drm/i915: Allocate intel_engine_cs structure only for the enabled engines

With the possibility of addition of many more number of rings in future,
the drm_i915_private structure could bloat as an array, of type
intel_engine_cs, is embedded inside it.
	struct intel_engine_cs engine[I915_NUM_ENGINES];
Though this is still fine as generally there is only a single instance of
drm_i915_private structure used, but not all of the possible rings would be
enabled or active on most of the platforms. Some memory can be saved by
allocating intel_engine_cs structure only for the enabled/active engines.
Currently the engine/ring ID is kept static and dev_priv->engine[] is simply
indexed using the enums defined in intel_engine_id.
To save memory and continue using the static engine/ring IDs, 'engine' is
defined as an array of pointers.
	struct intel_engine_cs *engine[I915_NUM_ENGINES];
dev_priv->engine[engine_ID] will be NULL for disabled engine instances.

There is a text size reduction of 928 bytes, from 1028200 to 1027272, for
i915.o file (but for i915.ko file text size remain same as 1193131 bytes).

v2:
- Remove the engine iterator field added in drm_i915_private structure,
  instead pass a local iterator variable to the for_each_engine**
  macros. (Chris)
- Do away with intel_engine_initialized() and instead directly use the
  NULL pointer check on engine pointer. (Chris)

v3:
- Remove for_each_engine_id() macro, as the updated macro for_each_engine()
  can be used in place of it. (Chris)
- Protect the access to Render engine Fault register with a NULL check, as
  engine specific init is done later in Driver load sequence.

v4:
- Use !!dev_priv->engine[VCS] style for the engine check in getparam. (Chris)
- Kill the superfluous init_engine_lists().

v5:
- Cleanup the intel_engines_init() & intel_engines_setup(), with respect to
  allocation of intel_engine_cs structure. (Chris)

v6:
- Rebase.

v7:
- Optimize the for_each_engine_masked() macro. (Chris)
- Change the type of 'iter' local variable to enum intel_engine_id. (Chris)
- Rebase.

v8: Rebase.

v9: Rebase.

v10:
- For index calculation use engine ID instead of pointer based arithmetic in
  intel_engine_sync_index() as engine pointers are not contiguous now (Chris)
- For appropriateness, rename local enum variable 'iter' to 'id'. (Joonas)
- Use for_each_engine macro for cleanup in intel_engines_init() and remove
  check for NULL engine pointer in cleanup() routines. (Joonas)

v11: Rebase.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Akash Goel <akash.goel@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1476378888-7372-1-git-send-email-akash.goel@intel.com

22 files changed, 194 insertions, 158 deletions

diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 70980f82a15b..f191d7b66b1d 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -1308,10 +1308,11 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	bool active = false;
 
 	/* If the command parser is not enabled, report 0 - unsupported */
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		if (intel_engine_needs_cmd_parser(engine)) {
 			active = true;
 			break;
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 2e312e0f2670..b20c1ccbd427 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -150,7 +150,7 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		   obj->base.size / 1024,
 		   obj->base.read_domains,
 		   obj->base.write_domain);
-	for_each_engine_id(engine, dev_priv, id)
+	for_each_engine(engine, dev_priv, id)
 		seq_printf(m, "%x ",
 			   i915_gem_active_get_seqno(&obj->last_read[id],
 						     &obj->base.dev->struct_mutex));
@@ -323,11 +323,12 @@ static void print_batch_pool_stats(struct seq_file *m,
 	struct drm_i915_gem_object *obj;
 	struct file_stats stats;
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int j;
 
 	memset(&stats, 0, sizeof(stats));
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		for (j = 0; j < ARRAY_SIZE(engine->batch_pool.cache_list); j++) {
 			list_for_each_entry(obj,
 					    &engine->batch_pool.cache_list[j],
@@ -596,6 +597,7 @@ static int i915_gem_batch_pool_info(struct seq_file *m, void *data)
 	struct drm_device *dev = &dev_priv->drm;
 	struct drm_i915_gem_object *obj;
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int total = 0;
 	int ret, j;
 
@@ -603,7 +605,7 @@ static int i915_gem_batch_pool_info(struct seq_file *m, void *data)
 	if (ret)
 		return ret;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		for (j = 0; j < ARRAY_SIZE(engine->batch_pool.cache_list); j++) {
 			int count;
 
@@ -655,8 +657,9 @@ static int i915_gem_request_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct drm_device *dev = &dev_priv->drm;
-	struct intel_engine_cs *engine;
 	struct drm_i915_gem_request *req;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int ret, any;
 
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
@@ -664,7 +667,7 @@ static int i915_gem_request_info(struct seq_file *m, void *data)
 		return ret;
 
 	any = 0;
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		int count;
 
 		count = 0;
@@ -710,8 +713,9 @@ static int i915_gem_seqno_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		i915_ring_seqno_info(m, engine);
 
 	return 0;
@@ -722,6 +726,7 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int i, pipe;
 
 	intel_runtime_pm_get(dev_priv);
@@ -890,7 +895,7 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 		seq_printf(m, "Graphics Interrupt mask:		%08x\n",
 			   I915_READ(GTIMR));
 	}
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		if (INTEL_GEN(dev_priv) >= 6) {
 			seq_printf(m,
 				   "Graphics Interrupt mask (%s):	%08x\n",
@@ -938,7 +943,7 @@ static int i915_hws_info(struct seq_file *m, void *data)
 	const u32 *hws;
 	int i;
 
-	engine = &dev_priv->engine[(uintptr_t)node->info_ent->data];
+	engine = dev_priv->engine[(uintptr_t)node->info_ent->data];
 	hws = engine->status_page.page_addr;
 	if (hws == NULL)
 		return 0;
@@ -1329,12 +1334,12 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 
 	intel_runtime_pm_get(dev_priv);
 
-	for_each_engine_id(engine, dev_priv, id) {
+	for_each_engine(engine, dev_priv, id) {
 		acthd[id] = intel_engine_get_active_head(engine);
 		seqno[id] = intel_engine_get_seqno(engine);
 	}
 
-	intel_engine_get_instdone(&dev_priv->engine[RCS], &instdone);
+	intel_engine_get_instdone(dev_priv->engine[RCS], &instdone);
 
 	intel_runtime_pm_put(dev_priv);
 
@@ -1345,7 +1350,7 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 	} else
 		seq_printf(m, "Hangcheck inactive\n");
 
-	for_each_engine_id(engine, dev_priv, id) {
+	for_each_engine(engine, dev_priv, id) {
 		struct intel_breadcrumbs *b = &engine->breadcrumbs;
 		struct rb_node *rb;
 
