[PATCH 48/52] drm/i915: Keep contexts pinned until after the next kernel context switch

Chris Wilson chris at chris-wilson.co.uk
Sun Mar 31 12:08:31 UTC 2019


We need to keep the context image pinned in memory until after the GPU
has finished writing into it. Since it continues to write as we signal
the final breadcrumb, we need to keep it pinned until the request after
it is complete. Currently we know the order in which requests execute on
each engine, and so to remove that presumption we need to identify a
request/context-switch we know must occur after our completion. Any
request queued after the signal must imply a context switch, for
simplicity we use a fresh request from the kernel context.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c   | 35 +++-----
 drivers/gpu/drm/i915/gem/i915_gem_context.h   |  1 -
 drivers/gpu/drm/i915/gem/i915_gem_pm.c        | 52 +++++++++--
 drivers/gpu/drm/i915/i915_active.c            | 88 ++++++++++++++++++-
 drivers/gpu/drm/i915/i915_active.h            |  5 ++
 drivers/gpu/drm/i915/i915_active_types.h      |  3 +
 drivers/gpu/drm/i915/i915_drv.h               |  1 +
 drivers/gpu/drm/i915/i915_gem.c               |  4 -
 drivers/gpu/drm/i915/i915_gem_evict.c         | 26 +++---
 drivers/gpu/drm/i915/i915_request.c           | 14 ---
 drivers/gpu/drm/i915/i915_reset.c             |  5 +-
 drivers/gpu/drm/i915/intel_context.c          | 80 +++++++++++++++--
 drivers/gpu/drm/i915/intel_context.h          |  3 +
 drivers/gpu/drm/i915/intel_context_types.h    |  6 +-
 drivers/gpu/drm/i915/intel_engine_cs.c        | 23 +----
 drivers/gpu/drm/i915/intel_engine_types.h     | 13 +--
 drivers/gpu/drm/i915/intel_lrc.c              | 62 ++-----------
 drivers/gpu/drm/i915/intel_ringbuffer.c       | 44 +---------
 drivers/gpu/drm/i915/intel_ringbuffer.h       |  2 -
 drivers/gpu/drm/i915/selftests/mock_engine.c  | 11 +--
 .../gpu/drm/i915/selftests/mock_gem_device.c  |  8 +-
 21 files changed, 275 insertions(+), 211 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 73113e7930ca..ebd36fe4049e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -660,17 +660,6 @@ int i915_gem_contexts_init(struct drm_i915_private *dev_priv)
 	return 0;
 }
 
-void i915_gem_contexts_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, id)
-		intel_engine_lost_context(engine);
-}
-
 void i915_gem_contexts_fini(struct drm_i915_private *i915)
 {
 	lockdep_assert_held(&i915->drm.struct_mutex);
@@ -1014,6 +1003,7 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915,
 							 I915_FENCE_GFP);
 		}
 
+		i915_request_add_barriers(rq);
 		i915_request_add(rq);
 	}
 	i915_gem_park(i915);
@@ -1244,15 +1234,6 @@ gen8_modify_rpcs(struct intel_context *ce, struct intel_sseu sseu)
 			goto out_add;
 	}
 
-	/* Order all following requests to be after. */
-	ret = i915_timeline_set_barrier(ce->ring->timeline, rq);
-	if (ret)
-		goto out_add;
-
-	ret = gen8_emit_rpcs_config(rq, ce, sseu);
-	if (ret)
-		goto out_add;
-
 	/*
 	 * Guarantee context image and the timeline remains pinned until the
 	 * modifying request is retired by setting the ce activity tracker.
@@ -1260,9 +1241,17 @@ gen8_modify_rpcs(struct intel_context *ce, struct intel_sseu sseu)
 	 * But we only need to take one pin on the account of it. Or in other
 	 * words transfer the pinned ce object to tracked active request.
 	 */
-	if (!i915_active_request_isset(&ce->active_tracker))
-		__intel_context_pin(ce);
-	__i915_active_request_set(&ce->active_tracker, rq);
+	GEM_BUG_ON(i915_active_is_idle(&ce->active));
+	ret = i915_active_ref(&ce->active, rq->fence.context, rq);
+	if (ret)
+		goto out_add;
+
+	/* Order all following requests to be after. */
+	ret = i915_timeline_set_barrier(ce->ring->timeline, rq);
+	if (ret)
+		goto out_add;
+
+	ret = gen8_emit_rpcs_config(rq, ce, sseu);
 
 out_add:
 	i915_request_add(rq);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h
index 52201d78606a..c432cdce8019 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h
@@ -133,7 +133,6 @@ static inline bool i915_gem_context_is_kernel(struct i915_gem_context *ctx)
 
