| .. | .. |
|---|
| 30 | 30 | |
|---|
| 31 | 31 | #include "amdgpu_irq.h" |
|---|
| 32 | 32 | |
|---|
| 33 | +/* VA hole for 48bit addresses on Vega10 */ |
|---|
| 34 | +#define AMDGPU_GMC_HOLE_START 0x0000800000000000ULL |
|---|
| 35 | +#define AMDGPU_GMC_HOLE_END 0xffff800000000000ULL |
|---|
| 36 | + |
|---|
| 37 | +/* |
|---|
| 38 | + * Hardware is programmed as if the hole doesn't exists with start and end |
|---|
| 39 | + * address values. |
|---|
| 40 | + * |
|---|
| 41 | + * This mask is used to remove the upper 16bits of the VA and so come up with |
|---|
| 42 | + * the linear addr value. |
|---|
| 43 | + */ |
|---|
| 44 | +#define AMDGPU_GMC_HOLE_MASK 0x0000ffffffffffffULL |
|---|
| 45 | + |
|---|
| 46 | +/* |
|---|
| 47 | + * Ring size as power of two for the log of recent faults. |
|---|
| 48 | + */ |
|---|
| 49 | +#define AMDGPU_GMC_FAULT_RING_ORDER 8 |
|---|
| 50 | +#define AMDGPU_GMC_FAULT_RING_SIZE (1 << AMDGPU_GMC_FAULT_RING_ORDER) |
|---|
| 51 | + |
|---|
| 52 | +/* |
|---|
| 53 | + * Hash size as power of two for the log of recent faults |
|---|
| 54 | + */ |
|---|
| 55 | +#define AMDGPU_GMC_FAULT_HASH_ORDER 8 |
|---|
| 56 | +#define AMDGPU_GMC_FAULT_HASH_SIZE (1 << AMDGPU_GMC_FAULT_HASH_ORDER) |
|---|
| 57 | + |
|---|
| 58 | +/* |
|---|
| 59 | + * Number of IH timestamp ticks until a fault is considered handled |
|---|
| 60 | + */ |
|---|
| 61 | +#define AMDGPU_GMC_FAULT_TIMEOUT 5000ULL |
|---|
| 62 | + |
|---|
| 33 | 63 | struct firmware; |
|---|
| 64 | + |
|---|
| 65 | +/* |
|---|
| 66 | + * GMC page fault information |
|---|
| 67 | + */ |
|---|
| 68 | +struct amdgpu_gmc_fault { |
|---|
| 69 | + uint64_t timestamp; |
|---|
| 70 | + uint64_t next:AMDGPU_GMC_FAULT_RING_ORDER; |
|---|
| 71 | + uint64_t key:52; |
|---|
| 72 | +}; |
|---|
| 34 | 73 | |
|---|
| 35 | 74 | /* |
|---|
| 36 | 75 | * VMHUB structures, functions & helpers |
|---|
| 37 | 76 | */ |
|---|
| 77 | +struct amdgpu_vmhub_funcs { |
|---|
| 78 | + void (*print_l2_protection_fault_status)(struct amdgpu_device *adev, |
|---|
| 79 | + uint32_t status); |
|---|
| 80 | + uint32_t (*get_invalidate_req)(unsigned int vmid, uint32_t flush_type); |
|---|
| 81 | +}; |
|---|
| 82 | + |
|---|
| 38 | 83 | struct amdgpu_vmhub { |
|---|
| 39 | 84 | uint32_t ctx0_ptb_addr_lo32; |
|---|
| 40 | 85 | uint32_t ctx0_ptb_addr_hi32; |
|---|
| 86 | + uint32_t vm_inv_eng0_sem; |
|---|
| 41 | 87 | uint32_t vm_inv_eng0_req; |
|---|
| 42 | 88 | uint32_t vm_inv_eng0_ack; |
|---|
| 43 | 89 | uint32_t vm_context0_cntl; |
|---|
| 44 | 90 | uint32_t vm_l2_pro_fault_status; |
|---|
| 45 | 91 | uint32_t vm_l2_pro_fault_cntl; |
|---|
| 92 | + |
|---|
| 93 | + /* |
|---|
| 94 | + * store the register distances between two continuous context domain |
|---|
| 95 | + * and invalidation engine. |
|---|
