1 files changed, 134 insertions, 130 deletions

diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c
index 4e746ae98888..bcb85a1bf26d 100644
--- a/drivers/gpu/drm/xe/xe_guc_ads.c
+++ b/drivers/gpu/drm/xe/xe_guc_ads.c
@@ -18,8 +18,10 @@
 #include "xe_bo.h"
 #include "xe_gt.h"
 #include "xe_gt_ccs_mode.h"
+#include "xe_gt_mcr.h"
 #include "xe_gt_printk.h"
 #include "xe_guc.h"
+#include "xe_guc_buf.h"
 #include "xe_guc_capture.h"
 #include "xe_guc_ct.h"
 #include "xe_hw_engine.h"
@@ -231,11 +233,6 @@ static size_t guc_ads_size(struct xe_guc_ads *ads)
 		guc_ads_private_data_size(ads);
 }
 
-static bool needs_wa_1607983814(struct xe_device *xe)
-{
-	return GRAPHICS_VERx100(xe) < 1250;
-}
-
 static size_t calculate_regset_size(struct xe_gt *gt)
 {
 	struct xe_reg_sr_entry *sr_entry;
@@ -250,7 +247,7 @@ static size_t calculate_regset_size(struct xe_gt *gt)
 
 	count += ADS_REGSET_EXTRA_MAX * XE_NUM_HW_ENGINES;
 
-	if (needs_wa_1607983814(gt_to_xe(gt)))
+	if (XE_GT_WA(gt, 1607983814))
 		count += LNCFCMOCS_REG_COUNT;
 
 	return count * sizeof(struct guc_mmio_reg);
@@ -287,52 +284,26 @@ static size_t calculate_golden_lrc_size(struct xe_guc_ads *ads)
 	return total_size;
 }
 
-static void guc_waklv_enable_one_word(struct xe_guc_ads *ads,
-				      enum xe_guc_klv_ids klv_id,
-				      u32 value,
-				      u32 *offset, u32 *remain)
+static void guc_waklv_enable(struct xe_guc_ads *ads,
+			     u32 data[], u32 data_len_dw,
+			     u32 *offset, u32 *remain,
+			     enum xe_guc_klv_ids klv_id)
 {
-	u32 size;
-	u32 klv_entry[] = {
-		/* 16:16 key/length */
-		FIELD_PREP(GUC_KLV_0_KEY, klv_id) |
-		FIELD_PREP(GUC_KLV_0_LEN, 1),
-		value,
-		/* 1 dword data */
-	};
-
-	size = sizeof(klv_entry);
+	size_t size = sizeof(u32) * (1 + data_len_dw);
 
 	if (*remain < size) {
 		drm_warn(&ads_to_xe(ads)->drm,
-			 "w/a klv buffer too small to add klv id %d\n", klv_id);
-	} else {
-		xe_map_memcpy_to(ads_to_xe(ads), ads_to_map(ads), *offset,
-				 klv_entry, size);
-		*offset += size;
-		*remain -= size;
+			 "w/a klv buffer too small to add klv id 0x%04X\n", klv_id);
+		return;
 	}
-}
-
-static void guc_waklv_enable_simple(struct xe_guc_ads *ads,
-				    enum xe_guc_klv_ids klv_id, u32 *offset, u32 *remain)
-{
-	u32 klv_entry[] = {
-		/* 16:16 key/length */
-		FIELD_PREP(GUC_KLV_0_KEY, klv_id) |
-		FIELD_PREP(GUC_KLV_0_LEN, 0),
-		/* 0 dwords data */
-	};
-	u32 size;
-
-	size = sizeof(klv_entry);
 
-	if (xe_gt_WARN(ads_to_gt(ads), *remain < size,
-		       "w/a klv buffer too small to add klv id %d\n", klv_id))
-		return;
+	/* 16:16 key/length */
+	xe_map_wr(ads_to_xe(ads), ads_to_map(ads), *offset, u32,
+		  FIELD_PREP(GUC_KLV_0_KEY, klv_id) | FIELD_PREP(GUC_KLV_0_LEN, data_len_dw));
+	/* data_len_dw dwords of data */
+	xe_map_memcpy_to(ads_to_xe(ads), ads_to_map(ads),
+			 *offset + sizeof(u32), data, data_len_dw * sizeof(u32));
 
-	xe_map_memcpy_to(ads_to_xe(ads), ads_to_map(ads), *offset,
-			 klv_entry, size);
 	*offset += size;
 	*remain -= size;
 }
@@ -346,39 +317,51 @@ static void guc_waklv_init(struct xe_guc_ads *ads)
 	offset = guc_ads_waklv_offset(ads);
 	remain = guc_ads_waklv_size(ads);
 
