[PATCH v2 2/7] drm/xe/devcoredump: Add GuC register snapshot to devcoredump

[Nareshkumar Gollakoti <naresh.kumar.g@intel.com>]

Add support for capturing GuC register state as part of the xe
devcoredump snapshot.

Define a dedicated GuC register snapshot structure, record selected
GT and media GuC status/error registers during devcoredump capture,
and free the snapshot during teardown.

Keeping these register values in the devcoredump helps with
post-mortem analysis of GuC-related failures.

v2:(Sashiko)
- Reuse the generic target GT snapshot helper for GuC register capture
- Capture primary and media GuC registers using correct GT MMIO context
- Avoid reading the same on SR-IOV VF
- skip reading media GT GuC registers when media is not present
- drop hardcoded media register address macros

Signed-off-by: Nareshkumar Gollakoti <naresh.kumar.g@intel.com>
---
 drivers/gpu/drm/xe/regs/xe_guc_regs.h     |  5 ++
 drivers/gpu/drm/xe/xe_devcoredump.c       | 58 +++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_devcoredump_types.h |  5 ++
 3 files changed, 68 insertions(+)

diff --git a/drivers/gpu/drm/xe/regs/xe_guc_regs.h b/drivers/gpu/drm/xe/regs/xe_guc_regs.h
index 5faac8316b66..c13ee6e21e37 100644
--- a/drivers/gpu/drm/xe/regs/xe_guc_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_guc_regs.h
@@ -150,6 +150,11 @@
 #define GUC_INTR_SW_INT_1			REG_BIT(1)
 #define GUC_INTR_SW_INT_0			REG_BIT(0)
 
+#define GUC_DEVICEID				XE_REG(0xc008)
+#define GUC_SHIM_ERR_TRAP			XE_REG(0xc070)
+#define GUC_HW_FATL_ERR				XE_REG(0xc598)
+#define GUC_HW_NOTIFY_ERR			XE_REG(0xc59c)
+
 #define GUC_NUM_DOORBELLS			256
 
 /* format of the HW-monitored doorbell cacheline */
diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
index e5c33bc94103..62b1158b89a5 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.c
+++ b/drivers/gpu/drm/xe/xe_devcoredump.c
@@ -27,6 +27,7 @@
 #include "xe_vm.h"
 #include "xe_mmio.h"
 #include "regs/xe_gt_regs.h"
+#include "regs/xe_guc_regs.h"
 
 /**
  * DOC: Xe device coredump
@@ -86,6 +87,16 @@ struct xe_reg_desc {
 
 #define XE_REG_DESC(_reg, _name)	{ .reg = (_reg), .name = (_name) }
 
+static const struct xe_reg_desc xe3p_gt_guc_reglist[] = {
+	XE_REG_DESC(GUC_STATUS,	"GUC_STATUS"),
+	XE_REG_DESC(GUC_WOPCM_SIZE,	"GUC_WOPCM_SIZE"),
+	XE_REG_DESC(GUC_DEVICEID,	"GUC_DEVICEID"),
+	XE_REG_DESC(DMA_CTRL,	"DMA_CTRL"),
+	XE_REG_DESC(GUC_HW_FATL_ERR,	"GUC_HW_FATL_ERR"),
+	XE_REG_DESC(GUC_HW_NOTIFY_ERR,	"GUC_HW_NOTIFY_ERR"),
+	XE_REG_DESC(GUC_SHIM_ERR_TRAP,	"GUC_SHIM_ERR_TRAP"),
+};
+
 static const struct xe_reg_desc xe3p_gt_fuse_reglist[] = {
 	XE_REG_DESC(XELP_GT_GEOMETRY_DSS_ENABLE, "GT_GEOMETRY_DSS_ENABLE"),
 	XE_REG_DESC(XEHP_GT_COMPUTE_DSS_ENABLE, "GT_COMPUTE_DSS_ENABLE"),
@@ -161,6 +172,17 @@ static const struct xe_gt_regset xe_rpm_regset = {
 	},
 };
 
+static const struct xe_gt_regset xe_guc_regset = {
+	.gt[XE_GT_TYPE_MAIN] = {
+		.regs = xe3p_gt_guc_reglist,
+		.num_regs = ARRAY_SIZE(xe3p_gt_guc_reglist),
+	},
+	.gt[XE_GT_TYPE_MEDIA] = {
+		.regs = xe3p_gt_guc_reglist,
+		.num_regs = ARRAY_SIZE(xe3p_gt_guc_reglist),
+	},
+};
+
 #define XE_GT_REG_LIST(_type, _gt_type) \
 	(&xe_##_type##_regset.gt[XE_GT_TYPE_##_gt_type])
 
