drm/i915/guc: Updates for GuC 32.0.3 firmware

New GuC 32.0.3 firmware made many changes around its ABI that
require driver updates:

* FW release version numbering schema now includes patch number
* FW release version encoding in CSS header
* Boot parameters
* Suspend/resume protocol
* Sample-forcewake command
* Additional Data Structures (ADS)

This commit is a squash of patches 3-8 from series [1].
[1] https://patchwork.freedesktop.org/series/58760/

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Anusha Srivatsa <anusha.srivatsa@intel.com>
Cc: Jeff Mcgee <jeff.mcgee@intel.com>
Cc: John Spotswood <john.a.spotswood@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Tomasz Lis <tomasz.lis@intel.com>
Acked-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> # numbering schema
Acked-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> # ccs heaser
Acked-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> # boot params
Acked-by: John Spotswood <john.a.spotswood@intel.com> # suspend/resume
Acked-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> # sample-forcewake
Acked-by: John Spotswood <john.a.spotswood@intel.com> # sample-forcewake
Acked-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> # ADS
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190527183613.17076-4-michal.wajdeczko@intel.com

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

@@ -526,6 +526,8 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine);
 struct i915_request *
 intel_engine_find_active_request(struct intel_engine_cs *engine);
 
+u32 intel_engine_context_size(struct drm_i915_private *i915, u8 class);
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 
 static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)

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

@@ -156,7 +156,7 @@ static const struct engine_info intel_engines[] = {
 };
 
 /**
- * ___intel_engine_context_size() - return the size of the context for an engine
+ * intel_engine_context_size() - return the size of the context for an engine
  * @dev_priv: i915 device private
  * @class: engine class
  *
@@ -169,8 +169,7 @@ static const struct engine_info intel_engines[] = {
  * in LRC mode, but does not include the "shared data page" used with
  * GuC submission. The caller should account for this if using the GuC.
  */
-static u32
-__intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
+u32 intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
 {
 	u32 cxt_size;
 
@@ -327,8 +326,8 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 
 	engine->uabi_class = intel_engine_classes[info->class].uabi_class;
 
-	engine->context_size = __intel_engine_context_size(dev_priv,
-							   engine->class);
+	engine->context_size = intel_engine_context_size(dev_priv,
+							 engine->class);
 	if (WARN_ON(engine->context_size > BIT(20)))
 		engine->context_size = 0;
 	if (engine->context_size)

drivers/gpu/drm/i915/intel_guc.c

@@ -250,14 +250,7 @@ void intel_guc_fini(struct intel_guc *guc)
 static u32 guc_ctl_debug_flags(struct intel_guc *guc)
 {
 	u32 level = intel_guc_log_get_level(&guc->log);
-	u32 flags;
-	u32 ads;
-
-	ads = intel_guc_ggtt_offset(guc, guc->ads_vma) >> PAGE_SHIFT;
-	flags = ads << GUC_ADS_ADDR_SHIFT | GUC_ADS_ENABLED;
-
-	if (!GUC_LOG_LEVEL_IS_ENABLED(level))
-		flags |= GUC_LOG_DEFAULT_DISABLED;
+	u32 flags = 0;
 
 	if (!GUC_LOG_LEVEL_IS_VERBOSE(level))
 		flags |= GUC_LOG_DISABLED;
@@ -272,11 +265,7 @@ static u32 guc_ctl_feature_flags(struct intel_guc *guc)
 {
 	u32 flags = 0;
 
-	flags |=  GUC_CTL_VCS2_ENABLED;
-
-	if (USES_GUC_SUBMISSION(guc_to_i915(guc)))
-		flags |= GUC_CTL_KERNEL_SUBMISSIONS;
-	else
+	if (!USES_GUC_SUBMISSION(guc_to_i915(guc)))
 		flags |= GUC_CTL_DISABLE_SCHEDULER;
 
 	return flags;
@@ -340,6 +329,14 @@ static u32 guc_ctl_log_params_flags(struct intel_guc *guc)
 	return flags;
 }
 