| 96 | + */ |
|---|
| 97 | + uint32_t ctx_distance; |
|---|
| 98 | + uint32_t ctx_addr_distance; /* include LO32/HI32 */ |
|---|
| 99 | + uint32_t eng_distance; |
|---|
| 100 | + uint32_t eng_addr_distance; /* include LO32/HI32 */ |
|---|
| 101 | + |
|---|
| 102 | + uint32_t vm_cntx_cntl_vm_fault; |
|---|
| 103 | + |
|---|
| 104 | + const struct amdgpu_vmhub_funcs *vmhub_funcs; |
|---|
| 46 | 105 | }; |
|---|
| 47 | 106 | |
|---|
| 48 | 107 | /* |
|---|
| .. | .. |
|---|
| 50 | 109 | */ |
|---|
| 51 | 110 | struct amdgpu_gmc_funcs { |
|---|
| 52 | 111 | /* flush the vm tlb via mmio */ |
|---|
| 53 | | - void (*flush_gpu_tlb)(struct amdgpu_device *adev, |
|---|
| 54 | | - uint32_t vmid); |
|---|
| 112 | + void (*flush_gpu_tlb)(struct amdgpu_device *adev, uint32_t vmid, |
|---|
| 113 | + uint32_t vmhub, uint32_t flush_type); |
|---|
| 114 | + /* flush the vm tlb via pasid */ |
|---|
| 115 | + int (*flush_gpu_tlb_pasid)(struct amdgpu_device *adev, uint16_t pasid, |
|---|
| 116 | + uint32_t flush_type, bool all_hub); |
|---|
| 55 | 117 | /* flush the vm tlb via ring */ |
|---|
| 56 | 118 | uint64_t (*emit_flush_gpu_tlb)(struct amdgpu_ring *ring, unsigned vmid, |
|---|
| 57 | 119 | uint64_t pd_addr); |
|---|
| 58 | 120 | /* Change the VMID -> PASID mapping */ |
|---|
| 59 | 121 | void (*emit_pasid_mapping)(struct amdgpu_ring *ring, unsigned vmid, |
|---|
| 60 | 122 | unsigned pasid); |
|---|
| 61 | | - /* write pte/pde updates using the cpu */ |
|---|
| 62 | | - int (*set_pte_pde)(struct amdgpu_device *adev, |
|---|
| 63 | | - void *cpu_pt_addr, /* cpu addr of page table */ |
|---|
| 64 | | - uint32_t gpu_page_idx, /* pte/pde to update */ |
|---|
| 65 | | - uint64_t addr, /* addr to write into pte/pde */ |
|---|
| 66 | | - uint64_t flags); /* access flags */ |
|---|
| 67 | 123 | /* enable/disable PRT support */ |
|---|
| 68 | 124 | void (*set_prt)(struct amdgpu_device *adev, bool enable); |
|---|
| 69 | | - /* set pte flags based per asic */ |
|---|
| 70 | | - uint64_t (*get_vm_pte_flags)(struct amdgpu_device *adev, |
|---|
| 71 | | - uint32_t flags); |
|---|
| 125 | + /* map mtype to hardware flags */ |
|---|
| 126 | + uint64_t (*map_mtype)(struct amdgpu_device *adev, uint32_t flags); |
|---|
| 72 | 127 | /* get the pde for a given mc addr */ |
|---|
| 73 | 128 | void (*get_vm_pde)(struct amdgpu_device *adev, int level, |
|---|
| 74 | 129 | u64 *dst, u64 *flags); |
|---|
| 130 | + /* get the pte flags to use for a BO VA mapping */ |
|---|
| 131 | + void (*get_vm_pte)(struct amdgpu_device *adev, |
|---|
| 132 | + struct amdgpu_bo_va_mapping *mapping, |
|---|
| 133 | + uint64_t *flags); |
|---|
| 134 | + /* get the amount of memory used by the vbios for pre-OS console */ |
|---|
| 135 | + unsigned int (*get_vbios_fb_size)(struct amdgpu_device *adev); |
|---|
