summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorRui Teng <rui.teng@amd.com>2019-09-24 14:40:56 +0800
committerRui Teng <rui.teng@amd.com>2019-09-24 14:40:56 +0800
commit10bbca70f5727e465e39b647081f3be8893f2306 (patch)
tree8e953fc6925277f652a2d5e51f584d289ee12eed
parent9deadd6b58b8b1a440a94b1ac17e118c0b76bee8 (diff)
parent747455f049ea48bb258dca5db295faf880eaeee8 (diff)
Merge amd-staging-hybrid-master20190125 into amd-mainline-hybrid-master20190125amd-19.50
Change-Id: I520691f2d27ab57eb11b76657732ffbb4ad8d2ff
-rw-r--r--tests/amdgpu/ras_tests.c446
1 files changed, 399 insertions, 47 deletions
diff --git a/tests/amdgpu/ras_tests.c b/tests/amdgpu/ras_tests.c
index 81c34ad6..c1c543c1 100644
--- a/tests/amdgpu/ras_tests.c
+++ b/tests/amdgpu/ras_tests.c
@@ -31,6 +31,8 @@
#include <stdio.h>
#include "xf86drm.h"
+#define ARRAY_SIZE(a) (sizeof(a) / sizeof((a)[0]))
+
const char *ras_block_string[] = {
"umc",
"sdma",
@@ -72,11 +74,251 @@ enum amdgpu_ras_block {
#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__SINGLE_CORRECTABLE = 2,
- AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE = 4,
- AMDGPU_RAS_ERROR__POISON = 8,
+ AMDGPU_RAS_ERROR__NONE = 0,
+ AMDGPU_RAS_ERROR__PARITY = 1,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE = 2,
+ AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE = 4,
+ AMDGPU_RAS_ERROR__POISON = 8,
+};
+
+struct ras_inject_test_config {
+ char name[64];
+ char block[32];
+ int sub_block;
+ enum amdgpu_ras_error_type type;
+ uint64_t address;
+ uint64_t value;
};
struct ras_common_if {
@@ -100,8 +342,10 @@ struct ras_debug_if {
int op;
};
/* for now, only umc, gfx, sdma has implemented. */
-#define DEFAULT_RAS_BLOCK_MASK_INJECT (1 << AMDGPU_RAS_BLOCK__UMC)
-#define DEFAULT_RAS_BLOCK_MASK_QUERY (1 << AMDGPU_RAS_BLOCK__UMC)
+#define DEFAULT_RAS_BLOCK_MASK_INJECT ((1 << AMDGPU_RAS_BLOCK__UMC) |\
+ (1 << AMDGPU_RAS_BLOCK__GFX))
+#define DEFAULT_RAS_BLOCK_MASK_QUERY ((1 << AMDGPU_RAS_BLOCK__UMC) |\
+ (1 << AMDGPU_RAS_BLOCK__GFX))
#define DEFAULT_RAS_BLOCK_MASK_BASIC (1 << AMDGPU_RAS_BLOCK__UMC |\
(1 << AMDGPU_RAS_BLOCK__SDMA) |\
(1 << AMDGPU_RAS_BLOCK__GFX))
@@ -146,12 +390,78 @@ struct ras_DID_test_mask{
DEFAULT_RAS_BLOCK_MASK_BASIC\
}
+static const struct ras_inject_test_config umc_ras_inject_test[] = {
+ {"ras_umc.1.0", "umc", 0, AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+};
+
+static const struct ras_inject_test_config gfx_ras_inject_test[] = {
+ {"ras_gfx.2.0", "gfx", AMDGPU_RAS_BLOCK__GFX_CPC_UCODE,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+ {"ras_gfx.2.1", "gfx", AMDGPU_RAS_BLOCK__GFX_CPF_TAG,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+ {"ras_gfx.2.2", "gfx", AMDGPU_RAS_BLOCK__GFX_CPG_TAG,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+ {"ras_gfx.2.3", "gfx", AMDGPU_RAS_BLOCK__GFX_SQ_LDS_D,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+ {"ras_gfx.2.4", "gfx", AMDGPU_RAS_BLOCK__GFX_SQC_DATA_CU1_UTCL1_LFIFO,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+ {"ras_gfx.2.5", "gfx", AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKA_TAG_RAM,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+ {"ras_gfx.2.6", "gfx", AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKB_TAG_RAM,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+ {"ras_gfx.2.7", "gfx", AMDGPU_RAS_BLOCK__GFX_TA_FS_DFIFO,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+ {"ras_gfx.2.8", "gfx", AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DATA,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+ {"ras_gfx.2.9", "gfx", AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DATA_BANK_0_1,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+ {"ras_gfx.2.10", "gfx", AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DATA_BANK_1_0,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+ {"ras_gfx.2.11", "gfx", AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DATA_BANK_1_1,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+ {"ras_gfx.2.12", "gfx", AMDGPU_RAS_BLOCK__GFX_TCP_CACHE_RAM,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+ {"ras_gfx.2.13", "gfx", AMDGPU_RAS_BLOCK__GFX_TD_SS_FIFO_LO,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+ {"ras_gfx.2.14", "gfx", AMDGPU_RAS_BLOCK__GFX_EA_DRAMRD_CMDMEM,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE, 0, 0},
+};
+
static const struct ras_DID_test_mask ras_DID_array[] = {
