Merge tag 'drm-next-2018-10-24' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This is going to rebuild more than drm as it adds a new helper to
  list.h for doing bulk updates. Seemed like a reasonable addition to
  me.

  Otherwise the usual merge window stuff lots of i915 and amdgpu, not so
  much nouveau, and piles of everything else.

  Core:
   - Adds a new list.h helper for doing bulk list updates for TTM.
   - Don't leak fb address in smem_start to userspace (comes with EXPORT
     workaround for people using mali out of tree hacks)
   - udmabuf device to turn memfd regions into dma-buf
   - Per-plane blend mode property
   - ref/unref replacements with get/put
   - fbdev conflicting framebuffers code cleaned up
   - host-endian format variants
   - panel orientation quirk for Acer One 10

  bridge:
   - TI SN65DSI86 chip support

  vkms:
   - GEM support.
   - Cursor support

  amdgpu:
   - Merge amdkfd and amdgpu into one module
   - CEC over DP AUX support
   - Picasso APU support + VCN dynamic powergating
   - Raven2 APU support
   - Vega20 enablement + kfd support
   - ACP powergating improvements
   - ABGR/XBGR display support
   - VCN jpeg support
   - xGMI support
   - DC i2c/aux cleanup
   - Ycbcr 4:2:0 support
   - GPUVM improvements
   - Powerplay and powerplay endian fixes
   - Display underflow fixes

  vmwgfx:
   - Move vmwgfx specific TTM code to vmwgfx
   - Split out vmwgfx buffer/resource validation code
   - Atomic operation rework

  bochs:
   - use more helpers
   - format/byteorder improvements

  qxl:
   - use more helpers

  i915:
   - GGTT coherency getparam
   - Turn off resource streamer API
   - More Icelake enablement + DMC firmware
   - Full PPGTT for Ivybridge, Haswell and Valleyview
   - DDB distribution based on resolution
   - Limited range DP display support

  nouveau:
   - CEC over DP AUX support
   - Initial HDMI 2.0 support

  virtio-gpu:
   - vmap support for PRIME objects

  tegra:
   - Initial Tegra194 support
   - DMA/IOMMU integration fixes

  msm:
   - a6xx perf improvements + clock prefix
   - GPU preemption optimisations
   - a6xx devfreq support
   - cursor support

  rockchip:
   - PX30 support
   - rgb output interface support

  mediatek:
   - HDMI output support on mt2701 and mt7623

  rcar-du:
   - Interlaced modes on Gen3
   - LVDS on R8A77980
   - D3 and E3 SoC support

  hisilicon:
   - misc fixes

  mxsfb:
   - runtime pm support

  sun4i:
   - R40 TCON support
   - Allwinner A64 support
   - R40 HDMI support

  omapdrm:
   - Driver rework changing display pipeline ordering to use common code
   - DMM memory barrier and irq fixes
   - Errata workarounds

  exynos:
   - out-bridge support for LVDS bridge driver
   - Samsung 16x16 tiled format support
   - Plane alpha and pixel blend mode support

  tilcdc:
   - suspend/resume update

  mali-dp:
   - misc updates"

* tag 'drm-next-2018-10-24' of git://anongit.freedesktop.org/drm/drm: (1382 commits)
  firmware/dmc/icl: Add missing MODULE_FIRMWARE() for Icelake.
  drm/i915/icl: Fix signal_levels
  drm/i915/icl: Fix DDI/TC port clk_off bits
  drm/i915/icl: create function to identify combophy port
  drm/i915/gen9+: Fix initial readout for Y tiled framebuffers
  drm/i915: Large page offsets for pread/pwrite
  drm/i915/selftests: Disable shrinker across mmap-exhaustion
  drm/i915/dp: Link train Fallback on eDP only if fallback link BW can fit panel's native mode
  drm/i915: Fix intel_dp_mst_best_encoder()
  drm/i915: Skip vcpi allocation for MSTB ports that are gone
  drm/i915: Don't unset intel_connector->mst_port
  drm/i915: Only reset seqno if actually idle
  drm/i915: Use the correct crtc when sanitizing plane mapping
  drm/i915: Restore vblank interrupts earlier
  drm/i915: Check fb stride against plane max stride
  drm/amdgpu/vcn:Fix uninitialized symbol error
  drm: panel-orientation-quirks: Add quirk for Acer One 10 (S1003)
  drm/amd/amdgpu: Fix debugfs error handling
  drm/amdgpu: Update gc_9_0 golden settings.
  drm/amd/powerplay: update PPtable with DC BTC and Tvr SocLimit fields
  ...