 /* i915_gem_context.c */
 int __must_check i915_gem_contexts_init(struct drm_i915_private *dev_priv);
-void i915_gem_contexts_lost(struct drm_i915_private *dev_priv);
 void i915_gem_contexts_fini(struct drm_i915_private *dev_priv);
 
 int i915_gem_context_open(struct drm_i915_private *i915,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 861f3ef05394..6be6fe9f4c43 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -9,6 +9,28 @@
 #include "i915_gem_context.h"
 #include "i915_gem_pm.h"
 
+static void call_idle_barriers(struct drm_i915_private *i915)
+{
+	unsigned long tmp = xchg(&i915->gt.idle_barriers, 0);
+	struct intel_engine_cs *engine;
+
+	for_each_engine_masked(engine, i915, tmp, tmp) {
+		struct llist_node *node, *next;
+
+		llist_for_each_safe(node, next,
+				    llist_del_all(&engine->barrier_tasks)) {
+			struct i915_active_request *active =
+				container_of((struct list_head *)node,
+					     typeof(*active), link);
+
+			INIT_LIST_HEAD(&active->link);
+			RCU_INIT_POINTER(active->request, NULL);
+
+			active->retire(active, NULL);
+		}
+	}
+}
+
 static void __i915_gem_park(struct drm_i915_private *i915)
 {
 	intel_wakeref_t wakeref;
@@ -22,6 +44,9 @@ static void __i915_gem_park(struct drm_i915_private *i915)
 	if (!i915->gt.awake)
 		return;
 
+	/* As we may have forcibly parked (via wedging) flush residual cb */
+	call_idle_barriers(i915);
+
 	/*
 	 * Be paranoid and flush a concurrent interrupt to make sure
 	 * we don't reactivate any irq tasklets after parking.
@@ -52,8 +77,8 @@ static void __i915_gem_park(struct drm_i915_private *i915)
 	i915_globals_park();
 }
 
-static bool switch_to_kernel_context_sync(struct drm_i915_private *i915,
-					  unsigned long mask)
+static bool __switch_to_kernel_context_sync(struct drm_i915_private *i915,
+					    unsigned long mask)
 {
 	bool result = true;
 
@@ -83,9 +108,26 @@ static bool switch_to_kernel_context_sync(struct drm_i915_private *i915,
 	}
 
 	i915_retire_requests(i915); /* ensure we flush after wedging */
+	if (i915_reset_failed(i915)) {
+		call_idle_barriers(i915);
+		result = false;
+	}
+
 	return result;
 }
 
+static bool switch_to_kernel_context_idle(struct drm_i915_private *i915,
+					  unsigned long mask)
+{
+	mask |= i915->gt.idle_barriers;
+	do {
+		if (!__switch_to_kernel_context_sync(i915, mask))
+			return false;
+	} while ((mask = i915->gt.idle_barriers));
+
+	return true;
+}
+
 static void idle_work_handler(struct work_struct *work)
 {
 	struct drm_i915_private *i915 =
@@ -121,7 +163,7 @@ static void idle_work_handler(struct work_struct *work)
 	    !atomic_read(&i915->gt.active_requests)) {
 		atomic_inc(&i915->gt.active_requests); /* don't requeue idle */
 
-		switch_to_kernel_context_sync(i915, i915->gt.active_engines);
+		switch_to_kernel_context_idle(i915, i915->gt.active_engines);
 
 		if (atomic_dec_and_test(&i915->gt.active_requests)) {
 			__i915_gem_park(i915);
@@ -206,7 +248,7 @@ bool i915_gem_load_power_context(struct drm_i915_private *i915)
 		__i915_gem_unpark(i915);
 
 	/* Force loading the kernel context on all engines */
-	if (!switch_to_kernel_context_sync(i915, ALL_ENGINES))
+	if (!switch_to_kernel_context_idle(i915, ALL_ENGINES))
 		goto err_active;
 
