diff options
| author | Stanley.Yang <Stanley.Yang@amd.com> | 2020-09-15 16:15:05 +0800 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2020-09-22 17:37:38 -0400 |
| commit | 3f975d0f71d384825f47c3598d1d5358e40a57f5 (patch) | |
| tree | 1daf6289c4aa95790897b0cf2ba2b450708b06a2 /drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c | |
| parent | d117413f5e1be245b7b3e0cd6afda402609b2572 (diff) | |
drm/amdgpu: update athub interrupt harvesting handle
GCEA/MMHUB EA error should not result to DF freeze, this is
fixed in next generation, but for some reasons the GCEA/MMHUB
EA error will result to DF freeze in previous generation,
diver should avoid to indicate GCEA/MMHUB EA error as hw fatal
error in kernel message by read GCEA/MMHUB err status registers.
Changed from V1:
make query_ras_error_status function more general
make read mmhub er status register more friendly
Changed from V2:
move ras error status query function into do_recovery workqueue
Changed from V3:
remove useless code from V2, print GCEA error status
instance number
Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c | 29 |
1 files changed, 29 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c index 6c6ad529c65c..c2ef8142136e 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c @@ -1624,6 +1624,34 @@ static void mmhub_v9_4_reset_ras_error_count(struct amdgpu_device *adev) } } +static const struct soc15_reg_entry mmhub_v9_4_err_status_regs[] = { + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_ERR_STATUS), 0, 0, 0 }, + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_ERR_STATUS), 0, 0, 0 }, + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA2_ERR_STATUS), 0, 0, 0 }, + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA3_ERR_STATUS), 0, 0, 0 }, + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA4_ERR_STATUS), 0, 0, 0 }, + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA5_ERR_STATUS), 0, 0, 0 }, + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA6_ERR_STATUS), 0, 0, 0 }, + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA7_ERR_STATUS), 0, 0, 0 }, +}; + +static void mmhub_v9_4_query_ras_error_status(struct amdgpu_device *adev) +{ + int i; + uint32_t reg_value; + + if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__MMHUB)) + return; + + for (i = 0; i < ARRAY_SIZE(mmhub_v9_4_err_status_regs); i++) { + reg_value = + RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v9_4_err_status_regs[i])); + if (reg_value) + dev_warn(adev->dev, "MMHUB EA err detected at instance: %d, status: 0x%x!\n", + i, reg_value); + } +} + const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs = { .ras_late_init = amdgpu_mmhub_ras_late_init, .query_ras_error_count = mmhub_v9_4_query_ras_error_count, @@ -1636,4 +1664,5 @@ const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs = { .set_clockgating = mmhub_v9_4_set_clockgating, .get_clockgating = mmhub_v9_4_get_clockgating, .setup_vm_pt_regs = mmhub_v9_4_setup_vm_pt_regs, + .query_ras_error_status = mmhub_v9_4_query_ras_error_status, }; |