Merge tag 'drm-misc-next-2019-05-24' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

drm-misc-next for v5.3, try #2:

UAPI Changes:
- Add HDR source metadata property.
- Make drm.h compile on GNU/kFreeBSD by including stdint.h
- Clarify how the userspace reviewer has to review new kernel UAPI.
- Clarify that for using new UAPI, merging to drm-next or drm-misc-next should be enough.

Cross-subsystem Changes:
- video/hdmi: Add unpack function for DRM infoframes.
- Device tree bindings:
  * Updating a property for Mali Midgard GPUs
  * Updating a property for STM32 DSI panel
  * Adding support for FriendlyELEC HD702E 800x1280 panel
  * Adding support for Evervision VGG804821 800x480 5.0" WVGA TFT panel
  * Adding support for the EDT ET035012DM6 3.5" 320x240 QVGA 24-bit RGB TFT.
  * Adding support for Three Five displays TFC S9700RTWV43TR-01B 800x480 panel
    with resistive touch found on TI's AM335X-EVM.
  * Adding support for EDT ETM0430G0DH6 480x272 panel.
- Add OSD101T2587-53TS driver with DT bindings.
- Add Samsung S6E63M0 panel driver with DT bindings.
- Add VXT VL050-8048NT-C01 800x480 panel with DT bindings.
- Dma-buf:
  - Make mmap callback actually optional.
  - Documentation updates.
  - Fix debugfs refcount inbalance.
  - Remove unused sync_dump function.
- Fix device tree bindings in drm-misc-next after a botched merge.

Core Changes:
- Add support for HDR infoframes and related EDID parsing.
- Remove prime sg_table caching, now done inside dma-buf.
- Add shiny new drm_gem_vram helpers for simple VRAM drivers;
  with some fixes to the new API on top.
- Small fix to job cleanup without timeout handler.
- Documentation fixes to drm_fourcc.
- Replace lookups of drm_format with struct drm_format_info;
  remove functions that become obsolete by this conversion.
- Remove double include in bridge/panel.c and some drivers.
- Remove drmP.h include from drm/edid and drm/dp.
- Fix null pointer deref in drm_fb_helper_hotplug_event().
- Remove most members from drm_fb_helper_crtc, only mode_set is kept.
- Remove race of fb helpers with userspace; only restore mode
  when userspace is not master.
- Move legacy setup from drm_file.c to drm_legacy_misc.c
- Rework scheduler job destruction.
- drm/bus was removed, remove from TODO.
- Add __drm_atomic_helper_crtc_reset() to subclass crtc_state,
  and convert some drivers to use it (conversion is not complete yet).
- Bump vblank timeout wait to 100 ms for atomic.
- Docbook fix for drm_hdmi_infoframe_set_hdr_metadata.

Driver Changes:
- sun4i: Use DRM_GEM_CMA_VMAP_DRIVER_OPS instead of definining manually.
- v3d: Small cleanups, adding support for compute shaders,
       reservation/synchronization fixes and job management refactoring,
       fixes MMU and debugfs.
- lima: Fix null pointer in irq handler on startup, set default timeout for scheduled jobs.
- stm/ltdc: Assorted fixes and adding FB modifier support.
- amdgpu: Avoid hw reset if guilty job was already signaled.
- virtio: Add seqno to fences, add trace events, use correct flags for fence allocation.
- Convert AST, bochs, mgag200, vboxvideo, hisilicon to the new drm_gem_vram API.
- sun6i_mipi_dsi: Support DSI GENERIC_SHORT_WRITE_2 transfers.
- bochs: Small fix to use PTR_RET_OR_ZERO and driver unload.
- gma500: header fixes
- cirrus: Remove unused files.
- mediatek: Fix compiler warning after merging the HDR series.
- vc4: Rework binner bo handling.

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

From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/052875a5-27ba-3832-60c2-193d950afdff@linux.intel.com

7 files changed, 137 insertions, 32 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index 88ebd681d7eb..1434bb829267 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -799,13 +799,36 @@ vc4_prime_import_sg_table(struct drm_device *dev,
 	return obj;
 }
 
+static int vc4_grab_bin_bo(struct vc4_dev *vc4, struct vc4_file *vc4file)
+{
+	int ret;
+
+	if (!vc4->v3d)
+		return -ENODEV;
+
+	if (vc4file->bin_bo_used)
+		return 0;
+
+	ret = vc4_v3d_bin_bo_get(vc4, &vc4file->bin_bo_used);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
 int vc4_create_bo_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_priv)
 {
 	struct drm_vc4_create_bo *args = data;
+	struct vc4_file *vc4file = file_priv->driver_priv;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_bo *bo = NULL;
 	int ret;
 
