drm/i915: Make execlist port count variable

As we emulate execlists on top of the GuC workqueue, it is not
restricted to just 2 ports and we can increase that number arbitrarily
to trade-off queue depth (i.e. scheduling latency) against pipeline
bubbles.

v2: rebase. better commit msg (Chris)
v3: rebase

Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170922124307.10914-5-mika.kuoppala@intel.com

drivers/gpu/drm/i915/i915_debugfs.c

@@ -3312,6 +3312,7 @@ static int i915_engine_info(struct seq_file *m, void *unused)
 
 		if (i915_modparams.enable_execlists) {
 			const u32 *hws = &engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
+			struct intel_engine_execlists * const execlists = &engine->execlists;
 			u32 ptr, read, write;
 			unsigned int idx;
 
@@ -3323,7 +3324,7 @@ 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->execlists.csb_head,
+				   read, execlists->csb_head,
 				   write,
 				   intel_read_status_page(engine, intel_hws_csb_write_index(engine->i915)),
 				   yesno(test_bit(ENGINE_IRQ_EXECLIST,
@@ -3345,11 +3346,10 @@ static int i915_engine_info(struct seq_file *m, void *unused)
 			}
 
 			rcu_read_lock();
-			for (idx = 0; idx < ARRAY_SIZE(engine->execlists.port); idx++) {
+			for (idx = 0; idx < execlists_num_ports(execlists); idx++) {
 				unsigned int count;
 
-				rq = port_unpack(&engine->execlists.port[idx],
+				rq = port_unpack(&execlists->port[idx], &count);
-						 &count);
 				if (rq) {
 					seq_printf(m, "\t\tELSP[%d] count=%d, ",
 						   idx, count);
@@ -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->execlists.first; rb; rb = rb_next(rb)) {
+			for (rb = execlists->first; rb; rb = rb_next(rb)) {
 				struct i915_priolist *p =
 					rb_entry(rb, typeof(*p), node);
 

drivers/gpu/drm/i915/i915_drv.h

@@ -1001,7 +1001,8 @@ struct i915_gpu_state {
 			u32 seqno;
 			u32 head;
 			u32 tail;
-		} *requests, execlist[2];
+		} *requests, execlist[EXECLIST_MAX_PORTS];
+		unsigned int num_ports;
 
 		struct drm_i915_error_waiter {
 			char comm[TASK_COMM_LEN];

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -396,6 +396,8 @@ static void error_print_context(struct drm_i915_error_state_buf *m,
 static void error_print_engine(struct drm_i915_error_state_buf *m,
 			       const struct drm_i915_error_engine *ee)
 {
+	int n;
+
 	err_printf(m, "%s command stream:\n", engine_str(ee->engine_id));
 	err_printf(m, "  START: 0x%08x\n", ee->start);
 	err_printf(m, "  HEAD:  0x%08x [0x%08x]\n", ee->head, ee->rq_head);
@@ -465,8 +467,11 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
 		   jiffies_to_msecs(jiffies - ee->hangcheck_timestamp));
 	err_printf(m, "  engine reset count: %u\n", ee->reset_count);
 
-	error_print_request(m, "  ELSP[0]: ", &ee->execlist[0]);
+	for (n = 0; n < ee->num_ports; n++) {
-	error_print_request(m, "  ELSP[1]: ", &ee->execlist[1]);
+		err_printf(m, "  ELSP[%d]:", n);
+		error_print_request(m, " ", &ee->execlist[n]);
+	}
+
 	error_print_context(m, "  Active context: ", &ee->context);
 }
 
@@ -1327,17 +1332,19 @@ 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->execlists.port;
+	const struct intel_engine_execlists * const execlists = &engine->execlists;
 	unsigned int n;
 
-	for (n = 0; n < ARRAY_SIZE(engine->execlists.port); n++) {
+	for (n = 0; n < execlists_num_ports(execlists); n++) {
-		struct drm_i915_gem_request *rq = port_request(&port[n]);
+		struct drm_i915_gem_request *rq = port_request(&execlists->port[n]);
 
 		if (!rq)
 			break;
 
 		record_request(rq, &ee->execlist[n]);
 	}
+
+	ee->num_ports = n;
 }
 
 static void record_context(struct drm_i915_error_context *e,

drivers/gpu/drm/i915/i915_guc_submission.c

@@ -562,6 +562,8 @@ static void i915_guc_dequeue(struct intel_engine_cs *engine)
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
 	struct drm_i915_gem_request *last = NULL;
+	const struct execlist_port * const last_port =
+		&execlists->port[execlists->port_mask];
 	bool submit = false;
 	struct rb_node *rb;
 
