#define AMDGPU_RAS_BLOCK_COUNT AMDGPU_RAS_BLOCK__LAST
#define AMDGPU_RAS_BLOCK_MASK ((1ULL << AMDGPU_RAS_BLOCK_COUNT) - 1)
+enum amdgpu_ras_gfx_subblock {
+ /* CPC */
+ AMDGPU_RAS_BLOCK__GFX_CPC_INDEX_START = 0,
+ AMDGPU_RAS_BLOCK__GFX_CPC_SCRATCH =
+ AMDGPU_RAS_BLOCK__GFX_CPC_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_CPC_UCODE,
+ AMDGPU_RAS_BLOCK__GFX_DC_STATE_ME1,
+ AMDGPU_RAS_BLOCK__GFX_DC_CSINVOC_ME1,
+ AMDGPU_RAS_BLOCK__GFX_DC_RESTORE_ME1,
+ AMDGPU_RAS_BLOCK__GFX_DC_STATE_ME2,
+ AMDGPU_RAS_BLOCK__GFX_DC_CSINVOC_ME2,
+ AMDGPU_RAS_BLOCK__GFX_DC_RESTORE_ME2,
+ AMDGPU_RAS_BLOCK__GFX_CPC_INDEX_END =
+ AMDGPU_RAS_BLOCK__GFX_DC_RESTORE_ME2,
+ /* CPF */
+ AMDGPU_RAS_BLOCK__GFX_CPF_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_CPF_ROQ_ME2 =
+ AMDGPU_RAS_BLOCK__GFX_CPF_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_CPF_ROQ_ME1,
+ AMDGPU_RAS_BLOCK__GFX_CPF_TAG,
+ AMDGPU_RAS_BLOCK__GFX_CPF_INDEX_END = AMDGPU_RAS_BLOCK__GFX_CPF_TAG,
+ /* CPG */
+ AMDGPU_RAS_BLOCK__GFX_CPG_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_CPG_DMA_ROQ =
+ AMDGPU_RAS_BLOCK__GFX_CPG_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_CPG_DMA_TAG,
+ AMDGPU_RAS_BLOCK__GFX_CPG_TAG,
+ AMDGPU_RAS_BLOCK__GFX_CPG_INDEX_END = AMDGPU_RAS_BLOCK__GFX_CPG_TAG,
+ /* GDS */
+ AMDGPU_RAS_BLOCK__GFX_GDS_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_GDS_MEM = AMDGPU_RAS_BLOCK__GFX_GDS_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_GDS_INPUT_QUEUE,
+ AMDGPU_RAS_BLOCK__GFX_GDS_OA_PHY_CMD_RAM_MEM,
+ AMDGPU_RAS_BLOCK__GFX_GDS_OA_PHY_DATA_RAM_MEM,
+ AMDGPU_RAS_BLOCK__GFX_GDS_OA_PIPE_MEM,
+ AMDGPU_RAS_BLOCK__GFX_GDS_INDEX_END =
+ AMDGPU_RAS_BLOCK__GFX_GDS_OA_PIPE_MEM,
+ /* SPI */
+ AMDGPU_RAS_BLOCK__GFX_SPI_SR_MEM,
+ /* SQ */
+ AMDGPU_RAS_BLOCK__GFX_SQ_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_SQ_SGPR = AMDGPU_RAS_BLOCK__GFX_SQ_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_SQ_LDS_D,
+ AMDGPU_RAS_BLOCK__GFX_SQ_LDS_I,
+ AMDGPU_RAS_BLOCK__GFX_SQ_VGPR,
+ AMDGPU_RAS_BLOCK__GFX_SQ_INDEX_END = AMDGPU_RAS_BLOCK__GFX_SQ_VGPR,
+ /* SQC (3 ranges) */
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX_START,
+ /* SQC range 0 */
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX0_START =
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_UTCL1_LFIFO =
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX0_START,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_CU0_WRITE_DATA_BUF,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_CU0_UTCL1_LFIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_CU1_WRITE_DATA_BUF,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_CU1_UTCL1_LFIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_CU2_WRITE_DATA_BUF,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_CU2_UTCL1_LFIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX0_END =
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_CU2_UTCL1_LFIFO,
+ /* SQC range 1 */
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX1_START,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKA_TAG_RAM =
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX1_START,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKA_UTCL1_MISS_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKA_MISS_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKA_BANK_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKA_TAG_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKA_HIT_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKA_MISS_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKA_DIRTY_BIT_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKA_BANK_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX1_END =