@@ -1944,6 +1949,7 @@ static int i915_context_status(struct seq_file *m, void *unused)
 	struct drm_device *dev = &dev_priv->drm;
 	struct intel_engine_cs *engine;
 	struct i915_gem_context *ctx;
+	enum intel_engine_id id;
 	int ret;
 
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
@@ -1970,7 +1976,7 @@ static int i915_context_status(struct seq_file *m, void *unused)
 		seq_putc(m, ctx->remap_slice ? 'R' : 'r');
 		seq_putc(m, '\n');
 
-		for_each_engine(engine, dev_priv) {
+		for_each_engine(engine, dev_priv, id) {
 			struct intel_context *ce = &ctx->engine[engine->id];
 
 			seq_printf(m, "%s: ", engine->name);
@@ -2037,6 +2043,7 @@ static int i915_dump_lrc(struct seq_file *m, void *unused)
 	struct drm_device *dev = &dev_priv->drm;
 	struct intel_engine_cs *engine;
 	struct i915_gem_context *ctx;
+	enum intel_engine_id id;
 	int ret;
 
 	if (!i915.enable_execlists) {
@@ -2049,7 +2056,7 @@ static int i915_dump_lrc(struct seq_file *m, void *unused)
 		return ret;
 
 	list_for_each_entry(ctx, &dev_priv->context_list, link)
-		for_each_engine(engine, dev_priv)
+		for_each_engine(engine, dev_priv, id)
 			i915_dump_lrc_obj(m, ctx, engine);
 
 	mutex_unlock(&dev->struct_mutex);
@@ -2158,14 +2165,15 @@ static int per_file_ctx(int id, void *ptr, void *data)
 static void gen8_ppgtt_info(struct seq_file *m,
 			    struct drm_i915_private *dev_priv)
 {
-	struct intel_engine_cs *engine;
 	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int i;
 
 	if (!ppgtt)
 		return;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		seq_printf(m, "%s\n", engine->name);
 		for (i = 0; i < 4; i++) {
 			u64 pdp = I915_READ(GEN8_RING_PDP_UDW(engine, i));
@@ -2180,11 +2188,12 @@ static void gen6_ppgtt_info(struct seq_file *m,
 			    struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
 	if (IS_GEN6(dev_priv))
 		seq_printf(m, "GFX_MODE: 0x%08x\n", I915_READ(GFX_MODE));
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		seq_printf(m, "%s\n", engine->name);
 		if (IS_GEN7(dev_priv))
 			seq_printf(m, "GFX_MODE: 0x%08x\n",
@@ -2253,9 +2262,10 @@ out_unlock:
 static int count_irq_waiters(struct drm_i915_private *i915)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int count = 0;
 
-	for_each_engine(engine, i915)
+	for_each_engine(engine, i915, id)
 		count += intel_engine_has_waiter(engine);
 
 	return count;
@@ -2418,7 +2428,7 @@ static void i915_guc_client_info(struct seq_file *m,
 	seq_printf(m, "\tFailed doorbell: %u\n", client->b_fail);
 	seq_printf(m, "\tLast submission result: %d\n", client->retcode);
 
-	for_each_engine_id(engine, dev_priv, id) {
+	for_each_engine(engine, dev_priv, id) {
 		u64 submissions = client->submissions[id];
 		tot += submissions;
 		seq_printf(m, "\tSubmissions: %llu %s\n",
@@ -2461,7 +2471,7 @@ static int i915_guc_info(struct seq_file *m, void *data)
 	seq_printf(m, "GuC last action error code: %d\n", guc.action_err);
 
 	seq_printf(m, "\nGuC submissions:\n");
-	for_each_engine_id(engine, dev_priv, id) {
+	for_each_engine(engine, dev_priv, id) {
 		u64 submissions = guc.submissions[id];
 		total += submissions;
 		seq_printf(m, "\t%-24s: %10llu, last seqno 0x%08x\n",
@@ -3082,8 +3092,9 @@ static int i915_engine_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		struct intel_breadcrumbs *b = &engine->breadcrumbs;
 		struct drm_i915_gem_request *rq;
 		struct rb_node *rb;
@@ -3231,7 +3242,7 @@ static int i915_semaphore_status(struct seq_file *m, void *unused)
 		page = i915_gem_object_get_page(dev_priv->semaphore->obj, 0);
 
 		seqno = (uint64_t *)kmap_atomic(page);
-		for_each_engine_id(engine, dev_priv, id) {
+		for_each_engine(engine, dev_priv, id) {
 			uint64_t offset;
 
 			seq_printf(m, "%s\n", engine->name);
@@ -3256,7 +3267,7 @@ static int i915_semaphore_status(struct seq_file *m, void *unused)
 		kunmap_atomic(seqno);
 	} else {
 		seq_puts(m, "  Last signal:");
-		for_each_engine(engine, dev_priv)
+		for_each_engine(engine, dev_priv, id)
 			for (j = 0; j < num_rings; j++)
 				seq_printf(m, "0x%08x\n",
 					   I915_READ(engine->semaphore.mbox.signal[j]));
@@ -3264,7 +3275,7 @@ static int i915_semaphore_status(struct seq_file *m, void *unused)
 	}
 
 	seq_puts(m, "\nSync seqno:\n");
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		for (j = 0; j < num_rings; j++)
 			seq_printf(m, "  0x%08x ",
 				   engine->semaphore.sync_seqno[j]);
@@ -3320,7 +3331,7 @@ static int i915_wa_registers(struct seq_file *m, void *unused)
 	intel_runtime_pm_get(dev_priv);
 
 	seq_printf(m, "Workarounds applied: %d\n", workarounds->count);
-	for_each_engine_id(engine, dev_priv, id)
+	for_each_engine(engine, dev_priv, id)
 		seq_printf(m, "HW whitelist count for %s: %d\n",
 			   engine->name, workarounds->hw_whitelist_count[id]);
 	for (i = 0; i < workarounds->count; ++i) {
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index e9b3bfcb347a..8c3d4761dfa0 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -255,16 +255,16 @@ static int i915_getparam(struct drm_device *dev, void *data,
 		value = dev_priv->overlay ? 1 : 0;
 		break;
 	case I915_PARAM_HAS_BSD:
-		value = intel_engine_initialized(&dev_priv->engine[VCS]);
+		value = !!dev_priv->engine[VCS];
 		break;
 	case I915_PARAM_HAS_BLT:
-		value = intel_engine_initialized(&dev_priv->engine[BCS]);
+		value = !!dev_priv->engine[BCS];
 		break;
 	case I915_PARAM_HAS_VEBOX:
-		value = intel_engine_initialized(&dev_priv->engine[VECS]);
+		value = !!dev_priv->engine[VECS];
 		break;
 	case I915_PARAM_HAS_BSD2:
-		value = intel_engine_initialized(&dev_priv->engine[VCS2]);
+		value = !!dev_priv->engine[VCS2];
 		break;
 	case I915_PARAM_HAS_EXEC_CONSTANTS:
 		value = INTEL_GEN(dev_priv) >= 4;
@@ -1707,10 +1707,11 @@ int i915_resume_switcheroo(struct drm_device *dev)
 static void disable_engines_irq(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
 	/* Ensure irq handler finishes, and not run again. */
 	disable_irq(dev_priv->drm.irq);
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		tasklet_kill(&engine->irq_tasklet);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 6360e807c6ba..9e830b58b06b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1808,7 +1808,7 @@ struct drm_i915_private {
 
