Merge tag 'amd-drm-fixes-5.19-2022-06-08' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-5.19-2022-06-08:

amdgpu:
- DCN 3.1 golden settings fix
- eDP fixes
- DMCUB fixes
- GFX11 fixes and cleanups
- VCN fix for yellow carp
- GMC11 fixes
- RAS fixes
- GPUVM TLB flush fixes
- SMU13 fixes
- VCN3 AV1 regression fix
- VCN2 JPEG fix
- Other misc fixes

amdkfd:
- MMU notifier fix
- Support for more GC 10.3.x families
- Pinned BO handling fix
- Partial migration bug fix

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220608203008.6187-1-alexander.deucher@amd.com

37 files changed, 330 insertions, 251 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 67abf8dcd30a..6b6d46e29e6e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1918,9 +1918,6 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct amdgpu_device *adev,
 		return -EINVAL;
 	}
 
-	/* delete kgd_mem from kfd_bo_list to avoid re-validating
-	 * this BO in BO's restoring after eviction.
-	 */
 	mutex_lock(&mem->process_info->lock);
 
 	ret = amdgpu_bo_reserve(bo, true);
@@ -1943,7 +1940,6 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct amdgpu_device *adev,
 
 	amdgpu_amdkfd_remove_eviction_fence(
 		bo, mem->process_info->eviction_fence);
-	list_del_init(&mem->validate_list.head);
 
 	if (size)
 		*size = amdgpu_bo_size(bo);
@@ -2512,12 +2508,15 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 	process_info->eviction_fence = new_fence;
 	*ef = dma_fence_get(&new_fence->base);
 
-	/* Attach new eviction fence to all BOs */
+	/* Attach new eviction fence to all BOs except pinned ones */
 	list_for_each_entry(mem, &process_info->kfd_bo_list,
-		validate_list.head)
+		validate_list.head) {
+		if (mem->bo->tbo.pin_count)
+			continue;
+
 		amdgpu_bo_fence(mem->bo,
 			&process_info->eviction_fence->base, true);
-
+	}
 	/* Attach eviction fence to PD / PT BOs */
 	list_for_each_entry(peer_vm, &process_info->vm_list_head,
 			    vm_list_node) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index ede2fa56f6c9..16699158e00d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -594,17 +594,20 @@ int amdgpu_get_gfx_off_status(struct amdgpu_device *adev, uint32_t *value)
 int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block)
 {
 	int r;
-	r = amdgpu_ras_block_late_init(adev, ras_block);
-	if (r)
-		return r;
 
 	if (amdgpu_ras_is_supported(adev, ras_block->block)) {
 		if (!amdgpu_persistent_edc_harvesting_supported(adev))
 			amdgpu_ras_reset_error_status(adev, AMDGPU_RAS_BLOCK__GFX);
 
+		r = amdgpu_ras_block_late_init(adev, ras_block);
+		if (r)
+			return r;
+
 		r = amdgpu_irq_get(adev, &adev->gfx.cp_ecc_error_irq, 0);
 		if (r)
 			goto late_fini;
+	} else {
+		amdgpu_ras_feature_enable_on_boot(adev, ras_block, 0);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 798c56214a23..aebc384531ac 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -518,6 +518,8 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
 	case IP_VERSION(9, 1, 0):
 	/* RENOIR looks like RAVEN */
 	case IP_VERSION(9, 3, 0):
+	/* GC 10.3.7 */
+	case IP_VERSION(10, 3, 7):
 		if (amdgpu_tmz == 0) {
 			adev->gmc.tmz_enabled = false;
 			dev_info(adev->dev,
@@ -540,8 +542,6 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
 	case IP_VERSION(10, 3, 1):
 	/* YELLOW_CARP*/
 	case IP_VERSION(10, 3, 3):
-	/* GC 10.3.7 */
-	case IP_VERSION(10, 3, 7):
 		/* Don't enable it by default yet.
 		 */
 		if (amdgpu_tmz < 1) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 2de9309a4193..dac202ae864d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -197,6 +197,13 @@ static ssize_t amdgpu_ras_debugfs_read(struct file *f, char __user *buf,
 	if (amdgpu_ras_query_error_status(obj->adev, &info))
 		return -EINVAL;
 
+	/* Hardware counter will be reset automatically after the query on Vega20 and Arcturus */
+	if (obj->adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) &&
+	    obj->adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) {
+		if (amdgpu_ras_reset_error_status(obj->adev, info.head.block))
+			dev_warn(obj->adev->dev, "Failed to reset error counter and error status");
+	}
+
 	s = snprintf(val, sizeof(val), "%s: %lu\n%s: %lu\n",
 			"ue", info.ue_count,
 			"ce", info.ce_count);
@@ -550,9 +557,10 @@ static ssize_t amdgpu_ras_sysfs_read(struct device *dev,
 	if (amdgpu_ras_query_error_status(obj->adev, &info))
 		return -EINVAL;
 
-	if (obj->adev->asic_type == CHIP_ALDEBARAN) {
+	if (obj->adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) &&
+	    obj->adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) {
 		if (amdgpu_ras_reset_error_status(obj->adev, info.head.block))
-			DRM_WARN("Failed to reset error counter and error status");
+			dev_warn(obj->adev->dev, "Failed to reset error counter and error status");
 	}
 
 	return sysfs_emit(buf, "%s: %lu\n%s: %lu\n", "ue", info.ue_count,
@@ -1027,9 +1035,6 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
 		}
 	}
 
-	if (!amdgpu_persistent_edc_harvesting_supported(adev))
-		amdgpu_ras_reset_error_status(adev, info->head.block);
-
 	return 0;
 }
 
@@ -1149,6 +1154,12 @@ int amdgpu_ras_query_error_count(struct amdgpu_device *adev,
 		if (res)
 			return res;
 
+		if (adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) &&
+		    adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) {
+			if (amdgpu_ras_reset_error_status(adev, info.head.block))
+				dev_warn(adev->dev, "Failed to reset error counter and error status");
+		}
+
 		ce += info.ce_count;
 		ue += info.ue_count;
 	}
@@ -1792,6 +1803,12 @@ static void amdgpu_ras_log_on_err_counter(struct amdgpu_device *adev)
 			continue;
 
 		amdgpu_ras_query_error_status(adev, &info);
+
+		if (adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) &&
+		    adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) {
+			if (amdgpu_ras_reset_error_status(adev, info.head.block))
+				dev_warn(adev->dev, "Failed to reset error counter and error status");
+		}
 	}
 }
 
@@ -2278,8 +2295,9 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev)
 	    !amdgpu_ras_asic_supported(adev))
 		return;
 
-	if (!(amdgpu_sriov_vf(adev) &&
-		(adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 2))))
+	/* If driver run on sriov guest side, only enable ras for aldebaran */
+	if (amdgpu_sriov_vf(adev) &&
+		adev->ip_versions[MP1_HWIP][0] != IP_VERSION(13, 0, 2))
 		return;
 
 	if (!adev->gmc.xgmi.connected_to_cpu) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 2ceeaa4c793a..dc76d2b3ce52 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -679,6 +679,7 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 {
 	struct amdgpu_vm_update_params params;
 	struct amdgpu_vm_bo_base *entry;
+	bool flush_tlb_needed = false;
 	int r, idx;
 
 	if (list_empty(&vm->relocated))
@@ -697,6 +698,9 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 		goto error;
 
 	list_for_each_entry(entry, &vm->relocated, vm_status) {
+		/* vm_flush_needed after updating moved PDEs */
+		flush_tlb_needed |= entry->moved;
+
 		r = amdgpu_vm_pde_update(&params, entry);
 		if (r)
 			goto error;
@@ -706,8 +710,8 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 	if (r)
 		goto error;
 
-	/* vm_flush_needed after updating PDEs */
-	atomic64_inc(&vm->tlb_seq);
+	if (flush_tlb_needed)
+		atomic64_inc(&vm->tlb_seq);
 
 	while (!list_empty(&vm->relocated)) {
 		entry = list_first_entry(&vm->relocated,
@@ -789,6 +793,11 @@ int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	flush_tlb |= adev->gmc.xgmi.num_physical_nodes &&
 		     adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 0);
 
+	/*
+	 * On GFX8 and older any 8 PTE block with a valid bit set enters the TLB
+	 */
+	flush_tlb |= adev->ip_versions[GC_HWIP][0] < IP_VERSION(9, 0, 0);
+
 	memset(&params, 0, sizeof(params));
 	params.adev = adev;
 	params.vm = vm;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 8c0a3fc7aaa6..a4a6751b1e44 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -1096,6 +1096,7 @@ static void gfx_v11_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd,
 	dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_IB_STS2);
 	dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_IB_DBG1);
 	dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_M0);
+	dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_MODE);
 }
 
 static void gfx_v11_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd,
@@ -1316,7 +1317,7 @@ static void gfx_v11_0_rlc_backdoor_autoload_copy_ucode(struct amdgpu_device *ade
 		memset(ptr + toc_offset + fw_size, 0, toc_fw_size - fw_size);
 
 	if ((id != SOC21_FIRMWARE_ID_RS64_PFP) && (id != SOC21_FIRMWARE_ID_RS64_ME))
-		*(uint64_t *)fw_autoload_mask |= 1 << id;
+		*(uint64_t *)fw_autoload_mask |= 1ULL << id;
 }
 
 static void gfx_v11_0_rlc_backdoor_autoload_copy_toc_ucode(struct amdgpu_device *adev,
@@ -1983,7 +1984,7 @@ static int gfx_v11_0_init_csb(struct amdgpu_device *adev)
 	return 0;
 }
 
