Merge tag 'drm-intel-gt-next-2022-08-24' of...

Merge tag 'drm-intel-gt-next-2022-08-24' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:

- Create gt/gtN/.defaults/ for per gt sysfs defaults

  Create a gt/gtN/.defaults/ directory (similar to
  engine/<engine-name>/.defaults/) to expose default parameter values for
  each gt in sysfs. This allows userspace to restore default parameter values
  after they have changed.

Driver Changes:

- Support GuC v69 in parallel to v70 (Daniele)
- Improve TLB invalidation to limit performance regression (Chris, Mauro)
- Expose per-gt RPS defaults in sysfs (Ashutosh)
- Suppress OOM warning for shmemfs object allocation failure (Chris, Nirmoy)
- Disable PCI resize on 32-bit machines (Nirmoy)
- Update DG2 to GuC v70.4.1 (John)
- Fix CCS data copying on DG2 during swapping (Matt A)
- Add DG2 performance tuning setting recommended by spec (Matt R)
- Add GuC <-> kernel time stamp translation information to error logs (John)
- Record GuC CTB info in error logs (John)

- Route semaphores to GuC for Gen12+ when enabled (Michal Wi, John)
- Improve resilency to bug #3575: Handle reset timeouts under unrelated kernel hangs (Chris, Ashutosh)
- Avoid system freeze by removing shared locking on freeing objects (Chris, Nirmoy)
- Demote GuC error "No response for request" into debug when expected (Zhanjun)
- Fix GuC capture size warning and bump the size (John)
- Use streaming loads to speed up dumping the GuC log (Chris, John)
- Don't abort on CTB_UNUSED status from GuC (John)
- Don't send spurious policy update for GuC child contexts (Daniele)
- Don't leak the CCS state (Matt A)

- Prefer drm_err over pr_err (John)
- Eliminate unused calc_ctrl_surf_instr_size (Matt A)
- Add dedicated function for non-ctx register tuning settings (Matt R)
- Style and typo fixes, documentation improvements (Jason Wang, Mauro)
- Selftest improvements (Matt B, Rahul, John)
Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/YwYTCjA/Rhpd1n4A@jlahtine-mobl.ger.corp.intel.com

drivers/gpu/drm/i915/gem/i915_gem_shmem.c

@@ -75,7 +75,7 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st,
 	if (size > resource_size(&mr->region))
 		return -ENOMEM;
 
-	if (sg_alloc_table(st, page_count, GFP_KERNEL))
+	if (sg_alloc_table(st, page_count, GFP_KERNEL | __GFP_NOWARN))
 		return -ENOMEM;
 
 	/*
@@ -137,7 +137,7 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st,
 				 * trigger the out-of-memory killer and for
 				 * this we want __GFP_RETRY_MAYFAIL.
 				 */
-				gfp |= __GFP_RETRY_MAYFAIL;
+				gfp |= __GFP_RETRY_MAYFAIL | __GFP_NOWARN;
 			}
 		} while (1);
 
@@ -209,7 +209,7 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj)
 	GEM_BUG_ON(obj->write_domain & I915_GEM_GPU_DOMAINS);
 
 rebuild_st:
-	st = kmalloc(sizeof(*st), GFP_KERNEL);
+	st = kmalloc(sizeof(*st), GFP_KERNEL | __GFP_NOWARN);
 	if (!st)
 		return -ENOMEM;
 

drivers/gpu/drm/i915/gt/intel_gt_pm.h

@@ -55,6 +55,14 @@ static inline void intel_gt_pm_might_put(struct intel_gt *gt)
 	for (tmp = 1, intel_gt_pm_get(gt); tmp; \
 	     intel_gt_pm_put(gt), tmp = 0)
 
+/**
+ * with_intel_gt_pm_if_awake - if GT is PM awake, get a reference to prevent
+ *	it to sleep, run some code and then asynchrously put the reference
+ *	away.
+ *
+ * @gt: pointer to the gt
+ * @wf: pointer to a temporary wakeref.
+ */
 #define with_intel_gt_pm_if_awake(gt, wf) \
 	for (wf = intel_gt_pm_get_if_awake(gt); wf; intel_gt_pm_put_async(gt), wf = 0)
 

drivers/gpu/drm/i915/gt/intel_gt_regs.h

@@ -259,6 +259,9 @@
 #define   GEN9_PREEMPT_GPGPU_COMMAND_LEVEL	GEN9_PREEMPT_GPGPU_LEVEL(1, 0)
 #define   GEN9_PREEMPT_GPGPU_LEVEL_MASK		GEN9_PREEMPT_GPGPU_LEVEL(1, 1)
 
+#define DRAW_WATERMARK				_MMIO(0x26c0)
+#define   VERT_WM_VAL				REG_GENMASK(9, 0)
+
 #define GEN12_GLOBAL_MOCS(i)			_MMIO(0x4000 + (i) * 4) /* Global MOCS regs */
 
 #define RENDER_HWS_PGA_GEN7			_MMIO(0x4080)
@@ -374,6 +377,9 @@
 #define CHICKEN_RASTER_1			_MMIO(0x6204)
 #define   DIS_SF_ROUND_NEAREST_EVEN		REG_BIT(8)
 
+#define CHICKEN_RASTER_2			_MMIO(0x6208)
+#define   TBIMR_FAST_CLIP			REG_BIT(5)
+
 #define VFLSKPD					_MMIO(0x62a8)
 #define   DIS_OVER_FETCH_CACHE			REG_BIT(1)
 #define   DIS_MULT_MISS_RD_SQUASH		REG_BIT(0)
@@ -1007,6 +1013,8 @@
 #define   GEN11_LSN_UNSLCVC_GAFS_HALF_CL2_MAXALLOC	(1 << 9)
 #define   GEN11_LSN_UNSLCVC_GAFS_HALF_SF_MAXALLOC	(1 << 7)
 
+#define GUCPMTIMESTAMP				_MMIO(0xc3e8)
+
 #define __GEN9_RCS0_MOCS0			0xc800
 #define GEN9_GFX_MOCS(i)			_MMIO(__GEN9_RCS0_MOCS0 + (i) * 4)
 #define __GEN9_VCS0_MOCS0			0xc900
@@ -1078,6 +1086,7 @@
 
 #define GEN10_SAMPLER_MODE			_MMIO(0xe18c)
 #define   ENABLE_SMALLPL			REG_BIT(15)
+#define   SC_DISABLE_POWER_OPTIMIZATION_EBB	REG_BIT(9)
 #define   GEN11_SAMPLER_ENABLE_HEADLESS_MSG	REG_BIT(5)
 
 #define GEN9_HALF_SLICE_CHICKEN7		_MMIO(0xe194)
@@ -1123,6 +1132,8 @@
 
 #define RT_CTRL					_MMIO(0xe530)
 #define   DIS_NULL_QUERY			REG_BIT(10)
+#define   STACKID_CTRL				REG_GENMASK(6, 5)
+#define   STACKID_CTRL_512			REG_FIELD_PREP(STACKID_CTRL, 0x2)
 
 #define EU_PERF_CNTL1				_MMIO(0xe558)
 #define EU_PERF_CNTL5				_MMIO(0xe55c)

drivers/gpu/drm/i915/gt/intel_gt_sysfs.c

@@ -22,11 +22,6 @@ bool is_object_gt(struct kobject *kobj)
 	return !strncmp(kobj->name, "gt", 2);
 }
 
-static struct intel_gt *kobj_to_gt(struct kobject *kobj)
-{
-	return container_of(kobj, struct intel_gt, sysfs_gt);
-}
-
 struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev,
 					    const char *name)
 {
@@ -101,6 +96,10 @@ void intel_gt_sysfs_register(struct intel_gt *gt)
 				 gt->i915->sysfs_gt, "gt%d", gt->info.id))
 		goto exit_fail;
 
+	gt->sysfs_defaults = kobject_create_and_add(".defaults", &gt->sysfs_gt);
+	if (!gt->sysfs_defaults)
+		goto exit_fail;
+
 	intel_gt_sysfs_pm_init(gt, &gt->sysfs_gt);
 
 	return;
@@ -113,5 +112,6 @@ void intel_gt_sysfs_register(struct intel_gt *gt)
 
 void intel_gt_sysfs_unregister(struct intel_gt *gt)
 {
+	kobject_put(gt->sysfs_defaults);
 	kobject_put(&gt->sysfs_gt);
 }

drivers/gpu/drm/i915/gt/intel_gt_sysfs.h

@@ -10,6 +10,7 @@
 #include <linux/kobject.h>
 
 #include "i915_gem.h" /* GEM_BUG_ON() */
+#include "intel_gt_types.h"
 
 struct intel_gt;
 
@@ -22,6 +23,11 @@ intel_gt_create_kobj(struct intel_gt *gt,
 		     struct kobject *dir,
 		     const char *name);
 
+static inline struct intel_gt *kobj_to_gt(struct kobject *kobj)
+{
+	return container_of(kobj, struct intel_gt, sysfs_gt);
+}
+
 void intel_gt_sysfs_register(struct intel_gt *gt);
 void intel_gt_sysfs_unregister(struct intel_gt *gt);
 struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev,

drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c

@@ -727,6 +727,34 @@ static const struct attribute *media_perf_power_attrs[] = {
 	NULL
 };
 
