Merge tag 'drm-next-2021-02-26' of git://anongit.freedesktop.org/drm/drm

Pull more drm updates from Dave Airlie:
 "This is mostly fixes but I missed msm-next pull last week. It's been
  in drm-next.

  Otherwise it's a selection of i915, amdgpu and misc fixes, one TTM
  memory leak, nothing really major stands out otherwise.

  core:
   - vblank fence timing improvements

  dma-buf:
   - improve error handling

  ttm:
   - memory leak fix

  msm:
   - a6xx speedbin support
   - a508, a509, a512 support
   - various a5xx fixes
   - various dpu fixes
   - qseed3lite support for sm8250
   - dsi fix for msm8994
   - mdp5 fix for framerate bug with cmd mode panels
   - a6xx GMU OOB race fixes that were showing up in CI
   - various addition and removal of semicolons
   - gem submit fix for legacy userspace relocs path

  amdgpu:
   - clang warning fix
   - S0ix platform shutdown/poweroff fix
   - misc display fixes

  i915:
   - color format fix
   - -Wuninitialised reenabled
   - GVT ww locking, cmd parser fixes

  atyfb:
   - fix build

  rockchip:
   - AFBC modifier fix"

* tag 'drm-next-2021-02-26' of git://anongit.freedesktop.org/drm/drm: (60 commits)
  drm/panel: kd35t133: allow using non-continuous dsi clock
  drm/rockchip: Require the YTR modifier for AFBC
  drm/ttm: Fix a memory leak
  drm/drm_vblank: set the dma-fence timestamp during send_vblank_event
  dma-fence: allow signaling drivers to set fence timestamp
  dma-buf: heaps: Rework heap allocation hooks to return struct dma_buf instead of fd
  dma-buf: system_heap: Make sure to return an error if we abort
  drm/amd/display: Fix system hang after multiple hotplugs (v3)
  drm/amdgpu: fix shutdown and poweroff process failed with s0ix
  drm/i915: Nuke INTEL_OUTPUT_FORMAT_INVALID
  drm/i915: Enable -Wuninitialized
  drm/amd/display: Remove Assert from dcn10_get_dig_frontend
  drm/amd/display: Add vupdate_no_lock interrupts for DCN2.1
  Revert "drm/amd/display: reuse current context instead of recreating one"
  drm/amd/pm/swsmu: Avoid using structure_size uninitialized in smu_cmn_init_soft_gpu_metrics
  fbdev: atyfb: add stubs for aty_{ld,st}_lcd()
  drm/i915/gvt: Introduce per object locking in GVT scheduler.
  drm/i915/gvt: Purge dev_priv->gt
  drm/i915/gvt: Parse default state to update reg whitelist
  dt-bindings: dp-connector: Drop maxItems from -supply
  ...

68 files changed, 1223 insertions, 423 deletions

diff --git a/Documentation/devicetree/bindings/display/connector/dp-connector.yaml b/Documentation/devicetree/bindings/display/connector/dp-connector.yaml
index 1c17d60e7760..22792a79e7ce 100644
--- a/Documentation/devicetree/bindings/display/connector/dp-connector.yaml
+++ b/Documentation/devicetree/bindings/display/connector/dp-connector.yaml
@@ -26,7 +26,6 @@ properties:
 
   dp-pwr-supply:
     description: Power supply for the DP_PWR pin
-    maxItems: 1
 
   port:
     $ref: /schemas/graph.yaml#/properties/port
diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index 7475e09b0680..d64fc03929be 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -312,22 +312,25 @@ void __dma_fence_might_wait(void)
 
 
 /**
- * dma_fence_signal_locked - signal completion of a fence
+ * dma_fence_signal_timestamp_locked - signal completion of a fence
  * @fence: the fence to signal
+ * @timestamp: fence signal timestamp in kernel's CLOCK_MONOTONIC time domain
  *
  * Signal completion for software callbacks on a fence, this will unblock
  * dma_fence_wait() calls and run all the callbacks added with
  * dma_fence_add_callback(). Can be called multiple times, but since a fence
  * can only go from the unsignaled to the signaled state and not back, it will
- * only be effective the first time.
+ * only be effective the first time. Set the timestamp provided as the fence
+ * signal timestamp.
  *
- * Unlike dma_fence_signal(), this function must be called with &dma_fence.lock
- * held.
+ * Unlike dma_fence_signal_timestamp(), this function must be called with
+ * &dma_fence.lock held.
  *
  * Returns 0 on success and a negative error value when @fence has been
  * signalled already.
  */
-int dma_fence_signal_locked(struct dma_fence *fence)
+int dma_fence_signal_timestamp_locked(struct dma_fence *fence,
+				      ktime_t timestamp)
 {
 	struct dma_fence_cb *cur, *tmp;
 	struct list_head cb_list;
@@ -341,7 +344,7 @@ int dma_fence_signal_locked(struct dma_fence *fence)
 	/* Stash the cb_list before replacing it with the timestamp */
 	list_replace(&fence->cb_list, &cb_list);
 