-void gfx_v11_0_rlc_stop(struct amdgpu_device *adev)
+static void gfx_v11_0_rlc_stop(struct amdgpu_device *adev)
 {
 	u32 tmp = RREG32_SOC15(GC, 0, regRLC_CNTL);
 
@@ -6028,6 +6029,7 @@ static void gfx_v11_0_handle_priv_fault(struct amdgpu_device *adev,
 		break;
 	default:
 		BUG();
+		break;
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index a0c0b7d9f444..7f4b480ae66e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -638,6 +638,12 @@ static int gmc_v11_0_mc_init(struct amdgpu_device *adev)
 	adev->gmc.aper_base = pci_resource_start(adev->pdev, 0);
 	adev->gmc.aper_size = pci_resource_len(adev->pdev, 0);
 
+#ifdef CONFIG_X86_64
+	if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) {
+		adev->gmc.aper_base = adev->mmhub.funcs->get_mc_fb_offset(adev);
+		adev->gmc.aper_size = adev->gmc.real_vram_size;
+	}
+#endif
 	/* In case the PCI BAR is larger than the actual amount of vram */
 	adev->gmc.visible_vram_size = adev->gmc.aper_size;
 	if (adev->gmc.visible_vram_size > adev->gmc.real_vram_size)
diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
index 5d2dfeff8fe5..d63d3f2b8a16 100644
--- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
@@ -299,7 +299,7 @@ static const struct imu_rlc_ram_golden imu_rlc_ram_golden_11_0_2[] =
 	IMU_RLC_RAM_GOLDEN_VALUE(GC, 0, regCPG_PSP_DEBUG, CPG_PSP_DEBUG__GPA_OVERRIDE_MASK, 0)
 };
 
-void program_imu_rlc_ram(struct amdgpu_device *adev,
+static void program_imu_rlc_ram(struct amdgpu_device *adev,
 				const struct imu_rlc_ram_golden *regs,
 				const u32 array_size)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
index d2722adabd1b..f3c1af5130ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
@@ -535,6 +535,10 @@ void jpeg_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring,
 {
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JPEG_IH_CTRL_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, (vmid << JPEG_IH_CTRL__IH_VMID__SHIFT));
+
 	amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET,
 		0, 0, PACKETJ_TYPE0));
 	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
@@ -768,7 +772,7 @@ static const struct amdgpu_ring_funcs jpeg_v2_0_dec_ring_vm_funcs = {
 		8 + /* jpeg_v2_0_dec_ring_emit_vm_flush */
 		18 + 18 + /* jpeg_v2_0_dec_ring_emit_fence x2 vm fence */
 		8 + 16,
-	.emit_ib_size = 22, /* jpeg_v2_0_dec_ring_emit_ib */
+	.emit_ib_size = 24, /* jpeg_v2_0_dec_ring_emit_ib */
 	.emit_ib = jpeg_v2_0_dec_ring_emit_ib,
 	.emit_fence = jpeg_v2_0_dec_ring_emit_fence,
 	.emit_vm_flush = jpeg_v2_0_dec_ring_emit_vm_flush,
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h
index 1a03baa59755..654e43e83e2c 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h
@@ -41,6 +41,7 @@
 #define mmUVD_JRBC_RB_REF_DATA_INTERNAL_OFFSET				0x4084
 #define mmUVD_JRBC_STATUS_INTERNAL_OFFSET				0x4089
 #define mmUVD_JPEG_PITCH_INTERNAL_OFFSET				0x401f
+#define mmUVD_JPEG_IH_CTRL_INTERNAL_OFFSET				0x4149
 
 #define JRBC_DEC_EXTERNAL_REG_WRITE_ADDR				0x18000
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index fcf51947bb18..7eee004cf3ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -541,7 +541,7 @@ static void mes_v11_0_enable(struct amdgpu_device *adev, bool enable)
 
 /* This function is for backdoor MES firmware */
 static int mes_v11_0_load_microcode(struct amdgpu_device *adev,
-				    enum admgpu_mes_pipe pipe)
+				    enum admgpu_mes_pipe pipe, bool prime_icache)
 {
 	int r;
 	uint32_t data;
@@ -593,16 +593,18 @@ static int mes_v11_0_load_microcode(struct amdgpu_device *adev,
 	/* Set 0x3FFFF (256K-1) to CP_MES_MDBOUND_LO */
 	WREG32_SOC15(GC, 0, regCP_MES_MDBOUND_LO, 0x3FFFF);
 
-	/* invalidate ICACHE */
-	data = RREG32_SOC15(GC, 0, regCP_MES_IC_OP_CNTL);
-	data = REG_SET_FIELD(data, CP_MES_IC_OP_CNTL, PRIME_ICACHE, 0);
-	data = REG_SET_FIELD(data, CP_MES_IC_OP_CNTL, INVALIDATE_CACHE, 1);
-	WREG32_SOC15(GC, 0, regCP_MES_IC_OP_CNTL, data);
-
-	/* prime the ICACHE. */
-	data = RREG32_SOC15(GC, 0, regCP_MES_IC_OP_CNTL);
-	data = REG_SET_FIELD(data, CP_MES_IC_OP_CNTL, PRIME_ICACHE, 1);
-	WREG32_SOC15(GC, 0, regCP_MES_IC_OP_CNTL, data);
+	if (prime_icache) {
+		/* invalidate ICACHE */
+		data = RREG32_SOC15(GC, 0, regCP_MES_IC_OP_CNTL);
+		data = REG_SET_FIELD(data, CP_MES_IC_OP_CNTL, PRIME_ICACHE, 0);
+		data = REG_SET_FIELD(data, CP_MES_IC_OP_CNTL, INVALIDATE_CACHE, 1);
+		WREG32_SOC15(GC, 0, regCP_MES_IC_OP_CNTL, data);
+
+		/* prime the ICACHE. */
+		data = RREG32_SOC15(GC, 0, regCP_MES_IC_OP_CNTL);
+		data = REG_SET_FIELD(data, CP_MES_IC_OP_CNTL, PRIME_ICACHE, 1);
+		WREG32_SOC15(GC, 0, regCP_MES_IC_OP_CNTL, data);
+	}
 
 	soc21_grbm_select(adev, 0, 0, 0, 0);
 	mutex_unlock(&adev->srbm_mutex);
@@ -1044,17 +1046,19 @@ static int mes_v11_0_kiq_hw_init(struct amdgpu_device *adev)
 	int r = 0;
 
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
-		r = mes_v11_0_load_microcode(adev, AMDGPU_MES_KIQ_PIPE);
+
+		r = mes_v11_0_load_microcode(adev, AMDGPU_MES_SCHED_PIPE, false);
 		if (r) {
-			DRM_ERROR("failed to load MES kiq fw, r=%d\n", r);
+			DRM_ERROR("failed to load MES fw, r=%d\n", r);
 			return r;
 		}
 
-		r = mes_v11_0_load_microcode(adev, AMDGPU_MES_SCHED_PIPE);
+		r = mes_v11_0_load_microcode(adev, AMDGPU_MES_KIQ_PIPE, true);
 		if (r) {
-			DRM_ERROR("failed to load MES fw, r=%d\n", r);
+			DRM_ERROR("failed to load MES kiq fw, r=%d\n", r);
 			return r;
 		}
+
 	}
 
 	mes_v11_0_enable(adev, true);
@@ -1086,7 +1090,7 @@ static int mes_v11_0_hw_init(void *handle)
 	if (!adev->enable_mes_kiq) {
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
 			r = mes_v11_0_load_microcode(adev,
-					     AMDGPU_MES_SCHED_PIPE);
+					     AMDGPU_MES_SCHED_PIPE, true);
 			if (r) {
 				DRM_ERROR("failed to MES fw, r=%d\n", r);
 				return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index d016e3c3e221..b3fba8dea63c 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -170,6 +170,7 @@ static const struct amdgpu_video_codec_info yc_video_codecs_decode_array[] = {
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codecs yc_video_codecs_decode = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index 06b2635b142a..83c6ccaaa9e4 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -469,6 +469,7 @@ static void sdma_v5_2_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se
 	}
 }
 
+
 /**
  * sdma_v5_2_gfx_stop - stop the gfx async dma engines
  *
@@ -514,21 +515,17 @@ static void sdma_v5_2_rlc_stop(struct amdgpu_device *adev)
 }
 