| 136 | +}; |
|---|
| 137 | + |
|---|
| 138 | +struct amdgpu_xgmi { |
|---|
| 139 | + /* from psp */ |
|---|
| 140 | + u64 node_id; |
|---|
| 141 | + u64 hive_id; |
|---|
| 142 | + /* fixed per family */ |
|---|
| 143 | + u64 node_segment_size; |
|---|
| 144 | + /* physical node (0-3) */ |
|---|
| 145 | + unsigned physical_node_id; |
|---|
| 146 | + /* number of nodes (0-4) */ |
|---|
| 147 | + unsigned num_physical_nodes; |
|---|
| 148 | + /* gpu list in the same hive */ |
|---|
| 149 | + struct list_head head; |
|---|
| 150 | + bool supported; |
|---|
| 151 | + struct ras_common_if *ras_if; |
|---|
| 75 | 152 | }; |
|---|
| 76 | 153 | |
|---|
| 77 | 154 | struct amdgpu_gmc { |
|---|
| 155 | + /* FB's physical address in MMIO space (for CPU to |
|---|
| 156 | + * map FB). This is different compared to the agp/ |
|---|
| 157 | + * gart/vram_start/end field as the later is from |
|---|
| 158 | + * GPU's view and aper_base is from CPU's view. |
|---|
| 159 | + */ |
|---|
| 78 | 160 | resource_size_t aper_size; |
|---|
| 79 | 161 | resource_size_t aper_base; |
|---|
| 80 | 162 | /* for some chips with <= 32MB we need to lie |
|---|
| 81 | 163 | * about vram size near mc fb location */ |
|---|
| 82 | 164 | u64 mc_vram_size; |
|---|
| 83 | 165 | u64 visible_vram_size; |
|---|
| 166 | + /* AGP aperture start and end in MC address space |
|---|
| 167 | + * Driver find a hole in the MC address space |
|---|
| 168 | + * to place AGP by setting MC_VM_AGP_BOT/TOP registers |
|---|
| 169 | + * Under VMID0, logical address == MC address. AGP |
|---|
| 170 | + * aperture maps to physical bus or IOVA addressed. |
|---|
| 171 | + * AGP aperture is used to simulate FB in ZFB case. |
|---|
| 172 | + * AGP aperture is also used for page table in system |
|---|
| 173 | + * memory (mainly for APU). |
|---|
| 174 | + * |
|---|
| 175 | + */ |
|---|
| 176 | + u64 agp_size; |
|---|
| 177 | + u64 agp_start; |
|---|
| 178 | + u64 agp_end; |
|---|
| 179 | + /* GART aperture start and end in MC address space |
|---|
| 180 | + * Driver find a hole in the MC address space |
|---|
| 181 | + * to place GART by setting VM_CONTEXT0_PAGE_TABLE_START/END_ADDR |
|---|
| 182 | + * registers |
|---|
| 183 | + * Under VMID0, logical address inside GART aperture will |
|---|
| 184 | + * be translated through gpuvm gart page table to access |
|---|
| 185 | + * paged system memory |
|---|
| 186 | + */ |
|---|
| 84 | 187 | u64 gart_size; |
|---|
| 85 | 188 | u64 gart_start; |
|---|
| 86 | 189 | u64 gart_end; |
|---|
| 190 | + /* Frame buffer aperture of this GPU device. Different from |
|---|
| 191 | + * fb_start (see below), this only covers the local GPU device. |
|---|
| 192 | + * Driver get fb_start from MC_VM_FB_LOCATION_BASE (set by vbios) |
|---|
| 193 | + * and calculate vram_start of this local device by adding an |
