Merge tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This seems to have been a comparatively quieter merge window, I assume
  due to holidays etc. The "biggest" change is AMD header cleanups, which
  merge/remove a bunch of them. The AMD gpu scheduler is now being made generic
  with the etnaviv driver wanting to reuse the code, hopefully other drivers
  can go in the same direction.

  Otherwise it's the usual lots of stuff in i915/amdgpu, not so much stuff
  elsewhere.

  Core:
   - Add .last_close and .output_poll_changed helpers to reduce driver footprints
   - Fix plane clipping
   - Improved debug printing support
   - Add panel orientation property
   - Update edid derived properties at edid setting
   - Reduction in fbdev driver footprint
   - Move amdgpu scheduler into core for other drivers to use.

  i915:
   - Selftest and IGT improvements
   - Fast boot prep work on IPS, pipe config
   - HW workarounds for Cannonlake, Geminilake
   - Cannonlake clock and HDMI2.0 fixes
   - GPU cache invalidation and context switch improvements
   - Display planes cleanup
   - New PMU interface for perf queries
   - New firmware support for KBL/SKL
   - Geminilake HW workaround for perforamce
   - Coffeelake stolen memory improvements
   - GPU reset robustness work
   - Cannonlake horizontal plane flipping
   - GVT work

  amdgpu/radeon:
   - RV and Vega header file cleanups (lots of lines gone!)
   - TTM operation context support
   - 48-bit GPUVM support for Vega/RV
   - ECC support for Vega
   - Resizeable BAR support
   - Multi-display sync support
   - Enable swapout for reserved BOs during allocation
   - S3 fixes on Raven
   - GPU reset cleanup and fixes
   - 2+1 level GPU page table

  amdkfd:
   - GFX7/8 SDMA user queues support
   - Hardware scheduling for multiple processes
   - dGPU prep work

  rcar:
   - Added R8A7743/5 support
   - System suspend/resume support

  sun4i:
   - Multi-plane support for YUV formats
   - A83T and LVDS support

  msm:
   - Devfreq support for GPU

  tegra:
   - Prep work for adding Tegra186 support
   - Tegra186 HDMI support
   - HDMI2.0 and zpos support by using generic helpers

  tilcdc:
   - Misc fixes

  omapdrm:
   - Support memory bandwidth limits
   - DSI command mode panel cleanups
   - DMM error handling

  exynos:
   - drop the old IPP subdriver.

  etnaviv:
   - Occlusion query fixes
   - Job handling fixes
   - Prep work for hooking in gpu scheduler

  armada:
   - Move closer to atomic modesetting
   - Allow disabling primary plane if overlay is full screen

  imx:
   - Format modifier support
   - Add tile prefetch to PRE
   - Runtime PM support for PRG

  ast:
   - fix LUT loading"

* tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux: (1471 commits)
  drm/ast: Load lut in crtc_commit
  drm: Check for lessee in DROP_MASTER ioctl
  drm: fix gpu scheduler link order
  drm/amd/display: Demote error print to debug print when ATOM impl missing
  dma-buf: fix reservation_object_wait_timeout_rcu once more v2
  drm/amdgpu: Avoid leaking PM domain on driver unbind (v2)
  drm/amd/amdgpu: Add Polaris version check
  drm/amdgpu: Reenable manual GPU reset from sysfs
  drm/amdgpu: disable MMHUB power gating on raven
  drm/ttm: Don't unreserve swapped BOs that were previously reserved
  drm/ttm: Don't add swapped BOs to swap-LRU list
  drm/amdgpu: only check for ECC on Vega10
  drm/amd/powerplay: Fix smu_table_entry.handle type
  drm/ttm: add VADDR_FLAG_UPDATED_COUNT to correctly update dma_page global count
  drm: Fix PANEL_ORIENTATION_QUIRKS breaking the Kconfig DRM menuconfig
  drm/radeon: fill in rb backend map on evergreen/ni.
  drm/amdgpu/gfx9: fix ngg enablement to clear gds reserved memory (v2)
  drm/ttm: only free pages rather than update global memory count together
  drm/amdgpu: fix CPU based VM updates
  drm/amdgpu: fix typo in amdgpu_vce_validate_bo
  ...

