hl_device *hdev, struct dup_block_ctx *cfg_ctx)
{
gaudi2_init_blocks_with_mask(hdev, cfg_ctx, U64_MAX);
}
static int gaudi2_debugfs_read_dma(struct hl_device *hdev, u64 addr, u32 size, void *blob_addr)
{
void *host_mem_virtual_addr;
dma_addr_t host_mem_dma_addr;
u64 reserved_va_base;
u32 pos, size_left, size_to_dma;
struct hl_ctx *ctx;
int rc = 0;
ctx = hl_get_compute_ctx(hdev);
if (!ctx) {
dev_err(hdev->dev, "No ctx available\n");
return -EINVAL;
}
host_mem_virtual_addr = hl_asic_dma_alloc_coherent(hdev, SZ_2M, &host_mem_dma_addr,
GFP_KERNEL | __GFP_ZERO);
if (host_mem_virtual_addr == NULL) {
dev_err(hdev->dev, "Failed to allocate memory for KDMA read\n");
rc = -ENOMEM;
goto put_ctx;
}
reserved_va_base = hl_reserve_va_block(hdev, ctx, HL_VA_RANGE_TYPE_HOST, SZ_2M,
HL_MMU_VA_ALIGNMENT_NOT_NEEDED);
if (!reserved_va_base) {
dev_err(hdev->dev, "Failed to reserve vmem on asic\n");
rc = -ENOMEM;
goto free_data_buffer;
}
mutex_lock(&hdev->mmu_lock);
rc = hl_mmu_map_contiguous(ctx, reserved_va_base, host_mem_dma_addr, SZ_2M);
if (rc) {
dev_err(hdev->dev, "Failed to create mapping on asic mmu\n");
goto unreserve_va;
}
rc = hl_mmu_invalidate_cache_range(hdev, false,
MMU_OP_USERPTR | MMU_OP_SKIP_LOW_CACHE_INV,
ctx->asid, reserved_va_base, SZ_2M);
if (rc) {
hl_mmu_unmap_contiguous(ctx, reserved_va_base, SZ_2M);
goto unreserve_va;
}
mutex_unlock(&hdev->mmu_lock);
gaudi2_kdma_set_mmbp_asid(hdev, false, ctx->asid);
pos = 0;
size_left = size;
size_to_dma = SZ_2M;
while (size_left > 0) {
if (size_left < SZ_2M)
size_to_dma = size_left;
rc = gaudi2_send_job_to_kdma(hdev, addr, reserved_va_base, size_to_dma, false);
if (rc)
break;
memcpy(blob_addr + pos, host_mem_virtual_addr, size_to_dma);
if (size_left <= SZ_2M)
break;
pos += SZ_2M;
addr += SZ_2M;
size_left -= SZ_2M;
}
gaudi2_kdma_set_mmbp_asid(hdev, true, HL_KERNEL_ASID_ID);
mutex_lock(&hdev->mmu_lock);
rc = hl_mmu_unmap_contiguous(ctx, reserved_va_base, SZ_2M);
if (rc)
goto unreserve_va;
rc = hl_mmu_invalidate_cache_range(hdev, false, MMU_OP_USERPTR,
ctx->asid, reserved_va_base, SZ_2M);
unreserve_va:
mutex_unlock(&hdev->mmu_lock);
hl_unreserve_va_block(hdev, ctx, reserved_va_base, SZ_2M);
free_data_buffer:
hl_asic_dma_free_coherent(hdev, SZ_2M, host_mem_virtual_addr, host_mem_dma_addr);
put_ctx:
hl_ctx_put(ctx);
return rc;
}
static int gaudi2_internal_cb_pool_init(struct hl_device *hdev, struct hl_ctx *ctx)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
int min_alloc_order, rc;
if (!(gaudi2->hw_cap_initialized & HW_CAP_PMMU))
return 0;
hdev->internal_cb_pool_virt_addr = hl_asic_dma_alloc_coherent(hdev,
HOST_SPACE_INTERNAL_CB_SZ,
&hdev->internal_cb_pool_dma_addr,
GFP_KERNEL | __GFP_ZERO);
if (!hdev->internal_cb_pool_virt_addr)
return -ENOMEM;
min_alloc_order = ilog2(min(gaudi2_get_signal_cb_size(hdev),
gaudi2_get_wait_cb_size(hdev)));
hdev->internal_cb_pool = gen_pool_create(min_alloc_order, -1);
if (!hdev->internal_cb_pool) {
dev_err(hdev->dev, "Failed to create internal CB pool\n");
rc = -ENOMEM;
goto free_internal_cb_pool;
}
rc = gen_pool_add(hdev->internal_cb_pool, (uintptr_t) hdev->internal_cb_pool_virt_addr,
HOST_SPACE_INTERNAL_CB_SZ, -1);