|---|
| 194 | + * offset inside the XGMI hive. |
|---|
| 195 | + * Under VMID0, logical address == MC address |
|---|
| 196 | + */ |
|---|
| 87 | 197 | u64 vram_start; |
|---|
| 88 | 198 | u64 vram_end; |
|---|
| 199 | + /* FB region , it's same as local vram region in single GPU, in XGMI |
|---|
| 200 | + * configuration, this region covers all GPUs in the same hive , |
|---|
| 201 | + * each GPU in the hive has the same view of this FB region . |
|---|
| 202 | + * GPU0's vram starts at offset (0 * segment size) , |
|---|
| 203 | + * GPU1 starts at offset (1 * segment size), etc. |
|---|
| 204 | + */ |
|---|
| 205 | + u64 fb_start; |
|---|
| 206 | + u64 fb_end; |
|---|
| 89 | 207 | unsigned vram_width; |
|---|
| 90 | 208 | u64 real_vram_size; |
|---|
| 91 | 209 | int vram_mtrr; |
|---|
| .. | .. |
|---|
| 94 | 212 | uint32_t fw_version; |
|---|
| 95 | 213 | struct amdgpu_irq_src vm_fault; |
|---|
| 96 | 214 | uint32_t vram_type; |
|---|
| 215 | + uint8_t vram_vendor; |
|---|
| 97 | 216 | uint32_t srbm_soft_reset; |
|---|
| 98 | 217 | bool prt_warning; |
|---|
| 99 | | - uint64_t stolen_size; |
|---|
| 100 | 218 | uint32_t sdpif_register; |
|---|
| 101 | 219 | /* apertures */ |
|---|
| 102 | 220 | u64 shared_aperture_start; |
|---|
| .. | .. |
|---|
| 109 | 227 | struct kfd_vm_fault_info *vm_fault_info; |
|---|
| 110 | 228 | atomic_t vm_fault_info_updated; |
|---|
| 111 | 229 | |
|---|
| 230 | + struct amdgpu_gmc_fault fault_ring[AMDGPU_GMC_FAULT_RING_SIZE]; |
|---|
| 231 | + struct { |
|---|
| 232 | + uint64_t idx:AMDGPU_GMC_FAULT_RING_ORDER; |
|---|
| 233 | + } fault_hash[AMDGPU_GMC_FAULT_HASH_SIZE]; |
|---|
| 234 | + uint64_t last_fault:AMDGPU_GMC_FAULT_RING_ORDER; |
|---|
| 235 | + |
|---|
| 236 | + bool tmz_enabled; |
|---|
| 237 | + |
|---|
| 112 | 238 | const struct amdgpu_gmc_funcs *gmc_funcs; |
|---|
| 239 | + |
|---|
| 240 | + struct amdgpu_xgmi xgmi; |
|---|
| 241 | + struct amdgpu_irq_src ecc_irq; |
|---|
| 242 | + int noretry; |
|---|
| 113 | 243 | }; |
|---|
| 244 | + |
|---|
| 245 | +#define amdgpu_gmc_flush_gpu_tlb(adev, vmid, vmhub, type) ((adev)->gmc.gmc_funcs->flush_gpu_tlb((adev), (vmid), (vmhub), (type))) |
|---|
| 246 | +#define amdgpu_gmc_flush_gpu_tlb_pasid(adev, pasid, type, allhub) \ |
|---|
| 247 | + ((adev)->gmc.gmc_funcs->flush_gpu_tlb_pasid \ |
|---|
| 248 | + ((adev), (pasid), (type), (allhub))) |
|---|
| 249 | +#define amdgpu_gmc_emit_flush_gpu_tlb(r, vmid, addr) (r)->adev->gmc.gmc_funcs->emit_flush_gpu_tlb((r), (vmid), (addr)) |
|---|
| 250 | +#define amdgpu_gmc_emit_pasid_mapping(r, vmid, pasid) (r)->adev->gmc.gmc_funcs->emit_pasid_mapping((r), (vmid), (pasid)) |
|---|
| 251 | +#define amdgpu_gmc_map_mtype(adev, flags) (adev)->gmc.gmc_funcs->map_mtype((adev),(flags)) |
|---|