 	struct pci_dev *bridge_dev;
 	struct i915_gem_context *kernel_context;
-	struct intel_engine_cs engine[I915_NUM_ENGINES];
+	struct intel_engine_cs *engine[I915_NUM_ENGINES];
 	struct i915_vma *semaphore;
 	u32 next_seqno;
 
@@ -2125,19 +2125,11 @@ static inline struct drm_i915_private *guc_to_i915(struct intel_guc *guc)
 }
 
 /* Simple iterator over all initialised engines */
-#define for_each_engine(engine__, dev_priv__) \
-	for ((engine__) = &(dev_priv__)->engine[0]; \
-	     (engine__) < &(dev_priv__)->engine[I915_NUM_ENGINES]; \
-	     (engine__)++) \
-		for_each_if (intel_engine_initialized(engine__))
-
-/* Iterator with engine_id */
-#define for_each_engine_id(engine__, dev_priv__, id__) \
-	for ((engine__) = &(dev_priv__)->engine[0], (id__) = 0; \
-	     (engine__) < &(dev_priv__)->engine[I915_NUM_ENGINES]; \
-	     (engine__)++) \
-		for_each_if (((id__) = (engine__)->id, \
-			      intel_engine_initialized(engine__)))
+#define for_each_engine(engine__, dev_priv__, id__) \
+	for ((id__) = 0; \
+	     (id__) < I915_NUM_ENGINES; \
+	     (id__)++) \
+		for_each_if ((engine__) = (dev_priv__)->engine[(id__)])
 
 #define __mask_next_bit(mask) ({					\
 	int __idx = ffs(mask) - 1;					\
@@ -2148,7 +2140,7 @@ static inline struct drm_i915_private *guc_to_i915(struct intel_guc *guc)
 /* Iterator over subset of engines selected by mask */
 #define for_each_engine_masked(engine__, dev_priv__, mask__, tmp__) \
 	for (tmp__ = mask__ & INTEL_INFO(dev_priv__)->ring_mask;	\
-	     tmp__ ? (engine__ = &(dev_priv__)->engine[__mask_next_bit(tmp__)]), 1 : 0; )
+	     tmp__ ? (engine__ = (dev_priv__)->engine[__mask_next_bit(tmp__)]), 1 : 0; )
 
 enum hdmi_force_audio {
 	HDMI_AUDIO_OFF_DVI = -2,	/* no aux data for HDMI-DVI converter */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 77dc0590ecc7..fb460cc2857c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2626,10 +2626,11 @@ static void i915_gem_reset_engine(struct intel_engine_cs *engine)
 void i915_gem_reset(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
 	i915_gem_retire_requests(dev_priv);
 
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		i915_gem_reset_engine(engine);
 
 	i915_gem_restore_fences(&dev_priv->drm);
@@ -2677,12 +2678,13 @@ static void i915_gem_cleanup_engine(struct intel_engine_cs *engine)
 void i915_gem_set_wedged(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 	set_bit(I915_WEDGED, &dev_priv->gpu_error.flags);
 
 	i915_gem_context_lost(dev_priv);
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		i915_gem_cleanup_engine(engine);
 	mod_delayed_work(dev_priv->wq, &dev_priv->gt.idle_work, 0);
 
@@ -2721,6 +2723,7 @@ i915_gem_idle_work_handler(struct work_struct *work)
 		container_of(work, typeof(*dev_priv), gt.idle_work.work);
 	struct drm_device *dev = &dev_priv->drm;
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	bool rearm_hangcheck;
 
 	if (!READ_ONCE(dev_priv->gt.awake))
@@ -2743,7 +2746,7 @@ i915_gem_idle_work_handler(struct work_struct *work)
 	if (dev_priv->gt.active_engines)
 		goto out_unlock;
 
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		i915_gem_batch_pool_fini(&engine->batch_pool);
 
 	GEM_BUG_ON(!dev_priv->gt.awake);
@@ -2936,9 +2939,10 @@ int i915_gem_wait_for_idle(struct drm_i915_private *dev_priv,
 			   unsigned int flags)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int ret;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		if (engine->last_context == NULL)
 			continue;
 
@@ -3181,7 +3185,7 @@ i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj)
 	 */
 	wmb();
 	if (INTEL_GEN(dev_priv) >= 6 && !HAS_LLC(dev_priv))
-		POSTING_READ(RING_ACTHD(dev_priv->engine[RCS].mmio_base));
+		POSTING_READ(RING_ACTHD(dev_priv->engine[RCS]->mmio_base));
 
 	intel_fb_obj_flush(obj, false, write_origin(obj, I915_GEM_DOMAIN_GTT));
 
@@ -4416,6 +4420,7 @@ i915_gem_init_hw(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int ret;
 
 	/* Double layer security blanket, see i915_gem_init() */
@@ -4459,7 +4464,7 @@ i915_gem_init_hw(struct drm_device *dev)
 	}
 
 	/* Need to do basic initialisation of all rings first: */
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		ret = engine->init_hw(engine);
 		if (ret)
 			goto out;
@@ -4558,17 +4563,12 @@ i915_gem_cleanup_engines(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		dev_priv->gt.cleanup_engine(engine);
 }
 
