diff options
Diffstat (limited to 'drivers/accel/habanalabs/gaudi/gaudi.c')
| -rw-r--r-- | drivers/accel/habanalabs/gaudi/gaudi.c | 57 |
1 files changed, 35 insertions, 22 deletions
diff --git a/drivers/accel/habanalabs/gaudi/gaudi.c b/drivers/accel/habanalabs/gaudi/gaudi.c index 056e2ef44afb..34771d75da9d 100644 --- a/drivers/accel/habanalabs/gaudi/gaudi.c +++ b/drivers/accel/habanalabs/gaudi/gaudi.c @@ -63,6 +63,10 @@ #define GAUDI_LINUX_FW_FILE "habanalabs/gaudi/gaudi-fit.itb" #define GAUDI_TPC_FW_FILE "habanalabs/gaudi/gaudi_tpc.bin" +MODULE_FIRMWARE(GAUDI_BOOT_FIT_FILE); +MODULE_FIRMWARE(GAUDI_LINUX_FW_FILE); +MODULE_FIRMWARE(GAUDI_TPC_FW_FILE); + #define GAUDI_DMA_POOL_BLK_SIZE 0x100 /* 256 bytes */ #define GAUDI_RESET_TIMEOUT_MSEC 2000 /* 2000ms */ @@ -610,8 +614,6 @@ static int gaudi_set_fixed_properties(struct hl_device *hdev) else prop->mmu_pgt_size = MMU_PAGE_TABLES_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->dram_page_size = PAGE_SIZE_2MB; prop->device_mem_alloc_default_page_size = prop->dram_page_size; prop->dram_supports_virtual_memory = false; @@ -633,8 +635,8 @@ static int gaudi_set_fixed_properties(struct hl_device *hdev) prop->pmmu.num_hops = MMU_ARCH_5_HOPS; prop->pmmu.last_mask = LAST_MASK; /* TODO: will be duplicated until implementing per-MMU props */ - prop->pmmu.hop_table_size = prop->mmu_hop_table_size; - prop->pmmu.hop0_tables_total_size = prop->mmu_hop0_tables_total_size; + prop->pmmu.hop_table_size = HOP_TABLE_SIZE_512_PTE; + prop->pmmu.hop0_tables_total_size = HOP0_512_PTE_TABLES_TOTAL_SIZE; /* PMMU and HPMMU are the same except of page size */ memcpy(&prop->pmmu_huge, &prop->pmmu, sizeof(prop->pmmu)); @@ -645,6 +647,7 @@ static int gaudi_set_fixed_properties(struct hl_device *hdev) prop->dmmu.start_addr = (VA_HOST_SPACE_START + VA_HOST_SPACE_SIZE / 2); prop->dmmu.end_addr = VA_HOST_SPACE_END; prop->dmmu.page_size = PAGE_SIZE_2MB; + prop->dmmu.pgt_size = prop->mmu_pgt_size; prop->cfg_size = CFG_SIZE; prop->max_asid = MAX_ASID; @@ -660,7 +663,7 @@ static int gaudi_set_fixed_properties(struct hl_device *hdev) prop->pcie_dbi_base_address = mmPCIE_DBI_BASE; prop->pcie_aux_dbi_reg_addr = CFG_BASE + mmPCIE_AUX_DBI; - strncpy(prop->cpucp_info.card_name, GAUDI_DEFAULT_CARD_NAME, + strscpy_pad(prop->cpucp_info.card_name, GAUDI_DEFAULT_CARD_NAME, CARD_NAME_MAX_LEN); prop->max_pending_cs = GAUDI_MAX_PENDING_CS; @@ -1636,10 +1639,8 @@ static int gaudi_late_init(struct hl_device *hdev) } rc = hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_ENABLE_PCI_ACCESS, 0x0); - if (rc) { - dev_err(hdev->dev, "Failed to enable PCI access from CPU\n"); + if (rc) return rc; - } /* Scrub both SRAM and DRAM */ rc = hdev->asic_funcs->scrub_device_mem(hdev); @@ -3648,7 +3649,7 @@ static int gaudi_mmu_init(struct hl_device *hdev) for (i = 0 ; i < prop->max_asid ; i++) { hop0_addr = prop->mmu_pgt_addr + - (i * prop->mmu_hop_table_size); + (i * prop->dmmu.hop_table_size); rc = gaudi_mmu_update_asid_hop0_addr(hdev, i, hop0_addr); if (rc) { @@ -4151,13 +4152,7 @@ skip_reset: static int gaudi_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; + return hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS, 0x0); } static int gaudi_resume(struct hl_device *hdev) @@ -4173,10 +4168,29 @@ static int gaudi_mmap(struct hl_device *hdev, struct vm_area_struct *vma, vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_DONTCOPY | VM_NORESERVE); +#ifdef _HAS_DMA_MMAP_COHERENT + /* + * If dma_alloc_coherent() returns a vmalloc address, set VM_MIXEDMAP + * so vm_insert_page() can handle it safely. Without this, the kernel + * may BUG_ON due to VM_PFNMAP. + */ + if (is_vmalloc_addr(cpu_addr)) + vm_flags_set(vma, VM_MIXEDMAP); + rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, (dma_addr - HOST_PHYS_BASE), 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; } @@ -4619,8 +4633,7 @@ static int gaudi_scrub_device_dram(struct hl_device *hdev, u64 val) static int gaudi_scrub_device_mem(struct hl_device *hdev) { struct asic_fixed_properties *prop = &hdev->asic_prop; - u64 wait_to_idle_time = hdev->pdev ? HBM_SCRUBBING_TIMEOUT_US : - min_t(u64, HBM_SCRUBBING_TIMEOUT_US * 10, HL_SIM_MAX_TIMEOUT_US); + u64 wait_to_idle_time = HBM_SCRUBBING_TIMEOUT_US; u64 addr, size, val = hdev->memory_scrub_val; ktime_t timeout; int rc = 0; @@ -4904,7 +4917,7 @@ static int gaudi_pin_memory_before_cs(struct hl_device *hdev, list_add_tail(&userptr->job_node, parser->job_userptr_list); - rc = hdev->asic_funcs->asic_dma_map_sgtable(hdev, userptr->sgt, dir); + rc = hl_dma_map_sgtable(hdev, userptr->sgt, dir); if (rc) { dev_err(hdev->dev, "failed to map sgt with DMA region\n"); goto unpin_memory; @@ -8000,7 +8013,7 @@ static int gaudi_cpucp_info_get(struct hl_device *hdev) return rc; if (!strlen(prop->cpucp_info.card_name)) - strncpy(prop->cpucp_info.card_name, GAUDI_DEFAULT_CARD_NAME, + strscpy_pad(prop->cpucp_info.card_name, GAUDI_DEFAULT_CARD_NAME, CARD_NAME_MAX_LEN); hdev->card_type = le32_to_cpu(hdev->asic_prop.cpucp_info.card_type); @@ -9140,9 +9153,9 @@ static const struct hl_asic_funcs gaudi_funcs = { .asic_dma_pool_free = gaudi_dma_pool_free, .cpu_accessible_dma_pool_alloc = gaudi_cpu_accessible_dma_pool_alloc, .cpu_accessible_dma_pool_free = gaudi_cpu_accessible_dma_pool_free, - .hl_dma_unmap_sgtable = hl_dma_unmap_sgtable, + .dma_unmap_sgtable = hl_asic_dma_unmap_sgtable, .cs_parser = gaudi_cs_parser, - .asic_dma_map_sgtable = hl_dma_map_sgtable, + .dma_map_sgtable = hl_asic_dma_map_sgtable, .add_end_of_cb_packets = gaudi_add_end_of_cb_packets, .update_eq_ci = gaudi_update_eq_ci, .context_switch = gaudi_context_switch, |