 /**
- * sdma_v5_2_ctx_switch_enable_for_instance - start the async dma engines
- * context switch for an instance
+ * sdma_v5_2_ctx_switch_enable - stop the async dma engines context switch
  *
  * @adev: amdgpu_device pointer
- * @instance_idx: the index of the SDMA instance
+ * @enable: enable/disable the DMA MEs context switch.
  *
- * Unhalt the async dma engines context switch.
+ * Halt or unhalt the async dma engines context switch.
  */
-static void sdma_v5_2_ctx_switch_enable_for_instance(struct amdgpu_device *adev, int instance_idx)
+static void sdma_v5_2_ctx_switch_enable(struct amdgpu_device *adev, bool enable)
 {
 	u32 f32_cntl, phase_quantum = 0;
-
-	if (WARN_ON(instance_idx >= adev->sdma.num_instances)) {
-		return;
-	}
+	int i;
 
 	if (amdgpu_sdma_phase_quantum) {
 		unsigned value = amdgpu_sdma_phase_quantum;
@@ -552,68 +549,50 @@ static void sdma_v5_2_ctx_switch_enable_for_instance(struct amdgpu_device *adev,
 		phase_quantum =
 			value << SDMA0_PHASE0_QUANTUM__VALUE__SHIFT |
 			unit  << SDMA0_PHASE0_QUANTUM__UNIT__SHIFT;
-
-		WREG32_SOC15_IP(GC,
-			sdma_v5_2_get_reg_offset(adev, instance_idx, mmSDMA0_PHASE0_QUANTUM),
-			phase_quantum);
-		WREG32_SOC15_IP(GC,
-			sdma_v5_2_get_reg_offset(adev, instance_idx, mmSDMA0_PHASE1_QUANTUM),
-		    phase_quantum);
-		WREG32_SOC15_IP(GC,
-			sdma_v5_2_get_reg_offset(adev, instance_idx, mmSDMA0_PHASE2_QUANTUM),
-		    phase_quantum);
 	}
 
-	if (!amdgpu_sriov_vf(adev)) {
-		f32_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, instance_idx, mmSDMA0_CNTL));
-		f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
-				AUTO_CTXSW_ENABLE, 1);
-		WREG32(sdma_v5_2_get_reg_offset(adev, instance_idx, mmSDMA0_CNTL), f32_cntl);
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		if (enable && amdgpu_sdma_phase_quantum) {
+			WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_PHASE0_QUANTUM),
+			       phase_quantum);
+			WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_PHASE1_QUANTUM),
+			       phase_quantum);
+			WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_PHASE2_QUANTUM),
+			       phase_quantum);
+		}
+
+		if (!amdgpu_sriov_vf(adev)) {
+			f32_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL));
+			f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
+					AUTO_CTXSW_ENABLE, enable ? 1 : 0);
+			WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL), f32_cntl);
+		}
 	}
+
 }
 
 /**
- * sdma_v5_2_ctx_switch_disable_all - stop the async dma engines context switch
+ * sdma_v5_2_enable - stop the async dma engines
  *
  * @adev: amdgpu_device pointer
+ * @enable: enable/disable the DMA MEs.
  *
- * Halt the async dma engines context switch.
+ * Halt or unhalt the async dma engines.
  */
-static void sdma_v5_2_ctx_switch_disable_all(struct amdgpu_device *adev)
+static void sdma_v5_2_enable(struct amdgpu_device *adev, bool enable)
 {
 	u32 f32_cntl;
 	int i;
 
-	if (amdgpu_sriov_vf(adev))
-		return;
-
-	for (i = 0; i < adev->sdma.num_instances; i++) {
-		f32_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL));
-		f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
-				AUTO_CTXSW_ENABLE, 0);
-		WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL), f32_cntl);
+	if (!enable) {
+		sdma_v5_2_gfx_stop(adev);
+		sdma_v5_2_rlc_stop(adev);
 	}
-}
-
-/**
- * sdma_v5_2_halt - stop the async dma engines
- *
- * @adev: amdgpu_device pointer
- *
- * Halt the async dma engines.
- */
-static void sdma_v5_2_halt(struct amdgpu_device *adev)
-{
-	int i;
-	u32 f32_cntl;
-
-	sdma_v5_2_gfx_stop(adev);
-	sdma_v5_2_rlc_stop(adev);
 
 	if (!amdgpu_sriov_vf(adev)) {
 		for (i = 0; i < adev->sdma.num_instances; i++) {
 			f32_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_F32_CNTL));
-			f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_F32_CNTL, HALT, 1);
+			f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_F32_CNTL, HALT, enable ? 0 : 1);
 			WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_F32_CNTL), f32_cntl);
 		}
 	}
@@ -625,9 +604,6 @@ static void sdma_v5_2_halt(struct amdgpu_device *adev)
  * @adev: amdgpu_device pointer
  *
  * Set up the gfx DMA ring buffers and enable them.
- * It assumes that the dma engine is stopped for each instance.
- * The function enables the engine and preemptions sequentially for each instance.
- *
  * Returns 0 for success, error for failure.
  */
 static int sdma_v5_2_gfx_resume(struct amdgpu_device *adev)
@@ -769,7 +745,10 @@ static int sdma_v5_2_gfx_resume(struct amdgpu_device *adev)
 
 		ring->sched.ready = true;
 
-		sdma_v5_2_ctx_switch_enable_for_instance(adev, i);
+		if (amdgpu_sriov_vf(adev)) { /* bare-metal sequence doesn't need below to lines */
+			sdma_v5_2_ctx_switch_enable(adev, true);
+			sdma_v5_2_enable(adev, true);
+		}
 
 		r = amdgpu_ring_test_ring(ring);
 		if (r) {
@@ -813,7 +792,7 @@ static int sdma_v5_2_load_microcode(struct amdgpu_device *adev)
 	int i, j;
 
 	/* halt the MEs */
-	sdma_v5_2_halt(adev);
+	sdma_v5_2_enable(adev, false);
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		if (!adev->sdma.instance[i].fw)
@@ -885,8 +864,8 @@ static int sdma_v5_2_start(struct amdgpu_device *adev)
 	int r = 0;
 
 	if (amdgpu_sriov_vf(adev)) {
-		sdma_v5_2_ctx_switch_disable_all(adev);
-		sdma_v5_2_halt(adev);
+		sdma_v5_2_ctx_switch_enable(adev, false);
+		sdma_v5_2_enable(adev, false);
 
 		/* set RB registers */
 		r = sdma_v5_2_gfx_resume(adev);
@@ -910,10 +889,12 @@ static int sdma_v5_2_start(struct amdgpu_device *adev)
 		amdgpu_gfx_off_ctrl(adev, false);
 
 	sdma_v5_2_soft_reset(adev);
+	/* unhalt the MEs */
+	sdma_v5_2_enable(adev, true);
+	/* enable sdma ring preemption */
+	sdma_v5_2_ctx_switch_enable(adev, true);
 
-	/* Soft reset supposes to disable the dma engine and preemption.
-	 * Now start the gfx rings and rlc compute queues.
-	 */
+	/* 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);
@@ -1447,8 +1428,8 @@ static int sdma_v5_2_hw_fini(void *handle)
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
-	sdma_v5_2_ctx_switch_disable_all(adev);
-	sdma_v5_2_halt(adev);
+	sdma_v5_2_ctx_switch_enable(adev, false);
+	sdma_v5_2_enable(adev, false);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 3cabceee5f57..39405f0db824 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -1761,23 +1761,21 @@ static const struct amdgpu_ring_funcs vcn_v3_0_dec_sw_ring_vm_funcs = {
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
-static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p,
-				struct amdgpu_job *job)
+static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p)
 {
 	struct drm_gpu_scheduler **scheds;
 
 	/* The create msg must be in the first IB submitted */
-	if (atomic_read(&job->base.entity->fence_seq))
+	if (atomic_read(&p->entity->fence_seq))
 		return -EINVAL;
 
 	scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_DEC]
 		[AMDGPU_RING_PRIO_DEFAULT].sched;
-	drm_sched_entity_modify_sched(job->base.entity, scheds, 1);
+	drm_sched_entity_modify_sched(p->entity, scheds, 1);
 	return 0;
 }
 
-static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job,
-			    uint64_t addr)
+static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, uint64_t addr)
 {
 	struct ttm_operation_ctx ctx = { false, false };
 	struct amdgpu_bo_va_mapping *map;
@@ -1848,7 +1846,7 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job,
 		if (create[0] == 0x7 || create[0] == 0x10 || create[0] == 0x11)
 			continue;
 
