Merge tag 'drm-intel-gt-next-2021-12-09' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Core Changes:

- Fix PENDING_ERROR leak in dma_fence_array_signaled() (Thomas Hellström)

Driver Changes:

- Fix runtime PM handling during PXP suspend (Tejas Upadhyay)
- Improve eviction performance on discrete by implementing async TTM moves (Thomas Hellström, Maarten Lankhorst)
- Improve robustness of error capture under memory pressure (Thomas Hellström)
- Fix GuC PMU versus GPU reset handling (Umesh Nerlige Ramappa)
- Use per device iommu check (Tvrtko Ursulin)
- Make error capture work with async migration (Thomas Hellström)
- Revert incorrect implementation of Wa_1508744258 causing hangs (José Roberto de Souza)
- Disable coarse power gating on some DG2 steppings workaround (Matt Roper)
- Add IC cache invalidation workaround on DG2 (Ramalingam C)
- Move two Icelake workarounds to the right place (Raviteja Goud Talla)
- Fix error pointer dereference in i915_gem_do_execbuffer() (Dan Carpenter)
- Fixup a couple of generic and DG2 specific issues in migration code (Matthew Auld)

- Fix kernel-doc warnings in i915_drm_object.c (Randy Dunlap)
- Drop stealing of bits from i915_sw_fence function pointer (Matthew Brost)
- Introduce new macros for i915 PTE (Michael Cheng)
- Prep work for engine reset by reset domain lookup (Tejas Upadhyay)

- Fixup drm-intel-gt-next build failure (Matthew Auld)
- Fix live_engine_busy_stats selftests in GuC mode (Umesh Nerlige Ramappa)
- Remove dma_resv_prune (Maarten Lankhorst)
- Preserve huge pages enablement after driver reload (Matthew Auld)
- Fix a NULL pointer dereference in igt_request_rewind() (selftests) (Zhou Qingyang)
- Add workaround numbers to GEN7_COMMON_SLICE_CHICKEN1 whitelisting (José Roberto de Souza)
- Increase timeouts in i915_gem_contexts selftests to handle GuC being slower (Bruce Chang)

Signed-off-by: Dave Airlie <airlied@redhat.com>

# Conflicts:
#	drivers/gpu/drm/i915/display/intel_fbc.c
From: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/YbIBOeqhn+nPzaYD@tursulin-mobl2

1 files changed, 65 insertions, 33 deletions

diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index bef795e265a6..927f0d4f8e11 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -40,12 +40,12 @@
 
 static struct kmem_cache *slab_vmas;
 
-struct i915_vma *i915_vma_alloc(void)
+static struct i915_vma *i915_vma_alloc(void)
 {
 	return kmem_cache_zalloc(slab_vmas, GFP_KERNEL);
 }
 
-void i915_vma_free(struct i915_vma *vma)
+static void i915_vma_free(struct i915_vma *vma)
 {
 	return kmem_cache_free(slab_vmas, vma);
 }
@@ -113,7 +113,6 @@ vma_create(struct drm_i915_gem_object *obj,
 	vma->vm = i915_vm_get(vm);
 	vma->ops = &vm->vma_ops;
 	vma->obj = obj;
-	vma->resv = obj->base.resv;
 	vma->size = obj->base.size;
 	vma->display_alignment = I915_GTT_MIN_ALIGNMENT;
 
@@ -346,7 +345,7 @@ int i915_vma_wait_for_bind(struct i915_vma *vma)
 		fence = dma_fence_get_rcu_safe(&vma->active.excl.fence);
 		rcu_read_unlock();
 		if (fence) {
-			err = dma_fence_wait(fence, MAX_SCHEDULE_TIMEOUT);
+			err = dma_fence_wait(fence, true);
 			dma_fence_put(fence);
 		}
 	}
@@ -354,6 +353,32 @@ int i915_vma_wait_for_bind(struct i915_vma *vma)
 	return err;
 }
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+static int i915_vma_verify_bind_complete(struct i915_vma *vma)
+{
+	int err = 0;
+
+	if (i915_active_has_exclusive(&vma->active)) {
+		struct dma_fence *fence =
+			i915_active_fence_get(&vma->active.excl);
+
+		if (!fence)
+			return 0;
+
+		if (dma_fence_is_signaled(fence))
+			err = fence->error;
+		else
+			err = -EBUSY;
+
+		dma_fence_put(fence);
+	}
+
+	return err;
+}
+#else
+#define i915_vma_verify_bind_complete(_vma) 0
+#endif
+
 /**
  * i915_vma_bind - Sets up PTEs for an VMA in it's corresponding address space.
  * @vma: VMA to map
@@ -423,11 +448,16 @@ int i915_vma_bind(struct i915_vma *vma,
 
 		work->base.dma.error = 0; /* enable the queue_work() */
 
+		__i915_gem_object_pin_pages(vma->obj);
+		work->pinned = i915_gem_object_get(vma->obj);
+	} else {
 		if (vma->obj) {
-			__i915_gem_object_pin_pages(vma->obj);
-			work->pinned = i915_gem_object_get(vma->obj);
+			int ret;
+
+			ret = i915_gem_object_wait_moving_fence(vma->obj, true);
+			if (ret)
+				return ret;
 		}
-	} else {
 		vma->ops->bind_vma(vma->vm, NULL, vma, cache_level, bind_flags);
 	}
 
@@ -449,6 +479,7 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
 	GEM_BUG_ON(!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND));
+	GEM_BUG_ON(i915_vma_verify_bind_complete(vma));
 
 	ptr = READ_ONCE(vma->iomap);
 	if (ptr == NULL) {
@@ -667,7 +698,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	}
 
 	color = 0;
-	if (vma->obj && i915_vm_has_cache_coloring(vma->vm))
+	if (i915_vm_has_cache_coloring(vma->vm))
 		color = vma->obj->cache_level;
 
 	if (flags & PIN_OFFSET_FIXED) {
@@ -792,17 +823,14 @@ unpinned:
 static int vma_get_pages(struct i915_vma *vma)
 {
 	int err = 0;
-	bool pinned_pages = false;
+	bool pinned_pages = true;
 
 	if (atomic_add_unless(&vma->pages_count, 1, 0))
 		return 0;
 
-	if (vma->obj) {
-		err = i915_gem_object_pin_pages(vma->obj);
-		if (err)
-			return err;
-		pinned_pages = true;
-	}
+	err = i915_gem_object_pin_pages(vma->obj);
+	if (err)
+		return err;
 
 	/* Allocations ahoy! */
 	if (mutex_lock_interruptible(&vma->pages_mutex)) {
@@ -835,8 +863,8 @@ static void __vma_put_pages(struct i915_vma *vma, unsigned int count)
 	if (atomic_sub_return(count, &vma->pages_count) == 0) {
 		vma->ops->clear_pages(vma);
 		GEM_BUG_ON(vma->pages);
-		if (vma->obj)
-			i915_gem_object_unpin_pages(vma->obj);
+
+		i915_gem_object_unpin_pages(vma->obj);
 	}
 	mutex_unlock(&vma->pages_mutex);
 }
@@ -867,12 +895,13 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 		    u64 size, u64 alignment, u64 flags)
 {
 	struct i915_vma_work *work = NULL;
+	struct dma_fence *moving = NULL;
 	intel_wakeref_t wakeref = 0;
 	unsigned int bound;
 	int err;
 
 #ifdef CONFIG_PROVE_LOCKING
-	if (debug_locks && !WARN_ON(!ww) && vma->resv)
+	if (debug_locks && !WARN_ON(!ww))
 		assert_vma_held(vma);
 #endif
 
@@ -892,7 +921,8 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 	if (flags & PIN_GLOBAL)
 		wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm);
 