-static void
-init_engine_lists(struct intel_engine_cs *engine)
-{
-	INIT_LIST_HEAD(&engine->request_list);
-}
-
 void
 i915_gem_load_init_fences(struct drm_i915_private *dev_priv)
 {
@@ -4605,7 +4605,6 @@ void
 i915_gem_load_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	int i;
 
 	dev_priv->objects =
 		kmem_cache_create("i915_gem_object",
@@ -4629,8 +4628,6 @@ i915_gem_load_init(struct drm_device *dev)
 	INIT_LIST_HEAD(&dev_priv->mm.unbound_list);
 	INIT_LIST_HEAD(&dev_priv->mm.bound_list);
 	INIT_LIST_HEAD(&dev_priv->mm.fence_list);
-	for (i = 0; i < I915_NUM_ENGINES; i++)
-		init_engine_lists(&dev_priv->engine[i]);
 	INIT_DELAYED_WORK(&dev_priv->gt.retire_work,
 			  i915_gem_retire_work_handler);
 	INIT_DELAYED_WORK(&dev_priv->gt.idle_work,
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index df10f4e95736..481ec43f8180 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -474,10 +474,11 @@ int i915_gem_context_init(struct drm_device *dev)
 void i915_gem_context_lost(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		if (engine->last_context) {
 			i915_gem_context_unpin(engine->last_context, engine);
 			engine->last_context = NULL;
@@ -492,13 +493,13 @@ void i915_gem_context_lost(struct drm_i915_private *dev_priv)
 			if (!i915_gem_context_is_default(ctx))
 				continue;
 
-			for_each_engine(engine, dev_priv)
+			for_each_engine(engine, dev_priv, id)
 				ctx->engine[engine->id].initialised = false;
 
 			ctx->remap_slice = ALL_L3_SLICES(dev_priv);
 		}
 
-		for_each_engine(engine, dev_priv) {
+		for_each_engine(engine, dev_priv, id) {
 			struct intel_context *kce =
 				&dev_priv->kernel_context->engine[engine->id];
 
@@ -563,6 +564,7 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 	struct drm_i915_private *dev_priv = req->i915;
 	struct intel_ring *ring = req->ring;
 	struct intel_engine_cs *engine = req->engine;
+	enum intel_engine_id id;
 	u32 flags = hw_flags | MI_MM_SPACE_GTT;
 	const int num_rings =
 		/* Use an extended w/a on ivb+ if signalling from other rings */
@@ -605,7 +607,7 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 
 			intel_ring_emit(ring,
 					MI_LOAD_REGISTER_IMM(num_rings));
-			for_each_engine(signaller, dev_priv) {
+			for_each_engine(signaller, dev_priv, id) {
 				if (signaller == engine)
 					continue;
 
@@ -634,7 +636,7 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 
 			intel_ring_emit(ring,
 					MI_LOAD_REGISTER_IMM(num_rings));
-			for_each_engine(signaller, dev_priv) {
+			for_each_engine(signaller, dev_priv, id) {
 				if (signaller == engine)
 					continue;
 
@@ -929,8 +931,9 @@ int i915_switch_context(struct drm_i915_gem_request *req)
 int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		struct drm_i915_gem_request *req;
 		int ret;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 5b6f81c1dbca..b5e9e669f50f 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -37,8 +37,9 @@ static bool
 gpu_is_idle(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		if (intel_engine_is_active(engine))
 			return false;
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 72c7c1855e70..fa4d27ca0c18 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1599,12 +1599,12 @@ eb_select_engine(struct drm_i915_private *dev_priv,
 			return NULL;
 		}
 
-		engine = &dev_priv->engine[_VCS(bsd_idx)];
+		engine = dev_priv->engine[_VCS(bsd_idx)];
 	} else {
-		engine = &dev_priv->engine[user_ring_map[user_ring_id]];
+		engine = dev_priv->engine[user_ring_map[user_ring_id]];
 	}
 
-	if (!intel_engine_initialized(engine)) {
+	if (!engine) {
 		DRM_DEBUG("execbuf with invalid ring: %u\n", user_ring_id);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 2d846aa39ca5..0a45063b465f 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1728,8 +1728,9 @@ static void gen8_ppgtt_enable(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		u32 four_level = USES_FULL_48BIT_PPGTT(dev) ? GEN8_GFX_PPGTT_48B : 0;
 		I915_WRITE(RING_MODE_GEN7(engine),
 			   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE | four_level));
@@ -1741,6 +1742,7 @@ static void gen7_ppgtt_enable(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
 	uint32_t ecochk, ecobits;
+	enum intel_engine_id id;
 
 	ecobits = I915_READ(GAC_ECO_BITS);
 	I915_WRITE(GAC_ECO_BITS, ecobits | ECOBITS_PPGTT_CACHE64B);
@@ -1754,7 +1756,7 @@ static void gen7_ppgtt_enable(struct drm_device *dev)
 	}
 	I915_WRITE(GAM_ECOCHK, ecochk);
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		/* GFX_MODE is per-ring on gen7+ */
 		I915_WRITE(RING_MODE_GEN7(engine),
 			   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
@@ -2239,11 +2241,12 @@ static bool needs_idle_maps(struct drm_i915_private *dev_priv)
 void i915_check_and_clear_faults(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
 	if (INTEL_INFO(dev_priv)->gen < 6)
 		return;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		u32 fault_reg;
 		fault_reg = I915_READ(RING_FAULT_REG(engine));
 		if (fault_reg & RING_FAULT_VALID) {
@@ -2260,7 +2263,10 @@ void i915_check_and_clear_faults(struct drm_i915_private *dev_priv)
 				   fault_reg & ~RING_FAULT_VALID);
 		}
 	}
-	POSTING_READ(RING_FAULT_REG(&dev_priv->engine[RCS]));
+
+	/* Engine specific init may not have been done till this point. */
+	if (dev_priv->engine[RCS])
+		POSTING_READ(RING_FAULT_REG(dev_priv->engine[RCS]));
 }
 
 static void i915_ggtt_flush(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index 8832f8ec1583..74ede1f53372 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -256,10 +256,11 @@ static int i915_gem_check_wedge(struct drm_i915_private *dev_priv)
 static int i915_gem_init_seqno(struct drm_i915_private *dev_priv, u32 seqno)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int ret;
 
 	/* Carefully retire all requests without writing to the rings */
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		ret = intel_engine_idle(engine,
 					I915_WAIT_INTERRUPTIBLE |
 					I915_WAIT_LOCKED);
@@ -276,7 +277,7 @@ static int i915_gem_init_seqno(struct drm_i915_private *dev_priv, u32 seqno)
 	}
 