-		r = vcn_v3_0_limit_sched(p, job);
+		r = vcn_v3_0_limit_sched(p);
 		if (r)
 			goto out;
 	}
@@ -1862,7 +1860,7 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
 					   struct amdgpu_job *job,
 					   struct amdgpu_ib *ib)
 {
-	struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched);
+	struct amdgpu_ring *ring = to_amdgpu_ring(p->entity->rq->sched);
 	uint32_t msg_lo = 0, msg_hi = 0;
 	unsigned i;
 	int r;
@@ -1881,8 +1879,7 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
 			msg_hi = val;
 		} else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0) &&
 			   val == 0) {
-			r = vcn_v3_0_dec_msg(p, job,
-					     ((u64)msg_hi) << 32 | msg_lo);
+			r = vcn_v3_0_dec_msg(p, ((u64)msg_hi) << 32 | msg_lo);
 			if (r)
 				return r;
 		}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 5e9adbc71bbd..cbfb32b3d235 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -1516,6 +1516,8 @@ static int kfd_fill_gpu_cache_info(struct kfd_dev *kdev,
 			num_of_cache_types = ARRAY_SIZE(beige_goby_cache_info);
 			break;
 		case IP_VERSION(10, 3, 3):
+		case IP_VERSION(10, 3, 6): /* TODO: Double check these on production silicon */
+		case IP_VERSION(10, 3, 7): /* TODO: Double check these on production silicon */
 			pcache_info = yellow_carp_cache_info;
 			num_of_cache_types = ARRAY_SIZE(yellow_carp_cache_info);
 			break;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 8667e3df2d0b..bf4200457772 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -73,6 +73,8 @@ static void kfd_device_info_set_sdma_info(struct kfd_dev *kfd)
 	case IP_VERSION(4, 1, 2):/* RENOIR */
 	case IP_VERSION(5, 2, 1):/* VANGOGH */
 	case IP_VERSION(5, 2, 3):/* YELLOW_CARP */
+	case IP_VERSION(5, 2, 6):/* GC 10.3.6 */
+	case IP_VERSION(5, 2, 7):/* GC 10.3.7 */
 	case IP_VERSION(6, 0, 1):
 		kfd->device_info.num_sdma_queues_per_engine = 2;
 		break;
@@ -127,6 +129,8 @@ static void kfd_device_info_set_event_interrupt_class(struct kfd_dev *kfd)
 	case IP_VERSION(9, 4, 2): /* ALDEBARAN */
 	case IP_VERSION(10, 3, 1): /* VANGOGH */
 	case IP_VERSION(10, 3, 3): /* YELLOW_CARP */
+	case IP_VERSION(10, 3, 6): /* GC 10.3.6 */
+	case IP_VERSION(10, 3, 7): /* GC 10.3.7 */
 	case IP_VERSION(10, 1, 3): /* CYAN_SKILLFISH */
 	case IP_VERSION(10, 1, 4):
 	case IP_VERSION(10, 1, 10): /* NAVI10 */
@@ -178,7 +182,9 @@ static void kfd_device_info_init(struct kfd_dev *kfd,
 
 		if (gc_version < IP_VERSION(11, 0, 0)) {
 			/* Navi2x+, Navi1x+ */
-			if (gc_version >= IP_VERSION(10, 3, 0))
+			if (gc_version == IP_VERSION(10, 3, 6))
+				kfd->device_info.no_atomic_fw_version = 14;
+			else if (gc_version >= IP_VERSION(10, 3, 0))
 				kfd->device_info.no_atomic_fw_version = 92;
 			else if (gc_version >= IP_VERSION(10, 1, 1))
 				kfd->device_info.no_atomic_fw_version = 145;
@@ -368,6 +374,16 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf)
 			if (!vf)
 				f2g = &gfx_v10_3_kfd2kgd;
 			break;
+		case IP_VERSION(10, 3, 6):
+			gfx_target_version = 100306;
+			if (!vf)
+				f2g = &gfx_v10_3_kfd2kgd;
+			break;
+		case IP_VERSION(10, 3, 7):
+			gfx_target_version = 100307;
+			if (!vf)
+				f2g = &gfx_v10_3_kfd2kgd;
+			break;
 		case IP_VERSION(11, 0, 0):
 			gfx_target_version = 110000;
 			f2g = &gfx_v11_kfd2kgd;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 997650d597ec..e44376c2ecdc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -296,7 +296,7 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 			 struct migrate_vma *migrate, struct dma_fence **mfence,
 			 dma_addr_t *scratch)
 {
-	uint64_t npages = migrate->cpages;
+	uint64_t npages = migrate->npages;
 	struct device *dev = adev->dev;
 	struct amdgpu_res_cursor cursor;
 	dma_addr_t *src;
@@ -344,7 +344,7 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 						mfence);
 				if (r)
 					goto out_free_vram_pages;
-				amdgpu_res_next(&cursor, j << PAGE_SHIFT);
+				amdgpu_res_next(&cursor, (j + 1) << PAGE_SHIFT);
 				j = 0;
 			} else {
 				amdgpu_res_next(&cursor, PAGE_SIZE);
@@ -590,7 +590,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 			continue;
 		}
 		src[i] = svm_migrate_addr(adev, spage);
-		if (i > 0 && src[i] != src[i - 1] + PAGE_SIZE) {
+		if (j > 0 && src[i] != src[i - 1] + PAGE_SIZE) {
 			r = svm_migrate_copy_memory_gart(adev, dst + i - j,
 							 src + i - j, j,
 							 FROM_VRAM_TO_RAM,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 2ebf0132c25b..7b332246eda3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1295,7 +1295,7 @@ svm_range_map_to_gpu(struct kfd_process_device *pdd, struct svm_range *prange,
 		r = amdgpu_vm_update_range(adev, vm, false, false, flush_tlb, NULL,
 					   last_start, prange->start + i,
 					   pte_flags,
-					   last_start - prange->start,
+					   (last_start - prange->start) << PAGE_SHIFT,
 					   bo_adev ? bo_adev->vm_manager.vram_base_offset : 0,
 					   NULL, dma_addr, &vm->last_update);
 
@@ -2307,6 +2307,8 @@ svm_range_cpu_invalidate_pagetables(struct mmu_interval_notifier *mni,
 
 	if (range->event == MMU_NOTIFY_RELEASE)
 		return true;
+	if (!mmget_not_zero(mni->mm))
+		return true;
 
 	start = mni->interval_tree.start;
 	last = mni->interval_tree.last;
@@ -2333,6 +2335,7 @@ svm_range_cpu_invalidate_pagetables(struct mmu_interval_notifier *mni,
 	}
 
 	svm_range_unlock(prange);
+	mmput(mni->mm);
 
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
index ceb34376decb..bca5f01da763 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
@@ -287,8 +287,11 @@ static void dcn31_enable_pme_wa(struct clk_mgr *clk_mgr_base)
 
 void dcn31_init_clocks(struct clk_mgr *clk_mgr)
 {
+	uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz;
+
 	memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks));
 	// Assumption is that boot state always supports pstate
+	clk_mgr->clks.ref_dtbclk_khz = ref_dtbclk;	// restore ref_dtbclk
 	clk_mgr->clks.p_state_change_support = true;
 	clk_mgr->clks.prev_p_state_change_support = true;
 	clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN;
@@ -638,8 +641,14 @@ static void dcn31_set_low_power_state(struct clk_mgr *clk_mgr_base)
 	}
 }
 
+int dcn31_get_dtb_ref_freq_khz(struct clk_mgr *clk_mgr_base)
+{
+	return clk_mgr_base->clks.ref_dtbclk_khz;
+}
+
 static struct clk_mgr_funcs dcn31_funcs = {
 	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
+	.get_dtb_ref_clk_frequency = dcn31_get_dtb_ref_freq_khz,
 	.update_clocks = dcn31_update_clocks,
 	.init_clocks = dcn31_init_clocks,
 	.enable_pme_wa = dcn31_enable_pme_wa,
@@ -719,7 +728,7 @@ void dcn31_clk_mgr_construct(
 	}
 
 	clk_mgr->base.base.dprefclk_khz = 600000;
-	clk_mgr->base.dccg->ref_dtbclk_khz = 600000;
+	clk_mgr->base.base.clks.ref_dtbclk_khz = 600000;
 	dce_clock_read_ss_info(&clk_mgr->base);
 	/*if bios enabled SS, driver needs to adjust dtb clock, only enable with correct bios*/
 	//clk_mgr->base.dccg->ref_dtbclk_khz = dce_adjust_dp_ref_freq_for_ss(clk_mgr_internal, clk_mgr->base.base.dprefclk_khz);
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h
index 961b10a49486..be06fdbd0c22 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h
@@ -51,6 +51,8 @@ void dcn31_clk_mgr_construct(struct dc_context *ctx,
 		struct pp_smu_funcs *pp_smu,
 		struct dccg *dccg);
 
+int dcn31_get_dtb_ref_freq_khz(struct clk_mgr *clk_mgr_base);
+
 void dcn31_clk_mgr_destroy(struct clk_mgr_internal *clk_mgr_int);
 
 #endif //__DCN31_CLK_MGR_H__
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
index a2ade6e93f5e..fb4ae800e919 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
@@ -41,9 +41,7 @@
 
 #include "dc_dmub_srv.h"
 