-	fence->timestamp = ktime_get();
+	fence->timestamp = timestamp;
 	set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags);
 	trace_dma_fence_signaled(fence);
 
@@ -352,6 +355,59 @@ int dma_fence_signal_locked(struct dma_fence *fence)
 
 	return 0;
 }
+EXPORT_SYMBOL(dma_fence_signal_timestamp_locked);
+
+/**
+ * dma_fence_signal_timestamp - signal completion of a fence
+ * @fence: the fence to signal
+ * @timestamp: fence signal timestamp in kernel's CLOCK_MONOTONIC time domain
+ *
+ * Signal completion for software callbacks on a fence, this will unblock
+ * dma_fence_wait() calls and run all the callbacks added with
+ * dma_fence_add_callback(). Can be called multiple times, but since a fence
+ * can only go from the unsignaled to the signaled state and not back, it will
+ * only be effective the first time. Set the timestamp provided as the fence
+ * signal timestamp.
+ *
+ * Returns 0 on success and a negative error value when @fence has been
+ * signalled already.
+ */
+int dma_fence_signal_timestamp(struct dma_fence *fence, ktime_t timestamp)
+{
+	unsigned long flags;
+	int ret;
+
+	if (!fence)
+		return -EINVAL;
+
+	spin_lock_irqsave(fence->lock, flags);
+	ret = dma_fence_signal_timestamp_locked(fence, timestamp);
+	spin_unlock_irqrestore(fence->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(dma_fence_signal_timestamp);
+
+/**
+ * dma_fence_signal_locked - signal completion of a fence
+ * @fence: the fence to signal
+ *
+ * Signal completion for software callbacks on a fence, this will unblock
+ * dma_fence_wait() calls and run all the callbacks added with
+ * dma_fence_add_callback(). Can be called multiple times, but since a fence
+ * can only go from the unsignaled to the signaled state and not back, it will
+ * only be effective the first time.
+ *
+ * Unlike dma_fence_signal(), this function must be called with &dma_fence.lock
+ * held.
+ *
+ * Returns 0 on success and a negative error value when @fence has been
+ * signalled already.
+ */
+int dma_fence_signal_locked(struct dma_fence *fence)
+{
+	return dma_fence_signal_timestamp_locked(fence, ktime_get());
+}
 EXPORT_SYMBOL(dma_fence_signal_locked);
 
 /**
@@ -379,7 +435,7 @@ int dma_fence_signal(struct dma_fence *fence)
 	tmp = dma_fence_begin_signalling();
 
 	spin_lock_irqsave(fence->lock, flags);
-	ret = dma_fence_signal_locked(fence);
+	ret = dma_fence_signal_timestamp_locked(fence, ktime_get());
 	spin_unlock_irqrestore(fence->lock, flags);
 
 	dma_fence_end_signalling(tmp);
diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c
index afd22c9dbdcf..6b5db954569f 100644
--- a/drivers/dma-buf/dma-heap.c
+++ b/drivers/dma-buf/dma-heap.c
@@ -52,6 +52,9 @@ static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len,
 				 unsigned int fd_flags,
 				 unsigned int heap_flags)
 {
+	struct dma_buf *dmabuf;
+	int fd;
+
 	/*
 	 * Allocations from all heaps have to begin
 	 * and end on page boundaries.
@@ -60,7 +63,16 @@ static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len,
 	if (!len)
 		return -EINVAL;
 
-	return heap->ops->allocate(heap, len, fd_flags, heap_flags);
+	dmabuf = heap->ops->allocate(heap, len, fd_flags, heap_flags);
+	if (IS_ERR(dmabuf))
+		return PTR_ERR(dmabuf);
+
+	fd = dma_buf_fd(dmabuf, fd_flags);
+	if (fd < 0) {
+		dma_buf_put(dmabuf);
+		/* just return, as put will call release and that will free */
+	}
+	return fd;
 }
 
 static int dma_heap_open(struct inode *inode, struct file *file)
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c
index 364fc2f3e499..5d64eccd21d6 100644
--- a/drivers/dma-buf/heaps/cma_heap.c
+++ b/drivers/dma-buf/heaps/cma_heap.c
@@ -271,10 +271,10 @@ static const struct dma_buf_ops cma_heap_buf_ops = {
 	.release = cma_heap_dma_buf_release,
 };
 