-	if (flags & vma->vm->bind_async_flags) {
+	moving = vma->obj ? i915_gem_object_get_moving_fence(vma->obj) : NULL;
+	if (flags & vma->vm->bind_async_flags || moving) {
 		/* lock VM */
 		err = i915_vm_lock_objects(vma->vm, ww);
 		if (err)
@@ -906,6 +936,8 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 
 		work->vm = i915_vm_get(vma->vm);
 
+		dma_fence_work_chain(&work->base, moving);
+
 		/* Allocate enough page directories to used PTE */
 		if (vma->vm->allocate_va_range) {
 			err = i915_vm_alloc_pt_stash(vma->vm,
@@ -980,7 +1012,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 
 	GEM_BUG_ON(!vma->pages);
 	err = i915_vma_bind(vma,
-			    vma->obj ? vma->obj->cache_level : 0,
+			    vma->obj->cache_level,
 			    flags, work);
 	if (err)
 		goto err_remove;
@@ -1010,7 +1042,10 @@ err_fence:
 err_rpm:
 	if (wakeref)
 		intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref);
+	if (moving)
+		dma_fence_put(moving);
 	vma_put_pages(vma);
+
 	return err;
 }
 
@@ -1034,7 +1069,7 @@ int i915_ggtt_pin(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
 
 #ifdef CONFIG_LOCKDEP
-	WARN_ON(!ww && vma->resv && dma_resv_held(vma->resv));
+	WARN_ON(!ww && dma_resv_held(vma->obj->base.resv));
 #endif
 
 	do {
@@ -1113,6 +1148,7 @@ void i915_vma_reopen(struct i915_vma *vma)
 void i915_vma_release(struct kref *ref)
 {
 	struct i915_vma *vma = container_of(ref, typeof(*vma), ref);
+	struct drm_i915_gem_object *obj = vma->obj;
 
 	if (drm_mm_node_allocated(&vma->node)) {
 		mutex_lock(&vma->vm->mutex);
@@ -1123,15 +1159,11 @@ void i915_vma_release(struct kref *ref)
 	}
 	GEM_BUG_ON(i915_vma_is_active(vma));
 
-	if (vma->obj) {
-		struct drm_i915_gem_object *obj = vma->obj;
-
-		spin_lock(&obj->vma.lock);
-		list_del(&vma->obj_link);
-		if (!RB_EMPTY_NODE(&vma->obj_node))
-			rb_erase(&vma->obj_node, &obj->vma.tree);
-		spin_unlock(&obj->vma.lock);
-	}
+	spin_lock(&obj->vma.lock);
+	list_del(&vma->obj_link);
+	if (!RB_EMPTY_NODE(&vma->obj_node))
+		rb_erase(&vma->obj_node, &obj->vma.tree);
+	spin_unlock(&obj->vma.lock);
 
 	__i915_vma_remove_closed(vma);
 	i915_vm_put(vma->vm);
@@ -1256,19 +1288,19 @@ int _i915_vma_move_to_active(struct i915_vma *vma,
 		}
 
 		if (fence) {
-			dma_resv_add_excl_fence(vma->resv, fence);
+			dma_resv_add_excl_fence(vma->obj->base.resv, fence);
 			obj->write_domain = I915_GEM_DOMAIN_RENDER;
 			obj->read_domains = 0;
 		}
 	} else {
 		if (!(flags & __EXEC_OBJECT_NO_RESERVE)) {
-			err = dma_resv_reserve_shared(vma->resv, 1);
+			err = dma_resv_reserve_shared(vma->obj->base.resv, 1);
 			if (unlikely(err))
 				return err;
 		}
 
 		if (fence) {
-			dma_resv_add_shared_fence(vma->resv, fence);
+			dma_resv_add_shared_fence(vma->obj->base.resv, fence);
 			obj->write_domain = 0;
 		}
 	}