 	/* Finally reset hw state */
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		intel_engine_init_seqno(engine, seqno);
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index cd38948107e7..8d4b9eb8718a 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -632,7 +632,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 
 			len += scnprintf(buf + len, sizeof(buf), "%s%s",
 					 first ? "" : ", ",
-					 dev_priv->engine[j].name);
+					 dev_priv->engine[j]->name);
 			first = 0;
 		}
 		scnprintf(buf + len, sizeof(buf), ")");
@@ -650,7 +650,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 
 		obj = ee->batchbuffer;
 		if (obj) {
-			err_puts(m, dev_priv->engine[i].name);
+			err_puts(m, dev_priv->engine[i]->name);
 			if (ee->pid != -1)
 				err_printf(m, " (submitted by %s [%d])",
 					   ee->comm,
@@ -658,12 +658,12 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 			err_printf(m, " --- gtt_offset = 0x%08x %08x\n",
 				   upper_32_bits(obj->gtt_offset),
 				   lower_32_bits(obj->gtt_offset));
-			print_error_obj(m, &dev_priv->engine[i], NULL, obj);
+			print_error_obj(m, dev_priv->engine[i], NULL, obj);
 		}
 
 		if (ee->num_requests) {
 			err_printf(m, "%s --- %d requests\n",
-				   dev_priv->engine[i].name,
+				   dev_priv->engine[i]->name,
 				   ee->num_requests);
 			for (j = 0; j < ee->num_requests; j++)
 				error_print_request(m, " ", &ee->requests[j]);
@@ -671,10 +671,10 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 
 		if (IS_ERR(ee->waiters)) {
 			err_printf(m, "%s --- ? waiters [unable to acquire spinlock]\n",
-				   dev_priv->engine[i].name);
+				   dev_priv->engine[i]->name);
 		} else if (ee->num_waiters) {
 			err_printf(m, "%s --- %d waiters\n",
-				   dev_priv->engine[i].name,
+				   dev_priv->engine[i]->name,
 				   ee->num_waiters);
 			for (j = 0; j < ee->num_waiters; j++) {
 				err_printf(m, " seqno 0x%08x for %s [%d]\n",
@@ -684,19 +684,19 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 			}
 		}
 
-		print_error_obj(m, &dev_priv->engine[i],
+		print_error_obj(m, dev_priv->engine[i],
 				"ringbuffer", ee->ringbuffer);
 
-		print_error_obj(m, &dev_priv->engine[i],
+		print_error_obj(m, dev_priv->engine[i],
 				"HW Status", ee->hws_page);
 
-		print_error_obj(m, &dev_priv->engine[i],
+		print_error_obj(m, dev_priv->engine[i],
 				"HW context", ee->ctx);
 
-		print_error_obj(m, &dev_priv->engine[i],
+		print_error_obj(m, dev_priv->engine[i],
 				"WA context", ee->wa_ctx);
 
-		print_error_obj(m, &dev_priv->engine[i],
+		print_error_obj(m, dev_priv->engine[i],
 				"WA batchbuffer", ee->wa_batchbuffer);
 	}
 
@@ -977,7 +977,7 @@ static void gen8_record_semaphore_state(struct drm_i915_error_state *error,
 	if (!error->semaphore)
 		return;
 
-	for_each_engine_id(to, dev_priv, id) {
+	for_each_engine(to, dev_priv, id) {
 		int idx;
 		u16 signal_offset;
 		u32 *tmp;
@@ -1247,14 +1247,14 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 		i915_error_object_create(dev_priv, dev_priv->semaphore);
 
 	for (i = 0; i < I915_NUM_ENGINES; i++) {
-		struct intel_engine_cs *engine = &dev_priv->engine[i];
+		struct intel_engine_cs *engine = dev_priv->engine[i];
 		struct drm_i915_error_engine *ee = &error->engine[i];
 		struct drm_i915_gem_request *request;
 
 		ee->pid = -1;
 		ee->engine_id = -1;
 
-		if (!intel_engine_initialized(engine))
+		if (!engine)
 			continue;
 
 		ee->engine_id = i;
diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index 3106dcc06fe9..a1f76c8f8cde 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -917,6 +917,7 @@ static void guc_addon_create(struct intel_guc *guc)
 	struct guc_policies *policies;
 	struct guc_mmio_reg_state *reg_state;
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	struct page *page;
 	u32 size;
 
@@ -944,10 +945,10 @@ static void guc_addon_create(struct intel_guc *guc)
 	 * so its address won't change after we've told the GuC where
 	 * to find it.
 	 */
-	engine = &dev_priv->engine[RCS];
+	engine = dev_priv->engine[RCS];
 	ads->golden_context_lrca = engine->status_page.ggtt_offset;
 
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		ads->eng_state_size[engine->guc_id] = intel_lr_context_size(engine);
 
 	/* GuC scheduling policies */
@@ -960,7 +961,7 @@ static void guc_addon_create(struct intel_guc *guc)
 	/* MMIO reg state */
 	reg_state = (void *)policies + sizeof(struct guc_policies);
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		reg_state->mmio_white_list[engine->guc_id].mmio_start =
 			engine->mmio_base + GUC_MMIO_WHITE_LIST_START;
 
@@ -1014,9 +1015,10 @@ int i915_guc_submission_init(struct drm_i915_private *dev_priv)
 int i915_guc_submission_enable(struct drm_i915_private *dev_priv)
 {
 	struct intel_guc *guc = &dev_priv->guc;
+	struct drm_i915_gem_request *request;
 	struct i915_guc_client *client;
 	struct intel_engine_cs *engine;
-	struct drm_i915_gem_request *request;
+	enum intel_engine_id id;
 
 	/* client for execbuf submission */
 	client = guc_client_alloc(dev_priv,
@@ -1033,7 +1035,7 @@ int i915_guc_submission_enable(struct drm_i915_private *dev_priv)
 	guc_init_doorbell_hw(guc);
 
 	/* Take over from manual control of ELSP (execlists) */
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		engine->submit_request = i915_guc_submit;
 
 		/* Replay the current set of previously submitted requests */
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 91077e426c77..89380c830cc0 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1058,8 +1058,9 @@ static u32 vlv_wa_c0_ei(struct drm_i915_private *dev_priv, u32 pm_iir)
 static bool any_waiters(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		if (intel_engine_has_waiter(engine))
 			return true;
 
