Merge tag 'v5.15-rc6' into asoc-5.16

Linux 5.15-rc6

161 files changed, 2203 insertions, 793 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index dc3c6b3a00e5..269437b01328 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -758,7 +758,7 @@ enum amd_hw_ip_block_type {
 	MAX_HWIP
 };
 
-#define HWIP_MAX_INSTANCE	8
+#define HWIP_MAX_INSTANCE	10
 
 struct amd_powerplay {
 	void *pp_handle;
@@ -1087,6 +1087,7 @@ struct amdgpu_device {
 
 	bool                            no_hw_access;
 	struct pci_saved_state          *pci_state;
+	pci_channel_state_t		pci_channel_state;
 
 	struct amdgpu_reset_control     *reset_cntl;
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 3003ee1c9487..1d41c2c00623 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -192,6 +192,16 @@ void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm)
 		kgd2kfd_suspend(adev->kfd.dev, run_pm);
 }
 
+int amdgpu_amdkfd_resume_iommu(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->kfd.dev)
+		r = kgd2kfd_resume_iommu(adev->kfd.dev);
+
+	return r;
+}
+
 int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm)
 {
 	int r = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index ec028cf963f5..3bc52b2c604f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -137,6 +137,7 @@ int amdgpu_amdkfd_init(void);
 void amdgpu_amdkfd_fini(void);
 
 void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm);
+int amdgpu_amdkfd_resume_iommu(struct amdgpu_device *adev);
 int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm);
 void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
 			const void *ih_ring_entry);
@@ -327,6 +328,7 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 			 const struct kgd2kfd_shared_resources *gpu_resources);
 void kgd2kfd_device_exit(struct kfd_dev *kfd);
 void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm);
+int kgd2kfd_resume_iommu(struct kfd_dev *kfd);
 int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm);
 int kgd2kfd_pre_reset(struct kfd_dev *kfd);
 int kgd2kfd_post_reset(struct kfd_dev *kfd);
@@ -365,6 +367,11 @@ static inline void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
 {
 }
 
+static int __maybe_unused kgd2kfd_resume_iommu(struct kfd_dev *kfd)
+{
+	return 0;
+}
+
 static inline int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
 {
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 2d6b2d77b738..054c1a224def 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -563,6 +563,7 @@ kfd_mem_dmaunmap_userptr(struct kgd_mem *mem,
 
 	dma_unmap_sgtable(adev->dev, ttm->sg, direction, 0);
 	sg_free_table(ttm->sg);
+	kfree(ttm->sg);
 	ttm->sg = NULL;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 277128846dd1..463b9c0283f7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1544,20 +1544,18 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 	struct dentry *ent;
 	int r, i;
 
-
-
 	ent = debugfs_create_file("amdgpu_preempt_ib", 0600, root, adev,
 				  &fops_ib_preempt);
-	if (!ent) {
+	if (IS_ERR(ent)) {
 		DRM_ERROR("unable to create amdgpu_preempt_ib debugsfs file\n");
-		return -EIO;
+		return PTR_ERR(ent);
 	}
 
 	ent = debugfs_create_file("amdgpu_force_sclk", 0200, root, adev,
 				  &fops_sclk_set);
-	if (!ent) {
+	if (IS_ERR(ent)) {
 		DRM_ERROR("unable to create amdgpu_set_sclk debugsfs file\n");
-		return -EIO;
+		return PTR_ERR(ent);
 	}
 
 	/* Register debugfs entries for amdgpu_ttm */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 41c6b3aacd37..af9bdf16eefd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2432,6 +2432,10 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	if (!adev->gmc.xgmi.pending_reset)
 		amdgpu_amdkfd_device_init(adev);
 
+	r = amdgpu_amdkfd_resume_iommu(adev);
+	if (r)
+		goto init_failed;
+
 	amdgpu_fru_get_product_info(adev);
 
 init_failed:
@@ -3148,6 +3152,10 @@ static int amdgpu_device_ip_resume(struct amdgpu_device *adev)
 {
 	int r;
 
+	r = amdgpu_amdkfd_resume_iommu(adev);
+	if (r)
+		return r;
+
 	r = amdgpu_device_ip_resume_phase1(adev);
 	if (r)
 		return r;
@@ -4601,6 +4609,10 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 				dev_warn(tmp_adev->dev, "asic atom init failed!");
 			} else {
 				dev_info(tmp_adev->dev, "GPU reset succeeded, trying to resume\n");
+				r = amdgpu_amdkfd_resume_iommu(tmp_adev);
+				if (r)
+					goto out;
+
 				r = amdgpu_device_ip_resume_phase1(tmp_adev);
 				if (r)
 					goto out;
@@ -5387,6 +5399,8 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
+	adev->pci_channel_state = state;
+
 	switch (state) {
 	case pci_channel_io_normal:
 		return PCI_ERS_RESULT_CAN_RECOVER;
@@ -5529,6 +5543,10 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 
 	DRM_INFO("PCI error: resume callback!!\n");
 
+	/* Only continue execution for the case of pci_channel_io_frozen */
+	if (adev->pci_channel_state != pci_channel_io_frozen)
+		return;
+
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 7a7316731911..dc50c05f23fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -837,6 +837,28 @@ static int convert_tiling_flags_to_modifier(struct amdgpu_framebuffer *afb)
 	return 0;
 }
 
+/* Mirrors the is_displayable check in radeonsi's gfx6_compute_surface */
+static int check_tiling_flags_gfx6(struct amdgpu_framebuffer *afb)
+{
+	u64 micro_tile_mode;
+
+	/* Zero swizzle mode means linear */
+	if (AMDGPU_TILING_GET(afb->tiling_flags, SWIZZLE_MODE) == 0)
+		return 0;
+
+	micro_tile_mode = AMDGPU_TILING_GET(afb->tiling_flags, MICRO_TILE_MODE);
+	switch (micro_tile_mode) {
+	case 0: /* DISPLAY */
+	case 3: /* RENDER */
+		return 0;
+	default:
+		drm_dbg_kms(afb->base.dev,
+			    "Micro tile mode %llu not supported for scanout\n",
+			    micro_tile_mode);
+		return -EINVAL;
+	}
+}
+
 static void get_block_dimensions(unsigned int block_log2, unsigned int cpp,
 				 unsigned int *width, unsigned int *height)
 {
@@ -1103,6 +1125,7 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev,
 				    const struct drm_mode_fb_cmd2 *mode_cmd,
 				    struct drm_gem_object *obj)
 {
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int ret, i;
 
 	/*
@@ -1122,6 +1145,14 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev,
 	if (ret)
 		return ret;
 
+	if (!dev->mode_config.allow_fb_modifiers) {
+		drm_WARN_ONCE(dev, adev->family >= AMDGPU_FAMILY_AI,
+			      "GFX9+ requires FB check based on format modifier\n");
+		ret = check_tiling_flags_gfx6(rfb);
+		if (ret)
+			return ret;
+	}
+
 	if (dev->mode_config.allow_fb_modifiers &&
 	    !(rfb->base.flags & DRM_MODE_FB_MODIFIERS)) {
 		ret = convert_tiling_flags_to_modifier(rfb);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index e7f06bd0f0cd..1916ec84dd71 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -31,6 +31,8 @@
 /* delay 0.1 second to enable gfx off feature */
 #define GFX_OFF_DELAY_ENABLE         msecs_to_jiffies(100)
 
+#define GFX_OFF_NO_DELAY 0
+
 /*
  * GPU GFX IP block helpers function.
  */
@@ -558,6 +560,8 @@ int amdgpu_gfx_enable_kcq(struct amdgpu_device *adev)
 
 void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 {
+	unsigned long delay = GFX_OFF_DELAY_ENABLE;
+
 	if (!(adev->pm.pp_feature & PP_GFXOFF_MASK))
 		return;
 
@@ -573,8 +577,14 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 
 		adev->gfx.gfx_off_req_count--;
 
-		if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state)
-			schedule_delayed_work(&adev->gfx.gfx_off_delay_work, GFX_OFF_DELAY_ENABLE);
+		if (adev->gfx.gfx_off_req_count == 0 &&
+		    !adev->gfx.gfx_off_state) {
+			/* If going to s2idle, no need to wait */
+			if (adev->in_s0ix)
+				delay = GFX_OFF_NO_DELAY;
+			schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
+					      delay);
+		}
 	} else {
 		if (adev->gfx.gfx_off_req_count == 0) {
 			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index c7797eac83c3..9ff600a38559 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -598,7 +598,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
 		break;
 	default:
 		adev->gmc.tmz_enabled = false;
-		dev_warn(adev->dev,
+		dev_info(adev->dev,
 			 "Trusted Memory Zone (TMZ) feature not supported\n");
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index dc44c946a244..98732518543e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -757,7 +757,7 @@ Out:
 	return res;
 }
 
-inline uint32_t amdgpu_ras_eeprom_max_record_count(void)
+uint32_t amdgpu_ras_eeprom_max_record_count(void)
 {
 	return RAS_MAX_RECORD_COUNT;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
index f95fc61b3021..6bb00578bfbb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
@@ -120,7 +120,7 @@ int amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control,
 int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control,
 			     struct eeprom_table_record *records, const u32 num);
 
-inline uint32_t amdgpu_ras_eeprom_max_record_count(void);
+uint32_t amdgpu_ras_eeprom_max_record_count(void);
 
 void amdgpu_ras_debugfs_set_ret_size(struct amdgpu_ras_eeprom_control *control);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 7b634a1517f9..0554576d3695 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -428,8 +428,8 @@ int amdgpu_debugfs_ring_init(struct amdgpu_device *adev,
 	ent = debugfs_create_file(name,
 				  S_IFREG | S_IRUGO, root,
 				  ring, &amdgpu_debugfs_ring_fops);
-	if (!ent)
-		return -ENOMEM;
+	if (IS_ERR(ent))
+		return PTR_ERR(ent);
 
 	i_size_write(ent->d_inode, ring->ring_size + 12);
 	ring->ent = ent;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 38dade421d46..94126dc39688 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -515,6 +515,15 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 		goto out;
 	}
 
+	if (bo->type == ttm_bo_type_device &&
+	    new_mem->mem_type == TTM_PL_VRAM &&
+	    old_mem->mem_type != TTM_PL_VRAM) {
+		/* amdgpu_bo_fault_reserve_notify will re-set this if the CPU
+		 * accesses the BO after it's moved.
+		 */
+		abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+	}
+
 	if (adev->mman.buffer_funcs_enabled) {
 		if (((old_mem->mem_type == TTM_PL_SYSTEM &&
 		      new_mem->mem_type == TTM_PL_VRAM) ||
@@ -545,15 +554,6 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			return r;
 	}
 
-	if (bo->type == ttm_bo_type_device &&
-	    new_mem->mem_type == TTM_PL_VRAM &&
-	    old_mem->mem_type != TTM_PL_VRAM) {
-		/* amdgpu_bo_fault_reserve_notify will re-set this if the CPU
-		 * accesses the BO after it's moved.
-		 */
-		abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
-	}
-
 out:
 	/* update statistics */
 	atomic64_add(bo->base.size, &adev->num_bytes_moved);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 603c259b073b..025184a556ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3599,7 +3599,7 @@ static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring)
 
 	/* set static priority for a queue/ring */
 	gfx_v9_0_mqd_set_priority(ring, mqd);
-	mqd->cp_hqd_quantum = RREG32(mmCP_HQD_QUANTUM);
+	mqd->cp_hqd_quantum = RREG32_SOC15(GC, 0, mmCP_HQD_QUANTUM);
 
 	/* map_queues packet doesn't need activate the queue,
 	 * so only kiq need set this field.
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 41c3a0d70b7c..e47104a1f559 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -1098,6 +1098,8 @@ static int gmc_v10_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	gmc_v10_0_gart_disable(adev);
+
 	if (amdgpu_sriov_vf(adev)) {
 		/* full access mode, so don't touch any GMC register */
 		DRM_DEBUG("For SRIOV client, shouldn't do anything.\n");
@@ -1106,7 +1108,6 @@ static int gmc_v10_0_hw_fini(void *handle)
 
 	amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
-	gmc_v10_0_gart_disable(adev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index d90c16a6b2b8..5551359d5dfd 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1794,6 +1794,8 @@ static int gmc_v9_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	gmc_v9_0_gart_disable(adev);
+
 	if (amdgpu_sriov_vf(adev)) {
 		/* full access mode, so don't touch any GMC register */
 		DRM_DEBUG("For SRIOV client, shouldn't do anything.\n");
@@ -1802,7 +1804,6 @@ static int gmc_v9_0_hw_fini(void *handle)
 
 	amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
-	gmc_v9_0_gart_disable(adev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index 779f5c911e11..e32efcfb0c8b 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -868,6 +868,12 @@ static int sdma_v5_2_start(struct amdgpu_device *adev)
 			msleep(1000);
 	}
 
+	/* TODO: check whether can submit a doorbell request to raise
+	 * a doorbell fence to exit gfxoff.
+	 */
+	if (adev->in_s0ix)
+		amdgpu_gfx_off_ctrl(adev, false);
+
 	sdma_v5_2_soft_reset(adev);
 	/* unhalt the MEs */
 	sdma_v5_2_enable(adev, true);
@@ -876,6 +882,8 @@ static int sdma_v5_2_start(struct amdgpu_device *adev)
 
 	/* start the gfx rings and rlc compute queues */
 	r = sdma_v5_2_gfx_resume(adev);
+	if (adev->in_s0ix)
+		amdgpu_gfx_off_ctrl(adev, true);
 	if (r)
 		return r;
 	r = sdma_v5_2_rlc_resume(adev);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 16a57b70cc1a..4a416231b24c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -468,6 +468,7 @@ static const struct kfd_device_info navi10_device_info = {
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
 	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 145,
 	.num_sdma_engines = 2,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -487,6 +488,7 @@ static const struct kfd_device_info navi12_device_info = {
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
 	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 145,
 	.num_sdma_engines = 2,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -506,6 +508,7 @@ static const struct kfd_device_info navi14_device_info = {
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
 	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 145,
 	.num_sdma_engines = 2,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -525,6 +528,7 @@ static const struct kfd_device_info sienna_cichlid_device_info = {
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
 	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 92,
 	.num_sdma_engines = 4,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -544,6 +548,7 @@ static const struct kfd_device_info navy_flounder_device_info = {
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
 	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 92,
 	.num_sdma_engines = 2,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -562,7 +567,8 @@ static const struct kfd_device_info vangogh_device_info = {
 	.mqd_size_aligned = MQD_SIZE_ALIGNED,
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
-	.needs_pci_atomics = false,
+	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 92,
 	.num_sdma_engines = 1,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
@@ -582,6 +588,7 @@ static const struct kfd_device_info dimgrey_cavefish_device_info = {
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
 	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 92,
 	.num_sdma_engines = 2,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -601,6 +608,7 @@ static const struct kfd_device_info beige_goby_device_info = {
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
 	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 92,
 	.num_sdma_engines = 1,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -619,7 +627,8 @@ static const struct kfd_device_info yellow_carp_device_info = {
 	.mqd_size_aligned = MQD_SIZE_ALIGNED,
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
-	.needs_pci_atomics = false,
+	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 92,
 	.num_sdma_engines = 1,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
@@ -708,20 +717,6 @@ struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd,
 	if (!kfd)
 		return NULL;
 
-	/* Allow BIF to recode atomics to PCIe 3.0 AtomicOps.
-	 * 32 and 64-bit requests are possible and must be
-	 * supported.
-	 */
-	kfd->pci_atomic_requested = amdgpu_amdkfd_have_atomics_support(kgd);
-	if (device_info->needs_pci_atomics &&
-	    !kfd->pci_atomic_requested) {
-		dev_info(kfd_device,
-			 "skipped device %x:%x, PCI rejects atomics\n",
-			 pdev->vendor, pdev->device);
-		kfree(kfd);
-		return NULL;
-	}
-
 	kfd->kgd = kgd;
 	kfd->device_info = device_info;
 	kfd->pdev = pdev;
@@ -821,6 +816,23 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 	kfd->vm_info.vmid_num_kfd = kfd->vm_info.last_vmid_kfd
 			- kfd->vm_info.first_vmid_kfd + 1;
 
+	/* Allow BIF to recode atomics to PCIe 3.0 AtomicOps.
+	 * 32 and 64-bit requests are possible and must be
+	 * supported.
+	 */
+	kfd->pci_atomic_requested = amdgpu_amdkfd_have_atomics_support(kfd->kgd);
+	if (!kfd->pci_atomic_requested &&
+	    kfd->device_info->needs_pci_atomics &&
+	    (!kfd->device_info->no_atomic_fw_version ||
+	     kfd->mec_fw_version < kfd->device_info->no_atomic_fw_version)) {
+		dev_info(kfd_device,
+			 "skipped device %x:%x, PCI rejects atomics %d<%d\n",
+			 kfd->pdev->vendor, kfd->pdev->device,
+			 kfd->mec_fw_version,
+			 kfd->device_info->no_atomic_fw_version);
+		return false;
+	}
+
 	/* Verify module parameters regarding mapped process number*/
 	if ((hws_max_conc_proc < 0)
 			|| (hws_max_conc_proc > kfd->vm_info.vmid_num_kfd)) {
@@ -959,7 +971,6 @@ out:
 void kgd2kfd_device_exit(struct kfd_dev *kfd)
 {
 	if (kfd->init_complete) {
-		svm_migrate_fini((struct amdgpu_device *)kfd->kgd);
 		device_queue_manager_uninit(kfd->dqm);
 		kfd_interrupt_exit(kfd);
 		kfd_topology_remove_device(kfd);
@@ -1057,31 +1068,29 @@ int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
 	return ret;
 }
 
-static int kfd_resume(struct kfd_dev *kfd)
+int kgd2kfd_resume_iommu(struct kfd_dev *kfd)
 {
 	int err = 0;
 
 	err = kfd_iommu_resume(kfd);
-	if (err) {
+	if (err)
 		dev_err(kfd_device,
 			"Failed to resume IOMMU for device %x:%x\n",
 			kfd->pdev->vendor, kfd->pdev->device);
-		return err;
-	}
+	return err;
+}
+
+static int kfd_resume(struct kfd_dev *kfd)
+{
+	int err = 0;
 
 	err = kfd->dqm->ops.start(kfd->dqm);
-	if (err) {
+	if (err)
 		dev_err(kfd_device,
 			"Error starting queue manager for device %x:%x\n",
 			kfd->pdev->vendor, kfd->pdev->device);
-		goto dqm_start_error;
-	}
 
 	return err;
-
-dqm_start_error:
-	kfd_iommu_suspend(kfd);
-	return err;
 }
 
 static inline void kfd_queue_work(struct workqueue_struct *wq,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index dab290a4d19d..4a16e3c257b9 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -891,9 +891,16 @@ int svm_migrate_init(struct amdgpu_device *adev)
 	pgmap->ops = &svm_migrate_pgmap_ops;
 	pgmap->owner = SVM_ADEV_PGMAP_OWNER(adev);
 	pgmap->flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
+
+	/* Device manager releases device-specific resources, memory region and
+	 * pgmap when driver disconnects from device.
+	 */
 	r = devm_memremap_pages(adev->dev, pgmap);
 	if (IS_ERR(r)) {
 		pr_err("failed to register HMM device memory\n");
+
+		/* Disable SVM support capability */
+		pgmap->type = 0;
 		devm_release_mem_region(adev->dev, res->start,
 					res->end - res->start + 1);
 		return PTR_ERR(r);
@@ -908,12 +915,3 @@ int svm_migrate_init(struct amdgpu_device *adev)
 
 	return 0;
 }
-
-void svm_migrate_fini(struct amdgpu_device *adev)
-{
-	struct dev_pagemap *pgmap = &adev->kfd.dev->pgmap;
-
-	devm_memunmap_pages(adev->dev, pgmap);
-	devm_release_mem_region(adev->dev, pgmap->range.start,
-				pgmap->range.end - pgmap->range.start + 1);
-}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h
index 0de76b5d4973..2f5b3394c9ed 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h
@@ -47,7 +47,6 @@ unsigned long
 svm_migrate_addr_to_pfn(struct amdgpu_device *adev, unsigned long addr);
 
 int svm_migrate_init(struct amdgpu_device *adev);
-void svm_migrate_fini(struct amdgpu_device *adev);
 
 #else
 
@@ -55,10 +54,6 @@ static inline int svm_migrate_init(struct amdgpu_device *adev)
 {
 	return 0;
 }
-static inline void svm_migrate_fini(struct amdgpu_device *adev)
-{
-	/* empty */
-}
 
 #endif /* IS_ENABLED(CONFIG_HSA_AMD_SVM) */
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index ab83b0de6b22..6d8f9bb2d905 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -207,6 +207,7 @@ struct kfd_device_info {
 	bool supports_cwsr;
 	bool needs_iommu_device;
 	bool needs_pci_atomics;
+	uint32_t no_atomic_fw_version;
 	unsigned int num_sdma_engines;
 	unsigned int num_xgmi_sdma_engines;
 	unsigned int num_sdma_queues_per_engine;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 9fc8021bb0ab..9d0f65a90002 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -118,6 +118,13 @@ static void svm_range_remove_notifier(struct svm_range *prange)
 		mmu_interval_notifier_remove(&prange->notifier);
 }
 
+static bool
+svm_is_valid_dma_mapping_addr(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr && !dma_mapping_error(dev, dma_addr) &&
+	       !(dma_addr & SVM_RANGE_VRAM_DOMAIN);
+}
+
 static int
 svm_range_dma_map_dev(struct amdgpu_device *adev, struct svm_range *prange,
 		      unsigned long offset, unsigned long npages,
@@ -139,8 +146,7 @@ svm_range_dma_map_dev(struct amdgpu_device *adev, struct svm_range *prange,
 
 	addr += offset;
 	for (i = 0; i < npages; i++) {
-		if (WARN_ONCE(addr[i] && !dma_mapping_error(dev, addr[i]),
-			      "leaking dma mapping\n"))
+		if (svm_is_valid_dma_mapping_addr(dev, addr[i]))
 			dma_unmap_page(dev, addr[i], PAGE_SIZE, dir);
 
 		page = hmm_pfn_to_page(hmm_pfns[i]);
@@ -209,7 +215,7 @@ void svm_range_dma_unmap(struct device *dev, dma_addr_t *dma_addr,
 		return;
 
 	for (i = offset; i < offset + npages; i++) {
-		if (!dma_addr[i] || dma_mapping_error(dev, dma_addr[i]))
+		if (!svm_is_valid_dma_mapping_addr(dev, dma_addr[i]))
 			continue;
 		pr_debug("dma unmapping 0x%llx\n", dma_addr[i] >> PAGE_SHIFT);
 		dma_unmap_page(dev, dma_addr[i], PAGE_SIZE, dir);
@@ -1165,7 +1171,7 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	unsigned long last_start;
 	int last_domain;
 	int r = 0;
-	int64_t i;
+	int64_t i, j;
 
 	last_start = prange->start + offset;
 
@@ -1178,7 +1184,11 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	for (i = offset; i < offset + npages; i++) {
 		last_domain = dma_addr[i] & SVM_RANGE_VRAM_DOMAIN;
 		dma_addr[i] &= ~SVM_RANGE_VRAM_DOMAIN;
-		if ((prange->start + i) < prange->last &&
+
+		/* Collect all pages in the same address range and memory domain
+		 * that can be mapped with a single call to update mapping.
+		 */
+		if (i < offset + npages - 1 &&
 		    last_domain == (dma_addr[i + 1] & SVM_RANGE_VRAM_DOMAIN))
 			continue;
 
@@ -1201,6 +1211,10 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 						NULL, dma_addr,
 						&vm->last_update,
 						&table_freed);
+
+		for (j = last_start - prange->start; j <= i; j++)
+			dma_addr[j] |= last_domain;
+
 		if (r) {
 			pr_debug("failed %d to map to gpu 0x%lx\n", r, prange->start);
 			goto out;
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index 7dffc04a557e..127667e549c1 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -25,6 +25,8 @@ config DRM_AMD_DC_HDCP
 
 config DRM_AMD_DC_SI
 	bool "AMD DC support for Southern Islands ASICs"
+	depends on DRM_AMDGPU_SI
+	depends on DRM_AMD_DC
 	default n
 	help
 	  Choose this option to enable new AMD DC support for SI asics
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 9b1fc54555ee..1ea31dcc7a8b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -998,6 +998,8 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_
 	uint32_t agp_base, agp_bot, agp_top;
 	PHYSICAL_ADDRESS_LOC page_table_start, page_table_end, page_table_base;
 
+	memset(pa_config, 0, sizeof(*pa_config));
+
 	logical_addr_low  = min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18;
 	pt_base = amdgpu_gmc_pd_addr(adev->gart.bo);
 
@@ -1113,6 +1115,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	init_data.asic_id.pci_revision_id = adev->pdev->revision;
 	init_data.asic_id.hw_internal_rev = adev->external_rev_id;
+	init_data.asic_id.chip_id = adev->pdev->device;
 
 	init_data.asic_id.vram_width = adev->gmc.vram_width;
 	/* TODO: initialize init_data.asic_id.vram_type here!!!! */
@@ -1717,6 +1720,7 @@ static int dm_late_init(void *handle)
 		linear_lut[i] = 0xFFFF * i / 15;
 
 	params.set = 0;
+	params.backlight_ramping_override = false;
 	params.backlight_ramping_start = 0xCCCC;
 	params.backlight_ramping_reduction = 0xCCCCCCCC;
 	params.backlight_lut_array_size = 16;
@@ -6024,21 +6028,23 @@ static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable)
 		return 0;
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-	work = kzalloc(sizeof(*work), GFP_ATOMIC);
-	if (!work)
-		return -ENOMEM;
+	if (dm->vblank_control_workqueue) {
+		work = kzalloc(sizeof(*work), GFP_ATOMIC);
+		if (!work)
+			return -ENOMEM;
 
-	INIT_WORK(&work->work, vblank_control_worker);
-	work->dm = dm;
-	work->acrtc = acrtc;
-	work->enable = enable;
+		INIT_WORK(&work->work, vblank_control_worker);
+		work->dm = dm;
+		work->acrtc = acrtc;
+		work->enable = enable;
 
-	if (acrtc_state->stream) {
-		dc_stream_retain(acrtc_state->stream);
-		work->stream = acrtc_state->stream;
-	}
+		if (acrtc_state->stream) {
+			dc_stream_retain(acrtc_state->stream);
+			work->stream = acrtc_state->stream;
+		}
 
-	queue_work(dm->vblank_control_workqueue, &work->work);
+		queue_work(dm->vblank_control_workqueue, &work->work);
+	}
 #endif
 
 	return 0;
@@ -6792,14 +6798,15 @@ const struct drm_encoder_helper_funcs amdgpu_dm_encoder_helper_funcs = {
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state,
-					    struct dc_state *dc_state)
+					    struct dc_state *dc_state,
+					    struct dsc_mst_fairness_vars *vars)
 {
 	struct dc_stream_state *stream = NULL;
 	struct drm_connector *connector;
 	struct drm_connector_state *new_con_state;
 	struct amdgpu_dm_connector *aconnector;
 	struct dm_connector_state *dm_conn_state;
-	int i, j, clock, bpp;
+	int i, j, clock;
 	int vcpi, pbn_div, pbn = 0;
 
 	for_each_new_connector_in_state(state, connector, new_con_state, i) {
@@ -6838,9 +6845,15 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state,
 		}
 
 		pbn_div = dm_mst_get_pbn_divider(stream->link);
-		bpp = stream->timing.dsc_cfg.bits_per_pixel;
 		clock = stream->timing.pix_clk_100hz / 10;
-		pbn = drm_dp_calc_pbn_mode(clock, bpp, true);
+		/* pbn is calculated by compute_mst_dsc_configs_for_state*/
+		for (j = 0; j < dc_state->stream_count; j++) {
+			if (vars[j].aconnector == aconnector) {
+				pbn = vars[j].pbn;
+				break;
+			}
+		}
+
 		vcpi = drm_dp_mst_atomic_enable_dsc(state,
 						    aconnector->port,
 						    pbn, pbn_div,
@@ -7519,6 +7532,32 @@ static void amdgpu_dm_connector_add_common_modes(struct drm_encoder *encoder,
 	}
 }
 
+static void amdgpu_set_panel_orientation(struct drm_connector *connector)
+{
+	struct drm_encoder *encoder;
+	struct amdgpu_encoder *amdgpu_encoder;
+	const struct drm_display_mode *native_mode;
+
+	if (connector->connector_type != DRM_MODE_CONNECTOR_eDP &&
+	    connector->connector_type != DRM_MODE_CONNECTOR_LVDS)
+		return;
+
+	encoder = amdgpu_dm_connector_to_encoder(connector);
+	if (!encoder)
+		return;
+
+	amdgpu_encoder = to_amdgpu_encoder(encoder);
+
+	native_mode = &amdgpu_encoder->native_mode;
+	if (native_mode->hdisplay == 0 || native_mode->vdisplay == 0)
+		return;
+
+	drm_connector_set_panel_orientation_with_quirk(connector,
+						       DRM_MODE_PANEL_ORIENTATION_UNKNOWN,
+						       native_mode->hdisplay,
+						       native_mode->vdisplay);
+}
+
 static void amdgpu_dm_connector_ddc_get_modes(struct drm_connector *connector,
 					      struct edid *edid)
 {
@@ -7547,6 +7586,8 @@ static void amdgpu_dm_connector_ddc_get_modes(struct drm_connector *connector,
 		 * restored here.
 		 */
 		amdgpu_dm_update_freesync_caps(connector, edid);
+
+		amdgpu_set_panel_orientation(connector);
 	} else {
 		amdgpu_dm_connector->num_modes = 0;
 	}
@@ -8058,8 +8099,26 @@ static bool is_content_protection_different(struct drm_connector_state *state,
 	    state->content_protection == DRM_MODE_CONTENT_PROTECTION_ENABLED)
 		state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED;
 
