Merge tag 'drm-for-v4.8' of git://people.freedesktop.org/~airlied/linux

Merge drm updates from Dave Airlie:
 "This is the main drm pull request for 4.8.

  I'm down with a cold at the moment so hopefully this isn't in too bad
  a state, I finished pulling stuff last week mostly (nouveau fixes just
  went in today), so only this message should be influenced by illness.
  Apologies to anyone who's major feature I missed :-)

  Core:
        Lockless GEM BO freeing
        Non-blocking atomic work
        Documentation changes (rst/sphinx)
        Prep for new fencing changes
        Simple display helpers
        Master/auth changes
        Register/unregister rework
        Loads of trivial patches/fixes.

  New stuff:
        ARM Mali display driver (not the 3D chip)
        sii902x RGB->HDMI bridge

  Panel:
        Support for new panels
        Improved backlight support

  Bridge:
        Convert ADV7511 to bridge driver
        ADV7533 support
        TC358767 (DSI/DPI to eDP) encoder chip support

  i915:
        BXT support enabled by default
        GVT-g infrastructure
        GuC command submission and fixes
        BXT workarounds
        SKL/BKL workarounds
        Demidlayering device registration
        Thundering herd fixes
        Missing pci ids
        Atomic updates

  amdgpu/radeon:
        ATPX improvements for better dGPU power control on PX systems
        New power features for CZ/BR/ST
        Pipelined BO moves and evictions in TTM
        GPU scheduler improvements
        GPU reset improvements
        Overclocking on dGPUs with amdgpu
        Polaris powermanagement enabled

  nouveau:
        GK20A/GM20B volt and clock improvements.
        Initial support for GP100/GP104 GPUs, GP104 will not yet support
        acceleration due to NVIDIA having not released firmware for them as of yet.

  exynos:
        Exynos5433 SoC with IOMMU support.

  vc4:
        Shader validation for branching

  imx-drm:
        Atomic mode setting conversion
        Reworked DMFC FIFO allocation
        External bridge support

  analogix-dp:
        RK3399 eDP support
        Lots of fixes.

  rockchip:
        Lots of small fixes.

  msm:
        DT bindings cleanups
        Shrinker and madvise support
        ASoC HDMI codec support

  tegra:
        Host1x driver cleanups
        SOR reworking for DP support
        Runtime PM support

  omapdrm:
        PLL enhancements
        Header refactoring
        Gamma table support

  arcgpu:
        Simulator support

  virtio-gpu:
        Atomic modesetting fixes.

  rcar-du:
        Misc fixes.

  mediatek:
        MT8173 HDMI support

  sti:
        ASOC HDMI codec support
        Minor fixes

  fsl-dcu:
        Suspend/resume support
        Bridge support

  amdkfd:
        Minor fixes.

  etnaviv:
        Enable GPU clock gating

  hisilicon:
        Vblank and other fixes"

* tag 'drm-for-v4.8' of git://people.freedesktop.org/~airlied/linux: (1575 commits)
  drm/nouveau/gr/nv3x: fix instobj write offsets in gr setup
  drm/nouveau/acpi: fix lockup with PCIe runtime PM
  drm/nouveau/acpi: check for function 0x1B before using it
  drm/nouveau/acpi: return supported DSM functions
  drm/nouveau/acpi: ensure matching ACPI handle and supported functions
  drm/nouveau/fbcon: fix font width not divisible by 8
  drm/amd/powerplay: remove enable_clock_power_gatings_tasks from initialize and resume events
  drm/amd/powerplay: move clockgating to after ungating power in pp for uvd/vce
  drm/amdgpu: add query device id and revision id into system info entry at CGS
  drm/amdgpu: add new definition in bif header
  drm/amd/powerplay: rename smum header guards
  drm/amdgpu: enable UVD context buffer for older HW
  drm/amdgpu: fix default UVD context size
  drm/amdgpu: fix incorrect type of info_id
  drm/amdgpu: make amdgpu_cgs_call_acpi_method as static
  drm/amdgpu: comment out unused defaults_staturn_pro static const structure to fix the build
  drm/amdgpu: enable UVD VM only on polaris
  drm/amdgpu: increase timeout of IB test
  drm/amdgpu: add destroy session when generate VCE destroy msg.
  drm/amd: fix deadlock of job_list_lock V2
  ...

