drm/i915: Make own struct for execlist items

Engine's execlist related items have been increasing to
a point where a separate struct is warranted. Carve execlist
specific items to a dedicated struct to add clarity.

v2: add kerneldoc and fix whitespace (Joonas, Chris)
v3: csb_mmio changes, rebase
v4: s/\b(el|execlist)\b/execlists/ (Joonas)
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com> (v3)
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> (v3)
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170922124307.10914-1-mika.kuoppala@intel.com

drivers/gpu/drm/i915/i915_debugfs.c

@@ -3323,7 +3323,7 @@ static int i915_engine_info(struct seq_file *m, void *unused)
 			read = GEN8_CSB_READ_PTR(ptr);
 			write = GEN8_CSB_WRITE_PTR(ptr);
 			seq_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], interrupt posted? %s\n",
-				   read, engine->csb_head,
+				   read, engine->execlists.csb_head,
 				   write,
 				   intel_read_status_page(engine, intel_hws_csb_write_index(engine->i915)),
 				   yesno(test_bit(ENGINE_IRQ_EXECLIST,
@@ -3345,10 +3345,10 @@ static int i915_engine_info(struct seq_file *m, void *unused)
 			}
 
 			rcu_read_lock();
-			for (idx = 0; idx < ARRAY_SIZE(engine->execlist_port); idx++) {
+			for (idx = 0; idx < ARRAY_SIZE(engine->execlists.port); idx++) {
 				unsigned int count;
 
-				rq = port_unpack(&engine->execlist_port[idx],
+				rq = port_unpack(&engine->execlists.port[idx],
 						 &count);
 				if (rq) {
 					seq_printf(m, "\t\tELSP[%d] count=%d, ",
@@ -3362,7 +3362,7 @@ static int i915_engine_info(struct seq_file *m, void *unused)
 			rcu_read_unlock();
 
 			spin_lock_irq(&engine->timeline->lock);
-			for (rb = engine->execlist_first; rb; rb = rb_next(rb)){
+			for (rb = engine->execlists.first; rb; rb = rb_next(rb)) {
 				struct i915_priolist *p =
 					rb_entry(rb, typeof(*p), node);
 

drivers/gpu/drm/i915/i915_gem.c

@@ -2815,8 +2815,8 @@ i915_gem_reset_prepare_engine(struct intel_engine_cs *engine)
 	 * Turning off the engine->irq_tasklet until the reset is over
 	 * prevents the race.
 	 */
-	tasklet_kill(&engine->irq_tasklet);
-	tasklet_disable(&engine->irq_tasklet);
+	tasklet_kill(&engine->execlists.irq_tasklet);
+	tasklet_disable(&engine->execlists.irq_tasklet);
 
 	if (engine->irq_seqno_barrier)
 		engine->irq_seqno_barrier(engine);
@@ -2995,7 +2995,7 @@ void i915_gem_reset(struct drm_i915_private *dev_priv)
 
 void i915_gem_reset_finish_engine(struct intel_engine_cs *engine)
 {
-	tasklet_enable(&engine->irq_tasklet);
+	tasklet_enable(&engine->execlists.irq_tasklet);
 	kthread_unpark(engine->breadcrumbs.signaler);
 }
 

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -1327,10 +1327,10 @@ static void engine_record_requests(struct intel_engine_cs *engine,
 static void error_record_engine_execlists(struct intel_engine_cs *engine,
 					  struct drm_i915_error_engine *ee)
 {
-	const struct execlist_port *port = engine->execlist_port;
+	const struct execlist_port *port = engine->execlists.port;
 	unsigned int n;
 
-	for (n = 0; n < ARRAY_SIZE(engine->execlist_port); n++) {
+	for (n = 0; n < ARRAY_SIZE(engine->execlists.port); n++) {
 		struct drm_i915_gem_request *rq = port_request(&port[n]);
 
 		if (!rq)

drivers/gpu/drm/i915/i915_guc_submission.c

@@ -494,11 +494,12 @@ static void i915_guc_submit(struct intel_engine_cs *engine)
 	struct drm_i915_private *dev_priv = engine->i915;
 	struct intel_guc *guc = &dev_priv->guc;
 	struct i915_guc_client *client = guc->execbuf_client;
-	struct execlist_port *port = engine->execlist_port;
-	unsigned int engine_id = engine->id;
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+	struct execlist_port *port = execlists->port;
+	const unsigned int engine_id = engine->id;
 	unsigned int n;
 
-	for (n = 0; n < ARRAY_SIZE(engine->execlist_port); n++) {
+	for (n = 0; n < ARRAY_SIZE(execlists->port); n++) {
 		struct drm_i915_gem_request *rq;
 		unsigned int count;
 