-	/* Check if something is connected/enabled, otherwise we start hdcp but nothing is connected/enabled
-	 * hot-plug, headless s3, dpms
+	/* Stream removed and re-enabled
+	 *
+	 * Can sometimes overlap with the HPD case,
+	 * thus set update_hdcp to false to avoid
+	 * setting HDCP multiple times.
+	 *
+	 * Handles:	DESIRED -> DESIRED (Special case)
+	 */
+	if (!(old_state->crtc && old_state->crtc->enabled) &&
+		state->crtc && state->crtc->enabled &&
+		connector->state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED) {
+		dm_con_state->update_hdcp = false;
+		return true;
+	}
+
+	/* Hot-plug, headless s3, dpms
+	 *
+	 * Only start HDCP if the display is connected/enabled.
+	 * update_hdcp flag will be set to false until the next
+	 * HPD comes in.
 	 *
 	 * Handles:	DESIRED -> DESIRED (Special case)
 	 */
@@ -8648,7 +8707,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		 * If PSR or idle optimizations are enabled then flush out
 		 * any pending work before hardware programming.
 		 */
-		flush_workqueue(dm->vblank_control_workqueue);
+		if (dm->vblank_control_workqueue)
+			flush_workqueue(dm->vblank_control_workqueue);
 #endif
 
 		bundle->stream_update.stream = acrtc_state->stream;
@@ -8983,7 +9043,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		/* if there mode set or reset, disable eDP PSR */
 		if (mode_set_reset_required) {
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-			flush_workqueue(dm->vblank_control_workqueue);
+			if (dm->vblank_control_workqueue)
+				flush_workqueue(dm->vblank_control_workqueue);
 #endif
 			amdgpu_dm_psr_disable_all(dm);
 		}
@@ -10243,6 +10304,9 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 	int ret, i;
 	bool lock_and_validation_needed = false;
 	struct dm_crtc_state *dm_old_crtc_state;
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	struct dsc_mst_fairness_vars vars[MAX_PIPES];
+#endif
 
 	trace_amdgpu_dm_atomic_check_begin(state);
 
@@ -10473,10 +10537,10 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 			goto fail;
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-		if (!compute_mst_dsc_configs_for_state(state, dm_state->context))
+		if (!compute_mst_dsc_configs_for_state(state, dm_state->context, vars))
 			goto fail;
 
-		ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context);
+		ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context, vars);
 		if (ret)
 			goto fail;
 #endif
@@ -10492,7 +10556,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 			goto fail;
 		status = dc_validate_global_state(dc, dm_state->context, false);
 		if (status != DC_OK) {
-			DC_LOG_WARNING("DC global validation failure: %s (%d)",
+			drm_dbg_atomic(dev,
+				       "DC global validation failure: %s (%d)",
 				       dc_status_to_str(status), status);
 			ret = -EINVAL;
 			goto fail;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 1bcba6943fd7..7af0d58c231b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -518,12 +518,7 @@ struct dsc_mst_fairness_params {
 	uint32_t num_slices_h;
 	uint32_t num_slices_v;
 	uint32_t bpp_overwrite;
-};
-
-struct dsc_mst_fairness_vars {
-	int pbn;
-	bool dsc_enabled;
-	int bpp_x16;
+	struct amdgpu_dm_connector *aconnector;
 };
 
 static int kbps_to_peak_pbn(int kbps)
@@ -750,12 +745,12 @@ static void try_disable_dsc(struct drm_atomic_state *state,
 
 static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 					     struct dc_state *dc_state,
-					     struct dc_link *dc_link)
+					     struct dc_link *dc_link,
+					     struct dsc_mst_fairness_vars *vars)
 {
 	int i;
 	struct dc_stream_state *stream;
 	struct dsc_mst_fairness_params params[MAX_PIPES];
-	struct dsc_mst_fairness_vars vars[MAX_PIPES];
 	struct amdgpu_dm_connector *aconnector;
 	int count = 0;
 	bool debugfs_overwrite = false;
@@ -776,6 +771,7 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 		params[count].timing = &stream->timing;
 		params[count].sink = stream->sink;
 		aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
+		params[count].aconnector = aconnector;
 		params[count].port = aconnector->port;
 		params[count].clock_force_enable = aconnector->dsc_settings.dsc_force_enable;
 		if (params[count].clock_force_enable == DSC_CLK_FORCE_ENABLE)
@@ -798,6 +794,7 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 	}
 	/* Try no compression */
 	for (i = 0; i < count; i++) {
+		vars[i].aconnector = params[i].aconnector;
 		vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
 		vars[i].dsc_enabled = false;
 		vars[i].bpp_x16 = 0;
@@ -851,7 +848,8 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 }
 
 bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
-				       struct dc_state *dc_state)
+				       struct dc_state *dc_state,
+				       struct dsc_mst_fairness_vars *vars)
 {
 	int i, j;
 	struct dc_stream_state *stream;
@@ -882,7 +880,7 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
 			return false;
 
 		mutex_lock(&aconnector->mst_mgr.lock);
-		if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link)) {
+		if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link, vars)) {
 			mutex_unlock(&aconnector->mst_mgr.lock);
 			return false;
 		}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
index b38bd68121ce..900d3f7a8498 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
@@ -39,8 +39,17 @@ void
 dm_dp_create_fake_mst_encoders(struct amdgpu_device *adev);
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
+
+struct dsc_mst_fairness_vars {
+	int pbn;
+	bool dsc_enabled;
+	int bpp_x16;
+	struct amdgpu_dm_connector *aconnector;
+};
+
 bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
-				       struct dc_state *dc_state);
+				       struct dc_state *dc_state,
+				       struct dsc_mst_fairness_vars *vars);
 #endif
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
index c9f47d167472..b1bf80da3a55 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
@@ -62,7 +62,7 @@ inline void dc_assert_fp_enabled(void)
 	depth = *pcpu;
 	put_cpu_ptr(&fpu_recursion_depth);
 
-	ASSERT(depth > 1);
+	ASSERT(depth >= 1);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 8bd7f42a8053..1e44b13c1c7d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -2586,13 +2586,21 @@ static struct abm *get_abm_from_stream_res(const struct dc_link *link)
 
 int dc_link_get_backlight_level(const struct dc_link *link)
 {
-
 	struct abm *abm = get_abm_from_stream_res(link);
+	struct panel_cntl *panel_cntl = link->panel_cntl;
+	struct dc  *dc = link->ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
+	bool fw_set_brightness = true;
 
-	if (abm == NULL || abm->funcs->get_current_backlight == NULL)
-		return DC_ERROR_UNEXPECTED;
+	if (dmcu)
+		fw_set_brightness = dmcu->funcs->is_dmcu_initialized(dmcu);
 
-	return (int) abm->funcs->get_current_backlight(abm);
+	if (!fw_set_brightness && panel_cntl->funcs->get_current_backlight)
+		return panel_cntl->funcs->get_current_backlight(panel_cntl);
+	else if (abm != NULL && abm->funcs->get_current_backlight != NULL)
+		return (int) abm->funcs->get_current_backlight(abm);
+	else
+		return DC_ERROR_UNEXPECTED;
 }
 
 int dc_link_get_target_backlight_pwm(const struct dc_link *link)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 330edd666b7d..6d655e158267 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1,4 +1,26 @@
-/* Copyright 2015 Advanced Micro Devices, Inc. */
+/*
+ * Copyright 2015 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ */
 #include "dm_services.h"
 #include "dc.h"
 #include "dc_link_dp.h"
@@ -1284,12 +1306,6 @@ static void override_training_settings(
 {
 	uint32_t lane;
 
-	/* Override link settings */
-	if (link->preferred_link_setting.link_rate != LINK_RATE_UNKNOWN)
-		lt_settings->link_settings.link_rate = link->preferred_link_setting.link_rate;
-	if (link->preferred_link_setting.lane_count != LANE_COUNT_UNKNOWN)
-		lt_settings->link_settings.lane_count = link->preferred_link_setting.lane_count;
-
 	/* Override link spread */
 	if (!link->dp_ss_off && overrides->downspread != NULL)
 		lt_settings->link_settings.link_spread = *overrides->downspread ?
@@ -1804,14 +1820,13 @@ bool perform_link_training_with_retries(
 		if (panel_mode == DP_PANEL_MODE_EDP) {
 			struct cp_psp *cp_psp = &stream->ctx->cp_psp;
 
-			if (cp_psp && cp_psp->funcs.enable_assr) {
-				if (!cp_psp->funcs.enable_assr(cp_psp->handle, link)) {
-					/* since eDP implies ASSR on, change panel
-					 * mode to disable ASSR
-					 */
-					panel_mode = DP_PANEL_MODE_DEFAULT;
-				}
-			}
+			if (cp_psp && cp_psp->funcs.enable_assr)
+				/* ASSR is bound to fail with unsigned PSP
+				 * verstage used during devlopment phase.
+				 * Report and continue with eDP panel mode to
+				 * perform eDP link training with right settings
+				 */
+				cp_psp->funcs.enable_assr(cp_psp->handle, link);
 		}
 #endif
 
@@ -1840,9 +1855,13 @@ bool perform_link_training_with_retries(
 		dp_disable_link_phy(link, signal);
 
 		/* Abort link training if failure due to sink being unplugged. */
-		if (status == LINK_TRAINING_ABORT)
-			break;
-		else if (do_fallback) {
+		if (status == LINK_TRAINING_ABORT) {
+			enum dc_connection_type type = dc_connection_none;
+
+			dc_link_detect_sink(link, &type);
+			if (type == dc_connection_none)
+				break;
+		} else if (do_fallback) {
 			decide_fallback_link_setting(*link_setting, &current_setting, status);
 			/* Fail link training if reduced link bandwidth no longer meets
 			 * stream requirements.
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
index e14f99b4b0c3..3c3347341103 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -42,7 +42,7 @@
 #define DC_LOGGER \
 	engine->ctx->logger
 
-#define DC_TRACE_LEVEL_MESSAGE(...) /* do nothing */
+#define DC_TRACE_LEVEL_MESSAGE(...) do { } while (0)
 #define IS_DC_I2CAUX_LOGGING_ENABLED() (false)
 #define LOG_FLAG_Error_I2cAux LOG_ERROR
 #define LOG_FLAG_I2cAux_DceAux LOG_I2C_AUX
@@ -76,7 +76,7 @@ enum {
 #define DEFAULT_AUX_ENGINE_MULT   0
 #define DEFAULT_AUX_ENGINE_LENGTH 69
 
-#define DC_TRACE_LEVEL_MESSAGE(...) /* do nothing */
+#define DC_TRACE_LEVEL_MESSAGE(...) do { } while (0)
 
 static void release_engine(
 	struct dce_aux *engine)
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
index e92339235863..e8570060d007 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
@@ -49,7 +49,6 @@
 static unsigned int dce_get_16_bit_backlight_from_pwm(struct panel_cntl *panel_cntl)
 {
 	uint64_t current_backlight;
-	uint32_t round_result;
 	uint32_t bl_period, bl_int_count;
 	uint32_t bl_pwm, fractional_duty_cycle_en;
 	uint32_t bl_period_mask, bl_pwm_mask;
@@ -84,15 +83,6 @@ static unsigned int dce_get_16_bit_backlight_from_pwm(struct panel_cntl *panel_c
 	current_backlight = div_u64(current_backlight, bl_period);
 	current_backlight = (current_backlight + 1) >> 1;
 
-	current_backlight = (uint64_t)(current_backlight) * bl_period;
-
-	round_result = (uint32_t)(current_backlight & 0xFFFFFFFF);
-
-	round_result = (round_result >> (bl_int_count-1)) & 1;
-
-	current_backlight >>= bl_int_count;
-	current_backlight += round_result;
-
 	return (uint32_t)(current_backlight);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
index d8b22618b79e..c337588231ff 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
@@ -118,6 +118,7 @@ struct dcn10_link_enc_registers {
 	uint32_t RDPCSTX_PHY_CNTL4;
 	uint32_t RDPCSTX_PHY_CNTL5;
 	uint32_t RDPCSTX_PHY_CNTL6;
+	uint32_t RDPCSPIPE_PHY_CNTL6;
 	uint32_t RDPCSTX_PHY_CNTL7;
 	uint32_t RDPCSTX_PHY_CNTL8;
 	uint32_t RDPCSTX_PHY_CNTL9;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c
index 90127c1f9e35..b0892443fbd5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c
@@ -37,6 +37,7 @@
 
 #include "link_enc_cfg.h"
 #include "dc_dmub_srv.h"
+#include "dal_asic_id.h"
 
 #define CTX \
 	enc10->base.ctx
@@ -62,6 +63,10 @@
 #define AUX_REG_WRITE(reg_name, val) \
 			dm_write_reg(CTX, AUX_REG(reg_name), val)
 
+#ifndef MIN
+#define MIN(X, Y) ((X) < (Y) ? (X) : (Y))
+#endif
+
 void dcn31_link_encoder_set_dio_phy_mux(
 	struct link_encoder *enc,
 	enum encoder_type_select sel,
@@ -215,8 +220,8 @@ static const struct link_encoder_funcs dcn31_link_enc_funcs = {
 	.fec_is_active = enc2_fec_is_active,
 	.get_dig_frontend = dcn10_get_dig_frontend,
 	.get_dig_mode = dcn10_get_dig_mode,
-	.is_in_alt_mode = dcn20_link_encoder_is_in_alt_mode,
-	.get_max_link_cap = dcn20_link_encoder_get_max_link_cap,
+	.is_in_alt_mode = dcn31_link_encoder_is_in_alt_mode,
+	.get_max_link_cap = dcn31_link_encoder_get_max_link_cap,
 	.set_dio_phy_mux = dcn31_link_encoder_set_dio_phy_mux,
 };
 
@@ -404,3 +409,60 @@ void dcn31_link_encoder_disable_output(
 	}
 }
 
+bool dcn31_link_encoder_is_in_alt_mode(struct link_encoder *enc)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	uint32_t dp_alt_mode_disable;
+	bool is_usb_c_alt_mode = false;
+
+	if (enc->features.flags.bits.DP_IS_USB_C) {
+		if (enc->ctx->asic_id.hw_internal_rev != YELLOW_CARP_B0) {
+			// [Note] no need to check hw_internal_rev once phy mux selection is ready
+			REG_GET(RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, &dp_alt_mode_disable);
+		} else {
+		/*
+		 * B0 phys use a new set of registers to check whether alt mode is disabled.
+		 * if value == 1 alt mode is disabled, otherwise it is enabled.
+		 */
+			if ((enc10->base.transmitter == TRANSMITTER_UNIPHY_A)
+					|| (enc10->base.transmitter == TRANSMITTER_UNIPHY_B)
+					|| (enc10->base.transmitter == TRANSMITTER_UNIPHY_E)) {
+				REG_GET(RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, &dp_alt_mode_disable);
+			} else {
+			// [Note] need to change TRANSMITTER_UNIPHY_C/D to F/G once phy mux selection is ready
+				REG_GET(RDPCSPIPE_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, &dp_alt_mode_disable);
+			}
+		}
+
+		is_usb_c_alt_mode = (dp_alt_mode_disable == 0);
+	}
+
+	return is_usb_c_alt_mode;
+}
+
+void dcn31_link_encoder_get_max_link_cap(struct link_encoder *enc,
+										 struct dc_link_settings *link_settings)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	uint32_t is_in_usb_c_dp4_mode = 0;
+
+	dcn10_link_encoder_get_max_link_cap(enc, link_settings);
+
+	/* in usb c dp2 mode, max lane count is 2 */
+	if (enc->funcs->is_in_alt_mode && enc->funcs->is_in_alt_mode(enc)) {
+		if (enc->ctx->asic_id.hw_internal_rev != YELLOW_CARP_B0) {
+			// [Note] no need to check hw_internal_rev once phy mux selection is ready
+			REG_GET(RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, &is_in_usb_c_dp4_mode);
+		} else {
+			if ((enc10->base.transmitter == TRANSMITTER_UNIPHY_A)
+					|| (enc10->base.transmitter == TRANSMITTER_UNIPHY_B)
+					|| (enc10->base.transmitter == TRANSMITTER_UNIPHY_E)) {
+				REG_GET(RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, &is_in_usb_c_dp4_mode);
+			} else {
+				REG_GET(RDPCSPIPE_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, &is_in_usb_c_dp4_mode);
+			}
+		}
+		if (!is_in_usb_c_dp4_mode)
+			link_settings->lane_count = MIN(LANE_COUNT_TWO, link_settings->lane_count);
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.h
index 32d146312838..3454f1e7c1f1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.h
@@ -69,6 +69,7 @@
 	SRI(RDPCSTX_PHY_CNTL4, RDPCSTX, id), \
 	SRI(RDPCSTX_PHY_CNTL5, RDPCSTX, id), \
 	SRI(RDPCSTX_PHY_CNTL6, RDPCSTX, id), \
+	SRI(RDPCSPIPE_PHY_CNTL6, RDPCSPIPE, id), \
 	SRI(RDPCSTX_PHY_CNTL7, RDPCSTX, id), \
 	SRI(RDPCSTX_PHY_CNTL8, RDPCSTX, id), \
 	SRI(RDPCSTX_PHY_CNTL9, RDPCSTX, id), \
@@ -115,7 +116,9 @@
 	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX2_MPLL_EN, mask_sh),\
 	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX3_MPLL_EN, mask_sh),\
 	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, mask_sh),\
-	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, mask_sh),\
+	LE_SF(RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, mask_sh),\
+	LE_SF(RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, mask_sh),\
+	LE_SF(RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE_ACK, mask_sh),\
 	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL7, RDPCS_PHY_DP_MPLLB_FRACN_QUOT, mask_sh),\
 	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL7, RDPCS_PHY_DP_MPLLB_FRACN_DEN, mask_sh),\
 	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL8, RDPCS_PHY_DP_MPLLB_SSC_PEAK, mask_sh),\
@@ -243,4 +246,13 @@ void dcn31_link_encoder_disable_output(
 	struct link_encoder *enc,
 	enum signal_type signal);
 
+/*
+ * Check whether USB-C DP Alt mode is disabled
+ */
+bool dcn31_link_encoder_is_in_alt_mode(
+	struct link_encoder *enc);
+
+void dcn31_link_encoder_get_max_link_cap(struct link_encoder *enc,
+	struct dc_link_settings *link_settings);
+
 #endif /* __DC_LINK_ENCODER__DCN31_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
index a7702d3c75cd..0006bbac466c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
@@ -928,7 +928,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.disable_dcc = DCC_ENABLE,
 	.vsr_support = true,
 	.performance_trace = false,
-	.max_downscale_src_width = 7680,/*upto 8K*/
+	.max_downscale_src_width = 3840,/*upto 4K*/
 	.disable_pplib_wm_range = false,
 	.scl_reset_length10 = true,
 	.sanity_checks = false,
@@ -1284,6 +1284,12 @@ static struct stream_encoder *dcn31_stream_encoder_create(
 	if (!enc1 || !vpg || !afmt)
 		return NULL;
 
+	if (ctx->asic_id.chip_family == FAMILY_YELLOW_CARP &&
+			ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0) {
+		if ((eng_id == ENGINE_ID_DIGC) || (eng_id == ENGINE_ID_DIGD))
+			eng_id = eng_id + 3; // For B0 only. C->F, D->G.
+	}
+
 	dcn30_dio_stream_encoder_construct(enc1, ctx, ctx->dc_bios,
 					eng_id, vpg, afmt,
 					&stream_enc_regs[eng_id],
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index 381c17caace1..5adc471bef57 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -227,7 +227,7 @@ enum {
 #define FAMILY_YELLOW_CARP                     146
 
 #define YELLOW_CARP_A0 0x01
-#define YELLOW_CARP_B0 0x02		// TODO: DCN31 - update with correct B0 ID
+#define YELLOW_CARP_B0 0x1A
 #define YELLOW_CARP_UNKNOWN 0xFF
 
 #ifndef ASICREV_IS_YELLOW_CARP
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_4_2_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_4_2_0_offset.h
index 92caf8441d1e..01a56556cde1 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_4_2_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_4_2_0_offset.h
@@ -11932,5 +11932,32 @@
 #define ixDPCSSYS_CR4_RAWLANEX_DIG_PCS_XF_RX_OVRD_OUT_2                                                0xe0c7
 #define ixDPCSSYS_CR4_RAWLANEX_DIG_PCS_XF_TX_OVRD_IN_2                                                 0xe0c8
 
+//RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6
+#define RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT                                            0x10
+#define RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT                                        0x11
+#define RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT                                    0x12
+#define RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK                                              0x00010000L
+#define RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK                                          0x00020000L
+#define RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK                                      0x00040000L
+
+//RDPCSPIPE1_RDPCSPIPE_PHY_CNTL6
+#define RDPCSPIPE1_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT                                            0x10
+#define RDPCSPIPE1_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT                                        0x11
+#define RDPCSPIPE1_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT                                    0x12
+#define RDPCSPIPE1_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK                                              0x00010000L
+#define RDPCSPIPE1_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK                                          0x00020000L
+#define RDPCSPIPE1_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK                                      0x00040000L
+
+//[Note] Hack. RDPCSPIPE only has 2 instances.
+#define regRDPCSPIPE0_RDPCSPIPE_PHY_CNTL6                                                              0x2d73
+#define regRDPCSPIPE0_RDPCSPIPE_PHY_CNTL6_BASE_IDX                                                     2
+#define regRDPCSPIPE1_RDPCSPIPE_PHY_CNTL6                                                              0x2e4b
+#define regRDPCSPIPE1_RDPCSPIPE_PHY_CNTL6_BASE_IDX                                                     2
+#define regRDPCSPIPE2_RDPCSPIPE_PHY_CNTL6                                                              0x2d73
+#define regRDPCSPIPE2_RDPCSPIPE_PHY_CNTL6_BASE_IDX                                                     2
+#define regRDPCSPIPE3_RDPCSPIPE_PHY_CNTL6                                                              0x2e4b
+#define regRDPCSPIPE3_RDPCSPIPE_PHY_CNTL6_BASE_IDX                                                     2
+#define regRDPCSPIPE4_RDPCSPIPE_PHY_CNTL6                                                              0x2d73
+#define regRDPCSPIPE4_RDPCSPIPE_PHY_CNTL6_BASE_IDX                                                     2
 
 #endif
diff --git a/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_cyan_skillfish.h b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_cyan_skillfish.h
index 8a08ecc34c69..4884a4e1f261 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_cyan_skillfish.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_cyan_skillfish.h
@@ -33,63 +33,47 @@
 #define TABLE_PMSTATUSLOG        3 // Called by Tools for Agm logging
 #define TABLE_DPMCLOCKS          4 // Called by Driver; defined here, but not used, for backward compatible
 #define TABLE_MOMENTARY_PM       5 // Called by Tools; defined here, but not used, for backward compatible
-#define TABLE_COUNT              6
+#define TABLE_SMU_METRICS        6 // Called by Driver
+#define TABLE_COUNT              7
 
-#define NUM_DSPCLK_LEVELS		8
-#define NUM_SOCCLK_DPM_LEVELS	8
-#define NUM_DCEFCLK_DPM_LEVELS	4
-#define NUM_FCLK_DPM_LEVELS		4
-#define NUM_MEMCLK_DPM_LEVELS	4
+typedef struct SmuMetricsTable_t {
+	//CPU status
+	uint16_t CoreFrequency[6];              //[MHz]
+	uint32_t CorePower[6];                  //[mW]
+	uint16_t CoreTemperature[6];            //[centi-Celsius]
+	uint16_t L3Frequency[2];                //[MHz]
+	uint16_t L3Temperature[2];              //[centi-Celsius]
+	uint16_t C0Residency[6];                //Percentage
 
-#define NUMBER_OF_PSTATES		8
-#define NUMBER_OF_CORES			8
+	// GFX status
+	uint16_t GfxclkFrequency;               //[MHz]
+	uint16_t GfxTemperature;                //[centi-Celsius]
 
-typedef enum {
-	S3_TYPE_ENTRY,
-	S5_TYPE_ENTRY,
-} Sleep_Type_e;
+	// SOC IP info
+	uint16_t SocclkFrequency;               //[MHz]
+	uint16_t VclkFrequency;                 //[MHz]
+	uint16_t DclkFrequency;                 //[MHz]
+	uint16_t MemclkFrequency;               //[MHz]
 
-typedef enum {
-	GFX_OFF = 0,
-	GFX_ON  = 1,
-} GFX_Mode_e;
+	// power, VF info for CPU/GFX telemetry rails, and then socket power total
+	uint32_t Voltage[2];                    //[mV] indices: VDDCR_VDD, VDDCR_GFX
+	uint32_t Current[2];                    //[mA] indices: VDDCR_VDD, VDDCR_GFX
+	uint32_t Power[2];                      //[mW] indices: VDDCR_VDD, VDDCR_GFX
+	uint32_t CurrentSocketPower;            //[mW]
 
-typedef enum {
-	CPU_P0 = 0,
-	CPU_P1,
-	CPU_P2,
-	CPU_P3,
-	CPU_P4,
-	CPU_P5,
-	CPU_P6,
-	CPU_P7
-} CPU_PState_e;
+	uint16_t SocTemperature;                //[centi-Celsius]
+	uint16_t EdgeTemperature;
+	uint16_t ThrottlerStatus;
+	uint16_t Spare;
 
-typedef enum {
-	CPU_CORE0 = 0,
-	CPU_CORE1,
-	CPU_CORE2,
-	CPU_CORE3,
-	CPU_CORE4,
-	CPU_CORE5,
-	CPU_CORE6,
-	CPU_CORE7
-} CORE_ID_e;
+} SmuMetricsTable_t;
 
-typedef enum {
-	DF_DPM0 = 0,
-	DF_DPM1,
-	DF_DPM2,
-	DF_DPM3,
-	DF_PState_Count
-} DF_PState_e;
-
-typedef enum {
-	GFX_DPM0 = 0,
-	GFX_DPM1,
-	GFX_DPM2,
-	GFX_DPM3,
-	GFX_PState_Count
-} GFX_PState_e;
+typedef struct SmuMetrics_t {
+	SmuMetricsTable_t Current;
+	SmuMetricsTable_t Average;
+	uint32_t SampleStartTime;
+	uint32_t SampleStopTime;
+	uint32_t Accnt;
+} SmuMetrics_t;
 
 #endif
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_types.h b/drivers/gpu/drm/amd/pm/inc/smu_types.h
index 6f1b1b50d527..18b862a90fbe 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_types.h
@@ -226,7 +226,10 @@
 	__SMU_DUMMY_MAP(SetUclkDpmMode),		\
 	__SMU_DUMMY_MAP(LightSBR),			\
 	__SMU_DUMMY_MAP(GfxDriverResetRecovery),	\
-	__SMU_DUMMY_MAP(BoardPowerCalibration),
+	__SMU_DUMMY_MAP(BoardPowerCalibration),   \
+	__SMU_DUMMY_MAP(RequestGfxclk),           \
+	__SMU_DUMMY_MAP(ForceGfxVid),             \
+	__SMU_DUMMY_MAP(UnforceGfxVid),
 
 #undef __SMU_DUMMY_MAP
 #define __SMU_DUMMY_MAP(type)	SMU_MSG_##type
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h
index 6e6088760b18..909a86aa60f3 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h
@@ -65,6 +65,13 @@
 #define PPSMC_MSG_SetDriverTableVMID                    0x34
 #define PPSMC_MSG_SetSoftMinCclk                        0x35
 #define PPSMC_MSG_SetSoftMaxCclk                        0x36
-#define PPSMC_Message_Count                             0x37
+#define PPSMC_MSG_GetGfxFrequency                       0x37
+#define PPSMC_MSG_GetGfxVid                             0x38
+#define PPSMC_MSG_ForceGfxFreq                          0x39
+#define PPSMC_MSG_UnForceGfxFreq                        0x3A
+#define PPSMC_MSG_ForceGfxVid                           0x3B
+#define PPSMC_MSG_UnforceGfxVid                         0x3C
+#define PPSMC_MSG_GetEnabledSmuFeatures                 0x3D
+#define PPSMC_Message_Count                             0x3E
 
 #endif
diff --git a/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c b/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c
index bdbbeb959c68..81f82aa05ec2 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c
@@ -6867,6 +6867,8 @@ static int si_dpm_enable(struct amdgpu_device *adev)
 	si_enable_auto_throttle_source(adev, AMDGPU_DPM_AUTO_THROTTLE_SRC_THERMAL, true);
 	si_thermal_start_thermal_controller(adev);
 
+	ni_update_current_ps(adev, boot_ps);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 3ab1ce4d3419..04863a797115 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1404,7 +1404,7 @@ static int smu_disable_dpms(struct smu_context *smu)
 	 */
 	if (smu->uploading_custom_pp_table &&
 	    (adev->asic_type >= CHIP_NAVI10) &&
-	    (adev->asic_type <= CHIP_DIMGREY_CAVEFISH))
+	    (adev->asic_type <= CHIP_BEIGE_GOBY))
 		return smu_disable_all_features_with_exception(smu,
 							       true,
 							       SMU_FEATURE_COUNT);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index e343cc218990..082f01893f3d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -771,8 +771,12 @@ static int arcturus_print_clk_levels(struct smu_context *smu,
 	struct smu_11_0_dpm_context *dpm_context = NULL;
 	uint32_t gen_speed, lane_width;
 
-	if (amdgpu_ras_intr_triggered())
-		return sysfs_emit(buf, "unavailable\n");
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
+	if (amdgpu_ras_intr_triggered()) {
+		size += sysfs_emit_at(buf, size, "unavailable\n");
+		return size;
+	}
 
 	dpm_context = smu_dpm->dpm_context;
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
index b05f9541accc..3d4c65bc29dc 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
@@ -44,6 +44,27 @@
 #undef pr_info
 #undef pr_debug
 
+/* unit: MHz */
+#define CYAN_SKILLFISH_SCLK_MIN			1000
+#define CYAN_SKILLFISH_SCLK_MAX			2000
+#define CYAN_SKILLFISH_SCLK_DEFAULT			1800
+
+/* unit: mV */
+#define CYAN_SKILLFISH_VDDC_MIN			700
+#define CYAN_SKILLFISH_VDDC_MAX			1129
+#define CYAN_SKILLFISH_VDDC_MAGIC			5118 // 0x13fe
+
+static struct gfx_user_settings {
+	uint32_t sclk;
+	uint32_t vddc;
+} cyan_skillfish_user_settings;
+
+#define FEATURE_MASK(feature) (1ULL << feature)
+#define SMC_DPM_FEATURE ( \
+	FEATURE_MASK(FEATURE_FCLK_DPM_BIT)	|	\
+	FEATURE_MASK(FEATURE_SOC_DPM_BIT)	|	\
+	FEATURE_MASK(FEATURE_GFX_DPM_BIT))
+
 static struct cmn2asic_msg_mapping cyan_skillfish_message_map[SMU_MSG_MAX_COUNT] = {
 	MSG_MAP(TestMessage,                    PPSMC_MSG_TestMessage,			0),
 	MSG_MAP(GetSmuVersion,                  PPSMC_MSG_GetSmuVersion,		0),
@@ -52,14 +73,473 @@ static struct cmn2asic_msg_mapping cyan_skillfish_message_map[SMU_MSG_MAX_COUNT]
 	MSG_MAP(SetDriverDramAddrLow,           PPSMC_MSG_SetDriverTableDramAddrLow,	0),
 	MSG_MAP(TransferTableSmu2Dram,          PPSMC_MSG_TransferTableSmu2Dram,	0),
 	MSG_MAP(TransferTableDram2Smu,          PPSMC_MSG_TransferTableDram2Smu,	0),
+	MSG_MAP(GetEnabledSmuFeatures,          PPSMC_MSG_GetEnabledSmuFeatures,	0),
+	MSG_MAP(RequestGfxclk,                  PPSMC_MSG_RequestGfxclk,		0),
+	MSG_MAP(ForceGfxVid,                    PPSMC_MSG_ForceGfxVid,			0),
+	MSG_MAP(UnforceGfxVid,                  PPSMC_MSG_UnforceGfxVid,		0),
+};
+
+static struct cmn2asic_mapping cyan_skillfish_table_map[SMU_TABLE_COUNT] = {
+	TAB_MAP_VALID(SMU_METRICS),
 };
 