1 files changed, 84 insertions, 81 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index a71cf98c655f..4054d804fe06 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -146,10 +146,9 @@ static void ttm_bo_release_list(struct kref *list_kref)
 	BUG_ON(bo->mem.mm_node != NULL);
 	BUG_ON(!list_empty(&bo->lru));
 	BUG_ON(!list_empty(&bo->ddestroy));
-
-	if (bo->ttm)
-		ttm_tt_destroy(bo->ttm);
+	ttm_tt_destroy(bo->ttm);
 	atomic_dec(&bo->glob->bo_count);
+	fence_put(bo->moving);
 	if (bo->resv == &bo->ttm_resv)
 		reservation_object_fini(&bo->ttm_resv);
 	mutex_destroy(&bo->wu_mutex);
@@ -360,7 +359,8 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 		ret = bdev->driver->move(bo, evict, interruptible,
 					 no_wait_gpu, mem);
 	else
-		ret = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, mem);
+		ret = ttm_bo_move_memcpy(bo, evict, interruptible,
+					 no_wait_gpu, mem);
 
 	if (ret) {
 		if (bdev->driver->move_notify) {
@@ -396,8 +396,7 @@ moved:
 
 out_err:
 	new_man = &bdev->man[bo->mem.mem_type];
-	if ((new_man->flags & TTM_MEMTYPE_FLAG_FIXED) && bo->ttm) {
-		ttm_tt_unbind(bo->ttm);
+	if (new_man->flags & TTM_MEMTYPE_FLAG_FIXED) {
 		ttm_tt_destroy(bo->ttm);
 		bo->ttm = NULL;
 	}
@@ -418,11 +417,8 @@ static void ttm_bo_cleanup_memtype_use(struct ttm_buffer_object *bo)
 	if (bo->bdev->driver->move_notify)
 		bo->bdev->driver->move_notify(bo, NULL);
 
-	if (bo->ttm) {
-		ttm_tt_unbind(bo->ttm);
-		ttm_tt_destroy(bo->ttm);
-		bo->ttm = NULL;
-	}
+	ttm_tt_destroy(bo->ttm);
+	bo->ttm = NULL;
 	ttm_bo_mem_put(bo, &bo->mem);
 
 	ww_mutex_unlock (&bo->resv->lock);
@@ -688,15 +684,6 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 	struct ttm_placement placement;
 	int ret = 0;
 
-	ret = ttm_bo_wait(bo, interruptible, no_wait_gpu);
-
-	if (unlikely(ret != 0)) {
-		if (ret != -ERESTARTSYS) {
-			pr_err("Failed to expire sync object before buffer eviction\n");
-		}
-		goto out;
-	}
-
 	lockdep_assert_held(&bo->resv->lock.base);
 
 	evict_mem = bo->mem;
@@ -720,7 +707,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 
 	ret = ttm_bo_handle_move_mem(bo, &evict_mem, true, interruptible,
 				     no_wait_gpu);
-	if (ret) {
+	if (unlikely(ret)) {
 		if (ret != -ERESTARTSYS)
 			pr_err("Buffer eviction failed\n");
 		ttm_bo_mem_put(bo, &evict_mem);
@@ -800,6 +787,34 @@ void ttm_bo_mem_put(struct ttm_buffer_object *bo, struct ttm_mem_reg *mem)
 EXPORT_SYMBOL(ttm_bo_mem_put);
 
 /**
+ * Add the last move fence to the BO and reserve a new shared slot.
+ */
+static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
+				 struct ttm_mem_type_manager *man,
+				 struct ttm_mem_reg *mem)
+{
+	struct fence *fence;
+	int ret;
+
+	spin_lock(&man->move_lock);
+	fence = fence_get(man->move);
+	spin_unlock(&man->move_lock);
+
+	if (fence) {
+		reservation_object_add_shared_fence(bo->resv, fence);
+
+		ret = reservation_object_reserve_shared(bo->resv);
+		if (unlikely(ret))
+			return ret;
+
+		fence_put(bo->moving);
+		bo->moving = fence;
+	}
+
+	return 0;
+}
+
+/**
  * Repeatedly evict memory from the LRU for @mem_type until we create enough
  * space, or we've evicted everything and there isn't enough space.
  */
@@ -825,10 +840,8 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 		if (unlikely(ret != 0))
 			return ret;
 	} while (1);
-	if (mem->mm_node == NULL)
-		return -ENOMEM;
 	mem->mem_type = mem_type;
-	return 0;
+	return ttm_bo_add_move_fence(bo, man, mem);
 }
 
 static uint32_t ttm_bo_select_caching(struct ttm_mem_type_manager *man,
@@ -898,6 +911,10 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 	bool has_erestartsys = false;
 	int i, ret;
 
+	ret = reservation_object_reserve_shared(bo->resv);
+	if (unlikely(ret))
+		return ret;
+
 	mem->mm_node = NULL;
 	for (i = 0; i < placement->num_placement; ++i) {
 		const struct ttm_place *place = &placement->placement[i];
@@ -931,9 +948,15 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		ret = (*man->func->get_node)(man, bo, place, mem);
 		if (unlikely(ret))
 			return ret;
-		
-		if (mem->mm_node)
+
+		if (mem->mm_node) {
+			ret = ttm_bo_add_move_fence(bo, man, mem);
+			if (unlikely(ret)) {
+				(*man->func->put_node)(man, mem);
+				return ret;
+			}
 			break;
+		}
 	}
 
 	if ((type_ok && (mem_type == TTM_PL_SYSTEM)) || mem->mm_node) {
@@ -1000,20 +1023,6 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 
 	lockdep_assert_held(&bo->resv->lock.base);
 
-	/*
-	 * Don't wait for the BO on initial allocation. This is important when
-	 * the BO has an imported reservation object.
-	 */
-	if (bo->mem.mem_type != TTM_PL_SYSTEM || bo->ttm != NULL) {
-		/*
-		 * FIXME: It's possible to pipeline buffer moves.
-		 * Have the driver move function wait for idle when necessary,
-		 * instead of doing it here.
-		 */
-		ret = ttm_bo_wait(bo, interruptible, no_wait_gpu);
-		if (ret)
-			return ret;
-	}
 	mem.num_pages = bo->num_pages;
 	mem.size = mem.num_pages << PAGE_SHIFT;
 	mem.page_alignment = bo->mem.page_alignment;
@@ -1166,7 +1175,7 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 	bo->mem.page_alignment = page_alignment;
 	bo->mem.bus.io_reserved_vm = false;
 	bo->mem.bus.io_reserved_count = 0;
-	bo->priv_flags = 0;
+	bo->moving = NULL;
 	bo->mem.placement = (TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED);
 	bo->persistent_swap_storage = persistent_swap_storage;
 	bo->acc_size = acc_size;
@@ -1278,6 +1287,7 @@ static int ttm_bo_force_list_clean(struct ttm_bo_device *bdev,
 {
 	struct ttm_mem_type_manager *man = &bdev->man[mem_type];
 	struct ttm_bo_global *glob = bdev->glob;
+	struct fence *fence;
 	int ret;
 
 	/*
@@ -1298,6 +1308,23 @@ static int ttm_bo_force_list_clean(struct ttm_bo_device *bdev,
 		spin_lock(&glob->lru_lock);
 	}
 	spin_unlock(&glob->lru_lock);
+
+	spin_lock(&man->move_lock);
+	fence = fence_get(man->move);
+	spin_unlock(&man->move_lock);
+
+	if (fence) {
+		ret = fence_wait(fence, false);
+		fence_put(fence);
+		if (ret) {
+			if (allow_errors) {
+				return ret;
+			} else {
+				pr_err("Cleanup eviction failed\n");
+			}
+		}
+	}
+
 	return 0;
 }
 
@@ -1317,6 +1344,7 @@ int ttm_bo_clean_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 		       mem_type);
 		return ret;
 	}
+	fence_put(man->move);
 
 	man->use_type = false;
 	man->has_type = false;
@@ -1362,6 +1390,7 @@ int ttm_bo_init_mm(struct ttm_bo_device *bdev, unsigned type,
 	man->io_reserve_fastpath = true;
 	man->use_io_reserve_lru = false;
 	mutex_init(&man->io_reserve_mutex);
+	spin_lock_init(&man->move_lock);
 	INIT_LIST_HEAD(&man->io_reserve_lru);
 
 	ret = bdev->driver->init_mem_type(bdev, type, man);
@@ -1380,6 +1409,7 @@ int ttm_bo_init_mm(struct ttm_bo_device *bdev, unsigned type,
 	man->size = p_size;
 
 	INIT_LIST_HEAD(&man->lru);
+	man->move = NULL;
 
 	return 0;
 }
@@ -1573,47 +1603,17 @@ EXPORT_SYMBOL(ttm_bo_unmap_virtual);
 int ttm_bo_wait(struct ttm_buffer_object *bo,
 		bool interruptible, bool no_wait)
 {
-	struct reservation_object_list *fobj;
-	struct reservation_object *resv;
-	struct fence *excl;
-	long timeout = 15 * HZ;
-	int i;
-
-	resv = bo->resv;
-	fobj = reservation_object_get_list(resv);
-	excl = reservation_object_get_excl(resv);
-	if (excl) {
-		if (!fence_is_signaled(excl)) {
-			if (no_wait)
-				return -EBUSY;
-
-			timeout = fence_wait_timeout(excl,
-						     interruptible, timeout);
-		}
-	}
-
-	for (i = 0; fobj && timeout > 0 && i < fobj->shared_count; ++i) {
-		struct fence *fence;
-		fence = rcu_dereference_protected(fobj->shared[i],
-						reservation_object_held(resv));
-
-		if (!fence_is_signaled(fence)) {
-			if (no_wait)
-				return -EBUSY;
-
-			timeout = fence_wait_timeout(fence,
-						     interruptible, timeout);
-		}
-	}
+	long timeout = no_wait ? 0 : 15 * HZ;
 
+	timeout = reservation_object_wait_timeout_rcu(bo->resv, true,
+						      interruptible, timeout);
 	if (timeout < 0)
 		return timeout;
 
 	if (timeout == 0)
 		return -EBUSY;
 
-	reservation_object_add_excl_fence(resv, NULL);
-	clear_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
+	reservation_object_add_excl_fence(bo->resv, NULL);
 	return 0;
 }
 EXPORT_SYMBOL(ttm_bo_wait);
@@ -1683,14 +1683,9 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 	ttm_bo_list_ref_sub(bo, put_count, true);
 
 	/**
-	 * Wait for GPU, then move to system cached.
+	 * Move to system cached
 	 */
 
-	ret = ttm_bo_wait(bo, false, false);
-
-	if (unlikely(ret != 0))
-		goto out;
-
 	if ((bo->mem.placement & swap_placement) != swap_placement) {
 		struct ttm_mem_reg evict_mem;
 
@@ -1705,6 +1700,14 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 			goto out;
 	}
 
+	/**
+	 * Make sure BO is idle.
+	 */
+
+	ret = ttm_bo_wait(bo, false, false);
+	if (unlikely(ret != 0))
+		goto out;
+
 	ttm_bo_unmap_virtual(bo);
 
 	/**