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKA_BANK_RAM,
+ /* SQC range 2 */
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX2_START,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKB_TAG_RAM =
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX2_START,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKB_UTCL1_MISS_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKB_MISS_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKB_BANK_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKB_TAG_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKB_HIT_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKB_MISS_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKB_DIRTY_BIT_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKB_BANK_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX2_END =
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKB_BANK_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX_END =
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX2_END,
+ /* TA */
+ AMDGPU_RAS_BLOCK__GFX_TA_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TA_FS_DFIFO =
+ AMDGPU_RAS_BLOCK__GFX_TA_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TA_FS_AFIFO,
+ AMDGPU_RAS_BLOCK__GFX_TA_FL_LFIFO,
+ AMDGPU_RAS_BLOCK__GFX_TA_FX_LFIFO,
+ AMDGPU_RAS_BLOCK__GFX_TA_FS_CFIFO,
+ AMDGPU_RAS_BLOCK__GFX_TA_INDEX_END = AMDGPU_RAS_BLOCK__GFX_TA_FS_CFIFO,
+ /* TCA */
+ AMDGPU_RAS_BLOCK__GFX_TCA_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TCA_HOLE_FIFO =
+ AMDGPU_RAS_BLOCK__GFX_TCA_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TCA_REQ_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_TCA_INDEX_END =
+ AMDGPU_RAS_BLOCK__GFX_TCA_REQ_FIFO,
+ /* TCC (5 sub-ranges) */
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX_START,
+ /* TCC range 0 */
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX0_START =
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DATA =
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX0_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DATA_BANK_0_1,
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DATA_BANK_1_0,
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DATA_BANK_1_1,
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DIRTY_BANK_0,
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DIRTY_BANK_1,
+ AMDGPU_RAS_BLOCK__GFX_TCC_HIGH_RATE_TAG,
+ AMDGPU_RAS_BLOCK__GFX_TCC_LOW_RATE_TAG,
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX0_END =
+ AMDGPU_RAS_BLOCK__GFX_TCC_LOW_RATE_TAG,
+ /* TCC range 1 */
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX1_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_IN_USE_DEC =
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX1_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_IN_USE_TRANSFER,
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX1_END =
+ AMDGPU_RAS_BLOCK__GFX_TCC_IN_USE_TRANSFER,
+ /* TCC range 2 */
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX2_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_RETURN_DATA =
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX2_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_RETURN_CONTROL,
+ AMDGPU_RAS_BLOCK__GFX_TCC_UC_ATOMIC_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_TCC_WRITE_RETURN,
+ AMDGPU_RAS_BLOCK__GFX_TCC_WRITE_CACHE_READ,
+ AMDGPU_RAS_BLOCK__GFX_TCC_SRC_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_TCC_SRC_FIFO_NEXT_RAM,
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_TAG_PROBE_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX2_END =
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_TAG_PROBE_FIFO,
+ /* TCC range 3 */
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX3_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_LATENCY_FIFO =
