[PATCH v4 7/7] drm/xe/guc: capture additional engine state registers

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

Add a wider set of engine state registers to GuC error capture to improve
post-mortem debugging of engine hangs and reset-related failures.

Define the missing register offsets in xe_engine_regs.h and include them in
the GuC capture list. The additional registers cover reset state, front-end
and back-end FSM state, power state, batch buffer state, instruction state,
preemption status, and related chicken/debug controls.

This provides more complete engine context in capture dumps, which should
help root-cause analysis when investigating GuC-reported engine failures.

v3:(Sashiko)
- Move FF_SLICE_CS_CHICKEN1/2 out of COMMON_BASE_ENGINE_INSTANCE
- Add XE3P_RC_SLICE_INSTANCE and include it only in xe3p_rc_inst_regs[]
- Add XE_BCS_RCS_ENGINE_INSTANCE for registers shared only by
  BCS/RCS paths
- Include XE_BCS_RCS_ENGINE_INSTANCE only in
  xe_blt_inst_regs[] and xe3p_rc_inst_regs[]
- Keep COMMON_BASE_ENGINE_INSTANCE limited to registers
  valid across all engine classes

Signed-off-by: Nareshkumar Gollakoti <naresh.kumar.g@intel.com>
---
 drivers/gpu/drm/xe/regs/xe_engine_regs.h | 22 +++++++++++++++
 drivers/gpu/drm/xe/xe_guc_capture.c      | 35 ++++++++++++++++++++----
 2 files changed, 52 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
index 94033982e694..9f328b1b18f5 100644
--- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
@@ -60,6 +60,8 @@
 
 #define RING_START_UDW(base)			XE_REG((base) + 0x48)
 
+#define RING_CSFE_GLB_CHICKEN3(base)		XE_REG((base) + 0x4c)
+
 #define RING_PSMI_CTL(base)			XE_REG((base) + 0x50, XE_REG_OPTION_MASKED)
 #define   RC_SEMA_IDLE_MSG_DISABLE		REG_BIT(12)
 #define   WAIT_FOR_EVENT_POWER_DOWN_DISABLE	REG_BIT(7)
@@ -72,6 +74,7 @@
 #define RING_DMA_FADD_UDW(base)			XE_REG((base) + 0x60)
 #define RING_IPEHR(base)			XE_REG((base) + 0x68)
 #define RING_INSTDONE(base)			XE_REG((base) + 0x6c)
+#define RING_INSTPS(base)			XE_REG((base) + 0x70)
 #define RING_ACTHD(base)			XE_REG((base) + 0x74)
 #define RING_DMA_FADD(base)			XE_REG((base) + 0x78)
 #define RING_HWS_PGA(base)			XE_REG((base) + 0x80)
@@ -102,6 +105,8 @@
 #define   SELECTIVE_READ_GROUP			REG_GENMASK(29, 23)
 #define   SELECTIVE_READ_INSTANCE		REG_GENMASK(22, 16)
 
+#define RESET_CTRL(base)			XE_REG((base) + 0xd0)
+
 /*
  * CMD_CCTL read/write fields take a MOCS value and _not_ a table index.
  * The lsb of each can be considered a separate enabling bit for encryption.
@@ -123,15 +128,21 @@
 #define FF_SLICE_CS_CHICKEN1(base)		XE_REG((base) + 0xe0, XE_REG_OPTION_MASKED)
 #define   FFSC_PERCTX_PREEMPT_CTRL		REG_BIT(14)
 
+#define FF_SLICE_CS_CHICKEN2(base)		XE_REG((base) + 0xe4, XE_REG_OPTION_MASKED)
+
 #define CS_DEBUG_MODE1(base)			XE_REG((base) + 0xec, XE_REG_OPTION_MASKED)
 #define   FF_DOP_CLOCK_GATE_DISABLE		REG_BIT(1)
 #define   REPLAY_MODE_GRANULARITY		REG_BIT(0)
 
 #define INDIRECT_RING_STATE(base)		XE_REG((base) + 0x108)
 
+#define RING_BB_STATE(base)			XE_REG((base) + 0x110)
+
 #define RING_BBADDR(base)			XE_REG((base) + 0x140)
 #define RING_BBADDR_UDW(base)			XE_REG((base) + 0x168)
 