if (rc) {
dev_err(hdev->dev, "Failed to add memory to internal CB pool\n");
rc = -EFAULT;
goto destroy_internal_cb_pool;
}
hdev->internal_cb_va_base = hl_reserve_va_block(hdev, ctx, HL_VA_RANGE_TYPE_HOST,
HOST_SPACE_INTERNAL_CB_SZ, HL_MMU_VA_ALIGNMENT_NOT_NEEDED);
if (!hdev->internal_cb_va_base) {
rc = -ENOMEM;
goto destroy_internal_cb_pool;
}
mutex_lock(&hdev->mmu_lock);
rc = hl_mmu_map_contiguous(ctx, hdev->internal_cb_va_base, hdev->internal_cb_pool_dma_addr,
HOST_SPACE_INTERNAL_CB_SZ);
if (rc)
goto unreserve_internal_cb_pool;
rc = hl_mmu_invalidate_cache(hdev, false, MMU_OP_USERPTR);
if (rc)
goto unmap_internal_cb_pool;
mutex_unlock(&hdev->mmu_lock);
return 0;
unmap_internal_cb_pool:
hl_mmu_unmap_contiguous(ctx, hdev->internal_cb_va_base, HOST_SPACE_INTERNAL_CB_SZ);
unreserve_internal_cb_pool:
mutex_unlock(&hdev->mmu_lock);
hl_unreserve_va_block(hdev, ctx, hdev->internal_cb_va_base, HOST_SPACE_INTERNAL_CB_SZ);
destroy_internal_cb_pool:
gen_pool_destroy(hdev->internal_cb_pool);
free_internal_cb_pool:
hl_asic_dma_free_coherent(hdev, HOST_SPACE_INTERNAL_CB_SZ, hdev->internal_cb_pool_virt_addr,
hdev->internal_cb_pool_dma_addr);
return rc;
}
static void gaudi2_internal_cb_pool_fini(struct hl_device *hdev, struct hl_ctx *ctx)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
if (!(gaudi2->hw_cap_initialized & HW_CAP_PMMU))
return;
mutex_lock(&hdev->mmu_lock);
hl_mmu_unmap_contiguous(ctx, hdev->internal_cb_va_base, HOST_SPACE_INTERNAL_CB_SZ);
hl_unreserve_va_block(hdev, ctx, hdev->internal_cb_va_base, HOST_SPACE_INTERNAL_CB_SZ);
hl_mmu_invalidate_cache(hdev, true, MMU_OP_USERPTR);
mutex_unlock(&hdev->mmu_lock);
gen_pool_destroy(hdev->internal_cb_pool);
hl_asic_dma_free_coherent(hdev, HOST_SPACE_INTERNAL_CB_SZ, hdev->internal_cb_pool_virt_addr,
hdev->internal_cb_pool_dma_addr);
}
static void gaudi2_restore_user_registers(struct hl_device *hdev)
{
gaudi2_restore_user_sm_registers(hdev);
gaudi2_restore_user_qm_registers(hdev);
}
static int gaudi2_map_virtual_msix_doorbell_memory(struct hl_ctx *ctx)
{
struct hl_device *hdev = ctx->hdev;
struct asic_fixed_properties *prop = &hdev->asic_prop;
struct gaudi2_device *gaudi2 = hdev->asic_specific;
int rc;
rc = hl_mmu_map_page(ctx, RESERVED_VA_FOR_VIRTUAL_MSIX_DOORBELL_START,
gaudi2->virt_msix_db_dma_addr, prop->pmmu.page_size, true);
if (rc)
dev_err(hdev->dev, "Failed to map VA %#llx for virtual MSI-X doorbell memory\n",
RESERVED_VA_FOR_VIRTUAL_MSIX_DOORBELL_START);
return rc;
}
static void gaudi2_unmap_virtual_msix_doorbell_memory(struct hl_ctx *ctx)
{
struct hl_device *hdev = ctx->hdev;
struct asic_fixed_properties *prop = &hdev->asic_prop;
int rc;
rc = hl_mmu_unmap_page(ctx, RESERVED_VA_FOR_VIRTUAL_MSIX_DOORBELL_START,
prop->pmmu.page_size, true);
if (rc)
dev_err(hdev->dev, "Failed to unmap VA %#llx of virtual MSI-X doorbell memory\n",
RESERVED_VA_FOR_VIRTUAL_MSIX_DOORBELL_START);
}
static int gaudi2_ctx_init(struct hl_ctx *ctx)
{
int rc;
rc = gaudi2_mmu_prepare(ctx->hdev, ctx->asid);
if (rc)
return rc;
if (ctx->hdev->reset_upon_device_release)
gaudi2_restore_nic_qm_registers(ctx->hdev);
else
gaudi2_restore_user_registers(ctx->hdev);