 	/*
@@ -252,7 +294,7 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 	 * state. Fortunately, the kernel_context is disposable and we do
 	 * not rely on its state.
 	 */
-	switch_to_kernel_context_sync(i915, i915->gt.active_engines);
+	switch_to_kernel_context_idle(i915, i915->gt.active_engines);
 
 	mutex_unlock(&i915->drm.struct_mutex);
 	i915_reset_flush(i915);
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index 863ae12707ba..006c67486809 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -100,7 +100,7 @@ active_instance(struct i915_active *ref, u64 idx)
 		parent = *p;
 
 		node = rb_entry(parent, struct active_node, node);
-		if (node->timeline == idx)
+		if (node->timeline == idx && !IS_ERR(node->base.request))
 			goto replace;
 
 		if (node->timeline < idx)
@@ -157,6 +157,7 @@ void i915_active_init(struct drm_i915_private *i915,
 	ref->retire = retire;
 	ref->tree = RB_ROOT;
 	i915_active_request_init(&ref->last, NULL, last_retire);
+	init_llist_head(&ref->barriers);
 	ref->count = 0;
 }
 
@@ -263,6 +264,91 @@ void i915_active_fini(struct i915_active *ref)
 }
 #endif
 
+int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
+					    struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *i915 = engine->i915;
+	unsigned long tmp;
+	int err = 0;
+
+	i915_active_acquire(ref);
+	for_each_engine_masked(engine, i915, engine->mask, tmp) {
+		struct intel_context *kctx = engine->kernel_context;
+		struct active_node *node;
+
+		node = kmem_cache_alloc(global.slab_cache, GFP_KERNEL);
+		if (unlikely(!node)) {
+			err = -ENOMEM;
+			break;
+		}
+
+		i915_active_request_init(&node->base,
+					 (void *)engine, node_retire);
+		node->timeline = kctx->ring->timeline->fence_context;
+		node->ref = ref;
+		ref->count++;
+
+		llist_add((struct llist_node *)&node->base.link,
+			  &ref->barriers);
+	}
+	i915_active_release(ref);
+
+	return err;
+}
+
+void i915_active_acquire_barrier(struct i915_active *ref)
+{
+	struct llist_node *pos, *next;
+
+	i915_active_acquire(ref);
+
+	llist_for_each_safe(pos, next, llist_del_all(&ref->barriers)) {
+		struct intel_engine_cs *engine;
+		struct active_node *node;
+		struct rb_node **p, *parent;
+
+		node = container_of((struct list_head *)pos,
+				    typeof(*node), base.link);
+
+		engine = (void *)rcu_access_pointer(node->base.request);
+		RCU_INIT_POINTER(node->base.request, ERR_PTR(-EAGAIN));
+
+		parent = NULL;
+		p = &ref->tree.rb_node;
+		while (*p) {
+			parent = *p;
+			if (rb_entry(parent,
+				     struct active_node,
+				     node)->timeline < node->timeline)
+				p = &parent->rb_right;
+			else
+				p = &parent->rb_left;
+		}
+		rb_link_node(&node->node, parent, p);
+		rb_insert_color(&node->node, &ref->tree);
+
+		llist_add((struct llist_node *)&node->base.link,
+			  &engine->barrier_tasks);
+		set_bit(engine->id,
+			(unsigned long *)&engine->i915->gt.idle_barriers);
+	}
+	i915_active_release(ref);
+}
+
+void i915_request_add_barriers(struct i915_request *rq)
+{
+	struct intel_engine_cs *engine = rq->engine;
+	struct llist_node *node, *next;
+
+	GEM_BUG_ON(!is_power_of_2(engine->mask));
+	if (!test_and_clear_bit(engine->id,
+				(unsigned long *)&engine->i915->gt.idle_barriers))
+		return;
+
+	llist_for_each_safe(node, next, llist_del_all(&engine->barrier_tasks))
+		list_add_tail((struct list_head *)node, &rq->active_list);
+}
+
 int i915_active_request_set(struct i915_active_request *active,
 			    struct i915_request *rq)
 {
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index 7d758719ce39..d55d37673944 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -406,4 +406,9 @@ void i915_active_fini(struct i915_active *ref);
 static inline void i915_active_fini(struct i915_active *ref) { }
 #endif
 
