Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Zhanjun Dong <zhanjun.dong@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: daniele.ceraolospurio@intel.com, Zhanjun Dong <zhanjun.dong@intel.com>
Subject: [PATCH v4 1/2] drm/xe/guc: Handle GuC local uncorrectable error notifications
Date: Mon, 29 Jun 2026 10:08:35 -0400	[thread overview]
Message-ID: <20260629140836.2074349-2-zhanjun.dong@intel.com> (raw)
In-Reply-To: <20260629140836.2074349-1-zhanjun.dong@intel.com>

Add support for the GuC uncorrectable local error G2H notification and
opt in to the feature when the submission ABI exposes it.

When the notification targets a known exec queue, treat it like an
engine reset request and route it through the existing timeout cleanup
path. This keeps the queue teardown, pending job cancellation and error
capture in one place instead of open-coding a parallel recovery flow.

Signed-off-by: Zhanjun Dong <zhanjun.dong@intel.com>

---
History:
v3: Remove not used flag bit and timeout worker check (Daniele)
    Remove wedged mode==2 check, which will be handled in separate patch(Daniele)
v2: Opt in for Xe3p only, excluding media GTs on NovaLake-P which don't support the feature
    Remove timeout bypass, which is outside the scope of this patch and can be added separately
---
 drivers/gpu/drm/xe/abi/guc_actions_abi.h |  1 +
 drivers/gpu/drm/xe/abi/guc_klvs_abi.h    |  8 ++++++
 drivers/gpu/drm/xe/xe_guc.c              | 10 +++++++
 drivers/gpu/drm/xe/xe_guc_ct.c           |  3 +++
 drivers/gpu/drm/xe/xe_guc_submit.c       | 33 ++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_guc_submit.h       |  1 +
 drivers/gpu/drm/xe/xe_trace.h            |  5 ++++
 7 files changed, 61 insertions(+)

diff --git a/drivers/gpu/drm/xe/abi/guc_actions_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
index 83a6e7794982..f5c9b37038d4 100644
--- a/drivers/gpu/drm/xe/abi/guc_actions_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
@@ -152,6 +152,7 @@ enum xe_guc_action {
 	XE_GUC_ACTION_REPORT_PAGE_FAULT_REQ_DESC = 0x6002,
 	XE_GUC_ACTION_PAGE_FAULT_RES_DESC = 0x6003,
 	XE_GUC_ACTION_ACCESS_COUNTER_NOTIFY = 0x6004,
+	XE_GUC_ACTION_NOTIFY_UNCORRECTABLE_LOCAL_ERROR = 0x6005,
 	XE_GUC_ACTION_TLB_INVALIDATION = 0x7000,
 	XE_GUC_ACTION_TLB_INVALIDATION_DONE = 0x7001,
 	XE_GUC_ACTION_TLB_INVALIDATION_ALL = 0x7002,
diff --git a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
index 644f5a4226d7..5c428f02a642 100644
--- a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
@@ -154,6 +154,11 @@ enum  {
  *      (instead of waiting the full timeslice duration). The bit is instead set
  *      to one if a single context is queued on the engine, to avoid it being
  *      switched out if there isn't another context that can run in its place.
+ *
+ * _`GUC_KLV_OPT_IN_FEATURE_UNCORRECTABLE_LOCAL_ERROR_NOTIFICATION` : 0x4004
+ *      This flag will enable notification from GuC to KMD via G2H message
+ *      GUC_ACTION_GUC2HOST_NOTIFY_UNCORRECTABLE_LOCAL_ERROR upon receiving the
+ *      same interrupt from the CS.
  */
 
 #define GUC_KLV_OPT_IN_FEATURE_EXT_CAT_ERR_TYPE_KEY 0x4001
@@ -162,6 +167,9 @@ enum  {
 #define GUC_KLV_OPT_IN_FEATURE_DYNAMIC_INHIBIT_CONTEXT_SWITCH_KEY 0x4003
 #define GUC_KLV_OPT_IN_FEATURE_DYNAMIC_INHIBIT_CONTEXT_SWITCH_LEN 0u
 
+#define GUC_KLV_OPT_IN_FEATURE_UNCORRECTABLE_LOCAL_ERROR_NOTIFICATION_KEY 0x4004
+#define GUC_KLV_OPT_IN_FEATURE_UNCORRECTABLE_LOCAL_ERROR_NOTIFICATION_LEN 0u
+
 /**
  * DOC: GuC Scheduling Policies KLVs
  *
diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index 4023700ff2a9..03a694a8a014 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -12,6 +12,7 @@
 
 #include "abi/guc_actions_abi.h"
 #include "abi/guc_errors_abi.h"
+#include "abi/guc_klvs_abi.h"
 #include "regs/xe_gt_regs.h"
 #include "regs/xe_gtt_defs.h"
 #include "regs/xe_guc_regs.h"
@@ -641,6 +642,15 @@ int xe_guc_opt_in_features_enable(struct xe_guc *guc)
 	if (GUC_SUBMIT_VER(guc) >= MAKE_GUC_VER(1, 7, 0))
 		klvs[count++] = PREP_GUC_KLV_TAG(OPT_IN_FEATURE_EXT_CAT_ERR_TYPE);
 