+static ssize_t
+default_min_freq_mhz_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+{
+	struct intel_gt *gt = kobj_to_gt(kobj->parent);
+
+	return sysfs_emit(buf, "%u\n", gt->defaults.min_freq);
+}
+
+static struct kobj_attribute default_min_freq_mhz =
+__ATTR(rps_min_freq_mhz, 0444, default_min_freq_mhz_show, NULL);
+
+static ssize_t
+default_max_freq_mhz_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+{
+	struct intel_gt *gt = kobj_to_gt(kobj->parent);
+
+	return sysfs_emit(buf, "%u\n", gt->defaults.max_freq);
+}
+
+static struct kobj_attribute default_max_freq_mhz =
+__ATTR(rps_max_freq_mhz, 0444, default_max_freq_mhz_show, NULL);
+
+static const struct attribute * const rps_defaults_attrs[] = {
+	&default_min_freq_mhz.attr,
+	&default_max_freq_mhz.attr,
+	NULL
+};
+
 static int intel_sysfs_rps_init(struct intel_gt *gt, struct kobject *kobj,
 				const struct attribute * const *attrs)
 {
@@ -776,4 +804,10 @@ void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj)
 				 "failed to create gt%u media_perf_power_attrs sysfs (%pe)\n",
 				 gt->info.id, ERR_PTR(ret));
 	}
+
+	ret = sysfs_create_files(gt->sysfs_defaults, rps_defaults_attrs);
+	if (ret)
+		drm_warn(&gt->i915->drm,
+			 "failed to add gt%u rps defaults (%pe)\n",
+			 gt->info.id, ERR_PTR(ret));
 }

drivers/gpu/drm/i915/gt/intel_gt_types.h

@@ -76,6 +76,11 @@ enum intel_submission_method {
 	INTEL_SUBMISSION_GUC,
 };
 
+struct gt_defaults {
+	u32 min_freq;
+	u32 max_freq;
+};
+
 struct intel_gt {
 	struct drm_i915_private *i915;
 	struct intel_uncore *uncore;
@@ -251,6 +256,10 @@ struct intel_gt {
 
 	/* gt/gtN sysfs */
 	struct kobject sysfs_gt;
+
+	/* sysfs defaults per gt */
+	struct gt_defaults defaults;
+	struct kobject *sysfs_defaults;
 };
 
 enum intel_gt_scratch_field {

drivers/gpu/drm/i915/gt/intel_migrate.c

@@ -511,44 +511,16 @@ static inline u32 *i915_flush_dw(u32 *cmd, u32 flags)
 	return cmd;
 }
 
-static u32 calc_ctrl_surf_instr_size(struct drm_i915_private *i915, int size)
-{
-	u32 num_cmds, num_blks, total_size;
-
-	if (!GET_CCS_BYTES(i915, size))
-		return 0;
-
-	/*
-	 * XY_CTRL_SURF_COPY_BLT transfers CCS in 256 byte
-	 * blocks. one XY_CTRL_SURF_COPY_BLT command can
-	 * transfer upto 1024 blocks.
-	 */
-	num_blks = DIV_ROUND_UP(GET_CCS_BYTES(i915, size),
-				NUM_CCS_BYTES_PER_BLOCK);
-	num_cmds = DIV_ROUND_UP(num_blks, NUM_CCS_BLKS_PER_XFER);
-	total_size = XY_CTRL_SURF_INSTR_SIZE * num_cmds;
-
-	/*
-	 * Adding a flush before and after XY_CTRL_SURF_COPY_BLT
-	 */
-	total_size += 2 * MI_FLUSH_DW_SIZE;
-
-	return total_size;
-}
-
 static int emit_copy_ccs(struct i915_request *rq,
 			 u32 dst_offset, u8 dst_access,
 			 u32 src_offset, u8 src_access, int size)
 {
 	struct drm_i915_private *i915 = rq->engine->i915;
 	int mocs = rq->engine->gt->mocs.uc_index << 1;
-	u32 num_ccs_blks, ccs_ring_size;
+	u32 num_ccs_blks;
 	u32 *cs;
 
-	ccs_ring_size = calc_ctrl_surf_instr_size(i915, size);
-	WARN_ON(!ccs_ring_size);
-
-	cs = intel_ring_begin(rq, round_up(ccs_ring_size, 2));
+	cs = intel_ring_begin(rq, 12);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
@@ -583,8 +555,7 @@ static int emit_copy_ccs(struct i915_request *rq,
 		FIELD_PREP(XY_CTRL_SURF_MOCS_MASK, mocs);
 
 	cs = i915_flush_dw(cs, MI_FLUSH_DW_LLC | MI_FLUSH_DW_CCS);
-	if (ccs_ring_size & 1)
-		*cs++ = MI_NOOP;
+	*cs++ = MI_NOOP;
 
 	intel_ring_advance(rq, cs);
 
@@ -638,40 +609,38 @@ static int emit_copy(struct i915_request *rq,
 	return 0;
 }
 
-static int scatter_list_length(struct scatterlist *sg)
+static u64 scatter_list_length(struct scatterlist *sg)
 {
-	int len = 0;
+	u64 len = 0;
 
 	while (sg && sg_dma_len(sg)) {
 		len += sg_dma_len(sg);
 		sg = sg_next(sg);
-	};
+	}
 
 	return len;
 }
 
-static void
+static int
 calculate_chunk_sz(struct drm_i915_private *i915, bool src_is_lmem,
-		   int *src_sz, u32 bytes_to_cpy, u32 ccs_bytes_to_cpy)
+		   u64 bytes_to_cpy, u64 ccs_bytes_to_cpy)
 {
-	if (ccs_bytes_to_cpy) {
-		if (!src_is_lmem)
-			/*
-			 * When CHUNK_SZ is passed all the pages upto CHUNK_SZ
-			 * will be taken for the blt. in Flat-ccs supported
-			 * platform Smem obj will have more pages than required
-			 * for main meory hence limit it to the required size
-			 * for main memory
-			 */
-			*src_sz = min_t(int, bytes_to_cpy, CHUNK_SZ);
-	} else { /* ccs handling is not required */
-		*src_sz = CHUNK_SZ;
-	}
+	if (ccs_bytes_to_cpy && !src_is_lmem)
+		/*
+		 * When CHUNK_SZ is passed all the pages upto CHUNK_SZ
+		 * will be taken for the blt. in Flat-ccs supported
+		 * platform Smem obj will have more pages than required
+		 * for main meory hence limit it to the required size
+		 * for main memory
+		 */
+		return min_t(u64, bytes_to_cpy, CHUNK_SZ);
+	else
+		return CHUNK_SZ;
 }
 
-static void get_ccs_sg_sgt(struct sgt_dma *it, u32 bytes_to_cpy)
+static void get_ccs_sg_sgt(struct sgt_dma *it, u64 bytes_to_cpy)
 {
-	u32 len;
+	u64 len;
 
 	do {
 		GEM_BUG_ON(!it->sg || !sg_dma_len(it->sg));
@@ -702,12 +671,12 @@ intel_context_migrate_copy(struct intel_context *ce,
 {
 	struct sgt_dma it_src = sg_sgt(src), it_dst = sg_sgt(dst), it_ccs;
 	struct drm_i915_private *i915 = ce->engine->i915;
-	u32 ccs_bytes_to_cpy = 0, bytes_to_cpy;
+	u64 ccs_bytes_to_cpy = 0, bytes_to_cpy;
 	enum i915_cache_level ccs_cache_level;
 	u32 src_offset, dst_offset;
 	u8 src_access, dst_access;
 	struct i915_request *rq;
-	int src_sz, dst_sz;
+	u64 src_sz, dst_sz;
 	bool ccs_is_src, overwrite_ccs;
 	int err;
 
@@ -790,8 +759,8 @@ intel_context_migrate_copy(struct intel_context *ce,
 		if (err)
 			goto out_rq;
 
-		calculate_chunk_sz(i915, src_is_lmem, &src_sz,
-				   bytes_to_cpy, ccs_bytes_to_cpy);
+		src_sz = calculate_chunk_sz(i915, src_is_lmem,
+					    bytes_to_cpy, ccs_bytes_to_cpy);
 
 		len = emit_pte(rq, &it_src, src_cache_level, src_is_lmem,
 			       src_offset, src_sz);

drivers/gpu/drm/i915/gt/intel_reset.c

@@ -1281,9 +1281,6 @@ static void intel_gt_reset_global(struct intel_gt *gt,
 	intel_wedge_on_timeout(&w, gt, 5 * HZ) {
 		intel_display_prepare_reset(gt->i915);
 
-		/* Flush everyone using a resource about to be clobbered */
-		synchronize_srcu_expedited(&gt->reset.backoff_srcu);
-
 		intel_gt_reset(gt, engine_mask, reason);
 
 		intel_display_finish_reset(gt->i915);
@@ -1392,6 +1389,9 @@ void intel_gt_handle_error(struct intel_gt *gt,
 		}
 	}
 
+	/* Flush everyone using a resource about to be clobbered */
+	synchronize_srcu_expedited(&gt->reset.backoff_srcu);
+
 	intel_gt_reset_global(gt, engine_mask, msg);
 
 	if (!intel_uc_uses_guc_submission(&gt->uc)) {

drivers/gpu/drm/i915/gt/intel_rps.c

@@ -1979,7 +1979,9 @@ void intel_rps_init(struct intel_rps *rps)
 
 	/* Derive initial user preferences/limits from the hardware limits */
 	rps->max_freq_softlimit = rps->max_freq;
+	rps_to_gt(rps)->defaults.max_freq = rps->max_freq_softlimit;
 	rps->min_freq_softlimit = rps->min_freq;
+	rps_to_gt(rps)->defaults.min_freq = rps->min_freq_softlimit;
 