6 files changed, 81 insertions, 21 deletions

diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 4756b3c9bf2c..9a9214ae0fb5 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -289,6 +289,7 @@ static void qxl_crtc_destroy(struct drm_crtc *crtc)
 {
 	struct qxl_crtc *qxl_crtc = to_qxl_crtc(crtc);
 
+	qxl_bo_unref(&qxl_crtc->cursor_bo);
 	drm_crtc_cleanup(crtc);
 	kfree(qxl_crtc);
 }
@@ -495,6 +496,53 @@ static int qxl_primary_atomic_check(struct drm_plane *plane,
 	return 0;
 }
 
+static int qxl_primary_apply_cursor(struct drm_plane *plane)
+{
+	struct drm_device *dev = plane->dev;
+	struct qxl_device *qdev = dev->dev_private;
+	struct drm_framebuffer *fb = plane->state->fb;
+	struct qxl_crtc *qcrtc = to_qxl_crtc(plane->state->crtc);
+	struct qxl_cursor_cmd *cmd;
+	struct qxl_release *release;
+	int ret = 0;
+
+	if (!qcrtc->cursor_bo)
+		return 0;
+
+	ret = qxl_alloc_release_reserved(qdev, sizeof(*cmd),
+					 QXL_RELEASE_CURSOR_CMD,
+					 &release, NULL);
+	if (ret)
+		return ret;
+
+	ret = qxl_release_list_add(release, qcrtc->cursor_bo);
+	if (ret)
+		goto out_free_release;
+
+	ret = qxl_release_reserve_list(release, false);
+	if (ret)
+		goto out_free_release;
+
+	cmd = (struct qxl_cursor_cmd *)qxl_release_map(qdev, release);
+	cmd->type = QXL_CURSOR_SET;
+	cmd->u.set.position.x = plane->state->crtc_x + fb->hot_x;
+	cmd->u.set.position.y = plane->state->crtc_y + fb->hot_y;
+
+	cmd->u.set.shape = qxl_bo_physical_address(qdev, qcrtc->cursor_bo, 0);
+
+	cmd->u.set.visible = 1;
+	qxl_release_unmap(qdev, release, &cmd->release_info);
+
+	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
+	qxl_release_fence_buffer_objects(release);
+
+	return ret;
+
+out_free_release:
+	qxl_release_free(qdev, release);
+	return ret;
+}
+
 static void qxl_primary_atomic_update(struct drm_plane *plane,
 				      struct drm_plane_state *old_state)
 {
@@ -510,6 +558,7 @@ static void qxl_primary_atomic_update(struct drm_plane *plane,
 	    .x2 = qfb->base.width,
 	    .y2 = qfb->base.height
 	};
+	int ret;
 	bool same_shadow = false;
 
 	if (old_state->fb) {
@@ -531,6 +580,11 @@ static void qxl_primary_atomic_update(struct drm_plane *plane,
 		if (!same_shadow)
 			qxl_io_destroy_primary(qdev);
 		bo_old->is_primary = false;
+
+		ret = qxl_primary_apply_cursor(plane);
+		if (ret)
+			DRM_ERROR(
+			"could not set cursor after creating primary");
 	}
 
 	if (!bo->is_primary) {
@@ -571,11 +625,12 @@ static void qxl_cursor_atomic_update(struct drm_plane *plane,
 	struct drm_device *dev = plane->dev;
 	struct qxl_device *qdev = dev->dev_private;
 	struct drm_framebuffer *fb = plane->state->fb;
+	struct qxl_crtc *qcrtc = to_qxl_crtc(plane->state->crtc);
 	struct qxl_release *release;
 	struct qxl_cursor_cmd *cmd;
 	struct qxl_cursor *cursor;
 	struct drm_gem_object *obj;
-	struct qxl_bo *cursor_bo, *user_bo = NULL;
+	struct qxl_bo *cursor_bo = NULL, *user_bo = NULL;
 	int ret;
 	void *user_ptr;
 	int size = 64*64*4;
@@ -628,6 +683,10 @@ static void qxl_cursor_atomic_update(struct drm_plane *plane,
 		cmd->u.set.shape = qxl_bo_physical_address(qdev,
 							   cursor_bo, 0);
 		cmd->type = QXL_CURSOR_SET;
+
+		qxl_bo_unref(&qcrtc->cursor_bo);
+		qcrtc->cursor_bo = cursor_bo;
+		cursor_bo = NULL;
 	} else {
 