+#define RING_BB_ADDR_DIFF(base)			XE_REG((base) + 0x154)
+
 #define PR_CTR_CTRL(base)			XE_REG((base) + 0x178)
 #define   CTR_COUNT_SELECT_FF			REG_BIT(31)
 #define   CTR_LOGIC_OP_MASK			REG_GENMASK(30, 0)
@@ -148,6 +159,8 @@
 #define   BLIT_CCTL_DST_MOCS_MASK		REG_GENMASK(14, 9)
 #define   BLIT_CCTL_SRC_MOCS_MASK		REG_GENMASK(6, 1)
 
+#define RING_CSBEFSM3(base)			XE_REG((base) + 0x224)
+
 #define RING_EXECLIST_STATUS_LO(base)		XE_REG((base) + 0x234)
 #define RING_EXECLIST_STATUS_HI(base)		XE_REG((base) + 0x234 + 4)
 
@@ -169,9 +182,16 @@
 #define   GFX_MSIX_INTERRUPT_ENABLE		REG_BIT(13)
 #define   GFX_DISABLE_LEGACY_MODE		REG_BIT(3)
 
+#define RING_CSFESM(base)			XE_REG((base) + 0x2a0)
+#define RING_CSFESM2(base)			XE_REG((base) + 0x2a4)
+#define RING_CSFESM3(base)			XE_REG((base) + 0x2a8)
+#define RING_CSPWRFSM(base)			XE_REG((base) + 0x2ac)
+
 #define RING_CSMQDEBUG(base)			XE_REG((base) + 0x2b0)
 #define   CURRENT_ACTIVE_QUEUE_ID_MASK		REG_GENMASK(7, 0)
 
+#define RING_CSBEFSM(base)			XE_REG((base) + 0x2bc)
+
 #define RING_QUEUE_TIMESTAMP(base)		XE_REG((base) + 0x4c0)
 #define RING_QUEUE_TIMESTAMP_UDW(base)		XE_REG((base) + 0x4c0 + 4)
 
@@ -217,6 +237,8 @@
 #define   PREEMPT_GPGPU_LEVEL_MASK		PREEMPT_GPGPU_LEVEL(1, 1)
 #define   PREEMPT_3D_OBJECT_LEVEL		REG_BIT(0)
 
+#define CS_PREEMPTION_STATUS(base)		XE_REG((base) + 0x5ac)
+
 #define CS_GPR_DATA(base, n)			XE_REG((base) + 0x600 + (n) * 4)
 #define CS_GPR_REG(base, n)			CS_GPR_DATA((base), (n) * 2)
 #define CS_GPR_REG_UDW(base, n)			CS_GPR_DATA((base), (n) * 2 + 1)
diff --git a/drivers/gpu/drm/xe/xe_guc_capture.c b/drivers/gpu/drm/xe/xe_guc_capture.c
index 6a20eab0f820..b3c42052b70b 100644
--- a/drivers/gpu/drm/xe/xe_guc_capture.c
+++ b/drivers/gpu/drm/xe/xe_guc_capture.c
@@ -127,11 +127,7 @@ struct __guc_capture_parsed_output {
 	{ RING_START(0),		REG_64BIT_LOW_DW, 0,	0,	0,	NULL}, \
 	{ RING_START_UDW(0),		REG_64BIT_HI_DW, 0,	0,	0,	"RING_START"}, \
 	{ RING_DMA_FADD(0),		REG_64BIT_LOW_DW, 0,	0,	0,	NULL}, \
-	{ RING_DMA_FADD_UDW(0),		REG_64BIT_HI_DW, 0,	0,	0,	"RING_DMA_FADD"}, \
-	{ RING_EXECLIST_STATUS_LO(0),	REG_64BIT_LOW_DW, 0,	0,	0,	NULL}, \
-	{ RING_EXECLIST_STATUS_HI(0),	REG_64BIT_HI_DW, 0,	0,	0,	"RING_EXECLIST_STATUS"}, \
-	{ RING_EXECLIST_SQ_CONTENTS_LO(0), REG_64BIT_LOW_DW, 0,	0,	0,	NULL}, \
-	{ RING_EXECLIST_SQ_CONTENTS_HI(0), REG_64BIT_HI_DW, 0,	0,	0,	"RING_EXECLIST_SQ_CONTENTS"}
+	{ RING_DMA_FADD_UDW(0),		REG_64BIT_HI_DW, 0,	0,	0,	"RING_DMA_FADD"}
 
 #define COMMON_XELP_RC_CLASS \
 	{ RCU_MODE,			REG_32BIT,	0,	0,	0,	"RCU_MODE"}
@@ -150,6 +146,32 @@ struct __guc_capture_parsed_output {
 #define XE3P_BASE_ENGINE_INSTANCE \
 	{ RING_CSMQDEBUG(0),		REG_32BIT,	0,	0,	0,	"CSMQDEBUG"}
 