@@ -1257,20 +1258,20 @@ static void ilk_gt_irq_handler(struct drm_i915_private *dev_priv,
 			       u32 gt_iir)
 {
 	if (gt_iir & GT_RENDER_USER_INTERRUPT)
-		notify_ring(&dev_priv->engine[RCS]);
+		notify_ring(dev_priv->engine[RCS]);
 	if (gt_iir & ILK_BSD_USER_INTERRUPT)
-		notify_ring(&dev_priv->engine[VCS]);
+		notify_ring(dev_priv->engine[VCS]);
 }
 
 static void snb_gt_irq_handler(struct drm_i915_private *dev_priv,
 			       u32 gt_iir)
 {
 	if (gt_iir & GT_RENDER_USER_INTERRUPT)
-		notify_ring(&dev_priv->engine[RCS]);
+		notify_ring(dev_priv->engine[RCS]);
 	if (gt_iir & GT_BSD_USER_INTERRUPT)
-		notify_ring(&dev_priv->engine[VCS]);
+		notify_ring(dev_priv->engine[VCS]);
 	if (gt_iir & GT_BLT_USER_INTERRUPT)
-		notify_ring(&dev_priv->engine[BCS]);
+		notify_ring(dev_priv->engine[BCS]);
 
 	if (gt_iir & (GT_BLT_CS_ERROR_INTERRUPT |
 		      GT_BSD_CS_ERROR_INTERRUPT |
@@ -1340,21 +1341,21 @@ static void gen8_gt_irq_handler(struct drm_i915_private *dev_priv,
 				u32 gt_iir[4])
 {
 	if (gt_iir[0]) {
-		gen8_cs_irq_handler(&dev_priv->engine[RCS],
+		gen8_cs_irq_handler(dev_priv->engine[RCS],
 				    gt_iir[0], GEN8_RCS_IRQ_SHIFT);
-		gen8_cs_irq_handler(&dev_priv->engine[BCS],
+		gen8_cs_irq_handler(dev_priv->engine[BCS],
 				    gt_iir[0], GEN8_BCS_IRQ_SHIFT);
 	}
 
 	if (gt_iir[1]) {
-		gen8_cs_irq_handler(&dev_priv->engine[VCS],
+		gen8_cs_irq_handler(dev_priv->engine[VCS],
 				    gt_iir[1], GEN8_VCS1_IRQ_SHIFT);
-		gen8_cs_irq_handler(&dev_priv->engine[VCS2],
+		gen8_cs_irq_handler(dev_priv->engine[VCS2],
 				    gt_iir[1], GEN8_VCS2_IRQ_SHIFT);
 	}
 
 	if (gt_iir[3])
-		gen8_cs_irq_handler(&dev_priv->engine[VECS],
+		gen8_cs_irq_handler(dev_priv->engine[VECS],
 				    gt_iir[3], GEN8_VECS_IRQ_SHIFT);
 
 	if (gt_iir[2] & dev_priv->pm_rps_events)
@@ -1598,7 +1599,7 @@ static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir)
 
 	if (HAS_VEBOX(dev_priv)) {
 		if (pm_iir & PM_VEBOX_USER_INTERRUPT)
-			notify_ring(&dev_priv->engine[VECS]);
+			notify_ring(dev_priv->engine[VECS]);
 
 		if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT)
 			DRM_DEBUG("Command parser error, pm_iir 0x%08x\n", pm_iir);
@@ -2588,7 +2589,7 @@ static void i915_report_and_clear_eir(struct drm_i915_private *dev_priv)
 
 	pr_err("render error detected, EIR: 0x%08x\n", eir);
 
-	intel_engine_get_instdone(&dev_priv->engine[RCS], &instdone);
+	intel_engine_get_instdone(dev_priv->engine[RCS], &instdone);
 
 	if (IS_G4X(dev_priv)) {
 		if (eir & (GM45_ERROR_MEM_PRIV | GM45_ERROR_CP_PRIV)) {
@@ -2833,9 +2834,10 @@ semaphore_wait_to_signaller_ring(struct intel_engine_cs *engine, u32 ipehr,
 {
 	struct drm_i915_private *dev_priv = engine->i915;
 	struct intel_engine_cs *signaller;
+	enum intel_engine_id id;
 
 	if (INTEL_GEN(dev_priv) >= 8) {
-		for_each_engine(signaller, dev_priv) {
+		for_each_engine(signaller, dev_priv, id) {
 			if (engine == signaller)
 				continue;
 
@@ -2845,7 +2847,7 @@ semaphore_wait_to_signaller_ring(struct intel_engine_cs *engine, u32 ipehr,
 	} else {
 		u32 sync_bits = ipehr & MI_SEMAPHORE_SYNC_MASK;
 
-		for_each_engine(signaller, dev_priv) {
+		for_each_engine(signaller, dev_priv, id) {
 			if(engine == signaller)
 				continue;
 
@@ -2966,8 +2968,9 @@ static int semaphore_passed(struct intel_engine_cs *engine)
 static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		engine->hangcheck.deadlock = 0;
 }
 
@@ -3094,6 +3097,7 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 		container_of(work, typeof(*dev_priv),
 			     gpu_error.hangcheck_work.work);
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	unsigned int hung = 0, stuck = 0;
 	int busy_count = 0;
 #define BUSY 1
@@ -3113,7 +3117,7 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 	 */
 	intel_uncore_arm_unclaimed_mmio_detection(dev_priv);
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		bool busy = intel_engine_has_waiter(engine);
 		u64 acthd;
 		u32 seqno;
@@ -4004,7 +4008,7 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 		new_iir = I915_READ16(IIR); /* Flush posted writes */
 
 		if (iir & I915_USER_INTERRUPT)
-			notify_ring(&dev_priv->engine[RCS]);
+			notify_ring(dev_priv->engine[RCS]);
 
 		for_each_pipe(dev_priv, pipe) {
 			int plane = pipe;
@@ -4201,7 +4205,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		new_iir = I915_READ(IIR); /* Flush posted writes */
 
 		if (iir & I915_USER_INTERRUPT)
-			notify_ring(&dev_priv->engine[RCS]);
+			notify_ring(dev_priv->engine[RCS]);
 
 		for_each_pipe(dev_priv, pipe) {
 			int plane = pipe;
@@ -4433,9 +4437,9 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		new_iir = I915_READ(IIR); /* Flush posted writes */
 
 		if (iir & I915_USER_INTERRUPT)
-			notify_ring(&dev_priv->engine[RCS]);
+			notify_ring(dev_priv->engine[RCS]);
 		if (iir & I915_BSD_USER_INTERRUPT)
-			notify_ring(&dev_priv->engine[VCS]);
+			notify_ring(dev_priv->engine[VCS]);
 
 		for_each_pipe(dev_priv, pipe) {
 			if (pipe_stats[pipe] & PIPE_START_VBLANK_INTERRUPT_STATUS &&
diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c
index 495611b7068d..23fc1042fed4 100644
--- a/drivers/gpu/drm/i915/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c
@@ -621,6 +621,7 @@ void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine)
 unsigned int intel_kick_waiters(struct drm_i915_private *i915)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	unsigned int mask = 0;
 
