drm/amdgpu: Check gmc requirement for reset on init

Add a callback to check if there is any condition detected by GMC block
for reset on init. One case is if a pending NPS change request is
detected. If reset is done because of NPS switch, refresh NPS info from
discovery table.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Lijo Lazar 2024-09-20 14:17:30 +05:30 committed by Alex Deucher
parent ee52489d12
commit ed3dac4bf9
3 changed files with 19 additions and 1 deletions

View file

@ -1249,12 +1249,15 @@ int amdgpu_gmc_get_nps_memranges(struct amdgpu_device *adev,
struct amdgpu_gmc_memrange *ranges;
int range_cnt, ret, i, j;
uint32_t nps_type;
bool refresh;
if (!mem_ranges)
return -EINVAL;
refresh = (adev->init_lvl->level != AMDGPU_INIT_LEVEL_MINIMAL_XGMI) &&
(adev->gmc.reset_flags & AMDGPU_GMC_INIT_RESET_NPS);
ret = amdgpu_discovery_get_nps_info(adev, &nps_type, &ranges,
&range_cnt, false);
&range_cnt, refresh);
if (ret)
return ret;
@ -1380,3 +1383,11 @@ void amdgpu_gmc_prepare_nps_mode_change(struct amdgpu_device *adev)
adev->dev,
"NPS mode change request done, reload driver to complete the change\n");
}
bool amdgpu_gmc_need_reset_on_init(struct amdgpu_device *adev)
{
if (adev->gmc.gmc_funcs->need_reset_on_init)
return adev->gmc.gmc_funcs->need_reset_on_init(adev);
return false;
}

View file

@ -78,6 +78,8 @@ enum amdgpu_memory_partition {
BIT(AMDGPU_NPS3_PARTITION_MODE) | BIT(AMDGPU_NPS4_PARTITION_MODE) | \
BIT(AMDGPU_NPS6_PARTITION_MODE) | BIT(AMDGPU_NPS8_PARTITION_MODE))
#define AMDGPU_GMC_INIT_RESET_NPS BIT(0)
/*
* GMC page fault information
*/
@ -169,6 +171,7 @@ struct amdgpu_gmc_funcs {
/* Request NPS mode */
int (*request_mem_partition_mode)(struct amdgpu_device *adev,
int nps_mode);
bool (*need_reset_on_init)(struct amdgpu_device *adev);
};
struct amdgpu_xgmi_ras {
@ -314,6 +317,7 @@ struct amdgpu_gmc {
const struct amdgpu_gmc_funcs *gmc_funcs;
enum amdgpu_memory_partition requested_nps_mode;
uint32_t supported_nps_modes;
uint32_t reset_flags;
struct amdgpu_xgmi xgmi;
struct amdgpu_irq_src ecc_irq;
@ -467,5 +471,6 @@ int amdgpu_gmc_get_nps_memranges(struct amdgpu_device *adev,
int amdgpu_gmc_request_memory_partition(struct amdgpu_device *adev,
int nps_mode);
void amdgpu_gmc_prepare_nps_mode_change(struct amdgpu_device *adev);
bool amdgpu_gmc_need_reset_on_init(struct amdgpu_device *adev);
#endif

View file

@ -831,6 +831,8 @@ static bool soc15_need_reset_on_init(struct amdgpu_device *adev)
if (adev->asic_type == CHIP_RENOIR)
return true;
if (amdgpu_gmc_need_reset_on_init(adev))
return true;
if (amdgpu_psp_tos_reload_needed(adev))
return true;
/* Just return false for soc15 GPUs. Reset does not seem to