-	if (XE_WA(gt, 14019882105))
-		guc_waklv_enable_simple(ads,
-					GUC_WORKAROUND_KLV_BLOCK_INTERRUPTS_WHEN_MGSR_BLOCKED,
-					&offset, &remain);
-	if (XE_WA(gt, 18024947630))
-		guc_waklv_enable_simple(ads,
-					GUC_WORKAROUND_KLV_ID_GAM_PFQ_SHADOW_TAIL_POLLING,
-					&offset, &remain);
-	if (XE_WA(gt, 16022287689))
-		guc_waklv_enable_simple(ads,
-					GUC_WORKAROUND_KLV_ID_DISABLE_MTP_DURING_ASYNC_COMPUTE,
-					&offset, &remain);
-
-	if (XE_WA(gt, 14022866841))
-		guc_waklv_enable_simple(ads,
-					GUC_WA_KLV_WAKE_POWER_DOMAINS_FOR_OUTBOUND_MMIO,
-					&offset, &remain);
+	if (XE_GT_WA(gt, 14019882105) || XE_GT_WA(gt, 16021333562))
+		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
+				 GUC_WORKAROUND_KLV_BLOCK_INTERRUPTS_WHEN_MGSR_BLOCKED);
+	if (XE_GT_WA(gt, 18024947630))
+		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
+				 GUC_WORKAROUND_KLV_ID_GAM_PFQ_SHADOW_TAIL_POLLING);
+	if (XE_GT_WA(gt, 16022287689))
+		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
+				 GUC_WORKAROUND_KLV_ID_DISABLE_MTP_DURING_ASYNC_COMPUTE);
+
+	if (XE_GT_WA(gt, 14022866841))
+		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
+				 GUC_WA_KLV_WAKE_POWER_DOMAINS_FOR_OUTBOUND_MMIO);
 
 	/*
 	 * On RC6 exit, GuC will write register 0xB04 with the default value provided. As of now,
 	 * the default value for this register is determined to be 0xC40. This could change in the
 	 * future, so GuC depends on KMD to send it the correct value.
 	 */
-	if (XE_WA(gt, 13011645652))
-		guc_waklv_enable_one_word(ads,
-					  GUC_WA_KLV_NP_RD_WRITE_TO_CLEAR_RCSM_AT_CGP_LATE_RESTORE,
-					  0xC40,
-					  &offset, &remain);
+	if (XE_GT_WA(gt, 13011645652)) {
+		u32 data = 0xC40;
+
+		guc_waklv_enable(ads, &data, 1, &offset, &remain,
+				 GUC_WA_KLV_NP_RD_WRITE_TO_CLEAR_RCSM_AT_CGP_LATE_RESTORE);
+	}
+
+	if (XE_GT_WA(gt, 14022293748) || XE_GT_WA(gt, 22019794406))
+		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
+				 GUC_WORKAROUND_KLV_ID_BACK_TO_BACK_RCS_ENGINE_RESET);
+
+	if (GUC_FIRMWARE_VER(&gt->uc.guc) >= MAKE_GUC_VER(70, 44, 0) && XE_GT_WA(gt, 16026508708))
+		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
+				 GUC_WA_KLV_RESET_BB_STACK_PTR_ON_VF_SWITCH);
+	if (GUC_FIRMWARE_VER(&gt->uc.guc) >= MAKE_GUC_VER(70, 47, 0) && XE_GT_WA(gt, 16026007364)) {
+		u32 data[] = {
+			0x0,
+			0xF,
+		};
+		guc_waklv_enable(ads, data, ARRAY_SIZE(data), &offset, &remain,
+				 GUC_WA_KLV_RESTORE_UNSAVED_MEDIA_CONTROL_REG);
+	}
 
-	if (XE_WA(gt, 14022293748) || XE_WA(gt, 22019794406))
-		guc_waklv_enable_simple(ads,
-					GUC_WORKAROUND_KLV_ID_BACK_TO_BACK_RCS_ENGINE_RESET,
-					&offset, &remain);
+	if (XE_GT_WA(gt, 14020001231))
+		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
+				 GUC_WORKAROUND_KLV_DISABLE_PSMI_INTERRUPTS_AT_C6_ENTRY_RESTORE_AT_EXIT);
 
 	size = guc_ads_waklv_size(ads) - remain;
 	if (!size)
@@ -418,7 +401,8 @@ int xe_guc_ads_init(struct xe_guc_ads *ads)
 	bo = xe_managed_bo_create_pin_map(xe, tile, guc_ads_size(ads) + MAX_GOLDEN_LRC_SIZE,
 					  XE_BO_FLAG_SYSTEM |
 					  XE_BO_FLAG_GGTT |
-					  XE_BO_FLAG_GGTT_INVALIDATE);
+					  XE_BO_FLAG_GGTT_INVALIDATE |
+					  XE_BO_FLAG_PINNED_NORESTORE);
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);
 