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX3_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_LATENCY_FIFO_NEXT_RAM,
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX3_END =
+ AMDGPU_RAS_BLOCK__GFX_TCC_LATENCY_FIFO_NEXT_RAM,
+ /* TCC range 4 */
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX4_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_WRRET_TAG_WRITE_RETURN =
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX4_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_ATOMIC_RETURN_BUFFER,
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX4_END =
+ AMDGPU_RAS_BLOCK__GFX_TCC_ATOMIC_RETURN_BUFFER,
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX_END =
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX4_END,
+ /* TCI */
+ AMDGPU_RAS_BLOCK__GFX_TCI_WRITE_RAM,
+ /* TCP */
+ AMDGPU_RAS_BLOCK__GFX_TCP_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TCP_CACHE_RAM =
+ AMDGPU_RAS_BLOCK__GFX_TCP_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TCP_LFIFO_RAM,
+ AMDGPU_RAS_BLOCK__GFX_TCP_CMD_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_TCP_VM_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_TCP_DB_RAM,
+ AMDGPU_RAS_BLOCK__GFX_TCP_UTCL1_LFIFO0,
+ AMDGPU_RAS_BLOCK__GFX_TCP_UTCL1_LFIFO1,
+ AMDGPU_RAS_BLOCK__GFX_TCP_INDEX_END =
+ AMDGPU_RAS_BLOCK__GFX_TCP_UTCL1_LFIFO1,
+ /* TD */
+ AMDGPU_RAS_BLOCK__GFX_TD_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TD_SS_FIFO_LO =
+ AMDGPU_RAS_BLOCK__GFX_TD_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TD_SS_FIFO_HI,
+ AMDGPU_RAS_BLOCK__GFX_TD_CS_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_TD_INDEX_END = AMDGPU_RAS_BLOCK__GFX_TD_CS_FIFO,
+ /* EA (3 sub-ranges) */
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX_START,
+ /* EA range 0 */
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX0_START =
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_EA_DRAMRD_CMDMEM =
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX0_START,
+ AMDGPU_RAS_BLOCK__GFX_EA_DRAMWR_CMDMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_DRAMWR_DATAMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_RRET_TAGMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_WRET_TAGMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_GMIRD_CMDMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_GMIWR_CMDMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_GMIWR_DATAMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX0_END =
+ AMDGPU_RAS_BLOCK__GFX_EA_GMIWR_DATAMEM,
+ /* EA range 1 */
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX1_START,
+ AMDGPU_RAS_BLOCK__GFX_EA_DRAMRD_PAGEMEM =
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX1_START,
+ AMDGPU_RAS_BLOCK__GFX_EA_DRAMWR_PAGEMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_IORD_CMDMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_IOWR_CMDMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_IOWR_DATAMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_GMIRD_PAGEMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_GMIWR_PAGEMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX1_END =
+ AMDGPU_RAS_BLOCK__GFX_EA_GMIWR_PAGEMEM,
+ /* EA range 2 */
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX2_START,
+ AMDGPU_RAS_BLOCK__GFX_EA_MAM_D0MEM =
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX2_START,
+ AMDGPU_RAS_BLOCK__GFX_EA_MAM_D1MEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_MAM_D2MEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_MAM_D3MEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX2_END =
+ AMDGPU_RAS_BLOCK__GFX_EA_MAM_D3MEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX_END =
