Re: [PATCH 05/20] drm/xe/eudebug: Mark guc contexts as debuggable

[Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>]

On 12/2/2025 5:52 AM, Mika Kuoppala wrote:
> We need to inform to guc which contexts are debuggable
> as their handling is different from ordinary contexts.
>
> v2: void return, use xe_gt_dbg, no need for lrc (Matt)
> v3: add the workaround enabling (Daniele)
> v4: version needed to 70.49.4
> v5: bail out early before registering eq (Daniele)
> v6: export the guc action for future (Mika)
>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Lucas De Marchi <lucas.demarchi@intel.com>
> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
> Cc: Jan Sokolowski <jan.sokolowski@intel.com>
> Signed-off-by: Dominik Grzegorzek <dominik.grzegorzek@intel.com>
> Signed-off-by: Maciej Patelczyk <maciej.patelczyk@intel.com>
> Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
> ---
>   drivers/gpu/drm/xe/abi/guc_actions_abi.h |  5 ++++
>   drivers/gpu/drm/xe/abi/guc_klvs_abi.h    |  1 +
>   drivers/gpu/drm/xe/xe_exec_queue.c       |  5 ++++
>   drivers/gpu/drm/xe/xe_guc.c              | 17 ++++++++++++
>   drivers/gpu/drm/xe/xe_guc.h              |  3 +++
>   drivers/gpu/drm/xe/xe_guc_ads.c          | 17 ++++++++++++
>   drivers/gpu/drm/xe/xe_guc_submit.c       | 34 ++++++++++++++++++++++++
>   drivers/gpu/drm/xe/xe_guc_submit.h       |  1 +
>   drivers/gpu/drm/xe/xe_wa_oob.rules       |  2 ++
>   9 files changed, 85 insertions(+)
>
> diff --git a/drivers/gpu/drm/xe/abi/guc_actions_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
> index 47756e4674a1..32a5f680a6d2 100644
> --- a/drivers/gpu/drm/xe/abi/guc_actions_abi.h
> +++ b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
> @@ -155,6 +155,7 @@ enum xe_guc_action {
>   	XE_GUC_ACTION_NOTIFY_FLUSH_LOG_BUFFER_TO_FILE = 0x8003,
>   	XE_GUC_ACTION_NOTIFY_CRASH_DUMP_POSTED = 0x8004,
>   	XE_GUC_ACTION_NOTIFY_EXCEPTION = 0x8005,
> +	XE_GUC_ACTION_EU_KERNEL_DEBUG = 0x8006,
>   	XE_GUC_ACTION_TEST_G2G_SEND = 0xF001,
>   	XE_GUC_ACTION_TEST_G2G_RECV = 0xF002,
>   	XE_GUC_ACTION_LIMIT
> @@ -278,4 +279,8 @@ enum xe_guc_g2g_type {
>   /* invalid type for XE_GUC_ACTION_NOTIFY_MEMORY_CAT_ERROR */
>   #define XE_GUC_CAT_ERR_TYPE_INVALID 0xdeadbeef
>   
> +enum  xe_guc_eu_kernel_debug_request_type {
> +	XE_GUC_EU_KERNEL_DEBUG_ENABLE = 0x3,
> +};
> +
>   #endif
> diff --git a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
> index 265a135e7061..fba190d4f84b 100644
> --- a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
> +++ b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
> @@ -423,6 +423,7 @@ enum xe_guc_klv_ids {
>   	GUC_WA_KLV_WAKE_POWER_DOMAINS_FOR_OUTBOUND_MMIO					= 0x900a,
>   	GUC_WA_KLV_RESET_BB_STACK_PTR_ON_VF_SWITCH					= 0x900b,
>   	GUC_WA_KLV_RESTORE_UNSAVED_MEDIA_CONTROL_REG					= 0x900c,
> +	GUC_WA_KLV_RESET_DEP_ENGINES_ON_DEBUG_CTX_SWITCH				= 0x900d,
>   };
>   
>   #endif
> diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
> index ddaef00b56ff..e5590c6e3148 100644
> --- a/drivers/gpu/drm/xe/xe_exec_queue.c
> +++ b/drivers/gpu/drm/xe/xe_exec_queue.c
> @@ -17,6 +17,7 @@
>   #include "xe_device.h"
>   #include "xe_gt.h"
>   #include "xe_gt_sriov_vf.h"
> +#include "xe_guc.h"
>   #include "xe_hw_engine_class_sysfs.h"
>   #include "xe_hw_engine_group.h"
>   #include "xe_hw_fence.h"
> @@ -593,6 +594,7 @@ static int exec_queue_set_eudebug(struct xe_device *xe, struct xe_exec_queue *q,
>   				  u64 value)
>   {
>   	const u64 known_flags = DRM_XE_EXEC_QUEUE_EUDEBUG_FLAG_ENABLE;
> +	struct xe_guc *guc = &q->gt->uc.guc;
>   
>   	if (XE_IOCTL_DBG(xe, (q->class != XE_ENGINE_CLASS_RENDER &&
>   			      q->class != XE_ENGINE_CLASS_COMPUTE)))
> @@ -604,6 +606,9 @@ static int exec_queue_set_eudebug(struct xe_device *xe, struct xe_exec_queue *q,
>   	if (XE_IOCTL_DBG(xe, !IS_ENABLED(CONFIG_DRM_XE_EUDEBUG)))
>   		return -EOPNOTSUPP;
>   
> +	if (XE_IOCTL_DBG(xe, !xe_guc_has_debug_contexts(guc)))
> +		return -EOPNOTSUPP;
> +
>   	if (XE_IOCTL_DBG(xe, !xe_exec_queue_is_lr(q)))
>   		return -EINVAL;
>   	/*
> diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
> index 88376bc2a483..ec0d6b5e0693 100644
> --- a/drivers/gpu/drm/xe/xe_guc.c
> +++ b/drivers/gpu/drm/xe/xe_guc.c
> @@ -1744,6 +1744,23 @@ bool xe_guc_using_main_gamctrl_queues(struct xe_guc *guc)
>   	return GT_VER(gt) >= 35;
>   }
>   
> +bool xe_guc_has_debug_contexts(struct xe_guc *guc)
> +{
> +	const struct xe_uc_fw_version required = XE_UC_FW_VERSION_DEBUG_CONTEXTS;
> +	struct xe_uc_fw_version *version = &guc->fw.versions.found[XE_UC_FW_VER_RELEASE];
> +	struct xe_gt *gt = guc_to_gt(guc);
> +
> +	if (MAKE_GUC_VER_STRUCT(*version) < MAKE_GUC_VER_STRUCT(required)) {
> +		xe_gt_info(gt,
> +			   "debug context unsupported in GuC interface v%u.%u.%u, need v%u.%u.%u or higher\n",
> +			   version->major, version->minor, version->patch, required.major,
> +			   required.minor, required.patch);
> +		return false;
> +	}
> +
> +	return true;
> +}
> +
>   #if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST)
>   #include "tests/xe_guc_g2g_test.c"
>   #endif
> diff --git a/drivers/gpu/drm/xe/xe_guc.h b/drivers/gpu/drm/xe/xe_guc.h
> index fdb08658d05a..10e387c72861 100644
> --- a/drivers/gpu/drm/xe/xe_guc.h
> +++ b/drivers/gpu/drm/xe/xe_guc.h
> @@ -23,6 +23,8 @@
>   #define GUC_FIRMWARE_VER(guc) \
>   	MAKE_GUC_VER_STRUCT((guc)->fw.versions.found[XE_UC_FW_VER_RELEASE])
>   
> +#define XE_UC_FW_VERSION_DEBUG_CONTEXTS { .major = 70, .minor = 49, .patch = 4 }
> +
>   struct drm_printer;
>   
>   void xe_guc_comm_init_early(struct xe_guc *guc);
> @@ -55,6 +57,7 @@ void xe_guc_stop(struct xe_guc *guc);
>   int xe_guc_start(struct xe_guc *guc);
>   void xe_guc_declare_wedged(struct xe_guc *guc);
>   bool xe_guc_using_main_gamctrl_queues(struct xe_guc *guc);
> +bool xe_guc_has_debug_contexts(struct xe_guc *guc);
>   
>   #if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST)
>   int xe_guc_g2g_test_notification(struct xe_guc *guc, u32 *payload, u32 len);
> diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c
> index bcb85a1bf26d..f4d1470229f1 100644
> --- a/drivers/gpu/drm/xe/xe_guc_ads.c
> +++ b/drivers/gpu/drm/xe/xe_guc_ads.c
> @@ -363,6 +363,23 @@ static void guc_waklv_init(struct xe_guc_ads *ads)
>   		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
>   				 GUC_WORKAROUND_KLV_DISABLE_PSMI_INTERRUPTS_AT_C6_ENTRY_RESTORE_AT_EXIT);
>   
> +#if IS_ENABLED(CONFIG_DRM_XE_EUDEBUG)
> +	if (XE_GT_WA(gt, 14022766366)) {
> +		if (xe_guc_has_debug_contexts(&gt->uc.guc)) {
> +			guc_waklv_enable(ads, NULL, 0, &offset, &remain,
> +					 GUC_WA_KLV_RESET_DEP_ENGINES_ON_DEBUG_CTX_SWITCH);
> +		} else  {
> +			const struct xe_uc_fw_version required =
> +				XE_UC_FW_VERSION_DEBUG_CONTEXTS;
> +
> +			xe_gt_info(gt, "eudebug needs GuC version %u.%u.%u or greater\n",
> +				   required.major,
> +				   required.minor,
> +				   required.patch);
> +		}
> +	}
> +#endif
> +
>   	size = guc_ads_waklv_size(ads) - remain;
>   	if (!size)
>   		return;
> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
> index 3ca2558c8c96..dd9d567f0a7b 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.c
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.c
> @@ -651,6 +651,37 @@ static void __register_exec_queue(struct xe_guc *guc,
>   	xe_guc_ct_send(&guc->ct, action, ARRAY_SIZE(action), 0, 0);
>   }
>   
> +int xe_guc_action_eu_kernel_debug(struct xe_guc *guc, u32 id, u32 cmd)
> +{
> +	const u32 action[] = {
> +		XE_GUC_ACTION_EU_KERNEL_DEBUG,
> +		id,
> +		cmd,
> +		0, /* reserved */
> +	};
> +
> +	return xe_guc_ct_send(&guc->ct, action,
> +			      ARRAY_SIZE(action), 0, 0);
> +}
> +
> +static void set_eu_kernel_debug(struct xe_exec_queue *q)
> +{
> +	struct xe_guc *guc = exec_queue_to_guc(q);
> +	struct xe_gt *gt = guc_to_gt(guc);
> +	int ret;
> +
> +	ret = xe_guc_action_eu_kernel_debug(guc, q->guc->id,
> +					    XE_GUC_EU_KERNEL_DEBUG_ENABLE);
> +
> +	if (ret)
> +		xe_gt_warn(gt,
> +			   "GuC ctx=%d debug enabling failed with %d",
> +			   q->guc->id, ret);
> +	else
> +		xe_gt_dbg(gt,
> +			  "GuC ctx=%d enabled for debug", q->guc->id);

