drm/i915/guc: Add multi-lrc context registration

Add multi-lrc context registration H2G. In addition a workqueue and
process descriptor are setup during multi-lrc context registration as
these data structures are needed for multi-lrc submission.

v2:
 (John Harrison)
  - Move GuC specific fields into sub-struct
  - Clean up WQ defines
  - Add comment explaining math to derive WQ / PD address
v3:
 (John Harrison)
  - Add PARENT_SCRATCH_SIZE define
  - Update comment explaining multi-lrc register
v4:
 (John Harrison)
  - Move PARENT_SCRATCH_SIZE to common file
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211014172005.27155-9-matthew.brost@intel.com

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

@@ -44,6 +44,8 @@ void intel_context_free(struct intel_context *ce);
 int intel_context_reconfigure_sseu(struct intel_context *ce,
 				   const struct intel_sseu sseu);
 
+#define PARENT_SCRATCH_SIZE	PAGE_SIZE
+
 static inline bool intel_context_is_child(struct intel_context *ce)
 {
 	return !!ce->parallel.parent;

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

@@ -239,6 +239,18 @@ struct intel_context {
 		struct intel_context *parent;
 		/** @number_children: number of children if parent */
 		u8 number_children;
+		/** @guc: GuC specific members for parallel submission */
+		struct {
+			/** @wqi_head: head pointer in work queue */
+			u16 wqi_head;
+			/** @wqi_tail: tail pointer in work queue */
+			u16 wqi_tail;
+			/**
+			 * @parent_page: page in context state (ce->state) used
+			 * by parent for work queue, process descriptor
+			 */
+			u8 parent_page;
+		} guc;
 	} parallel;
 
 #ifdef CONFIG_DRM_I915_SELFTEST

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

@@ -942,6 +942,11 @@ __lrc_alloc_state(struct intel_context *ce, struct intel_engine_cs *engine)
 		context_size += PAGE_SIZE;
 	}
 
+	if (intel_context_is_parent(ce) && intel_engine_uses_guc(engine)) {
+		ce->parallel.guc.parent_page = context_size / PAGE_SIZE;
+		context_size += PARENT_SCRATCH_SIZE;
+	}
+
 	obj = i915_gem_object_create_lmem(engine->i915, context_size,
 					  I915_BO_ALLOC_PM_VOLATILE);
 	if (IS_ERR(obj))

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

@@ -142,6 +142,7 @@ enum intel_guc_action {
 	INTEL_GUC_ACTION_REGISTER_COMMAND_TRANSPORT_BUFFER = 0x4505,
 	INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER = 0x4506,
 	INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE = 0x4600,
+	INTEL_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC = 0x4601,
 	INTEL_GUC_ACTION_RESET_CLIENT = 0x5507,
 	INTEL_GUC_ACTION_LIMIT
 };

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

@@ -52,8 +52,6 @@
 
 #define GUC_DOORBELL_INVALID		256
 
-#define GUC_WQ_SIZE			(PAGE_SIZE * 2)
-
 /* Work queue item header definitions */
 #define WQ_STATUS_ACTIVE		1
 #define WQ_STATUS_SUSPENDED		2

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

@@ -344,6 +344,46 @@ static inline struct i915_priolist *to_priolist(struct rb_node *rb)
 	return rb_entry(rb, struct i915_priolist, node);
 }
 
+/*
+ * When using multi-lrc submission a scratch memory area is reserved in the
+ * parent's context state for the process descriptor and work queue. Currently
+ * the scratch area is sized to a page.
+ *
+ * The layout of this scratch area is below:
+ * 0						guc_process_desc
+ * ...						unused
+ * PARENT_SCRATCH_SIZE / 2			work queue start
+ * ...						work queue
+ * PARENT_SCRATCH_SIZE - 1			work queue end
+ */
+#define WQ_SIZE			(PARENT_SCRATCH_SIZE / 2)
+#define WQ_OFFSET		(PARENT_SCRATCH_SIZE - WQ_SIZE)
+static u32 __get_process_desc_offset(struct intel_context *ce)
+{
+	GEM_BUG_ON(!ce->parallel.guc.parent_page);
+
+	return ce->parallel.guc.parent_page * PAGE_SIZE;
+}
+
+static u32 __get_wq_offset(struct intel_context *ce)
+{
+	return __get_process_desc_offset(ce) + WQ_OFFSET;
+}
+
+static struct guc_process_desc *
+__get_process_desc(struct intel_context *ce)
+{
+	/*
+	 * Need to subtract LRC_STATE_OFFSET here as the
+	 * parallel.guc.parent_page is the offset into ce->state while
+	 * ce->lrc_reg_reg is ce->state + LRC_STATE_OFFSET.
+	 */
+	return (struct guc_process_desc *)
+		(ce->lrc_reg_state +
+		 ((__get_process_desc_offset(ce) -
+		   LRC_STATE_OFFSET) / sizeof(u32)));
+}
+
 static struct guc_lrc_desc *__get_lrc_desc(struct intel_guc *guc, u32 index)
 {
 	struct guc_lrc_desc *base = guc->lrc_desc_pool_vaddr;
@@ -1365,6 +1405,30 @@ static void unpin_guc_id(struct intel_guc *guc, struct intel_context *ce)
 	spin_unlock_irqrestore(&guc->submission_state.lock, flags);
 }
 