+static u32 guc_ctl_ads_flags(struct intel_guc *guc)
+{
+	u32 ads = intel_guc_ggtt_offset(guc, guc->ads_vma) >> PAGE_SHIFT;
+	u32 flags = ads << GUC_ADS_ADDR_SHIFT;
+
+	return flags;
+}
+
 /*
  * Initialise the GuC parameter block before starting the firmware
  * transfer. These parameters are read by the firmware on startup
@@ -353,20 +350,11 @@ void intel_guc_init_params(struct intel_guc *guc)
 
 	memset(params, 0, sizeof(params));
 
-	/*
-	 * GuC ARAT increment is 10 ns. GuC default scheduler quantum is one
-	 * second. This ARAR is calculated by:
-	 * Scheduler-Quantum-in-ns / ARAT-increment-in-ns = 1000000000 / 10
-	 */
-	params[GUC_CTL_ARAT_HIGH] = 0;
-	params[GUC_CTL_ARAT_LOW] = 100000000;
-
-	params[GUC_CTL_WA] |= GUC_CTL_WA_UK_BY_DRIVER;
-
+	params[GUC_CTL_CTXINFO] = guc_ctl_ctxinfo_flags(guc);
+	params[GUC_CTL_LOG_PARAMS] = guc_ctl_log_params_flags(guc);
 	params[GUC_CTL_FEATURE] = guc_ctl_feature_flags(guc);
-	params[GUC_CTL_LOG_PARAMS]  = guc_ctl_log_params_flags(guc);
 	params[GUC_CTL_DEBUG] = guc_ctl_debug_flags(guc);
-	params[GUC_CTL_CTXINFO] = guc_ctl_ctxinfo_flags(guc);
+	params[GUC_CTL_ADS] = guc_ctl_ads_flags(guc);
 
 	for (i = 0; i < GUC_CTL_MAX_DWORDS; i++)
 		DRM_DEBUG_DRIVER("param[%2d] = %#x\n", i, params[i]);
@@ -550,25 +538,33 @@ int intel_guc_auth_huc(struct intel_guc *guc, u32 rsa_offset)
 	return intel_guc_send(guc, action, ARRAY_SIZE(action));
 }
 
-/*
- * The ENTER/EXIT_S_STATE actions queue the save/restore operation in GuC FW and
- * then return, so waiting on the H2G is not enough to guarantee GuC is done.
- * When all the processing is done, GuC writes INTEL_GUC_SLEEP_STATE_SUCCESS to
- * scratch register 14, so we can poll on that. Note that GuC does not ensure
- * that the value in the register is different from
- * INTEL_GUC_SLEEP_STATE_SUCCESS while the action is in progress so we need to
- * take care of that ourselves as well.
+/**
+ * intel_guc_suspend() - notify GuC entering suspend state
+ * @guc:	the guc
  */
-static int guc_sleep_state_action(struct intel_guc *guc,
-				  const u32 *action, u32 len)
+int intel_guc_suspend(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 	int ret;
 	u32 status;
+	u32 action[] = {
+		INTEL_GUC_ACTION_ENTER_S_STATE,
+		GUC_POWER_D1, /* any value greater than GUC_POWER_D0 */
+	};
+
+	/*
+	 * The ENTER_S_STATE action queues the save/restore operation in GuC FW
+	 * and then returns, so waiting on the H2G is not enough to guarantee
+	 * GuC is done. When all the processing is done, GuC writes
+	 * INTEL_GUC_SLEEP_STATE_SUCCESS to scratch register 14, so we can poll
+	 * on that. Note that GuC does not ensure that the value in the register
+	 * is different from INTEL_GUC_SLEEP_STATE_SUCCESS while the action is
+	 * in progress so we need to take care of that ourselves as well.
+	 */
 
 	I915_WRITE(SOFT_SCRATCH(14), INTEL_GUC_SLEEP_STATE_INVALID_MASK);
 
-	ret = intel_guc_send(guc, action, len);
+	ret = intel_guc_send(guc, action, ARRAY_SIZE(action));
 	if (ret)
 		return ret;
 