{0x66a1, 0x00, RAS_BLOCK_MASK_ALL},
{0x66a1, 0x01, RAS_BLOCK_MASK_ALL},
{0x66a1, 0x04, RAS_BLOCK_MASK_ALL},
};
+static uint32_t amdgpu_ras_find_block_id_by_name(const char *name)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(ras_block_string); i++) {
+ if (strcmp(name, ras_block_string[i]) == 0)
+ return i;
+ }
+
+ return ARRAY_SIZE(ras_block_string);
+}
+
+static char *amdgpu_ras_get_error_type_id(enum amdgpu_ras_error_type type)
+{
+ switch (type) {
+ case AMDGPU_RAS_ERROR__PARITY:
+ return "parity";
+ case AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE:
+ return "single_correctable";
+ case AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE:
+ return "multi_uncorrectable";
+ case AMDGPU_RAS_ERROR__POISON:
+ return "poison";
+ case AMDGPU_RAS_ERROR__NONE:
+ default:
+ return NULL;
+ }
+}
+
static struct ras_test_mask amdgpu_ras_get_test_mask(drmDevicePtr device)
{
int i;
@@ -453,6 +763,34 @@ static int amdgpu_ras_query_err_count(enum amdgpu_ras_block block,
return 0;
}
+static int amdgpu_ras_inject(enum amdgpu_ras_block block,
+ uint32_t sub_block, enum amdgpu_ras_error_type type,
+ uint64_t address, uint64_t value)
+{
+ struct ras_debug_if data = { .op = 2, };
+ struct ras_inject_if *inject = &data.inject;
+ int ret;
+
+ if (amdgpu_ras_is_feature_enabled(block) <= 0) {
+ fprintf(stderr, "block id(%d) is not valid\n", block);
+ return -1;
+ }
+
+ inject->head.block = block;
+ inject->head.type = type;
+ inject->head.sub_block_index = sub_block;
+ strncpy(inject->head.name, ras_block_str(block), 32);
+ inject->address = address;
+ inject->value = value;
+
+ ret = amdgpu_ras_invoke(&data);
+ CU_ASSERT_EQUAL(ret, 0);
+ if (ret)
+ return -1;
+
+ return 0;
+}
+
//tests
static void amdgpu_ras_features_test(int enable)
{
@@ -503,69 +841,83 @@ static void amdgpu_ras_enable_test(void)
}
}
-static void __amdgpu_ras_inject_test(void)
+static void __amdgpu_ras_ip_inject_test(const struct ras_inject_test_config *ip_test,
+ uint32_t size)
{
- struct ras_debug_if data;
- int ret;
- int i;
- unsigned long ue, ce, ue_old, ce_old;
+ int i, ret;
+ unsigned long old_ue, old_ce;
+ unsigned long ue, ce;
+ uint32_t block;
+ int timeout;
+ bool pass;
- data.op = 2;
- for (i = 0; i < AMDGPU_RAS_BLOCK__LAST; i++) {
- int timeout = 3;
- struct ras_inject_if inject = {
- .head = {
- .block = i,
- .type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE,
- .sub_block_index = 0,
- .name = "",
- },
- .address = 0,
- .value = 0,
- };
+ for (i = 0; i < size; i++) {
+ timeout = 3;
+ pass = false;
- if (amdgpu_ras_is_feature_enabled(i) <= 0)
- continue;
+ block = amdgpu_ras_find_block_id_by_name(ip_test[i].block);
- if (!((1 << i) & ras_block_mask_inject))
- continue;
+ /* Ensure one valid ip block */
+ if (block == ARRAY_SIZE(ras_block_string))
+ break;
- data.inject = inject;
+ /* Ensure RAS feature for the IP block is enabled by kernel */
+ if (amdgpu_ras_is_feature_supported(block) <= 0)
+ break;
- ret = amdgpu_ras_query_err_count(i, &ue_old, &ce_old);
+ ret = amdgpu_ras_query_err_count(block, &old_ue, &old_ce);
CU_ASSERT_EQUAL(ret, 0);
-
if (ret)
- continue;
+ break;
- ret = amdgpu_ras_invoke(&data);
+ ret = amdgpu_ras_inject(block,
+ ip_test[i].sub_block,
+ ip_test[i].type,
+ ip_test[i].address,
+ ip_test[i].value);
CU_ASSERT_EQUAL(ret, 0);
-
if (ret)
- continue;
+ break;
-loop:
while (timeout > 0) {
- ret = amdgpu_ras_query_err_count(i, &ue, &ce);
- CU_ASSERT_EQUAL(ret, 0);
+ sleep(5);
+ ret = amdgpu_ras_query_err_count(block, &ue, &ce);
+ CU_ASSERT_EQUAL(ret, 0);
if (ret)
- continue;
- if (ue_old != ue) {
- /*recovery takes ~10s*/
- sleep(10);
break;
- }
- sleep(1);
+ if (old_ue != ue || old_ce != ce) {
+ pass = true;
+ sleep(20);
+ break;
+ }
timeout -= 1;
}
-
- CU_ASSERT_EQUAL(ue_old + 1, ue);
- CU_ASSERT_EQUAL(ce_old, ce);
+ printf("\t Test %s@block %s, subblock %d, error_type %s, address %ld, value %ld: %s\n",
+ ip_test[i].name,
+ ip_test[i].block,
+ ip_test[i].sub_block,
+ amdgpu_ras_get_error_type_id(ip_test[i].type),
+ ip_test[i].address,
+ ip_test[i].value,
+ pass ? "Pass" : "Fail");
}
}
+static void __amdgpu_ras_inject_test(void)
+{
+ printf("...\n");
+
+ /* run UMC ras inject test */
+ __amdgpu_ras_ip_inject_test(umc_ras_inject_test,
+ ARRAY_SIZE(umc_ras_inject_test));
+
+ /* run GFX ras inject test */
+ __amdgpu_ras_ip_inject_test(gfx_ras_inject_test,
+ ARRAY_SIZE(gfx_ras_inject_test));
+}
+
static void amdgpu_ras_inject_test(void)
{
int i;