 	/* To avoid the task_struct disappearing beneath us as we wake up
@@ -628,7 +629,7 @@ unsigned int intel_kick_waiters(struct drm_i915_private *i915)
 	 * RCU lock, i.e. as we call wake_up_process() we must be holding the
 	 * rcu_read_lock().
 	 */
-	for_each_engine(engine, i915)
+	for_each_engine(engine, i915, id)
 		if (unlikely(intel_engine_wakeup(engine)))
 			mask |= intel_engine_flag(engine);
 
@@ -638,9 +639,10 @@ unsigned int intel_kick_waiters(struct drm_i915_private *i915)
 unsigned int intel_kick_signalers(struct drm_i915_private *i915)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	unsigned int mask = 0;
 
-	for_each_engine(engine, i915) {
+	for_each_engine(engine, i915, id) {
 		if (unlikely(READ_ONCE(engine->breadcrumbs.first_signal))) {
 			wake_up_process(engine->breadcrumbs.signaler);
 			mask |= intel_engine_flag(engine);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index cfcb03f82016..645a779b7ea4 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -12243,19 +12243,19 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 		work->flip_count = I915_READ(PIPE_FLIPCOUNT_G4X(pipe)) + 1;
 
 	if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) {
-		engine = &dev_priv->engine[BCS];
+		engine = dev_priv->engine[BCS];
 		if (fb->modifier[0] != old_fb->modifier[0])
 			/* vlv: DISPLAY_FLIP fails to change tiling */
 			engine = NULL;
 	} else if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev)) {
-		engine = &dev_priv->engine[BCS];
+		engine = dev_priv->engine[BCS];
 	} else if (INTEL_INFO(dev)->gen >= 7) {
 		engine = i915_gem_active_get_engine(&obj->last_write,
 						    &obj->base.dev->struct_mutex);
 		if (engine == NULL || engine->id != RCS)
-			engine = &dev_priv->engine[BCS];
+			engine = dev_priv->engine[BCS];
 	} else {
-		engine = &dev_priv->engine[RCS];
+		engine = dev_priv->engine[RCS];
 	}
 
 	mmio_flip = use_mmio_flip(engine, obj);
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 1d597feba97f..fba6edd9f819 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -82,12 +82,17 @@ static const struct engine_info {
 	},
 };
 
-static struct intel_engine_cs *
+static int
 intel_engine_setup(struct drm_i915_private *dev_priv,
 		   enum intel_engine_id id)
 {
 	const struct engine_info *info = &intel_engines[id];
-	struct intel_engine_cs *engine = &dev_priv->engine[id];
+	struct intel_engine_cs *engine;
+
+	GEM_BUG_ON(dev_priv->engine[id]);
+	engine = kzalloc(sizeof(*engine), GFP_KERNEL);
+	if (!engine)
+		return -ENOMEM;
 
 	engine->id = id;
 	engine->i915 = dev_priv;
@@ -97,7 +102,8 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 	engine->mmio_base = info->mmio_base;
 	engine->irq_shift = info->irq_shift;
 
-	return engine;
+	dev_priv->engine[id] = engine;
+	return 0;
 }
 
 /**
@@ -112,6 +118,8 @@ int intel_engines_init(struct drm_device *dev)
 	struct intel_device_info *device_info = mkwrite_device_info(dev_priv);
 	unsigned int mask = 0;
 	int (*init)(struct intel_engine_cs *engine);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	unsigned int i;
 	int ret;
 
@@ -131,7 +139,11 @@ int intel_engines_init(struct drm_device *dev)
 		if (!init)
 			continue;
 
-		ret = init(intel_engine_setup(dev_priv, i));
+		ret = intel_engine_setup(dev_priv, i);
+		if (ret)
+			goto cleanup;
+
+		ret = init(dev_priv->engine[i]);
 		if (ret)
 			goto cleanup;
 
@@ -151,11 +163,11 @@ int intel_engines_init(struct drm_device *dev)
 	return 0;
 
 cleanup:
-	for (i = 0; i < I915_NUM_ENGINES; i++) {
+	for_each_engine(engine, dev_priv, id) {
 		if (i915.enable_execlists)
-			intel_logical_ring_cleanup(&dev_priv->engine[i]);
+			intel_logical_ring_cleanup(engine);
 		else
-			intel_engine_cleanup(&dev_priv->engine[i]);
+			intel_engine_cleanup(engine);
 	}
 
 	return ret;
diff --git a/drivers/gpu/drm/i915/intel_guc_loader.c b/drivers/gpu/drm/i915/intel_guc_loader.c
index 7ace96be82a8..95c6751d598d 100644
--- a/drivers/gpu/drm/i915/intel_guc_loader.c
+++ b/drivers/gpu/drm/i915/intel_guc_loader.c
@@ -100,12 +100,13 @@ const char *intel_guc_fw_status_repr(enum intel_guc_fw_status status)
 static void guc_interrupts_release(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int irqs;
 
 	/* tell all command streamers NOT to forward interrupts or vblank to GuC */
 	irqs = _MASKED_FIELD(GFX_FORWARD_VBLANK_MASK, GFX_FORWARD_VBLANK_NEVER);
 	irqs |= _MASKED_BIT_DISABLE(GFX_INTERRUPT_STEERING);
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		I915_WRITE(RING_MODE_GEN7(engine), irqs);
 
 	/* route all GT interrupts to the host */
@@ -117,12 +118,13 @@ static void guc_interrupts_release(struct drm_i915_private *dev_priv)
 static void guc_interrupts_capture(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int irqs;
 	u32 tmp;
 
 	/* tell all command streamers to forward interrupts (but not vblank) to GuC */
 	irqs = _MASKED_BIT_ENABLE(GFX_INTERRUPT_STEERING);
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		I915_WRITE(RING_MODE_GEN7(engine), irqs);
 
 	/* route USER_INTERRUPT to Host, all others are sent to GuC. */
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 10fcea57e4dd..bc86585b9fbb 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1648,9 +1648,6 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv;
 
-	if (!intel_engine_initialized(engine))
-		return;
-
 	/*
 	 * Tasklet cannot be active at this point due intel_mark_active/idle
 	 * so this is just for documentation.
@@ -1677,13 +1674,16 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
 
 	lrc_destroy_wa_ctx_obj(engine);
 	engine->i915 = NULL;
+	dev_priv->engine[engine->id] = NULL;
+	kfree(engine);
 }
 
 void intel_execlists_enable_submission(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		engine->submit_request = execlists_submit_request;
 }
 
@@ -2151,6 +2151,7 @@ void intel_lr_context_resume(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
 	struct i915_gem_context *ctx;
+	enum intel_engine_id id;
 