| 252 | +#define amdgpu_gmc_get_vm_pde(adev, level, dst, flags) (adev)->gmc.gmc_funcs->get_vm_pde((adev), (level), (dst), (flags)) |
|---|
| 253 | +#define amdgpu_gmc_get_vm_pte(adev, mapping, flags) (adev)->gmc.gmc_funcs->get_vm_pte((adev), (mapping), (flags)) |
|---|
| 254 | +#define amdgpu_gmc_get_vbios_fb_size(adev) (adev)->gmc.gmc_funcs->get_vbios_fb_size((adev)) |
|---|
| 114 | 255 | |
|---|
| 115 | 256 | /** |
|---|
| 116 | 257 | * amdgpu_gmc_vram_full_visible - Check if full VRAM is visible through the BAR |
|---|
| .. | .. |
|---|
| 127 | 268 | return (gmc->real_vram_size == gmc->visible_vram_size); |
|---|
| 128 | 269 | } |
|---|
| 129 | 270 | |
|---|
| 271 | +/** |
|---|
| 272 | + * amdgpu_gmc_sign_extend - sign extend the given gmc address |
|---|
| 273 | + * |
|---|
| 274 | + * @addr: address to extend |
|---|
| 275 | + */ |
|---|
| 276 | +static inline uint64_t amdgpu_gmc_sign_extend(uint64_t addr) |
|---|
| 277 | +{ |
|---|
| 278 | + if (addr >= AMDGPU_GMC_HOLE_START) |
|---|
| 279 | + addr |= AMDGPU_GMC_HOLE_END; |
|---|
| 280 | + |
|---|
| 281 | + return addr; |
|---|
| 282 | +} |
|---|
| 283 | + |
|---|
| 284 | +void amdgpu_gmc_get_pde_for_bo(struct amdgpu_bo *bo, int level, |
|---|
| 285 | + uint64_t *addr, uint64_t *flags); |
|---|
| 286 | +int amdgpu_gmc_set_pte_pde(struct amdgpu_device *adev, void *cpu_pt_addr, |
|---|
| 287 | + uint32_t gpu_page_idx, uint64_t addr, |
|---|
| 288 | + uint64_t flags); |
|---|
| 289 | +uint64_t amdgpu_gmc_pd_addr(struct amdgpu_bo *bo); |
|---|
| 290 | +uint64_t amdgpu_gmc_agp_addr(struct ttm_buffer_object *bo); |
|---|
| 291 | +void amdgpu_gmc_vram_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc, |
|---|
| 292 | + u64 base); |
|---|
| 293 | +void amdgpu_gmc_gart_location(struct amdgpu_device *adev, |
|---|
| 294 | + struct amdgpu_gmc *mc); |
|---|
| 295 | +void amdgpu_gmc_agp_location(struct amdgpu_device *adev, |
|---|
| 296 | + struct amdgpu_gmc *mc); |
|---|
| 297 | +bool amdgpu_gmc_filter_faults(struct amdgpu_device *adev, uint64_t addr, |
|---|
| 298 | + uint16_t pasid, uint64_t timestamp); |
|---|
| 299 | +int amdgpu_gmc_ras_late_init(struct amdgpu_device *adev); |
|---|
| 300 | +void amdgpu_gmc_ras_fini(struct amdgpu_device *adev); |
|---|
| 301 | +int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev); |
|---|
| 302 | + |
|---|
| 303 | +extern void amdgpu_gmc_tmz_set(struct amdgpu_device *adev); |
|---|
| 304 | +extern void amdgpu_gmc_noretry_set(struct amdgpu_device *adev); |
|---|
| 305 | + |
|---|
| 306 | +extern void |
|---|
| 307 | +amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type, |
|---|
| 308 | + bool enable); |
|---|
| 309 | + |
|---|
| 310 | +void amdgpu_gmc_get_vbios_allocations(struct amdgpu_device *adev); |
|---|
| 311 | + |
|---|
| 130 | 312 | #endif |
|---|