+	ret = vc4_grab_bin_bo(vc4, vc4file);
+	if (ret)
+		return ret;
+
 	/*
 	 * We can't allocate from the BO cache, because the BOs don't
 	 * get zeroed, and that might leak data between users.
@@ -846,6 +869,8 @@ vc4_create_shader_bo_ioctl(struct drm_device *dev, void *data,
 			   struct drm_file *file_priv)
 {
 	struct drm_vc4_create_shader_bo *args = data;
+	struct vc4_file *vc4file = file_priv->driver_priv;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_bo *bo = NULL;
 	int ret;
 
@@ -865,6 +890,10 @@ vc4_create_shader_bo_ioctl(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
+	ret = vc4_grab_bin_bo(vc4, vc4file);
+	if (ret)
+		return ret;
+
 	bo = vc4_bo_create(dev, args->size, true, VC4_BO_TYPE_V3D_SHADER);
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);
@@ -894,7 +923,7 @@ vc4_create_shader_bo_ioctl(struct drm_device *dev, void *data,
 	 */
 	ret = drm_gem_handle_create(file_priv, &bo->base.base, &args->handle);
 
- fail:
+fail:
 	drm_gem_object_put_unlocked(&bo->base.base);
 
 	return ret;
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 6d9be20a32be..0f99ad03614e 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -128,8 +128,12 @@ static int vc4_open(struct drm_device *dev, struct drm_file *file)
 
 static void vc4_close(struct drm_device *dev, struct drm_file *file)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_file *vc4file = file->driver_priv;
 
+	if (vc4file->bin_bo_used)
+		vc4_v3d_bin_bo_put(vc4);
+
 	vc4_perfmon_close_file(vc4file);
 	kfree(vc4file);
 }
@@ -274,6 +278,8 @@ static int vc4_drm_bind(struct device *dev)
 	drm->dev_private = vc4;
 	INIT_LIST_HEAD(&vc4->debugfs_list);
 
+	mutex_init(&vc4->bin_bo_lock);
+
 	ret = vc4_bo_cache_init(drm);
 	if (ret)
 		goto dev_put;
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 4f13f6262491..9170a24ec5f5 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -216,6 +216,11 @@ struct vc4_dev {
 	 * the minor is available (after drm_dev_register()).
 	 */
 	struct list_head debugfs_list;
+
+	/* Mutex for binner bo allocation. */
+	struct mutex bin_bo_lock;
+	/* Reference count for our binner bo. */
+	struct kref bin_bo_kref;
 };
 
 static inline struct vc4_dev *
@@ -584,6 +589,11 @@ struct vc4_exec_info {
 	 * NULL otherwise.
 	 */
 	struct vc4_perfmon *perfmon;
+
+	/* Whether the exec has taken a reference to the binner BO, which should
+	 * happen with a VC4_PACKET_TILE_BINNING_MODE_CONFIG packet.
+	 */
+	bool bin_bo_used;
 };
 
 /* Per-open file private data. Any driver-specific resource that has to be
@@ -594,6 +604,8 @@ struct vc4_file {
 		struct idr idr;
 		struct mutex lock;
 	} perfmon;
+
+	bool bin_bo_used;
 };
 
 static inline struct vc4_exec_info *
@@ -833,6 +845,8 @@ void vc4_plane_async_set_fb(struct drm_plane *plane,
 extern struct platform_driver vc4_v3d_driver;
 extern const struct of_device_id vc4_v3d_dt_match[];
 int vc4_v3d_get_bin_slot(struct vc4_dev *vc4);
+int vc4_v3d_bin_bo_get(struct vc4_dev *vc4, bool *used);
+void vc4_v3d_bin_bo_put(struct vc4_dev *vc4);
 int vc4_v3d_pm_get(struct vc4_dev *vc4);
 void vc4_v3d_pm_put(struct vc4_dev *vc4);
 
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index d9311be32a4f..84795d928f20 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -820,6 +820,7 @@ static int
 vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec)
 {
 	struct drm_vc4_submit_cl *args = exec->args;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	void *temp = NULL;
 	void *bin;
 	int ret = 0;
@@ -918,6 +919,12 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec)
 	if (ret)
 		goto fail;
 
+	if (exec->found_tile_binning_mode_config_packet) {
+		ret = vc4_v3d_bin_bo_get(vc4, &exec->bin_bo_used);
+		if (ret)
+			goto fail;
+	}
+
 	/* Block waiting on any previous rendering into the CS's VBO,
 	 * IB, or textures, so that pixels are actually written by the
 	 * time we try to read them.
@@ -966,6 +973,10 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec)
 	vc4->bin_alloc_used &= ~exec->bin_slots;
 	spin_unlock_irqrestore(&vc4->job_lock, irqflags);
 
