Merge tag 'amd-drm-fixes-6.9-2024-03-27' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-6.9-2024-03-27:

amdgpu:
- SMU 14.0.1 updates
- DCN 3.5.x updates
- VPE fix
- eDP panel flickering fix
- Suspend fix
- PSR fix
- DCN 3.0+ fix
- VCN 4.0.6 updates
- debugfs fix

amdkfd:
- DMA-Buf fix
- GFX 9.4.2 TLB flush fix
- CP interrupt fix

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240328025342.8700-1-alexander.deucher@amd.com

36 files changed, 342 insertions, 275 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5dc24c971b41f0..aa16d51dd8421b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4539,6 +4539,8 @@ int amdgpu_device_prepare(struct drm_device *dev)
 	if (r)
 		goto unprepare;
 
+	flush_delayed_work(&adev->gfx.gfx_off_delay_work);
+
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index a07e4b87d4cae0..fdd36fb027ab6a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -2237,6 +2237,7 @@ static int amdgpu_discovery_set_umsch_mm_ip_blocks(struct amdgpu_device *adev)
 {
 	switch (amdgpu_ip_version(adev, VCN_HWIP, 0)) {
 	case IP_VERSION(4, 0, 5):
+	case IP_VERSION(4, 0, 6):
 		if (amdgpu_umsch_mm & 0x1) {
 			amdgpu_device_ip_block_add(adev, &umsch_mm_v4_0_ip_block);
 			adev->enable_umsch_mm = true;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 5505d646f43aa8..06f0a6534a94f7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -524,46 +524,58 @@ static ssize_t amdgpu_debugfs_mqd_read(struct file *f, char __user *buf,
 {
 	struct amdgpu_ring *ring = file_inode(f)->i_private;
 	volatile u32 *mqd;
-	int r;
+	u32 *kbuf;
+	int r, i;
 	uint32_t value, result;
 
 	if (*pos & 3 || size & 3)
 		return -EINVAL;
 
-	result = 0;
+	kbuf = kmalloc(ring->mqd_size, GFP_KERNEL);
+	if (!kbuf)
+		return -ENOMEM;
 
 	r = amdgpu_bo_reserve(ring->mqd_obj, false);
 	if (unlikely(r != 0))
-		return r;
+		goto err_free;
 
 	r = amdgpu_bo_kmap(ring->mqd_obj, (void **)&mqd);
-	if (r) {
-		amdgpu_bo_unreserve(ring->mqd_obj);
-		return r;
-	}
+	if (r)
+		goto err_unreserve;
 
+	/*
+	 * Copy to local buffer to avoid put_user(), which might fault
+	 * and acquire mmap_sem, under reservation_ww_class_mutex.
+	 */
+	for (i = 0; i < ring->mqd_size/sizeof(u32); i++)
+		kbuf[i] = mqd[i];
+
+	amdgpu_bo_kunmap(ring->mqd_obj);
+	amdgpu_bo_unreserve(ring->mqd_obj);
+
+	result = 0;
 	while (size) {
 		if (*pos >= ring->mqd_size)
-			goto done;
+			break;
 
-		value = mqd[*pos/4];
+		value = kbuf[*pos/4];
 		r = put_user(value, (uint32_t *)buf);
 		if (r)
-			goto done;
+			goto err_free;
 		buf += 4;
 		result += 4;
 		size -= 4;
 		*pos += 4;
 	}
 
-done:
-	amdgpu_bo_kunmap(ring->mqd_obj);
-	mqd = NULL;
-	amdgpu_bo_unreserve(ring->mqd_obj);
-	if (r)
-		return r;
-
+	kfree(kbuf);
 	return result;
+
+err_unreserve:
+	amdgpu_bo_unreserve(ring->mqd_obj);
+err_free:
+	kfree(kbuf);
+	return r;
 }
 
 static const struct file_operations amdgpu_debugfs_mqd_fops = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
index ab820cf526683b..0df97c3e3a700d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
@@ -189,10 +189,13 @@ static void setup_vpe_queue(struct amdgpu_device *adev,
 	mqd->rptr_val = 0;
 	mqd->unmapped = 1;
 
+	if (adev->vpe.collaborate_mode)
+		memcpy(++mqd, test->mqd_data_cpu_addr, sizeof(struct MQD_INFO));
+
 	qinfo->mqd_addr = test->mqd_data_gpu_addr;
 	qinfo->csa_addr = test->ctx_data_gpu_addr +
 		offsetof(struct umsch_mm_test_ctx_data, vpe_ctx_csa);
-	qinfo->doorbell_offset_0 = (adev->doorbell_index.vpe_ring + 1) << 1;
+	qinfo->doorbell_offset_0 = 0;
 	qinfo->doorbell_offset_1 = 0;
 }
 
@@ -287,7 +290,10 @@ static int submit_vpe_queue(struct amdgpu_device *adev, struct umsch_mm_test *te
 	ring[5] = 0;
 
 	mqd->wptr_val = (6 << 2);
-	// WDOORBELL32(adev->umsch_mm.agdb_index[CONTEXT_PRIORITY_LEVEL_NORMAL], mqd->wptr_val);
+	if (adev->vpe.collaborate_mode)
+		(++mqd)->wptr_val = (6 << 2);
+
+	WDOORBELL32(adev->umsch_mm.agdb_index[CONTEXT_PRIORITY_LEVEL_NORMAL], mqd->wptr_val);
 
 	for (i = 0; i < adev->usec_timeout; i++) {
 		if (*fence == test_pattern)
@@ -571,6 +577,7 @@ int amdgpu_umsch_mm_init_microcode(struct amdgpu_umsch_mm *umsch)
 
 	switch (amdgpu_ip_version(adev, VCN_HWIP, 0)) {
 	case IP_VERSION(4, 0, 5):
+	case IP_VERSION(4, 0, 6):
 		fw_name = "amdgpu/umsch_mm_4_0_0.bin";
 		break;
 	default:
@@ -750,6 +757,7 @@ static int umsch_mm_early_init(void *handle)
 
 	switch (amdgpu_ip_version(adev, VCN_HWIP, 0)) {
 	case IP_VERSION(4, 0, 5):
+	case IP_VERSION(4, 0, 6):
 		umsch_mm_v4_0_set_funcs(&adev->umsch_mm);
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.h
index 8258a43a6236c0..5014b5af95fd97 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.h
@@ -33,13 +33,6 @@ enum UMSCH_SWIP_ENGINE_TYPE {
 	UMSCH_SWIP_ENGINE_TYPE_MAX
 };
 
-enum UMSCH_SWIP_AFFINITY_TYPE {
-	UMSCH_SWIP_AFFINITY_TYPE_ANY = 0,
-	UMSCH_SWIP_AFFINITY_TYPE_VCN0 = 1,
-	UMSCH_SWIP_AFFINITY_TYPE_VCN1 = 2,
-	UMSCH_SWIP_AFFINITY_TYPE_MAX
-};
-
 enum UMSCH_CONTEXT_PRIORITY_LEVEL {
 	CONTEXT_PRIORITY_LEVEL_IDLE = 0,
 	CONTEXT_PRIORITY_LEVEL_NORMAL = 1,
@@ -51,13 +44,15 @@ enum UMSCH_CONTEXT_PRIORITY_LEVEL {
 struct umsch_mm_set_resource_input {
 	uint32_t vmid_mask_mm_vcn;
 	uint32_t vmid_mask_mm_vpe;
+	uint32_t collaboration_mask_vpe;
 	uint32_t logging_vmid;
 	uint32_t engine_mask;
 	union {
 		struct {
 			uint32_t disable_reset : 1;
 			uint32_t disable_umsch_mm_log : 1;
-			uint32_t reserved : 30;
+			uint32_t use_rs64mem_for_proc_ctx_csa : 1;
+			uint32_t reserved : 29;
 		};
 		uint32_t uint32_all;
 	};
@@ -78,15 +73,18 @@ struct umsch_mm_add_queue_input {
 	uint32_t doorbell_offset_1;
 	enum UMSCH_SWIP_ENGINE_TYPE engine_type;
 	uint32_t affinity;
-	enum UMSCH_SWIP_AFFINITY_TYPE affinity_type;
 	uint64_t mqd_addr;
 	uint64_t h_context;
 	uint64_t h_queue;
 	uint32_t vm_context_cntl;
 