 	/* After setting max-softlimit, find the overclock max freq */
 	if (GRAPHICS_VER(i915) == 6 || IS_IVYBRIDGE(i915) || IS_HASWELL(i915)) {

drivers/gpu/drm/i915/gt/intel_workarounds.c

@@ -568,6 +568,7 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void dg2_ctx_gt_tuning_init(struct intel_engine_cs *engine,
 				   struct i915_wa_list *wal)
 {
+	wa_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP);
 	wa_write_clr_set(wal, GEN11_L3SQCREG5, L3_PWM_TIMER_INIT_VAL_MASK,
 			 REG_FIELD_PREP(L3_PWM_TIMER_INIT_VAL_MASK, 0x7f));
 	wa_add(wal,
@@ -2102,13 +2103,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		/* Wa_1509235366:dg2 */
 		wa_write_or(wal, GEN12_GAMCNTRL_CTRL, INVALIDATION_BROADCAST_MODE_DIS |
 			    GLOBAL_INVALIDATION_MODE);
-
-		/*
-		 * The following are not actually "workarounds" but rather
-		 * recommended tuning settings documented in the bspec's
-		 * performance guide section.
-		 */
-		wa_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS);
 	}
 
 	if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) {
@@ -2119,6 +2113,13 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		wa_write_or(wal, LSC_CHICKEN_BIT_0_UDW, DIS_CHAIN_2XSIMD8);
 	}
 
+	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) ||
+	    IS_DG2_G11(i915) || IS_DG2_G12(i915)) {
+		/* Wa_1509727124:dg2 */
+		wa_masked_en(wal, GEN10_SAMPLER_MODE,
+			     SC_DISABLE_POWER_OPTIMIZATION_EBB);
+	}
+
 	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0) ||
 	    IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) {
 		/* Wa_14012419201:dg2 */
@@ -2195,15 +2196,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		wa_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE);
 	}
 
-	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_C0) ||
-	    IS_DG2_G11(i915)) {
-		/* Wa_22012654132:dg2 */
-		wa_add(wal, GEN10_CACHE_MODE_SS, 0,
-		       _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC),
-		       0 /* write-only, so skip validation */,
-		       true);
-	}
-
 	/* Wa_14013202645:dg2 */
 	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) ||
 	    IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0))
@@ -2669,6 +2661,49 @@ ccs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	}
 }
 
+/*
+ * The bspec performance guide has recommended MMIO tuning settings.  These
+ * aren't truly "workarounds" but we want to program them with the same
+ * workaround infrastructure to ensure that they're automatically added to
+ * the GuC save/restore lists, re-applied at the right times, and checked for
+ * any conflicting programming requested by real workarounds.
+ *
+ * Programming settings should be added here only if their registers are not
+ * part of an engine's register state context.  If a register is part of a
+ * context, then any tuning settings should be programmed in an appropriate
+ * function invoked by __intel_engine_init_ctx_wa().
+ */
+static void
+add_render_compute_tuning_settings(struct drm_i915_private *i915,
+				   struct i915_wa_list *wal)
+{
+	if (IS_PONTEVECCHIO(i915)) {
+		wa_write(wal, XEHPC_L3SCRUB,
+			 SCRUB_CL_DWNGRADE_SHARED | SCRUB_RATE_4B_PER_CLK);
+	}
+
+	if (IS_DG2(i915)) {
+		wa_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS);
+		wa_write_clr_set(wal, RT_CTRL, STACKID_CTRL, STACKID_CTRL_512);
+		wa_write_clr_set(wal, DRAW_WATERMARK, VERT_WM_VAL,
+				 REG_FIELD_PREP(VERT_WM_VAL, 0x3FF));
+
+		/*
+		 * This is also listed as Wa_22012654132 for certain DG2
+		 * steppings, but the tuning setting programming is a superset
+		 * since it applies to all DG2 variants and steppings.
+		 *
+		 * Note that register 0xE420 is write-only and cannot be read
+		 * back for verification on DG2 (due to Wa_14012342262), so
+		 * we need to explicitly skip the readback.
+		 */
+		wa_add(wal, GEN10_CACHE_MODE_SS, 0,
+		       _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC),
+		       0 /* write-only, so skip validation */,
+		       true);
+	}
+}
+
 /*
  * The workarounds in this function apply to shared registers in
  * the general render reset domain that aren't tied to a
@@ -2683,14 +2718,9 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li
 {
 	struct drm_i915_private *i915 = engine->i915;
 
-	if (IS_PONTEVECCHIO(i915)) {
-		/*
-		 * The following is not actually a "workaround" but rather
-		 * a recommended tuning setting documented in the bspec's
-		 * performance guide section.
-		 */
-		wa_write(wal, XEHPC_L3SCRUB, SCRUB_CL_DWNGRADE_SHARED | SCRUB_RATE_4B_PER_CLK);
+	add_render_compute_tuning_settings(i915, wal);
 
+	if (IS_PONTEVECCHIO(i915)) {
 		/* Wa_16016694945 */
 		wa_masked_en(wal, XEHPC_LNCFMISCCFGREG0, XEHPC_OVRLSCCC);
 	}

drivers/gpu/drm/i915/gt/selftest_execlists.c

@@ -2077,7 +2077,7 @@ static int __cancel_active0(struct live_preempt_cancel *arg)
 		goto out;
 	}
 
-	intel_context_set_banned(rq->context);
+	intel_context_ban(rq->context, rq);
 	err = intel_engine_pulse(arg->engine);
 	if (err)
 		goto out;
@@ -2136,7 +2136,7 @@ static int __cancel_active1(struct live_preempt_cancel *arg)
 	if (err)
 		goto out;
 
-	intel_context_set_banned(rq[1]->context);
+	intel_context_ban(rq[1]->context, rq[1]);
 	err = intel_engine_pulse(arg->engine);
 	if (err)
 		goto out;
@@ -2219,7 +2219,7 @@ static int __cancel_queued(struct live_preempt_cancel *arg)
 	if (err)
 		goto out;
 
-	intel_context_set_banned(rq[2]->context);
+	intel_context_ban(rq[2]->context, rq[2]);
 	err = intel_engine_pulse(arg->engine);
 	if (err)
 		goto out;
@@ -2234,7 +2234,13 @@ static int __cancel_queued(struct live_preempt_cancel *arg)
 		goto out;
 	}
 
-	if (rq[1]->fence.error != 0) {
+	/*
+	 * The behavior between having semaphores and not is different. With
+	 * semaphores the subsequent request is on the hardware and not cancelled
+	 * while without the request is held in the driver and cancelled.
+	 */
+	if (intel_engine_has_semaphores(rq[1]->engine) &&
+	    rq[1]->fence.error != 0) {
 		pr_err("Normal inflight1 request did not complete\n");
 		err = -EINVAL;
 		goto out;
@@ -2282,7 +2288,7 @@ static int __cancel_hostile(struct live_preempt_cancel *arg)
 		goto out;
 	}
 
-	intel_context_set_banned(rq->context);
+	intel_context_ban(rq->context, rq);
 	err = intel_engine_pulse(arg->engine); /* force reset */
 	if (err)
 		goto out;

drivers/gpu/drm/i915/gt/selftest_hangcheck.c

@@ -1302,13 +1302,15 @@ static int igt_reset_wait(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct i915_gpu_error *global = &gt->i915->gpu_error;
-	struct intel_engine_cs *engine = gt->engine[RCS0];
+	struct intel_engine_cs *engine;
 	struct i915_request *rq;
 	unsigned int reset_count;
 	struct hang h;
 	long timeout;
 	int err;
 
+	engine = intel_selftest_find_any_engine(gt);
+
 	if (!engine || !intel_engine_can_store_dword(engine))
 		return 0;
 
@@ -1432,7 +1434,7 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 				 int (*fn)(void *),
 				 unsigned int flags)
 {
-	struct intel_engine_cs *engine = gt->engine[RCS0];
+	struct intel_engine_cs *engine;
 	struct drm_i915_gem_object *obj;
 	struct task_struct *tsk = NULL;
 	struct i915_request *rq;
@@ -1444,6 +1446,8 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 	if (!gt->ggtt->num_fences && flags & EXEC_OBJECT_NEEDS_FENCE)
 		return 0;
 
+	engine = intel_selftest_find_any_engine(gt);
+
 	if (!engine || !intel_engine_can_store_dword(engine))
 		return 0;
 
@@ -1819,12 +1823,14 @@ static int igt_handle_error(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct i915_gpu_error *global = &gt->i915->gpu_error;
-	struct intel_engine_cs *engine = gt->engine[RCS0];
+	struct intel_engine_cs *engine;
 	struct hang h;
 	struct i915_request *rq;
 	struct i915_gpu_coredump *error;
 	int err;
 