-#if defined (CONFIG_DRM_AMD_DC_DP2_0)
 #include "dc_link_dp.h"
-#endif
 
 #define TO_CLK_MGR_DCN315(clk_mgr)\
 	container_of(clk_mgr, struct clk_mgr_dcn315, base)
@@ -580,6 +578,7 @@ static void dcn315_enable_pme_wa(struct clk_mgr *clk_mgr_base)
 
 static struct clk_mgr_funcs dcn315_funcs = {
 	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
+	.get_dtb_ref_clk_frequency = dcn31_get_dtb_ref_freq_khz,
 	.update_clocks = dcn315_update_clocks,
 	.init_clocks = dcn31_init_clocks,
 	.enable_pme_wa = dcn315_enable_pme_wa,
@@ -656,9 +655,9 @@ void dcn315_clk_mgr_construct(
 
 	clk_mgr->base.base.dprefclk_khz = 600000;
 	clk_mgr->base.base.dprefclk_khz = dcn315_smu_get_dpref_clk(&clk_mgr->base);
-	clk_mgr->base.dccg->ref_dtbclk_khz = clk_mgr->base.base.dprefclk_khz;
+	clk_mgr->base.base.clks.ref_dtbclk_khz = clk_mgr->base.base.dprefclk_khz;
 	dce_clock_read_ss_info(&clk_mgr->base);
-	clk_mgr->base.dccg->ref_dtbclk_khz = dce_adjust_dp_ref_freq_for_ss(&clk_mgr->base, clk_mgr->base.base.dprefclk_khz);
+	clk_mgr->base.base.clks.ref_dtbclk_khz = dce_adjust_dp_ref_freq_for_ss(&clk_mgr->base, clk_mgr->base.base.dprefclk_khz);
 
 	clk_mgr->base.base.bw_params = &dcn315_bw_params;
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c
index fc3af81ed6c6..e4bb9c6193b5 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c
@@ -571,6 +571,7 @@ static void dcn316_clk_mgr_helper_populate_bw_params(
 static struct clk_mgr_funcs dcn316_funcs = {
 	.enable_pme_wa = dcn316_enable_pme_wa,
 	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
+	.get_dtb_ref_clk_frequency = dcn31_get_dtb_ref_freq_khz,
 	.update_clocks = dcn316_update_clocks,
 	.init_clocks = dcn31_init_clocks,
 	.are_clock_states_equal = dcn31_are_clock_states_equal,
@@ -685,7 +686,7 @@ void dcn316_clk_mgr_construct(
 
 	clk_mgr->base.base.dprefclk_khz = 600000;
 	clk_mgr->base.base.dprefclk_khz = dcn316_smu_get_dpref_clk(&clk_mgr->base);
- 	clk_mgr->base.dccg->ref_dtbclk_khz = clk_mgr->base.base.dprefclk_khz;
+	clk_mgr->base.base.clks.ref_dtbclk_khz = clk_mgr->base.base.dprefclk_khz;
 	dce_clock_read_ss_info(&clk_mgr->base);
 	/*clk_mgr->base.dccg->ref_dtbclk_khz =
 	dce_adjust_dp_ref_freq_for_ss(&clk_mgr->base, clk_mgr->base.base.dprefclk_khz);*/
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 dc30ac366a50..cbc47aecd00f 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
@@ -114,8 +114,8 @@ static const struct dc_link_settings fail_safe_link_settings = {
 
 static bool decide_fallback_link_setting(
 		struct dc_link *link,
-		struct dc_link_settings initial_link_settings,
-		struct dc_link_settings *current_link_setting,
+		struct dc_link_settings *max,
+		struct dc_link_settings *cur,
 		enum link_training_result training_result);
 static void maximize_lane_settings(const struct link_training_settings *lt_settings,
 		struct dc_lane_settings lane_settings[LANE_COUNT_DP_MAX]);
@@ -2784,6 +2784,7 @@ bool perform_link_training_with_retries(
 	enum dp_panel_mode panel_mode = dp_get_panel_mode(link);
 	enum link_training_result status = LINK_TRAINING_CR_FAIL_LANE0;
 	struct dc_link_settings cur_link_settings = *link_setting;
+	struct dc_link_settings max_link_settings = *link_setting;
 	const struct link_hwss *link_hwss = get_link_hwss(link, &pipe_ctx->link_res);
 	int fail_count = 0;
 	bool is_link_bw_low = false; /* link bandwidth < stream bandwidth */
@@ -2793,7 +2794,6 @@ bool perform_link_training_with_retries(
 
 	dp_trace_commit_lt_init(link);
 
-
 	if (dp_get_link_encoding_format(&cur_link_settings) == DP_8b_10b_ENCODING)
 		/* We need to do this before the link training to ensure the idle
 		 * pattern in SST mode will be sent right after the link training
@@ -2909,19 +2909,15 @@ bool perform_link_training_with_retries(
 			uint32_t req_bw;
 			uint32_t link_bw;
 
-			decide_fallback_link_setting(link, *link_setting, &cur_link_settings, status);
-			/* Flag if reduced link bandwidth no longer meets stream requirements or fallen back to
-			 * minimum link bandwidth.
+			decide_fallback_link_setting(link, &max_link_settings,
+					&cur_link_settings, status);
+			/* Fail link training if reduced link bandwidth no longer meets
+			 * stream requirements.
 			 */
 			req_bw = dc_bandwidth_in_kbps_from_timing(&stream->timing);
 			link_bw = dc_link_bandwidth_kbps(link, &cur_link_settings);
-			is_link_bw_low = (req_bw > link_bw);
-			is_link_bw_min = ((cur_link_settings.link_rate <= LINK_RATE_LOW) &&
-				(cur_link_settings.lane_count <= LANE_COUNT_ONE));
-
-			if (is_link_bw_low)
-				DC_LOG_WARNING("%s: Link bandwidth too low after fallback req_bw(%d) > link_bw(%d)\n",
-					__func__, req_bw, link_bw);
+			if (req_bw > link_bw)
+				break;
 		}
 
 		msleep(delay_between_attempts);
@@ -3309,7 +3305,7 @@ static bool dp_verify_link_cap(
 	int *fail_count)
 {
 	struct dc_link_settings cur_link_settings = {0};
-	struct dc_link_settings initial_link_settings = *known_limit_link_setting;
+	struct dc_link_settings max_link_settings = *known_limit_link_setting;
 	bool success = false;
 	bool skip_video_pattern;
 	enum clock_source_id dp_cs_id = get_clock_source_id(link);
@@ -3318,7 +3314,7 @@ static bool dp_verify_link_cap(
 	struct link_resource link_res;
 
 	memset(&irq_data, 0, sizeof(irq_data));
-	cur_link_settings = initial_link_settings;
+	cur_link_settings = max_link_settings;
 
 	/* Grant extended timeout request */
 	if ((link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) && (link->dpcd_caps.lttpr_caps.max_ext_timeout > 0)) {
@@ -3361,7 +3357,7 @@ static bool dp_verify_link_cap(
 		dp_trace_lt_result_update(link, status, true);
 		dp_disable_link_phy(link, &link_res, link->connector_signal);
 	} while (!success && decide_fallback_link_setting(link,
-			initial_link_settings, &cur_link_settings, status));
+			&max_link_settings, &cur_link_settings, status));
 
 	link->verified_link_cap = success ?
 			cur_link_settings : fail_safe_link_settings;
@@ -3596,16 +3592,19 @@ static bool decide_fallback_link_setting_max_bw_policy(
  */
 static bool decide_fallback_link_setting(
 		struct dc_link *link,
-		struct dc_link_settings initial_link_settings,
-		struct dc_link_settings *current_link_setting,
+		struct dc_link_settings *max,
+		struct dc_link_settings *cur,
 		enum link_training_result training_result)
 {
-	if (!current_link_setting)
+	if (!cur)
 		return false;
-	if (dp_get_link_encoding_format(&initial_link_settings) == DP_128b_132b_ENCODING ||
+	if (!max)
+		return false;
+
+	if (dp_get_link_encoding_format(max) == DP_128b_132b_ENCODING ||
 			link->dc->debug.force_dp2_lt_fallback_method)
-		return decide_fallback_link_setting_max_bw_policy(link, &initial_link_settings,
-				current_link_setting, training_result);
+		return decide_fallback_link_setting_max_bw_policy(link, max, cur,
+				training_result);
 