+static int __guc_action_register_multi_lrc(struct intel_guc *guc,
+					   struct intel_context *ce,
+					   u32 guc_id,
+					   u32 offset,
+					   bool loop)
+{
+	struct intel_context *child;
+	u32 action[4 + MAX_ENGINE_INSTANCE];
+	int len = 0;
+
+	GEM_BUG_ON(ce->parallel.number_children > MAX_ENGINE_INSTANCE);
+
+	action[len++] = INTEL_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC;
+	action[len++] = guc_id;
+	action[len++] = ce->parallel.number_children + 1;
+	action[len++] = offset;
+	for_each_child(ce, child) {
+		offset += sizeof(struct guc_lrc_desc);
+		action[len++] = offset;
+	}
+
+	return guc_submission_send_busy_loop(guc, action, len, 0, loop);
+}
+
 static int __guc_action_register_context(struct intel_guc *guc,
 					 u32 guc_id,
 					 u32 offset,
@@ -1387,9 +1451,15 @@ static int register_context(struct intel_context *ce, bool loop)
 		ce->guc_id.id * sizeof(struct guc_lrc_desc);
 	int ret;
 
+	GEM_BUG_ON(intel_context_is_child(ce));
 	trace_intel_context_register(ce);
 
-	ret = __guc_action_register_context(guc, ce->guc_id.id, offset, loop);
+	if (intel_context_is_parent(ce))
+		ret = __guc_action_register_multi_lrc(guc, ce, ce->guc_id.id,
+						      offset, loop);
+	else
+		ret = __guc_action_register_context(guc, ce->guc_id.id, offset,
+						    loop);
 	if (likely(!ret)) {
 		unsigned long flags;
 
@@ -1418,6 +1488,7 @@ static int deregister_context(struct intel_context *ce, u32 guc_id)
 {
 	struct intel_guc *guc = ce_to_guc(ce);
 
+	GEM_BUG_ON(intel_context_is_child(ce));
 	trace_intel_context_deregister(ce);
 
 	return __guc_action_deregister_context(guc, guc_id);
@@ -1445,6 +1516,7 @@ static int guc_lrc_desc_pin(struct intel_context *ce, bool loop)
 	struct guc_lrc_desc *desc;
 	bool context_registered;
 	intel_wakeref_t wakeref;
+	struct intel_context *child;
 	int ret = 0;
 
 	GEM_BUG_ON(!engine->mask);
@@ -1470,6 +1542,41 @@ static int guc_lrc_desc_pin(struct intel_context *ce, bool loop)
 	desc->context_flags = CONTEXT_REGISTRATION_FLAG_KMD;
 	guc_context_policy_init(engine, desc);
 
+	/*
+	 * If context is a parent, we need to register a process descriptor
+	 * describing a work queue and register all child contexts.
+	 */
+	if (intel_context_is_parent(ce)) {
+		struct guc_process_desc *pdesc;
+
+		ce->parallel.guc.wqi_tail = 0;
+		ce->parallel.guc.wqi_head = 0;
+
+		desc->process_desc = i915_ggtt_offset(ce->state) +
+			__get_process_desc_offset(ce);
+		desc->wq_addr = i915_ggtt_offset(ce->state) +
+			__get_wq_offset(ce);
+		desc->wq_size = WQ_SIZE;
+
+		pdesc = __get_process_desc(ce);
+		memset(pdesc, 0, sizeof(*(pdesc)));
+		pdesc->stage_id = ce->guc_id.id;
+		pdesc->wq_base_addr = desc->wq_addr;
+		pdesc->wq_size_bytes = desc->wq_size;
+		pdesc->wq_status = WQ_STATUS_ACTIVE;
+
+		for_each_child(ce, child) {
+			desc = __get_lrc_desc(guc, child->guc_id.id);
+
+			desc->engine_class =
+				engine_class_to_guc_class(engine->class);
+			desc->hw_context_desc = child->lrc.lrca;
+			desc->priority = ce->guc_state.prio;
+			desc->context_flags = CONTEXT_REGISTRATION_FLAG_KMD;
+			guc_context_policy_init(engine, desc);
+		}
+	}
+
 	/*
 	 * The context_lookup xarray is used to determine if the hardware
 	 * context is currently registered. There are two cases in which it
@@ -2804,6 +2911,12 @@ g2h_context_lookup(struct intel_guc *guc, u32 desc_idx)
 		return NULL;
 	}
 
+	if (unlikely(intel_context_is_child(ce))) {
+		drm_err(&guc_to_gt(guc)->i915->drm,
+			"Context is child, desc_idx %u", desc_idx);
+		return NULL;
+	}
+
 	return ce;
 }