+int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
+					    struct intel_engine_cs *engine);
+void i915_active_acquire_barrier(struct i915_active *ref);
+void i915_request_add_barriers(struct i915_request *rq);
+
 #endif /* _I915_ACTIVE_H_ */
diff --git a/drivers/gpu/drm/i915/i915_active_types.h b/drivers/gpu/drm/i915/i915_active_types.h
index b679253b53a5..c025991b9233 100644
--- a/drivers/gpu/drm/i915/i915_active_types.h
+++ b/drivers/gpu/drm/i915/i915_active_types.h
@@ -7,6 +7,7 @@
 #ifndef _I915_ACTIVE_TYPES_H_
 #define _I915_ACTIVE_TYPES_H_
 
+#include <linux/llist.h>
 #include <linux/rbtree.h>
 #include <linux/rcupdate.h>
 
@@ -31,6 +32,8 @@ struct i915_active {
 	unsigned int count;
 
 	void (*retire)(struct i915_active *ref);
+
+	struct llist_head barriers;
 };
 
 #endif /* _I915_ACTIVE_TYPES_H_ */
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index fb4182a63f51..10c87583c6b6 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1997,6 +1997,7 @@ struct drm_i915_private {
 		} timelines;
 
 		intel_engine_mask_t active_engines;
+		intel_engine_mask_t idle_barriers;
 		struct list_head active_rings;
 		atomic_t active_requests;
 		struct mutex active_mutex;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 894144f93d2d..84355fde3d5b 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1176,10 +1176,6 @@ void i915_gem_sanitize(struct drm_i915_private *i915)
 
 	intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
 	intel_runtime_pm_put(i915, wakeref);
-
-	mutex_lock(&i915->drm.struct_mutex);
-	i915_gem_contexts_lost(i915);
-	mutex_unlock(&i915->drm.struct_mutex);
 }
 
 void i915_gem_init_swizzling(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index ba4b122ea45d..245d52754be1 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -40,7 +40,8 @@ I915_SELFTEST_DECLARE(static struct igt_evict_ctl {
 
 static bool ggtt_is_idle(struct drm_i915_private *i915)
 {
-	return !atomic_read(&i915->gt.active_requests);
+	return !atomic_read(&i915->gt.active_requests) &&
+		!i915->gt.idle_barriers;
 }
 
 static int ggtt_flush(struct drm_i915_private *i915)
@@ -54,19 +55,14 @@ static int ggtt_flush(struct drm_i915_private *i915)
 	 * the hopes that we can then remove contexts and the like only
 	 * bound by their active reference.
 	 */
-	err = i915_gem_switch_to_kernel_context(i915, i915->gt.active_engines);
+	err = i915_gem_switch_to_kernel_context(i915, i915->gt.idle_barriers);
 	if (err)
 		return err;
 
-	err = i915_gem_wait_for_idle(i915,
-				     I915_WAIT_INTERRUPTIBLE |
-				     I915_WAIT_LOCKED,
-				     MAX_SCHEDULE_TIMEOUT);
-	if (err)
-		return err;
-
-	GEM_BUG_ON(!ggtt_is_idle(i915));
-	return 0;
+	return i915_gem_wait_for_idle(i915,
+				      I915_WAIT_INTERRUPTIBLE |
+				      I915_WAIT_LOCKED,
+				      MAX_SCHEDULE_TIMEOUT);
 }
 
 static bool
@@ -416,9 +412,11 @@ int i915_gem_evict_vm(struct i915_address_space *vm)
 	 * switch otherwise is ineffective.
 	 */
 	if (i915_is_ggtt(vm)) {
-		ret = ggtt_flush(vm->i915);
-		if (ret)
-			return ret;
+		do {
+			ret = ggtt_flush(vm->i915);
+			if (ret)
+				return ret;
+		} while (!ggtt_is_idle(vm->i915));
 	}
 
 	INIT_LIST_HEAD(&eviction_list);
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index f23d802618be..362eb3af86e1 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -213,18 +213,6 @@ static void __retire_engine_request(struct intel_engine_cs *engine,
 	spin_unlock(&rq->lock);
 
 	local_irq_enable();
-
-	/*
-	 * The backing object for the context is done after switching to the
-	 * *next* context. Therefore we cannot retire the previous context until
-	 * the next context has already started running. However, since we
-	 * cannot take the required locks at i915_request_submit() we
-	 * defer the unpinning of the active context to now, retirement of
-	 * the subsequent request.
-	 */
-	if (engine->last_retired_context)
-		intel_context_unpin(engine->last_retired_context);
-	engine->last_retired_context = rq->hw_context;
 }
 
 static void __retire_engine_upto(struct intel_engine_cs *engine,
@@ -733,8 +721,6 @@ struct i915_request *i915_request_create(struct intel_context *ce)
 
 	rq->infix = rq->ring->emit; /* end of header; start of user payload */
 
-	/* Keep a second pin for the dual retirement along engine and ring */
-	__intel_context_pin(ce);
 	atomic_inc(&i915->gt.active_requests);
 
