Re: [PATCH] drm/xe/guc: suppress GuC error logs when device is wedged

["Anirban, Sk" <sk.anirban@intel.com>]

Hi,

On 21-04-2026 01:21 am, Summers, Stuart wrote:
> On Mon, 2026-04-20 at 16:59 +0530, Sk Anirban wrote:
>> When the device is wedged, GuC CT sends return -ECANCELED. This is
>> expected behavior, not an actionable error. Avoid logging these as
>> errors in the engine activity and power profile code paths.
>>
>> Signed-off-by: Sk Anirban <sk.anirban@intel.com>
>> ---
>>   drivers/gpu/drm/xe/xe_guc_engine_activity.c | 8 +++++---
>>   drivers/gpu/drm/xe/xe_guc_engine_activity.h | 2 +-
>>   drivers/gpu/drm/xe/xe_guc_pc.c              | 4 ++--
>>   drivers/gpu/drm/xe/xe_uc.c                  | 5 ++++-
>>   4 files changed, 12 insertions(+), 7 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/xe/xe_guc_engine_activity.c
>> b/drivers/gpu/drm/xe/xe_guc_engine_activity.c
>> index 2b99c1ebdd58..700f3464fb63 100644
>> --- a/drivers/gpu/drm/xe/xe_guc_engine_activity.c
>> +++ b/drivers/gpu/drm/xe/xe_guc_engine_activity.c
>> @@ -464,18 +464,20 @@ int
>> xe_guc_engine_activity_function_stats(struct xe_guc *guc, int
>> num_vfs, bool
>>    *
>>    * Enable engine activity stats and set initial timestamps
>>    */
>> -void xe_guc_engine_activity_enable_stats(struct xe_guc *guc)
>> +int xe_guc_engine_activity_enable_stats(struct xe_guc *guc)
>>   {
>>          int ret;
>>   
>>          if (!xe_guc_engine_activity_supported(guc))
>> -               return;
>> +               return 0;
>>   
>>          ret = enable_engine_activity_stats(guc);
>> -       if (ret)
>> +       if (ret && !(xe_device_wedged(guc_to_xe(guc)) && ret == -
>> ECANCELED))
> Is there a reason we don't handle all of the cases described in
> __guc_ct_send_locked()? It looks like before we do the ct->state ==
> STOPPED check (which is where we'd return -ECANCELED), we also check if
> the CT is broken (i.e. we got some bad return value from GuC and marked
> CT as "dead", hence returning -EPIPE here) or disabled (and return -
> ENODEV).
>
> Same question for the other cases you have below.
>
> Thanks,
> Stuart
-ECANCELED is the specific error returned when the CT is stopped & 
device is wedged.
Other errors may indicate different fault conditions and imo should be 
useful to log those.

This follows the same pattern as pc_action_reset.

Thanks,

Anirban

>
>>                  xe_gt_err(guc_to_gt(guc), "failed to enable activity
>> stats%d\n", ret);
>>          else
>>                  engine_activity_set_cpu_ts(guc, 0);
>> +
>> +       return ret;
>>   }
>>   
>>   static void engine_activity_fini(void *arg)
>> diff --git a/drivers/gpu/drm/xe/xe_guc_engine_activity.h
>> b/drivers/gpu/drm/xe/xe_guc_engine_activity.h
>> index b32926c2d208..188f325a462d 100644
>> --- a/drivers/gpu/drm/xe/xe_guc_engine_activity.h
>> +++ b/drivers/gpu/drm/xe/xe_guc_engine_activity.h
>> @@ -13,7 +13,7 @@ struct xe_guc;
>>   
>>   int xe_guc_engine_activity_init(struct xe_guc *guc);
>>   bool xe_guc_engine_activity_supported(struct xe_guc *guc);
>> -void xe_guc_engine_activity_enable_stats(struct xe_guc *guc);
>> +int xe_guc_engine_activity_enable_stats(struct xe_guc *guc);
>>   int xe_guc_engine_activity_function_stats(struct xe_guc *guc, int
>> num_vfs, bool enable);
>>   u64 xe_guc_engine_activity_active_ticks(struct xe_guc *guc, struct
>> xe_hw_engine *hwe,
>>                                          unsigned int fn_id);
>> diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c
>> b/drivers/gpu/drm/xe/xe_guc_pc.c
>> index 7ecd91ad6192..efcd432ef6ef 100644
>> --- a/drivers/gpu/drm/xe/xe_guc_pc.c
>> +++ b/drivers/gpu/drm/xe/xe_guc_pc.c
>> @@ -1202,7 +1202,7 @@ int xe_guc_pc_set_power_profile(struct
>> xe_guc_pc *pc, const char *buf)
>>          ret = pc_action_set_param(pc,
>>                                    SLPC_PARAM_POWER_PROFILE,
>>                                    val);
>> -       if (ret)
>> +       if (ret && !(xe_device_wedged(pc_to_xe(pc)) && ret == -
>> ECANCELED))
>>                  xe_gt_err_once(pc_to_gt(pc), "Failed to set power
>> profile to %d: %pe\n",
>>                                 val, ERR_PTR(ret));
>>          else
>> @@ -1306,7 +1306,7 @@ int xe_guc_pc_start(struct xe_guc_pc *pc)
>>   
>>          /* Set cached value of power_profile */
>>          ret = xe_guc_pc_set_power_profile(pc,
>> power_profile_to_string(pc));
>> -       if (unlikely(ret))
>> +       if (ret && !(xe_device_wedged(xe) && ret == -ECANCELED))
>>                  xe_gt_err(gt, "Failed to set SLPC power profile:
>> %pe\n", ERR_PTR(ret));
>>   
>>          return ret;
>> diff --git a/drivers/gpu/drm/xe/xe_uc.c b/drivers/gpu/drm/xe/xe_uc.c
>> index 75091bde0d50..b440cf8c431d 100644
>> --- a/drivers/gpu/drm/xe/xe_uc.c
>> +++ b/drivers/gpu/drm/xe/xe_uc.c
>> @@ -215,7 +215,10 @@ int xe_uc_load_hw(struct xe_uc *uc)
>>          if (ret)
>>                  return ret;
>>   
>> -       xe_guc_engine_activity_enable_stats(&uc->guc);
>> +       ret = xe_guc_engine_activity_enable_stats(&uc->guc);
>> +
>> +       if (xe_device_wedged(guc_to_xe(&uc->guc)) && ret == -
>> ECANCELED)
>> +               return ret;
>>   
>>          /* We don't fail the driver load if HuC fails to auth */
>>          ret = xe_huc_auth(&uc->huc, XE_HUC_AUTH_VIA_GUC);