12 files changed, 133 insertions, 52 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 026cb52ece0b..94b23fcbc989 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4603,11 +4603,17 @@ static void __i915_gem_free_work(struct work_struct *work)
          * unbound now.
          */
 
+        spin_lock(&i915->mm.free_lock);
         while ((freed = llist_del_all(&i915->mm.free_list))) {
+                spin_unlock(&i915->mm.free_lock);
+
                 __i915_gem_free_objects(i915, freed);
                 if (need_resched())
-                        break;
+                        return;
+
+                spin_lock(&i915->mm.free_lock);
         }
+        spin_unlock(&i915->mm.free_lock);
 }
 
 static void __i915_gem_free_object_rcu(struct rcu_head *head)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 5bf96a258509..e304dcbc6042 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -106,14 +106,9 @@ static void lut_close(struct i915_gem_context *ctx)
 
         radix_tree_for_each_slot(slot, &ctx->handles_vma, &iter, 0) {
                 struct i915_vma *vma = rcu_dereference_raw(*slot);
-                struct drm_i915_gem_object *obj = vma->obj;
 
                 radix_tree_iter_delete(&ctx->handles_vma, &iter, slot);
-
-                if (!i915_vma_is_ggtt(vma))
-                        i915_vma_close(vma);
-
-                __i915_gem_object_release_unless_active(obj);
+                __i915_gem_object_release_unless_active(vma->obj);
         }
 }
 
@@ -198,6 +193,11 @@ static void context_close(struct i915_gem_context *ctx)
 {
         i915_gem_context_set_closed(ctx);
 
+        /*
+         * The LUT uses the VMA as a backpointer to unref the object,
+         * so we need to clear the LUT before we close all the VMA (inside
+         * the ppgtt).
+         */
         lut_close(ctx);
         if (ctx->ppgtt)
                 i915_ppgtt_close(&ctx->ppgtt->base);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 527a2d2d6281..5eaa6893daaa 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1341,7 +1341,7 @@ static int gen8_ppgtt_alloc_pd(struct i915_address_space *vm,
                         if (IS_ERR(pt))
                                 goto unwind;
 
-                        if (count < GEN8_PTES)
+                        if (count < GEN8_PTES || intel_vgpu_active(vm->i915))
                                 gen8_initialize_pt(vm, pt);
 
                         gen8_ppgtt_set_pde(vm, pd, pt, pde);
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index eb31f8aa5c21..3770e3323fc8 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -162,6 +162,18 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
         if (!shrinker_lock(dev_priv, &unlock))
                 return 0;
 
+        /*
+         * When shrinking the active list, also consider active contexts.
+         * Active contexts are pinned until they are retired, and so can
+         * not be simply unbound to retire and unpin their pages. To shrink
+         * the contexts, we must wait until the gpu is idle.
+         *
+         * We don't care about errors here; if we cannot wait upon the GPU,
+         * we will free as much as we can and hope to get a second chance.
+         */
+        if (flags & I915_SHRINK_ACTIVE)
+                i915_gem_wait_for_idle(dev_priv, I915_WAIT_LOCKED);
+
         trace_i915_gem_shrink(dev_priv, target, flags);
         i915_gem_retire_requests(dev_priv);
 
diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index a2e8114b739d..f84c267728fd 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -610,6 +610,7 @@ done:
         execlists->first = rb;
         if (submit) {
                 port_assign(port, last);
+                execlists_set_active(execlists, EXECLISTS_ACTIVE_USER);
                 i915_guc_submit(engine);
         }
         spin_unlock_irq(&engine->timeline->lock);
@@ -633,6 +634,8 @@ static void i915_guc_irq_handler(unsigned long data)
 
                 rq = port_request(&port[0]);
         }
+        if (!rq)
+                execlists_clear_active(execlists, EXECLISTS_ACTIVE_USER);
 
         if (!port_isset(last_port))
                 i915_guc_dequeue(engine);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index b1296a55c1e4..f8205841868b 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1388,8 +1388,10 @@ gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir, int test_shift)
         bool tasklet = false;
 
         if (iir & (GT_CONTEXT_SWITCH_INTERRUPT << test_shift)) {
-                __set_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
-                tasklet = true;
+                if (READ_ONCE(engine->execlists.active)) {
+                        __set_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
+                        tasklet = true;
+                }
         }
 
         if (iir & (GT_RENDER_USER_INTERRUPT << test_shift)) {
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index fc77e8191eb5..fbfab2f33023 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -54,6 +54,13 @@ i915_vma_retire(struct i915_gem_active *active,
         if (--obj->active_count)
                 return;
 
+        /* Prune the shared fence arrays iff completely idle (inc. external) */
+        if (reservation_object_trylock(obj->resv)) {
+                if (reservation_object_test_signaled_rcu(obj->resv, true))
+                        reservation_object_add_excl_fence(obj->resv, NULL);
+                reservation_object_unlock(obj->resv);
+        }
+
         /* Bump our place on the bound list to keep it roughly in LRU order
          * so that we don't steal from recently used but inactive objects
          * (unless we are forced to ofc!)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index e2ac976844d8..f4a9a182868f 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3676,6 +3676,7 @@ void intel_finish_reset(struct drm_i915_private *dev_priv)
 
                 intel_pps_unlock_regs_wa(dev_priv);
                 intel_modeset_init_hw(dev);
+                intel_init_clock_gating(dev_priv);
 
                 spin_lock_irq(&dev_priv->irq_lock);
                 if (dev_priv->display.hpd_irq_setup)
@@ -14350,8 +14351,6 @@ void intel_modeset_init_hw(struct drm_device *dev)
 
         intel_update_cdclk(dev_priv);
         dev_priv->cdclk.logical = dev_priv->cdclk.actual = dev_priv->cdclk.hw;
-
-        intel_init_clock_gating(dev_priv);
 }
 
 /*
@@ -15063,6 +15062,15 @@ intel_modeset_setup_hw_state(struct drm_device *dev,
         struct intel_encoder *encoder;