 	/* Check that we didn't interrupt ourselves with a new request */
diff --git a/drivers/gpu/drm/i915/i915_reset.c b/drivers/gpu/drm/i915/i915_reset.c
index d0e603326962..9d7ac6e5c723 100644
--- a/drivers/gpu/drm/i915/i915_reset.c
+++ b/drivers/gpu/drm/i915/i915_reset.c
@@ -780,9 +780,8 @@ static void reset_restart(struct drm_i915_private *i915)
 
 	/*
 	 * Following the reset, ensure that we always reload context for
-	 * powersaving, and to correct engine->last_retired_context. Since
-	 * this requires us to submit a request, queue a worker to do that
-	 * task for us to evade any locking here.
+	 * powersaving. Since this requires us to submit a request, queue
+	 * a worker to do that task for us to evade any locking here.
 	 */
 	if (READ_ONCE(i915->gpu_error.restart))
 		return;
diff --git a/drivers/gpu/drm/i915/intel_context.c b/drivers/gpu/drm/i915/intel_context.c
index d6318518aab6..fe403c5897a2 100644
--- a/drivers/gpu/drm/i915/intel_context.c
+++ b/drivers/gpu/drm/i915/intel_context.c
@@ -54,7 +54,6 @@ int __intel_context_do_pin(struct intel_context *ce)
 
 		i915_gem_context_get(ce->gem_context); /* for ctx->ppgtt */
 
-		intel_context_get(ce);
 		smp_mb__before_atomic(); /* flush pin before it is visible */
 	}
 
@@ -82,20 +81,45 @@ void intel_context_unpin(struct intel_context *ce)
 		ce->ops->unpin(ce);
 
 		i915_gem_context_put(ce->gem_context);
-		intel_context_put(ce);
+		intel_context_inactive(ce);
 	}
 
 	mutex_unlock(&ce->pin_mutex);
 	intel_context_put(ce);
 }
 
-static void intel_context_retire(struct i915_active_request *active,
-				 struct i915_request *rq)
+static int __context_pin_state(struct i915_vma *vma, unsigned long flags)
+{
+	int err;
+
+	err = i915_vma_pin(vma, 0, 0, flags | PIN_GLOBAL);
+	if (err)
+		return err;
+
+	/*
+	 * And mark is as a globally pinned object to let the shrinker know
+	 * it cannot reclaim the object until we release it.
+	 */
+	vma->obj->pin_global++;
+	vma->obj->mm.dirty = true;
+
+	return 0;
+}
+
+static void __context_unpin_state(struct i915_vma *vma)
+{
+	vma->obj->pin_global--;
+	__i915_vma_unpin(vma);
+}
+
+static void intel_context_retire(struct i915_active *active)
 {
-	struct intel_context *ce =
-		container_of(active, typeof(*ce), active_tracker);
+	struct intel_context *ce = container_of(active, typeof(*ce), active);
 
-	intel_context_unpin(ce);
+	if (ce->state)
+		__context_unpin_state(ce->state);
+
+	intel_context_put(ce);
 }
 
 void
@@ -119,8 +143,46 @@ intel_context_init(struct intel_context *ce,
 	/* Use the whole device by default */
 	ce->sseu = intel_device_default_sseu(ctx->i915);
 
