[PATCH v6 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

v5:
- Rebase as per patch1 changes

v6:(Tejas)
- Refactor register name as per spec

Signed-off-by: Nareshkumar Gollakoti <naresh.kumar.g@intel.com>
Reviewed-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
---
 drivers/gpu/drm/xe/regs/xe_guc_regs.h     |  5 ++++
 drivers/gpu/drm/xe/xe_devcoredump.c       | 35 +++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_devcoredump_types.h |  5 ++++
 3 files changed, 45 insertions(+)

diff --git a/drivers/gpu/drm/xe/regs/xe_guc_regs.h b/drivers/gpu/drm/xe/regs/xe_guc_regs.h
index 5faac8316b66c..5a8a67eb37eea 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 SHIM_ERR_TRAP				XE_REG(0xc070)
+#define GUC_HW_FATAL_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 b3fb8a521c9ba..cd2c641111d68 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
@@ -73,6 +74,16 @@
 
 #define XE_REG_DESC(_reg, _name)	{ .reg = (_reg), .name = (_name) }
 
+static const struct xe_reg_desc xe_dbg_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_FATAL_ERR,	"GUC_HW_FATAL_ERR"),
+	XE_REG_DESC(GUC_HW_NOTIFY_ERR,	"GUC_HW_NOTIFY_ERR"),
+	XE_REG_DESC(SHIM_ERR_TRAP,	"SHIM_ERR_TRAP"),
+};
+
 static const struct xe_reg_desc xe_dbg_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"),
@@ -121,11 +132,13 @@ struct xe_gt_regset {
  * enum xe_dbg_regset_type - debug register set types
  * @XE_DBG_REGSET_FUSE: Fuse register set
  * @XE_DBG_REGSET_RPM: RPM register set
+ * @XE_DBG_REGSET_GUC: GUC register set
  * @XE_DBG_REGSET_MAX: Number of debug register set types
  */
 enum xe_dbg_regset_type {
 	XE_DBG_REGSET_FUSE,
 	XE_DBG_REGSET_RPM,
+	XE_DBG_REGSET_GUC,
 	XE_DBG_REGSET_MAX,
 };
 
@@ -142,6 +155,12 @@ static const struct xe_gt_regset xe_dbg_regsets[XE_DBG_REGSET_MAX] = {
 		.gt[XE_GT_TYPE_MEDIA] = { xe_dbg_media_gt_rpm_reglist,
 					  ARRAY_SIZE(xe_dbg_media_gt_rpm_reglist) },
 	},
+	[XE_DBG_REGSET_GUC] = {
+		.gt[XE_GT_TYPE_MAIN] = { xe_dbg_gt_guc_reglist,
+					ARRAY_SIZE(xe_dbg_gt_guc_reglist) },
+		.gt[XE_GT_TYPE_MEDIA] = { xe_dbg_gt_guc_reglist,
+					  ARRAY_SIZE(xe_dbg_gt_guc_reglist) },
+	},
 };
 
 static void xe_dbg_reg_snapshot_print(struct drm_printer *p,
@@ -288,6 +307,8 @@ static ssize_t __xe_devcoredump_read(char *buffer, ssize_t count,
 	xe_dbg_reg_snapshot_print(&p, "Media GT Fuse Register Dump", ss->media_fuse);
 	xe_gt_rpm_snapshot_print(&p, "GT RPM Register Dump", ss->gt_rpm);
 	xe_dbg_reg_snapshot_print(&p, "Media GT RPM Register Dump", ss->media_gt_rpm);
+	xe_dbg_reg_snapshot_print(&p, "GT GuC Register Dump", ss->gt_guc_reg);
+	xe_dbg_reg_snapshot_print(&p, "Media GT GuC Register Dump", ss->media_gt_guc_reg);
 
 	drm_puts(&p, "\n**** GuC Log ****\n");
 	xe_guc_log_snapshot_print(ss->guc.log, &p, ss->gt);
@@ -338,6 +359,12 @@ 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;
@@ -530,6 +557,14 @@ static void xe_devcoredump_capture_gt_regs(struct xe_devcoredump_snapshot *ss,
 						      other_gt,
 						      XE_DBG_REGSET_RPM,
 						      XE_GT_TYPE_MEDIA);
+	ss->gt_guc_reg = xe_dbg_gt_snapshot_capture(gt,
+						    other_gt,
+						    XE_DBG_REGSET_GUC,
+						    XE_GT_TYPE_MAIN);
+	ss->media_gt_guc_reg = xe_dbg_gt_snapshot_capture(gt,
+							  other_gt,
+							  XE_DBG_REGSET_GUC,
+							  XE_GT_TYPE_MEDIA);
 }
 
 static void devcoredump_snapshot(struct xe_devcoredump *coredump,
diff --git a/drivers/gpu/drm/xe/xe_devcoredump_types.h b/drivers/gpu/drm/xe/xe_devcoredump_types.h
index e2fac33dce091..52db64640f89e 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump_types.h
+++ b/drivers/gpu/drm/xe/xe_devcoredump_types.h
@@ -87,6 +87,11 @@ 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