+	engine = intel_selftest_find_any_engine(gt);
+
 	/* Check that we can issue a global GPU and engine reset */
 
 	if (!intel_has_reset_engine(gt))

drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h

@@ -37,6 +37,7 @@
  *  |   |       |   - _`GUC_CTB_STATUS_OVERFLOW` = 1 (head/tail too large)     |
  *  |   |       |   - _`GUC_CTB_STATUS_UNDERFLOW` = 2 (truncated message)      |
  *  |   |       |   - _`GUC_CTB_STATUS_MISMATCH` = 4 (head/tail modified)      |
+ *  |   |       |   - _`GUC_CTB_STATUS_UNUSED` = 8 (CTB is not in use)         |
  *  +---+-------+--------------------------------------------------------------+
  *  |...|       | RESERVED = MBZ                                               |
  *  +---+-------+--------------------------------------------------------------+
@@ -49,9 +50,10 @@ struct guc_ct_buffer_desc {
 	u32 tail;
 	u32 status;
 #define GUC_CTB_STATUS_NO_ERROR				0
-#define GUC_CTB_STATUS_OVERFLOW				(1 << 0)
-#define GUC_CTB_STATUS_UNDERFLOW			(1 << 1)
-#define GUC_CTB_STATUS_MISMATCH				(1 << 2)
+#define GUC_CTB_STATUS_OVERFLOW				BIT(0)
+#define GUC_CTB_STATUS_UNDERFLOW			BIT(1)
+#define GUC_CTB_STATUS_MISMATCH				BIT(2)
+#define GUC_CTB_STATUS_UNUSED				BIT(3)
 	u32 reserved[13];
 } __packed;
 static_assert(sizeof(struct guc_ct_buffer_desc) == 64);

drivers/gpu/drm/i915/gt/uc/intel_guc.c

@@ -389,6 +389,25 @@ void intel_guc_write_params(struct intel_guc *guc)
 	intel_uncore_forcewake_put(uncore, FORCEWAKE_GT);
 }
 
+void intel_guc_dump_time_info(struct intel_guc *guc, struct drm_printer *p)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+	intel_wakeref_t wakeref;
+	u32 stamp = 0;
+	u64 ktime;
+
+	intel_device_info_print_runtime(RUNTIME_INFO(gt->i915), p);
+
+	with_intel_runtime_pm(&gt->i915->runtime_pm, wakeref)
+		stamp = intel_uncore_read(gt->uncore, GUCPMTIMESTAMP);
+	ktime = ktime_get_boottime_ns();
+
+	drm_printf(p, "Kernel timestamp: 0x%08llX [%llu]\n", ktime, ktime);
+	drm_printf(p, "GuC timestamp: 0x%08X [%u]\n", stamp, stamp);
+	drm_printf(p, "CS timestamp frequency: %u Hz, %u ns\n",
+		   gt->clock_frequency, gt->clock_period_ns);
+}
+
 int intel_guc_init(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);

drivers/gpu/drm/i915/gt/uc/intel_guc.h

@@ -464,4 +464,6 @@ void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p);
 
 void intel_guc_write_barrier(struct intel_guc *guc);
 
+void intel_guc_dump_time_info(struct intel_guc *guc, struct drm_printer *p);
+
 #endif

drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c

@@ -464,7 +464,11 @@ static void fill_engine_enable_masks(struct intel_gt *gt,
 }
 
 #define LR_HW_CONTEXT_SIZE (80 * sizeof(u32))
-#define LRC_SKIP_SIZE (LRC_PPHWSP_SZ * PAGE_SIZE + LR_HW_CONTEXT_SIZE)
+#define XEHP_LR_HW_CONTEXT_SIZE (96 * sizeof(u32))
+#define LR_HW_CONTEXT_SZ(i915) (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50) ? \
+				    XEHP_LR_HW_CONTEXT_SIZE : \
+				    LR_HW_CONTEXT_SIZE)
+#define LRC_SKIP_SIZE(i915) (LRC_PPHWSP_SZ * PAGE_SIZE + LR_HW_CONTEXT_SZ(i915))
 static int guc_prep_golden_context(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
@@ -525,7 +529,7 @@ static int guc_prep_golden_context(struct intel_guc *guc)
 		 * on all engines).
 		 */
 		ads_blob_write(guc, ads.eng_state_size[guc_class],
-			       real_size - LRC_SKIP_SIZE);
+			       real_size - LRC_SKIP_SIZE(gt->i915));
 		ads_blob_write(guc, ads.golden_context_lrca[guc_class],
 			       addr_ggtt);
 
@@ -599,7 +603,7 @@ static void guc_init_golden_context(struct intel_guc *guc)
 		}
 
 		GEM_BUG_ON(ads_blob_read(guc, ads.eng_state_size[guc_class]) !=
-			   real_size - LRC_SKIP_SIZE);
+			   real_size - LRC_SKIP_SIZE(gt->i915));
 		GEM_BUG_ON(ads_blob_read(guc, ads.golden_context_lrca[guc_class]) != addr_ggtt);
 
 		addr_ggtt += alloc_size;

drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c

@@ -600,10 +600,8 @@ intel_guc_capture_getnullheader(struct intel_guc *guc,
 	return 0;
 }
 
-#define GUC_CAPTURE_OVERBUFFER_MULTIPLIER 3
-
-int
-intel_guc_capture_output_min_size_est(struct intel_guc *guc)
+static int
+guc_capture_output_min_size_est(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
 	struct intel_engine_cs *engine;
@@ -623,13 +621,8 @@ intel_guc_capture_output_min_size_est(struct intel_guc *guc)
 	 * For each engine instance, there would be 1 x guc_state_capture_group_t output
 	 * followed by 3 x guc_state_capture_t lists. The latter is how the register
 	 * dumps are split across different register types (where the '3' are global vs class
-	 * vs instance). Finally, let's multiply the whole thing by 3x (just so we are
-	 * not limited to just 1 round of data in a worst case full register dump log)
-	 *
-	 * NOTE: intel_guc_log that allocates the log buffer would round this size up to
-	 * a power of two.
+	 * vs instance).
 	 */
-
 	for_each_engine(engine, gt, id) {
 		worst_min_size += sizeof(struct guc_state_capture_group_header_t) +
 					 (3 * sizeof(struct guc_state_capture_header_t));
@@ -649,7 +642,30 @@ intel_guc_capture_output_min_size_est(struct intel_guc *guc)
 
 	worst_min_size += (num_regs * sizeof(struct guc_mmio_reg));
 
-	return (worst_min_size * GUC_CAPTURE_OVERBUFFER_MULTIPLIER);
+	return worst_min_size;
+}
+
+/*
+ * Add on a 3x multiplier to allow for multiple back-to-back captures occurring
+ * before the i915 can read the data out and process it
+ */
+#define GUC_CAPTURE_OVERBUFFER_MULTIPLIER 3
+
+static void check_guc_capture_size(struct intel_guc *guc)
+{
+	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+	int min_size = guc_capture_output_min_size_est(guc);
+	int spare_size = min_size * GUC_CAPTURE_OVERBUFFER_MULTIPLIER;
+
+	if (min_size < 0)
+		drm_warn(&i915->drm, "Failed to calculate GuC error state capture buffer minimum size: %d!\n",
+			 min_size);
+	else if (min_size > CAPTURE_BUFFER_SIZE)
+		drm_warn(&i915->drm, "GuC error state capture buffer is too small: %d < %d\n",
+			 CAPTURE_BUFFER_SIZE, min_size);
+	else if (spare_size > CAPTURE_BUFFER_SIZE)
+		drm_notice(&i915->drm, "GuC error state capture buffer maybe too small: %d < %d (min = %d)\n",
+			   CAPTURE_BUFFER_SIZE, spare_size, min_size);
 }
 
 /*
@@ -1580,5 +1596,7 @@ int intel_guc_capture_init(struct intel_guc *guc)
 	INIT_LIST_HEAD(&guc->capture->outlist);
 	INIT_LIST_HEAD(&guc->capture->cachelist);
 
+	check_guc_capture_size(guc);
+
 	return 0;
 }

drivers/gpu/drm/i915/gt/uc/intel_guc_capture.h

@@ -21,7 +21,6 @@ int intel_guc_capture_print_engine_node(struct drm_i915_error_state_buf *m,
 void intel_guc_capture_get_matching_node(struct intel_gt *gt, struct intel_engine_coredump *ee,
 					 struct intel_context *ce);
 void intel_guc_capture_process(struct intel_guc *guc);
-int intel_guc_capture_output_min_size_est(struct intel_guc *guc);
 int intel_guc_capture_getlist(struct intel_guc *guc, u32 owner, u32 type, u32 classid,
 			      void **outptr);
 int intel_guc_capture_getlistsize(struct intel_guc *guc, u32 owner, u32 type, u32 classid,

drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c

@@ -455,6 +455,7 @@ static int ct_write(struct intel_guc_ct *ct,
 
 /**
  * wait_for_ct_request_update - Wait for CT request state update.
+ * @ct:		pointer to CT
  * @req:	pointer to pending request
  * @status:	placeholder for status
  *
@@ -467,9 +468,10 @@ static int ct_write(struct intel_guc_ct *ct,
  * *	0 response received (status is valid)
  * *	-ETIMEDOUT no response within hardcoded timeout
  */
-static int wait_for_ct_request_update(struct ct_request *req, u32 *status)
+static int wait_for_ct_request_update(struct intel_guc_ct *ct, struct ct_request *req, u32 *status)
 {
 	int err;
+	bool ct_enabled;
 
 	/*
 	 * Fast commands should complete in less than 10us, so sample quickly
@@ -481,12 +483,15 @@ static int wait_for_ct_request_update(struct ct_request *req, u32 *status)
 #define GUC_CTB_RESPONSE_TIMEOUT_SHORT_MS 10
 #define GUC_CTB_RESPONSE_TIMEOUT_LONG_MS 1000
 #define done \
-	(FIELD_GET(GUC_HXG_MSG_0_ORIGIN, READ_ONCE(req->status)) == \
+	(!(ct_enabled = intel_guc_ct_enabled(ct)) || \
+	 FIELD_GET(GUC_HXG_MSG_0_ORIGIN, READ_ONCE(req->status)) == \
 	 GUC_HXG_ORIGIN_GUC)
 	err = wait_for_us(done, GUC_CTB_RESPONSE_TIMEOUT_SHORT_MS);
 	if (err)
 		err = wait_for(done, GUC_CTB_RESPONSE_TIMEOUT_LONG_MS);
 #undef done
+	if (!ct_enabled)
+		err = -ENODEV;
 
 	*status = req->status;
 	return err;
@@ -703,11 +708,18 @@ static int ct_send(struct intel_guc_ct *ct,
 
 	intel_guc_notify(ct_to_guc(ct));
 
-	err = wait_for_ct_request_update(&request, status);
+	err = wait_for_ct_request_update(ct, &request, status);
 	g2h_release_space(ct, GUC_CTB_HXG_MSG_MAX_LEN);
 	if (unlikely(err)) {
-		CT_ERROR(ct, "No response for request %#x (fence %u)\n",
-			 action[0], request.fence);
+		if (err == -ENODEV)
+			/* wait_for_ct_request_update returns -ENODEV on reset/suspend in progress.
+			 * In this case, output is debug rather than error info
+			 */
+			CT_DEBUG(ct, "Request %#x (fence %u) cancelled as CTB is disabled\n",
+				 action[0], request.fence);
+		else
+			CT_ERROR(ct, "No response for request %#x (fence %u)\n",
+				 action[0], request.fence);
 		goto unlink;
 	}
 
@@ -771,8 +783,9 @@ int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len,
 
 	ret = ct_send(ct, action, len, response_buf, response_buf_size, &status);
 	if (unlikely(ret < 0)) {
-		CT_ERROR(ct, "Sending action %#x failed (%pe) status=%#X\n",
-			 action[0], ERR_PTR(ret), status);
+		if (ret != -ENODEV)
+			CT_ERROR(ct, "Sending action %#x failed (%pe) status=%#X\n",
+				 action[0], ERR_PTR(ret), status);
 	} else if (unlikely(ret)) {
 		CT_DEBUG(ct, "send action %#x returned %d (%#x)\n",
 			 action[0], ret, ret);
@@ -816,8 +829,22 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg)
 	if (unlikely(ctb->broken))
 		return -EPIPE;
 
-	if (unlikely(desc->status))
-		goto corrupted;
+	if (unlikely(desc->status)) {
+		u32 status = desc->status;
+
+		if (status & GUC_CTB_STATUS_UNUSED) {
+			/*
+			 * Potentially valid if a CLIENT_RESET request resulted in
+			 * contexts/engines being reset. But should never happen as
+			 * no contexts should be active when CLIENT_RESET is sent.
+			 */
+			CT_ERROR(ct, "Unexpected G2H after GuC has stopped!\n");
+			status &= ~GUC_CTB_STATUS_UNUSED;
+		}
+
+		if (status)
+			goto corrupted;
+	}
 
 	GEM_BUG_ON(head > size);
 

drivers/gpu/drm/i915/gt/uc/intel_guc_log.c

@@ -15,6 +15,32 @@
 
 static void guc_log_copy_debuglogs_for_relay(struct intel_guc_log *log);
 
+static u32 intel_guc_log_size(struct intel_guc_log *log)
+{
+	/*
+	 *  GuC Log buffer Layout:
+	 *
+	 *  NB: Ordering must follow "enum guc_log_buffer_type".
+	 *
+	 *  +===============================+ 00B
+	 *  |      Debug state header       |
+	 *  +-------------------------------+ 32B
+	 *  |    Crash dump state header    |
+	 *  +-------------------------------+ 64B
+	 *  |     Capture state header      |
+	 *  +-------------------------------+ 96B
+	 *  |                               |
+	 *  +===============================+ PAGE_SIZE (4KB)
+	 *  |          Debug logs           |
+	 *  +===============================+ + DEBUG_SIZE
+	 *  |        Crash Dump logs        |
+	 *  +===============================+ + CRASH_SIZE
+	 *  |         Capture logs          |
+	 *  +===============================+ + CAPTURE_SIZE
+	 */
+	return PAGE_SIZE + CRASH_BUFFER_SIZE + DEBUG_BUFFER_SIZE + CAPTURE_BUFFER_SIZE;
+}
+
 /**
  * DOC: GuC firmware log
  *
@@ -461,32 +487,7 @@ int intel_guc_log_create(struct intel_guc_log *log)
 
 	GEM_BUG_ON(log->vma);
 
-	/*
-	 *  GuC Log buffer Layout
-	 * (this ordering must follow "enum guc_log_buffer_type" definition)
-	 *
-	 *  +===============================+ 00B
-	 *  |      Debug state header       |
-	 *  +-------------------------------+ 32B
-	 *  |    Crash dump state header    |
-	 *  +-------------------------------+ 64B
-	 *  |     Capture state header      |
-	 *  +-------------------------------+ 96B
-	 *  |                               |
-	 *  +===============================+ PAGE_SIZE (4KB)
-	 *  |          Debug logs           |
-	 *  +===============================+ + DEBUG_SIZE
-	 *  |        Crash Dump logs        |
-	 *  +===============================+ + CRASH_SIZE
-	 *  |         Capture logs          |
-	 *  +===============================+ + CAPTURE_SIZE
-	 */
-	if (intel_guc_capture_output_min_size_est(guc) > CAPTURE_BUFFER_SIZE)
-		DRM_WARN("GuC log buffer for state_capture maybe too small. %d < %d\n",
-			 CAPTURE_BUFFER_SIZE, intel_guc_capture_output_min_size_est(guc));
-
-	guc_log_size = PAGE_SIZE + CRASH_BUFFER_SIZE + DEBUG_BUFFER_SIZE +
-		       CAPTURE_BUFFER_SIZE;
+	guc_log_size = intel_guc_log_size(log);
 
 	vma = intel_guc_allocate_vma(guc, guc_log_size);
 	if (IS_ERR(vma)) {
@@ -749,8 +750,9 @@ int intel_guc_log_dump(struct intel_guc_log *log, struct drm_printer *p,
 	struct intel_guc *guc = log_to_guc(log);
 	struct intel_uc *uc = container_of(guc, struct intel_uc, guc);
 	struct drm_i915_gem_object *obj = NULL;
-	u32 *map;
-	int i = 0;
+	void *map;
+	u32 *page;
+	int i, j;
 
 	if (!intel_guc_is_supported(guc))
 		return -ENODEV;
@@ -763,21 +765,34 @@ int intel_guc_log_dump(struct intel_guc_log *log, struct drm_printer *p,
 	if (!obj)
 		return 0;
 
+	page = (u32 *)__get_free_page(GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+
+	intel_guc_dump_time_info(guc, p);
+
 	map = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC);
 	if (IS_ERR(map)) {
 		DRM_DEBUG("Failed to pin object\n");
 		drm_puts(p, "(log data unaccessible)\n");
+		free_page((unsigned long)page);
 		return PTR_ERR(map);
 	}
 
-	for (i = 0; i < obj->base.size / sizeof(u32); i += 4)
-		drm_printf(p, "0x%08x 0x%08x 0x%08x 0x%08x\n",
-			   *(map + i), *(map + i + 1),
-			   *(map + i + 2), *(map + i + 3));
+	for (i = 0; i < obj->base.size; i += PAGE_SIZE) {
+		if (!i915_memcpy_from_wc(page, map + i, PAGE_SIZE))
+			memcpy(page, map + i, PAGE_SIZE);
+
+		for (j = 0; j < PAGE_SIZE / sizeof(u32); j += 4)
+			drm_printf(p, "0x%08x 0x%08x 0x%08x 0x%08x\n",
+				   *(page + j + 0), *(page + j + 1),
+				   *(page + j + 2), *(page + j + 3));
+	}
 
 	drm_puts(p, "\n");
 
 	i915_gem_object_unpin_map(obj);
+	free_page((unsigned long)page);
 
 	return 0;
 }

drivers/gpu/drm/i915/gt/uc/intel_guc_log.h

@@ -22,11 +22,11 @@ struct intel_guc;
 #elif defined(CONFIG_DRM_I915_DEBUG_GEM)
 #define CRASH_BUFFER_SIZE	SZ_1M
 #define DEBUG_BUFFER_SIZE	SZ_2M
-#define CAPTURE_BUFFER_SIZE	SZ_1M
+#define CAPTURE_BUFFER_SIZE	SZ_4M
 #else
 #define CRASH_BUFFER_SIZE	SZ_8K
 #define DEBUG_BUFFER_SIZE	SZ_64K
-#define CAPTURE_BUFFER_SIZE	SZ_16K
+#define CAPTURE_BUFFER_SIZE	SZ_2M
 #endif
 
 /*

drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h

@@ -102,6 +102,10 @@
 #define   GUC_SEND_TRIGGER		  (1<<0)
 #define GEN11_GUC_HOST_INTERRUPT	_MMIO(0x1901f0)
 
+#define GEN12_GUC_SEM_INTR_ENABLES	_MMIO(0xc71c)
+#define   GUC_SEM_INTR_ROUTE_TO_GUC	BIT(31)
+#define   GUC_SEM_INTR_ENABLE_ALL	(0xff)
+
 #define GUC_NUM_DOORBELLS		256
 
 /* format of the HW-monitored doorbell cacheline */

drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c

@@ -575,20 +575,24 @@ static int slpc_set_softlimits(struct intel_guc_slpc *slpc)
 	 * unless they have deviated from defaults, in which case,
 	 * we retain the values and set min/max accordingly.
 	 */
-	if (!slpc->max_freq_softlimit)
+	if (!slpc->max_freq_softlimit) {
 		slpc->max_freq_softlimit = slpc->rp0_freq;
-	else if (slpc->max_freq_softlimit != slpc->rp0_freq)
+		slpc_to_gt(slpc)->defaults.max_freq = slpc->max_freq_softlimit;
+	} else if (slpc->max_freq_softlimit != slpc->rp0_freq) {
 		ret = intel_guc_slpc_set_max_freq(slpc,
 						  slpc->max_freq_softlimit);
+	}
 
 	if (unlikely(ret))
 		return ret;
 