+static int cyan_skillfish_tables_init(struct smu_context *smu)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct smu_table *tables = smu_table->tables;
+
+	SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS,
+				sizeof(SmuMetrics_t),
+				PAGE_SIZE,
+				AMDGPU_GEM_DOMAIN_VRAM);
+
+	smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL);
+	if (!smu_table->metrics_table)
+		goto err0_out;
+
+	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_2);
+	smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL);
+	if (!smu_table->gpu_metrics_table)
+		goto err1_out;
+
+	smu_table->metrics_time = 0;
+
+	return 0;
+
+err1_out:
+	smu_table->gpu_metrics_table_size = 0;
+	kfree(smu_table->metrics_table);
+err0_out:
+	return -ENOMEM;
+}
+
+static int cyan_skillfish_init_smc_tables(struct smu_context *smu)
+{
+	int ret = 0;
+
+	ret = cyan_skillfish_tables_init(smu);
+	if (ret)
+		return ret;
+
+	return smu_v11_0_init_smc_tables(smu);
+}
+
+static int cyan_skillfish_finit_smc_tables(struct smu_context *smu)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+
+	kfree(smu_table->metrics_table);
+	smu_table->metrics_table = NULL;
+
+	kfree(smu_table->gpu_metrics_table);
+	smu_table->gpu_metrics_table = NULL;
+	smu_table->gpu_metrics_table_size = 0;
+
+	smu_table->metrics_time = 0;
+
+	return 0;
+}
+
+static int
+cyan_skillfish_get_smu_metrics_data(struct smu_context *smu,
+					MetricsMember_t member,
+					uint32_t *value)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	SmuMetrics_t *metrics = (SmuMetrics_t *)smu_table->metrics_table;
+	int ret = 0;
+
+	mutex_lock(&smu->metrics_lock);
+
+	ret = smu_cmn_get_metrics_table_locked(smu, NULL, false);
+	if (ret) {
+		mutex_unlock(&smu->metrics_lock);
+		return ret;
+	}
+
+	switch (member) {
+	case METRICS_CURR_GFXCLK:
+		*value = metrics->Current.GfxclkFrequency;
+		break;
+	case METRICS_CURR_SOCCLK:
+		*value = metrics->Current.SocclkFrequency;
+		break;
+	case METRICS_CURR_VCLK:
+		*value = metrics->Current.VclkFrequency;
+		break;
+	case METRICS_CURR_DCLK:
+		*value = metrics->Current.DclkFrequency;
+		break;
+	case METRICS_CURR_UCLK:
+		*value = metrics->Current.MemclkFrequency;
+		break;
+	case METRICS_AVERAGE_SOCKETPOWER:
+		*value = (metrics->Current.CurrentSocketPower << 8) /
+				1000;
+		break;
+	case METRICS_TEMPERATURE_EDGE:
+		*value = metrics->Current.GfxTemperature / 100 *
+				SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+		break;
+	case METRICS_TEMPERATURE_HOTSPOT:
+		*value = metrics->Current.SocTemperature / 100 *
+				SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+		break;
+	case METRICS_VOLTAGE_VDDSOC:
+		*value = metrics->Current.Voltage[0];
+		break;
+	case METRICS_VOLTAGE_VDDGFX:
+		*value = metrics->Current.Voltage[1];
+		break;
+	case METRICS_THROTTLER_STATUS:
+		*value = metrics->Current.ThrottlerStatus;
+		break;
+	default:
+		*value = UINT_MAX;
+		break;
+	}
+
+	mutex_unlock(&smu->metrics_lock);
+
+	return ret;
+}
+
+static int cyan_skillfish_read_sensor(struct smu_context *smu,
+					enum amd_pp_sensors sensor,
+					void *data,
+					uint32_t *size)
+{
+	int ret = 0;
+
+	if (!data || !size)
+		return -EINVAL;
+
+	mutex_lock(&smu->sensor_lock);
+
+	switch (sensor) {
+	case AMDGPU_PP_SENSOR_GFX_SCLK:
+		ret = cyan_skillfish_get_smu_metrics_data(smu,
+						   METRICS_CURR_GFXCLK,
+						   (uint32_t *)data);
+		*(uint32_t *)data *= 100;
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_GFX_MCLK:
+		ret = cyan_skillfish_get_smu_metrics_data(smu,
+						   METRICS_CURR_UCLK,
+						   (uint32_t *)data);
+		*(uint32_t *)data *= 100;
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_GPU_POWER:
+		ret = cyan_skillfish_get_smu_metrics_data(smu,
+						   METRICS_AVERAGE_SOCKETPOWER,
+						   (uint32_t *)data);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_HOTSPOT_TEMP:
+		ret = cyan_skillfish_get_smu_metrics_data(smu,
+						   METRICS_TEMPERATURE_HOTSPOT,
+						   (uint32_t *)data);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_EDGE_TEMP:
+		ret = cyan_skillfish_get_smu_metrics_data(smu,
+						   METRICS_TEMPERATURE_EDGE,
+						   (uint32_t *)data);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_VDDNB:
+		ret = cyan_skillfish_get_smu_metrics_data(smu,
+						   METRICS_VOLTAGE_VDDSOC,
+						   (uint32_t *)data);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_VDDGFX:
+		ret = cyan_skillfish_get_smu_metrics_data(smu,
+						   METRICS_VOLTAGE_VDDGFX,
+						   (uint32_t *)data);
+		*size = 4;
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+
+	mutex_unlock(&smu->sensor_lock);
+
+	return ret;
+}
+
+static int cyan_skillfish_get_current_clk_freq(struct smu_context *smu,
+						enum smu_clk_type clk_type,
+						uint32_t *value)
+{
+	MetricsMember_t member_type;
+
+	switch (clk_type) {
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+		member_type = METRICS_CURR_GFXCLK;
+		break;
+	case SMU_FCLK:
+	case SMU_MCLK:
+		member_type = METRICS_CURR_UCLK;
+		break;
+	case SMU_SOCCLK:
+		member_type = METRICS_CURR_SOCCLK;
+		break;
+	case SMU_VCLK:
+		member_type = METRICS_CURR_VCLK;
+		break;
+	case SMU_DCLK:
+		member_type = METRICS_CURR_DCLK;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return cyan_skillfish_get_smu_metrics_data(smu, member_type, value);
+}
+
+static int cyan_skillfish_print_clk_levels(struct smu_context *smu,
+					enum smu_clk_type clk_type,
+					char *buf)
+{
+	int ret = 0, size = 0;
+	uint32_t cur_value = 0;
+
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
+	switch (clk_type) {
+	case SMU_OD_SCLK:
+		ret  = cyan_skillfish_get_smu_metrics_data(smu, METRICS_CURR_GFXCLK, &cur_value);
+		if (ret)
+			return ret;
+		size += sysfs_emit_at(buf, size,"%s:\n", "OD_SCLK");
+		size += sysfs_emit_at(buf, size, "0: %uMhz *\n", cur_value);
+		break;
+	case SMU_OD_VDDC_CURVE:
+		ret  = cyan_skillfish_get_smu_metrics_data(smu, METRICS_VOLTAGE_VDDGFX, &cur_value);
+		if (ret)
+			return ret;
+		size += sysfs_emit_at(buf, size,"%s:\n", "OD_VDDC");
+		size += sysfs_emit_at(buf, size, "0: %umV *\n", cur_value);
+		break;
+	case SMU_OD_RANGE:
+		size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
+		size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
+						CYAN_SKILLFISH_SCLK_MIN, CYAN_SKILLFISH_SCLK_MAX);
+		size += sysfs_emit_at(buf, size, "VDDC: %7umV  %10umV\n",
+						CYAN_SKILLFISH_VDDC_MIN, CYAN_SKILLFISH_VDDC_MAX);
+		break;
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+	case SMU_FCLK:
+	case SMU_MCLK:
+	case SMU_SOCCLK:
+	case SMU_VCLK:
+	case SMU_DCLK:
+		ret = cyan_skillfish_get_current_clk_freq(smu, clk_type, &cur_value);
+		if (ret)
+			return ret;
+		size += sysfs_emit_at(buf, size, "0: %uMhz *\n", cur_value);
+		break;
+	default:
+		dev_warn(smu->adev->dev, "Unsupported clock type\n");
+		return ret;
+	}
+
+	return size;
+}
+
+static bool cyan_skillfish_is_dpm_running(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+	int ret = 0;
+	uint32_t feature_mask[2];
+	uint64_t feature_enabled;
+
+	/* we need to re-init after suspend so return false */
+	if (adev->in_suspend)
+		return false;
+
+	ret = smu_cmn_get_enabled_32_bits_mask(smu, feature_mask, 2);
+
+	if (ret)
+		return false;
+
+	feature_enabled = (uint64_t)feature_mask[0] |
+				((uint64_t)feature_mask[1] << 32);
+
+	return !!(feature_enabled & SMC_DPM_FEATURE);
+}
+
+static ssize_t cyan_skillfish_get_gpu_metrics(struct smu_context *smu,
+						void **table)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct gpu_metrics_v2_2 *gpu_metrics =
+		(struct gpu_metrics_v2_2 *)smu_table->gpu_metrics_table;
+	SmuMetrics_t metrics;
+	int i, ret = 0;
+
+	ret = smu_cmn_get_metrics_table(smu, &metrics, true);
+	if (ret)
+		return ret;
+
+	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 2, 2);
+
+	gpu_metrics->temperature_gfx = metrics.Current.GfxTemperature;
+	gpu_metrics->temperature_soc = metrics.Current.SocTemperature;
+
+	gpu_metrics->average_socket_power = metrics.Current.CurrentSocketPower;
+	gpu_metrics->average_soc_power = metrics.Current.Power[0];
+	gpu_metrics->average_gfx_power = metrics.Current.Power[1];
+
+	gpu_metrics->average_gfxclk_frequency = metrics.Average.GfxclkFrequency;
+	gpu_metrics->average_socclk_frequency = metrics.Average.SocclkFrequency;
+	gpu_metrics->average_uclk_frequency = metrics.Average.MemclkFrequency;
+	gpu_metrics->average_fclk_frequency = metrics.Average.MemclkFrequency;
+	gpu_metrics->average_vclk_frequency = metrics.Average.VclkFrequency;
+	gpu_metrics->average_dclk_frequency = metrics.Average.DclkFrequency;
+
+	gpu_metrics->current_gfxclk = metrics.Current.GfxclkFrequency;
+	gpu_metrics->current_socclk = metrics.Current.SocclkFrequency;
+	gpu_metrics->current_uclk = metrics.Current.MemclkFrequency;
+	gpu_metrics->current_fclk = metrics.Current.MemclkFrequency;
+	gpu_metrics->current_vclk = metrics.Current.VclkFrequency;
+	gpu_metrics->current_dclk = metrics.Current.DclkFrequency;
+
+	for (i = 0; i < 6; i++) {
+		gpu_metrics->temperature_core[i] = metrics.Current.CoreTemperature[i];
+		gpu_metrics->average_core_power[i] = metrics.Average.CorePower[i];
+		gpu_metrics->current_coreclk[i] = metrics.Current.CoreFrequency[i];
+	}
+
+	for (i = 0; i < 2; i++) {
+		gpu_metrics->temperature_l3[i] = metrics.Current.L3Temperature[i];
+		gpu_metrics->current_l3clk[i] = metrics.Current.L3Frequency[i];
+	}
+
+	gpu_metrics->throttle_status = metrics.Current.ThrottlerStatus;
+	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();
+
+	*table = (void *)gpu_metrics;
+
+	return sizeof(struct gpu_metrics_v2_2);
+}
+
+static int cyan_skillfish_od_edit_dpm_table(struct smu_context *smu,
+					enum PP_OD_DPM_TABLE_COMMAND type,
+					long input[], uint32_t size)
+{
+	int ret = 0;
+	uint32_t vid;
+
+	switch (type) {
+	case PP_OD_EDIT_VDDC_CURVE:
+		if (size != 3 || input[0] != 0) {
+			dev_err(smu->adev->dev, "Invalid parameter!\n");
+			return -EINVAL;
+		}
+
+		if (input[1] <= CYAN_SKILLFISH_SCLK_MIN ||
+			input[1] > CYAN_SKILLFISH_SCLK_MAX) {
+			dev_err(smu->adev->dev, "Invalid sclk! Valid sclk range: %uMHz - %uMhz\n",
+					CYAN_SKILLFISH_SCLK_MIN, CYAN_SKILLFISH_SCLK_MAX);
+			return -EINVAL;
+		}
+
+		if (input[2] <= CYAN_SKILLFISH_VDDC_MIN ||
+			input[2] > CYAN_SKILLFISH_VDDC_MAX) {
+			dev_err(smu->adev->dev, "Invalid vddc! Valid vddc range: %umV - %umV\n",
+					CYAN_SKILLFISH_VDDC_MIN, CYAN_SKILLFISH_VDDC_MAX);
+			return -EINVAL;
+		}
+
+		cyan_skillfish_user_settings.sclk = input[1];
+		cyan_skillfish_user_settings.vddc = input[2];
+
+		break;
+	case PP_OD_RESTORE_DEFAULT_TABLE:
+		if (size != 0) {
+			dev_err(smu->adev->dev, "Invalid parameter!\n");
+			return -EINVAL;
+		}
+
+		cyan_skillfish_user_settings.sclk = CYAN_SKILLFISH_SCLK_DEFAULT;
+		cyan_skillfish_user_settings.vddc = CYAN_SKILLFISH_VDDC_MAGIC;
+
+		break;
+	case PP_OD_COMMIT_DPM_TABLE:
+		if (size != 0) {
+			dev_err(smu->adev->dev, "Invalid parameter!\n");
+			return -EINVAL;
+		}
+
+		if (cyan_skillfish_user_settings.sclk < CYAN_SKILLFISH_SCLK_MIN ||
+		    cyan_skillfish_user_settings.sclk > CYAN_SKILLFISH_SCLK_MAX) {
+			dev_err(smu->adev->dev, "Invalid sclk! Valid sclk range: %uMHz - %uMhz\n",
+					CYAN_SKILLFISH_SCLK_MIN, CYAN_SKILLFISH_SCLK_MAX);
+			return -EINVAL;
+		}
+
+		if ((cyan_skillfish_user_settings.vddc != CYAN_SKILLFISH_VDDC_MAGIC) &&
+			(cyan_skillfish_user_settings.vddc < CYAN_SKILLFISH_VDDC_MIN ||
+			cyan_skillfish_user_settings.vddc > CYAN_SKILLFISH_VDDC_MAX)) {
+			dev_err(smu->adev->dev, "Invalid vddc! Valid vddc range: %umV - %umV\n",
+					CYAN_SKILLFISH_VDDC_MIN, CYAN_SKILLFISH_VDDC_MAX);
+			return -EINVAL;
+		}
+
+		ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_RequestGfxclk,
+					cyan_skillfish_user_settings.sclk, NULL);
+		if (ret) {
+			dev_err(smu->adev->dev, "Set sclk failed!\n");
+			return ret;
+		}
+
+		if (cyan_skillfish_user_settings.vddc == CYAN_SKILLFISH_VDDC_MAGIC) {
+			ret = smu_cmn_send_smc_msg(smu, SMU_MSG_UnforceGfxVid, NULL);
+			if (ret) {
+				dev_err(smu->adev->dev, "Unforce vddc failed!\n");
+				return ret;
+			}
+		} else {
+			/*
+			 * PMFW accepts SVI2 VID code, convert voltage to VID:
+			 * vid = (uint32_t)((1.55 - voltage) * 160.0 + 0.00001)
+			 */
+			vid = (1550 - cyan_skillfish_user_settings.vddc) * 160 / 1000;
+			ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_ForceGfxVid, vid, NULL);
+			if (ret) {
+				dev_err(smu->adev->dev, "Force vddc failed!\n");
+				return ret;
+			}
+		}
+
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
 static const struct pptable_funcs cyan_skillfish_ppt_funcs = {
 
 	.check_fw_status = smu_v11_0_check_fw_status,
 	.check_fw_version = smu_v11_0_check_fw_version,
 	.init_power = smu_v11_0_init_power,
 	.fini_power = smu_v11_0_fini_power,
+	.init_smc_tables = cyan_skillfish_init_smc_tables,
+	.fini_smc_tables = cyan_skillfish_finit_smc_tables,
+	.read_sensor = cyan_skillfish_read_sensor,
+	.print_clk_levels = cyan_skillfish_print_clk_levels,
+	.is_dpm_running = cyan_skillfish_is_dpm_running,
+	.get_gpu_metrics = cyan_skillfish_get_gpu_metrics,
+	.od_edit_dpm_table = cyan_skillfish_od_edit_dpm_table,
 	.register_irq_handler = smu_v11_0_register_irq_handler,
 	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
 	.send_smc_msg_with_param = smu_cmn_send_smc_msg_with_param,
@@ -72,5 +552,6 @@ void cyan_skillfish_set_ppt_funcs(struct smu_context *smu)
 {
 	smu->ppt_funcs = &cyan_skillfish_ppt_funcs;
 	smu->message_map = cyan_skillfish_message_map;
+	smu->table_map = cyan_skillfish_table_map;
 	smu->is_apu = true;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index a5fc5d7cb6c7..b1ad451af06b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -1279,6 +1279,8 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 	struct smu_11_0_overdrive_table *od_settings = smu->od_settings;
 	uint32_t min_value, max_value;
 
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
 	switch (clk_type) {
 	case SMU_GFXCLK:
 	case SMU_SCLK:
@@ -1392,7 +1394,7 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 	case SMU_OD_RANGE:
 		if (!smu->od_enabled || !od_table || !od_settings)
 			break;
-		size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+		size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 
 		if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_LIMITS)) {
 			navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_GFXCLKFMIN,
@@ -2272,7 +2274,27 @@ static int navi10_baco_enter(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	if (adev->in_runpm)
+	/*
+	 * This aims the case below:
+	 *   amdgpu driver loaded -> runpm suspend kicked -> sound driver loaded
+	 *
+	 * For NAVI10 and later ASICs, we rely on PMFW to handle the runpm. To
+	 * make that possible, PMFW needs to acknowledge the dstate transition
+	 * process for both gfx(function 0) and audio(function 1) function of
+	 * the ASIC.
+	 *
+	 * The PCI device's initial runpm status is RUNPM_SUSPENDED. So as the
+	 * device representing the audio function of the ASIC. And that means
+	 * even if the sound driver(snd_hda_intel) was not loaded yet, it's still
+	 * possible runpm suspend kicked on the ASIC. However without the dstate
+	 * transition notification from audio function, pmfw cannot handle the
+	 * BACO in/exit correctly. And that will cause driver hang on runpm
+	 * resuming.
+	 *
+	 * To address this, we revert to legacy message way(driver masters the
+	 * timing for BACO in/exit) on sound driver missing.
+	 */
+	if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev))
 		return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_BACO);
 	else
 		return smu_v11_0_baco_enter(smu);
@@ -2282,7 +2304,7 @@ static int navi10_baco_exit(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	if (adev->in_runpm) {
+	if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) {
 		/* Wait for PMFW handling for the Dstate change */
 		msleep(10);
 		return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 5e292c3f5050..ca57221e3962 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -1058,6 +1058,8 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu,
 	uint32_t min_value, max_value;
 	uint32_t smu_version;
 
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
 	switch (clk_type) {
 	case SMU_GFXCLK:
 	case SMU_SCLK:
@@ -1180,7 +1182,7 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu,
 		if (!smu->od_enabled || !od_table || !od_settings)
 			break;
 
-		size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+		size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 
 		if (sienna_cichlid_is_od_feature_supported(od_settings, SMU_11_0_7_ODCAP_GFXCLK_LIMITS)) {
 			sienna_cichlid_get_od_setting_range(od_settings, SMU_11_0_7_ODSETTING_GFXCLKFMIN,
@@ -2187,7 +2189,7 @@ static int sienna_cichlid_baco_enter(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	if (adev->in_runpm)
+	if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev))
 		return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_BACO);
 	else
 		return smu_v11_0_baco_enter(smu);
@@ -2197,7 +2199,7 @@ static int sienna_cichlid_baco_exit(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	if (adev->in_runpm) {
+	if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) {
 		/* Wait for PMFW handling for the Dstate change */
 		msleep(10);
 		return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 3a3421452e57..f6ef0ce6e9e2 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -589,10 +589,12 @@ static int vangogh_print_legacy_clk_levels(struct smu_context *smu,
 	if (ret)
 		return ret;
 
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
 	switch (clk_type) {
 	case SMU_OD_SCLK:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
 			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 			(smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq);
 			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
@@ -601,7 +603,7 @@ static int vangogh_print_legacy_clk_levels(struct smu_context *smu,
 		break;
 	case SMU_OD_CCLK:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sysfs_emit(buf, "CCLK_RANGE in Core%d:\n",  smu->cpu_core_id_select);
+			size += sysfs_emit_at(buf, size, "CCLK_RANGE in Core%d:\n",  smu->cpu_core_id_select);
 			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 			(smu->cpu_actual_soft_min_freq > 0) ? smu->cpu_actual_soft_min_freq : smu->cpu_default_soft_min_freq);
 			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
@@ -610,7 +612,7 @@ static int vangogh_print_legacy_clk_levels(struct smu_context *smu,
 		break;
 	case SMU_OD_RANGE:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 			size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
 				smu->gfx_default_hard_min_freq, smu->gfx_default_soft_max_freq);
 			size += sysfs_emit_at(buf, size, "CCLK: %7uMhz %10uMhz\n",
@@ -688,10 +690,12 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 	if (ret)
 		return ret;
 
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
 	switch (clk_type) {
 	case SMU_OD_SCLK:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
 			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 			(smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq);
 			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
@@ -700,7 +704,7 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 		break;
 	case SMU_OD_CCLK:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sysfs_emit(buf, "CCLK_RANGE in Core%d:\n",  smu->cpu_core_id_select);
+			size += sysfs_emit_at(buf, size, "CCLK_RANGE in Core%d:\n",  smu->cpu_core_id_select);
 			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 			(smu->cpu_actual_soft_min_freq > 0) ? smu->cpu_actual_soft_min_freq : smu->cpu_default_soft_min_freq);
 			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
@@ -709,7 +713,7 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 		break;
 	case SMU_OD_RANGE:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 			size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
 				smu->gfx_default_hard_min_freq, smu->gfx_default_soft_max_freq);
 			size += sysfs_emit_at(buf, size, "CCLK: %7uMhz %10uMhz\n",
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
index 5aa175e12a78..145f13b8c977 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
@@ -497,6 +497,8 @@ static int renoir_print_clk_levels(struct smu_context *smu,
 	if (ret)
 		return ret;
 
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
 	switch (clk_type) {
 	case SMU_OD_RANGE:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index ab652028e003..5019903db492 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -733,15 +733,19 @@ static int aldebaran_print_clk_levels(struct smu_context *smu,
 	uint32_t freq_values[3] = {0};
 	uint32_t min_clk, max_clk;
 
-	if (amdgpu_ras_intr_triggered())
-		return sysfs_emit(buf, "unavailable\n");
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
+	if (amdgpu_ras_intr_triggered()) {
+		size += sysfs_emit_at(buf, size, "unavailable\n");
+		return size;
+	}
 
 	dpm_context = smu_dpm->dpm_context;
 
 	switch (type) {
 
 	case SMU_OD_SCLK:
-		size = sysfs_emit(buf, "%s:\n", "GFXCLK");
+		size += sysfs_emit_at(buf, size, "%s:\n", "GFXCLK");
 		fallthrough;
 	case SMU_SCLK:
 		ret = aldebaran_get_current_clk_freq_by_table(smu, SMU_GFXCLK, &now);
@@ -795,7 +799,7 @@ static int aldebaran_print_clk_levels(struct smu_context *smu,
 		break;
 
 	case SMU_OD_MCLK:
-		size = sysfs_emit(buf, "%s:\n", "MCLK");
+		size += sysfs_emit_at(buf, size, "%s:\n", "MCLK");
 		fallthrough;
 	case SMU_MCLK:
 		ret = aldebaran_get_current_clk_freq_by_table(smu, SMU_UCLK, &now);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
index 627ba2eec7fd..a403657151ba 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
@@ -1052,16 +1052,18 @@ static int yellow_carp_print_clk_levels(struct smu_context *smu,
 	int i, size = 0, ret = 0;
 	uint32_t cur_value = 0, value = 0, count = 0;
 
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
 	switch (clk_type) {
 	case SMU_OD_SCLK:
-		size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+		size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
 		size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 		(smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq);
 		size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
 		(smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq);
 		break;
 	case SMU_OD_RANGE:
-		size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+		size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 		size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
 						smu->gfx_default_hard_min_freq, smu->gfx_default_soft_max_freq);
 		break;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index 66711ab24c15..843d2cbfc71d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -1053,3 +1053,24 @@ int smu_cmn_set_mp1_state(struct smu_context *smu,
 
 	return ret;
 }
+
+bool smu_cmn_is_audio_func_enabled(struct amdgpu_device *adev)
+{
+	struct pci_dev *p = NULL;
+	bool snd_driver_loaded;
+
+	/*
+	 * If the ASIC comes with no audio function, we always assume
+	 * it is "enabled".
+	 */
+	p = pci_get_domain_bus_and_slot(pci_domain_nr(adev->pdev->bus),
+			adev->pdev->bus->number, 1);
+	if (!p)
+		return true;
+
+	snd_driver_loaded = pci_is_enabled(p) ? true : false;
+
+	pci_dev_put(p);
+
+	return snd_driver_loaded;
+}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
index 16993daa2ae0..beea03810bca 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
@@ -110,5 +110,20 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev);
 int smu_cmn_set_mp1_state(struct smu_context *smu,
 			  enum pp_mp1_state mp1_state);
 
+/*
+ * Helper function to make sysfs_emit_at() happy. Align buf to
+ * the current page boundary and record the offset.
+ */
+static inline void smu_cmn_get_sysfs_buf(char **buf, int *offset)
+{
+	if (!*buf || !offset)
+		return;
+
+	*offset = offset_in_page(*buf);
+	*buf -= *offset;
+}
+
+bool smu_cmn_is_audio_func_enabled(struct amdgpu_device *adev);
+
 #endif
 #endif
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 6325877c5fd6..ea9a79bc9583 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -1834,11 +1834,20 @@ static void connector_bad_edid(struct drm_connector *connector,
 			       u8 *edid, int num_blocks)
 {
 	int i;
-	u8 num_of_ext = edid[0x7e];
+	u8 last_block;
+
+	/*
+	 * 0x7e in the EDID is the number of extension blocks. The EDID
+	 * is 1 (base block) + num_ext_blocks big. That means we can think
+	 * of 0x7e in the EDID of the _index_ of the last block in the
+	 * combined chunk of memory.
+	 */
+	last_block = edid[0x7e];
 
 	/* Calculate real checksum for the last edid extension block data */
-	connector->real_edid_checksum =
-		drm_edid_block_checksum(edid + num_of_ext * EDID_LENGTH);
+	if (last_block < num_blocks)
+		connector->real_edid_checksum =
+			drm_edid_block_checksum(edid + last_block * EDID_LENGTH);
 
 	if (connector->bad_edid_counter++ && !drm_debug_enabled(DRM_UT_KMS))
 		return;
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 3ab078321045..8e7a124d6c5a 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -1506,6 +1506,7 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
 {
 	struct drm_client_dev *client = &fb_helper->client;
 	struct drm_device *dev = fb_helper->dev;
+	struct drm_mode_config *config = &dev->mode_config;
 	int ret = 0;
 	int crtc_count = 0;
 	struct drm_connector_list_iter conn_iter;
@@ -1663,6 +1664,11 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
 	/* Handle our overallocation */
 	sizes.surface_height *= drm_fbdev_overalloc;
 	sizes.surface_height /= 100;
+	if (sizes.surface_height > config->max_height) {
+		drm_dbg_kms(dev, "Fbdev over-allocation too large; clamping height to %d\n",
+			    config->max_height);
+		sizes.surface_height = config->max_height;
+	}
 
 	/* push down into drivers */
 	ret = (*fb_helper->funcs->fb_probe)(fb_helper, &sizes);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
index 76d38561c910..cf741c5c82d2 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
@@ -397,8 +397,7 @@ void etnaviv_buffer_queue(struct etnaviv_gpu *gpu, u32 exec_state,
 		if (switch_mmu_context) {
 			struct etnaviv_iommu_context *old_context = gpu->mmu_context;
 
-			etnaviv_iommu_context_get(mmu_context);
-			gpu->mmu_context = mmu_context;
+			gpu->mmu_context = etnaviv_iommu_context_get(mmu_context);
 			etnaviv_iommu_context_put(old_context);
 		}
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 8f1b5af47dd6..f0b2540e60e4 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -294,8 +294,7 @@ struct etnaviv_vram_mapping *etnaviv_gem_mapping_get(
 		list_del(&mapping->obj_node);
 	}
 
-	etnaviv_iommu_context_get(mmu_context);
-	mapping->context = mmu_context;
+	mapping->context = etnaviv_iommu_context_get(mmu_context);
 	mapping->use = 1;
 
 	ret = etnaviv_iommu_map_gem(mmu_context, etnaviv_obj,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
index 4dd7d9d541c0..486259e154af 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
@@ -532,8 +532,7 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data,
 		goto err_submit_objects;
 
 	submit->ctx = file->driver_priv;
-	etnaviv_iommu_context_get(submit->ctx->mmu);
-	submit->mmu_context = submit->ctx->mmu;
+	submit->mmu_context = etnaviv_iommu_context_get(submit->ctx->mmu);
 	submit->exec_state = args->exec_state;
 	submit->flags = args->flags;
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index c297fffe06eb..cc5b07f86346 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -569,6 +569,12 @@ static int etnaviv_hw_reset(struct etnaviv_gpu *gpu)
 	/* We rely on the GPU running, so program the clock */
 	etnaviv_gpu_update_clock(gpu);
 
+	gpu->fe_running = false;
+	gpu->exec_state = -1;
+	if (gpu->mmu_context)
+		etnaviv_iommu_context_put(gpu->mmu_context);
+	gpu->mmu_context = NULL;
+
 	return 0;
 }
 
@@ -637,19 +643,23 @@ void etnaviv_gpu_start_fe(struct etnaviv_gpu *gpu, u32 address, u16 prefetch)
 			  VIVS_MMUv2_SEC_COMMAND_CONTROL_ENABLE |
 			  VIVS_MMUv2_SEC_COMMAND_CONTROL_PREFETCH(prefetch));
 	}
+
+	gpu->fe_running = true;
 }
 
-static void etnaviv_gpu_start_fe_idleloop(struct etnaviv_gpu *gpu)
+static void etnaviv_gpu_start_fe_idleloop(struct etnaviv_gpu *gpu,
+					  struct etnaviv_iommu_context *context)
 {
-	u32 address = etnaviv_cmdbuf_get_va(&gpu->buffer,
-				&gpu->mmu_context->cmdbuf_mapping);
 	u16 prefetch;
+	u32 address;
 
 	/* setup the MMU */
-	etnaviv_iommu_restore(gpu, gpu->mmu_context);
+	etnaviv_iommu_restore(gpu, context);
 
 	/* Start command processor */
 	prefetch = etnaviv_buffer_init(gpu);
+	address = etnaviv_cmdbuf_get_va(&gpu->buffer,
+					&gpu->mmu_context->cmdbuf_mapping);
 
 	etnaviv_gpu_start_fe(gpu, address, prefetch);
 }
@@ -832,7 +842,6 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu)
 	/* Now program the hardware */
 	mutex_lock(&gpu->lock);
 	etnaviv_gpu_hw_init(gpu);
-	gpu->exec_state = -1;
 	mutex_unlock(&gpu->lock);
 
 	pm_runtime_mark_last_busy(gpu->dev);
@@ -1057,8 +1066,6 @@ void etnaviv_gpu_recover_hang(struct etnaviv_gpu *gpu)
 	spin_unlock(&gpu->event_spinlock);
 
 	etnaviv_gpu_hw_init(gpu);
-	gpu->exec_state = -1;
-	gpu->mmu_context = NULL;
 
 	mutex_unlock(&gpu->lock);
 	pm_runtime_mark_last_busy(gpu->dev);
@@ -1370,14 +1377,12 @@ struct dma_fence *etnaviv_gpu_submit(struct etnaviv_gem_submit *submit)
 		goto out_unlock;
 	}
 
-	if (!gpu->mmu_context) {
-		etnaviv_iommu_context_get(submit->mmu_context);
-		gpu->mmu_context = submit->mmu_context;
-		etnaviv_gpu_start_fe_idleloop(gpu);
-	} else {
-		etnaviv_iommu_context_get(gpu->mmu_context);
-		submit->prev_mmu_context = gpu->mmu_context;
-	}
+	if (!gpu->fe_running)
+		etnaviv_gpu_start_fe_idleloop(gpu, submit->mmu_context);
+
+	if (submit->prev_mmu_context)
+		etnaviv_iommu_context_put(submit->prev_mmu_context);
+	submit->prev_mmu_context = etnaviv_iommu_context_get(gpu->mmu_context);
 
 	if (submit->nr_pmrs) {
 		gpu->event[event[1]].sync_point = &sync_point_perfmon_sample_pre;
@@ -1579,7 +1584,7 @@ int etnaviv_gpu_wait_idle(struct etnaviv_gpu *gpu, unsigned int timeout_ms)
 
 static int etnaviv_gpu_hw_suspend(struct etnaviv_gpu *gpu)
 {
-	if (gpu->initialized && gpu->mmu_context) {
+	if (gpu->initialized && gpu->fe_running) {
 		/* Replace the last WAIT with END */
 		mutex_lock(&gpu->lock);
 		etnaviv_buffer_end(gpu);
@@ -1592,8 +1597,7 @@ static int etnaviv_gpu_hw_suspend(struct etnaviv_gpu *gpu)
 		 */
 		etnaviv_gpu_wait_idle(gpu, 100);
 
-		etnaviv_iommu_context_put(gpu->mmu_context);
-		gpu->mmu_context = NULL;
+		gpu->fe_running = false;
 	}
 
 	gpu->exec_state = -1;
@@ -1741,6 +1745,9 @@ static void etnaviv_gpu_unbind(struct device *dev, struct device *master,
 	etnaviv_gpu_hw_suspend(gpu);
 #endif
 
+	if (gpu->mmu_context)
+		etnaviv_iommu_context_put(gpu->mmu_context);
+
 	if (gpu->initialized) {
 		etnaviv_cmdbuf_free(&gpu->buffer);
 		etnaviv_iommu_global_fini(gpu);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
index 8ea48697d132..1c75c8ed5bce 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
@@ -101,6 +101,7 @@ struct etnaviv_gpu {
 	struct workqueue_struct *wq;
 	struct drm_gpu_scheduler sched;
 	bool initialized;
+	bool fe_running;
 
 	/* 'ring'-buffer: */
 	struct etnaviv_cmdbuf buffer;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
index 1a7c89a67bea..afe5dd6a9925 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
@@ -92,6 +92,10 @@ static void etnaviv_iommuv1_restore(struct etnaviv_gpu *gpu,
 	struct etnaviv_iommuv1_context *v1_context = to_v1_context(context);
 	u32 pgtable;
 
+	if (gpu->mmu_context)
+		etnaviv_iommu_context_put(gpu->mmu_context);
+	gpu->mmu_context = etnaviv_iommu_context_get(context);
+
 	/* set base addresses */
 	gpu_write(gpu, VIVS_MC_MEMORY_BASE_ADDR_RA, context->global->memory_base);
 	gpu_write(gpu, VIVS_MC_MEMORY_BASE_ADDR_FE, context->global->memory_base);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
index f8bf488e9d71..d664ae29ae20 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
@@ -172,6 +172,10 @@ static void etnaviv_iommuv2_restore_nonsec(struct etnaviv_gpu *gpu,
 	if (gpu_read(gpu, VIVS_MMUv2_CONTROL) & VIVS_MMUv2_CONTROL_ENABLE)
 		return;
 
+	if (gpu->mmu_context)
+		etnaviv_iommu_context_put(gpu->mmu_context);
+	gpu->mmu_context = etnaviv_iommu_context_get(context);
+
 	prefetch = etnaviv_buffer_config_mmuv2(gpu,
 				(u32)v2_context->mtlb_dma,
 				(u32)context->global->bad_page_dma);
@@ -192,6 +196,10 @@ static void etnaviv_iommuv2_restore_sec(struct etnaviv_gpu *gpu,
 	if (gpu_read(gpu, VIVS_MMUv2_SEC_CONTROL) & VIVS_MMUv2_SEC_CONTROL_ENABLE)
 		return;
 
+	if (gpu->mmu_context)
+		etnaviv_iommu_context_put(gpu->mmu_context);
+	gpu->mmu_context = etnaviv_iommu_context_get(context);
+
 	gpu_write(gpu, VIVS_MMUv2_PTA_ADDRESS_LOW,
 		  lower_32_bits(context->global->v2.pta_dma));
 	gpu_write(gpu, VIVS_MMUv2_PTA_ADDRESS_HIGH,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
index dab1b58006d8..9fb1a2aadbcb 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
@@ -199,6 +199,7 @@ static int etnaviv_iommu_find_iova(struct etnaviv_iommu_context *context,
 		 */
 		list_for_each_entry_safe(m, n, &list, scan_node) {
 			etnaviv_iommu_remove_mapping(context, m);
+			etnaviv_iommu_context_put(m->context);
 			m->context = NULL;
 			list_del_init(&m->mmu_node);
 			list_del_init(&m->scan_node);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.h b/drivers/gpu/drm/etnaviv/etnaviv_mmu.h
index d1d6902fd13b..e4a0b7d09c2e 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.h
@@ -105,9 +105,11 @@ void etnaviv_iommu_dump(struct etnaviv_iommu_context *ctx, void *buf);
 struct etnaviv_iommu_context *
 etnaviv_iommu_context_init(struct etnaviv_iommu_global *global,
 			   struct etnaviv_cmdbuf_suballoc *suballoc);
-static inline void etnaviv_iommu_context_get(struct etnaviv_iommu_context *ctx)
+static inline struct etnaviv_iommu_context *
+etnaviv_iommu_context_get(struct etnaviv_iommu_context *ctx)
 {
 	kref_get(&ctx->refcount);
+	return ctx;
 }
 void etnaviv_iommu_context_put(struct etnaviv_iommu_context *ctx);
 void etnaviv_iommu_restore(struct etnaviv_gpu *gpu,
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 9870c4e6af36..b5001db7a95c 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -793,7 +793,6 @@ static int exynos5433_decon_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct decon_context *ctx;
-	struct resource *res;
 	int ret;
 	int i;
 
@@ -818,8 +817,7 @@ static int exynos5433_decon_probe(struct platform_device *pdev)
 		ctx->clks[i] = clk;
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	ctx->addr = devm_ioremap_resource(dev, res);
+	ctx->addr = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(ctx->addr))
 		return PTR_ERR(ctx->addr);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index e39fac889edc..8d137857818c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -1738,7 +1738,6 @@ static const struct component_ops exynos_dsi_component_ops = {
 static int exynos_dsi_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct resource *res;
 	struct exynos_dsi *dsi;
 	int ret, i;
 
@@ -1789,8 +1788,7 @@ static int exynos_dsi_probe(struct platform_device *pdev)
 		}
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	dsi->reg_base = devm_ioremap_resource(dev, res);
+	dsi->reg_base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(dsi->reg_base))
 		return PTR_ERR(dsi->reg_base);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index a3c718148c45..ecfd82d0afb7 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -85,7 +85,6 @@ struct fimc_scaler {
 /*
  * A structure of fimc context.
  *
- * @regs_res: register resources.
  * @regs: memory mapped io registers.
  * @lock: locking of operations.
  * @clocks: fimc clocks.
@@ -103,7 +102,6 @@ struct fimc_context {
 	struct exynos_drm_ipp_formats	*formats;
 	unsigned int			num_formats;
 
-	struct resource	*regs_res;
 	void __iomem	*regs;
 	spinlock_t	lock;
 	struct clk	*clocks[FIMC_CLKS_MAX];
@@ -1327,8 +1325,7 @@ static int fimc_probe(struct platform_device *pdev)
 	ctx->num_formats = num_formats;
 
 	/* resource memory */
-	ctx->regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	ctx->regs = devm_ioremap_resource(dev, ctx->regs_res);
+	ctx->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(ctx->regs))
 		return PTR_ERR(ctx->regs);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 700ca4fa6665..c735e53939d8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -1202,9 +1202,7 @@ static int fimd_probe(struct platform_device *pdev)
 		return PTR_ERR(ctx->lcd_clk);
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-
-	ctx->regs = devm_ioremap_resource(dev, res);
+	ctx->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(ctx->regs))
 		return PTR_ERR(ctx->regs);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index b00230626c6a..471fd6c8135f 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -1449,7 +1449,6 @@ static const struct component_ops g2d_component_ops = {
 static int g2d_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct resource *res;
 	struct g2d_data *g2d;
 	int ret;
 
@@ -1491,9 +1490,7 @@ static int g2d_probe(struct platform_device *pdev)
 	clear_bit(G2D_BIT_SUSPEND_RUNQUEUE, &g2d->flags);
 	clear_bit(G2D_BIT_ENGINE_BUSY, &g2d->flags);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-
-	g2d->regs = devm_ioremap_resource(dev, res);
+	g2d->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(g2d->regs)) {
 		ret = PTR_ERR(g2d->regs);
 		goto err_put_clk;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index 90d7bf906885..166a80262896 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -86,7 +86,6 @@ struct gsc_scaler {
 /*
  * A structure of gsc context.
  *
- * @regs_res: register resources.
  * @regs: memory mapped io registers.
  * @gsc_clk: gsc gate clock.
  * @sc: scaler infomations.
@@ -103,7 +102,6 @@ struct gsc_context {
 	struct exynos_drm_ipp_formats	*formats;
 	unsigned int			num_formats;
 
-	struct resource	*regs_res;
 	void __iomem	*regs;
 	const char	**clk_names;
 	struct clk	*clocks[GSC_MAX_CLOCKS];
@@ -1272,9 +1270,7 @@ static int gsc_probe(struct platform_device *pdev)
 		}
 	}
 
-	/* resource memory */
-	ctx->regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	ctx->regs = devm_ioremap_resource(dev, ctx->regs_res);
+	ctx->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(ctx->regs))
 		return PTR_ERR(ctx->regs);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index ee61be4cf152..dec7df35baa9 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -278,7 +278,6 @@ static const struct component_ops rotator_component_ops = {
 static int rotator_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct resource	*regs_res;
 	struct rot_context *rot;
 	const struct rot_variant *variant;
 	int irq;
@@ -292,8 +291,7 @@ static int rotator_probe(struct platform_device *pdev)
 	rot->formats = variant->formats;
 	rot->num_formats = variant->num_formats;
 	rot->dev = dev;
-	regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	rot->regs = devm_ioremap_resource(dev, regs_res);
+	rot->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(rot->regs))
 		return PTR_ERR(rot->regs);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_scaler.c b/drivers/gpu/drm/exynos/exynos_drm_scaler.c
index f9ae5b038d59..3a7851b7dc66 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_scaler.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_scaler.c
@@ -485,7 +485,6 @@ static const struct component_ops scaler_component_ops = {
 static int scaler_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct resource	*regs_res;
 	struct scaler_context *scaler;
 	int irq;
 	int ret, i;
@@ -498,8 +497,7 @@ static int scaler_probe(struct platform_device *pdev)
 		(struct scaler_data *)of_device_get_match_data(dev);
 
 	scaler->dev = dev;
-	regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	scaler->regs = devm_ioremap_resource(dev, regs_res);
+	scaler->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(scaler->regs))
 		return PTR_ERR(scaler->regs);
 
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index c769dec576de..7655142a4651 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -1957,7 +1957,6 @@ static int hdmi_probe(struct platform_device *pdev)
 	struct hdmi_audio_infoframe *audio_infoframe;
 	struct device *dev = &pdev->dev;
 	struct hdmi_context *hdata;
-	struct resource *res;
 	int ret;
 
 	hdata = devm_kzalloc(dev, sizeof(struct hdmi_context), GFP_KERNEL);
@@ -1979,8 +1978,7 @@ static int hdmi_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	hdata->regs = devm_ioremap_resource(dev, res);
+	hdata->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(hdata->regs)) {
 		ret = PTR_ERR(hdata->regs);
 		return ret;
diff --git a/drivers/gpu/drm/hyperv/hyperv_drm.h b/drivers/gpu/drm/hyperv/hyperv_drm.h
index 886add4f9cd0..d2d8582b36df 100644
--- a/drivers/gpu/drm/hyperv/hyperv_drm.h
+++ b/drivers/gpu/drm/hyperv/hyperv_drm.h
@@ -46,6 +46,7 @@ int hyperv_mode_config_init(struct hyperv_drm_device *hv);
 int hyperv_update_vram_location(struct hv_device *hdev, phys_addr_t vram_pp);
 int hyperv_update_situation(struct hv_device *hdev, u8 active, u32 bpp,
 			    u32 w, u32 h, u32 pitch);
+int hyperv_hide_hw_ptr(struct hv_device *hdev);
 int hyperv_update_dirt(struct hv_device *hdev, struct drm_rect *rect);
 int hyperv_connect_vsp(struct hv_device *hdev);
 
diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c b/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c
index 6dd4717d3e1e..8c97a20dfe23 100644
--- a/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c
+++ b/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c
@@ -101,6 +101,7 @@ static void hyperv_pipe_enable(struct drm_simple_display_pipe *pipe,
 	struct hyperv_drm_device *hv = to_hv(pipe->crtc.dev);
 	struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(plane_state);
 
+	hyperv_hide_hw_ptr(hv->hdev);
 	hyperv_update_situation(hv->hdev, 1,  hv->screen_depth,
 				crtc_state->mode.hdisplay,
 				crtc_state->mode.vdisplay,
diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_proto.c b/drivers/gpu/drm/hyperv/hyperv_drm_proto.c
index 6d4bdccfbd1a..c0155c6271bf 100644
--- a/drivers/gpu/drm/hyperv/hyperv_drm_proto.c
+++ b/drivers/gpu/drm/hyperv/hyperv_drm_proto.c
@@ -299,6 +299,55 @@ int hyperv_update_situation(struct hv_device *hdev, u8 active, u32 bpp,
 	return 0;
 }
 
+/*
+ * Hyper-V supports a hardware cursor feature. It's not used by Linux VM,
+ * but the Hyper-V host still draws a point as an extra mouse pointer,
+ * which is unwanted, especially when Xorg is running.
+ *
+ * The hyperv_fb driver uses synthvid_send_ptr() to hide the unwanted
+ * pointer, by setting msg.ptr_pos.is_visible = 1 and setting the
+ * msg.ptr_shape.data. Note: setting msg.ptr_pos.is_visible to 0 doesn't
+ * work in tests.
+ *
+ * Copy synthvid_send_ptr() to hyperv_drm and rename it to
+ * hyperv_hide_hw_ptr(). Note: hyperv_hide_hw_ptr() is also called in the
+ * handler of the SYNTHVID_FEATURE_CHANGE event, otherwise the host still
+ * draws an extra unwanted mouse pointer after the VM Connection window is
+ * closed and reopened.
+ */
+int hyperv_hide_hw_ptr(struct hv_device *hdev)
+{
+	struct synthvid_msg msg;
+
+	memset(&msg, 0, sizeof(struct synthvid_msg));
+	msg.vid_hdr.type = SYNTHVID_POINTER_POSITION;
+	msg.vid_hdr.size = sizeof(struct synthvid_msg_hdr) +
+		sizeof(struct synthvid_pointer_position);
+	msg.ptr_pos.is_visible = 1;
+	msg.ptr_pos.video_output = 0;
+	msg.ptr_pos.image_x = 0;
+	msg.ptr_pos.image_y = 0;
+	hyperv_sendpacket(hdev, &msg);
+
+	memset(&msg, 0, sizeof(struct synthvid_msg));
+	msg.vid_hdr.type = SYNTHVID_POINTER_SHAPE;
+	msg.vid_hdr.size = sizeof(struct synthvid_msg_hdr) +
+		sizeof(struct synthvid_pointer_shape);
+	msg.ptr_shape.part_idx = SYNTHVID_CURSOR_COMPLETE;
+	msg.ptr_shape.is_argb = 1;
+	msg.ptr_shape.width = 1;
+	msg.ptr_shape.height = 1;
+	msg.ptr_shape.hot_x = 0;
+	msg.ptr_shape.hot_y = 0;
+	msg.ptr_shape.data[0] = 0;
+	msg.ptr_shape.data[1] = 1;
+	msg.ptr_shape.data[2] = 1;
+	msg.ptr_shape.data[3] = 1;
+	hyperv_sendpacket(hdev, &msg);
+
+	return 0;
+}
+
 int hyperv_update_dirt(struct hv_device *hdev, struct drm_rect *rect)
 {
 	struct hyperv_drm_device *hv = hv_get_drvdata(hdev);
@@ -392,8 +441,11 @@ static void hyperv_receive_sub(struct hv_device *hdev)
 		return;
 	}
 
-	if (msg->vid_hdr.type == SYNTHVID_FEATURE_CHANGE)
+	if (msg->vid_hdr.type == SYNTHVID_FEATURE_CHANGE) {
 		hv->dirt_needed = msg->feature_chg.is_dirt_needed;
+		if (hv->dirt_needed)
+			hyperv_hide_hw_ptr(hv->hdev);
+	}
 }
 
 static void hyperv_receive(void *ctx)
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 642a5b5a1b81..335ba9f43d8f 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -19,7 +19,6 @@ subdir-ccflags-y += $(call cc-disable-warning, missing-field-initializers)
 subdir-ccflags-y += $(call cc-disable-warning, unused-but-set-variable)
 # clang warnings
 subdir-ccflags-y += $(call cc-disable-warning, sign-compare)
-subdir-ccflags-y += $(call cc-disable-warning, sometimes-uninitialized)
 subdir-ccflags-y += $(call cc-disable-warning, initializer-overrides)
 subdir-ccflags-y += $(call cc-disable-warning, frame-address)
 subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index 43ec7fcd3f5d..a3eae3f3eadc 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -1577,8 +1577,14 @@ static void gen11_dsi_sync_state(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	struct intel_crtc *intel_crtc;
+	enum pipe pipe;
+
+	if (!crtc_state)
+		return;
+
+	intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	pipe = intel_crtc->pipe;
 
 	/* wa verify 1409054076:icl,jsl,ehl */
 	if (DISPLAY_VER(dev_priv) == 11 && pipe == PIPE_B &&
diff --git a/drivers/gpu/drm/i915/display/intel_acpi.c b/drivers/gpu/drm/i915/display/intel_acpi.c
index 7cfe91fc05f2..68abeaf2d7d4 100644
--- a/drivers/gpu/drm/i915/display/intel_acpi.c
+++ b/drivers/gpu/drm/i915/display/intel_acpi.c
@@ -186,13 +186,16 @@ void intel_dsm_get_bios_data_funcs_supported(struct drm_i915_private *i915)
 {
 	struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
 	acpi_handle dhandle;
+	union acpi_object *obj;
 
 	dhandle = ACPI_HANDLE(&pdev->dev);
 	if (!dhandle)
 		return;
 
-	acpi_evaluate_dsm(dhandle, &intel_dsm_guid2, INTEL_DSM_REVISION_ID,
-			  INTEL_DSM_FN_GET_BIOS_DATA_FUNCS_SUPPORTED, NULL);
+	obj = acpi_evaluate_dsm(dhandle, &intel_dsm_guid2, INTEL_DSM_REVISION_ID,
+				INTEL_DSM_FN_GET_BIOS_DATA_FUNCS_SUPPORTED, NULL);
+	if (obj)
+		ACPI_FREE(obj);
 }
 
 /*
diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index 532237588511..4e0f96bf6158 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -1308,8 +1308,9 @@ static void i915_audio_component_init(struct drm_i915_private *dev_priv)
 		else
 			aud_freq = aud_freq_init;
 
-		/* use BIOS provided value for TGL unless it is a known bad value */
-		if (IS_TIGERLAKE(dev_priv) && aud_freq_init != AUD_FREQ_TGL_BROKEN)
+		/* use BIOS provided value for TGL and RKL unless it is a known bad value */
+		if ((IS_TIGERLAKE(dev_priv) || IS_ROCKETLAKE(dev_priv)) &&
+		    aud_freq_init != AUD_FREQ_TGL_BROKEN)
 			aud_freq = aud_freq_init;
 
 		drm_dbg_kms(&dev_priv->drm, "use AUD_FREQ_CNTRL of 0x%x (init value 0x%x)\n",
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index e86e6ed2d3bf..fd71346aac7b 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -451,13 +451,23 @@ parse_lfp_backlight(struct drm_i915_private *i915,
 	}
 
 	i915->vbt.backlight.type = INTEL_BACKLIGHT_DISPLAY_DDI;
-	if (bdb->version >= 191 &&
-	    get_blocksize(backlight_data) >= sizeof(*backlight_data)) {
-		const struct lfp_backlight_control_method *method;
+	if (bdb->version >= 191) {
+		size_t exp_size;
 
-		method = &backlight_data->backlight_control[panel_type];
-		i915->vbt.backlight.type = method->type;
-		i915->vbt.backlight.controller = method->controller;
+		if (bdb->version >= 236)
+			exp_size = sizeof(struct bdb_lfp_backlight_data);
+		else if (bdb->version >= 234)
+			exp_size = EXP_BDB_LFP_BL_DATA_SIZE_REV_234;
+		else
+			exp_size = EXP_BDB_LFP_BL_DATA_SIZE_REV_191;
+
+		if (get_blocksize(backlight_data) >= exp_size) {
+			const struct lfp_backlight_control_method *method;
+
+			method = &backlight_data->backlight_control[panel_type];
+			i915->vbt.backlight.type = method->type;
+			i915->vbt.backlight.controller = method->controller;
+		}
 	}
 
 	i915->vbt.backlight.pwm_freq_hz = entry->pwm_freq_hz;
diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c
index e91e0e0191fb..4b94256d7319 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.c
+++ b/drivers/gpu/drm/i915/display/intel_bw.c
@@ -222,31 +222,42 @@ static int icl_sagv_max_dclk(const struct intel_qgv_info *qi)
 
 struct intel_sa_info {
 	u16 displayrtids;
-	u8 deburst, deprogbwlimit;
+	u8 deburst, deprogbwlimit, derating;
 };
 
 static const struct intel_sa_info icl_sa_info = {
 	.deburst = 8,
 	.deprogbwlimit = 25, /* GB/s */
 	.displayrtids = 128,
+	.derating = 10,
 };
 
 static const struct intel_sa_info tgl_sa_info = {
 	.deburst = 16,
 	.deprogbwlimit = 34, /* GB/s */
 	.displayrtids = 256,
+	.derating = 10,
 };
 
 static const struct intel_sa_info rkl_sa_info = {
 	.deburst = 16,
 	.deprogbwlimit = 20, /* GB/s */
 	.displayrtids = 128,
+	.derating = 10,
 };
 
 static const struct intel_sa_info adls_sa_info = {
 	.deburst = 16,
 	.deprogbwlimit = 38, /* GB/s */
 	.displayrtids = 256,
+	.derating = 10,
+};
+
+static const struct intel_sa_info adlp_sa_info = {
+	.deburst = 16,
+	.deprogbwlimit = 38, /* GB/s */
+	.displayrtids = 256,
+	.derating = 20,
 };
 
 static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel_sa_info *sa)
@@ -302,7 +313,7 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel
 			bw = icl_calc_bw(sp->dclk, clpchgroup * 32 * num_channels, ct);
 
 			bi->deratedbw[j] = min(maxdebw,
-					       bw * 9 / 10); /* 90% */
+					       bw * (100 - sa->derating) / 100);
 
 			drm_dbg_kms(&dev_priv->drm,
 				    "BW%d / QGV %d: num_planes=%d deratedbw=%u\n",
@@ -400,7 +411,9 @@ void intel_bw_init_hw(struct drm_i915_private *dev_priv)
 
 	if (IS_DG2(dev_priv))
 		dg2_get_bw_info(dev_priv);
-	else if (IS_ALDERLAKE_S(dev_priv) || IS_ALDERLAKE_P(dev_priv))
+	else if (IS_ALDERLAKE_P(dev_priv))
+		icl_get_bw_info(dev_priv, &adlp_sa_info);
+	else if (IS_ALDERLAKE_S(dev_priv))
 		icl_get_bw_info(dev_priv, &adls_sa_info);
 	else if (IS_ROCKETLAKE(dev_priv))
 		icl_get_bw_info(dev_priv, &rkl_sa_info);
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 9903a78df896..bd184325d0c7 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -3807,7 +3807,13 @@ void hsw_ddi_get_config(struct intel_encoder *encoder,
 static void intel_ddi_sync_state(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *crtc_state)
 {
-	if (intel_crtc_has_dp_encoder(crtc_state))
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	enum phy phy = intel_port_to_phy(i915, encoder->port);
+
+	if (intel_phy_is_tc(i915, phy))
+		intel_tc_port_sanitize(enc_to_dig_port(encoder));
+
+	if (crtc_state && intel_crtc_has_dp_encoder(crtc_state))
 		intel_dp_sync_state(encoder, crtc_state);
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 134a6acbd8fb..17f44ffea586 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -13082,18 +13082,16 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 	readout_plane_state(dev_priv);
 
 	for_each_intel_encoder(dev, encoder) {
+		struct intel_crtc_state *crtc_state = NULL;
+
 		pipe = 0;
 
 		if (encoder->get_hw_state(encoder, &pipe)) {
-			struct intel_crtc_state *crtc_state;
-
 			crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
 			crtc_state = to_intel_crtc_state(crtc->base.state);
 
 			encoder->base.crtc = &crtc->base;
 			intel_encoder_get_config(encoder, crtc_state);
-			if (encoder->sync_state)
-				encoder->sync_state(encoder, crtc_state);
 
 			/* read out to slave crtc as well for bigjoiner */
 			if (crtc_state->bigjoiner) {
@@ -13108,6 +13106,9 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			encoder->base.crtc = NULL;
 		}
 
+		if (encoder->sync_state)
+			encoder->sync_state(encoder, crtc_state);
+
 		drm_dbg_kms(&dev_priv->drm,
 			    "[ENCODER:%d:%s] hw state readout: %s, pipe %c\n",
 			    encoder->base.base.id, encoder->base.name,
@@ -13390,17 +13391,6 @@ intel_modeset_setup_hw_state(struct drm_device *dev,
 	intel_modeset_readout_hw_state(dev);
 
 	/* HW state is read out, now we need to sanitize this mess. */
-
-	/* Sanitize the TypeC port mode upfront, encoders depend on this */
-	for_each_intel_encoder(dev, encoder) {
-		enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
-
-		/* We need to sanitize only the MST primary port. */
-		if (encoder->type != INTEL_OUTPUT_DP_MST &&
-		    intel_phy_is_tc(dev_priv, phy))
-			intel_tc_port_sanitize(enc_to_dig_port(encoder));
-	}
-
 	get_encoder_power_domains(dev_priv);
 
 	if (HAS_PCH_IBX(dev_priv))
diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c
index 3c3c6cb5c0df..b3c8e1c450ef 100644
--- a/drivers/gpu/drm/i915/display/intel_dmc.c
+++ b/drivers/gpu/drm/i915/display/intel_dmc.c
@@ -805,11 +805,14 @@ void intel_dmc_ucode_resume(struct drm_i915_private *dev_priv)
  */
 void intel_dmc_ucode_fini(struct drm_i915_private *dev_priv)
 {
+	int id;
+
 	if (!HAS_DMC(dev_priv))
 		return;
 
 	intel_dmc_ucode_suspend(dev_priv);
 	drm_WARN_ON(&dev_priv->drm, dev_priv->dmc.wakeref);
 
-	kfree(dev_priv->dmc.dmc_info[DMC_FW_MAIN].payload);
+	for (id = 0; id < DMC_FW_MAX; id++)
+		kfree(dev_priv->dmc.dmc_info[id].payload);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 04175f359fd6..abe3d61b6243 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2445,11 +2445,14 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp)
 	 */
 	if (drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_DPCD_REV,
 			     intel_dp->edp_dpcd, sizeof(intel_dp->edp_dpcd)) ==
-			     sizeof(intel_dp->edp_dpcd))
+			     sizeof(intel_dp->edp_dpcd)) {
 		drm_dbg_kms(&dev_priv->drm, "eDP DPCD: %*ph\n",
 			    (int)sizeof(intel_dp->edp_dpcd),
 			    intel_dp->edp_dpcd);
 
+		intel_dp->use_max_params = intel_dp->edp_dpcd[0] < DP_EDP_14;
+	}
+
 	/*
 	 * This has to be called after intel_dp->edp_dpcd is filled, PSR checks
 	 * for SET_POWER_CAPABLE bit in intel_dp->edp_dpcd[1]
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 053a3c2f7267..508a514c5e37 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -848,7 +848,7 @@ intel_dp_link_train_all_phys(struct intel_dp *intel_dp,
 	}
 
 	if (ret)
-		intel_dp_link_train_phy(intel_dp, crtc_state, DP_PHY_DPRX);
+		ret = intel_dp_link_train_phy(intel_dp, crtc_state, DP_PHY_DPRX);
 
 	if (intel_dp->set_idle_link_train)
 		intel_dp->set_idle_link_train(intel_dp, crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
index 330077c2e588..a2108a8f544d 100644
--- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
@@ -814,6 +814,11 @@ struct lfp_brightness_level {
 	u16 reserved;
 } __packed;
 
+#define EXP_BDB_LFP_BL_DATA_SIZE_REV_191 \
+	offsetof(struct bdb_lfp_backlight_data, brightness_level)
+#define EXP_BDB_LFP_BL_DATA_SIZE_REV_234 \
+	offsetof(struct bdb_lfp_backlight_data, brightness_precision_bits)
+
 struct bdb_lfp_backlight_data {
 	u8 entry_size;
 	struct lfp_backlight_data_entry data[16];
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index cff72679ad7c..166bb46408a9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -937,6 +937,10 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx,
 	unsigned int n;
 
 	e = alloc_engines(num_engines);
+	if (!e)
+		return ERR_PTR(-ENOMEM);
+	e->num_engines = num_engines;
+
 	for (n = 0; n < num_engines; n++) {
 		struct intel_context *ce;
 		int ret;
@@ -970,7 +974,6 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx,
 			goto free_engines;
 		}
 	}
-	e->num_engines = num_engines;
 
 	return e;
 
@@ -986,6 +989,9 @@ void i915_gem_context_release(struct kref *ref)
 	trace_i915_context_free(ctx);
 	GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
 
+	if (ctx->syncobj)
+		drm_syncobj_put(ctx->syncobj);
+
 	mutex_destroy(&ctx->engines_mutex);
 	mutex_destroy(&ctx->lut_mutex);
 
@@ -1205,9 +1211,6 @@ static void context_close(struct i915_gem_context *ctx)
 	if (vm)
 		i915_vm_close(vm);
 
-	if (ctx->syncobj)
-		drm_syncobj_put(ctx->syncobj);
-
 	ctx->file_priv = ERR_PTR(-EBADF);
 
 	/*
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index e382b7f2353b..5ab136ffdeb2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -118,7 +118,7 @@ i915_gem_shrink(struct i915_gem_ww_ctx *ww,
 	intel_wakeref_t wakeref = 0;
 	unsigned long count = 0;
 	unsigned long scanned = 0;
-	int err;
+	int err = 0;
 
 	/* CHV + VTD workaround use stop_machine(); need to trylock vm->mutex */
 	bool trylock_vm = !ww && intel_vm_no_concurrent_access_wa(i915);
@@ -242,12 +242,15 @@ skip:
 		list_splice_tail(&still_in_list, phase->list);
 		spin_unlock_irqrestore(&i915->mm.obj_lock, flags);
 		if (err)
-			return err;
+			break;
 	}
 
 	if (shrink & I915_SHRINK_BOUND)
 		intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 
+	if (err)
+		return err;
+
 	if (nr_scanned)
 		*nr_scanned += scanned;
 	return count;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 35eedc14f522..6ea13159bffc 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -356,11 +356,8 @@ static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo)
 {
 	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
 
-	if (likely(obj)) {
-		/* This releases all gem object bindings to the backend. */
+	if (likely(obj))
 		i915_ttm_free_cached_io_st(obj);
-		__i915_gem_free_object(obj);
-	}
 }
 
 static struct intel_memory_region *
@@ -875,8 +872,12 @@ void i915_ttm_bo_destroy(struct ttm_buffer_object *bo)
 {
 	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
 
+	/* This releases all gem object bindings to the backend. */
+	__i915_gem_free_object(obj);
+
 	i915_gem_object_release_memory_region(obj);
 	mutex_destroy(&obj->ttm.get_io_page.lock);
+
 	if (obj->ttm.created)
 		call_rcu(&obj->rcu, __i915_gem_free_object_rcu);
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
index ffae7df5e4d7..4a6bb64c3a35 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
@@ -59,13 +59,13 @@ static int igt_dmabuf_import_self(void *arg)
 		err = PTR_ERR(import);
 		goto out_dmabuf;
 	}
+	import_obj = to_intel_bo(import);
 
 	if (import != &obj->base) {
 		pr_err("i915_gem_prime_import created a new object!\n");
 		err = -EINVAL;
 		goto out_import;
 	}
-	import_obj = to_intel_bo(import);
 
 	i915_gem_object_lock(import_obj, NULL);
 	err = __i915_gem_object_get_pages(import_obj);
@@ -128,6 +128,8 @@ static int igt_dmabuf_import_same_driver_lmem(void *arg)
 		pr_err("i915_gem_prime_import failed with the wrong err=%ld\n",
 		       PTR_ERR(import));
 		err = PTR_ERR(import);
+	} else {
+		err = 0;
 	}
 
 	dma_buf_put(dmabuf);
@@ -176,6 +178,7 @@ static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915,
 		err = PTR_ERR(import);
 		goto out_dmabuf;
 	}
+	import_obj = to_intel_bo(import);
 
 	if (import == &obj->base) {
 		pr_err("i915_gem_prime_import reused gem object!\n");
@@ -183,8 +186,6 @@ static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915,
 		goto out_import;
 	}
 
-	import_obj = to_intel_bo(import);
-
 	i915_gem_object_lock(import_obj, NULL);
 	err = __i915_gem_object_get_pages(import_obj);
 	if (err) {
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index b20f5621f62b..a2c34e5a1c54 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -581,6 +581,20 @@ static enum i915_mmap_type default_mapping(struct drm_i915_private *i915)
 	return I915_MMAP_TYPE_GTT;
 }
 
+static struct drm_i915_gem_object *
+create_sys_or_internal(struct drm_i915_private *i915,
+		       unsigned long size)
+{
+	if (HAS_LMEM(i915)) {
+		struct intel_memory_region *sys_region =
+			i915->mm.regions[INTEL_REGION_SMEM];
+
+		return __i915_gem_object_create_user(i915, size, &sys_region, 1);
+	}
+
+	return i915_gem_object_create_internal(i915, size);
+}
+
 static bool assert_mmap_offset(struct drm_i915_private *i915,
 			       unsigned long size,
 			       int expected)
@@ -589,7 +603,7 @@ static bool assert_mmap_offset(struct drm_i915_private *i915,
 	u64 offset;
 	int ret;
 
-	obj = i915_gem_object_create_internal(i915, size);
+	obj = create_sys_or_internal(i915, size);
 	if (IS_ERR(obj))
 		return expected && expected == PTR_ERR(obj);
 
@@ -633,6 +647,7 @@ static int igt_mmap_offset_exhaustion(void *arg)
 	struct drm_mm_node *hole, *next;
 	int loop, err = 0;
 	u64 offset;
+	int enospc = HAS_LMEM(i915) ? -ENXIO : -ENOSPC;
 
 	/* Disable background reaper */
 	disable_retire_worker(i915);
@@ -683,14 +698,14 @@ static int igt_mmap_offset_exhaustion(void *arg)
 	}
 
 	/* Too large */
-	if (!assert_mmap_offset(i915, 2 * PAGE_SIZE, -ENOSPC)) {
+	if (!assert_mmap_offset(i915, 2 * PAGE_SIZE, enospc)) {
 		pr_err("Unexpectedly succeeded in inserting too large object into single page hole\n");
 		err = -EINVAL;
 		goto out;
 	}
 
 	/* Fill the hole, further allocation attempts should then fail */
-	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	obj = create_sys_or_internal(i915, PAGE_SIZE);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
 		pr_err("Unable to create object for reclaimed hole\n");
@@ -703,7 +718,7 @@ static int igt_mmap_offset_exhaustion(void *arg)
 		goto err_obj;
 	}
 
-	if (!assert_mmap_offset(i915, PAGE_SIZE, -ENOSPC)) {
+	if (!assert_mmap_offset(i915, PAGE_SIZE, enospc)) {
 		pr_err("Unexpectedly succeeded in inserting object into no holes!\n");
 		err = -EINVAL;
 		goto err_obj;
@@ -839,10 +854,9 @@ static int wc_check(struct drm_i915_gem_object *obj)
 
 static bool can_mmap(struct drm_i915_gem_object *obj, enum i915_mmap_type type)
 {
-	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	bool no_map;
 
-	if (HAS_LMEM(i915))
+	if (obj->ops->mmap_offset)
 		return type == I915_MMAP_TYPE_FIXED;
 	else if (type == I915_MMAP_TYPE_FIXED)
 		return false;
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 745e84c72c90..17ca4dc4d0cb 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -362,8 +362,9 @@ static int __intel_context_active(struct i915_active *active)
 	return 0;
 }
 
-static int sw_fence_dummy_notify(struct i915_sw_fence *sf,
-				 enum i915_sw_fence_notify state)
+static int __i915_sw_fence_call
+sw_fence_dummy_notify(struct i915_sw_fence *sf,
+		      enum i915_sw_fence_notify state)
 {
 	return NOTIFY_DONE;
 }
@@ -420,6 +421,7 @@ void intel_context_fini(struct intel_context *ce)
 
 	mutex_destroy(&ce->pin_mutex);
 	i915_active_fini(&ce->active);
+	i915_sw_fence_fini(&ce->guc_blocked);
 }
 
 void i915_context_module_exit(void)
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index d812b27835f8..0a03fbed9f9b 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -882,8 +882,6 @@ void intel_rps_park(struct intel_rps *rps)
 	if (!intel_rps_is_enabled(rps))
 		return;
 
-	GEM_BUG_ON(atomic_read(&rps->num_waiters));
-
 	if (!intel_rps_clear_active(rps))
 		return;
 
@@ -1973,8 +1971,14 @@ u32 intel_rps_read_actual_frequency(struct intel_rps *rps)
 u32 intel_rps_read_punit_req(struct intel_rps *rps)
 {
 	struct intel_uncore *uncore = rps_to_uncore(rps);
+	struct intel_runtime_pm *rpm = rps_to_uncore(rps)->rpm;
+	intel_wakeref_t wakeref;
+	u32 freq = 0;
 
-	return intel_uncore_read(uncore, GEN6_RPNSWREQ);
+	with_intel_runtime_pm_if_in_use(rpm, wakeref)
+		freq = intel_uncore_read(uncore, GEN6_RPNSWREQ);
+
+	return freq;
 }
 
 static u32 intel_rps_get_req(u32 pureq)
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h
index 99e1fad5ca20..c9086a600bce 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h
@@ -102,11 +102,11 @@ static_assert(sizeof(struct guc_ct_buffer_desc) == 64);
  *  |   +-------+--------------------------------------------------------------+
  *  |   |   7:0 | NUM_DWORDS = length (in dwords) of the embedded HXG message  |
  *  +---+-------+--------------------------------------------------------------+
- *  | 1 |  31:0 |  +--------------------------------------------------------+  |
- *  +---+-------+  |                                                        |  |
- *  |...|       |  |  Embedded `HXG Message`_                               |  |
- *  +---+-------+  |                                                        |  |
- *  | n |  31:0 |  +--------------------------------------------------------+  |
+ *  | 1 |  31:0 |                                                              |
+ *  +---+-------+                                                              |
+ *  |...|       | [Embedded `HXG Message`_]                                    |
+ *  +---+-------+                                                              |
+ *  | n |  31:0 |                                                              |
  *  +---+-------+--------------------------------------------------------------+
  */
 
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h
index bbf1ddb77434..9baa3cb07d13 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h
@@ -38,11 +38,11 @@
  *  +---+-------+--------------------------------------------------------------+
  *  |   | Bits  | Description                                                  |
  *  +===+=======+==============================================================+
- *  | 0 |  31:0 |  +--------------------------------------------------------+  |
- *  +---+-------+  |                                                        |  |
- *  |...|       |  |  Embedded `HXG Message`_                               |  |
- *  +---+-------+  |                                                        |  |
- *  | n |  31:0 |  +--------------------------------------------------------+  |
+ *  | 0 |  31:0 |                                                              |
+ *  +---+-------+                                                              |
+ *  |...|       | [Embedded `HXG Message`_]                                    |
+ *  +---+-------+                                                              |
+ *  | n |  31:0 |                                                              |
  *  +---+-------+--------------------------------------------------------------+
  */
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index b104fb7607eb..86c318516e14 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -172,11 +172,6 @@ void intel_uc_driver_remove(struct intel_uc *uc)
 	__uc_free_load_err_log(uc);
 }
 
-static inline bool guc_communication_enabled(struct intel_guc *guc)
-{
-	return intel_guc_ct_enabled(&guc->ct);
-}
-
 /*
  * Events triggered while CT buffers are disabled are logged in the SCRATCH_15
  * register using the same bits used in the CT message payload. Since our
@@ -210,7 +205,7 @@ static void guc_get_mmio_msg(struct intel_guc *guc)
 static void guc_handle_mmio_msg(struct intel_guc *guc)
 {
 	/* we need communication to be enabled to reply to GuC */
-	GEM_BUG_ON(!guc_communication_enabled(guc));
+	GEM_BUG_ON(!intel_guc_ct_enabled(&guc->ct));
 
 	spin_lock_irq(&guc->irq_lock);
 	if (guc->mmio_msg) {
@@ -226,7 +221,7 @@ static int guc_enable_communication(struct intel_guc *guc)
 	struct drm_i915_private *i915 = gt->i915;
 	int ret;
 
-	GEM_BUG_ON(guc_communication_enabled(guc));
+	GEM_BUG_ON(intel_guc_ct_enabled(&guc->ct));
 
 	ret = i915_inject_probe_error(i915, -ENXIO);
 	if (ret)
@@ -662,7 +657,7 @@ static int __uc_resume(struct intel_uc *uc, bool enable_communication)
 		return 0;
 
 	/* Make sure we enable communication if and only if it's disabled */
-	GEM_BUG_ON(enable_communication == guc_communication_enabled(guc));
+	GEM_BUG_ON(enable_communication == intel_guc_ct_enabled(&guc->ct));
 
 	if (enable_communication)
 		guc_enable_communication(guc);
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index b56a8e37a3cd..1bb1be5c48c8 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -576,7 +576,7 @@ retry:
 
 			/* No one is going to touch shadow bb from now on. */
 			i915_gem_object_flush_map(bb->obj);
-			i915_gem_object_unlock(bb->obj);
+			i915_gem_ww_ctx_fini(&ww);
 		}
 	}
 	return 0;
@@ -630,7 +630,7 @@ retry:
 		return ret;
 	}
 
-	i915_gem_object_unlock(wa_ctx->indirect_ctx.obj);
+	i915_gem_ww_ctx_fini(&ww);
 
 	/* FIXME: we are not tracking our pinned VMA leaving it
 	 * up to the core to fix up the stray pin_count upon
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 664970f2bc62..4037030f0984 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -8193,6 +8193,11 @@ enum {
 #define  HSW_SPR_STRETCH_MAX_X1		REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 3)
 #define  HSW_FBCQ_DIS			(1 << 22)
 #define  BDW_DPRS_MASK_VBLANK_SRD	(1 << 0)
+#define  SKL_PLANE1_STRETCH_MAX_MASK	REG_GENMASK(1, 0)
+#define  SKL_PLANE1_STRETCH_MAX_X8	REG_FIELD_PREP(SKL_PLANE1_STRETCH_MAX_MASK, 0)
+#define  SKL_PLANE1_STRETCH_MAX_X4	REG_FIELD_PREP(SKL_PLANE1_STRETCH_MAX_MASK, 1)
+#define  SKL_PLANE1_STRETCH_MAX_X2	REG_FIELD_PREP(SKL_PLANE1_STRETCH_MAX_MASK, 2)
+#define  SKL_PLANE1_STRETCH_MAX_X1	REG_FIELD_PREP(SKL_PLANE1_STRETCH_MAX_MASK, 3)
 #define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B)
 
 #define _CHICKEN_TRANS_A	0x420c0
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index ce446716d092..79da5eca60af 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -829,8 +829,6 @@ static void __i915_request_ctor(void *arg)
 	i915_sw_fence_init(&rq->submit, submit_notify);
 	i915_sw_fence_init(&rq->semaphore, semaphore_notify);
 
-	dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, 0, 0);
-
 	rq->capture_list = NULL;
 
 	init_llist_head(&rq->execute_cb);
@@ -905,17 +903,12 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->ring = ce->ring;
 	rq->execution_mask = ce->engine->mask;
 
-	kref_init(&rq->fence.refcount);
-	rq->fence.flags = 0;
-	rq->fence.error = 0;
-	INIT_LIST_HEAD(&rq->fence.cb_list);
-
 	ret = intel_timeline_get_seqno(tl, rq, &seqno);
 	if (ret)
 		goto err_free;
 
-	rq->fence.context = tl->fence_context;
-	rq->fence.seqno = seqno;
+	dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock,
+		       tl->fence_context, seqno);
 
 	RCU_INIT_POINTER(rq->timeline, tl);
 	rq->hwsp_seqno = tl->hwsp_seqno;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 65bc3709f54c..a725792d5248 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -76,6 +76,8 @@ struct intel_wm_config {
 
 static void gen9_init_clock_gating(struct drm_i915_private *dev_priv)
 {
+	enum pipe pipe;
+
 	if (HAS_LLC(dev_priv)) {
 		/*
 		 * WaCompressedResourceDisplayNewHashMode:skl,kbl
@@ -89,6 +91,16 @@ static void gen9_init_clock_gating(struct drm_i915_private *dev_priv)
 			   SKL_DE_COMPRESSED_HASH_MODE);
 	}
 
+	for_each_pipe(dev_priv, pipe) {
+		/*
+		 * "Plane N strech max must be programmed to 11b (x1)
+		 *  when Async flips are enabled on that plane."
+		 */
+		if (!IS_GEMINILAKE(dev_priv) && intel_vtd_active())
+			intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
+					 SKL_PLANE1_STRETCH_MAX_MASK, SKL_PLANE1_STRETCH_MAX_X1);
+	}
+
 	/* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,bxt,kbl,cfl */
 	intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR1_1,
 		   intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP);
diff --git a/drivers/gpu/drm/kmb/kmb_drv.c b/drivers/gpu/drm/kmb/kmb_drv.c
index 1c2f4799f421..12ce669650cc 100644
--- a/drivers/gpu/drm/kmb/kmb_drv.c
+++ b/drivers/gpu/drm/kmb/kmb_drv.c
@@ -172,10 +172,10 @@ static int kmb_setup_mode_config(struct drm_device *drm)
 	ret = drmm_mode_config_init(drm);
 	if (ret)
 		return ret;
-	drm->mode_config.min_width = KMB_MIN_WIDTH;
-	drm->mode_config.min_height = KMB_MIN_HEIGHT;
-	drm->mode_config.max_width = KMB_MAX_WIDTH;
-	drm->mode_config.max_height = KMB_MAX_HEIGHT;
+	drm->mode_config.min_width = KMB_FB_MIN_WIDTH;
+	drm->mode_config.min_height = KMB_FB_MIN_HEIGHT;
+	drm->mode_config.max_width = KMB_FB_MAX_WIDTH;
+	drm->mode_config.max_height = KMB_FB_MAX_HEIGHT;
 	drm->mode_config.funcs = &kmb_mode_config_funcs;
 
 	ret = kmb_setup_crtc(drm);
diff --git a/drivers/gpu/drm/kmb/kmb_drv.h b/drivers/gpu/drm/kmb/kmb_drv.h
index ebbaa5f422d5..69a62e2d03ff 100644
--- a/drivers/gpu/drm/kmb/kmb_drv.h
+++ b/drivers/gpu/drm/kmb/kmb_drv.h
@@ -20,6 +20,11 @@
 #define DRIVER_MAJOR			1
 #define DRIVER_MINOR			1
 
+#define KMB_FB_MAX_WIDTH		1920
+#define KMB_FB_MAX_HEIGHT		1080
+#define KMB_FB_MIN_WIDTH		1
+#define KMB_FB_MIN_HEIGHT		1
+
 #define KMB_LCD_DEFAULT_CLK		200000000
 #define KMB_SYS_CLK_MHZ			500
 
diff --git a/drivers/gpu/drm/kmb/kmb_plane.c b/drivers/gpu/drm/kmb/kmb_plane.c
index ecee6782612d..06b0c42c9e91 100644
--- a/drivers/gpu/drm/kmb/kmb_plane.c
+++ b/drivers/gpu/drm/kmb/kmb_plane.c
@@ -94,9 +94,10 @@ static int kmb_plane_atomic_check(struct drm_plane *plane,
 	if (ret)
 		return ret;
 
-	if (new_plane_state->crtc_w > KMB_MAX_WIDTH || new_plane_state->crtc_h > KMB_MAX_HEIGHT)
-		return -EINVAL;
-	if (new_plane_state->crtc_w < KMB_MIN_WIDTH || new_plane_state->crtc_h < KMB_MIN_HEIGHT)
+	if (new_plane_state->crtc_w > KMB_FB_MAX_WIDTH ||
+	    new_plane_state->crtc_h > KMB_FB_MAX_HEIGHT ||
+	    new_plane_state->crtc_w < KMB_FB_MIN_WIDTH ||
+	    new_plane_state->crtc_h < KMB_FB_MIN_HEIGHT)
 		return -EINVAL;
 	can_position = (plane->type == DRM_PLANE_TYPE_OVERLAY);
 	crtc_state =
@@ -277,6 +278,44 @@ static void config_csc(struct kmb_drm_private *kmb, int plane_id)
 	kmb_write_lcd(kmb, LCD_LAYERn_CSC_OFF3(plane_id), csc_coef_lcd[11]);
 }
 
+static void kmb_plane_set_alpha(struct kmb_drm_private *kmb,
+				const struct drm_plane_state *state,
+				unsigned char plane_id,
+				unsigned int *val)
+{
+	u16 plane_alpha = state->alpha;
+	u16 pixel_blend_mode = state->pixel_blend_mode;
+	int has_alpha = state->fb->format->has_alpha;
+
+	if (plane_alpha != DRM_BLEND_ALPHA_OPAQUE)
+		*val |= LCD_LAYER_ALPHA_STATIC;
+
+	if (has_alpha) {
+		switch (pixel_blend_mode) {
+		case DRM_MODE_BLEND_PIXEL_NONE:
+			break;
+		case DRM_MODE_BLEND_PREMULTI:
+			*val |= LCD_LAYER_ALPHA_EMBED | LCD_LAYER_ALPHA_PREMULT;
+			break;
+		case DRM_MODE_BLEND_COVERAGE:
+			*val |= LCD_LAYER_ALPHA_EMBED;
+			break;
+		default:
+			DRM_DEBUG("Missing pixel blend mode case (%s == %ld)\n",
+				  __stringify(pixel_blend_mode),
+				  (long)pixel_blend_mode);
+			break;
+		}
+	}
+
+	if (plane_alpha == DRM_BLEND_ALPHA_OPAQUE && !has_alpha) {
+		*val &= LCD_LAYER_ALPHA_DISABLED;
+		return;
+	}
+
+	kmb_write_lcd(kmb, LCD_LAYERn_ALPHA(plane_id), plane_alpha);
+}
+
 static void kmb_plane_atomic_update(struct drm_plane *plane,
 				    struct drm_atomic_state *state)
 {
@@ -303,11 +342,12 @@ static void kmb_plane_atomic_update(struct drm_plane *plane,
 	fb = new_plane_state->fb;
 	if (!fb)
 		return;
+
 	num_planes = fb->format->num_planes;
 	kmb_plane = to_kmb_plane(plane);
-	plane_id = kmb_plane->id;
 
 	kmb = to_kmb(plane->dev);
+	plane_id = kmb_plane->id;
 
 	spin_lock_irq(&kmb->irq_lock);
 	if (kmb->kmb_under_flow || kmb->kmb_flush_done) {
@@ -400,20 +440,32 @@ static void kmb_plane_atomic_update(struct drm_plane *plane,
 		config_csc(kmb, plane_id);
 	}
 
+	kmb_plane_set_alpha(kmb, plane->state, plane_id, &val);
+
 	kmb_write_lcd(kmb, LCD_LAYERn_CFG(plane_id), val);
 
+	/* Configure LCD_CONTROL */
+	ctrl = kmb_read_lcd(kmb, LCD_CONTROL);
+
+	/* Set layer blending config */
+	ctrl &= ~LCD_CTRL_ALPHA_ALL;
+	ctrl |= LCD_CTRL_ALPHA_BOTTOM_VL1 |
+		LCD_CTRL_ALPHA_BLEND_VL2;
+
+	ctrl &= ~LCD_CTRL_ALPHA_BLEND_BKGND_DISABLE;
+
 	switch (plane_id) {
 	case LAYER_0:
-		ctrl = LCD_CTRL_VL1_ENABLE;
+		ctrl |= LCD_CTRL_VL1_ENABLE;
 		break;
 	case LAYER_1:
-		ctrl = LCD_CTRL_VL2_ENABLE;
+		ctrl |= LCD_CTRL_VL2_ENABLE;
 		break;
 	case LAYER_2:
-		ctrl = LCD_CTRL_GL1_ENABLE;
+		ctrl |= LCD_CTRL_GL1_ENABLE;
 		break;
 	case LAYER_3:
-		ctrl = LCD_CTRL_GL2_ENABLE;
+		ctrl |= LCD_CTRL_GL2_ENABLE;
 		break;
 	}
 
@@ -425,7 +477,7 @@ static void kmb_plane_atomic_update(struct drm_plane *plane,
 	 */
 	ctrl |= LCD_CTRL_VHSYNC_IDLE_LVL;
 
-	kmb_set_bitmask_lcd(kmb, LCD_CONTROL, ctrl);
+	kmb_write_lcd(kmb, LCD_CONTROL, ctrl);
 
 	/* Enable pipeline AXI read transactions for the DMA
 	 * after setting graphics layers. This must be done
@@ -490,6 +542,9 @@ struct kmb_plane *kmb_plane_init(struct drm_device *drm)
 	enum drm_plane_type plane_type;
 	const u32 *plane_formats;
 	int num_plane_formats;
+	unsigned int blend_caps = BIT(DRM_MODE_BLEND_PIXEL_NONE) |
+				  BIT(DRM_MODE_BLEND_PREMULTI)   |
+				  BIT(DRM_MODE_BLEND_COVERAGE);
 
 	for (i = 0; i < KMB_MAX_PLANES; i++) {
 		plane = drmm_kzalloc(drm, sizeof(*plane), GFP_KERNEL);
@@ -521,8 +576,16 @@ struct kmb_plane *kmb_plane_init(struct drm_device *drm)
 		drm_dbg(drm, "%s : %d i=%d type=%d",
 			__func__, __LINE__,
 			  i, plane_type);
+		drm_plane_create_alpha_property(&plane->base_plane);
+
+		drm_plane_create_blend_mode_property(&plane->base_plane,
+						     blend_caps);
+
+		drm_plane_create_zpos_immutable_property(&plane->base_plane, i);
+
 		drm_plane_helper_add(&plane->base_plane,
 				     &kmb_plane_helper_funcs);
+
 		if (plane_type == DRM_PLANE_TYPE_PRIMARY) {
 			primary = plane;
 			kmb->plane = plane;
diff --git a/drivers/gpu/drm/kmb/kmb_plane.h b/drivers/gpu/drm/kmb/kmb_plane.h
index 486490f7a3ec..6e8d22cf8819 100644
--- a/drivers/gpu/drm/kmb/kmb_plane.h
+++ b/drivers/gpu/drm/kmb/kmb_plane.h
@@ -35,6 +35,9 @@
 #define POSSIBLE_CRTCS 1
 #define to_kmb_plane(x) container_of(x, struct kmb_plane, base_plane)
 
+#define POSSIBLE_CRTCS		1
+#define KMB_MAX_PLANES		2
+
 enum layer_id {
 	LAYER_0,
 	LAYER_1,
@@ -43,8 +46,6 @@ enum layer_id {
 	/* KMB_MAX_PLANES */
 };
 
-#define KMB_MAX_PLANES 1
-
 enum sub_plane_id {
 	Y_PLANE,
 	U_PLANE,
diff --git a/drivers/gpu/drm/kmb/kmb_regs.h b/drivers/gpu/drm/kmb/kmb_regs.h
index 48150569f702..9756101b0d32 100644
--- a/drivers/gpu/drm/kmb/kmb_regs.h
+++ b/drivers/gpu/drm/kmb/kmb_regs.h
@@ -43,8 +43,10 @@
 #define LCD_CTRL_OUTPUT_ENABLED			  BIT(19)
 #define LCD_CTRL_BPORCH_ENABLE			  BIT(21)
 #define LCD_CTRL_FPORCH_ENABLE			  BIT(22)
+#define LCD_CTRL_ALPHA_BLEND_BKGND_DISABLE	  BIT(23)
 #define LCD_CTRL_PIPELINE_DMA			  BIT(28)
 #define LCD_CTRL_VHSYNC_IDLE_LVL		  BIT(31)
+#define LCD_CTRL_ALPHA_ALL			  (0xff << 6)
 
 /* interrupts */
 #define LCD_INT_STATUS				(0x4 * 0x001)
@@ -115,6 +117,7 @@
 #define LCD_LAYER_ALPHA_EMBED			BIT(5)
 #define LCD_LAYER_ALPHA_COMBI			(LCD_LAYER_ALPHA_STATIC | \
 						      LCD_LAYER_ALPHA_EMBED)
+#define LCD_LAYER_ALPHA_DISABLED		~(LCD_LAYER_ALPHA_COMBI)
 /* RGB multiplied with alpha */
 #define LCD_LAYER_ALPHA_PREMULT			BIT(6)
 #define LCD_LAYER_INVERT_COL			BIT(7)
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index 5f81489fc60c..a4e80e499674 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -4,8 +4,6 @@
  */
 
 #include <linux/clk.h>
-#include <linux/dma-mapping.h>
-#include <linux/mailbox_controller.h>
 #include <linux/pm_runtime.h>
 #include <linux/soc/mediatek/mtk-cmdq.h>
 #include <linux/soc/mediatek/mtk-mmsys.h>
@@ -52,11 +50,8 @@ struct mtk_drm_crtc {
 	bool				pending_async_planes;
 
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	struct mbox_client		cmdq_cl;
-	struct mbox_chan		*cmdq_chan;
-	struct cmdq_pkt			cmdq_handle;
+	struct cmdq_client		*cmdq_client;
 	u32				cmdq_event;
-	u32				cmdq_vblank_cnt;
 #endif
 
 	struct device			*mmsys_dev;
@@ -227,79 +222,9 @@ struct mtk_ddp_comp *mtk_drm_ddp_comp_for_plane(struct drm_crtc *crtc,
 }
 