@@ -494,24 +478,52 @@ static void fill_engine_enable_masks(struct xe_gt *gt,
 		       engine_enable_mask(gt, XE_ENGINE_CLASS_OTHER));
 }
 
-static void guc_prep_golden_lrc_null(struct xe_guc_ads *ads)
+/*
+ * Write the offsets corresponding to the golden LRCs. The actual data is
+ * populated later by guc_golden_lrc_populate()
+ */
+static void guc_golden_lrc_init(struct xe_guc_ads *ads)
 {
 	struct xe_device *xe = ads_to_xe(ads);
+	struct xe_gt *gt = ads_to_gt(ads);
 	struct iosys_map info_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads),
 			offsetof(struct __guc_ads_blob, system_info));
-	u8 guc_class;
+	size_t alloc_size, real_size;
+	u32 addr_ggtt, offset;
+	int class;
+
+	offset = guc_ads_golden_lrc_offset(ads);
+	addr_ggtt = xe_bo_ggtt_addr(ads->bo) + offset;
+
+	for (class = 0; class < XE_ENGINE_CLASS_MAX; ++class) {
+		u8 guc_class;
+
+		guc_class = xe_engine_class_to_guc_class(class);
 
-	for (guc_class = 0; guc_class <= GUC_MAX_ENGINE_CLASSES; ++guc_class) {
 		if (!info_map_read(xe, &info_map,
 				   engine_enabled_masks[guc_class]))
 			continue;
 
+		real_size = xe_gt_lrc_size(gt, class);
+		alloc_size = PAGE_ALIGN(real_size);
+
+		/*
+		 * This interface is slightly confusing. We need to pass the
+		 * base address of the full golden context and the size of just
+		 * the engine state, which is the section of the context image
+		 * that starts after the execlists LRC registers. This is
+		 * required to allow the GuC to restore just the engine state
+		 * when a watchdog reset occurs.
+		 * We calculate the engine state size by removing the size of
+		 * what comes before it in the context image (which is identical
+		 * on all engines).
+		 */
 		ads_blob_write(ads, ads.eng_state_size[guc_class],
-			       guc_ads_golden_lrc_size(ads) -
-			       xe_lrc_skip_size(xe));
+			       real_size - xe_lrc_skip_size(xe));
 		ads_blob_write(ads, ads.golden_context_lrca[guc_class],
-			       xe_bo_ggtt_addr(ads->bo) +
-			       guc_ads_golden_lrc_offset(ads));
+			       addr_ggtt);
+
+		addr_ggtt += alloc_size;
 	}
 }
 
@@ -686,8 +698,8 @@ static int guc_capture_prep_lists(struct xe_guc_ads *ads)
 	}
 
 	if (ads->capture_size != PAGE_ALIGN(total_size))
-		xe_gt_dbg(gt, "ADS capture alloc size changed from %d to %d\n",
-			  ads->capture_size, PAGE_ALIGN(total_size));
+		xe_gt_dbg(gt, "Updated ADS capture size %d (was %d)\n",
+			  PAGE_ALIGN(total_size), ads->capture_size);
 	return PAGE_ALIGN(total_size);
 }
 
@@ -701,6 +713,20 @@ static void guc_mmio_regset_write_one(struct xe_guc_ads *ads,
 		.flags = reg.masked ? GUC_REGSET_MASKED : 0,
 	};
 