-	if (!slpc->min_freq_softlimit)
+	if (!slpc->min_freq_softlimit) {
 		slpc->min_freq_softlimit = slpc->min_freq;
-	else if (slpc->min_freq_softlimit != slpc->min_freq)
+		slpc_to_gt(slpc)->defaults.min_freq = slpc->min_freq_softlimit;
+	} else if (slpc->min_freq_softlimit != slpc->min_freq) {
 		return intel_guc_slpc_set_min_freq(slpc,
 						   slpc->min_freq_softlimit);
+	}
 
 	return 0;
 }

drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c

@@ -2420,7 +2420,6 @@ static int guc_context_policy_init_v70(struct intel_context *ce, bool loop)
 	struct context_policy policy;
 	u32 execution_quantum;
 	u32 preemption_timeout;
-	bool missing = false;
 	unsigned long flags;
 	int ret;
 
@@ -2438,32 +2437,9 @@ static int guc_context_policy_init_v70(struct intel_context *ce, bool loop)
 		__guc_context_policy_add_preempt_to_idle(&policy, 1);
 
 	ret = __guc_context_set_context_policies(guc, &policy, loop);
-	missing = ret != 0;
-
-	if (!missing && intel_context_is_parent(ce)) {
-		struct intel_context *child;
-
-		for_each_child(ce, child) {
-			__guc_context_policy_start_klv(&policy, child->guc_id.id);
-
-			if (engine->flags & I915_ENGINE_WANT_FORCED_PREEMPTION)
-				__guc_context_policy_add_preempt_to_idle(&policy, 1);
-
-			child->guc_state.prio = ce->guc_state.prio;
-			__guc_context_policy_add_priority(&policy, ce->guc_state.prio);
-			__guc_context_policy_add_execution_quantum(&policy, execution_quantum);
-			__guc_context_policy_add_preemption_timeout(&policy, preemption_timeout);
-
-			ret = __guc_context_set_context_policies(guc, &policy, loop);
-			if (ret) {
-				missing = true;
-				break;
-			}
-		}
-	}
 
 	spin_lock_irqsave(&ce->guc_state.lock, flags);
-	if (missing)
+	if (ret != 0)
 		set_context_policy_required(ce);
 	else
 		clr_context_policy_required(ce);
@@ -4191,13 +4167,27 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine)
 
 void intel_guc_submission_enable(struct intel_guc *guc)
 {
+	struct intel_gt *gt = guc_to_gt(guc);
+
+	/* Enable and route to GuC */
+	if (GRAPHICS_VER(gt->i915) >= 12)
+		intel_uncore_write(gt->uncore, GEN12_GUC_SEM_INTR_ENABLES,
+				   GUC_SEM_INTR_ROUTE_TO_GUC |
+				   GUC_SEM_INTR_ENABLE_ALL);
+
 	guc_init_lrc_mapping(guc);
 	guc_init_engine_stats(guc);
 }
 
 void intel_guc_submission_disable(struct intel_guc *guc)
 {
+	struct intel_gt *gt = guc_to_gt(guc);
+
 	/* Note: By the time we're here, GuC may have already been reset */
+
+	/* Disable and route to host */
+	if (GRAPHICS_VER(gt->i915) >= 12)
+		intel_uncore_write(gt->uncore, GEN12_GUC_SEM_INTR_ENABLES, 0x0);
 }
 
 static bool __guc_submission_supported(struct intel_guc *guc)
@@ -5163,4 +5153,5 @@ bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve)
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftest_guc.c"
 #include "selftest_guc_multi_lrc.c"
+#include "selftest_guc_hangcheck.c"
 #endif

drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c

@@ -53,7 +53,7 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
  * firmware as TGL.
  */
 #define INTEL_GUC_FIRMWARE_DEFS(fw_def, guc_def) \
-	fw_def(DG2,          0, guc_def(dg2,  70, 1, 2)) \
+	fw_def(DG2,          0, guc_def(dg2,  70, 4, 1)) \
 	fw_def(ALDERLAKE_P,  0, guc_def(adlp, 70, 1, 1)) \
 	fw_def(ALDERLAKE_S,  0, guc_def(tgl,  70, 1, 1)) \
 	fw_def(DG1,          0, guc_def(dg1,  70, 1, 1)) \
@@ -220,11 +220,11 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw)
 			    fw_blobs[i].rev < fw_blobs[i - 1].rev)
 				continue;
 
-			pr_err("invalid FW blob order: %s r%u comes before %s r%u\n",
-			       intel_platform_name(fw_blobs[i - 1].p),
-			       fw_blobs[i - 1].rev,
-			       intel_platform_name(fw_blobs[i].p),
-			       fw_blobs[i].rev);
+			drm_err(&i915->drm, "Invalid FW blob order: %s r%u comes before %s r%u\n",
+				intel_platform_name(fw_blobs[i - 1].p),
+				fw_blobs[i - 1].rev,
+				intel_platform_name(fw_blobs[i].p),
+				fw_blobs[i].rev);
 
 			uc_fw->path = NULL;
 		}

drivers/gpu/drm/i915/gt/uc/selftest_guc.c

@@ -62,7 +62,7 @@ static int intel_guc_scrub_ctbs(void *arg)
 		ce = intel_context_create(engine);
 		if (IS_ERR(ce)) {
 			ret = PTR_ERR(ce);
-			pr_err("Failed to create context, %d: %d\n", i, ret);
+			drm_err(&gt->i915->drm, "Failed to create context, %d: %d\n", i, ret);
 			goto err;
 		}
 
@@ -83,7 +83,7 @@ static int intel_guc_scrub_ctbs(void *arg)
 
 		if (IS_ERR(rq)) {
 			ret = PTR_ERR(rq);
-			pr_err("Failed to create request, %d: %d\n", i, ret);
+			drm_err(&gt->i915->drm, "Failed to create request, %d: %d\n", i, ret);
 			goto err;
 		}
 
@@ -93,7 +93,7 @@ static int intel_guc_scrub_ctbs(void *arg)
 	for (i = 0; i < 3; ++i) {
 		ret = i915_request_wait(last[i], 0, HZ);
 		if (ret < 0) {
-			pr_err("Last request failed to complete: %d\n", ret);
+			drm_err(&gt->i915->drm, "Last request failed to complete: %d\n", ret);
 			goto err;
 		}
 		i915_request_put(last[i]);
@@ -110,7 +110,7 @@ static int intel_guc_scrub_ctbs(void *arg)
 	/* GT will not idle if G2H are lost */
 	ret = intel_gt_wait_for_idle(gt, HZ);
 	if (ret < 0) {
-		pr_err("GT failed to idle: %d\n", ret);
+		drm_err(&gt->i915->drm, "GT failed to idle: %d\n", ret);
 		goto err;
 	}
 
@@ -150,7 +150,7 @@ static int intel_guc_steal_guc_ids(void *arg)
 
 	ce = kcalloc(GUC_MAX_CONTEXT_ID, sizeof(*ce), GFP_KERNEL);
 	if (!ce) {
-		pr_err("Context array allocation failed\n");
+		drm_err(&gt->i915->drm, "Context array allocation failed\n");
 		return -ENOMEM;
 	}
 
@@ -164,24 +164,24 @@ static int intel_guc_steal_guc_ids(void *arg)
 	if (IS_ERR(ce[context_index])) {
 		ret = PTR_ERR(ce[context_index]);
 		ce[context_index] = NULL;
-		pr_err("Failed to create context: %d\n", ret);
+		drm_err(&gt->i915->drm, "Failed to create context: %d\n", ret);
 		goto err_wakeref;
 	}
 	ret = igt_spinner_init(&spin, engine->gt);
 	if (ret) {
-		pr_err("Failed to create spinner: %d\n", ret);
+		drm_err(&gt->i915->drm, "Failed to create spinner: %d\n", ret);
 		goto err_contexts;
 	}
 	spin_rq = igt_spinner_create_request(&spin, ce[context_index],
 					     MI_ARB_CHECK);
 	if (IS_ERR(spin_rq)) {
 		ret = PTR_ERR(spin_rq);
-		pr_err("Failed to create spinner request: %d\n", ret);
+		drm_err(&gt->i915->drm, "Failed to create spinner request: %d\n", ret);
 		goto err_contexts;
 	}
 	ret = request_add_spin(spin_rq, &spin);
 	if (ret) {
-		pr_err("Failed to add Spinner request: %d\n", ret);
+		drm_err(&gt->i915->drm, "Failed to add Spinner request: %d\n", ret);
 		goto err_spin_rq;
 	}
 
@@ -191,7 +191,7 @@ static int intel_guc_steal_guc_ids(void *arg)
 		if (IS_ERR(ce[context_index])) {
 			ret = PTR_ERR(ce[context_index--]);
 			ce[context_index] = NULL;
-			pr_err("Failed to create context: %d\n", ret);
+			drm_err(&gt->i915->drm, "Failed to create context: %d\n", ret);
 			goto err_spin_rq;
 		}
 
