bybrooklyn/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-04-18 14:53:58 -04:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: add ras event id support

Browse Source 
add amdgpu ras event id support to better distinguish different
error information sources in dmesg logs.

the following log will be identify by event id:
{event_id} interrupt to inform RAS event
{event_id} ACA logs
{event_id} errors statistic since from current injection/error query
{event_id} errors statistic since from gpu load

Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Yang Wang
2024-03-13 12:50:43 +08:00
committed by Alex Deucher
parent d5586e2f53
commit 9dc57c2adf
6 changed files with 195 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
View File

@@ -210,22 +210,26 @@ int amdgpu_mca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable)
return -EOPNOTSUPP;
}
static void amdgpu_mca_smu_mca_bank_dump(struct amdgpu_device *adev, int idx, struct mca_bank_entry *entry)
static void amdgpu_mca_smu_mca_bank_dump(struct amdgpu_device *adev, int idx, struct mca_bank_entry *entry,
struct ras_query_context *qctx)
{
dev_info(adev->dev, HW_ERR "Accelerator Check Architecture events logged\n");
dev_info(adev->dev, HW_ERR "aca entry[%02d].STATUS=0x%016llx\n",
idx, entry->regs[MCA_REG_IDX_STATUS]);
dev_info(adev->dev, HW_ERR "aca entry[%02d].ADDR=0x%016llx\n",
idx, entry->regs[MCA_REG_IDX_ADDR]);
dev_info(adev->dev, HW_ERR "aca entry[%02d].MISC0=0x%016llx\n",
idx, entry->regs[MCA_REG_IDX_MISC0]);
dev_info(adev->dev, HW_ERR "aca entry[%02d].IPID=0x%016llx\n",
idx, entry->regs[MCA_REG_IDX_IPID]);
dev_info(adev->dev, HW_ERR "aca entry[%02d].SYND=0x%016llx\n",
idx, entry->regs[MCA_REG_IDX_SYND]);
u64 event_id = qctx->event_id;
RAS_EVENT_LOG(adev, event_id, HW_ERR "Accelerator Check Architecture events logged\n");
RAS_EVENT_LOG(adev, event_id, HW_ERR "aca entry[%02d].STATUS=0x%016llx\n",
idx, entry->regs[MCA_REG_IDX_STATUS]);
RAS_EVENT_LOG(adev, event_id, HW_ERR "aca entry[%02d].ADDR=0x%016llx\n",
idx, entry->regs[MCA_REG_IDX_ADDR]);
RAS_EVENT_LOG(adev, event_id, HW_ERR "aca entry[%02d].MISC0=0x%016llx\n",
idx, entry->regs[MCA_REG_IDX_MISC0]);
RAS_EVENT_LOG(adev, event_id, HW_ERR "aca entry[%02d].IPID=0x%016llx\n",
idx, entry->regs[MCA_REG_IDX_IPID]);
RAS_EVENT_LOG(adev, event_id, HW_ERR "aca entry[%02d].SYND=0x%016llx\n",
idx, entry->regs[MCA_REG_IDX_SYND]);
}
int amdgpu_mca_smu_log_ras_error(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type, struct ras_err_data *err_data)
int amdgpu_mca_smu_log_ras_error(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type,
struct ras_err_data *err_data, struct ras_query_context *qctx)
{
struct amdgpu_smuio_mcm_config_info mcm_info;
struct ras_err_addr err_addr = {0};
@@ -244,7 +248,7 @@ int amdgpu_mca_smu_log_ras_error(struct amdgpu_device *adev, enum amdgpu_ras_blo
list_for_each_entry(node, &mca_set.list, node) {
entry = &node->entry;
amdgpu_mca_smu_mca_bank_dump(adev, i++, entry);
amdgpu_mca_smu_mca_bank_dump(adev, i++, entry, qctx);
count = 0;
ret = amdgpu_mca_smu_parse_mca_error_count(adev, blk, type, entry, &count);