11 files changed, 136 insertions, 174 deletions

diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c
index 25503b933599..8f8fed471e34 100644
--- a/drivers/gpu/drm/virtio/virtgpu_display.c
+++ b/drivers/gpu/drm/virtio/virtgpu_display.c
@@ -75,12 +75,9 @@ virtio_gpu_framebuffer_init(struct drm_device *dev,
 			    struct drm_gem_object *obj)
 {
 	int ret;
-	struct virtio_gpu_object *bo;
 
 	vgfb->base.obj[0] = obj;
 
-	bo = gem_to_virtio_gpu_obj(obj);
-
 	drm_helper_mode_fill_fb_struct(dev, &vgfb->base, mode_cmd);
 
 	ret = drm_framebuffer_init(dev, &vgfb->base, &virtio_gpu_fb_funcs);
@@ -109,6 +106,9 @@ static void virtio_gpu_crtc_mode_set_nofb(struct drm_crtc *crtc)
 static void virtio_gpu_crtc_atomic_enable(struct drm_crtc *crtc,
 					  struct drm_crtc_state *old_state)
 {
+	struct virtio_gpu_output *output = drm_crtc_to_virtio_gpu_output(crtc);
+
+	output->enabled = true;
 }
 
 static void virtio_gpu_crtc_atomic_disable(struct drm_crtc *crtc,
@@ -119,6 +119,7 @@ static void virtio_gpu_crtc_atomic_disable(struct drm_crtc *crtc,
 	struct virtio_gpu_output *output = drm_crtc_to_virtio_gpu_output(crtc);
 
 	virtio_gpu_cmd_set_scanout(vgdev, output->index, 0, 0, 0, 0, 0);
+	output->enabled = false;
 }
 
 static int virtio_gpu_crtc_atomic_check(struct drm_crtc *crtc,
@@ -306,6 +307,10 @@ virtio_gpu_user_framebuffer_create(struct drm_device *dev,
 	struct virtio_gpu_framebuffer *virtio_gpu_fb;
 	int ret;
 
+	if (mode_cmd->pixel_format != DRM_FORMAT_HOST_XRGB8888 &&
+	    mode_cmd->pixel_format != DRM_FORMAT_HOST_ARGB8888)
+		return ERR_PTR(-ENOENT);
+
 	/* lookup object associated with res handle */
 	obj = drm_gem_object_lookup(file_priv, mode_cmd->handles[0]);
 	if (!obj)
@@ -354,6 +359,7 @@ int virtio_gpu_modeset_init(struct virtio_gpu_device *vgdev)
 	int i;
 
 	drm_mode_config_init(vgdev->ddev);
+	vgdev->ddev->mode_config.quirk_addfb_prefer_host_byte_order = true;
 	vgdev->ddev->mode_config.funcs = &virtio_gpu_mode_funcs;
 	vgdev->ddev->mode_config.helper_private = &virtio_mode_config_helpers;
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_drm_bus.c b/drivers/gpu/drm/virtio/virtgpu_drm_bus.c
index 7df8d0c9026a..757ca28ab93e 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drm_bus.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drm_bus.c
@@ -28,26 +28,6 @@
 
 #include "virtgpu_drv.h"
 
-static void virtio_pci_kick_out_firmware_fb(struct pci_dev *pci_dev)
-{
-	struct apertures_struct *ap;
-	bool primary;
-
-	ap = alloc_apertures(1);
-	if (!ap)
-		return;
-
-	ap->ranges[0].base = pci_resource_start(pci_dev, 0);
-	ap->ranges[0].size = pci_resource_len(pci_dev, 0);
-
-	primary = pci_dev->resource[PCI_ROM_RESOURCE].flags
-		& IORESOURCE_ROM_SHADOW;
-
-	drm_fb_helper_remove_conflicting_framebuffers(ap, "virtiodrmfb", primary);
-
-	kfree(ap);
-}
-
 int drm_virtio_init(struct drm_driver *driver, struct virtio_device *vdev)
 {
 	struct drm_device *dev;
@@ -69,7 +49,9 @@ int drm_virtio_init(struct drm_driver *driver, struct virtio_device *vdev)
 			 pname);
 		dev->pdev = pdev;
 		if (vga)
-			virtio_pci_kick_out_firmware_fb(pdev);
+			drm_fb_helper_remove_conflicting_pci_framebuffers(pdev,
+									  0,
+									  "virtiodrmfb");
 
 		snprintf(unique, sizeof(unique), "pci:%s", pname);
 		ret = drm_dev_set_unique(dev, unique);
@@ -85,6 +67,6 @@ int drm_virtio_init(struct drm_driver *driver, struct virtio_device *vdev)
 	return 0;
 
 err_free:
-	drm_dev_unref(dev);
+	drm_dev_put(dev);
 	return ret;
 }
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index 65605e207bbe..d29f0c7c768c 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -36,6 +36,7 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_encoder.h>
+#include <drm/drm_fb_helper.h>
 #include <drm/ttm/ttm_bo_api.h>
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_placement.h>
@@ -57,6 +58,7 @@ struct virtio_gpu_object {
 	uint32_t hw_res_handle;
 
 	struct sg_table *pages;
+	uint32_t mapped;
 	void *vmap;
 	bool dumb;
 	struct ttm_place                placement_code;
@@ -114,6 +116,7 @@ struct virtio_gpu_output {
 	struct virtio_gpu_update_cursor cursor;
 	int cur_x;
 	int cur_y;
+	bool enabled;
 };
 #define drm_crtc_to_virtio_gpu_output(x) \
 	container_of(x, struct virtio_gpu_output, crtc)
@@ -131,6 +134,13 @@ struct virtio_gpu_framebuffer {
 #define to_virtio_gpu_framebuffer(x) \
 	container_of(x, struct virtio_gpu_framebuffer, base)
 
