diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index cf4e190c0a72..1c49b8266d69 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1428,6 +1428,9 @@ int amdgpu_cs_fence_to_handle_ioctl(struct drm_device *dev, void *data,
 	if (IS_ERR(fence))
 		return PTR_ERR(fence);
 
+	if (!fence)
+		fence = dma_fence_get_stub();
+
 	switch (info->in.what) {
 	case AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ:
 		r = drm_syncobj_create(&syncobj, 0, fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b60afeade50a..8a078f4ae73d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3476,14 +3476,16 @@ static void amdgpu_device_lock_adev(struct amdgpu_device *adev)
 	mutex_lock(&adev->lock_reset);
 	atomic_inc(&adev->gpu_reset_counter);
 	adev->in_gpu_reset = 1;
-	/* Block kfd */
-	amdgpu_amdkfd_pre_reset(adev);
+	/* Block kfd: SRIOV would do it separately */
+	if (!amdgpu_sriov_vf(adev))
+                amdgpu_amdkfd_pre_reset(adev);
 }
 
 static void amdgpu_device_unlock_adev(struct amdgpu_device *adev)
 {
-	/*unlock kfd */
-	amdgpu_amdkfd_post_reset(adev);
+	/*unlock kfd: SRIOV would do it separately */
+	if (!amdgpu_sriov_vf(adev))
+                amdgpu_amdkfd_post_reset(adev);
 	amdgpu_vf_error_trans_all(adev);
 	adev->in_gpu_reset = 0;
 	mutex_unlock(&adev->lock_reset);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 9c77eaa45982..c806f984bcc5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -865,6 +865,7 @@ static const struct pci_device_id pciidlist[] = {
 	/* VEGAM */
 	{0x1002, 0x694C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGAM},
 	{0x1002, 0x694E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGAM},
+	{0x1002, 0x694F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGAM},
 	/* Vega 10 */
 	{0x1002, 0x6860, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10},
 	{0x1002, 0x6861, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10},
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index e0af44fd6a0c..0a17fb1af204 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -32,6 +32,9 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job)
 {
 	struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
 	struct amdgpu_job *job = to_amdgpu_job(s_job);
+	struct amdgpu_task_info ti;
+
+	memset(&ti, 0, sizeof(struct amdgpu_task_info));
 
 	if (amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
 		DRM_ERROR("ring %s timeout, but soft recovered\n",
@@ -39,9 +42,12 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job)
 		return;
 	}
 
+	amdgpu_vm_get_task_info(ring->adev, job->pasid, &ti);
 	DRM_ERROR("ring %s timeout, signaled seq=%u, emitted seq=%u\n",
 		  job->base.sched->name, atomic_read(&ring->fence_drv.last_seq),
 		  ring->fence_drv.sync_seq);
+	DRM_ERROR("Process information: process %s pid %d thread %s pid %d\n",
+		  ti.process_name, ti.tgid, ti.task_name, ti.pid);
 
 	if (amdgpu_device_should_recover_gpu(ring->adev))
 		amdgpu_device_gpu_recover(ring->adev, job);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index fd271f9746a2..728e15e5d68a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -912,7 +912,7 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo)
 	struct ttm_operation_ctx ctx = { false, false };
 	int r, i;
 
-	if (!bo->pin_count) {
+	if (WARN_ON_ONCE(!bo->pin_count)) {
 		dev_warn(adev->dev, "%p unpin not necessary\n", bo);
 		return 0;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 6759d898b3ab..8fab0d637ee5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -155,14 +155,6 @@ psp_cmd_submit_buf(struct psp_context *psp,
 	return ret;
 }
 
-bool psp_support_vmr_ring(struct psp_context *psp)
-{
-	if (amdgpu_sriov_vf(psp->adev) && psp->sos_fw_version > 0x80045)
-		return true;
-	else
-		return false;
-}
-
 static void psp_prep_tmr_cmd_buf(struct psp_context *psp,
 				 struct psp_gfx_cmd_resp *cmd,
 				 uint64_t tmr_mc, uint32_t size)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index 10decf70c9aa..3ee573b4016e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -83,12 +83,13 @@ struct psp_funcs
 				  enum AMDGPU_UCODE_ID ucode_type);
 	bool (*smu_reload_quirk)(struct psp_context *psp);
 	int (*mode1_reset)(struct psp_context *psp);
-	uint64_t (*xgmi_get_node_id)(struct psp_context *psp);
-	uint64_t (*xgmi_get_hive_id)(struct psp_context *psp);
+	int (*xgmi_get_node_id)(struct psp_context *psp, uint64_t *node_id);
+	int (*xgmi_get_hive_id)(struct psp_context *psp, uint64_t *hive_id);
 	int (*xgmi_get_topology_info)(struct psp_context *psp, int number_devices,
 				      struct psp_xgmi_topology_info *topology);
 	int (*xgmi_set_topology_info)(struct psp_context *psp, int number_devices,
 				      struct psp_xgmi_topology_info *topology);
+	bool (*support_vmr_ring)(struct psp_context *psp);
 };
 
 struct psp_xgmi_context {
@@ -192,12 +193,14 @@ struct psp_xgmi_topology_info {
 		((psp)->funcs->bootloader_load_sos ? (psp)->funcs->bootloader_load_sos((psp)) : 0)
 #define psp_smu_reload_quirk(psp) \
 		((psp)->funcs->smu_reload_quirk ? (psp)->funcs->smu_reload_quirk((psp)) : false)
+#define psp_support_vmr_ring(psp) \
+		((psp)->funcs->support_vmr_ring ? (psp)->funcs->support_vmr_ring((psp)) : false)
 #define psp_mode1_reset(psp) \
 		((psp)->funcs->mode1_reset ? (psp)->funcs->mode1_reset((psp)) : false)
-#define psp_xgmi_get_node_id(psp) \
-		((psp)->funcs->xgmi_get_node_id ? (psp)->funcs->xgmi_get_node_id((psp)) : 0)
-#define psp_xgmi_get_hive_id(psp) \
-		((psp)->funcs->xgmi_get_hive_id ? (psp)->funcs->xgmi_get_hive_id((psp)) : 0)
+#define psp_xgmi_get_node_id(psp, node_id) \
+		((psp)->funcs->xgmi_get_node_id ? (psp)->funcs->xgmi_get_node_id((psp), (node_id)) : -EINVAL)
+#define psp_xgmi_get_hive_id(psp, hive_id) \
+		((psp)->funcs->xgmi_get_hive_id ? (psp)->funcs->xgmi_get_hive_id((psp), (hive_id)) : -EINVAL)
 #define psp_xgmi_get_topology_info(psp, num_device, topology) \
 		((psp)->funcs->xgmi_get_topology_info ? \
 		(psp)->funcs->xgmi_get_topology_info((psp), (num_device), (topology)) : -EINVAL)
@@ -217,8 +220,6 @@ extern const struct amdgpu_ip_block_version psp_v10_0_ip_block;
 
 int psp_gpu_reset(struct amdgpu_device *adev);
 int psp_xgmi_invoke(struct psp_context *psp, uint32_t ta_cmd_id);
-bool psp_support_vmr_ring(struct psp_context *psp);
-
 extern const struct amdgpu_ip_block_version psp_v11_0_ip_block;
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 0beb01fef83f..d87e828a084b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -29,7 +29,7 @@
 #include <drm/drm_print.h>
 
 /* max number of rings */
-#define AMDGPU_MAX_RINGS		21
+#define AMDGPU_MAX_RINGS		23
 #define AMDGPU_MAX_GFX_RINGS		1
 #define AMDGPU_MAX_COMPUTE_RINGS	8
 #define AMDGPU_MAX_VCE_RINGS		3
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index e2e42e3fbcf3..ecf6f96df2ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -262,7 +262,7 @@ static int amdgpu_vcn_pause_dpg_mode(struct amdgpu_device *adev,
 
 				ring = &adev->vcn.ring_dec;
 				WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR,
-						   RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2));
+						   RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2) & 0x7FFFFFFF);
 				SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
 						   UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON,
 						   UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
@@ -322,7 +322,7 @@ static int amdgpu_vcn_pause_dpg_mode(struct amdgpu_device *adev,
 
 				ring = &adev->vcn.ring_dec;
 				WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR,
-						   RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2));
+						   RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2) & 0x7FFFFFFF);
 				SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
 						   UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON,
 						   UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
@@ -396,16 +396,26 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)	{
 		struct dpg_pause_state new_state;
+		unsigned int fences = 0;
+		unsigned int i;
+
+		for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+			fences += amdgpu_fence_count_emitted(&adev->vcn.ring_enc[i]);
+		}
+		if (fences)
+			new_state.fw_based = VCN_DPG_STATE__PAUSE;
+		else
+			new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
+
+		if (amdgpu_fence_count_emitted(&adev->vcn.ring_jpeg))
+			new_state.jpeg = VCN_DPG_STATE__PAUSE;
+		else
+			new_state.jpeg = VCN_DPG_STATE__UNPAUSE;
 
 		if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC)
 			new_state.fw_based = VCN_DPG_STATE__PAUSE;
-		else
-			new_state.fw_based = adev->vcn.pause_state.fw_based;
-
-		if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG)
+		else if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG)
 			new_state.jpeg = VCN_DPG_STATE__PAUSE;
-		else
-			new_state.jpeg = adev->vcn.pause_state.jpeg;
 
 		amdgpu_vcn_pause_dpg_mode(adev, &new_state);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 0b263a9857c6..8a8bc60cb6b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -97,8 +97,19 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 	if (!adev->gmc.xgmi.supported)
 		return 0;
 
-	adev->gmc.xgmi.node_id = psp_xgmi_get_node_id(&adev->psp);
-	adev->gmc.xgmi.hive_id = psp_xgmi_get_hive_id(&adev->psp);
+	ret = psp_xgmi_get_node_id(&adev->psp, &adev->gmc.xgmi.node_id);
+	if (ret) {
+		dev_err(adev->dev,
+			"XGMI: Failed to get node id\n");
+		return ret;
+	}
+
+	ret = psp_xgmi_get_hive_id(&adev->psp, &adev->gmc.xgmi.hive_id);
+	if (ret) {
+		dev_err(adev->dev,
+			"XGMI: Failed to get hive id\n");
+		return ret;
+	}
 
 	mutex_lock(&xgmi_mutex);
 	hive = amdgpu_get_xgmi_hive(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index ce150de723c9..bacdaef77b6c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -718,37 +718,46 @@ static bool gmc_v9_0_keep_stolen_memory(struct amdgpu_device *adev)
 	}
 }
 