+	uint32_t process_csa_array_index;
+	uint32_t context_csa_array_index;
+
 	struct {
 		uint32_t is_context_suspended : 1;
-		uint32_t reserved : 31;
+		uint32_t collaboration_mode : 1;
+		uint32_t reserved : 30;
 	};
 };
 
@@ -94,6 +92,7 @@ struct umsch_mm_remove_queue_input {
 	uint32_t doorbell_offset_0;
 	uint32_t doorbell_offset_1;
 	uint64_t context_csa_addr;
+	uint32_t context_csa_array_index;
 };
 
 struct MQD_INFO {
@@ -103,6 +102,7 @@ struct MQD_INFO {
 	uint32_t wptr_val;
 	uint32_t rptr_val;
 	uint32_t unmapped;
+	uint32_t vmid;
 };
 
 struct amdgpu_umsch_mm;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
index 7a65a2b128ec43..6695481f870f8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
@@ -396,6 +396,12 @@ static int vpe_hw_init(void *handle)
 	struct amdgpu_vpe *vpe = &adev->vpe;
 	int ret;
 
+	/* Power on VPE */
+	ret = amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VPE,
+						     AMD_PG_STATE_UNGATE);
+	if (ret)
+		return ret;
+
 	ret = vpe_load_microcode(vpe);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c b/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
index 8e7b763cfdb7ef..84368cf1e17535 100644
--- a/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
@@ -60,7 +60,7 @@ static int umsch_mm_v4_0_load_microcode(struct amdgpu_umsch_mm *umsch)
 
 	umsch->cmd_buf_curr_ptr = umsch->cmd_buf_ptr;
 
-	if (amdgpu_ip_version(adev, VCN_HWIP, 0) == IP_VERSION(4, 0, 5)) {
+	if (amdgpu_ip_version(adev, VCN_HWIP, 0) >= IP_VERSION(4, 0, 5)) {
 		WREG32_SOC15(VCN, 0, regUVD_IPX_DLDO_CONFIG,
 			1 << UVD_IPX_DLDO_CONFIG__ONO0_PWR_CONFIG__SHIFT);
 		SOC15_WAIT_ON_RREG(VCN, 0, regUVD_IPX_DLDO_STATUS,
@@ -248,7 +248,7 @@ static int umsch_mm_v4_0_ring_stop(struct amdgpu_umsch_mm *umsch)
 	data = REG_SET_FIELD(data, VCN_UMSCH_RB_DB_CTRL, EN, 0);
 	WREG32_SOC15(VCN, 0, regVCN_UMSCH_RB_DB_CTRL, data);
 
-	if (amdgpu_ip_version(adev, VCN_HWIP, 0) == IP_VERSION(4, 0, 5)) {
+	if (amdgpu_ip_version(adev, VCN_HWIP, 0) >= IP_VERSION(4, 0, 5)) {
 		WREG32_SOC15(VCN, 0, regUVD_IPX_DLDO_CONFIG,
 			2 << UVD_IPX_DLDO_CONFIG__ONO0_PWR_CONFIG__SHIFT);
 		SOC15_WAIT_ON_RREG(VCN, 0, regUVD_IPX_DLDO_STATUS,
@@ -271,6 +271,8 @@ static int umsch_mm_v4_0_set_hw_resources(struct amdgpu_umsch_mm *umsch)
 
 	set_hw_resources.vmid_mask_mm_vcn = umsch->vmid_mask_mm_vcn;
 	set_hw_resources.vmid_mask_mm_vpe = umsch->vmid_mask_mm_vpe;
+	set_hw_resources.collaboration_mask_vpe =
+		adev->vpe.collaborate_mode ? 0x3 : 0x0;
 	set_hw_resources.engine_mask = umsch->engine_mask;
 
 	set_hw_resources.vcn0_hqd_mask[0] = umsch->vcn0_hqd_mask;
@@ -346,6 +348,7 @@ static int umsch_mm_v4_0_add_queue(struct amdgpu_umsch_mm *umsch,
 	add_queue.h_queue = input_ptr->h_queue;
 	add_queue.vm_context_cntl = input_ptr->vm_context_cntl;
 	add_queue.is_context_suspended = input_ptr->is_context_suspended;
+	add_queue.collaboration_mode = adev->vpe.collaborate_mode ? 1 : 0;
 
 	add_queue.api_status.api_completion_fence_addr = umsch->ring.fence_drv.gpu_addr;
 	add_queue.api_status.api_completion_fence_value = ++umsch->ring.fence_drv.sync_seq;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index dfa8c69532d470..f9631f4b1a02ca 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1523,7 +1523,7 @@ static int kfd_ioctl_get_dmabuf_info(struct file *filep,
 
 	/* Find a KFD GPU device that supports the get_dmabuf_info query */
 	for (i = 0; kfd_topology_enum_kfd_devices(i, &dev) == 0; i++)
-		if (dev)
+		if (dev && !kfd_devcgroup_check_permission(dev))
 			break;
 	if (!dev)
 		return -EINVAL;
@@ -1545,7 +1545,7 @@ static int kfd_ioctl_get_dmabuf_info(struct file *filep,
 	if (xcp_id >= 0)
 		args->gpu_id = dmabuf_adev->kfd.dev->nodes[xcp_id]->id;
 	else
-		args->gpu_id = dmabuf_adev->kfd.dev->nodes[0]->id;
+		args->gpu_id = dev->id;
 	args->flags = flags;
 
 	/* Copy metadata buffer to user mode */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c
index 9a06c6fb660585..40a21be6c07c9b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c
@@ -339,7 +339,8 @@ static void event_interrupt_wq_v10(struct kfd_node *dev,
 				break;
 			}
 			kfd_signal_event_interrupt(pasid, context_id0 & 0x7fffff, 23);
-		} else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) {
+		} else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE &&
+			   KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) {
 			kfd_set_dbg_ev_from_interrupt(dev, pasid,
 				KFD_DEBUG_DOORBELL_ID(context_id0),
 				KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)),
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
index 7e2859736a558f..fe2ad0c0de9543 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
@@ -328,7 +328,8 @@ static void event_interrupt_wq_v11(struct kfd_node *dev,
 		/* CP */
 		if (source_id == SOC15_INTSRC_CP_END_OF_PIPE)
 			kfd_signal_event_interrupt(pasid, context_id0, 32);
-		else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE)
+		else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE &&
+			 KFD_DBG_EC_TYPE_IS_PACKET(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0)))
 			kfd_set_dbg_ev_from_interrupt(dev, pasid,
 				KFD_CTXID0_DOORBELL_ID(context_id0),
 				KFD_EC_MASK(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0)),
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
index 91dd5e045b511d..c4c6a29052ac8f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -388,7 +388,8 @@ static void event_interrupt_wq_v9(struct kfd_node *dev,
 				break;
 			}
 			kfd_signal_event_interrupt(pasid, sq_int_data, 24);
-		} else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) {
+		} else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE &&
+			   KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) {
 			kfd_set_dbg_ev_from_interrupt(dev, pasid,
 				KFD_DEBUG_DOORBELL_ID(context_id0),
 				KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)),
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 42d40560cd30d7..a81ef232fdef96 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1473,7 +1473,7 @@ static inline void kfd_flush_tlb(struct kfd_process_device *pdd,
 
 static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev)
 {
-	return KFD_GC_VERSION(dev) > IP_VERSION(9, 4, 2) ||
+	return KFD_GC_VERSION(dev) >= IP_VERSION(9, 4, 2) ||
 	       (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) && dev->sdma_fw_version >= 18) ||
 	       KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0);
 }
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 2851719d712161..71d2d44681b218 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -6305,9 +6305,8 @@ create_stream_for_sink(struct drm_connector *connector,
 
 	if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
 		mod_build_hf_vsif_infopacket(stream, &stream->vsp_infopacket);
-	else if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT ||
-			 stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST ||
-			 stream->signal == SIGNAL_TYPE_EDP) {
+
+	if (stream->link->psr_settings.psr_feature_enabled || stream->link->replay_settings.replay_feature_enabled) {
 		//
 		// should decide stream support vsc sdp colorimetry capability
 		// before building vsc info packet
@@ -6323,9 +6322,8 @@ create_stream_for_sink(struct drm_connector *connector,
 		if (stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22)
 			tf = TRANSFER_FUNC_GAMMA_22;
 		mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf);
+		aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
 