+struct virtio_gpu_fbdev {
+	struct drm_fb_helper           helper;
+	struct virtio_gpu_framebuffer  vgfb;
+	struct virtio_gpu_device       *vgdev;
+	struct delayed_work            work;
+};
+
 struct virtio_gpu_mman {
 	struct ttm_bo_global_ref        bo_global_ref;
 	struct drm_global_reference	mem_global_ref;
@@ -260,7 +270,8 @@ void virtio_gpu_cmd_create_resource(struct virtio_gpu_device *vgdev,
 void virtio_gpu_cmd_unref_resource(struct virtio_gpu_device *vgdev,
 				   uint32_t resource_id);
 void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev,
-					uint32_t resource_id, uint64_t offset,
+					struct virtio_gpu_object *bo,
+					uint64_t offset,
 					__le32 width, __le32 height,
 					__le32 x, __le32 y,
 					struct virtio_gpu_fence **fence);
@@ -276,13 +287,13 @@ int virtio_gpu_object_attach(struct virtio_gpu_device *vgdev,
 			     struct virtio_gpu_object *obj,
 			     uint32_t resource_id,
 			     struct virtio_gpu_fence **fence);
+void virtio_gpu_object_detach(struct virtio_gpu_device *vgdev,
+			      struct virtio_gpu_object *obj);
 int virtio_gpu_attach_status_page(struct virtio_gpu_device *vgdev);
 int virtio_gpu_detach_status_page(struct virtio_gpu_device *vgdev);
 void virtio_gpu_cursor_ping(struct virtio_gpu_device *vgdev,
 			    struct virtio_gpu_output *output);
 int virtio_gpu_cmd_get_display_info(struct virtio_gpu_device *vgdev);
-void virtio_gpu_cmd_resource_inval_backing(struct virtio_gpu_device *vgdev,
-					   uint32_t resource_id);
 int virtio_gpu_cmd_get_capset_info(struct virtio_gpu_device *vgdev, int idx);
 int virtio_gpu_cmd_get_capset(struct virtio_gpu_device *vgdev,
 			      int idx, int version,
@@ -306,7 +317,8 @@ void virtio_gpu_cmd_transfer_from_host_3d(struct virtio_gpu_device *vgdev,
 					  struct virtio_gpu_box *box,
 					  struct virtio_gpu_fence **fence);
 void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev,
-					uint32_t resource_id, uint32_t ctx_id,
+					struct virtio_gpu_object *bo,
+					uint32_t ctx_id,
 					uint64_t offset, uint32_t level,
 					struct virtio_gpu_box *box,
 					struct virtio_gpu_fence **fence);
@@ -351,7 +363,8 @@ void virtio_gpu_fence_event_process(struct virtio_gpu_device *vdev,
 int virtio_gpu_object_create(struct virtio_gpu_device *vgdev,
 			     unsigned long size, bool kernel, bool pinned,
 			     struct virtio_gpu_object **bo_ptr);
-int virtio_gpu_object_kmap(struct virtio_gpu_object *bo, void **ptr);
+void virtio_gpu_object_kunmap(struct virtio_gpu_object *bo);
+int virtio_gpu_object_kmap(struct virtio_gpu_object *bo);
 int virtio_gpu_object_get_sg_table(struct virtio_gpu_device *qdev,
 				   struct virtio_gpu_object *bo);
 void virtio_gpu_object_free_sg_table(struct virtio_gpu_object *bo);
@@ -372,7 +385,7 @@ int virtgpu_gem_prime_mmap(struct drm_gem_object *obj,
 static inline struct virtio_gpu_object*
 virtio_gpu_object_ref(struct virtio_gpu_object *bo)
 {
-	ttm_bo_reference(&bo->tbo);
+	ttm_bo_get(&bo->tbo);
 	return bo;
 }
 