+static int gmc_v9_0_allocate_vm_inv_eng(struct amdgpu_device *adev)
+{
+	struct amdgpu_ring *ring;
+	unsigned vm_inv_engs[AMDGPU_MAX_VMHUBS] =
+		{GFXHUB_FREE_VM_INV_ENGS_BITMAP, MMHUB_FREE_VM_INV_ENGS_BITMAP};
+	unsigned i;
+	unsigned vmhub, inv_eng;
+
+	for (i = 0; i < adev->num_rings; ++i) {
+		ring = adev->rings[i];
+		vmhub = ring->funcs->vmhub;
+
+		inv_eng = ffs(vm_inv_engs[vmhub]);
+		if (!inv_eng) {
+			dev_err(adev->dev, "no VM inv eng for ring %s\n",
+				ring->name);
+			return -EINVAL;
+		}
+
+		ring->vm_inv_eng = inv_eng - 1;
+		change_bit(inv_eng - 1, (unsigned long *)(&vm_inv_engs[vmhub]));
+
+		dev_info(adev->dev, "ring %s uses VM inv eng %u on hub %u\n",
+			 ring->name, ring->vm_inv_eng, ring->funcs->vmhub);
+	}
+
+	return 0;
+}
+
 static int gmc_v9_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	/*
-	 * The latest engine allocation on gfx9 is:
-	 * Engine 0, 1: idle
-	 * Engine 2, 3: firmware
-	 * Engine 4~13: amdgpu ring, subject to change when ring number changes
-	 * Engine 14~15: idle
-	 * Engine 16: kfd tlb invalidation
-	 * Engine 17: Gart flushes
-	 */
-	unsigned vm_inv_eng[AMDGPU_MAX_VMHUBS] = { 4, 4 };
-	unsigned i;
 	int r;
 
 	if (!gmc_v9_0_keep_stolen_memory(adev))
 		amdgpu_bo_late_init(adev);
 
-	for(i = 0; i < adev->num_rings; ++i) {
-		struct amdgpu_ring *ring = adev->rings[i];
-		unsigned vmhub = ring->funcs->vmhub;
-
-		ring->vm_inv_eng = vm_inv_eng[vmhub]++;
-		dev_info(adev->dev, "ring %s uses VM inv eng %u on hub %u\n",
-			 ring->name, ring->vm_inv_eng, ring->funcs->vmhub);
-	}
-
-	/* Engine 16 is used for KFD and 17 for GART flushes */
-	for(i = 0; i < AMDGPU_MAX_VMHUBS; ++i)
-		BUG_ON(vm_inv_eng[i] > 16);
+	r = gmc_v9_0_allocate_vm_inv_eng(adev);
+	if (r)
+		return r;
 
 	if (adev->asic_type == CHIP_VEGA10 && !amdgpu_sriov_vf(adev)) {
 		r = gmc_v9_0_ecc_available(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h
index b030ca5ea107..5c8deac65580 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h
@@ -24,6 +24,16 @@
 #ifndef __GMC_V9_0_H__
 #define __GMC_V9_0_H__
 
+	/*
+	 * The latest engine allocation on gfx9 is:
+	 * Engine 2, 3: firmware
+	 * Engine 0, 1, 4~16: amdgpu ring,
+	 *                    subject to change when ring number changes
+	 * Engine 17: Gart flushes
+	 */
+#define GFXHUB_FREE_VM_INV_ENGS_BITMAP		0x1FFF3
+#define MMHUB_FREE_VM_INV_ENGS_BITMAP		0x1FFF3
+
 extern const struct amd_ip_funcs gmc_v9_0_ip_funcs;
 extern const struct amdgpu_ip_block_version gmc_v9_0_ip_block;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
index 6f9c54978cc1..accdedd63c98 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
@@ -32,6 +32,7 @@
 #define smnCPM_CONTROL                                                                                  0x11180460
 #define smnPCIE_CNTL2                                                                                   0x11180070
 #define smnPCIE_CONFIG_CNTL                                                                             0x11180044
+#define smnPCIE_CI_CNTL                                                                                 0x11180080
 
 static u32 nbio_v6_1_get_rev_id(struct amdgpu_device *adev)
 {
@@ -270,6 +271,12 @@ static void nbio_v6_1_init_registers(struct amdgpu_device *adev)
 
 	if (def != data)
 		WREG32_PCIE(smnPCIE_CONFIG_CNTL, data);
+
+	def = data = RREG32_PCIE(smnPCIE_CI_CNTL);
+	data = REG_SET_FIELD(data, PCIE_CI_CNTL, CI_SLV_ORDERING_DIS, 1);
+
+	if (def != data)
+		WREG32_PCIE(smnPCIE_CI_CNTL, data);
 }
 
 const struct amdgpu_nbio_funcs nbio_v6_1_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index f8cee95d61cc..4cd31a276dcd 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -31,6 +31,7 @@
 
 #define smnCPM_CONTROL                                                                                  0x11180460
 #define smnPCIE_CNTL2                                                                                   0x11180070
+#define smnPCIE_CI_CNTL                                                                                 0x11180080
 
 static u32 nbio_v7_4_get_rev_id(struct amdgpu_device *adev)
 {
@@ -222,7 +223,13 @@ static void nbio_v7_4_detect_hw_virt(struct amdgpu_device *adev)
 
 static void nbio_v7_4_init_registers(struct amdgpu_device *adev)
 {
+	uint32_t def, data;
 
+	def = data = RREG32_PCIE(smnPCIE_CI_CNTL);
+	data = REG_SET_FIELD(data, PCIE_CI_CNTL, CI_SLV_ORDERING_DIS, 1);
+
+	if (def != data)
+		WREG32_PCIE(smnPCIE_CI_CNTL, data);
 }
 
 const struct amdgpu_nbio_funcs nbio_v7_4_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index 6c9a1b748ca7..0c6e7f9b143f 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -34,6 +34,7 @@
 #include "nbio/nbio_7_4_offset.h"
 
 MODULE_FIRMWARE("amdgpu/vega20_sos.bin");
+MODULE_FIRMWARE("amdgpu/vega20_asd.bin");
 MODULE_FIRMWARE("amdgpu/vega20_ta.bin");
 
 /* address block */
@@ -100,6 +101,7 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 	char fw_name[30];
 	int err = 0;
 	const struct psp_firmware_header_v1_0 *sos_hdr;
+	const struct psp_firmware_header_v1_0 *asd_hdr;
 	const struct ta_firmware_header_v1_0 *ta_hdr;
 
 	DRM_DEBUG("\n");
@@ -132,14 +134,30 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 	adev->psp.sos_start_addr = (uint8_t *)adev->psp.sys_start_addr +
 				le32_to_cpu(sos_hdr->sos_offset_bytes);
 
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_asd.bin", chip_name);
+	err = request_firmware(&adev->psp.asd_fw, fw_name, adev->dev);
+	if (err)
+		goto out1;
+
+	err = amdgpu_ucode_validate(adev->psp.asd_fw);
+	if (err)
+		goto out1;
+
+	asd_hdr = (const struct psp_firmware_header_v1_0 *)adev->psp.asd_fw->data;
+	adev->psp.asd_fw_version = le32_to_cpu(asd_hdr->header.ucode_version);
+	adev->psp.asd_feature_version = le32_to_cpu(asd_hdr->ucode_feature_version);
+	adev->psp.asd_ucode_size = le32_to_cpu(asd_hdr->header.ucode_size_bytes);
+	adev->psp.asd_start_addr = (uint8_t *)asd_hdr +
+				le32_to_cpu(asd_hdr->header.ucode_array_offset_bytes);
+
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name);
 	err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev);
 	if (err)
-		goto out;
+		goto out2;
 
 	err = amdgpu_ucode_validate(adev->psp.ta_fw);
 	if (err)
-		goto out;
+		goto out2;
 
 	ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data;
 	adev->psp.ta_xgmi_ucode_version = le32_to_cpu(ta_hdr->ta_xgmi_ucode_version);
@@ -148,14 +166,18 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 		le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
 
 	return 0;
+
+out2:
+	release_firmware(adev->psp.ta_fw);
+	adev->psp.ta_fw = NULL;
+out1:
+	release_firmware(adev->psp.asd_fw);
+	adev->psp.asd_fw = NULL;
 out:
-	if (err) {
-		dev_err(adev->dev,
-			"psp v11.0: Failed to load firmware \"%s\"\n",
-			fw_name);
-		release_firmware(adev->psp.sos_fw);
-		adev->psp.sos_fw = NULL;
-	}
+	dev_err(adev->dev,
+		"psp v11.0: Failed to load firmware \"%s\"\n", fw_name);
+	release_firmware(adev->psp.sos_fw);
+	adev->psp.sos_fw = NULL;
 
 	return err;
 }
@@ -291,6 +313,13 @@ static int psp_v11_0_ring_init(struct psp_context *psp,
 	return 0;
 }
 
+static bool psp_v11_0_support_vmr_ring(struct psp_context *psp)
+{
+	if (amdgpu_sriov_vf(psp->adev) && psp->sos_fw_version > 0x80045)
+		return true;
+	return false;
+}
+
 static int psp_v11_0_ring_create(struct psp_context *psp,
 				enum psp_ring_type ring_type)
 {
@@ -299,7 +328,7 @@ static int psp_v11_0_ring_create(struct psp_context *psp,
 	struct psp_ring *ring = &psp->km_ring;
 	struct amdgpu_device *adev = psp->adev;
 
-	if (psp_support_vmr_ring(psp)) {
+	if (psp_v11_0_support_vmr_ring(psp)) {
 		/* Write low address of the ring to C2PMSG_102 */
 		psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr);
 		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, psp_ring_reg);
@@ -351,7 +380,7 @@ static int psp_v11_0_ring_stop(struct psp_context *psp,
 	struct amdgpu_device *adev = psp->adev;
 
 	/* Write the ring destroy command*/
-	if (psp_support_vmr_ring(psp))
+	if (psp_v11_0_support_vmr_ring(psp))
 		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101,
 				     GFX_CTRL_CMD_ID_DESTROY_GPCOM_RING);
 	else
@@ -362,7 +391,7 @@ static int psp_v11_0_ring_stop(struct psp_context *psp,
 	mdelay(20);
 
 	/* Wait for response flag (bit 31) */
-	if (psp_support_vmr_ring(psp))
+	if (psp_v11_0_support_vmr_ring(psp))
 		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_101),
 				   0x80000000, 0x80000000, false);
 	else
@@ -406,7 +435,7 @@ static int psp_v11_0_cmd_submit(struct psp_context *psp,
 	uint32_t rb_frame_size_dw = sizeof(struct psp_gfx_rb_frame) / 4;
 
 	/* KM (GPCOM) prepare write pointer */
-	if (psp_support_vmr_ring(psp))
+	if (psp_v11_0_support_vmr_ring(psp))
 		psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102);
 	else
 		psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
@@ -438,7 +467,7 @@ static int psp_v11_0_cmd_submit(struct psp_context *psp,
 
 	/* Update the write Pointer in DWORDs */
 	psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw;
-	if (psp_support_vmr_ring(psp)) {
+	if (psp_v11_0_support_vmr_ring(psp)) {
 		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, psp_write_ptr_reg);
 		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101, GFX_CTRL_CMD_ID_CONSUME_CMD);
 	} else
@@ -680,7 +709,7 @@ static int psp_v11_0_xgmi_set_topology_info(struct psp_context *psp,
 	return psp_xgmi_invoke(psp, TA_COMMAND_XGMI__SET_TOPOLOGY_INFO);
 }
 
-static u64 psp_v11_0_xgmi_get_hive_id(struct psp_context *psp)
+static int psp_v11_0_xgmi_get_hive_id(struct psp_context *psp, uint64_t *hive_id)
 {
 	struct ta_xgmi_shared_memory *xgmi_cmd;
 	int ret;
@@ -693,12 +722,14 @@ static u64 psp_v11_0_xgmi_get_hive_id(struct psp_context *psp)
 	/* Invoke xgmi ta to get hive id */
 	ret = psp_xgmi_invoke(psp, xgmi_cmd->cmd_id);
 	if (ret)
-		return 0;
-	else
-		return xgmi_cmd->xgmi_out_message.get_hive_id.hive_id;
+		return ret;
+
+	*hive_id = xgmi_cmd->xgmi_out_message.get_hive_id.hive_id;
+
+	return 0;
 }
 
-static u64 psp_v11_0_xgmi_get_node_id(struct psp_context *psp)
+static int psp_v11_0_xgmi_get_node_id(struct psp_context *psp, uint64_t *node_id)
 {
 	struct ta_xgmi_shared_memory *xgmi_cmd;
 	int ret;
@@ -711,9 +742,11 @@ static u64 psp_v11_0_xgmi_get_node_id(struct psp_context *psp)
 	/* Invoke xgmi ta to get the node id */
 	ret = psp_xgmi_invoke(psp, xgmi_cmd->cmd_id);
 	if (ret)
-		return 0;
-	else
-		return xgmi_cmd->xgmi_out_message.get_node_id.node_id;
+		return ret;
+
+	*node_id = xgmi_cmd->xgmi_out_message.get_node_id.node_id;
+
+	return 0;
 }
 
 static const struct psp_funcs psp_v11_0_funcs = {
@@ -732,6 +765,7 @@ static const struct psp_funcs psp_v11_0_funcs = {
 	.xgmi_set_topology_info = psp_v11_0_xgmi_set_topology_info,
 	.xgmi_get_hive_id = psp_v11_0_xgmi_get_hive_id,
 	.xgmi_get_node_id = psp_v11_0_xgmi_get_node_id,
+	.support_vmr_ring = psp_v11_0_support_vmr_ring,
 };
 
 void psp_v11_0_set_psp_funcs(struct psp_context *psp)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
index 7357fd56e614..79694ff16969 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
@@ -240,8 +240,11 @@ static int psp_v3_1_bootloader_load_sos(struct psp_context *psp)
 	 * are already been loaded.
 	 */
 	sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
-	if (sol_reg)
+	if (sol_reg) {
+		psp->sos_fw_version = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_58);
+		printk("sos fw version = 0x%x.\n", psp->sos_fw_version);
 		return 0;
+	}
 
 	/* Wait for bootloader to signify that is ready having bit 31 of C2PMSG_35 set to 1 */
 	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 4b6d3e5c821f..fd0bfe140ee0 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -1458,8 +1458,7 @@ static bool sdma_v4_0_fw_support_paging_queue(struct amdgpu_device *adev)
 		/*return fw_version >= 31;*/
 		return false;
 	case CHIP_VEGA20:
-		/*return fw_version >= 115;*/
-		return false;
+		return fw_version >= 123;
 	default:
 		return false;
 	}
@@ -1706,13 +1705,15 @@ static int sdma_v4_0_process_trap_irq(struct amdgpu_device *adev,
 		amdgpu_fence_process(&adev->sdma.instance[instance].ring);
 		break;
 	case 1:
-		/* XXX compute */
+		if (adev->asic_type == CHIP_VEGA20)
+			amdgpu_fence_process(&adev->sdma.instance[instance].page);
 		break;
 	case 2:
 		/* XXX compute */
 		break;
 	case 3:
-		amdgpu_fence_process(&adev->sdma.instance[instance].page);
+		if (adev->asic_type != CHIP_VEGA20)
+			amdgpu_fence_process(&adev->sdma.instance[instance].page);
 		break;
 	}
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15_common.h b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
index 958b10a57073..49c262540940 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15_common.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
@@ -49,14 +49,19 @@
 
 #define SOC15_WAIT_ON_RREG(ip, inst, reg, expected_value, mask, ret) \
 	do {							\
+		uint32_t old_ = 0;	\
 		uint32_t tmp_ = RREG32(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg); \
 		uint32_t loop = adev->usec_timeout;		\
 		while ((tmp_ & (mask)) != (expected_value)) {	\
-			udelay(2);				\
+			if (old_ != tmp_) {			\
+				loop = adev->usec_timeout;	\
+				old_ = tmp_;				\
+			} else						\
+				udelay(1);				\
 			tmp_ = RREG32(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg); \
 			loop--;					\
 			if (!loop) {				\
-				DRM_ERROR("Register(%d) [%s] failed to reach value 0x%08x != 0x%08x\n", \
+				DRM_WARN("Register(%d) [%s] failed to reach value 0x%08x != 0x%08x\n", \
 					  inst, #reg, (unsigned)expected_value, (unsigned)(tmp_ & (mask))); \
 				ret = -ETIMEDOUT;		\
 				break;				\
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index 089645e78f98..aef924026a28 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -435,7 +435,7 @@ static int uvd_v7_0_sw_init(void *handle)
 			continue;
 		if (!amdgpu_sriov_vf(adev)) {
 			ring = &adev->uvd.inst[j].ring;
-			sprintf(ring->name, "uvd<%d>", j);
+			sprintf(ring->name, "uvd_%d", ring->me);
 			r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst[j].irq, 0);
 			if (r)
 				return r;
@@ -443,7 +443,7 @@ static int uvd_v7_0_sw_init(void *handle)
 
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
 			ring = &adev->uvd.inst[j].ring_enc[i];
-			sprintf(ring->name, "uvd_enc%d<%d>", i, j);
+			sprintf(ring->name, "uvd_enc_%d.%d", ring->me, i);
 			if (amdgpu_sriov_vf(adev)) {
 				ring->use_doorbell = true;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 4f8352044563..89bb2fef90eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -214,7 +214,8 @@ static int vcn_v1_0_hw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct amdgpu_ring *ring = &adev->vcn.ring_dec;
 
-	if (RREG32_SOC15(VCN, 0, mmUVD_STATUS))
+	if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ||
+		RREG32_SOC15(VCN, 0, mmUVD_STATUS))
 		vcn_v1_0_set_powergating_state(adev, AMD_PG_STATE_GATE);
 
 	ring->sched.ready = false;
@@ -1087,7 +1088,8 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
 	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_RBC_RB_CNTL), 0,
 			~UVD_RBC_RB_CNTL__RB_NO_FETCH_MASK);
 
-	/* initialize wptr */
+	/* initialize JPEG wptr */
+	ring = &adev->vcn.ring_jpeg;
 	ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
 
 	/* copy patch commands to the jpeg ring */
@@ -1159,21 +1161,29 @@ static int vcn_v1_0_stop_spg_mode(struct amdgpu_device *adev)
 static int vcn_v1_0_stop_dpg_mode(struct amdgpu_device *adev)
 {
 	int ret_code = 0;
+	uint32_t tmp;
 
 	/* Wait for power status to be UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF */
 	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
 			UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF,
 			UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
 
-	if (!ret_code) {
-		int tmp = RREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR) & 0x7FFFFFFF;
-		/* wait for read ptr to be equal to write ptr */
-		SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RBC_RB_RPTR, tmp, 0xFFFFFFFF, ret_code);
+	/* wait for read ptr to be equal to write ptr */
+	tmp = RREG32_SOC15(UVD, 0, mmUVD_RB_WPTR);
+	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RB_RPTR, tmp, 0xFFFFFFFF, ret_code);
 
-		SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
-			UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF,
-			UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
-	}
+	tmp = RREG32_SOC15(UVD, 0, mmUVD_RB_WPTR2);
+	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RB_RPTR2, tmp, 0xFFFFFFFF, ret_code);
+
+	tmp = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
+	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_JRBC_RB_RPTR, tmp, 0xFFFFFFFF, ret_code);
+
+	tmp = RREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR) & 0x7FFFFFFF;
+	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RBC_RB_RPTR, tmp, 0xFFFFFFFF, ret_code);
+
+	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
+		UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF,
+		UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
 
 	/* disable dynamic power gating mode */
 	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS), 0,
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index ff2906c215fa..77e367459101 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -87,9 +87,9 @@ static u32 vi_pcie_rreg(struct amdgpu_device *adev, u32 reg)
 	u32 r;
 
 	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
-	WREG32(mmPCIE_INDEX, reg);
-	(void)RREG32(mmPCIE_INDEX);
-	r = RREG32(mmPCIE_DATA);
+	WREG32_NO_KIQ(mmPCIE_INDEX, reg);
+	(void)RREG32_NO_KIQ(mmPCIE_INDEX);
+	r = RREG32_NO_KIQ(mmPCIE_DATA);
 	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
 	return r;
 }
@@ -99,10 +99,10 @@ static void vi_pcie_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 	unsigned long flags;
 
 	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
-	WREG32(mmPCIE_INDEX, reg);
-	(void)RREG32(mmPCIE_INDEX);
-	WREG32(mmPCIE_DATA, v);
-	(void)RREG32(mmPCIE_DATA);
+	WREG32_NO_KIQ(mmPCIE_INDEX, reg);
+	(void)RREG32_NO_KIQ(mmPCIE_INDEX);
+	WREG32_NO_KIQ(mmPCIE_DATA, v);
+	(void)RREG32_NO_KIQ(mmPCIE_DATA);
 	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
 }
 