-		if (stream->link->psr_settings.psr_feature_enabled)
-			aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
 	}
 finish:
 	dc_sink_release(sink);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
index 1f08c6564c3bfe..286ecd28cc6e66 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
@@ -141,9 +141,8 @@ bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream)
  * amdgpu_dm_psr_enable() - enable psr f/w
  * @stream: stream state
  *
- * Return: true if success
  */
-bool amdgpu_dm_psr_enable(struct dc_stream_state *stream)
+void amdgpu_dm_psr_enable(struct dc_stream_state *stream)
 {
 	struct dc_link *link = stream->link;
 	unsigned int vsync_rate_hz = 0;
@@ -190,7 +189,10 @@ bool amdgpu_dm_psr_enable(struct dc_stream_state *stream)
 	if (link->psr_settings.psr_version < DC_PSR_VERSION_SU_1)
 		power_opt |= psr_power_opt_z10_static_screen;
 
-	return dc_link_set_psr_allow_active(link, &psr_enable, false, false, &power_opt);
+	dc_link_set_psr_allow_active(link, &psr_enable, false, false, &power_opt);
+
+	if (link->ctx->dc->caps.ips_support)
+		dc_allow_idle_optimizations(link->ctx->dc, true);
 }
 
 /*
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h
index 6806b3c9c84ba0..1fdfd183c0d91a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h
@@ -32,7 +32,7 @@
 #define AMDGPU_DM_PSR_ENTRY_DELAY 5
 
 void amdgpu_dm_set_psr_caps(struct dc_link *link);
-bool amdgpu_dm_psr_enable(struct dc_stream_state *stream);
+void amdgpu_dm_psr_enable(struct dc_stream_state *stream);
 bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream);
 bool amdgpu_dm_psr_disable(struct dc_stream_state *stream);
 bool amdgpu_dm_psr_disable_all(struct amdgpu_display_manager *dm);
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index c378b879c76d8c..101fe96287cb48 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -73,6 +73,8 @@
 #define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL_MASK		0x00000007L
 #define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV_MASK		0x000F0000L
 
+#define SMU_VER_THRESHOLD 0x5D4A00 //93.74.0
+
 #define REG(reg_name) \
 	(ctx->clk_reg_offsets[reg ## reg_name ## _BASE_IDX] + reg ## reg_name)
 
@@ -411,9 +413,12 @@ static void dcn35_dump_clk_registers(struct clk_state_registers_and_bypass *regs
 
 static void init_clk_states(struct clk_mgr *clk_mgr)
 {
+	struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr);
 	uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz;
 	memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks));
 
+	if (clk_mgr_int->smu_ver >= SMU_VER_THRESHOLD)
+		clk_mgr->clks.dtbclk_en = true; // request DTBCLK disable on first commit
 	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;
@@ -709,7 +714,7 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 		clock_table->NumFclkLevelsEnabled;
 	max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, num_fclk);
 
-	num_dcfclk = (clock_table->NumFclkLevelsEnabled > NUM_DCFCLK_DPM_LEVELS) ? NUM_DCFCLK_DPM_LEVELS :
+	num_dcfclk = (clock_table->NumDcfClkLevelsEnabled > NUM_DCFCLK_DPM_LEVELS) ? NUM_DCFCLK_DPM_LEVELS :
 		clock_table->NumDcfClkLevelsEnabled;
 	for (i = 0; i < num_dcfclk; i++) {
 		int j;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index e7dc128f6284b4..03b554e912a20d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -3024,7 +3024,8 @@ static void backup_planes_and_stream_state(
 		scratch->blend_tf[i] = *status->plane_states[i]->blend_tf;
 	}
 	scratch->stream_state = *stream;
-	scratch->out_transfer_func = *stream->out_transfer_func;
+	if (stream->out_transfer_func)
+		scratch->out_transfer_func = *stream->out_transfer_func;
 }
 
 static void restore_planes_and_stream_state(
@@ -3046,7 +3047,8 @@ static void restore_planes_and_stream_state(
 		*status->plane_states[i]->blend_tf = scratch->blend_tf[i];
 	}
 	*stream = scratch->stream_state;
-	*stream->out_transfer_func = scratch->out_transfer_func;
+	if (stream->out_transfer_func)
+		*stream->out_transfer_func = scratch->out_transfer_func;
 }
 
 static bool update_planes_and_stream_state(struct dc *dc,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
index bf3386cd444d62..5ebb5730313048 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
@@ -44,6 +44,36 @@
 #define NUM_ELEMENTS(a) (sizeof(a) / sizeof((a)[0]))
 
 
+void mpc3_mpc_init(struct mpc *mpc)
+{
+	struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc);
+	int opp_id;
+
+	mpc1_mpc_init(mpc);
+
+	for (opp_id = 0; opp_id < MAX_OPP; opp_id++) {
+		if (REG(MUX[opp_id]))
+			/* disable mpc out rate and flow control */
+			REG_UPDATE_2(MUX[opp_id], MPC_OUT_RATE_CONTROL_DISABLE,
+					1, MPC_OUT_FLOW_CONTROL_COUNT, 0);
+	}
+}
+
+void mpc3_mpc_init_single_inst(struct mpc *mpc, unsigned int mpcc_id)
+{
+	struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc);
+
+	mpc1_mpc_init_single_inst(mpc, mpcc_id);
+
+	/* assuming mpc out mux is connected to opp with the same index at this
+	 * point in time (e.g. transitioning from vbios to driver)
+	 */
+	if (mpcc_id < MAX_OPP && REG(MUX[mpcc_id]))
+		/* disable mpc out rate and flow control */
+		REG_UPDATE_2(MUX[mpcc_id], MPC_OUT_RATE_CONTROL_DISABLE,
+				1, MPC_OUT_FLOW_CONTROL_COUNT, 0);
+}
+
 bool mpc3_is_dwb_idle(
 	struct mpc *mpc,
 	int dwb_id)
@@ -80,25 +110,6 @@ void mpc3_disable_dwb_mux(
 		MPC_DWB0_MUX, 0xf);
 }
 
-void mpc3_set_out_rate_control(
-	struct mpc *mpc,
-	int opp_id,
-	bool enable,
-	bool rate_2x_mode,
-	struct mpc_dwb_flow_control *flow_control)
-{
-	struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc);
-
-	REG_UPDATE_2(MUX[opp_id],
-			MPC_OUT_RATE_CONTROL_DISABLE, !enable,
-			MPC_OUT_RATE_CONTROL, rate_2x_mode);
-
-	if (flow_control)
-		REG_UPDATE_2(MUX[opp_id],
-			MPC_OUT_FLOW_CONTROL_MODE, flow_control->flow_ctrl_mode,
-			MPC_OUT_FLOW_CONTROL_COUNT, flow_control->flow_ctrl_cnt1);
-}
-
 enum dc_lut_mode mpc3_get_ogam_current(struct mpc *mpc, int mpcc_id)
 {
 	/*Contrary to DCN2 and DCN1 wherein a single status register field holds this info;
@@ -1490,8 +1501,8 @@ static const struct mpc_funcs dcn30_mpc_funcs = {
 	.read_mpcc_state = mpc3_read_mpcc_state,
 	.insert_plane = mpc1_insert_plane,
 	.remove_mpcc = mpc1_remove_mpcc,
-	.mpc_init = mpc1_mpc_init,
-	.mpc_init_single_inst = mpc1_mpc_init_single_inst,
+	.mpc_init = mpc3_mpc_init,
+	.mpc_init_single_inst = mpc3_mpc_init_single_inst,
 	.update_blending = mpc2_update_blending,
 	.cursor_lock = mpc1_cursor_lock,
 	.get_mpcc_for_dpp = mpc1_get_mpcc_for_dpp,
@@ -1508,7 +1519,6 @@ static const struct mpc_funcs dcn30_mpc_funcs = {
 	.set_dwb_mux = mpc3_set_dwb_mux,
 	.disable_dwb_mux = mpc3_disable_dwb_mux,
 	.is_dwb_idle = mpc3_is_dwb_idle,
-	.set_out_rate_control = mpc3_set_out_rate_control,
 	.set_gamut_remap = mpc3_set_gamut_remap,
 	.program_shaper = mpc3_program_shaper,
 	.acquire_rmu = mpcc3_acquire_rmu,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h
index 9cb96ae95a2f75..ce93003dae0113 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h
@@ -1007,6 +1007,13 @@ void dcn30_mpc_construct(struct dcn30_mpc *mpc30,
 	int num_mpcc,
 	int num_rmu);
 