@@ -588,21 +584,6 @@ static int guc_sleep_state_action(struct intel_guc *guc,
 	return 0;
 }
 
-/**
- * intel_guc_suspend() - notify GuC entering suspend state
- * @guc:	the guc
- */
-int intel_guc_suspend(struct intel_guc *guc)
-{
-	u32 data[] = {
-		INTEL_GUC_ACTION_ENTER_S_STATE,
-		GUC_POWER_D1, /* any value greater than GUC_POWER_D0 */
-		intel_guc_ggtt_offset(guc, guc->shared_data)
-	};
-
-	return guc_sleep_state_action(guc, data, ARRAY_SIZE(data));
-}
-
 /**
  * intel_guc_reset_engine() - ask GuC to reset an engine
  * @guc:	intel_guc structure
@@ -632,13 +613,12 @@ int intel_guc_reset_engine(struct intel_guc *guc,
  */
 int intel_guc_resume(struct intel_guc *guc)
 {
-	u32 data[] = {
+	u32 action[] = {
 		INTEL_GUC_ACTION_EXIT_S_STATE,
 		GUC_POWER_D0,
-		intel_guc_ggtt_offset(guc, guc->shared_data)
 	};
 
-	return guc_sleep_state_action(guc, data, ARRAY_SIZE(data));
+	return intel_guc_send(guc, action, ARRAY_SIZE(action));
 }
 
 /**

drivers/gpu/drm/i915/intel_guc_ads.c

@@ -51,7 +51,7 @@ static void guc_policies_init(struct guc_policies *policies)
 	policies->max_num_work_items = POLICY_MAX_NUM_WI;
 
 	for (p = 0; p < GUC_CLIENT_PRIORITY_NUM; p++) {
-		for (i = GUC_RENDER_ENGINE; i < GUC_MAX_ENGINES_NUM; i++) {
+		for (i = 0; i < GUC_MAX_ENGINE_CLASSES; i++) {
 			policy = &policies->policy[p][i];
 
 			guc_policy_init(policy);
@@ -61,6 +61,11 @@ static void guc_policies_init(struct guc_policies *policies)
 	policies->is_valid = 1;
 }
 
+static void guc_ct_pool_entries_init(struct guc_ct_pool_entry *pool, u32 num)
+{
+	memset(pool, 0, num * sizeof(*pool));
+}
+
 /*
  * The first 80 dwords of the register state context, containing the
  * execlists and ppgtt registers.
@@ -75,20 +80,21 @@ static void guc_policies_init(struct guc_policies *policies)
 int intel_guc_ads_create(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
-	struct i915_vma *vma, *kernel_ctx_vma;
-	struct page *page;
+	struct i915_vma *vma;
 	/* The ads obj includes the struct itself and buffers passed to GuC */
 	struct {
 		struct guc_ads ads;
 		struct guc_policies policies;
 		struct guc_mmio_reg_state reg_state;
+		struct guc_gt_system_info system_info;
+		struct guc_clients_info clients_info;
+		struct guc_ct_pool_entry ct_pool[GUC_CT_POOL_SIZE];
 		u8 reg_state_buffer[GUC_S3_SAVE_SPACE_PAGES * PAGE_SIZE];
 	} __packed *blob;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	const u32 skipped_offset = LRC_HEADER_PAGES * PAGE_SIZE;
 	const u32 skipped_size = LRC_PPHWSP_SZ * PAGE_SIZE + LR_HW_CONTEXT_SIZE;
 	u32 base;
+	u8 engine_class;
+	int ret;
 
 	GEM_BUG_ON(guc->ads_vma);
 
@@ -98,51 +104,68 @@ int intel_guc_ads_create(struct intel_guc *guc)
 
 	guc->ads_vma = vma;
 
-	page = i915_vma_first_page(vma);
-	blob = kmap(page);
+	blob = i915_gem_object_pin_map(guc->ads_vma->obj, I915_MAP_WB);
+	if (IS_ERR(blob)) {
+		ret = PTR_ERR(blob);
+		goto err_vma;
+	}
 
 	/* GuC scheduling policies */
 	guc_policies_init(&blob->policies);
 