@@ -558,7 +559,8 @@ static void port_assign(struct execlist_port *port,
 
 static void i915_guc_dequeue(struct intel_engine_cs *engine)
 {
-	struct execlist_port *port = engine->execlist_port;
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+	struct execlist_port *port = execlists->port;
 	struct drm_i915_gem_request *last = NULL;
 	bool submit = false;
 	struct rb_node *rb;
@@ -567,15 +569,15 @@ static void i915_guc_dequeue(struct intel_engine_cs *engine)
 		port++;
 
 	spin_lock_irq(&engine->timeline->lock);
-	rb = engine->execlist_first;
-	GEM_BUG_ON(rb_first(&engine->execlist_queue) != rb);
+	rb = execlists->first;
+	GEM_BUG_ON(rb_first(&execlists->queue) != rb);
 	while (rb) {
 		struct i915_priolist *p = rb_entry(rb, typeof(*p), node);
 		struct drm_i915_gem_request *rq, *rn;
 
 		list_for_each_entry_safe(rq, rn, &p->requests, priotree.link) {
 			if (last && rq->ctx != last->ctx) {
-				if (port != engine->execlist_port) {
+				if (port != execlists->port) {
 					__list_del_many(&p->requests,
 							&rq->priotree.link);
 					goto done;
@@ -596,13 +598,13 @@ static void i915_guc_dequeue(struct intel_engine_cs *engine)
 		}
 
 		rb = rb_next(rb);
-		rb_erase(&p->node, &engine->execlist_queue);
+		rb_erase(&p->node, &execlists->queue);
 		INIT_LIST_HEAD(&p->requests);
 		if (p->priority != I915_PRIORITY_NORMAL)
 			kmem_cache_free(engine->i915->priorities, p);
 	}
 done:
-	engine->execlist_first = rb;
+	execlists->first = rb;
 	if (submit) {
 		port_assign(port, last);
 		i915_guc_submit(engine);
@@ -612,8 +614,8 @@ static void i915_guc_dequeue(struct intel_engine_cs *engine)
 
 static void i915_guc_irq_handler(unsigned long data)
 {
-	struct intel_engine_cs *engine = (struct intel_engine_cs *)data;
-	struct execlist_port *port = engine->execlist_port;
+	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
+	struct execlist_port *port = engine->execlists.port;
 	struct drm_i915_gem_request *rq;
 
 	rq = port_request(&port[0]);
@@ -1144,7 +1146,7 @@ int i915_guc_submission_enable(struct drm_i915_private *dev_priv)
 	 * and it is guaranteed that it will remove the work item from the
 	 * queue before our request is completed.
 	 */
-	BUILD_BUG_ON(ARRAY_SIZE(engine->execlist_port) *
+	BUILD_BUG_ON(ARRAY_SIZE(engine->execlists.port) *
 		     sizeof(struct guc_wq_item) *
 		     I915_NUM_ENGINES > GUC_WQ_SIZE);
 
@@ -1175,14 +1177,15 @@ int i915_guc_submission_enable(struct drm_i915_private *dev_priv)
 	guc_interrupts_capture(dev_priv);
 
 	for_each_engine(engine, dev_priv, id) {
+		struct intel_engine_execlists * const execlists = &engine->execlists;
 		/* The tasklet was initialised by execlists, and may be in
 		 * a state of flux (across a reset) and so we just want to
 		 * take over the callback without changing any other state
 		 * in the tasklet.
 		 */
-		engine->irq_tasklet.func = i915_guc_irq_handler;
+		execlists->irq_tasklet.func = i915_guc_irq_handler;
 		clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
-		tasklet_schedule(&engine->irq_tasklet);
+		tasklet_schedule(&execlists->irq_tasklet);
 	}
 
 	return 0;

drivers/gpu/drm/i915/i915_irq.c

@@ -1346,10 +1346,11 @@ static void snb_gt_irq_handler(struct drm_i915_private *dev_priv,
 static void
 gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir, int test_shift)
 {
+	struct intel_engine_execlists * const execlists = &engine->execlists;
 	bool tasklet = false;
 
 	if (iir & (GT_CONTEXT_SWITCH_INTERRUPT << test_shift)) {
-		if (port_count(&engine->execlist_port[0])) {
+		if (port_count(&execlists->port[0])) {
 			__set_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
 			tasklet = true;
 		}
@@ -1361,7 +1362,7 @@ gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir, int test_shift)
 	}
 
 	if (tasklet)
-		tasklet_hi_schedule(&engine->irq_tasklet);
+		tasklet_hi_schedule(&execlists->irq_tasklet);
 }
 
 static irqreturn_t gen8_gt_irq_ack(struct drm_i915_private *dev_priv,

drivers/gpu/drm/i915/intel_engine_cs.c

@@ -393,8 +393,8 @@ static void intel_engine_init_timeline(struct intel_engine_cs *engine)
  */
 void intel_engine_setup_common(struct intel_engine_cs *engine)
 {
-	engine->execlist_queue = RB_ROOT;
-	engine->execlist_first = NULL;
+	engine->execlists.queue = RB_ROOT;
+	engine->execlists.first = NULL;
 
 	intel_engine_init_timeline(engine);
 	intel_engine_init_hangcheck(engine);
@@ -1475,11 +1475,11 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 		return false;
 
 	/* Both ports drained, no more ELSP submission? */
-	if (port_request(&engine->execlist_port[0]))
+	if (port_request(&engine->execlists.port[0]))
 		return false;
 
