[PATCH 1/2] drm/xe/guc_pc: Do not stop probe or resume if GuC PC fails

[Belgaumkar, Vinay]

On 2/11/2025 12:09 PM, Rodrigo Vivi wrote:
> In a rare situation of thermal limit during resume, GuC can
> be slow and run into delays like this:
>
> xe 0000:00:02.0: [drm] GT1: excessive init time: 667ms! \
>     		 [status = 0x8002F034, timeouts = 0]
> xe 0000:00:02.0: [drm] GT1: excessive init time: \
>     		 [freq = 100MHz (req = 800MHz), before = 100MHz, \
>     		 perf_limit_reasons = 0x1C001000]
> xe 0000:00:02.0: [drm] *ERROR* GT1: GuC PC Start failed
> ------------[ cut here ]------------
> xe 0000:00:02.0: [drm] GT1: Failed to start GuC PC: -EIO
>
> If this happens, this can block entirely the GPU to be used.
> However, GPU can still be used, although the GT frequencies might be
> messed up.
>
> Let's report the error, but not block the flow.

Can we expect other random CI failures due to this? If GT is not getting 
expected frequencies, certain tests which rely on this will likely fail, 
causing a bunch of noise. Is that worse than driver load failing in this 
case?

Thanks,

Vinay.

> But, instead of just giving up and moving on, let's re-attempt a wait
> with a very long second timeout.
>
> v2: Keep the precision comment (Jonathan)
>      Use a define for the regular SLPC reset timeout.
>
> Cc: Vinay Belgaumkar <vinay.belgaumkar at intel.com>
> Reviewed-by: Jonathan Cavitt <jonathan.cavitt at intel.com>
> Signed-off-by: Rodrigo Vivi <rodrigo.vivi at intel.com>
> ---
>   drivers/gpu/drm/xe/xe_guc_pc.c | 26 ++++++++++++++++++--------
>   1 file changed, 18 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
> index 02409eedb914..3b04b62937eb 100644
> --- a/drivers/gpu/drm/xe/xe_guc_pc.c
> +++ b/drivers/gpu/drm/xe/xe_guc_pc.c
> @@ -50,6 +50,8 @@
>   #define LNL_MERT_FREQ_CAP	800
>   #define BMG_MERT_FREQ_CAP	2133
>   
> +#define SLPC_RESET_TIMEOUT_MS 5 /* rought 5ms, but no need for precision */
> +
>   /**
>    * DOC: GuC Power Conservation (PC)
>    *
> @@ -114,9 +116,10 @@ static struct iosys_map *pc_to_maps(struct xe_guc_pc *pc)
>   	 FIELD_PREP(HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ARGC, count))
>   
>   static int wait_for_pc_state(struct xe_guc_pc *pc,
> -			     enum slpc_global_state state)
> +			     enum slpc_global_state state,
> +			     int timeout_ms)
>   {
> -	int timeout_us = 5000; /* rought 5ms, but no need for precision */
> +	int timeout_us = 1000 * timeout_ms;
>   	int slept, wait = 10;
>   
>   	xe_device_assert_mem_access(pc_to_xe(pc));
> @@ -165,7 +168,8 @@ static int pc_action_query_task_state(struct xe_guc_pc *pc)
>   	};
>   	int ret;
>   
> -	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING))
> +	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING,
> +			      SLPC_RESET_TIMEOUT_MS))
>   		return -EAGAIN;
>   
>   	/* Blocking here to ensure the results are ready before reading them */
> @@ -188,7 +192,8 @@ static int pc_action_set_param(struct xe_guc_pc *pc, u8 id, u32 value)
>   	};
>   	int ret;
>   
> -	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING))
> +	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING,
> +			      SLPC_RESET_TIMEOUT_MS))
>   		return -EAGAIN;
>   
>   	ret = xe_guc_ct_send(ct, action, ARRAY_SIZE(action), 0, 0);
> @@ -209,7 +214,8 @@ static int pc_action_unset_param(struct xe_guc_pc *pc, u8 id)
>   	struct xe_guc_ct *ct = &pc_to_guc(pc)->ct;
>   	int ret;
>   
> -	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING))
> +	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING,
> +			      SLPC_RESET_TIMEOUT_MS))
>   		return -EAGAIN;
>   
>   	ret = xe_guc_ct_send(ct, action, ARRAY_SIZE(action), 0, 0);
> @@ -1033,9 +1039,13 @@ int xe_guc_pc_start(struct xe_guc_pc *pc)
>   	if (ret)
>   		goto out;
>   
> -	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING)) {
> -		xe_gt_err(gt, "GuC PC Start failed\n");
> -		ret = -EIO;
> +	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING,
> +			      SLPC_RESET_TIMEOUT_MS)) {
> +		xe_gt_warn(gt, "GuC PC Start taking longer than expected\n");
> +		if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING, 1000))
> +			xe_gt_err(gt, "GuC PC Start failed\n");
> +		/* Although GuC PC failed, do not block the usage of GPU */
> +		ret = 0;
>   		goto out;
>   	}
>