@@ -383,9 +396,8 @@ static inline void virtio_gpu_object_unref(struct virtio_gpu_object **bo)
 	if ((*bo) == NULL)
 		return;
 	tbo = &((*bo)->tbo);
-	ttm_bo_unref(&tbo);
-	if (tbo == NULL)
-		*bo = NULL;
+	ttm_bo_put(tbo);
+	*bo = NULL;
 }
 
 static inline u64 virtio_gpu_object_mmap_offset(struct virtio_gpu_object *bo)
diff --git a/drivers/gpu/drm/virtio/virtgpu_fb.c b/drivers/gpu/drm/virtio/virtgpu_fb.c
index a121b1c79522..cea749f4ec39 100644
--- a/drivers/gpu/drm/virtio/virtgpu_fb.c
+++ b/drivers/gpu/drm/virtio/virtgpu_fb.c
@@ -29,13 +29,6 @@
 
 #define VIRTIO_GPU_FBCON_POLL_PERIOD (HZ / 60)
 
-struct virtio_gpu_fbdev {
-	struct drm_fb_helper           helper;
-	struct virtio_gpu_framebuffer  vgfb;
-	struct virtio_gpu_device       *vgdev;
-	struct delayed_work            work;
-};
-
 static int virtio_gpu_dirty_update(struct virtio_gpu_framebuffer *fb,
 				   bool store, int x, int y,
 				   int width, int height)
@@ -102,7 +95,7 @@ static int virtio_gpu_dirty_update(struct virtio_gpu_framebuffer *fb,
 
 		offset = (y * fb->base.pitches[0]) + x * bpp;
 
-		virtio_gpu_cmd_transfer_to_host_2d(vgdev, obj->hw_res_handle,
+		virtio_gpu_cmd_transfer_to_host_2d(vgdev, obj,
 						   offset,
 						   cpu_to_le32(w),
 						   cpu_to_le32(h),
@@ -210,12 +203,6 @@ static struct fb_ops virtio_gpufb_ops = {
 	.fb_imageblit = virtio_gpu_3d_imageblit,
 };
 
-static int virtio_gpu_vmap_fb(struct virtio_gpu_device *vgdev,
-			      struct virtio_gpu_object *obj)
-{
-	return virtio_gpu_object_kmap(obj, NULL);
-}
-
 static int virtio_gpufb_create(struct drm_fb_helper *helper,
 			       struct drm_fb_helper_surface_size *sizes)
 {
@@ -233,7 +220,7 @@ static int virtio_gpufb_create(struct drm_fb_helper *helper,
 	mode_cmd.width = sizes->surface_width;
 	mode_cmd.height = sizes->surface_height;
 	mode_cmd.pitches[0] = mode_cmd.width * 4;
-	mode_cmd.pixel_format = drm_mode_legacy_fb_format(32, 24);
+	mode_cmd.pixel_format = DRM_FORMAT_HOST_XRGB8888;
 
 	format = virtio_gpu_translate_format(mode_cmd.pixel_format);
 	if (format == 0)
@@ -248,9 +235,9 @@ static int virtio_gpufb_create(struct drm_fb_helper *helper,
 	virtio_gpu_cmd_create_resource(vgdev, resid, format,
 				       mode_cmd.width, mode_cmd.height);
 
-	ret = virtio_gpu_vmap_fb(vgdev, obj);
+	ret = virtio_gpu_object_kmap(obj);
 	if (ret) {
-		DRM_ERROR("failed to vmap fb %d\n", ret);
+		DRM_ERROR("failed to kmap fb %d\n", ret);
 		goto err_obj_vmap;
 	}
 
@@ -291,7 +278,7 @@ static int virtio_gpufb_create(struct drm_fb_helper *helper,
 	return 0;
 
 err_fb_alloc:
-	virtio_gpu_cmd_resource_inval_backing(vgdev, resid);
+	virtio_gpu_object_detach(vgdev, obj);
 err_obj_attach:
 err_obj_vmap:
 	virtio_gpu_gem_free_object(&obj->gem_base);
diff --git a/drivers/gpu/drm/virtio/virtgpu_gem.c b/drivers/gpu/drm/virtio/virtgpu_gem.c
index 0f2768eacaee..82c817f37cf7 100644
--- a/drivers/gpu/drm/virtio/virtgpu_gem.c
+++ b/drivers/gpu/drm/virtio/virtgpu_gem.c
@@ -90,7 +90,10 @@ int virtio_gpu_mode_dumb_create(struct drm_file *file_priv,
 	uint32_t resid;
 	uint32_t format;
 
-	pitch = args->width * ((args->bpp + 1) / 8);
+	if (args->bpp != 32)
+		return -EINVAL;
+
+	pitch = args->width * 4;
 	args->size = pitch * args->height;
 	args->size = ALIGN(args->size, PAGE_SIZE);
 
@@ -99,7 +102,7 @@ int virtio_gpu_mode_dumb_create(struct drm_file *file_priv,
 	if (ret)
 		goto fail;
 