@@ -123,8 +123,8 @@ static void vi_smc_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 	unsigned long flags;
 
 	spin_lock_irqsave(&adev->smc_idx_lock, flags);
-	WREG32(mmSMC_IND_INDEX_11, (reg));
-	WREG32(mmSMC_IND_DATA_11, (v));
+	WREG32_NO_KIQ(mmSMC_IND_INDEX_11, (reg));
+	WREG32_NO_KIQ(mmSMC_IND_DATA_11, (v));
 	spin_unlock_irqrestore(&adev->smc_idx_lock, flags);
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index be68752c3469..083bd8114db1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1623,8 +1623,8 @@ static int kfd_ioctl_import_dmabuf(struct file *filep,
 		return -EINVAL;
 
 	dmabuf = dma_buf_get(args->dmabuf_fd);
-	if (!dmabuf)
-		return -EINVAL;
+	if (IS_ERR(dmabuf))
+		return PTR_ERR(dmabuf);
 
 	mutex_lock(&p->mutex);
 
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 d01315965af0..a9a28dbc3e24 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -331,12 +331,29 @@ static void dm_crtc_high_irq(void *interrupt_params)
 	struct common_irq_params *irq_params = interrupt_params;
 	struct amdgpu_device *adev = irq_params->adev;
 	struct amdgpu_crtc *acrtc;
+	struct dm_crtc_state *acrtc_state;
 
 	acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK);
 
 	if (acrtc) {
 		drm_crtc_handle_vblank(&acrtc->base);
 		amdgpu_dm_crtc_handle_crc_irq(&acrtc->base);
+
+		acrtc_state = to_dm_crtc_state(acrtc->base.state);
+
+		if (acrtc_state->stream &&
+		    acrtc_state->vrr_params.supported &&
+		    acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) {
+			mod_freesync_handle_v_update(
+				adev->dm.freesync_module,
+				acrtc_state->stream,
+				&acrtc_state->vrr_params);
+
+			dc_stream_adjust_vmin_vmax(
+				adev->dm.dc,
+				acrtc_state->stream,
+				&acrtc_state->vrr_params.adjust);
+		}
 	}
 }
 
@@ -3009,7 +3026,7 @@ dm_crtc_duplicate_state(struct drm_crtc *crtc)
 		dc_stream_retain(state->stream);
 	}
 
-	state->adjust = cur->adjust;
+	state->vrr_params = cur->vrr_params;
 	state->vrr_infopacket = cur->vrr_infopacket;
 	state->abm_level = cur->abm_level;
 	state->vrr_supported = cur->vrr_supported;
@@ -3628,10 +3645,20 @@ static int dm_plane_atomic_check(struct drm_plane *plane,
 static int dm_plane_atomic_async_check(struct drm_plane *plane,
 				       struct drm_plane_state *new_plane_state)
 {
+	struct drm_plane_state *old_plane_state =
+		drm_atomic_get_old_plane_state(new_plane_state->state, plane);
+
 	/* Only support async updates on cursor planes. */
 	if (plane->type != DRM_PLANE_TYPE_CURSOR)
 		return -EINVAL;
 
+	/*
+	 * DRM calls prepare_fb and cleanup_fb on new_plane_state for
+	 * async commits so don't allow fb changes.
+	 */
+	if (old_plane_state->fb != new_plane_state->fb)
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -4445,9 +4472,11 @@ struct dc_stream_status *dc_state_get_stream_status(
 static void update_freesync_state_on_stream(
 	struct amdgpu_display_manager *dm,
 	struct dm_crtc_state *new_crtc_state,
-	struct dc_stream_state *new_stream)
+	struct dc_stream_state *new_stream,
+	struct dc_plane_state *surface,
+	u32 flip_timestamp_in_us)
 {
-	struct mod_vrr_params vrr = {0};
+	struct mod_vrr_params vrr_params = new_crtc_state->vrr_params;
 	struct dc_info_packet vrr_infopacket = {0};
 	struct mod_freesync_config config = new_crtc_state->freesync_config;
 
@@ -4474,43 +4503,52 @@ static void update_freesync_state_on_stream(
 
 	mod_freesync_build_vrr_params(dm->freesync_module,
 				      new_stream,
-				      &config, &vrr);
+				      &config, &vrr_params);
+
+	if (surface) {
+		mod_freesync_handle_preflip(
+			dm->freesync_module,
+			surface,
+			new_stream,
+			flip_timestamp_in_us,
+			&vrr_params);
+	}
 
 	mod_freesync_build_vrr_infopacket(
 		dm->freesync_module,
 		new_stream,
-		&vrr,
+		&vrr_params,
 		PACKET_TYPE_VRR,
 		TRANSFER_FUNC_UNKNOWN,
 		&vrr_infopacket);
 
 	new_crtc_state->freesync_timing_changed =
-		(memcmp(&new_crtc_state->adjust,
-			&vrr.adjust,
-			sizeof(vrr.adjust)) != 0);
+		(memcmp(&new_crtc_state->vrr_params.adjust,
+			&vrr_params.adjust,
+			sizeof(vrr_params.adjust)) != 0);
 
 	new_crtc_state->freesync_vrr_info_changed =
 		(memcmp(&new_crtc_state->vrr_infopacket,
 			&vrr_infopacket,
 			sizeof(vrr_infopacket)) != 0);
 
-	new_crtc_state->adjust = vrr.adjust;
+	new_crtc_state->vrr_params = vrr_params;
 	new_crtc_state->vrr_infopacket = vrr_infopacket;
 
-	new_stream->adjust = new_crtc_state->adjust;
+	new_stream->adjust = new_crtc_state->vrr_params.adjust;
 	new_stream->vrr_infopacket = vrr_infopacket;
 
 	if (new_crtc_state->freesync_vrr_info_changed)
 		DRM_DEBUG_KMS("VRR packet update: crtc=%u enabled=%d state=%d",
 			      new_crtc_state->base.crtc->base.id,
 			      (int)new_crtc_state->base.vrr_enabled,
-			      (int)vrr.state);
+			      (int)vrr_params.state);
 
 	if (new_crtc_state->freesync_timing_changed)
 		DRM_DEBUG_KMS("VRR timing update: crtc=%u min=%u max=%u\n",
 			      new_crtc_state->base.crtc->base.id,
-			      vrr.adjust.v_total_min,
-			      vrr.adjust.v_total_max);
+				  vrr_params.adjust.v_total_min,
+				  vrr_params.adjust.v_total_max);
 }
 
 /*
@@ -4524,6 +4562,7 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc,
 			      struct dc_state *state)
 {
 	unsigned long flags;
+	uint64_t timestamp_ns;
 	uint32_t target_vblank;
 	int r, vpos, hpos;
 	struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
@@ -4537,6 +4576,7 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc,
 	struct dc_stream_update stream_update = {0};
 	struct dm_crtc_state *acrtc_state = to_dm_crtc_state(crtc->state);
 	struct dc_stream_status *stream_status;
+	struct dc_plane_state *surface;
 
 
 	/* Prepare wait for target vblank early - before the fence-waits */
@@ -4586,6 +4626,9 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc,
 	addr.address.grph.addr.high_part = upper_32_bits(afb->address);
 	addr.flip_immediate = async_flip;
 
+	timestamp_ns = ktime_get_ns();
+	addr.flip_timestamp_in_us = div_u64(timestamp_ns, 1000);
+
 
 	if (acrtc->base.state->event)
 		prepare_flip_isr(acrtc);
@@ -4599,8 +4642,10 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc,
 		return;
 	}
 
-	surface_updates->surface = stream_status->plane_states[0];
-	if (!surface_updates->surface) {
+	surface = stream_status->plane_states[0];
+	surface_updates->surface = surface;
+
+	if (!surface) {
 		DRM_ERROR("No surface for CRTC: id=%d\n",
 			acrtc->crtc_id);
 		return;
@@ -4611,7 +4656,9 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc,
 		update_freesync_state_on_stream(
 			&adev->dm,
 			acrtc_state,
-			acrtc_state->stream);
+			acrtc_state->stream,
+			surface,
+			addr.flip_timestamp_in_us);
 
 		if (acrtc_state->freesync_timing_changed)
 			stream_update.adjust =
@@ -4622,7 +4669,16 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc,
 				&acrtc_state->stream->vrr_infopacket;
 	}
 
+	/* Update surface timing information. */
+	surface->time.time_elapsed_in_us[surface->time.index] =
+		addr.flip_timestamp_in_us - surface->time.prev_update_time_in_us;
+	surface->time.prev_update_time_in_us = addr.flip_timestamp_in_us;
+	surface->time.index++;
+	if (surface->time.index >= DC_PLANE_UPDATE_TIMES_MAX)
+		surface->time.index = 0;
+
 	mutex_lock(&adev->dm.dc_lock);
+
 	dc_commit_updates_for_stream(adev->dm.dc,
 					     surface_updates,
 					     1,
@@ -5314,6 +5370,7 @@ static void get_freesync_config_for_crtc(
 		config.max_refresh_in_uhz =
 				aconnector->max_vfreq * 1000000;
 		config.vsif_supported = true;
+		config.btr = true;
 	}
 
 	new_crtc_state->freesync_config = config;
@@ -5324,8 +5381,8 @@ static void reset_freesync_config_for_crtc(
 {
 	new_crtc_state->vrr_supported = false;
 
-	memset(&new_crtc_state->adjust, 0,
-	       sizeof(new_crtc_state->adjust));
+	memset(&new_crtc_state->vrr_params, 0,
+	       sizeof(new_crtc_state->vrr_params));
 	memset(&new_crtc_state->vrr_infopacket, 0,
 	       sizeof(new_crtc_state->vrr_infopacket));
 }
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 25bb91ee80ba..fbd161ddc3f4 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -268,7 +268,7 @@ struct dm_crtc_state {
 
 	bool vrr_supported;
 	struct mod_freesync_config freesync_config;
-	struct dc_crtc_timing_adjust adjust;
+	struct mod_vrr_params vrr_params;
 	struct dc_info_packet vrr_infopacket;
 
 	int abm_level;
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 751bb614fc0e..c513ab6f3843 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -638,6 +638,7 @@ static enum bp_result get_ss_info_v4_1(
 {
 	enum bp_result result = BP_RESULT_OK;
 	struct atom_display_controller_info_v4_1 *disp_cntl_tbl = NULL;
+	struct atom_smu_info_v3_3 *smu_info = NULL;
 
 	if (!ss_info)
 		return BP_RESULT_BADINPUT;
@@ -650,6 +651,7 @@ static enum bp_result get_ss_info_v4_1(
 	if (!disp_cntl_tbl)
 		return BP_RESULT_BADBIOSTABLE;
 
+
 	ss_info->type.STEP_AND_DELAY_INFO = false;
 	ss_info->spread_percentage_divider = 1000;
 	/* BIOS no longer uses target clock.  Always enable for now */
@@ -688,6 +690,19 @@ static enum bp_result get_ss_info_v4_1(
 		 */
 		result = BP_RESULT_UNSUPPORTED;
 		break;
+	case AS_SIGNAL_TYPE_XGMI:
+		smu_info =  GET_IMAGE(struct atom_smu_info_v3_3,
+				      DATA_TABLES(smu_info));
+		if (!smu_info)
+			return BP_RESULT_BADBIOSTABLE;
+
+		ss_info->spread_spectrum_percentage =
+				smu_info->waflclk_ss_percentage;
+		ss_info->spread_spectrum_range =
+				smu_info->gpuclk_ss_rate_10hz * 10;
+		if (smu_info->waflclk_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE)
+			ss_info->type.CENTER_MODE = true;
+		break;
 	default:
 		result = BP_RESULT_UNSUPPORTED;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
index 65b006ad372e..8196f3bb10c7 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
@@ -67,6 +67,7 @@ bool dal_bios_parser_init_cmd_tbl_helper2(
 		return true;
 #endif
 	case DCE_VERSION_12_0:
+	case DCE_VERSION_12_1:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return true;
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index d9c57984394b..5fd52094d459 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -151,10 +151,6 @@ static bool create_links(
 		return false;
 	}
 
-	if (connectors_num == 0 && num_virtual_links == 0) {
-		dm_error("DC: Number of connectors is zero!\n");
-	}
-
 	dm_output_to_console(
 		"DC: %s: connectors_num: physical:%d, virtual:%d\n",
 		__func__,
@@ -1471,7 +1467,8 @@ static void commit_planes_do_stream_update(struct dc *dc,
 
 			if ((stream_update->hdr_static_metadata && !stream->use_dynamic_meta) ||
 					stream_update->vrr_infopacket ||
-					stream_update->vsc_infopacket) {
+					stream_update->vsc_infopacket ||
+					stream_update->vsp_infopacket) {
 				resource_build_info_frame(pipe_ctx);
 				dc->hwss.update_info_frame(pipe_ctx);
 			}
@@ -1573,9 +1570,6 @@ static void commit_planes_for_stream(struct dc *dc,
 		}
 	}
 
-	if (update_type == UPDATE_TYPE_FULL)
-		context_timing_trace(dc, &context->res_ctx);
-
 	// Update Type FAST, Surface updates
 	if (update_type == UPDATE_TYPE_FAST) {
 		/* Lock the top pipe while updating plane addrs, since freesync requires
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 4dc5846de5c4..52deacf39841 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -215,6 +215,9 @@ bool dc_link_detect_sink(struct dc_link *link, enum dc_connection_type *type)
 		return true;
 	}
 
+	if (link->connector_signal == SIGNAL_TYPE_EDP)
+		link->dc->hwss.edp_wait_for_hpd_ready(link, true);
+
 	/* todo: may need to lock gpio access */
 	hpd_pin = get_hpd_gpio(link->ctx->dc_bios, link->link_id, link->ctx->gpio_service);
 	if (hpd_pin == NULL)
@@ -339,7 +342,7 @@ bool dc_link_is_dp_sink_present(struct dc_link *link)
 {
 	enum gpio_result gpio_result;
 	uint32_t clock_pin = 0;
-
+	uint8_t retry = 0;
 	struct ddc *ddc;
 
 	enum connector_id connector_id =
@@ -368,11 +371,22 @@ bool dc_link_is_dp_sink_present(struct dc_link *link)
 		return present;
 	}
 
-	/* Read GPIO: DP sink is present if both clock and data pins are zero */
-	/* [anaumov] in DAL2, there was no check for GPIO failure */
-
-	gpio_result = dal_gpio_get_value(ddc->pin_clock, &clock_pin);
-	ASSERT(gpio_result == GPIO_RESULT_OK);
+	/*
+	 * Read GPIO: DP sink is present if both clock and data pins are zero
+	 *
+	 * [W/A] plug-unplug DP cable, sometimes customer board has
+	 * one short pulse on clk_pin(1V, < 1ms). DP will be config to HDMI/DVI
+	 * then monitor can't br light up. Add retry 3 times
+	 * But in real passive dongle, it need additional 3ms to detect
+	 */
+	do {
+		gpio_result = dal_gpio_get_value(ddc->pin_clock, &clock_pin);
+		ASSERT(gpio_result == GPIO_RESULT_OK);
+		if (clock_pin)
+			udelay(1000);
+		else
+			break;
+	} while (retry++ < 3);
 
 	present = (gpio_result == GPIO_RESULT_OK) && !clock_pin;
 
@@ -703,12 +717,26 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 				if (memcmp(&link->dpcd_caps, &prev_dpcd_caps, sizeof(struct dpcd_caps)))
 					same_dpcd = false;
 			}
-			/* Active dongle downstream unplug */
+			/* Active dongle plug in without display or downstream unplug*/
 			if (link->type == dc_connection_active_dongle
 					&& link->dpcd_caps.sink_count.
 					bits.SINK_COUNT == 0) {
-				if (prev_sink != NULL)
+				if (prev_sink != NULL) {
+					/* Downstream unplug */
 					dc_sink_release(prev_sink);
+				} else {
+					/* Empty dongle plug in */
+					for (i = 0; i < LINK_TRAINING_MAX_VERIFY_RETRY; i++) {
+						int fail_count = 0;
+
+						dp_verify_link_cap(link,
+								  &link->reported_link_cap,
+								  &fail_count);
+
+						if (fail_count == 0)
+							break;
+					}
+				}
 				return true;
 			}
 
@@ -2622,11 +2650,11 @@ void core_link_disable_stream(struct pipe_ctx *pipe_ctx, int option)
 {
 	struct dc  *core_dc = pipe_ctx->stream->ctx->dc;
 
+	core_dc->hwss.blank_stream(pipe_ctx);
+
 	if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
 		deallocate_mst_payload(pipe_ctx);
 
-	core_dc->hwss.blank_stream(pipe_ctx);
-
 	core_dc->hwss.disable_stream(pipe_ctx, option);
 
 	disable_link(pipe_ctx->stream->sink->link, pipe_ctx->stream->signal);
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 849a3a3032f7..0caacb60b02f 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
@@ -1089,6 +1089,121 @@ static struct dc_link_settings get_max_link_cap(struct dc_link *link)
 	return max_link_cap;
 }
 
+static enum dc_status read_hpd_rx_irq_data(
+	struct dc_link *link,
+	union hpd_irq_data *irq_data)
+{
+	static enum dc_status retval;
+
+	/* The HW reads 16 bytes from 200h on HPD,
+	 * but if we get an AUX_DEFER, the HW cannot retry
+	 * and this causes the CTS tests 4.3.2.1 - 3.2.4 to
+	 * fail, so we now explicitly read 6 bytes which is
+	 * the req from the above mentioned test cases.
+	 *
+	 * For DP 1.4 we need to read those from 2002h range.
+	 */
+	if (link->dpcd_caps.dpcd_rev.raw < DPCD_REV_14)
+		retval = core_link_read_dpcd(
+			link,
+			DP_SINK_COUNT,
+			irq_data->raw,
+			sizeof(union hpd_irq_data));
+	else {
+		/* Read 14 bytes in a single read and then copy only the required fields.
+		 * This is more efficient than doing it in two separate AUX reads. */
+
+		uint8_t tmp[DP_SINK_STATUS_ESI - DP_SINK_COUNT_ESI + 1];
+
+		retval = core_link_read_dpcd(
+			link,
+			DP_SINK_COUNT_ESI,
+			tmp,
+			sizeof(tmp));
+
+		if (retval != DC_OK)
+			return retval;
+
+		irq_data->bytes.sink_cnt.raw = tmp[DP_SINK_COUNT_ESI - DP_SINK_COUNT_ESI];
+		irq_data->bytes.device_service_irq.raw = tmp[DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0 - DP_SINK_COUNT_ESI];
+		irq_data->bytes.lane01_status.raw = tmp[DP_LANE0_1_STATUS_ESI - DP_SINK_COUNT_ESI];
+		irq_data->bytes.lane23_status.raw = tmp[DP_LANE2_3_STATUS_ESI - DP_SINK_COUNT_ESI];
+		irq_data->bytes.lane_status_updated.raw = tmp[DP_LANE_ALIGN_STATUS_UPDATED_ESI - DP_SINK_COUNT_ESI];
+		irq_data->bytes.sink_status.raw = tmp[DP_SINK_STATUS_ESI - DP_SINK_COUNT_ESI];
+	}
+
+	return retval;
+}
+
+static bool hpd_rx_irq_check_link_loss_status(
+	struct dc_link *link,
+	union hpd_irq_data *hpd_irq_dpcd_data)
+{
+	uint8_t irq_reg_rx_power_state = 0;
+	enum dc_status dpcd_result = DC_ERROR_UNEXPECTED;
+	union lane_status lane_status;
+	uint32_t lane;
+	bool sink_status_changed;
+	bool return_code;
+
+	sink_status_changed = false;
+	return_code = false;
+
+	if (link->cur_link_settings.lane_count == 0)
+		return return_code;
+
+	/*1. Check that Link Status changed, before re-training.*/
+
+	/*parse lane status*/
+	for (lane = 0; lane < link->cur_link_settings.lane_count; lane++) {
+		/* check status of lanes 0,1
+		 * changed DpcdAddress_Lane01Status (0x202)
+		 */
+		lane_status.raw = get_nibble_at_index(
+			&hpd_irq_dpcd_data->bytes.lane01_status.raw,
+			lane);
+
+		if (!lane_status.bits.CHANNEL_EQ_DONE_0 ||
+			!lane_status.bits.CR_DONE_0 ||
+			!lane_status.bits.SYMBOL_LOCKED_0) {
+			/* if one of the channel equalization, clock
+			 * recovery or symbol lock is dropped
+			 * consider it as (link has been
+			 * dropped) dp sink status has changed
+			 */
+			sink_status_changed = true;
+			break;
+		}
+	}
+
+	/* Check interlane align.*/
+	if (sink_status_changed ||
+		!hpd_irq_dpcd_data->bytes.lane_status_updated.bits.INTERLANE_ALIGN_DONE) {
+
+		DC_LOG_HW_HPD_IRQ("%s: Link Status changed.\n", __func__);
+
+		return_code = true;
+
+		/*2. Check that we can handle interrupt: Not in FS DOS,
+		 *  Not in "Display Timeout" state, Link is trained.
+		 */
+		dpcd_result = core_link_read_dpcd(link,
+			DP_SET_POWER,
+			&irq_reg_rx_power_state,
+			sizeof(irq_reg_rx_power_state));
+
+		if (dpcd_result != DC_OK) {
+			DC_LOG_HW_HPD_IRQ("%s: DPCD read failed to obtain power state.\n",
+				__func__);
+		} else {
+			if (irq_reg_rx_power_state != DP_SET_POWER_D0)
+				return_code = false;
+		}
+	}
+
+	return return_code;
+}
+
 bool dp_verify_link_cap(
 	struct dc_link *link,
 	struct dc_link_settings *known_limit_link_setting,
@@ -1104,12 +1219,14 @@ bool dp_verify_link_cap(
 	struct clock_source *dp_cs;
 	enum clock_source_id dp_cs_id = CLOCK_SOURCE_ID_EXTERNAL;
 	enum link_training_result status;
+	union hpd_irq_data irq_data;
 
 	if (link->dc->debug.skip_detection_link_training) {
 		link->verified_link_cap = *known_limit_link_setting;
 		return true;
 	}
 
+	memset(&irq_data, 0, sizeof(irq_data));
 	success = false;
 	skip_link_training = false;
 
@@ -1168,9 +1285,15 @@ bool dp_verify_link_cap(
 				(*fail_count)++;
 		}
 
-		if (success)
+		if (success) {
 			link->verified_link_cap = *cur;
-
+			udelay(1000);
+			if (read_hpd_rx_irq_data(link, &irq_data) == DC_OK)
+				if (hpd_rx_irq_check_link_loss_status(
+						link,
+						&irq_data))
+					(*fail_count)++;
+		}
 		/* always disable the link before trying another
 		 * setting or before returning we'll enable it later
 		 * based on the actual mode we're driving
@@ -1572,122 +1695,6 @@ void decide_link_settings(struct dc_stream_state *stream,
 }
 
 /*************************Short Pulse IRQ***************************/
-
-static bool hpd_rx_irq_check_link_loss_status(
-	struct dc_link *link,
-	union hpd_irq_data *hpd_irq_dpcd_data)
-{
-	uint8_t irq_reg_rx_power_state = 0;
-	enum dc_status dpcd_result = DC_ERROR_UNEXPECTED;
-	union lane_status lane_status;
-	uint32_t lane;
-	bool sink_status_changed;
-	bool return_code;
-
-	sink_status_changed = false;
-	return_code = false;
-
-	if (link->cur_link_settings.lane_count == 0)
-		return return_code;
-
-	/*1. Check that Link Status changed, before re-training.*/
-
-	/*parse lane status*/
-	for (lane = 0; lane < link->cur_link_settings.lane_count; lane++) {
-		/* check status of lanes 0,1
-		 * changed DpcdAddress_Lane01Status (0x202)
-		 */
-		lane_status.raw = get_nibble_at_index(
-			&hpd_irq_dpcd_data->bytes.lane01_status.raw,
-			lane);
-
-		if (!lane_status.bits.CHANNEL_EQ_DONE_0 ||
-			!lane_status.bits.CR_DONE_0 ||
-			!lane_status.bits.SYMBOL_LOCKED_0) {
-			/* if one of the channel equalization, clock
-			 * recovery or symbol lock is dropped
-			 * consider it as (link has been
-			 * dropped) dp sink status has changed
-			 */
-			sink_status_changed = true;
-			break;
-		}
-	}
-
-	/* Check interlane align.*/
-	if (sink_status_changed ||
-		!hpd_irq_dpcd_data->bytes.lane_status_updated.bits.INTERLANE_ALIGN_DONE) {
-
-		DC_LOG_HW_HPD_IRQ("%s: Link Status changed.\n", __func__);
-
-		return_code = true;
-
-		/*2. Check that we can handle interrupt: Not in FS DOS,
-		 *  Not in "Display Timeout" state, Link is trained.
-		 */
-		dpcd_result = core_link_read_dpcd(link,
-			DP_SET_POWER,
-			&irq_reg_rx_power_state,
-			sizeof(irq_reg_rx_power_state));
-
-		if (dpcd_result != DC_OK) {
-			DC_LOG_HW_HPD_IRQ("%s: DPCD read failed to obtain power state.\n",
-				__func__);
-		} else {
-			if (irq_reg_rx_power_state != DP_SET_POWER_D0)
-				return_code = false;
-		}
-	}
-
-	return return_code;
-}
-
-static enum dc_status read_hpd_rx_irq_data(
-	struct dc_link *link,
-	union hpd_irq_data *irq_data)
-{
-	static enum dc_status retval;
-
-	/* The HW reads 16 bytes from 200h on HPD,
-	 * but if we get an AUX_DEFER, the HW cannot retry
-	 * and this causes the CTS tests 4.3.2.1 - 3.2.4 to
-	 * fail, so we now explicitly read 6 bytes which is
-	 * the req from the above mentioned test cases.
-	 *
-	 * For DP 1.4 we need to read those from 2002h range.
-	 */
-	if (link->dpcd_caps.dpcd_rev.raw < DPCD_REV_14)
-		retval = core_link_read_dpcd(
-			link,
-			DP_SINK_COUNT,
-			irq_data->raw,
-			sizeof(union hpd_irq_data));
-	else {
-		/* Read 14 bytes in a single read and then copy only the required fields.
-		 * This is more efficient than doing it in two separate AUX reads. */
-
-		uint8_t tmp[DP_SINK_STATUS_ESI - DP_SINK_COUNT_ESI + 1];
-
-		retval = core_link_read_dpcd(
-			link,
-			DP_SINK_COUNT_ESI,
-			tmp,
-			sizeof(tmp));
-
-		if (retval != DC_OK)
-			return retval;
-
-		irq_data->bytes.sink_cnt.raw = tmp[DP_SINK_COUNT_ESI - DP_SINK_COUNT_ESI];
-		irq_data->bytes.device_service_irq.raw = tmp[DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0 - DP_SINK_COUNT_ESI];
-		irq_data->bytes.lane01_status.raw = tmp[DP_LANE0_1_STATUS_ESI - DP_SINK_COUNT_ESI];
-		irq_data->bytes.lane23_status.raw = tmp[DP_LANE2_3_STATUS_ESI - DP_SINK_COUNT_ESI];
-		irq_data->bytes.lane_status_updated.raw = tmp[DP_LANE_ALIGN_STATUS_UPDATED_ESI - DP_SINK_COUNT_ESI];
-		irq_data->bytes.sink_status.raw = tmp[DP_SINK_STATUS_ESI - DP_SINK_COUNT_ESI];
-	}
-
-	return retval;
-}
-
 static bool allow_hpd_rx_irq(const struct dc_link *link)
 {
 	/*
@@ -2240,7 +2247,8 @@ static void get_active_converter_info(
 					translate_dpcd_max_bpc(
 						hdmi_color_caps.bits.MAX_BITS_PER_COLOR_COMPONENT);
 
-				link->dpcd_caps.dongle_caps.extendedCapValid = true;
+				if (link->dpcd_caps.dongle_caps.dp_hdmi_max_pixel_clk != 0)
+					link->dpcd_caps.dongle_caps.extendedCapValid = true;
 			}
 
 			break;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
index 82cd1d6e6e59..0065ec7d5330 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
@@ -96,6 +96,7 @@ void dp_enable_link_phy(
 						link_settings,
 						clock_source);
 	}
+	link->cur_link_settings = *link_settings;
 
 	dp_receiver_power_ctrl(link, true);
 }
@@ -307,6 +308,7 @@ void dp_retrain_link_dp_test(struct dc_link *link,
 						link->link_enc,
 						link_setting,
 						pipes[i].clock_source->id);
+			link->cur_link_settings = *link_setting;
 
 			dp_receiver_power_ctrl(link, true);
 
@@ -316,7 +318,6 @@ void dp_retrain_link_dp_test(struct dc_link *link,
 					skip_video_pattern,
 					LINK_TRAINING_ATTEMPTS);
 
-			link->cur_link_settings = *link_setting;
 
 			link->dc->hwss.enable_stream(&pipes[i]);
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index c347afd1030f..76137df74a53 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -83,7 +83,10 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id)
 			dc_version = DCE_VERSION_11_22;
 		break;
 	case FAMILY_AI:
-		dc_version = DCE_VERSION_12_0;
+		if (ASICREV_IS_VEGA20_P(asic_id.hw_internal_rev))
+			dc_version = DCE_VERSION_12_1;
+		else
+			dc_version = DCE_VERSION_12_0;
 		break;
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
 	case FAMILY_RV:
@@ -136,6 +139,7 @@ struct resource_pool *dc_create_resource_pool(
 			num_virtual_links, dc);
 		break;
 	case DCE_VERSION_12_0:
+	case DCE_VERSION_12_1:
 		res_pool = dce120_create_resource_pool(
 			num_virtual_links, dc);
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c
index fcfd50b5dba0..4842d2378bbf 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c
@@ -234,14 +234,14 @@ uint32_t generic_reg_wait(const struct dc_context *ctx,
 		if (field_value == condition_value) {
 			if (i * delay_between_poll_us > 1000 &&
 					!IS_FPGA_MAXIMUS_DC(ctx->dce_environment))
-				dm_output_to_console("REG_WAIT taking a while: %dms in %s line:%d\n",
+				DC_LOG_DC("REG_WAIT taking a while: %dms in %s line:%d\n",
 						delay_between_poll_us * i / 1000,
 						func_name, line);
 			return reg_val;
 		}
 	}
 
-	dm_error("REG_WAIT timeout %dus * %d tries - %s line:%d\n",
+	DC_LOG_WARNING("REG_WAIT timeout %dus * %d tries - %s line:%d\n",
 			delay_between_poll_us, time_out_num_tries,
 			func_name, line);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index 9ddfe4c6938b..e72fce4eca65 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -192,7 +192,6 @@ enum surface_pixel_format {
 	/*swaped & float*/
 	SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F,
 	/*grow graphics here if necessary */
-	SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888,
 	SURFACE_PIXEL_FORMAT_VIDEO_BEGIN,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_YCbCr =
 		SURFACE_PIXEL_FORMAT_VIDEO_BEGIN,
@@ -200,6 +199,7 @@ enum surface_pixel_format {
 	SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb,
 		SURFACE_PIXEL_FORMAT_SUBSAMPLE_END,
+	SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888,
 	SURFACE_PIXEL_FORMAT_INVALID
 
 	/*grow 444 video here if necessary */
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c
index bd22f51813bf..afd287f08bc9 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c
@@ -676,6 +676,11 @@ static void dce112_update_clocks(struct clk_mgr *clk_mgr,
 {
 	struct dce_clk_mgr *clk_mgr_dce = TO_DCE_CLK_MGR(clk_mgr);
 	struct dm_pp_power_level_change_request level_change_req;
+	int unpatched_disp_clk = context->bw.dce.dispclk_khz;
+
+	/*TODO: W/A for dal3 linux, investigate why this works */
+	if (!clk_mgr_dce->dfs_bypass_active)
+		context->bw.dce.dispclk_khz = context->bw.dce.dispclk_khz * 115 / 100;
 
 	level_change_req.power_level = dce_get_required_clocks_state(clk_mgr, context);
 	/* get max clock state from PPLIB */
@@ -690,6 +695,8 @@ static void dce112_update_clocks(struct clk_mgr *clk_mgr,
 		clk_mgr->clks.dispclk_khz = context->bw.dce.dispclk_khz;
 	}
 	dce11_pplib_apply_display_requirements(clk_mgr->ctx->dc, context);
+
+	context->bw.dce.dispclk_khz = unpatched_disp_clk;
 }
 
 static void dce12_update_clocks(struct clk_mgr *clk_mgr,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 6349ba7bec7c..4bf24758217f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -1267,10 +1267,19 @@ static void program_scaler(const struct dc *dc,
 		pipe_ctx->plane_res.scl_data.lb_params.depth,
 		&pipe_ctx->stream->bit_depth_params);
 
-	if (pipe_ctx->stream_res.tg->funcs->set_overscan_blank_color)
+	if (pipe_ctx->stream_res.tg->funcs->set_overscan_blank_color) {
+		/*
+		 * The way 420 is packed, 2 channels carry Y component, 1 channel
+		 * alternate between Cb and Cr, so both channels need the pixel
+		 * value for Y
+		 */
+		if (pipe_ctx->stream->timing.pixel_encoding == PIXEL_ENCODING_YCBCR420)
+			color.color_r_cr = color.color_g_y;
+
 		pipe_ctx->stream_res.tg->funcs->set_overscan_blank_color(
 				pipe_ctx->stream_res.tg,
 				&color);
+	}
 
 	pipe_ctx->plane_res.xfm->funcs->transform_set_scaler(pipe_ctx->plane_res.xfm,
 		&pipe_ctx->plane_res.scl_data);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 0bd33a713836..91e015e14355 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2159,6 +2159,15 @@ static void dcn10_blank_pixel_data(
 	color_space = stream->output_color_space;
 	color_space_to_black_color(dc, color_space, &black_color);
 
+	/*
+	 * The way 420 is packed, 2 channels carry Y component, 1 channel
+	 * alternate between Cb and Cr, so both channels need the pixel
+	 * value for Y
+	 */
+	if (stream->timing.pixel_encoding == PIXEL_ENCODING_YCBCR420)
+		black_color.color_r_cr = black_color.color_g_y;
+
+
 	if (stream_res->tg->funcs->set_blank_color)
 		stream_res->tg->funcs->set_blank_color(
 				stream_res->tg,
@@ -2348,7 +2357,8 @@ static void dcn10_apply_ctx_for_surface(
 			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 
 			/* Skip inactive pipes and ones already updated */
-			if (!pipe_ctx->stream || pipe_ctx->stream == stream)
+			if (!pipe_ctx->stream || pipe_ctx->stream == stream
+					|| !pipe_ctx->plane_state)
 				continue;
 
 			pipe_ctx->stream_res.tg->funcs->lock(pipe_ctx->stream_res.tg);
@@ -2362,7 +2372,8 @@ static void dcn10_apply_ctx_for_surface(
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 
-		if (!pipe_ctx->stream || pipe_ctx->stream == stream)
+		if (!pipe_ctx->stream || pipe_ctx->stream == stream
+				|| !pipe_ctx->plane_state)
 			continue;
 
 		dcn10_pipe_control_lock(dc, pipe_ctx, false);
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
index a683f4102e65..c2028c4744a6 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
@@ -79,6 +79,7 @@ bool dal_hw_factory_init(
 		dal_hw_factory_dce110_init(factory);
 		return true;
 	case DCE_VERSION_12_0:
+	case DCE_VERSION_12_1:
 		dal_hw_factory_dce120_init(factory);
 		return true;
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
index 096f45628630..236ca28784a9 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
@@ -76,6 +76,7 @@ bool dal_hw_translate_init(
 		dal_hw_translate_dce110_init(translate);
 		return true;
 	case DCE_VERSION_12_0:
+	case DCE_VERSION_12_1:
 		dal_hw_translate_dce120_init(translate);
 		return true;
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c b/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
index e56093f26eed..1ad6e49102ff 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
@@ -90,6 +90,7 @@ struct i2caux *dal_i2caux_create(
 	case DCE_VERSION_10_0:
 		return dal_i2caux_dce100_create(ctx);
 	case DCE_VERSION_12_0:
+	case DCE_VERSION_12_1:
 		return dal_i2caux_dce120_create(ctx);
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
 	case DCN_VERSION_1_0:
diff --git a/drivers/gpu/drm/amd/display/include/bios_parser_types.h b/drivers/gpu/drm/amd/display/include/bios_parser_types.h
index f8dbfa5b89f2..7fd78a696800 100644
--- a/drivers/gpu/drm/amd/display/include/bios_parser_types.h
+++ b/drivers/gpu/drm/amd/display/include/bios_parser_types.h
@@ -41,6 +41,7 @@ enum as_signal_type {
 	AS_SIGNAL_TYPE_LVDS,
 	AS_SIGNAL_TYPE_DISPLAY_PORT,
 	AS_SIGNAL_TYPE_GPU_PLL,
+	AS_SIGNAL_TYPE_XGMI,
 	AS_SIGNAL_TYPE_UNKNOWN
 };
 
diff --git a/drivers/gpu/drm/amd/display/include/dal_types.h b/drivers/gpu/drm/amd/display/include/dal_types.h
index 89627133e188..f5bd869d4320 100644
--- a/drivers/gpu/drm/amd/display/include/dal_types.h
+++ b/drivers/gpu/drm/amd/display/include/dal_types.h
@@ -42,6 +42,7 @@ enum dce_version {
 	DCE_VERSION_11_2,
 	DCE_VERSION_11_22,
 	DCE_VERSION_12_0,
+	DCE_VERSION_12_1,
 	DCE_VERSION_MAX,
 	DCN_VERSION_1_0,
 #if defined(CONFIG_DRM_AMD_DC_DCN1_01)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
index 2e99ecf4ab76..26154f9b2178 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
@@ -49,6 +49,10 @@
 #include "soc15_common.h"
 #include "smuio/smuio_9_0_offset.h"
 #include "smuio/smuio_9_0_sh_mask.h"
+#include "nbio/nbio_7_4_sh_mask.h"
+
+#define smnPCIE_LC_SPEED_CNTL			0x11140290
+#define smnPCIE_LC_LINK_WIDTH_CNTL		0x11140288
 
 static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr)
 {
@@ -2282,6 +2286,18 @@ static int vega20_force_clock_level(struct pp_hwmgr *hwmgr,
 		break;
 
 	case PP_PCIE:
+		soft_min_level = mask ? (ffs(mask) - 1) : 0;
+		soft_max_level = mask ? (fls(mask) - 1) : 0;
+		if (soft_min_level >= NUM_LINK_LEVELS ||
+		    soft_max_level >= NUM_LINK_LEVELS)
+			return -EINVAL;
+
+		ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_SetMinLinkDpmByIndex, soft_min_level);
+		PP_ASSERT_WITH_CODE(!ret,
+			"Failed to set min link dpm level!",
+			return ret);
+
 		break;
 
 	default:
@@ -2758,9 +2774,14 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 			data->od8_settings.od8_settings_array;
 	OverDriveTable_t *od_table =
 			&(data->smc_state_table.overdrive_table);
+	struct phm_ppt_v3_information *pptable_information =
+		(struct phm_ppt_v3_information *)hwmgr->pptable;
+	PPTable_t *pptable = (PPTable_t *)pptable_information->smc_pptable;
+	struct amdgpu_device *adev = hwmgr->adev;
 	struct pp_clock_levels_with_latency clocks;
 	int i, now, size = 0;
 	int ret = 0;
+	uint32_t gen_speed, lane_width;
 
 	switch (type) {
 	case PP_SCLK:
@@ -2798,6 +2819,28 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 
 	case PP_PCIE:
+		gen_speed = (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) &
+			     PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK)
+			    >> PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT;
+		lane_width = (RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL) &
+			      PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK)
+			    >> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT;
+		for (i = 0; i < NUM_LINK_LEVELS; i++)
+			size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i,
+					(pptable->PcieGenSpeed[i] == 0) ? "2.5GT/s," :
+					(pptable->PcieGenSpeed[i] == 1) ? "5.0GT/s," :
+					(pptable->PcieGenSpeed[i] == 2) ? "8.0GT/s," :
+					(pptable->PcieGenSpeed[i] == 3) ? "16.0GT/s," : "",
+					(pptable->PcieLaneCount[i] == 1) ? "x1" :
+					(pptable->PcieLaneCount[i] == 2) ? "x2" :
+					(pptable->PcieLaneCount[i] == 3) ? "x4" :
+					(pptable->PcieLaneCount[i] == 4) ? "x8" :
+					(pptable->PcieLaneCount[i] == 5) ? "x12" :
+					(pptable->PcieLaneCount[i] == 6) ? "x16" : "",
+					pptable->LclkFreq[i],
+					(gen_speed == pptable->PcieGenSpeed[i]) &&
+					(lane_width == pptable->PcieLaneCount[i]) ?
+					"*" : "");
 		break;
 
 	case OD_SCLK:
diff --git a/drivers/gpu/drm/drm_atomic_state_helper.c b/drivers/gpu/drm/drm_atomic_state_helper.c
index 60bd7d708e35..4985384e51f6 100644
--- a/drivers/gpu/drm/drm_atomic_state_helper.c
+++ b/drivers/gpu/drm/drm_atomic_state_helper.c
@@ -241,6 +241,7 @@ void __drm_atomic_helper_plane_duplicate_state(struct drm_plane *plane,
 
 	state->fence = NULL;
 	state->commit = NULL;
+	state->fb_damage_clips = NULL;
 }
 EXPORT_SYMBOL(__drm_atomic_helper_plane_duplicate_state);
 
@@ -285,6 +286,8 @@ void __drm_atomic_helper_plane_destroy_state(struct drm_plane_state *state)
 
 	if (state->commit)
 		drm_crtc_commit_put(state->commit);
+
+	drm_property_blob_put(state->fb_damage_clips);
 }
 EXPORT_SYMBOL(__drm_atomic_helper_plane_destroy_state);
 
diff --git a/drivers/gpu/drm/drm_damage_helper.c b/drivers/gpu/drm/drm_damage_helper.c
index d2a1c7372f36..31032407254d 100644
--- a/drivers/gpu/drm/drm_damage_helper.c
+++ b/drivers/gpu/drm/drm_damage_helper.c
@@ -178,7 +178,7 @@ int drm_atomic_helper_dirtyfb(struct drm_framebuffer *fb,
 	state = drm_atomic_state_alloc(fb->dev);
 	if (!state) {
 		ret = -ENOMEM;
-		goto out;
+		goto out_drop_locks;
 	}
 	state->acquire_ctx = &ctx;
 
@@ -238,6 +238,7 @@ out:
 	kfree(rects);
 	drm_atomic_state_put(state);
 
+out_drop_locks:
 	drm_modeset_drop_locks(&ctx);
 	drm_modeset_acquire_fini(&ctx);
 
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 77edbfcb0f75..77ae634eb11c 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -1900,11 +1900,11 @@ static struct cmd_info cmd_info[] = {
 
 	{"MI_URB_CLEAR", OP_MI_URB_CLEAR, F_LEN_VAR, R_RCS, D_ALL, 0, 8, NULL},
 
-	{"ME_SEMAPHORE_SIGNAL", OP_MI_SEMAPHORE_SIGNAL, F_LEN_VAR, R_ALL,
+	{"MI_SEMAPHORE_SIGNAL", OP_MI_SEMAPHORE_SIGNAL, F_LEN_VAR, R_ALL,
 		D_BDW_PLUS, 0, 8, NULL},
 
-	{"ME_SEMAPHORE_WAIT", OP_MI_SEMAPHORE_WAIT, F_LEN_VAR, R_ALL, D_BDW_PLUS,
-		ADDR_FIX_1(2), 8, cmd_handler_mi_semaphore_wait},
+	{"MI_SEMAPHORE_WAIT", OP_MI_SEMAPHORE_WAIT, F_LEN_VAR, R_ALL,
+		D_BDW_PLUS, ADDR_FIX_1(2), 8, cmd_handler_mi_semaphore_wait},
 
 	{"MI_STORE_DATA_IMM", OP_MI_STORE_DATA_IMM, F_LEN_VAR, R_ALL, D_BDW_PLUS,
 		ADDR_FIX_1(1), 10, cmd_handler_mi_store_data_imm},
diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c
index 6ef5a7fc70df..733a2a0d0c30 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.c
+++ b/drivers/gpu/drm/i915/gvt/gvt.c
@@ -437,7 +437,7 @@ int intel_gvt_init_device(struct drm_i915_private *dev_priv)
 
 	ret = intel_gvt_debugfs_init(gvt);
 	if (ret)
-		gvt_err("debugfs registeration failed, go on.\n");
+		gvt_err("debugfs registration failed, go on.\n");
 
 	gvt_dbg_core("gvt device initialization is done\n");
 	dev_priv->gvt = gvt;
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 31f6cdbe5c42..b4ab1dad0143 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -159,6 +159,10 @@ struct intel_vgpu_submission {
 	struct kmem_cache *workloads;
 	atomic_t running_workload_num;
 	struct i915_gem_context *shadow_ctx;
+	union {
+		u64 i915_context_pml4;
+		u64 i915_context_pdps[GEN8_3LVL_PDPES];
+	};
 	DECLARE_BITMAP(shadow_ctx_desc_updated, I915_NUM_ENGINES);
 	DECLARE_BITMAP(tlb_handle_pending, I915_NUM_ENGINES);
 	void *ring_scan_buffer[I915_NUM_ENGINES];
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index aa280bb07125..b5475c91e2ef 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -475,6 +475,7 @@ static i915_reg_t force_nonpriv_white_list[] = {
 	_MMIO(0x7704),
 	_MMIO(0x7708),
 	_MMIO(0x770c),
+	_MMIO(0x83a8),
 	_MMIO(0xb110),
 	GEN8_L3SQCREG4,//_MMIO(0xb118)
 	_MMIO(0xe100),
diff --git a/drivers/gpu/drm/i915/gvt/interrupt.c b/drivers/gpu/drm/i915/gvt/interrupt.c
index 5daa23ae566b..6b9d1354ff29 100644
--- a/drivers/gpu/drm/i915/gvt/interrupt.c
+++ b/drivers/gpu/drm/i915/gvt/interrupt.c
@@ -126,7 +126,7 @@ static const char * const irq_name[INTEL_GVT_EVENT_MAX] = {
 	[FDI_RX_INTERRUPTS_TRANSCODER_C] = "FDI RX Interrupts Combined C",
 	[AUDIO_CP_CHANGE_TRANSCODER_C] = "Audio CP Change Transcoder C",
 	[AUDIO_CP_REQUEST_TRANSCODER_C] = "Audio CP Request Transcoder C",
-	[ERR_AND_DBG] = "South Error and Debug Interupts Combined",
+	[ERR_AND_DBG] = "South Error and Debug Interrupts Combined",
 	[GMBUS] = "Gmbus",
 	[SDVO_B_HOTPLUG] = "SDVO B hotplug",
 	[CRT_HOTPLUG] = "CRT Hotplug",
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index b8fbe3fabea3..1ad8c5e1455d 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -1079,6 +1079,21 @@ err:
 	return ret;
 }
 
+static void
+i915_context_ppgtt_root_restore(struct intel_vgpu_submission *s)
+{
+	struct i915_hw_ppgtt *i915_ppgtt = s->shadow_ctx->ppgtt;
+	int i;
+
+	if (i915_vm_is_48bit(&i915_ppgtt->vm))
+		px_dma(&i915_ppgtt->pml4) = s->i915_context_pml4;
+	else {
+		for (i = 0; i < GEN8_3LVL_PDPES; i++)
+			px_dma(i915_ppgtt->pdp.page_directory[i]) =
+						s->i915_context_pdps[i];
+	}
+}
+
 /**
  * intel_vgpu_clean_submission - free submission-related resource for vGPU
  * @vgpu: a vGPU
@@ -1091,6 +1106,7 @@ void intel_vgpu_clean_submission(struct intel_vgpu *vgpu)
 	struct intel_vgpu_submission *s = &vgpu->submission;
 
 	intel_vgpu_select_submission_ops(vgpu, ALL_ENGINES, 0);
+	i915_context_ppgtt_root_restore(s);
 	i915_gem_context_put(s->shadow_ctx);
 	kmem_cache_destroy(s->workloads);
 }
@@ -1116,6 +1132,21 @@ void intel_vgpu_reset_submission(struct intel_vgpu *vgpu,
 	s->ops->reset(vgpu, engine_mask);
 }
 
+static void
+i915_context_ppgtt_root_save(struct intel_vgpu_submission *s)
+{
+	struct i915_hw_ppgtt *i915_ppgtt = s->shadow_ctx->ppgtt;
+	int i;
+
+	if (i915_vm_is_48bit(&i915_ppgtt->vm))
+		s->i915_context_pml4 = px_dma(&i915_ppgtt->pml4);
+	else {
+		for (i = 0; i < GEN8_3LVL_PDPES; i++)
+			s->i915_context_pdps[i] =
+				px_dma(i915_ppgtt->pdp.page_directory[i]);
+	}
+}
+
 /**
  * intel_vgpu_setup_submission - setup submission-related resource for vGPU
  * @vgpu: a vGPU
@@ -1138,6 +1169,8 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu)
 	if (IS_ERR(s->shadow_ctx))
 		return PTR_ERR(s->shadow_ctx);
 
+	i915_context_ppgtt_root_save(s);
+
 	bitmap_zero(s->shadow_ctx_desc_updated, I915_NUM_ENGINES);
 
 	s->workloads = kmem_cache_create_usercopy("gvt-g_vgpu_workload",
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index d87935bf8e30..0ec08394e17a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -77,38 +77,39 @@ static inline int ttm_mem_type_from_place(const struct ttm_place *place,
 	return 0;
 }
 
-static void ttm_mem_type_debug(struct ttm_bo_device *bdev, int mem_type)
+static void ttm_mem_type_debug(struct ttm_bo_device *bdev, struct drm_printer *p,
+			       int mem_type)
 {
 	struct ttm_mem_type_manager *man = &bdev->man[mem_type];
-	struct drm_printer p = drm_debug_printer(TTM_PFX);
 
-	pr_err("    has_type: %d\n", man->has_type);
-	pr_err("    use_type: %d\n", man->use_type);
-	pr_err("    flags: 0x%08X\n", man->flags);
-	pr_err("    gpu_offset: 0x%08llX\n", man->gpu_offset);
-	pr_err("    size: %llu\n", man->size);
-	pr_err("    available_caching: 0x%08X\n", man->available_caching);
-	pr_err("    default_caching: 0x%08X\n", man->default_caching);
+	drm_printf(p, "    has_type: %d\n", man->has_type);
+	drm_printf(p, "    use_type: %d\n", man->use_type);
+	drm_printf(p, "    flags: 0x%08X\n", man->flags);
+	drm_printf(p, "    gpu_offset: 0x%08llX\n", man->gpu_offset);
+	drm_printf(p, "    size: %llu\n", man->size);
+	drm_printf(p, "    available_caching: 0x%08X\n", man->available_caching);
+	drm_printf(p, "    default_caching: 0x%08X\n", man->default_caching);
 	if (mem_type != TTM_PL_SYSTEM)
-		(*man->func->debug)(man, &p);
+		(*man->func->debug)(man, p);
 }
 
 static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo,
 					struct ttm_placement *placement)
 {
+	struct drm_printer p = drm_debug_printer(TTM_PFX);
 	int i, ret, mem_type;
 
-	pr_err("No space for %p (%lu pages, %luK, %luM)\n",
-	       bo, bo->mem.num_pages, bo->mem.size >> 10,
-	       bo->mem.size >> 20);
+	drm_printf(&p, "No space for %p (%lu pages, %luK, %luM)\n",
+		   bo, bo->mem.num_pages, bo->mem.size >> 10,
+		   bo->mem.size >> 20);
 	for (i = 0; i < placement->num_placement; i++) {
 		ret = ttm_mem_type_from_place(&placement->placement[i],
 						&mem_type);
 		if (ret)
 			return;
-		pr_err("  placement[%d]=0x%08X (%d)\n",
-		       i, placement->placement[i].flags, mem_type);
-		ttm_mem_type_debug(bo->bdev, mem_type);
+		drm_printf(&p, "  placement[%d]=0x%08X (%d)\n",
+			   i, placement->placement[i].flags, mem_type);
+		ttm_mem_type_debug(bo->bdev, &p, mem_type);
 	}
 }