rc = gaudi2_internal_cb_pool_init(ctx->hdev, ctx);
if (rc)
return rc;
rc = gaudi2_map_virtual_msix_doorbell_memory(ctx);
if (rc)
gaudi2_internal_cb_pool_fini(ctx->hdev, ctx);
return rc;
}
static void gaudi2_ctx_fini(struct hl_ctx *ctx)
{
if (ctx->asid == HL_KERNEL_ASID_ID)
return;
gaudi2_internal_cb_pool_fini(ctx->hdev, ctx);
gaudi2_unmap_virtual_msix_doorbell_memory(ctx);
}
static int gaudi2_pre_schedule_cs(struct hl_cs *cs)
{
struct hl_device *hdev = cs->ctx->hdev;
int index = cs->sequence & (hdev->asic_prop.max_pending_cs - 1);
u32 mon_payload, sob_id, mon_id;
if (!cs_needs_completion(cs))
return 0;
sob_id = mon_id = index;
mon_payload = (1 << CQ_ENTRY_SHADOW_INDEX_VALID_SHIFT) |
(1 << CQ_ENTRY_READY_SHIFT) | index;
gaudi2_arm_cq_monitor(hdev, sob_id, mon_id, GAUDI2_RESERVED_CQ_CS_COMPLETION, mon_payload,
cs->jobs_cnt);
return 0;
}
static u32 gaudi2_get_queue_id_for_cq(struct hl_device *hdev, u32 cq_idx)
{
return HL_INVALID_QUEUE;
}
static u32 gaudi2_gen_signal_cb(struct hl_device *hdev, void *data, u16 sob_id, u32 size, bool eb)
{
struct hl_cb *cb = data;
struct packet_msg_short *pkt;
u32 value, ctl, pkt_size = sizeof(*pkt);
pkt = (struct packet_msg_short *) (uintptr_t) (cb->kernel_address + size);
memset(pkt, 0, pkt_size);
value = FIELD_PREP(GAUDI2_PKT_SHORT_VAL_SOB_SYNC_VAL_MASK, 1);
value |= FIELD_PREP(GAUDI2_PKT_SHORT_VAL_SOB_MOD_MASK, 1);
ctl = FIELD_PREP(GAUDI2_PKT_SHORT_CTL_ADDR_MASK, sob_id * 4);
ctl |= FIELD_PREP(GAUDI2_PKT_SHORT_CTL_BASE_MASK, 1);
ctl |= FIELD_PREP(GAUDI2_PKT_CTL_OPCODE_MASK, PACKET_MSG_SHORT);
ctl |= FIELD_PREP(GAUDI2_PKT_CTL_EB_MASK, eb);
ctl |= FIELD_PREP(GAUDI2_PKT_CTL_MB_MASK, 1);
pkt->value = cpu_to_le32(value);
pkt->ctl = cpu_to_le32(ctl);
return size + pkt_size;
}
static u32 gaudi2_add_mon_msg_short(struct packet_msg_short *pkt, u32 value, u16 addr)
{
u32 ctl, pkt_size = sizeof(*pkt);
memset(pkt, 0, pkt_size);
ctl = FIELD_PREP(GAUDI2_PKT_SHORT_CTL_ADDR_MASK, addr);
ctl |= FIELD_PREP(GAUDI2_PKT_SHORT_CTL_BASE_MASK, 0);
ctl |= FIELD_PREP(GAUDI2_PKT_CTL_OPCODE_MASK, PACKET_MSG_SHORT);
ctl |= FIELD_PREP(GAUDI2_PKT_CTL_EB_MASK, 0);
ctl |= FIELD_PREP(GAUDI2_PKT_CTL_MB_MASK, 0);
pkt->value = cpu_to_le32(value);
pkt->ctl = cpu_to_le32(ctl);
return pkt_size;
}
static u32 gaudi2_add_arm_monitor_pkt(struct hl_device *hdev, struct packet_msg_short *pkt,
u16 sob_base, u8 sob_mask, u16 sob_val, u16 addr)
{
u32 ctl, value, pkt_size = sizeof(*pkt);
u8 mask;
if (hl_gen_sob_mask(sob_base, sob_mask, &mask)) {
dev_err(hdev->dev, "sob_base %u (mask %#x) is not valid\n", sob_base, sob_mask);
return 0;
}
memset(pkt, 0, pkt_size);
value = FIELD_PREP(GAUDI2_PKT_SHORT_VAL_MON_SYNC_GID_MASK, sob_base / 8);
value |= FIELD_PREP(GAUDI2_PKT_SHORT_VAL_MON_SYNC_VAL_MASK, sob_val);
value |= FIELD_PREP(GAUDI2_PKT_SHORT_VAL_MON_MODE_MASK, 0);
value |= FIELD_PREP(GAUDI2_PKT_SHORT_VAL_MON_MASK_MASK, mask);
ctl = FIELD_PREP(GAUDI2_PKT_SHORT_CTL_ADDR_MASK, addr);
ctl |= FIELD_PREP(GAUDI2_PKT_SHORT_CTL_BASE_MASK, 0);
ctl |= FIELD_PREP(GAUDI2_PKT_CTL_OPCODE_MASK, PACKET_MSG_SHORT);
ctl |= FIELD_PREP(GAUDI2_PKT_CTL_EB_MASK, 0);
ctl |= FIELD_PREP(GAUDI2_PKT_CTL_MB_MASK, 1);