 	/* ELSP is empty, but there are ready requests? */
-	if (READ_ONCE(engine->execlist_first))
+	if (READ_ONCE(engine->execlists.first))
 		return false;
 
 	/* Ring stopped? */
@@ -1528,8 +1528,8 @@ void intel_engines_mark_idle(struct drm_i915_private *i915)
 	for_each_engine(engine, i915, id) {
 		intel_engine_disarm_breadcrumbs(engine);
 		i915_gem_batch_pool_fini(&engine->batch_pool);
-		tasklet_kill(&engine->irq_tasklet);
-		engine->no_priolist = false;
+		tasklet_kill(&engine->execlists.irq_tasklet);
+		engine->execlists.no_priolist = false;
 	}
 }
 

drivers/gpu/drm/i915/intel_ringbuffer.h

@@ -184,6 +184,84 @@ struct i915_priolist {
 	int priority;
 };
 
+/**
+ * struct intel_engine_execlists - execlist submission queue and port state
+ *
+ * The struct intel_engine_execlists represents the combined logical state of
+ * driver and the hardware state for execlist mode of submission.
+ */
+struct intel_engine_execlists {
+	/**
+	 * @irq_tasklet: softirq tasklet for bottom handler
+	 */
+	struct tasklet_struct irq_tasklet;
+
+	/**
+	 * @default_priolist: priority list for I915_PRIORITY_NORMAL
+	 */
+	struct i915_priolist default_priolist;
+
+	/**
+	 * @no_priolist: priority lists disabled
+	 */
+	bool no_priolist;
+
+	/**
+	 * @port: execlist port states
+	 *
+	 * For each hardware ELSP (ExecList Submission Port) we keep
+	 * track of the last request and the number of times we submitted
+	 * that port to hw. We then count the number of times the hw reports
+	 * a context completion or preemption. As only one context can
+	 * be active on hw, we limit resubmission of context to port[0]. This
+	 * is called Lite Restore, of the context.
+	 */
+	struct execlist_port {
+		/**
+		 * @request_count: combined request and submission count
+		 */
+		struct drm_i915_gem_request *request_count;
+#define EXECLIST_COUNT_BITS 2
+#define port_request(p) ptr_mask_bits((p)->request_count, EXECLIST_COUNT_BITS)
+#define port_count(p) ptr_unmask_bits((p)->request_count, EXECLIST_COUNT_BITS)
+#define port_pack(rq, count) ptr_pack_bits(rq, count, EXECLIST_COUNT_BITS)
+#define port_unpack(p, count) ptr_unpack_bits((p)->request_count, count, EXECLIST_COUNT_BITS)
+#define port_set(p, packed) ((p)->request_count = (packed))
+#define port_isset(p) ((p)->request_count)
+#define port_index(p, e) ((p) - (e)->execlists.port)
+
+		/**
+		 * @context_id: context ID for port
+		 */
+		GEM_DEBUG_DECL(u32 context_id);
+	} port[2];
+
+	/**
+	 * @queue: queue of requests, in priority lists
+	 */
+	struct rb_root queue;
+
+	/**
+	 * @first: leftmost level in priority @queue
+	 */
+	struct rb_node *first;
+
+	/**
+	 * @fw_domains: forcewake domains for irq tasklet
+	 */
+	unsigned int fw_domains;
+
+	/**
+	 * @csb_head: context status buffer head
+	 */
+	unsigned int csb_head;
+
+	/**
+	 * @csb_use_mmio: access csb through mmio, instead of hwsp
+	 */
+	bool csb_use_mmio;
+};
+
 #define INTEL_ENGINE_CS_MAX_NAME 8
 
 struct intel_engine_cs {
@@ -380,27 +458,7 @@ struct intel_engine_cs {
 		u32	*(*signal)(struct drm_i915_gem_request *req, u32 *cs);
 	} semaphore;
 
-	/* Execlists */
-	struct tasklet_struct irq_tasklet;
-	struct i915_priolist default_priolist;
-	bool no_priolist;
-	struct execlist_port {
-		struct drm_i915_gem_request *request_count;
-#define EXECLIST_COUNT_BITS 2
-#define port_request(p) ptr_mask_bits((p)->request_count, EXECLIST_COUNT_BITS)
-#define port_count(p) ptr_unmask_bits((p)->request_count, EXECLIST_COUNT_BITS)
-#define port_pack(rq, count) ptr_pack_bits(rq, count, EXECLIST_COUNT_BITS)
-#define port_unpack(p, count) ptr_unpack_bits((p)->request_count, count, EXECLIST_COUNT_BITS)
-#define port_set(p, packed) ((p)->request_count = (packed))
-#define port_isset(p) ((p)->request_count)
-#define port_index(p, e) ((p) - (e)->execlist_port)
-		GEM_DEBUG_DECL(u32 context_id);
-	} execlist_port[2];
-	struct rb_root execlist_queue;
-	struct rb_node *execlist_first;
-	unsigned int fw_domains;
-	unsigned int csb_head;
-	bool csb_use_mmio;
+	struct intel_engine_execlists execlists;
 
 	/* Contexts are pinned whilst they are active on the GPU. The last
 	 * context executed remains active whilst the GPU is idle - the