-	i915_active_request_init(&ce->active_tracker,
-				 NULL, intel_context_retire);
+	i915_active_init(ctx->i915, &ce->active, intel_context_retire);
+}
+
+int intel_context_active(struct intel_context *ce, unsigned long flags)
+{
+	int err;
+
+	if (!i915_active_acquire(&ce->active))
+		return 0;
+
+	intel_context_get(ce);
+
+	if (!ce->state)
+		return 0;
+
+	err = __context_pin_state(ce->state, flags);
+	if (err) {
+		i915_active_cancel(&ce->active);
+		intel_context_put(ce);
+		return err;
+	}
+
+	/* Preallocate tracking nodes */
+	if (!i915_gem_context_is_kernel(ce->gem_context)) {
+		err = i915_active_acquire_preallocate_barrier(&ce->active,
+							      ce->engine);
+		if (err) {
+			i915_active_release(&ce->active);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+void intel_context_inactive(struct intel_context *ce)
+{
+	/* Nodes preallocated in intel_context_active() */
+	i915_active_acquire_barrier(&ce->active);
+	i915_active_release(&ce->active);
 }
 
 static void i915_global_context_shrink(void)
diff --git a/drivers/gpu/drm/i915/intel_context.h b/drivers/gpu/drm/i915/intel_context.h
index 460b5c34cede..3134ff57aa67 100644
--- a/drivers/gpu/drm/i915/intel_context.h
+++ b/drivers/gpu/drm/i915/intel_context.h
@@ -69,6 +69,9 @@ static inline void __intel_context_pin(struct intel_context *ce)
 
 void intel_context_unpin(struct intel_context *ce);
 
+int intel_context_active(struct intel_context *ce, unsigned long flags);
+void intel_context_inactive(struct intel_context *ce);
+
 static inline struct intel_context *intel_context_get(struct intel_context *ce)
 {
 	kref_get(&ce->ref);
diff --git a/drivers/gpu/drm/i915/intel_context_types.h b/drivers/gpu/drm/i915/intel_context_types.h
index 053ff8457888..0f9c1ea40de6 100644
--- a/drivers/gpu/drm/i915/intel_context_types.h
+++ b/drivers/gpu/drm/i915/intel_context_types.h
@@ -57,10 +57,10 @@ struct intel_context {
 	struct mutex pin_mutex; /* guards pinning and associated on-gpuing */
 
 	/**
-	 * active_tracker: Active tracker for the external rq activity
-	 * on this intel_context object.
+	 * active: Active tracker for the rq activity (inc. external) on this
+	 * intel_context object.
 	 */
-	struct i915_active_request active_tracker;
+	struct i915_active active;
 
 	const struct intel_context_ops *ops;
 
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 201deea88993..892744bdcccd 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -544,6 +544,8 @@ static int intel_engine_setup_common(struct intel_engine_cs *engine)
 {
 	int err;
 
+	init_llist_head(&engine->barrier_tasks);
+
 	err = init_status_page(engine);
 	if (err)
 		return err;
@@ -818,6 +820,7 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 	if (engine->preempt_context)
 		intel_context_unpin(engine->preempt_context);
 	intel_context_unpin(engine->kernel_context);
+	GEM_BUG_ON(!llist_empty(&engine->barrier_tasks));
 
 	i915_timeline_fini(&engine->timeline);
 
@@ -1254,26 +1257,6 @@ void intel_engines_unpark(struct drm_i915_private *i915)
 	}
 }
 
-/**
- * intel_engine_lost_context: called when the GPU is reset into unknown state
- * @engine: the engine
- *
- * We have either reset the GPU or otherwise about to lose state tracking of
- * the current GPU logical state (e.g. suspend). On next use, it is therefore
- * imperative that we make no presumptions about the current state and load
- * from scratch.
- */
-void intel_engine_lost_context(struct intel_engine_cs *engine)
-{
-	struct intel_context *ce;
-
-	lockdep_assert_held(&engine->i915->drm.struct_mutex);
-
-	ce = fetch_and_zero(&engine->last_retired_context);
-	if (ce)
-		intel_context_unpin(ce);
-}
-
 bool intel_engine_can_store_dword(struct intel_engine_cs *engine)
 {
 	switch (INTEL_GEN(engine->i915)) {
diff --git a/drivers/gpu/drm/i915/intel_engine_types.h b/drivers/gpu/drm/i915/intel_engine_types.h
index 01059122e3d5..7226d11339fb 100644
--- a/drivers/gpu/drm/i915/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/intel_engine_types.h
@@ -11,6 +11,7 @@
 #include <linux/irq_work.h>
 #include <linux/kref.h>
 #include <linux/list.h>
+#include <linux/llist.h>
 #include <linux/types.h>
 