-static int cma_heap_allocate(struct dma_heap *heap,
-				  unsigned long len,
-				  unsigned long fd_flags,
-				  unsigned long heap_flags)
+static struct dma_buf *cma_heap_allocate(struct dma_heap *heap,
+					 unsigned long len,
+					 unsigned long fd_flags,
+					 unsigned long heap_flags)
 {
 	struct cma_heap *cma_heap = dma_heap_get_drvdata(heap);
 	struct cma_heap_buffer *buffer;
@@ -289,7 +289,7 @@ static int cma_heap_allocate(struct dma_heap *heap,
 
 	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
 	if (!buffer)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&buffer->attachments);
 	mutex_init(&buffer->lock);
@@ -348,15 +348,7 @@ static int cma_heap_allocate(struct dma_heap *heap,
 		ret = PTR_ERR(dmabuf);
 		goto free_pages;
 	}
-
-	ret = dma_buf_fd(dmabuf, fd_flags);
-	if (ret < 0) {
-		dma_buf_put(dmabuf);
-		/* just return, as put will call release and that will free */
-		return ret;
-	}
-
-	return ret;
+	return dmabuf;
 
 free_pages:
 	kfree(buffer->pages);
@@ -365,7 +357,7 @@ free_cma:
 free_buffer:
 	kfree(buffer);
 
-	return ret;
+	return ERR_PTR(ret);
 }
 
 static const struct dma_heap_ops cma_heap_ops = {
diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c
index 17e0e9a68baf..29e49ac17251 100644
--- a/drivers/dma-buf/heaps/system_heap.c
+++ b/drivers/dma-buf/heaps/system_heap.c
@@ -331,10 +331,10 @@ static struct page *alloc_largest_available(unsigned long size,
 	return NULL;
 }
 
-static int system_heap_allocate(struct dma_heap *heap,
-				unsigned long len,
-				unsigned long fd_flags,
-				unsigned long heap_flags)
+static struct dma_buf *system_heap_allocate(struct dma_heap *heap,
+					    unsigned long len,
+					    unsigned long fd_flags,
+					    unsigned long heap_flags)
 {
 	struct system_heap_buffer *buffer;
 	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
@@ -349,7 +349,7 @@ static int system_heap_allocate(struct dma_heap *heap,
 
 	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
 	if (!buffer)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&buffer->attachments);
 	mutex_init(&buffer->lock);
@@ -363,8 +363,10 @@ static int system_heap_allocate(struct dma_heap *heap,
 		 * Avoid trying to allocate memory if the process
 		 * has been killed by SIGKILL
 		 */
-		if (fatal_signal_pending(current))
+		if (fatal_signal_pending(current)) {
+			ret = -EINTR;
 			goto free_buffer;
+		}
 
 		page = alloc_largest_available(size_remaining, max_order);
 		if (!page)
@@ -397,14 +399,7 @@ static int system_heap_allocate(struct dma_heap *heap,
 		ret = PTR_ERR(dmabuf);
 		goto free_pages;
 	}
-
-	ret = dma_buf_fd(dmabuf, fd_flags);
-	if (ret < 0) {
-		dma_buf_put(dmabuf);
-		/* just return, as put will call release and that will free */
-		return ret;
-	}
-	return ret;
+	return dmabuf;
 
 free_pages:
 	for_each_sgtable_sg(table, sg, i) {
@@ -418,7 +413,7 @@ free_buffer:
 		__free_pages(page, compound_order(page));
 	kfree(buffer);
 
-	return ret;
+	return ERR_PTR(ret);
 }
 
 static const struct dma_heap_ops system_heap_ops = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 86452f4f3c82..b6879d97c9c9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1008,6 +1008,12 @@ struct amdgpu_device {
 	bool                            in_suspend;
 	bool				in_hibernate;
 
+	/*
+	 * The combination flag in_poweroff_reboot_com used to identify the poweroff
+	 * and reboot opt in the s0i3 system-wide suspend.
+	 */
+	bool 				in_poweroff_reboot_com;
+
 	atomic_t 			in_gpu_reset;
 	enum pp_mp1_state               mp1_state;
 	struct rw_semaphore reset_sem;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7052dc35d278..6447cd6ca5a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2678,7 +2678,8 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
 {
 	int i, r;
 
-	if (!amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) {
+	if (adev->in_poweroff_reboot_com ||
+	    !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) {
 		amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
 		amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
 	}
@@ -3741,7 +3742,8 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 
 	amdgpu_fence_driver_suspend(adev);
 
-	if (!amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev))
+	if (adev->in_poweroff_reboot_com ||
+	    !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev))
 		r = amdgpu_device_ip_suspend_phase2(adev);
 	else
 		amdgpu_gfx_state_change_set(adev, sGpuChangeState_D3Entry);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 03c529630c21..4575192d9b08 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1270,7 +1270,9 @@ amdgpu_pci_shutdown(struct pci_dev *pdev)
 	 */
 	if (!amdgpu_passthrough(adev))
 		adev->mp1_state = PP_MP1_STATE_UNLOAD;
+	adev->in_poweroff_reboot_com = true;
 	amdgpu_device_ip_suspend(adev);
+	adev->in_poweroff_reboot_com = false;
 	adev->mp1_state = PP_MP1_STATE_NONE;
 }
 
@@ -1312,8 +1314,13 @@ static int amdgpu_pmops_thaw(struct device *dev)
 static int amdgpu_pmops_poweroff(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
+	int r;
 
-	return amdgpu_device_suspend(drm_dev, true);
+	adev->in_poweroff_reboot_com = true;
+	r =  amdgpu_device_suspend(drm_dev, true);
+	adev->in_poweroff_reboot_com = false;
+	return r;
 }
 
 static int amdgpu_pmops_restore(struct device *dev)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 94cd5ddd67ef..3e1fd1e7d09f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -937,7 +937,49 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_
 
 }
 #endif
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+static void event_mall_stutter(struct work_struct *work)
+{
+
+	struct vblank_workqueue *vblank_work = container_of(work, struct vblank_workqueue, mall_work);
+	struct amdgpu_display_manager *dm = vblank_work->dm;
+
+	mutex_lock(&dm->dc_lock);
+
+	if (vblank_work->enable)
+		dm->active_vblank_irq_count++;
+	else
+		dm->active_vblank_irq_count--;
+
+
+	dc_allow_idle_optimizations(
+		dm->dc, dm->active_vblank_irq_count == 0 ? true : false);
+
+	DRM_DEBUG_DRIVER("Allow idle optimizations (MALL): %d\n", dm->active_vblank_irq_count == 0);
 
+
+	mutex_unlock(&dm->dc_lock);
+}
+
+static struct vblank_workqueue *vblank_create_workqueue(struct amdgpu_device *adev, struct dc *dc)
+{
+
+	int max_caps = dc->caps.max_links;
+	struct vblank_workqueue *vblank_work;
+	int i = 0;
+
+	vblank_work = kcalloc(max_caps, sizeof(*vblank_work), GFP_KERNEL);
+	if (ZERO_OR_NULL_PTR(vblank_work)) {
+		kfree(vblank_work);
+		return NULL;
+	}
+
+	for (i = 0; i < max_caps; i++)
+		INIT_WORK(&vblank_work[i].mall_work, event_mall_stutter);
+
+	return vblank_work;
+}
+#endif
 static int amdgpu_dm_init(struct amdgpu_device *adev)
 {
 	struct dc_init_data init_data;
@@ -957,6 +999,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	mutex_init(&adev->dm.dc_lock);
 	mutex_init(&adev->dm.audio_lock);
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	spin_lock_init(&adev->dm.vblank_lock);
+#endif
 
 	if(amdgpu_dm_irq_init(adev)) {
 		DRM_ERROR("amdgpu: failed to initialize DM IRQ support.\n");
@@ -1071,6 +1116,17 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	amdgpu_dm_init_color_mod();
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	if (adev->dm.dc->caps.max_links > 0) {
+		adev->dm.vblank_workqueue = vblank_create_workqueue(adev, adev->dm.dc);
+
+		if (!adev->dm.vblank_workqueue)
+			DRM_ERROR("amdgpu: failed to initialize vblank_workqueue.\n");
+		else
+			DRM_DEBUG_DRIVER("amdgpu: vblank_workqueue init done %p.\n", adev->dm.vblank_workqueue);
+	}
+#endif
+
 #ifdef CONFIG_DRM_AMD_DC_HDCP
 	if (adev->dm.dc->caps.max_links > 0 && adev->asic_type >= CHIP_RAVEN) {
 		adev->dm.hdcp_workqueue = hdcp_create_workqueue(adev, &init_params.cp_psp, adev->dm.dc);
@@