+	if (reg.mcr) {
+		struct xe_reg_mcr mcr_reg = XE_REG_MCR(reg.addr);
+		u8 group, instance;
+
+		bool steer = xe_gt_mcr_get_nonterminated_steering(ads_to_gt(ads), mcr_reg,
+								  &group, &instance);
+
+		if (steer) {
+			entry.flags |= FIELD_PREP(GUC_REGSET_STEERING_GROUP, group);
+			entry.flags |= FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, instance);
+			entry.flags |= GUC_REGSET_STEERING_NEEDED;
+		}
+	}
+
 	xe_map_memcpy_to(ads_to_xe(ads), regset_map, n_entry * sizeof(entry),
 			 &entry, sizeof(entry));
 }
@@ -709,7 +735,6 @@ static unsigned int guc_mmio_regset_write(struct xe_guc_ads *ads,
 					  struct iosys_map *regset_map,
 					  struct xe_hw_engine *hwe)
 {
-	struct xe_device *xe = ads_to_xe(ads);
 	struct xe_hw_engine *hwe_rcs_reset_domain =
 		xe_gt_any_hw_engine_by_reset_domain(hwe->gt, XE_ENGINE_CLASS_RENDER);
 	struct xe_reg_sr_entry *entry;
@@ -740,8 +765,7 @@ static unsigned int guc_mmio_regset_write(struct xe_guc_ads *ads,
 		guc_mmio_regset_write_one(ads, regset_map, e->reg, count++);
 	}
 
-	/* Wa_1607983814 */
-	if (needs_wa_1607983814(xe) && hwe->class == XE_ENGINE_CLASS_RENDER) {
+	if (XE_GT_WA(hwe->gt, 1607983814) && hwe->class == XE_ENGINE_CLASS_RENDER) {
 		for (i = 0; i < LNCFCMOCS_REG_COUNT; i++) {
 			guc_mmio_regset_write_one(ads, regset_map,
 						  XELP_LNCFCMOCS(i), count++);
@@ -796,16 +820,20 @@ static void guc_mmio_reg_state_init(struct xe_guc_ads *ads)
 static void guc_um_init_params(struct xe_guc_ads *ads)
 {
 	u32 um_queue_offset = guc_ads_um_queues_offset(ads);
+	struct xe_guc *guc = ads_to_guc(ads);
 	u64 base_dpa;
 	u32 base_ggtt;
+	bool with_dpa;
 	int i;
 
+	with_dpa = !xe_guc_using_main_gamctrl_queues(guc);
+
 	base_ggtt = xe_bo_ggtt_addr(ads->bo) + um_queue_offset;
 	base_dpa = xe_bo_main_addr(ads->bo, PAGE_SIZE) + um_queue_offset;
 
 	for (i = 0; i < GUC_UM_HW_QUEUE_MAX; ++i) {
 		ads_blob_write(ads, um_init_params.queue_params[i].base_dpa,
-			       base_dpa + (i * GUC_UM_QUEUE_SIZE));
+			       with_dpa ? (base_dpa + (i * GUC_UM_QUEUE_SIZE)) : 0);
 		ads_blob_write(ads, um_init_params.queue_params[i].base_ggtt_address,
 			       base_ggtt + (i * GUC_UM_QUEUE_SIZE));
 		ads_blob_write(ads, um_init_params.queue_params[i].size_in_bytes,
@@ -847,9 +875,9 @@ void xe_guc_ads_populate_minimal(struct xe_guc_ads *ads)
 
 	xe_gt_assert(gt, ads->bo);
 
-	xe_map_memset(ads_to_xe(ads), ads_to_map(ads), 0, 0, ads->bo->size);
+	xe_map_memset(ads_to_xe(ads), ads_to_map(ads), 0, 0, xe_bo_size(ads->bo));
 	guc_policies_init(ads);
-	guc_prep_golden_lrc_null(ads);
+	guc_golden_lrc_init(ads);
 	guc_mapping_table_init_invalid(gt, &info_map);
 	guc_doorbell_init(ads);
 
@@ -871,11 +899,11 @@ void xe_guc_ads_populate(struct xe_guc_ads *ads)
 
 	xe_gt_assert(gt, ads->bo);
 
-	xe_map_memset(ads_to_xe(ads), ads_to_map(ads), 0, 0, ads->bo->size);
+	xe_map_memset(ads_to_xe(ads), ads_to_map(ads), 0, 0, xe_bo_size(ads->bo));
 	guc_policies_init(ads);
 	fill_engine_enable_masks(gt, &info_map);
 	guc_mmio_reg_state_init(ads);
-	guc_prep_golden_lrc_null(ads);
+	guc_golden_lrc_init(ads);
 	guc_mapping_table_init(gt, &info_map);
 	guc_capture_prep_lists(ads);
 	guc_doorbell_init(ads);
@@ -895,18 +923,22 @@ void xe_guc_ads_populate(struct xe_guc_ads *ads)
 		       guc_ads_private_data_offset(ads));
 }
 