+#define XE3P_RC_SLICE_INSTANCE \
+	{ FF_SLICE_CS_CHICKEN1(0), REG_32BIT, 0, 0, 0, "FF_SLICE_CS_CHICKEN1"}, \
+	{ FF_SLICE_CS_CHICKEN2(0), REG_32BIT, 0, 0, 0, "FF_SLICE_CS_CHICKEN2"}
+
+#define XE_BCS_RCS_ENGINE_INSTANCE \
+	{ RING_EXECLIST_STATUS_LO(0), REG_64BIT_LOW_DW, 0, 0, 0, NULL}, \
+	{ RING_EXECLIST_STATUS_HI(0), REG_64BIT_HI_DW, 0, 0, 0, "RING_EXECLIST_STATUS"}, \
+	{ RING_EXECLIST_SQ_CONTENTS_LO(0), REG_64BIT_LOW_DW, 0, 0, 0, NULL}, \
+	{ RING_EXECLIST_SQ_CONTENTS_HI(0), REG_64BIT_HI_DW, 0, 0, 0, "RING_EXECLIST_SQ_CONTENTS"}, \
+	{ RESET_CTRL(0), REG_32BIT, 0, 0, 0, "RESET_CTRL"}, \
+	{ RING_CSBEFSM3(0), REG_32BIT, 0, 0, 0, "RING_CSBEFSM3"}, \
+	{ RING_CSFESM(0), REG_32BIT, 0, 0, 0, "RING_CSFESM"}, \
+	{ RING_CSFESM2(0), REG_32BIT, 0, 0, 0, "RING_CSFESM2"}, \
+	{ RING_CSFESM3(0), REG_32BIT, 0, 0, 0, "RING_CSFESM3"}, \
+	{ RING_CSPWRFSM(0), REG_32BIT, 0, 0, 0, "RING_CSPWRFSM"}, \
+	{ RING_CSBEFSM(0), REG_32BIT, 0, 0, 0, "RING_CSBEFSM"}, \
+	{ BCS_SWCTRL(0), REG_32BIT, 0, 0, 0, "BCS_SWCTRL"}, \
+	{ RING_CSFE_GLB_CHICKEN3(0), REG_32BIT, 0, 0, 0, "RING_CSFE_GLB_CHICKEN3"}, \
+	{ RING_PSMI_CTL(0), REG_32BIT, 0, 0, 0, "RING_PSMI_CTL"}, \
+	{ RING_INSTPS(0), REG_32BIT, 0, 0, 0, "RING_INSTPS"}, \
+	{ RING_BB_ADDR_DIFF(0), REG_32BIT, 0, 0, 0, "RING_BB_ADDR_DIFF"}, \
+	{ RING_BB_STATE(0), REG_32BIT, 0, 0, 0, "RING_BB_STATE"}, \
+	{ CS_DEBUG_MODE1(0), REG_32BIT, 0, 0, 0, "CS_DEBUG_MODE1"}, \
+	{ CS_CHICKEN1(0), REG_32BIT, 0, 0, 0, "CS_CHICKEN1"}, \
+	{ CS_PREEMPTION_STATUS(0), REG_32BIT, 0, 0, 0, "CS_PREEMPTION_STATUS"}
+
 /* XE_LP Global */
 static const struct __guc_mmio_reg_descr xe_lp_global_regs[] = {
 	COMMON_XELP_BASE_GLOBAL,
@@ -189,6 +211,7 @@ static const struct __guc_mmio_reg_descr xe_vec_inst_regs[] = {
 /* Blitter Per-Engine-Instance */
 static const struct __guc_mmio_reg_descr xe_blt_inst_regs[] = {
 	COMMON_BASE_ENGINE_INSTANCE,
+	XE_BCS_RCS_ENGINE_INSTANCE,
 };
 
 /* XE_LP - GSC Per-Engine-Instance */
@@ -200,6 +223,8 @@ static const struct __guc_mmio_reg_descr xe_lp_gsc_inst_regs[] = {
 static const struct __guc_mmio_reg_descr xe3p_rc_inst_regs[] = {
 	COMMON_BASE_ENGINE_INSTANCE,
 	XE3P_BASE_ENGINE_INSTANCE,
+	XE_BCS_RCS_ENGINE_INSTANCE,
+	XE3P_RC_SLICE_INSTANCE,
 };
 
 /*
-- 
2.43.0