@@ -200,8 +200,8 @@ static int intel_guc_steal_guc_ids(void *arg)
 			ret = PTR_ERR(rq);
 			rq = NULL;
 			if (ret != -EAGAIN) {
-				pr_err("Failed to create request, %d: %d\n",
-				       context_index, ret);
+				drm_err(&gt->i915->drm, "Failed to create request, %d: %d\n",
+					context_index, ret);
 				goto err_spin_rq;
 			}
 		} else {
@@ -215,7 +215,7 @@ static int intel_guc_steal_guc_ids(void *arg)
 	igt_spinner_end(&spin);
 	ret = intel_selftest_wait_for_rq(spin_rq);
 	if (ret) {
-		pr_err("Spin request failed to complete: %d\n", ret);
+		drm_err(&gt->i915->drm, "Spin request failed to complete: %d\n", ret);
 		i915_request_put(last);
 		goto err_spin_rq;
 	}
@@ -227,7 +227,7 @@ static int intel_guc_steal_guc_ids(void *arg)
 	ret = i915_request_wait(last, 0, HZ * 30);
 	i915_request_put(last);
 	if (ret < 0) {
-		pr_err("Last request failed to complete: %d\n", ret);
+		drm_err(&gt->i915->drm, "Last request failed to complete: %d\n", ret);
 		goto err_spin_rq;
 	}
 
@@ -235,7 +235,7 @@ static int intel_guc_steal_guc_ids(void *arg)
 	rq = nop_user_request(ce[context_index], NULL);
 	if (IS_ERR(rq)) {
 		ret = PTR_ERR(rq);
-		pr_err("Failed to steal guc_id, %d: %d\n", context_index, ret);
+		drm_err(&gt->i915->drm, "Failed to steal guc_id, %d: %d\n", context_index, ret);
 		goto err_spin_rq;
 	}
 
@@ -243,21 +243,20 @@ static int intel_guc_steal_guc_ids(void *arg)
 	ret = i915_request_wait(rq, 0, HZ);
 	i915_request_put(rq);
 	if (ret < 0) {
-		pr_err("Request with stolen guc_id failed to complete: %d\n",
-		       ret);
+		drm_err(&gt->i915->drm, "Request with stolen guc_id failed to complete: %d\n", ret);
 		goto err_spin_rq;
 	}
 
 	/* Wait for idle */
 	ret = intel_gt_wait_for_idle(gt, HZ * 30);
 	if (ret < 0) {
-		pr_err("GT failed to idle: %d\n", ret);
+		drm_err(&gt->i915->drm, "GT failed to idle: %d\n", ret);
 		goto err_spin_rq;
 	}
 
 	/* Verify a guc_id was stolen */
 	if (guc->number_guc_id_stolen == number_guc_id_stolen) {
-		pr_err("No guc_id was stolen");
+		drm_err(&gt->i915->drm, "No guc_id was stolen");
 		ret = -EINVAL;
 	} else {
 		ret = 0;

drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c

+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#include "selftests/igt_spinner.h"
+#include "selftests/igt_reset.h"
+#include "selftests/intel_scheduler_helpers.h"
+#include "gt/intel_engine_heartbeat.h"
+#include "gem/selftests/mock_context.h"
+
+#define BEAT_INTERVAL	100
+
+static struct i915_request *nop_request(struct intel_engine_cs *engine)
+{
+	struct i915_request *rq;
+
+	rq = intel_engine_create_kernel_request(engine);
+	if (IS_ERR(rq))
+		return rq;
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+
+	return rq;
+}
+
+static int intel_hang_guc(void *arg)
+{
+	struct intel_gt *gt = arg;
+	int ret = 0;
+	struct i915_gem_context *ctx;
+	struct intel_context *ce;
+	struct igt_spinner spin;
+	struct i915_request *rq;
+	intel_wakeref_t wakeref;
+	struct i915_gpu_error *global = &gt->i915->gpu_error;
+	struct intel_engine_cs *engine;
+	unsigned int reset_count;
+	u32 guc_status;
+	u32 old_beat;
+
+	ctx = kernel_context(gt->i915, NULL);
+	if (IS_ERR(ctx)) {
+		drm_err(&gt->i915->drm, "Failed get kernel context: %ld\n", PTR_ERR(ctx));
+		return PTR_ERR(ctx);
+	}
+
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
+
+	ce = intel_context_create(gt->engine[BCS0]);
+	if (IS_ERR(ce)) {
+		ret = PTR_ERR(ce);
+		drm_err(&gt->i915->drm, "Failed to create spinner request: %d\n", ret);
+		goto err;
+	}
+
+	engine = ce->engine;
+	reset_count = i915_reset_count(global);
+
+	old_beat = engine->props.heartbeat_interval_ms;
+	ret = intel_engine_set_heartbeat(engine, BEAT_INTERVAL);
+	if (ret) {
+		drm_err(&gt->i915->drm, "Failed to boost heatbeat interval: %d\n", ret);
+		goto err;
+	}
+
+	ret = igt_spinner_init(&spin, engine->gt);
+	if (ret) {
+		drm_err(&gt->i915->drm, "Failed to create spinner: %d\n", ret);
+		goto err;
+	}
+
+	rq = igt_spinner_create_request(&spin, ce, MI_NOOP);
+	intel_context_put(ce);
+	if (IS_ERR(rq)) {
+		ret = PTR_ERR(rq);
+		drm_err(&gt->i915->drm, "Failed to create spinner request: %d\n", ret);
+		goto err_spin;
+	}
+
+	ret = request_add_spin(rq, &spin);
+	if (ret) {
+		i915_request_put(rq);
+		drm_err(&gt->i915->drm, "Failed to add Spinner request: %d\n", ret);
+		goto err_spin;
+	}
+
+	ret = intel_reset_guc(gt);
+	if (ret) {
+		i915_request_put(rq);
+		drm_err(&gt->i915->drm, "Failed to reset GuC, ret = %d\n", ret);
+		goto err_spin;
+	}
+
+	guc_status = intel_uncore_read(gt->uncore, GUC_STATUS);
+	if (!(guc_status & GS_MIA_IN_RESET)) {
+		i915_request_put(rq);
+		drm_err(&gt->i915->drm, "GuC failed to reset: status = 0x%08X\n", guc_status);
+		ret = -EIO;
+		goto err_spin;
+	}
+
+	/* Wait for the heartbeat to cause a reset */
+	ret = intel_selftest_wait_for_rq(rq);
+	i915_request_put(rq);
+	if (ret) {
+		drm_err(&gt->i915->drm, "Request failed to complete: %d\n", ret);
+		goto err_spin;
+	}
+
+	if (i915_reset_count(global) == reset_count) {
+		drm_err(&gt->i915->drm, "Failed to record a GPU reset\n");
+		ret = -EINVAL;
+		goto err_spin;
+	}
+
+err_spin:
+	igt_spinner_end(&spin);
+	igt_spinner_fini(&spin);
+	intel_engine_set_heartbeat(engine, old_beat);
+
+	if (ret == 0) {
+		rq = nop_request(engine);
+		if (IS_ERR(rq)) {
+			ret = PTR_ERR(rq);
+			goto err;
+		}
+
+		ret = intel_selftest_wait_for_rq(rq);
+		i915_request_put(rq);
+		if (ret) {
+			drm_err(&gt->i915->drm, "No-op failed to complete: %d\n", ret);
+			goto err;
+		}
+	}
+
+err:
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
+	kernel_context_close(ctx);
+
+	return ret;
+}
+
+int intel_guc_hang_check(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(intel_hang_guc),
+	};
+	struct intel_gt *gt = to_gt(i915);
+
+	if (intel_gt_is_wedged(gt))
+		return 0;
+
+	if (!intel_uc_uses_guc_submission(&gt->uc))
+		return 0;
+
+	return intel_gt_live_subtests(tests, gt);
+}

drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c

@@ -115,30 +115,30 @@ static int __intel_guc_multi_lrc_basic(struct intel_gt *gt, unsigned int class)
 
 	parent = multi_lrc_create_parent(gt, class, 0);
 	if (IS_ERR(parent)) {
-		pr_err("Failed creating contexts: %ld", PTR_ERR(parent));
+		drm_err(&gt->i915->drm, "Failed creating contexts: %ld", PTR_ERR(parent));
 		return PTR_ERR(parent);
 	} else if (!parent) {
-		pr_debug("Not enough engines in class: %d", class);
+		drm_dbg(&gt->i915->drm, "Not enough engines in class: %d", class);
 		return 0;
 	}
 
 	rq = multi_lrc_nop_request(parent);
 	if (IS_ERR(rq)) {
 		ret = PTR_ERR(rq);
-		pr_err("Failed creating requests: %d", ret);
+		drm_err(&gt->i915->drm, "Failed creating requests: %d", ret);
 		goto out;
 	}
 
 	ret = intel_selftest_wait_for_rq(rq);
 	if (ret)
-		pr_err("Failed waiting on request: %d", ret);
+		drm_err(&gt->i915->drm, "Failed waiting on request: %d", ret);
 
 	i915_request_put(rq);
 
 	if (ret >= 0) {
 		ret = intel_gt_wait_for_idle(gt, HZ * 5);
 		if (ret < 0)
-			pr_err("GT failed to idle: %d\n", ret);
+			drm_err(&gt->i915->drm, "GT failed to idle: %d\n", ret);
 	}
 
 out:

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -671,6 +671,18 @@ static void err_print_pciid(struct drm_i915_error_state_buf *m,
 		   pdev->subsystem_device);
 }
 