-static void guc_populate_golden_lrc(struct xe_guc_ads *ads)
+/*
+ * After the golden LRC's are recorded for each engine class by the first
+ * submission, copy them to the ADS, as initialized earlier by
+ * guc_golden_lrc_init().
+ */
+static void guc_golden_lrc_populate(struct xe_guc_ads *ads)
 {
 	struct xe_device *xe = ads_to_xe(ads);
 	struct xe_gt *gt = ads_to_gt(ads);
 	struct iosys_map info_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads),
 			offsetof(struct __guc_ads_blob, system_info));
 	size_t total_size = 0, alloc_size, real_size;
-	u32 addr_ggtt, offset;
+	u32 offset;
 	int class;
 
 	offset = guc_ads_golden_lrc_offset(ads);
-	addr_ggtt = xe_bo_ggtt_addr(ads->bo) + offset;
 
 	for (class = 0; class < XE_ENGINE_CLASS_MAX; ++class) {
 		u8 guc_class;
@@ -923,26 +955,9 @@ static void guc_populate_golden_lrc(struct xe_guc_ads *ads)
 		alloc_size = PAGE_ALIGN(real_size);
 		total_size += alloc_size;
 
-		/*
-		 * This interface is slightly confusing. We need to pass the
-		 * base address of the full golden context and the size of just
-		 * the engine state, which is the section of the context image
-		 * that starts after the execlists LRC registers. This is
-		 * required to allow the GuC to restore just the engine state
-		 * when a watchdog reset occurs.
-		 * We calculate the engine state size by removing the size of
-		 * what comes before it in the context image (which is identical
-		 * on all engines).
-		 */
-		ads_blob_write(ads, ads.eng_state_size[guc_class],
-			       real_size - xe_lrc_skip_size(xe));
-		ads_blob_write(ads, ads.golden_context_lrca[guc_class],
-			       addr_ggtt);
-
 		xe_map_memcpy_to(xe, ads_to_map(ads), offset,
 				 gt->default_lrc[class], real_size);
 
-		addr_ggtt += alloc_size;
 		offset += alloc_size;
 	}
 
@@ -951,7 +966,7 @@ static void guc_populate_golden_lrc(struct xe_guc_ads *ads)
 
 void xe_guc_ads_populate_post_load(struct xe_guc_ads *ads)
 {
-	guc_populate_golden_lrc(ads);
+	guc_golden_lrc_populate(ads);
 }
 
 static int guc_ads_action_update_policies(struct xe_guc_ads *ads, u32 policy_offset)
@@ -975,16 +990,16 @@ static int guc_ads_action_update_policies(struct xe_guc_ads *ads, u32 policy_off
  */
 int xe_guc_ads_scheduler_policy_toggle_reset(struct xe_guc_ads *ads)
 {
-	struct xe_device *xe = ads_to_xe(ads);
-	struct xe_gt *gt = ads_to_gt(ads);
-	struct xe_tile *tile = gt_to_tile(gt);
 	struct guc_policies *policies;
-	struct xe_bo *bo;
-	int ret = 0;
+	struct xe_guc *guc = ads_to_guc(ads);
+	struct xe_device *xe = ads_to_xe(ads);
+	CLASS(xe_guc_buf, buf)(&guc->buf, sizeof(*policies));
+
+	if (!xe_guc_buf_is_valid(buf))
+		return -ENOBUFS;
 
-	policies = kmalloc(sizeof(*policies), GFP_KERNEL);
-	if (!policies)
-		return -ENOMEM;
+	policies = xe_guc_buf_cpu_ptr(buf);
+	memset(policies, 0, sizeof(*policies));
 
 	policies->dpc_promote_time = ads_blob_read(ads, policies.dpc_promote_time);
 	policies->max_num_work_items = ads_blob_read(ads, policies.max_num_work_items);
@@ -994,16 +1009,5 @@ int xe_guc_ads_scheduler_policy_toggle_reset(struct xe_guc_ads *ads)
 	else
 		policies->global_flags &= ~GLOBAL_POLICY_DISABLE_ENGINE_RESET;
 
-	bo = xe_managed_bo_create_from_data(xe, tile, policies, sizeof(struct guc_policies),
-					    XE_BO_FLAG_VRAM_IF_DGFX(tile) |
-					    XE_BO_FLAG_GGTT);
-	if (IS_ERR(bo)) {
-		ret = PTR_ERR(bo);
-		goto out;
-	}
-
-	ret = guc_ads_action_update_policies(ads, xe_bo_ggtt_addr(bo));
-out:
-	kfree(policies);
-	return ret;
+	return guc_ads_action_update_policies(ads, xe_guc_buf_flush(buf));
 }