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-static int mtk_drm_cmdq_pkt_create(struct mbox_chan *chan, struct cmdq_pkt *pkt,
-				    size_t size)
+static void ddp_cmdq_cb(struct cmdq_cb_data data)
 {
-	struct device *dev;
-	dma_addr_t dma_addr;
-
-	pkt->va_base = kzalloc(size, GFP_KERNEL);
-	if (!pkt->va_base) {
-		kfree(pkt);
-		return -ENOMEM;
-	}
-	pkt->buf_size = size;
-
-	dev = chan->mbox->dev;
-	dma_addr = dma_map_single(dev, pkt->va_base, pkt->buf_size,
-				  DMA_TO_DEVICE);
-	if (dma_mapping_error(dev, dma_addr)) {
-		dev_err(dev, "dma map failed, size=%u\n", (u32)(u64)size);
-		kfree(pkt->va_base);
-		kfree(pkt);
-		return -ENOMEM;
-	}
-
-	pkt->pa_base = dma_addr;
-
-	return 0;
-}
-
-static void mtk_drm_cmdq_pkt_destroy(struct mbox_chan *chan, struct cmdq_pkt *pkt)
-{
-	dma_unmap_single(chan->mbox->dev, pkt->pa_base, pkt->buf_size,
-			 DMA_TO_DEVICE);
-	kfree(pkt->va_base);
-	kfree(pkt);
-}
-
-static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg)
-{
-	struct mtk_drm_crtc *mtk_crtc = container_of(cl, struct mtk_drm_crtc, cmdq_cl);
-	struct cmdq_cb_data *data = mssg;
-	struct mtk_crtc_state *state;
-	unsigned int i;
-
-	state = to_mtk_crtc_state(mtk_crtc->base.state);
-
-	state->pending_config = false;
-
-	if (mtk_crtc->pending_planes) {
-		for (i = 0; i < mtk_crtc->layer_nr; i++) {
-			struct drm_plane *plane = &mtk_crtc->planes[i];
-			struct mtk_plane_state *plane_state;
-
-			plane_state = to_mtk_plane_state(plane->state);
-
-			plane_state->pending.config = false;
-		}
-		mtk_crtc->pending_planes = false;
-	}
-
-	if (mtk_crtc->pending_async_planes) {
-		for (i = 0; i < mtk_crtc->layer_nr; i++) {
-			struct drm_plane *plane = &mtk_crtc->planes[i];
-			struct mtk_plane_state *plane_state;
-
-			plane_state = to_mtk_plane_state(plane->state);
-
-			plane_state->pending.async_config = false;
-		}
-		mtk_crtc->pending_async_planes = false;
-	}
-
-	mtk_crtc->cmdq_vblank_cnt = 0;
-	mtk_drm_cmdq_pkt_destroy(mtk_crtc->cmdq_chan, data->pkt);
+	cmdq_pkt_destroy(data.data);
 }
 #endif
 
@@ -453,8 +378,7 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc,
 				    state->pending_vrefresh, 0,
 				    cmdq_handle);
 
-		if (!cmdq_handle)
-			state->pending_config = false;
+		state->pending_config = false;
 	}
 
 	if (mtk_crtc->pending_planes) {
@@ -474,12 +398,9 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc,
 				mtk_ddp_comp_layer_config(comp, local_layer,
 							  plane_state,
 							  cmdq_handle);
-			if (!cmdq_handle)
-				plane_state->pending.config = false;
+			plane_state->pending.config = false;
 		}
-
-		if (!cmdq_handle)
-			mtk_crtc->pending_planes = false;
+		mtk_crtc->pending_planes = false;
 	}
 
 	if (mtk_crtc->pending_async_planes) {
@@ -499,12 +420,9 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc,
 				mtk_ddp_comp_layer_config(comp, local_layer,
 							  plane_state,
 							  cmdq_handle);
-			if (!cmdq_handle)
-				plane_state->pending.async_config = false;
+			plane_state->pending.async_config = false;
 		}
-
-		if (!cmdq_handle)
-			mtk_crtc->pending_async_planes = false;
+		mtk_crtc->pending_async_planes = false;
 	}
 }
 
@@ -512,7 +430,7 @@ static void mtk_drm_crtc_update_config(struct mtk_drm_crtc *mtk_crtc,
 				       bool needs_vblank)
 {
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	struct cmdq_pkt *cmdq_handle = &mtk_crtc->cmdq_handle;
+	struct cmdq_pkt *cmdq_handle;
 #endif
 	struct drm_crtc *crtc = &mtk_crtc->base;
 	struct mtk_drm_private *priv = crtc->dev->dev_private;
@@ -550,24 +468,14 @@ static void mtk_drm_crtc_update_config(struct mtk_drm_crtc *mtk_crtc,
 		mtk_mutex_release(mtk_crtc->mutex);
 	}
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	if (mtk_crtc->cmdq_chan) {
-		mbox_flush(mtk_crtc->cmdq_chan, 2000);
-		cmdq_handle->cmd_buf_size = 0;
+	if (mtk_crtc->cmdq_client) {
+		mbox_flush(mtk_crtc->cmdq_client->chan, 2000);
+		cmdq_handle = cmdq_pkt_create(mtk_crtc->cmdq_client, PAGE_SIZE);
 		cmdq_pkt_clear_event(cmdq_handle, mtk_crtc->cmdq_event);
 		cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event, false);
 		mtk_crtc_ddp_config(crtc, cmdq_handle);
 		cmdq_pkt_finalize(cmdq_handle);
-		dma_sync_single_for_device(mtk_crtc->cmdq_chan->mbox->dev,
-					    cmdq_handle->pa_base,
-					    cmdq_handle->cmd_buf_size,
-					    DMA_TO_DEVICE);
-		/*
-		 * CMDQ command should execute in next vblank,
-		 * If it fail to execute in next 2 vblank, timeout happen.
-		 */
-		mtk_crtc->cmdq_vblank_cnt = 2;
-		mbox_send_message(mtk_crtc->cmdq_chan, cmdq_handle);
-		mbox_client_txdone(mtk_crtc->cmdq_chan, 0);
+		cmdq_pkt_flush_async(cmdq_handle, ddp_cmdq_cb, cmdq_handle);
 	}
 #endif
 	mtk_crtc->config_updating = false;
@@ -581,15 +489,12 @@ static void mtk_crtc_ddp_irq(void *data)
 	struct mtk_drm_private *priv = crtc->dev->dev_private;
 
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	if (!priv->data->shadow_register && !mtk_crtc->cmdq_chan)
-		mtk_crtc_ddp_config(crtc, NULL);
-	else if (mtk_crtc->cmdq_vblank_cnt > 0 && --mtk_crtc->cmdq_vblank_cnt == 0)
-		DRM_ERROR("mtk_crtc %d CMDQ execute command timeout!\n",
-			  drm_crtc_index(&mtk_crtc->base));
+	if (!priv->data->shadow_register && !mtk_crtc->cmdq_client)
 #else
 	if (!priv->data->shadow_register)
-		mtk_crtc_ddp_config(crtc, NULL);
 #endif
+		mtk_crtc_ddp_config(crtc, NULL);
+
 	mtk_drm_finish_page_flip(mtk_crtc);
 }
 
@@ -924,20 +829,16 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 	mutex_init(&mtk_crtc->hw_lock);
 
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	mtk_crtc->cmdq_cl.dev = mtk_crtc->mmsys_dev;
-	mtk_crtc->cmdq_cl.tx_block = false;
-	mtk_crtc->cmdq_cl.knows_txdone = true;
-	mtk_crtc->cmdq_cl.rx_callback = ddp_cmdq_cb;
-	mtk_crtc->cmdq_chan =
-			mbox_request_channel(&mtk_crtc->cmdq_cl,
-					      drm_crtc_index(&mtk_crtc->base));
-	if (IS_ERR(mtk_crtc->cmdq_chan)) {
+	mtk_crtc->cmdq_client =
+			cmdq_mbox_create(mtk_crtc->mmsys_dev,
+					 drm_crtc_index(&mtk_crtc->base));
+	if (IS_ERR(mtk_crtc->cmdq_client)) {
 		dev_dbg(dev, "mtk_crtc %d failed to create mailbox client, writing register by CPU now\n",
 			drm_crtc_index(&mtk_crtc->base));
-		mtk_crtc->cmdq_chan = NULL;
+		mtk_crtc->cmdq_client = NULL;
 	}
 
-	if (mtk_crtc->cmdq_chan) {
+	if (mtk_crtc->cmdq_client) {
 		ret = of_property_read_u32_index(priv->mutex_node,
 						 "mediatek,gce-events",
 						 drm_crtc_index(&mtk_crtc->base),
@@ -945,18 +846,8 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 		if (ret) {
 			dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n",
 				drm_crtc_index(&mtk_crtc->base));
-			mbox_free_channel(mtk_crtc->cmdq_chan);
-			mtk_crtc->cmdq_chan = NULL;
-		} else {
-			ret = mtk_drm_cmdq_pkt_create(mtk_crtc->cmdq_chan,
-						       &mtk_crtc->cmdq_handle,
-						       PAGE_SIZE);
-			if (ret) {
-				dev_dbg(dev, "mtk_crtc %d failed to create cmdq packet\n",
-					drm_crtc_index(&mtk_crtc->base));
-				mbox_free_channel(mtk_crtc->cmdq_chan);
-				mtk_crtc->cmdq_chan = NULL;
-			}
+			cmdq_mbox_destroy(mtk_crtc->cmdq_client);
+			mtk_crtc->cmdq_client = NULL;
 		}
 	}
 #endif
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index e9c6af78b1d7..3ddf739a6f9b 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -17,7 +17,7 @@ config DRM_MSM
 	select DRM_SCHED
 	select SHMEM
 	select TMPFS
-	select QCOM_SCM if ARCH_QCOM
+	select QCOM_SCM
 	select WANT_DEV_COREDUMP
 	select SND_SOC_HDMI_CODEC if SND_SOC
 	select SYNC_FILE
@@ -55,7 +55,7 @@ config DRM_MSM_GPU_SUDO
 
 config DRM_MSM_HDMI_HDCP
 	bool "Enable HDMI HDCP support in MSM DRM driver"
-	depends on DRM_MSM && QCOM_SCM
+	depends on DRM_MSM
 	default y
 	help
 	  Choose this option to enable HDCP state machine
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 4534633fe7cd..8fb847c174ff 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -571,13 +571,14 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 	}
 
 	icc_path = devm_of_icc_get(&pdev->dev, "gfx-mem");
-	ret = IS_ERR(icc_path);
-	if (ret)
+	if (IS_ERR(icc_path)) {
+		ret = PTR_ERR(icc_path);
 		goto fail;
+	}
 
 	ocmem_icc_path = devm_of_icc_get(&pdev->dev, "ocmem");
-	ret = IS_ERR(ocmem_icc_path);
-	if (ret) {
+	if (IS_ERR(ocmem_icc_path)) {
+		ret = PTR_ERR(ocmem_icc_path);
 		/* allow -ENODATA, ocmem icc is optional */
 		if (ret != -ENODATA)
 			goto fail;
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 82bebb40234d..a96ee79cc5e0 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -699,13 +699,14 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev)
 	}
 
 	icc_path = devm_of_icc_get(&pdev->dev, "gfx-mem");
-	ret = IS_ERR(icc_path);
-	if (ret)
+	if (IS_ERR(icc_path)) {
+		ret = PTR_ERR(icc_path);
 		goto fail;
+	}
 
 	ocmem_icc_path = devm_of_icc_get(&pdev->dev, "ocmem");
-	ret = IS_ERR(ocmem_icc_path);
-	if (ret) {
+	if (IS_ERR(ocmem_icc_path)) {
+		ret = PTR_ERR(ocmem_icc_path);
 		/* allow -ENODATA, ocmem icc is optional */
 		if (ret != -ENODATA)
 			goto fail;
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index a7c58018959f..8b73f70766a4 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -296,6 +296,8 @@ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
 	u32 val;
 	int request, ack;
 
+	WARN_ON_ONCE(!mutex_is_locked(&gmu->lock));
+
 	if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits))
 		return -EINVAL;
 
@@ -337,6 +339,8 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
 {
 	int bit;
 
+	WARN_ON_ONCE(!mutex_is_locked(&gmu->lock));
+
 	if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits))
 		return;
 
@@ -1482,6 +1486,8 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	if (!pdev)
 		return -ENODEV;
 
+	mutex_init(&gmu->lock);
+
 	gmu->dev = &pdev->dev;
 
 	of_dma_configure(gmu->dev, node, true);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
index 3c74f64e3126..84bd516f01e8 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
@@ -44,6 +44,9 @@ struct a6xx_gmu_bo {
 struct a6xx_gmu {
 	struct device *dev;
 
+	/* For serializing communication with the GMU: */
+	struct mutex lock;
+
 	struct msm_gem_address_space *aspace;
 
 	void * __iomem mmio;
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 40c9fef457a4..33da25b81615 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -106,7 +106,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
 	u32 asid;
 	u64 memptr = rbmemptr(ring, ttbr0);
 
-	if (ctx == a6xx_gpu->cur_ctx)
+	if (ctx->seqno == a6xx_gpu->cur_ctx_seqno)
 		return;
 
 	if (msm_iommu_pagetable_params(ctx->aspace->mmu, &ttbr, &asid))
@@ -139,7 +139,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
 	OUT_PKT7(ring, CP_EVENT_WRITE, 1);
 	OUT_RING(ring, 0x31);
 
-	a6xx_gpu->cur_ctx = ctx;
+	a6xx_gpu->cur_ctx_seqno = ctx->seqno;
 }
 
 static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
@@ -881,7 +881,7 @@ static int a6xx_zap_shader_init(struct msm_gpu *gpu)
 	  A6XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS | \
 	  A6XX_RBBM_INT_0_MASK_UCHE_TRAP_INTR)
 
-static int a6xx_hw_init(struct msm_gpu *gpu)
+static int hw_init(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
@@ -1081,7 +1081,7 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	/* Always come up on rb 0 */
 	a6xx_gpu->cur_ring = gpu->rb[0];
 
-	a6xx_gpu->cur_ctx = NULL;
+	a6xx_gpu->cur_ctx_seqno = 0;
 
 	/* Enable the SQE_to start the CP engine */
 	gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 1);
@@ -1135,6 +1135,19 @@ out:
 	return ret;
 }
 
+static int a6xx_hw_init(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+	int ret;
+
+	mutex_lock(&a6xx_gpu->gmu.lock);
+	ret = hw_init(gpu);
+	mutex_unlock(&a6xx_gpu->gmu.lock);
+
+	return ret;
+}
+
 static void a6xx_dump(struct msm_gpu *gpu)
 {
 	DRM_DEV_INFO(&gpu->pdev->dev, "status:   %08x\n",
@@ -1509,7 +1522,9 @@ static int a6xx_pm_resume(struct msm_gpu *gpu)
 
 	trace_msm_gpu_resume(0);
 
+	mutex_lock(&a6xx_gpu->gmu.lock);
 	ret = a6xx_gmu_resume(a6xx_gpu);
+	mutex_unlock(&a6xx_gpu->gmu.lock);
 	if (ret)
 		return ret;
 
@@ -1532,7 +1547,9 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
 
 	msm_devfreq_suspend(gpu);
 
+	mutex_lock(&a6xx_gpu->gmu.lock);
 	ret = a6xx_gmu_stop(a6xx_gpu);
+	mutex_unlock(&a6xx_gpu->gmu.lock);
 	if (ret)
 		return ret;
 
@@ -1547,18 +1564,19 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
-	static DEFINE_MUTEX(perfcounter_oob);
 
-	mutex_lock(&perfcounter_oob);
+	mutex_lock(&a6xx_gpu->gmu.lock);
 
 	/* Force the GPU power on so we can read this register */
 	a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
 
 	*value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO,
-		REG_A6XX_CP_ALWAYS_ON_COUNTER_HI);
+			    REG_A6XX_CP_ALWAYS_ON_COUNTER_HI);
 
 	a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
-	mutex_unlock(&perfcounter_oob);
+
+	mutex_unlock(&a6xx_gpu->gmu.lock);
+
 	return 0;
 }
 
@@ -1622,6 +1640,16 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu)
 	return (unsigned long)busy_time;
 }
 
+void a6xx_gpu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+
+	mutex_lock(&a6xx_gpu->gmu.lock);
+	a6xx_gmu_set_freq(gpu, opp);
+	mutex_unlock(&a6xx_gpu->gmu.lock);
+}
+
 static struct msm_gem_address_space *
 a6xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev)
 {
@@ -1766,7 +1794,7 @@ static const struct adreno_gpu_funcs funcs = {
 #endif
 		.gpu_busy = a6xx_gpu_busy,
 		.gpu_get_freq = a6xx_gmu_get_freq,
-		.gpu_set_freq = a6xx_gmu_set_freq,
+		.gpu_set_freq = a6xx_gpu_set_freq,
 #if defined(CONFIG_DRM_MSM_GPU_STATE)
 		.gpu_state_get = a6xx_gpu_state_get,
 		.gpu_state_put = a6xx_gpu_state_put,
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
index 0bc2d062f54a..8e5527c881b1 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
@@ -19,7 +19,16 @@ struct a6xx_gpu {
 	uint64_t sqe_iova;
 
 	struct msm_ringbuffer *cur_ring;
-	struct msm_file_private *cur_ctx;
+
+	/**
+	 * cur_ctx_seqno:
+	 *
+	 * The ctx->seqno value of the context with current pgtables
+	 * installed.  Tracked by seqno rather than pointer value to
+	 * avoid dangling pointers, and cases where a ctx can be freed
+	 * and a new one created with the same address.
+	 */
+	int cur_ctx_seqno;
 
 	struct a6xx_gmu gmu;
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
index b131fd376192..700d65e39feb 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
@@ -794,7 +794,7 @@ static const struct dpu_pingpong_cfg sm8150_pp[] = {
 			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30),
 			-1),
 	PP_BLK("pingpong_5", PINGPONG_5, 0x72800, MERGE_3D_2, sdm845_pp_sblk,
-			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30),
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31),
 			-1),
 };
 
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index f482e0911d03..bb7d066618e6 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -1125,6 +1125,20 @@ static void mdp5_crtc_reset(struct drm_crtc *crtc)
 	__drm_atomic_helper_crtc_reset(crtc, &mdp5_cstate->base);
 }
 
+static const struct drm_crtc_funcs mdp5_crtc_no_lm_cursor_funcs = {
+	.set_config = drm_atomic_helper_set_config,
+	.destroy = mdp5_crtc_destroy,
+	.page_flip = drm_atomic_helper_page_flip,
+	.reset = mdp5_crtc_reset,
+	.atomic_duplicate_state = mdp5_crtc_duplicate_state,
+	.atomic_destroy_state = mdp5_crtc_destroy_state,
+	.atomic_print_state = mdp5_crtc_atomic_print_state,
+	.get_vblank_counter = mdp5_crtc_get_vblank_counter,
+	.enable_vblank  = msm_crtc_enable_vblank,
+	.disable_vblank = msm_crtc_disable_vblank,
+	.get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp,
+};
+
 static const struct drm_crtc_funcs mdp5_crtc_funcs = {
 	.set_config = drm_atomic_helper_set_config,
 	.destroy = mdp5_crtc_destroy,
@@ -1313,6 +1327,8 @@ struct drm_crtc *mdp5_crtc_init(struct drm_device *dev,
 	mdp5_crtc->lm_cursor_enabled = cursor_plane ? false : true;
 
 	drm_crtc_init_with_planes(dev, crtc, plane, cursor_plane,
+				  cursor_plane ?
+				  &mdp5_crtc_no_lm_cursor_funcs :
 				  &mdp5_crtc_funcs, NULL);
 
 	drm_flip_work_init(&mdp5_crtc->unref_cursor_work,
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index fbe4c2cd52a3..a0392e4d8134 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -1309,14 +1309,14 @@ static int dp_pm_resume(struct device *dev)
 	 * can not declared display is connected unless
 	 * HDMI cable is plugged in and sink_count of
 	 * dongle become 1
+	 * also only signal audio when disconnected
 	 */
-	if (dp->link->sink_count)
+	if (dp->link->sink_count) {
 		dp->dp_display.is_connected = true;
-	else
+	} else {
 		dp->dp_display.is_connected = false;
-
-	dp_display_handle_plugged_change(g_dp_display,
-				dp->dp_display.is_connected);
+		dp_display_handle_plugged_change(g_dp_display, false);
+	}
 
 	DRM_DEBUG_DP("After, sink_count=%d is_connected=%d core_inited=%d power_on=%d\n",
 			dp->link->sink_count, dp->dp_display.is_connected,
diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c
index 614dc7f26f2c..75ae3008b68f 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.c
+++ b/drivers/gpu/drm/msm/dsi/dsi.c
@@ -215,8 +215,10 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
 		goto fail;
 	}
 
-	if (!msm_dsi_manager_validate_current_config(msm_dsi->id))
+	if (!msm_dsi_manager_validate_current_config(msm_dsi->id)) {
+		ret = -EINVAL;
 		goto fail;
+	}
 
 	msm_dsi->encoder = encoder;
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index e269df285136..c86b5090fae6 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -451,7 +451,7 @@ static int dsi_bus_clk_enable(struct msm_dsi_host *msm_host)
 
 	return 0;
 err:
-	for (; i > 0; i--)
+	while (--i >= 0)
 		clk_disable_unprepare(msm_host->bus_clks[i]);
 
 	return ret;
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c
index d13552b2213b..5b4e991f220d 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c
@@ -110,14 +110,13 @@ static struct dsi_pll_14nm *pll_14nm_list[DSI_MAX];
 static bool pll_14nm_poll_for_ready(struct dsi_pll_14nm *pll_14nm,
 				    u32 nb_tries, u32 timeout_us)
 {
-	bool pll_locked = false;
+	bool pll_locked = false, pll_ready = false;
 	void __iomem *base = pll_14nm->phy->pll_base;
 	u32 tries, val;
 
 	tries = nb_tries;
 	while (tries--) {
-		val = dsi_phy_read(base +
-			       REG_DSI_14nm_PHY_PLL_RESET_SM_READY_STATUS);
+		val = dsi_phy_read(base + REG_DSI_14nm_PHY_PLL_RESET_SM_READY_STATUS);
 		pll_locked = !!(val & BIT(5));
 
 		if (pll_locked)
@@ -126,23 +125,24 @@ static bool pll_14nm_poll_for_ready(struct dsi_pll_14nm *pll_14nm,
 		udelay(timeout_us);
 	}
 
-	if (!pll_locked) {
-		tries = nb_tries;
-		while (tries--) {
-			val = dsi_phy_read(base +
-				REG_DSI_14nm_PHY_PLL_RESET_SM_READY_STATUS);
-			pll_locked = !!(val & BIT(0));
+	if (!pll_locked)
+		goto out;
 
-			if (pll_locked)
-				break;
+	tries = nb_tries;
+	while (tries--) {
+		val = dsi_phy_read(base + REG_DSI_14nm_PHY_PLL_RESET_SM_READY_STATUS);
+		pll_ready = !!(val & BIT(0));
 
-			udelay(timeout_us);
-		}
+		if (pll_ready)
+			break;
+
+		udelay(timeout_us);
 	}
 
-	DBG("DSI PLL is %slocked", pll_locked ? "" : "*not* ");
+out:
+	DBG("DSI PLL is %slocked, %sready", pll_locked ? "" : "*not* ", pll_ready ? "" : "*not* ");
 
-	return pll_locked;
+	return pll_locked && pll_ready;
 }
 
 static void dsi_pll_14nm_config_init(struct dsi_pll_config *pconf)
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c
index aaa37456f4ee..71ed4aa0dc67 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c
@@ -428,7 +428,7 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **prov
 	bytediv->reg = pll_28nm->phy->pll_base + REG_DSI_28nm_8960_PHY_PLL_CTRL_9;
 
 	snprintf(parent_name, 32, "dsi%dvco_clk", pll_28nm->phy->id);
-	snprintf(clk_name, 32, "dsi%dpllbyte", pll_28nm->phy->id);
+	snprintf(clk_name, 32, "dsi%dpllbyte", pll_28nm->phy->id + 1);
 
 	bytediv_init.name = clk_name;
 	bytediv_init.ops = &clk_bytediv_ops;
@@ -442,7 +442,7 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **prov
 		return ret;
 	provided_clocks[DSI_BYTE_PLL_CLK] = &bytediv->hw;
 
-	snprintf(clk_name, 32, "dsi%dpll", pll_28nm->phy->id);
+	snprintf(clk_name, 32, "dsi%dpll", pll_28nm->phy->id + 1);
 	/* DIV3 */
 	hw = devm_clk_hw_register_divider(dev, clk_name,
 				parent_name, 0, pll_28nm->phy->pll_base +
diff --git a/drivers/gpu/drm/msm/edp/edp_ctrl.c b/drivers/gpu/drm/msm/edp/edp_ctrl.c
index 4fb397ee7c84..fe1366b4c49f 100644
--- a/drivers/gpu/drm/msm/edp/edp_ctrl.c
+++ b/drivers/gpu/drm/msm/edp/edp_ctrl.c
@@ -1116,7 +1116,7 @@ void msm_edp_ctrl_power(struct edp_ctrl *ctrl, bool on)
 int msm_edp_ctrl_init(struct msm_edp *edp)
 {
 	struct edp_ctrl *ctrl = NULL;
-	struct device *dev = &edp->pdev->dev;
+	struct device *dev;
 	int ret;
 
 	if (!edp) {
@@ -1124,6 +1124,7 @@ int msm_edp_ctrl_init(struct msm_edp *edp)
 		return -EINVAL;
 	}
 
+	dev = &edp->pdev->dev;
 	ctrl = devm_kzalloc(dev, sizeof(*ctrl), GFP_KERNEL);
 	if (!ctrl)
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 2e6fc185e54d..d4e09703a87d 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -630,10 +630,11 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
 	if (ret)
 		goto err_msm_uninit;
 
-	ret = msm_disp_snapshot_init(ddev);
-	if (ret)
-		DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret);
-
+	if (kms) {
+		ret = msm_disp_snapshot_init(ddev);
+		if (ret)
+			DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret);
+	}
 	drm_mode_config_reset(ddev);
 
 #ifdef CONFIG_DRM_FBDEV_EMULATION
@@ -682,6 +683,7 @@ static void load_gpu(struct drm_device *dev)
 
 static int context_init(struct drm_device *dev, struct drm_file *file)
 {
+	static atomic_t ident = ATOMIC_INIT(0);
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_file_private *ctx;
 
@@ -689,12 +691,17 @@ static int context_init(struct drm_device *dev, struct drm_file *file)
 	if (!ctx)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&ctx->submitqueues);
+	rwlock_init(&ctx->queuelock);
+
 	kref_init(&ctx->ref);
 	msm_submitqueue_init(dev, ctx);
 
 	ctx->aspace = msm_gpu_create_private_address_space(priv->gpu, current);
 	file->driver_priv = ctx;
 
+	ctx->seqno = atomic_inc_return(&ident);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 8b005d1ac899..c552f0c3890c 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -53,14 +53,6 @@ struct msm_disp_state;
 
 #define FRAC_16_16(mult, div)    (((mult) << 16) / (div))
 
-struct msm_file_private {
-	rwlock_t queuelock;
-	struct list_head submitqueues;
-	int queueid;
-	struct msm_gem_address_space *aspace;
-	struct kref ref;
-};
-
 enum msm_mdp_plane_property {
 	PLANE_PROP_ZPOS,
 	PLANE_PROP_ALPHA,
@@ -488,41 +480,6 @@ void msm_writel(u32 data, void __iomem *addr);
 u32 msm_readl(const void __iomem *addr);
 void msm_rmw(void __iomem *addr, u32 mask, u32 or);
 
-struct msm_gpu_submitqueue;
-int msm_submitqueue_init(struct drm_device *drm, struct msm_file_private *ctx);
-struct msm_gpu_submitqueue *msm_submitqueue_get(struct msm_file_private *ctx,
-		u32 id);
-int msm_submitqueue_create(struct drm_device *drm,
-		struct msm_file_private *ctx,
-		u32 prio, u32 flags, u32 *id);
-int msm_submitqueue_query(struct drm_device *drm, struct msm_file_private *ctx,
-		struct drm_msm_submitqueue_query *args);
-int msm_submitqueue_remove(struct msm_file_private *ctx, u32 id);
-void msm_submitqueue_close(struct msm_file_private *ctx);
-
-void msm_submitqueue_destroy(struct kref *kref);
-
-static inline void __msm_file_private_destroy(struct kref *kref)
-{
-	struct msm_file_private *ctx = container_of(kref,
-		struct msm_file_private, ref);
-
-	msm_gem_address_space_put(ctx->aspace);
-	kfree(ctx);
-}
-
-static inline void msm_file_private_put(struct msm_file_private *ctx)
-{
-	kref_put(&ctx->ref, __msm_file_private_destroy);
-}
-
-static inline struct msm_file_private *msm_file_private_get(
-	struct msm_file_private *ctx)
-{
-	kref_get(&ctx->ref);
-	return ctx;
-}
-
 #define DBG(fmt, ...) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__)
 #define VERB(fmt, ...) if (0) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__)
 
@@ -547,7 +504,7 @@ static inline int align_pitch(int width, int bpp)
 static inline unsigned long timeout_to_jiffies(const ktime_t *timeout)
 {
 	ktime_t now = ktime_get();
-	unsigned long remaining_jiffies;
+	s64 remaining_jiffies;
 
 	if (ktime_compare(*timeout, now) < 0) {
 		remaining_jiffies = 0;
@@ -556,7 +513,7 @@ static inline unsigned long timeout_to_jiffies(const ktime_t *timeout)
 		remaining_jiffies = ktime_divns(rem, NSEC_PER_SEC / HZ);
 	}
 
-	return remaining_jiffies;
+	return clamp(remaining_jiffies, 0LL, (s64)INT_MAX);
 }
 
 #endif /* __MSM_DRV_H__ */
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index fdc5367aecaa..151d19e4453c 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -46,7 +46,7 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 	if (!submit)
 		return ERR_PTR(-ENOMEM);
 
-	ret = drm_sched_job_init(&submit->base, &queue->entity, queue);
+	ret = drm_sched_job_init(&submit->base, queue->entity, queue);
 	if (ret) {
 		kfree(submit);
 		return ERR_PTR(ret);
@@ -171,7 +171,8 @@ out:
 static int submit_lookup_cmds(struct msm_gem_submit *submit,
 		struct drm_msm_gem_submit *args, struct drm_file *file)
 {
-	unsigned i, sz;
+	unsigned i;
+	size_t sz;
 	int ret = 0;
 
 	for (i = 0; i < args->nr_cmds; i++) {
@@ -907,7 +908,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	/* The scheduler owns a ref now: */
 	msm_gem_submit_get(submit);
 
-	drm_sched_entity_push_job(&submit->base, &queue->entity);
+	drm_sched_entity_push_job(&submit->base, queue->entity);
 
 	args->fence = submit->fence_id;
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 0e4b45bff2e6..030f82f149c2 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -258,6 +258,39 @@ struct msm_gpu_perfcntr {
 #define NR_SCHED_PRIORITIES (1 + DRM_SCHED_PRIORITY_HIGH - DRM_SCHED_PRIORITY_MIN)
 
 /**
+ * struct msm_file_private - per-drm_file context
+ *
+ * @queuelock:    synchronizes access to submitqueues list
+ * @submitqueues: list of &msm_gpu_submitqueue created by userspace
+ * @queueid:      counter incremented each time a submitqueue is created,
+ *                used to assign &msm_gpu_submitqueue.id
+ * @aspace:       the per-process GPU address-space
+ * @ref:          reference count
+ * @seqno:        unique per process seqno
+ */
+struct msm_file_private {
+	rwlock_t queuelock;
+	struct list_head submitqueues;
+	int queueid;
+	struct msm_gem_address_space *aspace;
+	struct kref ref;
+	int seqno;
+
+	/**
+	 * entities:
+	 *
+	 * Table of per-priority-level sched entities used by submitqueues
+	 * associated with this &drm_file.  Because some userspace apps
+	 * make assumptions about rendering from multiple gl contexts
+	 * (of the same priority) within the process happening in FIFO
+	 * order without requiring any fencing beyond MakeCurrent(), we
+	 * create at most one &drm_sched_entity per-process per-priority-
+	 * level.
+	 */
+	struct drm_sched_entity *entities[NR_SCHED_PRIORITIES * MSM_GPU_MAX_RINGS];
+};
+
+/**
  * msm_gpu_convert_priority - Map userspace priority to ring # and sched priority
  *
  * @gpu:        the gpu instance
@@ -304,6 +337,8 @@ static inline int msm_gpu_convert_priority(struct msm_gpu *gpu, int prio,
 }
 
 /**
+ * struct msm_gpu_submitqueues - Userspace created context.
+ *
  * A submitqueue is associated with a gl context or vk queue (or equiv)
  * in userspace.
  *
@@ -321,7 +356,7 @@ static inline int msm_gpu_convert_priority(struct msm_gpu *gpu, int prio,
  *             seqno, protected by submitqueue lock
  * @lock:      submitqueue lock
  * @ref:       reference count
- * @entity: the submit job-queue
+ * @entity:    the submit job-queue
  */
 struct msm_gpu_submitqueue {
 	int id;
@@ -333,7 +368,7 @@ struct msm_gpu_submitqueue {
 	struct idr fence_idr;
 	struct mutex lock;
 	struct kref ref;
-	struct drm_sched_entity entity;
+	struct drm_sched_entity *entity;
 };
 
 struct msm_gpu_state_bo {
@@ -421,6 +456,33 @@ static inline void gpu_write64(struct msm_gpu *gpu, u32 lo, u32 hi, u64 val)
 int msm_gpu_pm_suspend(struct msm_gpu *gpu);
 int msm_gpu_pm_resume(struct msm_gpu *gpu);
 
+int msm_submitqueue_init(struct drm_device *drm, struct msm_file_private *ctx);
+struct msm_gpu_submitqueue *msm_submitqueue_get(struct msm_file_private *ctx,
+		u32 id);
+int msm_submitqueue_create(struct drm_device *drm,
+		struct msm_file_private *ctx,
+		u32 prio, u32 flags, u32 *id);
+int msm_submitqueue_query(struct drm_device *drm, struct msm_file_private *ctx,
+		struct drm_msm_submitqueue_query *args);
+int msm_submitqueue_remove(struct msm_file_private *ctx, u32 id);
+void msm_submitqueue_close(struct msm_file_private *ctx);
+
+void msm_submitqueue_destroy(struct kref *kref);
+
+void __msm_file_private_destroy(struct kref *kref);
+
+static inline void msm_file_private_put(struct msm_file_private *ctx)
+{
+	kref_put(&ctx->ref, __msm_file_private_destroy);
+}
+
+static inline struct msm_file_private *msm_file_private_get(
+	struct msm_file_private *ctx)
+{
+	kref_get(&ctx->ref);
+	return ctx;
+}
+
 void msm_devfreq_init(struct msm_gpu *gpu);
 void msm_devfreq_cleanup(struct msm_gpu *gpu);
 void msm_devfreq_resume(struct msm_gpu *gpu);
diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
index 0a1ee20296a2..84e98c07c900 100644
--- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c
+++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
@@ -151,6 +151,9 @@ void msm_devfreq_active(struct msm_gpu *gpu)
 	unsigned int idle_time;
 	unsigned long target_freq = df->idle_freq;
 
+	if (!df->devfreq)
+		return;
+
 	/*
 	 * Hold devfreq lock to synchronize with get_dev_status()/
 	 * target() callbacks
@@ -186,6 +189,9 @@ void msm_devfreq_idle(struct msm_gpu *gpu)
 	struct msm_gpu_devfreq *df = &gpu->devfreq;
 	unsigned long idle_freq, target_freq = 0;
 
+	if (!df->devfreq)
+		return;
+
 	/*
 	 * Hold devfreq lock to synchronize with get_dev_status()/
 	 * target() callbacks
diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index 32a55d81b58b..b8621c6e0554 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -7,6 +7,24 @@
 
 #include "msm_gpu.h"
 
+void __msm_file_private_destroy(struct kref *kref)
+{
+	struct msm_file_private *ctx = container_of(kref,
+		struct msm_file_private, ref);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ctx->entities); i++) {
+		if (!ctx->entities[i])
+			continue;
+
+		drm_sched_entity_destroy(ctx->entities[i]);
+		kfree(ctx->entities[i]);
+	}
+
+	msm_gem_address_space_put(ctx->aspace);
+	kfree(ctx);
+}
+
 void msm_submitqueue_destroy(struct kref *kref)
 {
 	struct msm_gpu_submitqueue *queue = container_of(kref,
@@ -14,8 +32,6 @@ void msm_submitqueue_destroy(struct kref *kref)
 
 	idr_destroy(&queue->fence_idr);
 
-	drm_sched_entity_destroy(&queue->entity);
-
 	msm_file_private_put(queue->ctx);
 
 	kfree(queue);
@@ -61,13 +77,47 @@ void msm_submitqueue_close(struct msm_file_private *ctx)
 	}
 }
 
+static struct drm_sched_entity *
+get_sched_entity(struct msm_file_private *ctx, struct msm_ringbuffer *ring,
+		 unsigned ring_nr, enum drm_sched_priority sched_prio)
+{
+	static DEFINE_MUTEX(entity_lock);
+	unsigned idx = (ring_nr * NR_SCHED_PRIORITIES) + sched_prio;
+
+	/* We should have already validated that the requested priority is
+	 * valid by the time we get here.
+	 */
+	if (WARN_ON(idx >= ARRAY_SIZE(ctx->entities)))
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&entity_lock);
+
+	if (!ctx->entities[idx]) {
+		struct drm_sched_entity *entity;
+		struct drm_gpu_scheduler *sched = &ring->sched;
+		int ret;
+
+		entity = kzalloc(sizeof(*ctx->entities[idx]), GFP_KERNEL);
+
+		ret = drm_sched_entity_init(entity, sched_prio, &sched, 1, NULL);
+		if (ret) {
+			kfree(entity);
+			return ERR_PTR(ret);
+		}
+
+		ctx->entities[idx] = entity;
+	}
+
+	mutex_unlock(&entity_lock);
+
+	return ctx->entities[idx];
+}
+
 int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 		u32 prio, u32 flags, u32 *id)
 {
 	struct msm_drm_private *priv = drm->dev_private;
 	struct msm_gpu_submitqueue *queue;
-	struct msm_ringbuffer *ring;
-	struct drm_gpu_scheduler *sched;
 	enum drm_sched_priority sched_prio;
 	unsigned ring_nr;
 	int ret;
@@ -91,12 +141,10 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 	queue->flags = flags;
 	queue->ring_nr = ring_nr;
 
-	ring = priv->gpu->rb[ring_nr];
-	sched = &ring->sched;
-
-	ret = drm_sched_entity_init(&queue->entity,
-			sched_prio, &sched, 1, NULL);
-	if (ret) {
+	queue->entity = get_sched_entity(ctx, priv->gpu->rb[ring_nr],
+					 ring_nr, sched_prio);
+	if (IS_ERR(queue->entity)) {
+		ret = PTR_ERR(queue->entity);
 		kfree(queue);
 		return ret;
 	}
@@ -140,10 +188,6 @@ int msm_submitqueue_init(struct drm_device *drm, struct msm_file_private *ctx)
 	 */
 	default_prio = DIV_ROUND_UP(max_priority, 2);
 
-	INIT_LIST_HEAD(&ctx->submitqueues);
-
-	rwlock_init(&ctx->queuelock);
-
 	return msm_submitqueue_create(drm, ctx, default_prio, 0, NULL);
 }
 
diff --git a/drivers/gpu/drm/nouveau/dispnv50/crc.c b/drivers/gpu/drm/nouveau/dispnv50/crc.c
index b8c31b697797..66f32d965c72 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/crc.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/crc.c
@@ -704,6 +704,7 @@ static const struct file_operations nv50_crc_flip_threshold_fops = {
 	.open = nv50_crc_debugfs_flip_threshold_open,
 	.read = seq_read,
 	.write = nv50_crc_debugfs_flip_threshold_set,
+	.release = single_release,
 };
 
 int nv50_head_crc_late_register(struct nv50_head *head)
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c
index d66f97280282..72099d1e4816 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head.c
@@ -52,6 +52,7 @@ nv50_head_flush_clr(struct nv50_head *head,
 void
 nv50_head_flush_set_wndw(struct nv50_head *head, struct nv50_head_atom *asyh)
 {
+	if (asyh->set.curs   ) head->func->curs_set(head, asyh);
 	if (asyh->set.olut   ) {
 		asyh->olut.offset = nv50_lut_load(&head->olut,
 						  asyh->olut.buffer,
@@ -67,7 +68,6 @@ nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh)
 	if (asyh->set.view   ) head->func->view    (head, asyh);
 	if (asyh->set.mode   ) head->func->mode    (head, asyh);
 	if (asyh->set.core   ) head->func->core_set(head, asyh);
-	if (asyh->set.curs   ) head->func->curs_set(head, asyh);
 	if (asyh->set.base   ) head->func->base    (head, asyh);
 	if (asyh->set.ovly   ) head->func->ovly    (head, asyh);
 	if (asyh->set.dither ) head->func->dither  (head, asyh);
diff --git a/drivers/gpu/drm/nouveau/include/nvif/class.h b/drivers/gpu/drm/nouveau/include/nvif/class.h
index c68cc957248e..a582c0cb0cb0 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/class.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/class.h
@@ -71,6 +71,7 @@
 #define PASCAL_CHANNEL_GPFIFO_A                       /* cla06f.h */ 0x0000c06f
 #define VOLTA_CHANNEL_GPFIFO_A                        /* clc36f.h */ 0x0000c36f
 #define TURING_CHANNEL_GPFIFO_A                       /* clc36f.h */ 0x0000c46f
+#define AMPERE_CHANNEL_GPFIFO_B                       /* clc36f.h */ 0x0000c76f
 
 #define NV50_DISP                                     /* cl5070.h */ 0x00005070
 #define G82_DISP                                      /* cl5070.h */ 0x00008270
@@ -200,6 +201,7 @@
 #define PASCAL_DMA_COPY_B                                            0x0000c1b5
 #define VOLTA_DMA_COPY_A                                             0x0000c3b5
 #define TURING_DMA_COPY_A                                            0x0000c5b5
+#define AMPERE_DMA_COPY_B                                            0x0000c7b5
 
 #define FERMI_DECOMPRESS                                             0x000090b8
 
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h
index 54fab7cc36c1..64ee82c7c1be 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h
@@ -77,4 +77,5 @@ int gp100_fifo_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct
 int gp10b_fifo_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fifo **);
 int gv100_fifo_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fifo **);
 int tu102_fifo_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fifo **);
+int ga102_fifo_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fifo **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 6d07e653f82d..c58bcdba2c7a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -844,6 +844,7 @@ nouveau_bo_move_init(struct nouveau_drm *drm)
 			    struct ttm_resource *, struct ttm_resource *);
 		int (*init)(struct nouveau_channel *, u32 handle);
 	} _methods[] = {
+		{  "COPY", 4, 0xc7b5, nve0_bo_move_copy, nve0_bo_move_init },
 		{  "COPY", 4, 0xc5b5, nve0_bo_move_copy, nve0_bo_move_init },
 		{  "GRCE", 0, 0xc5b5, nve0_bo_move_copy, nvc0_bo_move_init },
 		{  "COPY", 4, 0xc3b5, nve0_bo_move_copy, nve0_bo_move_init },
diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c
index 80099ef75702..ea7769135b0d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_chan.c
+++ b/drivers/gpu/drm/nouveau/nouveau_chan.c
@@ -250,7 +250,8 @@ static int
 nouveau_channel_ind(struct nouveau_drm *drm, struct nvif_device *device,
 		    u64 runlist, bool priv, struct nouveau_channel **pchan)
 {
-	static const u16 oclasses[] = { TURING_CHANNEL_GPFIFO_A,
+	static const u16 oclasses[] = { AMPERE_CHANNEL_GPFIFO_B,
+					TURING_CHANNEL_GPFIFO_A,
 					VOLTA_CHANNEL_GPFIFO_A,
 					PASCAL_CHANNEL_GPFIFO_A,
 					MAXWELL_CHANNEL_GPFIFO_A,
@@ -386,7 +387,8 @@ nouveau_channel_init(struct nouveau_channel *chan, u32 vram, u32 gart)
 
 	nvif_object_map(&chan->user, NULL, 0);
 
-	if (chan->user.oclass >= FERMI_CHANNEL_GPFIFO) {
+	if (chan->user.oclass >= FERMI_CHANNEL_GPFIFO &&
+	    chan->user.oclass < AMPERE_CHANNEL_GPFIFO_B) {
 		ret = nvif_notify_ctor(&chan->user, "abi16ChanKilled",
 				       nouveau_channel_killed,
 				       true, NV906F_V0_NTFY_KILLED,
diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
index c2bc05eb2e54..1cbe01048b93 100644
--- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c
+++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
@@ -207,6 +207,7 @@ static const struct file_operations nouveau_pstate_fops = {
 	.open = nouveau_debugfs_pstate_open,
 	.read = seq_read,
 	.write = nouveau_debugfs_pstate_set,
+	.release = single_release,
 };
 
 static struct drm_info_list nouveau_debugfs_list[] = {
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 1f828c9f691c..6109cd9e3399 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -345,6 +345,9 @@ nouveau_accel_gr_init(struct nouveau_drm *drm)
 	u32 arg0, arg1;
 	int ret;
 
+	if (device->info.family >= NV_DEVICE_INFO_V0_AMPERE)
+		return;
+
 	/* Allocate channel that has access to the graphics engine. */
 	if (device->info.family >= NV_DEVICE_INFO_V0_KEPLER) {
 		arg0 = nvif_fifo_runlist(device, NV_DEVICE_HOST_RUNLIST_ENGINES_GR);
@@ -469,6 +472,7 @@ nouveau_accel_init(struct nouveau_drm *drm)
 		case PASCAL_CHANNEL_GPFIFO_A:
 		case VOLTA_CHANNEL_GPFIFO_A:
 		case TURING_CHANNEL_GPFIFO_A:
+		case AMPERE_CHANNEL_GPFIFO_B:
 			ret = nvc0_fence_create(drm);
 			break;
 		default:
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 5b27845075a1..8c2ecc282723 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -247,10 +247,8 @@ nouveau_gem_new(struct nouveau_cli *cli, u64 size, int align, uint32_t domain,
 	}
 
 	ret = nouveau_bo_init(nvbo, size, align, domain, NULL, NULL);
-	if (ret) {
-		nouveau_bo_ref(NULL, &nvbo);
+	if (ret)
 		return ret;
-	}
 
 	/* we restrict allowed domains on nv50+ to only the types
 	 * that were requested at creation time.  not possibly on
diff --git a/drivers/gpu/drm/nouveau/nv84_fence.c b/drivers/gpu/drm/nouveau/nv84_fence.c
index 7c9c928c3196..c3526a8622e3 100644
--- a/drivers/gpu/drm/nouveau/nv84_fence.c
+++ b/drivers/gpu/drm/nouveau/nv84_fence.c
@@ -204,7 +204,7 @@ nv84_fence_create(struct nouveau_drm *drm)
 	priv->base.context_new = nv84_fence_context_new;
 	priv->base.context_del = nv84_fence_context_del;
 
-	priv->base.uevent = true;
+	priv->base.uevent = drm->client.device.info.family < NV_DEVICE_INFO_V0_AMPERE;
 
 	mutex_init(&priv->mutex);
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 93ddf63d1114..ca75c5f6ecaf 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -2602,6 +2602,7 @@ nv172_chipset = {
 	.top      = { 0x00000001, ga100_top_new },
 	.disp     = { 0x00000001, ga102_disp_new },
 	.dma      = { 0x00000001, gv100_dma_new },
+	.fifo     = { 0x00000001, ga102_fifo_new },
 };
 
 static const struct nvkm_device_chip
@@ -2622,6 +2623,7 @@ nv174_chipset = {
 	.top      = { 0x00000001, ga100_top_new },
 	.disp     = { 0x00000001, ga102_disp_new },
 	.dma      = { 0x00000001, gv100_dma_new },
+	.fifo     = { 0x00000001, ga102_fifo_new },
 };
 
 static const struct nvkm_device_chip
@@ -2642,6 +2644,7 @@ nv177_chipset = {
 	.top      = { 0x00000001, ga100_top_new },
 	.disp     = { 0x00000001, ga102_disp_new },
 	.dma      = { 0x00000001, gv100_dma_new },
+	.fifo     = { 0x00000001, ga102_fifo_new },
 };
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/ctrl.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/ctrl.c
index b0ece71aefde..ce774579c89d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/ctrl.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/ctrl.c
@@ -57,7 +57,7 @@ nvkm_control_mthd_pstate_info(struct nvkm_control *ctrl, void *data, u32 size)
 		args->v0.count = 0;
 		args->v0.ustate_ac = NVIF_CONTROL_PSTATE_INFO_V0_USTATE_DISABLE;
 		args->v0.ustate_dc = NVIF_CONTROL_PSTATE_INFO_V0_USTATE_DISABLE;
-		args->v0.pwrsrc = -ENOSYS;
+		args->v0.pwrsrc = -ENODEV;
 		args->v0.pstate = NVIF_CONTROL_PSTATE_INFO_V0_PSTATE_UNKNOWN;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild
index 3209eb7af65f..5e831d347a95 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild
@@ -18,6 +18,7 @@ nvkm-y += nvkm/engine/fifo/gp100.o
 nvkm-y += nvkm/engine/fifo/gp10b.o
 nvkm-y += nvkm/engine/fifo/gv100.o
 nvkm-y += nvkm/engine/fifo/tu102.o
+nvkm-y += nvkm/engine/fifo/ga102.o
 
 nvkm-y += nvkm/engine/fifo/chan.o
 nvkm-y += nvkm/engine/fifo/channv50.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/chang84.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/chang84.c
index 353b77d9b3dc..3492c561f2cf 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/chang84.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/chang84.c
@@ -82,7 +82,7 @@ g84_fifo_chan_engine_fini(struct nvkm_fifo_chan *base,
 	if (offset < 0)
 		return 0;
 
-	engn = fifo->base.func->engine_id(&fifo->base, engine);
+	engn = fifo->base.func->engine_id(&fifo->base, engine) - 1;
 	save = nvkm_mask(device, 0x002520, 0x0000003f, 1 << engn);
 	nvkm_wr32(device, 0x0032fc, chan->base.inst->addr >> 12);
 	done = nvkm_msec(device, 2000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c
new file mode 100644
index 000000000000..c630dbd2911a
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c
@@ -0,0 +1,311 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#define ga102_fifo(p) container_of((p), struct ga102_fifo, base.engine)
+#define ga102_chan(p) container_of((p), struct ga102_chan, object)
+#include <engine/fifo.h>
+#include "user.h"
+
+#include <core/memory.h>
+#include <subdev/mmu.h>
+#include <subdev/timer.h>
+#include <subdev/top.h>
+
+#include <nvif/cl0080.h>
+#include <nvif/clc36f.h>
+#include <nvif/class.h>
+
+struct ga102_fifo {
+	struct nvkm_fifo base;
+};
+
+struct ga102_chan {
+	struct nvkm_object object;
+
+	struct {
+		u32 runl;
+		u32 chan;
+	} ctrl;
+
+	struct nvkm_memory *mthd;
+	struct nvkm_memory *inst;
+	struct nvkm_memory *user;
+	struct nvkm_memory *runl;
+
+	struct nvkm_vmm *vmm;
+};
+
+static int
+ga102_chan_sclass(struct nvkm_object *object, int index, struct nvkm_oclass *oclass)
+{
+	if (index == 0) {
+		oclass->ctor = nvkm_object_new;
+		oclass->base = (struct nvkm_sclass) { -1, -1, AMPERE_DMA_COPY_B };
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int
+ga102_chan_map(struct nvkm_object *object, void *argv, u32 argc,
+	       enum nvkm_object_map *type, u64 *addr, u64 *size)
+{
+	struct ga102_chan *chan = ga102_chan(object);
+	struct nvkm_device *device = chan->object.engine->subdev.device;
+	u64 bar2 = nvkm_memory_bar2(chan->user);
+
+	if (bar2 == ~0ULL)
+		return -EFAULT;
+
+	*type = NVKM_OBJECT_MAP_IO;
+	*addr = device->func->resource_addr(device, 3) + bar2;
+	*size = 0x1000;
+	return 0;
+}
+
+static int
+ga102_chan_fini(struct nvkm_object *object, bool suspend)
+{
+	struct ga102_chan *chan = ga102_chan(object);
+	struct nvkm_device *device = chan->object.engine->subdev.device;
+
+	nvkm_wr32(device, chan->ctrl.chan, 0x00000003);
+
+	nvkm_wr32(device, chan->ctrl.runl + 0x098, 0x01000000);
+	nvkm_msec(device, 2000,
+		if (!(nvkm_rd32(device, chan->ctrl.runl + 0x098) & 0x00100000))
+			break;
+	);
+
+	nvkm_wr32(device, chan->ctrl.runl + 0x088, 0);
+
+	nvkm_wr32(device, chan->ctrl.chan, 0xffffffff);
+	return 0;
+}
+
+static int
+ga102_chan_init(struct nvkm_object *object)
+{
+	struct ga102_chan *chan = ga102_chan(object);
+	struct nvkm_device *device = chan->object.engine->subdev.device;
+
+	nvkm_mask(device, chan->ctrl.runl + 0x300, 0x80000000, 0x80000000);
+
+	nvkm_wr32(device, chan->ctrl.runl + 0x080, lower_32_bits(nvkm_memory_addr(chan->runl)));
+	nvkm_wr32(device, chan->ctrl.runl + 0x084, upper_32_bits(nvkm_memory_addr(chan->runl)));
+	nvkm_wr32(device, chan->ctrl.runl + 0x088, 2);
+
+	nvkm_wr32(device, chan->ctrl.chan, 0x00000002);
+	nvkm_wr32(device, chan->ctrl.runl + 0x0090, 0);
+	return 0;
+}
+
+static void *
+ga102_chan_dtor(struct nvkm_object *object)
+{
+	struct ga102_chan *chan = ga102_chan(object);
+
+	if (chan->vmm) {
+		nvkm_vmm_part(chan->vmm, chan->inst);
+		nvkm_vmm_unref(&chan->vmm);
+	}
+
+	nvkm_memory_unref(&chan->runl);
+	nvkm_memory_unref(&chan->user);
+	nvkm_memory_unref(&chan->inst);
+	nvkm_memory_unref(&chan->mthd);
+	return chan;
+}
+
+static const struct nvkm_object_func
+ga102_chan = {
+	.dtor = ga102_chan_dtor,
+	.init = ga102_chan_init,
+	.fini = ga102_chan_fini,
+	.map = ga102_chan_map,
+	.sclass = ga102_chan_sclass,
+};
+
+static int
+ga102_chan_new(struct nvkm_device *device,
+	       const struct nvkm_oclass *oclass, void *argv, u32 argc, struct nvkm_object **pobject)
+{
+	struct volta_channel_gpfifo_a_v0 *args = argv;
+	struct nvkm_top_device *tdev;
+	struct nvkm_vmm *vmm;
+	struct ga102_chan *chan;
+	int ret;
+
+	if (argc != sizeof(*args))
+		return -ENOSYS;
+
+	vmm = nvkm_uvmm_search(oclass->client, args->vmm);
+	if (IS_ERR(vmm))
+		return PTR_ERR(vmm);
+
+	if (!(chan = kzalloc(sizeof(*chan), GFP_KERNEL)))
+		return -ENOMEM;
+
+	nvkm_object_ctor(&ga102_chan, oclass, &chan->object);
+	*pobject = &chan->object;
+
+	list_for_each_entry(tdev, &device->top->device, head) {
+		if (tdev->type == NVKM_ENGINE_CE) {
+			chan->ctrl.runl = tdev->runlist;
+			break;
+		}
+	}
+
+	if (!chan->ctrl.runl)
+		return -ENODEV;
+
+	chan->ctrl.chan = nvkm_rd32(device, chan->ctrl.runl + 0x004) & 0xfffffff0;
+
+	args->chid = 0;
+	args->inst = 0;
+	args->token = nvkm_rd32(device, chan->ctrl.runl + 0x008) & 0xffff0000;
+
+	ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST, 0x1000, 0x1000, true, &chan->mthd);
+	if (ret)
+		return ret;
+
+	ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST, 0x1000, 0x1000, true, &chan->inst);
+	if (ret)
+		return ret;
+
+	nvkm_kmap(chan->inst);
+	nvkm_wo32(chan->inst, 0x010, 0x0000face);
+	nvkm_wo32(chan->inst, 0x030, 0x7ffff902);
+	nvkm_wo32(chan->inst, 0x048, lower_32_bits(args->ioffset));
+	nvkm_wo32(chan->inst, 0x04c, upper_32_bits(args->ioffset) |
+				     (order_base_2(args->ilength / 8) << 16));
+	nvkm_wo32(chan->inst, 0x084, 0x20400000);
+	nvkm_wo32(chan->inst, 0x094, 0x30000001);
+	nvkm_wo32(chan->inst, 0x0ac, 0x00020000);
+	nvkm_wo32(chan->inst, 0x0e4, 0x00000000);
+	nvkm_wo32(chan->inst, 0x0e8, 0);
+	nvkm_wo32(chan->inst, 0x0f4, 0x00001000);
+	nvkm_wo32(chan->inst, 0x0f8, 0x10003080);
+	nvkm_mo32(chan->inst, 0x218, 0x00000000, 0x00000000);
+	nvkm_wo32(chan->inst, 0x220, lower_32_bits(nvkm_memory_bar2(chan->mthd)));
+	nvkm_wo32(chan->inst, 0x224, upper_32_bits(nvkm_memory_bar2(chan->mthd)));
+	nvkm_done(chan->inst);
+
+	ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST, 0x1000, 0x1000, true, &chan->user);
+	if (ret)
+		return ret;
+
+	ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST, 0x1000, 0x1000, true, &chan->runl);
+	if (ret)
+		return ret;
+
+	nvkm_kmap(chan->runl);
+	nvkm_wo32(chan->runl, 0x00, 0x80030001);
+	nvkm_wo32(chan->runl, 0x04, 1);
+	nvkm_wo32(chan->runl, 0x08, 0);
+	nvkm_wo32(chan->runl, 0x0c, 0x00000000);
+	nvkm_wo32(chan->runl, 0x10, lower_32_bits(nvkm_memory_addr(chan->user)));
+	nvkm_wo32(chan->runl, 0x14, upper_32_bits(nvkm_memory_addr(chan->user)));
+	nvkm_wo32(chan->runl, 0x18, lower_32_bits(nvkm_memory_addr(chan->inst)));
+	nvkm_wo32(chan->runl, 0x1c, upper_32_bits(nvkm_memory_addr(chan->inst)));
+	nvkm_done(chan->runl);
+
+	ret = nvkm_vmm_join(vmm, chan->inst);
+	if (ret)
+		return ret;
+
+	chan->vmm = nvkm_vmm_ref(vmm);
+	return 0;
+}
+
+static const struct nvkm_device_oclass
+ga102_chan_oclass = {
+	.ctor = ga102_chan_new,
+};
+
+static int
+ga102_user_new(struct nvkm_device *device,
+	       const struct nvkm_oclass *oclass, void *argv, u32 argc, struct nvkm_object **pobject)
+{
+	return tu102_fifo_user_new(oclass, argv, argc, pobject);
+}
+
+static const struct nvkm_device_oclass
+ga102_user_oclass = {
+	.ctor = ga102_user_new,
+};
+
+static int
+ga102_fifo_sclass(struct nvkm_oclass *oclass, int index, const struct nvkm_device_oclass **class)
+{
+	if (index == 0) {
+		oclass->base = (struct nvkm_sclass) { -1, -1, VOLTA_USERMODE_A };
+		*class = &ga102_user_oclass;
+		return 0;
+	} else
+	if (index == 1) {
+		oclass->base = (struct nvkm_sclass) { 0, 0, AMPERE_CHANNEL_GPFIFO_B };
+		*class = &ga102_chan_oclass;
+		return 0;
+	}
+
+	return 2;
+}
+
+static int
+ga102_fifo_info(struct nvkm_engine *engine, u64 mthd, u64 *data)
+{
+	switch (mthd) {
+	case NV_DEVICE_HOST_CHANNELS: *data = 1; return 0;
+	default:
+		break;
+	}
+
+	return -ENOSYS;
+}
+
+static void *
+ga102_fifo_dtor(struct nvkm_engine *engine)
+{
+	return ga102_fifo(engine);
+}
+
+static const struct nvkm_engine_func
+ga102_fifo = {
+	.dtor = ga102_fifo_dtor,
+	.info = ga102_fifo_info,
+	.base.sclass = ga102_fifo_sclass,
+};
+
+int
+ga102_fifo_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst,
+	       struct nvkm_fifo **pfifo)
+{
+	struct ga102_fifo *fifo;
+
+	if (!(fifo = kzalloc(sizeof(*fifo), GFP_KERNEL)))
+		return -ENOMEM;
+
+	nvkm_engine_ctor(&ga102_fifo, device, type, inst, true, &fifo->base.engine);
+	*pfifo = &fifo->base;
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/top/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/top/ga100.c
index 31933f3e5a07..c982d834c8d9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/top/ga100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/top/ga100.c
@@ -54,7 +54,7 @@ ga100_top_oneinit(struct nvkm_top *top)
 			info->reset   = (data & 0x0000001f);
 			break;
 		case 2:
-			info->runlist = (data & 0x0000fc00) >> 10;
+			info->runlist = (data & 0x00fffc00);
 			info->engine  = (data & 0x00000003);
 			break;
 		default:
@@ -85,9 +85,10 @@ ga100_top_oneinit(struct nvkm_top *top)
 		}
 
 		nvkm_debug(subdev, "%02x.%d (%8s): addr %06x fault %2d "
-				   "runlist %2d engine %2d reset %2d\n", type, inst,
+				   "runlist %6x engine %2d reset %2d\n", type, inst,
 			   info->type == NVKM_SUBDEV_NR ? "????????" : nvkm_subdev_type[info->type],
-			   info->addr, info->fault, info->runlist, info->engine, info->reset);
+			   info->addr, info->fault, info->runlist < 0 ? 0 : info->runlist,
+			   info->engine, info->reset);
 		info = NULL;
 	}
 
diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig
index beb581b96ecd..418638e6e3b0 100644
--- a/drivers/gpu/drm/panel/Kconfig
+++ b/drivers/gpu/drm/panel/Kconfig
@@ -295,6 +295,7 @@ config DRM_PANEL_OLIMEX_LCD_OLINUXINO
 	depends on OF
 	depends on I2C
 	depends on BACKLIGHT_CLASS_DEVICE
+	select CRC32
 	help
 	  The panel is used with different sizes LCDs, from 480x272 to
 	  1280x800, and 24 bit per pixel.
diff --git a/drivers/gpu/drm/panel/panel-abt-y030xx067a.c b/drivers/gpu/drm/panel/panel-abt-y030xx067a.c
index 2d8794d495d0..3d8a9ab47cae 100644
--- a/drivers/gpu/drm/panel/panel-abt-y030xx067a.c
+++ b/drivers/gpu/drm/panel/panel-abt-y030xx067a.c
@@ -146,8 +146,8 @@ static const struct reg_sequence y030xx067a_init_sequence[] = {
 	{ 0x09, REG09_SUB_BRIGHT_R(0x20) },
 	{ 0x0a, REG0A_SUB_BRIGHT_B(0x20) },
 	{ 0x0b, REG0B_HD_FREERUN | REG0B_VD_FREERUN },
-	{ 0x0c, REG0C_CONTRAST_R(0x10) },
-	{ 0x0d, REG0D_CONTRAST_G(0x10) },
+	{ 0x0c, REG0C_CONTRAST_R(0x00) },
+	{ 0x0d, REG0D_CONTRAST_G(0x00) },
 	{ 0x0e, REG0E_CONTRAST_B(0x10) },
 	{ 0x0f, 0 },
 	{ 0x10, REG10_BRIGHT(0x7f) },
diff --git a/drivers/gpu/drm/r128/ati_pcigart.c b/drivers/gpu/drm/r128/ati_pcigart.c
index 0ecccf25a3c7..d2a0f5394fef 100644
--- a/drivers/gpu/drm/r128/ati_pcigart.c
+++ b/drivers/gpu/drm/r128/ati_pcigart.c
@@ -214,7 +214,7 @@ int drm_ati_pcigart_init(struct drm_device *dev, struct drm_ati_pcigart_info *ga
 	}
 	ret = 0;
 