pkt->value = cpu_to_le32(value);
pkt->ctl = cpu_to_le32(ctl);
return pkt_size;
}
static u32 gaudi2_add_fence_pkt(struct packet_fence *pkt)
{
u32 ctl, cfg, pkt_size = sizeof(*pkt);
memset(pkt, 0, pkt_size);
cfg = FIELD_PREP(GAUDI2_PKT_FENCE_CFG_DEC_VAL_MASK, 1);
cfg |= FIELD_PREP(GAUDI2_PKT_FENCE_CFG_TARGET_VAL_MASK, 1);
cfg |= FIELD_PREP(GAUDI2_PKT_FENCE_CFG_ID_MASK, 2);
ctl = FIELD_PREP(GAUDI2_PKT_CTL_OPCODE_MASK, PACKET_FENCE);
ctl |= FIELD_PREP(GAUDI2_PKT_CTL_EB_MASK, 0);
ctl |= FIELD_PREP(GAUDI2_PKT_CTL_MB_MASK, 1);
pkt->cfg = cpu_to_le32(cfg);
pkt->ctl = cpu_to_le32(ctl);
return pkt_size;
}
static u32 gaudi2_gen_wait_cb(struct hl_device *hdev, struct hl_gen_wait_properties *prop)
{
struct hl_cb *cb = prop->data;
void *buf = (void *) (uintptr_t) (cb->kernel_address);
u64 monitor_base, fence_addr = 0;
u32 stream_index, size = prop->size;
u16 msg_addr_offset;
stream_index = prop->q_idx % 4;
fence_addr = CFG_BASE + gaudi2_qm_blocks_bases[prop->q_idx] +
QM_FENCE2_OFFSET + stream_index * 4;
monitor_base = mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0;
msg_addr_offset = (mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0 + prop->mon_id * 4) -
monitor_base;
size += gaudi2_add_mon_msg_short(buf + size, (u32) fence_addr, msg_addr_offset);
msg_addr_offset = (mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_ADDRH_0 + prop->mon_id * 4) -
monitor_base;
size += gaudi2_add_mon_msg_short(buf + size, (u32) (fence_addr >> 32), msg_addr_offset);
msg_addr_offset = (mmDCORE0_SYNC_MNGR_OBJS_MON_PAY_DATA_0 + prop->mon_id * 4) -
monitor_base;
size += gaudi2_add_mon_msg_short(buf + size, 1, msg_addr_offset);
msg_addr_offset = (mmDCORE0_SYNC_MNGR_OBJS_MON_ARM_0 + prop->mon_id * 4) - monitor_base;
size += gaudi2_add_arm_monitor_pkt(hdev, buf + size, prop->sob_base, prop->sob_mask,
prop->sob_val, msg_addr_offset);
size += gaudi2_add_fence_pkt(buf + size);
return size;
}
static void gaudi2_reset_sob(struct hl_device *hdev, void *data)
{
struct hl_hw_sob *hw_sob = data;
dev_dbg(hdev->dev, "reset SOB, q_idx: %d, sob_id: %d\n", hw_sob->q_idx, hw_sob->sob_id);
WREG32(mmDCORE0_SYNC_MNGR_OBJS_SOB_OBJ_0 + hw_sob->sob_id * 4, 0);
kref_init(&hw_sob->kref);
}
static void gaudi2_reset_sob_group(struct hl_device *hdev, u16 sob_group)
{
}
static u64 gaudi2_get_device_time(struct hl_device *hdev)
{
u64 device_time = ((u64) RREG32(mmPSOC_TIMESTAMP_CNTCVU)) << 32;
return device_time | RREG32(mmPSOC_TIMESTAMP_CNTCVL);
}
static int gaudi2_collective_wait_init_cs(struct hl_cs *cs)
{
return 0;
}
static int gaudi2_collective_wait_create_jobs(struct hl_device *hdev, struct hl_ctx *ctx,
struct hl_cs *cs, u32 wait_queue_id,
u32 collective_engine_id, u32 encaps_signal_offset)
{
return -EINVAL;
}
static u64 gaudi2_mmu_scramble_addr(struct hl_device *hdev, u64 raw_addr)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
u32 divisor, mod_va;
u64 div_va;
if (hl_mem_area_inside_range(raw_addr, sizeof(raw_addr), DRAM_PHYS_BASE,
VA_HBM_SPACE_END)) {
divisor = prop->num_functional_hbms * GAUDI2_HBM_MMU_SCRM_MEM_SIZE;
div_va = div_u64_rem(raw_addr & GAUDI2_HBM_MMU_SCRM_ADDRESS_MASK, divisor, &mod_va);