+void mpc3_mpc_init(
+	struct mpc *mpc);
+
+void mpc3_mpc_init_single_inst(
+	struct mpc *mpc,
+	unsigned int mpcc_id);
+
 bool mpc3_program_shaper(
 		struct mpc *mpc,
 		const struct pwl_params *params,
@@ -1078,13 +1085,6 @@ bool mpc3_is_dwb_idle(
 	struct mpc *mpc,
 	int dwb_id);
 
-void mpc3_set_out_rate_control(
-	struct mpc *mpc,
-	int opp_id,
-	bool enable,
-	bool rate_2x_mode,
-	struct mpc_dwb_flow_control *flow_control);
-
 void mpc3_power_on_ogam_lut(
 	struct mpc *mpc, int mpcc_id,
 	bool power_on);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c
index e789e654c38705..e408e859b35561 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c
@@ -47,7 +47,7 @@ void mpc32_mpc_init(struct mpc *mpc)
 	struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc);
 	int mpcc_id;
 
-	mpc1_mpc_init(mpc);
+	mpc3_mpc_init(mpc);
 
 	if (mpc->ctx->dc->debug.enable_mem_low_power.bits.mpc) {
 		if (mpc30->mpc_mask->MPCC_MCM_SHAPER_MEM_LOW_PWR_MODE && mpc30->mpc_mask->MPCC_MCM_3DLUT_MEM_LOW_PWR_MODE) {
@@ -991,7 +991,7 @@ static const struct mpc_funcs dcn32_mpc_funcs = {
 	.insert_plane = mpc1_insert_plane,
 	.remove_mpcc = mpc1_remove_mpcc,
 	.mpc_init = mpc32_mpc_init,
-	.mpc_init_single_inst = mpc1_mpc_init_single_inst,
+	.mpc_init_single_inst = mpc3_mpc_init_single_inst,
 	.update_blending = mpc2_update_blending,
 	.cursor_lock = mpc1_cursor_lock,
 	.get_mpcc_for_dpp = mpc1_get_mpcc_for_dpp,
@@ -1008,7 +1008,6 @@ static const struct mpc_funcs dcn32_mpc_funcs = {
 	.set_dwb_mux = mpc3_set_dwb_mux,
 	.disable_dwb_mux = mpc3_disable_dwb_mux,
 	.is_dwb_idle = mpc3_is_dwb_idle,
-	.set_out_rate_control = mpc3_set_out_rate_control,
 	.set_gamut_remap = mpc3_set_gamut_remap,
 	.program_shaper = mpc32_program_shaper,
 	.program_3dlut = mpc32_program_3dlut,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index 80bebfc268db0f..21e0eef3269b10 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -166,8 +166,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 	.num_states = 5,
 	.sr_exit_time_us = 28.0,
 	.sr_enter_plus_exit_time_us = 30.0,
-	.sr_exit_z8_time_us = 210.0,
-	.sr_enter_plus_exit_z8_time_us = 320.0,
+	.sr_exit_z8_time_us = 250.0,
+	.sr_enter_plus_exit_z8_time_us = 350.0,
 	.fclk_change_latency_us = 24.0,
 	.usr_retraining_latency_us = 2,
 	.writeback_latency_us = 12.0,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
index dc9e1b758ed6a1..b3ffab77cf8894 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
@@ -98,55 +98,114 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_51_soc = {
 	.clock_limits = {
 		{
 			.state = 0,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
+			.dcfclk_mhz = 400.0,
+			.fabricclk_mhz = 400.0,
+			.socclk_mhz = 600.0,
+			.dram_speed_mts = 3200.0,
+			.dispclk_mhz = 600.0,
+			.dppclk_mhz = 600.0,
 			.phyclk_mhz = 600.0,
 			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 186.0,
+			.dscclk_mhz = 200.0,
 			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 1,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
+			.dcfclk_mhz = 600.0,
+			.fabricclk_mhz = 1000.0,
+			.socclk_mhz = 733.0,
+			.dram_speed_mts = 6400.0,
+			.dispclk_mhz = 800.0,
+			.dppclk_mhz = 800.0,
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 209.0,
+			.dscclk_mhz = 266.7,
 			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 2,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
+			.dcfclk_mhz = 738.0,
+			.fabricclk_mhz = 1200.0,
+			.socclk_mhz = 880.0,
+			.dram_speed_mts = 7500.0,
+			.dispclk_mhz = 800.0,
+			.dppclk_mhz = 800.0,
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 209.0,
+			.dscclk_mhz = 266.7,
 			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 3,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
+			.dcfclk_mhz = 800.0,
+			.fabricclk_mhz = 1400.0,
+			.socclk_mhz = 978.0,
+			.dram_speed_mts = 7500.0,
+			.dispclk_mhz = 960.0,
+			.dppclk_mhz = 960.0,
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 371.0,
+			.dscclk_mhz = 320.0,
 			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 4,
+			.dcfclk_mhz = 873.0,
+			.fabricclk_mhz = 1600.0,
+			.socclk_mhz = 1100.0,
+			.dram_speed_mts = 8533.0,
+			.dispclk_mhz = 1066.7,
+			.dppclk_mhz = 1066.7,
+			.phyclk_mhz = 810.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 355.6,
+			.dtbclk_mhz = 600.0,
+		},
+		{
+			.state = 5,
+			.dcfclk_mhz = 960.0,
+			.fabricclk_mhz = 1700.0,
+			.socclk_mhz = 1257.0,
+			.dram_speed_mts = 8533.0,
 			.dispclk_mhz = 1200.0,
 			.dppclk_mhz = 1200.0,
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 417.0,
+			.dscclk_mhz = 400.0,
+			.dtbclk_mhz = 600.0,
+		},
+		{
+			.state = 6,
+			.dcfclk_mhz = 1067.0,
+			.fabricclk_mhz = 1850.0,
+			.socclk_mhz = 1257.0,
+			.dram_speed_mts = 8533.0,
+			.dispclk_mhz = 1371.4,
+			.dppclk_mhz = 1371.4,
+			.phyclk_mhz = 810.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 457.1,
+			.dtbclk_mhz = 600.0,
+		},
+		{
+			.state = 7,
+			.dcfclk_mhz = 1200.0,
+			.fabricclk_mhz = 2000.0,
+			.socclk_mhz = 1467.0,
+			.dram_speed_mts = 8533.0,
+			.dispclk_mhz = 1600.0,
+			.dppclk_mhz = 1600.0,
+			.phyclk_mhz = 810.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 533.3,
 			.dtbclk_mhz = 600.0,
 		},
 	},
-	.num_states = 5,
+	.num_states = 8,
 	.sr_exit_time_us = 28.0,
 	.sr_enter_plus_exit_time_us = 30.0,
-	.sr_exit_z8_time_us = 210.0,
-	.sr_enter_plus_exit_z8_time_us = 320.0,
+	.sr_exit_z8_time_us = 250.0,
+	.sr_enter_plus_exit_z8_time_us = 350.0,
 	.fclk_change_latency_us = 24.0,
 	.usr_retraining_latency_us = 2,
 	.writeback_latency_us = 12.0,
@@ -177,6 +236,9 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_51_soc = {
 	.do_urgent_latency_adjustment = 0,
 	.urgent_latency_adjustment_fabric_clock_component_us = 0,
 	.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
+	.num_chans = 4,
+	.dram_clock_change_latency_us = 11.72,
+	.dispclk_dppclk_vco_speed_mhz = 2400.0,
 };
 
 /*
@@ -340,6 +402,8 @@ void dcn351_update_bw_bounding_box_fpu(struct dc *dc,
 				clock_limits[i].socclk_mhz;
 			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].memclk_mhz =
 				clk_table->entries[i].memclk_mhz * clk_table->entries[i].wck_ratio;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz =
+				clock_limits[i].dtbclk_mhz;
 			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels =
 				clk_table->num_entries;
 			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_fclk_levels =
@@ -352,6 +416,8 @@ void dcn351_update_bw_bounding_box_fpu(struct dc *dc,
 				clk_table->num_entries;
 			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_memclk_levels =
 				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dtbclk_levels =
+				clk_table->num_entries;
 		}
 	}
 
@@ -551,6 +617,7 @@ void dcn351_decide_zstate_support(struct dc *dc, struct dc_state *context)
 		if (context->res_ctx.pipe_ctx[i].plane_state)
 			plane_count++;
 	}
+
 	/*dcn351 does not support z9/z10*/
 	if (context->stream_count == 0 || plane_count == 0) {
 		support = DCN_ZSTATE_SUPPORT_ALLOW_Z8_ONLY;
@@ -564,11 +631,9 @@ void dcn351_decide_zstate_support(struct dc *dc, struct dc_state *context)
 			dc->debug.minimum_z8_residency_time > 0 ? dc->debug.minimum_z8_residency_time : 1000;
 		bool allow_z8 = context->bw_ctx.dml.vba.StutterPeriod > (double)minmum_z8_residency;
 
-
 		/*for psr1/psr-su, we allow z8 and z10 based on latency, for replay with IPS enabled, it will enter ips2*/
-		 if (is_pwrseq0 && (is_psr || is_replay))
+		if (is_pwrseq0 && (is_psr || is_replay))
 			support = allow_z8 ? allow_z8 : DCN_ZSTATE_SUPPORT_DISALLOW;
-
 	}
 	context->bw_ctx.bw.dcn.clk.zstate_support = support;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index 17a58f41fc6a85..a20f28a5d2e7b0 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -228,17 +228,13 @@ void dml2_init_socbb_params(struct dml2_context *dml2, const struct dc *in_dc, s
 		break;
 
 	case dml_project_dcn35:
+	case dml_project_dcn351:
 		out->num_chans = 4;
 		out->round_trip_ping_latency_dcfclk_cycles = 106;
 		out->smn_latency_us = 2;
 		out->dispclk_dppclk_vco_speed_mhz = 3600;
 		break;
 
-	case dml_project_dcn351:
-		out->num_chans = 16;
-		out->round_trip_ping_latency_dcfclk_cycles = 1100;
-		out->smn_latency_us = 2;
-		break;
 	}
 	/* ---Overrides if available--- */
 	if (dml2->config.bbox_overrides.dram_num_chan)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index 9d5df4c0da5979..0ba1feaf96c0d7 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1185,7 +1185,8 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx)
 		if (dccg) {
 			dccg->funcs->disable_symclk32_se(dccg, dp_hpo_inst);
 			dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, dp_hpo_inst);
-			dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
+			if (dccg && dccg->funcs->set_dtbclk_dto)
+				dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
 		}
 	} else if (dccg && dccg->funcs->disable_symclk_se) {
 		dccg->funcs->disable_symclk_se(dccg, stream_enc->stream_enc_inst,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
index 3a9cc8ac0c0793..093f4387553ce3 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
@@ -69,29 +69,6 @@
 #define FN(reg_name, field_name) \
 	hws->shifts->field_name, hws->masks->field_name
 
-static int calc_mpc_flow_ctrl_cnt(const struct dc_stream_state *stream,
-		int opp_cnt)
-{
-	bool hblank_halved = optc2_is_two_pixels_per_containter(&stream->timing);
-	int flow_ctrl_cnt;
-
-	if (opp_cnt >= 2)
-		hblank_halved = true;
-
-	flow_ctrl_cnt = stream->timing.h_total - stream->timing.h_addressable -
-			stream->timing.h_border_left -
-			stream->timing.h_border_right;
-
-	if (hblank_halved)
-		flow_ctrl_cnt /= 2;
-
-	/* ODM combine 4:1 case */
-	if (opp_cnt == 4)
-		flow_ctrl_cnt /= 2;
-
-	return flow_ctrl_cnt;
-}
-
 static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 {
 	struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
@@ -183,10 +160,6 @@ void dcn314_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx
 	struct pipe_ctx *odm_pipe;
 	int opp_cnt = 0;
 	int opp_inst[MAX_PIPES] = {0};
-	bool rate_control_2x_pclk = (pipe_ctx->stream->timing.flags.INTERLACE || optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing));
-	struct mpc_dwb_flow_control flow_control;
-	struct mpc *mpc = dc->res_pool->mpc;
-	int i;
 
 	opp_cnt = get_odm_config(pipe_ctx, opp_inst);
 
@@ -199,20 +172,6 @@ void dcn314_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx
 		pipe_ctx->stream_res.tg->funcs->set_odm_bypass(
 				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
 
-	rate_control_2x_pclk = rate_control_2x_pclk || opp_cnt > 1;
-	flow_control.flow_ctrl_mode = 0;
-	flow_control.flow_ctrl_cnt0 = 0x80;
-	flow_control.flow_ctrl_cnt1 = calc_mpc_flow_ctrl_cnt(pipe_ctx->stream, opp_cnt);
-	if (mpc->funcs->set_out_rate_control) {
-		for (i = 0; i < opp_cnt; ++i) {
-			mpc->funcs->set_out_rate_control(
-					mpc, opp_inst[i],
-					true,
-					rate_control_2x_pclk,
-					&flow_control);
-		}
-	}
-
 	for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) {
 		odm_pipe->stream_res.opp->funcs->opp_pipe_clock_control(
 				odm_pipe->stream_res.opp,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
index c0b526cf178654..7668229438da22 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
@@ -966,29 +966,6 @@ void dcn32_init_hw(struct dc *dc)
 	}
 }
 
-static int calc_mpc_flow_ctrl_cnt(const struct dc_stream_state *stream,
-		int opp_cnt)
-{
-	bool hblank_halved = optc2_is_two_pixels_per_containter(&stream->timing);
-	int flow_ctrl_cnt;
-
-	if (opp_cnt >= 2)
-		hblank_halved = true;
-
-	flow_ctrl_cnt = stream->timing.h_total - stream->timing.h_addressable -
-			stream->timing.h_border_left -
-			stream->timing.h_border_right;
-
-	if (hblank_halved)
-		flow_ctrl_cnt /= 2;
-
-	/* ODM combine 4:1 case */
-	if (opp_cnt == 4)
-		flow_ctrl_cnt /= 2;
-
-	return flow_ctrl_cnt;
-}
-
 static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 {
 	struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
@@ -1103,10 +1080,6 @@ void dcn32_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *
 	struct pipe_ctx *odm_pipe;
 	int opp_cnt = 0;
 	int opp_inst[MAX_PIPES] = {0};
-	bool rate_control_2x_pclk = (pipe_ctx->stream->timing.flags.INTERLACE || optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing));
-	struct mpc_dwb_flow_control flow_control;
-	struct mpc *mpc = dc->res_pool->mpc;
-	int i;
 
 	opp_cnt = get_odm_config(pipe_ctx, opp_inst);
 
@@ -1119,20 +1092,6 @@ void dcn32_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *
 		pipe_ctx->stream_res.tg->funcs->set_odm_bypass(
 				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
 
-	rate_control_2x_pclk = rate_control_2x_pclk || opp_cnt > 1;
-	flow_control.flow_ctrl_mode = 0;
-	flow_control.flow_ctrl_cnt0 = 0x80;
-	flow_control.flow_ctrl_cnt1 = calc_mpc_flow_ctrl_cnt(pipe_ctx->stream, opp_cnt);
-	if (mpc->funcs->set_out_rate_control) {
-		for (i = 0; i < opp_cnt; ++i) {
-			mpc->funcs->set_out_rate_control(
-					mpc, opp_inst[i],
-					true,
-					rate_control_2x_pclk,
-					&flow_control);
-		}
-	}
-
 	for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) {
 		odm_pipe->stream_res.opp->funcs->opp_pipe_clock_control(
 				odm_pipe->stream_res.opp,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
index 4b92df23ff0db9..a5560b3fc39ba9 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
@@ -358,29 +358,6 @@ void dcn35_init_hw(struct dc *dc)
 	}
 }
 
-static int calc_mpc_flow_ctrl_cnt(const struct dc_stream_state *stream,
-		int opp_cnt)
-{
-	bool hblank_halved = optc2_is_two_pixels_per_containter(&stream->timing);
-	int flow_ctrl_cnt;
-
-	if (opp_cnt >= 2)
-		hblank_halved = true;
-
-	flow_ctrl_cnt = stream->timing.h_total - stream->timing.h_addressable -
-			stream->timing.h_border_left -
-			stream->timing.h_border_right;
-
-	if (hblank_halved)
-		flow_ctrl_cnt /= 2;
-
-	/* ODM combine 4:1 case */
-	if (opp_cnt == 4)
-		flow_ctrl_cnt /= 2;
-
-	return flow_ctrl_cnt;
-}
-
 static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 {
 	struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
@@ -474,10 +451,6 @@ void dcn35_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *
 	struct pipe_ctx *odm_pipe;
 	int opp_cnt = 0;
 	int opp_inst[MAX_PIPES] = {0};
-	bool rate_control_2x_pclk = (pipe_ctx->stream->timing.flags.INTERLACE || optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing));
-	struct mpc_dwb_flow_control flow_control;
-	struct mpc *mpc = dc->res_pool->mpc;
-	int i;
 
 	opp_cnt = get_odm_config(pipe_ctx, opp_inst);
 
@@ -490,20 +463,6 @@ void dcn35_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *
 		pipe_ctx->stream_res.tg->funcs->set_odm_bypass(
 				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
 
-	rate_control_2x_pclk = rate_control_2x_pclk || opp_cnt > 1;
-	flow_control.flow_ctrl_mode = 0;
-	flow_control.flow_ctrl_cnt0 = 0x80;
-	flow_control.flow_ctrl_cnt1 = calc_mpc_flow_ctrl_cnt(pipe_ctx->stream, opp_cnt);
-	if (mpc->funcs->set_out_rate_control) {
-		for (i = 0; i < opp_cnt; ++i) {
-			mpc->funcs->set_out_rate_control(
-					mpc, opp_inst[i],
-					true,
-					rate_control_2x_pclk,
-					&flow_control);
-		}
-	}
-
 	for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) {
 		odm_pipe->stream_res.opp->funcs->opp_pipe_clock_control(
 				odm_pipe->stream_res.opp,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
index ab17fa1c64e8c5..670255c9bc8228 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
@@ -67,7 +67,7 @@ static const struct hw_sequencer_funcs dcn351_funcs = {
 	.prepare_bandwidth = dcn35_prepare_bandwidth,
 	.optimize_bandwidth = dcn35_optimize_bandwidth,
 	.update_bandwidth = dcn20_update_bandwidth,
-	.set_drr = dcn10_set_drr,
+	.set_drr = dcn35_set_drr,
 	.get_position = dcn10_get_position,
 	.set_static_screen_control = dcn35_set_static_screen_control,
 	.setup_stereo = dcn10_setup_stereo,
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
index 5b486400dfdb5b..909e14261f9b49 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
@@ -700,6 +700,8 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.disable_dcc = DCC_ENABLE,
 	.disable_dpp_power_gate = true,
 	.disable_hubp_power_gate = true,
+	.disable_optc_power_gate = true, /*should the same as above two*/
+	.disable_hpo_power_gate = true, /*dmubfw force domain25 on*/
 	.disable_clock_gate = false,
 	.disable_dsc_power_gate = true,
 	.vsr_support = true,
@@ -742,12 +744,13 @@ static const struct dc_debug_options debug_defaults_drv = {
 	},
 	.seamless_boot_odm_combine = DML_FAIL_SOURCE_PIXEL_FORMAT,
 	.enable_z9_disable_interface = true, /* Allow support for the PMFW interface for disable Z9*/
+	.minimum_z8_residency_time = 2100,
 	.using_dml2 = true,
 	.support_eDP1_5 = true,
 	.enable_hpo_pg_support = false,
 	.enable_legacy_fast_update = true,
 	.enable_single_display_2to1_odm_policy = true,
-	.disable_idle_power_optimizations = true,
+	.disable_idle_power_optimizations = false,
 	.dmcub_emulation = false,
 	.disable_boot_optimizations = false,
 	.disable_unbounded_requesting = false,
@@ -758,8 +761,10 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.disable_z10 = true,
 	.ignore_pg = true,
 	.psp_disabled_wa = true,
-	.ips2_eval_delay_us = 200,
-	.ips2_entry_delay_us = 400
+	.ips2_eval_delay_us = 2000,
+	.ips2_entry_delay_us = 800,
+	.disable_dmub_reallow_idle = true,
+	.static_screen_wait_frames = 2,
 };
 
 static const struct dc_panel_config panel_config_defaults = {
diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
index 738ee763f24a51..84f9b412a4f117 100644
--- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
+++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
@@ -147,15 +147,12 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 	}
 
 	/* VSC packet set to 4 for PSR-SU, or 2 for PSR1 */
-	if (stream->link->psr_settings.psr_feature_enabled) {
-		if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1)
-			vsc_packet_revision = vsc_packet_rev4;
-		else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1)
-			vsc_packet_revision = vsc_packet_rev2;
-	}
-
-	if (stream->link->replay_settings.config.replay_supported)
+	if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1)
+		vsc_packet_revision = vsc_packet_rev4;
+	else if (stream->link->replay_settings.config.replay_supported)
 		vsc_packet_revision = vsc_packet_rev4;
+	else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1)
+		vsc_packet_revision = vsc_packet_rev2;
 
 	/* Update to revision 5 for extended colorimetry support */
 	if (stream->use_vsc_sdp_for_colorimetry)
diff --git a/drivers/gpu/drm/amd/include/umsch_mm_4_0_api_def.h b/drivers/gpu/drm/amd/include/umsch_mm_4_0_api_def.h
index beadb9e42850c7..ca83e9e5c3ffb8 100644
--- a/drivers/gpu/drm/amd/include/umsch_mm_4_0_api_def.h
+++ b/drivers/gpu/drm/amd/include/umsch_mm_4_0_api_def.h
@@ -234,7 +234,8 @@ union UMSCHAPI__SET_HW_RESOURCES {
 				uint32_t enable_level_process_quantum_check : 1;
 				uint32_t is_vcn0_enabled : 1;
 				uint32_t is_vcn1_enabled : 1;
-				uint32_t reserved : 27;
+				uint32_t use_rs64mem_for_proc_ctx_csa : 1;
+				uint32_t reserved : 26;
 			};
 			uint32_t uint32_all;
 		};
@@ -297,9 +298,12 @@ union UMSCHAPI__ADD_QUEUE {
 
 		struct {
 			uint32_t is_context_suspended : 1;
-			uint32_t reserved : 31;
+			uint32_t collaboration_mode : 1;
+			uint32_t reserved : 30;
 		};
 		struct UMSCH_API_STATUS api_status;
+		uint32_t process_csa_array_index;
+		uint32_t context_csa_array_index;
 	};
 
 	uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -314,6 +318,7 @@ union UMSCHAPI__REMOVE_QUEUE {
 		uint64_t context_csa_addr;
 
 		struct UMSCH_API_STATUS api_status;
+		uint32_t context_csa_array_index;
 	};
 
 	uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -337,6 +342,7 @@ union UMSCHAPI__SUSPEND {
 		uint32_t suspend_fence_value;
 
 		struct UMSCH_API_STATUS api_status;
+		uint32_t context_csa_array_index;
 	};
 
 	uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -356,6 +362,7 @@ union UMSCHAPI__RESUME {
 		enum UMSCH_ENGINE_TYPE engine_type;
 
 		struct UMSCH_API_STATUS api_status;
+		uint32_t context_csa_array_index;
 	};
 
 	uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -404,6 +411,7 @@ union UMSCHAPI__UPDATE_AFFINITY {
 		union UMSCH_AFFINITY affinity;
 		uint64_t context_csa_addr;
 		struct UMSCH_API_STATUS api_status;
+		uint32_t context_csa_array_index;
 	};
 
 	uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -417,6 +425,7 @@ union UMSCHAPI__CHANGE_CONTEXT_PRIORITY_LEVEL {
 		uint64_t context_quantum;
 		uint64_t context_csa_addr;
 		struct UMSCH_API_STATUS api_status;
+		uint32_t context_csa_array_index;
 	};
 
 	uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h
index 8a8a57c56bc0c4..ca7ce4251482db 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h
@@ -54,14 +54,14 @@
 #define PPSMC_MSG_TestMessage                   0x01 ///< To check if PMFW is alive and responding. Requirement specified by PMFW team
 #define PPSMC_MSG_GetPmfwVersion                0x02 ///< Get PMFW version
 #define PPSMC_MSG_GetDriverIfVersion            0x03 ///< Get PMFW_DRIVER_IF version
-#define PPSMC_MSG_SPARE0                        0x04 ///< SPARE
-#define PPSMC_MSG_SPARE1                        0x05 ///< SPARE
-#define PPSMC_MSG_PowerDownVcn                  0x06 ///< Power down VCN
-#define PPSMC_MSG_PowerUpVcn                    0x07 ///< Power up VCN; VCN is power gated by default
-#define PPSMC_MSG_SetHardMinVcn                 0x08 ///< For wireless display
+#define PPSMC_MSG_PowerDownVcn1                 0x04 ///< Power down VCN1
+#define PPSMC_MSG_PowerUpVcn1                   0x05 ///< Power up VCN1; VCN1 is power gated by default
+#define PPSMC_MSG_PowerDownVcn0                 0x06 ///< Power down VCN0
+#define PPSMC_MSG_PowerUpVcn0                   0x07 ///< Power up VCN0; VCN0 is power gated by default
+#define PPSMC_MSG_SetHardMinVcn0                0x08 ///< For wireless display
 #define PPSMC_MSG_SetSoftMinGfxclk              0x09 ///< Set SoftMin for GFXCLK, argument is frequency in MHz
-#define PPSMC_MSG_SPARE2                        0x0A ///< SPARE
-#define PPSMC_MSG_SPARE3                        0x0B ///< SPARE
+#define PPSMC_MSG_SetHardMinVcn1                0x0A ///< For wireless display
+#define PPSMC_MSG_SetSoftMinVcn1                0x0B ///< Set soft min for VCN1 clocks (VCLK1 and DCLK1)
 #define PPSMC_MSG_PrepareMp1ForUnload           0x0C ///< Prepare PMFW for GFX driver unload
 #define PPSMC_MSG_SetDriverDramAddrHigh         0x0D ///< Set high 32 bits of DRAM address for Driver table transfer
 #define PPSMC_MSG_SetDriverDramAddrLow          0x0E ///< Set low 32 bits of DRAM address for Driver table transfer
@@ -71,7 +71,7 @@
 #define PPSMC_MSG_GetEnabledSmuFeatures         0x12 ///< Get enabled features in PMFW
 #define PPSMC_MSG_SetHardMinSocclkByFreq        0x13 ///< Set hard min for SOC CLK
 #define PPSMC_MSG_SetSoftMinFclk                0x14 ///< Set hard min for FCLK
-#define PPSMC_MSG_SetSoftMinVcn                 0x15 ///< Set soft min for VCN clocks (VCLK and DCLK)
+#define PPSMC_MSG_SetSoftMinVcn0                0x15 ///< Set soft min for VCN0 clocks (VCLK0 and DCLK0)
 
 #define PPSMC_MSG_EnableGfxImu                  0x16 ///< Enable GFX IMU
 
@@ -84,17 +84,17 @@
 
 #define PPSMC_MSG_SetSoftMaxSocclkByFreq        0x1D ///< Set soft max for SOC CLK
 #define PPSMC_MSG_SetSoftMaxFclkByFreq          0x1E ///< Set soft max for FCLK
-#define PPSMC_MSG_SetSoftMaxVcn                 0x1F ///< Set soft max for VCN clocks (VCLK and DCLK)
+#define PPSMC_MSG_SetSoftMaxVcn0                0x1F ///< Set soft max for VCN0 clocks (VCLK0 and DCLK0)
 #define PPSMC_MSG_spare_0x20                    0x20
-#define PPSMC_MSG_PowerDownJpeg                 0x21 ///< Power down Jpeg
-#define PPSMC_MSG_PowerUpJpeg                   0x22 ///< Power up Jpeg; VCN is power gated by default
+#define PPSMC_MSG_PowerDownJpeg0                0x21 ///< Power down Jpeg of VCN0
+#define PPSMC_MSG_PowerUpJpeg0                  0x22 ///< Power up Jpeg of VCN0; VCN0 is power gated by default
 
 #define PPSMC_MSG_SetHardMinFclkByFreq          0x23 ///< Set hard min for FCLK
 #define PPSMC_MSG_SetSoftMinSocclkByFreq        0x24 ///< Set soft min for SOC CLK
 #define PPSMC_MSG_AllowZstates                  0x25 ///< Inform PMFM of allowing Zstate entry, i.e. no Miracast activity
-#define PPSMC_MSG_Reserved                      0x26 ///< Not used
-#define PPSMC_MSG_Reserved1                     0x27 ///< Not used, previously PPSMC_MSG_RequestActiveWgp
-#define PPSMC_MSG_Reserved2                     0x28 ///< Not used, previously PPSMC_MSG_QueryActiveWgp
+#define PPSMC_MSG_PowerDownJpeg1                0x26 ///< Power down Jpeg of VCN1
+#define PPSMC_MSG_PowerUpJpeg1                  0x27 ///< Power up Jpeg of VCN1; VCN1 is power gated by default
+#define PPSMC_MSG_SetSoftMaxVcn1                0x28 ///< Set soft max for VCN1 clocks (VCLK1 and DCLK1)
 #define PPSMC_MSG_PowerDownIspByTile            0x29 ///< ISP is power gated by default
 #define PPSMC_MSG_PowerUpIspByTile              0x2A ///< This message is used to power up ISP tiles and enable the ISP DPM
 #define PPSMC_MSG_SetHardMinIspiclkByFreq       0x2B ///< Set HardMin by frequency for ISPICLK
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
index a941fdbf78b6b3..af427cc7dbb845 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
@@ -115,6 +115,10 @@
        __SMU_DUMMY_MAP(PowerDownVcn),                 \
        __SMU_DUMMY_MAP(PowerUpJpeg),                  \
        __SMU_DUMMY_MAP(PowerDownJpeg),                \
+       __SMU_DUMMY_MAP(PowerUpJpeg0),                 \
+       __SMU_DUMMY_MAP(PowerDownJpeg0),               \
+       __SMU_DUMMY_MAP(PowerUpJpeg1),                 \
+       __SMU_DUMMY_MAP(PowerDownJpeg1),               \
        __SMU_DUMMY_MAP(BacoAudioD3PME),               \
        __SMU_DUMMY_MAP(ArmD3),                        \
        __SMU_DUMMY_MAP(RunDcBtc),                     \
@@ -135,6 +139,8 @@
 	__SMU_DUMMY_MAP(PowerUpSdma),                 \
 	__SMU_DUMMY_MAP(SetHardMinIspclkByFreq),      \
 	__SMU_DUMMY_MAP(SetHardMinVcn),               \
+       __SMU_DUMMY_MAP(SetHardMinVcn0),               \
+       __SMU_DUMMY_MAP(SetHardMinVcn1),               \
 	__SMU_DUMMY_MAP(SetAllowFclkSwitch),          \
 	__SMU_DUMMY_MAP(SetMinVideoGfxclkFreq),       \
 	__SMU_DUMMY_MAP(ActiveProcessNotify),         \
@@ -150,6 +156,8 @@
 	__SMU_DUMMY_MAP(SetPhyclkVoltageByFreq),      \
 	__SMU_DUMMY_MAP(SetDppclkVoltageByFreq),      \
 	__SMU_DUMMY_MAP(SetSoftMinVcn),               \
+       __SMU_DUMMY_MAP(SetSoftMinVcn0),              \
+       __SMU_DUMMY_MAP(SetSoftMinVcn1),              \
 	__SMU_DUMMY_MAP(EnablePostCode),              \
 	__SMU_DUMMY_MAP(GetGfxclkFrequency),          \
 	__SMU_DUMMY_MAP(GetFclkFrequency),            \
@@ -161,6 +169,8 @@
 	__SMU_DUMMY_MAP(SetSoftMaxSocclkByFreq),      \
 	__SMU_DUMMY_MAP(SetSoftMaxFclkByFreq),        \
 	__SMU_DUMMY_MAP(SetSoftMaxVcn),               \
+       __SMU_DUMMY_MAP(SetSoftMaxVcn0),              \
+       __SMU_DUMMY_MAP(SetSoftMaxVcn1),              \
 	__SMU_DUMMY_MAP(PowerGateMmHub),              \
 	__SMU_DUMMY_MAP(UpdatePmeRestore),            \
 	__SMU_DUMMY_MAP(GpuChangeState),              \
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index b06a3cc4330542..9e39f99154f94d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -1402,9 +1402,22 @@ int smu_v14_0_set_vcn_enable(struct smu_context *smu,
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
-		ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
-						      SMU_MSG_PowerUpVcn : SMU_MSG_PowerDownVcn,
-						      i << 16U, NULL);
+		if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0) ||
+		    amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1)) {
+			if (i == 0)
+				ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+								      SMU_MSG_PowerUpVcn0 : SMU_MSG_PowerDownVcn0,
+								      i << 16U, NULL);
+			else if (i == 1)
+				ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+								      SMU_MSG_PowerUpVcn1 : SMU_MSG_PowerDownVcn1,
+								      i << 16U, NULL);
+		} else {
+			ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+							      SMU_MSG_PowerUpVcn : SMU_MSG_PowerDownVcn,
+							      i << 16U, NULL);
+		}
+
 		if (ret)
 			return ret;
 	}
@@ -1415,9 +1428,34 @@ int smu_v14_0_set_vcn_enable(struct smu_context *smu,
 int smu_v14_0_set_jpeg_enable(struct smu_context *smu,
 			      bool enable)
 {
-	return smu_cmn_send_smc_msg_with_param(smu, enable ?
-					       SMU_MSG_PowerUpJpeg : SMU_MSG_PowerDownJpeg,
-					       0, NULL);
+	struct amdgpu_device *adev = smu->adev;
+	int i, ret = 0;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; i++) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0) ||
+		    amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1)) {
+			if (i == 0)
+				ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+								      SMU_MSG_PowerUpJpeg0 : SMU_MSG_PowerDownJpeg0,
+								      i << 16U, NULL);
+			else if (i == 1 && amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
+				ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+								      SMU_MSG_PowerUpJpeg1 : SMU_MSG_PowerDownJpeg1,
+								      i << 16U, NULL);
+		} else {
+			ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+							      SMU_MSG_PowerUpJpeg : SMU_MSG_PowerDownJpeg,
+							      i << 16U, NULL);
+		}
+
+		if (ret)
+			return ret;
+	}
+
+	return ret;
 }
 
 int smu_v14_0_run_btc(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
index 9310c4758e38ce..d6de6d97286c69 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
@@ -70,9 +70,12 @@ static struct cmn2asic_msg_mapping smu_v14_0_0_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(TestMessage,                    PPSMC_MSG_TestMessage,				1),
 	MSG_MAP(GetSmuVersion,                  PPSMC_MSG_GetPmfwVersion,			1),
 	MSG_MAP(GetDriverIfVersion,             PPSMC_MSG_GetDriverIfVersion,		1),
-	MSG_MAP(PowerDownVcn,                   PPSMC_MSG_PowerDownVcn,				1),
-	MSG_MAP(PowerUpVcn,                     PPSMC_MSG_PowerUpVcn,				1),
-	MSG_MAP(SetHardMinVcn,                  PPSMC_MSG_SetHardMinVcn,			1),
+	MSG_MAP(PowerDownVcn0,                  PPSMC_MSG_PowerDownVcn0,			1),
+	MSG_MAP(PowerUpVcn0,                    PPSMC_MSG_PowerUpVcn0,				1),
+	MSG_MAP(SetHardMinVcn0,                 PPSMC_MSG_SetHardMinVcn0,			1),
+	MSG_MAP(PowerDownVcn1,                  PPSMC_MSG_PowerDownVcn1,			1),
+	MSG_MAP(PowerUpVcn1,                    PPSMC_MSG_PowerUpVcn1,				1),
+	MSG_MAP(SetHardMinVcn1,                 PPSMC_MSG_SetHardMinVcn1,			1),
 	MSG_MAP(SetSoftMinGfxclk,               PPSMC_MSG_SetSoftMinGfxclk,			1),
 	MSG_MAP(PrepareMp1ForUnload,            PPSMC_MSG_PrepareMp1ForUnload,		1),
 	MSG_MAP(SetDriverDramAddrHigh,          PPSMC_MSG_SetDriverDramAddrHigh,	1),
@@ -83,7 +86,8 @@ static struct cmn2asic_msg_mapping smu_v14_0_0_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(GetEnabledSmuFeatures,          PPSMC_MSG_GetEnabledSmuFeatures,	1),
 	MSG_MAP(SetHardMinSocclkByFreq,         PPSMC_MSG_SetHardMinSocclkByFreq,	1),
 	MSG_MAP(SetSoftMinFclk,                 PPSMC_MSG_SetSoftMinFclk,			1),
-	MSG_MAP(SetSoftMinVcn,                  PPSMC_MSG_SetSoftMinVcn,			1),
+	MSG_MAP(SetSoftMinVcn0,                 PPSMC_MSG_SetSoftMinVcn0,			1),
+	MSG_MAP(SetSoftMinVcn1,                 PPSMC_MSG_SetSoftMinVcn1,			1),
 	MSG_MAP(EnableGfxImu,                   PPSMC_MSG_EnableGfxImu,				1),
 	MSG_MAP(AllowGfxOff,                    PPSMC_MSG_AllowGfxOff,				1),
 	MSG_MAP(DisallowGfxOff,                 PPSMC_MSG_DisallowGfxOff,			1),
@@ -91,9 +95,12 @@ static struct cmn2asic_msg_mapping smu_v14_0_0_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(SetHardMinGfxClk,               PPSMC_MSG_SetHardMinGfxClk,			1),
 	MSG_MAP(SetSoftMaxSocclkByFreq,         PPSMC_MSG_SetSoftMaxSocclkByFreq,	1),
 	MSG_MAP(SetSoftMaxFclkByFreq,           PPSMC_MSG_SetSoftMaxFclkByFreq,		1),
-	MSG_MAP(SetSoftMaxVcn,                  PPSMC_MSG_SetSoftMaxVcn,			1),
-	MSG_MAP(PowerDownJpeg,                  PPSMC_MSG_PowerDownJpeg,			1),
-	MSG_MAP(PowerUpJpeg,                    PPSMC_MSG_PowerUpJpeg,				1),
+	MSG_MAP(SetSoftMaxVcn0,                 PPSMC_MSG_SetSoftMaxVcn0,			1),
+	MSG_MAP(SetSoftMaxVcn1,                 PPSMC_MSG_SetSoftMaxVcn1,			1),
+	MSG_MAP(PowerDownJpeg0,                 PPSMC_MSG_PowerDownJpeg0,			1),
+	MSG_MAP(PowerUpJpeg0,                   PPSMC_MSG_PowerUpJpeg0,				1),
+	MSG_MAP(PowerDownJpeg1,                 PPSMC_MSG_PowerDownJpeg1,			1),
+	MSG_MAP(PowerUpJpeg1,                   PPSMC_MSG_PowerUpJpeg1,				1),
 	MSG_MAP(SetHardMinFclkByFreq,           PPSMC_MSG_SetHardMinFclkByFreq,		1),
 	MSG_MAP(SetSoftMinSocclkByFreq,         PPSMC_MSG_SetSoftMinSocclkByFreq,	1),
 	MSG_MAP(PowerDownIspByTile,             PPSMC_MSG_PowerDownIspByTile,		1),
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 9ce46edc62a5b1..2040a470ddb41b 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -913,14 +913,25 @@ enum kfd_dbg_trap_exception_code {
 				 KFD_EC_MASK(EC_DEVICE_NEW))
 #define KFD_EC_MASK_PROCESS	(KFD_EC_MASK(EC_PROCESS_RUNTIME) |	\
 				 KFD_EC_MASK(EC_PROCESS_DEVICE_REMOVE))
+#define KFD_EC_MASK_PACKET	(KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_DIM_INVALID) |	\
+				 KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_GROUP_SEGMENT_SIZE_INVALID) |	\
+				 KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_CODE_INVALID) |	\
+				 KFD_EC_MASK(EC_QUEUE_PACKET_RESERVED) |	\
+				 KFD_EC_MASK(EC_QUEUE_PACKET_UNSUPPORTED) |	\
+				 KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_WORK_GROUP_SIZE_INVALID) |	\
+				 KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_REGISTER_INVALID) |	\
+				 KFD_EC_MASK(EC_QUEUE_PACKET_VENDOR_UNSUPPORTED))
 
 /* Checks for exception code types for KFD search */
+#define KFD_DBG_EC_IS_VALID(ecode) (ecode > EC_NONE && ecode < EC_MAX)
 #define KFD_DBG_EC_TYPE_IS_QUEUE(ecode)					\
-			(!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_QUEUE))
+			(KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_QUEUE))
 #define KFD_DBG_EC_TYPE_IS_DEVICE(ecode)				\
-			(!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_DEVICE))
+			(KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_DEVICE))
 #define KFD_DBG_EC_TYPE_IS_PROCESS(ecode)				\
-			(!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PROCESS))
+			(KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PROCESS))
+#define KFD_DBG_EC_TYPE_IS_PACKET(ecode)				\
+			(KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PACKET))
 
 
 /* Runtime enable states */