-	format = virtio_gpu_translate_format(DRM_FORMAT_XRGB8888);
+	format = virtio_gpu_translate_format(DRM_FORMAT_HOST_XRGB8888);
 	virtio_gpu_resource_id_get(vgdev, &resid);
 	virtio_gpu_cmd_create_resource(vgdev, resid, format,
 				       args->width, args->height);
diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
index 7bdf6f0e58a5..f16b875d6a46 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
@@ -429,11 +429,11 @@ static int virtio_gpu_transfer_to_host_ioctl(struct drm_device *dev, void *data,
 	convert_to_hw_box(&box, &args->box);
 	if (!vgdev->has_virgl_3d) {
 		virtio_gpu_cmd_transfer_to_host_2d
-			(vgdev, qobj->hw_res_handle, offset,
+			(vgdev, qobj, offset,
 			 box.w, box.h, box.x, box.y, NULL);
 	} else {
 		virtio_gpu_cmd_transfer_to_host_3d
-			(vgdev, qobj->hw_res_handle,
+			(vgdev, qobj,
 			 vfpriv ? vfpriv->ctx_id : 0, offset,
 			 args->level, &box, &fence);
 		reservation_object_add_excl_fence(qobj->tbo.resv,
diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c
index 9f2f470efd9b..eca765537470 100644
--- a/drivers/gpu/drm/virtio/virtgpu_object.c
+++ b/drivers/gpu/drm/virtio/virtgpu_object.c
@@ -37,6 +37,8 @@ static void virtio_gpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 		virtio_gpu_cmd_unref_resource(vgdev, bo->hw_res_handle);
 	if (bo->pages)
 		virtio_gpu_object_free_sg_table(bo);
+	if (bo->vmap)
+		virtio_gpu_object_kunmap(bo);
 	drm_gem_object_release(&bo->gem_base);
 	kfree(bo);
 }
@@ -99,22 +101,23 @@ int virtio_gpu_object_create(struct virtio_gpu_device *vgdev,
 	return 0;
 }
 
-int virtio_gpu_object_kmap(struct virtio_gpu_object *bo, void **ptr)
+void virtio_gpu_object_kunmap(struct virtio_gpu_object *bo)
+{
+	bo->vmap = NULL;
+	ttm_bo_kunmap(&bo->kmap);
+}
+
+int virtio_gpu_object_kmap(struct virtio_gpu_object *bo)
 {
 	bool is_iomem;
 	int r;
 
-	if (bo->vmap) {
-		if (ptr)
-			*ptr = bo->vmap;
-		return 0;
-	}
+	WARN_ON(bo->vmap);
+
 	r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.num_pages, &bo->kmap);
 	if (r)
 		return r;
 	bo->vmap = ttm_kmap_obj_virtual(&bo->kmap, &is_iomem);
-	if (ptr)
-		*ptr = bo->vmap;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c
index dc5b5b2b7aab..a9f4ae7d4483 100644
--- a/drivers/gpu/drm/virtio/virtgpu_plane.c
+++ b/drivers/gpu/drm/virtio/virtgpu_plane.c
@@ -28,22 +28,11 @@
 #include <drm/drm_atomic_helper.h>
 
 static const uint32_t virtio_gpu_formats[] = {
-	DRM_FORMAT_XRGB8888,
-	DRM_FORMAT_ARGB8888,
-	DRM_FORMAT_BGRX8888,
-	DRM_FORMAT_BGRA8888,
-	DRM_FORMAT_RGBX8888,
-	DRM_FORMAT_RGBA8888,
-	DRM_FORMAT_XBGR8888,
-	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_HOST_XRGB8888,
 };
 
 static const uint32_t virtio_gpu_cursor_formats[] = {
-#ifdef __BIG_ENDIAN
-	DRM_FORMAT_BGRA8888,
-#else
-	DRM_FORMAT_ARGB8888,
-#endif
+	DRM_FORMAT_HOST_ARGB8888,
 };
 
 uint32_t virtio_gpu_translate_format(uint32_t drm_fourcc)
@@ -51,32 +40,6 @@ uint32_t virtio_gpu_translate_format(uint32_t drm_fourcc)
 	uint32_t format;
 
 	switch (drm_fourcc) {
-#ifdef __BIG_ENDIAN
-	case DRM_FORMAT_XRGB8888:
-		format = VIRTIO_GPU_FORMAT_X8R8G8B8_UNORM;
-		break;
-	case DRM_FORMAT_ARGB8888:
-		format = VIRTIO_GPU_FORMAT_A8R8G8B8_UNORM;
-		break;
-	case DRM_FORMAT_BGRX8888:
-		format = VIRTIO_GPU_FORMAT_B8G8R8X8_UNORM;
-		break;
-	case DRM_FORMAT_BGRA8888:
-		format = VIRTIO_GPU_FORMAT_B8G8R8A8_UNORM;
-		break;
-	case DRM_FORMAT_RGBX8888:
-		format = VIRTIO_GPU_FORMAT_R8G8B8X8_UNORM;
-		break;
-	case DRM_FORMAT_RGBA8888:
-		format = VIRTIO_GPU_FORMAT_R8G8B8A8_UNORM;
-		break;
-	case DRM_FORMAT_XBGR8888:
-		format = VIRTIO_GPU_FORMAT_X8B8G8R8_UNORM;
-		break;
-	case DRM_FORMAT_ABGR8888:
-		format = VIRTIO_GPU_FORMAT_A8B8G8R8_UNORM;
-		break;
-#else
 	case DRM_FORMAT_XRGB8888:
 		format = VIRTIO_GPU_FORMAT_B8G8R8X8_UNORM;
 		break;
@@ -89,19 +52,6 @@ uint32_t virtio_gpu_translate_format(uint32_t drm_fourcc)
 	case DRM_FORMAT_BGRA8888:
 		format = VIRTIO_GPU_FORMAT_A8R8G8B8_UNORM;
 		break;
-	case DRM_FORMAT_RGBX8888:
-		format = VIRTIO_GPU_FORMAT_X8B8G8R8_UNORM;
-		break;
-	case DRM_FORMAT_RGBA8888:
-		format = VIRTIO_GPU_FORMAT_A8B8G8R8_UNORM;
-		break;
-	case DRM_FORMAT_XBGR8888:
-		format = VIRTIO_GPU_FORMAT_R8G8B8X8_UNORM;
-		break;
-	case DRM_FORMAT_ABGR8888:
-		format = VIRTIO_GPU_FORMAT_R8G8B8A8_UNORM;
-		break;
-#endif
 	default:
 		/*
 		 * This should not happen, we handle everything listed
@@ -152,13 +102,13 @@ static void virtio_gpu_primary_plane_update(struct drm_plane *plane,
 	if (WARN_ON(!output))
 		return;
 
-	if (plane->state->fb) {
+	if (plane->state->fb && output->enabled) {
 		vgfb = to_virtio_gpu_framebuffer(plane->state->fb);
 		bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
 		handle = bo->hw_res_handle;
 		if (bo->dumb) {
 			virtio_gpu_cmd_transfer_to_host_2d
-				(vgdev, handle, 0,
+				(vgdev, bo, 0,
 				 cpu_to_le32(plane->state->src_w >> 16),
 				 cpu_to_le32(plane->state->src_h >> 16),
 				 cpu_to_le32(plane->state->src_x >> 16),
@@ -217,7 +167,7 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane,
 	if (bo && bo->dumb && (plane->state->fb != old_state->fb)) {
 		/* new cursor -- update & wait */
 		virtio_gpu_cmd_transfer_to_host_2d
-			(vgdev, handle, 0,
+			(vgdev, bo, 0,
 			 cpu_to_le32(plane->state->crtc_w),
 			 cpu_to_le32(plane->state->crtc_h),
 			 0, 0, &fence);
diff --git a/drivers/gpu/drm/virtio/virtgpu_prime.c b/drivers/gpu/drm/virtio/virtgpu_prime.c
index d27a1688714f..86ce0ae93f59 100644
--- a/drivers/gpu/drm/virtio/virtgpu_prime.c
+++ b/drivers/gpu/drm/virtio/virtgpu_prime.c
@@ -55,13 +55,18 @@ struct drm_gem_object *virtgpu_gem_prime_import_sg_table(
 
 void *virtgpu_gem_prime_vmap(struct drm_gem_object *obj)
 {
-	WARN_ONCE(1, "not implemented");
-	return ERR_PTR(-ENODEV);
+	struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(obj);
+	int ret;
+
+	ret = virtio_gpu_object_kmap(bo);
+	if (ret)
+		return NULL;
+	return bo->vmap;
 }
 
 void virtgpu_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 {
-	WARN_ONCE(1, "not implemented");
+	virtio_gpu_object_kunmap(gem_to_virtio_gpu_obj(obj));
 }
 
 int virtgpu_gem_prime_mmap(struct drm_gem_object *obj,
diff --git a/drivers/gpu/drm/virtio/virtgpu_ttm.c b/drivers/gpu/drm/virtio/virtgpu_ttm.c
index 11f8ae5b5332..e3152d45c5f1 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ttm.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ttm.c
@@ -106,29 +106,6 @@ static void virtio_gpu_ttm_global_fini(struct virtio_gpu_device *vgdev)
 	}
 }
 
-#if 0
-/*
- * Hmm, seems to not do anything useful.  Leftover debug hack?
- * Something like printing pagefaults to kernel log?
- */
-static struct vm_operations_struct virtio_gpu_ttm_vm_ops;
-static const struct vm_operations_struct *ttm_vm_ops;
-
-static int virtio_gpu_ttm_fault(struct vm_fault *vmf)
-{
-	struct ttm_buffer_object *bo;
-	struct virtio_gpu_device *vgdev;
-	int r;
-
-	bo = (struct ttm_buffer_object *)vmf->vma->vm_private_data;
-	if (bo == NULL)
-		return VM_FAULT_NOPAGE;
-	vgdev = virtio_gpu_get_vgdev(bo->bdev);
-	r = ttm_vm_ops->fault(vmf);
-	return r;
-}
-#endif
-
 int virtio_gpu_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct drm_file *file_priv;
@@ -143,19 +120,8 @@ int virtio_gpu_mmap(struct file *filp, struct vm_area_struct *vma)
 		return -EINVAL;
 	}
 	r = ttm_bo_mmap(filp, vma, &vgdev->mman.bdev);
-#if 0
-	if (unlikely(r != 0))
-		return r;
-	if (unlikely(ttm_vm_ops == NULL)) {
-		ttm_vm_ops = vma->vm_ops;
-		virtio_gpu_ttm_vm_ops = *ttm_vm_ops;
-		virtio_gpu_ttm_vm_ops.fault = &virtio_gpu_ttm_fault;
-	}
-	vma->vm_ops = &virtio_gpu_ttm_vm_ops;
-	return 0;
-#else
+
 	return r;
-#endif
 }
 
 static int virtio_gpu_invalidate_caches(struct ttm_bo_device *bdev,
@@ -377,8 +343,7 @@ static void virtio_gpu_bo_move_notify(struct ttm_buffer_object *tbo,
 
 	if (!new_mem || (new_mem->placement & TTM_PL_FLAG_SYSTEM)) {
 		if (bo->hw_res_handle)
-			virtio_gpu_cmd_resource_inval_backing(vgdev,
-							   bo->hw_res_handle);
+			virtio_gpu_object_detach(vgdev, bo);
 
 	} else if (new_mem->placement & TTM_PL_FLAG_TT) {
 		if (bo->hw_res_handle) {
diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index 020070d483d3..4e2e037aed34 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -423,8 +423,9 @@ void virtio_gpu_cmd_unref_resource(struct virtio_gpu_device *vgdev,
 	virtio_gpu_queue_ctrl_buffer(vgdev, vbuf);
 }
 
-void virtio_gpu_cmd_resource_inval_backing(struct virtio_gpu_device *vgdev,
-					   uint32_t resource_id)
+static void virtio_gpu_cmd_resource_inval_backing(struct virtio_gpu_device *vgdev,
+						  uint32_t resource_id,
+						  struct virtio_gpu_fence **fence)
 {
 	struct virtio_gpu_resource_detach_backing *cmd_p;
 	struct virtio_gpu_vbuffer *vbuf;
@@ -435,7 +436,7 @@ void virtio_gpu_cmd_resource_inval_backing(struct virtio_gpu_device *vgdev,
 	cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_RESOURCE_DETACH_BACKING);
 	cmd_p->resource_id = cpu_to_le32(resource_id);
 
-	virtio_gpu_queue_ctrl_buffer(vgdev, vbuf);
+	virtio_gpu_queue_fenced_ctrl_buffer(vgdev, vbuf, &cmd_p->hdr, fence);
 }
 
 void virtio_gpu_cmd_set_scanout(struct virtio_gpu_device *vgdev,
@@ -482,19 +483,26 @@ void virtio_gpu_cmd_resource_flush(struct virtio_gpu_device *vgdev,
 }
 
 void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev,
-					uint32_t resource_id, uint64_t offset,
+					struct virtio_gpu_object *bo,
+					uint64_t offset,
 					__le32 width, __le32 height,
 					__le32 x, __le32 y,
 					struct virtio_gpu_fence **fence)
 {
 	struct virtio_gpu_transfer_to_host_2d *cmd_p;
 	struct virtio_gpu_vbuffer *vbuf;
+	bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
+
+	if (use_dma_api)
+		dma_sync_sg_for_device(vgdev->vdev->dev.parent,
+				       bo->pages->sgl, bo->pages->nents,
+				       DMA_TO_DEVICE);
 
 	cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p));
 	memset(cmd_p, 0, sizeof(*cmd_p));
 
 	cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_TRANSFER_TO_HOST_2D);
-	cmd_p->resource_id = cpu_to_le32(resource_id);
+	cmd_p->resource_id = cpu_to_le32(bo->hw_res_handle);
 	cmd_p->offset = cpu_to_le64(offset);
 	cmd_p->r.width = width;
 	cmd_p->r.height = height;
@@ -648,11 +656,11 @@ int virtio_gpu_cmd_get_capset(struct virtio_gpu_device *vgdev,
 {
 	struct virtio_gpu_get_capset *cmd_p;
 	struct virtio_gpu_vbuffer *vbuf;
-	int max_size = vgdev->capsets[idx].max_size;
+	int max_size;
 	struct virtio_gpu_drv_cap_cache *cache_ent;
 	void *resp_buf;
 