return (raw_addr & ~GAUDI2_HBM_MMU_SCRM_ADDRESS_MASK) |
(div_va << GAUDI2_HBM_MMU_SCRM_DIV_SHIFT) |
(mod_va << GAUDI2_HBM_MMU_SCRM_MOD_SHIFT);
}
return raw_addr;
}
static u64 gaudi2_mmu_descramble_addr(struct hl_device *hdev, u64 scrambled_addr)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
u32 divisor, mod_va;
u64 div_va;
if (hl_mem_area_inside_range(scrambled_addr, sizeof(scrambled_addr), DRAM_PHYS_BASE,
VA_HBM_SPACE_END)) {
divisor = prop->num_functional_hbms * GAUDI2_HBM_MMU_SCRM_MEM_SIZE;
div_va = div_u64_rem(scrambled_addr & GAUDI2_HBM_MMU_SCRM_ADDRESS_MASK,
PAGE_SIZE_64MB, &mod_va);
return ((scrambled_addr & ~GAUDI2_HBM_MMU_SCRM_ADDRESS_MASK) +
(div_va * divisor + mod_va));
}
return scrambled_addr;
}
static u32 gaudi2_get_dec_base_addr(struct hl_device *hdev, u32 core_id)
{
u32 base = 0, dcore_id, dec_id;
if (core_id >= NUMBER_OF_DEC) {
dev_err(hdev->dev, "Unexpected core number %d for DEC\n", core_id);
goto out;
}
if (core_id < 8) {
dcore_id = core_id / NUM_OF_DEC_PER_DCORE;
dec_id = core_id % NUM_OF_DEC_PER_DCORE;
base = mmDCORE0_DEC0_CMD_BASE + dcore_id * DCORE_OFFSET +
dec_id * DCORE_VDEC_OFFSET;
} else {
base = mmPCIE_DEC0_CMD_BASE + ((core_id % 8) * PCIE_VDEC_OFFSET);
}
out:
return base;
}
static int gaudi2_get_hw_block_id(struct hl_device *hdev, u64 block_addr,
u32 *block_size, u32 *block_id)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
int i;
for (i = 0 ; i < NUM_USER_MAPPED_BLOCKS ; i++) {
if (block_addr == CFG_BASE + gaudi2->mapped_blocks[i].address) {
*block_id = i;
if (block_size)
*block_size = gaudi2->mapped_blocks[i].size;
return 0;
}
}
dev_err(hdev->dev, "Invalid block address %#llx", block_addr);
return -EINVAL;
}
static int gaudi2_block_mmap(struct hl_device *hdev, struct vm_area_struct *vma,
u32 block_id, u32 block_size)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u64 offset_in_bar;
u64 address;
int rc;
if (block_id >= NUM_USER_MAPPED_BLOCKS) {
dev_err(hdev->dev, "Invalid block id %u", block_id);
return -EINVAL;
}
if (block_size != gaudi2->mapped_blocks[block_id].size) {
dev_err(hdev->dev, "Invalid block size %u", block_size);
return -EINVAL;
}
offset_in_bar = CFG_BASE + gaudi2->mapped_blocks[block_id].address - STM_FLASH_BASE_ADDR;
address = pci_resource_start(hdev->pdev, SRAM_CFG_BAR_ID) + offset_in_bar;
vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP |
VM_DONTCOPY | VM_NORESERVE);
rc = remap_pfn_range(vma, vma->vm_start, address >> PAGE_SHIFT,
block_size, vma->vm_page_prot);
if (rc)
dev_err(hdev->dev, "remap_pfn_range error %d", rc);
return rc;
}
static void gaudi2_enable_events_from_fw(struct hl_device *hdev)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
struct cpu_dyn_regs *dyn_regs = &hdev->fw_loader.dynamic_loader.comm_desc.cpu_dyn_regs;
u32 irq_handler_offset = le32_to_cpu(dyn_regs->gic_host_ints_irq);
if (gaudi2->hw_cap_initialized & HW_CAP_CPU_Q)
WREG32(irq_handler_offset,
gaudi2_irq_map_table[GAUDI2_EVENT_CPU_INTS_REGISTER].cpu_id);
}
static int gaudi2_get_mmu_base(struct hl_device *hdev, u64 mmu_id, u32 *mmu_base)
{
switch (mmu_id) {
case HW_CAP_DCORE0_DMMU0:
*mmu_base = mmDCORE0_HMMU0_MMU_BASE;