 		ret = qxl_release_reserve_list(release, true);
@@ -645,6 +704,8 @@ static void qxl_cursor_atomic_update(struct drm_plane *plane,
 	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 	qxl_release_fence_buffer_objects(release);
 
+	qxl_bo_unref(&cursor_bo);
+
 	return;
 
 out_backoff:
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index 08752c0ffb35..00a1a66b052a 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -111,6 +111,8 @@ struct qxl_bo_list {
 struct qxl_crtc {
 	struct drm_crtc base;
 	int index;
+
+	struct qxl_bo *cursor_bo;
 };
 
 struct qxl_output {
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index 31effed4a3c8..e8c0b1037230 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -309,6 +309,7 @@ static int qxl_update_area_ioctl(struct drm_device *dev, void *data,
 	int ret;
 	struct drm_gem_object *gobj = NULL;
 	struct qxl_bo *qobj = NULL;
+	struct ttm_operation_ctx ctx = { true, false };
 
 	if (update_area->left >= update_area->right ||
 	    update_area->top >= update_area->bottom)
@@ -326,8 +327,7 @@ static int qxl_update_area_ioctl(struct drm_device *dev, void *data,
 
 	if (!qobj->pin_count) {
 		qxl_ttm_placement_from_domain(qobj, qobj->type, false);
-		ret = ttm_bo_validate(&qobj->tbo, &qobj->placement,
-				      true, false);
+		ret = ttm_bo_validate(&qobj->tbo, &qobj->placement, &ctx);
 		if (unlikely(ret))
 			goto out;
 	}
diff --git a/drivers/gpu/drm/qxl/qxl_object.c b/drivers/gpu/drm/qxl/qxl_object.c
index 0a67ddf19c3d..f6b80fe47d1f 100644
--- a/drivers/gpu/drm/qxl/qxl_object.c
+++ b/drivers/gpu/drm/qxl/qxl_object.c
@@ -223,6 +223,7 @@ struct qxl_bo *qxl_bo_ref(struct qxl_bo *bo)
 
 static int __qxl_bo_pin(struct qxl_bo *bo, u32 domain, u64 *gpu_addr)
 {
+	struct ttm_operation_ctx ctx = { false, false };
 	struct drm_device *ddev = bo->gem_base.dev;
 	int r;
 
@@ -233,7 +234,7 @@ static int __qxl_bo_pin(struct qxl_bo *bo, u32 domain, u64 *gpu_addr)
 		return 0;
 	}
 	qxl_ttm_placement_from_domain(bo, domain, true);
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (likely(r == 0)) {
 		bo->pin_count = 1;
 		if (gpu_addr != NULL)
@@ -246,6 +247,7 @@ static int __qxl_bo_pin(struct qxl_bo *bo, u32 domain, u64 *gpu_addr)
 
 static int __qxl_bo_unpin(struct qxl_bo *bo)
 {
+	struct ttm_operation_ctx ctx = { false, false };
 	struct drm_device *ddev = bo->gem_base.dev;
 	int r, i;
 