 	switch (training_result) {
 	case LINK_TRAINING_CR_FAIL_LANE0:
@@ -3613,28 +3612,18 @@ static bool decide_fallback_link_setting(
 	case LINK_TRAINING_CR_FAIL_LANE23:
 	case LINK_TRAINING_LQA_FAIL:
 	{
-		if (!reached_minimum_link_rate
-				(current_link_setting->link_rate)) {
-			current_link_setting->link_rate =
-				reduce_link_rate(
-					current_link_setting->link_rate);
-		} else if (!reached_minimum_lane_count
-				(current_link_setting->lane_count)) {
-			current_link_setting->link_rate =
-				initial_link_settings.link_rate;
+		if (!reached_minimum_link_rate(cur->link_rate)) {
+			cur->link_rate = reduce_link_rate(cur->link_rate);
+		} else if (!reached_minimum_lane_count(cur->lane_count)) {
+			cur->link_rate = max->link_rate;
 			if (training_result == LINK_TRAINING_CR_FAIL_LANE0)
 				return false;
 			else if (training_result == LINK_TRAINING_CR_FAIL_LANE1)
-				current_link_setting->lane_count =
-						LANE_COUNT_ONE;
-			else if (training_result ==
-					LINK_TRAINING_CR_FAIL_LANE23)
-				current_link_setting->lane_count =
-						LANE_COUNT_TWO;
+				cur->lane_count = LANE_COUNT_ONE;
+			else if (training_result == LINK_TRAINING_CR_FAIL_LANE23)
+				cur->lane_count = LANE_COUNT_TWO;
 			else
-				current_link_setting->lane_count =
-					reduce_lane_count(
-					current_link_setting->lane_count);
+				cur->lane_count = reduce_lane_count(cur->lane_count);
 		} else {
 			return false;
 		}
@@ -3642,17 +3631,17 @@ static bool decide_fallback_link_setting(
 	}
 	case LINK_TRAINING_EQ_FAIL_EQ:
 	{
-		if (!reached_minimum_lane_count
-				(current_link_setting->lane_count)) {
-			current_link_setting->lane_count =
-				reduce_lane_count(
-					current_link_setting->lane_count);
-		} else if (!reached_minimum_link_rate
-				(current_link_setting->link_rate)) {
-			current_link_setting->link_rate =
-				reduce_link_rate(
-					current_link_setting->link_rate);
-			current_link_setting->lane_count = initial_link_settings.lane_count;
+		if (!reached_minimum_lane_count(cur->lane_count)) {
+			cur->lane_count = reduce_lane_count(cur->lane_count);
+		} else if (!reached_minimum_link_rate(cur->link_rate)) {
+			cur->link_rate = reduce_link_rate(cur->link_rate);
+			/* Reduce max link rate to avoid potential infinite loop.
+			 * Needed so that any subsequent CR_FAIL fallback can't
+			 * re-set the link rate higher than the link rate from
+			 * the latest EQ_FAIL fallback.
+			 */
+			max->link_rate = cur->link_rate;
+			cur->lane_count = max->lane_count;
 		} else {
 			return false;
 		}
@@ -3660,12 +3649,15 @@ static bool decide_fallback_link_setting(
 	}
 	case LINK_TRAINING_EQ_FAIL_CR:
 	{
-		if (!reached_minimum_link_rate
-				(current_link_setting->link_rate)) {
-			current_link_setting->link_rate =
-				reduce_link_rate(
-					current_link_setting->link_rate);
-			current_link_setting->lane_count = initial_link_settings.lane_count;
+		if (!reached_minimum_link_rate(cur->link_rate)) {
+			cur->link_rate = reduce_link_rate(cur->link_rate);
+			/* Reduce max link rate to avoid potential infinite loop.
+			 * Needed so that any subsequent CR_FAIL fallback can't
+			 * re-set the link rate higher than the link rate from
+			 * the latest EQ_FAIL fallback.
+			 */
+			max->link_rate = cur->link_rate;
+			cur->lane_count = max->lane_count;
 		} else {
 			return false;
 		}
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 3960c74482be..817028d3c4a0 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -47,7 +47,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.186"
+#define DC_VER "3.2.187"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
@@ -416,6 +416,7 @@ struct dc_clocks {
 	bool p_state_change_support;
 	enum dcn_zstate_support_state zstate_support;
 	bool dtbclk_en;
+	int ref_dtbclk_khz;
 	enum dcn_pwr_state pwr_state;
 	/*
 	 * Elements below are not compared for the purposes of
@@ -719,6 +720,8 @@ struct dc_debug_options {
 	bool apply_vendor_specific_lttpr_wa;
 	bool extended_blank_optimization;
 	union aux_wake_wa_options aux_wake_wa;
+	/* uses value at boot and disables switch */
+	bool disable_dtb_ref_clk_switch;
 	uint8_t psr_power_use_phy_fsm;
 	enum dml_hostvm_override_opts dml_hostvm_override;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c
index 287a1066b547..bbc58d167c63 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c
@@ -513,12 +513,10 @@ void dccg31_set_physymclk(
 /* Controls the generation of pixel valid for OTG in (OTG -> HPO case) */
 static void dccg31_set_dtbclk_dto(
 		struct dccg *dccg,
-		int dtbclk_inst,
-		int req_dtbclk_khz,
-		int num_odm_segments,
-		const struct dc_crtc_timing *timing)
+		struct dtbclk_dto_params *params)
 {
 	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
+	int req_dtbclk_khz = params->pixclk_khz;
 	uint32_t dtbdto_div;
 
 	/* Mode	                DTBDTO Rate       DTBCLK_DTO<x>_DIV Register
@@ -529,57 +527,53 @@ static void dccg31_set_dtbclk_dto(
 	 * DSC native 4:2:2     pixel rate/2      4
 	 * Other modes          pixel rate        8
 	 */
-	if (num_odm_segments == 4) {
+	if (params->num_odm_segments == 4) {
 		dtbdto_div = 2;
-		req_dtbclk_khz = req_dtbclk_khz / 4;
-	} else if ((num_odm_segments == 2) ||
-			(timing->pixel_encoding == PIXEL_ENCODING_YCBCR420) ||
-			(timing->flags.DSC && timing->pixel_encoding == PIXEL_ENCODING_YCBCR422
-					&& !timing->dsc_cfg.ycbcr422_simple)) {
+		req_dtbclk_khz = params->pixclk_khz / 4;
+	} else if ((params->num_odm_segments == 2) ||
+			(params->timing->pixel_encoding == PIXEL_ENCODING_YCBCR420) ||
+			(params->timing->flags.DSC && params->timing->pixel_encoding == PIXEL_ENCODING_YCBCR422
+					&& !params->timing->dsc_cfg.ycbcr422_simple)) {
 		dtbdto_div = 4;
-		req_dtbclk_khz = req_dtbclk_khz / 2;
+		req_dtbclk_khz = params->pixclk_khz / 2;
 	} else
 		dtbdto_div = 8;
 
-	if (dccg->ref_dtbclk_khz && req_dtbclk_khz) {
+	if (params->ref_dtbclk_khz && req_dtbclk_khz) {
 		uint32_t modulo, phase;
 
 		// phase / modulo = dtbclk / dtbclk ref
-		modulo = dccg->ref_dtbclk_khz * 1000;
-		phase = div_u64((((unsigned long long)modulo * req_dtbclk_khz) + dccg->ref_dtbclk_khz - 1),
-			dccg->ref_dtbclk_khz);
+		modulo = params->ref_dtbclk_khz * 1000;
+		phase = div_u64((((unsigned long long)modulo * req_dtbclk_khz) + params->ref_dtbclk_khz - 1),
+				params->ref_dtbclk_khz);
 
-		REG_UPDATE(OTG_PIXEL_RATE_CNTL[dtbclk_inst],
-				DTBCLK_DTO_DIV[dtbclk_inst], dtbdto_div);
+		REG_UPDATE(OTG_PIXEL_RATE_CNTL[params->otg_inst],
+				DTBCLK_DTO_DIV[params->otg_inst], dtbdto_div);
 
-		REG_WRITE(DTBCLK_DTO_MODULO[dtbclk_inst], modulo);
-		REG_WRITE(DTBCLK_DTO_PHASE[dtbclk_inst], phase);
+		REG_WRITE(DTBCLK_DTO_MODULO[params->otg_inst], modulo);
+		REG_WRITE(DTBCLK_DTO_PHASE[params->otg_inst], phase);
 
-		REG_UPDATE(OTG_PIXEL_RATE_CNTL[dtbclk_inst],
-				DTBCLK_DTO_ENABLE[dtbclk_inst], 1);
+		REG_UPDATE(OTG_PIXEL_RATE_CNTL[params->otg_inst],
+				DTBCLK_DTO_ENABLE[params->otg_inst], 1);
 
-		REG_WAIT(OTG_PIXEL_RATE_CNTL[dtbclk_inst],
-				DTBCLKDTO_ENABLE_STATUS[dtbclk_inst], 1,
+		REG_WAIT(OTG_PIXEL_RATE_CNTL[params->otg_inst],
+				DTBCLKDTO_ENABLE_STATUS[params->otg_inst], 1,
 				1, 100);
 
 		/* The recommended programming sequence to enable DTBCLK DTO to generate
 		 * valid pixel HPO DPSTREAM ENCODER, specifies that DTO source select should
 		 * be set only after DTO is enabled
 		 */
-		REG_UPDATE(OTG_PIXEL_RATE_CNTL[dtbclk_inst],
-				PIPE_DTO_SRC_SEL[dtbclk_inst], 1);
-
-		dccg->dtbclk_khz[dtbclk_inst] = req_dtbclk_khz;
+		REG_UPDATE(OTG_PIXEL_RATE_CNTL[params->otg_inst],
+				PIPE_DTO_SRC_SEL[params->otg_inst], 1);
 	} else {
-		REG_UPDATE_3(OTG_PIXEL_RATE_CNTL[dtbclk_inst],
-				DTBCLK_DTO_ENABLE[dtbclk_inst], 0,
-				PIPE_DTO_SRC_SEL[dtbclk_inst], 0,
-				DTBCLK_DTO_DIV[dtbclk_inst], dtbdto_div);
+		REG_UPDATE_3(OTG_PIXEL_RATE_CNTL[params->otg_inst],
+				DTBCLK_DTO_ENABLE[params->otg_inst], 0,
+				PIPE_DTO_SRC_SEL[params->otg_inst], 0,
+				DTBCLK_DTO_DIV[params->otg_inst], dtbdto_div);
 
-		REG_WRITE(DTBCLK_DTO_MODULO[dtbclk_inst], 0);
-		REG_WRITE(DTBCLK_DTO_PHASE[dtbclk_inst], 0);
-
-		dccg->dtbclk_khz[dtbclk_inst] = 0;
+		REG_WRITE(DTBCLK_DTO_MODULO[params->otg_inst], 0);
+		REG_WRITE(DTBCLK_DTO_PHASE[params->otg_inst], 0);
 	}
 }
 
@@ -606,16 +600,12 @@ void dccg31_set_audio_dtbclk_dto(
 
 		REG_UPDATE(DCCG_AUDIO_DTO_SOURCE,
 				DCCG_AUDIO_DTO_SEL, 4);  //  04 - DCCG_AUDIO_DTO_SEL_AUDIO_DTO_DTBCLK
-
-		dccg->audio_dtbclk_khz = req_audio_dtbclk_khz;
 	} else {
 		REG_WRITE(DCCG_AUDIO_DTBCLK_DTO_PHASE, 0);
 		REG_WRITE(DCCG_AUDIO_DTBCLK_DTO_MODULO, 0);
 
 		REG_UPDATE(DCCG_AUDIO_DTO_SOURCE,
 				DCCG_AUDIO_DTO_SEL, 3);  //  03 - DCCG_AUDIO_DTO_SEL_NO_AUDIO_DTO
-
-		dccg->audio_dtbclk_khz = 0;
 	}
 }
 
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 d94fd1010deb..8b12b4111c88 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
@@ -230,9 +230,7 @@ static void enc31_hw_init(struct link_encoder *enc)
 	AUX_RX_PHASE_DETECT_LEN,  [21,20] = 0x3 default is 3
 	AUX_RX_DETECTION_THRESHOLD [30:28] = 1
 */
-	AUX_REG_WRITE(AUX_DPHY_RX_CONTROL0, 0x103d1110);
-
-	AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c7a);
+	// dmub will read AUX_DPHY_RX_CONTROL0/AUX_DPHY_TX_CONTROL from vbios table in dp_aux_init
 
 	//AUX_DPHY_TX_REF_CONTROL'AUX_TX_REF_DIV HW default is 0x32;
 	// Set AUX_TX_REF_DIV Divider to generate 2 MHz reference from refclk
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml/dml_wrapper.c
index 789f7562cdc7..d2273674e872 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml_wrapper.c
@@ -1284,10 +1284,8 @@ static bool is_dtbclk_required(struct dc *dc, struct dc_state *context)
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		if (!context->res_ctx.pipe_ctx[i].stream)
 			continue;
-#if defined (CONFIG_DRM_AMD_DC_DP2_0)
 		if (is_dp_128b_132b_signal(&context->res_ctx.pipe_ctx[i]))
 			return true;
-#endif
 	}
 	return false;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
index 46ce5a0ee4ec..b5570aa8e39d 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
@@ -237,6 +237,7 @@ struct clk_mgr_funcs {
 			bool safe_to_lower);
 
 	int (*get_dp_ref_clk_frequency)(struct clk_mgr *clk_mgr);
+	int (*get_dtb_ref_clk_frequency)(struct clk_mgr *clk_mgr);
 
 	void (*set_low_power_state)(struct clk_mgr *clk_mgr);
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h
index b2fa4de47734..c7021915bac8 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h
@@ -60,8 +60,17 @@ struct dccg {
 	const struct dccg_funcs *funcs;
 	int pipe_dppclk_khz[MAX_PIPES];
 	int ref_dppclk;
-	int dtbclk_khz[MAX_PIPES];
-	int audio_dtbclk_khz;
+	//int dtbclk_khz[MAX_PIPES];/* TODO needs to be removed */
+	//int audio_dtbclk_khz;/* TODO needs to be removed */
+	int ref_dtbclk_khz;/* TODO needs to be removed */
+};
+
+struct dtbclk_dto_params {
+	const struct dc_crtc_timing *timing;
+	int otg_inst;
+	int pixclk_khz;
+	int req_audio_dtbclk_khz;
+	int num_odm_segments;
 	int ref_dtbclk_khz;
 };
 
@@ -111,10 +120,7 @@ struct dccg_funcs {
 
 	void (*set_dtbclk_dto)(
 			struct dccg *dccg,
-			int dtbclk_inst,
-			int req_dtbclk_khz,
-			int num_odm_segments,
-			const struct dc_crtc_timing *timing);
+			struct dtbclk_dto_params *dto_params);
 
 	void (*set_audio_dtbclk_dto)(
 			struct dccg *dccg,
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c b/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c
index 87972dc8443d..ea6cf8bfce30 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c
@@ -27,6 +27,7 @@
 #include "core_types.h"
 #include "dccg.h"
 #include "dc_link_dp.h"
+#include "clk_mgr.h"
 
 static enum phyd32clk_clock_source get_phyd32clk_src(struct dc_link *link)
 {
@@ -106,14 +107,18 @@ static void setup_hpo_dp_stream_encoder(struct pipe_ctx *pipe_ctx)
 	struct hpo_dp_link_encoder *link_enc = pipe_ctx->link_res.hpo_dp_link_enc;
 	struct dccg *dccg = dc->res_pool->dccg;
 	struct timing_generator *tg = pipe_ctx->stream_res.tg;
-	int odm_segment_count = get_odm_segment_count(pipe_ctx);
+	struct dtbclk_dto_params dto_params = {0};
 	enum phyd32clk_clock_source phyd32clk = get_phyd32clk_src(pipe_ctx->stream->link);
 
+	dto_params.otg_inst = tg->inst;
+	dto_params.pixclk_khz = pipe_ctx->stream->phy_pix_clk;
+	dto_params.num_odm_segments = get_odm_segment_count(pipe_ctx);
+	dto_params.timing = &pipe_ctx->stream->timing;
+	dto_params.ref_dtbclk_khz = dc->clk_mgr->funcs->get_dtb_ref_clk_frequency(dc->clk_mgr);
+
 	dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst);
 	dccg->funcs->enable_symclk32_se(dccg, stream_enc->inst, phyd32clk);
-	dccg->funcs->set_dtbclk_dto(dccg, tg->inst, pipe_ctx->stream->phy_pix_clk,
-			odm_segment_count,
-			&pipe_ctx->stream->timing);
+	dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
 	stream_enc->funcs->enable_stream(stream_enc);
 	stream_enc->funcs->map_stream_to_link(stream_enc, stream_enc->inst, link_enc->inst);
 }
@@ -124,9 +129,13 @@ static void reset_hpo_dp_stream_encoder(struct pipe_ctx *pipe_ctx)
 	struct hpo_dp_stream_encoder *stream_enc = pipe_ctx->stream_res.hpo_dp_stream_enc;
 	struct dccg *dccg = dc->res_pool->dccg;
 	struct timing_generator *tg = pipe_ctx->stream_res.tg;
+	struct dtbclk_dto_params dto_params = {0};
+
+	dto_params.otg_inst = tg->inst;
+	dto_params.timing = &pipe_ctx->stream->timing;
 
 	stream_enc->funcs->disable(stream_enc);
-	dccg->funcs->set_dtbclk_dto(dccg, tg->inst, 0, 0, &pipe_ctx->stream->timing);
+	dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
 	dccg->funcs->disable_symclk32_se(dccg, stream_enc->inst);
 	dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst);
 }
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
index 7c9330a61ac1..c7bd7e216710 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
@@ -84,7 +84,7 @@ void dmub_dcn31_reset(struct dmub_srv *dmub)
 {
 	union dmub_gpint_data_register cmd;
 	const uint32_t timeout = 100;
-	uint32_t in_reset, scratch, i;
+	uint32_t in_reset, scratch, i, pwait_mode;
 
 	REG_GET(DMCUB_CNTL2, DMCUB_SOFT_RESET, &in_reset);
 
@@ -115,6 +115,13 @@ void dmub_dcn31_reset(struct dmub_srv *dmub)
 			udelay(1);
 		}
 
+		for (i = 0; i < timeout; ++i) {
+			REG_GET(DMCUB_CNTL, DMCUB_PWAIT_MODE_STATUS, &pwait_mode);
+			if (pwait_mode & (1 << 0))
+				break;
+
+			udelay(1);
+		}
 		/* Force reset in case we timed out, DMCUB is likely hung. */
 	}
 
@@ -125,6 +132,8 @@ void dmub_dcn31_reset(struct dmub_srv *dmub)
 	REG_WRITE(DMCUB_INBOX1_WPTR, 0);
 	REG_WRITE(DMCUB_OUTBOX1_RPTR, 0);
 	REG_WRITE(DMCUB_OUTBOX1_WPTR, 0);
+	REG_WRITE(DMCUB_OUTBOX0_RPTR, 0);
+	REG_WRITE(DMCUB_OUTBOX0_WPTR, 0);
 	REG_WRITE(DMCUB_SCRATCH0, 0);
 
 	/* Clear the GPINT command manually so we don't send anything during boot. */
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h
index 59ddc81b5a0e..f6db6f89d45d 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h
@@ -151,7 +151,8 @@ struct dmub_srv;
 	DMUB_SF(DCN_VM_FB_OFFSET, FB_OFFSET) \
 	DMUB_SF(DMCUB_INBOX0_WPTR, DMCUB_INBOX0_WPTR) \
 	DMUB_SF(DMCUB_INTERRUPT_ENABLE, DMCUB_GPINT_IH_INT_EN) \
-	DMUB_SF(DMCUB_INTERRUPT_ACK, DMCUB_GPINT_IH_INT_ACK)
+	DMUB_SF(DMCUB_INTERRUPT_ACK, DMCUB_GPINT_IH_INT_ACK) \
+	DMUB_SF(DMCUB_CNTL, DMCUB_PWAIT_MODE_STATUS)
 
 struct dmub_srv_dcn31_reg_offset {
 #define DMUB_SR(reg) uint32_t reg;
diff --git a/drivers/gpu/drm/amd/display/include/ddc_service_types.h b/drivers/gpu/drm/amd/display/include/ddc_service_types.h
index 73b9e0a87e54..20a3d4e23f66 100644
--- a/drivers/gpu/drm/amd/display/include/ddc_service_types.h
+++ b/drivers/gpu/drm/amd/display/include/ddc_service_types.h
@@ -127,6 +127,8 @@ struct av_sync_data {
 static const uint8_t DP_SINK_DEVICE_STR_ID_1[] = {7, 1, 8, 7, 3, 0};
 static const uint8_t DP_SINK_DEVICE_STR_ID_2[] = {7, 1, 8, 7, 5, 0};
 
+static const u8 DP_SINK_BRANCH_DEV_NAME_7580[] = "7580\x80u";
+
 /*MST Dock*/
 static const uint8_t SYNAPTICS_DEVICE_ID[] = "SYNA";
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v11_0_7_pptable.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v11_0_7_pptable.h
index 247c6e9632ba..1cb399dbc7cc 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v11_0_7_pptable.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v11_0_7_pptable.h
@@ -22,6 +22,7 @@
 #ifndef SMU_11_0_7_PPTABLE_H
 #define SMU_11_0_7_PPTABLE_H
 
+#pragma pack(push, 1)
 
 #define SMU_11_0_7_TABLE_FORMAT_REVISION                  15
 
@@ -139,7 +140,7 @@ struct smu_11_0_7_overdrive_table
     uint32_t max[SMU_11_0_7_MAX_ODSETTING];                   //default maximum settings
     uint32_t min[SMU_11_0_7_MAX_ODSETTING];                   //default minimum settings
     int16_t  pm_setting[SMU_11_0_7_MAX_PMSETTING];            //Optimized power mode feature settings
-} __attribute__((packed));
+};
 
 enum SMU_11_0_7_PPCLOCK_ID {
     SMU_11_0_7_PPCLOCK_GFXCLK = 0,
@@ -166,7 +167,7 @@ struct smu_11_0_7_power_saving_clock_table
     uint32_t count;                                           //power_saving_clock_count = SMU_11_0_7_PPCLOCK_COUNT
     uint32_t max[SMU_11_0_7_MAX_PPCLOCK];                       //PowerSavingClock Mode Clock Maximum array In MHz
     uint32_t min[SMU_11_0_7_MAX_PPCLOCK];                       //PowerSavingClock Mode Clock Minimum array In MHz
-} __attribute__((packed));
+};
 
 struct smu_11_0_7_powerplay_table
 {
@@ -191,6 +192,8 @@ struct smu_11_0_7_powerplay_table
       struct smu_11_0_7_overdrive_table               overdrive_table;
 
       PPTable_t smc_pptable;                        //PPTable_t in smu11_driver_if.h
-} __attribute__((packed));
+};
+
+#pragma pack(pop)
 
 #endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v11_0_pptable.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v11_0_pptable.h
index 7a63cf8e85ed..0116e3d04fad 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v11_0_pptable.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v11_0_pptable.h
@@ -22,6 +22,7 @@
 #ifndef SMU_11_0_PPTABLE_H
 #define SMU_11_0_PPTABLE_H
 
+#pragma pack(push, 1)
 
 #define SMU_11_0_TABLE_FORMAT_REVISION                  12
 
@@ -109,7 +110,7 @@ struct smu_11_0_overdrive_table
     uint8_t  cap[SMU_11_0_MAX_ODFEATURE];                     //OD feature support flags
     uint32_t max[SMU_11_0_MAX_ODSETTING];                     //default maximum settings
     uint32_t min[SMU_11_0_MAX_ODSETTING];                     //default minimum settings
-} __attribute__((packed));
+};
 
 enum SMU_11_0_PPCLOCK_ID {
     SMU_11_0_PPCLOCK_GFXCLK = 0,
@@ -133,7 +134,7 @@ struct smu_11_0_power_saving_clock_table
     uint32_t count;                                           //power_saving_clock_count = SMU_11_0_PPCLOCK_COUNT
     uint32_t max[SMU_11_0_MAX_PPCLOCK];                       //PowerSavingClock Mode Clock Maximum array In MHz
     uint32_t min[SMU_11_0_MAX_PPCLOCK];                       //PowerSavingClock Mode Clock Minimum array In MHz
-} __attribute__((packed));
+};
 
 struct smu_11_0_powerplay_table
 {
@@ -162,6 +163,8 @@ struct smu_11_0_powerplay_table
 #ifndef SMU_11_0_PARTIAL_PPTABLE
       PPTable_t smc_pptable;                        //PPTable_t in smu11_driver_if.h
 #endif
-} __attribute__((packed));
+};
+
+#pragma pack(pop)
 
 #endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0_7_pptable.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0_7_pptable.h
index 3f29f4327378..478862ded0bd 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0_7_pptable.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0_7_pptable.h
@@ -22,6 +22,8 @@
 #ifndef SMU_13_0_7_PPTABLE_H
 #define SMU_13_0_7_PPTABLE_H
 
+#pragma pack(push, 1)
+
 #define SMU_13_0_7_TABLE_FORMAT_REVISION 15
 
 //// POWERPLAYTABLE::ulPlatformCaps
@@ -194,7 +196,8 @@ struct smu_13_0_7_powerplay_table
     struct smu_13_0_7_overdrive_table overdrive_table;
     uint8_t padding1;
     PPTable_t smc_pptable; //PPTable_t in driver_if.h
-} __attribute__((packed));
+};
 
+#pragma pack(pop)
 
 #endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0_pptable.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0_pptable.h
index 1f311396b706..043307485528 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0_pptable.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0_pptable.h
@@ -22,6 +22,8 @@
 #ifndef SMU_13_0_PPTABLE_H
 #define SMU_13_0_PPTABLE_H
 
+#pragma pack(push, 1)
+
 #define SMU_13_0_TABLE_FORMAT_REVISION                  1
 
 //// POWERPLAYTABLE::ulPlatformCaps
@@ -109,7 +111,7 @@ struct smu_13_0_overdrive_table {
 	uint8_t  cap[SMU_13_0_MAX_ODFEATURE];                     //OD feature support flags
 	uint32_t max[SMU_13_0_MAX_ODSETTING];                     //default maximum settings
 	uint32_t min[SMU_13_0_MAX_ODSETTING];                     //default minimum settings
-} __attribute__((packed));
+};
 
 enum SMU_13_0_PPCLOCK_ID {
 	SMU_13_0_PPCLOCK_GFXCLK = 0,
@@ -132,7 +134,7 @@ struct smu_13_0_power_saving_clock_table {
 	uint32_t count;                                           //power_saving_clock_count = SMU_11_0_PPCLOCK_COUNT
 	uint32_t max[SMU_13_0_MAX_PPCLOCK];                       //PowerSavingClock Mode Clock Maximum array In MHz
 	uint32_t min[SMU_13_0_MAX_PPCLOCK];                       //PowerSavingClock Mode Clock Minimum array In MHz
-} __attribute__((packed));
+};
 
 struct smu_13_0_powerplay_table {
 	struct atom_common_table_header header;
@@ -160,6 +162,8 @@ struct smu_13_0_powerplay_table {
 #ifndef SMU_13_0_PARTIAL_PPTABLE
 	PPTable_t smc_pptable;                        //PPTable_t in driver_if.h
 #endif
-} __attribute__((packed));
+};
+
+#pragma pack(pop)
 
 #endif