+	/* Release the reference on the binner BO if needed. */
+	if (exec->bin_bo_used)
+		vc4_v3d_bin_bo_put(vc4);
+
 	/* Release the reference we had on the perf monitor. */
 	vc4_perfmon_put(exec->perfmon);
 
diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c
index ffd0a4388752..e226c24e543f 100644
--- a/drivers/gpu/drm/vc4/vc4_irq.c
+++ b/drivers/gpu/drm/vc4/vc4_irq.c
@@ -59,15 +59,22 @@ vc4_overflow_mem_work(struct work_struct *work)
 {
 	struct vc4_dev *vc4 =
 		container_of(work, struct vc4_dev, overflow_mem_work);
-	struct vc4_bo *bo = vc4->bin_bo;
+	struct vc4_bo *bo;
 	int bin_bo_slot;
 	struct vc4_exec_info *exec;
 	unsigned long irqflags;
 
+	mutex_lock(&vc4->bin_bo_lock);
+
+	if (!vc4->bin_bo)
+		goto complete;
+
+	bo = vc4->bin_bo;
+
 	bin_bo_slot = vc4_v3d_get_bin_slot(vc4);
 	if (bin_bo_slot < 0) {
 		DRM_ERROR("Couldn't allocate binner overflow mem\n");
-		return;
+		goto complete;
 	}
 
 	spin_lock_irqsave(&vc4->job_lock, irqflags);
@@ -98,6 +105,9 @@ vc4_overflow_mem_work(struct work_struct *work)
 	V3D_WRITE(V3D_INTCTL, V3D_INT_OUTOMEM);
 	V3D_WRITE(V3D_INTENA, V3D_INT_OUTOMEM);
 	spin_unlock_irqrestore(&vc4->job_lock, irqflags);
+
+complete:
+	mutex_unlock(&vc4->bin_bo_lock);
 }
 
 static void
@@ -249,8 +259,10 @@ vc4_irq_postinstall(struct drm_device *dev)
 	if (!vc4->v3d)
 		return 0;
 
-	/* Enable both the render done and out of memory interrupts. */
-	V3D_WRITE(V3D_INTENA, V3D_DRIVER_IRQS);
+	/* Enable the render done interrupts. The out-of-memory interrupt is
+	 * enabled as soon as we have a binner BO allocated.
+	 */
+	V3D_WRITE(V3D_INTENA, V3D_INT_FLDONE | V3D_INT_FRDONE);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 4d918d3e4858..be2274924b34 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -310,10 +310,10 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state)
 	struct drm_framebuffer *fb = state->fb;
 	struct drm_gem_cma_object *bo = drm_fb_cma_get_gem_obj(fb, 0);
 	u32 subpixel_src_mask = (1 << 16) - 1;
-	u32 format = fb->format->format;
 	int num_planes = fb->format->num_planes;
 	struct drm_crtc_state *crtc_state;
-	u32 h_subsample, v_subsample;
+	u32 h_subsample = fb->format->hsub;
+	u32 v_subsample = fb->format->vsub;
 	int i, ret;
 
 	crtc_state = drm_atomic_get_existing_crtc_state(state->state,
@@ -328,9 +328,6 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state)
 	if (ret)
 		return ret;
 
-	h_subsample = drm_format_horz_chroma_subsampling(format);
-	v_subsample = drm_format_vert_chroma_subsampling(format);
-
 	for (i = 0; i < num_planes; i++)
 		vc4_state->offsets[i] = bo->paddr + fb->offsets[i];
 
@@ -592,8 +589,9 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	u32 ctl0_offset = vc4_state->dlist_count;
 	const struct hvs_format *format = vc4_get_hvs_format(fb->format->format);
 	u64 base_format_mod = fourcc_mod_broadcom_mod(fb->modifier);
-	int num_planes = drm_format_num_planes(format->drm);
-	u32 h_subsample, v_subsample;
+	int num_planes = fb->format->num_planes;
+	u32 h_subsample = fb->format->hsub;
+	u32 v_subsample = fb->format->vsub;
 	bool mix_plane_alpha;
 	bool covers_screen;
 	u32 scl0, scl1, pitch0;
@@ -623,9 +621,6 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 		scl1 = vc4_get_scl_field(state, 0);
 	}
 
-	h_subsample = drm_format_horz_chroma_subsampling(format->drm);
-	v_subsample = drm_format_vert_chroma_subsampling(format->drm);
-
 	rotation = drm_rotation_simplify(state->rotation,
 					 DRM_MODE_ROTATE_0 |
 					 DRM_MODE_REFLECT_X |
diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c
index a4b6859e3af6..0533646a4d13 100644
--- a/drivers/gpu/drm/vc4/vc4_v3d.c
+++ b/drivers/gpu/drm/vc4/vc4_v3d.c
@@ -213,7 +213,7 @@ try_again:
 }
 
 /**
- * vc4_allocate_bin_bo() - allocates the memory that will be used for
+ * bin_bo_alloc() - allocates the memory that will be used for
  * tile binning.
  *
  * The binner has a limitation that the addresses in the tile state
@@ -234,14 +234,16 @@ try_again:
  * overall CMA pool before they make scenes complicated enough to run
  * out of bin space.
  */
-static int vc4_allocate_bin_bo(struct drm_device *drm)
+static int bin_bo_alloc(struct vc4_dev *vc4)
 {
-	struct vc4_dev *vc4 = to_vc4_dev(drm);
 	struct vc4_v3d *v3d = vc4->v3d;
 	uint32_t size = 16 * 1024 * 1024;
 	int ret = 0;
 	struct list_head list;
 
+	if (!v3d)
+		return -ENODEV;
+
 	/* We may need to try allocating more than once to get a BO
 	 * that doesn't cross 256MB.  Track the ones we've allocated
 	 * that failed so far, so that we can free them when we've got
@@ -251,7 +253,7 @@ static int vc4_allocate_bin_bo(struct drm_device *drm)
 	INIT_LIST_HEAD(&list);
 
 	while (true) {
-		struct vc4_bo *bo = vc4_bo_create(drm, size, true,
+		struct vc4_bo *bo = vc4_bo_create(vc4->dev, size, true,
 						  VC4_BO_TYPE_BIN);
 
 		if (IS_ERR(bo)) {
@@ -292,6 +294,14 @@ static int vc4_allocate_bin_bo(struct drm_device *drm)
 			WARN_ON_ONCE(sizeof(vc4->bin_alloc_used) * 8 !=
 				     bo->base.base.size / vc4->bin_alloc_size);
 
+			kref_init(&vc4->bin_bo_kref);
+
+			/* Enable the out-of-memory interrupt to set our
+			 * newly-allocated binner BO, potentially from an
+			 * already-pending-but-masked interrupt.
+			 */
+			V3D_WRITE(V3D_INTENA, V3D_INT_OUTOMEM);
+
 			break;
 		}
 
@@ -311,6 +321,47 @@ static int vc4_allocate_bin_bo(struct drm_device *drm)
 	return ret;
 }
 
+int vc4_v3d_bin_bo_get(struct vc4_dev *vc4, bool *used)
+{
+	int ret = 0;
+
+	mutex_lock(&vc4->bin_bo_lock);
+
+	if (used && *used)
+		goto complete;
+
+	if (vc4->bin_bo)
+		kref_get(&vc4->bin_bo_kref);
+	else
+		ret = bin_bo_alloc(vc4);
+
+	if (ret == 0 && used)
+		*used = true;
+
+complete:
+	mutex_unlock(&vc4->bin_bo_lock);
+
+	return ret;
+}
+
+static void bin_bo_release(struct kref *ref)
+{
+	struct vc4_dev *vc4 = container_of(ref, struct vc4_dev, bin_bo_kref);
+
+	if (WARN_ON_ONCE(!vc4->bin_bo))
+		return;
+
+	drm_gem_object_put_unlocked(&vc4->bin_bo->base.base);
+	vc4->bin_bo = NULL;
+}
+
+void vc4_v3d_bin_bo_put(struct vc4_dev *vc4)
+{
+	mutex_lock(&vc4->bin_bo_lock);
+	kref_put(&vc4->bin_bo_kref, bin_bo_release);
+	mutex_unlock(&vc4->bin_bo_lock);
+}
+
 #ifdef CONFIG_PM
 static int vc4_v3d_runtime_suspend(struct device *dev)
 {
@@ -319,9 +370,6 @@ static int vc4_v3d_runtime_suspend(struct device *dev)
 
 	vc4_irq_uninstall(vc4->dev);
 
-	drm_gem_object_put_unlocked(&vc4->bin_bo->base.base);
-	vc4->bin_bo = NULL;
-
 	clk_disable_unprepare(v3d->clk);
 
 	return 0;
@@ -333,10 +381,6 @@ static int vc4_v3d_runtime_resume(struct device *dev)
 	struct vc4_dev *vc4 = v3d->vc4;
 	int ret;
 
-	ret = vc4_allocate_bin_bo(vc4->dev);
-	if (ret)
-		return ret;
-
 	ret = clk_prepare_enable(v3d->clk);
 	if (ret != 0)
 		return ret;
@@ -403,12 +447,6 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data)
 	if (ret != 0)
 		return ret;
 
-	ret = vc4_allocate_bin_bo(drm);
-	if (ret) {
-		clk_disable_unprepare(v3d->clk);
-		return ret;
-	}
-
 	/* Reset the binner overflow address/size at setup, to be sure
 	 * we don't reuse an old one.
 	 */