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX2_END,
+ /* UTC VM L2 bank */
+ AMDGPU_RAS_BLOCK__UTC_VML2_BANK_CACHE,
+ /* UTC VM walker */
+ AMDGPU_RAS_BLOCK__UTC_VML2_WALKER,
+ /* UTC ATC L2 2MB cache */
+ AMDGPU_RAS_BLOCK__UTC_ATCL2_CACHE_2M_BANK,
+ /* UTC ATC L2 4KB cache */
+ AMDGPU_RAS_BLOCK__UTC_ATCL2_CACHE_4K_BANK,
+ AMDGPU_RAS_BLOCK__GFX_MAX
+};
+
enum amdgpu_ras_error_type {
AMDGPU_RAS_ERROR__NONE = 0,
AMDGPU_RAS_ERROR__PARITY = 1,
char name[32];
};
-typedef int (*ras_ih_cb)(struct amdgpu_device *adev,
- struct amdgpu_iv_entry *entry);
-
struct amdgpu_ras {
/* ras infrastructure */
/* for ras itself. */
struct dentry *ent;
/* sysfs */
struct device_attribute features_attr;
+ struct bin_attribute badpages_attr;
/* block array */
struct ras_manager *objs;
uint32_t flags;
};
-/* interfaces for IP */
+struct ras_fs_data {
+ char sysfs_name[32];
+ char debugfs_name[32];
+};
+struct ras_err_data {
+ unsigned long ue_count;
+ unsigned long ce_count;
+ unsigned long err_addr_cnt;
+ uint64_t *err_addr;
+};
+
+struct ras_err_handler_data {
+ /* point to bad pages array */
+ struct {
+ unsigned long bp;
+ struct amdgpu_bo *bo;
+ } *bps;
+ /* the count of entries */
+ int count;
+ /* the space can place new entries */
+ int space_left;
+ /* last reserved entry's index + 1 */
+ int last_reserved;
+};
+
+typedef int (*ras_ih_cb)(struct amdgpu_device *adev,
+ struct ras_err_data *err_data,
+ struct amdgpu_iv_entry *entry);
+
+struct ras_ih_data {
+ /* interrupt bottom half */
+ struct work_struct ih_work;
+ int inuse;
+ /* IP callback */
+ ras_ih_cb cb;
+ /* full of entries */
+ unsigned char *ring;
+ unsigned int ring_size;
+ unsigned int element_size;
+ unsigned int aligned_element_size;
+ unsigned int rptr;
+ unsigned int wptr;
+};
+
+struct ras_manager {
+ struct ras_common_if head;
+ /* reference count */
+ int use;
+ /* ras block link */
+ struct list_head node;
+ /* the device */
+ struct amdgpu_device *adev;
+ /* debugfs */
+ struct dentry *ent;
+ /* sysfs */
+ struct device_attribute sysfs_attr;
+ int attr_inuse;
+
+ /* fs node name */
+ struct ras_fs_data fs_data;
+
+ /* IH data */
+ struct ras_ih_data ih_data;
+
+ struct ras_err_data err_data;
+};
+
+struct ras_badpage {
+ unsigned int bp;
+ unsigned int size;
+ unsigned int flags;
+};
+
+/* interfaces for IP */
struct ras_fs_if {
struct ras_common_if head;
char sysfs_name[32];
return ras && (ras->supported & (1 << block));
}
+int amdgpu_ras_request_reset_on_boot(struct amdgpu_device *adev,
+ unsigned int block);
+
+void amdgpu_ras_resume(struct amdgpu_device *adev);
+void amdgpu_ras_suspend(struct amdgpu_device *adev);
+
int amdgpu_ras_query_error_count(struct amdgpu_device *adev,
bool is_ce);
static inline int amdgpu_ras_reset_gpu(struct amdgpu_device *adev,
bool is_baco)
{
- /* remove me when gpu reset works on vega20 A1. */
-#if 0
struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
if (atomic_cmpxchg(&ras->in_recovery, 0, 1) == 0)
schedule_work(&ras->recovery_work);
-#endif
return 0;
}
/* called in ip_init and ip_fini */
int amdgpu_ras_init(struct amdgpu_device *adev);
-void amdgpu_ras_post_init(struct amdgpu_device *adev);
int amdgpu_ras_fini(struct amdgpu_device *adev);
int amdgpu_ras_pre_fini(struct amdgpu_device *adev);
int amdgpu_ras_sysfs_remove(struct amdgpu_device *adev,
struct ras_common_if *head);
-int amdgpu_ras_debugfs_create(struct amdgpu_device *adev,
+void amdgpu_ras_debugfs_create(struct amdgpu_device *adev,
struct ras_fs_if *head);
-int amdgpu_ras_debugfs_remove(struct amdgpu_device *adev,
+void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev,
struct ras_common_if *head);
int amdgpu_ras_error_query(struct amdgpu_device *adev,
projects / J-linux.git / blobdiff