break;
case HW_CAP_DCORE0_DMMU1:
*mmu_base = mmDCORE0_HMMU1_MMU_BASE;
break;
case HW_CAP_DCORE0_DMMU2:
*mmu_base = mmDCORE0_HMMU2_MMU_BASE;
break;
case HW_CAP_DCORE0_DMMU3:
*mmu_base = mmDCORE0_HMMU3_MMU_BASE;
break;
case HW_CAP_DCORE1_DMMU0:
*mmu_base = mmDCORE1_HMMU0_MMU_BASE;
break;
case HW_CAP_DCORE1_DMMU1:
*mmu_base = mmDCORE1_HMMU1_MMU_BASE;
break;
case HW_CAP_DCORE1_DMMU2:
*mmu_base = mmDCORE1_HMMU2_MMU_BASE;
break;
case HW_CAP_DCORE1_DMMU3:
*mmu_base = mmDCORE1_HMMU3_MMU_BASE;
break;
case HW_CAP_DCORE2_DMMU0:
*mmu_base = mmDCORE2_HMMU0_MMU_BASE;
break;
case HW_CAP_DCORE2_DMMU1:
*mmu_base = mmDCORE2_HMMU1_MMU_BASE;
break;
case HW_CAP_DCORE2_DMMU2:
*mmu_base = mmDCORE2_HMMU2_MMU_BASE;
break;
case HW_CAP_DCORE2_DMMU3:
*mmu_base = mmDCORE2_HMMU3_MMU_BASE;
break;
case HW_CAP_DCORE3_DMMU0:
*mmu_base = mmDCORE3_HMMU0_MMU_BASE;
break;
case HW_CAP_DCORE3_DMMU1:
*mmu_base = mmDCORE3_HMMU1_MMU_BASE;
break;
case HW_CAP_DCORE3_DMMU2:
*mmu_base = mmDCORE3_HMMU2_MMU_BASE;
break;
case HW_CAP_DCORE3_DMMU3:
*mmu_base = mmDCORE3_HMMU3_MMU_BASE;
break;
case HW_CAP_PMMU:
*mmu_base = mmPMMU_HBW_MMU_BASE;
break;
default:
return -EINVAL;
}
return 0;
}
static void gaudi2_ack_mmu_error(struct hl_device *hdev, u64 mmu_id)
{
bool is_pmmu = (mmu_id == HW_CAP_PMMU);
struct gaudi2_device *gaudi2 = hdev->asic_specific;
u32 mmu_base;
if (!(gaudi2->hw_cap_initialized & mmu_id))
return;
if (gaudi2_get_mmu_base(hdev, mmu_id, &mmu_base))
return;
gaudi2_handle_page_error(hdev, mmu_base, is_pmmu, NULL);
gaudi2_handle_access_error(hdev, mmu_base, is_pmmu);
}
static int gaudi2_ack_mmu_page_fault_or_access_error(struct hl_device *hdev, u64 mmu_cap_mask)
{
u32 i, mmu_id, num_of_hmmus = NUM_OF_HMMU_PER_DCORE * NUM_OF_DCORES;
for (i = 0 ; i < num_of_hmmus ; i++) {
mmu_id = HW_CAP_DCORE0_DMMU0 << i;
if (mmu_cap_mask & mmu_id)
gaudi2_ack_mmu_error(hdev, mmu_id);
}
if (mmu_cap_mask & HW_CAP_PMMU)
gaudi2_ack_mmu_error(hdev, HW_CAP_PMMU);
return 0;
}
static void gaudi2_get_msi_info(__le32 *table)
{
table[CPUCP_EVENT_QUEUE_MSI_TYPE] = cpu_to_le32(GAUDI2_EVENT_QUEUE_MSIX_IDX);
}
static int gaudi2_map_pll_idx_to_fw_idx(u32 pll_idx)
{
switch (pll_idx) {
case HL_GAUDI2_CPU_PLL: return CPU_PLL;
case HL_GAUDI2_PCI_PLL: return PCI_PLL;
case HL_GAUDI2_NIC_PLL: return NIC_PLL;
case HL_GAUDI2_DMA_PLL: return DMA_PLL;
case HL_GAUDI2_MESH_PLL: return MESH_PLL;
case HL_GAUDI2_MME_PLL: return MME_PLL;
case HL_GAUDI2_TPC_PLL: return TPC_PLL;
case HL_GAUDI2_IF_PLL: return IF_PLL;
case HL_GAUDI2_SRAM_PLL: return SRAM_PLL;
case HL_GAUDI2_HBM_PLL: return HBM_PLL;
case HL_GAUDI2_VID_PLL: return VID_PLL;
case HL_GAUDI2_MSS_PLL: return MSS_PLL;
default: return -EINVAL;
}
}
static int gaudi2_gen_sync_to_engine_map(struct hl_device *hdev, struct hl_sync_to_engine_map *map)
{
return 0;
}
static int gaudi2_monitor_valid(struct hl_mon_state_dump *mon)
{
return 0;
}
static int gaudi2_print_single_monitor(char **buf, size_t *size, size_t *offset,
struct hl_device *hdev, struct hl_mon_state_dump *mon)
{
return 0;
}
static int gaudi2_print_fences_single_engine(struct hl_device *hdev, u64 base_offset,
u64 status_base_offset, enum hl_sync_engine_type engine_type,