@@ -258,7 +260,7 @@ static int __qxl_bo_unpin(struct qxl_bo *bo)
 		return 0;
 	for (i = 0; i < bo->placement.num_placement; i++)
 		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (unlikely(r != 0))
 		dev_err(ddev->dev, "%p validate failed for unpin\n", bo);
 	return r;
diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index a6da6fa6ad58..b223c8d0a491 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -230,12 +230,12 @@ int qxl_release_list_add(struct qxl_release *release, struct qxl_bo *bo)
 
 static int qxl_release_validate_bo(struct qxl_bo *bo)
 {
+	struct ttm_operation_ctx ctx = { true, false };
 	int ret;
 
 	if (!bo->pin_count) {
 		qxl_ttm_placement_from_domain(bo, bo->type, false);
-		ret = ttm_bo_validate(&bo->tbo, &bo->placement,
-				      true, false);
+		ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		if (ret)
 			return ret;
 	}
@@ -468,7 +468,7 @@ void qxl_release_fence_buffer_objects(struct qxl_release *release)
 
 		reservation_object_add_shared_fence(bo->resv, &release->base);
 		ttm_bo_add_to_lru(bo);
-		__ttm_bo_unreserve(bo);
+		reservation_object_unlock(bo->resv);
 	}
 	spin_unlock(&glob->lru_lock);
 	ww_acquire_fini(&release->ticket);
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index ab4823875311..59cd74c3f3af 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -123,11 +123,8 @@ int qxl_mmap(struct file *filp, struct vm_area_struct *vma)
 	struct qxl_device *qdev;
 	int r;
 
-	if (unlikely(vma->vm_pgoff < DRM_FILE_PAGE_OFFSET)) {
-		pr_info("%s: vma->vm_pgoff (%ld) < DRM_FILE_PAGE_OFFSET\n",
-			__func__, vma->vm_pgoff);
+	if (unlikely(vma->vm_pgoff < DRM_FILE_PAGE_OFFSET))
 		return -EINVAL;
-	}
 
 	file_priv = filp->private_data;
 	qdev = file_priv->minor->dev->dev_private;
@@ -294,14 +291,15 @@ static struct ttm_backend_func qxl_backend_func = {
 	.destroy = &qxl_ttm_backend_destroy,
 };
 
-static int qxl_ttm_tt_populate(struct ttm_tt *ttm)
+static int qxl_ttm_tt_populate(struct ttm_tt *ttm,
+			struct ttm_operation_ctx *ctx)
 {
 	int r;
 
 	if (ttm->state != tt_unpopulated)
 		return 0;
 
-	r = ttm_pool_populate(ttm);
+	r = ttm_pool_populate(ttm, ctx);
 	if (r)
 		return r;
 
@@ -344,15 +342,14 @@ static void qxl_move_null(struct ttm_buffer_object *bo,
 	new_mem->mm_node = NULL;
 }
 
-static int qxl_bo_move(struct ttm_buffer_object *bo,
-		       bool evict, bool interruptible,
-		       bool no_wait_gpu,
+static int qxl_bo_move(struct ttm_buffer_object *bo, bool evict,
+		       struct ttm_operation_ctx *ctx,
 		       struct ttm_mem_reg *new_mem)
 {
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	int ret;
 
-	ret = ttm_bo_wait(bo, interruptible, no_wait_gpu);
+	ret = ttm_bo_wait(bo, ctx->interruptible, ctx->no_wait_gpu);
 	if (ret)
 		return ret;
 
@@ -361,8 +358,7 @@ static int qxl_bo_move(struct ttm_buffer_object *bo,
 		qxl_move_null(bo, new_mem);
 		return 0;
 	}
-	return ttm_bo_move_memcpy(bo, interruptible, no_wait_gpu,
-				  new_mem);
+	return ttm_bo_move_memcpy(bo, ctx, new_mem);
 }
 
 static void qxl_bo_move_notify(struct ttm_buffer_object *bo,
@@ -393,7 +389,6 @@ static struct ttm_bo_driver qxl_bo_driver = {
 	.verify_access = &qxl_verify_access,
 	.io_mem_reserve = &qxl_ttm_io_mem_reserve,
 	.io_mem_free = &qxl_ttm_io_mem_free,
-	.io_mem_pfn = ttm_bo_default_io_mem_pfn,
 	.move_notify = &qxl_bo_move_notify,
 };