@@ -297,6 +319,28 @@ xe_media_gt_rpm_snapshot_capture(struct xe_gt *gt)
 						  XE_GT_REG_LIST(rpm, MEDIA));
 }
 
+static struct xe_dbg_reg_snapshot *
+xe_gt_guc_reg_snapshot_capture(struct xe_gt *gt)
+{
+	if (!gt || !gt->tile || !gt->tile->primary_gt)
+		return NULL;
+
+	return xe_dbg_reg_snapshot_capture_target(gt,
+						  gt->tile->primary_gt,
+						  XE_GT_REG_LIST(guc, MAIN));
+}
+
+static struct xe_dbg_reg_snapshot *
+xe_media_gt_guc_reg_snapshot_capture(struct xe_gt *gt)
+{
+	if (!gt || !gt->tile || !gt->tile->media_gt)
+		return NULL;
+
+	return xe_dbg_reg_snapshot_capture_target(gt,
+						  gt->tile->media_gt,
+						  XE_GT_REG_LIST(guc, MEDIA));
+}
+
 static struct xe_device *coredump_to_xe(const struct xe_devcoredump *coredump)
 {
 	return container_of(coredump, struct xe_device, devcoredump);
@@ -351,6 +395,11 @@ static ssize_t __xe_devcoredump_read(char *buffer, ssize_t count,
 	drm_printf(&p, "\n**** Media GT RPM Register Dump ****\n");
 	xe_dbg_reg_snapshot_print(&p, ss->media_gt_rpm);
 
+	drm_printf(&p, "\n**** GT GuC Register Dump ****\n");
+	xe_dbg_reg_snapshot_print(&p, ss->gt_guc_reg);
+	drm_printf(&p, "\n**** Media GT GuC Register Dump ****\n");
+	xe_dbg_reg_snapshot_print(&p, ss->media_gt_guc_reg);
+
 	drm_puts(&p, "\n**** GuC Log ****\n");
 	xe_guc_log_snapshot_print(ss->guc.log, &p);
 	drm_puts(&p, "\n**** GuC CT ****\n");
@@ -398,6 +447,12 @@ static void xe_devcoredump_snapshot_free(struct xe_devcoredump_snapshot *ss)
 	xe_dbg_reg_snapshot_free(ss->media_gt_rpm);
 	ss->media_gt_rpm = NULL;
 
+	xe_dbg_reg_snapshot_free(ss->gt_guc_reg);
+	ss->gt_guc_reg = NULL;
+
+	xe_dbg_reg_snapshot_free(ss->media_gt_guc_reg);
+	ss->media_gt_guc_reg = NULL;
+
 	if (!IS_ERR_OR_NULL(ss->gt))
 		xe_guc_capture_put_matched_nodes(&ss->gt->uc.guc);
 	ss->matched_node = NULL;
@@ -603,6 +658,9 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
 	ss->gt_rpm = xe_gt_rpm_snapshot_capture(q->gt);
 	ss->media_gt_rpm = xe_media_gt_rpm_snapshot_capture(q->gt);
 
+	ss->gt_guc_reg = xe_gt_guc_reg_snapshot_capture(q->gt);
+	ss->media_gt_guc_reg = xe_media_gt_guc_reg_snapshot_capture(q->gt);
+
 	ss->guc.log = xe_guc_log_snapshot_capture(&guc->log, true);
 	ss->guc.ct = xe_guc_ct_snapshot_capture(&guc->ct);
 	ss->ge = xe_guc_exec_queue_snapshot_capture(q);
diff --git a/drivers/gpu/drm/xe/xe_devcoredump_types.h b/drivers/gpu/drm/xe/xe_devcoredump_types.h
index 75f317a5fe36..4671e00558db 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump_types.h
+++ b/drivers/gpu/drm/xe/xe_devcoredump_types.h
@@ -74,6 +74,11 @@ struct xe_devcoredump_snapshot {
 	/** @media_gt_rpm: Media GT RPM snapshot */
 	struct xe_dbg_reg_snapshot *media_gt_rpm;
 
+	/** @gt_guc_reg: gt guc reg snapshot */
+	struct xe_dbg_reg_snapshot *gt_guc_reg;
+	/** @media_gt_guc_reg: media gt guc reg snapshot */
+	struct xe_dbg_reg_snapshot *media_gt_guc_reg;
+
 	/** @work: Workqueue for deferred capture outside of signaling context */
 	struct work_struct work;
 
-- 
2.43.0