u32 engine_id, char **buf, size_t *size, size_t *offset)
{
return 0;
}
static struct hl_state_dump_specs_funcs gaudi2_state_dump_funcs = {
.monitor_valid = gaudi2_monitor_valid,
.print_single_monitor = gaudi2_print_single_monitor,
.gen_sync_to_engine_map = gaudi2_gen_sync_to_engine_map,
.print_fences_single_engine = gaudi2_print_fences_single_engine,
};
static void gaudi2_state_dump_init(struct hl_device *hdev)
{
hdev->state_dump_specs.props = gaudi2_state_dump_specs_props;
hdev->state_dump_specs.funcs = gaudi2_state_dump_funcs;
}
static u32 gaudi2_get_sob_addr(struct hl_device *hdev, u32 sob_id)
{
return 0;
}
static u32 *gaudi2_get_stream_master_qid_arr(void)
{
return NULL;
}
static void gaudi2_add_device_attr(struct hl_device *hdev, struct attribute_group *dev_clk_attr_grp,
struct attribute_group *dev_vrm_attr_grp)
{
hl_sysfs_add_dev_clk_attr(hdev, dev_clk_attr_grp);
hl_sysfs_add_dev_vrm_attr(hdev, dev_vrm_attr_grp);
}
static int gaudi2_mmu_get_real_page_size(struct hl_device *hdev, struct hl_mmu_properties *mmu_prop,
u32 page_size, u32 *real_page_size, bool is_dram_addr)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
if (!is_dram_addr) {
if (page_size % mmu_prop->page_size)
goto page_size_err;
*real_page_size = mmu_prop->page_size;
return 0;
}
if ((page_size % prop->dram_page_size) || (prop->dram_page_size > mmu_prop->page_size))
goto page_size_err;
*real_page_size = prop->dram_page_size;
return 0;
page_size_err:
dev_err(hdev->dev, "page size of %u is not %uKB aligned, can't map\n",
page_size, mmu_prop->page_size >> 10);
return -EFAULT;
}
static int gaudi2_get_monitor_dump(struct hl_device *hdev, void *data)
{
return -EOPNOTSUPP;
}
int gaudi2_send_device_activity(struct hl_device *hdev, bool open)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
if (!(gaudi2->hw_cap_initialized & HW_CAP_CPU_Q))
return 0;
return hl_fw_send_device_activity(hdev, open);
}
static const struct hl_asic_funcs gaudi2_funcs = {
.early_init = gaudi2_early_init,
.early_fini = gaudi2_early_fini,
.late_init = gaudi2_late_init,
.late_fini = gaudi2_late_fini,
.sw_init = gaudi2_sw_init,
.sw_fini = gaudi2_sw_fini,
.hw_init = gaudi2_hw_init,
.hw_fini = gaudi2_hw_fini,
.halt_engines = gaudi2_halt_engines,
.suspend = gaudi2_suspend,
.resume = gaudi2_resume,
.mmap = gaudi2_mmap,
.ring_doorbell = gaudi2_ring_doorbell,
.pqe_write = gaudi2_pqe_write,
.asic_dma_alloc_coherent = gaudi2_dma_alloc_coherent,
.asic_dma_free_coherent = gaudi2_dma_free_coherent,
.scrub_device_mem = gaudi2_scrub_device_mem,
.scrub_device_dram = gaudi2_scrub_device_dram,
.get_int_queue_base = NULL,
.test_queues = gaudi2_test_queues,
.asic_dma_pool_zalloc = gaudi2_dma_pool_zalloc,
.asic_dma_pool_free = gaudi2_dma_pool_free,
.cpu_accessible_dma_pool_alloc = gaudi2_cpu_accessible_dma_pool_alloc,
.cpu_accessible_dma_pool_free = gaudi2_cpu_accessible_dma_pool_free,
.asic_dma_unmap_single = gaudi2_dma_unmap_single,
.asic_dma_map_single = gaudi2_dma_map_single,
.hl_dma_unmap_sgtable = hl_dma_unmap_sgtable,
.cs_parser = gaudi2_cs_parser,
.asic_dma_map_sgtable = hl_dma_map_sgtable,
.add_end_of_cb_packets = NULL,
.update_eq_ci = gaudi2_update_eq_ci,
.context_switch = gaudi2_context_switch,
.restore_phase_topology = gaudi2_restore_phase_topology,
.debugfs_read_dma = gaudi2_debugfs_read_dma,
.add_device_attr = gaudi2_add_device_attr,
.handle_eqe = gaudi2_handle_eqe,
.get_events_stat = gaudi2_get_events_stat,
.read_pte = NULL,
.write_pte = NULL,
.mmu_invalidate_cache = gaudi2_mmu_invalidate_cache,
.mmu_invalidate_cache_range = gaudi2_mmu_invalidate_cache_range,
.mmu_prefetch_cache_range = NULL,
.send_heartbeat = gaudi2_send_heartbeat,
.debug_coresight = gaudi2_debug_coresight,
.is_device_idle = gaudi2_is_device_idle,
.compute_reset_late_init = gaudi2_compute_reset_late_init,
.hw_queues_lock = gaudi2_hw_queues_lock,
.hw_queues_unlock = gaudi2_hw_queues_unlock,
.get_pci_id = gaudi2_get_pci_id,
.get_eeprom_data = gaudi2_get_eeprom_data,
.get_monitor_dump = gaudi2_get_monitor_dump,
.send_cpu_message = gaudi2_send_cpu_message,
.pci_bars_map = gaudi2_pci_bars_map,
.init_iatu = gaudi2_init_iatu,
.rreg = hl_rreg,
.wreg = hl_wreg,
.halt_coresight = gaudi2_halt_coresight,
.ctx_init = gaudi2_ctx_init,
.ctx_fini = gaudi2_ctx_fini,
.pre_schedule_cs = gaudi2_pre_schedule_cs,
.get_queue_id_for_cq = gaudi2_get_queue_id_for_cq,
.load_firmware_to_device = NULL,
.load_boot_fit_to_device = NULL,
.get_signal_cb_size = gaudi2_get_signal_cb_size,
.get_wait_cb_size = gaudi2_get_wait_cb_size,
.gen_signal_cb = gaudi2_gen_signal_cb,
.gen_wait_cb = gaudi2_gen_wait_cb,
.reset_sob = gaudi2_reset_sob,
.reset_sob_group = gaudi2_reset_sob_group,
.get_device_time = gaudi2_get_device_time,
.pb_print_security_errors = gaudi2_pb_print_security_errors,
.collective_wait_init_cs = gaudi2_collective_wait_init_cs,
.collective_wait_create_jobs = gaudi2_collective_wait_create_jobs,
.get_dec_base_addr = gaudi2_get_dec_base_addr,
.scramble_addr = gaudi2_mmu_scramble_addr,
.descramble_addr = gaudi2_mmu_descramble_addr,
.ack_protection_bits_errors = gaudi2_ack_protection_bits_errors,
.get_hw_block_id = gaudi2_get_hw_block_id,
.hw_block_mmap = gaudi2_block_mmap,
.enable_events_from_fw = gaudi2_enable_events_from_fw,
.ack_mmu_errors = gaudi2_ack_mmu_page_fault_or_access_error,
.get_msi_info = gaudi2_get_msi_info,
.map_pll_idx_to_fw_idx = gaudi2_map_pll_idx_to_fw_idx,
.init_firmware_preload_params = gaudi2_init_firmware_preload_params,
.init_firmware_loader = gaudi2_init_firmware_loader,
.init_cpu_scrambler_dram = gaudi2_init_scrambler_hbm,
.state_dump_init = gaudi2_state_dump_init,
.get_sob_addr = &gaudi2_get_sob_addr,
.set_pci_memory_regions = gaudi2_set_pci_memory_regions,
.get_stream_master_qid_arr = gaudi2_get_stream_master_qid_arr,
.check_if_razwi_happened = gaudi2_check_if_razwi_happened,
.mmu_get_real_page_size = gaudi2_mmu_get_real_page_size,
.access_dev_mem = hl_access_dev_mem,
.set_dram_bar_base = gaudi2_set_hbm_bar_base,
.set_engine_cores = gaudi2_set_engine_cores,
.set_engines = gaudi2_set_engines,
.send_device_activity = gaudi2_send_device_activity,
.set_dram_properties = gaudi2_set_dram_properties,
.set_binning_masks = gaudi2_set_binning_masks,
};
void gaudi2_set_asic_funcs(struct hl_device *hdev)
{
hdev->asic_funcs = &gaudi2_funcs;
}