+static void err_print_guc_ctb(struct drm_i915_error_state_buf *m,
+			      const char *name,
+			      const struct intel_ctb_coredump *ctb)
+{
+	if (!ctb->size)
+		return;
+
+	err_printf(m, "GuC %s CTB: raw: 0x%08X, 0x%08X/%08X, cached: 0x%08X/%08X, desc = 0x%08X, buf = 0x%08X x 0x%08X\n",
+		   name, ctb->raw_status, ctb->raw_head, ctb->raw_tail,
+		   ctb->head, ctb->tail, ctb->desc_offset, ctb->cmds_offset, ctb->size);
+}
+
 static void err_print_uc(struct drm_i915_error_state_buf *m,
 			 const struct intel_uc_coredump *error_uc)
 {
@@ -678,7 +690,12 @@ static void err_print_uc(struct drm_i915_error_state_buf *m,
 
 	intel_uc_fw_dump(&error_uc->guc_fw, &p);
 	intel_uc_fw_dump(&error_uc->huc_fw, &p);
-	intel_gpu_error_print_vma(m, NULL, error_uc->guc_log);
+	err_printf(m, "GuC timestamp: 0x%08x\n", error_uc->guc.timestamp);
+	intel_gpu_error_print_vma(m, NULL, error_uc->guc.vma_log);
+	err_printf(m, "GuC CTB fence: %d\n", error_uc->guc.last_fence);
+	err_print_guc_ctb(m, "Send", error_uc->guc.ctb + 0);
+	err_print_guc_ctb(m, "Recv", error_uc->guc.ctb + 1);
+	intel_gpu_error_print_vma(m, NULL, error_uc->guc.vma_ctb);
 }
 
 static void err_free_sgl(struct scatterlist *sgl)
@@ -720,6 +737,8 @@ static void err_print_gt_global_nonguc(struct drm_i915_error_state_buf *m,
 	int i;
 
 	err_printf(m, "GT awake: %s\n", str_yes_no(gt->awake));
+	err_printf(m, "CS timestamp frequency: %u Hz, %d ns\n",
+		   gt->clock_frequency, gt->clock_period_ns);
 	err_printf(m, "EIR: 0x%08x\n", gt->eir);
 	err_printf(m, "PGTBL_ER: 0x%08x\n", gt->pgtbl_er);
 
@@ -851,7 +870,7 @@ static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
 	if (error->gt) {
 		bool print_guc_capture = false;
 
-		if (error->gt->uc && error->gt->uc->is_guc_capture)
+		if (error->gt->uc && error->gt->uc->guc.is_guc_capture)
 			print_guc_capture = true;
 
 		err_print_gt_display(m, error->gt);
@@ -1006,7 +1025,8 @@ static void cleanup_uc(struct intel_uc_coredump *uc)
 {
 	kfree(uc->guc_fw.path);
 	kfree(uc->huc_fw.path);
-	i915_vma_coredump_free(uc->guc_log);
+	i915_vma_coredump_free(uc->guc.vma_log);
+	i915_vma_coredump_free(uc->guc.vma_ctb);
 
 	kfree(uc);
 }
@@ -1655,6 +1675,23 @@ gt_record_engines(struct intel_gt_coredump *gt,
 	}
 }
 
+static void gt_record_guc_ctb(struct intel_ctb_coredump *saved,
+			      const struct intel_guc_ct_buffer *ctb,
+			      const void *blob_ptr, struct intel_guc *guc)
+{
+	if (!ctb || !ctb->desc)
+		return;
+
+	saved->raw_status = ctb->desc->status;
+	saved->raw_head = ctb->desc->head;
+	saved->raw_tail = ctb->desc->tail;
+	saved->head = ctb->head;
+	saved->tail = ctb->tail;
+	saved->size = ctb->size;
+	saved->desc_offset = ((void *)ctb->desc) - blob_ptr;
+	saved->cmds_offset = ((void *)ctb->cmds) - blob_ptr;
+}
+
 static struct intel_uc_coredump *
 gt_record_uc(struct intel_gt_coredump *gt,
 	     struct i915_vma_compress *compress)
@@ -1675,8 +1712,22 @@ gt_record_uc(struct intel_gt_coredump *gt,
 	 */
 	error_uc->guc_fw.path = kstrdup(uc->guc.fw.path, ALLOW_FAIL);
 	error_uc->huc_fw.path = kstrdup(uc->huc.fw.path, ALLOW_FAIL);
-	error_uc->guc_log = create_vma_coredump(gt->_gt, uc->guc.log.vma,
-						"GuC log buffer", compress);
+
+	/*
+	 * Save the GuC log and include a timestamp reference for converting the
+	 * log times to system times (in conjunction with the error->boottime and
+	 * gt->clock_frequency fields saved elsewhere).
+	 */
+	error_uc->guc.timestamp = intel_uncore_read(gt->_gt->uncore, GUCPMTIMESTAMP);
+	error_uc->guc.vma_log = create_vma_coredump(gt->_gt, uc->guc.log.vma,
+						    "GuC log buffer", compress);
+	error_uc->guc.vma_ctb = create_vma_coredump(gt->_gt, uc->guc.ct.vma,
+						    "GuC CT buffer", compress);
+	error_uc->guc.last_fence = uc->guc.ct.requests.last_fence;
+	gt_record_guc_ctb(error_uc->guc.ctb + 0, &uc->guc.ct.ctbs.send,
+			  uc->guc.ct.ctbs.send.desc, (struct intel_guc *)&uc->guc);
+	gt_record_guc_ctb(error_uc->guc.ctb + 1, &uc->guc.ct.ctbs.recv,
+			  uc->guc.ct.ctbs.send.desc, (struct intel_guc *)&uc->guc);
 
 	return error_uc;
 }
@@ -1833,6 +1884,8 @@ static void gt_record_global_regs(struct intel_gt_coredump *gt)
 static void gt_record_info(struct intel_gt_coredump *gt)
 {
 	memcpy(&gt->info, &gt->_gt->info, sizeof(struct intel_gt_info));
+	gt->clock_frequency = gt->_gt->clock_frequency;
+	gt->clock_period_ns = gt->_gt->clock_period_ns;
 }
 
 /*
@@ -2027,9 +2080,9 @@ __i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask, u32 du
 			error->gt->uc = gt_record_uc(error->gt, compress);
 			if (error->gt->uc) {
 				if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE)
-					error->gt->uc->is_guc_capture = true;
+					error->gt->uc->guc.is_guc_capture = true;
 				else
-					GEM_BUG_ON(error->gt->uc->is_guc_capture);
+					GEM_BUG_ON(error->gt->uc->guc.is_guc_capture);
 			}
 		}
 

drivers/gpu/drm/i915/i915_gpu_error.h

@@ -125,6 +125,15 @@ struct intel_engine_coredump {
 	struct intel_engine_coredump *next;
 };
 
+struct intel_ctb_coredump {
+	u32 raw_head, head;
+	u32 raw_tail, tail;
+	u32 raw_status;
+	u32 desc_offset;
+	u32 cmds_offset;
+	u32 size;
+};
+
 struct intel_gt_coredump {
 	const struct intel_gt *_gt;
 	bool awake;
@@ -150,6 +159,8 @@ struct intel_gt_coredump {
 	u32 gtt_cache;
 	u32 aux_err; /* gen12 */
 	u32 gam_done; /* gen12 */
+	u32 clock_frequency;
+	u32 clock_period_ns;
 
 	/* Display related */
 	u32 derrmr;
@@ -163,8 +174,14 @@ struct intel_gt_coredump {
 	struct intel_uc_coredump {
 		struct intel_uc_fw guc_fw;
 		struct intel_uc_fw huc_fw;
-		struct i915_vma_coredump *guc_log;
-		bool is_guc_capture;
+		struct guc_info {
+			struct intel_ctb_coredump ctb[2];
+			struct i915_vma_coredump *vma_ctb;
+			struct i915_vma_coredump *vma_log;
+			u32 timestamp;
+			u16 last_fence;
+			bool is_guc_capture;
+		} guc;
 	} *uc;
 
 	struct intel_gt_coredump *next;

drivers/gpu/drm/i915/i915_vma_resource.c

@@ -216,6 +216,10 @@ i915_vma_resource_fence_notify(struct i915_sw_fence *fence,
 /**
  * i915_vma_resource_unbind - Unbind a vma resource
  * @vma_res: The vma resource to unbind.
+ * @tlb: pointer to vma->obj->mm.tlb associated with the resource
+ *	 to be stored at vma_res->tlb. When not-NULL, it will be used
+ *	 to do TLB cache invalidation before freeing a VMA resource.
+ *	 Used only for async unbind.
  *
  * At this point this function does little more than publish a fence that
  * signals immediately unless signaling is held back.

drivers/gpu/drm/i915/selftests/i915_live_selftests.h

@@ -49,5 +49,6 @@ selftest(perf, i915_perf_live_selftests)
 selftest(slpc, intel_slpc_live_selftests)
 selftest(guc, intel_guc_live_selftests)
 selftest(guc_multi_lrc, intel_guc_multi_lrc_live_selftests)
+selftest(guc_hang, intel_guc_hang_check)
 /* Here be dragons: keep last to run last! */
 selftest(late_gt_pm, intel_gt_pm_late_selftests)

drivers/gpu/drm/i915/selftests/i915_request.c

@@ -971,7 +971,7 @@ static struct i915_vma *empty_batch(struct drm_i915_private *i915)
 	if (err)
 		goto err;
 
-	/* Force the wait wait now to avoid including it in the benchmark */
+	/* Force the wait now to avoid including it in the benchmark */
 	err = i915_vma_sync(vma);
 	if (err)
 		goto err_pin;