 	/* Because we emit WA_TAIL_DWORDS there may be a disparity
 	 * between our bookkeeping in ce->ring->head and ce->ring->tail and
@@ -2163,7 +2164,7 @@ void intel_lr_context_resume(struct drm_i915_private *dev_priv)
 	 * simplicity, we just zero everything out.
 	 */
 	list_for_each_entry(ctx, &dev_priv->context_list, link) {
-		for_each_engine(engine, dev_priv) {
+		for_each_engine(engine, dev_priv, id) {
 			struct intel_context *ce = &ctx->engine[engine->id];
 			u32 *reg;
 
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 8c411bfc3b3f..25bcd4a178d3 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -233,7 +233,7 @@ static int intel_overlay_do_wait_request(struct intel_overlay *overlay,
 static struct drm_i915_gem_request *alloc_request(struct intel_overlay *overlay)
 {
 	struct drm_i915_private *dev_priv = overlay->i915;
-	struct intel_engine_cs *engine = &dev_priv->engine[RCS];
+	struct intel_engine_cs *engine = dev_priv->engine[RCS];
 
 	return i915_gem_request_alloc(engine, dev_priv->kernel_context);
 }
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 38081387802d..15f21c6eb4f4 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5367,6 +5367,7 @@ static void gen9_enable_rps(struct drm_i915_private *dev_priv)
 static void gen9_enable_rc6(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	uint32_t rc6_mask = 0;
 
 	/* 1a: Software RC state - RC0 */
@@ -5388,7 +5389,7 @@ static void gen9_enable_rc6(struct drm_i915_private *dev_priv)
 		I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16);
 	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
 	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 
 	if (HAS_GUC(dev_priv))
@@ -5433,6 +5434,7 @@ static void gen9_enable_rc6(struct drm_i915_private *dev_priv)
 static void gen8_enable_rps(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	uint32_t rc6_mask = 0;
 
 	/* 1a: Software RC state - RC0 */
@@ -5449,7 +5451,7 @@ static void gen8_enable_rps(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
 	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
 	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 	I915_WRITE(GEN6_RC_SLEEP, 0);
 	if (IS_BROADWELL(dev_priv))
@@ -5509,6 +5511,7 @@ static void gen8_enable_rps(struct drm_i915_private *dev_priv)
 static void gen6_enable_rps(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	u32 rc6vids, rc6_mask = 0;
 	u32 gtfifodbg;
 	int rc6_mode;
@@ -5542,7 +5545,7 @@ static void gen6_enable_rps(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000);
 	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25);
 
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 
 	I915_WRITE(GEN6_RC_SLEEP, 0);
@@ -5991,6 +5994,7 @@ static void valleyview_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
 static void cherryview_enable_rps(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	u32 gtfifodbg, val, rc6_mode = 0, pcbr;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
@@ -6017,7 +6021,7 @@ static void cherryview_enable_rps(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
 	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
 
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 	I915_WRITE(GEN6_RC_SLEEP, 0);
 
@@ -6079,6 +6083,7 @@ static void cherryview_enable_rps(struct drm_i915_private *dev_priv)
 static void valleyview_enable_rps(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	u32 gtfifodbg, val, rc6_mode = 0;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
@@ -6118,7 +6123,7 @@ static void valleyview_enable_rps(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000);
 	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25);
 
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, id)
 		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 
 	I915_WRITE(GEN6_RC6_THRESHOLD, 0x557);
@@ -6801,7 +6806,7 @@ static void __intel_autoenable_gt_powersave(struct work_struct *work)
 	if (READ_ONCE(dev_priv->rps.enabled))
 		goto out;
 
-	rcs = &dev_priv->engine[RCS];
+	rcs = dev_priv->engine[RCS];
 	if (rcs->last_context)
 		goto out;
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 729f373782e2..e107455b0168 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1228,7 +1228,7 @@ static int gen8_rcs_signal(struct drm_i915_gem_request *req)
 	if (ret)
 		return ret;
 
-	for_each_engine_id(waiter, dev_priv, id) {
+	for_each_engine(waiter, dev_priv, id) {
 		u64 gtt_offset = req->engine->semaphore.signal_ggtt[id];
 		if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
 			continue;
@@ -1265,7 +1265,7 @@ static int gen8_xcs_signal(struct drm_i915_gem_request *req)
 	if (ret)
 		return ret;
 
-	for_each_engine_id(waiter, dev_priv, id) {
+	for_each_engine(waiter, dev_priv, id) {
 		u64 gtt_offset = req->engine->semaphore.signal_ggtt[id];
 		if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
 			continue;
@@ -1292,6 +1292,7 @@ static int gen6_signal(struct drm_i915_gem_request *req)
 	struct intel_ring *ring = req->ring;
 	struct drm_i915_private *dev_priv = req->i915;
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int ret, num_rings;
 
 	num_rings = INTEL_INFO(dev_priv)->num_rings;
@@ -1299,7 +1300,7 @@ static int gen6_signal(struct drm_i915_gem_request *req)
 	if (ret)
 		return ret;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		i915_reg_t mbox_reg;
 
 		if (!(BIT(engine->hw_id) & GEN6_SEMAPHORES_MASK))
@@ -2091,9 +2092,6 @@ void intel_engine_cleanup(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv;
 
-	if (!intel_engine_initialized(engine))
-		return;
-
 	dev_priv = engine->i915;
 
 	if (engine->buffer) {
@@ -2120,13 +2118,16 @@ void intel_engine_cleanup(struct intel_engine_cs *engine)
 	intel_ring_context_unpin(dev_priv->kernel_context, engine);
 
 	engine->i915 = NULL;
+	dev_priv->engine[engine->id] = NULL;
+	kfree(engine);
 }
 
 void intel_legacy_submission_resume(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		engine->buffer->head = engine->buffer->tail;
 		engine->buffer->last_retired_head = -1;
 	}
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 36eff9765cc2..32b2e6332ccf 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -395,12 +395,6 @@ struct intel_engine_cs {
 	u32 (*get_cmd_length_mask)(u32 cmd_header);
 };
 
-static inline bool
-intel_engine_initialized(const struct intel_engine_cs *engine)
-{
-	return engine->i915 != NULL;
-}
-
 static inline unsigned
 intel_engine_flag(const struct intel_engine_cs *engine)
 {
@@ -421,7 +415,7 @@ intel_engine_sync_index(struct intel_engine_cs *engine,
 	 * vcs2 -> 0 = rcs, 1 = vcs, 2 = bcs, 3 = vecs;
 	 */
 
-	idx = (other - engine) - 1;
+	idx = (other->id - engine->id) - 1;
 	if (idx < 0)
 		idx += I915_NUM_ENGINES;