 #include "i915_gem.h"
@@ -279,6 +280,7 @@ struct intel_engine_cs {
 	struct intel_ring *buffer;
 
 	struct i915_timeline timeline;
+	struct llist_head barrier_tasks;
 
 	struct intel_context *kernel_context; /* pinned */
 	struct intel_context *preempt_context; /* pinned; optional */
@@ -422,17 +424,6 @@ struct intel_engine_cs {
 
 	struct intel_engine_execlists execlists;
 
-	/* Contexts are pinned whilst they are active on the GPU. The last
-	 * context executed remains active whilst the GPU is idle - the
-	 * switch away and write to the context object only occurs on the
-	 * next execution.  Contexts are only unpinned on retirement of the
-	 * following request ensuring that we can always write to the object
-	 * on the context switch even after idling. Across suspend, we switch
-	 * to the kernel context and trash it as the save may not happen
-	 * before the hardware is powered down.
-	 */
-	struct intel_context *last_retired_context;
-
 	/* status_notifier: list of callbacks for context-switch changes */
 	struct atomic_notifier_head context_status_notifier;
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 11ab08712a66..a9011530db1a 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1538,60 +1538,11 @@ static void execlists_context_destroy(struct kref *kref)
 	intel_context_free(ce);
 }
 
-static int __context_pin(struct i915_vma *vma)
-{
-	unsigned int flags;
-	int err;
-
-	flags = PIN_GLOBAL | PIN_HIGH;
-	flags |= PIN_OFFSET_BIAS | i915_ggtt_pin_bias(vma);
-
-	err = i915_vma_pin(vma, 0, 0, flags);
-	if (err)
-		return err;
-
-	vma->obj->pin_global++;
-	vma->obj->mm.dirty = true;
-
-	return 0;
-}
-
-static void __context_unpin(struct i915_vma *vma)
-{
-	vma->obj->pin_global--;
-	__i915_vma_unpin(vma);
-}
-
 static void execlists_context_unpin(struct intel_context *ce)
 {
-	struct intel_engine_cs *engine;
-
-	/*
-	 * The tasklet may still be using a pointer to our state, via an
-	 * old request. However, since we know we only unpin the context
-	 * on retirement of the following request, we know that the last
-	 * request referencing us will have had a completion CS interrupt.
-	 * If we see that it is still active, it means that the tasklet hasn't
-	 * had the chance to run yet; let it run before we teardown the
-	 * reference it may use.
-	 */
-	engine = READ_ONCE(ce->inflight);
-	if (unlikely(engine)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&engine->timeline.lock, flags);
-		process_csb(engine);
-		spin_unlock_irqrestore(&engine->timeline.lock, flags);
-
-		GEM_BUG_ON(READ_ONCE(ce->inflight));
-	}
-
 	i915_gem_context_unpin_hw_id(ce->gem_context);
-
-	intel_ring_unpin(ce->ring);
-
 	i915_gem_object_unpin_map(ce->state->obj);
-	__context_unpin(ce->state);
+	intel_ring_unpin(ce->ring);
 }
 
 static void
@@ -1628,7 +1579,10 @@ __execlists_context_pin(struct intel_context *ce,
 		goto err;
 	GEM_BUG_ON(!ce->state);
 
-	ret = __context_pin(ce->state);
+	ret = intel_context_active(ce,
+				   engine->i915->ggtt.pin_bias |
+				   PIN_OFFSET_BIAS |
+				   PIN_HIGH);
 	if (ret)
 		goto err;
 
@@ -1637,7 +1591,7 @@ __execlists_context_pin(struct intel_context *ce,
 					I915_MAP_OVERRIDE);
 	if (IS_ERR(vaddr)) {
 		ret = PTR_ERR(vaddr);
-		goto unpin_vma;
+		goto unpin_active;
 	}
 
 	ret = intel_ring_pin(ce->ring);
@@ -1658,8 +1612,8 @@ __execlists_context_pin(struct intel_context *ce,
 	intel_ring_unpin(ce->ring);
 unpin_map:
 	i915_gem_object_unpin_map(ce->state->obj);
-unpin_vma:
-	__context_unpin(ce->state);
+unpin_active:
+	intel_context_inactive(ce);
 err:
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index fb4d3100848c..3cd1f413ec7f 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1367,45 +1367,9 @@ static void __context_unpin_ppgtt(struct i915_gem_context *ctx)
 		gen6_ppgtt_unpin(ppgtt);
 }
 