-#if defined(__i386__) || defined(__x86_64__)
+#ifdef CONFIG_X86
 	wbinvd();
 #else
 	mb();
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 0473583dcdac..482fb0ae6cb5 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -119,7 +119,7 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags)
 #endif
 
 	if (pci_find_capability(pdev, PCI_CAP_ID_AGP))
-		rdev->agp = radeon_agp_head_init(rdev->ddev);
+		rdev->agp = radeon_agp_head_init(dev);
 	if (rdev->agp) {
 		rdev->agp->agp_mtrr = arch_phys_wc_add(
 			rdev->agp->agp_info.aper_base,
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
index 0daa8bba50f5..4bf4e25d7f01 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
@@ -86,12 +86,20 @@ int rcar_du_encoder_init(struct rcar_du_device *rcdu,
 	}
 
 	/*
-	 * Create and initialize the encoder. On Gen3 skip the LVDS1 output if
+	 * Create and initialize the encoder. On Gen3, skip the LVDS1 output if
 	 * the LVDS1 encoder is used as a companion for LVDS0 in dual-link
-	 * mode.
+	 * mode, or any LVDS output if it isn't connected. The latter may happen
+	 * on D3 or E3 as the LVDS encoders are needed to provide the pixel
+	 * clock to the DU, even when the LVDS outputs are not used.
 	 */
-	if (rcdu->info->gen >= 3 && output == RCAR_DU_OUTPUT_LVDS1) {
-		if (rcar_lvds_dual_link(bridge))
+	if (rcdu->info->gen >= 3) {
+		if (output == RCAR_DU_OUTPUT_LVDS1 &&
+		    rcar_lvds_dual_link(bridge))
+			return -ENOLINK;
+
+		if ((output == RCAR_DU_OUTPUT_LVDS0 ||
+		     output == RCAR_DU_OUTPUT_LVDS1) &&
+		    !rcar_lvds_is_connected(bridge))
 			return -ENOLINK;
 	}
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c
index d061b8de748f..b672c5bd72ee 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds.c
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c
@@ -576,6 +576,9 @@ static int rcar_lvds_attach(struct drm_bridge *bridge,
 {
 	struct rcar_lvds *lvds = bridge_to_rcar_lvds(bridge);
 
+	if (!lvds->next_bridge)
+		return 0;
+
 	return drm_bridge_attach(bridge->encoder, lvds->next_bridge, bridge,
 				 flags);
 }
@@ -598,6 +601,14 @@ bool rcar_lvds_dual_link(struct drm_bridge *bridge)
 }
 EXPORT_SYMBOL_GPL(rcar_lvds_dual_link);
 
+bool rcar_lvds_is_connected(struct drm_bridge *bridge)
+{
+	struct rcar_lvds *lvds = bridge_to_rcar_lvds(bridge);
+
+	return lvds->next_bridge != NULL;
+}
+EXPORT_SYMBOL_GPL(rcar_lvds_is_connected);
+
 /* -----------------------------------------------------------------------------
  * Probe & Remove
  */
diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.h b/drivers/gpu/drm/rcar-du/rcar_lvds.h
index 222ec0e60785..eb7c6ef03b00 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds.h
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds.h
@@ -16,6 +16,7 @@ struct drm_bridge;
 int rcar_lvds_clk_enable(struct drm_bridge *bridge, unsigned long freq);
 void rcar_lvds_clk_disable(struct drm_bridge *bridge);
 bool rcar_lvds_dual_link(struct drm_bridge *bridge);
+bool rcar_lvds_is_connected(struct drm_bridge *bridge);
 #else
 static inline int rcar_lvds_clk_enable(struct drm_bridge *bridge,
 				       unsigned long freq)
@@ -27,6 +28,10 @@ static inline bool rcar_lvds_dual_link(struct drm_bridge *bridge)
 {
 	return false;
 }
+static inline bool rcar_lvds_is_connected(struct drm_bridge *bridge)
+{
+	return false;
+}
 #endif /* CONFIG_DRM_RCAR_LVDS */
 
 #endif /* __RCAR_LVDS_H__ */
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c
index 8ab3247dbc4a..13c6b857158f 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c
@@ -1123,7 +1123,7 @@ static int cdn_dp_suspend(struct device *dev)
 	return ret;
 }
 
-static int cdn_dp_resume(struct device *dev)
+static __maybe_unused int cdn_dp_resume(struct device *dev)
 {
 	struct cdn_dp_device *dp = dev_get_drvdata(dev);
 
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index ba9e14da41b4..a25b98b7f5bd 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -1174,26 +1174,24 @@ static bool vop_crtc_mode_fixup(struct drm_crtc *crtc,
 	 *
 	 * Action plan:
 	 *
-	 * 1. When DRM gives us a mode, we should add 999 Hz to it.  That way
-	 *    if the clock we need is 60000001 Hz (~60 MHz) and DRM tells us to
-	 *    make 60000 kHz then the clock framework will actually give us
-	 *    the right clock.
+	 * 1. Try to set the exact rate first, and confirm the clock framework
+	 *    can provide it.
 	 *
-	 *    NOTE: if the PLL (maybe through a divider) could actually make
-	 *    a clock rate 999 Hz higher instead of the one we want then this
-	 *    could be a problem.  Unfortunately there's not much we can do
-	 *    since it's baked into DRM to use kHz.  It shouldn't matter in
-	 *    practice since Rockchip PLLs are controlled by tables and
-	 *    even if there is a divider in the middle I wouldn't expect PLL
-	 *    rates in the table that are just a few kHz different.
+	 * 2. If the clock framework cannot provide the exact rate, we should
+	 *    add 999 Hz to the requested rate.  That way if the clock we need
+	 *    is 60000001 Hz (~60 MHz) and DRM tells us to make 60000 kHz then
+	 *    the clock framework will actually give us the right clock.
 	 *
-	 * 2. Get the clock framework to round the rate for us to tell us
+	 * 3. Get the clock framework to round the rate for us to tell us
 	 *    what it will actually make.
 	 *
-	 * 3. Store the rounded up rate so that we don't need to worry about
+	 * 4. Store the rounded up rate so that we don't need to worry about
 	 *    this in the actual clk_set_rate().
 	 */
-	rate = clk_round_rate(vop->dclk, adjusted_mode->clock * 1000 + 999);
+	rate = clk_round_rate(vop->dclk, adjusted_mode->clock * 1000);
+	if (rate / 1000 != adjusted_mode->clock)
+		rate = clk_round_rate(vop->dclk,
+				      adjusted_mode->clock * 1000 + 999);
 	adjusted_mode->clock = DIV_ROUND_UP(rate, 1000);
 
 	return true;
diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
index f75fb157f2ff..016b877051da 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
@@ -216,11 +216,13 @@ static int sun8i_dw_hdmi_bind(struct device *dev, struct device *master,
 		goto err_disable_clk_tmds;
 	}
 
+	ret = sun8i_hdmi_phy_init(hdmi->phy);
+	if (ret)
+		goto err_disable_clk_tmds;
+
 	drm_encoder_helper_add(encoder, &sun8i_dw_hdmi_encoder_helper_funcs);
 	drm_simple_encoder_init(drm, encoder, DRM_MODE_ENCODER_TMDS);
 
-	sun8i_hdmi_phy_init(hdmi->phy);
-
 	plat_data->mode_valid = hdmi->quirks->mode_valid;
 	plat_data->use_drm_infoframe = hdmi->quirks->use_drm_infoframe;
 	sun8i_hdmi_phy_set_ops(hdmi->phy, plat_data);
@@ -262,6 +264,7 @@ static void sun8i_dw_hdmi_unbind(struct device *dev, struct device *master,
 	struct sun8i_dw_hdmi *hdmi = dev_get_drvdata(dev);
 
 	dw_hdmi_unbind(hdmi->hdmi);
+	sun8i_hdmi_phy_deinit(hdmi->phy);
 	clk_disable_unprepare(hdmi->clk_tmds);
 	reset_control_assert(hdmi->rst_ctrl);
 	gpiod_set_value(hdmi->ddc_en, 0);
diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
index 74f6ed0e2570..bffe1b9cd3dc 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
@@ -169,6 +169,7 @@ struct sun8i_hdmi_phy {
 	struct clk			*clk_phy;
 	struct clk			*clk_pll0;
 	struct clk			*clk_pll1;
+	struct device			*dev;
 	unsigned int			rcal;
 	struct regmap			*regs;
 	struct reset_control		*rst_phy;
@@ -205,7 +206,8 @@ encoder_to_sun8i_dw_hdmi(struct drm_encoder *encoder)
 
 int sun8i_hdmi_phy_get(struct sun8i_dw_hdmi *hdmi, struct device_node *node);
 
-void sun8i_hdmi_phy_init(struct sun8i_hdmi_phy *phy);
+int sun8i_hdmi_phy_init(struct sun8i_hdmi_phy *phy);
+void sun8i_hdmi_phy_deinit(struct sun8i_hdmi_phy *phy);
 void sun8i_hdmi_phy_set_ops(struct sun8i_hdmi_phy *phy,
 			    struct dw_hdmi_plat_data *plat_data);
 
diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
index c9239708d398..b64d93da651d 100644
--- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
+++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
@@ -506,9 +506,60 @@ static void sun8i_hdmi_phy_init_h3(struct sun8i_hdmi_phy *phy)
 	phy->rcal = (val & SUN8I_HDMI_PHY_ANA_STS_RCAL_MASK) >> 2;
 }
 
-void sun8i_hdmi_phy_init(struct sun8i_hdmi_phy *phy)
+int sun8i_hdmi_phy_init(struct sun8i_hdmi_phy *phy)
 {
+	int ret;
+
+	ret = reset_control_deassert(phy->rst_phy);
+	if (ret) {
+		dev_err(phy->dev, "Cannot deassert phy reset control: %d\n", ret);
+		return ret;
+	}
+
+	ret = clk_prepare_enable(phy->clk_bus);
+	if (ret) {
+		dev_err(phy->dev, "Cannot enable bus clock: %d\n", ret);
+		goto err_assert_rst_phy;
+	}
+
+	ret = clk_prepare_enable(phy->clk_mod);
+	if (ret) {
+		dev_err(phy->dev, "Cannot enable mod clock: %d\n", ret);
+		goto err_disable_clk_bus;
+	}
+
+	if (phy->variant->has_phy_clk) {
+		ret = sun8i_phy_clk_create(phy, phy->dev,
+					   phy->variant->has_second_pll);
+		if (ret) {
+			dev_err(phy->dev, "Couldn't create the PHY clock\n");
+			goto err_disable_clk_mod;
+		}
+
+		clk_prepare_enable(phy->clk_phy);
+	}
+
 	phy->variant->phy_init(phy);
+
+	return 0;
+
+err_disable_clk_mod:
+	clk_disable_unprepare(phy->clk_mod);
+err_disable_clk_bus:
+	clk_disable_unprepare(phy->clk_bus);
+err_assert_rst_phy:
+	reset_control_assert(phy->rst_phy);
+
+	return ret;
+}
+
+void sun8i_hdmi_phy_deinit(struct sun8i_hdmi_phy *phy)
+{
+	clk_disable_unprepare(phy->clk_mod);
+	clk_disable_unprepare(phy->clk_bus);
+	clk_disable_unprepare(phy->clk_phy);
+
+	reset_control_assert(phy->rst_phy);
 }
 
 void sun8i_hdmi_phy_set_ops(struct sun8i_hdmi_phy *phy,
@@ -638,6 +689,7 @@ static int sun8i_hdmi_phy_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	phy->variant = (struct sun8i_hdmi_phy_variant *)match->data;
+	phy->dev = dev;
 
 	ret = of_address_to_resource(node, 0, &res);
 	if (ret) {
@@ -696,47 +748,10 @@ static int sun8i_hdmi_phy_probe(struct platform_device *pdev)
 		goto err_put_clk_pll1;
 	}
 
-	ret = reset_control_deassert(phy->rst_phy);
-	if (ret) {
-		dev_err(dev, "Cannot deassert phy reset control: %d\n", ret);
-		goto err_put_rst_phy;
-	}
-
-	ret = clk_prepare_enable(phy->clk_bus);
-	if (ret) {
-		dev_err(dev, "Cannot enable bus clock: %d\n", ret);
-		goto err_deassert_rst_phy;
-	}
-
-	ret = clk_prepare_enable(phy->clk_mod);
-	if (ret) {
-		dev_err(dev, "Cannot enable mod clock: %d\n", ret);
-		goto err_disable_clk_bus;
-	}
-
-	if (phy->variant->has_phy_clk) {
-		ret = sun8i_phy_clk_create(phy, dev,
-					   phy->variant->has_second_pll);
-		if (ret) {
-			dev_err(dev, "Couldn't create the PHY clock\n");
-			goto err_disable_clk_mod;
-		}
-
-		clk_prepare_enable(phy->clk_phy);
-	}
-
 	platform_set_drvdata(pdev, phy);
 
 	return 0;
 
-err_disable_clk_mod:
-	clk_disable_unprepare(phy->clk_mod);
-err_disable_clk_bus:
-	clk_disable_unprepare(phy->clk_bus);
-err_deassert_rst_phy:
-	reset_control_assert(phy->rst_phy);
-err_put_rst_phy:
-	reset_control_put(phy->rst_phy);
 err_put_clk_pll1:
 	clk_put(phy->clk_pll1);
 err_put_clk_pll0:
@@ -753,12 +768,6 @@ static int sun8i_hdmi_phy_remove(struct platform_device *pdev)
 {
 	struct sun8i_hdmi_phy *phy = platform_get_drvdata(pdev);
 
-	clk_disable_unprepare(phy->clk_mod);
-	clk_disable_unprepare(phy->clk_bus);
-	clk_disable_unprepare(phy->clk_phy);
-
-	reset_control_assert(phy->rst_phy);
-
 	reset_control_put(phy->rst_phy);
 
 	clk_put(phy->clk_pll0);
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index 16c7aabb94d3..a29d64f87563 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -1845,7 +1845,6 @@ tegra_crtc_update_memory_bandwidth(struct drm_crtc *crtc,
 				   bool prepare_bandwidth_transition)
 {
 	const struct tegra_plane_state *old_tegra_state, *new_tegra_state;
-	const struct tegra_dc_state *old_dc_state, *new_dc_state;
 	u32 i, new_avg_bw, old_avg_bw, new_peak_bw, old_peak_bw;
 	const struct drm_plane_state *old_plane_state;
 	const struct drm_crtc_state *old_crtc_state;
@@ -1858,8 +1857,6 @@ tegra_crtc_update_memory_bandwidth(struct drm_crtc *crtc,
 		return;
 
 	old_crtc_state = drm_atomic_get_old_crtc_state(state, crtc);
-	old_dc_state = to_const_dc_state(old_crtc_state);
-	new_dc_state = to_const_dc_state(crtc->state);
 
 	if (!crtc->state->active) {
 		if (!old_crtc_state->active)
diff --git a/drivers/gpu/drm/tegra/dc.h b/drivers/gpu/drm/tegra/dc.h
index f0cb691852a1..40378308d527 100644
--- a/drivers/gpu/drm/tegra/dc.h
+++ b/drivers/gpu/drm/tegra/dc.h
@@ -35,12 +35,6 @@ static inline struct tegra_dc_state *to_dc_state(struct drm_crtc_state *state)
 	return NULL;
 }
 
-static inline const struct tegra_dc_state *
-to_const_dc_state(const struct drm_crtc_state *state)
-{
-	return to_dc_state((struct drm_crtc_state *)state);
-}
-
 struct tegra_dc_stats {
 	unsigned long frames;
 	unsigned long vblank;
diff --git a/drivers/gpu/drm/tegra/uapi.c b/drivers/gpu/drm/tegra/uapi.c
index dc16a24f4dbe..690a339c52ec 100644
--- a/drivers/gpu/drm/tegra/uapi.c
+++ b/drivers/gpu/drm/tegra/uapi.c
@@ -222,7 +222,7 @@ int tegra_drm_ioctl_channel_map(struct drm_device *drm, void *data, struct drm_f
 		mapping->iova = sg_dma_address(mapping->sgt->sgl);
 	}
 
-	mapping->iova_end = mapping->iova + host1x_to_tegra_bo(mapping->bo)->size;
+	mapping->iova_end = mapping->iova + host1x_to_tegra_bo(mapping->bo)->gem.size;
 
 	err = xa_alloc(&context->mappings, &args->mapping, mapping, XA_LIMIT(1, U32_MAX),
 		       GFP_KERNEL);
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index cb38b1a17b09..82cbb29a05aa 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -383,7 +383,8 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 	else
 		gfp_flags |= GFP_HIGHUSER;
 
-	for (order = min(MAX_ORDER - 1UL, __fls(num_pages)); num_pages;
+	for (order = min_t(unsigned int, MAX_ORDER - 1, __fls(num_pages));
+	     num_pages;
 	     order = min_t(unsigned int, order, __fls(num_pages))) {
 		bool apply_caching = false;
 		struct ttm_pool_type *pt;
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 4a1115043114..ed8a4b7f8b6e 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -167,8 +167,6 @@ vc4_hdmi_connector_detect(struct drm_connector *connector, bool force)
 	struct vc4_hdmi *vc4_hdmi = connector_to_vc4_hdmi(connector);
 	bool connected = false;
 
-	WARN_ON(pm_runtime_resume_and_get(&vc4_hdmi->pdev->dev));
-
 	if (vc4_hdmi->hpd_gpio &&
 	    gpiod_get_value_cansleep(vc4_hdmi->hpd_gpio)) {
 		connected = true;
@@ -189,12 +187,10 @@ vc4_hdmi_connector_detect(struct drm_connector *connector, bool force)
 			}
 		}
 
-		pm_runtime_put(&vc4_hdmi->pdev->dev);
 		return connector_status_connected;
 	}
 
 	cec_phys_addr_invalidate(vc4_hdmi->cec_adap);
-	pm_runtime_put(&vc4_hdmi->pdev->dev);
 	return connector_status_disconnected;
 }
 
@@ -436,7 +432,7 @@ static void vc4_hdmi_set_avi_infoframe(struct drm_encoder *encoder)
 	struct vc4_hdmi_encoder *vc4_encoder = to_vc4_hdmi_encoder(encoder);
 	struct drm_connector *connector = &vc4_hdmi->connector;
 	struct drm_connector_state *cstate = connector->state;
-	struct drm_crtc *crtc = cstate->crtc;
+	struct drm_crtc *crtc = encoder->crtc;
 	const struct drm_display_mode *mode = &crtc->state->adjusted_mode;
 	union hdmi_infoframe frame;
 	int ret;
@@ -541,11 +537,8 @@ static bool vc4_hdmi_supports_scrambling(struct drm_encoder *encoder,
 
 static void vc4_hdmi_enable_scrambling(struct drm_encoder *encoder)
 {
+	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
-	struct drm_connector *connector = &vc4_hdmi->connector;
-	struct drm_connector_state *cstate = connector->state;
-	struct drm_crtc *crtc = cstate->crtc;
-	struct drm_display_mode *mode = &crtc->state->adjusted_mode;
 
 	if (!vc4_hdmi_supports_scrambling(encoder, mode))
 		return;
@@ -566,18 +559,17 @@ static void vc4_hdmi_enable_scrambling(struct drm_encoder *encoder)
 static void vc4_hdmi_disable_scrambling(struct drm_encoder *encoder)
 {
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
-	struct drm_connector *connector = &vc4_hdmi->connector;
-	struct drm_connector_state *cstate = connector->state;
+	struct drm_crtc *crtc = encoder->crtc;
 
 	/*
-	 * At boot, connector->state will be NULL. Since we don't know the
+	 * At boot, encoder->crtc will be NULL. Since we don't know the
 	 * state of the scrambler and in order to avoid any
 	 * inconsistency, let's disable it all the time.
 	 */
-	if (cstate && !vc4_hdmi_supports_scrambling(encoder, &cstate->crtc->mode))
+	if (crtc && !vc4_hdmi_supports_scrambling(encoder, &crtc->mode))
 		return;
 
-	if (cstate && !vc4_hdmi_mode_needs_scrambling(&cstate->crtc->mode))
+	if (crtc && !vc4_hdmi_mode_needs_scrambling(&crtc->mode))
 		return;
 
 	if (delayed_work_pending(&vc4_hdmi->scrambling_work))
@@ -635,6 +627,7 @@ static void vc4_hdmi_encoder_post_crtc_powerdown(struct drm_encoder *encoder,
 		vc4_hdmi->variant->phy_disable(vc4_hdmi);
 
 	clk_disable_unprepare(vc4_hdmi->pixel_bvb_clock);
+	clk_disable_unprepare(vc4_hdmi->hsm_clock);
 	clk_disable_unprepare(vc4_hdmi->pixel_clock);
 
 	ret = pm_runtime_put(&vc4_hdmi->pdev->dev);
@@ -898,9 +891,7 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder,
 		vc4_hdmi_encoder_get_connector_state(encoder, state);
 	struct vc4_hdmi_connector_state *vc4_conn_state =
 		conn_state_to_vc4_hdmi_conn_state(conn_state);
-	struct drm_crtc_state *crtc_state =
-		drm_atomic_get_new_crtc_state(state, conn_state->crtc);
-	struct drm_display_mode *mode = &crtc_state->adjusted_mode;
+	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
 	unsigned long bvb_rate, pixel_rate, hsm_rate;
 	int ret;
@@ -947,6 +938,13 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder,
 		return;
 	}
 
+	ret = clk_prepare_enable(vc4_hdmi->hsm_clock);
+	if (ret) {
+		DRM_ERROR("Failed to turn on HSM clock: %d\n", ret);
+		clk_disable_unprepare(vc4_hdmi->pixel_clock);
+		return;
+	}
+
 	vc4_hdmi_cec_update_clk_div(vc4_hdmi);
 
 	if (pixel_rate > 297000000)
@@ -959,6 +957,7 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder,
 	ret = clk_set_min_rate(vc4_hdmi->pixel_bvb_clock, bvb_rate);
 	if (ret) {
 		DRM_ERROR("Failed to set pixel bvb clock rate: %d\n", ret);
+		clk_disable_unprepare(vc4_hdmi->hsm_clock);
 		clk_disable_unprepare(vc4_hdmi->pixel_clock);
 		return;
 	}
@@ -966,6 +965,7 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder,
 	ret = clk_prepare_enable(vc4_hdmi->pixel_bvb_clock);
 	if (ret) {
 		DRM_ERROR("Failed to turn on pixel bvb clock: %d\n", ret);
+		clk_disable_unprepare(vc4_hdmi->hsm_clock);
 		clk_disable_unprepare(vc4_hdmi->pixel_clock);
 		return;
 	}
@@ -985,11 +985,7 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder,
 static void vc4_hdmi_encoder_pre_crtc_enable(struct drm_encoder *encoder,
 					     struct drm_atomic_state *state)
 {
-	struct drm_connector_state *conn_state =
-		vc4_hdmi_encoder_get_connector_state(encoder, state);
-	struct drm_crtc_state *crtc_state =
-		drm_atomic_get_new_crtc_state(state, conn_state->crtc);
-	struct drm_display_mode *mode = &crtc_state->adjusted_mode;
+	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
 	struct vc4_hdmi_encoder *vc4_encoder = to_vc4_hdmi_encoder(encoder);
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
 
@@ -1012,11 +1008,7 @@ static void vc4_hdmi_encoder_pre_crtc_enable(struct drm_encoder *encoder,
 static void vc4_hdmi_encoder_post_crtc_enable(struct drm_encoder *encoder,
 					      struct drm_atomic_state *state)
 {
-	struct drm_connector_state *conn_state =
-		vc4_hdmi_encoder_get_connector_state(encoder, state);
-	struct drm_crtc_state *crtc_state =
-		drm_atomic_get_new_crtc_state(state, conn_state->crtc);
-	struct drm_display_mode *mode = &crtc_state->adjusted_mode;
+	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
 	struct vc4_hdmi_encoder *vc4_encoder = to_vc4_hdmi_encoder(encoder);
 	bool hsync_pos = mode->flags & DRM_MODE_FLAG_PHSYNC;
@@ -1204,8 +1196,8 @@ static void vc4_hdmi_audio_set_mai_clock(struct vc4_hdmi *vc4_hdmi,
 
 static void vc4_hdmi_set_n_cts(struct vc4_hdmi *vc4_hdmi, unsigned int samplerate)
 {
-	struct drm_connector *connector = &vc4_hdmi->connector;
-	struct drm_crtc *crtc = connector->state->crtc;
+	struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base;
+	struct drm_crtc *crtc = encoder->crtc;
 	const struct drm_display_mode *mode = &crtc->state->adjusted_mode;
 	u32 n, cts;
 	u64 tmp;
@@ -1238,13 +1230,13 @@ static inline struct vc4_hdmi *dai_to_hdmi(struct snd_soc_dai *dai)
 static int vc4_hdmi_audio_startup(struct device *dev, void *data)
 {
 	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
-	struct drm_connector *connector = &vc4_hdmi->connector;
+	struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base;
 
 	/*
 	 * If the HDMI encoder hasn't probed, or the encoder is
 	 * currently in DVI mode, treat the codec dai as missing.
 	 */
-	if (!connector->state || !(HDMI_READ(HDMI_RAM_PACKET_CONFIG) &
+	if (!encoder->crtc || !(HDMI_READ(HDMI_RAM_PACKET_CONFIG) &
 				VC4_HDMI_RAM_PACKET_ENABLE))
 		return -ENODEV;
 
@@ -1403,14 +1395,6 @@ static int vc4_hdmi_audio_prepare(struct device *dev, void *data,
 	return 0;
 }
 
-static const struct snd_soc_dapm_widget vc4_hdmi_audio_widgets[] = {
-	SND_SOC_DAPM_OUTPUT("TX"),
-};
-
-static const struct snd_soc_dapm_route vc4_hdmi_audio_routes[] = {
-	{ "TX", NULL, "Playback" },
-};
-
 static const struct snd_soc_component_driver vc4_hdmi_audio_cpu_dai_comp = {
 	.name = "vc4-hdmi-cpu-dai-component",
 };
@@ -2114,29 +2098,6 @@ static int vc5_hdmi_init_resources(struct vc4_hdmi *vc4_hdmi)
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int vc4_hdmi_runtime_suspend(struct device *dev)
-{
-	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
-
-	clk_disable_unprepare(vc4_hdmi->hsm_clock);
-
-	return 0;
-}
-
-static int vc4_hdmi_runtime_resume(struct device *dev)
-{
-	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
-	int ret;
-
-	ret = clk_prepare_enable(vc4_hdmi->hsm_clock);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-#endif
-
 static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 {
 	const struct vc4_hdmi_variant *variant = of_device_get_match_data(dev);
@@ -2391,18 +2352,11 @@ static const struct of_device_id vc4_hdmi_dt_match[] = {
 	{}
 };
 
-static const struct dev_pm_ops vc4_hdmi_pm_ops = {
-	SET_RUNTIME_PM_OPS(vc4_hdmi_runtime_suspend,
-			   vc4_hdmi_runtime_resume,
-			   NULL)
-};
-
 struct platform_driver vc4_hdmi_driver = {
 	.probe = vc4_hdmi_dev_probe,
 	.remove = vc4_hdmi_dev_remove,
 	.driver = {
 		.name = "vc4_hdmi",
 		.of_match_table = vc4_hdmi_dt_match,
-		.pm = &vc4_hdmi_pm_ops,
 	},
 };