nit: q->guc->id is unsigned, so maybe use %u?

Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>

Daniele

> +}
> +
>   static void register_exec_queue(struct xe_exec_queue *q, int ctx_type)
>   {
>   	struct xe_guc *guc = exec_queue_to_guc(q);
> @@ -705,6 +736,9 @@ static void register_exec_queue(struct xe_exec_queue *q, int ctx_type)
>   	else
>   		__register_exec_queue(guc, &info);
>   	init_policies(guc, q);
> +
> +	if (xe_exec_queue_is_debuggable(q))
> +		set_eu_kernel_debug(q);
>   }
>   
>   static u32 wq_space_until_wrap(struct xe_exec_queue *q)
> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
> index 100a7891b918..b25bd8f32abf 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.h
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.h
> @@ -50,5 +50,6 @@ void xe_guc_submit_print(struct xe_guc *guc, struct drm_printer *p);
>   void xe_guc_register_vf_exec_queue(struct xe_exec_queue *q, int ctx_type);
>   
>   int xe_guc_contexts_hwsp_rebase(struct xe_guc *guc, void *scratch);
> +int xe_guc_action_eu_kernel_debug(struct xe_guc *guc, u32 id, u32 cmd);
>   
>   #endif
> diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
> index 7ca7258eb5d8..ae6daa50eaf1 100644
> --- a/drivers/gpu/drm/xe/xe_wa_oob.rules
> +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
> @@ -77,3 +77,5 @@
>   15015404425_disable	PLATFORM(PANTHERLAKE), MEDIA_STEP(B0, FOREVER)
>   16026007364    MEDIA_VERSION(3000)
>   14020316580    MEDIA_VERSION(1301)
> +14022766366	GRAPHICS_VERSION_RANGE(2001, 2004)
> +		GRAPHICS_VERSION_RANGE(3000, 3005)