-static int __context_pin(struct intel_context *ce)
-{
-	struct i915_vma *vma;
-	int err;
-
-	vma = ce->state;
-	if (!vma)
-		return 0;
-
-	err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
-	if (err)
-		return err;
-
-	/*
-	 * And mark is as a globally pinned object to let the shrinker know
-	 * it cannot reclaim the object until we release it.
-	 */
-	vma->obj->pin_global++;
-	vma->obj->mm.dirty = true;
-
-	return 0;
-}
-
-static void __context_unpin(struct intel_context *ce)
-{
-	struct i915_vma *vma;
-
-	vma = ce->state;
-	if (!vma)
-		return;
-
-	vma->obj->pin_global--;
-	i915_vma_unpin(vma);
-}
-
 static void ring_context_unpin(struct intel_context *ce)
 {
 	__context_unpin_ppgtt(ce->gem_context);
-	__context_unpin(ce);
 }
 
 static struct i915_vma *
@@ -1495,18 +1459,18 @@ static int ring_context_pin(struct intel_context *ce)
 		ce->state = vma;
 	}
 
-	err = __context_pin(ce);
+	err = intel_context_active(ce, PIN_HIGH);
 	if (err)
 		return err;
 
 	err = __context_pin_ppgtt(ce->gem_context);
 	if (err)
-		goto err_unpin;
+		goto err_active;
 
 	return 0;
 
-err_unpin:
-	__context_unpin(ce);
+err_active:
+	intel_context_inactive(ce);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 29d80d82a6a2..d34ef476bb03 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -464,8 +464,6 @@ void intel_engines_resume(struct drm_i915_private *i915);
 bool intel_engine_is_idle(struct intel_engine_cs *engine);
 bool intel_engines_are_idle(struct drm_i915_private *dev_priv);
 
-void intel_engine_lost_context(struct intel_engine_cs *engine);
-
 void intel_engines_park(struct drm_i915_private *i915);
 void intel_engines_unpark(struct drm_i915_private *i915);
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_engine.c b/drivers/gpu/drm/i915/selftests/mock_engine.c
index b9908df92310..96d90405dae5 100644
--- a/drivers/gpu/drm/i915/selftests/mock_engine.c
+++ b/drivers/gpu/drm/i915/selftests/mock_engine.c
@@ -142,12 +142,18 @@ static void mock_context_destroy(struct kref *ref)
 
 static int mock_context_pin(struct intel_context *ce)
 {
+	int ret;
+
 	if (!ce->ring) {
 		ce->ring = mock_ring(ce->engine);
 		if (!ce->ring)
 			return -ENOMEM;
 	}
 
+	ret = intel_context_active(ce, PIN_HIGH);
+	if (ret)
+		return ret;
+
 	mock_timeline_pin(ce->ring->timeline);
 	return 0;
 }
@@ -311,14 +317,9 @@ void mock_engine_free(struct intel_engine_cs *engine)
 {
 	struct mock_engine *mock =
 		container_of(engine, typeof(*mock), base);
-	struct intel_context *ce;
 
 	GEM_BUG_ON(timer_pending(&mock->hw_delay));
 
-	ce = fetch_and_zero(&engine->last_retired_context);
-	if (ce)
-		intel_context_unpin(ce);
-
 	intel_context_unpin(engine->kernel_context);
 
 	intel_engine_fini_breadcrumbs(engine);
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index bc6f28132e88..4d34c42383f7 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -55,7 +55,6 @@ static void mock_device_release(struct drm_device *dev)
 
 	mutex_lock(&i915->drm.struct_mutex);
 	mock_device_flush(i915);
-	i915_gem_contexts_lost(i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 
 	drain_delayed_work(&i915->gt.retire_work);
@@ -112,7 +111,12 @@ static void mock_idle_work_handler(struct work_struct *work)
 	struct drm_i915_private *i915 =
 		container_of(work, typeof(*i915), gt.idle_work.work);
 
-	i915->gt.active_engines = 0;
+	mutex_lock(&i915->drm.struct_mutex);
+	if (!atomic_read(&i915->gt.active_requests)) {
+		//call_idle_barriers(i915);
+		i915->gt.active_engines = 0;
+	}
+	mutex_unlock(&i915->drm.struct_mutex);
 }
 
 static int pm_domain_resume(struct device *dev)
-- 
2.20.1



More information about the Intel-gfx-trybot mailing list