-	if (idx > vgdev->num_capsets)
+	if (idx >= vgdev->num_capsets)
 		return -EINVAL;
 
 	if (version > vgdev->capsets[idx].max_version)
@@ -662,6 +670,7 @@ int virtio_gpu_cmd_get_capset(struct virtio_gpu_device *vgdev,
 	if (!cache_ent)
 		return -ENOMEM;
 
+	max_size = vgdev->capsets[idx].max_size;
 	cache_ent->caps_cache = kmalloc(max_size, GFP_KERNEL);
 	if (!cache_ent->caps_cache) {
 		kfree(cache_ent);
@@ -780,20 +789,27 @@ virtio_gpu_cmd_resource_create_3d(struct virtio_gpu_device *vgdev,
 }
 
 void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev,
-					uint32_t resource_id, uint32_t ctx_id,
+					struct virtio_gpu_object *bo,
+					uint32_t ctx_id,
 					uint64_t offset, uint32_t level,
 					struct virtio_gpu_box *box,
 					struct virtio_gpu_fence **fence)
 {
 	struct virtio_gpu_transfer_host_3d *cmd_p;
 	struct virtio_gpu_vbuffer *vbuf;
+	bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
+
+	if (use_dma_api)
+		dma_sync_sg_for_device(vgdev->vdev->dev.parent,
+				       bo->pages->sgl, bo->pages->nents,
+				       DMA_TO_DEVICE);
 
 	cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p));
 	memset(cmd_p, 0, sizeof(*cmd_p));
 
 	cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_TRANSFER_TO_HOST_3D);
 	cmd_p->hdr.ctx_id = cpu_to_le32(ctx_id);
-	cmd_p->resource_id = cpu_to_le32(resource_id);
+	cmd_p->resource_id = cpu_to_le32(bo->hw_res_handle);
 	cmd_p->box = *box;
 	cmd_p->offset = cpu_to_le64(offset);
 	cmd_p->level = cpu_to_le32(level);
@@ -848,9 +864,10 @@ int virtio_gpu_object_attach(struct virtio_gpu_device *vgdev,
 			     uint32_t resource_id,
 			     struct virtio_gpu_fence **fence)
 {
+	bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
 	struct virtio_gpu_mem_entry *ents;
 	struct scatterlist *sg;
-	int si;
+	int si, nents;
 
 	if (!obj->pages) {
 		int ret;
@@ -860,28 +877,60 @@ int virtio_gpu_object_attach(struct virtio_gpu_device *vgdev,
 			return ret;
 	}
 
+	if (use_dma_api) {
+		obj->mapped = dma_map_sg(vgdev->vdev->dev.parent,
+					 obj->pages->sgl, obj->pages->nents,
+					 DMA_TO_DEVICE);
+		nents = obj->mapped;
+	} else {
+		nents = obj->pages->nents;
+	}
+
 	/* gets freed when the ring has consumed it */
-	ents = kmalloc_array(obj->pages->nents,
-			     sizeof(struct virtio_gpu_mem_entry),
+	ents = kmalloc_array(nents, sizeof(struct virtio_gpu_mem_entry),
 			     GFP_KERNEL);
 	if (!ents) {
 		DRM_ERROR("failed to allocate ent list\n");
 		return -ENOMEM;
 	}
 
-	for_each_sg(obj->pages->sgl, sg, obj->pages->nents, si) {
-		ents[si].addr = cpu_to_le64(sg_phys(sg));
+	for_each_sg(obj->pages->sgl, sg, nents, si) {
+		ents[si].addr = cpu_to_le64(use_dma_api
+					    ? sg_dma_address(sg)
+					    : sg_phys(sg));
 		ents[si].length = cpu_to_le32(sg->length);
 		ents[si].padding = 0;
 	}
 
 	virtio_gpu_cmd_resource_attach_backing(vgdev, resource_id,
-					       ents, obj->pages->nents,
+					       ents, nents,
 					       fence);
 	obj->hw_res_handle = resource_id;
 	return 0;
 }
 
+void virtio_gpu_object_detach(struct virtio_gpu_device *vgdev,
+			      struct virtio_gpu_object *obj)
+{
+	bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
+	struct virtio_gpu_fence *fence;
+
+	if (use_dma_api && obj->mapped) {
+		/* detach backing and wait for the host process it ... */
+		virtio_gpu_cmd_resource_inval_backing(vgdev, obj->hw_res_handle, &fence);
+		dma_fence_wait(&fence->f, true);
+		dma_fence_put(&fence->f);
+
+		/* ... then tear down iommu mappings */
+		dma_unmap_sg(vgdev->vdev->dev.parent,
+			     obj->pages->sgl, obj->mapped,
+			     DMA_TO_DEVICE);
+		obj->mapped = 0;
+	} else {
+		virtio_gpu_cmd_resource_inval_backing(vgdev, obj->hw_res_handle, NULL);
+	}
+}
+
 void virtio_gpu_cursor_ping(struct virtio_gpu_device *vgdev,
 			    struct virtio_gpu_output *output)
 {