@@ -577,7 +579,7 @@ static void i915_guc_dequeue(struct intel_engine_cs *engine)
 
 		list_for_each_entry_safe(rq, rn, &p->requests, priotree.link) {
 			if (last && rq->ctx != last->ctx) {
-				if (port != execlists->port) {
+				if (port == last_port) {
 					__list_del_many(&p->requests,
 							&rq->priotree.link);
 					goto done;
@@ -617,6 +619,8 @@ static void i915_guc_irq_handler(unsigned long data)
 	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
+	const struct execlist_port * const last_port =
+		&execlists->port[execlists->port_mask];
 	struct drm_i915_gem_request *rq;
 
 	rq = port_request(&port[0]);
@@ -629,7 +633,7 @@ static void i915_guc_irq_handler(unsigned long data)
 		rq = port_request(&port[0]);
 	}
 
-	if (!port_isset(&port[1]))
+	if (!port_isset(last_port))
 		i915_guc_dequeue(engine);
 }
 

drivers/gpu/drm/i915/intel_engine_cs.c

@@ -405,6 +405,10 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine)
 
 	execlists->csb_use_mmio = csb_force_mmio(engine->i915);
 
+	execlists->port_mask = 1;
+	BUILD_BUG_ON_NOT_POWER_OF_2(execlists_num_ports(execlists));
+	GEM_BUG_ON(execlists_num_ports(execlists) > EXECLIST_MAX_PORTS);
+
 	execlists->queue = RB_ROOT;
 	execlists->first = NULL;
 }

drivers/gpu/drm/i915/intel_lrc.c

@@ -399,7 +399,7 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
 		engine->i915->regs + i915_mmio_reg_offset(RING_ELSP(engine));
 	unsigned int n;
 
-	for (n = ARRAY_SIZE(engine->execlists.port); n--; ) {
+	for (n = execlists_num_ports(&engine->execlists); n--; ) {
 		struct drm_i915_gem_request *rq;
 		unsigned int count;
 		u64 desc;
@@ -456,6 +456,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	struct drm_i915_gem_request *last;
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
+	const struct execlist_port * const last_port =
+		&execlists->port[execlists->port_mask];
 	struct rb_node *rb;
 	bool submit = false;
 
@@ -515,7 +517,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * combine this request with the last, then we
 				 * are done.
 				 */
-				if (port != execlists->port) {
+				if (port == last_port) {
 					__list_del_many(&p->requests,
 							&rq->priotree.link);
 					goto done;

drivers/gpu/drm/i915/intel_ringbuffer.h

@@ -234,7 +234,14 @@ struct intel_engine_execlists {
 		 * @context_id: context ID for port
 		 */
 		GEM_DEBUG_DECL(u32 context_id);
-	} port[2];
+
+#define EXECLIST_MAX_PORTS 2
+	} port[EXECLIST_MAX_PORTS];
+
+	/**
+	 * @port_mask: number of execlist ports - 1
+	 */
+	unsigned int port_mask;
 
 	/**
 	 * @queue: queue of requests, in priority lists
@@ -511,16 +518,22 @@ struct intel_engine_cs {
 	u32 (*get_cmd_length_mask)(u32 cmd_header);
 };
 
+static inline unsigned int
+execlists_num_ports(const struct intel_engine_execlists * const execlists)
+{
+	return execlists->port_mask + 1;
+}
+
 static inline void
 execlists_port_complete(struct intel_engine_execlists * const execlists,
 			struct execlist_port * const port)
 {
-	struct execlist_port * const port1 = &execlists->port[1];
+	const unsigned int m = execlists->port_mask;
 
 	GEM_BUG_ON(port_index(port, execlists) != 0);
 
-	*port = *port1;
+	memmove(port, port + 1, m * sizeof(struct execlist_port));
-	memset(port1, 0, sizeof(struct execlist_port));
+	memset(port + m, 0, sizeof(struct execlist_port));
 }
 
 static inline unsigned int