-	/* MMIO reg state */
-	for_each_engine(engine, dev_priv, id) {
-		blob->reg_state.white_list[engine->guc_id].mmio_start =
-			engine->mmio_base + GUC_MMIO_WHITE_LIST_START;
-
-		/* Nothing to be saved or restored for now. */
-		blob->reg_state.white_list[engine->guc_id].count = 0;
-	}
-
 	/*
-	 * The GuC requires a "Golden Context" when it reinitialises
-	 * engines after a reset. Here we use the Render ring default
-	 * context, which must already exist and be pinned in the GGTT,
-	 * so its address won't change after we've told the GuC where
-	 * to find it. Note that we have to skip our header (1 page),
-	 * because our GuC shared data is there.
+	 * GuC expects a per-engine-class context image and size
+	 * (minus hwsp and ring context). The context image will be
+	 * used to reinitialize engines after a reset. It must exist
+	 * and be pinned in the GGTT, so that the address won't change after
+	 * we have told GuC where to find it. The context size will be used
+	 * to validate that the LRC base + size fall within allowed GGTT.
 	 */
-	kernel_ctx_vma = dev_priv->engine[RCS0]->kernel_context->state;
-	blob->ads.golden_context_lrca =
-		intel_guc_ggtt_offset(guc, kernel_ctx_vma) + skipped_offset;
+	for (engine_class = 0; engine_class <= MAX_ENGINE_CLASS; ++engine_class) {
+		if (engine_class == OTHER_CLASS)
+			continue;
+		/*
+		 * TODO: Set context pointer to default state to allow
+		 * GuC to re-init guilty contexts after internal reset.
+		 */
+		blob->ads.golden_context_lrca[engine_class] = 0;
+		blob->ads.eng_state_size[engine_class] =
+			intel_engine_context_size(dev_priv, engine_class) -
+			skipped_size;
+	}
 
-	/*
-	 * The GuC expects us to exclude the portion of the context image that
-	 * it skips from the size it is to read. It starts reading from after
-	 * the execlist context (so skipping the first page [PPHWSP] and 80
-	 * dwords). Weird guc is weird.
-	 */
-	for_each_engine(engine, dev_priv, id)
-		blob->ads.eng_state_size[engine->guc_id] =
-			engine->context_size - skipped_size;
+	/* System info */
+	blob->system_info.slice_enabled = hweight8(RUNTIME_INFO(dev_priv)->sseu.slice_mask);
+	blob->system_info.rcs_enabled = 1;
+	blob->system_info.bcs_enabled = 1;
+
+	blob->system_info.vdbox_enable_mask = VDBOX_MASK(dev_priv);
+	blob->system_info.vebox_enable_mask = VEBOX_MASK(dev_priv);
+	blob->system_info.vdbox_sfc_support_mask = RUNTIME_INFO(dev_priv)->vdbox_sfc_access;
 
 	base = intel_guc_ggtt_offset(guc, vma);
+
+	/* Clients info  */
+	guc_ct_pool_entries_init(blob->ct_pool, ARRAY_SIZE(blob->ct_pool));
+
+	blob->clients_info.clients_num = 1;
+	blob->clients_info.ct_pool_addr = base + ptr_offset(blob, ct_pool);
+	blob->clients_info.ct_pool_count = ARRAY_SIZE(blob->ct_pool);
+
+	/* ADS */
 	blob->ads.scheduler_policies = base + ptr_offset(blob, policies);
 	blob->ads.reg_state_buffer = base + ptr_offset(blob, reg_state_buffer);
 	blob->ads.reg_state_addr = base + ptr_offset(blob, reg_state);
+	blob->ads.gt_system_info = base + ptr_offset(blob, system_info);
+	blob->ads.clients_info = base + ptr_offset(blob, clients_info);
 
-	kunmap(page);
+	i915_gem_object_unpin_map(guc->ads_vma->obj);
 
 	return 0;
+
+err_vma:
+	i915_vma_unpin_and_release(&guc->ads_vma, 0);
+	return ret;
 }
 
 void intel_guc_ads_destroy(struct intel_guc *guc)