+	/*
+	 * The uncorrectable local error notification opt-in was added in
+	 * GuC v70.38.0, which maps to compatibility version v1.18.0.
+	 */
+	if (GRAPHICS_VER(xe) >= 35 && GUC_SUBMIT_VER(guc) >= MAKE_GUC_VER(1, 18, 0) &&
+	    !(xe->info.platform == XE_NOVALAKE_P && xe_gt_is_media_type(guc_to_gt(guc))))
+		klvs[count++] =
+			PREP_GUC_KLV_TAG(OPT_IN_FEATURE_UNCORRECTABLE_LOCAL_ERROR_NOTIFICATION);
+
 	if (supports_dynamic_ics(guc))
 		klvs[count++] = PREP_GUC_KLV_TAG(OPT_IN_FEATURE_DYNAMIC_INHIBIT_CONTEXT_SWITCH);
 
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 21e0dad9a481..fe6a55fe7fb5 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -1661,6 +1661,9 @@ static int process_g2h_msg(struct xe_guc_ct *ct, u32 *msg, u32 len)
 		ret = xe_guc_exec_queue_memory_cat_error_handler(guc, payload,
 								 adj_len);
 		break;
+	case XE_GUC_ACTION_NOTIFY_UNCORRECTABLE_LOCAL_ERROR:
+		ret = xe_guc_uncorrectable_error_handler(guc, payload, adj_len);
+		break;
 	case XE_GUC_ACTION_REPORT_PAGE_FAULT_REQ_DESC:
 		ret = xe_guc_pagefault_handler(guc, payload, adj_len);
 		break;
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index b29cc08e6291..29ccabc4b7a4 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -9,6 +9,7 @@
 #include <linux/bitmap.h>
 #include <linux/circ_buf.h>
 #include <linux/dma-fence-array.h>
+#include <linux/workqueue.h>
 
 #include <drm/drm_managed.h>
 
@@ -2997,6 +2998,38 @@ int xe_guc_exec_queue_memory_cat_error_handler(struct xe_guc *guc, u32 *msg,
 	return 0;
 }
 
+int xe_guc_uncorrectable_error_handler(struct xe_guc *guc, u32 *msg, u32 len)
+{
+	struct xe_gt *gt = guc_to_gt(guc);
+	struct xe_exec_queue *q;
+	u32 guc_id;
+
+	if (unlikely(!len || len > 2))
+		return -EPROTO;
+
+	guc_id = msg[0];
+
+	if (guc_id == GUC_ID_UNKNOWN) {
+		xe_gt_err(gt, "GuC: Uncorrectable local error! guc_id=%d\n", guc_id);
+		return 0;
+	}
+
+	q = g2h_exec_queue_lookup(guc, guc_id);
+	if (unlikely(!q))
+		return -EPROTO;
+
+	xe_gt_err(gt,
+		  "GuC: Uncorrectable local error! guc_id=%d class=%s, logical_mask=0x%x",
+		  guc_id, xe_hw_engine_class_to_str(q->class), q->logical_mask);
+
+	trace_xe_guc_uncorrectable_error(q);
+
+	/* Treat the same as engine reset */
+	xe_guc_exec_queue_reset_trigger_cleanup(q);
+
+	return 0;
+}
+
 int xe_guc_exec_queue_reset_failure_handler(struct xe_guc *guc, u32 *msg, u32 len)
 {
 	struct xe_gt *gt = guc_to_gt(guc);
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
index b3839a90c142..ccade320dc69 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.h
+++ b/drivers/gpu/drm/xe/xe_guc_submit.h
@@ -34,6 +34,7 @@ int xe_guc_deregister_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
 int xe_guc_exec_queue_reset_handler(struct xe_guc *guc, u32 *msg, u32 len);
 int xe_guc_exec_queue_memory_cat_error_handler(struct xe_guc *guc, u32 *msg,
 					       u32 len);
+int xe_guc_uncorrectable_error_handler(struct xe_guc *guc, u32 *msg, u32 len);
 int xe_guc_exec_queue_reset_failure_handler(struct xe_guc *guc, u32 *msg, u32 len);
 int xe_guc_error_capture_handler(struct xe_guc *guc, u32 *msg, u32 len);
 int xe_guc_exec_queue_cgp_sync_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
index 750fa32c13b2..2fe8f89a1e34 100644
--- a/drivers/gpu/drm/xe/xe_trace.h
+++ b/drivers/gpu/drm/xe/xe_trace.h
@@ -213,6 +213,11 @@ DEFINE_EVENT(xe_exec_queue, xe_exec_queue_memory_cat_error,
 	     TP_ARGS(q)
 );
 
+DEFINE_EVENT(xe_exec_queue, xe_guc_uncorrectable_error,
+	     TP_PROTO(struct xe_exec_queue *q),
+	     TP_ARGS(q)
+);
+
 DEFINE_EVENT(xe_exec_queue, xe_exec_queue_cgp_context_error,
 	     TP_PROTO(struct xe_exec_queue *q),
 	     TP_ARGS(q)
-- 
2.34.1


  reply	other threads:[~2026-06-29 14:08 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-29 14:08 [PATCH v4 0/2] drm/xe/guc: Handle GuC local uncorrectable error notifications Zhanjun Dong
2026-06-29 14:08 ` Zhanjun Dong [this message]
2026-06-29 14:08 ` [PATCH v4 2/2] drm/xe/guc: Preserve HW error state in wedged mode 2 Zhanjun Dong
2026-06-29 23:31   ` Daniele Ceraolo Spurio
2026-06-30 19:27     ` Dong, Zhanjun
2026-06-30  0:52 ` ✓ CI.KUnit: success for drm/xe/guc: Handle GuC local uncorrectable error notifications Patchwork
2026-06-30  1:36 ` ✓ Xe.CI.BAT: " Patchwork
2026-06-30 13:58 ` ✓ Xe.CI.FULL: " Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260629140836.2074349-2-zhanjun.dong@intel.com \
    --to=zhanjun.dong@intel.com \
    --cc=daniele.ceraolospurio@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox