Skip to contentSkip to conversation

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

PATCH Applied [email protected] 8 participants 19 messages Oct 7, 2016 – Oct 14, 2016

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH v9 1/1 drm/i915: Allocate intel_engine_cs structure only for the enabled engines

From: Akash Goel <[email protected]>

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.

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.

---
 drivers/gpu/drm/i915/i915_cmd_parser.c     |  3 +-
 drivers/gpu/drm/i915/i915_debugfs.c        | 57 ++++++++++++++++++------------
 drivers/gpu/drm/i915/i915_drv.c            | 11 +++---
 drivers/gpu/drm/i915/i915_drv.h            | 22 ++++--------
 drivers/gpu/drm/i915/i915_gem.c            | 29 +++++++--------
 drivers/gpu/drm/i915/i915_gem_context.c    | 15 ++++----
 drivers/gpu/drm/i915/i915_gem_evict.c      |  3 +-
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  6 ++--
 drivers/gpu/drm/i915/i915_gem_gtt.c        | 14 +++++---
 drivers/gpu/drm/i915/i915_gem_request.c    |  5 +--
 drivers/gpu/drm/i915/i915_gpu_error.c      | 30 ++++++++--------
 drivers/gpu/drm/i915/i915_guc_submission.c | 12 ++++---
 drivers/gpu/drm/i915/i915_irq.c            | 44 ++++++++++++-----------
 drivers/gpu/drm/i915/intel_breadcrumbs.c   |  6 ++--
 drivers/gpu/drm/i915/intel_display.c       |  8 ++---
 drivers/gpu/drm/i915/intel_engine_cs.c     | 22 ++++++++----
 drivers/gpu/drm/i915/intel_guc_loader.c    |  6 ++--
 drivers/gpu/drm/i915/intel_lrc.c           | 10 ++++--
 drivers/gpu/drm/i915/intel_overlay.c       |  2 +-
 drivers/gpu/drm/i915/intel_pm.c            | 17 +++++----
 drivers/gpu/drm/i915/intel_ringbuffer.c    | 14 +++++---
 drivers/gpu/drm/i915/intel_ringbuffer.h    |  6 ----
 22 files changed, 191 insertions(+), 151 deletions(-)
drivers/gpu/drm/i915/i915_cmd_parser.c +2 -1
index 70980f8..bbcd2ec 100644
@@ -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 iter;
 	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, iter) {
 		if (intel_engine_needs_cmd_parser(engine)) {
 			active = true;
 			break;
drivers/gpu/drm/i915/i915_debugfs.c +34 -23

232 lines not on this page · raw message

drivers/gpu/drm/i915/i915_drv.c +6 -5
index 89d3222..5788593 100644
@@ -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;
@@ -1731,10 +1731,11 @@ 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 iter;
 
 	/* 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, iter)
 		tasklet_kill(&engine->irq_tasklet);
 }
 
drivers/gpu/drm/i915/i915_drv.h +7 -15
index a219a35..3efd5a6 100644
@@ -1804,7 +1804,7 @@ 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;
 
@@ -2121,19 +2121,11 @@ 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__, iter__) \
+	for ((iter__) = 0; \
+	     (iter__) < I915_NUM_ENGINES; \
+	     (iter__)++) \
+		for_each_if ((engine__) = (dev_priv__)->engine[(iter__)])
 
 #define __mask_next_bit(mask) ({					\
 	int __idx = ffs(mask) - 1;					\
@@ -2144,7 +2136,7 @@ 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 */
drivers/gpu/drm/i915/i915_gem.c +13 -16
index a89a889..adc7f09 100644
@@ -2622,10 +2622,11 @@ 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 iter;
 
 	i915_gem_retire_requests(dev_priv);
 
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, iter)
 		i915_gem_reset_engine(engine);
 
 	i915_gem_restore_fences(&dev_priv->drm);
@@ -2673,12 +2674,13 @@ 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 iter;
 
 	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, iter)
 		i915_gem_cleanup_engine(engine);
 	mod_delayed_work(dev_priv->wq, &dev_priv->gt.idle_work, 0);
 
@@ -2717,6 +2719,7 @@ 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 iter;
 	bool rearm_hangcheck;
 
 	if (!READ_ONCE(dev_priv->gt.awake))
@@ -2739,7 +2742,7 @@ 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, iter)
 		i915_gem_batch_pool_fini(&engine->batch_pool);
 
 	GEM_BUG_ON(!dev_priv->gt.awake);
@@ -2932,9 +2935,10 @@ int i915_gem_wait_for_idle(struct drm_i915_private *dev_priv,
 			   unsigned int flags)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id iter;
 	int ret;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, iter) {
 		if (engine->last_context == NULL)
 			continue;
 
@@ -3174,7 +3178,7 @@ 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));
 
@@ -4349,6 +4353,7 @@ 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 iter;
 	int ret;
 
 	/* Double layer security blanket, see i915_gem_init() */
@@ -4392,7 +4397,7 @@ 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, iter) {
 		ret = engine->init_hw(engine);
 		if (ret)
 			goto out;
@@ -4491,17 +4496,12 @@ 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 iter;
 
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, iter)
 		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)
 {
@@ -4538,7 +4538,6 @@ 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",
@@ -4562,8 +4561,6 @@ 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,
drivers/gpu/drm/i915/i915_gem_context.c +9 -6
index df10f4e9..3641955 100644
@@ -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 iter;
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, iter) {
 		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, iter)
 				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, iter) {
 			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 iter;
 	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, iter) {
 				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, iter) {
 				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 iter;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, iter) {
 		struct drm_i915_gem_request *req;
 		int ret;
 
drivers/gpu/drm/i915/i915_gem_evict.c +2 -1
index 5b6f81c..189b3be8 100644
@@ -37,8 +37,9 @@ static bool
 gpu_is_idle(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id iter;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, iter) {
 		if (intel_engine_is_active(engine))
 			return false;
 	}
drivers/gpu/drm/i915/i915_gem_execbuffer.c +3 -3
index e88786e..b70a7ab 100644
@@ -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;
 	}
drivers/gpu/drm/i915/i915_gem_gtt.c +10 -4
index 0bb4232..488db38 100644
@@ -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 iter;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, iter) {
 		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));
@@ -1740,6 +1741,7 @@ static void gen7_ppgtt_enable(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
+	enum intel_engine_id iter;
 	uint32_t ecochk, ecobits;
 
 	ecobits = I915_READ(GAC_ECO_BITS);
@@ -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, iter) {
 		/* 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 iter;
 
 	if (INTEL_INFO(dev_priv)->gen < 6)
 		return;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, iter) {
 		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)
drivers/gpu/drm/i915/i915_gem_request.c +3 -2
index 40978bc..c51151e 100644
@@ -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 iter;
 	int ret;
 
 	/* Carefully retire all requests without writing to the rings */
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, iter) {
 		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, iter)
 		intel_engine_init_seqno(engine, seqno);
 
 	return 0;
drivers/gpu/drm/i915/i915_gpu_error.c +15 -15
index b5b5869..8176b86 100644
@@ -464,7 +464,7 @@ 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), ")");
@@ -482,7 +482,7 @@ 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,
@@ -496,14 +496,14 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 		obj = ee->wa_batchbuffer;
 		if (obj) {
 			err_printf(m, "%s (w/a) --- gtt_offset = 0x%08x\n",
-				   dev_priv->engine[i].name,
+				   dev_priv->engine[i]->name,
 				   lower_32_bits(obj->gtt_offset));
 			print_error_obj(m, 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++) {
 				err_printf(m, "  pid %d, seqno 0x%08x, emitted %ld, head 0x%08x, tail 0x%08x\n",
@@ -517,10 +517,10 @@ 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",
@@ -532,7 +532,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 
 		if ((obj = ee->ringbuffer)) {
 			err_printf(m, "%s --- ringbuffer = 0x%08x\n",
-				   dev_priv->engine[i].name,
+				   dev_priv->engine[i]->name,
 				   lower_32_bits(obj->gtt_offset));
 			print_error_obj(m, obj);
 		}
@@ -546,7 +546,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 				hws_page = &obj->pages[LRC_PPHWSP_PN][0];
 			}
 			err_printf(m, "%s --- HW Status = 0x%08llx\n",
-				   dev_priv->engine[i].name, hws_offset);
+				   dev_priv->engine[i]->name, hws_offset);
 			offset = 0;
 			for (elt = 0; elt < PAGE_SIZE/16; elt += 4) {
 				err_printf(m, "[%04x] %08x %08x %08x %08x\n",
@@ -563,12 +563,12 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 		if (obj) {
 			u64 wa_ctx_offset = obj->gtt_offset;
 			u32 *wa_ctx_page = &obj->pages[0][0];
-			struct intel_engine_cs *engine = &dev_priv->engine[RCS];
+			struct intel_engine_cs *engine = dev_priv->engine[RCS];
 			u32 wa_ctx_size = (engine->wa_ctx.indirect_ctx.size +
 					   engine->wa_ctx.per_ctx.size);
 
 			err_printf(m, "%s --- WA ctx batch buffer = 0x%08llx\n",
-				   dev_priv->engine[i].name, wa_ctx_offset);
+				   dev_priv->engine[i]->name, wa_ctx_offset);
 			offset = 0;
 			for (elt = 0; elt < wa_ctx_size; elt += 4) {
 				err_printf(m, "[%04x] %08x %08x %08x %08x\n",
@@ -583,7 +583,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 
 		if ((obj = ee->ctx)) {
 			err_printf(m, "%s --- HW Context = 0x%08x\n",
-				   dev_priv->engine[i].name,
+				   dev_priv->engine[i]->name,
 				   lower_32_bits(obj->gtt_offset));
 			print_error_obj(m, obj);
 		}
@@ -918,7 +918,7 @@ 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;
@@ -1173,14 +1173,14 @@ 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;
@@ -1603,7 +1603,7 @@ void i915_get_engine_instdone(struct drm_i915_private *dev_priv,
 			      enum intel_engine_id engine_id,
 			      struct intel_instdone *instdone)
 {
-	u32 mmio_base = dev_priv->engine[engine_id].mmio_base;
+	u32 mmio_base = dev_priv->engine[engine_id]->mmio_base;
 	int slice;
 	int subslice;
 
drivers/gpu/drm/i915/i915_guc_submission.c +7 -5
index 43358e1..b09327c 100644
@@ -905,6 +905,7 @@ 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 iter;
 	struct page *page;
 	u32 size;
 
@@ -932,10 +933,10 @@ 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, iter)
 		ads->eng_state_size[engine->guc_id] = intel_lr_context_size(engine);
 
 	/* GuC scheduling policies */
@@ -948,7 +949,7 @@ 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, iter) {
 		reg_state->mmio_white_list[engine->guc_id].mmio_start =
 			engine->mmio_base + GUC_MMIO_WHITE_LIST_START;
 
@@ -1002,9 +1003,10 @@ 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 iter;
 
 	/* client for execbuf submission */
 	client = guc_client_alloc(dev_priv,
@@ -1021,7 +1023,7 @@ 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, iter) {
 		engine->submit_request = i915_guc_submit;
 
 		/* Replay the current set of previously submitted requests */
drivers/gpu/drm/i915/i915_irq.c +24 -20

140 lines not on this page · raw message

drivers/gpu/drm/i915/intel_breadcrumbs.c +4 -2
index 9bad14d..5e3bd38 100644
@@ -592,6 +592,7 @@ 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 iter;
 	unsigned int mask = 0;
 
 	/* To avoid the task_struct disappearing beneath us as we wake up
@@ -599,7 +600,7 @@ 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, iter)
 		if (unlikely(intel_engine_wakeup(engine)))
 			mask |= intel_engine_flag(engine);
 
@@ -609,9 +610,10 @@ 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 iter;
 	unsigned int mask = 0;
 
-	for_each_engine(engine, i915) {
+	for_each_engine(engine, i915, iter) {
 		if (unlikely(READ_ONCE(engine->breadcrumbs.first_signal))) {
 			wake_up_process(engine->breadcrumbs.signaler);
 			mask |= intel_engine_flag(engine);
drivers/gpu/drm/i915/intel_display.c +4 -4
index a366656..df5d9f8 100644
@@ -12242,19 +12242,19 @@ 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);
drivers/gpu/drm/i915/intel_engine_cs.c +16 -6
index d00ec80..9a028bb 100644
@@ -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;
 }
 
 /**
@@ -131,7 +137,11 @@ 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;
 
@@ -153,9 +163,9 @@ int intel_engines_init(struct drm_device *dev)
 cleanup:
 	for (i = 0; i < I915_NUM_ENGINES; i++) {
 		if (i915.enable_execlists)
-			intel_logical_ring_cleanup(&dev_priv->engine[i]);
+			intel_logical_ring_cleanup(dev_priv->engine[i]);
 		else
-			intel_engine_cleanup(&dev_priv->engine[i]);
+			intel_engine_cleanup(dev_priv->engine[i]);
 	}
 
 	return ret;
drivers/gpu/drm/i915/intel_guc_loader.c +4 -2
index 7ace96b..fd49bfb 100644
@@ -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 iter;
 	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, iter)
 		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 iter;
 	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, iter)
 		I915_WRITE(RING_MODE_GEN7(engine), irqs);
 
 	/* route USER_INTERRUPT to Host, all others are sent to GuC. */
drivers/gpu/drm/i915/intel_lrc.c +7 -3
index 936f6f6..08303e3 100644
@@ -1645,7 +1645,7 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv;
 
-	if (!intel_engine_initialized(engine))
+	if (!engine)
 		return;
 
 	/*
@@ -1674,13 +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 iter;
 
-	for_each_engine(engine, dev_priv)
+	for_each_engine(engine, dev_priv, iter)
 		engine->submit_request = execlists_submit_request;
 }
 
@@ -2148,6 +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 iter;
 
 	/* Because we emit WA_TAIL_DWORDS there may be a disparity
 	 * between our bookkeeping in ce->ring->head and ce->ring->tail and
@@ -2160,7 +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, iter) {
 			struct intel_context *ce = &ctx->engine[engine->id];
 			u32 *reg;
 
drivers/gpu/drm/i915/intel_overlay.c +1 -1
index a24bc8c..272eb93 100644
@@ -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);
 }
drivers/gpu/drm/i915/intel_pm.c +11 -6
index 7f1748a..8755580 100644
@@ -5359,6 +5359,7 @@ 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 iter;
 	uint32_t rc6_mask = 0;
 
 	/* 1a: Software RC state - RC0 */
@@ -5380,7 +5381,7 @@ 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, iter)
 		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 
 	if (HAS_GUC(dev_priv))
@@ -5425,6 +5426,7 @@ 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 iter;
 	uint32_t rc6_mask = 0;
 
 	/* 1a: Software RC state - RC0 */
@@ -5441,7 +5443,7 @@ 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, iter)
 		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 	I915_WRITE(GEN6_RC_SLEEP, 0);
 	if (IS_BROADWELL(dev_priv))
@@ -5501,6 +5503,7 @@ 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 iter;
 	u32 rc6vids, rc6_mask = 0;
 	u32 gtfifodbg;
 	int rc6_mode;
@@ -5534,7 +5537,7 @@ 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, iter)
 		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 
 	I915_WRITE(GEN6_RC_SLEEP, 0);
@@ -5983,6 +5986,7 @@ 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 iter;
 	u32 gtfifodbg, val, rc6_mode = 0, pcbr;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
@@ -6009,7 +6013,7 @@ 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, iter)
 		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 	I915_WRITE(GEN6_RC_SLEEP, 0);
 
@@ -6071,6 +6075,7 @@ 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 iter;
 	u32 gtfifodbg, val, rc6_mode = 0;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
@@ -6110,7 +6115,7 @@ 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, iter)
 		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 
 	I915_WRITE(GEN6_RC6_THRESHOLD, 0x557);
@@ -6793,7 +6798,7 @@ 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;
 
drivers/gpu/drm/i915/intel_ringbuffer.c +9 -5
index 35f359e..ad0cdd1 100644
@@ -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))
@@ -2091,7 +2092,7 @@ void intel_engine_cleanup(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv;
 
-	if (!intel_engine_initialized(engine))
+	if (!engine)
 		return;
 
 	dev_priv = engine->i915;
@@ -2120,13 +2121,16 @@ 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 iter;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, iter) {
 		engine->buffer->head = engine->buffer->tail;
 		engine->buffer->last_retired_head = -1;
 	}
drivers/gpu/drm/i915/intel_ringbuffer.h +0 -6
index 498931f0..60a8d9c 100644
@@ -394,12 +394,6 @@ 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)
 {
Signature · 6 lines
1.9.2

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#1 lore raw

✗ Fi.CI.BAT: failure for drm/i915: Allocate intel_engine_cs structure only for the enabled engines

== Series Details ==

== Series Details ==

Series: drm/i915: Allocate intel_engine_cs structure only for the enabled engines
URL : https://patchwork.freedesktop.org/series/13435/
State : failure

== Summary ==

Series 13435v1 drm/i915: Allocate intel_engine_cs structure only for the enabled engines
https://patchwork.freedesktop.org/api/1.0/series/13435/revisions/1/mbox/

Test drv_module_reload_basic:

                dmesg-warn -> PASS       (fi-ilk-650)
Test gem_exec_parallel:
        Subgroup basic:
                pass       -> INCOMPLETE (fi-snb-2600)
Test gem_sync:
        Subgroup basic-store-all:
                pass       -> INCOMPLETE (fi-bxt-t5700)
                pass       -> INCOMPLETE (fi-byt-j1900)
                pass       -> INCOMPLETE (fi-bsw-n3050)
                pass       -> INCOMPLETE (fi-hsw-4770)
                pass       -> INCOMPLETE (fi-skl-6700k)
                pass       -> INCOMPLETE (fi-skl-6770hq)
                pass       -> INCOMPLETE (fi-hsw-4770r)
                pass       -> INCOMPLETE (fi-snb-2520m)
                pass       -> INCOMPLETE (fi-kbl-7200u)
                pass       -> INCOMPLETE (fi-skl-6700hq)
                pass       -> INCOMPLETE (fi-ivb-3520m)
                pass       -> INCOMPLETE (fi-ivb-3770)
                pass       -> INCOMPLETE (fi-bdw-5557u)
                pass       -> INCOMPLETE (fi-skl-6260u)
Test vgem_basic:
        Subgroup unload:
                pass       -> SKIP       (fi-ilk-650)
fi-bdw-5557u     total:22   pass:21   dwarn:0   dfail:0   fail:0   skip:0  
fi-bsw-n3050     total:22   pass:19   dwarn:0   dfail:0   fail:0   skip:2  
fi-bxt-t5700     total:22   pass:19   dwarn:0   dfail:0   fail:0   skip:2  
fi-byt-j1900     total:22   pass:18   dwarn:0   dfail:0   fail:0   skip:3  
fi-hsw-4770      total:22   pass:19   dwarn:0   dfail:0   fail:0   skip:2  
fi-hsw-4770r     total:22   pass:19   dwarn:0   dfail:0   fail:0   skip:2  
fi-ilk-650       total:248  pass:184  dwarn:0   dfail:0   fail:2   skip:62 
fi-ivb-3520m     total:22   pass:18   dwarn:0   dfail:0   fail:0   skip:3  
fi-ivb-3770      total:22   pass:18   dwarn:0   dfail:0   fail:0   skip:3  
fi-kbl-7200u     total:22   pass:19   dwarn:0   dfail:0   fail:0   skip:2  
fi-skl-6260u     total:22   pass:21   dwarn:0   dfail:0   fail:0   skip:0  
fi-skl-6700hq    total:22   pass:19   dwarn:0   dfail:0   fail:0   skip:2  
fi-skl-6700k     total:22   pass:19   dwarn:0   dfail:0   fail:0   skip:2  
fi-skl-6770hq    total:22   pass:21   dwarn:0   dfail:0   fail:0   skip:0  
fi-snb-2520m     total:22   pass:17   dwarn:0   dfail:0   fail:0   skip:4  
fi-snb-2600      total:87   pass:71   dwarn:0   dfail:0   fail:0   skip:15 

Results at /archive/results/CI_IGT_test/Patchwork_2646/

81b22c4383bfe6290f7b9d821bf56768567c1718 drm-intel-nightly: 2016y-10m-07d-07h-29m-30s UTC integration manifest 385704a drm/i915: Allocate intel_engine_cs structure only for the enabled engines

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#2 lore raw

Re: ✗ Fi.CI.BAT: failure for drm/i915: Allocate intel_engine_cs structure only for the enabled engines

Quoted 24 lines · Patchwork

== Series Details ==

Series: drm/i915: Allocate intel_engine_cs structure only for the enabled engines
URL : https://patchwork.freedesktop.org/series/13435/
State : failure

== Summary ==

Series 13435v1 drm/i915: Allocate intel_engine_cs structure only for the enabled engines
https://patchwork.freedesktop.org/api/1.0/series/13435/revisions/1/mbox/

Test drv_module_reload_basic:

                dmesg-warn -> PASS       (fi-ilk-650)
Test gem_exec_parallel:
        Subgroup basic:
                pass       -> INCOMPLETE (fi-snb-2600)
Test gem_sync:
        Subgroup basic-store-all:
                pass       -> INCOMPLETE (fi-bxt-t5700)
                pass       -> INCOMPLETE (fi-byt-j1900)
                pass       -> INCOMPLETE (fi-bsw-n3050)
                pass       -> INCOMPLETE (fi-hsw-4770)
                pass       -> INCOMPLETE (fi-skl-6700k)
                pass       -> INCOMPLETE (fi-skl-6770hq)
Quoted 8 lines
                pass       -> INCOMPLETE (fi-hsw-4770r)
                pass       -> INCOMPLETE (fi-snb-2520m)
                pass       -> INCOMPLETE (fi-kbl-7200u)
                pass       -> INCOMPLETE (fi-skl-6700hq)
                pass       -> INCOMPLETE (fi-ivb-3520m)
                pass       -> INCOMPLETE (fi-ivb-3770)
                pass       -> INCOMPLETE (fi-bdw-5557u)
                pass       -> INCOMPLETE (fi-skl-6260u)

This is due to missing:

git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 8c08ced..44ef6b5 100644

drivers/gpu/drm/i915/intel_ringbuffer.h +1 -1
@@ -415,7 +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;
 

I believe that's the only case where we compare elements of the array, and even scheduled for removal.
-Chris

Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#3 lore raw

Re: ✗ Fi.CI.BAT: failure for drm/i915: Allocate intel_engine_cs structure only for the enabled engines

Quoted 49 lines · Chris Wilson
Quoted 24 lines · Patchwork

== Series Details ==

Series: drm/i915: Allocate intel_engine_cs structure only for the enabled engines
URL : https://patchwork.freedesktop.org/series/13435/
State : failure

== Summary ==

Series 13435v1 drm/i915: Allocate intel_engine_cs structure only for the enabled engines
https://patchwork.freedesktop.org/api/1.0/series/13435/revisions/1/mbox/

Test drv_module_reload_basic:

                dmesg-warn -> PASS       (fi-ilk-650)
Test gem_exec_parallel:
        Subgroup basic:
                pass       -> INCOMPLETE (fi-snb-2600)
Test gem_sync:
        Subgroup basic-store-all:
                pass       -> INCOMPLETE (fi-bxt-t5700)
                pass       -> INCOMPLETE (fi-byt-j1900)
                pass       -> INCOMPLETE (fi-bsw-n3050)
                pass       -> INCOMPLETE (fi-hsw-4770)
                pass       -> INCOMPLETE (fi-skl-6700k)
                pass       -> INCOMPLETE (fi-skl-6770hq)
Quoted 8 lines
                pass       -> INCOMPLETE (fi-hsw-4770r)
                pass       -> INCOMPLETE (fi-snb-2520m)
                pass       -> INCOMPLETE (fi-kbl-7200u)
                pass       -> INCOMPLETE (fi-skl-6700hq)
                pass       -> INCOMPLETE (fi-ivb-3520m)
                pass       -> INCOMPLETE (fi-ivb-3770)
                pass       -> INCOMPLETE (fi-bdw-5557u)
                pass       -> INCOMPLETE (fi-skl-6260u)

This is due to missing:

git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 8c08ced..44ef6b5 100644

drivers/gpu/drm/i915/intel_ringbuffer.h +1 -1
@@ -415,7 +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;
 
Quoted 2 lines

I believe that's the only case where we compare elements of the array, and even scheduled for removal.

Thank you very much for finding this anomaly.
So the cross engine synchronization was going for a toss, causing the above tests to get stuck or execute slowly ?.

best regards
Akash

Quoted 3 lines

-Chris

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

maintainer Reviewed-by on v9 1/1
#4 lore raw
In reply to [email protected]
Quoted 38 lines · On pe, 2016-10-07 at 15:03 +0530, [email protected] wrote:
Quoted 1 line

From: Akash Goel <[email protected]>

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.

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)

Quoted 8 lines

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.

Would not it be consistent to go with 'id' everywhere rather than 'iter'. Consistency is good, and my vote for 'id' as it's more descriptive?

Quoted 3 lines
(quoted diff) +0 -0
@@ -153,9 +163,9 @@ int intel_engines_init(struct drm_device *dev)

 cleanup:
  for (i = 0; i < I915_NUM_ENGINES; i++) {

Use for_each_engine here too.

Quoted 11 lines
drivers/gpu/drm/i915/intel_lrc.c +0 -0
index 936f6f6..08303e3 100644
@@ -1645,7 +1645,7 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
  {
  	struct drm_i915_private *dev_priv;

drivers/gpu/drm/i915/intel_lrc.c +1 -1
-	if (!intel_engine_initialized(engine))
+	if (!engine)

  return;

Remove this check or make it GEM_BUG_ON(!engine); but I don't think we need that much paranoia.

Quoted 2 lines
drivers/gpu/drm/i915/intel_ringbuffer.c +0 -0

<SNIP>

Quoted 7 lines
drivers/gpu/drm/i915/intel_ringbuffer.c +0 -0
@@ -2091,7 +2092,7 @@ void intel_engine_cleanup(struct intel_engine_cs *engine)
  {
 >  	struct drm_i915_private *dev_priv;

drivers/gpu/drm/i915/intel_ringbuffer.c +1 -1
-	if (!intel_engine_initialized(engine))
+	if (!engine)

  return;

Same as above.

With those points fixed;

Regards, Joonas

Signature · 7 lines
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#5 lore raw
Quoted 48 lines · Joonas Lahtinen
Quoted 38 lines · On pe, 2016-10-07 at 15:03 +0530, [email protected] wrote:
Quoted 1 line

From: Akash Goel <[email protected]>

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.

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)

Quoted 8 lines

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.

Quoted 3 lines

Would not it be consistent to go with 'id' everywhere rather than 'iter'. Consistency is good, and my vote for 'id' as it's more descriptive?

Fine will then go with 'id' only.

Quoted 7 lines

drivers/gpu/drm/i915/intel_engine_cs.c int intel_engines_init(struct drm_device *dev) · line 164

Quoted 4 lines
drivers/gpu/drm/i915/intel_engine_cs.c +0 -0
@@ -153,9 +163,9 @@ int intel_engines_init(struct drm_device *dev)
 cleanup:
      for (i = 0; i < I915_NUM_ENGINES; i++) {

Use for_each_engine here too.

Fine after using 'for_each_engine' here, the below Null pointer check on 'engine' can be removed safely.
As you suggested, will not keep BUG_ON also.

Quoted 24 lines

drivers/gpu/drm/i915/intel_lrc.c void intel_logical_ring_cleanup(struct intel_engine_cs *engine) · line 1649

Quoted 11 lines
drivers/gpu/drm/i915/intel_lrc.c +1 -1
index 936f6f6..08303e3 100644
@@ -1645,7 +1645,7 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
 {
      struct drm_i915_private *dev_priv;
 
-     if (!intel_engine_initialized(engine))
+     if (!engine)
              return;

Remove this check or make it GEM_BUG_ON(!engine); but I don't think we need that much paranoia.

Quoted 2 lines
drivers/gpu/drm/i915/intel_ringbuffer.c +0 -0

<SNIP>

Quoted 4 lines
drivers/gpu/drm/i915/intel_ringbuffer.c +0 -0
@@ -2091,7 +2092,7 @@ void intel_engine_cleanup(struct intel_engine_cs *engine)
 {
 >     struct drm_i915_private *dev_priv;
 
Quoted 8 lines

drivers/gpu/drm/i915/intel_ringbuffer.c void intel_engine_cleanup(struct intel_engine_cs *engine) · line 2096

Quoted 3 lines
drivers/gpu/drm/i915/intel_ringbuffer.c +1 -1
-     if (!intel_engine_initialized(engine))
+     if (!engine)
              return;

Same as above.

With those points fixed;

Chris found an issue inside intel_engine_sync_index(), will add his suggested fix also in the next version.

Quoted 1 line

Thanks much for the review.

Best regards
Akash

Quoted 10 lines

Regards, Joonas
--
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#6 lore raw

PATCH v10 1/1 drm/i915: Allocate intel_engine_cs structure only for the enabled engines

From: Akash Goel <[email protected]>

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)

---
 drivers/gpu/drm/i915/i915_cmd_parser.c     |  3 +-
 drivers/gpu/drm/i915/i915_debugfs.c        | 57 ++++++++++++++++++------------
 drivers/gpu/drm/i915/i915_drv.c            | 11 +++---
 drivers/gpu/drm/i915/i915_drv.h            | 22 ++++--------
 drivers/gpu/drm/i915/i915_gem.c            | 29 +++++++--------
 drivers/gpu/drm/i915/i915_gem_context.c    | 15 ++++----
 drivers/gpu/drm/i915/i915_gem_evict.c      |  3 +-
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  6 ++--
 drivers/gpu/drm/i915/i915_gem_gtt.c        | 14 +++++---
 drivers/gpu/drm/i915/i915_gem_request.c    |  5 +--
 drivers/gpu/drm/i915/i915_gpu_error.c      | 30 ++++++++--------
 drivers/gpu/drm/i915/i915_guc_submission.c | 12 ++++---
 drivers/gpu/drm/i915/i915_irq.c            | 44 ++++++++++++-----------
 drivers/gpu/drm/i915/intel_breadcrumbs.c   |  6 ++--
 drivers/gpu/drm/i915/intel_display.c       |  8 ++---
 drivers/gpu/drm/i915/intel_engine_cs.c     | 26 ++++++++++----
 drivers/gpu/drm/i915/intel_guc_loader.c    |  6 ++--
 drivers/gpu/drm/i915/intel_lrc.c           | 11 +++---
 drivers/gpu/drm/i915/intel_overlay.c       |  2 +-
 drivers/gpu/drm/i915/intel_pm.c            | 17 +++++----
 drivers/gpu/drm/i915/intel_ringbuffer.c    | 15 ++++----
 drivers/gpu/drm/i915/intel_ringbuffer.h    |  8 +----
 22 files changed, 193 insertions(+), 157 deletions(-)
drivers/gpu/drm/i915/i915_cmd_parser.c +2 -1
index 70980f8..f191d7b 100644
@@ -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;
drivers/gpu/drm/i915/i915_debugfs.c +34 -23

232 lines not on this page · raw message

drivers/gpu/drm/i915/i915_drv.c +6 -5
index 89d3222..b6b8dea 100644
@@ -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;
@@ -1731,10 +1731,11 @@ 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);
 }
 
drivers/gpu/drm/i915/i915_drv.h +7 -15
index a219a35..76d1167 100644
@@ -1804,7 +1804,7 @@ 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;
 
@@ -2121,19 +2121,11 @@ 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;					\
@@ -2144,7 +2136,7 @@ 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 */
drivers/gpu/drm/i915/i915_gem.c +13 -16
index a89a889..e6f0fbf 100644
@@ -2622,10 +2622,11 @@ 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);
@@ -2673,12 +2674,13 @@ 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);
 
@@ -2717,6 +2719,7 @@ 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))
@@ -2739,7 +2742,7 @@ 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);
@@ -2932,9 +2935,10 @@ 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;
 
@@ -3174,7 +3178,7 @@ 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));
 
@@ -4349,6 +4353,7 @@ 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() */
@@ -4392,7 +4397,7 @@ 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;
@@ -4491,17 +4496,12 @@ 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)
 {
@@ -4538,7 +4538,6 @@ 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",
@@ -4562,8 +4561,6 @@ 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,
drivers/gpu/drm/i915/i915_gem_context.c +9 -6
index df10f4e9..481ec43 100644
@@ -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;
 
drivers/gpu/drm/i915/i915_gem_evict.c +2 -1
index 5b6f81c..b5e9e66 100644
@@ -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;
 	}
drivers/gpu/drm/i915/i915_gem_execbuffer.c +3 -3
index 72c7c18..fa4d27c 100644
@@ -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;
 	}
drivers/gpu/drm/i915/i915_gem_gtt.c +10 -4
index 0bb4232..b35701c 100644
@@ -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)
drivers/gpu/drm/i915/i915_gem_request.c +3 -2
index 8832f8e..74ede1f 100644
@@ -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;
drivers/gpu/drm/i915/i915_gpu_error.c +15 -15
index b5b5869..8176b86 100644
@@ -464,7 +464,7 @@ 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), ")");
@@ -482,7 +482,7 @@ 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,
@@ -496,14 +496,14 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 		obj = ee->wa_batchbuffer;
 		if (obj) {
 			err_printf(m, "%s (w/a) --- gtt_offset = 0x%08x\n",
-				   dev_priv->engine[i].name,
+				   dev_priv->engine[i]->name,
 				   lower_32_bits(obj->gtt_offset));
 			print_error_obj(m, 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++) {
 				err_printf(m, "  pid %d, seqno 0x%08x, emitted %ld, head 0x%08x, tail 0x%08x\n",
@@ -517,10 +517,10 @@ 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",
@@ -532,7 +532,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 
 		if ((obj = ee->ringbuffer)) {
 			err_printf(m, "%s --- ringbuffer = 0x%08x\n",
-				   dev_priv->engine[i].name,
+				   dev_priv->engine[i]->name,
 				   lower_32_bits(obj->gtt_offset));
 			print_error_obj(m, obj);
 		}
@@ -546,7 +546,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 				hws_page = &obj->pages[LRC_PPHWSP_PN][0];
 			}
 			err_printf(m, "%s --- HW Status = 0x%08llx\n",
-				   dev_priv->engine[i].name, hws_offset);
+				   dev_priv->engine[i]->name, hws_offset);
 			offset = 0;
 			for (elt = 0; elt < PAGE_SIZE/16; elt += 4) {
 				err_printf(m, "[%04x] %08x %08x %08x %08x\n",
@@ -563,12 +563,12 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 		if (obj) {
 			u64 wa_ctx_offset = obj->gtt_offset;
 			u32 *wa_ctx_page = &obj->pages[0][0];
-			struct intel_engine_cs *engine = &dev_priv->engine[RCS];
+			struct intel_engine_cs *engine = dev_priv->engine[RCS];
 			u32 wa_ctx_size = (engine->wa_ctx.indirect_ctx.size +
 					   engine->wa_ctx.per_ctx.size);
 
 			err_printf(m, "%s --- WA ctx batch buffer = 0x%08llx\n",
-				   dev_priv->engine[i].name, wa_ctx_offset);
+				   dev_priv->engine[i]->name, wa_ctx_offset);
 			offset = 0;
 			for (elt = 0; elt < wa_ctx_size; elt += 4) {
 				err_printf(m, "[%04x] %08x %08x %08x %08x\n",
@@ -583,7 +583,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 
 		if ((obj = ee->ctx)) {
 			err_printf(m, "%s --- HW Context = 0x%08x\n",
-				   dev_priv->engine[i].name,
+				   dev_priv->engine[i]->name,
 				   lower_32_bits(obj->gtt_offset));
 			print_error_obj(m, obj);
 		}
@@ -918,7 +918,7 @@ 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;
@@ -1173,14 +1173,14 @@ 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;
@@ -1603,7 +1603,7 @@ void i915_get_engine_instdone(struct drm_i915_private *dev_priv,
 			      enum intel_engine_id engine_id,
 			      struct intel_instdone *instdone)
 {
-	u32 mmio_base = dev_priv->engine[engine_id].mmio_base;
+	u32 mmio_base = dev_priv->engine[engine_id]->mmio_base;
 	int slice;
 	int subslice;
 
drivers/gpu/drm/i915/i915_guc_submission.c +7 -5
index 3106dcc..a1f76c8 100644
@@ -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 */
drivers/gpu/drm/i915/i915_irq.c +24 -20

140 lines not on this page · raw message

drivers/gpu/drm/i915/intel_breadcrumbs.c +4 -2
index 495611b..23fc104 100644
@@ -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);
drivers/gpu/drm/i915/intel_display.c +4 -4
index a366656..df5d9f8 100644
@@ -12242,19 +12242,19 @@ 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);
drivers/gpu/drm/i915/intel_engine_cs.c +19 -7
index 480584c..1685da1 100644
@@ -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;
drivers/gpu/drm/i915/intel_guc_loader.c +4 -2
index 7ace96b..95c6751 100644
@@ -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. */
drivers/gpu/drm/i915/intel_lrc.c +6 -5
index 10fcea57..bc86585 100644
@@ -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;
 
drivers/gpu/drm/i915/intel_overlay.c +1 -1
index a24bc8c..272eb93 100644
@@ -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);
 }
drivers/gpu/drm/i915/intel_pm.c +11 -6
index 7f1748a..f5e3cc5 100644
@@ -5359,6 +5359,7 @@ 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 */
@@ -5380,7 +5381,7 @@ 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))
@@ -5425,6 +5426,7 @@ 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 */
@@ -5441,7 +5443,7 @@ 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))
@@ -5501,6 +5503,7 @@ 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;
@@ -5534,7 +5537,7 @@ 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);
@@ -5983,6 +5986,7 @@ 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));
@@ -6009,7 +6013,7 @@ 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);
 
@@ -6071,6 +6075,7 @@ 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));
@@ -6110,7 +6115,7 @@ 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);
@@ -6793,7 +6798,7 @@ 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;
 
drivers/gpu/drm/i915/intel_ringbuffer.c +8 -7
index 729f373..e107455 100644
@@ -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;
 	}
drivers/gpu/drm/i915/intel_ringbuffer.h +1 -7
index 124f464..44ef6b5 100644
@@ -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;
 
Signature · 6 lines
1.9.2

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#7 lore raw

✗ Fi.CI.BAT: warning for drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev3)

In reply to [email protected]
== Series Details ==

== Series Details ==

Series: drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev3)
URL : https://patchwork.freedesktop.org/series/13435/
State : warning

== Summary ==

Series 13435v3 drm/i915: Allocate intel_engine_cs structure only for the enabled engines
https://patchwork.freedesktop.org/api/1.0/series/13435/revisions/3/mbox/

Test vgem_basic:

        Subgroup unload:
                pass       -> SKIP       (fi-skl-6260u)
                pass       -> SKIP       (fi-skl-6700hq)
                skip       -> PASS       (fi-skl-6700k)
fi-bdw-5557u     total:248  pass:231  dwarn:0   dfail:0   fail:0   skip:17 
fi-bsw-n3050     total:248  pass:204  dwarn:0   dfail:0   fail:0   skip:44 
fi-bxt-t5700     total:248  pass:217  dwarn:0   dfail:0   fail:0   skip:31 
fi-byt-j1900     total:248  pass:214  dwarn:1   dfail:0   fail:1   skip:32 
fi-byt-n2820     total:248  pass:210  dwarn:0   dfail:0   fail:1   skip:37 
fi-hsw-4770      total:248  pass:224  dwarn:0   dfail:0   fail:0   skip:24 
fi-hsw-4770r     total:248  pass:224  dwarn:0   dfail:0   fail:0   skip:24 
fi-ilk-650       total:248  pass:185  dwarn:0   dfail:0   fail:2   skip:61 
fi-ivb-3520m     total:248  pass:221  dwarn:0   dfail:0   fail:0   skip:27 
fi-ivb-3770      total:248  pass:207  dwarn:0   dfail:0   fail:0   skip:41 
fi-kbl-7200u     total:248  pass:222  dwarn:0   dfail:0   fail:0   skip:26 
fi-skl-6260u     total:248  pass:232  dwarn:0   dfail:0   fail:0   skip:16 
fi-skl-6700hq    total:248  pass:223  dwarn:1   dfail:0   fail:0   skip:24 
fi-skl-6700k     total:248  pass:222  dwarn:1   dfail:0   fail:0   skip:25 
fi-skl-6770hq    total:248  pass:231  dwarn:1   dfail:0   fail:1   skip:15 
fi-snb-2520m     total:248  pass:211  dwarn:0   dfail:0   fail:0   skip:37 
fi-snb-2600      total:248  pass:209  dwarn:0   dfail:0   fail:0   skip:39 

Results at /archive/results/CI_IGT_test/Patchwork_2652/

f35ed31aea66b3230c366fcba5f3456ae2cb956e drm-intel-nightly: 2016y-10m-10d-11h-28m-51s UTC integration manifest 401facf drm/i915: Allocate intel_engine_cs structure only for the enabled engines

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#8 lore raw

Re: ✗ Fi.CI.BAT: warning for drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev3)

Quoted 8 lines · Patchwork

== Series Details ==

Series: drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev3)
URL : https://patchwork.freedesktop.org/series/13435/
State : warning

== Summary ==

Quoted 9 lines

Series 13435v3 drm/i915: Allocate intel_engine_cs structure only for the enabled engines
https://patchwork.freedesktop.org/api/1.0/series/13435/revisions/3/mbox/

Test vgem_basic:

        Subgroup unload:
                pass       -> SKIP       (fi-skl-6260u)
                pass       -> SKIP       (fi-skl-6700hq)
                skip       -> PASS       (fi-skl-6700k)

Checked with Chris about the above failure.
He said that the above unload failure for vgem module can't be attributed to the patch, most likely a CI framework issue.

Best regards
Akash

Quoted 18 lines
fi-bdw-5557u     total:248  pass:231  dwarn:0   dfail:0   fail:0   skip:17
fi-bsw-n3050     total:248  pass:204  dwarn:0   dfail:0   fail:0   skip:44
fi-bxt-t5700     total:248  pass:217  dwarn:0   dfail:0   fail:0   skip:31
fi-byt-j1900     total:248  pass:214  dwarn:1   dfail:0   fail:1   skip:32
fi-byt-n2820     total:248  pass:210  dwarn:0   dfail:0   fail:1   skip:37
fi-hsw-4770      total:248  pass:224  dwarn:0   dfail:0   fail:0   skip:24
fi-hsw-4770r     total:248  pass:224  dwarn:0   dfail:0   fail:0   skip:24
fi-ilk-650       total:248  pass:185  dwarn:0   dfail:0   fail:2   skip:61
fi-ivb-3520m     total:248  pass:221  dwarn:0   dfail:0   fail:0   skip:27
fi-ivb-3770      total:248  pass:207  dwarn:0   dfail:0   fail:0   skip:41
fi-kbl-7200u     total:248  pass:222  dwarn:0   dfail:0   fail:0   skip:26
fi-skl-6260u     total:248  pass:232  dwarn:0   dfail:0   fail:0   skip:16
fi-skl-6700hq    total:248  pass:223  dwarn:1   dfail:0   fail:0   skip:24
fi-skl-6700k     total:248  pass:222  dwarn:1   dfail:0   fail:0   skip:25
fi-skl-6770hq    total:248  pass:231  dwarn:1   dfail:0   fail:1   skip:15
fi-snb-2520m     total:248  pass:211  dwarn:0   dfail:0   fail:0   skip:37
fi-snb-2600      total:248  pass:209  dwarn:0   dfail:0   fail:0   skip:39
Quoted 5 lines

Results at /archive/results/CI_IGT_test/Patchwork_2652/

f35ed31aea66b3230c366fcba5f3456ae2cb956e drm-intel-nightly: 2016y-10m-10d-11h-28m-51s UTC integration manifest 401facf drm/i915: Allocate intel_engine_cs structure only for the enabled engines

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#9 lore raw

Re: ✗ Fi.CI.BAT: warning for drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev3)

Quoted 20 lines · Akash
Quoted 8 lines · Patchwork

== Series Details ==

Series: drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev3)
URL : https://patchwork.freedesktop.org/series/13435/
State : warning

== Summary ==

Quoted 9 lines

Series 13435v3 drm/i915: Allocate intel_engine_cs structure only for the enabled engines
https://patchwork.freedesktop.org/api/1.0/series/13435/revisions/3/mbox/

Test vgem_basic:

        Subgroup unload:
                pass       -> SKIP       (fi-skl-6260u)
                pass       -> SKIP       (fi-skl-6700hq)
                skip       -> PASS       (fi-skl-6700k)
Quoted 4 lines

Checked with Chris about the above failure.
He said that the above unload failure for vgem module can't be attributed to the patch, most likely a CI framework issue.

I tried to merge it but due recent changes to error capture it doesn't apply any longer. Can you please rebase and resend?

Regards,

Tvrtko

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#10 lore raw

PATCH v11 1/1 drm/i915: Allocate intel_engine_cs structure only for the enabled engines

From: Akash Goel <[email protected]>

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.

---
 drivers/gpu/drm/i915/i915_cmd_parser.c     |  3 +-
 drivers/gpu/drm/i915/i915_debugfs.c        | 59 ++++++++++++++++++------------
 drivers/gpu/drm/i915/i915_drv.c            | 11 +++---
 drivers/gpu/drm/i915/i915_drv.h            | 22 ++++-------
 drivers/gpu/drm/i915/i915_gem.c            | 29 +++++++--------
 drivers/gpu/drm/i915/i915_gem_context.c    | 15 +++++---
 drivers/gpu/drm/i915/i915_gem_evict.c      |  3 +-
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  6 +--
 drivers/gpu/drm/i915/i915_gem_gtt.c        | 14 +++++--
 drivers/gpu/drm/i915/i915_gem_request.c    |  5 ++-
 drivers/gpu/drm/i915/i915_gpu_error.c      | 28 +++++++-------
 drivers/gpu/drm/i915/i915_guc_submission.c | 12 +++---
 drivers/gpu/drm/i915/i915_irq.c            | 46 ++++++++++++-----------
 drivers/gpu/drm/i915/intel_breadcrumbs.c   |  6 ++-
 drivers/gpu/drm/i915/intel_display.c       |  8 ++--
 drivers/gpu/drm/i915/intel_engine_cs.c     | 26 +++++++++----
 drivers/gpu/drm/i915/intel_guc_loader.c    |  6 ++-
 drivers/gpu/drm/i915/intel_lrc.c           | 11 +++---
 drivers/gpu/drm/i915/intel_overlay.c       |  2 +-
 drivers/gpu/drm/i915/intel_pm.c            | 17 ++++++---
 drivers/gpu/drm/i915/intel_ringbuffer.c    | 15 ++++----
 drivers/gpu/drm/i915/intel_ringbuffer.h    |  8 +---
 22 files changed, 194 insertions(+), 158 deletions(-)
drivers/gpu/drm/i915/i915_cmd_parser.c +2 -1
index 70980f8..f191d7b 100644
@@ -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;
drivers/gpu/drm/i915/i915_debugfs.c +35 -24

238 lines not on this page · raw message

drivers/gpu/drm/i915/i915_drv.c +6 -5
index e9b3bfc..8c3d476 100644
@@ -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);
 }
 
drivers/gpu/drm/i915/i915_drv.h +7 -15
index 6360e80..9e830b5 100644
@@ -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 */
drivers/gpu/drm/i915/i915_gem.c +13 -16
index 77dc059..fb460cc 100644
@@ -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,
drivers/gpu/drm/i915/i915_gem_context.c +9 -6
index df10f4e9..481ec43 100644
@@ -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;
 
drivers/gpu/drm/i915/i915_gem_evict.c +2 -1
index 5b6f81c..b5e9e66 100644
@@ -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;
 	}
drivers/gpu/drm/i915/i915_gem_execbuffer.c +3 -3
index 72c7c18..fa4d27c 100644
@@ -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;
 	}
drivers/gpu/drm/i915/i915_gem_gtt.c +10 -4
index 2d846aa..0a45063 100644
@@ -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)
drivers/gpu/drm/i915/i915_gem_request.c +3 -2
index 8832f8e..74ede1f 100644
@@ -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;
drivers/gpu/drm/i915/i915_gpu_error.c +14 -14
index cd38948..8d4b9eb 100644
@@ -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;
drivers/gpu/drm/i915/i915_guc_submission.c +7 -5
index 3106dcc..a1f76c8 100644
@@ -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 */
drivers/gpu/drm/i915/i915_irq.c +25 -21

148 lines not on this page · raw message

drivers/gpu/drm/i915/intel_breadcrumbs.c +4 -2
index 495611b..23fc104 100644
@@ -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);
drivers/gpu/drm/i915/intel_display.c +4 -4
index cfcb03f..645a779 100644
@@ -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);
drivers/gpu/drm/i915/intel_engine_cs.c +19 -7
index 1d597fe..fba6edd 100644
@@ -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;
drivers/gpu/drm/i915/intel_guc_loader.c +4 -2
index 7ace96b..95c6751 100644
@@ -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. */
drivers/gpu/drm/i915/intel_lrc.c +6 -5
index 10fcea57..bc86585 100644
@@ -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;
 
drivers/gpu/drm/i915/intel_overlay.c +1 -1
index 8c411bf..25bcd4a1 100644
@@ -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);
 }
drivers/gpu/drm/i915/intel_pm.c +11 -6
index 4dccdca..eed59bd 100644
@@ -5402,6 +5402,7 @@ 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 */
@@ -5423,7 +5424,7 @@ 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))
@@ -5468,6 +5469,7 @@ 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 */
@@ -5484,7 +5486,7 @@ 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))
@@ -5544,6 +5546,7 @@ 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;
@@ -5577,7 +5580,7 @@ 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);
@@ -6026,6 +6029,7 @@ 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));
@@ -6052,7 +6056,7 @@ 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);
 
@@ -6114,6 +6118,7 @@ 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));
@@ -6153,7 +6158,7 @@ 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);
@@ -6836,7 +6841,7 @@ 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;
 
drivers/gpu/drm/i915/intel_ringbuffer.c +8 -7
index 729f373..e107455 100644
@@ -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;
 	}
drivers/gpu/drm/i915/intel_ringbuffer.h +1 -7
index 36eff97..32b2e63 100644
@@ -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;
 
Signature · 6 lines
1.9.2

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#11 lore raw

Re: ✗ Fi.CI.BAT: warning for drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev3)

In reply to Goel, Akash
Quoted 20 lines
Quoted 3 lines

== Series Details ==

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

engines (rev3)

Quoted 10 lines

URL : https://patchwork.freedesktop.org/series/13435/
State : warning

== Summary ==

Series 13435v3 drm/i915: Allocate intel_engine_cs structure only for the enabled engines
https://patchwork.freedesktop.org/api/1.0/series/13435/revisions/3/mbo
x/

Quoted 6 lines

Test vgem_basic:

        Subgroup unload:
                pass       -> SKIP       (fi-skl-6260u)
                pass       -> SKIP       (fi-skl-6700hq)
                skip       -> PASS       (fi-skl-6700k)
Quoted 3 lines

Checked with Chris about the above failure.
He said that the above unload failure for vgem module can't be attributed to the patch, most likely a CI framework issue.

Yes, this test is still behaving badly especially with SKL systems but also with bdw and kbl.

Quoted 28 lines

Best regards
Akash

Quoted 24 lines
fi-bdw-5557u     total:248  pass:231  dwarn:0   dfail:0   fail:0   skip:17
fi-bsw-n3050     total:248  pass:204  dwarn:0   dfail:0   fail:0   skip:44
fi-bxt-t5700     total:248  pass:217  dwarn:0   dfail:0   fail:0   skip:31
fi-byt-j1900     total:248  pass:214  dwarn:1   dfail:0   fail:1   skip:32
fi-byt-n2820     total:248  pass:210  dwarn:0   dfail:0   fail:1   skip:37
fi-hsw-4770      total:248  pass:224  dwarn:0   dfail:0   fail:0   skip:24
fi-hsw-4770r     total:248  pass:224  dwarn:0   dfail:0   fail:0   skip:24
fi-ilk-650       total:248  pass:185  dwarn:0   dfail:0   fail:2   skip:61
fi-ivb-3520m     total:248  pass:221  dwarn:0   dfail:0   fail:0   skip:27
fi-ivb-3770      total:248  pass:207  dwarn:0   dfail:0   fail:0   skip:41
fi-kbl-7200u     total:248  pass:222  dwarn:0   dfail:0   fail:0   skip:26
fi-skl-6260u     total:248  pass:232  dwarn:0   dfail:0   fail:0   skip:16
fi-skl-6700hq    total:248  pass:223  dwarn:1   dfail:0   fail:0   skip:24
fi-skl-6700k     total:248  pass:222  dwarn:1   dfail:0   fail:0   skip:25
fi-skl-6770hq    total:248  pass:231  dwarn:1   dfail:0   fail:1   skip:15
fi-snb-2520m     total:248  pass:211  dwarn:0   dfail:0   fail:0   skip:37
fi-snb-2600      total:248  pass:209  dwarn:0   dfail:0   fail:0   skip:39

Results at /archive/results/CI_IGT_test/Patchwork_2652/

f35ed31aea66b3230c366fcba5f3456ae2cb956e drm-intel-nightly:
2016y-10m-10d-11h-28m-51s UTC integration manifest 401facf drm/i915:
Allocate intel_engine_cs structure only for the enabled engines

Jani Saarinen

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#12 lore raw

Re: ✗ Fi.CI.BAT: warning for drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev3)

Quoted 20 lines · Jani
Quoted 20 lines
Quoted 3 lines

== Series Details ==

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

engines (rev3)

Quoted 16 lines

URL : https://patchwork.freedesktop.org/series/13435/
State : warning

== Summary ==

Series 13435v3 drm/i915: Allocate intel_engine_cs structure only for the enabled engines
https://patchwork.freedesktop.org/api/1.0/series/13435/revisions/3/mbo
x/

Test vgem_basic:

        Subgroup unload:
                pass       -> SKIP       (fi-skl-6260u)
                pass       -> SKIP       (fi-skl-6700hq)
                skip       -> PASS       (fi-skl-6700k)
Quoted 4 lines
Quoted 3 lines

Checked with Chris about the above failure.
He said that the above unload failure for vgem module can't be attributed to the patch, most likely a CI framework issue.

Yes, this test is still behaving badly especially with SKL systems but also with bdw and kbl.

Are the test run in the order defined by fast-feedback.testlist ? I intended the vgem unload test to be run as the first vgem testcase to minimise the chance of a stray module leak. Can we define the order within CI? Can we put comments into fast-feedback.testlist ? -Chris

Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#13 lore raw

Re: ✗ Fi.CI.BAT: warning for drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev3)

Quoted 25 lines
Quoted 25 lines
Quoted 25 lines
Quoted 4 lines

== Series Details ==

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

engines (rev3)

Quoted 11 lines

URL : https://patchwork.freedesktop.org/series/13435/
State : warning

== Summary ==

Series 13435v3 drm/i915: Allocate intel_engine_cs structure only for the enabled engines
https://patchwork.freedesktop.org/api/1.0/series/13435/revisions/3
/mbo
x/

Quoted 6 lines

Test vgem_basic:

        Subgroup unload:
                pass       -> SKIP       (fi-skl-6260u)
                pass       -> SKIP       (fi-skl-6700hq)
                skip       -> PASS       (fi-skl-6700k)

Checked with Chris about the above failure.
He said that the above unload failure for vgem module can't be attributed to the patch, most likely a CI framework issue.

Quoted 7 lines
Quoted 1 line

Yes, this test is still behaving badly especially with SKL systems but also with

bdw and kbl.

Are the test run in the order defined by fast-feedback.testlist ? I intended the vgem unload test to be run as the first vgem testcase to minimise the chance of a stray module leak. Can we define the order within CI? Can we put comments into fast-feedback.testlist ?

My understanding, yes, we are running on that order. Adding comment, no I think no, Petri, Tomi?

Quoted 4 lines

-Chris

--
Chris Wilson, Intel Open Source Technology Centre

Jani Saarinen
Intel Finland Oy - BIC 0357606-4 - Westendinkatu 7, 02160 Espoo

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#14 lore raw

Re: ✗ Fi.CI.BAT: warning for drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev3)

Quoted 8 lines
Quoted 5 lines

Are the test run in the order defined by fast-feedback.testlist ? I intended the vgem unload test to be run as the first vgem testcase to minimise the chance of a stray module leak. Can we define the order within CI? Can we put comments into fast-feedback.testlist ?

My understanding, yes, we are running on that order. Adding comment, no I think no, Petri, Tomi?

Order: Yes, that order. I'm waiting for an opportune moment to test a patch to sleep-and-retry in vgem unload to prune out the cases of just having soon-to-finish work left over. Just need to tune the amount of retries and sleeping.

We can also order vgem unload test to be first (along with drv_module_reload) depending on whether we want to catch those stray module leaks. Comments on that tradeoff?

Comments in the test list: Not yet. Piglit patch for them just sent to piglit mailing list.

Petri Latvala

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#15 lore raw

Re: ✗ Fi.CI.BAT: warning for drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev3)

Quoted 9 lines · Petri Latvala
Quoted 8 lines
Quoted 5 lines

Are the test run in the order defined by fast-feedback.testlist ? I intended the vgem unload test to be run as the first vgem testcase to minimise the chance of a stray module leak. Can we define the order within CI? Can we put comments into fast-feedback.testlist ?

My understanding, yes, we are running on that order. Adding comment, no I think no, Petri, Tomi?

Quoted 8 lines

Order: Yes, that order. I'm waiting for an opportune moment to test a patch to sleep-and-retry in vgem unload to prune out the cases of just having soon-to-finish work left over. Just need to tune the amount of retries and sleeping.

We can also order vgem unload test to be first (along with drv_module_reload) depending on whether we want to catch those stray module leaks. Comments on that tradeoff?

I planned on having vgem/unload be the first vgem test. It probably makes sense to have a second one at the end to catch a leak over the run.
-Chris

Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#16 lore raw

✗ Fi.CI.BAT: warning for drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev4)

In reply to [email protected]
== Series Details ==

== Series Details ==

Series: drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev4)
URL : https://patchwork.freedesktop.org/series/13435/
State : warning

== Summary ==

Series 13435v4 drm/i915: Allocate intel_engine_cs structure only for the enabled engines
https://patchwork.freedesktop.org/api/1.0/series/13435/revisions/4/mbox/

Test kms_pipe_crc_basic:

        Subgroup nonblocking-crc-pipe-b:
                pass       -> DMESG-WARN (fi-ilk-650)
        Subgroup read-crc-pipe-b-frame-sequence:
                dmesg-warn -> PASS       (fi-ilk-650)
Test vgem_basic:
        Subgroup unload:
                skip       -> PASS       (fi-skl-6770hq)
fi-bdw-5557u     total:246  pass:231  dwarn:0   dfail:0   fail:0   skip:15 
fi-bsw-n3050     total:246  pass:204  dwarn:0   dfail:0   fail:0   skip:42 
fi-bxt-t5700     total:246  pass:216  dwarn:0   dfail:0   fail:0   skip:30 
fi-byt-j1900     total:246  pass:212  dwarn:2   dfail:0   fail:1   skip:31 
fi-byt-n2820     total:246  pass:210  dwarn:0   dfail:0   fail:1   skip:35 
fi-hsw-4770      total:246  pass:223  dwarn:0   dfail:0   fail:0   skip:23 
fi-hsw-4770r     total:246  pass:224  dwarn:0   dfail:0   fail:0   skip:22 
fi-ilk-650       total:246  pass:183  dwarn:1   dfail:0   fail:2   skip:60 
fi-ivb-3520m     total:246  pass:221  dwarn:0   dfail:0   fail:0   skip:25 
fi-ivb-3770      total:246  pass:221  dwarn:0   dfail:0   fail:0   skip:25 
fi-kbl-7200u     total:246  pass:222  dwarn:0   dfail:0   fail:0   skip:24 
fi-skl-6260u     total:246  pass:232  dwarn:0   dfail:0   fail:0   skip:14 
fi-skl-6700hq    total:246  pass:223  dwarn:0   dfail:0   fail:0   skip:23 
fi-skl-6700k     total:246  pass:221  dwarn:1   dfail:0   fail:0   skip:24 
fi-skl-6770hq    total:246  pass:229  dwarn:1   dfail:0   fail:1   skip:15 
fi-snb-2520m     total:246  pass:210  dwarn:0   dfail:0   fail:0   skip:36 
fi-snb-2600      total:246  pass:209  dwarn:0   dfail:0   fail:0   skip:37 

Results at /archive/results/CI_IGT_test/Patchwork_2708/

dbcf6fbb541e70fac7db669631958eab2e4e0d9c drm-intel-nightly: 2016y-10m-13d-15h-31m-19s UTC integration manifest 391ff6c drm/i915: Allocate intel_engine_cs structure only for the enabled engines

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#17 lore raw

Re: ✗ Fi.CI.BAT: warning for drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev4)

Quoted 6 lines · Patchwork

== Series Details ==

Series: drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev4)
URL : https://patchwork.freedesktop.org/series/13435/
State : warning

Quoted 8 lines

== Summary ==

Series 13435v4 drm/i915: Allocate intel_engine_cs structure only for the enabled engines
https://patchwork.freedesktop.org/api/1.0/series/13435/revisions/4/mbox/

Test kms_pipe_crc_basic:

        Subgroup nonblocking-crc-pipe-b:
                pass       -> DMESG-WARN (fi-ilk-650)

Have filed a new BZ: https://bugs.freedesktop.org/show_bug.cgi?id=98251

Most likely the above failure isn't related with the concerned patch.

Best regards
Akash

Quoted 24 lines
        Subgroup read-crc-pipe-b-frame-sequence:
                dmesg-warn -> PASS       (fi-ilk-650)
Test vgem_basic:
        Subgroup unload:
                skip       -> PASS       (fi-skl-6770hq)
fi-bdw-5557u     total:246  pass:231  dwarn:0   dfail:0   fail:0   skip:15
fi-bsw-n3050     total:246  pass:204  dwarn:0   dfail:0   fail:0   skip:42
fi-bxt-t5700     total:246  pass:216  dwarn:0   dfail:0   fail:0   skip:30
fi-byt-j1900     total:246  pass:212  dwarn:2   dfail:0   fail:1   skip:31
fi-byt-n2820     total:246  pass:210  dwarn:0   dfail:0   fail:1   skip:35
fi-hsw-4770      total:246  pass:223  dwarn:0   dfail:0   fail:0   skip:23
fi-hsw-4770r     total:246  pass:224  dwarn:0   dfail:0   fail:0   skip:22
fi-ilk-650       total:246  pass:183  dwarn:1   dfail:0   fail:2   skip:60
fi-ivb-3520m     total:246  pass:221  dwarn:0   dfail:0   fail:0   skip:25
fi-ivb-3770      total:246  pass:221  dwarn:0   dfail:0   fail:0   skip:25
fi-kbl-7200u     total:246  pass:222  dwarn:0   dfail:0   fail:0   skip:24
fi-skl-6260u     total:246  pass:232  dwarn:0   dfail:0   fail:0   skip:14
fi-skl-6700hq    total:246  pass:223  dwarn:0   dfail:0   fail:0   skip:23
fi-skl-6700k     total:246  pass:221  dwarn:1   dfail:0   fail:0   skip:24
fi-skl-6770hq    total:246  pass:229  dwarn:1   dfail:0   fail:1   skip:15
fi-snb-2520m     total:246  pass:210  dwarn:0   dfail:0   fail:0   skip:36
fi-snb-2600      total:246  pass:209  dwarn:0   dfail:0   fail:0   skip:37
Quoted 5 lines

Results at /archive/results/CI_IGT_test/Patchwork_2708/

dbcf6fbb541e70fac7db669631958eab2e4e0d9c drm-intel-nightly: 2016y-10m-13d-15h-31m-19s UTC integration manifest 391ff6c drm/i915: Allocate intel_engine_cs structure only for the enabled engines

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#18 lore raw

Re: ✗ Fi.CI.BAT: warning for drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev4)

Quoted 14 lines · Akash
Quoted 11 lines · Patchwork

== Series Details ==

Series: drm/i915: Allocate intel_engine_cs structure only for the enabled engines (rev4)
URL : https://patchwork.freedesktop.org/series/13435/
State : warning

== Summary ==

Series 13435v4 drm/i915: Allocate intel_engine_cs structure only for the enabled engines
https://patchwork.freedesktop.org/api/1.0/series/13435/revisions/4/mbox/

Quoted 8 lines
Quoted 3 lines

Test kms_pipe_crc_basic:

        Subgroup nonblocking-crc-pipe-b:
                pass       -> DMESG-WARN (fi-ilk-650)

Have filed a new BZ: https://bugs.freedesktop.org/show_bug.cgi?id=98251

Most likely the above failure isn't related with the concerned patch.

Agreed.

In the future also please put a fail log snippet here when replying and a bug title.

Quoted 32 lines

Best regards
Akash

Quoted 29 lines
        Subgroup read-crc-pipe-b-frame-sequence:
                dmesg-warn -> PASS       (fi-ilk-650)
Test vgem_basic:
        Subgroup unload:
                skip       -> PASS       (fi-skl-6770hq)
fi-bdw-5557u     total:246  pass:231 dwarn:0   dfail:0   fail:0   skip:15
fi-bsw-n3050     total:246  pass:204  dwarn:0   dfail:0 fail:0   skip:42
fi-bxt-t5700     total:246  pass:216  dwarn:0   dfail:0 fail:0   skip:30
fi-byt-j1900     total:246  pass:212  dwarn:2   dfail:0 fail:1   skip:31
fi-byt-n2820     total:246  pass:210  dwarn:0   dfail:0 fail:1   skip:35
fi-hsw-4770      total:246  pass:223  dwarn:0   dfail:0 fail:0   skip:23
fi-hsw-4770r     total:246  pass:224  dwarn:0   dfail:0 fail:0   skip:22
fi-ilk-650       total:246  pass:183  dwarn:1   dfail:0 fail:2   skip:60
fi-ivb-3520m     total:246  pass:221  dwarn:0   dfail:0 fail:0   skip:25
fi-ivb-3770      total:246  pass:221  dwarn:0   dfail:0 fail:0   skip:25
fi-kbl-7200u     total:246  pass:222  dwarn:0   dfail:0 fail:0   skip:24
fi-skl-6260u     total:246  pass:232  dwarn:0   dfail:0 fail:0   skip:14
fi-skl-6700hq    total:246  pass:223  dwarn:0   dfail:0 fail:0   skip:23
fi-skl-6700k     total:246  pass:221  dwarn:1   dfail:0 fail:0   skip:24
fi-skl-6770hq    total:246  pass:229  dwarn:1   dfail:0 fail:1   skip:15
fi-snb-2520m     total:246  pass:210  dwarn:0   dfail:0 fail:0   skip:36
fi-snb-2600      total:246  pass:209  dwarn:0   dfail:0 fail:0   skip:37

Results at /archive/results/CI_IGT_test/Patchwork_2708/

dbcf6fbb541e70fac7db669631958eab2e4e0d9c drm-intel-nightly: 2016y-10m-13d-15h-31m-19s UTC integration manifest 391ff6c drm/i915: Allocate intel_engine_cs structure only for the enabled engines

Merged to dinq, thanks for the patch and review!

Regards,

Tvrtko

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx