Merge back thermal control material for v6.1.

254 files changed, 4692 insertions, 3187 deletions

diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c
index 79aa9f285312..b734e069034d 100644
--- a/drivers/ata/ahci_imx.c
+++ b/drivers/ata/ahci_imx.c
@@ -327,7 +327,7 @@ static int read_adc_sum(void *dev, u16 rtune_ctl_reg, void __iomem * mmio)
 }
 
 /* SATA AHCI temperature monitor */
-static int sata_ahci_read_temperature(void *dev, int *temp)
+static int __sata_ahci_read_temperature(void *dev, int *temp)
 {
 	u16 mpll_test_reg, rtune_ctl_reg, dac_ctl_reg, read_sum;
 	u32 str1, str2, str3, str4;
@@ -416,6 +416,11 @@ static int sata_ahci_read_temperature(void *dev, int *temp)
 	return 0;
 }
 
+static int sata_ahci_read_temperature(struct thermal_zone_device *tz, int *temp)
+{
+	return __sata_ahci_read_temperature(tz->devdata, temp);
+}
+
 static ssize_t sata_ahci_show_temp(struct device *dev,
 				   struct device_attribute *da,
 				   char *buf)
@@ -423,14 +428,14 @@ static ssize_t sata_ahci_show_temp(struct device *dev,
 	unsigned int temp = 0;
 	int err;
 
-	err = sata_ahci_read_temperature(dev, &temp);
+	err = __sata_ahci_read_temperature(dev, &temp);
 	if (err < 0)
 		return err;
 
 	return sprintf(buf, "%u\n", temp);
 }
 
-static const struct thermal_zone_of_device_ops fsl_sata_ahci_of_thermal_ops = {
+static const struct thermal_zone_device_ops fsl_sata_ahci_of_thermal_ops = {
 	.get_temp = sata_ahci_read_temperature,
 };
 
@@ -1131,8 +1136,8 @@ static int imx_ahci_probe(struct platform_device *pdev)
 			ret = PTR_ERR(hwmon_dev);
 			goto disable_clk;
 		}
-		devm_thermal_zone_of_sensor_register(hwmon_dev, 0, hwmon_dev,
-					     &fsl_sata_ahci_of_thermal_ops);
+		devm_thermal_of_zone_register(hwmon_dev, 0, hwmon_dev,
+					      &fsl_sata_ahci_of_thermal_ops);
 		dev_info(dev, "%s: sensor 'sata_ahci'\n", dev_name(hwmon_dev));
 	}
 
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index ef4508d72c02..7c128c89b454 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -2122,6 +2122,7 @@ const char *ata_get_cmd_name(u8 command)
 		{ ATA_CMD_WRITE_QUEUED_FUA_EXT, "WRITE DMA QUEUED FUA EXT" },
 		{ ATA_CMD_FPDMA_READ,		"READ FPDMA QUEUED" },
 		{ ATA_CMD_FPDMA_WRITE,		"WRITE FPDMA QUEUED" },
+		{ ATA_CMD_NCQ_NON_DATA,		"NCQ NON-DATA" },
 		{ ATA_CMD_FPDMA_SEND,		"SEND FPDMA QUEUED" },
 		{ ATA_CMD_FPDMA_RECV,		"RECEIVE FPDMA QUEUED" },
 		{ ATA_CMD_PIO_READ,		"READ SECTOR(S)" },
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 2b7d1db5c4a7..6a4a94b4cdf4 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -555,7 +555,7 @@ static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu(
 	return (struct ublk_uring_cmd_pdu *)&ioucmd->pdu;
 }
 
-static bool ubq_daemon_is_dying(struct ublk_queue *ubq)
+static inline bool ubq_daemon_is_dying(struct ublk_queue *ubq)
 {
 	return ubq->ubq_daemon->flags & PF_EXITING;
 }
@@ -605,8 +605,9 @@ static void ublk_complete_rq(struct request *req)
 }
 
 /*
- * __ublk_fail_req() may be called from abort context or ->ubq_daemon
- * context during exiting, so lock is required.
+ * Since __ublk_rq_task_work always fails requests immediately during
+ * exiting, __ublk_fail_req() is only called from abort context during
+ * exiting. So lock is unnecessary.
  *
  * Also aborting may not be started yet, keep in mind that one failed
  * request may be issued by block layer again.
@@ -644,8 +645,7 @@ static inline void __ublk_rq_task_work(struct request *req)
 	struct ublk_device *ub = ubq->dev;
 	int tag = req->tag;
 	struct ublk_io *io = &ubq->ios[tag];
-	bool task_exiting = current != ubq->ubq_daemon ||
-		(current->flags & PF_EXITING);
+	bool task_exiting = current != ubq->ubq_daemon || ubq_daemon_is_dying(ubq);
 	unsigned int mapped_bytes;
 
 	pr_devel("%s: complete: op %d, qid %d tag %d io_flags %x addr %llx\n",
@@ -680,6 +680,11 @@ static inline void __ublk_rq_task_work(struct request *req)
 		 * do the copy work.
 		 */
 		io->flags &= ~UBLK_IO_FLAG_NEED_GET_DATA;
+		/* update iod->addr because ublksrv may have passed a new io buffer */
+		ublk_get_iod(ubq, req->tag)->addr = io->addr;
+		pr_devel("%s: update iod->addr: op %d, qid %d tag %d io_flags %x addr %llx\n",
+				__func__, io->cmd->cmd_op, ubq->q_id, req->tag, io->flags,
+				ublk_get_iod(ubq, req->tag)->addr);
 	}
 
 	mapped_bytes = ublk_map_io(ubq, req, io);
@@ -751,9 +756,25 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
 		if (task_work_add(ubq->ubq_daemon, &data->work, notify_mode))
 			goto fail;
 	} else {
-		struct io_uring_cmd *cmd = ubq->ios[rq->tag].cmd;
+		struct ublk_io *io = &ubq->ios[rq->tag];
+		struct io_uring_cmd *cmd = io->cmd;
 		struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
 
+		/*
+		 * If the check pass, we know that this is a re-issued request aborted
+		 * previously in monitor_work because the ubq_daemon(cmd's task) is
+		 * PF_EXITING. We cannot call io_uring_cmd_complete_in_task() anymore
+		 * because this ioucmd's io_uring context may be freed now if no inflight
+		 * ioucmd exists. Otherwise we may cause null-deref in ctx->fallback_work.
+		 *
+		 * Note: monitor_work sets UBLK_IO_FLAG_ABORTED and ends this request(releasing
+		 * the tag). Then the request is re-started(allocating the tag) and we are here.
+		 * Since releasing/allocating a tag implies smp_mb(), finding UBLK_IO_FLAG_ABORTED
+		 * guarantees that here is a re-issued request aborted previously.
+		 */
+		if ((io->flags & UBLK_IO_FLAG_ABORTED))
+			goto fail;
+
 		pdu->req = rq;
 		io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/aldebaran.c b/drivers/gpu/drm/amd/amdgpu/aldebaran.c
index c6cc493a5486..2b97b8a96fb4 100644
--- a/drivers/gpu/drm/amd/amdgpu/aldebaran.c
+++ b/drivers/gpu/drm/amd/amdgpu/aldebaran.c
@@ -148,30 +148,22 @@ aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl,
 			      struct amdgpu_reset_context *reset_context)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle;
+	struct list_head *reset_device_list = reset_context->reset_device_list;
 	struct amdgpu_device *tmp_adev = NULL;
-	struct list_head reset_device_list;
 	int r = 0;
 
 	dev_dbg(adev->dev, "aldebaran perform hw reset\n");
+
+	if (reset_device_list == NULL)
+		return -EINVAL;
+
 	if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 2) &&
 	    reset_context->hive == NULL) {
 		/* Wrong context, return error */
 		return -EINVAL;
 	}
 
-	INIT_LIST_HEAD(&reset_device_list);
-	if (reset_context->hive) {
-		list_for_each_entry (tmp_adev,
-				     &reset_context->hive->device_list,
-				     gmc.xgmi.head)
-			list_add_tail(&tmp_adev->reset_list,
-				      &reset_device_list);
-	} else {
-		list_add_tail(&reset_context->reset_req_dev->reset_list,
-			      &reset_device_list);
-	}
-
-	list_for_each_entry (tmp_adev, &reset_device_list, reset_list) {
+	list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
 		mutex_lock(&tmp_adev->reset_cntl->reset_lock);
 		tmp_adev->reset_cntl->active_reset = AMD_RESET_METHOD_MODE2;
 	}
@@ -179,7 +171,7 @@ aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl,
 	 * Mode2 reset doesn't need any sync between nodes in XGMI hive, instead launch
 	 * them together so that they can be completed asynchronously on multiple nodes
 	 */
-	list_for_each_entry (tmp_adev, &reset_device_list, reset_list) {
+	list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
 		/* For XGMI run all resets in parallel to speed up the process */
 		if (tmp_adev->gmc.xgmi.num_physical_nodes > 1) {
 			if (!queue_work(system_unbound_wq,
@@ -197,7 +189,7 @@ aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl,
 
 	/* For XGMI wait for all resets to complete before proceed */
 	if (!r) {
-		list_for_each_entry (tmp_adev, &reset_device_list, reset_list) {
+		list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
 			if (tmp_adev->gmc.xgmi.num_physical_nodes > 1) {
 				flush_work(&tmp_adev->reset_cntl->reset_work);
 				r = tmp_adev->asic_reset_res;
@@ -207,7 +199,7 @@ aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl,
 		}
 	}
 
-	list_for_each_entry (tmp_adev, &reset_device_list, reset_list) {
+	list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
 		mutex_unlock(&tmp_adev->reset_cntl->reset_lock);
 		tmp_adev->reset_cntl->active_reset = AMD_RESET_METHOD_NONE;
 	}
@@ -339,10 +331,13 @@ static int
 aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 				  struct amdgpu_reset_context *reset_context)
 {
+	struct list_head *reset_device_list = reset_context->reset_device_list;
 	struct amdgpu_device *tmp_adev = NULL;
-	struct list_head reset_device_list;
 	int r;
 
+	if (reset_device_list == NULL)
+		return -EINVAL;
+
 	if (reset_context->reset_req_dev->ip_versions[MP1_HWIP][0] ==
 		    IP_VERSION(13, 0, 2) &&
 	    reset_context->hive == NULL) {
@@ -350,19 +345,7 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 		return -EINVAL;
 	}
 
-	INIT_LIST_HEAD(&reset_device_list);
-	if (reset_context->hive) {
-		list_for_each_entry (tmp_adev,
-				     &reset_context->hive->device_list,
-				     gmc.xgmi.head)
-			list_add_tail(&tmp_adev->reset_list,
-				      &reset_device_list);
-	} else {
-		list_add_tail(&reset_context->reset_req_dev->reset_list,
-			      &reset_device_list);
-	}
-
-	list_for_each_entry (tmp_adev, &reset_device_list, reset_list) {
+	list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
 		dev_info(tmp_adev->dev,
 			 "GPU reset succeeded, trying to resume\n");
 		r = aldebaran_mode2_restore_ip(tmp_adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index e146810c700b..d597e2656c47 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -317,7 +317,7 @@ enum amdgpu_kiq_irq {
 	AMDGPU_CP_KIQ_IRQ_DRIVER0 = 0,
 	AMDGPU_CP_KIQ_IRQ_LAST
 };
-
+#define SRIOV_USEC_TIMEOUT  1200000 /* wait 12 * 100ms for SRIOV */
 #define MAX_KIQ_REG_WAIT       5000 /* in usecs, 5ms */
 #define MAX_KIQ_REG_BAILOUT_INTERVAL   5 /* in msecs, 5ms */
 #define MAX_KIQ_REG_TRY 1000
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 3c09dcc0986e..647220a8762d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -96,6 +96,7 @@ struct amdgpu_amdkfd_fence {
 struct amdgpu_kfd_dev {
 	struct kfd_dev *dev;
 	uint64_t vram_used;
+	uint64_t vram_used_aligned;
 	bool init_complete;
 	struct work_struct reset_work;
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index a699134a1e8c..cbd593f7d553 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -40,10 +40,10 @@
 #define AMDGPU_USERPTR_RESTORE_DELAY_MS 1
 
 /*
- * Align VRAM allocations to 2MB to avoid fragmentation caused by 4K allocations in the tail 2MB
+ * Align VRAM availability to 2MB to avoid fragmentation caused by 4K allocations in the tail 2MB
  * BO chunk
  */
-#define VRAM_ALLOCATION_ALIGN (1 << 21)
+#define VRAM_AVAILABLITY_ALIGN (1 << 21)
 
 /* Impose limit on how much memory KFD can use */
 static struct {
@@ -149,7 +149,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 		 * to avoid fragmentation caused by 4K allocations in the tail
 		 * 2M BO chunk.
 		 */
-		vram_needed = ALIGN(size, VRAM_ALLOCATION_ALIGN);
+		vram_needed = size;
 	} else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_USERPTR) {
 		system_mem_needed = size;
 	} else if (!(alloc_flag &
@@ -182,8 +182,10 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 	 */
 	WARN_ONCE(vram_needed && !adev,
 		  "adev reference can't be null when vram is used");
-	if (adev)
+	if (adev) {
 		adev->kfd.vram_used += vram_needed;
+		adev->kfd.vram_used_aligned += ALIGN(vram_needed, VRAM_AVAILABLITY_ALIGN);
+	}
 	kfd_mem_limit.system_mem_used += system_mem_needed;
 	kfd_mem_limit.ttm_mem_used += ttm_mem_needed;
 
@@ -203,8 +205,10 @@ void amdgpu_amdkfd_unreserve_mem_limit(struct amdgpu_device *adev,
 	} else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) {
 		WARN_ONCE(!adev,
 			  "adev reference can't be null when alloc mem flags vram is set");
-		if (adev)
-			adev->kfd.vram_used -= ALIGN(size, VRAM_ALLOCATION_ALIGN);
+		if (adev) {
+			adev->kfd.vram_used -= size;
+			adev->kfd.vram_used_aligned -= ALIGN(size, VRAM_AVAILABLITY_ALIGN);
+		}
 	} else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_USERPTR) {
 		kfd_mem_limit.system_mem_used -= size;
 	} else if (!(alloc_flag &
@@ -1608,15 +1612,14 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev)
 	uint64_t reserved_for_pt =
 		ESTIMATE_PT_SIZE(amdgpu_amdkfd_total_mem_size);
 	size_t available;
-
 	spin_lock(&kfd_mem_limit.mem_limit_lock);
 	available = adev->gmc.real_vram_size
-		- adev->kfd.vram_used
+		- adev->kfd.vram_used_aligned
 		- atomic64_read(&adev->vram_pin_size)
 		- reserved_for_pt;
 	spin_unlock(&kfd_mem_limit.mem_limit_lock);
 
-	return ALIGN_DOWN(available, VRAM_ALLOCATION_ALIGN);
+	return ALIGN_DOWN(available, VRAM_AVAILABLITY_ALIGN);
 }
 
 int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index fd8f3731758e..b81b77a9efa6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -314,7 +314,7 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 					mem_channel_number = vram_info->v30.channel_num;
 					mem_channel_width = vram_info->v30.channel_width;
 					if (vram_width)
-						*vram_width = mem_channel_number * mem_channel_width;
+						*vram_width = mem_channel_number * (1 << mem_channel_width);
 					break;
 				default:
 					return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index d8f1335bc68f..b7bae833c804 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -837,16 +837,12 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 			continue;
 
 		r = amdgpu_vm_bo_update(adev, bo_va, false);
-		if (r) {
-			mutex_unlock(&p->bo_list->bo_list_mutex);
+		if (r)
 			return r;
-		}
 
 		r = amdgpu_sync_fence(&p->job->sync, bo_va->last_pt_update);
-		if (r) {
-			mutex_unlock(&p->bo_list->bo_list_mutex);
+		if (r)
 			return r;
-		}
 	}
 
 	r = amdgpu_vm_handle_moved(adev, vm);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index e2eec985adb3..cb00c7d6f50b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1705,7 +1705,7 @@ static ssize_t amdgpu_reset_dump_register_list_write(struct file *f,
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private;
 	char reg_offset[11];
-	uint32_t *new, *tmp = NULL;
+	uint32_t *new = NULL, *tmp = NULL;
 	int ret, i = 0, len = 0;
 
 	do {
@@ -1747,7 +1747,8 @@ static ssize_t amdgpu_reset_dump_register_list_write(struct file *f,
 	ret = size;
 
 error_free:
-	kfree(tmp);
+	if (tmp != new)
+		kfree(tmp);
 	kfree(new);
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c4a6fe3070b6..e8a0b19b7398 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4742,6 +4742,8 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 	tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
 				    reset_list);
 	amdgpu_reset_reg_dumps(tmp_adev);
+
+	reset_context->reset_device_list = device_list_handle;
 	r = amdgpu_reset_perform_reset(tmp_adev, reset_context);
 	/* If reset handler not implemented, continue; otherwise return */
 	if (r == -ENOSYS)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 5071b96be982..b1099ee79c50 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -272,10 +272,6 @@ void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched)
 	/* Signal all jobs not yet scheduled */
 	for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
 		struct drm_sched_rq *rq = &sched->sched_rq[i];
-
-		if (!rq)
-			continue;
-
 		spin_lock(&rq->lock);
 		list_for_each_entry(s_entity, &rq->entities, list) {
 			while ((s_job = to_drm_sched_job(spsc_queue_pop(&s_entity->job_queue)))) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
index 9e55a5d7a825..ffda1560c648 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
@@ -37,6 +37,7 @@ struct amdgpu_reset_context {
 	struct amdgpu_device *reset_req_dev;
 	struct amdgpu_job *job;
 	struct amdgpu_hive_info *hive;
+	struct list_head *reset_device_list;
 	unsigned long flags;
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 3b4c19412625..134575a3893c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -637,6 +637,8 @@ struct amdgpu_ttm_tt {
 #endif
 };
 
+#define ttm_to_amdgpu_ttm_tt(ptr)	container_of(ptr, struct amdgpu_ttm_tt, ttm)
+
 #ifdef CONFIG_DRM_AMDGPU_USERPTR
 /*
  * amdgpu_ttm_tt_get_user_pages - get device accessible pages that back user
@@ -648,7 +650,7 @@ struct amdgpu_ttm_tt {
 int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 {
 	struct ttm_tt *ttm = bo->tbo.ttm;
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	unsigned long start = gtt->userptr;
 	struct vm_area_struct *vma;
 	struct mm_struct *mm;
@@ -702,7 +704,7 @@ out_unlock:
  */
 bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	bool r = false;
 
 	if (!gtt || !gtt->userptr)
@@ -751,7 +753,7 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_device *bdev,
 				     struct ttm_tt *ttm)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	int write = !(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY);
 	enum dma_data_direction direction = write ?
 		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
@@ -788,7 +790,7 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_device *bdev,
 					struct ttm_tt *ttm)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	int write = !(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY);
 	enum dma_data_direction direction = write ?
 		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
@@ -822,7 +824,7 @@ static void amdgpu_ttm_gart_bind(struct amdgpu_device *adev,
 {
 	struct amdgpu_bo *abo = ttm_to_amdgpu_bo(tbo);
 	struct ttm_tt *ttm = tbo->ttm;
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	if (amdgpu_bo_encrypted(abo))
 		flags |= AMDGPU_PTE_TMZ;
@@ -860,7 +862,7 @@ static int amdgpu_ttm_backend_bind(struct ttm_device *bdev,
 				   struct ttm_resource *bo_mem)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	struct amdgpu_ttm_tt *gtt = (void*)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	uint64_t flags;
 	int r;
 
@@ -927,7 +929,7 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 	struct ttm_operation_ctx ctx = { false, false };
-	struct amdgpu_ttm_tt *gtt = (void *)bo->ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(bo->ttm);
 	struct ttm_placement placement;
 	struct ttm_place placements;
 	struct ttm_resource *tmp;
@@ -998,7 +1000,7 @@ static void amdgpu_ttm_backend_unbind(struct ttm_device *bdev,
 				      struct ttm_tt *ttm)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	/* if the pages have userptr pinning then clear that first */
 	if (gtt->userptr) {
@@ -1025,7 +1027,7 @@ static void amdgpu_ttm_backend_unbind(struct ttm_device *bdev,
 static void amdgpu_ttm_backend_destroy(struct ttm_device *bdev,
 				       struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	if (gtt->usertask)
 		put_task_struct(gtt->usertask);
@@ -1079,7 +1081,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_device *bdev,
 				  struct ttm_operation_ctx *ctx)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	pgoff_t i;
 	int ret;
 
@@ -1113,7 +1115,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_device *bdev,
 static void amdgpu_ttm_tt_unpopulate(struct ttm_device *bdev,
 				     struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	struct amdgpu_device *adev;
 	pgoff_t i;
 
@@ -1182,7 +1184,7 @@ int amdgpu_ttm_tt_set_userptr(struct ttm_buffer_object *bo,
 	/* Set TTM_TT_FLAG_EXTERNAL before populate but after create. */
 	bo->ttm->page_flags |= TTM_TT_FLAG_EXTERNAL;
 
-	gtt = (void *)bo->ttm;
+	gtt = ttm_to_amdgpu_ttm_tt(bo->ttm);
 	gtt->userptr = addr;
 	gtt->userflags = flags;
 
@@ -1199,7 +1201,7 @@ int amdgpu_ttm_tt_set_userptr(struct ttm_buffer_object *bo,
  */
 struct mm_struct *amdgpu_ttm_tt_get_usermm(struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	if (gtt == NULL)
 		return NULL;
@@ -1218,7 +1220,7 @@ struct mm_struct *amdgpu_ttm_tt_get_usermm(struct ttm_tt *ttm)
 bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
 				  unsigned long end, unsigned long *userptr)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	unsigned long size;
 
 	if (gtt == NULL || !gtt->userptr)
@@ -1241,7 +1243,7 @@ bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
  */
 bool amdgpu_ttm_tt_is_userptr(struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	if (gtt == NULL || !gtt->userptr)
 		return false;
@@ -1254,7 +1256,7 @@ bool amdgpu_ttm_tt_is_userptr(struct ttm_tt *ttm)
  */
 bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	if (gtt == NULL)
 		return false;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
index 108e8e8a1a36..576849e95296 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
@@ -496,8 +496,7 @@ static int amdgpu_vkms_sw_init(void *handle)
 	adev_to_drm(adev)->mode_config.max_height = YRES_MAX;
 
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 
 	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c b/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c
index 33a8a7365aef..f0e235f98afb 100644
--- a/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c
@@ -28,13 +28,44 @@
 #include "navi10_enum.h"
 #include "soc15_common.h"
 
+#define regATHUB_MISC_CNTL_V3_0_1			0x00d7
+#define regATHUB_MISC_CNTL_V3_0_1_BASE_IDX		0
+
+
+static uint32_t athub_v3_0_get_cg_cntl(struct amdgpu_device *adev)
+{
+	uint32_t data;
+
+	switch (adev->ip_versions[ATHUB_HWIP][0]) {
+	case IP_VERSION(3, 0, 1):
+		data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_0_1);
+		break;
+	default:
+		data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL);
+		break;
+	}
+	return data;
+}
+
+static void athub_v3_0_set_cg_cntl(struct amdgpu_device *adev, uint32_t data)
+{
+	switch (adev->ip_versions[ATHUB_HWIP][0]) {
+	case IP_VERSION(3, 0, 1):
+		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_0_1, data);
+		break;
+	default:
+		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL, data);
+		break;
+	}
+}
+
 static void
 athub_v3_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 					    bool enable)
 {
 	uint32_t def, data;
 
-	def = data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL);
+	def = data = athub_v3_0_get_cg_cntl(adev);
 
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_ATHUB_MGCG))
 		data |= ATHUB_MISC_CNTL__CG_ENABLE_MASK;
@@ -42,7 +73,7 @@ athub_v3_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 		data &= ~ATHUB_MISC_CNTL__CG_ENABLE_MASK;
 
 	if (def != data)
-		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL, data);
+		athub_v3_0_set_cg_cntl(adev, data);
 }
 
 static void
@@ -51,7 +82,7 @@ athub_v3_0_update_medium_grain_light_sleep(struct amdgpu_device *adev,
 {
 	uint32_t def, data;
 
-	def = data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL);
+	def = data = athub_v3_0_get_cg_cntl(adev);
 
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_ATHUB_LS))
 		data |= ATHUB_MISC_CNTL__CG_MEM_LS_ENABLE_MASK;
@@ -59,7 +90,7 @@ athub_v3_0_update_medium_grain_light_sleep(struct amdgpu_device *adev,
 		data &= ~ATHUB_MISC_CNTL__CG_MEM_LS_ENABLE_MASK;
 
 	if (def != data)
-		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL, data);
+		athub_v3_0_set_cg_cntl(adev, data);
 }
 
 int athub_v3_0_set_clockgating(struct amdgpu_device *adev,
@@ -70,6 +101,7 @@ int athub_v3_0_set_clockgating(struct amdgpu_device *adev,
 
 	switch (adev->ip_versions[ATHUB_HWIP][0]) {
 	case IP_VERSION(3, 0, 0):
+	case IP_VERSION(3, 0, 1):
 	case IP_VERSION(3, 0, 2):
 		athub_v3_0_update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE);
@@ -88,7 +120,7 @@ void athub_v3_0_get_clockgating(struct amdgpu_device *adev, u64 *flags)
 	int data;
 
 	/* AMD_CG_SUPPORT_ATHUB_MGCG */
-	data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL);
+	data = athub_v3_0_get_cg_cntl(adev);
 	if (data & ATHUB_MISC_CNTL__CG_ENABLE_MASK)
 		*flags |= AMD_CG_SUPPORT_ATHUB_MGCG;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 9c964cd3b5d4..288fce7dc0ed 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -2796,8 +2796,7 @@ static int dce_v10_0_sw_init(void *handle)
 	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 
 	adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index e0ad9f27dc3f..cbe5250b31cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -2914,8 +2914,7 @@ static int dce_v11_0_sw_init(void *handle)
 	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 
 	adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index 77f5e998a120..b1c44fab074f 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -2673,8 +2673,7 @@ static int dce_v6_0_sw_init(void *handle)
 	adev_to_drm(adev)->mode_config.max_width = 16384;
 	adev_to_drm(adev)->mode_config.max_height = 16384;
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 	adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true;
 	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 802e5c753271..a22b45c92792 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -2693,8 +2693,11 @@ static int dce_v8_0_sw_init(void *handle)
 	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	if (adev->asic_type == CHIP_HAWAII)
+		/* disable prefer shadow for now due to hibernation issues */
+		adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	else
+		adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 
 	adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index fafbad3cf08d..a2a4dc1844c0 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -4846,7 +4846,7 @@ static int gfx_v10_0_sw_init(void *handle)
 	case IP_VERSION(10, 3, 3):
 	case IP_VERSION(10, 3, 7):
 		adev->gfx.me.num_me = 1;
-		adev->gfx.me.num_pipe_per_me = 2;
+		adev->gfx.me.num_pipe_per_me = 1;
 		adev->gfx.me.num_queue_per_pipe = 1;
 		adev->gfx.mec.num_mec = 2;
 		adev->gfx.mec.num_pipe_per_mec = 4;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 6fd71cb10e54..158d87e6805d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -53,6 +53,7 @@
 #define GFX11_MEC_HPD_SIZE	2048
 
 #define RLCG_UCODE_LOADING_START_ADDRESS	0x00002000L
+#define RLC_PG_DELAY_3_DEFAULT_GC_11_0_1	0x1388
 
 #define regCGTT_WD_CLK_CTRL		0x5086
 #define regCGTT_WD_CLK_CTRL_BASE_IDX	1
@@ -5279,6 +5280,38 @@ static const struct amdgpu_rlc_funcs gfx_v11_0_rlc_funcs = {
 	.update_spm_vmid = gfx_v11_0_update_spm_vmid,
 };
 
+static void gfx_v11_cntl_power_gating(struct amdgpu_device *adev, bool enable)
+{
+	u32 data = RREG32_SOC15(GC, 0, regRLC_PG_CNTL);
+
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG))
+		data |= RLC_PG_CNTL__GFX_POWER_GATING_ENABLE_MASK;
+	else
+		data &= ~RLC_PG_CNTL__GFX_POWER_GATING_ENABLE_MASK;
+
+	WREG32_SOC15(GC, 0, regRLC_PG_CNTL, data);
+
+	// Program RLC_PG_DELAY3 for CGPG hysteresis
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) {
+		switch (adev->ip_versions[GC_HWIP][0]) {
+		case IP_VERSION(11, 0, 1):
+			WREG32_SOC15(GC, 0, regRLC_PG_DELAY_3, RLC_PG_DELAY_3_DEFAULT_GC_11_0_1);
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+static void gfx_v11_cntl_pg(struct amdgpu_device *adev, bool enable)
+{
+	amdgpu_gfx_rlc_enter_safe_mode(adev);
+
+	gfx_v11_cntl_power_gating(adev, enable);
+
+	amdgpu_gfx_rlc_exit_safe_mode(adev);
+}
+
 static int gfx_v11_0_set_powergating_state(void *handle,
 					   enum amd_powergating_state state)
 {
@@ -5293,6 +5326,11 @@ static int gfx_v11_0_set_powergating_state(void *handle,
 	case IP_VERSION(11, 0, 2):
 		amdgpu_gfx_off_ctrl(adev, enable);
 		break;
+	case IP_VERSION(11, 0, 1):
+		gfx_v11_cntl_pg(adev, enable);
+		/* TODO: Enable this when GFXOFF is ready */
+		// amdgpu_gfx_off_ctrl(adev, enable);
+		break;
 	default:
 		break;
 	}
@@ -5310,6 +5348,7 @@ static int gfx_v11_0_set_clockgating_state(void *handle,
 
 	switch (adev->ip_versions[GC_HWIP][0]) {
 	case IP_VERSION(11, 0, 0):
+	case IP_VERSION(11, 0, 1):
 	case IP_VERSION(11, 0, 2):
 	        gfx_v11_0_update_gfx_clock_gating(adev,
 	                        state ==  AMD_CG_STATE_GATE);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 9ae8cdaa033e..f513e2c2e964 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -419,6 +419,7 @@ static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 	uint32_t seq;
 	uint16_t queried_pasid;
 	bool ret;
+	u32 usec_timeout = amdgpu_sriov_vf(adev) ? SRIOV_USEC_TIMEOUT : adev->usec_timeout;
 	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 
@@ -437,7 +438,7 @@ static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 
 		amdgpu_ring_commit(ring);
 		spin_unlock(&adev->gfx.kiq.ring_lock);
-		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
+		r = amdgpu_fence_wait_polling(ring, seq, usec_timeout);
 		if (r < 1) {
 			dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r);
 			return -ETIME;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 22761a3bb818..4603653916f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -896,6 +896,7 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 	uint32_t seq;
 	uint16_t queried_pasid;
 	bool ret;
+	u32 usec_timeout = amdgpu_sriov_vf(adev) ? SRIOV_USEC_TIMEOUT : adev->usec_timeout;
 	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 
@@ -935,7 +936,7 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 
 		amdgpu_ring_commit(ring);
 		spin_unlock(&adev->gfx.kiq.ring_lock);
-		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
+		r = amdgpu_fence_wait_polling(ring, seq, usec_timeout);
 		if (r < 1) {
 			dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r);
 			up_read(&adev->reset_domain->sem);
@@ -1624,12 +1625,15 @@ static int gmc_v9_0_sw_init(void *handle)
 			amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 47);
 		else
 			amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 48);
+		if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2))
+			adev->gmc.translate_further = adev->vm_manager.num_level > 1;
 		break;
 	case IP_VERSION(9, 4, 1):
 		adev->num_vmhubs = 3;
 
 		/* Keep the vm size same with Vega20 */
 		amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 48);
+		adev->gmc.translate_further = adev->vm_manager.num_level > 1;
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
index 39a696cd45b5..29c3484ae1f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
@@ -40,6 +40,156 @@ static void hdp_v5_2_flush_hdp(struct amdgpu_device *adev,
 			0);
 }
 
+static void hdp_v5_2_update_mem_power_gating(struct amdgpu_device *adev,
+					     bool enable)
+{
+	uint32_t hdp_clk_cntl;
+	uint32_t hdp_mem_pwr_cntl;
+
+	if (!(adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS |
+				AMD_CG_SUPPORT_HDP_DS |
+				AMD_CG_SUPPORT_HDP_SD)))
+		return;
+
+	hdp_clk_cntl = RREG32_SOC15(HDP, 0, regHDP_CLK_CNTL);
+	hdp_mem_pwr_cntl = RREG32_SOC15(HDP, 0, regHDP_MEM_POWER_CTRL);
+
+	/* Before doing clock/power mode switch, forced on MEM clock */
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     ATOMIC_MEM_CLK_SOFT_OVERRIDE, 1);
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     RC_MEM_CLK_SOFT_OVERRIDE, 1);
+	WREG32_SOC15(HDP, 0, regHDP_CLK_CNTL, hdp_clk_cntl);
+
+	/* disable clock and power gating before any changing */
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 ATOMIC_MEM_POWER_CTRL_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 ATOMIC_MEM_POWER_LS_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 ATOMIC_MEM_POWER_DS_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 ATOMIC_MEM_POWER_SD_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 RC_MEM_POWER_CTRL_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 RC_MEM_POWER_LS_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 RC_MEM_POWER_DS_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 RC_MEM_POWER_SD_EN, 0);
+	WREG32_SOC15(HDP, 0, regHDP_MEM_POWER_CTRL, hdp_mem_pwr_cntl);
+
+	/* Already disabled above. The actions below are for "enabled" only */
+	if (enable) {
+		/* only one clock gating mode (LS/DS/SD) can be enabled */
+		if (adev->cg_flags & AMD_CG_SUPPORT_HDP_SD) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 ATOMIC_MEM_POWER_SD_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_SD_EN, 1);
+		} else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 ATOMIC_MEM_POWER_LS_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_LS_EN, 1);
+		} else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_DS) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 ATOMIC_MEM_POWER_DS_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_DS_EN, 1);
+		}
+
+		/* confirmed that ATOMIC/RC_MEM_POWER_CTRL_EN have to be set for SRAM LS/DS/SD */
+		if (adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_HDP_DS |
+				      AMD_CG_SUPPORT_HDP_SD)) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+							 ATOMIC_MEM_POWER_CTRL_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_CTRL_EN, 1);
+			WREG32_SOC15(HDP, 0, regHDP_MEM_POWER_CTRL, hdp_mem_pwr_cntl);
+		}
+	}
+
+	/* disable MEM clock override after clock/power mode changing */
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     ATOMIC_MEM_CLK_SOFT_OVERRIDE, 0);
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     RC_MEM_CLK_SOFT_OVERRIDE, 0);
+	WREG32_SOC15(HDP, 0, regHDP_CLK_CNTL, hdp_clk_cntl);
+}
+
+static void hdp_v5_2_update_medium_grain_clock_gating(struct amdgpu_device *adev,
+						      bool enable)
+{
+	uint32_t hdp_clk_cntl;
+
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_HDP_MGCG))
+		return;
+
+	hdp_clk_cntl = RREG32_SOC15(HDP, 0, regHDP_CLK_CNTL);
+
+	if (enable) {
+		hdp_clk_cntl &=
+			~(uint32_t)
+			(HDP_CLK_CNTL__ATOMIC_MEM_CLK_SOFT_OVERRIDE_MASK |
+			 HDP_CLK_CNTL__RC_MEM_CLK_SOFT_OVERRIDE_MASK |
+			 HDP_CLK_CNTL__DBUS_CLK_SOFT_OVERRIDE_MASK |
+			 HDP_CLK_CNTL__DYN_CLK_SOFT_OVERRIDE_MASK |
+			 HDP_CLK_CNTL__XDP_REG_CLK_SOFT_OVERRIDE_MASK |
+			 HDP_CLK_CNTL__HDP_REG_CLK_SOFT_OVERRIDE_MASK);
+	} else {
+		hdp_clk_cntl |= HDP_CLK_CNTL__ATOMIC_MEM_CLK_SOFT_OVERRIDE_MASK |
+			HDP_CLK_CNTL__RC_MEM_CLK_SOFT_OVERRIDE_MASK |
+			HDP_CLK_CNTL__DBUS_CLK_SOFT_OVERRIDE_MASK |
+			HDP_CLK_CNTL__DYN_CLK_SOFT_OVERRIDE_MASK |
+			HDP_CLK_CNTL__XDP_REG_CLK_SOFT_OVERRIDE_MASK |
+			HDP_CLK_CNTL__HDP_REG_CLK_SOFT_OVERRIDE_MASK;
+	}
+
+	WREG32_SOC15(HDP, 0, regHDP_CLK_CNTL, hdp_clk_cntl);
+}
+
+static void hdp_v5_2_get_clockgating_state(struct amdgpu_device *adev,
+					   u64 *flags)
+{
+	uint32_t tmp;
+
+	/* AMD_CG_SUPPORT_HDP_MGCG */
+	tmp = RREG32_SOC15(HDP, 0, regHDP_CLK_CNTL);
+	if (!(tmp & (HDP_CLK_CNTL__ATOMIC_MEM_CLK_SOFT_OVERRIDE_MASK |
+		     HDP_CLK_CNTL__RC_MEM_CLK_SOFT_OVERRIDE_MASK |
+		     HDP_CLK_CNTL__DBUS_CLK_SOFT_OVERRIDE_MASK |
+		     HDP_CLK_CNTL__DYN_CLK_SOFT_OVERRIDE_MASK |
+		     HDP_CLK_CNTL__XDP_REG_CLK_SOFT_OVERRIDE_MASK |
+		     HDP_CLK_CNTL__HDP_REG_CLK_SOFT_OVERRIDE_MASK)))
+		*flags |= AMD_CG_SUPPORT_HDP_MGCG;
+
+	/* AMD_CG_SUPPORT_HDP_LS/DS/SD */
+	tmp = RREG32_SOC15(HDP, 0, regHDP_MEM_POWER_CTRL);
+	if (tmp & HDP_MEM_POWER_CTRL__ATOMIC_MEM_POWER_LS_EN_MASK)
+		*flags |= AMD_CG_SUPPORT_HDP_LS;
+	else if (tmp & HDP_MEM_POWER_CTRL__ATOMIC_MEM_POWER_DS_EN_MASK)
+		*flags |= AMD_CG_SUPPORT_HDP_DS;
+	else if (tmp & HDP_MEM_POWER_CTRL__ATOMIC_MEM_POWER_SD_EN_MASK)
+		*flags |= AMD_CG_SUPPORT_HDP_SD;
+}
+
+static void hdp_v5_2_update_clock_gating(struct amdgpu_device *adev,
+					      bool enable)
+{
+	hdp_v5_2_update_mem_power_gating(adev, enable);
+	hdp_v5_2_update_medium_grain_clock_gating(adev, enable);
+}
+
 const struct amdgpu_hdp_funcs hdp_v5_2_funcs = {
 	.flush_hdp = hdp_v5_2_flush_hdp,
+	.update_clock_gating = hdp_v5_2_update_clock_gating,
+	.get_clock_gating_state = hdp_v5_2_get_clockgating_state,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
index 92dc60a9d209..085e613f3646 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
@@ -727,6 +727,7 @@ static const struct amd_ip_funcs ih_v6_0_ip_funcs = {
 static const struct amdgpu_ih_funcs ih_v6_0_funcs = {
 	.get_wptr = ih_v6_0_get_wptr,
 	.decode_iv = amdgpu_ih_decode_iv_helper,
+	.decode_iv_ts = amdgpu_ih_decode_iv_ts_helper,
 	.set_rptr = ih_v6_0_set_rptr
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c
index cac72ced94c8..e8058edc1d10 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c
@@ -518,18 +518,41 @@ static u64 mmhub_v3_0_1_get_mc_fb_offset(struct amdgpu_device *adev)
 static void mmhub_v3_0_1_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 							  bool enable)
 {
-	//TODO
+	uint32_t def, data;
+
+	def = data = RREG32_SOC15(MMHUB, 0, regMM_ATC_L2_MISC_CG);
+
+	if (enable)
+		data |= MM_ATC_L2_MISC_CG__ENABLE_MASK;
+	else
+		data &= ~MM_ATC_L2_MISC_CG__ENABLE_MASK;
+
+	if (def != data)
+		WREG32_SOC15(MMHUB, 0, regMM_ATC_L2_MISC_CG, data);
 }
 
 static void mmhub_v3_0_1_update_medium_grain_light_sleep(struct amdgpu_device *adev,
 							 bool enable)
 {
-	//TODO
+	uint32_t def, data;
+
+	def = data = RREG32_SOC15(MMHUB, 0, regMM_ATC_L2_MISC_CG);
+
+	if (enable)
+		data |= MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
+	else
+		data &= ~MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
+
+	if (def != data)
+		WREG32_SOC15(MMHUB, 0, regMM_ATC_L2_MISC_CG, data);
 }
 
 static int mmhub_v3_0_1_set_clockgating(struct amdgpu_device *adev,
 					enum amd_clockgating_state state)
 {
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	mmhub_v3_0_1_update_medium_grain_clock_gating(adev,
 			state == AMD_CG_STATE_GATE);
 	mmhub_v3_0_1_update_medium_grain_light_sleep(adev,
@@ -539,7 +562,20 @@ static int mmhub_v3_0_1_set_clockgating(struct amdgpu_device *adev,
 
 static void mmhub_v3_0_1_get_clockgating(struct amdgpu_device *adev, u64 *flags)
 {
-	//TODO
+	int data;
+
+	if (amdgpu_sriov_vf(adev))
+		*flags = 0;
+
+	data = RREG32_SOC15(MMHUB, 0, regMM_ATC_L2_MISC_CG);
+
+	/* AMD_CG_SUPPORT_MC_MGCG */
+	if (data & MM_ATC_L2_MISC_CG__ENABLE_MASK)
+		*flags |= AMD_CG_SUPPORT_MC_MGCG;
+
+	/* AMD_CG_SUPPORT_MC_LS */
+	if (data & MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK)
+		*flags |= AMD_CG_SUPPORT_MC_LS;
 }
 
 const struct amdgpu_mmhub_funcs mmhub_v3_0_1_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index 4b5396d3e60f..eec13cb5bf75 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -409,9 +409,11 @@ static u32 navi10_ih_get_wptr(struct amdgpu_device *adev,
 	u32 wptr, tmp;
 	struct amdgpu_ih_regs *ih_regs;
 
-	if (ih == &adev->irq.ih) {
+	if (ih == &adev->irq.ih || ih == &adev->irq.ih_soft) {
 		/* Only ring0 supports writeback. On other rings fall back
 		 * to register-based code with overflow checking below.
+		 * ih_soft ring doesn't have any backing hardware registers,
+		 * update wptr and return.
 		 */
 		wptr = le32_to_cpu(*ih->wptr_cpu);
 
@@ -483,6 +485,9 @@ static void navi10_ih_set_rptr(struct amdgpu_device *adev,
 {
 	struct amdgpu_ih_regs *ih_regs;
 
+	if (ih == &adev->irq.ih_soft)
+		return;
+
 	if (ih->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
 		*ih->rptr_cpu = ih->rptr;
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
index a2588200ea58..0b2ac418e4ac 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
@@ -101,6 +101,16 @@ static int psp_v12_0_init_microcode(struct psp_context *psp)
 		adev->psp.dtm_context.context.bin_desc.start_addr =
 			(uint8_t *)adev->psp.hdcp_context.context.bin_desc.start_addr +
 			le32_to_cpu(ta_hdr->dtm.offset_bytes);
+
+		if (adev->apu_flags & AMD_APU_IS_RENOIR) {
+			adev->psp.securedisplay_context.context.bin_desc.fw_version =
+				le32_to_cpu(ta_hdr->securedisplay.fw_version);
+			adev->psp.securedisplay_context.context.bin_desc.size_bytes =
+				le32_to_cpu(ta_hdr->securedisplay.size_bytes);
+			adev->psp.securedisplay_context.context.bin_desc.start_addr =
+				(uint8_t *)adev->psp.hdcp_context.context.bin_desc.start_addr +
+				le32_to_cpu(ta_hdr->securedisplay.offset_bytes);
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index 726a5bba40b2..a75a286e1ecf 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -20,7 +20,6 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  */
-#include <linux/dev_printk.h>
 #include <drm/drm_drv.h>
 #include <linux/vmalloc.h>
 #include "amdgpu.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 52816de5e17b..1ff7fc7bb340 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -546,8 +546,10 @@ static int soc21_common_early_init(void *handle)
 	case IP_VERSION(11, 0, 0):
 		adev->cg_flags = AMD_CG_SUPPORT_GFX_CGCG |
 			AMD_CG_SUPPORT_GFX_CGLS |
+#if 0
 			AMD_CG_SUPPORT_GFX_3D_CGCG |
 			AMD_CG_SUPPORT_GFX_3D_CGLS |
+#endif
 			AMD_CG_SUPPORT_GFX_MGCG |
 			AMD_CG_SUPPORT_REPEATER_FGCG |
 			AMD_CG_SUPPORT_GFX_FGCG |
@@ -575,7 +577,9 @@ static int soc21_common_early_init(void *handle)
 			AMD_CG_SUPPORT_VCN_MGCG |
 			AMD_CG_SUPPORT_JPEG_MGCG |
 			AMD_CG_SUPPORT_ATHUB_MGCG |
-			AMD_CG_SUPPORT_ATHUB_LS;
+			AMD_CG_SUPPORT_ATHUB_LS |
+			AMD_CG_SUPPORT_IH_CG |
+			AMD_CG_SUPPORT_HDP_SD;
 		adev->pg_flags =
 			AMD_PG_SUPPORT_VCN |
 			AMD_PG_SUPPORT_VCN_DPG |
@@ -586,9 +590,23 @@ static int soc21_common_early_init(void *handle)
 		break;
 	case IP_VERSION(11, 0, 1):
 		adev->cg_flags =
+			AMD_CG_SUPPORT_GFX_CGCG |
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_FGCG |
+			AMD_CG_SUPPORT_REPEATER_FGCG |
+			AMD_CG_SUPPORT_GFX_PERF_CLK |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_HDP_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_ATHUB_MGCG |
+			AMD_CG_SUPPORT_ATHUB_LS |
+			AMD_CG_SUPPORT_IH_CG |
 			AMD_CG_SUPPORT_VCN_MGCG |
 			AMD_CG_SUPPORT_JPEG_MGCG;
 		adev->pg_flags =
+			AMD_PG_SUPPORT_GFX_PG |
 			AMD_PG_SUPPORT_JPEG;
 		adev->external_rev_id = adev->rev_id + 0x1;
 		break;
@@ -683,6 +701,7 @@ static int soc21_common_set_clockgating_state(void *handle,
 
 	switch (adev->ip_versions[NBIO_HWIP][0]) {
 	case IP_VERSION(4, 3, 0):
+	case IP_VERSION(4, 3, 1):
 		adev->nbio.funcs->update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE);
 		adev->nbio.funcs->update_medium_grain_light_sleep(adev,
@@ -690,6 +709,10 @@ static int soc21_common_set_clockgating_state(void *handle,
 		adev->hdp.funcs->update_clock_gating(adev,
 				state == AMD_CG_STATE_GATE);
 		break;
+	case IP_VERSION(7, 7, 0):
+		adev->hdp.funcs->update_clock_gating(adev,
+				state == AMD_CG_STATE_GATE);
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index ca14c3ef742e..fb2d74f30448 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -1115,7 +1115,7 @@ static int vcn_v4_0_start(struct amdgpu_device *adev)
  *
  * Stop VCN block with dpg mode
  */
-static int vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
+static void vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 {
 	uint32_t tmp;
 
@@ -1133,7 +1133,6 @@ static int vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 	/* disable dynamic power gating mode */
 	WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, regUVD_POWER_STATUS), 0,
 		~UVD_POWER_STATUS__UVD_PG_MODE_MASK);
-	return 0;
 }
 
 /**
@@ -1154,7 +1153,7 @@ static int vcn_v4_0_stop(struct amdgpu_device *adev)
 		fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
 
 		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v4_0_stop_dpg_mode(adev, i);
+			vcn_v4_0_stop_dpg_mode(adev, i);
 			continue;
 		}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index cdd599a08125..03b7066471f9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -334,9 +334,11 @@ static u32 vega10_ih_get_wptr(struct amdgpu_device *adev,
 	u32 wptr, tmp;
 	struct amdgpu_ih_regs *ih_regs;
 
-	if (ih == &adev->irq.ih) {
+	if (ih == &adev->irq.ih || ih == &adev->irq.ih_soft) {
 		/* Only ring0 supports writeback. On other rings fall back
 		 * to register-based code with overflow checking below.
+		 * ih_soft ring doesn't have any backing hardware registers,
+		 * update wptr and return.
 		 */
 		wptr = le32_to_cpu(*ih->wptr_cpu);
 
@@ -409,6 +411,9 @@ static void vega10_ih_set_rptr(struct amdgpu_device *adev,
 {
 	struct amdgpu_ih_regs *ih_regs;
 
+	if (ih == &adev->irq.ih_soft)
+		return;
+
 	if (ih->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
 		*ih->rptr_cpu = ih->rptr;
diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
index 3b4eb8285943..2022ffbb8dba 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
@@ -385,9 +385,11 @@ static u32 vega20_ih_get_wptr(struct amdgpu_device *adev,
 	u32 wptr, tmp;
 	struct amdgpu_ih_regs *ih_regs;
 
-	if (ih == &adev->irq.ih) {
+	if (ih == &adev->irq.ih || ih == &adev->irq.ih_soft) {
 		/* Only ring0 supports writeback. On other rings fall back
 		 * to register-based code with overflow checking below.
+		 * ih_soft ring doesn't have any backing hardware registers,
+		 * update wptr and return.
 		 */
 		wptr = le32_to_cpu(*ih->wptr_cpu);
 
@@ -461,6 +463,9 @@ static void vega20_ih_set_rptr(struct amdgpu_device *adev,
 {
 	struct amdgpu_ih_regs *ih_regs;
 
+	if (ih == &adev->irq.ih_soft)
+		return;
+
 	if (ih->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
 		*ih->rptr_cpu = ih->rptr;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 2b3d8bc8f0aa..dc774ddf3445 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -874,7 +874,7 @@ static int kfd_ioctl_wait_events(struct file *filp, struct kfd_process *p,
 	err = kfd_wait_on_events(p, args->num_events,
 			(void __user *)args->events_ptr,
 			(args->wait_for_all != 0),
-			args->timeout, &args->wait_result);
+			&args->timeout, &args->wait_result);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index f5853835f03a..357298e69495 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -102,13 +102,18 @@ static void kfd_device_info_set_sdma_info(struct kfd_dev *kfd)
 
 	switch (sdma_version) {
 	case IP_VERSION(6, 0, 0):
-	case IP_VERSION(6, 0, 1):
 	case IP_VERSION(6, 0, 2):
 		/* Reserve 1 for paging and 1 for gfx */
 		kfd->device_info.num_reserved_sdma_queues_per_engine = 2;
 		/* BIT(0)=engine-0 queue-0; BIT(1)=engine-1 queue-0; BIT(2)=engine-0 queue-1; ... */
 		kfd->device_info.reserved_sdma_queues_bitmap = 0xFULL;
 		break;
+	case IP_VERSION(6, 0, 1):
+		/* Reserve 1 for paging and 1 for gfx */
+		kfd->device_info.num_reserved_sdma_queues_per_engine = 2;
+		/* BIT(0)=engine-0 queue-0; BIT(1)=engine-0 queue-1; ... */
+		kfd->device_info.reserved_sdma_queues_bitmap = 0x3ULL;
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 3942a56c28bb..83e3ce9f6049 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -894,7 +894,8 @@ static long user_timeout_to_jiffies(uint32_t user_timeout_ms)
 	return msecs_to_jiffies(user_timeout_ms) + 1;
 }
 
-static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
+static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters,
+			 bool undo_auto_reset)
 {
 	uint32_t i;
 
@@ -903,6 +904,9 @@ static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
 			spin_lock(&waiters[i].event->lock);
 			remove_wait_queue(&waiters[i].event->wq,
 					  &waiters[i].wait);
+			if (undo_auto_reset && waiters[i].activated &&
+			    waiters[i].event && waiters[i].event->auto_reset)
+				set_event(waiters[i].event);
 			spin_unlock(&waiters[i].event->lock);
 		}
 
@@ -911,7 +915,7 @@ static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
 
 int kfd_wait_on_events(struct kfd_process *p,
 		       uint32_t num_events, void __user *data,
-		       bool all, uint32_t user_timeout_ms,
+		       bool all, uint32_t *user_timeout_ms,
 		       uint32_t *wait_result)
 {
 	struct kfd_event_data __user *events =
@@ -920,7 +924,7 @@ int kfd_wait_on_events(struct kfd_process *p,
 	int ret = 0;
 
 	struct kfd_event_waiter *event_waiters = NULL;
-	long timeout = user_timeout_to_jiffies(user_timeout_ms);
+	long timeout = user_timeout_to_jiffies(*user_timeout_ms);
 
 	event_waiters = alloc_event_waiters(num_events);
 	if (!event_waiters) {
@@ -970,15 +974,11 @@ int kfd_wait_on_events(struct kfd_process *p,
 		}
 
 		if (signal_pending(current)) {
-			/*
-			 * This is wrong when a nonzero, non-infinite timeout
-			 * is specified. We need to use
-			 * ERESTARTSYS_RESTARTBLOCK, but struct restart_block
-			 * contains a union with data for each user and it's
-			 * in generic kernel code that I don't want to
-			 * touch yet.
-			 */
 			ret = -ERESTARTSYS;
+			if (*user_timeout_ms != KFD_EVENT_TIMEOUT_IMMEDIATE &&
+			    *user_timeout_ms != KFD_EVENT_TIMEOUT_INFINITE)
+				*user_timeout_ms = jiffies_to_msecs(
+					max(0l, timeout-1));
 			break;
 		}
 
@@ -1019,7 +1019,7 @@ int kfd_wait_on_events(struct kfd_process *p,
 					       event_waiters, events);
 
 out_unlock:
-	free_waiters(num_events, event_waiters);
+	free_waiters(num_events, event_waiters, ret == -ERESTARTSYS);
 	mutex_unlock(&p->event_mutex);
 out:
 	if (ret)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index d03a3b9c9c5d..bf610e3b683b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1317,7 +1317,7 @@ void kfd_event_free_process(struct kfd_process *p);
 int kfd_event_mmap(struct kfd_process *process, struct vm_area_struct *vma);
 int kfd_wait_on_events(struct kfd_process *p,
 		       uint32_t num_events, void __user *data,
-		       bool all, uint32_t user_timeout_ms,
+		       bool all, uint32_t *user_timeout_ms,
 		       uint32_t *wait_result);
 void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
 				uint32_t valid_id_bits);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index a67ba8879a56..11074cc8c333 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -541,7 +541,6 @@ svm_range_vram_node_new(struct amdgpu_device *adev, struct svm_range *prange,
 		kfree(svm_bo);
 		return -ESRCH;
 	}
-	svm_bo->svms = prange->svms;
 	svm_bo->eviction_fence =
 		amdgpu_amdkfd_fence_create(dma_fence_context_alloc(1),
 					   mm,
@@ -3273,7 +3272,6 @@ int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence)
 static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 {
 	struct svm_range_bo *svm_bo;
-	struct kfd_process *p;
 	struct mm_struct *mm;
 	int r = 0;
 
@@ -3281,13 +3279,12 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 	if (!svm_bo_ref_unless_zero(svm_bo))
 		return; /* svm_bo was freed while eviction was pending */
 
-	/* svm_range_bo_release destroys this worker thread. So during
-	 * the lifetime of this thread, kfd_process and mm will be valid.
-	 */
-	p = container_of(svm_bo->svms, struct kfd_process, svms);
-	mm = p->mm;
-	if (!mm)
+	if (mmget_not_zero(svm_bo->eviction_fence->mm)) {
+		mm = svm_bo->eviction_fence->mm;
+	} else {
+		svm_range_bo_unref(svm_bo);
 		return;
+	}
 
 	mmap_read_lock(mm);
 	spin_lock(&svm_bo->list_lock);
@@ -3305,8 +3302,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 
 		mutex_lock(&prange->migrate_mutex);
 		do {
-			r = svm_migrate_vram_to_ram(prange,
-						svm_bo->eviction_fence->mm,
+			r = svm_migrate_vram_to_ram(prange, mm,
 						KFD_MIGRATE_TRIGGER_TTM_EVICTION);
 		} while (!r && prange->actual_loc && --retries);
 
@@ -3324,6 +3320,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 	}
 	spin_unlock(&svm_bo->list_lock);
 	mmap_read_unlock(mm);
+	mmput(mm);
 
 	dma_fence_signal(&svm_bo->eviction_fence->base);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index 9156b041ef17..cfac13ad06ef 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -46,7 +46,6 @@ struct svm_range_bo {
 	spinlock_t			list_lock;
 	struct amdgpu_amdkfd_fence	*eviction_fence;
 	struct work_struct		eviction_work;
-	struct svm_range_list		*svms;
 	uint32_t			evicting;
 	struct work_struct		release_work;
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 25990bec600d..3f0a4a415907 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1392,8 +1392,8 @@ static int kfd_build_p2p_node_entry(struct kfd_topology_device *dev,
 
 static int kfd_create_indirect_link_prop(struct kfd_topology_device *kdev, int gpu_node)
 {
+	struct kfd_iolink_properties *gpu_link, *tmp_link, *cpu_link;
 	struct kfd_iolink_properties *props = NULL, *props2 = NULL;
-	struct kfd_iolink_properties *gpu_link, *cpu_link;
 	struct kfd_topology_device *cpu_dev;
 	int ret = 0;
 	int i, num_cpu;
@@ -1416,16 +1416,19 @@ static int kfd_create_indirect_link_prop(struct kfd_topology_device *kdev, int g
 			continue;
 
 		/* find CPU <-->  CPU links */
+		cpu_link = NULL;
 		cpu_dev = kfd_topology_device_by_proximity_domain(i);
 		if (cpu_dev) {
-			list_for_each_entry(cpu_link,
+			list_for_each_entry(tmp_link,
 					&cpu_dev->io_link_props, list) {
-				if (cpu_link->node_to == gpu_link->node_to)
+				if (tmp_link->node_to == gpu_link->node_to) {
+					cpu_link = tmp_link;
 					break;
+				}
 			}
 		}
 
-		if (cpu_link->node_to != gpu_link->node_to)
+		if (!cpu_link)
 			return -ENOMEM;
 
 		/* CPU <--> CPU <--> GPU, GPU node*/
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 8660d93cc405..5140d9c2bf3b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3825,8 +3825,11 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev)
 	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	if (adev->asic_type == CHIP_HAWAII)
+		/* disable prefer shadow for now due to hibernation issues */
+		adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	else
+		adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 	/* indicates support for immediate flip */
 	adev_to_drm(adev)->mode_config.async_page_flip = true;
 
@@ -4135,6 +4138,7 @@ static void register_backlight_device(struct amdgpu_display_manager *dm,
 	}
 }
 
+static void amdgpu_set_panel_orientation(struct drm_connector *connector);
 
 /*
  * In this architecture, the association
@@ -4326,6 +4330,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 					adev_to_drm(adev)->vblank_disable_immediate = false;
 			}
 		}
+		amdgpu_set_panel_orientation(&aconnector->base);
 	}
 
 	/* Software is initialized. Now we can register interrupt handlers. */
@@ -6684,6 +6689,10 @@ static void amdgpu_set_panel_orientation(struct drm_connector *connector)
 	    connector->connector_type != DRM_MODE_CONNECTOR_LVDS)
 		return;
 
+	mutex_lock(&connector->dev->mode_config.mutex);
+	amdgpu_dm_connector_get_modes(connector);
+	mutex_unlock(&connector->dev->mode_config.mutex);
+
 	encoder = amdgpu_dm_connector_to_encoder(connector);
 	if (!encoder)
 		return;
@@ -6728,8 +6737,6 @@ static void amdgpu_dm_connector_ddc_get_modes(struct drm_connector *connector,
 		 * restored here.
 		 */
 		amdgpu_dm_update_freesync_caps(connector, edid);
-
-		amdgpu_set_panel_orientation(connector);
 	} else {
 		amdgpu_dm_connector->num_modes = 0;
 	}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index b841b8b0a9d8..fca7cf9dbaee 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -660,7 +660,7 @@ static int get_plane_modifiers(struct amdgpu_device *adev, unsigned int plane_ty
 			add_gfx10_1_modifiers(adev, mods, &size, &capacity);
 		break;
 	case AMDGPU_FAMILY_GC_11_0_0:
-	case AMDGPU_FAMILY_GC_11_0_2:
+	case AMDGPU_FAMILY_GC_11_0_1:
 		add_gfx11_modifiers(adev, mods, &size, &capacity);
 		break;
 	}
@@ -1412,7 +1412,7 @@ static bool dm_plane_format_mod_supported(struct drm_plane *plane,
 		}
 		break;
 	case AMDGPU_FAMILY_GC_11_0_0:
-	case AMDGPU_FAMILY_GC_11_0_2:
+	case AMDGPU_FAMILY_GC_11_0_1:
 		switch (AMD_FMT_MOD_GET(TILE, modifier)) {
 		case AMD_FMT_MOD_TILE_GFX11_256K_R_X:
 		case AMD_FMT_MOD_TILE_GFX9_64K_R_X:
diff --git a/drivers/gpu/drm/amd/display/dc/basics/conversion.c b/drivers/gpu/drm/amd/display/dc/basics/conversion.c
index 6767fab55c26..352e9afb85c6 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/conversion.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/conversion.c
@@ -100,3 +100,24 @@ void convert_float_matrix(
 		matrix[i] = (uint16_t)reg_value;
 	}
 }
+
+static uint32_t find_gcd(uint32_t a, uint32_t b)
+{
+	uint32_t remainder = 0;
+	while (b != 0) {
+		remainder = a % b;
+		a = b;
+		b = remainder;
+	}
+	return a;
+}
+
+void reduce_fraction(uint32_t num, uint32_t den,
+		uint32_t *out_num, uint32_t *out_den)
+{
+	uint32_t gcd = 0;
+
+	gcd = find_gcd(num, den);
+	*out_num = num / gcd;
+	*out_den = den / gcd;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/basics/conversion.h b/drivers/gpu/drm/amd/display/dc/basics/conversion.h
index ade785c4fdc7..81da4e6f7a1a 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/conversion.h
+++ b/drivers/gpu/drm/amd/display/dc/basics/conversion.h
@@ -38,6 +38,9 @@ void convert_float_matrix(
 	struct fixed31_32 *flt,
 	uint32_t buffer_size);
 
+void reduce_fraction(uint32_t num, uint32_t den,
+		uint32_t *out_num, uint32_t *out_den);
+
 static inline unsigned int log_2(unsigned int num)
 {
 	return ilog2(num);
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
index 4c76091fd1f2..f276abb63bcd 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
@@ -337,7 +337,7 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p
 	    break;
 	}
 
-	case AMDGPU_FAMILY_GC_11_0_2: {
+	case AMDGPU_FAMILY_GC_11_0_1: {
 		struct clk_mgr_dcn314 *clk_mgr = kzalloc(sizeof(*clk_mgr), GFP_KERNEL);
 
 		if (clk_mgr == NULL) {
@@ -397,7 +397,7 @@ void dc_destroy_clk_mgr(struct clk_mgr *clk_mgr_base)
 		dcn32_clk_mgr_destroy(clk_mgr);
 		break;
 
-	case AMDGPU_FAMILY_GC_11_0_2:
+	case AMDGPU_FAMILY_GC_11_0_1:
 		dcn314_clk_mgr_destroy(clk_mgr);
 		break;
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
index 0202dc682682..ca6dfd2d7561 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
@@ -24,10 +24,9 @@
  */
 
 #include "dccg.h"
-#include "clk_mgr_internal.h"
+#include "rn_clk_mgr.h"
 
 #include "dcn20/dcn20_clk_mgr.h"
-#include "rn_clk_mgr.h"
 #include "dml/dcn20/dcn20_fpu.h"
 
 #include "dce100/dce_clk_mgr.h"
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h
index 2e088c5171b2..f1319957e400 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h
@@ -28,6 +28,7 @@
 
 #include "clk_mgr.h"
 #include "dm_pp_smu.h"
+#include "clk_mgr_internal.h"
 
 extern struct wm_table ddr4_wm_table_gs;
 extern struct wm_table lpddr4_wm_table_gs;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
index ee99974b3b62..beb025cd3dc2 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
@@ -307,16 +307,6 @@ static void dcn314_enable_pme_wa(struct clk_mgr *clk_mgr_base)
 	dcn314_smu_enable_pme_wa(clk_mgr);
 }
 
-void dcn314_init_clocks(struct clk_mgr *clk_mgr)
-{
-	memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks));
-	// Assumption is that boot state always supports pstate
-	clk_mgr->clks.p_state_change_support = true;
-	clk_mgr->clks.prev_p_state_change_support = true;
-	clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN;
-	clk_mgr->clks.zstate_support = DCN_ZSTATE_SUPPORT_UNKNOWN;
-}
-
 bool dcn314_are_clock_states_equal(struct dc_clocks *a,
 		struct dc_clocks *b)
 {
@@ -425,7 +415,7 @@ static struct wm_table lpddr5_wm_table = {
 	}
 };
 
-static DpmClocks_t dummy_clocks;
+static DpmClocks314_t dummy_clocks;
 
 static struct dcn314_watermarks dummy_wms = { 0 };
 
@@ -510,7 +500,7 @@ static void dcn314_notify_wm_ranges(struct clk_mgr *clk_mgr_base)
 static void dcn314_get_dpm_table_from_smu(struct clk_mgr_internal *clk_mgr,
 		struct dcn314_smu_dpm_clks *smu_dpm_clks)
 {
-	DpmClocks_t *table = smu_dpm_clks->dpm_clks;
+	DpmClocks314_t *table = smu_dpm_clks->dpm_clks;
 
 	if (!clk_mgr->smu_ver)
 		return;
@@ -527,6 +517,26 @@ static void dcn314_get_dpm_table_from_smu(struct clk_mgr_internal *clk_mgr,
 	dcn314_smu_transfer_dpm_table_smu_2_dram(clk_mgr);
 }
 
+static inline bool is_valid_clock_value(uint32_t clock_value)
+{
+	return clock_value > 1 && clock_value < 100000;
+}
+
+static unsigned int convert_wck_ratio(uint8_t wck_ratio)
+{
+	switch (wck_ratio) {
+	case WCK_RATIO_1_2:
+		return 2;
+
+	case WCK_RATIO_1_4:
+		return 4;
+
+	default:
+		break;
+	}
+	return 1;
+}
+
 static uint32_t find_max_clk_value(const uint32_t clocks[], uint32_t num_clocks)
 {
 	uint32_t max = 0;
@@ -540,89 +550,127 @@ static uint32_t find_max_clk_value(const uint32_t clocks[], uint32_t num_clocks)
 	return max;
 }
 
-static unsigned int find_clk_for_voltage(
-		const DpmClocks_t *clock_table,
-		const uint32_t clocks[],
-		unsigned int voltage)
-{
-	int i;
-	int max_voltage = 0;
-	int clock = 0;
-
-	for (i = 0; i < NUM_SOC_VOLTAGE_LEVELS; i++) {
-		if (clock_table->SocVoltage[i] == voltage) {
-			return clocks[i];
-		} else if (clock_table->SocVoltage[i] >= max_voltage &&
-				clock_table->SocVoltage[i] < voltage) {
-			max_voltage = clock_table->SocVoltage[i];
-			clock = clocks[i];
-		}
-	}
-
-	ASSERT(clock);
-	return clock;
-}
-
 static void dcn314_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk_mgr,
 						    struct integrated_info *bios_info,
-						    const DpmClocks_t *clock_table)
+						    const DpmClocks314_t *clock_table)
 {
-	int i, j;
 	struct clk_bw_params *bw_params = clk_mgr->base.bw_params;
-	uint32_t max_dispclk = 0, max_dppclk = 0;
-
-	j = -1;
-
-	ASSERT(NUM_DF_PSTATE_LEVELS <= MAX_NUM_DPM_LVL);
-
-	/* Find lowest DPM, FCLK is filled in reverse order*/
+	struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1];
+	uint32_t max_pstate = 0,  max_fclk = 0,  min_pstate = 0, max_dispclk = 0, max_dppclk = 0;
+	int i;
 
-	for (i = NUM_DF_PSTATE_LEVELS - 1; i >= 0; i--) {
-		if (clock_table->DfPstateTable[i].FClk != 0) {
-			j = i;
-			break;
+	/* Find highest valid fclk pstate */
+	for (i = 0; i < clock_table->NumDfPstatesEnabled; i++) {
+		if (is_valid_clock_value(clock_table->DfPstateTable[i].FClk) &&
+		    clock_table->DfPstateTable[i].FClk > max_fclk) {
+			max_fclk = clock_table->DfPstateTable[i].FClk;
+			max_pstate = i;
 		}
 	}
 
-	if (j == -1) {
-		/* clock table is all 0s, just use our own hardcode */
-		ASSERT(0);
-		return;
-	}
-
-	bw_params->clk_table.num_entries = j + 1;
+	/* We expect the table to contain at least one valid fclk entry. */
+	ASSERT(is_valid_clock_value(max_fclk));
 
-	/* dispclk and dppclk can be max at any voltage, same number of levels for both */
+	/* Dispclk and dppclk can be max at any voltage, same number of levels for both */
 	if (clock_table->NumDispClkLevelsEnabled <= NUM_DISPCLK_DPM_LEVELS &&
 	    clock_table->NumDispClkLevelsEnabled <= NUM_DPPCLK_DPM_LEVELS) {
 		max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled);
 		max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled);
 	} else {
+		/* Invalid number of entries in the table from PMFW. */
 		ASSERT(0);
 	}
 
-	for (i = 0; i < bw_params->clk_table.num_entries; i++, j--) {
-		bw_params->clk_table.entries[i].fclk_mhz = clock_table->DfPstateTable[j].FClk;
-		bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[j].MemClk;
-		bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[j].Voltage;
-		switch (clock_table->DfPstateTable[j].WckRatio) {
-		case WCK_RATIO_1_2:
-			bw_params->clk_table.entries[i].wck_ratio = 2;
-			break;
-		case WCK_RATIO_1_4:
-			bw_params->clk_table.entries[i].wck_ratio = 4;
-			break;
-		default:
-			bw_params->clk_table.entries[i].wck_ratio = 1;
+	/* Base the clock table on dcfclk, need at least one entry regardless of pmfw table */
+	for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) {
+		uint32_t min_fclk = clock_table->DfPstateTable[0].FClk;
+		int j;
+
+		for (j = 1; j < clock_table->NumDfPstatesEnabled; j++) {
+			if (is_valid_clock_value(clock_table->DfPstateTable[j].FClk) &&
+			    clock_table->DfPstateTable[j].FClk < min_fclk &&
+			    clock_table->DfPstateTable[j].Voltage <= clock_table->SocVoltage[i]) {
+				min_fclk = clock_table->DfPstateTable[j].FClk;
+				min_pstate = j;
+			}
 		}
-		bw_params->clk_table.entries[i].dcfclk_mhz = find_clk_for_voltage(clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[j].Voltage);
-		bw_params->clk_table.entries[i].socclk_mhz = find_clk_for_voltage(clock_table, clock_table->SocClocks, clock_table->DfPstateTable[j].Voltage);
+
+		/* First search defaults for the clocks we don't read using closest lower or equal default dcfclk */
+		for (j = bw_params->clk_table.num_entries - 1; j > 0; j--)
+			if (bw_params->clk_table.entries[j].dcfclk_mhz <= clock_table->DcfClocks[i])
+				break;
+
+		bw_params->clk_table.entries[i].phyclk_mhz = bw_params->clk_table.entries[j].phyclk_mhz;
+		bw_params->clk_table.entries[i].phyclk_d18_mhz = bw_params->clk_table.entries[j].phyclk_d18_mhz;
+		bw_params->clk_table.entries[i].dtbclk_mhz = bw_params->clk_table.entries[j].dtbclk_mhz;
+
+		/* Now update clocks we do read */
+		bw_params->clk_table.entries[i].fclk_mhz = min_fclk;
+		bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[min_pstate].MemClk;
+		bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[min_pstate].Voltage;
+		bw_params->clk_table.entries[i].dcfclk_mhz = clock_table->DcfClocks[i];
+		bw_params->clk_table.entries[i].socclk_mhz = clock_table->SocClocks[i];
 		bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk;
 		bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk;
+		bw_params->clk_table.entries[i].wck_ratio = convert_wck_ratio(
+			clock_table->DfPstateTable[min_pstate].WckRatio);
+	};
+
+	/* Make sure to include at least one entry at highest pstate */
+	if (max_pstate != min_pstate || i == 0) {
+		if (i > MAX_NUM_DPM_LVL - 1)
+			i = MAX_NUM_DPM_LVL - 1;
+
+		bw_params->clk_table.entries[i].fclk_mhz = max_fclk;
+		bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[max_pstate].MemClk;
+		bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[max_pstate].Voltage;
+		bw_params->clk_table.entries[i].dcfclk_mhz = find_max_clk_value(clock_table->DcfClocks, NUM_DCFCLK_DPM_LEVELS);
+		bw_params->clk_table.entries[i].socclk_mhz = find_max_clk_value(clock_table->SocClocks, NUM_SOCCLK_DPM_LEVELS);
+		bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk;
+		bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk;
+		bw_params->clk_table.entries[i].wck_ratio = convert_wck_ratio(
+			clock_table->DfPstateTable[max_pstate].WckRatio);
+		i++;
 	}
+	bw_params->clk_table.num_entries = i--;
+
+	/* Make sure all highest clocks are included*/
+	bw_params->clk_table.entries[i].socclk_mhz = find_max_clk_value(clock_table->SocClocks, NUM_SOCCLK_DPM_LEVELS);
+	bw_params->clk_table.entries[i].dispclk_mhz = find_max_clk_value(clock_table->DispClocks, NUM_DISPCLK_DPM_LEVELS);
+	bw_params->clk_table.entries[i].dppclk_mhz = find_max_clk_value(clock_table->DppClocks, NUM_DPPCLK_DPM_LEVELS);
+	ASSERT(clock_table->DcfClocks[i] == find_max_clk_value(clock_table->DcfClocks, NUM_DCFCLK_DPM_LEVELS));
+	bw_params->clk_table.entries[i].phyclk_mhz = def_max.phyclk_mhz;
+	bw_params->clk_table.entries[i].phyclk_d18_mhz = def_max.phyclk_d18_mhz;
+	bw_params->clk_table.entries[i].dtbclk_mhz = def_max.dtbclk_mhz;
 
+	/*
+	 * Set any 0 clocks to max default setting. Not an issue for
+	 * power since we aren't doing switching in such case anyway
+	 */
+	for (i = 0; i < bw_params->clk_table.num_entries; i++) {
+		if (!bw_params->clk_table.entries[i].fclk_mhz) {
+			bw_params->clk_table.entries[i].fclk_mhz = def_max.fclk_mhz;
+			bw_params->clk_table.entries[i].memclk_mhz = def_max.memclk_mhz;
+			bw_params->clk_table.entries[i].voltage = def_max.voltage;
+		}
+		if (!bw_params->clk_table.entries[i].dcfclk_mhz)
+			bw_params->clk_table.entries[i].dcfclk_mhz = def_max.dcfclk_mhz;
+		if (!bw_params->clk_table.entries[i].socclk_mhz)
+			bw_params->clk_table.entries[i].socclk_mhz = def_max.socclk_mhz;
+		if (!bw_params->clk_table.entries[i].dispclk_mhz)
+			bw_params->clk_table.entries[i].dispclk_mhz = def_max.dispclk_mhz;
+		if (!bw_params->clk_table.entries[i].dppclk_mhz)
+			bw_params->clk_table.entries[i].dppclk_mhz = def_max.dppclk_mhz;
+		if (!bw_params->clk_table.entries[i].phyclk_mhz)
+			bw_params->clk_table.entries[i].phyclk_mhz = def_max.phyclk_mhz;
+		if (!bw_params->clk_table.entries[i].phyclk_d18_mhz)
+			bw_params->clk_table.entries[i].phyclk_d18_mhz = def_max.phyclk_d18_mhz;
+		if (!bw_params->clk_table.entries[i].dtbclk_mhz)
+			bw_params->clk_table.entries[i].dtbclk_mhz = def_max.dtbclk_mhz;
+	}
+	ASSERT(bw_params->clk_table.entries[i-1].dcfclk_mhz);
 	bw_params->vram_type = bios_info->memory_type;
-	bw_params->num_channels = bios_info->ma_channel_number;
+	bw_params->num_channels = bios_info->ma_channel_number ? bios_info->ma_channel_number : 4;
 
 	for (i = 0; i < WM_SET_COUNT; i++) {
 		bw_params->wm_table.entries[i].wm_inst = i;
@@ -641,7 +689,7 @@ static struct clk_mgr_funcs dcn314_funcs = {
 	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
 	.get_dtb_ref_clk_frequency = dcn31_get_dtb_ref_freq_khz,
 	.update_clocks = dcn314_update_clocks,
-	.init_clocks = dcn314_init_clocks,
+	.init_clocks = dcn31_init_clocks,
 	.enable_pme_wa = dcn314_enable_pme_wa,
 	.are_clock_states_equal = dcn314_are_clock_states_equal,
 	.notify_wm_ranges = dcn314_notify_wm_ranges
@@ -681,10 +729,10 @@ void dcn314_clk_mgr_construct(
 	}
 	ASSERT(clk_mgr->smu_wm_set.wm_set);
 
-	smu_dpm_clks.dpm_clks = (DpmClocks_t *)dm_helpers_allocate_gpu_mem(
+	smu_dpm_clks.dpm_clks = (DpmClocks314_t *)dm_helpers_allocate_gpu_mem(
 				clk_mgr->base.base.ctx,
 				DC_MEM_ALLOC_TYPE_FRAME_BUFFER,
-				sizeof(DpmClocks_t),
+				sizeof(DpmClocks314_t),
 				&smu_dpm_clks.mc_address.quad_part);
 
 	if (smu_dpm_clks.dpm_clks == NULL) {
@@ -729,7 +777,7 @@ void dcn314_clk_mgr_construct(
 	if (clk_mgr->base.base.ctx->dc->debug.pstate_enabled) {
 		dcn314_get_dpm_table_from_smu(&clk_mgr->base, &smu_dpm_clks);
 
-		if (ctx->dc_bios && ctx->dc_bios->integrated_info) {
+		if (ctx->dc_bios && ctx->dc_bios->integrated_info && ctx->dc->config.use_default_clock_table == false) {
 			dcn314_clk_mgr_helper_populate_bw_params(
 					&clk_mgr->base,
 					ctx->dc_bios->integrated_info,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
index c695a4498c50..171f84340eb2 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
@@ -42,7 +42,7 @@ struct clk_mgr_dcn314 {
 
 bool dcn314_are_clock_states_equal(struct dc_clocks *a,
 		struct dc_clocks *b);
-void dcn314_init_clocks(struct clk_mgr *clk_mgr);
+
 void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
 			struct dc_state *context,
 			bool safe_to_lower);
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.h
index a7958dc96581..047d19ea919c 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.h
@@ -36,6 +36,37 @@ typedef enum {
 	WCK_RATIO_MAX
 } WCK_RATIO_e;
 
+typedef struct {
+  uint32_t FClk;
+  uint32_t MemClk;
+  uint32_t Voltage;
+  uint8_t  WckRatio;
+  uint8_t  Spare[3];
+} DfPstateTable314_t;
+
+//Freq in MHz
+//Voltage in milli volts with 2 fractional bits
+typedef struct {
+  uint32_t DcfClocks[NUM_DCFCLK_DPM_LEVELS];
+  uint32_t DispClocks[NUM_DISPCLK_DPM_LEVELS];
+  uint32_t DppClocks[NUM_DPPCLK_DPM_LEVELS];
+  uint32_t SocClocks[NUM_SOCCLK_DPM_LEVELS];
+  uint32_t VClocks[NUM_VCN_DPM_LEVELS];
+  uint32_t DClocks[NUM_VCN_DPM_LEVELS];
+  uint32_t SocVoltage[NUM_SOC_VOLTAGE_LEVELS];
+  DfPstateTable314_t DfPstateTable[NUM_DF_PSTATE_LEVELS];
+
+  uint8_t  NumDcfClkLevelsEnabled;
+  uint8_t  NumDispClkLevelsEnabled; //Applies to both Dispclk and Dppclk
+  uint8_t  NumSocClkLevelsEnabled;
+  uint8_t  VcnClkLevelsEnabled;     //Applies to both Vclk and Dclk
+  uint8_t  NumDfPstatesEnabled;
+  uint8_t  spare[3];
+
+  uint32_t MinGfxClk;
+  uint32_t MaxGfxClk;
+} DpmClocks314_t;
+
 struct dcn314_watermarks {
 	// Watermarks
 	WatermarkRowGeneric_t WatermarkRow[WM_COUNT][NUM_WM_RANGES];
@@ -43,7 +74,7 @@ struct dcn314_watermarks {
 };
 
 struct dcn314_smu_dpm_clks {
-	DpmClocks_t *dpm_clks;
+	DpmClocks314_t *dpm_clks;
 	union large_integer mc_address;
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index e42f44fc1c08..aeecca68dea7 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1074,8 +1074,15 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 		struct dc_stream_state *old_stream =
 				dc->current_state->res_ctx.pipe_ctx[i].stream;
 		bool should_disable = true;
-		bool pipe_split_change =
-			context->res_ctx.pipe_ctx[i].top_pipe != dc->current_state->res_ctx.pipe_ctx[i].top_pipe;
+		bool pipe_split_change = false;
+
+		if ((context->res_ctx.pipe_ctx[i].top_pipe) &&
+			(dc->current_state->res_ctx.pipe_ctx[i].top_pipe))
+			pipe_split_change = context->res_ctx.pipe_ctx[i].top_pipe->pipe_idx !=
+				dc->current_state->res_ctx.pipe_ctx[i].top_pipe->pipe_idx;
+		else
+			pipe_split_change = context->res_ctx.pipe_ctx[i].top_pipe !=
+				dc->current_state->res_ctx.pipe_ctx[i].top_pipe;
 
 		for (j = 0; j < context->stream_count; j++) {
 			if (old_stream == context->streams[j]) {
@@ -3229,7 +3236,7 @@ static void commit_planes_for_stream(struct dc *dc,
 				odm_pipe->ttu_regs.min_ttu_vblank = MAX_TTU;
 	}
 
-	if ((update_type != UPDATE_TYPE_FAST) && stream->update_flags.bits.dsc_changed) {
+	if ((update_type != UPDATE_TYPE_FAST) && stream->update_flags.bits.dsc_changed)
 		if (top_pipe_to_program &&
 			top_pipe_to_program->stream_res.tg->funcs->lock_doublebuffer_enable) {
 			if (should_use_dmub_lock(stream->link)) {
@@ -3247,7 +3254,6 @@ static void commit_planes_for_stream(struct dc *dc,
 				top_pipe_to_program->stream_res.tg->funcs->lock_doublebuffer_enable(
 						top_pipe_to_program->stream_res.tg);
 		}
-	}
 
 	if (should_lock_all_pipes && dc->hwss.interdependent_update_lock) {
 		if (dc->hwss.subvp_pipe_control_lock)
@@ -3466,7 +3472,7 @@ static void commit_planes_for_stream(struct dc *dc,
 		dc->hwss.pipe_control_lock(dc, top_pipe_to_program, false);
 	}
 
-	if ((update_type != UPDATE_TYPE_FAST) && stream->update_flags.bits.dsc_changed) {
+	if ((update_type != UPDATE_TYPE_FAST) && stream->update_flags.bits.dsc_changed)
 		if (top_pipe_to_program->stream_res.tg->funcs->lock_doublebuffer_enable) {
 			top_pipe_to_program->stream_res.tg->funcs->wait_for_state(
 				top_pipe_to_program->stream_res.tg,
@@ -3493,21 +3499,19 @@ static void commit_planes_for_stream(struct dc *dc,
 				top_pipe_to_program->stream_res.tg->funcs->lock_doublebuffer_disable(
 					top_pipe_to_program->stream_res.tg);
 		}
-	}
 
-	if (update_type != UPDATE_TYPE_FAST) {
+	if (update_type != UPDATE_TYPE_FAST)
 		dc->hwss.post_unlock_program_front_end(dc, context);
 
-		/* Since phantom pipe programming is moved to post_unlock_program_front_end,
-		 * move the SubVP lock to after the phantom pipes have been setup
-		 */
-		if (should_lock_all_pipes && dc->hwss.interdependent_update_lock) {
-			if (dc->hwss.subvp_pipe_control_lock)
-				dc->hwss.subvp_pipe_control_lock(dc, context, false, should_lock_all_pipes, NULL, subvp_prev_use);
-		} else {
-			if (dc->hwss.subvp_pipe_control_lock)
-				dc->hwss.subvp_pipe_control_lock(dc, context, false, should_lock_all_pipes, top_pipe_to_program, subvp_prev_use);
-		}
+	/* Since phantom pipe programming is moved to post_unlock_program_front_end,
+	 * move the SubVP lock to after the phantom pipes have been setup
+	 */
+	if (should_lock_all_pipes && dc->hwss.interdependent_update_lock) {
+		if (dc->hwss.subvp_pipe_control_lock)
+			dc->hwss.subvp_pipe_control_lock(dc, context, false, should_lock_all_pipes, NULL, subvp_prev_use);
+	} else {
+		if (dc->hwss.subvp_pipe_control_lock)
+			dc->hwss.subvp_pipe_control_lock(dc, context, false, should_lock_all_pipes, top_pipe_to_program, subvp_prev_use);
 	}
 
 	// Fire manual trigger only when bottom plane is flipped
@@ -4292,7 +4296,7 @@ bool dc_is_dmub_outbox_supported(struct dc *dc)
 	    !dc->debug.dpia_debug.bits.disable_dpia)
 		return true;
 
-	if (dc->ctx->asic_id.chip_family == AMDGPU_FAMILY_GC_11_0_2 &&
+	if (dc->ctx->asic_id.chip_family == AMDGPU_FAMILY_GC_11_0_1 &&
 	    !dc->debug.dpia_debug.bits.disable_dpia)
 		return true;
 
@@ -4340,6 +4344,7 @@ void dc_enable_dmub_outbox(struct dc *dc)
 	struct dc_context *dc_ctx = dc->ctx;
 
 	dmub_enable_outbox_notification(dc_ctx->dmub_srv);
+	DC_LOG_DC("%s: dmub outbox notifications enabled\n", __func__);
 }
 
 /**
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 9e51338441d0..66d2ae7aacf5 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -3372,7 +3372,7 @@ bool dc_link_setup_psr(struct dc_link *link,
 		switch(link->ctx->asic_id.chip_family) {
 		case FAMILY_YELLOW_CARP:
 		case AMDGPU_FAMILY_GC_10_3_6:
-		case AMDGPU_FAMILY_GC_11_0_2:
+		case AMDGPU_FAMILY_GC_11_0_1:
 			if(!dc->debug.disable_z10)
 				psr_context->psr_level.bits.SKIP_CRTC_DISABLE = false;
 			break;
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 ffc0f1c0ea93..7dbab15bfa68 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -169,7 +169,7 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id)
 		if (ASICREV_IS_GC_11_0_2(asic_id.hw_internal_rev))
 			dc_version = DCN_VERSION_3_21;
 		break;
-	case AMDGPU_FAMILY_GC_11_0_2:
+	case AMDGPU_FAMILY_GC_11_0_1:
 		dc_version = DCN_VERSION_3_14;
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 8e1e40083ec8..5908b60db313 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -47,7 +47,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.196"
+#define DC_VER "3.2.198"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
@@ -213,6 +213,7 @@ struct dc_caps {
 	uint32_t cache_num_ways;
 	uint16_t subvp_fw_processing_delay_us;
 	uint16_t subvp_prefetch_end_to_mall_start_us;
+	uint8_t subvp_swath_height_margin_lines; // subvp start line must be aligned to 2 x swath height
 	uint16_t subvp_pstate_allow_width_us;
 	uint16_t subvp_vertical_int_margin_us;
 	bool seamless_odm;
@@ -352,6 +353,7 @@ struct dc_config {
 	bool use_pipe_ctx_sync_logic;
 	bool ignore_dpref_ss;
 	bool enable_mipi_converter_optimization;
+	bool use_default_clock_table;
 };
 
 enum visual_confirm {
@@ -609,6 +611,7 @@ struct dc_bounding_box_overrides {
 	int percent_of_ideal_drambw;
 	int dram_clock_change_latency_ns;
 	int dummy_clock_change_latency_ns;
+	int fclk_clock_change_latency_ns;
 	/* This forces a hard min on the DCFCLK we use
 	 * for DML.  Unlike the debug option for forcing
 	 * DCFCLK, this override affects watermark calculations
@@ -751,6 +754,7 @@ struct dc_debug_options {
 	uint32_t mst_start_top_delay;
 	uint8_t psr_power_use_phy_fsm;
 	enum dml_hostvm_override_opts dml_hostvm_override;
+	bool dml_disallow_alternate_prefetch_modes;
 	bool use_legacy_soc_bb_mechanism;
 	bool exit_idle_opt_for_cursor_updates;
 	bool enable_single_display_2to1_odm_policy;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
index 2d61c2a91cee..09b304507bad 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -29,6 +29,7 @@
 #include "dm_helpers.h"
 #include "dc_hw_types.h"
 #include "core_types.h"
+#include "../basics/conversion.h"
 
 #define CTX dc_dmub_srv->ctx
 #define DC_LOGGER CTX->logger
@@ -275,8 +276,7 @@ void dc_dmub_srv_set_drr_manual_trigger_cmd(struct dc *dc, uint32_t tg_inst)
 	union dmub_rb_cmd cmd = { 0 };
 
 	cmd.drr_update.header.type = DMUB_CMD__FW_ASSISTED_MCLK_SWITCH;
-	// TODO: Uncomment once FW headers are promoted
-	//cmd.drr_update.header.sub_type = DMUB_CMD__FAMS_SET_MANUAL_TRIGGER;
+	cmd.drr_update.header.sub_type = DMUB_CMD__FAMS_SET_MANUAL_TRIGGER;
 	cmd.drr_update.dmub_optc_state_req.tg_inst = tg_inst;
 
 	cmd.drr_update.header.payload_bytes = sizeof(cmd.drr_update) - sizeof(cmd.drr_update.header);
@@ -601,6 +601,7 @@ static void populate_subvp_cmd_pipe_info(struct dc *dc,
 			&cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[cmd_pipe_index];
 	struct dc_crtc_timing *main_timing = &subvp_pipe->stream->timing;
 	struct dc_crtc_timing *phantom_timing = &subvp_pipe->stream->mall_stream_config.paired_stream->timing;
+	uint32_t out_num, out_den;
 
 	pipe_data->mode = SUBVP;
 	pipe_data->pipe_config.subvp_data.pix_clk_100hz = subvp_pipe->stream->timing.pix_clk_100hz;
@@ -612,6 +613,16 @@ static void populate_subvp_cmd_pipe_info(struct dc *dc,
 			main_timing->v_total - main_timing->v_front_porch - main_timing->v_addressable;
 	pipe_data->pipe_config.subvp_data.mall_region_lines = phantom_timing->v_addressable;
 	pipe_data->pipe_config.subvp_data.main_pipe_index = subvp_pipe->pipe_idx;
+	pipe_data->pipe_config.subvp_data.is_drr = subvp_pipe->stream->ignore_msa_timing_param;
+
+	/* Calculate the scaling factor from the src and dst height.
+	 * e.g. If 3840x2160 being downscaled to 1920x1080, the scaling factor is 1/2.
+	 * Reduce the fraction 1080/2160 = 1/2 for the "scaling factor"
+	 */
+	reduce_fraction(subvp_pipe->stream->src.height, subvp_pipe->stream->dst.height, &out_num, &out_den);
+	// TODO: Uncomment below lines once DMCUB include headers are promoted
+	//pipe_data->pipe_config.subvp_data.scale_factor_numerator = out_num;
+	//pipe_data->pipe_config.subvp_data.scale_factor_denominator = out_den;
 
 	// Prefetch lines is equal to VACTIVE + BP + VSYNC
 	pipe_data->pipe_config.subvp_data.prefetch_lines =
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index a0af0f6afeef..9544abf75e84 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -344,6 +344,7 @@ enum dc_detect_reason {
 	DETECT_REASON_HPDRX,
 	DETECT_REASON_FALLBACK,
 	DETECT_REASON_RETRAIN,
+	DETECT_REASON_TDR,
 };
 
 bool dc_link_detect(struct dc_link *dc_link, enum dc_detect_reason reason);
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index 213de8cabfad..165392380842 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -543,9 +543,11 @@ static void dce112_get_pix_clk_dividers_helper (
 		switch (pix_clk_params->color_depth) {
 		case COLOR_DEPTH_101010:
 			actual_pixel_clock_100hz = (actual_pixel_clock_100hz * 5) >> 2;
+			actual_pixel_clock_100hz -= actual_pixel_clock_100hz % 10;
 			break;
 		case COLOR_DEPTH_121212:
 			actual_pixel_clock_100hz = (actual_pixel_clock_100hz * 6) >> 2;
+			actual_pixel_clock_100hz -= actual_pixel_clock_100hz % 10;
 			break;
 		case COLOR_DEPTH_161616:
 			actual_pixel_clock_100hz = actual_pixel_clock_100hz * 2;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
index d4a6504dfe00..db7ca4b0cdb9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
@@ -361,8 +361,6 @@ void dpp1_cnv_setup (
 		select = INPUT_CSC_SELECT_ICSC;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
-		pixel_format = 22;
-		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616:
 		pixel_format = 26; /* ARGB16161616_UNORM */
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index b54c12400323..564e061ccb58 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -278,9 +278,6 @@ void hubp1_program_pixel_format(
 				SURFACE_PIXEL_FORMAT, 10);
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
-		REG_UPDATE(DCSURF_SURFACE_CONFIG,
-				SURFACE_PIXEL_FORMAT, 22);
-		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616: /*we use crossbar already*/
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 26); /* ARGB16161616_UNORM */
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 bed783747f16..5b5d952b2b8c 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
@@ -110,6 +110,7 @@ void dcn10_lock_all_pipes(struct dc *dc,
 		 */
 		if (pipe_ctx->top_pipe ||
 		    !pipe_ctx->stream ||
+		    !pipe_ctx->plane_state ||
 		    !tg->funcs->is_tg_enabled(tg))
 			continue;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
index 769974375b4b..8e9384094f6d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -131,6 +131,12 @@ struct mpcc *mpc1_get_mpcc_for_dpp(struct mpc_tree *tree, int dpp_id)
 	while (tmp_mpcc != NULL) {
 		if (tmp_mpcc->dpp_id == dpp_id)
 			return tmp_mpcc;
+
+		/* avoid circular linked list */
+		ASSERT(tmp_mpcc != tmp_mpcc->mpcc_bot);
+		if (tmp_mpcc == tmp_mpcc->mpcc_bot)
+			break;
+
 		tmp_mpcc = tmp_mpcc->mpcc_bot;
 	}
 	return NULL;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
index e1a9a45b03b6..3fc300cd1ce9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
@@ -465,6 +465,11 @@ void optc1_enable_optc_clock(struct timing_generator *optc, bool enable)
 				OTG_CLOCK_ON, 1,
 				1, 1000);
 	} else  {
+
+		//last chance to clear underflow, otherwise, it will always there due to clock is off.
+		if (optc->funcs->is_optc_underflow_occurred(optc) == true)
+			optc->funcs->clear_optc_underflow(optc);
+
 		REG_UPDATE_2(OTG_CLOCK_CONTROL,
 				OTG_CLOCK_GATE_DIS, 0,
 				OTG_CLOCK_EN, 0);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
index ea1f14af0db7..eaa7032f0f1a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
@@ -166,8 +166,6 @@ static void dpp2_cnv_setup (
 		select = DCN2_ICSC_SELECT_ICSC_A;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
-		pixel_format = 22;
-		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616:
 		pixel_format = 26; /* ARGB16161616_UNORM */
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
index 936af65381ef..9570c2118ccc 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
@@ -463,9 +463,6 @@ void hubp2_program_pixel_format(
 				SURFACE_PIXEL_FORMAT, 10);
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
-		REG_UPDATE(DCSURF_SURFACE_CONFIG,
-				SURFACE_PIXEL_FORMAT, 22);
-		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616: /*we use crossbar already*/
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 26); /* ARGB16161616_UNORM */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
index 3d307dd58e9a..116f67a0b989 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
@@ -531,6 +531,12 @@ static struct mpcc *mpc2_get_mpcc_for_dpp(struct mpc_tree *tree, int dpp_id)
 	while (tmp_mpcc != NULL) {
 		if (tmp_mpcc->dpp_id == 0xf || tmp_mpcc->dpp_id == dpp_id)
 			return tmp_mpcc;
+
+		/* avoid circular linked list */
+		ASSERT(tmp_mpcc != tmp_mpcc->mpcc_bot);
+		if (tmp_mpcc == tmp_mpcc->mpcc_bot)
+			break;
+
 		tmp_mpcc = tmp_mpcc->mpcc_bot;
 	}
 	return NULL;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
index c5e200d09038..5752271f22df 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
@@ -67,9 +67,15 @@ static uint32_t convert_and_clamp(
 void dcn21_dchvm_init(struct hubbub *hubbub)
 {
 	struct dcn20_hubbub *hubbub1 = TO_DCN20_HUBBUB(hubbub);
-	uint32_t riommu_active;
+	uint32_t riommu_active, prefetch_done;
 	int i;
 
+	REG_GET(DCHVM_RIOMMU_STAT0, HOSTVM_PREFETCH_DONE, &prefetch_done);
+
+	if (prefetch_done) {
+		hubbub->riommu_active = true;
+		return;
+	}
 	//Init DCHVM block
 	REG_UPDATE(DCHVM_CTRL0, HOSTVM_INIT_REQ, 1);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c
index 77b00f86c216..4a668d6563df 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c
@@ -244,8 +244,6 @@ void dpp3_cnv_setup (
 		select = INPUT_CSC_SELECT_ICSC;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
-		pixel_format = 22;
-		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616:
 		pixel_format = 26; /* ARGB16161616_UNORM */
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c
index 6a4dcafb9bba..dc3e8df706b3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c
@@ -86,7 +86,7 @@ bool hubp3_program_surface_flip_and_addr(
 			VMID, address->vmid);
 
 	if (address->type == PLN_ADDR_TYPE_GRPH_STEREO) {
-		REG_UPDATE(DCSURF_FLIP_CONTROL, SURFACE_FLIP_MODE_FOR_STEREOSYNC, 0x1);
+		REG_UPDATE(DCSURF_FLIP_CONTROL, SURFACE_FLIP_MODE_FOR_STEREOSYNC, 0);
 		REG_UPDATE(DCSURF_FLIP_CONTROL, SURFACE_FLIP_IN_STEREOSYNC, 0x1);
 
 	} else {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
index 0a67f8a5656d..d97076648acb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
@@ -372,7 +372,7 @@ static struct stream_encoder *dcn303_stream_encoder_create(enum engine_id eng_id
 	int afmt_inst;
 
 	/* Mapping of VPG, AFMT, DME register blocks to DIO block instance */
-	if (eng_id <= ENGINE_ID_DIGE) {
+	if (eng_id <= ENGINE_ID_DIGB) {
 		vpg_inst = eng_id;
 		afmt_inst = eng_id;
 	} else
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.h
index 7c77c71591a0..82c3b3ac1f0d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.h
@@ -162,7 +162,8 @@
 	SE_SF(DP_SYM32_ENC0_DP_SYM32_ENC_SDP_AUDIO_CONTROL0, AIP_ENABLE, mask_sh),\
 	SE_SF(DP_SYM32_ENC0_DP_SYM32_ENC_SDP_AUDIO_CONTROL0, ACM_ENABLE, mask_sh),\
 	SE_SF(DP_SYM32_ENC0_DP_SYM32_ENC_VID_CRC_CONTROL, CRC_ENABLE, mask_sh),\
-	SE_SF(DP_SYM32_ENC0_DP_SYM32_ENC_VID_CRC_CONTROL, CRC_CONT_MODE_ENABLE, mask_sh)
+	SE_SF(DP_SYM32_ENC0_DP_SYM32_ENC_VID_CRC_CONTROL, CRC_CONT_MODE_ENABLE, mask_sh),\
+	SE_SF(DP_SYM32_ENC0_DP_SYM32_ENC_HBLANK_CONTROL, HBLANK_MINIMUM_SYMBOL_WIDTH, mask_sh)
 
 
 #define DCN3_1_HPO_DP_STREAM_ENC_REG_FIELD_LIST(type) \
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
index 468a893ff785..aedff18aff56 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
@@ -2153,7 +2153,7 @@ static bool dcn31_resource_construct(
 		pool->base.usb4_dpia_count = 4;
 	}
 
-	if (dc->ctx->asic_id.chip_family == AMDGPU_FAMILY_GC_11_0_2)
+	if (dc->ctx->asic_id.chip_family == AMDGPU_FAMILY_GC_11_0_1)
 		pool->base.usb4_dpia_count = 4;
 
 	/* Audio, Stream Encoders including HPO and virtual, MPC 3D LUTs */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h
index 41f8ec99da6b..901436591ed4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h
@@ -32,7 +32,6 @@
 	container_of(pool, struct dcn31_resource_pool, base)
 
 extern struct _vcs_dpi_ip_params_st dcn3_1_ip;
-extern struct _vcs_dpi_soc_bounding_box_st dcn3_1_soc;
 
 struct dcn31_resource_pool {
 	struct resource_pool base;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/Makefile b/drivers/gpu/drm/amd/display/dc/dcn314/Makefile
index e3b5a95e03b1..702c28c2560e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/Makefile
@@ -13,31 +13,6 @@
 DCN314 = dcn314_resource.o dcn314_hwseq.o dcn314_init.o \
 		dcn314_dio_stream_encoder.o dcn314_dccg.o dcn314_optc.o
 
-ifdef CONFIG_X86
-CFLAGS_$(AMDDALPATH)/dc/dcn314/dcn314_resource.o := -mhard-float -msse
-endif
-
-ifdef CONFIG_PPC64
-CFLAGS_$(AMDDALPATH)/dc/dcn314/dcn314_resource.o := -mhard-float -maltivec
-endif
-
-ifdef CONFIG_CC_IS_GCC
-ifeq ($(call cc-ifversion, -lt, 0701, y), y)
-IS_OLD_GCC = 1
-endif
-endif
-
-ifdef CONFIG_X86
-ifdef IS_OLD_GCC
-# Stack alignment mismatch, proceed with caution.
-# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
-# (8B stack alignment).
-CFLAGS_$(AMDDALPATH)/dc/dcn314/dcn314_resource.o += -mpreferred-stack-boundary=4
-else
-CFLAGS_$(AMDDALPATH)/dc/dcn314/dcn314_resource.o += -msse2
-endif
-endif
-
 AMD_DAL_DCN314 = $(addprefix $(AMDDALPATH)/dc/dcn314/,$(DCN314))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_DCN314)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c
index 755c715ad8dc..39931d48f385 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c
@@ -343,7 +343,10 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig
 {
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	unsigned int odm_combine_factor = 0;
+	struct dc *dc = pipe_ctx->stream->ctx->dc;
+	bool two_pix_per_container = false;
 
+	two_pix_per_container = optc2_is_two_pixels_per_containter(&stream->timing);
 	odm_combine_factor = get_odm_config(pipe_ctx, NULL);
 
 	if (is_dp_128b_132b_signal(pipe_ctx)) {
@@ -355,16 +358,13 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig
 		else
 			*k2_div = PIXEL_RATE_DIV_BY_4;
 	} else if (dc_is_dp_signal(pipe_ctx->stream->signal)) {
-		if (stream->timing.pixel_encoding == PIXEL_ENCODING_YCBCR420) {
+		if (two_pix_per_container) {
 			*k1_div = PIXEL_RATE_DIV_BY_1;
 			*k2_div = PIXEL_RATE_DIV_BY_2;
-		} else if (stream->timing.pixel_encoding == PIXEL_ENCODING_YCBCR422) {
-			*k1_div = PIXEL_RATE_DIV_BY_2;
-			*k2_div = PIXEL_RATE_DIV_BY_2;
 		} else {
-			if (odm_combine_factor == 1)
-				*k2_div = PIXEL_RATE_DIV_BY_4;
-			else if (odm_combine_factor == 2)
+			*k1_div = PIXEL_RATE_DIV_BY_1;
+			*k2_div = PIXEL_RATE_DIV_BY_4;
+			if ((odm_combine_factor == 2) || dc->debug.enable_dp_dig_pixel_rate_div_policy)
 				*k2_div = PIXEL_RATE_DIV_BY_2;
 		}
 	}
@@ -374,3 +374,31 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig
 
 	return odm_combine_factor;
 }
+
+void dcn314_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx)
+{
+	uint32_t pix_per_cycle = 1;
+	uint32_t odm_combine_factor = 1;
+
+	if (!pipe_ctx || !pipe_ctx->stream || !pipe_ctx->stream_res.stream_enc)
+		return;
+
+	odm_combine_factor = get_odm_config(pipe_ctx, NULL);
+	if (optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing) || odm_combine_factor > 1
+		|| dcn314_is_dp_dig_pixel_rate_div_policy(pipe_ctx))
+		pix_per_cycle = 2;
+
+	if (pipe_ctx->stream_res.stream_enc->funcs->set_input_mode)
+		pipe_ctx->stream_res.stream_enc->funcs->set_input_mode(pipe_ctx->stream_res.stream_enc,
+				pix_per_cycle);
+}
+
+bool dcn314_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx)
+{
+	struct dc *dc = pipe_ctx->stream->ctx->dc;
+
+	if (dc_is_dp_signal(pipe_ctx->stream->signal) && !is_dp_128b_132b_signal(pipe_ctx) &&
+		dc->debug.enable_dp_dig_pixel_rate_div_policy)
+		return true;
+	return false;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h
index be0f5e4d48e1..d014580592ac 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h
@@ -39,4 +39,8 @@ void dcn314_enable_power_gating_plane(struct dce_hwseq *hws, bool enable);
 
 unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *k1_div, unsigned int *k2_div);
 
+void dcn314_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx);
+
+bool dcn314_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx);
+
 #endif /* __DC_HWSS_DCN314_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c
index b9debeb081fd..fcf67eb3478f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c
@@ -145,6 +145,8 @@ static const struct hwseq_private_funcs dcn314_private_funcs = {
 	.set_shaper_3dlut = dcn20_set_shaper_3dlut,
 	.setup_hpo_hw_control = dcn31_setup_hpo_hw_control,
 	.calculate_dccg_k1_k2_values = dcn314_calculate_dccg_k1_k2_values,
+	.set_pixels_per_cycle = dcn314_set_pixels_per_cycle,
+	.is_dp_dig_pixel_rate_div_policy = dcn314_is_dp_dig_pixel_rate_div_policy,
 };
 
 void dcn314_hw_sequencer_construct(struct dc *dc)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
index 63861cdfb09f..85f32206a766 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
@@ -70,6 +70,7 @@
 #include "dce110/dce110_resource.h"
 #include "dml/display_mode_vba.h"
 #include "dml/dcn31/dcn31_fpu.h"
+#include "dml/dcn314/dcn314_fpu.h"
 #include "dcn314/dcn314_dccg.h"
 #include "dcn10/dcn10_resource.h"
 #include "dcn31/dcn31_panel_cntl.h"
@@ -132,155 +133,6 @@ static const struct IP_BASE DCN_BASE = { { { { 0x00000012, 0x000000C0, 0x000034C
 
 #define DC_LOGGER_INIT(logger)
 
-#define DCN3_14_DEFAULT_DET_SIZE 384
-#define DCN3_14_MAX_DET_SIZE 384
-#define DCN3_14_MIN_COMPBUF_SIZE_KB 128
-#define DCN3_14_CRB_SEGMENT_SIZE_KB 64
-struct _vcs_dpi_ip_params_st dcn3_14_ip = {
-	.VBlankNomDefaultUS = 668,
-	.gpuvm_enable = 1,
-	.gpuvm_max_page_table_levels = 1,
-	.hostvm_enable = 1,
-	.hostvm_max_page_table_levels = 2,
-	.rob_buffer_size_kbytes = 64,
-	.det_buffer_size_kbytes = DCN3_14_DEFAULT_DET_SIZE,
-	.config_return_buffer_size_in_kbytes = 1792,
-	.compressed_buffer_segment_size_in_kbytes = 64,
-	.meta_fifo_size_in_kentries = 32,
-	.zero_size_buffer_entries = 512,
-	.compbuf_reserved_space_64b = 256,
-	.compbuf_reserved_space_zs = 64,
-	.dpp_output_buffer_pixels = 2560,
-	.opp_output_buffer_lines = 1,
-	.pixel_chunk_size_kbytes = 8,
-	.meta_chunk_size_kbytes = 2,
-	.min_meta_chunk_size_bytes = 256,
-	.writeback_chunk_size_kbytes = 8,
-	.ptoi_supported = false,
-	.num_dsc = 4,
-	.maximum_dsc_bits_per_component = 10,
-	.dsc422_native_support = false,
-	.is_line_buffer_bpp_fixed = true,
-	.line_buffer_fixed_bpp = 48,
-	.line_buffer_size_bits = 789504,
-	.max_line_buffer_lines = 12,
-	.writeback_interface_buffer_size_kbytes = 90,
-	.max_num_dpp = 4,
-	.max_num_otg = 4,
-	.max_num_hdmi_frl_outputs = 1,
-	.max_num_wb = 1,
-	.max_dchub_pscl_bw_pix_per_clk = 4,
-	.max_pscl_lb_bw_pix_per_clk = 2,
-	.max_lb_vscl_bw_pix_per_clk = 4,
-	.max_vscl_hscl_bw_pix_per_clk = 4,
-	.max_hscl_ratio = 6,
-	.max_vscl_ratio = 6,
-	.max_hscl_taps = 8,
-	.max_vscl_taps = 8,
-	.dpte_buffer_size_in_pte_reqs_luma = 64,
-	.dpte_buffer_size_in_pte_reqs_chroma = 34,
-	.dispclk_ramp_margin_percent = 1,
-	.max_inter_dcn_tile_repeaters = 8,
-	.cursor_buffer_size = 16,
-	.cursor_chunk_size = 2,
-	.writeback_line_buffer_buffer_size = 0,
-	.writeback_min_hscl_ratio = 1,
-	.writeback_min_vscl_ratio = 1,
-	.writeback_max_hscl_ratio = 1,
-	.writeback_max_vscl_ratio = 1,
-	.writeback_max_hscl_taps = 1,
-	.writeback_max_vscl_taps = 1,
-	.dppclk_delay_subtotal = 46,
-	.dppclk_delay_scl = 50,
-	.dppclk_delay_scl_lb_only = 16,
-	.dppclk_delay_cnvc_formatter = 27,
-	.dppclk_delay_cnvc_cursor = 6,
-	.dispclk_delay_subtotal = 119,
-	.dynamic_metadata_vm_enabled = false,
-	.odm_combine_4to1_supported = false,
-	.dcc_supported = true,
-};
-
-struct _vcs_dpi_soc_bounding_box_st dcn3_14_soc = {
-		/*TODO: correct dispclk/dppclk voltage level determination*/
-	.clock_limits = {
-		{
-			.state = 0,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
-			.phyclk_mhz = 600.0,
-			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 186.0,
-			.dtbclk_mhz = 625.0,
-		},
-		{
-			.state = 1,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
-			.phyclk_mhz = 810.0,
-			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 209.0,
-			.dtbclk_mhz = 625.0,
-		},
-		{
-			.state = 2,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
-			.phyclk_mhz = 810.0,
-			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 209.0,
-			.dtbclk_mhz = 625.0,
-		},
-		{
-			.state = 3,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
-			.phyclk_mhz = 810.0,
-			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 371.0,
-			.dtbclk_mhz = 625.0,
-		},
-		{
-			.state = 4,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
-			.phyclk_mhz = 810.0,
-			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 417.0,
-			.dtbclk_mhz = 625.0,
-		},
-	},
-	.num_states = 5,
-	.sr_exit_time_us = 9.0,
-	.sr_enter_plus_exit_time_us = 11.0,
-	.sr_exit_z8_time_us = 442.0,
-	.sr_enter_plus_exit_z8_time_us = 560.0,
-	.writeback_latency_us = 12.0,
-	.dram_channel_width_bytes = 4,
-	.round_trip_ping_latency_dcfclk_cycles = 106,
-	.urgent_latency_pixel_data_only_us = 4.0,
-	.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
-	.urgent_latency_vm_data_only_us = 4.0,
-	.urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096,
-	.urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096,
-	.urgent_out_of_order_return_per_channel_vm_only_bytes = 4096,
-	.pct_ideal_sdp_bw_after_urgent = 80.0,
-	.pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 65.0,
-	.pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 60.0,
-	.pct_ideal_dram_sdp_bw_after_urgent_vm_only = 30.0,
-	.max_avg_sdp_bw_use_normal_percent = 60.0,
-	.max_avg_dram_bw_use_normal_percent = 60.0,
-	.fabric_datapath_to_dcn_data_return_bytes = 32,
-	.return_bus_width_bytes = 64,
-	.downspread_percent = 0.38,
-	.dcn_downspread_percent = 0.5,
-	.gpuvm_min_page_size_bytes = 4096,
-	.hostvm_min_page_size_bytes = 4096,
-	.do_urgent_latency_adjustment = false,
-	.urgent_latency_adjustment_fabric_clock_component_us = 0,
-	.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
-};
-
 enum dcn31_clk_src_array_id {
 	DCN31_CLK_SRC_PLL0,
 	DCN31_CLK_SRC_PLL1,
@@ -1402,7 +1254,7 @@ static struct stream_encoder *dcn314_stream_encoder_create(
 	int afmt_inst;
 
 	/* Mapping of VPG, AFMT, DME register blocks to DIO block instance */
-	if (eng_id <= ENGINE_ID_DIGF) {
+	if (eng_id < ENGINE_ID_DIGF) {
 		vpg_inst = eng_id;
 		afmt_inst = eng_id;
 	} else
@@ -1447,7 +1299,8 @@ static struct hpo_dp_stream_encoder *dcn31_hpo_dp_stream_encoder_create(
 	 * VPG[8] -> HPO_DP[2]
 	 * VPG[9] -> HPO_DP[3]
 	 */
-	vpg_inst = hpo_dp_inst + 6;
+	//Uses offset index 5-8, but actually maps to vpg_inst 6-9
+	vpg_inst = hpo_dp_inst + 5;
 
 	/* Mapping of APG register blocks to HPO DP block instance:
 	 * APG[0] -> HPO_DP[0]
@@ -1793,109 +1646,16 @@ static struct clock_source *dcn31_clock_source_create(
 	return NULL;
 }
 
-static bool is_dual_plane(enum surface_pixel_format format)
-{
-	return format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN || format == SURFACE_PIXEL_FORMAT_GRPH_RGBE_ALPHA;
-}
-
 static int dcn314_populate_dml_pipes_from_context(
 	struct dc *dc, struct dc_state *context,
 	display_e2e_pipe_params_st *pipes,
 	bool fast_validate)
 {
-	int i, pipe_cnt;
-	struct resource_context *res_ctx = &context->res_ctx;
-	struct pipe_ctx *pipe;
-	bool upscaled = false;
-
-	dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate);
-
-	for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
-		struct dc_crtc_timing *timing;
-
-		if (!res_ctx->pipe_ctx[i].stream)
-			continue;
-		pipe = &res_ctx->pipe_ctx[i];
-		timing = &pipe->stream->timing;
-
-		if (dc_extended_blank_supported(dc) && pipe->stream->adjust.v_total_max == pipe->stream->adjust.v_total_min
-			&& pipe->stream->adjust.v_total_min > timing->v_total)
-			pipes[pipe_cnt].pipe.dest.vtotal = pipe->stream->adjust.v_total_min;
-
-		if (pipe->plane_state &&
-				(pipe->plane_state->src_rect.height < pipe->plane_state->dst_rect.height ||
-				pipe->plane_state->src_rect.width < pipe->plane_state->dst_rect.width))
-			upscaled = true;
-
-		/*
-		 * Immediate flip can be set dynamically after enabling the plane.
-		 * We need to require support for immediate flip or underflow can be
-		 * intermittently experienced depending on peak b/w requirements.
-		 */
-		pipes[pipe_cnt].pipe.src.immediate_flip = true;
-
-		pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
-		pipes[pipe_cnt].pipe.src.hostvm = dc->res_pool->hubbub->riommu_active;
-		pipes[pipe_cnt].pipe.src.gpuvm = true;
-		pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_luma = 0;
-		pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_chroma = 0;
-		pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
-		pipes[pipe_cnt].pipe.src.dcc_rate = 3;
-		pipes[pipe_cnt].dout.dsc_input_bpc = 0;
-
-		if (pipes[pipe_cnt].dout.dsc_enable) {
-			switch (timing->display_color_depth) {
-			case COLOR_DEPTH_888:
-				pipes[pipe_cnt].dout.dsc_input_bpc = 8;
-				break;
-			case COLOR_DEPTH_101010:
-				pipes[pipe_cnt].dout.dsc_input_bpc = 10;
-				break;
-			case COLOR_DEPTH_121212:
-				pipes[pipe_cnt].dout.dsc_input_bpc = 12;
-				break;
-			default:
-				ASSERT(0);
-				break;
-			}
-		}
-
-		pipe_cnt++;
-	}
-	context->bw_ctx.dml.ip.det_buffer_size_kbytes = DCN3_14_DEFAULT_DET_SIZE;
-
-	dc->config.enable_4to1MPC = false;
-	if (pipe_cnt == 1 && pipe->plane_state && !dc->debug.disable_z9_mpc) {
-		if (is_dual_plane(pipe->plane_state->format)
-				&& pipe->plane_state->src_rect.width <= 1920 && pipe->plane_state->src_rect.height <= 1080) {
-			dc->config.enable_4to1MPC = true;
-		} else if (!is_dual_plane(pipe->plane_state->format) && pipe->plane_state->src_rect.width <= 5120) {
-			/* Limit to 5k max to avoid forced pipe split when there is not enough detile for swath */
-			context->bw_ctx.dml.ip.det_buffer_size_kbytes = 192;
-			pipes[0].pipe.src.unbounded_req_mode = true;
-		}
-	} else if (context->stream_count >= dc->debug.crb_alloc_policy_min_disp_count
-			&& dc->debug.crb_alloc_policy > DET_SIZE_DEFAULT) {
-		context->bw_ctx.dml.ip.det_buffer_size_kbytes = dc->debug.crb_alloc_policy * 64;
-	} else if (context->stream_count >= 3 && upscaled) {
-		context->bw_ctx.dml.ip.det_buffer_size_kbytes = 192;
-	}
-
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
-
-		if (!pipe->stream)
-			continue;
+	int pipe_cnt;
 
-		if (pipe->stream->signal == SIGNAL_TYPE_EDP && dc->debug.seamless_boot_odm_combine &&
-				pipe->stream->apply_seamless_boot_optimization) {
-
-			if (pipe->stream->apply_boot_odm_mode == dm_odm_combine_policy_2to1) {
-				context->bw_ctx.dml.vba.ODMCombinePolicy = dm_odm_combine_policy_2to1;
-				break;
-			}
-		}
-	}
+	DC_FP_START();
+	pipe_cnt = dcn314_populate_dml_pipes_from_context_fpu(dc, context, pipes, fast_validate);
+	DC_FP_END();
 
 	return pipe_cnt;
 }
@@ -1906,88 +1666,9 @@ static struct dc_cap_funcs cap_funcs = {
 
 static void dcn314_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
 {
-	struct clk_limit_table *clk_table = &bw_params->clk_table;
-	struct _vcs_dpi_voltage_scaling_st *clock_tmp = dcn3_14_soc._clock_tmp;
-	unsigned int i, closest_clk_lvl;
-	int max_dispclk_mhz = 0, max_dppclk_mhz = 0;
-	int j;
-
-	// Default clock levels are used for diags, which may lead to overclocking.
-	if (!IS_DIAG_DC(dc->ctx->dce_environment)) {
-
-		dcn3_14_ip.max_num_otg = dc->res_pool->res_cap->num_timing_generator;
-		dcn3_14_ip.max_num_dpp = dc->res_pool->pipe_count;
-
-		if (bw_params->num_channels > 0)
-			dcn3_14_soc.num_chans = bw_params->num_channels;
-
-		ASSERT(dcn3_14_soc.num_chans);
-		ASSERT(clk_table->num_entries);
-
-		/* Prepass to find max clocks independent of voltage level. */
-		for (i = 0; i < clk_table->num_entries; ++i) {
-			if (clk_table->entries[i].dispclk_mhz > max_dispclk_mhz)
-				max_dispclk_mhz = clk_table->entries[i].dispclk_mhz;
-			if (clk_table->entries[i].dppclk_mhz > max_dppclk_mhz)
-				max_dppclk_mhz = clk_table->entries[i].dppclk_mhz;
-		}
-
-		for (i = 0; i < clk_table->num_entries; i++) {
-			/* loop backwards*/
-			for (closest_clk_lvl = 0, j = dcn3_14_soc.num_states - 1; j >= 0; j--) {
-				if ((unsigned int) dcn3_14_soc.clock_limits[j].dcfclk_mhz <= clk_table->entries[i].dcfclk_mhz) {
-					closest_clk_lvl = j;
-					break;
-				}
-			}
-			if (clk_table->num_entries == 1) {
-				/*smu gives one DPM level, let's take the highest one*/
-				closest_clk_lvl = dcn3_14_soc.num_states - 1;
-			}
-
-			clock_tmp[i].state = i;
-
-			/* Clocks dependent on voltage level. */
-			clock_tmp[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz;
-			if (clk_table->num_entries == 1 &&
-				clock_tmp[i].dcfclk_mhz < dcn3_14_soc.clock_limits[closest_clk_lvl].dcfclk_mhz) {
-				/*SMU fix not released yet*/
-				clock_tmp[i].dcfclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].dcfclk_mhz;
-			}
-			clock_tmp[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz;
-			clock_tmp[i].socclk_mhz = clk_table->entries[i].socclk_mhz;
-
-			if (clk_table->entries[i].memclk_mhz && clk_table->entries[i].wck_ratio)
-				clock_tmp[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2 * clk_table->entries[i].wck_ratio;
-
-			/* Clocks independent of voltage level. */
-			clock_tmp[i].dispclk_mhz = max_dispclk_mhz ? max_dispclk_mhz :
-				dcn3_14_soc.clock_limits[closest_clk_lvl].dispclk_mhz;
-
-			clock_tmp[i].dppclk_mhz = max_dppclk_mhz ? max_dppclk_mhz :
-				dcn3_14_soc.clock_limits[closest_clk_lvl].dppclk_mhz;
-
-			clock_tmp[i].dram_bw_per_chan_gbps = dcn3_14_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps;
-			clock_tmp[i].dscclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].dscclk_mhz;
-			clock_tmp[i].dtbclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].dtbclk_mhz;
-			clock_tmp[i].phyclk_d18_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz;
-			clock_tmp[i].phyclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].phyclk_mhz;
-		}
-		for (i = 0; i < clk_table->num_entries; i++)
-			dcn3_14_soc.clock_limits[i] = clock_tmp[i];
-		if (clk_table->num_entries)
-			dcn3_14_soc.num_states = clk_table->num_entries;
-	}
-
-	if (max_dispclk_mhz) {
-		dcn3_14_soc.dispclk_dppclk_vco_speed_mhz = max_dispclk_mhz * 2;
-		dc->dml.soc.dispclk_dppclk_vco_speed_mhz = max_dispclk_mhz * 2;
-	}
-
-	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
-		dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN31);
-	else
-		dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN31_FPGA);
+	DC_FP_START();
+	dcn314_update_bw_bounding_box_fpu(dc, bw_params);
+	DC_FP_END();
 }
 
 static struct resource_funcs dcn314_res_pool_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.h b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.h
index c41108847ce0..0dd3153aa5c1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.h
@@ -29,6 +29,9 @@
 
 #include "core_types.h"
 
+extern struct _vcs_dpi_ip_params_st dcn3_14_ip;
+extern struct _vcs_dpi_soc_bounding_box_st dcn3_14_soc;
+
 #define TO_DCN314_RES_POOL(pool)\
 	container_of(pool, struct dcn314_resource_pool, base)
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.h b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.h
index 39929fa67a51..22849eaa6f24 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.h
@@ -32,7 +32,6 @@
 	container_of(pool, struct dcn315_resource_pool, base)
 
 extern struct _vcs_dpi_ip_params_st dcn3_15_ip;
-extern struct _vcs_dpi_ip_params_st dcn3_15_soc;
 
 struct dcn315_resource_pool {
 	struct resource_pool base;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.h b/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.h
index 0dc5a6c13ae7..aba6d634131b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.h
@@ -32,7 +32,6 @@
 	container_of(pool, struct dcn316_resource_pool, base)
 
 extern struct _vcs_dpi_ip_params_st dcn3_16_ip;
-extern struct _vcs_dpi_ip_params_st dcn3_16_soc;
 
 struct dcn316_resource_pool {
 	struct resource_pool base;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
index d38341f68b17..ebd3945c71f1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
@@ -250,6 +250,7 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c
 	uint32_t total_lines = 0;
 	uint32_t lines_per_way = 0;
 	uint32_t num_ways = 0;
+	uint32_t prev_addr_low = 0;
 
 	for (i = 0; i < ctx->stream_count; i++) {
 		stream = ctx->streams[i];
@@ -267,10 +268,20 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c
 			plane = ctx->stream_status[i].plane_states[j];
 
 			// Calculate total surface size
-			surface_size = plane->plane_size.surface_pitch *
+			if (prev_addr_low != plane->address.grph.addr.u.low_part) {
+				/* if plane address are different from prev FB, then userspace allocated separate FBs*/
+				surface_size += plane->plane_size.surface_pitch *
 					plane->plane_size.surface_size.height *
 					(plane->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4);
 
+				prev_addr_low = plane->address.grph.addr.u.low_part;
+			} else {
+				/* We have the same fb for all the planes.
+				 * Xorg always creates one giant fb that holds all surfaces,
+				 * so allocating it once is sufficient.
+				 * */
+				continue;
+			}
 			// Convert surface size + starting address to number of cache lines required
 			// (alignment accounted for)
 			cache_lines_used += dcn32_cache_lines_for_surface(dc, surface_size,
@@ -320,7 +331,10 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c
 bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable)
 {
 	union dmub_rb_cmd cmd;
-	uint8_t ways;
+	uint8_t ways, i;
+	int j;
+	bool stereo_in_use = false;
+	struct dc_plane_state *plane = NULL;
 
 	if (!dc->ctx->dmub_srv)
 		return false;
@@ -349,7 +363,23 @@ bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable)
 			 * and configure HUBP's to fetch from MALL
 			 */
 			ways = dcn32_calculate_cab_allocation(dc, dc->current_state);
-			if (ways <= dc->caps.cache_num_ways) {
+
+			/* MALL not supported with Stereo3D. If any plane is using stereo,
+			 * don't try to enter MALL.
+			 */
+			for (i = 0; i < dc->current_state->stream_count; i++) {
+				for (j = 0; j < dc->current_state->stream_status[i].plane_count; j++) {
+					plane = dc->current_state->stream_status[i].plane_states[j];
+
+					if (plane->address.type == PLN_ADDR_TYPE_GRPH_STEREO) {
+						stereo_in_use = true;
+						break;
+					}
+				}
+				if (stereo_in_use)
+					break;
+			}
+			if (ways <= dc->caps.cache_num_ways && !stereo_in_use) {
 				memset(&cmd, 0, sizeof(cmd));
 				cmd.cab.header.type = DMUB_CMD__CAB_FOR_SS;
 				cmd.cab.header.sub_type = DMUB_CMD__CAB_DCN_SS_FIT_IN_CAB;
@@ -683,9 +713,11 @@ void dcn32_update_mall_sel(struct dc *dc, struct dc_state *context)
 			if (pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) {
 					hubp->funcs->hubp_update_mall_sel(hubp, 1, false);
 			} else {
+				// MALL not supported with Stereo3D
 				hubp->funcs->hubp_update_mall_sel(hubp,
 					num_ways <= dc->caps.cache_num_ways &&
-					pipe->stream->link->psr_settings.psr_version == DC_PSR_VERSION_UNSUPPORTED ? 2 : 0,
+					pipe->stream->link->psr_settings.psr_version == DC_PSR_VERSION_UNSUPPORTED &&
+					pipe->plane_state->address.type !=  PLN_ADDR_TYPE_GRPH_STEREO ? 2 : 0,
 							cache_cursor);
 			}
 		}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c
index eff1f4e17689..1fad7b48bd5b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c
@@ -281,7 +281,7 @@ static struct timing_generator_funcs dcn32_tg_funcs = {
 		.lock_doublebuffer_enable = optc3_lock_doublebuffer_enable,
 		.lock_doublebuffer_disable = optc3_lock_doublebuffer_disable,
 		.enable_optc_clock = optc1_enable_optc_clock,
-		.set_drr = optc31_set_drr, // TODO: Update to optc32_set_drr once FW headers are promoted
+		.set_drr = optc32_set_drr,
 		.get_last_used_drr_vtotal = optc2_get_last_used_drr_vtotal,
 		.set_vtotal_min_max = optc3_set_vtotal_min_max,
 		.set_static_screen_control = optc1_set_static_screen_control,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
index 9a26d24b579f..8b887b552f2c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
@@ -867,7 +867,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 		}
 	},
 	.use_max_lb = true,
-	.force_disable_subvp = true,
+	.force_disable_subvp = false,
 	.exit_idle_opt_for_cursor_updates = true,
 	.enable_single_display_2to1_odm_policy = true,
 	.enable_dp_dig_pixel_rate_div_policy = 1,
@@ -2051,6 +2051,7 @@ static bool dcn32_resource_construct(
 	dc->caps.max_cab_allocation_bytes = 67108864; // 64MB = 1024 * 1024 * 64
 	dc->caps.subvp_fw_processing_delay_us = 15;
 	dc->caps.subvp_prefetch_end_to_mall_start_us = 15;
+	dc->caps.subvp_swath_height_margin_lines = 16;
 	dc->caps.subvp_pstate_allow_width_us = 20;
 	dc->caps.subvp_vertical_int_margin_us = 30;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
index b3f8503cea9c..955f52e6064d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
@@ -63,7 +63,7 @@ uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_stat
 		if (pipe->stream && pipe->plane_state && !pipe->top_pipe &&
 				pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) {
 			bytes_per_pixel = pipe->plane_state->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4;
-			mall_region_pixels = pipe->stream->timing.h_addressable * pipe->stream->timing.v_addressable;
+			mall_region_pixels = pipe->plane_state->plane_size.surface_pitch * pipe->stream->timing.v_addressable;
 
 			// For bytes required in MALL, calculate based on number of MBlks required
 			num_mblks = (mall_region_pixels * bytes_per_pixel +
diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
index 8157e40d2c7e..c8b7d6ff38f4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
@@ -868,7 +868,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 		}
 	},
 	.use_max_lb = true,
-	.force_disable_subvp = true,
+	.force_disable_subvp = false,
 	.exit_idle_opt_for_cursor_updates = true,
 	.enable_single_display_2to1_odm_policy = true,
 	.enable_dp_dig_pixel_rate_div_policy = 1,
@@ -1662,8 +1662,9 @@ static bool dcn321_resource_construct(
 	dc->caps.max_cab_allocation_bytes = 33554432; // 32MB = 1024 * 1024 * 32
 	dc->caps.subvp_fw_processing_delay_us = 15;
 	dc->caps.subvp_prefetch_end_to_mall_start_us = 15;
+	dc->caps.subvp_swath_height_margin_lines = 16;
 	dc->caps.subvp_pstate_allow_width_us = 20;
-
+	dc->caps.subvp_vertical_int_margin_us = 30;
 	dc->caps.max_slave_planes = 1;
 	dc->caps.max_slave_yuv_planes = 1;
 	dc->caps.max_slave_rgb_planes = 1;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 359f6e9a1da0..86a3b5bfd699 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -61,7 +61,6 @@ CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags)
@@ -71,6 +70,7 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(fram
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/dcn314_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/dcn30_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn32/dcn32_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn32/display_mode_vba_32.o := $(dml_ccflags) $(frame_warn_flag)
@@ -82,7 +82,6 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn301/dcn301_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn302/dcn302_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn303/dcn303_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dsc/rc_calc_fpu.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/calcs/dcn_calcs.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/calcs/dcn_calc_auto.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/calcs/dcn_calc_math.o := $(dml_ccflags) -Wno-tautological-compare
@@ -131,6 +130,7 @@ DML += dcn321/dcn321_fpu.o
 DML += dcn301/dcn301_fpu.o
 DML += dcn302/dcn302_fpu.o
 DML += dcn303/dcn303_fpu.o
+DML += dcn314/dcn314_fpu.o
 DML += dsc/rc_calc_fpu.o
 DML += calcs/dcn_calcs.o calcs/dcn_calc_math.o calcs/dcn_calc_auto.o
 endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index ca44df4fca74..d34e0f1314d9 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -30,6 +30,7 @@
 #include "dchubbub.h"
 #include "dcn20/dcn20_resource.h"
 #include "dcn21/dcn21_resource.h"
+#include "clk_mgr/dcn21/rn_clk_mgr.h"
 
 #include "dcn20_fpu.h"
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c
index 7ef66e511ec8..d211cf6d234c 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c
@@ -26,6 +26,7 @@
 #include "clk_mgr.h"
 #include "dcn20/dcn20_resource.h"
 #include "dcn301/dcn301_resource.h"
+#include "clk_mgr/dcn301/vg_clk_mgr.h"
 
 #include "dml/dcn20/dcn20_fpu.h"
 #include "dcn301_fpu.h"
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
index e36cfa5985ea..149a1b17cdf3 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
@@ -25,6 +25,9 @@
 
 #include "resource.h"
 #include "clk_mgr.h"
+#include "dcn31/dcn31_resource.h"
+#include "dcn315/dcn315_resource.h"
+#include "dcn316/dcn316_resource.h"
 
 #include "dml/dcn20/dcn20_fpu.h"
 #include "dcn31_fpu.h"
@@ -114,7 +117,7 @@ struct _vcs_dpi_ip_params_st dcn3_1_ip = {
 	.dcc_supported = true,
 };
 
-struct _vcs_dpi_soc_bounding_box_st dcn3_1_soc = {
+static struct _vcs_dpi_soc_bounding_box_st dcn3_1_soc = {
 		/*TODO: correct dispclk/dppclk voltage level determination*/
 	.clock_limits = {
 		{
@@ -259,7 +262,7 @@ struct _vcs_dpi_ip_params_st dcn3_15_ip = {
 	.dcc_supported = true,
 };
 
-struct _vcs_dpi_soc_bounding_box_st dcn3_15_soc = {
+static struct _vcs_dpi_soc_bounding_box_st dcn3_15_soc = {
 	.sr_exit_time_us = 9.0,
 	.sr_enter_plus_exit_time_us = 11.0,
 	.sr_exit_z8_time_us = 50.0,
@@ -355,7 +358,7 @@ struct _vcs_dpi_ip_params_st dcn3_16_ip = {
 	.dcc_supported = true,
 };
 
-struct _vcs_dpi_soc_bounding_box_st dcn3_16_soc = {
+static struct _vcs_dpi_soc_bounding_box_st dcn3_16_soc = {
 		/*TODO: correct dispclk/dppclk voltage level determination*/
 	.clock_limits = {
 		{
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
index 3fab19134480..d63b4209b14c 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
@@ -26,7 +26,7 @@
 #include "dc.h"
 #include "dc_link.h"
 #include "../display_mode_lib.h"
-#include "dml/dcn30/display_mode_vba_30.h"
+#include "../dcn30/display_mode_vba_30.h"
 #include "display_mode_vba_31.h"
 #include "../dml_inline_defs.h"
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
index 66b82e4f05c6..35d10b4d018b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
@@ -27,7 +27,7 @@
 #include "../display_mode_vba.h"
 #include "../dml_inline_defs.h"
 #include "display_rq_dlg_calc_31.h"
-#include "dml/dcn30/display_mode_vba_30.h"
+#include "../dcn30/display_mode_vba_30.h"
 
 static bool is_dual_plane(enum source_format_class source_format)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
new file mode 100644
index 000000000000..34a5d0f87b5f
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
@@ -0,0 +1,376 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright 2022 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "clk_mgr.h"
+#include "resource.h"
+#include "dcn31/dcn31_hubbub.h"
+#include "dcn314_fpu.h"
+#include "dml/dcn20/dcn20_fpu.h"
+#include "dml/display_mode_vba.h"
+
+struct _vcs_dpi_ip_params_st dcn3_14_ip = {
+	.VBlankNomDefaultUS = 668,
+	.gpuvm_enable = 1,
+	.gpuvm_max_page_table_levels = 1,
+	.hostvm_enable = 1,
+	.hostvm_max_page_table_levels = 2,
+	.rob_buffer_size_kbytes = 64,
+	.det_buffer_size_kbytes = DCN3_14_DEFAULT_DET_SIZE,
+	.config_return_buffer_size_in_kbytes = 1792,
+	.compressed_buffer_segment_size_in_kbytes = 64,
+	.meta_fifo_size_in_kentries = 32,
+	.zero_size_buffer_entries = 512,
+	.compbuf_reserved_space_64b = 256,
+	.compbuf_reserved_space_zs = 64,
+	.dpp_output_buffer_pixels = 2560,
+	.opp_output_buffer_lines = 1,
+	.pixel_chunk_size_kbytes = 8,
+	.meta_chunk_size_kbytes = 2,
+	.min_meta_chunk_size_bytes = 256,
+	.writeback_chunk_size_kbytes = 8,
+	.ptoi_supported = false,
+	.num_dsc = 4,
+	.maximum_dsc_bits_per_component = 10,
+	.dsc422_native_support = false,
+	.is_line_buffer_bpp_fixed = true,
+	.line_buffer_fixed_bpp = 48,
+	.line_buffer_size_bits = 789504,
+	.max_line_buffer_lines = 12,
+	.writeback_interface_buffer_size_kbytes = 90,
+	.max_num_dpp = 4,
+	.max_num_otg = 4,
+	.max_num_hdmi_frl_outputs = 1,
+	.max_num_wb = 1,
+	.max_dchub_pscl_bw_pix_per_clk = 4,
+	.max_pscl_lb_bw_pix_per_clk = 2,
+	.max_lb_vscl_bw_pix_per_clk = 4,
+	.max_vscl_hscl_bw_pix_per_clk = 4,
+	.max_hscl_ratio = 6,
+	.max_vscl_ratio = 6,
+	.max_hscl_taps = 8,
+	.max_vscl_taps = 8,
+	.dpte_buffer_size_in_pte_reqs_luma = 64,
+	.dpte_buffer_size_in_pte_reqs_chroma = 34,
+	.dispclk_ramp_margin_percent = 1,
+	.max_inter_dcn_tile_repeaters = 8,
+	.cursor_buffer_size = 16,
+	.cursor_chunk_size = 2,
+	.writeback_line_buffer_buffer_size = 0,
+	.writeback_min_hscl_ratio = 1,
+	.writeback_min_vscl_ratio = 1,
+	.writeback_max_hscl_ratio = 1,
+	.writeback_max_vscl_ratio = 1,
+	.writeback_max_hscl_taps = 1,
+	.writeback_max_vscl_taps = 1,
+	.dppclk_delay_subtotal = 46,
+	.dppclk_delay_scl = 50,
+	.dppclk_delay_scl_lb_only = 16,
+	.dppclk_delay_cnvc_formatter = 27,
+	.dppclk_delay_cnvc_cursor = 6,
+	.dispclk_delay_subtotal = 119,
+	.dynamic_metadata_vm_enabled = false,
+	.odm_combine_4to1_supported = false,
+	.dcc_supported = true,
+};
+
+struct _vcs_dpi_soc_bounding_box_st dcn3_14_soc = {
+		/*TODO: correct dispclk/dppclk voltage level determination*/
+	.clock_limits = {
+		{
+			.state = 0,
+			.dispclk_mhz = 1200.0,
+			.dppclk_mhz = 1200.0,
+			.phyclk_mhz = 600.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 186.0,
+			.dtbclk_mhz = 600.0,
+		},
+		{
+			.state = 1,
+			.dispclk_mhz = 1200.0,
+			.dppclk_mhz = 1200.0,
+			.phyclk_mhz = 810.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 209.0,
+			.dtbclk_mhz = 600.0,
+		},
+		{
+			.state = 2,
+			.dispclk_mhz = 1200.0,
+			.dppclk_mhz = 1200.0,
+			.phyclk_mhz = 810.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 209.0,
+			.dtbclk_mhz = 600.0,
+		},
+		{
+			.state = 3,
+			.dispclk_mhz = 1200.0,
+			.dppclk_mhz = 1200.0,
+			.phyclk_mhz = 810.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 371.0,
+			.dtbclk_mhz = 600.0,
+		},
+		{
+			.state = 4,
+			.dispclk_mhz = 1200.0,
+			.dppclk_mhz = 1200.0,
+			.phyclk_mhz = 810.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 417.0,
+			.dtbclk_mhz = 600.0,
+		},
+	},
+	.num_states = 5,
+	.sr_exit_time_us = 9.0,
+	.sr_enter_plus_exit_time_us = 11.0,
+	.sr_exit_z8_time_us = 442.0,
+	.sr_enter_plus_exit_z8_time_us = 560.0,
+	.writeback_latency_us = 12.0,
+	.dram_channel_width_bytes = 4,
+	.round_trip_ping_latency_dcfclk_cycles = 106,
+	.urgent_latency_pixel_data_only_us = 4.0,
+	.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
+	.urgent_latency_vm_data_only_us = 4.0,
+	.urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096,
+	.urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096,
+	.urgent_out_of_order_return_per_channel_vm_only_bytes = 4096,
+	.pct_ideal_sdp_bw_after_urgent = 80.0,
+	.pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 65.0,
+	.pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 60.0,
+	.pct_ideal_dram_sdp_bw_after_urgent_vm_only = 30.0,
+	.max_avg_sdp_bw_use_normal_percent = 60.0,
+	.max_avg_dram_bw_use_normal_percent = 60.0,
+	.fabric_datapath_to_dcn_data_return_bytes = 32,
+	.return_bus_width_bytes = 64,
+	.downspread_percent = 0.38,
+	.dcn_downspread_percent = 0.5,
+	.gpuvm_min_page_size_bytes = 4096,
+	.hostvm_min_page_size_bytes = 4096,
+	.do_urgent_latency_adjustment = false,
+	.urgent_latency_adjustment_fabric_clock_component_us = 0,
+	.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
+};
+
+
+void dcn314_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_params)
+{
+	struct clk_limit_table *clk_table = &bw_params->clk_table;
+	struct _vcs_dpi_voltage_scaling_st *clock_limits =
+		dcn3_14_soc.clock_limits;
+	unsigned int i, closest_clk_lvl;
+	int max_dispclk_mhz = 0, max_dppclk_mhz = 0;
+	int j;
+
+	dc_assert_fp_enabled();
+
+	// Default clock levels are used for diags, which may lead to overclocking.
+	if (!IS_DIAG_DC(dc->ctx->dce_environment) && dc->config.use_default_clock_table == false) {
+
+		dcn3_14_ip.max_num_otg = dc->res_pool->res_cap->num_timing_generator;
+		dcn3_14_ip.max_num_dpp = dc->res_pool->pipe_count;
+
+		if (bw_params->num_channels > 0)
+			dcn3_14_soc.num_chans = bw_params->num_channels;
+
+		ASSERT(dcn3_14_soc.num_chans);
+		ASSERT(clk_table->num_entries);
+
+		/* Prepass to find max clocks independent of voltage level. */
+		for (i = 0; i < clk_table->num_entries; ++i) {
+			if (clk_table->entries[i].dispclk_mhz > max_dispclk_mhz)
+				max_dispclk_mhz = clk_table->entries[i].dispclk_mhz;
+			if (clk_table->entries[i].dppclk_mhz > max_dppclk_mhz)
+				max_dppclk_mhz = clk_table->entries[i].dppclk_mhz;
+		}
+
+		for (i = 0; i < clk_table->num_entries; i++) {
+			/* loop backwards*/
+			for (closest_clk_lvl = 0, j = dcn3_14_soc.num_states - 1; j >= 0; j--) {
+				if ((unsigned int) dcn3_14_soc.clock_limits[j].dcfclk_mhz <= clk_table->entries[i].dcfclk_mhz) {
+					closest_clk_lvl = j;
+					break;
+				}
+			}
+			if (clk_table->num_entries == 1) {
+				/*smu gives one DPM level, let's take the highest one*/
+				closest_clk_lvl = dcn3_14_soc.num_states - 1;
+			}
+
+			clock_limits[i].state = i;
+
+			/* Clocks dependent on voltage level. */
+			clock_limits[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz;
+			if (clk_table->num_entries == 1 &&
+				clock_limits[i].dcfclk_mhz < dcn3_14_soc.clock_limits[closest_clk_lvl].dcfclk_mhz) {
+				/*SMU fix not released yet*/
+				clock_limits[i].dcfclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].dcfclk_mhz;
+			}
+			clock_limits[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz;
+			clock_limits[i].socclk_mhz = clk_table->entries[i].socclk_mhz;
+
+			if (clk_table->entries[i].memclk_mhz && clk_table->entries[i].wck_ratio)
+				clock_limits[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2 * clk_table->entries[i].wck_ratio;
+
+			/* Clocks independent of voltage level. */
+			clock_limits[i].dispclk_mhz = max_dispclk_mhz ? max_dispclk_mhz :
+				dcn3_14_soc.clock_limits[closest_clk_lvl].dispclk_mhz;
+
+			clock_limits[i].dppclk_mhz = max_dppclk_mhz ? max_dppclk_mhz :
+				dcn3_14_soc.clock_limits[closest_clk_lvl].dppclk_mhz;
+
+			clock_limits[i].dram_bw_per_chan_gbps = dcn3_14_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps;
+			clock_limits[i].dscclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].dscclk_mhz;
+			clock_limits[i].dtbclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].dtbclk_mhz;
+			clock_limits[i].phyclk_d18_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz;
+			clock_limits[i].phyclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].phyclk_mhz;
+		}
+		for (i = 0; i < clk_table->num_entries; i++)
+			dcn3_14_soc.clock_limits[i] = clock_limits[i];
+		if (clk_table->num_entries) {
+			dcn3_14_soc.num_states = clk_table->num_entries;
+		}
+	}
+
+	if (max_dispclk_mhz) {
+		dcn3_14_soc.dispclk_dppclk_vco_speed_mhz = max_dispclk_mhz * 2;
+		dc->dml.soc.dispclk_dppclk_vco_speed_mhz = max_dispclk_mhz * 2;
+	}
+
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
+		dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN31);
+	else
+		dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN31_FPGA);
+}
+
+static bool is_dual_plane(enum surface_pixel_format format)
+{
+	return format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN || format == SURFACE_PIXEL_FORMAT_GRPH_RGBE_ALPHA;
+}
+
+int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *context,
+					       display_e2e_pipe_params_st *pipes,
+					       bool fast_validate)
+{
+	int i, pipe_cnt;
+	struct resource_context *res_ctx = &context->res_ctx;
+	struct pipe_ctx *pipe;
+	bool upscaled = false;
+
+	dc_assert_fp_enabled();
+
+	dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate);
+
+	for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
+		struct dc_crtc_timing *timing;
+
+		if (!res_ctx->pipe_ctx[i].stream)
+			continue;
+		pipe = &res_ctx->pipe_ctx[i];
+		timing = &pipe->stream->timing;
+
+		if (dc_extended_blank_supported(dc) && pipe->stream->adjust.v_total_max == pipe->stream->adjust.v_total_min
+			&& pipe->stream->adjust.v_total_min > timing->v_total)
+			pipes[pipe_cnt].pipe.dest.vtotal = pipe->stream->adjust.v_total_min;
+
+		if (pipe->plane_state &&
+				(pipe->plane_state->src_rect.height < pipe->plane_state->dst_rect.height ||
+				pipe->plane_state->src_rect.width < pipe->plane_state->dst_rect.width))
+			upscaled = true;
+
+		/*
+		 * Immediate flip can be set dynamically after enabling the plane.
+		 * We need to require support for immediate flip or underflow can be
+		 * intermittently experienced depending on peak b/w requirements.
+		 */
+		pipes[pipe_cnt].pipe.src.immediate_flip = true;
+
+		pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
+		pipes[pipe_cnt].pipe.src.hostvm = dc->res_pool->hubbub->riommu_active;
+		pipes[pipe_cnt].pipe.src.gpuvm = true;
+		pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_luma = 0;
+		pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_chroma = 0;
+		pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
+		pipes[pipe_cnt].pipe.src.dcc_rate = 3;
+		pipes[pipe_cnt].dout.dsc_input_bpc = 0;
+
+		if (pipes[pipe_cnt].dout.dsc_enable) {
+			switch (timing->display_color_depth) {
+			case COLOR_DEPTH_888:
+				pipes[pipe_cnt].dout.dsc_input_bpc = 8;
+				break;
+			case COLOR_DEPTH_101010:
+				pipes[pipe_cnt].dout.dsc_input_bpc = 10;
+				break;
+			case COLOR_DEPTH_121212:
+				pipes[pipe_cnt].dout.dsc_input_bpc = 12;
+				break;
+			default:
+				ASSERT(0);
+				break;
+			}
+		}
+
+		pipe_cnt++;
+	}
+	context->bw_ctx.dml.ip.det_buffer_size_kbytes = DCN3_14_DEFAULT_DET_SIZE;
+
+	dc->config.enable_4to1MPC = false;
+	if (pipe_cnt == 1 && pipe->plane_state && !dc->debug.disable_z9_mpc) {
+		if (is_dual_plane(pipe->plane_state->format)
+				&& pipe->plane_state->src_rect.width <= 1920 && pipe->plane_state->src_rect.height <= 1080) {
+			dc->config.enable_4to1MPC = true;
+		} else if (!is_dual_plane(pipe->plane_state->format) && pipe->plane_state->src_rect.width <= 5120) {
+			/* Limit to 5k max to avoid forced pipe split when there is not enough detile for swath */
+			context->bw_ctx.dml.ip.det_buffer_size_kbytes = 192;
+			pipes[0].pipe.src.unbounded_req_mode = true;
+		}
+	} else if (context->stream_count >= dc->debug.crb_alloc_policy_min_disp_count
+			&& dc->debug.crb_alloc_policy > DET_SIZE_DEFAULT) {
+		context->bw_ctx.dml.ip.det_buffer_size_kbytes = dc->debug.crb_alloc_policy * 64;
+	} else if (context->stream_count >= 3 && upscaled) {
+		context->bw_ctx.dml.ip.det_buffer_size_kbytes = 192;
+	}
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
+
+		if (!pipe->stream)
+			continue;
+
+		if (pipe->stream->signal == SIGNAL_TYPE_EDP && dc->debug.seamless_boot_odm_combine &&
+				pipe->stream->apply_seamless_boot_optimization) {
+
+			if (pipe->stream->apply_boot_odm_mode == dm_odm_combine_policy_2to1) {
+				context->bw_ctx.dml.vba.ODMCombinePolicy = dm_odm_combine_policy_2to1;
+				break;
+			}
+		}
+	}
+
+	return pipe_cnt;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.h
new file mode 100644
index 000000000000..d32c5bb99f4c
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright 2022 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DCN314_FPU_H__
+#define __DCN314_FPU_H__
+
+#define DCN3_14_DEFAULT_DET_SIZE 384
+#define DCN3_14_MAX_DET_SIZE 384
+#define DCN3_14_MIN_COMPBUF_SIZE_KB 128
+#define DCN3_14_CRB_SEGMENT_SIZE_KB 64
+
+void dcn314_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_params);
+int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *context,
+					       display_e2e_pipe_params_st *pipes,
+					       bool fast_validate);
+
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index 66453546e24f..8118cfc5b405 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -473,8 +473,11 @@ void dcn32_set_phantom_stream_timing(struct dc *dc,
 
 	// DML calculation for MALL region doesn't take into account FW delay
 	// and required pstate allow width for multi-display cases
+	/* Add 16 lines margin to the MALL REGION because SUB_VP_START_LINE must be aligned
+	 * to 2 swaths (i.e. 16 lines)
+	 */
 	phantom_vactive = get_subviewport_lines_needed_in_mall(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx) +
-				pstate_width_fw_delay_lines;
+				pstate_width_fw_delay_lines + dc->caps.subvp_swath_height_margin_lines;
 
 	// For backporch of phantom pipe, use vstartup of the main pipe
 	phantom_bp = get_vstartup(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
@@ -490,6 +493,7 @@ void dcn32_set_phantom_stream_timing(struct dc *dc,
 						phantom_stream->timing.v_front_porch +
 						phantom_stream->timing.v_sync_width +
 						phantom_bp;
+	phantom_stream->timing.flags.DSC = 0; // Don't need DSC for phantom timing
 }
 
 /**
@@ -983,9 +987,15 @@ static void dcn32_full_validate_bw_helper(struct dc *dc,
 	 * DML favors voltage over p-state, but we're more interested in
 	 * supporting p-state over voltage. We can't support p-state in
 	 * prefetch mode > 0 so try capping the prefetch mode to start.
+	 * Override present for testing.
 	 */
-	context->bw_ctx.dml.soc.allow_for_pstate_or_stutter_in_vblank_final =
+	if (dc->debug.dml_disallow_alternate_prefetch_modes)
+		context->bw_ctx.dml.soc.allow_for_pstate_or_stutter_in_vblank_final =
 			dm_prefetch_support_uclk_fclk_and_stutter;
+	else
+		context->bw_ctx.dml.soc.allow_for_pstate_or_stutter_in_vblank_final =
+			dm_prefetch_support_uclk_fclk_and_stutter_if_possible;
+
 	*vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, *pipe_cnt);
 	/* This may adjust vlevel and maxMpcComb */
 	if (*vlevel < context->bw_ctx.dml.soc.num_states)
@@ -1014,7 +1024,9 @@ static void dcn32_full_validate_bw_helper(struct dc *dc,
 			 * will not allow for switch in VBLANK. The DRR display must have it's VBLANK stretched
 			 * enough to support MCLK switching.
 			 */
-			if (*vlevel == context->bw_ctx.dml.soc.num_states) {
+			if (*vlevel == context->bw_ctx.dml.soc.num_states &&
+				context->bw_ctx.dml.soc.allow_for_pstate_or_stutter_in_vblank_final ==
+					dm_prefetch_support_uclk_fclk_and_stutter) {
 				context->bw_ctx.dml.soc.allow_for_pstate_or_stutter_in_vblank_final =
 								dm_prefetch_support_stutter;
 				/* There are params (such as FabricClock) that need to be recalculated
@@ -1344,7 +1356,8 @@ bool dcn32_internal_validate_bw(struct dc *dc,
 	int split[MAX_PIPES] = { 0 };
 	bool merge[MAX_PIPES] = { false };
 	bool newly_split[MAX_PIPES] = { false };
-	int pipe_cnt, i, pipe_idx, vlevel;
+	int pipe_cnt, i, pipe_idx;
+	int vlevel = context->bw_ctx.dml.soc.num_states;
 	struct vba_vars_st *vba = &context->bw_ctx.dml.vba;
 
 	dc_assert_fp_enabled();
@@ -1373,17 +1386,22 @@ bool dcn32_internal_validate_bw(struct dc *dc,
 		DC_FP_END();
 	}
 
-	if (fast_validate || vlevel == context->bw_ctx.dml.soc.num_states ||
-			vba->DRAMClockChangeSupport[vlevel][vba->maxMpcComb] == dm_dram_clock_change_unsupported) {
+	if (fast_validate ||
+			(dc->debug.dml_disallow_alternate_prefetch_modes &&
+			(vlevel == context->bw_ctx.dml.soc.num_states ||
+				vba->DRAMClockChangeSupport[vlevel][vba->maxMpcComb] == dm_dram_clock_change_unsupported))) {
 		/*
-		 * If mode is unsupported or there's still no p-state support then
-		 * fall back to favoring voltage.
+		 * If dml_disallow_alternate_prefetch_modes is false, then we have already
+		 * tried alternate prefetch modes during full validation.
+		 *
+		 * If mode is unsupported or there is no p-state support, then
+		 * fall back to favouring voltage.
 		 *
-		 * If Prefetch mode 0 failed for this config, or passed with Max UCLK, try if
-		 * supported with Prefetch mode 1 (dm_prefetch_support_fclk_and_stutter == 2)
+		 * If Prefetch mode 0 failed for this config, or passed with Max UCLK, then try
+		 * to support with Prefetch mode 1 (dm_prefetch_support_fclk_and_stutter == 2)
 		 */
 		context->bw_ctx.dml.soc.allow_for_pstate_or_stutter_in_vblank_final =
-				dm_prefetch_support_fclk_and_stutter;
+			dm_prefetch_support_fclk_and_stutter;
 
 		vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, pipe_cnt);
 
@@ -2098,6 +2116,13 @@ void dcn32_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_pa
 				dc->bb_overrides.dram_clock_change_latency_ns / 1000.0;
 		}
 
+		if ((int)(dcn3_2_soc.fclk_change_latency_us * 1000)
+				!= dc->bb_overrides.fclk_clock_change_latency_ns
+				&& dc->bb_overrides.fclk_clock_change_latency_ns) {
+			dcn3_2_soc.fclk_change_latency_us =
+				dc->bb_overrides.fclk_clock_change_latency_ns / 1000;
+		}
+
 		if ((int)(dcn3_2_soc.dummy_pstate_latency_us * 1000)
 				!= dc->bb_overrides.dummy_clock_change_latency_ns
 				&& dc->bb_overrides.dummy_clock_change_latency_ns) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c
index 890612db08dc..cb2025771646 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c
@@ -221,7 +221,6 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 		// VBA_DELTA
 		// Calculate DET size, swath height
 		dml32_CalculateSwathAndDETConfiguration(
-				&v->dummy_vars.dml32_CalculateSwathAndDETConfiguration,
 				mode_lib->vba.DETSizeOverride,
 				mode_lib->vba.UsesMALLForPStateChange,
 				mode_lib->vba.ConfigReturnBufferSizeInKByte,
@@ -461,7 +460,6 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 	{
 
 		dml32_CalculateVMRowAndSwath(
-				&v->dummy_vars.dml32_CalculateVMRowAndSwath,
 				mode_lib->vba.NumberOfActiveSurfaces,
 				v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.SurfaceParameters,
 				v->SurfaceSizeInMALL,
@@ -757,9 +755,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 			v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.BytePerPixelY = v->BytePerPixelY[k];
 			v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.BytePerPixelC = v->BytePerPixelC[k];
 			v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.ProgressiveToInterlaceUnitInOPP = mode_lib->vba.ProgressiveToInterlaceUnitInOPP;
-			v->ErrorResult[k] = dml32_CalculatePrefetchSchedule(
-					&v->dummy_vars.dml32_CalculatePrefetchSchedule,
-					v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.HostVMInefficiencyFactor,
+			v->ErrorResult[k] = dml32_CalculatePrefetchSchedule(v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.HostVMInefficiencyFactor,
 					&v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe, v->DSCDelay[k],
 					mode_lib->vba.DPPCLKDelaySubtotal + mode_lib->vba.DPPCLKDelayCNVCFormater,
 					mode_lib->vba.DPPCLKDelaySCL,
@@ -1167,7 +1163,6 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 		v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.mmSOCParameters.SMNLatency = mode_lib->vba.SMNLatency;
 
 		dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
-			&v->dummy_vars.dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport,
 			mode_lib->vba.USRRetrainingRequiredFinal,
 			mode_lib->vba.UsesMALLForPStateChange,
 			mode_lib->vba.PrefetchModePerState[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb],
@@ -1952,7 +1947,6 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	}
 
 	dml32_CalculateSwathAndDETConfiguration(
-			&v->dummy_vars.dml32_CalculateSwathAndDETConfiguration,
 			mode_lib->vba.DETSizeOverride,
 			mode_lib->vba.UsesMALLForPStateChange,
 			mode_lib->vba.ConfigReturnBufferSizeInKByte,
@@ -2549,7 +2543,6 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 			}
 
 			dml32_CalculateSwathAndDETConfiguration(
-					&v->dummy_vars.dml32_CalculateSwathAndDETConfiguration,
 					mode_lib->vba.DETSizeOverride,
 					mode_lib->vba.UsesMALLForPStateChange,
 					mode_lib->vba.ConfigReturnBufferSizeInKByte,
@@ -2749,7 +2742,6 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 
 			{
 				dml32_CalculateVMRowAndSwath(
-						&v->dummy_vars.dml32_CalculateVMRowAndSwath,
 						mode_lib->vba.NumberOfActiveSurfaces,
 						v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters,
 						mode_lib->vba.SurfaceSizeInMALL,
@@ -3266,7 +3258,6 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 
 					mode_lib->vba.NoTimeForPrefetch[i][j][k] =
 						dml32_CalculatePrefetchSchedule(
-							&v->dummy_vars.dml32_CalculatePrefetchSchedule,
 							v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.HostVMInefficiencyFactor,
 							&v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.myPipe,
 							mode_lib->vba.DSCDelayPerState[i][k],
@@ -3566,7 +3557,6 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 
 			{
 				dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
-						&v->dummy_vars.dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport,
 						mode_lib->vba.USRRetrainingRequiredFinal,
 						mode_lib->vba.UsesMALLForPStateChange,
 						mode_lib->vba.PrefetchModePerState[i][j],
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
index 07f8f3b8626b..05fc14a47fba 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
@@ -391,7 +391,6 @@ void dml32_CalculateBytePerPixelAndBlockSizes(
 } // CalculateBytePerPixelAndBlockSizes
 
 void dml32_CalculateSwathAndDETConfiguration(
-		struct dml32_CalculateSwathAndDETConfiguration *st_vars,
 		unsigned int DETSizeOverride[],
 		enum dm_use_mall_for_pstate_change_mode UseMALLForPStateChange[],
 		unsigned int ConfigReturnBufferSizeInKByte,
@@ -456,10 +455,18 @@ void dml32_CalculateSwathAndDETConfiguration(
 		bool ViewportSizeSupportPerSurface[],
 		bool *ViewportSizeSupport)
 {
+	unsigned int MaximumSwathHeightY[DC__NUM_DPP__MAX];
+	unsigned int MaximumSwathHeightC[DC__NUM_DPP__MAX];
+	unsigned int RoundedUpMaxSwathSizeBytesY[DC__NUM_DPP__MAX];
+	unsigned int RoundedUpMaxSwathSizeBytesC[DC__NUM_DPP__MAX];
+	unsigned int RoundedUpSwathSizeBytesY;
+	unsigned int RoundedUpSwathSizeBytesC;
+	double SwathWidthdoubleDPP[DC__NUM_DPP__MAX];
+	double SwathWidthdoubleDPPChroma[DC__NUM_DPP__MAX];
 	unsigned int k;
-
-	st_vars->TotalActiveDPP = 0;
-	st_vars->NoChromaSurfaces = true;
+	unsigned int TotalActiveDPP = 0;
+	bool NoChromaSurfaces = true;
+	unsigned int DETBufferSizeInKByteForSwathCalculation;
 
 #ifdef __DML_VBA_DEBUG__
 	dml_print("DML::%s: ForceSingleDPP = %d\n", __func__, ForceSingleDPP);
@@ -494,43 +501,43 @@ void dml32_CalculateSwathAndDETConfiguration(
 			DPPPerSurface,
 
 			/* Output */
-			st_vars->SwathWidthdoubleDPP,
-			st_vars->SwathWidthdoubleDPPChroma,
+			SwathWidthdoubleDPP,
+			SwathWidthdoubleDPPChroma,
 			SwathWidth,
 			SwathWidthChroma,
-			st_vars->MaximumSwathHeightY,
-			st_vars->MaximumSwathHeightC,
+			MaximumSwathHeightY,
+			MaximumSwathHeightC,
 			swath_width_luma_ub,
 			swath_width_chroma_ub);
 
 	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
-		st_vars->RoundedUpMaxSwathSizeBytesY[k] = swath_width_luma_ub[k] * BytePerPixDETY[k] * st_vars->MaximumSwathHeightY[k];
-		st_vars->RoundedUpMaxSwathSizeBytesC[k] = swath_width_chroma_ub[k] * BytePerPixDETC[k] * st_vars->MaximumSwathHeightC[k];
+		RoundedUpMaxSwathSizeBytesY[k] = swath_width_luma_ub[k] * BytePerPixDETY[k] * MaximumSwathHeightY[k];
+		RoundedUpMaxSwathSizeBytesC[k] = swath_width_chroma_ub[k] * BytePerPixDETC[k] * MaximumSwathHeightC[k];
 #ifdef __DML_VBA_DEBUG__
 		dml_print("DML::%s: k=%0d DPPPerSurface = %d\n", __func__, k, DPPPerSurface[k]);
 		dml_print("DML::%s: k=%0d swath_width_luma_ub = %d\n", __func__, k, swath_width_luma_ub[k]);
 		dml_print("DML::%s: k=%0d BytePerPixDETY = %f\n", __func__, k, BytePerPixDETY[k]);
-		dml_print("DML::%s: k=%0d MaximumSwathHeightY = %d\n", __func__, k, st_vars->MaximumSwathHeightY[k]);
+		dml_print("DML::%s: k=%0d MaximumSwathHeightY = %d\n", __func__, k, MaximumSwathHeightY[k]);
 		dml_print("DML::%s: k=%0d RoundedUpMaxSwathSizeBytesY = %d\n", __func__, k,
-				st_vars->RoundedUpMaxSwathSizeBytesY[k]);
+				RoundedUpMaxSwathSizeBytesY[k]);
 		dml_print("DML::%s: k=%0d swath_width_chroma_ub = %d\n", __func__, k, swath_width_chroma_ub[k]);
 		dml_print("DML::%s: k=%0d BytePerPixDETC = %f\n", __func__, k, BytePerPixDETC[k]);
-		dml_print("DML::%s: k=%0d MaximumSwathHeightC = %d\n", __func__, k, st_vars->MaximumSwathHeightC[k]);
+		dml_print("DML::%s: k=%0d MaximumSwathHeightC = %d\n", __func__, k, MaximumSwathHeightC[k]);
 		dml_print("DML::%s: k=%0d RoundedUpMaxSwathSizeBytesC = %d\n", __func__, k,
-				st_vars->RoundedUpMaxSwathSizeBytesC[k]);
+				RoundedUpMaxSwathSizeBytesC[k]);
 #endif
 
 		if (SourcePixelFormat[k] == dm_420_10) {
-			st_vars->RoundedUpMaxSwathSizeBytesY[k] = dml_ceil((unsigned int) st_vars->RoundedUpMaxSwathSizeBytesY[k], 256);
-			st_vars->RoundedUpMaxSwathSizeBytesC[k] = dml_ceil((unsigned int) st_vars->RoundedUpMaxSwathSizeBytesC[k], 256);
+			RoundedUpMaxSwathSizeBytesY[k] = dml_ceil((unsigned int) RoundedUpMaxSwathSizeBytesY[k], 256);
+			RoundedUpMaxSwathSizeBytesC[k] = dml_ceil((unsigned int) RoundedUpMaxSwathSizeBytesC[k], 256);
 		}
 	}
 
 	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
-		st_vars->TotalActiveDPP = st_vars->TotalActiveDPP + (ForceSingleDPP ? 1 : DPPPerSurface[k]);
+		TotalActiveDPP = TotalActiveDPP + (ForceSingleDPP ? 1 : DPPPerSurface[k]);
 		if (SourcePixelFormat[k] == dm_420_8 || SourcePixelFormat[k] == dm_420_10 ||
 				SourcePixelFormat[k] == dm_420_12 || SourcePixelFormat[k] == dm_rgbe_alpha) {
-			st_vars->NoChromaSurfaces = false;
+			NoChromaSurfaces = false;
 		}
 	}
 
@@ -540,10 +547,10 @@ void dml32_CalculateSwathAndDETConfiguration(
 	// if unbounded req is enabled, program reserved space such that the ROB will not hold more than 8 swaths worth of data
 	// - assume worst-case compression rate of 4. [ROB size - 8 * swath_size / max_compression ratio]
 	// - assume for "narrow" vp case in which the ROB can fit 8 swaths, the DET should be big enough to do full size req
-	*CompBufReservedSpaceNeedAdjustment = ((int) ROBSizeKBytes - (int) *CompBufReservedSpaceKBytes) > (int) (st_vars->RoundedUpMaxSwathSizeBytesY[0]/512);
+	*CompBufReservedSpaceNeedAdjustment = ((int) ROBSizeKBytes - (int) *CompBufReservedSpaceKBytes) > (int) (RoundedUpMaxSwathSizeBytesY[0]/512);
 
 	if (*CompBufReservedSpaceNeedAdjustment == 1) {
-		*CompBufReservedSpaceKBytes = ROBSizeKBytes - st_vars->RoundedUpMaxSwathSizeBytesY[0]/512;
+		*CompBufReservedSpaceKBytes = ROBSizeKBytes - RoundedUpMaxSwathSizeBytesY[0]/512;
 	}
 
 	#ifdef __DML_VBA_DEBUG__
@@ -551,7 +558,7 @@ void dml32_CalculateSwathAndDETConfiguration(
 		dml_print("DML::%s: CompBufReservedSpaceNeedAdjustment  = %d\n",  __func__, *CompBufReservedSpaceNeedAdjustment);
 	#endif
 
-	*UnboundedRequestEnabled = dml32_UnboundedRequest(UseUnboundedRequestingFinal, st_vars->TotalActiveDPP, st_vars->NoChromaSurfaces, Output[0], SurfaceTiling[0], *CompBufReservedSpaceNeedAdjustment, DisableUnboundRequestIfCompBufReservedSpaceNeedAdjustment);
+	*UnboundedRequestEnabled = dml32_UnboundedRequest(UseUnboundedRequestingFinal, TotalActiveDPP, NoChromaSurfaces, Output[0], SurfaceTiling[0], *CompBufReservedSpaceNeedAdjustment, DisableUnboundRequestIfCompBufReservedSpaceNeedAdjustment);
 
 	dml32_CalculateDETBufferSize(DETSizeOverride,
 			UseMALLForPStateChange,
@@ -566,8 +573,8 @@ void dml32_CalculateSwathAndDETConfiguration(
 			SourcePixelFormat,
 			ReadBandwidthLuma,
 			ReadBandwidthChroma,
-			st_vars->RoundedUpMaxSwathSizeBytesY,
-			st_vars->RoundedUpMaxSwathSizeBytesC,
+			RoundedUpMaxSwathSizeBytesY,
+			RoundedUpMaxSwathSizeBytesC,
 			DPPPerSurface,
 
 			/* Output */
@@ -575,7 +582,7 @@ void dml32_CalculateSwathAndDETConfiguration(
 			CompressedBufferSizeInkByte);
 
 #ifdef __DML_VBA_DEBUG__
-	dml_print("DML::%s: TotalActiveDPP = %d\n", __func__, st_vars->TotalActiveDPP);
+	dml_print("DML::%s: TotalActiveDPP = %d\n", __func__, TotalActiveDPP);
 	dml_print("DML::%s: nomDETInKByte = %d\n", __func__, nomDETInKByte);
 	dml_print("DML::%s: ConfigReturnBufferSizeInKByte = %d\n", __func__, ConfigReturnBufferSizeInKByte);
 	dml_print("DML::%s: UseUnboundedRequestingFinal = %d\n", __func__, UseUnboundedRequestingFinal);
@@ -586,42 +593,42 @@ void dml32_CalculateSwathAndDETConfiguration(
 	*ViewportSizeSupport = true;
 	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
 
-		st_vars->DETBufferSizeInKByteForSwathCalculation = (UseMALLForPStateChange[k] ==
+		DETBufferSizeInKByteForSwathCalculation = (UseMALLForPStateChange[k] ==
 				dm_use_mall_pstate_change_phantom_pipe ? 1024 : DETBufferSizeInKByte[k]);
 #ifdef __DML_VBA_DEBUG__
 		dml_print("DML::%s: k=%0d DETBufferSizeInKByteForSwathCalculation = %d\n", __func__, k,
-				st_vars->DETBufferSizeInKByteForSwathCalculation);
+				DETBufferSizeInKByteForSwathCalculation);
 #endif
 
-		if (st_vars->RoundedUpMaxSwathSizeBytesY[k] + st_vars->RoundedUpMaxSwathSizeBytesC[k] <=
-				st_vars->DETBufferSizeInKByteForSwathCalculation * 1024 / 2) {
-			SwathHeightY[k] = st_vars->MaximumSwathHeightY[k];
-			SwathHeightC[k] = st_vars->MaximumSwathHeightC[k];
-			st_vars->RoundedUpSwathSizeBytesY = st_vars->RoundedUpMaxSwathSizeBytesY[k];
-			st_vars->RoundedUpSwathSizeBytesC = st_vars->RoundedUpMaxSwathSizeBytesC[k];
-		} else if (st_vars->RoundedUpMaxSwathSizeBytesY[k] >= 1.5 * st_vars->RoundedUpMaxSwathSizeBytesC[k] &&
-				st_vars->RoundedUpMaxSwathSizeBytesY[k] / 2 + st_vars->RoundedUpMaxSwathSizeBytesC[k] <=
-				st_vars->DETBufferSizeInKByteForSwathCalculation * 1024 / 2) {
-			SwathHeightY[k] = st_vars->MaximumSwathHeightY[k] / 2;
-			SwathHeightC[k] = st_vars->MaximumSwathHeightC[k];
-			st_vars->RoundedUpSwathSizeBytesY = st_vars->RoundedUpMaxSwathSizeBytesY[k] / 2;
-			st_vars->RoundedUpSwathSizeBytesC = st_vars->RoundedUpMaxSwathSizeBytesC[k];
-		} else if (st_vars->RoundedUpMaxSwathSizeBytesY[k] < 1.5 * st_vars->RoundedUpMaxSwathSizeBytesC[k] &&
-				st_vars->RoundedUpMaxSwathSizeBytesY[k] + st_vars->RoundedUpMaxSwathSizeBytesC[k] / 2 <=
-				st_vars->DETBufferSizeInKByteForSwathCalculation * 1024 / 2) {
-			SwathHeightY[k] = st_vars->MaximumSwathHeightY[k];
-			SwathHeightC[k] = st_vars->MaximumSwathHeightC[k] / 2;
-			st_vars->RoundedUpSwathSizeBytesY = st_vars->RoundedUpMaxSwathSizeBytesY[k];
-			st_vars->RoundedUpSwathSizeBytesC = st_vars->RoundedUpMaxSwathSizeBytesC[k] / 2;
+		if (RoundedUpMaxSwathSizeBytesY[k] + RoundedUpMaxSwathSizeBytesC[k] <=
+				DETBufferSizeInKByteForSwathCalculation * 1024 / 2) {
+			SwathHeightY[k] = MaximumSwathHeightY[k];
+			SwathHeightC[k] = MaximumSwathHeightC[k];
+			RoundedUpSwathSizeBytesY = RoundedUpMaxSwathSizeBytesY[k];
+			RoundedUpSwathSizeBytesC = RoundedUpMaxSwathSizeBytesC[k];
+		} else if (RoundedUpMaxSwathSizeBytesY[k] >= 1.5 * RoundedUpMaxSwathSizeBytesC[k] &&
+				RoundedUpMaxSwathSizeBytesY[k] / 2 + RoundedUpMaxSwathSizeBytesC[k] <=
+				DETBufferSizeInKByteForSwathCalculation * 1024 / 2) {
+			SwathHeightY[k] = MaximumSwathHeightY[k] / 2;
+			SwathHeightC[k] = MaximumSwathHeightC[k];
+			RoundedUpSwathSizeBytesY = RoundedUpMaxSwathSizeBytesY[k] / 2;
+			RoundedUpSwathSizeBytesC = RoundedUpMaxSwathSizeBytesC[k];
+		} else if (RoundedUpMaxSwathSizeBytesY[k] < 1.5 * RoundedUpMaxSwathSizeBytesC[k] &&
+				RoundedUpMaxSwathSizeBytesY[k] + RoundedUpMaxSwathSizeBytesC[k] / 2 <=
+				DETBufferSizeInKByteForSwathCalculation * 1024 / 2) {
+			SwathHeightY[k] = MaximumSwathHeightY[k];
+			SwathHeightC[k] = MaximumSwathHeightC[k] / 2;
+			RoundedUpSwathSizeBytesY = RoundedUpMaxSwathSizeBytesY[k];
+			RoundedUpSwathSizeBytesC = RoundedUpMaxSwathSizeBytesC[k] / 2;
 		} else {
-			SwathHeightY[k] = st_vars->MaximumSwathHeightY[k] / 2;
-			SwathHeightC[k] = st_vars->MaximumSwathHeightC[k] / 2;
-			st_vars->RoundedUpSwathSizeBytesY = st_vars->RoundedUpMaxSwathSizeBytesY[k] / 2;
-			st_vars->RoundedUpSwathSizeBytesC = st_vars->RoundedUpMaxSwathSizeBytesC[k] / 2;
+			SwathHeightY[k] = MaximumSwathHeightY[k] / 2;
+			SwathHeightC[k] = MaximumSwathHeightC[k] / 2;
+			RoundedUpSwathSizeBytesY = RoundedUpMaxSwathSizeBytesY[k] / 2;
+			RoundedUpSwathSizeBytesC = RoundedUpMaxSwathSizeBytesC[k] / 2;
 		}
 
-		if ((st_vars->RoundedUpMaxSwathSizeBytesY[k] / 2 + st_vars->RoundedUpMaxSwathSizeBytesC[k] / 2 >
-				st_vars->DETBufferSizeInKByteForSwathCalculation * 1024 / 2)
+		if ((RoundedUpMaxSwathSizeBytesY[k] / 2 + RoundedUpMaxSwathSizeBytesC[k] / 2 >
+				DETBufferSizeInKByteForSwathCalculation * 1024 / 2)
 				|| SwathWidth[k] > MaximumSwathWidthLuma[k] || (SwathHeightC[k] > 0 &&
 						SwathWidthChroma[k] > MaximumSwathWidthChroma[k])) {
 			*ViewportSizeSupport = false;
@@ -636,7 +643,7 @@ void dml32_CalculateSwathAndDETConfiguration(
 #endif
 			DETBufferSizeY[k] = DETBufferSizeInKByte[k] * 1024;
 			DETBufferSizeC[k] = 0;
-		} else if (st_vars->RoundedUpSwathSizeBytesY <= 1.5 * st_vars->RoundedUpSwathSizeBytesC) {
+		} else if (RoundedUpSwathSizeBytesY <= 1.5 * RoundedUpSwathSizeBytesC) {
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML::%s: k=%0d Half DET for plane0, half for plane1\n", __func__, k);
 #endif
@@ -654,11 +661,11 @@ void dml32_CalculateSwathAndDETConfiguration(
 		dml_print("DML::%s: k=%0d SwathHeightY = %d\n", __func__, k, SwathHeightY[k]);
 		dml_print("DML::%s: k=%0d SwathHeightC = %d\n", __func__, k, SwathHeightC[k]);
 		dml_print("DML::%s: k=%0d RoundedUpMaxSwathSizeBytesY = %d\n", __func__,
-				k, st_vars->RoundedUpMaxSwathSizeBytesY[k]);
+				k, RoundedUpMaxSwathSizeBytesY[k]);
 		dml_print("DML::%s: k=%0d RoundedUpMaxSwathSizeBytesC = %d\n", __func__,
-				k, st_vars->RoundedUpMaxSwathSizeBytesC[k]);
-		dml_print("DML::%s: k=%0d RoundedUpSwathSizeBytesY = %d\n", __func__, k, st_vars->RoundedUpSwathSizeBytesY);
-		dml_print("DML::%s: k=%0d RoundedUpSwathSizeBytesC = %d\n", __func__, k, st_vars->RoundedUpSwathSizeBytesC);
+				k, RoundedUpMaxSwathSizeBytesC[k]);
+		dml_print("DML::%s: k=%0d RoundedUpSwathSizeBytesY = %d\n", __func__, k, RoundedUpSwathSizeBytesY);
+		dml_print("DML::%s: k=%0d RoundedUpSwathSizeBytesC = %d\n", __func__, k, RoundedUpSwathSizeBytesC);
 		dml_print("DML::%s: k=%0d DETBufferSizeInKByte = %d\n", __func__, k, DETBufferSizeInKByte[k]);
 		dml_print("DML::%s: k=%0d DETBufferSizeY = %d\n", __func__, k, DETBufferSizeY[k]);
 		dml_print("DML::%s: k=%0d DETBufferSizeC = %d\n", __func__, k, DETBufferSizeC[k]);
@@ -1867,7 +1874,6 @@ void dml32_CalculateSurfaceSizeInMall(
 } // CalculateSurfaceSizeInMall
 
 void dml32_CalculateVMRowAndSwath(
-		struct dml32_CalculateVMRowAndSwath *st_vars,
 		unsigned int NumberOfActiveSurfaces,
 		DmlPipe myPipe[],
 		unsigned int SurfaceSizeInMALL[],
@@ -1933,6 +1939,21 @@ void dml32_CalculateVMRowAndSwath(
 		unsigned int BIGK_FRAGMENT_SIZE[])
 {
 	unsigned int k;
+	unsigned int PTEBufferSizeInRequestsForLuma[DC__NUM_DPP__MAX];
+	unsigned int PTEBufferSizeInRequestsForChroma[DC__NUM_DPP__MAX];
+	unsigned int PDEAndMetaPTEBytesFrameY;
+	unsigned int PDEAndMetaPTEBytesFrameC;
+	unsigned int MetaRowByteY[DC__NUM_DPP__MAX];
+	unsigned int MetaRowByteC[DC__NUM_DPP__MAX];
+	unsigned int PixelPTEBytesPerRowY[DC__NUM_DPP__MAX];
+	unsigned int PixelPTEBytesPerRowC[DC__NUM_DPP__MAX];
+	unsigned int PixelPTEBytesPerRowY_one_row_per_frame[DC__NUM_DPP__MAX];
+	unsigned int PixelPTEBytesPerRowC_one_row_per_frame[DC__NUM_DPP__MAX];
+	unsigned int dpte_row_width_luma_ub_one_row_per_frame[DC__NUM_DPP__MAX];
+	unsigned int dpte_row_height_luma_one_row_per_frame[DC__NUM_DPP__MAX];
+	unsigned int dpte_row_width_chroma_ub_one_row_per_frame[DC__NUM_DPP__MAX];
+	unsigned int dpte_row_height_chroma_one_row_per_frame[DC__NUM_DPP__MAX];
+	bool one_row_per_frame_fits_in_buffer[DC__NUM_DPP__MAX];
 
 	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
 		if (HostVMEnable == true) {
@@ -1954,15 +1975,15 @@ void dml32_CalculateVMRowAndSwath(
 				myPipe[k].SourcePixelFormat == dm_rgbe_alpha) {
 			if ((myPipe[k].SourcePixelFormat == dm_420_10 || myPipe[k].SourcePixelFormat == dm_420_12) &&
 					!IsVertical(myPipe[k].SourceRotation)) {
-				st_vars->PTEBufferSizeInRequestsForLuma[k] =
+				PTEBufferSizeInRequestsForLuma[k] =
 						(PTEBufferSizeInRequestsLuma + PTEBufferSizeInRequestsChroma) / 2;
-				st_vars->PTEBufferSizeInRequestsForChroma[k] = st_vars->PTEBufferSizeInRequestsForLuma[k];
+				PTEBufferSizeInRequestsForChroma[k] = PTEBufferSizeInRequestsForLuma[k];
 			} else {
-				st_vars->PTEBufferSizeInRequestsForLuma[k] = PTEBufferSizeInRequestsLuma;
-				st_vars->PTEBufferSizeInRequestsForChroma[k] = PTEBufferSizeInRequestsChroma;
+				PTEBufferSizeInRequestsForLuma[k] = PTEBufferSizeInRequestsLuma;
+				PTEBufferSizeInRequestsForChroma[k] = PTEBufferSizeInRequestsChroma;
 			}
 
-			st_vars->PDEAndMetaPTEBytesFrameC = dml32_CalculateVMAndRowBytes(
+			PDEAndMetaPTEBytesFrameC = dml32_CalculateVMAndRowBytes(
 					myPipe[k].ViewportStationary,
 					myPipe[k].DCCEnable,
 					myPipe[k].DPPPerSurface,
@@ -1982,21 +2003,21 @@ void dml32_CalculateVMRowAndSwath(
 					GPUVMMaxPageTableLevels,
 					GPUVMMinPageSizeKBytes[k],
 					HostVMMinPageSize,
-					st_vars->PTEBufferSizeInRequestsForChroma[k],
+					PTEBufferSizeInRequestsForChroma[k],
 					myPipe[k].PitchC,
 					myPipe[k].DCCMetaPitchC,
 					myPipe[k].BlockWidthC,
 					myPipe[k].BlockHeightC,
 
 					/* Output */
-					&st_vars->MetaRowByteC[k],
-					&st_vars->PixelPTEBytesPerRowC[k],
+					&MetaRowByteC[k],
+					&PixelPTEBytesPerRowC[k],
 					&dpte_row_width_chroma_ub[k],
 					&dpte_row_height_chroma[k],
 					&dpte_row_height_linear_chroma[k],
-					&st_vars->PixelPTEBytesPerRowC_one_row_per_frame[k],
-					&st_vars->dpte_row_width_chroma_ub_one_row_per_frame[k],
-					&st_vars->dpte_row_height_chroma_one_row_per_frame[k],
+					&PixelPTEBytesPerRowC_one_row_per_frame[k],
+					&dpte_row_width_chroma_ub_one_row_per_frame[k],
+					&dpte_row_height_chroma_one_row_per_frame[k],
 					&meta_req_width_chroma[k],
 					&meta_req_height_chroma[k],
 					&meta_row_width_chroma[k],
@@ -2024,19 +2045,19 @@ void dml32_CalculateVMRowAndSwath(
 					&VInitPreFillC[k],
 					&MaxNumSwathC[k]);
 		} else {
-			st_vars->PTEBufferSizeInRequestsForLuma[k] = PTEBufferSizeInRequestsLuma + PTEBufferSizeInRequestsChroma;
-			st_vars->PTEBufferSizeInRequestsForChroma[k] = 0;
-			st_vars->PixelPTEBytesPerRowC[k] = 0;
-			st_vars->PDEAndMetaPTEBytesFrameC = 0;
-			st_vars->MetaRowByteC[k] = 0;
+			PTEBufferSizeInRequestsForLuma[k] = PTEBufferSizeInRequestsLuma + PTEBufferSizeInRequestsChroma;
+			PTEBufferSizeInRequestsForChroma[k] = 0;
+			PixelPTEBytesPerRowC[k] = 0;
+			PDEAndMetaPTEBytesFrameC = 0;
+			MetaRowByteC[k] = 0;
 			MaxNumSwathC[k] = 0;
 			PrefetchSourceLinesC[k] = 0;
-			st_vars->dpte_row_height_chroma_one_row_per_frame[k] = 0;
-			st_vars->dpte_row_width_chroma_ub_one_row_per_frame[k] = 0;
-			st_vars->PixelPTEBytesPerRowC_one_row_per_frame[k] = 0;
+			dpte_row_height_chroma_one_row_per_frame[k] = 0;
+			dpte_row_width_chroma_ub_one_row_per_frame[k] = 0;
+			PixelPTEBytesPerRowC_one_row_per_frame[k] = 0;
 		}
 
-		st_vars->PDEAndMetaPTEBytesFrameY = dml32_CalculateVMAndRowBytes(
+		PDEAndMetaPTEBytesFrameY = dml32_CalculateVMAndRowBytes(
 				myPipe[k].ViewportStationary,
 				myPipe[k].DCCEnable,
 				myPipe[k].DPPPerSurface,
@@ -2056,21 +2077,21 @@ void dml32_CalculateVMRowAndSwath(
 				GPUVMMaxPageTableLevels,
 				GPUVMMinPageSizeKBytes[k],
 				HostVMMinPageSize,
-				st_vars->PTEBufferSizeInRequestsForLuma[k],
+				PTEBufferSizeInRequestsForLuma[k],
 				myPipe[k].PitchY,
 				myPipe[k].DCCMetaPitchY,
 				myPipe[k].BlockWidthY,
 				myPipe[k].BlockHeightY,
 
 				/* Output */
-				&st_vars->MetaRowByteY[k],
-				&st_vars->PixelPTEBytesPerRowY[k],
+				&MetaRowByteY[k],
+				&PixelPTEBytesPerRowY[k],
 				&dpte_row_width_luma_ub[k],
 				&dpte_row_height_luma[k],
 				&dpte_row_height_linear_luma[k],
-				&st_vars->PixelPTEBytesPerRowY_one_row_per_frame[k],
-				&st_vars->dpte_row_width_luma_ub_one_row_per_frame[k],
-				&st_vars->dpte_row_height_luma_one_row_per_frame[k],
+				&PixelPTEBytesPerRowY_one_row_per_frame[k],
+				&dpte_row_width_luma_ub_one_row_per_frame[k],
+				&dpte_row_height_luma_one_row_per_frame[k],
 				&meta_req_width[k],
 				&meta_req_height[k],
 				&meta_row_width[k],
@@ -2098,19 +2119,19 @@ void dml32_CalculateVMRowAndSwath(
 				&VInitPreFillY[k],
 				&MaxNumSwathY[k]);
 
-		PDEAndMetaPTEBytesFrame[k] = st_vars->PDEAndMetaPTEBytesFrameY + st_vars->PDEAndMetaPTEBytesFrameC;
-		MetaRowByte[k] = st_vars->MetaRowByteY[k] + st_vars->MetaRowByteC[k];
+		PDEAndMetaPTEBytesFrame[k] = PDEAndMetaPTEBytesFrameY + PDEAndMetaPTEBytesFrameC;
+		MetaRowByte[k] = MetaRowByteY[k] + MetaRowByteC[k];
 
-		if (st_vars->PixelPTEBytesPerRowY[k] <= 64 * st_vars->PTEBufferSizeInRequestsForLuma[k] &&
-				st_vars->PixelPTEBytesPerRowC[k] <= 64 * st_vars->PTEBufferSizeInRequestsForChroma[k]) {
+		if (PixelPTEBytesPerRowY[k] <= 64 * PTEBufferSizeInRequestsForLuma[k] &&
+				PixelPTEBytesPerRowC[k] <= 64 * PTEBufferSizeInRequestsForChroma[k]) {
 			PTEBufferSizeNotExceeded[k] = true;
 		} else {
 			PTEBufferSizeNotExceeded[k] = false;
 		}
 
-		st_vars->one_row_per_frame_fits_in_buffer[k] = (st_vars->PixelPTEBytesPerRowY_one_row_per_frame[k] <= 64 * 2 *
-			st_vars->PTEBufferSizeInRequestsForLuma[k] &&
-			st_vars->PixelPTEBytesPerRowC_one_row_per_frame[k] <= 64 * 2 * st_vars->PTEBufferSizeInRequestsForChroma[k]);
+		one_row_per_frame_fits_in_buffer[k] = (PixelPTEBytesPerRowY_one_row_per_frame[k] <= 64 * 2 *
+			PTEBufferSizeInRequestsForLuma[k] &&
+			PixelPTEBytesPerRowC_one_row_per_frame[k] <= 64 * 2 * PTEBufferSizeInRequestsForChroma[k]);
 	}
 
 	dml32_CalculateMALLUseForStaticScreen(
@@ -2118,7 +2139,7 @@ void dml32_CalculateVMRowAndSwath(
 			MALLAllocatedForDCN,
 			UseMALLForStaticScreen,   // mode
 			SurfaceSizeInMALL,
-			st_vars->one_row_per_frame_fits_in_buffer,
+			one_row_per_frame_fits_in_buffer,
 			/* Output */
 			UsesMALLForStaticScreen); // boolen
 
@@ -2144,13 +2165,13 @@ void dml32_CalculateVMRowAndSwath(
 				!(UseMALLForPStateChange[k] == dm_use_mall_pstate_change_full_frame);
 
 		if (use_one_row_for_frame[k]) {
-			dpte_row_height_luma[k] = st_vars->dpte_row_height_luma_one_row_per_frame[k];
-			dpte_row_width_luma_ub[k] = st_vars->dpte_row_width_luma_ub_one_row_per_frame[k];
-			st_vars->PixelPTEBytesPerRowY[k] = st_vars->PixelPTEBytesPerRowY_one_row_per_frame[k];
-			dpte_row_height_chroma[k] = st_vars->dpte_row_height_chroma_one_row_per_frame[k];
-			dpte_row_width_chroma_ub[k] = st_vars->dpte_row_width_chroma_ub_one_row_per_frame[k];
-			st_vars->PixelPTEBytesPerRowC[k] = st_vars->PixelPTEBytesPerRowC_one_row_per_frame[k];
-			PTEBufferSizeNotExceeded[k] = st_vars->one_row_per_frame_fits_in_buffer[k];
+			dpte_row_height_luma[k] = dpte_row_height_luma_one_row_per_frame[k];
+			dpte_row_width_luma_ub[k] = dpte_row_width_luma_ub_one_row_per_frame[k];
+			PixelPTEBytesPerRowY[k] = PixelPTEBytesPerRowY_one_row_per_frame[k];
+			dpte_row_height_chroma[k] = dpte_row_height_chroma_one_row_per_frame[k];
+			dpte_row_width_chroma_ub[k] = dpte_row_width_chroma_ub_one_row_per_frame[k];
+			PixelPTEBytesPerRowC[k] = PixelPTEBytesPerRowC_one_row_per_frame[k];
+			PTEBufferSizeNotExceeded[k] = one_row_per_frame_fits_in_buffer[k];
 		}
 
 		if (MetaRowByte[k] <= DCCMetaBufferSizeBytes)
@@ -2158,7 +2179,7 @@ void dml32_CalculateVMRowAndSwath(
 		else
 			DCCMetaBufferSizeNotExceeded[k] = false;
 
-		PixelPTEBytesPerRow[k] = st_vars->PixelPTEBytesPerRowY[k] + st_vars->PixelPTEBytesPerRowC[k];
+		PixelPTEBytesPerRow[k] = PixelPTEBytesPerRowY[k] + PixelPTEBytesPerRowC[k];
 		if (use_one_row_for_frame[k])
 			PixelPTEBytesPerRow[k] = PixelPTEBytesPerRow[k] / 2;
 
@@ -2169,11 +2190,11 @@ void dml32_CalculateVMRowAndSwath(
 				myPipe[k].VRatioChroma,
 				myPipe[k].DCCEnable,
 				myPipe[k].HTotal / myPipe[k].PixelClock,
-				st_vars->MetaRowByteY[k], st_vars->MetaRowByteC[k],
+				MetaRowByteY[k], MetaRowByteC[k],
 				meta_row_height[k],
 				meta_row_height_chroma[k],
-				st_vars->PixelPTEBytesPerRowY[k],
-				st_vars->PixelPTEBytesPerRowC[k],
+				PixelPTEBytesPerRowY[k],
+				PixelPTEBytesPerRowC[k],
 				dpte_row_height_luma[k],
 				dpte_row_height_chroma[k],
 
@@ -2189,12 +2210,12 @@ void dml32_CalculateVMRowAndSwath(
 		dml_print("DML::%s: k=%d, dpte_row_height_luma         = %d\n",  __func__, k, dpte_row_height_luma[k]);
 		dml_print("DML::%s: k=%d, dpte_row_width_luma_ub       = %d\n",
 				__func__, k, dpte_row_width_luma_ub[k]);
-		dml_print("DML::%s: k=%d, PixelPTEBytesPerRowY         = %d\n",  __func__, k, st_vars->PixelPTEBytesPerRowY[k]);
+		dml_print("DML::%s: k=%d, PixelPTEBytesPerRowY         = %d\n",  __func__, k, PixelPTEBytesPerRowY[k]);
 		dml_print("DML::%s: k=%d, dpte_row_height_chroma       = %d\n",
 				__func__, k, dpte_row_height_chroma[k]);
 		dml_print("DML::%s: k=%d, dpte_row_width_chroma_ub     = %d\n",
 				__func__, k, dpte_row_width_chroma_ub[k]);
-		dml_print("DML::%s: k=%d, PixelPTEBytesPerRowC         = %d\n",  __func__, k, st_vars->PixelPTEBytesPerRowC[k]);
+		dml_print("DML::%s: k=%d, PixelPTEBytesPerRowC         = %d\n",  __func__, k, PixelPTEBytesPerRowC[k]);
 		dml_print("DML::%s: k=%d, PixelPTEBytesPerRow          = %d\n",  __func__, k, PixelPTEBytesPerRow[k]);
 		dml_print("DML::%s: k=%d, PTEBufferSizeNotExceeded     = %d\n",
 				__func__, k, PTEBufferSizeNotExceeded[k]);
@@ -3342,7 +3363,6 @@ double dml32_CalculateExtraLatency(
 } // CalculateExtraLatency
 
 bool dml32_CalculatePrefetchSchedule(
-		struct dml32_CalculatePrefetchSchedule *st_vars,
 		double HostVMInefficiencyFactor,
 		DmlPipe *myPipe,
 		unsigned int DSCDelay,
@@ -3406,18 +3426,45 @@ bool dml32_CalculatePrefetchSchedule(
 		double   *VReadyOffsetPix)
 {
 	bool MyError = false;
-
-	st_vars->TimeForFetchingMetaPTE = 0;
-	st_vars->TimeForFetchingRowInVBlank = 0;
-	st_vars->LinesToRequestPrefetchPixelData = 0;
-	st_vars->max_vratio_pre = __DML_MAX_VRATIO_PRE__;
-	st_vars->Tsw_est1 = 0;
-	st_vars->Tsw_est3 = 0;
+	unsigned int DPPCycles, DISPCLKCycles;
+	double DSTTotalPixelsAfterScaler;
+	double LineTime;
+	double dst_y_prefetch_equ;
+	double prefetch_bw_oto;
+	double Tvm_oto;
+	double Tr0_oto;
+	double Tvm_oto_lines;
+	double Tr0_oto_lines;
+	double dst_y_prefetch_oto;
+	double TimeForFetchingMetaPTE = 0;
+	double TimeForFetchingRowInVBlank = 0;
+	double LinesToRequestPrefetchPixelData = 0;
+	unsigned int HostVMDynamicLevelsTrips;
+	double  trip_to_mem;
+	double  Tvm_trips;
+	double  Tr0_trips;
+	double  Tvm_trips_rounded;
+	double  Tr0_trips_rounded;
+	double  Lsw_oto;
+	double  Tpre_rounded;
+	double  prefetch_bw_equ;
+	double  Tvm_equ;
+	double  Tr0_equ;
+	double  Tdmbf;
+	double  Tdmec;
+	double  Tdmsks;
+	double  prefetch_sw_bytes;
+	double  bytes_pp;
+	double  dep_bytes;
+	unsigned int max_vratio_pre = __DML_MAX_VRATIO_PRE__;
+	double  min_Lsw;
+	double  Tsw_est1 = 0;
+	double  Tsw_est3 = 0;
 
 	if (GPUVMEnable == true && HostVMEnable == true)
-		st_vars->HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels;
+		HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels;
 	else
-		st_vars->HostVMDynamicLevelsTrips = 0;
+		HostVMDynamicLevelsTrips = 0;
 #ifdef __DML_VBA_DEBUG__
 	dml_print("DML::%s: GPUVMEnable = %d\n", __func__, GPUVMEnable);
 	dml_print("DML::%s: GPUVMPageTableLevels = %d\n", __func__, GPUVMPageTableLevels);
@@ -3440,19 +3487,19 @@ bool dml32_CalculatePrefetchSchedule(
 			TSetup,
 
 			/* output */
-			&st_vars->Tdmbf,
-			&st_vars->Tdmec,
-			&st_vars->Tdmsks,
+			&Tdmbf,
+			&Tdmec,
+			&Tdmsks,
 			VUpdateOffsetPix,
 			VUpdateWidthPix,
 			VReadyOffsetPix);
 
-	st_vars->LineTime = myPipe->HTotal / myPipe->PixelClock;
-	st_vars->trip_to_mem = UrgentLatency;
-	st_vars->Tvm_trips = UrgentExtraLatency + st_vars->trip_to_mem * (GPUVMPageTableLevels * (st_vars->HostVMDynamicLevelsTrips + 1) - 1);
+	LineTime = myPipe->HTotal / myPipe->PixelClock;
+	trip_to_mem = UrgentLatency;
+	Tvm_trips = UrgentExtraLatency + trip_to_mem * (GPUVMPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1);
 
 	if (DynamicMetadataVMEnabled == true)
-		*Tdmdl = TWait + st_vars->Tvm_trips + st_vars->trip_to_mem;
+		*Tdmdl = TWait + Tvm_trips + trip_to_mem;
 	else
 		*Tdmdl = TWait + UrgentExtraLatency;
 
@@ -3462,15 +3509,15 @@ bool dml32_CalculatePrefetchSchedule(
 #endif
 
 	if (DynamicMetadataEnable == true) {
-		if (VStartup * st_vars->LineTime < *TSetup + *Tdmdl + st_vars->Tdmbf + st_vars->Tdmec + st_vars->Tdmsks) {
+		if (VStartup * LineTime < *TSetup + *Tdmdl + Tdmbf + Tdmec + Tdmsks) {
 			*NotEnoughTimeForDynamicMetadata = true;
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML::%s: Not Enough Time for Dynamic Meta!\n", __func__);
 			dml_print("DML::%s: Tdmbf: %fus - time for dmd transfer from dchub to dio output buffer\n",
-					__func__, st_vars->Tdmbf);
-			dml_print("DML::%s: Tdmec: %fus - time dio takes to transfer dmd\n", __func__, st_vars->Tdmec);
+					__func__, Tdmbf);
+			dml_print("DML::%s: Tdmec: %fus - time dio takes to transfer dmd\n", __func__, Tdmec);
 			dml_print("DML::%s: Tdmsks: %fus - time before active dmd must complete transmission at dio\n",
-					__func__, st_vars->Tdmsks);
+					__func__, Tdmsks);
 			dml_print("DML::%s: Tdmdl: %fus - time for fabric to become ready and fetch dmd\n",
 					__func__, *Tdmdl);
 #endif
@@ -3482,21 +3529,21 @@ bool dml32_CalculatePrefetchSchedule(
 	}
 
 	*Tdmdl_vm =  (DynamicMetadataEnable == true && DynamicMetadataVMEnabled == true &&
-			GPUVMEnable == true ? TWait + st_vars->Tvm_trips : 0);
+			GPUVMEnable == true ? TWait + Tvm_trips : 0);
 
 	if (myPipe->ScalerEnabled)
-		st_vars->DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCL;
+		DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCL;
 	else
-		st_vars->DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCLLBOnly;
+		DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCLLBOnly;
 
-	st_vars->DPPCycles = st_vars->DPPCycles + myPipe->NumberOfCursors * DPPCLKDelayCNVCCursor;
+	DPPCycles = DPPCycles + myPipe->NumberOfCursors * DPPCLKDelayCNVCCursor;
 
-	st_vars->DISPCLKCycles = DISPCLKDelaySubtotal;
+	DISPCLKCycles = DISPCLKDelaySubtotal;
 
 	if (myPipe->Dppclk == 0.0 || myPipe->Dispclk == 0.0)
 		return true;
 
-	*DSTXAfterScaler = st_vars->DPPCycles * myPipe->PixelClock / myPipe->Dppclk + st_vars->DISPCLKCycles *
+	*DSTXAfterScaler = DPPCycles * myPipe->PixelClock / myPipe->Dppclk + DISPCLKCycles *
 			myPipe->PixelClock / myPipe->Dispclk + DSCDelay;
 
 	*DSTXAfterScaler = *DSTXAfterScaler + (myPipe->ODMMode != dm_odm_combine_mode_disabled ? 18 : 0)
@@ -3506,10 +3553,10 @@ bool dml32_CalculatePrefetchSchedule(
 			+ ((myPipe->ODMMode == dm_odm_mode_mso_1to4) ? myPipe->HActive * 3 / 4 : 0);
 
 #ifdef __DML_VBA_DEBUG__
-	dml_print("DML::%s: DPPCycles: %d\n", __func__, st_vars->DPPCycles);
+	dml_print("DML::%s: DPPCycles: %d\n", __func__, DPPCycles);
 	dml_print("DML::%s: PixelClock: %f\n", __func__, myPipe->PixelClock);
 	dml_print("DML::%s: Dppclk: %f\n", __func__, myPipe->Dppclk);
-	dml_print("DML::%s: DISPCLKCycles: %d\n", __func__, st_vars->DISPCLKCycles);
+	dml_print("DML::%s: DISPCLKCycles: %d\n", __func__, DISPCLKCycles);
 	dml_print("DML::%s: DISPCLK: %f\n", __func__,  myPipe->Dispclk);
 	dml_print("DML::%s: DSCDelay: %d\n", __func__,  DSCDelay);
 	dml_print("DML::%s: ODMMode: %d\n", __func__,  myPipe->ODMMode);
@@ -3522,9 +3569,9 @@ bool dml32_CalculatePrefetchSchedule(
 	else
 		*DSTYAfterScaler = 0;
 
-	st_vars->DSTTotalPixelsAfterScaler = *DSTYAfterScaler * myPipe->HTotal + *DSTXAfterScaler;
-	*DSTYAfterScaler = dml_floor(st_vars->DSTTotalPixelsAfterScaler / myPipe->HTotal, 1);
-	*DSTXAfterScaler = st_vars->DSTTotalPixelsAfterScaler - ((double) (*DSTYAfterScaler * myPipe->HTotal));
+	DSTTotalPixelsAfterScaler = *DSTYAfterScaler * myPipe->HTotal + *DSTXAfterScaler;
+	*DSTYAfterScaler = dml_floor(DSTTotalPixelsAfterScaler / myPipe->HTotal, 1);
+	*DSTXAfterScaler = DSTTotalPixelsAfterScaler - ((double) (*DSTYAfterScaler * myPipe->HTotal));
 #ifdef __DML_VBA_DEBUG__
 	dml_print("DML::%s: DSTXAfterScaler: %d (final)\n", __func__,  *DSTXAfterScaler);
 	dml_print("DML::%s: DSTYAfterScaler: %d (final)\n", __func__, *DSTYAfterScaler);
@@ -3532,132 +3579,132 @@ bool dml32_CalculatePrefetchSchedule(
 
 	MyError = false;
 
-	st_vars->Tr0_trips = st_vars->trip_to_mem * (st_vars->HostVMDynamicLevelsTrips + 1);
+	Tr0_trips = trip_to_mem * (HostVMDynamicLevelsTrips + 1);
 
 	if (GPUVMEnable == true) {
-		st_vars->Tvm_trips_rounded = dml_ceil(4.0 * st_vars->Tvm_trips / st_vars->LineTime, 1.0) / 4.0 * st_vars->LineTime;
-		st_vars->Tr0_trips_rounded = dml_ceil(4.0 * st_vars->Tr0_trips / st_vars->LineTime, 1.0) / 4.0 * st_vars->LineTime;
+		Tvm_trips_rounded = dml_ceil(4.0 * Tvm_trips / LineTime, 1.0) / 4.0 * LineTime;
+		Tr0_trips_rounded = dml_ceil(4.0 * Tr0_trips / LineTime, 1.0) / 4.0 * LineTime;
 		if (GPUVMPageTableLevels >= 3) {
-			*Tno_bw = UrgentExtraLatency + st_vars->trip_to_mem *
-					(double) ((GPUVMPageTableLevels - 2) * (st_vars->HostVMDynamicLevelsTrips + 1) - 1);
+			*Tno_bw = UrgentExtraLatency + trip_to_mem *
+					(double) ((GPUVMPageTableLevels - 2) * (HostVMDynamicLevelsTrips + 1) - 1);
 		} else if (GPUVMPageTableLevels == 1 && myPipe->DCCEnable != true) {
-			st_vars->Tr0_trips_rounded = dml_ceil(4.0 * UrgentExtraLatency / st_vars->LineTime, 1.0) /
-					4.0 * st_vars->LineTime; // VBA_ERROR
+			Tr0_trips_rounded = dml_ceil(4.0 * UrgentExtraLatency / LineTime, 1.0) /
+					4.0 * LineTime; // VBA_ERROR
 			*Tno_bw = UrgentExtraLatency;
 		} else {
 			*Tno_bw = 0;
 		}
 	} else if (myPipe->DCCEnable == true) {
-		st_vars->Tvm_trips_rounded = st_vars->LineTime / 4.0;
-		st_vars->Tr0_trips_rounded = dml_ceil(4.0 * st_vars->Tr0_trips / st_vars->LineTime, 1.0) / 4.0 * st_vars->LineTime;
+		Tvm_trips_rounded = LineTime / 4.0;
+		Tr0_trips_rounded = dml_ceil(4.0 * Tr0_trips / LineTime, 1.0) / 4.0 * LineTime;
 		*Tno_bw = 0;
 	} else {
-		st_vars->Tvm_trips_rounded = st_vars->LineTime / 4.0;
-		st_vars->Tr0_trips_rounded = st_vars->LineTime / 2.0;
+		Tvm_trips_rounded = LineTime / 4.0;
+		Tr0_trips_rounded = LineTime / 2.0;
 		*Tno_bw = 0;
 	}
-	st_vars->Tvm_trips_rounded = dml_max(st_vars->Tvm_trips_rounded, st_vars->LineTime / 4.0);
-	st_vars->Tr0_trips_rounded = dml_max(st_vars->Tr0_trips_rounded, st_vars->LineTime / 4.0);
+	Tvm_trips_rounded = dml_max(Tvm_trips_rounded, LineTime / 4.0);
+	Tr0_trips_rounded = dml_max(Tr0_trips_rounded, LineTime / 4.0);
 
 	if (myPipe->SourcePixelFormat == dm_420_8 || myPipe->SourcePixelFormat == dm_420_10
 			|| myPipe->SourcePixelFormat == dm_420_12) {
-		st_vars->bytes_pp = myPipe->BytePerPixelY + myPipe->BytePerPixelC / 4;
+		bytes_pp = myPipe->BytePerPixelY + myPipe->BytePerPixelC / 4;
 	} else {
-		st_vars->bytes_pp = myPipe->BytePerPixelY + myPipe->BytePerPixelC;
+		bytes_pp = myPipe->BytePerPixelY + myPipe->BytePerPixelC;
 	}
 
-	st_vars->prefetch_sw_bytes = PrefetchSourceLinesY * swath_width_luma_ub * myPipe->BytePerPixelY
+	prefetch_sw_bytes = PrefetchSourceLinesY * swath_width_luma_ub * myPipe->BytePerPixelY
 			+ PrefetchSourceLinesC * swath_width_chroma_ub * myPipe->BytePerPixelC;
-	st_vars->prefetch_bw_oto = dml_max(st_vars->bytes_pp * myPipe->PixelClock / myPipe->DPPPerSurface,
-			st_vars->prefetch_sw_bytes / (dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) * st_vars->LineTime));
+	prefetch_bw_oto = dml_max(bytes_pp * myPipe->PixelClock / myPipe->DPPPerSurface,
+			prefetch_sw_bytes / (dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) * LineTime));
 
-	st_vars->min_Lsw = dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) / st_vars->max_vratio_pre;
-	st_vars->min_Lsw = dml_max(st_vars->min_Lsw, 1.0);
-	st_vars->Lsw_oto = dml_ceil(4.0 * dml_max(st_vars->prefetch_sw_bytes / st_vars->prefetch_bw_oto / st_vars->LineTime, st_vars->min_Lsw), 1.0) / 4.0;
+	min_Lsw = dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) / max_vratio_pre;
+	min_Lsw = dml_max(min_Lsw, 1.0);
+	Lsw_oto = dml_ceil(4.0 * dml_max(prefetch_sw_bytes / prefetch_bw_oto / LineTime, min_Lsw), 1.0) / 4.0;
 
 	if (GPUVMEnable == true) {
-		st_vars->Tvm_oto = dml_max3(
-				st_vars->Tvm_trips,
-				*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / st_vars->prefetch_bw_oto,
-				st_vars->LineTime / 4.0);
+		Tvm_oto = dml_max3(
+				Tvm_trips,
+				*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_oto,
+				LineTime / 4.0);
 	} else
-		st_vars->Tvm_oto = st_vars->LineTime / 4.0;
+		Tvm_oto = LineTime / 4.0;
 
 	if ((GPUVMEnable == true || myPipe->DCCEnable == true)) {
-		st_vars->Tr0_oto = dml_max4(
-				st_vars->Tr0_trips,
-				(MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / st_vars->prefetch_bw_oto,
-				(st_vars->LineTime - st_vars->Tvm_oto)/2.0,
-				st_vars->LineTime / 4.0);
+		Tr0_oto = dml_max4(
+				Tr0_trips,
+				(MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_oto,
+				(LineTime - Tvm_oto)/2.0,
+				LineTime / 4.0);
 #ifdef __DML_VBA_DEBUG__
 		dml_print("DML::%s: Tr0_oto max0 = %f\n", __func__,
-				(MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / st_vars->prefetch_bw_oto);
-		dml_print("DML::%s: Tr0_oto max1 = %f\n", __func__, st_vars->Tr0_trips);
-		dml_print("DML::%s: Tr0_oto max2 = %f\n", __func__, st_vars->LineTime - st_vars->Tvm_oto);
-		dml_print("DML::%s: Tr0_oto max3 = %f\n", __func__, st_vars->LineTime / 4);
+				(MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_oto);
+		dml_print("DML::%s: Tr0_oto max1 = %f\n", __func__, Tr0_trips);
+		dml_print("DML::%s: Tr0_oto max2 = %f\n", __func__, LineTime - Tvm_oto);
+		dml_print("DML::%s: Tr0_oto max3 = %f\n", __func__, LineTime / 4);
 #endif
 	} else
-		st_vars->Tr0_oto = (st_vars->LineTime - st_vars->Tvm_oto) / 2.0;
+		Tr0_oto = (LineTime - Tvm_oto) / 2.0;
 
-	st_vars->Tvm_oto_lines = dml_ceil(4.0 * st_vars->Tvm_oto / st_vars->LineTime, 1) / 4.0;
-	st_vars->Tr0_oto_lines = dml_ceil(4.0 * st_vars->Tr0_oto / st_vars->LineTime, 1) / 4.0;
-	st_vars->dst_y_prefetch_oto = st_vars->Tvm_oto_lines + 2 * st_vars->Tr0_oto_lines + st_vars->Lsw_oto;
+	Tvm_oto_lines = dml_ceil(4.0 * Tvm_oto / LineTime, 1) / 4.0;
+	Tr0_oto_lines = dml_ceil(4.0 * Tr0_oto / LineTime, 1) / 4.0;
+	dst_y_prefetch_oto = Tvm_oto_lines + 2 * Tr0_oto_lines + Lsw_oto;
 
-	st_vars->dst_y_prefetch_equ = VStartup - (*TSetup + dml_max(TWait + TCalc, *Tdmdl)) / st_vars->LineTime -
+	dst_y_prefetch_equ = VStartup - (*TSetup + dml_max(TWait + TCalc, *Tdmdl)) / LineTime -
 			(*DSTYAfterScaler + (double) *DSTXAfterScaler / (double) myPipe->HTotal);
 
 #ifdef __DML_VBA_DEBUG__
 	dml_print("DML::%s: HTotal = %d\n", __func__, myPipe->HTotal);
-	dml_print("DML::%s: min_Lsw = %f\n", __func__, st_vars->min_Lsw);
+	dml_print("DML::%s: min_Lsw = %f\n", __func__, min_Lsw);
 	dml_print("DML::%s: *Tno_bw = %f\n", __func__, *Tno_bw);
 	dml_print("DML::%s: UrgentExtraLatency = %f\n", __func__, UrgentExtraLatency);
-	dml_print("DML::%s: trip_to_mem = %f\n", __func__, st_vars->trip_to_mem);
+	dml_print("DML::%s: trip_to_mem = %f\n", __func__, trip_to_mem);
 	dml_print("DML::%s: BytePerPixelY = %d\n", __func__, myPipe->BytePerPixelY);
 	dml_print("DML::%s: PrefetchSourceLinesY = %f\n", __func__, PrefetchSourceLinesY);
 	dml_print("DML::%s: swath_width_luma_ub = %d\n", __func__, swath_width_luma_ub);
 	dml_print("DML::%s: BytePerPixelC = %d\n", __func__, myPipe->BytePerPixelC);
 	dml_print("DML::%s: PrefetchSourceLinesC = %f\n", __func__, PrefetchSourceLinesC);
 	dml_print("DML::%s: swath_width_chroma_ub = %d\n", __func__, swath_width_chroma_ub);
-	dml_print("DML::%s: prefetch_sw_bytes = %f\n", __func__, st_vars->prefetch_sw_bytes);
-	dml_print("DML::%s: bytes_pp = %f\n", __func__, st_vars->bytes_pp);
+	dml_print("DML::%s: prefetch_sw_bytes = %f\n", __func__, prefetch_sw_bytes);
+	dml_print("DML::%s: bytes_pp = %f\n", __func__, bytes_pp);
 	dml_print("DML::%s: PDEAndMetaPTEBytesFrame = %d\n", __func__, PDEAndMetaPTEBytesFrame);
 	dml_print("DML::%s: MetaRowByte = %d\n", __func__, MetaRowByte);
 	dml_print("DML::%s: PixelPTEBytesPerRow = %d\n", __func__, PixelPTEBytesPerRow);
 	dml_print("DML::%s: HostVMInefficiencyFactor = %f\n", __func__, HostVMInefficiencyFactor);
-	dml_print("DML::%s: Tvm_trips = %f\n", __func__, st_vars->Tvm_trips);
-	dml_print("DML::%s: Tr0_trips = %f\n", __func__, st_vars->Tr0_trips);
-	dml_print("DML::%s: prefetch_bw_oto = %f\n", __func__, st_vars->prefetch_bw_oto);
-	dml_print("DML::%s: Tr0_oto = %f\n", __func__, st_vars->Tr0_oto);
-	dml_print("DML::%s: Tvm_oto = %f\n", __func__, st_vars->Tvm_oto);
-	dml_print("DML::%s: Tvm_oto_lines = %f\n", __func__, st_vars->Tvm_oto_lines);
-	dml_print("DML::%s: Tr0_oto_lines = %f\n", __func__, st_vars->Tr0_oto_lines);
-	dml_print("DML::%s: Lsw_oto = %f\n", __func__, st_vars->Lsw_oto);
-	dml_print("DML::%s: dst_y_prefetch_oto = %f\n", __func__, st_vars->dst_y_prefetch_oto);
-	dml_print("DML::%s: dst_y_prefetch_equ = %f\n", __func__, st_vars->dst_y_prefetch_equ);
+	dml_print("DML::%s: Tvm_trips = %f\n", __func__, Tvm_trips);
+	dml_print("DML::%s: Tr0_trips = %f\n", __func__, Tr0_trips);
+	dml_print("DML::%s: prefetch_bw_oto = %f\n", __func__, prefetch_bw_oto);
+	dml_print("DML::%s: Tr0_oto = %f\n", __func__, Tr0_oto);
+	dml_print("DML::%s: Tvm_oto = %f\n", __func__, Tvm_oto);
+	dml_print("DML::%s: Tvm_oto_lines = %f\n", __func__, Tvm_oto_lines);
+	dml_print("DML::%s: Tr0_oto_lines = %f\n", __func__, Tr0_oto_lines);
+	dml_print("DML::%s: Lsw_oto = %f\n", __func__, Lsw_oto);
+	dml_print("DML::%s: dst_y_prefetch_oto = %f\n", __func__, dst_y_prefetch_oto);
+	dml_print("DML::%s: dst_y_prefetch_equ = %f\n", __func__, dst_y_prefetch_equ);
 #endif
 
-	st_vars->dst_y_prefetch_equ = dml_floor(4.0 * (st_vars->dst_y_prefetch_equ + 0.125), 1) / 4.0;
-	st_vars->Tpre_rounded = st_vars->dst_y_prefetch_equ * st_vars->LineTime;
+	dst_y_prefetch_equ = dml_floor(4.0 * (dst_y_prefetch_equ + 0.125), 1) / 4.0;
+	Tpre_rounded = dst_y_prefetch_equ * LineTime;
 #ifdef __DML_VBA_DEBUG__
-	dml_print("DML::%s: dst_y_prefetch_equ: %f (after round)\n", __func__, st_vars->dst_y_prefetch_equ);
-	dml_print("DML::%s: LineTime: %f\n", __func__, st_vars->LineTime);
+	dml_print("DML::%s: dst_y_prefetch_equ: %f (after round)\n", __func__, dst_y_prefetch_equ);
+	dml_print("DML::%s: LineTime: %f\n", __func__, LineTime);
 	dml_print("DML::%s: VStartup: %d\n", __func__, VStartup);
 	dml_print("DML::%s: Tvstartup: %fus - time between vstartup and first pixel of active\n",
-			__func__, VStartup * st_vars->LineTime);
+			__func__, VStartup * LineTime);
 	dml_print("DML::%s: TSetup: %fus - time from vstartup to vready\n", __func__, *TSetup);
 	dml_print("DML::%s: TCalc: %fus - time for calculations in dchub starting at vready\n", __func__, TCalc);
-	dml_print("DML::%s: Tdmbf: %fus - time for dmd transfer from dchub to dio output buffer\n", __func__, st_vars->Tdmbf);
-	dml_print("DML::%s: Tdmec: %fus - time dio takes to transfer dmd\n", __func__, st_vars->Tdmec);
+	dml_print("DML::%s: Tdmbf: %fus - time for dmd transfer from dchub to dio output buffer\n", __func__, Tdmbf);
+	dml_print("DML::%s: Tdmec: %fus - time dio takes to transfer dmd\n", __func__, Tdmec);
 	dml_print("DML::%s: Tdmdl_vm: %fus - time for vm stages of dmd\n", __func__, *Tdmdl_vm);
 	dml_print("DML::%s: Tdmdl: %fus - time for fabric to become ready and fetch dmd\n", __func__, *Tdmdl);
 	dml_print("DML::%s: DSTYAfterScaler: %d lines - number of lines of pipeline and buffer delay after scaler\n",
 			__func__, *DSTYAfterScaler);
 #endif
-	st_vars->dep_bytes = dml_max(PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor,
+	dep_bytes = dml_max(PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor,
 			MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor);
 
-	if (st_vars->prefetch_sw_bytes < st_vars->dep_bytes)
-		st_vars->prefetch_sw_bytes = 2 * st_vars->dep_bytes;
+	if (prefetch_sw_bytes < dep_bytes)
+		prefetch_sw_bytes = 2 * dep_bytes;
 
 	*PrefetchBandwidth = 0;
 	*DestinationLinesToRequestVMInVBlank = 0;
@@ -3665,61 +3712,61 @@ bool dml32_CalculatePrefetchSchedule(
 	*VRatioPrefetchY = 0;
 	*VRatioPrefetchC = 0;
 	*RequiredPrefetchPixDataBWLuma = 0;
-	if (st_vars->dst_y_prefetch_equ > 1) {
+	if (dst_y_prefetch_equ > 1) {
 		double PrefetchBandwidth1;
 		double PrefetchBandwidth2;
 		double PrefetchBandwidth3;
 		double PrefetchBandwidth4;
 
-		if (st_vars->Tpre_rounded - *Tno_bw > 0) {
+		if (Tpre_rounded - *Tno_bw > 0) {
 			PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte
 					+ 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor
-					+ st_vars->prefetch_sw_bytes) / (st_vars->Tpre_rounded - *Tno_bw);
-			st_vars->Tsw_est1 = st_vars->prefetch_sw_bytes / PrefetchBandwidth1;
+					+ prefetch_sw_bytes) / (Tpre_rounded - *Tno_bw);
+			Tsw_est1 = prefetch_sw_bytes / PrefetchBandwidth1;
 		} else
 			PrefetchBandwidth1 = 0;
 
-		if (VStartup == MaxVStartup && (st_vars->Tsw_est1 / st_vars->LineTime < st_vars->min_Lsw)
-				&& st_vars->Tpre_rounded - st_vars->min_Lsw * st_vars->LineTime - 0.75 * st_vars->LineTime - *Tno_bw > 0) {
+		if (VStartup == MaxVStartup && (Tsw_est1 / LineTime < min_Lsw)
+				&& Tpre_rounded - min_Lsw * LineTime - 0.75 * LineTime - *Tno_bw > 0) {
 			PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte
 					+ 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor)
-					/ (st_vars->Tpre_rounded - st_vars->min_Lsw * st_vars->LineTime - 0.75 * st_vars->LineTime - *Tno_bw);
+					/ (Tpre_rounded - min_Lsw * LineTime - 0.75 * LineTime - *Tno_bw);
 		}
 
-		if (st_vars->Tpre_rounded - *Tno_bw - 2 * st_vars->Tr0_trips_rounded > 0)
-			PrefetchBandwidth2 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + st_vars->prefetch_sw_bytes) /
-			(st_vars->Tpre_rounded - *Tno_bw - 2 * st_vars->Tr0_trips_rounded);
+		if (Tpre_rounded - *Tno_bw - 2 * Tr0_trips_rounded > 0)
+			PrefetchBandwidth2 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + prefetch_sw_bytes) /
+			(Tpre_rounded - *Tno_bw - 2 * Tr0_trips_rounded);
 		else
 			PrefetchBandwidth2 = 0;
 
-		if (st_vars->Tpre_rounded - st_vars->Tvm_trips_rounded > 0) {
+		if (Tpre_rounded - Tvm_trips_rounded > 0) {
 			PrefetchBandwidth3 = (2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor
-					+ st_vars->prefetch_sw_bytes) / (st_vars->Tpre_rounded - st_vars->Tvm_trips_rounded);
-			st_vars->Tsw_est3 = st_vars->prefetch_sw_bytes / PrefetchBandwidth3;
+					+ prefetch_sw_bytes) / (Tpre_rounded - Tvm_trips_rounded);
+			Tsw_est3 = prefetch_sw_bytes / PrefetchBandwidth3;
 		} else
 			PrefetchBandwidth3 = 0;
 
 
 		if (VStartup == MaxVStartup &&
-				(st_vars->Tsw_est3 / st_vars->LineTime < st_vars->min_Lsw) && st_vars->Tpre_rounded - st_vars->min_Lsw * st_vars->LineTime - 0.75 *
-				st_vars->LineTime - st_vars->Tvm_trips_rounded > 0) {
+				(Tsw_est3 / LineTime < min_Lsw) && Tpre_rounded - min_Lsw * LineTime - 0.75 *
+				LineTime - Tvm_trips_rounded > 0) {
 			PrefetchBandwidth3 = (2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor)
-					/ (st_vars->Tpre_rounded - st_vars->min_Lsw * st_vars->LineTime - 0.75 * st_vars->LineTime - st_vars->Tvm_trips_rounded);
+					/ (Tpre_rounded - min_Lsw * LineTime - 0.75 * LineTime - Tvm_trips_rounded);
 		}
 
-		if (st_vars->Tpre_rounded - st_vars->Tvm_trips_rounded - 2 * st_vars->Tr0_trips_rounded > 0) {
-			PrefetchBandwidth4 = st_vars->prefetch_sw_bytes /
-					(st_vars->Tpre_rounded - st_vars->Tvm_trips_rounded - 2 * st_vars->Tr0_trips_rounded);
+		if (Tpre_rounded - Tvm_trips_rounded - 2 * Tr0_trips_rounded > 0) {
+			PrefetchBandwidth4 = prefetch_sw_bytes /
+					(Tpre_rounded - Tvm_trips_rounded - 2 * Tr0_trips_rounded);
 		} else {
 			PrefetchBandwidth4 = 0;
 		}
 
 #ifdef __DML_VBA_DEBUG__
-		dml_print("DML::%s: Tpre_rounded: %f\n", __func__, st_vars->Tpre_rounded);
+		dml_print("DML::%s: Tpre_rounded: %f\n", __func__, Tpre_rounded);
 		dml_print("DML::%s: Tno_bw: %f\n", __func__, *Tno_bw);
-		dml_print("DML::%s: Tvm_trips_rounded: %f\n", __func__, st_vars->Tvm_trips_rounded);
-		dml_print("DML::%s: Tsw_est1: %f\n", __func__, st_vars->Tsw_est1);
-		dml_print("DML::%s: Tsw_est3: %f\n", __func__, st_vars->Tsw_est3);
+		dml_print("DML::%s: Tvm_trips_rounded: %f\n", __func__, Tvm_trips_rounded);
+		dml_print("DML::%s: Tsw_est1: %f\n", __func__, Tsw_est1);
+		dml_print("DML::%s: Tsw_est3: %f\n", __func__, Tsw_est3);
 		dml_print("DML::%s: PrefetchBandwidth1: %f\n", __func__, PrefetchBandwidth1);
 		dml_print("DML::%s: PrefetchBandwidth2: %f\n", __func__, PrefetchBandwidth2);
 		dml_print("DML::%s: PrefetchBandwidth3: %f\n", __func__, PrefetchBandwidth3);
@@ -3732,9 +3779,9 @@ bool dml32_CalculatePrefetchSchedule(
 
 			if (PrefetchBandwidth1 > 0) {
 				if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth1
-						>= st_vars->Tvm_trips_rounded
+						>= Tvm_trips_rounded
 						&& (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor)
-								/ PrefetchBandwidth1 >= st_vars->Tr0_trips_rounded) {
+								/ PrefetchBandwidth1 >= Tr0_trips_rounded) {
 					Case1OK = true;
 				} else {
 					Case1OK = false;
@@ -3745,9 +3792,9 @@ bool dml32_CalculatePrefetchSchedule(
 
 			if (PrefetchBandwidth2 > 0) {
 				if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth2
-						>= st_vars->Tvm_trips_rounded
+						>= Tvm_trips_rounded
 						&& (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor)
-						/ PrefetchBandwidth2 < st_vars->Tr0_trips_rounded) {
+						/ PrefetchBandwidth2 < Tr0_trips_rounded) {
 					Case2OK = true;
 				} else {
 					Case2OK = false;
@@ -3758,9 +3805,9 @@ bool dml32_CalculatePrefetchSchedule(
 
 			if (PrefetchBandwidth3 > 0) {
 				if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth3 <
-						st_vars->Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow *
+						Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow *
 								HostVMInefficiencyFactor) / PrefetchBandwidth3 >=
-								st_vars->Tr0_trips_rounded) {
+								Tr0_trips_rounded) {
 					Case3OK = true;
 				} else {
 					Case3OK = false;
@@ -3770,80 +3817,80 @@ bool dml32_CalculatePrefetchSchedule(
 			}
 
 			if (Case1OK)
-				st_vars->prefetch_bw_equ = PrefetchBandwidth1;
+				prefetch_bw_equ = PrefetchBandwidth1;
 			else if (Case2OK)
-				st_vars->prefetch_bw_equ = PrefetchBandwidth2;
+				prefetch_bw_equ = PrefetchBandwidth2;
 			else if (Case3OK)
-				st_vars->prefetch_bw_equ = PrefetchBandwidth3;
+				prefetch_bw_equ = PrefetchBandwidth3;
 			else
-				st_vars->prefetch_bw_equ = PrefetchBandwidth4;
+				prefetch_bw_equ = PrefetchBandwidth4;
 
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML::%s: Case1OK: %d\n", __func__, Case1OK);
 			dml_print("DML::%s: Case2OK: %d\n", __func__, Case2OK);
 			dml_print("DML::%s: Case3OK: %d\n", __func__, Case3OK);
-			dml_print("DML::%s: prefetch_bw_equ: %f\n", __func__, st_vars->prefetch_bw_equ);
+			dml_print("DML::%s: prefetch_bw_equ: %f\n", __func__, prefetch_bw_equ);
 #endif
 
-			if (st_vars->prefetch_bw_equ > 0) {
+			if (prefetch_bw_equ > 0) {
 				if (GPUVMEnable == true) {
-					st_vars->Tvm_equ = dml_max3(*Tno_bw + PDEAndMetaPTEBytesFrame *
-							HostVMInefficiencyFactor / st_vars->prefetch_bw_equ,
-							st_vars->Tvm_trips, st_vars->LineTime / 4);
+					Tvm_equ = dml_max3(*Tno_bw + PDEAndMetaPTEBytesFrame *
+							HostVMInefficiencyFactor / prefetch_bw_equ,
+							Tvm_trips, LineTime / 4);
 				} else {
-					st_vars->Tvm_equ = st_vars->LineTime / 4;
+					Tvm_equ = LineTime / 4;
 				}
 
 				if ((GPUVMEnable == true || myPipe->DCCEnable == true)) {
-					st_vars->Tr0_equ = dml_max4((MetaRowByte + PixelPTEBytesPerRow *
-							HostVMInefficiencyFactor) / st_vars->prefetch_bw_equ, st_vars->Tr0_trips,
-							(st_vars->LineTime - st_vars->Tvm_equ) / 2, st_vars->LineTime / 4);
+					Tr0_equ = dml_max4((MetaRowByte + PixelPTEBytesPerRow *
+							HostVMInefficiencyFactor) / prefetch_bw_equ, Tr0_trips,
+							(LineTime - Tvm_equ) / 2, LineTime / 4);
 				} else {
-					st_vars->Tr0_equ = (st_vars->LineTime - st_vars->Tvm_equ) / 2;
+					Tr0_equ = (LineTime - Tvm_equ) / 2;
 				}
 			} else {
-				st_vars->Tvm_equ = 0;
-				st_vars->Tr0_equ = 0;
+				Tvm_equ = 0;
+				Tr0_equ = 0;
 #ifdef __DML_VBA_DEBUG__
 				dml_print("DML: prefetch_bw_equ equals 0! %s:%d\n", __FILE__, __LINE__);
 #endif
 			}
 		}
 
-		if (st_vars->dst_y_prefetch_oto < st_vars->dst_y_prefetch_equ) {
-			*DestinationLinesForPrefetch = st_vars->dst_y_prefetch_oto;
-			st_vars->TimeForFetchingMetaPTE = st_vars->Tvm_oto;
-			st_vars->TimeForFetchingRowInVBlank = st_vars->Tr0_oto;
-			*PrefetchBandwidth = st_vars->prefetch_bw_oto;
+		if (dst_y_prefetch_oto < dst_y_prefetch_equ) {
+			*DestinationLinesForPrefetch = dst_y_prefetch_oto;
+			TimeForFetchingMetaPTE = Tvm_oto;
+			TimeForFetchingRowInVBlank = Tr0_oto;
+			*PrefetchBandwidth = prefetch_bw_oto;
 		} else {
-			*DestinationLinesForPrefetch = st_vars->dst_y_prefetch_equ;
-			st_vars->TimeForFetchingMetaPTE = st_vars->Tvm_equ;
-			st_vars->TimeForFetchingRowInVBlank = st_vars->Tr0_equ;
-			*PrefetchBandwidth = st_vars->prefetch_bw_equ;
+			*DestinationLinesForPrefetch = dst_y_prefetch_equ;
+			TimeForFetchingMetaPTE = Tvm_equ;
+			TimeForFetchingRowInVBlank = Tr0_equ;
+			*PrefetchBandwidth = prefetch_bw_equ;
 		}
 
-		*DestinationLinesToRequestVMInVBlank = dml_ceil(4.0 * st_vars->TimeForFetchingMetaPTE / st_vars->LineTime, 1.0) / 4.0;
+		*DestinationLinesToRequestVMInVBlank = dml_ceil(4.0 * TimeForFetchingMetaPTE / LineTime, 1.0) / 4.0;
 
 		*DestinationLinesToRequestRowInVBlank =
-				dml_ceil(4.0 * st_vars->TimeForFetchingRowInVBlank / st_vars->LineTime, 1.0) / 4.0;
+				dml_ceil(4.0 * TimeForFetchingRowInVBlank / LineTime, 1.0) / 4.0;
 
-		st_vars->LinesToRequestPrefetchPixelData = *DestinationLinesForPrefetch -
+		LinesToRequestPrefetchPixelData = *DestinationLinesForPrefetch -
 				*DestinationLinesToRequestVMInVBlank - 2 * *DestinationLinesToRequestRowInVBlank;
 
 #ifdef __DML_VBA_DEBUG__
 		dml_print("DML::%s: DestinationLinesForPrefetch = %f\n", __func__, *DestinationLinesForPrefetch);
 		dml_print("DML::%s: DestinationLinesToRequestVMInVBlank = %f\n",
 				__func__, *DestinationLinesToRequestVMInVBlank);
-		dml_print("DML::%s: TimeForFetchingRowInVBlank = %f\n", __func__, st_vars->TimeForFetchingRowInVBlank);
-		dml_print("DML::%s: LineTime = %f\n", __func__, st_vars->LineTime);
+		dml_print("DML::%s: TimeForFetchingRowInVBlank = %f\n", __func__, TimeForFetchingRowInVBlank);
+		dml_print("DML::%s: LineTime = %f\n", __func__, LineTime);
 		dml_print("DML::%s: DestinationLinesToRequestRowInVBlank = %f\n",
 				__func__, *DestinationLinesToRequestRowInVBlank);
 		dml_print("DML::%s: PrefetchSourceLinesY = %f\n", __func__, PrefetchSourceLinesY);
-		dml_print("DML::%s: LinesToRequestPrefetchPixelData = %f\n", __func__, st_vars->LinesToRequestPrefetchPixelData);
+		dml_print("DML::%s: LinesToRequestPrefetchPixelData = %f\n", __func__, LinesToRequestPrefetchPixelData);
 #endif
 
-		if (st_vars->LinesToRequestPrefetchPixelData >= 1 && st_vars->prefetch_bw_equ > 0) {
-			*VRatioPrefetchY = (double) PrefetchSourceLinesY / st_vars->LinesToRequestPrefetchPixelData;
+		if (LinesToRequestPrefetchPixelData >= 1 && prefetch_bw_equ > 0) {
+			*VRatioPrefetchY = (double) PrefetchSourceLinesY / LinesToRequestPrefetchPixelData;
 			*VRatioPrefetchY = dml_max(*VRatioPrefetchY, 1.0);
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML::%s: VRatioPrefetchY = %f\n", __func__, *VRatioPrefetchY);
@@ -3851,12 +3898,12 @@ bool dml32_CalculatePrefetchSchedule(
 			dml_print("DML::%s: VInitPreFillY = %d\n", __func__, VInitPreFillY);
 #endif
 			if ((SwathHeightY > 4) && (VInitPreFillY > 3)) {
-				if (st_vars->LinesToRequestPrefetchPixelData > (VInitPreFillY - 3.0) / 2.0) {
+				if (LinesToRequestPrefetchPixelData > (VInitPreFillY - 3.0) / 2.0) {
 					*VRatioPrefetchY =
 							dml_max((double) PrefetchSourceLinesY /
-									st_vars->LinesToRequestPrefetchPixelData,
+									LinesToRequestPrefetchPixelData,
 									(double) MaxNumSwathY * SwathHeightY /
-									(st_vars->LinesToRequestPrefetchPixelData -
+									(LinesToRequestPrefetchPixelData -
 									(VInitPreFillY - 3.0) / 2.0));
 					*VRatioPrefetchY = dml_max(*VRatioPrefetchY, 1.0);
 				} else {
@@ -3870,7 +3917,7 @@ bool dml32_CalculatePrefetchSchedule(
 #endif
 			}
 
-			*VRatioPrefetchC = (double) PrefetchSourceLinesC / st_vars->LinesToRequestPrefetchPixelData;
+			*VRatioPrefetchC = (double) PrefetchSourceLinesC / LinesToRequestPrefetchPixelData;
 			*VRatioPrefetchC = dml_max(*VRatioPrefetchC, 1.0);
 
 #ifdef __DML_VBA_DEBUG__
@@ -3879,11 +3926,11 @@ bool dml32_CalculatePrefetchSchedule(
 			dml_print("DML::%s: VInitPreFillC = %d\n", __func__, VInitPreFillC);
 #endif
 			if ((SwathHeightC > 4)) {
-				if (st_vars->LinesToRequestPrefetchPixelData > (VInitPreFillC - 3.0) / 2.0) {
+				if (LinesToRequestPrefetchPixelData > (VInitPreFillC - 3.0) / 2.0) {
 					*VRatioPrefetchC =
 						dml_max(*VRatioPrefetchC,
 							(double) MaxNumSwathC * SwathHeightC /
-							(st_vars->LinesToRequestPrefetchPixelData -
+							(LinesToRequestPrefetchPixelData -
 							(VInitPreFillC - 3.0) / 2.0));
 					*VRatioPrefetchC = dml_max(*VRatioPrefetchC, 1.0);
 				} else {
@@ -3898,25 +3945,25 @@ bool dml32_CalculatePrefetchSchedule(
 			}
 
 			*RequiredPrefetchPixDataBWLuma = (double) PrefetchSourceLinesY
-					/ st_vars->LinesToRequestPrefetchPixelData * myPipe->BytePerPixelY * swath_width_luma_ub
-					/ st_vars->LineTime;
+					/ LinesToRequestPrefetchPixelData * myPipe->BytePerPixelY * swath_width_luma_ub
+					/ LineTime;
 
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML::%s: BytePerPixelY = %d\n", __func__, myPipe->BytePerPixelY);
 			dml_print("DML::%s: swath_width_luma_ub = %d\n", __func__, swath_width_luma_ub);
-			dml_print("DML::%s: LineTime = %f\n", __func__, st_vars->LineTime);
+			dml_print("DML::%s: LineTime = %f\n", __func__, LineTime);
 			dml_print("DML::%s: RequiredPrefetchPixDataBWLuma = %f\n",
 					__func__, *RequiredPrefetchPixDataBWLuma);
 #endif
 			*RequiredPrefetchPixDataBWChroma = (double) PrefetchSourceLinesC /
-					st_vars->LinesToRequestPrefetchPixelData
+					LinesToRequestPrefetchPixelData
 					* myPipe->BytePerPixelC
-					* swath_width_chroma_ub / st_vars->LineTime;
+					* swath_width_chroma_ub / LineTime;
 		} else {
 			MyError = true;
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML:%s: MyErr set. LinesToRequestPrefetchPixelData: %f, should be > 0\n",
-					__func__, st_vars->LinesToRequestPrefetchPixelData);
+					__func__, LinesToRequestPrefetchPixelData);
 #endif
 			*VRatioPrefetchY = 0;
 			*VRatioPrefetchC = 0;
@@ -3925,15 +3972,15 @@ bool dml32_CalculatePrefetchSchedule(
 		}
 #ifdef __DML_VBA_DEBUG__
 		dml_print("DML: Tpre: %fus - sum of time to request meta pte, 2 x data pte + meta data, swaths\n",
-			(double)st_vars->LinesToRequestPrefetchPixelData * st_vars->LineTime +
-			2.0*st_vars->TimeForFetchingRowInVBlank + st_vars->TimeForFetchingMetaPTE);
-		dml_print("DML:  Tvm: %fus - time to fetch page tables for meta surface\n", st_vars->TimeForFetchingMetaPTE);
+			(double)LinesToRequestPrefetchPixelData * LineTime +
+			2.0*TimeForFetchingRowInVBlank + TimeForFetchingMetaPTE);
+		dml_print("DML:  Tvm: %fus - time to fetch page tables for meta surface\n", TimeForFetchingMetaPTE);
 		dml_print("DML: To: %fus - time for propagation from scaler to optc\n",
-			(*DSTYAfterScaler + ((double) (*DSTXAfterScaler) / (double) myPipe->HTotal)) * st_vars->LineTime);
+			(*DSTYAfterScaler + ((double) (*DSTXAfterScaler) / (double) myPipe->HTotal)) * LineTime);
 		dml_print("DML: Tvstartup - TSetup - Tcalc - Twait - Tpre - To > 0\n");
-		dml_print("DML: Tslack(pre): %fus - time left over in schedule\n", VStartup * st_vars->LineTime -
-			st_vars->TimeForFetchingMetaPTE - 2*st_vars->TimeForFetchingRowInVBlank - (*DSTYAfterScaler +
-			((double) (*DSTXAfterScaler) / (double) myPipe->HTotal)) * st_vars->LineTime - TWait - TCalc - *TSetup);
+		dml_print("DML: Tslack(pre): %fus - time left over in schedule\n", VStartup * LineTime -
+			TimeForFetchingMetaPTE - 2*TimeForFetchingRowInVBlank - (*DSTYAfterScaler +
+			((double) (*DSTXAfterScaler) / (double) myPipe->HTotal)) * LineTime - TWait - TCalc - *TSetup);
 		dml_print("DML: row_bytes = dpte_row_bytes (per_pipe) = PixelPTEBytesPerRow = : %d\n",
 				PixelPTEBytesPerRow);
 #endif
@@ -3941,7 +3988,7 @@ bool dml32_CalculatePrefetchSchedule(
 		MyError = true;
 #ifdef __DML_VBA_DEBUG__
 		dml_print("DML::%s: MyErr set, dst_y_prefetch_equ = %f (should be > 1)\n",
-				__func__, st_vars->dst_y_prefetch_equ);
+				__func__, dst_y_prefetch_equ);
 #endif
 	}
 
@@ -3957,10 +4004,10 @@ bool dml32_CalculatePrefetchSchedule(
 			dml_print("DML::%s: HostVMInefficiencyFactor = %f\n", __func__, HostVMInefficiencyFactor);
 			dml_print("DML::%s: DestinationLinesToRequestVMInVBlank = %f\n",
 					__func__, *DestinationLinesToRequestVMInVBlank);
-			dml_print("DML::%s: LineTime = %f\n", __func__, st_vars->LineTime);
+			dml_print("DML::%s: LineTime = %f\n", __func__, LineTime);
 #endif
 			prefetch_vm_bw = PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor /
-					(*DestinationLinesToRequestVMInVBlank * st_vars->LineTime);
+					(*DestinationLinesToRequestVMInVBlank * LineTime);
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML::%s: prefetch_vm_bw = %f\n", __func__, prefetch_vm_bw);
 #endif
@@ -3977,7 +4024,7 @@ bool dml32_CalculatePrefetchSchedule(
 			prefetch_row_bw = 0;
 		} else if (*DestinationLinesToRequestRowInVBlank > 0) {
 			prefetch_row_bw = (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) /
-					(*DestinationLinesToRequestRowInVBlank * st_vars->LineTime);
+					(*DestinationLinesToRequestRowInVBlank * LineTime);
 
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML::%s: MetaRowByte = %d\n", __func__, MetaRowByte);
@@ -4000,12 +4047,12 @@ bool dml32_CalculatePrefetchSchedule(
 
 	if (MyError) {
 		*PrefetchBandwidth = 0;
-		st_vars->TimeForFetchingMetaPTE = 0;
-		st_vars->TimeForFetchingRowInVBlank = 0;
+		TimeForFetchingMetaPTE = 0;
+		TimeForFetchingRowInVBlank = 0;
 		*DestinationLinesToRequestVMInVBlank = 0;
 		*DestinationLinesToRequestRowInVBlank = 0;
 		*DestinationLinesForPrefetch = 0;
-		st_vars->LinesToRequestPrefetchPixelData = 0;
+		LinesToRequestPrefetchPixelData = 0;
 		*VRatioPrefetchY = 0;
 		*VRatioPrefetchC = 0;
 		*RequiredPrefetchPixDataBWLuma = 0;
@@ -4159,7 +4206,6 @@ void dml32_CalculateFlipSchedule(
 } // CalculateFlipSchedule
 
 void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
-		struct dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport *st_vars,
 		bool USRRetrainingRequiredFinal,
 		enum dm_use_mall_for_pstate_change_mode UseMALLForPStateChange[],
 		unsigned int PrefetchMode,
@@ -4221,15 +4267,37 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 		double ActiveDRAMClockChangeLatencyMargin[])
 {
 	unsigned int i, j, k;
-
-	st_vars->SurfaceWithMinActiveFCLKChangeMargin = 0;
-	st_vars->DRAMClockChangeSupportNumber = 0;
-	st_vars->DRAMClockChangeMethod = 0;
-	st_vars->FoundFirstSurfaceWithMinActiveFCLKChangeMargin = false;
-	st_vars->MinActiveFCLKChangeMargin = 0.;
-	st_vars->SecondMinActiveFCLKChangeMarginOneDisplayInVBLank = 0.;
-	st_vars->TotalPixelBW = 0.0;
-	st_vars->TotalActiveWriteback = 0;
+	unsigned int SurfaceWithMinActiveFCLKChangeMargin = 0;
+	unsigned int DRAMClockChangeSupportNumber = 0;
+	unsigned int LastSurfaceWithoutMargin;
+	unsigned int DRAMClockChangeMethod = 0;
+	bool FoundFirstSurfaceWithMinActiveFCLKChangeMargin = false;
+	double MinActiveFCLKChangeMargin = 0.;
+	double SecondMinActiveFCLKChangeMarginOneDisplayInVBLank = 0.;
+	double ActiveClockChangeLatencyHidingY;
+	double ActiveClockChangeLatencyHidingC;
+	double ActiveClockChangeLatencyHiding;
+    double EffectiveDETBufferSizeY;
+	double     ActiveFCLKChangeLatencyMargin[DC__NUM_DPP__MAX];
+	double     USRRetrainingLatencyMargin[DC__NUM_DPP__MAX];
+	double TotalPixelBW = 0.0;
+	bool    SynchronizedSurfaces[DC__NUM_DPP__MAX][DC__NUM_DPP__MAX];
+	double     EffectiveLBLatencyHidingY;
+	double     EffectiveLBLatencyHidingC;
+	double     LinesInDETY[DC__NUM_DPP__MAX];
+	double     LinesInDETC[DC__NUM_DPP__MAX];
+	unsigned int    LinesInDETYRoundedDownToSwath[DC__NUM_DPP__MAX];
+	unsigned int    LinesInDETCRoundedDownToSwath[DC__NUM_DPP__MAX];
+	double     FullDETBufferingTimeY;
+	double     FullDETBufferingTimeC;
+	double     WritebackDRAMClockChangeLatencyMargin;
+	double     WritebackFCLKChangeLatencyMargin;
+	double     WritebackLatencyHiding;
+	bool    SameTimingForFCLKChange;
+
+	unsigned int    TotalActiveWriteback = 0;
+	unsigned int LBLatencyHidingSourceLinesY[DC__NUM_DPP__MAX];
+	unsigned int LBLatencyHidingSourceLinesC[DC__NUM_DPP__MAX];
 
 	Watermark->UrgentWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency;
 	Watermark->USRRetrainingWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency
@@ -4261,13 +4329,13 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 #endif
 
 
-	st_vars->TotalActiveWriteback = 0;
+	TotalActiveWriteback = 0;
 	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
 		if (WritebackEnable[k] == true)
-			st_vars->TotalActiveWriteback = st_vars->TotalActiveWriteback + 1;
+			TotalActiveWriteback = TotalActiveWriteback + 1;
 	}
 
-	if (st_vars->TotalActiveWriteback <= 1) {
+	if (TotalActiveWriteback <= 1) {
 		Watermark->WritebackUrgentWatermark = mmSOCParameters.WritebackLatency;
 	} else {
 		Watermark->WritebackUrgentWatermark = mmSOCParameters.WritebackLatency
@@ -4277,7 +4345,7 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 		Watermark->WritebackUrgentWatermark = Watermark->WritebackUrgentWatermark
 				+ mmSOCParameters.USRRetrainingLatency;
 
-	if (st_vars->TotalActiveWriteback <= 1) {
+	if (TotalActiveWriteback <= 1) {
 		Watermark->WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency
 				+ mmSOCParameters.WritebackLatency;
 		Watermark->WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency
@@ -4307,14 +4375,14 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 #endif
 
 	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
-		st_vars->TotalPixelBW = st_vars->TotalPixelBW + DPPPerSurface[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] +
+		TotalPixelBW = TotalPixelBW + DPPPerSurface[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] +
 				SwathWidthC[k] * BytePerPixelDETC[k] * VRatioChroma[k]) / (HTotal[k] / PixelClock[k]);
 	}
 
 	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
 
-		st_vars->LBLatencyHidingSourceLinesY[k] = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (VTaps[k] - 1);
-		st_vars->LBLatencyHidingSourceLinesC[k] = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTapsChroma[k] - 1);
+		LBLatencyHidingSourceLinesY[k] = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (VTaps[k] - 1);
+		LBLatencyHidingSourceLinesC[k] = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTapsChroma[k] - 1);
 
 
 #ifdef __DML_VBA_DEBUG__
@@ -4325,72 +4393,72 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 		dml_print("DML::%s: k=%d, VTaps              = %d\n", __func__, k, VTaps[k]);
 #endif
 
-		st_vars->EffectiveLBLatencyHidingY = st_vars->LBLatencyHidingSourceLinesY[k] / VRatio[k] * (HTotal[k] / PixelClock[k]);
-		st_vars->EffectiveLBLatencyHidingC = st_vars->LBLatencyHidingSourceLinesC[k] / VRatioChroma[k] * (HTotal[k] / PixelClock[k]);
-		st_vars->EffectiveDETBufferSizeY = DETBufferSizeY[k];
+		EffectiveLBLatencyHidingY = LBLatencyHidingSourceLinesY[k] / VRatio[k] * (HTotal[k] / PixelClock[k]);
+		EffectiveLBLatencyHidingC = LBLatencyHidingSourceLinesC[k] / VRatioChroma[k] * (HTotal[k] / PixelClock[k]);
+		EffectiveDETBufferSizeY = DETBufferSizeY[k];
 
 		if (UnboundedRequestEnabled) {
-			st_vars->EffectiveDETBufferSizeY = st_vars->EffectiveDETBufferSizeY
+			EffectiveDETBufferSizeY = EffectiveDETBufferSizeY
 					+ CompressedBufferSizeInkByte * 1024
 							* (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k])
-							/ (HTotal[k] / PixelClock[k]) / st_vars->TotalPixelBW;
+							/ (HTotal[k] / PixelClock[k]) / TotalPixelBW;
 		}
 
-		st_vars->LinesInDETY[k] = (double) st_vars->EffectiveDETBufferSizeY / BytePerPixelDETY[k] / SwathWidthY[k];
-		st_vars->LinesInDETYRoundedDownToSwath[k] = dml_floor(st_vars->LinesInDETY[k], SwathHeightY[k]);
-		st_vars->FullDETBufferingTimeY = st_vars->LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k];
+		LinesInDETY[k] = (double) EffectiveDETBufferSizeY / BytePerPixelDETY[k] / SwathWidthY[k];
+		LinesInDETYRoundedDownToSwath[k] = dml_floor(LinesInDETY[k], SwathHeightY[k]);
+		FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k];
 
-		st_vars->ActiveClockChangeLatencyHidingY = st_vars->EffectiveLBLatencyHidingY + st_vars->FullDETBufferingTimeY
+		ActiveClockChangeLatencyHidingY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY
 				- (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k];
 
 		if (NumberOfActiveSurfaces > 1) {
-			st_vars->ActiveClockChangeLatencyHidingY = st_vars->ActiveClockChangeLatencyHidingY
+			ActiveClockChangeLatencyHidingY = ActiveClockChangeLatencyHidingY
 					- (1 - 1 / NumberOfActiveSurfaces) * SwathHeightY[k] * HTotal[k]
 							/ PixelClock[k] / VRatio[k];
 		}
 
 		if (BytePerPixelDETC[k] > 0) {
-			st_vars->LinesInDETC[k] = DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k];
-			st_vars->LinesInDETCRoundedDownToSwath[k] = dml_floor(st_vars->LinesInDETC[k], SwathHeightC[k]);
-			st_vars->FullDETBufferingTimeC = st_vars->LinesInDETCRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k])
+			LinesInDETC[k] = DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k];
+			LinesInDETCRoundedDownToSwath[k] = dml_floor(LinesInDETC[k], SwathHeightC[k]);
+			FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k])
 					/ VRatioChroma[k];
-			st_vars->ActiveClockChangeLatencyHidingC = st_vars->EffectiveLBLatencyHidingC + st_vars->FullDETBufferingTimeC
+			ActiveClockChangeLatencyHidingC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC
 					- (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k]
 							/ PixelClock[k];
 			if (NumberOfActiveSurfaces > 1) {
-				st_vars->ActiveClockChangeLatencyHidingC = st_vars->ActiveClockChangeLatencyHidingC
+				ActiveClockChangeLatencyHidingC = ActiveClockChangeLatencyHidingC
 						- (1 - 1 / NumberOfActiveSurfaces) * SwathHeightC[k] * HTotal[k]
 								/ PixelClock[k] / VRatioChroma[k];
 			}
-			st_vars->ActiveClockChangeLatencyHiding = dml_min(st_vars->ActiveClockChangeLatencyHidingY,
-					st_vars->ActiveClockChangeLatencyHidingC);
+			ActiveClockChangeLatencyHiding = dml_min(ActiveClockChangeLatencyHidingY,
+					ActiveClockChangeLatencyHidingC);
 		} else {
-			st_vars->ActiveClockChangeLatencyHiding = st_vars->ActiveClockChangeLatencyHidingY;
+			ActiveClockChangeLatencyHiding = ActiveClockChangeLatencyHidingY;
 		}
 
-		ActiveDRAMClockChangeLatencyMargin[k] = st_vars->ActiveClockChangeLatencyHiding - Watermark->UrgentWatermark
+		ActiveDRAMClockChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - Watermark->UrgentWatermark
 				- Watermark->DRAMClockChangeWatermark;
-		st_vars->ActiveFCLKChangeLatencyMargin[k] = st_vars->ActiveClockChangeLatencyHiding - Watermark->UrgentWatermark
+		ActiveFCLKChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - Watermark->UrgentWatermark
 				- Watermark->FCLKChangeWatermark;
-		st_vars->USRRetrainingLatencyMargin[k] = st_vars->ActiveClockChangeLatencyHiding - Watermark->USRRetrainingWatermark;
+		USRRetrainingLatencyMargin[k] = ActiveClockChangeLatencyHiding - Watermark->USRRetrainingWatermark;
 
 		if (WritebackEnable[k]) {
-			st_vars->WritebackLatencyHiding = WritebackInterfaceBufferSize * 1024
+			WritebackLatencyHiding = WritebackInterfaceBufferSize * 1024
 					/ (WritebackDestinationWidth[k] * WritebackDestinationHeight[k]
 							/ (WritebackSourceHeight[k] * HTotal[k] / PixelClock[k]) * 4);
 			if (WritebackPixelFormat[k] == dm_444_64)
-				st_vars->WritebackLatencyHiding = st_vars->WritebackLatencyHiding / 2;
+				WritebackLatencyHiding = WritebackLatencyHiding / 2;
 
-			st_vars->WritebackDRAMClockChangeLatencyMargin = st_vars->WritebackLatencyHiding
+			WritebackDRAMClockChangeLatencyMargin = WritebackLatencyHiding
 					- Watermark->WritebackDRAMClockChangeWatermark;
 
-			st_vars->WritebackFCLKChangeLatencyMargin = st_vars->WritebackLatencyHiding
+			WritebackFCLKChangeLatencyMargin = WritebackLatencyHiding
 					- Watermark->WritebackFCLKChangeWatermark;
 
 			ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMargin[k],
-					st_vars->WritebackFCLKChangeLatencyMargin);
-			st_vars->ActiveFCLKChangeLatencyMargin[k] = dml_min(st_vars->ActiveFCLKChangeLatencyMargin[k],
-					st_vars->WritebackDRAMClockChangeLatencyMargin);
+					WritebackFCLKChangeLatencyMargin);
+			ActiveFCLKChangeLatencyMargin[k] = dml_min(ActiveFCLKChangeLatencyMargin[k],
+					WritebackDRAMClockChangeLatencyMargin);
 		}
 		MaxActiveDRAMClockChangeLatencySupported[k] =
 				(UseMALLForPStateChange[k] == dm_use_mall_pstate_change_phantom_pipe) ?
@@ -4409,41 +4477,41 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 					HTotal[i] == HTotal[j] && VTotal[i] == VTotal[j] &&
 					VActive[i] == VActive[j]) || (SynchronizeDRRDisplaysForUCLKPStateChangeFinal &&
 					(DRRDisplay[i] || DRRDisplay[j]))) {
-				st_vars->SynchronizedSurfaces[i][j] = true;
+				SynchronizedSurfaces[i][j] = true;
 			} else {
-				st_vars->SynchronizedSurfaces[i][j] = false;
+				SynchronizedSurfaces[i][j] = false;
 			}
 		}
 	}
 
 	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
 		if ((UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) &&
-				(!st_vars->FoundFirstSurfaceWithMinActiveFCLKChangeMargin ||
-				st_vars->ActiveFCLKChangeLatencyMargin[k] < st_vars->MinActiveFCLKChangeMargin)) {
-			st_vars->FoundFirstSurfaceWithMinActiveFCLKChangeMargin = true;
-			st_vars->MinActiveFCLKChangeMargin = st_vars->ActiveFCLKChangeLatencyMargin[k];
-			st_vars->SurfaceWithMinActiveFCLKChangeMargin = k;
+				(!FoundFirstSurfaceWithMinActiveFCLKChangeMargin ||
+				ActiveFCLKChangeLatencyMargin[k] < MinActiveFCLKChangeMargin)) {
+			FoundFirstSurfaceWithMinActiveFCLKChangeMargin = true;
+			MinActiveFCLKChangeMargin = ActiveFCLKChangeLatencyMargin[k];
+			SurfaceWithMinActiveFCLKChangeMargin = k;
 		}
 	}
 
-	*MinActiveFCLKChangeLatencySupported = st_vars->MinActiveFCLKChangeMargin + mmSOCParameters.FCLKChangeLatency;
+	*MinActiveFCLKChangeLatencySupported = MinActiveFCLKChangeMargin + mmSOCParameters.FCLKChangeLatency;
 
-	st_vars->SameTimingForFCLKChange = true;
+	SameTimingForFCLKChange = true;
 	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
-		if (!st_vars->SynchronizedSurfaces[k][st_vars->SurfaceWithMinActiveFCLKChangeMargin]) {
+		if (!SynchronizedSurfaces[k][SurfaceWithMinActiveFCLKChangeMargin]) {
 			if ((UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) &&
-					(st_vars->SameTimingForFCLKChange ||
-					st_vars->ActiveFCLKChangeLatencyMargin[k] <
-					st_vars->SecondMinActiveFCLKChangeMarginOneDisplayInVBLank)) {
-				st_vars->SecondMinActiveFCLKChangeMarginOneDisplayInVBLank = st_vars->ActiveFCLKChangeLatencyMargin[k];
+					(SameTimingForFCLKChange ||
+					ActiveFCLKChangeLatencyMargin[k] <
+					SecondMinActiveFCLKChangeMarginOneDisplayInVBLank)) {
+				SecondMinActiveFCLKChangeMarginOneDisplayInVBLank = ActiveFCLKChangeLatencyMargin[k];
 			}
-			st_vars->SameTimingForFCLKChange = false;
+			SameTimingForFCLKChange = false;
 		}
 	}
 
-	if (st_vars->MinActiveFCLKChangeMargin > 0) {
+	if (MinActiveFCLKChangeMargin > 0) {
 		*FCLKChangeSupport = dm_fclock_change_vactive;
-	} else if ((st_vars->SameTimingForFCLKChange || st_vars->SecondMinActiveFCLKChangeMarginOneDisplayInVBLank > 0) &&
+	} else if ((SameTimingForFCLKChange || SecondMinActiveFCLKChangeMarginOneDisplayInVBLank > 0) &&
 			(PrefetchMode <= 1)) {
 		*FCLKChangeSupport = dm_fclock_change_vblank;
 	} else {
@@ -4453,7 +4521,7 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 	*USRRetrainingSupport = true;
 	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
 		if ((UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) &&
-				(st_vars->USRRetrainingLatencyMargin[k] < 0)) {
+				(USRRetrainingLatencyMargin[k] < 0)) {
 			*USRRetrainingSupport = false;
 		}
 	}
@@ -4464,42 +4532,42 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 				UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe &&
 				ActiveDRAMClockChangeLatencyMargin[k] < 0) {
 			if (PrefetchMode > 0) {
-				st_vars->DRAMClockChangeSupportNumber = 2;
-			} else if (st_vars->DRAMClockChangeSupportNumber == 0) {
-				st_vars->DRAMClockChangeSupportNumber = 1;
-				st_vars->LastSurfaceWithoutMargin = k;
-			} else if (st_vars->DRAMClockChangeSupportNumber == 1 &&
-					!st_vars->SynchronizedSurfaces[st_vars->LastSurfaceWithoutMargin][k]) {
-				st_vars->DRAMClockChangeSupportNumber = 2;
+				DRAMClockChangeSupportNumber = 2;
+			} else if (DRAMClockChangeSupportNumber == 0) {
+				DRAMClockChangeSupportNumber = 1;
+				LastSurfaceWithoutMargin = k;
+			} else if (DRAMClockChangeSupportNumber == 1 &&
+					!SynchronizedSurfaces[LastSurfaceWithoutMargin][k]) {
+				DRAMClockChangeSupportNumber = 2;
 			}
 		}
 	}
 
 	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
 		if (UseMALLForPStateChange[k] == dm_use_mall_pstate_change_full_frame)
-			st_vars->DRAMClockChangeMethod = 1;
+			DRAMClockChangeMethod = 1;
 		else if (UseMALLForPStateChange[k] == dm_use_mall_pstate_change_sub_viewport)
-			st_vars->DRAMClockChangeMethod = 2;
+			DRAMClockChangeMethod = 2;
 	}
 
-	if (st_vars->DRAMClockChangeMethod == 0) {
-		if (st_vars->DRAMClockChangeSupportNumber == 0)
+	if (DRAMClockChangeMethod == 0) {
+		if (DRAMClockChangeSupportNumber == 0)
 			*DRAMClockChangeSupport = dm_dram_clock_change_vactive;
-		else if (st_vars->DRAMClockChangeSupportNumber == 1)
+		else if (DRAMClockChangeSupportNumber == 1)
 			*DRAMClockChangeSupport = dm_dram_clock_change_vblank;
 		else
 			*DRAMClockChangeSupport = dm_dram_clock_change_unsupported;
-	} else if (st_vars->DRAMClockChangeMethod == 1) {
-		if (st_vars->DRAMClockChangeSupportNumber == 0)
+	} else if (DRAMClockChangeMethod == 1) {
+		if (DRAMClockChangeSupportNumber == 0)
 			*DRAMClockChangeSupport = dm_dram_clock_change_vactive_w_mall_full_frame;
-		else if (st_vars->DRAMClockChangeSupportNumber == 1)
+		else if (DRAMClockChangeSupportNumber == 1)
 			*DRAMClockChangeSupport = dm_dram_clock_change_vblank_w_mall_full_frame;
 		else
 			*DRAMClockChangeSupport = dm_dram_clock_change_unsupported;
 	} else {
-		if (st_vars->DRAMClockChangeSupportNumber == 0)
+		if (DRAMClockChangeSupportNumber == 0)
 			*DRAMClockChangeSupport = dm_dram_clock_change_vactive_w_mall_sub_vp;
-		else if (st_vars->DRAMClockChangeSupportNumber == 1)
+		else if (DRAMClockChangeSupportNumber == 1)
 			*DRAMClockChangeSupport = dm_dram_clock_change_vblank_w_mall_sub_vp;
 		else
 			*DRAMClockChangeSupport = dm_dram_clock_change_unsupported;
@@ -4513,7 +4581,7 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 
 		dst_y_pstate = dml_ceil((mmSOCParameters.DRAMClockChangeLatency + mmSOCParameters.UrgentLatency) / (HTotal[k] / PixelClock[k]), 1);
 		src_y_pstate_l = dml_ceil(dst_y_pstate * VRatio[k], SwathHeightY[k]);
-		src_y_ahead_l = dml_floor(DETBufferSizeY[k] / BytePerPixelDETY[k] / SwathWidthY[k], SwathHeightY[k]) + st_vars->LBLatencyHidingSourceLinesY[k];
+		src_y_ahead_l = dml_floor(DETBufferSizeY[k] / BytePerPixelDETY[k] / SwathWidthY[k], SwathHeightY[k]) + LBLatencyHidingSourceLinesY[k];
 		sub_vp_lines_l = src_y_pstate_l + src_y_ahead_l + meta_row_height[k];
 
 #ifdef __DML_VBA_DEBUG__
@@ -4521,7 +4589,7 @@ dml_print("DML::%s: k=%d, DETBufferSizeY               = %d\n", __func__, k, DET
 dml_print("DML::%s: k=%d, BytePerPixelDETY             = %f\n", __func__, k, BytePerPixelDETY[k]);
 dml_print("DML::%s: k=%d, SwathWidthY                  = %d\n", __func__, k, SwathWidthY[k]);
 dml_print("DML::%s: k=%d, SwathHeightY                 = %d\n", __func__, k, SwathHeightY[k]);
-dml_print("DML::%s: k=%d, LBLatencyHidingSourceLinesY  = %d\n", __func__, k, st_vars->LBLatencyHidingSourceLinesY[k]);
+dml_print("DML::%s: k=%d, LBLatencyHidingSourceLinesY  = %d\n", __func__, k, LBLatencyHidingSourceLinesY[k]);
 dml_print("DML::%s: k=%d, dst_y_pstate      = %d\n", __func__, k, dst_y_pstate);
 dml_print("DML::%s: k=%d, src_y_pstate_l    = %d\n", __func__, k, src_y_pstate_l);
 dml_print("DML::%s: k=%d, src_y_ahead_l     = %d\n", __func__, k, src_y_ahead_l);
@@ -4532,7 +4600,7 @@ dml_print("DML::%s: k=%d, sub_vp_lines_l    = %d\n", __func__, k, sub_vp_lines_l
 
 		if (BytePerPixelDETC[k] > 0) {
 			src_y_pstate_c = dml_ceil(dst_y_pstate * VRatioChroma[k], SwathHeightC[k]);
-			src_y_ahead_c = dml_floor(DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k], SwathHeightC[k]) + st_vars->LBLatencyHidingSourceLinesC[k];
+			src_y_ahead_c = dml_floor(DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k], SwathHeightC[k]) + LBLatencyHidingSourceLinesC[k];
 			sub_vp_lines_c = src_y_pstate_c + src_y_ahead_c + meta_row_height_chroma[k];
 			SubViewportLinesNeededInMALL[k] = dml_max(sub_vp_lines_l, sub_vp_lines_c);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h
index 37a314ce284b..d293856ba906 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h
@@ -30,7 +30,6 @@
 #include "os_types.h"
 #include "../dc_features.h"
 #include "../display_mode_structs.h"
-#include "dml/display_mode_vba.h"
 
 unsigned int dml32_dscceComputeDelay(
 		unsigned int bpc,
@@ -82,7 +81,6 @@ void dml32_CalculateSinglePipeDPPCLKAndSCLThroughput(
 		double *DPPCLKUsingSingleDPP);
 
 void dml32_CalculateSwathAndDETConfiguration(
-		struct dml32_CalculateSwathAndDETConfiguration *st_vars,
 		unsigned int DETSizeOverride[],
 		enum dm_use_mall_for_pstate_change_mode UseMALLForPStateChange[],
 		unsigned int ConfigReturnBufferSizeInKByte,
@@ -362,7 +360,6 @@ void dml32_CalculateSurfaceSizeInMall(
 		bool *ExceededMALLSize);
 
 void dml32_CalculateVMRowAndSwath(
-		struct dml32_CalculateVMRowAndSwath *st_vars,
 		unsigned int NumberOfActiveSurfaces,
 		DmlPipe myPipe[],
 		unsigned int SurfaceSizeInMALL[],
@@ -715,7 +712,6 @@ double dml32_CalculateExtraLatency(
 		unsigned int HostVMMaxNonCachedPageTableLevels);
 
 bool dml32_CalculatePrefetchSchedule(
-		struct dml32_CalculatePrefetchSchedule *st_vars,
 		double HostVMInefficiencyFactor,
 		DmlPipe *myPipe,
 		unsigned int DSCDelay,
@@ -811,7 +807,6 @@ void dml32_CalculateFlipSchedule(
 		bool *ImmediateFlipSupportedForPipe);
 
 void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
-		struct dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport *st_vars,
 		bool USRRetrainingRequiredFinal,
 		enum dm_use_mall_for_pstate_change_mode UseMALLForPStateChange[],
 		unsigned int PrefetchMode,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
index 84b4b00f29cb..c87091683b5d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
@@ -498,6 +498,13 @@ void dcn321_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p
 				dc->bb_overrides.dram_clock_change_latency_ns / 1000.0;
 		}
 
+		if ((int)(dcn3_21_soc.fclk_change_latency_us * 1000)
+				!= dc->bb_overrides.fclk_clock_change_latency_ns
+				&& dc->bb_overrides.fclk_clock_change_latency_ns) {
+			dcn3_21_soc.fclk_change_latency_us =
+				dc->bb_overrides.fclk_clock_change_latency_ns / 1000;
+		}
+
 		if ((int)(dcn3_21_soc.dummy_pstate_latency_us * 1000)
 				!= dc->bb_overrides.dummy_clock_change_latency_ns
 				&& dc->bb_overrides.dummy_clock_change_latency_ns) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
index 8460aefe7b6d..492aec634b68 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
@@ -182,108 +182,6 @@ void Calculate256BBlockSizes(
 		unsigned int *BlockWidth256BytesY,
 		unsigned int *BlockWidth256BytesC);
 
-struct dml32_CalculateSwathAndDETConfiguration {
-	unsigned int MaximumSwathHeightY[DC__NUM_DPP__MAX];
-	unsigned int MaximumSwathHeightC[DC__NUM_DPP__MAX];
-	unsigned int RoundedUpMaxSwathSizeBytesY[DC__NUM_DPP__MAX];
-	unsigned int RoundedUpMaxSwathSizeBytesC[DC__NUM_DPP__MAX];
-	unsigned int RoundedUpSwathSizeBytesY;
-	unsigned int RoundedUpSwathSizeBytesC;
-	double SwathWidthdoubleDPP[DC__NUM_DPP__MAX];
-	double SwathWidthdoubleDPPChroma[DC__NUM_DPP__MAX];
-	unsigned int TotalActiveDPP;
-	bool NoChromaSurfaces;
-	unsigned int DETBufferSizeInKByteForSwathCalculation;
-};
-
-struct dml32_CalculateVMRowAndSwath {
-	unsigned int PTEBufferSizeInRequestsForLuma[DC__NUM_DPP__MAX];
-	unsigned int PTEBufferSizeInRequestsForChroma[DC__NUM_DPP__MAX];
-	unsigned int PDEAndMetaPTEBytesFrameY;
-	unsigned int PDEAndMetaPTEBytesFrameC;
-	unsigned int MetaRowByteY[DC__NUM_DPP__MAX];
-	unsigned int MetaRowByteC[DC__NUM_DPP__MAX];
-	unsigned int PixelPTEBytesPerRowY[DC__NUM_DPP__MAX];
-	unsigned int PixelPTEBytesPerRowC[DC__NUM_DPP__MAX];
-	unsigned int PixelPTEBytesPerRowY_one_row_per_frame[DC__NUM_DPP__MAX];
-	unsigned int PixelPTEBytesPerRowC_one_row_per_frame[DC__NUM_DPP__MAX];
-	unsigned int dpte_row_width_luma_ub_one_row_per_frame[DC__NUM_DPP__MAX];
-	unsigned int dpte_row_height_luma_one_row_per_frame[DC__NUM_DPP__MAX];
-	unsigned int dpte_row_width_chroma_ub_one_row_per_frame[DC__NUM_DPP__MAX];
-	unsigned int dpte_row_height_chroma_one_row_per_frame[DC__NUM_DPP__MAX];
-	bool one_row_per_frame_fits_in_buffer[DC__NUM_DPP__MAX];
-};
-
-struct dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport {
-	unsigned int SurfaceWithMinActiveFCLKChangeMargin;
-	unsigned int DRAMClockChangeSupportNumber;
-	unsigned int LastSurfaceWithoutMargin;
-	unsigned int DRAMClockChangeMethod;
-	bool FoundFirstSurfaceWithMinActiveFCLKChangeMargin;
-	double MinActiveFCLKChangeMargin;
-	double SecondMinActiveFCLKChangeMarginOneDisplayInVBLank;
-	double ActiveClockChangeLatencyHidingY;
-	double ActiveClockChangeLatencyHidingC;
-	double ActiveClockChangeLatencyHiding;
-	double EffectiveDETBufferSizeY;
-	double ActiveFCLKChangeLatencyMargin[DC__NUM_DPP__MAX];
-	double USRRetrainingLatencyMargin[DC__NUM_DPP__MAX];
-	double TotalPixelBW;
-	bool SynchronizedSurfaces[DC__NUM_DPP__MAX][DC__NUM_DPP__MAX];
-	double EffectiveLBLatencyHidingY;
-	double EffectiveLBLatencyHidingC;
-	double LinesInDETY[DC__NUM_DPP__MAX];
-	double LinesInDETC[DC__NUM_DPP__MAX];
-	unsigned int LinesInDETYRoundedDownToSwath[DC__NUM_DPP__MAX];
-	unsigned int LinesInDETCRoundedDownToSwath[DC__NUM_DPP__MAX];
-	double FullDETBufferingTimeY;
-	double FullDETBufferingTimeC;
-	double WritebackDRAMClockChangeLatencyMargin;
-	double WritebackFCLKChangeLatencyMargin;
-	double WritebackLatencyHiding;
-	bool SameTimingForFCLKChange;
-	unsigned int TotalActiveWriteback;
-	unsigned int LBLatencyHidingSourceLinesY[DC__NUM_DPP__MAX];
-	unsigned int LBLatencyHidingSourceLinesC[DC__NUM_DPP__MAX];
-};
-
-struct dml32_CalculatePrefetchSchedule {
-	unsigned int DPPCycles, DISPCLKCycles;
-	double DSTTotalPixelsAfterScaler;
-	double LineTime;
-	double dst_y_prefetch_equ;
-	double prefetch_bw_oto;
-	double Tvm_oto;
-	double Tr0_oto;
-	double Tvm_oto_lines;
-	double Tr0_oto_lines;
-	double dst_y_prefetch_oto;
-	double TimeForFetchingMetaPTE;
-	double TimeForFetchingRowInVBlank;
-	double LinesToRequestPrefetchPixelData;
-	unsigned int HostVMDynamicLevelsTrips;
-	double trip_to_mem;
-	double Tvm_trips;
-	double Tr0_trips;
-	double Tvm_trips_rounded;
-	double Tr0_trips_rounded;
-	double Lsw_oto;
-	double Tpre_rounded;
-	double prefetch_bw_equ;
-	double Tvm_equ;
-	double Tr0_equ;
-	double Tdmbf;
-	double Tdmec;
-	double Tdmsks;
-	double prefetch_sw_bytes;
-	double bytes_pp;
-	double dep_bytes;
-	unsigned int max_vratio_pre;
-	double min_Lsw;
-	double Tsw_est1;
-	double Tsw_est3;
-};
-
 struct DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation {
 	unsigned int dummy_integer_array[2][DC__NUM_DPP__MAX];
 	double dummy_single_array[2][DC__NUM_DPP__MAX];
@@ -355,10 +253,6 @@ struct dummy_vars {
 	struct DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation
 	DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation;
 	struct dml32_ModeSupportAndSystemConfigurationFull dml32_ModeSupportAndSystemConfigurationFull;
-	struct dml32_CalculateSwathAndDETConfiguration dml32_CalculateSwathAndDETConfiguration;
-	struct dml32_CalculateVMRowAndSwath dml32_CalculateVMRowAndSwath;
-	struct dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport;
-	struct dml32_CalculatePrefetchSchedule dml32_CalculatePrefetchSchedule;
 };
 
 struct vba_vars_st {
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index ab06c7fc7452..9f3558c0ef11 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -244,13 +244,15 @@ enum {
 #define ASICREV_IS_GC_10_3_7(eChipRev) ((eChipRev >= GC_10_3_7_A0) && (eChipRev < GC_10_3_7_UNKNOWN))
 
 #define AMDGPU_FAMILY_GC_11_0_0 145
-#define AMDGPU_FAMILY_GC_11_0_2 148
+#define AMDGPU_FAMILY_GC_11_0_1 148
 #define GC_11_0_0_A0 0x1
 #define GC_11_0_2_A0 0x10
+#define GC_11_0_3_A0 0x20
 #define GC_11_UNKNOWN 0xFF
 
 #define ASICREV_IS_GC_11_0_0(eChipRev) (eChipRev < GC_11_0_2_A0)
-#define ASICREV_IS_GC_11_0_2(eChipRev) (eChipRev >= GC_11_0_2_A0 && eChipRev < GC_11_UNKNOWN)
+#define ASICREV_IS_GC_11_0_2(eChipRev) (eChipRev >= GC_11_0_2_A0 && eChipRev < GC_11_0_3_A0)
+#define ASICREV_IS_GC_11_0_3(eChipRev) (eChipRev >= GC_11_0_3_A0 && eChipRev < GC_11_UNKNOWN)
 
 /*
  * ASIC chip ID
diff --git a/drivers/gpu/drm/amd/display/include/logger_types.h b/drivers/gpu/drm/amd/display/include/logger_types.h
index f093b49c5e6e..3bf08a60c45c 100644
--- a/drivers/gpu/drm/amd/display/include/logger_types.h
+++ b/drivers/gpu/drm/amd/display/include/logger_types.h
@@ -119,13 +119,15 @@ enum dc_log_type {
 	LOG_HDMI_RETIMER_REDRIVER,
 	LOG_DSC,
 	LOG_SMU_MSG,
+	LOG_DC2RESERVED4,
+	LOG_DC2RESERVED5,
 	LOG_DWB,
 	LOG_GAMMA_DEBUG,
 	LOG_MAX_HW_POINTS,
 	LOG_ALL_TF_CHANNELS,
 	LOG_SAMPLE_1DLUT,
 	LOG_DP2,
-	LOG_SECTION_TOTAL_COUNT
+	LOG_DC2RESERVED12,
 };
 
 #define DC_MIN_LOG_MASK ((1 << LOG_ERROR) | \
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index da09ba7589f7..0f39ab9dc5b4 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -613,10 +613,6 @@ static void build_vrr_infopacket_data_v1(const struct mod_vrr_params *vrr,
 	 * Note: We should never go above the field rate of the mode timing set.
 	 */
 	infopacket->sb[8] = (unsigned char)((vrr->max_refresh_in_uhz + 500000) / 1000000);
-
-	/* FreeSync HDR */
-	infopacket->sb[9] = 0;
-	infopacket->sb[10] = 0;
 }
 
 static void build_vrr_infopacket_data_v3(const struct mod_vrr_params *vrr,
@@ -684,10 +680,6 @@ static void build_vrr_infopacket_data_v3(const struct mod_vrr_params *vrr,
 
 	/* PB16 : Reserved bits 7:1, FixedRate bit 0 */
 	infopacket->sb[16] = (vrr->state == VRR_STATE_ACTIVE_FIXED) ? 1 : 0;
-
-	//FreeSync HDR
-	infopacket->sb[9] = 0;
-	infopacket->sb[10] = 0;
 }
 
 static void build_vrr_infopacket_fs2_data(enum color_transfer_func app_tf,
@@ -772,8 +764,7 @@ static void build_vrr_infopacket_header_v2(enum signal_type signal,
 		/* HB2  = [Bits 7:5 = 0] [Bits 4:0 = Length = 0x09] */
 		infopacket->hb2 = 0x09;
 
-		*payload_size = 0x0A;
-
+		*payload_size = 0x09;
 	} else if (dc_is_dp_signal(signal)) {
 
 		/* HEADER */
@@ -822,9 +813,9 @@ static void build_vrr_infopacket_header_v3(enum signal_type signal,
 		infopacket->hb1 = version;
 
 		/* HB2  = [Bits 7:5 = 0] [Bits 4:0 = Length] */
-		*payload_size = 0x10;
-		infopacket->hb2 = *payload_size - 1; //-1 for checksum
+		infopacket->hb2 = 0x10;
 
+		*payload_size = 0x10;
 	} else if (dc_is_dp_signal(signal)) {
 
 		/* HEADER */
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h
index 76f695a1d065..ae2d337158f3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h
@@ -27,7 +27,7 @@
 // *** IMPORTANT ***
 // SMU TEAM: Always increment the interface version if
 // any structure is changed in this file
-#define PMFW_DRIVER_IF_VERSION 4
+#define PMFW_DRIVER_IF_VERSION 5
 
 typedef struct {
   int32_t value;
@@ -197,6 +197,8 @@ typedef struct {
 
   uint16_t SkinTemp;
   uint16_t DeviceState;
+  uint16_t CurTemp;                     //[centi-Celsius]
+  uint16_t spare2;
 } SmuMetrics_t;
 
 typedef struct {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
index c02e5e576728..6fe2fe92ebd7 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
@@ -28,7 +28,7 @@
 #define SMU13_DRIVER_IF_VERSION_INV 0xFFFFFFFF
 #define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x04
 #define SMU13_DRIVER_IF_VERSION_ALDE 0x08
-#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x04
+#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x05
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0 0x2C
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x2C
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index fa520d79ef67..6db67f082d91 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -4283,6 +4283,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.dump_pptable = sienna_cichlid_dump_pptable,
 	.init_microcode = smu_v11_0_init_microcode,
 	.load_microcode = smu_v11_0_load_microcode,
+	.fini_microcode = smu_v11_0_fini_microcode,
 	.init_smc_tables = sienna_cichlid_init_smc_tables,
 	.fini_smc_tables = smu_v11_0_fini_smc_tables,
 	.init_power = smu_v11_0_init_power,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index e8fe84f806d1..18ee3b5e64c5 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -212,6 +212,9 @@ int smu_v13_0_init_pptable_microcode(struct smu_context *smu)
 	if (!adev->scpm_enabled)
 		return 0;
 
+	if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 7))
+		return 0;
+
 	/* override pptable_id from driver parameter */
 	if (amdgpu_smu_pptable_id >= 0) {
 		pptable_id = amdgpu_smu_pptable_id;
@@ -219,16 +222,10 @@ int smu_v13_0_init_pptable_microcode(struct smu_context *smu)
 	} else {
 		pptable_id = smu->smu_table.boot_values.pp_table_id;
 
-		if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 7) &&
-			pptable_id == 3667)
-			pptable_id = 36671;
-
-		if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 7) &&
-			pptable_id == 3688)
-			pptable_id = 36881;
 		/*
 		 * Temporary solution for SMU V13.0.0 with SCPM enabled:
 		 *   - use 36831 signed pptable when pp_table_id is 3683
+		 *   - use 37151 signed pptable when pp_table_id is 3715
 		 *   - use 36641 signed pptable when pp_table_id is 3664 or 0
 		 * TODO: drop these when the pptable carried in vbios is ready.
 		 */
@@ -241,6 +238,9 @@ int smu_v13_0_init_pptable_microcode(struct smu_context *smu)
 			case 3683:
 				pptable_id = 36831;
 				break;
+			case 3715:
+				pptable_id = 37151;
+				break;
 			default:
 				dev_err(adev->dev, "Unsupported pptable id %d\n", pptable_id);
 				return -EINVAL;
@@ -478,7 +478,7 @@ int smu_v13_0_setup_pptable(struct smu_context *smu)
 
 		/*
 		 * Temporary solution for SMU V13.0.0 with SCPM disabled:
-		 *   - use 3664 or 3683 on request
+		 *   - use 3664, 3683 or 3715 on request
 		 *   - use 3664 when pptable_id is 0
 		 * TODO: drop these when the pptable carried in vbios is ready.
 		 */
@@ -489,6 +489,7 @@ int smu_v13_0_setup_pptable(struct smu_context *smu)
 				break;
 			case 3664:
 			case 3683:
+			case 3715:
 				break;
 			default:
 				dev_err(adev->dev, "Unsupported pptable id %d\n", pptable_id);
@@ -2344,8 +2345,8 @@ int smu_v13_0_set_gfx_power_up_by_imu(struct smu_context *smu)
 
 	index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_MSG,
 					       SMU_MSG_EnableGfxImu);
-
-	return smu_cmn_send_msg_without_waiting(smu, index, 0);
+	/* Param 1 to tell PMFW to enable GFXOFF feature */
+	return smu_cmn_send_msg_without_waiting(smu, index, 1);
 }
 
 int smu_v13_0_od_edit_dpm_table(struct smu_context *smu,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 1bbeceeb9e3c..df4a47acd724 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -1792,7 +1792,9 @@ static const struct pptable_funcs smu_v13_0_0_ppt_funcs = {
 	.dump_pptable = smu_v13_0_0_dump_pptable,
 	.init_microcode = smu_v13_0_init_microcode,
 	.load_microcode = smu_v13_0_load_microcode,
+	.fini_microcode = smu_v13_0_fini_microcode,
 	.init_smc_tables = smu_v13_0_0_init_smc_tables,
+	.fini_smc_tables = smu_v13_0_fini_smc_tables,
 	.init_power = smu_v13_0_init_power,
 	.fini_power = smu_v13_0_fini_power,
 	.check_fw_status = smu_v13_0_check_fw_status,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
index 82d3718d8324..97e1d55dcaad 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
@@ -71,7 +71,6 @@ static struct cmn2asic_msg_mapping smu_v13_0_4_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(EnableGfxOff,                   PPSMC_MSG_EnableGfxOff,			1),
 	MSG_MAP(AllowGfxOff,                    PPSMC_MSG_AllowGfxOff,			1),
 	MSG_MAP(DisallowGfxOff,                 PPSMC_MSG_DisallowGfxOff,		1),
 	MSG_MAP(PowerDownVcn,                   PPSMC_MSG_PowerDownVcn,			1),
@@ -199,6 +198,9 @@ static int smu_v13_0_4_fini_smc_tables(struct smu_context *smu)
 	kfree(smu_table->watermarks_table);
 	smu_table->watermarks_table = NULL;
 
+	kfree(smu_table->gpu_metrics_table);
+	smu_table->gpu_metrics_table = NULL;
+
 	return 0;
 }
 
@@ -226,18 +228,6 @@ static int smu_v13_0_4_system_features_control(struct smu_context *smu, bool en)
 	return ret;
 }
 
-static int smu_v13_0_4_post_smu_init(struct smu_context *smu)
-{
-	struct amdgpu_device *adev = smu->adev;
-	int ret = 0;
-
-	/* allow message will be sent after enable message */
-	ret = smu_cmn_send_smc_msg(smu, SMU_MSG_EnableGfxOff, NULL);
-	if (ret)
-		dev_err(adev->dev, "Failed to Enable GfxOff!\n");
-	return ret;
-}
-
 static ssize_t smu_v13_0_4_get_gpu_metrics(struct smu_context *smu,
 					   void **table)
 {
@@ -1026,7 +1016,6 @@ static const struct pptable_funcs smu_v13_0_4_ppt_funcs = {
 	.get_pp_feature_mask = smu_cmn_get_pp_feature_mask,
 	.set_driver_table_location = smu_v13_0_set_driver_table_location,
 	.gfx_off_control = smu_v13_0_gfx_off_control,
-	.post_init = smu_v13_0_4_post_smu_init,
 	.mode2_reset = smu_v13_0_4_mode2_reset,
 	.get_dpm_ultimate_freq = smu_v13_0_4_get_dpm_ultimate_freq,
 	.od_edit_dpm_table = smu_v13_0_od_edit_dpm_table,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c
index 47360ef5c175..66445964efbd 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c
@@ -176,6 +176,9 @@ static int smu_v13_0_5_fini_smc_tables(struct smu_context *smu)
 	kfree(smu_table->watermarks_table);
 	smu_table->watermarks_table = NULL;
 
+	kfree(smu_table->gpu_metrics_table);
+	smu_table->gpu_metrics_table = NULL;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index 9dd56e73218b..1016d1c216d8 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -1567,6 +1567,16 @@ static int smu_v13_0_7_set_mp1_state(struct smu_context *smu,
 	return ret;
 }
 
+static bool smu_v13_0_7_is_mode1_reset_supported(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+
+	/* SRIOV does not support SMU mode1 reset */
+	if (amdgpu_sriov_vf(adev))
+		return false;
+
+	return true;
+}
 static const struct pptable_funcs smu_v13_0_7_ppt_funcs = {
 	.get_allowed_feature_mask = smu_v13_0_7_get_allowed_feature_mask,
 	.set_default_dpm_table = smu_v13_0_7_set_default_dpm_table,
@@ -1574,7 +1584,9 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = {
 	.dump_pptable = smu_v13_0_7_dump_pptable,
 	.init_microcode = smu_v13_0_init_microcode,
 	.load_microcode = smu_v13_0_load_microcode,
+	.fini_microcode = smu_v13_0_fini_microcode,
 	.init_smc_tables = smu_v13_0_7_init_smc_tables,
+	.fini_smc_tables = smu_v13_0_fini_smc_tables,
 	.init_power = smu_v13_0_init_power,
 	.fini_power = smu_v13_0_fini_power,
 	.check_fw_status = smu_v13_0_7_check_fw_status,
@@ -1624,6 +1636,8 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = {
 	.baco_set_state = smu_v13_0_baco_set_state,
 	.baco_enter = smu_v13_0_baco_enter,
 	.baco_exit = smu_v13_0_baco_exit,
+	.mode1_reset_is_support = smu_v13_0_7_is_mode1_reset_supported,
+	.mode1_reset = smu_v13_0_mode1_reset,
 	.set_mp1_state = smu_v13_0_7_set_mp1_state,
 };
 
diff --git a/drivers/gpu/drm/bridge/lvds-codec.c b/drivers/gpu/drm/bridge/lvds-codec.c
index 702ea803a743..39e7004de720 100644
--- a/drivers/gpu/drm/bridge/lvds-codec.c
+++ b/drivers/gpu/drm/bridge/lvds-codec.c
@@ -180,7 +180,7 @@ static int lvds_codec_probe(struct platform_device *pdev)
 		of_node_put(bus_node);
 		if (ret == -ENODEV) {
 			dev_warn(dev, "missing 'data-mapping' DT property\n");
-		} else if (ret) {
+		} else if (ret < 0) {
 			dev_err(dev, "invalid 'data-mapping' DT property\n");
 			return ret;
 		} else {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index ccec4055fde3..389e9f157ca5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -268,7 +268,7 @@ static void __i915_gem_object_free_mmaps(struct drm_i915_gem_object *obj)
  */
 void __i915_gem_object_pages_fini(struct drm_i915_gem_object *obj)
 {
-	assert_object_held(obj);
+	assert_object_held_shared(obj);
 
 	if (!list_empty(&obj->vma.list)) {
 		struct i915_vma *vma;
@@ -331,15 +331,7 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 			continue;
 		}
 
-		if (!i915_gem_object_trylock(obj, NULL)) {
-			/* busy, toss it back to the pile */
-			if (llist_add(&obj->freed, &i915->mm.free_list))
-				queue_delayed_work(i915->wq, &i915->mm.free_work, msecs_to_jiffies(10));
-			continue;
-		}
-
 		__i915_gem_object_pages_fini(obj);
-		i915_gem_object_unlock(obj);
 		__i915_gem_free_object(obj);
 
 		/* But keep the pointer alive for RCU-protected lookups */
@@ -359,7 +351,7 @@ void i915_gem_flush_free_objects(struct drm_i915_private *i915)
 static void __i915_gem_free_work(struct work_struct *work)
 {
 	struct drm_i915_private *i915 =
-		container_of(work, struct drm_i915_private, mm.free_work.work);
+		container_of(work, struct drm_i915_private, mm.free_work);
 
 	i915_gem_flush_free_objects(i915);
 }
@@ -391,7 +383,7 @@ static void i915_gem_free_object(struct drm_gem_object *gem_obj)
 	 */
 
 	if (llist_add(&obj->freed, &i915->mm.free_list))
-		queue_delayed_work(i915->wq, &i915->mm.free_work, 0);
+		queue_work(i915->wq, &i915->mm.free_work);
 }
 
 void __i915_gem_object_flush_frontbuffer(struct drm_i915_gem_object *obj,
@@ -745,7 +737,7 @@ bool i915_gem_object_needs_ccs_pages(struct drm_i915_gem_object *obj)
 
 void i915_gem_init__objects(struct drm_i915_private *i915)
 {
-	INIT_DELAYED_WORK(&i915->mm.free_work, __i915_gem_free_work);
+	INIT_WORK(&i915->mm.free_work, __i915_gem_free_work);
 }
 
 void i915_objects_module_exit(void)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index 5cf36a130061..9f6b14ec189a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -335,7 +335,6 @@ struct drm_i915_gem_object {
 #define I915_BO_READONLY          BIT(7)
 #define I915_TILING_QUIRK_BIT     8 /* unknown swizzling; do not release! */
 #define I915_BO_PROTECTED         BIT(9)
-#define I915_BO_WAS_BOUND_BIT     10
 	/**
 	 * @mem_flags - Mutable placement-related flags
 	 *
@@ -616,6 +615,8 @@ struct drm_i915_gem_object {
 		 * pages were last acquired.
 		 */
 		bool dirty:1;
+
+		u32 tlb;
 	} mm;
 
 	struct {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 97c820eee115..8357dbdcab5c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -6,14 +6,15 @@
 
 #include <drm/drm_cache.h>
 
+#include "gt/intel_gt.h"
+#include "gt/intel_gt_pm.h"
+
 #include "i915_drv.h"
 #include "i915_gem_object.h"
 #include "i915_scatterlist.h"
 #include "i915_gem_lmem.h"
 #include "i915_gem_mman.h"
 
-#include "gt/intel_gt.h"
-
 void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj,
 				 struct sg_table *pages,
 				 unsigned int sg_page_sizes)
@@ -190,6 +191,18 @@ static void unmap_object(struct drm_i915_gem_object *obj, void *ptr)
 		vunmap(ptr);
 }
 
+static void flush_tlb_invalidate(struct drm_i915_gem_object *obj)
+{
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	struct intel_gt *gt = to_gt(i915);
+
+	if (!obj->mm.tlb)
+		return;
+
+	intel_gt_invalidate_tlb(gt, obj->mm.tlb);
+	obj->mm.tlb = 0;
+}
+
 struct sg_table *
 __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
 {
@@ -215,13 +228,7 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
 	__i915_gem_object_reset_page_iter(obj);
 	obj->mm.page_sizes.phys = obj->mm.page_sizes.sg = 0;
 
-	if (test_and_clear_bit(I915_BO_WAS_BOUND_BIT, &obj->flags)) {
-		struct drm_i915_private *i915 = to_i915(obj->base.dev);
-		intel_wakeref_t wakeref;
-
-		with_intel_runtime_pm_if_active(&i915->runtime_pm, wakeref)
-			intel_gt_invalidate_tlbs(to_gt(i915));
-	}
+	flush_tlb_invalidate(obj);
 
 	return pages;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 68c2b0d8f187..f435e06125aa 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -11,7 +11,9 @@
 #include "pxp/intel_pxp.h"
 
 #include "i915_drv.h"
+#include "i915_perf_oa_regs.h"
 #include "intel_context.h"
+#include "intel_engine_pm.h"
 #include "intel_engine_regs.h"
 #include "intel_ggtt_gmch.h"
 #include "intel_gt.h"
@@ -36,8 +38,6 @@ static void __intel_gt_init_early(struct intel_gt *gt)
 {
 	spin_lock_init(&gt->irq_lock);
 
-	mutex_init(&gt->tlb_invalidate_lock);
-
 	INIT_LIST_HEAD(&gt->closed_vma);
 	spin_lock_init(&gt->closed_lock);
 
@@ -48,6 +48,8 @@ static void __intel_gt_init_early(struct intel_gt *gt)
 	intel_gt_init_reset(gt);
 	intel_gt_init_requests(gt);
 	intel_gt_init_timelines(gt);
+	mutex_init(&gt->tlb.invalidate_lock);
+	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
 	intel_gt_pm_init_early(gt);
 
 	intel_uc_init_early(&gt->uc);
@@ -768,6 +770,7 @@ void intel_gt_driver_late_release_all(struct drm_i915_private *i915)
 		intel_gt_fini_requests(gt);
 		intel_gt_fini_reset(gt);
 		intel_gt_fini_timelines(gt);
+		mutex_destroy(&gt->tlb.invalidate_lock);
 		intel_engines_free(gt);
 	}
 }
@@ -906,7 +909,7 @@ get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8,
 	return rb;
 }
 
-void intel_gt_invalidate_tlbs(struct intel_gt *gt)
+static void mmio_invalidate_full(struct intel_gt *gt)
 {
 	static const i915_reg_t gen8_regs[] = {
 		[RENDER_CLASS]			= GEN8_RTCR,
@@ -924,13 +927,11 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 	struct drm_i915_private *i915 = gt->i915;
 	struct intel_uncore *uncore = gt->uncore;
 	struct intel_engine_cs *engine;
+	intel_engine_mask_t awake, tmp;
 	enum intel_engine_id id;
 	const i915_reg_t *regs;
 	unsigned int num = 0;
 
-	if (I915_SELFTEST_ONLY(gt->awake == -ENODEV))
-		return;
-
 	if (GRAPHICS_VER(i915) == 12) {
 		regs = gen12_regs;
 		num = ARRAY_SIZE(gen12_regs);
@@ -945,28 +946,41 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 			  "Platform does not implement TLB invalidation!"))
 		return;
 
-	GEM_TRACE("\n");
-
-	assert_rpm_wakelock_held(&i915->runtime_pm);
-
-	mutex_lock(&gt->tlb_invalidate_lock);
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
 
 	spin_lock_irq(&uncore->lock); /* serialise invalidate with GT reset */
 
+	awake = 0;
 	for_each_engine(engine, gt, id) {
 		struct reg_and_bit rb;
 
+		if (!intel_engine_pm_is_awake(engine))
+			continue;
+
 		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
 		if (!i915_mmio_reg_offset(rb.reg))
 			continue;
 
 		intel_uncore_write_fw(uncore, rb.reg, rb.bit);
+		awake |= engine->mask;
 	}
 
+	GT_TRACE(gt, "invalidated engines %08x\n", awake);
+
+	/* Wa_2207587034:tgl,dg1,rkl,adl-s,adl-p */
+	if (awake &&
+	    (IS_TIGERLAKE(i915) ||
+	     IS_DG1(i915) ||
+	     IS_ROCKETLAKE(i915) ||
+	     IS_ALDERLAKE_S(i915) ||
+	     IS_ALDERLAKE_P(i915)))
+		intel_uncore_write_fw(uncore, GEN12_OA_TLB_INV_CR, 1);
+
 	spin_unlock_irq(&uncore->lock);
 
-	for_each_engine(engine, gt, id) {
+	for_each_engine_masked(engine, gt, awake, tmp) {
+		struct reg_and_bit rb;
+
 		/*
 		 * HW architecture suggest typical invalidation time at 40us,
 		 * with pessimistic cases up to 100us and a recommendation to
@@ -974,12 +988,8 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 		 */
 		const unsigned int timeout_us = 100;
 		const unsigned int timeout_ms = 4;
-		struct reg_and_bit rb;
 
 		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
-		if (!i915_mmio_reg_offset(rb.reg))
-			continue;
-
 		if (__intel_wait_for_register_fw(uncore,
 						 rb.reg, rb.bit, 0,
 						 timeout_us, timeout_ms,
@@ -996,5 +1006,38 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 	 * transitions.
 	 */
 	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
-	mutex_unlock(&gt->tlb_invalidate_lock);
+}
+
+static bool tlb_seqno_passed(const struct intel_gt *gt, u32 seqno)
+{
+	u32 cur = intel_gt_tlb_seqno(gt);
+
+	/* Only skip if a *full* TLB invalidate barrier has passed */
+	return (s32)(cur - ALIGN(seqno, 2)) > 0;
+}
+
+void intel_gt_invalidate_tlb(struct intel_gt *gt, u32 seqno)
+{
+	intel_wakeref_t wakeref;
+
+	if (I915_SELFTEST_ONLY(gt->awake == -ENODEV))
+		return;
+
+	if (intel_gt_is_wedged(gt))
+		return;
+
+	if (tlb_seqno_passed(gt, seqno))
+		return;
+
+	with_intel_gt_pm_if_awake(gt, wakeref) {
+		mutex_lock(&gt->tlb.invalidate_lock);
+		if (tlb_seqno_passed(gt, seqno))
+			goto unlock;
+
+		mmio_invalidate_full(gt);
+
+		write_seqcount_invalidate(&gt->tlb.seqno);
+unlock:
+		mutex_unlock(&gt->tlb.invalidate_lock);
+	}
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 82d6f248d876..40b06adf509a 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -101,6 +101,16 @@ void intel_gt_info_print(const struct intel_gt_info *info,
 
 void intel_gt_watchdog_work(struct work_struct *work);
 
-void intel_gt_invalidate_tlbs(struct intel_gt *gt);
+static inline u32 intel_gt_tlb_seqno(const struct intel_gt *gt)
+{
+	return seqprop_sequence(&gt->tlb.seqno);
+}
+
+static inline u32 intel_gt_next_invalidate_tlb_full(const struct intel_gt *gt)
+{
+	return intel_gt_tlb_seqno(gt) | 1;
+}
+
+void intel_gt_invalidate_tlb(struct intel_gt *gt, u32 seqno);
 
 #endif /* __INTEL_GT_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
index bc898df7a48c..a334787a4939 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
@@ -55,6 +55,9 @@ static inline void intel_gt_pm_might_put(struct intel_gt *gt)
 	for (tmp = 1, intel_gt_pm_get(gt); tmp; \
 	     intel_gt_pm_put(gt), tmp = 0)
 
+#define with_intel_gt_pm_if_awake(gt, wf) \
+	for (wf = intel_gt_pm_get_if_awake(gt); wf; intel_gt_pm_put_async(gt), wf = 0)
+
 static inline int intel_gt_pm_wait_for_idle(struct intel_gt *gt)
 {
 	return intel_wakeref_wait_for_idle(&gt->wakeref);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index df708802889d..3804a583382b 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -11,6 +11,7 @@
 #include <linux/llist.h>
 #include <linux/mutex.h>
 #include <linux/notifier.h>
+#include <linux/seqlock.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 #include <linux/workqueue.h>
@@ -83,7 +84,22 @@ struct intel_gt {
 	struct intel_uc uc;
 	struct intel_gsc gsc;
 
-	struct mutex tlb_invalidate_lock;
+	struct {
+		/* Serialize global tlb invalidations */
+		struct mutex invalidate_lock;
+
+		/*
+		 * Batch TLB invalidations
+		 *
+		 * After unbinding the PTE, we need to ensure the TLB
+		 * are invalidated prior to releasing the physical pages.
+		 * But we only need one such invalidation for all unbinds,
+		 * so we track how many TLB invalidations have been
+		 * performed since unbind the PTE and only emit an extra
+		 * invalidate if no full barrier has been passed.
+		 */
+		seqcount_mutex_t seqno;
+	} tlb;
 
 	struct i915_wa_list wa_list;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c
index 2c35324b5f68..2b10b96b17b5 100644
--- a/drivers/gpu/drm/i915/gt/intel_migrate.c
+++ b/drivers/gpu/drm/i915/gt/intel_migrate.c
@@ -708,7 +708,7 @@ intel_context_migrate_copy(struct intel_context *ce,
 	u8 src_access, dst_access;
 	struct i915_request *rq;
 	int src_sz, dst_sz;
-	bool ccs_is_src;
+	bool ccs_is_src, overwrite_ccs;
 	int err;
 
 	GEM_BUG_ON(ce->vm != ce->engine->gt->migrate.context->vm);
@@ -749,6 +749,8 @@ intel_context_migrate_copy(struct intel_context *ce,
 			get_ccs_sg_sgt(&it_ccs, bytes_to_cpy);
 	}
 
+	overwrite_ccs = HAS_FLAT_CCS(i915) && !ccs_bytes_to_cpy && dst_is_lmem;
+
 	src_offset = 0;
 	dst_offset = CHUNK_SZ;
 	if (HAS_64K_PAGES(ce->engine->i915)) {
@@ -852,6 +854,25 @@ intel_context_migrate_copy(struct intel_context *ce,
 			if (err)
 				goto out_rq;
 			ccs_bytes_to_cpy -= ccs_sz;
+		} else if (overwrite_ccs) {
+			err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
+			if (err)
+				goto out_rq;
+
+			/*
+			 * While we can't always restore/manage the CCS state,
+			 * we still need to ensure we don't leak the CCS state
+			 * from the previous user, so make sure we overwrite it
+			 * with something.
+			 */
+			err = emit_copy_ccs(rq, dst_offset, INDIRECT_ACCESS,
+					    dst_offset, DIRECT_ACCESS, len);
+			if (err)
+				goto out_rq;
+
+			err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
+			if (err)
+				goto out_rq;
 		}
 
 		/* Arbitration is re-enabled between requests. */
diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
index d8b94d638559..6ee8d1127016 100644
--- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
@@ -206,8 +206,12 @@ void ppgtt_bind_vma(struct i915_address_space *vm,
 void ppgtt_unbind_vma(struct i915_address_space *vm,
 		      struct i915_vma_resource *vma_res)
 {
-	if (vma_res->allocated)
-		vm->clear_range(vm, vma_res->start, vma_res->vma_size);
+	if (!vma_res->allocated)
+		return;
+
+	vm->clear_range(vm, vma_res->start, vma_res->vma_size);
+	if (vma_res->tlb)
+		vma_invalidate_tlb(vm, vma_res->tlb);
 }
 
 static unsigned long pd_count(u64 size, int shift)
diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c
index 6e90032e12e9..aa6aed837194 100644
--- a/drivers/gpu/drm/i915/gt/intel_region_lmem.c
+++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.c
@@ -15,6 +15,7 @@
 #include "gt/intel_gt_mcr.h"
 #include "gt/intel_gt_regs.h"
 
+#ifdef CONFIG_64BIT
 static void _release_bars(struct pci_dev *pdev)
 {
 	int resno;
@@ -111,6 +112,9 @@ static void i915_resize_lmem_bar(struct drm_i915_private *i915, resource_size_t
 	pci_assign_unassigned_bus_resources(pdev->bus);
 	pci_write_config_dword(pdev, PCI_COMMAND, pci_cmd);
 }
+#else
+static void i915_resize_lmem_bar(struct drm_i915_private *i915, resource_size_t lmem_size) {}
+#endif
 
 static int
 region_lmem_release(struct intel_memory_region *mem)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d25647be25d1..086bbe8945d6 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -247,7 +247,7 @@ struct i915_gem_mm {
 	 * List of objects which are pending destruction.
 	 */
 	struct llist_head free_list;
-	struct delayed_work free_work;
+	struct work_struct free_work;
 	/**
 	 * Count of objects pending destructions. Used to skip needlessly
 	 * waiting on an RCU barrier if no objects are waiting to be freed.
@@ -1378,7 +1378,7 @@ static inline void i915_gem_drain_freed_objects(struct drm_i915_private *i915)
 	 * armed the work again.
 	 */
 	while (atomic_read(&i915->mm.free_count)) {
-		flush_delayed_work(&i915->mm.free_work);
+		flush_work(&i915->mm.free_work);
 		flush_delayed_work(&i915->bdev.wq);
 		rcu_barrier();
 	}
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index ef3b04c7e153..260371716490 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -538,8 +538,6 @@ int i915_vma_bind(struct i915_vma *vma,
 				   bind_flags);
 	}
 
-	set_bit(I915_BO_WAS_BOUND_BIT, &vma->obj->flags);
-
 	atomic_or(bind_flags, &vma->flags);
 	return 0;
 }
@@ -1310,6 +1308,19 @@ err_unpin:
 	return err;
 }
 
+void vma_invalidate_tlb(struct i915_address_space *vm, u32 *tlb)
+{
+	/*
+	 * Before we release the pages that were bound by this vma, we
+	 * must invalidate all the TLBs that may still have a reference
+	 * back to our physical address. It only needs to be done once,
+	 * so after updating the PTE to point away from the pages, record
+	 * the most recent TLB invalidation seqno, and if we have not yet
+	 * flushed the TLBs upon release, perform a full invalidation.
+	 */
+	WRITE_ONCE(*tlb, intel_gt_next_invalidate_tlb_full(vm->gt));
+}
+
 static void __vma_put_pages(struct i915_vma *vma, unsigned int count)
 {
 	/* We allocate under vma_get_pages, so beware the shrinker */
@@ -1941,7 +1952,12 @@ struct dma_fence *__i915_vma_evict(struct i915_vma *vma, bool async)
 		vma->vm->skip_pte_rewrite;
 	trace_i915_vma_unbind(vma);
 
-	unbind_fence = i915_vma_resource_unbind(vma_res);
+	if (async)
+		unbind_fence = i915_vma_resource_unbind(vma_res,
+							&vma->obj->mm.tlb);
+	else
+		unbind_fence = i915_vma_resource_unbind(vma_res, NULL);
+
 	vma->resource = NULL;
 
 	atomic_and(~(I915_VMA_BIND_MASK | I915_VMA_ERROR | I915_VMA_GGTT_WRITE),
@@ -1949,10 +1965,13 @@ struct dma_fence *__i915_vma_evict(struct i915_vma *vma, bool async)
 
 	i915_vma_detach(vma);
 
-	if (!async && unbind_fence) {
-		dma_fence_wait(unbind_fence, false);
-		dma_fence_put(unbind_fence);
-		unbind_fence = NULL;
+	if (!async) {
+		if (unbind_fence) {
+			dma_fence_wait(unbind_fence, false);
+			dma_fence_put(unbind_fence);
+			unbind_fence = NULL;
+		}
+		vma_invalidate_tlb(vma->vm, &vma->obj->mm.tlb);
 	}
 
 	/*
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 88ca0bd9c900..33a58f605d75 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -213,6 +213,7 @@ bool i915_vma_misplaced(const struct i915_vma *vma,
 			u64 size, u64 alignment, u64 flags);
 void __i915_vma_set_map_and_fenceable(struct i915_vma *vma);
 void i915_vma_revoke_mmap(struct i915_vma *vma);
+void vma_invalidate_tlb(struct i915_address_space *vm, u32 *tlb);
 struct dma_fence *__i915_vma_evict(struct i915_vma *vma, bool async);
 int __i915_vma_unbind(struct i915_vma *vma);
 int __must_check i915_vma_unbind(struct i915_vma *vma);
diff --git a/drivers/gpu/drm/i915/i915_vma_resource.c b/drivers/gpu/drm/i915/i915_vma_resource.c
index 27c55027387a..5a67995ea5fe 100644
--- a/drivers/gpu/drm/i915/i915_vma_resource.c
+++ b/drivers/gpu/drm/i915/i915_vma_resource.c
@@ -223,10 +223,13 @@ i915_vma_resource_fence_notify(struct i915_sw_fence *fence,
  * Return: A refcounted pointer to a dma-fence that signals when unbinding is
  * complete.
  */
-struct dma_fence *i915_vma_resource_unbind(struct i915_vma_resource *vma_res)
+struct dma_fence *i915_vma_resource_unbind(struct i915_vma_resource *vma_res,
+					   u32 *tlb)
 {
 	struct i915_address_space *vm = vma_res->vm;
 
+	vma_res->tlb = tlb;
+
 	/* Reference for the sw fence */
 	i915_vma_resource_get(vma_res);
 
diff --git a/drivers/gpu/drm/i915/i915_vma_resource.h b/drivers/gpu/drm/i915/i915_vma_resource.h
index 5d8427caa2ba..06923d1816e7 100644
--- a/drivers/gpu/drm/i915/i915_vma_resource.h
+++ b/drivers/gpu/drm/i915/i915_vma_resource.h
@@ -67,6 +67,7 @@ struct i915_page_sizes {
  * taken when the unbind is scheduled.
  * @skip_pte_rewrite: During ggtt suspend and vm takedown pte rewriting
  * needs to be skipped for unbind.
+ * @tlb: pointer for obj->mm.tlb, if async unbind. Otherwise, NULL
  *
  * The lifetime of a struct i915_vma_resource is from a binding request to
  * the actual possible asynchronous unbind has completed.
@@ -119,6 +120,8 @@ struct i915_vma_resource {
 	bool immediate_unbind:1;
 	bool needs_wakeref:1;
 	bool skip_pte_rewrite:1;
+
+	u32 *tlb;
 };
 
 bool i915_vma_resource_hold(struct i915_vma_resource *vma_res,
@@ -131,7 +134,8 @@ struct i915_vma_resource *i915_vma_resource_alloc(void);
 
 void i915_vma_resource_free(struct i915_vma_resource *vma_res);
 
-struct dma_fence *i915_vma_resource_unbind(struct i915_vma_resource *vma_res);
+struct dma_fence *i915_vma_resource_unbind(struct i915_vma_resource *vma_res,
+					   u32 *tlb);
 
 void __i915_vma_resource_init(struct i915_vma_resource *vma_res);
 
diff --git a/drivers/gpu/drm/imx/dcss/dcss-kms.c b/drivers/gpu/drm/imx/dcss/dcss-kms.c
index 9b84df34a6a1..8cf3352d8858 100644
--- a/drivers/gpu/drm/imx/dcss/dcss-kms.c
+++ b/drivers/gpu/drm/imx/dcss/dcss-kms.c
@@ -142,8 +142,6 @@ struct dcss_kms_dev *dcss_kms_attach(struct dcss_dev *dcss)
 
 	drm_kms_helper_poll_init(drm);
 
-	drm_bridge_connector_enable_hpd(kms->connector);
-
 	ret = drm_dev_register(drm, 0);
 	if (ret)
 		goto cleanup_crtc;
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index 1b70938cfd2c..bd4ca11d3ff5 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -115,8 +115,11 @@ static bool meson_vpu_has_available_connectors(struct device *dev)
 	for_each_endpoint_of_node(dev->of_node, ep) {
 		/* If the endpoint node exists, consider it enabled */
 		remote = of_graph_get_remote_port(ep);
-		if (remote)
+		if (remote) {
+			of_node_put(remote);
+			of_node_put(ep);
 			return true;
+		}
 	}
 
 	return false;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 568182e68dd7..d8cf71fb0512 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -2605,6 +2605,27 @@ nv172_chipset = {
 };
 
 static const struct nvkm_device_chip
+nv173_chipset = {
+	.name = "GA103",
+	.bar      = { 0x00000001, tu102_bar_new },
+	.bios     = { 0x00000001, nvkm_bios_new },
+	.devinit  = { 0x00000001, ga100_devinit_new },
+	.fb       = { 0x00000001, ga102_fb_new },
+	.gpio     = { 0x00000001, ga102_gpio_new },
+	.i2c      = { 0x00000001, gm200_i2c_new },
+	.imem     = { 0x00000001, nv50_instmem_new },
+	.mc       = { 0x00000001, ga100_mc_new },
+	.mmu      = { 0x00000001, tu102_mmu_new },
+	.pci      = { 0x00000001, gp100_pci_new },
+	.privring = { 0x00000001, gm200_privring_new },
+	.timer    = { 0x00000001, gk20a_timer_new },
+	.top      = { 0x00000001, ga100_top_new },
+	.disp     = { 0x00000001, ga102_disp_new },
+	.dma      = { 0x00000001, gv100_dma_new },
+	.fifo     = { 0x00000001, ga102_fifo_new },
+};
+
+static const struct nvkm_device_chip
 nv174_chipset = {
 	.name = "GA104",
 	.bar      = { 0x00000001, tu102_bar_new },
@@ -3067,6 +3088,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		case 0x167: device->chip = &nv167_chipset; break;
 		case 0x168: device->chip = &nv168_chipset; break;
 		case 0x172: device->chip = &nv172_chipset; break;
+		case 0x173: device->chip = &nv173_chipset; break;
 		case 0x174: device->chip = &nv174_chipset; break;
 		case 0x176: device->chip = &nv176_chipset; break;
 		case 0x177: device->chip = &nv177_chipset; break;
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index b4dfa166eccd..34234a144e87 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -531,7 +531,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 				    struct drm_display_mode *mode)
 {
 	struct mipi_dsi_device *device = dsi->device;
-	unsigned int Bpp = mipi_dsi_pixel_format_to_bpp(device->format) / 8;
+	int Bpp = mipi_dsi_pixel_format_to_bpp(device->format) / 8;
 	u16 hbp = 0, hfp = 0, hsa = 0, hblk = 0, vblk = 0;
 	u32 basic_ctl = 0;
 	size_t bytes;
@@ -555,7 +555,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 		 * (4 bytes). Its minimal size is therefore 10 bytes
 		 */
 #define HSA_PACKET_OVERHEAD	10
-		hsa = max((unsigned int)HSA_PACKET_OVERHEAD,
+		hsa = max(HSA_PACKET_OVERHEAD,
 			  (mode->hsync_end - mode->hsync_start) * Bpp - HSA_PACKET_OVERHEAD);
 
 		/*
@@ -564,7 +564,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 		 * therefore 6 bytes
 		 */
 #define HBP_PACKET_OVERHEAD	6
-		hbp = max((unsigned int)HBP_PACKET_OVERHEAD,
+		hbp = max(HBP_PACKET_OVERHEAD,
 			  (mode->htotal - mode->hsync_end) * Bpp - HBP_PACKET_OVERHEAD);
 
 		/*
@@ -574,7 +574,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 		 * 16 bytes
 		 */
 #define HFP_PACKET_OVERHEAD	16
-		hfp = max((unsigned int)HFP_PACKET_OVERHEAD,
+		hfp = max(HFP_PACKET_OVERHEAD,
 			  (mode->hsync_start - mode->hdisplay) * Bpp - HFP_PACKET_OVERHEAD);
 
 		/*
@@ -583,7 +583,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 		 * bytes). Its minimal size is therefore 10 bytes.
 		 */
 #define HBLK_PACKET_OVERHEAD	10
-		hblk = max((unsigned int)HBLK_PACKET_OVERHEAD,
+		hblk = max(HBLK_PACKET_OVERHEAD,
 			   (mode->htotal - (mode->hsync_end - mode->hsync_start)) * Bpp -
 			   HBLK_PACKET_OVERHEAD);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 0e210df65c30..97184c333526 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -912,7 +912,7 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 	/*
 	 * We might need to add a TTM.
 	 */
-	if (bo->resource->mem_type == TTM_PL_SYSTEM) {
+	if (!bo->resource || bo->resource->mem_type == TTM_PL_SYSTEM) {
 		ret = ttm_tt_create(bo, true);
 		if (ret)
 			return ret;
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 2e2cd79d89eb..4218750d5a66 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -151,9 +151,9 @@ static DEFINE_IDA(hwmon_ida);
  * between hwmon and thermal_sys modules.
  */
 #ifdef CONFIG_THERMAL_OF
-static int hwmon_thermal_get_temp(void *data, int *temp)
+static int hwmon_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct hwmon_thermal_data *tdata = data;
+	struct hwmon_thermal_data *tdata = tz->devdata;
 	struct hwmon_device *hwdev = to_hwmon_device(tdata->dev);
 	int ret;
 	long t;
@@ -168,9 +168,9 @@ static int hwmon_thermal_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static int hwmon_thermal_set_trips(void *data, int low, int high)
+static int hwmon_thermal_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	struct hwmon_thermal_data *tdata = data;
+	struct hwmon_thermal_data *tdata = tz->devdata;
 	struct hwmon_device *hwdev = to_hwmon_device(tdata->dev);
 	const struct hwmon_chip_info *chip = hwdev->chip;
 	const struct hwmon_channel_info **info = chip->info;
@@ -203,7 +203,7 @@ static int hwmon_thermal_set_trips(void *data, int low, int high)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops hwmon_thermal_ops = {
+static const struct thermal_zone_device_ops hwmon_thermal_ops = {
 	.get_temp = hwmon_thermal_get_temp,
 	.set_trips = hwmon_thermal_set_trips,
 };
@@ -227,8 +227,8 @@ static int hwmon_thermal_add_sensor(struct device *dev, int index)
 	tdata->dev = dev;
 	tdata->index = index;
 
-	tzd = devm_thermal_zone_of_sensor_register(dev, index, tdata,
-						   &hwmon_thermal_ops);
+	tzd = devm_thermal_of_zone_register(dev, index, tdata,
+					    &hwmon_thermal_ops);
 	if (IS_ERR(tzd)) {
 		if (PTR_ERR(tzd) != -ENODEV)
 			return PTR_ERR(tzd);
diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c
index f10bac8860fc..5541d26e8623 100644
--- a/drivers/hwmon/pmbus/pmbus_core.c
+++ b/drivers/hwmon/pmbus/pmbus_core.c
@@ -1270,9 +1270,9 @@ struct pmbus_thermal_data {
 	struct pmbus_sensor *sensor;
 };
 
-static int pmbus_thermal_get_temp(void *data, int *temp)
+static int pmbus_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct pmbus_thermal_data *tdata = data;
+	struct pmbus_thermal_data *tdata = tz->devdata;
 	struct pmbus_sensor *sensor = tdata->sensor;
 	struct pmbus_data *pmbus_data = tdata->pmbus_data;
 	struct i2c_client *client = to_i2c_client(pmbus_data->dev);
@@ -1296,7 +1296,7 @@ static int pmbus_thermal_get_temp(void *data, int *temp)
 	return ret;
 }
 
-static const struct thermal_zone_of_device_ops pmbus_thermal_ops = {
+static const struct thermal_zone_device_ops pmbus_thermal_ops = {
 	.get_temp = pmbus_thermal_get_temp,
 };
 
@@ -1314,8 +1314,8 @@ static int pmbus_thermal_add_sensor(struct pmbus_data *pmbus_data,
 	tdata->sensor = sensor;
 	tdata->pmbus_data = pmbus_data;
 
-	tzd = devm_thermal_zone_of_sensor_register(dev, index, tdata,
-						   &pmbus_thermal_ops);
+	tzd = devm_thermal_of_zone_register(dev, index, tdata,
+					    &pmbus_thermal_ops);
 	/*
 	 * If CONFIG_THERMAL_OF is disabled, this returns -ENODEV,
 	 * so ignore that error but forward any other error.
diff --git a/drivers/hwmon/scpi-hwmon.c b/drivers/hwmon/scpi-hwmon.c
index 5187c6dd5a4f..4d75385f7d5e 100644
--- a/drivers/hwmon/scpi-hwmon.c
+++ b/drivers/hwmon/scpi-hwmon.c
@@ -62,9 +62,9 @@ static void scpi_scale_reading(u64 *value, struct sensor_data *sensor)
 	}
 }
 
-static int scpi_read_temp(void *dev, int *temp)
+static int scpi_read_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct scpi_thermal_zone *zone = dev;
+	struct scpi_thermal_zone *zone = tz->devdata;
 	struct scpi_sensors *scpi_sensors = zone->scpi_sensors;
 	struct scpi_ops *scpi_ops = scpi_sensors->scpi_ops;
 	struct sensor_data *sensor = &scpi_sensors->data[zone->sensor_id];
@@ -121,7 +121,7 @@ scpi_show_label(struct device *dev, struct device_attribute *attr, char *buf)
 	return sprintf(buf, "%s\n", sensor->info.name);
 }
 
-static const struct thermal_zone_of_device_ops scpi_sensor_ops = {
+static const struct thermal_zone_device_ops scpi_sensor_ops = {
 	.get_temp = scpi_read_temp,
 };
 
@@ -275,10 +275,10 @@ static int scpi_hwmon_probe(struct platform_device *pdev)
 
 		zone->sensor_id = i;
 		zone->scpi_sensors = scpi_sensors;
-		z = devm_thermal_zone_of_sensor_register(dev,
-							 sensor->info.sensor_id,
-							 zone,
-							 &scpi_sensor_ops);
+		z = devm_thermal_of_zone_register(dev,
+						  sensor->info.sensor_id,
+						  zone,
+						  &scpi_sensor_ops);
 		/*
 		 * The call to thermal_zone_of_sensor_register returns
 		 * an error for sensors that are not associated with
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 78fb1a4274a6..e47fa3465671 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1572,9 +1572,7 @@ static int i2c_imx_remove(struct platform_device *pdev)
 	struct imx_i2c_struct *i2c_imx = platform_get_drvdata(pdev);
 	int irq, ret;
 
-	ret = pm_runtime_resume_and_get(&pdev->dev);
-	if (ret < 0)
-		return ret;
+	ret = pm_runtime_get_sync(&pdev->dev);
 
 	hrtimer_cancel(&i2c_imx->slave_timer);
 
@@ -1585,17 +1583,21 @@ static int i2c_imx_remove(struct platform_device *pdev)
 	if (i2c_imx->dma)
 		i2c_imx_dma_free(i2c_imx);
 
-	/* setup chip registers to defaults */
-	imx_i2c_write_reg(0, i2c_imx, IMX_I2C_IADR);
-	imx_i2c_write_reg(0, i2c_imx, IMX_I2C_IFDR);
-	imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2CR);
-	imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2SR);
+	if (ret == 0) {
+		/* setup chip registers to defaults */
+		imx_i2c_write_reg(0, i2c_imx, IMX_I2C_IADR);
+		imx_i2c_write_reg(0, i2c_imx, IMX_I2C_IFDR);
+		imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2CR);
+		imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2SR);
+		clk_disable(i2c_imx->clk);
+	}
 
 	clk_notifier_unregister(i2c_imx->clk, &i2c_imx->clk_change_nb);
 	irq = platform_get_irq(pdev, 0);
 	if (irq >= 0)
 		free_irq(irq, i2c_imx);
-	clk_disable_unprepare(i2c_imx->clk);
+
+	clk_unprepare(i2c_imx->clk);
 
 	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
diff --git a/drivers/i2c/busses/i2c-scmi.c b/drivers/i2c/busses/i2c-scmi.c
index 79798fc7462a..6746aa46d96c 100644
--- a/drivers/i2c/busses/i2c-scmi.c
+++ b/drivers/i2c/busses/i2c-scmi.c
@@ -30,7 +30,7 @@ struct acpi_smbus_cmi {
 	u8 cap_info:1;
 	u8 cap_read:1;
 	u8 cap_write:1;
-	const struct smbus_methods_t *methods;
+	struct smbus_methods_t *methods;
 };
 
 static const struct smbus_methods_t smbus_methods = {
@@ -361,6 +361,7 @@ static acpi_status acpi_smbus_cmi_query_methods(acpi_handle handle, u32 level,
 static int acpi_smbus_cmi_add(struct acpi_device *device)
 {
 	struct acpi_smbus_cmi *smbus_cmi;
+	const struct acpi_device_id *id;
 	int ret;
 
 	smbus_cmi = kzalloc(sizeof(struct acpi_smbus_cmi), GFP_KERNEL);
@@ -368,7 +369,6 @@ static int acpi_smbus_cmi_add(struct acpi_device *device)
 		return -ENOMEM;
 
 	smbus_cmi->handle = device->handle;
-	smbus_cmi->methods = device_get_match_data(&device->dev);
 	strcpy(acpi_device_name(device), ACPI_SMBUS_HC_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_SMBUS_HC_CLASS);
 	device->driver_data = smbus_cmi;
@@ -376,6 +376,11 @@ static int acpi_smbus_cmi_add(struct acpi_device *device)
 	smbus_cmi->cap_read = 0;
 	smbus_cmi->cap_write = 0;
 
+	for (id = acpi_smbus_cmi_ids; id->id[0]; id++)
+		if (!strcmp(id->id, acpi_device_hid(device)))
+			smbus_cmi->methods =
+				(struct smbus_methods_t *) id->driver_data;
+
 	acpi_walk_namespace(ACPI_TYPE_METHOD, smbus_cmi->handle, 1,
 			    acpi_smbus_cmi_query_methods, NULL, smbus_cmi, NULL);
 
diff --git a/drivers/iio/adc/sun4i-gpadc-iio.c b/drivers/iio/adc/sun4i-gpadc-iio.c
index 2d393a4dfff6..a6ade70dedf8 100644
--- a/drivers/iio/adc/sun4i-gpadc-iio.c
+++ b/drivers/iio/adc/sun4i-gpadc-iio.c
@@ -412,9 +412,9 @@ static int sun4i_gpadc_runtime_resume(struct device *dev)
 	return 0;
 }
 
-static int sun4i_gpadc_get_temp(void *data, int *temp)
+static int sun4i_gpadc_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct sun4i_gpadc_iio *info = data;
+	struct sun4i_gpadc_iio *info = tz->devdata;
 	int val, scale, offset;
 
 	if (sun4i_gpadc_temp_read(info->indio_dev, &val))
@@ -428,7 +428,7 @@ static int sun4i_gpadc_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops sun4i_ts_tz_ops = {
+static const struct thermal_zone_device_ops sun4i_ts_tz_ops = {
 	.get_temp = &sun4i_gpadc_get_temp,
 };
 
@@ -637,9 +637,9 @@ static int sun4i_gpadc_probe(struct platform_device *pdev)
 	pm_runtime_enable(&pdev->dev);
 
 	if (IS_ENABLED(CONFIG_THERMAL_OF)) {
-		info->tzd = thermal_zone_of_sensor_register(info->sensor_device,
-							    0, info,
-							    &sun4i_ts_tz_ops);
+		info->tzd = devm_thermal_of_zone_register(info->sensor_device,
+							  0, info,
+							  &sun4i_ts_tz_ops);
 		/*
 		 * Do not fail driver probing when failing to register in
 		 * thermal because no thermal DT node is found.
@@ -681,8 +681,6 @@ static int sun4i_gpadc_remove(struct platform_device *pdev)
 	if (!IS_ENABLED(CONFIG_THERMAL_OF))
 		return 0;
 
-	thermal_zone_of_sensor_unregister(info->sensor_device, info->tzd);
-
 	if (!info->no_irq)
 		iio_map_array_unregister(indio_dev);
 
diff --git a/drivers/infiniband/core/umem_dmabuf.c b/drivers/infiniband/core/umem_dmabuf.c
index fce80a4a5147..04c04e6d24c3 100644
--- a/drivers/infiniband/core/umem_dmabuf.c
+++ b/drivers/infiniband/core/umem_dmabuf.c
@@ -18,6 +18,7 @@ int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf)
 	struct scatterlist *sg;
 	unsigned long start, end, cur = 0;
 	unsigned int nmap = 0;
+	long ret;
 	int i;
 
 	dma_resv_assert_held(umem_dmabuf->attach->dmabuf->resv);
@@ -67,9 +68,14 @@ wait_fence:
 	 * may be not up-to-date. Wait for the exporter to finish
 	 * the migration.
 	 */
-	return dma_resv_wait_timeout(umem_dmabuf->attach->dmabuf->resv,
+	ret = dma_resv_wait_timeout(umem_dmabuf->attach->dmabuf->resv,
 				     DMA_RESV_USAGE_KERNEL,
 				     false, MAX_SCHEDULE_TIMEOUT);
+	if (ret < 0)
+		return ret;
+	if (ret == 0)
+		return -ETIMEDOUT;
+	return 0;
 }
 EXPORT_SYMBOL(ib_umem_dmabuf_map_pages);
 
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index c16017f6e8db..14392c942f49 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -2468,31 +2468,24 @@ static int accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
 			opt2 |= CCTRL_ECN_V(1);
 	}
 
-	skb_get(skb);
-	rpl = cplhdr(skb);
 	if (!is_t4(adapter_type)) {
-		BUILD_BUG_ON(sizeof(*rpl5) != roundup(sizeof(*rpl5), 16));
-		skb_trim(skb, sizeof(*rpl5));
-		rpl5 = (void *)rpl;
-		INIT_TP_WR(rpl5, ep->hwtid);
-	} else {
-		skb_trim(skb, sizeof(*rpl));
-		INIT_TP_WR(rpl, ep->hwtid);
-	}
-	OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL,
-						    ep->hwtid));
-
-	if (CHELSIO_CHIP_VERSION(adapter_type) > CHELSIO_T4) {
 		u32 isn = (prandom_u32() & ~7UL) - 1;
+
+		skb = get_skb(skb, roundup(sizeof(*rpl5), 16), GFP_KERNEL);
+		rpl5 = __skb_put_zero(skb, roundup(sizeof(*rpl5), 16));
+		rpl = (void *)rpl5;
+		INIT_TP_WR_CPL(rpl5, CPL_PASS_ACCEPT_RPL, ep->hwtid);
 		opt2 |= T5_OPT_2_VALID_F;
 		opt2 |= CONG_CNTRL_V(CONG_ALG_TAHOE);
 		opt2 |= T5_ISS_F;
-		rpl5 = (void *)rpl;
-		memset_after(rpl5, 0, iss);
 		if (peer2peer)
 			isn += 4;
 		rpl5->iss = cpu_to_be32(isn);
 		pr_debug("iss %u\n", be32_to_cpu(rpl5->iss));
+	} else {
+		skb = get_skb(skb, sizeof(*rpl), GFP_KERNEL);
+		rpl = __skb_put_zero(skb, sizeof(*rpl));
+		INIT_TP_WR_CPL(rpl, CPL_PASS_ACCEPT_RPL, ep->hwtid);
 	}
 
 	rpl->opt0 = cpu_to_be64(opt0);
diff --git a/drivers/infiniband/hw/erdma/erdma_qp.c b/drivers/infiniband/hw/erdma/erdma_qp.c
index 72f08171a28a..bc3ec22a62c5 100644
--- a/drivers/infiniband/hw/erdma/erdma_qp.c
+++ b/drivers/infiniband/hw/erdma/erdma_qp.c
@@ -407,7 +407,7 @@ static int erdma_push_one_sqe(struct erdma_qp *qp, u16 *pi,
 			     to_erdma_access_flags(reg_wr(send_wr)->access);
 		regmr_sge->addr = cpu_to_le64(mr->ibmr.iova);
 		regmr_sge->length = cpu_to_le32(mr->ibmr.length);
-		regmr_sge->stag = cpu_to_le32(mr->ibmr.lkey);
+		regmr_sge->stag = cpu_to_le32(reg_wr(send_wr)->key);
 		attrs = FIELD_PREP(ERDMA_SQE_MR_MODE_MASK, 0) |
 			FIELD_PREP(ERDMA_SQE_MR_ACCESS_MASK, mr->access) |
 			FIELD_PREP(ERDMA_SQE_MR_MTT_CNT_MASK,
diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.c b/drivers/infiniband/hw/erdma/erdma_verbs.c
index a7a3d42e2016..699bd3f59cd3 100644
--- a/drivers/infiniband/hw/erdma/erdma_verbs.c
+++ b/drivers/infiniband/hw/erdma/erdma_verbs.c
@@ -280,7 +280,7 @@ int erdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr,
 	attr->vendor_id = PCI_VENDOR_ID_ALIBABA;
 	attr->vendor_part_id = dev->pdev->device;
 	attr->hw_ver = dev->pdev->revision;
-	attr->max_qp = dev->attrs.max_qp;
+	attr->max_qp = dev->attrs.max_qp - 1;
 	attr->max_qp_wr = min(dev->attrs.max_send_wr, dev->attrs.max_recv_wr);
 	attr->max_qp_rd_atom = dev->attrs.max_ord;
 	attr->max_qp_init_rd_atom = dev->attrs.max_ird;
@@ -291,7 +291,7 @@ int erdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr,
 	attr->max_send_sge = dev->attrs.max_send_sge;
 	attr->max_recv_sge = dev->attrs.max_recv_sge;
 	attr->max_sge_rd = dev->attrs.max_sge_rd;
-	attr->max_cq = dev->attrs.max_cq;
+	attr->max_cq = dev->attrs.max_cq - 1;
 	attr->max_cqe = dev->attrs.max_cqe;
 	attr->max_mr = dev->attrs.max_mr;
 	attr->max_pd = dev->attrs.max_pd;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index a174a0eee8dc..fc94a1b25485 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2738,26 +2738,24 @@ static int set_has_smi_cap(struct mlx5_ib_dev *dev)
 	int err;
 	int port;
 
-	for (port = 1; port <= ARRAY_SIZE(dev->port_caps); port++) {
-		dev->port_caps[port - 1].has_smi = false;
-		if (MLX5_CAP_GEN(dev->mdev, port_type) ==
-		    MLX5_CAP_PORT_TYPE_IB) {
-			if (MLX5_CAP_GEN(dev->mdev, ib_virt)) {
-				err = mlx5_query_hca_vport_context(dev->mdev, 0,
-								   port, 0,
-								   &vport_ctx);
-				if (err) {
-					mlx5_ib_err(dev, "query_hca_vport_context for port=%d failed %d\n",
-						    port, err);
-					return err;
-				}
-				dev->port_caps[port - 1].has_smi =
-					vport_ctx.has_smi;
-			} else {
-				dev->port_caps[port - 1].has_smi = true;
-			}
+	if (MLX5_CAP_GEN(dev->mdev, port_type) != MLX5_CAP_PORT_TYPE_IB)
+		return 0;
+
+	for (port = 1; port <= dev->num_ports; port++) {
+		if (!MLX5_CAP_GEN(dev->mdev, ib_virt)) {
+			dev->port_caps[port - 1].has_smi = true;
+			continue;
 		}
+		err = mlx5_query_hca_vport_context(dev->mdev, 0, port, 0,
+						   &vport_ctx);
+		if (err) {
+			mlx5_ib_err(dev, "query_hca_vport_context for port=%d failed %d\n",
+				    port, err);
+			return err;
+		}
+		dev->port_caps[port - 1].has_smi = vport_ctx.has_smi;
 	}
+
 	return 0;
 }
 
diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c
index bd5f3b5e1727..7b83f48f60c5 100644
--- a/drivers/infiniband/ulp/iser/iser_initiator.c
+++ b/drivers/infiniband/ulp/iser/iser_initiator.c
@@ -537,6 +537,7 @@ void iser_login_rsp(struct ib_cq *cq, struct ib_wc *wc)
 	struct iscsi_hdr *hdr;
 	char *data;
 	int length;
+	bool full_feature_phase;
 
 	if (unlikely(wc->status != IB_WC_SUCCESS)) {
 		iser_err_comp(wc, "login_rsp");
@@ -550,6 +551,9 @@ void iser_login_rsp(struct ib_cq *cq, struct ib_wc *wc)
 	hdr = desc->rsp + sizeof(struct iser_ctrl);
 	data = desc->rsp + ISER_HEADERS_LEN;
 	length = wc->byte_len - ISER_HEADERS_LEN;
+	full_feature_phase = ((hdr->flags & ISCSI_FULL_FEATURE_PHASE) ==
+			      ISCSI_FULL_FEATURE_PHASE) &&
+			     (hdr->flags & ISCSI_FLAG_CMD_FINAL);
 
 	iser_dbg("op 0x%x itt 0x%x dlen %d\n", hdr->opcode,
 		 hdr->itt, length);
@@ -560,7 +564,8 @@ void iser_login_rsp(struct ib_cq *cq, struct ib_wc *wc)
 				      desc->rsp_dma, ISER_RX_LOGIN_SIZE,
 				      DMA_FROM_DEVICE);
 
-	if (iser_conn->iscsi_conn->session->discovery_sess)
+	if (!full_feature_phase ||
+	    iser_conn->iscsi_conn->session->discovery_sess)
 		return;
 
 	/* Post the first RX buffer that is skipped in iser_post_rx_bufs() */
diff --git a/drivers/input/touchscreen/sun4i-ts.c b/drivers/input/touchscreen/sun4i-ts.c
index 742a7e96c1b5..73eb8f80be6e 100644
--- a/drivers/input/touchscreen/sun4i-ts.c
+++ b/drivers/input/touchscreen/sun4i-ts.c
@@ -192,12 +192,12 @@ static int sun4i_get_temp(const struct sun4i_ts_data *ts, int *temp)
 	return 0;
 }
 
-static int sun4i_get_tz_temp(void *data, int *temp)
+static int sun4i_get_tz_temp(struct thermal_zone_device *tz, int *temp)
 {
-	return sun4i_get_temp(data, temp);
+	return sun4i_get_temp(tz->devdata, temp);
 }
 
-static const struct thermal_zone_of_device_ops sun4i_ts_tz_ops = {
+static const struct thermal_zone_device_ops sun4i_ts_tz_ops = {
 	.get_temp = sun4i_get_tz_temp,
 };
 
@@ -356,8 +356,8 @@ static int sun4i_ts_probe(struct platform_device *pdev)
 	if (IS_ERR(hwmon))
 		return PTR_ERR(hwmon);
 
-	thermal = devm_thermal_zone_of_sensor_register(ts->dev, 0, ts,
-						       &sun4i_ts_tz_ops);
+	thermal = devm_thermal_of_zone_register(ts->dev, 0, ts,
+						&sun4i_ts_tz_ops);
 	if (IS_ERR(thermal))
 		return PTR_ERR(thermal);
 
diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c
index 51bd66a45a11..e190bb8c225c 100644
--- a/drivers/iommu/hyperv-iommu.c
+++ b/drivers/iommu/hyperv-iommu.c
@@ -68,7 +68,6 @@ static int hyperv_irq_remapping_alloc(struct irq_domain *domain,
 {
 	struct irq_alloc_info *info = arg;
 	struct irq_data *irq_data;
-	struct irq_desc *desc;
 	int ret = 0;
 
 	if (!info || info->type != X86_IRQ_ALLOC_TYPE_IOAPIC || nr_irqs > 1)
@@ -90,8 +89,7 @@ static int hyperv_irq_remapping_alloc(struct irq_domain *domain,
 	 * Hypver-V IO APIC irq affinity should be in the scope of
 	 * ioapic_max_cpumask because no irq remapping support.
 	 */
-	desc = irq_data_to_desc(irq_data);
-	cpumask_copy(desc->irq_common_data.affinity, &ioapic_max_cpumask);
+	irq_data_update_affinity(irq_data, &ioapic_max_cpumask);
 
 	return 0;
 }
diff --git a/drivers/irqchip/irq-loongarch-cpu.c b/drivers/irqchip/irq-loongarch-cpu.c
index 327f3ab62c03..741612ba6a52 100644
--- a/drivers/irqchip/irq-loongarch-cpu.c
+++ b/drivers/irqchip/irq-loongarch-cpu.c
@@ -129,7 +129,7 @@ static int __init cpuintc_acpi_init(union acpi_subtable_headers *header,
 	clear_csr_ecfg(ECFG0_IM);
 	clear_csr_estat(ESTATF_IP);
 
-	cpuintc_handle = irq_domain_alloc_fwnode(NULL);
+	cpuintc_handle = irq_domain_alloc_named_fwnode("CPUINTC");
 	irq_domain = irq_domain_create_linear(cpuintc_handle, EXCCODE_INT_NUM,
 					&loongarch_cpu_intc_irq_domain_ops, NULL);
 
diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c
index 80d8ca6f2d46..16e9af8d8b1e 100644
--- a/drivers/irqchip/irq-loongson-eiointc.c
+++ b/drivers/irqchip/irq-loongson-eiointc.c
@@ -111,11 +111,15 @@ static int eiointc_set_irq_affinity(struct irq_data *d, const struct cpumask *af
 	regaddr = EIOINTC_REG_ENABLE + ((vector >> 5) << 2);
 
 	/* Mask target vector */
-	csr_any_send(regaddr, EIOINTC_ALL_ENABLE & (~BIT(vector & 0x1F)), 0x0, 0);
+	csr_any_send(regaddr, EIOINTC_ALL_ENABLE & (~BIT(vector & 0x1F)),
+			0x0, priv->node * CORES_PER_EIO_NODE);
+
 	/* Set route for target vector */
 	eiointc_set_irq_route(vector, cpu, priv->node, &priv->node_map);
+
 	/* Unmask target vector */
-	csr_any_send(regaddr, EIOINTC_ALL_ENABLE, 0x0, 0);
+	csr_any_send(regaddr, EIOINTC_ALL_ENABLE,
+			0x0, priv->node * CORES_PER_EIO_NODE);
 
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 
@@ -286,7 +290,7 @@ static void acpi_set_vec_parent(int node, struct irq_domain *parent, struct acpi
 	}
 }
 
-struct irq_domain *acpi_get_vec_parent(int node, struct acpi_vector_group *vec_group)
+static struct irq_domain *acpi_get_vec_parent(int node, struct acpi_vector_group *vec_group)
 {
 	int i;
 
@@ -344,7 +348,8 @@ int __init eiointc_acpi_init(struct irq_domain *parent,
 	if (!priv)
 		return -ENOMEM;
 
-	priv->domain_handle = irq_domain_alloc_fwnode((phys_addr_t *)acpi_eiointc);
+	priv->domain_handle = irq_domain_alloc_named_id_fwnode("EIOPIC",
+							       acpi_eiointc->node);
 	if (!priv->domain_handle) {
 		pr_err("Unable to allocate domain handle\n");
 		goto out_free_priv;
diff --git a/drivers/irqchip/irq-loongson-liointc.c b/drivers/irqchip/irq-loongson-liointc.c
index c4f3c886ad61..0da8716f8f24 100644
--- a/drivers/irqchip/irq-loongson-liointc.c
+++ b/drivers/irqchip/irq-loongson-liointc.c
@@ -207,7 +207,7 @@ static int liointc_init(phys_addr_t addr, unsigned long size, int revision,
 					"reg-names", core_reg_names[i]);
 
 			if (index < 0)
-				return -EINVAL;
+				goto out_iounmap;
 
 			priv->core_isr[i] = of_iomap(node, index);
 		}
@@ -360,7 +360,7 @@ int __init liointc_acpi_init(struct irq_domain *parent, struct acpi_madt_lio_pic
 	parent_irq[0] = irq_create_mapping(parent, acpi_liointc->cascade[0]);
 	parent_irq[1] = irq_create_mapping(parent, acpi_liointc->cascade[1]);
 
-	domain_handle = irq_domain_alloc_fwnode((phys_addr_t *)acpi_liointc);
+	domain_handle = irq_domain_alloc_fwnode(&acpi_liointc->address);
 	if (!domain_handle) {
 		pr_err("Unable to allocate domain handle\n");
 		return -ENOMEM;
diff --git a/drivers/irqchip/irq-loongson-pch-msi.c b/drivers/irqchip/irq-loongson-pch-msi.c
index d0e8551bebfa..a72ede90ffc6 100644
--- a/drivers/irqchip/irq-loongson-pch-msi.c
+++ b/drivers/irqchip/irq-loongson-pch-msi.c
@@ -282,7 +282,7 @@ int __init pch_msi_acpi_init(struct irq_domain *parent,
 	int ret;
 	struct fwnode_handle *domain_handle;
 
-	domain_handle = irq_domain_alloc_fwnode((phys_addr_t *)acpi_pchmsi);
+	domain_handle = irq_domain_alloc_fwnode(&acpi_pchmsi->msg_address);
 	ret = pch_msi_init(acpi_pchmsi->msg_address, acpi_pchmsi->start,
 				acpi_pchmsi->count, parent, domain_handle);
 	if (ret < 0)
diff --git a/drivers/irqchip/irq-loongson-pch-pic.c b/drivers/irqchip/irq-loongson-pch-pic.c
index b6f1392964b1..c01b9c257005 100644
--- a/drivers/irqchip/irq-loongson-pch-pic.c
+++ b/drivers/irqchip/irq-loongson-pch-pic.c
@@ -48,25 +48,6 @@ static struct pch_pic *pch_pic_priv[MAX_IO_PICS];
 
 struct fwnode_handle *pch_pic_handle[MAX_IO_PICS];
 
-int find_pch_pic(u32 gsi)
-{
-	int i;
-
-	/* Find the PCH_PIC that manages this GSI. */
-	for (i = 0; i < MAX_IO_PICS; i++) {
-		struct pch_pic *priv = pch_pic_priv[i];
-
-		if (!priv)
-			return -1;
-
-		if (gsi >= priv->gsi_base && gsi < (priv->gsi_base + priv->vec_count))
-			return i;
-	}
-
-	pr_err("ERROR: Unable to locate PCH_PIC for GSI %d\n", gsi);
-	return -1;
-}
-
 static void pch_pic_bitset(struct pch_pic *priv, int offset, int bit)
 {
 	u32 reg;
@@ -325,6 +306,25 @@ IRQCHIP_DECLARE(pch_pic, "loongson,pch-pic-1.0", pch_pic_of_init);
 #endif
 
 #ifdef CONFIG_ACPI
+int find_pch_pic(u32 gsi)
+{
+	int i;
+
+	/* Find the PCH_PIC that manages this GSI. */
+	for (i = 0; i < MAX_IO_PICS; i++) {
+		struct pch_pic *priv = pch_pic_priv[i];
+
+		if (!priv)
+			return -1;
+
+		if (gsi >= priv->gsi_base && gsi < (priv->gsi_base + priv->vec_count))
+			return i;
+	}
+
+	pr_err("ERROR: Unable to locate PCH_PIC for GSI %d\n", gsi);
+	return -1;
+}
+
 static int __init
 pch_lpc_parse_madt(union acpi_subtable_headers *header,
 		       const unsigned long end)
@@ -349,7 +349,7 @@ int __init pch_pic_acpi_init(struct irq_domain *parent,
 
 	vec_base = acpi_pchpic->gsi_base - GSI_MIN_PCH_IRQ;
 
-	domain_handle = irq_domain_alloc_fwnode((phys_addr_t *)acpi_pchpic);
+	domain_handle = irq_domain_alloc_fwnode(&acpi_pchpic->address);
 	if (!domain_handle) {
 		pr_err("Unable to allocate domain handle\n");
 		return -ENOMEM;
diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c
index 2f08d442e557..fc462995cf94 100644
--- a/drivers/mmc/host/meson-gx-mmc.c
+++ b/drivers/mmc/host/meson-gx-mmc.c
@@ -1172,8 +1172,10 @@ static int meson_mmc_probe(struct platform_device *pdev)
 	}
 
 	ret = device_reset_optional(&pdev->dev);
-	if (ret)
-		return dev_err_probe(&pdev->dev, ret, "device reset failed\n");
+	if (ret) {
+		dev_err_probe(&pdev->dev, ret, "device reset failed\n");
+		goto free_host;
+	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	host->regs = devm_ioremap_resource(&pdev->dev, res);
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 4ff73d1883de..69d78604d1fc 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -2446,6 +2446,9 @@ static void msdc_cqe_disable(struct mmc_host *mmc, bool recovery)
 	/* disable busy check */
 	sdr_clr_bits(host->base + MSDC_PATCH_BIT1, MSDC_PB1_BUSY_CHECK_SEL);
 
+	val = readl(host->base + MSDC_INT);
+	writel(val, host->base + MSDC_INT);
+
 	if (recovery) {
 		sdr_set_field(host->base + MSDC_DMA_CTRL,
 			      MSDC_DMA_CTRL_STOP, 1);
@@ -2932,11 +2935,14 @@ static int __maybe_unused msdc_suspend(struct device *dev)
 	struct mmc_host *mmc = dev_get_drvdata(dev);
 	struct msdc_host *host = mmc_priv(mmc);
 	int ret;
+	u32 val;
 
 	if (mmc->caps2 & MMC_CAP2_CQE) {
 		ret = cqhci_suspend(mmc);
 		if (ret)
 			return ret;
+		val = readl(host->base + MSDC_INT);
+		writel(val, host->base + MSDC_INT);
 	}
 
 	/*
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index 0db9490dc659..e4003f6058eb 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -648,7 +648,7 @@ static int pxamci_probe(struct platform_device *pdev)
 
 	ret = pxamci_of_init(pdev, mmc);
 	if (ret)
-		return ret;
+		goto out;
 
 	host = mmc_priv(mmc);
 	host->mmc = mmc;
@@ -672,7 +672,7 @@ static int pxamci_probe(struct platform_device *pdev)
 
 	ret = pxamci_init_ocr(host);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	mmc->caps = 0;
 	host->cmdat = 0;
diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c
index 4e904850973c..a7343d4bc50e 100644
--- a/drivers/mmc/host/sdhci-of-dwcmshc.c
+++ b/drivers/mmc/host/sdhci-of-dwcmshc.c
@@ -349,6 +349,15 @@ static const struct sdhci_pltfm_data sdhci_dwcmshc_pdata = {
 	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
 };
 
+#ifdef CONFIG_ACPI
+static const struct sdhci_pltfm_data sdhci_dwcmshc_bf3_pdata = {
+	.ops = &sdhci_dwcmshc_ops,
+	.quirks = SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+		   SDHCI_QUIRK2_ACMD23_BROKEN,
+};
+#endif
+
 static const struct sdhci_pltfm_data sdhci_dwcmshc_rk35xx_pdata = {
 	.ops = &sdhci_dwcmshc_rk35xx_ops,
 	.quirks = SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN |
@@ -431,7 +440,10 @@ MODULE_DEVICE_TABLE(of, sdhci_dwcmshc_dt_ids);
 
 #ifdef CONFIG_ACPI
 static const struct acpi_device_id sdhci_dwcmshc_acpi_ids[] = {
-	{ .id = "MLNXBF30" },
+	{
+		.id = "MLNXBF30",
+		.driver_data = (kernel_ulong_t)&sdhci_dwcmshc_bf3_pdata,
+	},
 	{}
 };
 #endif
@@ -447,7 +459,7 @@ static int dwcmshc_probe(struct platform_device *pdev)
 	int err;
 	u32 extra;
 
-	pltfm_data = of_device_get_match_data(&pdev->dev);
+	pltfm_data = device_get_match_data(&pdev->dev);
 	if (!pltfm_data) {
 		dev_err(&pdev->dev, "Error: No device match data found\n");
 		return -ENODEV;
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 4b14d80d27ed..e4f446db0ca1 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -613,6 +613,9 @@ int ksz9477_fdb_dump(struct ksz_device *dev, int port,
 			goto exit;
 		}
 
+		if (!(ksz_data & ALU_VALID))
+			continue;
+
 		/* read ALU table */
 		ksz9477_read_table(dev, alu_table);
 
diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c
index a4c6eb9a52d0..83dca9179aa0 100644
--- a/drivers/net/dsa/mv88e6060.c
+++ b/drivers/net/dsa/mv88e6060.c
@@ -118,6 +118,9 @@ static int mv88e6060_setup_port(struct mv88e6060_priv *priv, int p)
 	int addr = REG_PORT(p);
 	int ret;
 
+	if (dsa_is_unused_port(priv->ds, p))
+		return 0;
+
 	/* Do not force flow control, disable Ingress and Egress
 	 * Header tagging, disable VLAN tunneling, and set the port
 	 * state to Forwarding.  Additionally, if this is the CPU
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index b4034b78c0ca..1cdce8a98d1d 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -274,27 +274,98 @@ static const u32 vsc9959_rew_regmap[] = {
 
 static const u32 vsc9959_sys_regmap[] = {
 	REG(SYS_COUNT_RX_OCTETS,		0x000000),
+	REG(SYS_COUNT_RX_UNICAST,		0x000004),
 	REG(SYS_COUNT_RX_MULTICAST,		0x000008),
+	REG(SYS_COUNT_RX_BROADCAST,		0x00000c),
 	REG(SYS_COUNT_RX_SHORTS,		0x000010),
 	REG(SYS_COUNT_RX_FRAGMENTS,		0x000014),
 	REG(SYS_COUNT_RX_JABBERS,		0x000018),
+	REG(SYS_COUNT_RX_CRC_ALIGN_ERRS,	0x00001c),
+	REG(SYS_COUNT_RX_SYM_ERRS,		0x000020),
 	REG(SYS_COUNT_RX_64,			0x000024),
 	REG(SYS_COUNT_RX_65_127,		0x000028),
 	REG(SYS_COUNT_RX_128_255,		0x00002c),
-	REG(SYS_COUNT_RX_256_1023,		0x000030),
-	REG(SYS_COUNT_RX_1024_1526,		0x000034),
-	REG(SYS_COUNT_RX_1527_MAX,		0x000038),
-	REG(SYS_COUNT_RX_LONGS,			0x000044),
+	REG(SYS_COUNT_RX_256_511,		0x000030),
+	REG(SYS_COUNT_RX_512_1023,		0x000034),
+	REG(SYS_COUNT_RX_1024_1526,		0x000038),
+	REG(SYS_COUNT_RX_1527_MAX,		0x00003c),
+	REG(SYS_COUNT_RX_PAUSE,			0x000040),
+	REG(SYS_COUNT_RX_CONTROL,		0x000044),
+	REG(SYS_COUNT_RX_LONGS,			0x000048),
+	REG(SYS_COUNT_RX_CLASSIFIED_DROPS,	0x00004c),
+	REG(SYS_COUNT_RX_RED_PRIO_0,		0x000050),
+	REG(SYS_COUNT_RX_RED_PRIO_1,		0x000054),
+	REG(SYS_COUNT_RX_RED_PRIO_2,		0x000058),
+	REG(SYS_COUNT_RX_RED_PRIO_3,		0x00005c),
+	REG(SYS_COUNT_RX_RED_PRIO_4,		0x000060),
+	REG(SYS_COUNT_RX_RED_PRIO_5,		0x000064),
+	REG(SYS_COUNT_RX_RED_PRIO_6,		0x000068),
+	REG(SYS_COUNT_RX_RED_PRIO_7,		0x00006c),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_0,		0x000070),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_1,		0x000074),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_2,		0x000078),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_3,		0x00007c),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_4,		0x000080),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_5,		0x000084),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_6,		0x000088),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_7,		0x00008c),
+	REG(SYS_COUNT_RX_GREEN_PRIO_0,		0x000090),
+	REG(SYS_COUNT_RX_GREEN_PRIO_1,		0x000094),
+	REG(SYS_COUNT_RX_GREEN_PRIO_2,		0x000098),
+	REG(SYS_COUNT_RX_GREEN_PRIO_3,		0x00009c),
+	REG(SYS_COUNT_RX_GREEN_PRIO_4,		0x0000a0),
+	REG(SYS_COUNT_RX_GREEN_PRIO_5,		0x0000a4),
+	REG(SYS_COUNT_RX_GREEN_PRIO_6,		0x0000a8),
+	REG(SYS_COUNT_RX_GREEN_PRIO_7,		0x0000ac),
 	REG(SYS_COUNT_TX_OCTETS,		0x000200),
+	REG(SYS_COUNT_TX_UNICAST,		0x000204),
+	REG(SYS_COUNT_TX_MULTICAST,		0x000208),
+	REG(SYS_COUNT_TX_BROADCAST,		0x00020c),
 	REG(SYS_COUNT_TX_COLLISION,		0x000210),
 	REG(SYS_COUNT_TX_DROPS,			0x000214),
+	REG(SYS_COUNT_TX_PAUSE,			0x000218),
 	REG(SYS_COUNT_TX_64,			0x00021c),
 	REG(SYS_COUNT_TX_65_127,		0x000220),
-	REG(SYS_COUNT_TX_128_511,		0x000224),
-	REG(SYS_COUNT_TX_512_1023,		0x000228),
-	REG(SYS_COUNT_TX_1024_1526,		0x00022c),
-	REG(SYS_COUNT_TX_1527_MAX,		0x000230),
+	REG(SYS_COUNT_TX_128_255,		0x000224),
+	REG(SYS_COUNT_TX_256_511,		0x000228),
+	REG(SYS_COUNT_TX_512_1023,		0x00022c),
+	REG(SYS_COUNT_TX_1024_1526,		0x000230),
+	REG(SYS_COUNT_TX_1527_MAX,		0x000234),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_0,		0x000238),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_1,		0x00023c),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_2,		0x000240),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_3,		0x000244),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_4,		0x000248),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_5,		0x00024c),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_6,		0x000250),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_7,		0x000254),
+	REG(SYS_COUNT_TX_GREEN_PRIO_0,		0x000258),
+	REG(SYS_COUNT_TX_GREEN_PRIO_1,		0x00025c),
+	REG(SYS_COUNT_TX_GREEN_PRIO_2,		0x000260),
+	REG(SYS_COUNT_TX_GREEN_PRIO_3,		0x000264),
+	REG(SYS_COUNT_TX_GREEN_PRIO_4,		0x000268),
+	REG(SYS_COUNT_TX_GREEN_PRIO_5,		0x00026c),
+	REG(SYS_COUNT_TX_GREEN_PRIO_6,		0x000270),
+	REG(SYS_COUNT_TX_GREEN_PRIO_7,		0x000274),
 	REG(SYS_COUNT_TX_AGING,			0x000278),
+	REG(SYS_COUNT_DROP_LOCAL,		0x000400),
+	REG(SYS_COUNT_DROP_TAIL,		0x000404),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_0,	0x000408),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_1,	0x00040c),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_2,	0x000410),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_3,	0x000414),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_4,	0x000418),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_5,	0x00041c),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_6,	0x000420),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_7,	0x000424),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_0,	0x000428),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_1,	0x00042c),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_2,	0x000430),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_3,	0x000434),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_4,	0x000438),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_5,	0x00043c),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_6,	0x000440),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_7,	0x000444),
 	REG(SYS_RESET_CFG,			0x000e00),
 	REG(SYS_SR_ETYPE_CFG,			0x000e04),
 	REG(SYS_VLAN_ETYPE_CFG,			0x000e08),
@@ -547,100 +618,379 @@ static const struct reg_field vsc9959_regfields[REGFIELD_MAX] = {
 	[SYS_PAUSE_CFG_PAUSE_ENA] = REG_FIELD_ID(SYS_PAUSE_CFG, 0, 1, 7, 4),
 };
 
-static const struct ocelot_stat_layout vsc9959_stats_layout[] = {
-	{ .offset = 0x00,	.name = "rx_octets", },
-	{ .offset = 0x01,	.name = "rx_unicast", },
-	{ .offset = 0x02,	.name = "rx_multicast", },
-	{ .offset = 0x03,	.name = "rx_broadcast", },
-	{ .offset = 0x04,	.name = "rx_shorts", },
-	{ .offset = 0x05,	.name = "rx_fragments", },
-	{ .offset = 0x06,	.name = "rx_jabbers", },
-	{ .offset = 0x07,	.name = "rx_crc_align_errs", },
-	{ .offset = 0x08,	.name = "rx_sym_errs", },
-	{ .offset = 0x09,	.name = "rx_frames_below_65_octets", },
-	{ .offset = 0x0A,	.name = "rx_frames_65_to_127_octets", },
-	{ .offset = 0x0B,	.name = "rx_frames_128_to_255_octets", },
-	{ .offset = 0x0C,	.name = "rx_frames_256_to_511_octets", },
-	{ .offset = 0x0D,	.name = "rx_frames_512_to_1023_octets", },
-	{ .offset = 0x0E,	.name = "rx_frames_1024_to_1526_octets", },
-	{ .offset = 0x0F,	.name = "rx_frames_over_1526_octets", },
-	{ .offset = 0x10,	.name = "rx_pause", },
-	{ .offset = 0x11,	.name = "rx_control", },
-	{ .offset = 0x12,	.name = "rx_longs", },
-	{ .offset = 0x13,	.name = "rx_classified_drops", },
-	{ .offset = 0x14,	.name = "rx_red_prio_0", },
-	{ .offset = 0x15,	.name = "rx_red_prio_1", },
-	{ .offset = 0x16,	.name = "rx_red_prio_2", },
-	{ .offset = 0x17,	.name = "rx_red_prio_3", },
-	{ .offset = 0x18,	.name = "rx_red_prio_4", },
-	{ .offset = 0x19,	.name = "rx_red_prio_5", },
-	{ .offset = 0x1A,	.name = "rx_red_prio_6", },
-	{ .offset = 0x1B,	.name = "rx_red_prio_7", },
-	{ .offset = 0x1C,	.name = "rx_yellow_prio_0", },
-	{ .offset = 0x1D,	.name = "rx_yellow_prio_1", },
-	{ .offset = 0x1E,	.name = "rx_yellow_prio_2", },
-	{ .offset = 0x1F,	.name = "rx_yellow_prio_3", },
-	{ .offset = 0x20,	.name = "rx_yellow_prio_4", },
-	{ .offset = 0x21,	.name = "rx_yellow_prio_5", },
-	{ .offset = 0x22,	.name = "rx_yellow_prio_6", },
-	{ .offset = 0x23,	.name = "rx_yellow_prio_7", },
-	{ .offset = 0x24,	.name = "rx_green_prio_0", },
-	{ .offset = 0x25,	.name = "rx_green_prio_1", },
-	{ .offset = 0x26,	.name = "rx_green_prio_2", },
-	{ .offset = 0x27,	.name = "rx_green_prio_3", },
-	{ .offset = 0x28,	.name = "rx_green_prio_4", },
-	{ .offset = 0x29,	.name = "rx_green_prio_5", },
-	{ .offset = 0x2A,	.name = "rx_green_prio_6", },
-	{ .offset = 0x2B,	.name = "rx_green_prio_7", },
-	{ .offset = 0x80,	.name = "tx_octets", },
-	{ .offset = 0x81,	.name = "tx_unicast", },
-	{ .offset = 0x82,	.name = "tx_multicast", },
-	{ .offset = 0x83,	.name = "tx_broadcast", },
-	{ .offset = 0x84,	.name = "tx_collision", },
-	{ .offset = 0x85,	.name = "tx_drops", },
-	{ .offset = 0x86,	.name = "tx_pause", },
-	{ .offset = 0x87,	.name = "tx_frames_below_65_octets", },
-	{ .offset = 0x88,	.name = "tx_frames_65_to_127_octets", },
-	{ .offset = 0x89,	.name = "tx_frames_128_255_octets", },
-	{ .offset = 0x8B,	.name = "tx_frames_256_511_octets", },
-	{ .offset = 0x8C,	.name = "tx_frames_1024_1526_octets", },
-	{ .offset = 0x8D,	.name = "tx_frames_over_1526_octets", },
-	{ .offset = 0x8E,	.name = "tx_yellow_prio_0", },
-	{ .offset = 0x8F,	.name = "tx_yellow_prio_1", },
-	{ .offset = 0x90,	.name = "tx_yellow_prio_2", },
-	{ .offset = 0x91,	.name = "tx_yellow_prio_3", },
-	{ .offset = 0x92,	.name = "tx_yellow_prio_4", },
-	{ .offset = 0x93,	.name = "tx_yellow_prio_5", },
-	{ .offset = 0x94,	.name = "tx_yellow_prio_6", },
-	{ .offset = 0x95,	.name = "tx_yellow_prio_7", },
-	{ .offset = 0x96,	.name = "tx_green_prio_0", },
-	{ .offset = 0x97,	.name = "tx_green_prio_1", },
-	{ .offset = 0x98,	.name = "tx_green_prio_2", },
-	{ .offset = 0x99,	.name = "tx_green_prio_3", },
-	{ .offset = 0x9A,	.name = "tx_green_prio_4", },
-	{ .offset = 0x9B,	.name = "tx_green_prio_5", },
-	{ .offset = 0x9C,	.name = "tx_green_prio_6", },
-	{ .offset = 0x9D,	.name = "tx_green_prio_7", },
-	{ .offset = 0x9E,	.name = "tx_aged", },
-	{ .offset = 0x100,	.name = "drop_local", },
-	{ .offset = 0x101,	.name = "drop_tail", },
-	{ .offset = 0x102,	.name = "drop_yellow_prio_0", },
-	{ .offset = 0x103,	.name = "drop_yellow_prio_1", },
-	{ .offset = 0x104,	.name = "drop_yellow_prio_2", },
-	{ .offset = 0x105,	.name = "drop_yellow_prio_3", },
-	{ .offset = 0x106,	.name = "drop_yellow_prio_4", },
-	{ .offset = 0x107,	.name = "drop_yellow_prio_5", },
-	{ .offset = 0x108,	.name = "drop_yellow_prio_6", },
-	{ .offset = 0x109,	.name = "drop_yellow_prio_7", },
-	{ .offset = 0x10A,	.name = "drop_green_prio_0", },
-	{ .offset = 0x10B,	.name = "drop_green_prio_1", },
-	{ .offset = 0x10C,	.name = "drop_green_prio_2", },
-	{ .offset = 0x10D,	.name = "drop_green_prio_3", },
-	{ .offset = 0x10E,	.name = "drop_green_prio_4", },
-	{ .offset = 0x10F,	.name = "drop_green_prio_5", },
-	{ .offset = 0x110,	.name = "drop_green_prio_6", },
-	{ .offset = 0x111,	.name = "drop_green_prio_7", },
-	OCELOT_STAT_END
+static const struct ocelot_stat_layout vsc9959_stats_layout[OCELOT_NUM_STATS] = {
+	[OCELOT_STAT_RX_OCTETS] = {
+		.name = "rx_octets",
+		.reg = SYS_COUNT_RX_OCTETS,
+	},
+	[OCELOT_STAT_RX_UNICAST] = {
+		.name = "rx_unicast",
+		.reg = SYS_COUNT_RX_UNICAST,
+	},
+	[OCELOT_STAT_RX_MULTICAST] = {
+		.name = "rx_multicast",
+		.reg = SYS_COUNT_RX_MULTICAST,
+	},
+	[OCELOT_STAT_RX_BROADCAST] = {
+		.name = "rx_broadcast",
+		.reg = SYS_COUNT_RX_BROADCAST,
+	},
+	[OCELOT_STAT_RX_SHORTS] = {
+		.name = "rx_shorts",
+		.reg = SYS_COUNT_RX_SHORTS,
+	},
+	[OCELOT_STAT_RX_FRAGMENTS] = {
+		.name = "rx_fragments",
+		.reg = SYS_COUNT_RX_FRAGMENTS,
+	},
+	[OCELOT_STAT_RX_JABBERS] = {
+		.name = "rx_jabbers",
+		.reg = SYS_COUNT_RX_JABBERS,
+	},
+	[OCELOT_STAT_RX_CRC_ALIGN_ERRS] = {
+		.name = "rx_crc_align_errs",
+		.reg = SYS_COUNT_RX_CRC_ALIGN_ERRS,
+	},
+	[OCELOT_STAT_RX_SYM_ERRS] = {
+		.name = "rx_sym_errs",
+		.reg = SYS_COUNT_RX_SYM_ERRS,
+	},
+	[OCELOT_STAT_RX_64] = {
+		.name = "rx_frames_below_65_octets",
+		.reg = SYS_COUNT_RX_64,
+	},
+	[OCELOT_STAT_RX_65_127] = {
+		.name = "rx_frames_65_to_127_octets",
+		.reg = SYS_COUNT_RX_65_127,
+	},
+	[OCELOT_STAT_RX_128_255] = {
+		.name = "rx_frames_128_to_255_octets",
+		.reg = SYS_COUNT_RX_128_255,
+	},
+	[OCELOT_STAT_RX_256_511] = {
+		.name = "rx_frames_256_to_511_octets",
+		.reg = SYS_COUNT_RX_256_511,
+	},
+	[OCELOT_STAT_RX_512_1023] = {
+		.name = "rx_frames_512_to_1023_octets",
+		.reg = SYS_COUNT_RX_512_1023,
+	},
+	[OCELOT_STAT_RX_1024_1526] = {
+		.name = "rx_frames_1024_to_1526_octets",
+		.reg = SYS_COUNT_RX_1024_1526,
+	},
+	[OCELOT_STAT_RX_1527_MAX] = {
+		.name = "rx_frames_over_1526_octets",
+		.reg = SYS_COUNT_RX_1527_MAX,
+	},
+	[OCELOT_STAT_RX_PAUSE] = {
+		.name = "rx_pause",
+		.reg = SYS_COUNT_RX_PAUSE,
+	},
+	[OCELOT_STAT_RX_CONTROL] = {
+		.name = "rx_control",
+		.reg = SYS_COUNT_RX_CONTROL,
+	},
+	[OCELOT_STAT_RX_LONGS] = {
+		.name = "rx_longs",
+		.reg = SYS_COUNT_RX_LONGS,
+	},
+	[OCELOT_STAT_RX_CLASSIFIED_DROPS] = {
+		.name = "rx_classified_drops",
+		.reg = SYS_COUNT_RX_CLASSIFIED_DROPS,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_0] = {
+		.name = "rx_red_prio_0",
+		.reg = SYS_COUNT_RX_RED_PRIO_0,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_1] = {
+		.name = "rx_red_prio_1",
+		.reg = SYS_COUNT_RX_RED_PRIO_1,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_2] = {
+		.name = "rx_red_prio_2",
+		.reg = SYS_COUNT_RX_RED_PRIO_2,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_3] = {
+		.name = "rx_red_prio_3",
+		.reg = SYS_COUNT_RX_RED_PRIO_3,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_4] = {
+		.name = "rx_red_prio_4",
+		.reg = SYS_COUNT_RX_RED_PRIO_4,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_5] = {
+		.name = "rx_red_prio_5",
+		.reg = SYS_COUNT_RX_RED_PRIO_5,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_6] = {
+		.name = "rx_red_prio_6",
+		.reg = SYS_COUNT_RX_RED_PRIO_6,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_7] = {
+		.name = "rx_red_prio_7",
+		.reg = SYS_COUNT_RX_RED_PRIO_7,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_0] = {
+		.name = "rx_yellow_prio_0",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_1] = {
+		.name = "rx_yellow_prio_1",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_2] = {
+		.name = "rx_yellow_prio_2",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_3] = {
+		.name = "rx_yellow_prio_3",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_4] = {
+		.name = "rx_yellow_prio_4",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_5] = {
+		.name = "rx_yellow_prio_5",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_6] = {
+		.name = "rx_yellow_prio_6",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_7] = {
+		.name = "rx_yellow_prio_7",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_0] = {
+		.name = "rx_green_prio_0",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_1] = {
+		.name = "rx_green_prio_1",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_2] = {
+		.name = "rx_green_prio_2",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_3] = {
+		.name = "rx_green_prio_3",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_4] = {
+		.name = "rx_green_prio_4",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_5] = {
+		.name = "rx_green_prio_5",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_6] = {
+		.name = "rx_green_prio_6",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_7] = {
+		.name = "rx_green_prio_7",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_7,
+	},
+	[OCELOT_STAT_TX_OCTETS] = {
+		.name = "tx_octets",
+		.reg = SYS_COUNT_TX_OCTETS,
+	},
+	[OCELOT_STAT_TX_UNICAST] = {
+		.name = "tx_unicast",
+		.reg = SYS_COUNT_TX_UNICAST,
+	},
+	[OCELOT_STAT_TX_MULTICAST] = {
+		.name = "tx_multicast",
+		.reg = SYS_COUNT_TX_MULTICAST,
+	},
+	[OCELOT_STAT_TX_BROADCAST] = {
+		.name = "tx_broadcast",
+		.reg = SYS_COUNT_TX_BROADCAST,
+	},
+	[OCELOT_STAT_TX_COLLISION] = {
+		.name = "tx_collision",
+		.reg = SYS_COUNT_TX_COLLISION,
+	},
+	[OCELOT_STAT_TX_DROPS] = {
+		.name = "tx_drops",
+		.reg = SYS_COUNT_TX_DROPS,
+	},
+	[OCELOT_STAT_TX_PAUSE] = {
+		.name = "tx_pause",
+		.reg = SYS_COUNT_TX_PAUSE,
+	},
+	[OCELOT_STAT_TX_64] = {
+		.name = "tx_frames_below_65_octets",
+		.reg = SYS_COUNT_TX_64,
+	},
+	[OCELOT_STAT_TX_65_127] = {
+		.name = "tx_frames_65_to_127_octets",
+		.reg = SYS_COUNT_TX_65_127,
+	},
+	[OCELOT_STAT_TX_128_255] = {
+		.name = "tx_frames_128_255_octets",
+		.reg = SYS_COUNT_TX_128_255,
+	},
+	[OCELOT_STAT_TX_256_511] = {
+		.name = "tx_frames_256_511_octets",
+		.reg = SYS_COUNT_TX_256_511,
+	},
+	[OCELOT_STAT_TX_512_1023] = {
+		.name = "tx_frames_512_1023_octets",
+		.reg = SYS_COUNT_TX_512_1023,
+	},
+	[OCELOT_STAT_TX_1024_1526] = {
+		.name = "tx_frames_1024_1526_octets",
+		.reg = SYS_COUNT_TX_1024_1526,
+	},
+	[OCELOT_STAT_TX_1527_MAX] = {
+		.name = "tx_frames_over_1526_octets",
+		.reg = SYS_COUNT_TX_1527_MAX,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_0] = {
+		.name = "tx_yellow_prio_0",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_1] = {
+		.name = "tx_yellow_prio_1",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_2] = {
+		.name = "tx_yellow_prio_2",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_3] = {
+		.name = "tx_yellow_prio_3",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_4] = {
+		.name = "tx_yellow_prio_4",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_5] = {
+		.name = "tx_yellow_prio_5",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_6] = {
+		.name = "tx_yellow_prio_6",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_7] = {
+		.name = "tx_yellow_prio_7",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_0] = {
+		.name = "tx_green_prio_0",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_1] = {
+		.name = "tx_green_prio_1",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_2] = {
+		.name = "tx_green_prio_2",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_3] = {
+		.name = "tx_green_prio_3",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_4] = {
+		.name = "tx_green_prio_4",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_5] = {
+		.name = "tx_green_prio_5",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_6] = {
+		.name = "tx_green_prio_6",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_7] = {
+		.name = "tx_green_prio_7",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_7,
+	},
+	[OCELOT_STAT_TX_AGED] = {
+		.name = "tx_aged",
+		.reg = SYS_COUNT_TX_AGING,
+	},
+	[OCELOT_STAT_DROP_LOCAL] = {
+		.name = "drop_local",
+		.reg = SYS_COUNT_DROP_LOCAL,
+	},
+	[OCELOT_STAT_DROP_TAIL] = {
+		.name = "drop_tail",
+		.reg = SYS_COUNT_DROP_TAIL,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_0] = {
+		.name = "drop_yellow_prio_0",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_1] = {
+		.name = "drop_yellow_prio_1",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_2] = {
+		.name = "drop_yellow_prio_2",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_3] = {
+		.name = "drop_yellow_prio_3",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_4] = {
+		.name = "drop_yellow_prio_4",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_5] = {
+		.name = "drop_yellow_prio_5",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_6] = {
+		.name = "drop_yellow_prio_6",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_7] = {
+		.name = "drop_yellow_prio_7",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_0] = {
+		.name = "drop_green_prio_0",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_1] = {
+		.name = "drop_green_prio_1",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_2] = {
+		.name = "drop_green_prio_2",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_3] = {
+		.name = "drop_green_prio_3",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_4] = {
+		.name = "drop_green_prio_4",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_5] = {
+		.name = "drop_green_prio_5",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_6] = {
+		.name = "drop_green_prio_6",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_7] = {
+		.name = "drop_green_prio_7",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_7,
+	},
 };
 
 static const struct vcap_field vsc9959_vcap_es0_keys[] = {
@@ -2166,7 +2516,7 @@ static void vsc9959_psfp_sgi_table_del(struct ocelot *ocelot,
 static void vsc9959_psfp_counters_get(struct ocelot *ocelot, u32 index,
 				      struct felix_stream_filter_counters *counters)
 {
-	mutex_lock(&ocelot->stats_lock);
+	spin_lock(&ocelot->stats_lock);
 
 	ocelot_rmw(ocelot, SYS_STAT_CFG_STAT_VIEW(index),
 		   SYS_STAT_CFG_STAT_VIEW_M,
@@ -2183,7 +2533,7 @@ static void vsc9959_psfp_counters_get(struct ocelot *ocelot, u32 index,
 		     SYS_STAT_CFG_STAT_CLEAR_SHOT(0x10),
 		     SYS_STAT_CFG);
 
-	mutex_unlock(&ocelot->stats_lock);
+	spin_unlock(&ocelot->stats_lock);
 }
 
 static int vsc9959_psfp_filter_add(struct ocelot *ocelot, int port,
diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c
index ea0649211356..b34f4cdfe814 100644
--- a/drivers/net/dsa/ocelot/seville_vsc9953.c
+++ b/drivers/net/dsa/ocelot/seville_vsc9953.c
@@ -270,27 +270,98 @@ static const u32 vsc9953_rew_regmap[] = {
 
 static const u32 vsc9953_sys_regmap[] = {
 	REG(SYS_COUNT_RX_OCTETS,		0x000000),
+	REG(SYS_COUNT_RX_UNICAST,		0x000004),
 	REG(SYS_COUNT_RX_MULTICAST,		0x000008),
+	REG(SYS_COUNT_RX_BROADCAST,		0x00000c),
 	REG(SYS_COUNT_RX_SHORTS,		0x000010),
 	REG(SYS_COUNT_RX_FRAGMENTS,		0x000014),
 	REG(SYS_COUNT_RX_JABBERS,		0x000018),
+	REG(SYS_COUNT_RX_CRC_ALIGN_ERRS,	0x00001c),
+	REG(SYS_COUNT_RX_SYM_ERRS,		0x000020),
 	REG(SYS_COUNT_RX_64,			0x000024),
 	REG(SYS_COUNT_RX_65_127,		0x000028),
 	REG(SYS_COUNT_RX_128_255,		0x00002c),
-	REG(SYS_COUNT_RX_256_1023,		0x000030),
-	REG(SYS_COUNT_RX_1024_1526,		0x000034),
-	REG(SYS_COUNT_RX_1527_MAX,		0x000038),
+	REG(SYS_COUNT_RX_256_511,		0x000030),
+	REG(SYS_COUNT_RX_512_1023,		0x000034),
+	REG(SYS_COUNT_RX_1024_1526,		0x000038),
+	REG(SYS_COUNT_RX_1527_MAX,		0x00003c),
+	REG(SYS_COUNT_RX_PAUSE,			0x000040),
+	REG(SYS_COUNT_RX_CONTROL,		0x000044),
 	REG(SYS_COUNT_RX_LONGS,			0x000048),
+	REG(SYS_COUNT_RX_CLASSIFIED_DROPS,	0x00004c),
+	REG(SYS_COUNT_RX_RED_PRIO_0,		0x000050),
+	REG(SYS_COUNT_RX_RED_PRIO_1,		0x000054),
+	REG(SYS_COUNT_RX_RED_PRIO_2,		0x000058),
+	REG(SYS_COUNT_RX_RED_PRIO_3,		0x00005c),
+	REG(SYS_COUNT_RX_RED_PRIO_4,		0x000060),
+	REG(SYS_COUNT_RX_RED_PRIO_5,		0x000064),
+	REG(SYS_COUNT_RX_RED_PRIO_6,		0x000068),
+	REG(SYS_COUNT_RX_RED_PRIO_7,		0x00006c),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_0,		0x000070),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_1,		0x000074),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_2,		0x000078),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_3,		0x00007c),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_4,		0x000080),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_5,		0x000084),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_6,		0x000088),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_7,		0x00008c),
+	REG(SYS_COUNT_RX_GREEN_PRIO_0,		0x000090),
+	REG(SYS_COUNT_RX_GREEN_PRIO_1,		0x000094),
+	REG(SYS_COUNT_RX_GREEN_PRIO_2,		0x000098),
+	REG(SYS_COUNT_RX_GREEN_PRIO_3,		0x00009c),
+	REG(SYS_COUNT_RX_GREEN_PRIO_4,		0x0000a0),
+	REG(SYS_COUNT_RX_GREEN_PRIO_5,		0x0000a4),
+	REG(SYS_COUNT_RX_GREEN_PRIO_6,		0x0000a8),
+	REG(SYS_COUNT_RX_GREEN_PRIO_7,		0x0000ac),
 	REG(SYS_COUNT_TX_OCTETS,		0x000100),
+	REG(SYS_COUNT_TX_UNICAST,		0x000104),
+	REG(SYS_COUNT_TX_MULTICAST,		0x000108),
+	REG(SYS_COUNT_TX_BROADCAST,		0x00010c),
 	REG(SYS_COUNT_TX_COLLISION,		0x000110),
 	REG(SYS_COUNT_TX_DROPS,			0x000114),
+	REG(SYS_COUNT_TX_PAUSE,			0x000118),
 	REG(SYS_COUNT_TX_64,			0x00011c),
 	REG(SYS_COUNT_TX_65_127,		0x000120),
-	REG(SYS_COUNT_TX_128_511,		0x000124),
-	REG(SYS_COUNT_TX_512_1023,		0x000128),
-	REG(SYS_COUNT_TX_1024_1526,		0x00012c),
-	REG(SYS_COUNT_TX_1527_MAX,		0x000130),
+	REG(SYS_COUNT_TX_128_255,		0x000124),
+	REG(SYS_COUNT_TX_256_511,		0x000128),
+	REG(SYS_COUNT_TX_512_1023,		0x00012c),
+	REG(SYS_COUNT_TX_1024_1526,		0x000130),
+	REG(SYS_COUNT_TX_1527_MAX,		0x000134),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_0,		0x000138),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_1,		0x00013c),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_2,		0x000140),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_3,		0x000144),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_4,		0x000148),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_5,		0x00014c),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_6,		0x000150),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_7,		0x000154),
+	REG(SYS_COUNT_TX_GREEN_PRIO_0,		0x000158),
+	REG(SYS_COUNT_TX_GREEN_PRIO_1,		0x00015c),
+	REG(SYS_COUNT_TX_GREEN_PRIO_2,		0x000160),
+	REG(SYS_COUNT_TX_GREEN_PRIO_3,		0x000164),
+	REG(SYS_COUNT_TX_GREEN_PRIO_4,		0x000168),
+	REG(SYS_COUNT_TX_GREEN_PRIO_5,		0x00016c),
+	REG(SYS_COUNT_TX_GREEN_PRIO_6,		0x000170),
+	REG(SYS_COUNT_TX_GREEN_PRIO_7,		0x000174),
 	REG(SYS_COUNT_TX_AGING,			0x000178),
+	REG(SYS_COUNT_DROP_LOCAL,		0x000200),
+	REG(SYS_COUNT_DROP_TAIL,		0x000204),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_0,	0x000208),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_1,	0x00020c),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_2,	0x000210),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_3,	0x000214),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_4,	0x000218),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_5,	0x00021c),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_6,	0x000220),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_7,	0x000224),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_0,	0x000228),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_1,	0x00022c),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_2,	0x000230),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_3,	0x000234),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_4,	0x000238),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_5,	0x00023c),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_6,	0x000240),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_7,	0x000244),
 	REG(SYS_RESET_CFG,			0x000318),
 	REG_RESERVED(SYS_SR_ETYPE_CFG),
 	REG(SYS_VLAN_ETYPE_CFG,			0x000320),
@@ -543,101 +614,379 @@ static const struct reg_field vsc9953_regfields[REGFIELD_MAX] = {
 	[SYS_PAUSE_CFG_PAUSE_ENA] = REG_FIELD_ID(SYS_PAUSE_CFG, 0, 1, 11, 4),
 };
 
-static const struct ocelot_stat_layout vsc9953_stats_layout[] = {
-	{ .offset = 0x00,	.name = "rx_octets", },
-	{ .offset = 0x01,	.name = "rx_unicast", },
-	{ .offset = 0x02,	.name = "rx_multicast", },
-	{ .offset = 0x03,	.name = "rx_broadcast", },
-	{ .offset = 0x04,	.name = "rx_shorts", },
-	{ .offset = 0x05,	.name = "rx_fragments", },
-	{ .offset = 0x06,	.name = "rx_jabbers", },
-	{ .offset = 0x07,	.name = "rx_crc_align_errs", },
-	{ .offset = 0x08,	.name = "rx_sym_errs", },
-	{ .offset = 0x09,	.name = "rx_frames_below_65_octets", },
-	{ .offset = 0x0A,	.name = "rx_frames_65_to_127_octets", },
-	{ .offset = 0x0B,	.name = "rx_frames_128_to_255_octets", },
-	{ .offset = 0x0C,	.name = "rx_frames_256_to_511_octets", },
-	{ .offset = 0x0D,	.name = "rx_frames_512_to_1023_octets", },
-	{ .offset = 0x0E,	.name = "rx_frames_1024_to_1526_octets", },
-	{ .offset = 0x0F,	.name = "rx_frames_over_1526_octets", },
-	{ .offset = 0x10,	.name = "rx_pause", },
-	{ .offset = 0x11,	.name = "rx_control", },
-	{ .offset = 0x12,	.name = "rx_longs", },
-	{ .offset = 0x13,	.name = "rx_classified_drops", },
-	{ .offset = 0x14,	.name = "rx_red_prio_0", },
-	{ .offset = 0x15,	.name = "rx_red_prio_1", },
-	{ .offset = 0x16,	.name = "rx_red_prio_2", },
-	{ .offset = 0x17,	.name = "rx_red_prio_3", },
-	{ .offset = 0x18,	.name = "rx_red_prio_4", },
-	{ .offset = 0x19,	.name = "rx_red_prio_5", },
-	{ .offset = 0x1A,	.name = "rx_red_prio_6", },
-	{ .offset = 0x1B,	.name = "rx_red_prio_7", },
-	{ .offset = 0x1C,	.name = "rx_yellow_prio_0", },
-	{ .offset = 0x1D,	.name = "rx_yellow_prio_1", },
-	{ .offset = 0x1E,	.name = "rx_yellow_prio_2", },
-	{ .offset = 0x1F,	.name = "rx_yellow_prio_3", },
-	{ .offset = 0x20,	.name = "rx_yellow_prio_4", },
-	{ .offset = 0x21,	.name = "rx_yellow_prio_5", },
-	{ .offset = 0x22,	.name = "rx_yellow_prio_6", },
-	{ .offset = 0x23,	.name = "rx_yellow_prio_7", },
-	{ .offset = 0x24,	.name = "rx_green_prio_0", },
-	{ .offset = 0x25,	.name = "rx_green_prio_1", },
-	{ .offset = 0x26,	.name = "rx_green_prio_2", },
-	{ .offset = 0x27,	.name = "rx_green_prio_3", },
-	{ .offset = 0x28,	.name = "rx_green_prio_4", },
-	{ .offset = 0x29,	.name = "rx_green_prio_5", },
-	{ .offset = 0x2A,	.name = "rx_green_prio_6", },
-	{ .offset = 0x2B,	.name = "rx_green_prio_7", },
-	{ .offset = 0x40,	.name = "tx_octets", },
-	{ .offset = 0x41,	.name = "tx_unicast", },
-	{ .offset = 0x42,	.name = "tx_multicast", },
-	{ .offset = 0x43,	.name = "tx_broadcast", },
-	{ .offset = 0x44,	.name = "tx_collision", },
-	{ .offset = 0x45,	.name = "tx_drops", },
-	{ .offset = 0x46,	.name = "tx_pause", },
-	{ .offset = 0x47,	.name = "tx_frames_below_65_octets", },
-	{ .offset = 0x48,	.name = "tx_frames_65_to_127_octets", },
-	{ .offset = 0x49,	.name = "tx_frames_128_255_octets", },
-	{ .offset = 0x4A,	.name = "tx_frames_256_511_octets", },
-	{ .offset = 0x4B,	.name = "tx_frames_512_1023_octets", },
-	{ .offset = 0x4C,	.name = "tx_frames_1024_1526_octets", },
-	{ .offset = 0x4D,	.name = "tx_frames_over_1526_octets", },
-	{ .offset = 0x4E,	.name = "tx_yellow_prio_0", },
-	{ .offset = 0x4F,	.name = "tx_yellow_prio_1", },
-	{ .offset = 0x50,	.name = "tx_yellow_prio_2", },
-	{ .offset = 0x51,	.name = "tx_yellow_prio_3", },
-	{ .offset = 0x52,	.name = "tx_yellow_prio_4", },
-	{ .offset = 0x53,	.name = "tx_yellow_prio_5", },
-	{ .offset = 0x54,	.name = "tx_yellow_prio_6", },
-	{ .offset = 0x55,	.name = "tx_yellow_prio_7", },
-	{ .offset = 0x56,	.name = "tx_green_prio_0", },
-	{ .offset = 0x57,	.name = "tx_green_prio_1", },
-	{ .offset = 0x58,	.name = "tx_green_prio_2", },
-	{ .offset = 0x59,	.name = "tx_green_prio_3", },
-	{ .offset = 0x5A,	.name = "tx_green_prio_4", },
-	{ .offset = 0x5B,	.name = "tx_green_prio_5", },
-	{ .offset = 0x5C,	.name = "tx_green_prio_6", },
-	{ .offset = 0x5D,	.name = "tx_green_prio_7", },
-	{ .offset = 0x5E,	.name = "tx_aged", },
-	{ .offset = 0x80,	.name = "drop_local", },
-	{ .offset = 0x81,	.name = "drop_tail", },
-	{ .offset = 0x82,	.name = "drop_yellow_prio_0", },
-	{ .offset = 0x83,	.name = "drop_yellow_prio_1", },
-	{ .offset = 0x84,	.name = "drop_yellow_prio_2", },
-	{ .offset = 0x85,	.name = "drop_yellow_prio_3", },
-	{ .offset = 0x86,	.name = "drop_yellow_prio_4", },
-	{ .offset = 0x87,	.name = "drop_yellow_prio_5", },
-	{ .offset = 0x88,	.name = "drop_yellow_prio_6", },
-	{ .offset = 0x89,	.name = "drop_yellow_prio_7", },
-	{ .offset = 0x8A,	.name = "drop_green_prio_0", },
-	{ .offset = 0x8B,	.name = "drop_green_prio_1", },
-	{ .offset = 0x8C,	.name = "drop_green_prio_2", },
-	{ .offset = 0x8D,	.name = "drop_green_prio_3", },
-	{ .offset = 0x8E,	.name = "drop_green_prio_4", },
-	{ .offset = 0x8F,	.name = "drop_green_prio_5", },
-	{ .offset = 0x90,	.name = "drop_green_prio_6", },
-	{ .offset = 0x91,	.name = "drop_green_prio_7", },
-	OCELOT_STAT_END
+static const struct ocelot_stat_layout vsc9953_stats_layout[OCELOT_NUM_STATS] = {
+	[OCELOT_STAT_RX_OCTETS] = {
+		.name = "rx_octets",
+		.reg = SYS_COUNT_RX_OCTETS,
+	},
+	[OCELOT_STAT_RX_UNICAST] = {
+		.name = "rx_unicast",
+		.reg = SYS_COUNT_RX_UNICAST,
+	},
+	[OCELOT_STAT_RX_MULTICAST] = {
+		.name = "rx_multicast",
+		.reg = SYS_COUNT_RX_MULTICAST,
+	},
+	[OCELOT_STAT_RX_BROADCAST] = {
+		.name = "rx_broadcast",
+		.reg = SYS_COUNT_RX_BROADCAST,
+	},
+	[OCELOT_STAT_RX_SHORTS] = {
+		.name = "rx_shorts",
+		.reg = SYS_COUNT_RX_SHORTS,
+	},
+	[OCELOT_STAT_RX_FRAGMENTS] = {
+		.name = "rx_fragments",
+		.reg = SYS_COUNT_RX_FRAGMENTS,
+	},
+	[OCELOT_STAT_RX_JABBERS] = {
+		.name = "rx_jabbers",
+		.reg = SYS_COUNT_RX_JABBERS,
+	},
+	[OCELOT_STAT_RX_CRC_ALIGN_ERRS] = {
+		.name = "rx_crc_align_errs",
+		.reg = SYS_COUNT_RX_CRC_ALIGN_ERRS,
+	},
+	[OCELOT_STAT_RX_SYM_ERRS] = {
+		.name = "rx_sym_errs",
+		.reg = SYS_COUNT_RX_SYM_ERRS,
+	},
+	[OCELOT_STAT_RX_64] = {
+		.name = "rx_frames_below_65_octets",
+		.reg = SYS_COUNT_RX_64,
+	},
+	[OCELOT_STAT_RX_65_127] = {
+		.name = "rx_frames_65_to_127_octets",
+		.reg = SYS_COUNT_RX_65_127,
+	},
+	[OCELOT_STAT_RX_128_255] = {
+		.name = "rx_frames_128_to_255_octets",
+		.reg = SYS_COUNT_RX_128_255,
+	},
+	[OCELOT_STAT_RX_256_511] = {
+		.name = "rx_frames_256_to_511_octets",
+		.reg = SYS_COUNT_RX_256_511,
+	},
+	[OCELOT_STAT_RX_512_1023] = {
+		.name = "rx_frames_512_to_1023_octets",
+		.reg = SYS_COUNT_RX_512_1023,
+	},
+	[OCELOT_STAT_RX_1024_1526] = {
+		.name = "rx_frames_1024_to_1526_octets",
+		.reg = SYS_COUNT_RX_1024_1526,
+	},
+	[OCELOT_STAT_RX_1527_MAX] = {
+		.name = "rx_frames_over_1526_octets",
+		.reg = SYS_COUNT_RX_1527_MAX,
+	},
+	[OCELOT_STAT_RX_PAUSE] = {
+		.name = "rx_pause",
+		.reg = SYS_COUNT_RX_PAUSE,
+	},
+	[OCELOT_STAT_RX_CONTROL] = {
+		.name = "rx_control",
+		.reg = SYS_COUNT_RX_CONTROL,
+	},
+	[OCELOT_STAT_RX_LONGS] = {
+		.name = "rx_longs",
+		.reg = SYS_COUNT_RX_LONGS,
+	},
+	[OCELOT_STAT_RX_CLASSIFIED_DROPS] = {
+		.name = "rx_classified_drops",
+		.reg = SYS_COUNT_RX_CLASSIFIED_DROPS,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_0] = {
+		.name = "rx_red_prio_0",
+		.reg = SYS_COUNT_RX_RED_PRIO_0,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_1] = {
+		.name = "rx_red_prio_1",
+		.reg = SYS_COUNT_RX_RED_PRIO_1,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_2] = {
+		.name = "rx_red_prio_2",
+		.reg = SYS_COUNT_RX_RED_PRIO_2,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_3] = {
+		.name = "rx_red_prio_3",
+		.reg = SYS_COUNT_RX_RED_PRIO_3,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_4] = {
+		.name = "rx_red_prio_4",
+		.reg = SYS_COUNT_RX_RED_PRIO_4,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_5] = {
+		.name = "rx_red_prio_5",
+		.reg = SYS_COUNT_RX_RED_PRIO_5,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_6] = {
+		.name = "rx_red_prio_6",
+		.reg = SYS_COUNT_RX_RED_PRIO_6,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_7] = {
+		.name = "rx_red_prio_7",
+		.reg = SYS_COUNT_RX_RED_PRIO_7,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_0] = {
+		.name = "rx_yellow_prio_0",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_1] = {
+		.name = "rx_yellow_prio_1",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_2] = {
+		.name = "rx_yellow_prio_2",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_3] = {
+		.name = "rx_yellow_prio_3",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_4] = {
+		.name = "rx_yellow_prio_4",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_5] = {
+		.name = "rx_yellow_prio_5",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_6] = {
+		.name = "rx_yellow_prio_6",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_7] = {
+		.name = "rx_yellow_prio_7",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_0] = {
+		.name = "rx_green_prio_0",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_1] = {
+		.name = "rx_green_prio_1",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_2] = {
+		.name = "rx_green_prio_2",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_3] = {
+		.name = "rx_green_prio_3",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_4] = {
+		.name = "rx_green_prio_4",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_5] = {
+		.name = "rx_green_prio_5",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_6] = {
+		.name = "rx_green_prio_6",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_7] = {
+		.name = "rx_green_prio_7",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_7,
+	},
+	[OCELOT_STAT_TX_OCTETS] = {
+		.name = "tx_octets",
+		.reg = SYS_COUNT_TX_OCTETS,
+	},
+	[OCELOT_STAT_TX_UNICAST] = {
+		.name = "tx_unicast",
+		.reg = SYS_COUNT_TX_UNICAST,
+	},
+	[OCELOT_STAT_TX_MULTICAST] = {
+		.name = "tx_multicast",
+		.reg = SYS_COUNT_TX_MULTICAST,
+	},
+	[OCELOT_STAT_TX_BROADCAST] = {
+		.name = "tx_broadcast",
+		.reg = SYS_COUNT_TX_BROADCAST,
+	},
+	[OCELOT_STAT_TX_COLLISION] = {
+		.name = "tx_collision",
+		.reg = SYS_COUNT_TX_COLLISION,
+	},
+	[OCELOT_STAT_TX_DROPS] = {
+		.name = "tx_drops",
+		.reg = SYS_COUNT_TX_DROPS,
+	},
+	[OCELOT_STAT_TX_PAUSE] = {
+		.name = "tx_pause",
+		.reg = SYS_COUNT_TX_PAUSE,
+	},
+	[OCELOT_STAT_TX_64] = {
+		.name = "tx_frames_below_65_octets",
+		.reg = SYS_COUNT_TX_64,
+	},
+	[OCELOT_STAT_TX_65_127] = {
+		.name = "tx_frames_65_to_127_octets",
+		.reg = SYS_COUNT_TX_65_127,
+	},
+	[OCELOT_STAT_TX_128_255] = {
+		.name = "tx_frames_128_255_octets",
+		.reg = SYS_COUNT_TX_128_255,
+	},
+	[OCELOT_STAT_TX_256_511] = {
+		.name = "tx_frames_256_511_octets",
+		.reg = SYS_COUNT_TX_256_511,
+	},
+	[OCELOT_STAT_TX_512_1023] = {
+		.name = "tx_frames_512_1023_octets",
+		.reg = SYS_COUNT_TX_512_1023,
+	},
+	[OCELOT_STAT_TX_1024_1526] = {
+		.name = "tx_frames_1024_1526_octets",
+		.reg = SYS_COUNT_TX_1024_1526,
+	},
+	[OCELOT_STAT_TX_1527_MAX] = {
+		.name = "tx_frames_over_1526_octets",
+		.reg = SYS_COUNT_TX_1527_MAX,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_0] = {
+		.name = "tx_yellow_prio_0",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_1] = {
+		.name = "tx_yellow_prio_1",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_2] = {
+		.name = "tx_yellow_prio_2",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_3] = {
+		.name = "tx_yellow_prio_3",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_4] = {
+		.name = "tx_yellow_prio_4",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_5] = {
+		.name = "tx_yellow_prio_5",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_6] = {
+		.name = "tx_yellow_prio_6",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_7] = {
+		.name = "tx_yellow_prio_7",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_0] = {
+		.name = "tx_green_prio_0",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_1] = {
+		.name = "tx_green_prio_1",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_2] = {
+		.name = "tx_green_prio_2",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_3] = {
+		.name = "tx_green_prio_3",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_4] = {
+		.name = "tx_green_prio_4",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_5] = {
+		.name = "tx_green_prio_5",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_6] = {
+		.name = "tx_green_prio_6",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_7] = {
+		.name = "tx_green_prio_7",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_7,
+	},
+	[OCELOT_STAT_TX_AGED] = {
+		.name = "tx_aged",
+		.reg = SYS_COUNT_TX_AGING,
+	},
+	[OCELOT_STAT_DROP_LOCAL] = {
+		.name = "drop_local",
+		.reg = SYS_COUNT_DROP_LOCAL,
+	},
+	[OCELOT_STAT_DROP_TAIL] = {
+		.name = "drop_tail",
+		.reg = SYS_COUNT_DROP_TAIL,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_0] = {
+		.name = "drop_yellow_prio_0",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_1] = {
+		.name = "drop_yellow_prio_1",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_2] = {
+		.name = "drop_yellow_prio_2",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_3] = {
+		.name = "drop_yellow_prio_3",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_4] = {
+		.name = "drop_yellow_prio_4",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_5] = {
+		.name = "drop_yellow_prio_5",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_6] = {
+		.name = "drop_yellow_prio_6",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_7] = {
+		.name = "drop_yellow_prio_7",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_0] = {
+		.name = "drop_green_prio_0",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_1] = {
+		.name = "drop_green_prio_1",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_2] = {
+		.name = "drop_green_prio_2",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_3] = {
+		.name = "drop_green_prio_3",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_4] = {
+		.name = "drop_green_prio_4",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_5] = {
+		.name = "drop_green_prio_5",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_6] = {
+		.name = "drop_green_prio_6",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_7] = {
+		.name = "drop_green_prio_7",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_7,
+	},
 };
 
 static const struct vcap_field vsc9953_vcap_es0_keys[] = {
diff --git a/drivers/net/dsa/sja1105/sja1105_devlink.c b/drivers/net/dsa/sja1105/sja1105_devlink.c
index 0569ff066634..10c6fea1227f 100644
--- a/drivers/net/dsa/sja1105/sja1105_devlink.c
+++ b/drivers/net/dsa/sja1105/sja1105_devlink.c
@@ -93,7 +93,7 @@ static int sja1105_setup_devlink_regions(struct dsa_switch *ds)
 
 		region = dsa_devlink_region_create(ds, ops, 1, size);
 		if (IS_ERR(region)) {
-			while (i-- >= 0)
+			while (--i >= 0)
 				dsa_devlink_region_destroy(priv->regions[i]);
 			return PTR_ERR(region);
 		}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 7071604f9984..02808513ffe4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -13844,7 +13844,7 @@ static void bnx2x_check_kr2_wa(struct link_params *params,
 
 	/* Once KR2 was disabled, wait 5 seconds before checking KR2 recovery
 	 * Since some switches tend to reinit the AN process and clear the
-	 * the advertised BP/NP after ~2 seconds causing the KR2 to be disabled
+	 * advertised BP/NP after ~2 seconds causing the KR2 to be disabled
 	 * and recovered many times
 	 */
 	if (vars->check_kr2_recovery_cnt > 0) {
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c
index 84604aff53ce..89256b866840 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c
@@ -243,7 +243,7 @@ static int cxgb_ulp_iscsi_ctl(struct adapter *adapter, unsigned int req,
 
 		/*
 		 * on rx, the iscsi pdu has to be < rx page size and the
-		 * the max rx data length programmed in TP
+		 * max rx data length programmed in TP
 		 */
 		val = min(adapter->params.tp.rx_pg_size,
 			  ((t3_read_reg(adapter, A_TP_PARA_REG2)) >>
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index 26433a62d7f0..fed5f93bf620 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -497,7 +497,7 @@ struct cpl_t5_pass_accept_rpl {
 	__be32 opt2;
 	__be64 opt0;
 	__be32 iss;
-	__be32 rsvd[3];
+	__be32 rsvd;
 };
 
 struct cpl_act_open_req {
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 7d49c28215f3..3dc3c0b626c2 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -135,11 +135,7 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
 		 * NSEC_PER_SEC - ts.tv_nsec. Add the remaining nanoseconds
 		 * to current timer would be next second.
 		 */
-		tempval = readl(fep->hwp + FEC_ATIME_CTRL);
-		tempval |= FEC_T_CTRL_CAPTURE;
-		writel(tempval, fep->hwp + FEC_ATIME_CTRL);
-
-		tempval = readl(fep->hwp + FEC_ATIME);
+		tempval = fep->cc.read(&fep->cc);
 		/* Convert the ptp local counter to 1588 timestamp */
 		ns = timecounter_cyc2time(&fep->tc, tempval);
 		ts = ns_to_timespec64(ns);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index b36bf9c3e1e4..9f1d5de7bf16 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -384,7 +384,9 @@ static void i40e_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 		set_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state);
 		break;
 	default:
-		netdev_err(netdev, "tx_timeout recovery unsuccessful\n");
+		netdev_err(netdev, "tx_timeout recovery unsuccessful, device is in non-recoverable state.\n");
+		set_bit(__I40E_DOWN_REQUESTED, pf->state);
+		set_bit(__I40E_VSI_DOWN_REQUESTED, vsi->state);
 		break;
 	}
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index f6ba97a0166e..d4226161a3ef 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -3203,11 +3203,13 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 
 	protocol = vlan_get_protocol(skb);
 
-	if (eth_p_mpls(protocol))
+	if (eth_p_mpls(protocol)) {
 		ip.hdr = skb_inner_network_header(skb);
-	else
+		l4.hdr = skb_checksum_start(skb);
+	} else {
 		ip.hdr = skb_network_header(skb);
-	l4.hdr = skb_checksum_start(skb);
+		l4.hdr = skb_transport_header(skb);
+	}
 
 	/* set the tx_flags to indicate the IP protocol type. this is
 	 * required so that checksum header computation below is accurate.
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adminq.c b/drivers/net/ethernet/intel/iavf/iavf_adminq.c
index cd4e6a22d0f9..9ffbd24d83cb 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_adminq.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_adminq.c
@@ -324,6 +324,7 @@ static enum iavf_status iavf_config_arq_regs(struct iavf_hw *hw)
 static enum iavf_status iavf_init_asq(struct iavf_hw *hw)
 {
 	enum iavf_status ret_code = 0;
+	int i;
 
 	if (hw->aq.asq.count > 0) {
 		/* queue already initialized */
@@ -354,12 +355,17 @@ static enum iavf_status iavf_init_asq(struct iavf_hw *hw)
 	/* initialize base registers */
 	ret_code = iavf_config_asq_regs(hw);
 	if (ret_code)
-		goto init_adminq_free_rings;
+		goto init_free_asq_bufs;
 
 	/* success! */
 	hw->aq.asq.count = hw->aq.num_asq_entries;
 	goto init_adminq_exit;
 
+init_free_asq_bufs:
+	for (i = 0; i < hw->aq.num_asq_entries; i++)
+		iavf_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]);
+	iavf_free_virt_mem(hw, &hw->aq.asq.dma_head);
+
 init_adminq_free_rings:
 	iavf_free_adminq_asq(hw);
 
@@ -383,6 +389,7 @@ init_adminq_exit:
 static enum iavf_status iavf_init_arq(struct iavf_hw *hw)
 {
 	enum iavf_status ret_code = 0;
+	int i;
 
 	if (hw->aq.arq.count > 0) {
 		/* queue already initialized */
@@ -413,12 +420,16 @@ static enum iavf_status iavf_init_arq(struct iavf_hw *hw)
 	/* initialize base registers */
 	ret_code = iavf_config_arq_regs(hw);
 	if (ret_code)
-		goto init_adminq_free_rings;
+		goto init_free_arq_bufs;
 
 	/* success! */
 	hw->aq.arq.count = hw->aq.num_arq_entries;
 	goto init_adminq_exit;
 
+init_free_arq_bufs:
+	for (i = 0; i < hw->aq.num_arq_entries; i++)
+		iavf_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]);
+	iavf_free_virt_mem(hw, &hw->aq.arq.dma_head);
 init_adminq_free_rings:
 	iavf_free_adminq_arq(hw);
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 45d097a164ad..f39440ad5c50 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2367,7 +2367,7 @@ static void iavf_init_get_resources(struct iavf_adapter *adapter)
 	err = iavf_get_vf_config(adapter);
 	if (err == -EALREADY) {
 		err = iavf_send_vf_config_msg(adapter);
-		goto err_alloc;
+		goto err;
 	} else if (err == -EINVAL) {
 		/* We only get -EINVAL if the device is in a very bad
 		 * state or if we've been disabled for previous bad
@@ -3086,12 +3086,15 @@ continue_reset:
 
 	return;
 reset_err:
+	if (running) {
+		set_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
+		iavf_free_traffic_irqs(adapter);
+	}
+	iavf_disable_vf(adapter);
+
 	mutex_unlock(&adapter->client_lock);
 	mutex_unlock(&adapter->crit_lock);
-	if (running)
-		iavf_change_state(adapter, __IAVF_RUNNING);
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
-	iavf_close(netdev);
 }
 
 /**
@@ -4085,8 +4088,17 @@ static int iavf_open(struct net_device *netdev)
 		return -EIO;
 	}
 
-	while (!mutex_trylock(&adapter->crit_lock))
+	while (!mutex_trylock(&adapter->crit_lock)) {
+		/* If we are in __IAVF_INIT_CONFIG_ADAPTER state the crit_lock
+		 * is already taken and iavf_open is called from an upper
+		 * device's notifier reacting on NETDEV_REGISTER event.
+		 * We have to leave here to avoid dead lock.
+		 */
+		if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER)
+			return -EBUSY;
+
 		usleep_range(500, 1000);
+	}
 
 	if (adapter->state != __IAVF_DOWN) {
 		err = -EBUSY;
diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c
index 85a94483c2ed..40e678cfb507 100644
--- a/drivers/net/ethernet/intel/ice/ice_fltr.c
+++ b/drivers/net/ethernet/intel/ice/ice_fltr.c
@@ -62,7 +62,7 @@ ice_fltr_set_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi,
 	int result;
 
 	result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false);
-	if (result)
+	if (result && result != -EEXIST)
 		dev_err(ice_pf_to_dev(pf),
 			"Error setting promisc mode on VSI %i (rc=%d)\n",
 			vsi->vsi_num, result);
@@ -86,7 +86,7 @@ ice_fltr_clear_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi,
 	int result;
 
 	result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true);
-	if (result)
+	if (result && result != -EEXIST)
 		dev_err(ice_pf_to_dev(pf),
 			"Error clearing promisc mode on VSI %i (rc=%d)\n",
 			vsi->vsi_num, result);
@@ -109,7 +109,7 @@ ice_fltr_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
 	int result;
 
 	result = ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid);
-	if (result)
+	if (result && result != -EEXIST)
 		dev_err(ice_pf_to_dev(pf),
 			"Error clearing promisc mode on VSI %i for VID %u (rc=%d)\n",
 			ice_get_hw_vsi_num(hw, vsi_handle), vid, result);
@@ -132,7 +132,7 @@ ice_fltr_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
 	int result;
 
 	result = ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid);
-	if (result)
+	if (result && result != -EEXIST)
 		dev_err(ice_pf_to_dev(pf),
 			"Error setting promisc mode on VSI %i for VID %u (rc=%d)\n",
 			ice_get_hw_vsi_num(hw, vsi_handle), vid, result);
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index a830f7f9aed0..733c455f6574 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -3181,7 +3181,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi)
 
 	pf = vsi->back;
 	vtype = vsi->type;
-	if (WARN_ON(vtype == ICE_VSI_VF) && !vsi->vf)
+	if (WARN_ON(vtype == ICE_VSI_VF && !vsi->vf))
 		return -EINVAL;
 
 	ice_vsi_init_vlan_ops(vsi);
@@ -4062,7 +4062,11 @@ int ice_vsi_del_vlan_zero(struct ice_vsi *vsi)
 	if (err && err != -EEXIST)
 		return err;
 
-	return 0;
+	/* when deleting the last VLAN filter, make sure to disable the VLAN
+	 * promisc mode so the filter isn't left by accident
+	 */
+	return ice_clear_vsi_promisc(&vsi->back->hw, vsi->idx,
+				    ICE_MCAST_VLAN_PROMISC_BITS, 0);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index eb40526ee179..4ecaf40cf946 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -267,8 +267,10 @@ static int ice_set_promisc(struct ice_vsi *vsi, u8 promisc_m)
 		status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx,
 						  promisc_m, 0);
 	}
+	if (status && status != -EEXIST)
+		return status;
 
-	return status;
+	return 0;
 }
 
 /**
@@ -3573,6 +3575,14 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid)
 	while (test_and_set_bit(ICE_CFG_BUSY, vsi->state))
 		usleep_range(1000, 2000);
 
+	ret = ice_clear_vsi_promisc(&vsi->back->hw, vsi->idx,
+				    ICE_MCAST_VLAN_PROMISC_BITS, vid);
+	if (ret) {
+		netdev_err(netdev, "Error clearing multicast promiscuous mode on VSI %i\n",
+			   vsi->vsi_num);
+		vsi->current_netdev_flags |= IFF_ALLMULTI;
+	}
+
 	vlan_ops = ice_get_compat_vsi_vlan_ops(vsi);
 
 	/* Make sure VLAN delete is successful before updating VLAN
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 262e553e3b58..3808034f7e7e 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -4445,6 +4445,13 @@ ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
 		goto free_fltr_list;
 
 	list_for_each_entry(list_itr, &vsi_list_head, list_entry) {
+		/* Avoid enabling or disabling VLAN zero twice when in double
+		 * VLAN mode
+		 */
+		if (ice_is_dvm_ena(hw) &&
+		    list_itr->fltr_info.l_data.vlan.tpid == 0)
+			continue;
+
 		vlan_id = list_itr->fltr_info.l_data.vlan.vlan_id;
 		if (rm_vlan_promisc)
 			status = ice_clear_vsi_promisc(hw, vsi_handle,
@@ -4452,7 +4459,7 @@ ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
 		else
 			status = ice_set_vsi_promisc(hw, vsi_handle,
 						     promisc_mask, vlan_id);
-		if (status)
+		if (status && status != -EEXIST)
 			break;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index 8fd7c3e37f5e..0abeed092de1 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -571,8 +571,10 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags)
 
 	if (ice_is_vf_disabled(vf)) {
 		vsi = ice_get_vf_vsi(vf);
-		if (WARN_ON(!vsi))
+		if (!vsi) {
+			dev_dbg(dev, "VF is already removed\n");
 			return -EINVAL;
+		}
 		ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id);
 		ice_vsi_stop_all_rx_rings(vsi);
 		dev_dbg(dev, "VF is already disabled, there is no need for resetting it, telling VM, all is fine %d\n",
@@ -762,13 +764,16 @@ static int ice_cfg_mac_antispoof(struct ice_vsi *vsi, bool enable)
 static int ice_vsi_ena_spoofchk(struct ice_vsi *vsi)
 {
 	struct ice_vsi_vlan_ops *vlan_ops;
-	int err;
+	int err = 0;
 
 	vlan_ops = ice_get_compat_vsi_vlan_ops(vsi);
 
-	err = vlan_ops->ena_tx_filtering(vsi);
-	if (err)
-		return err;
+	/* Allow VF with VLAN 0 only to send all tagged traffic */
+	if (vsi->type != ICE_VSI_VF || ice_vsi_has_non_zero_vlans(vsi)) {
+		err = vlan_ops->ena_tx_filtering(vsi);
+		if (err)
+			return err;
+	}
 
 	return ice_cfg_mac_antispoof(vsi, true);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 094e3c97a1ea..2b4c791b6cba 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -2288,6 +2288,15 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
 
 			/* Enable VLAN filtering on first non-zero VLAN */
 			if (!vlan_promisc && vid && !ice_is_dvm_ena(&pf->hw)) {
+				if (vf->spoofchk) {
+					status = vsi->inner_vlan_ops.ena_tx_filtering(vsi);
+					if (status) {
+						v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+						dev_err(dev, "Enable VLAN anti-spoofing on VLAN ID: %d failed error-%d\n",
+							vid, status);
+						goto error_param;
+					}
+				}
 				if (vsi->inner_vlan_ops.ena_rx_filtering(vsi)) {
 					v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 					dev_err(dev, "Enable VLAN pruning on VLAN ID: %d failed error-%d\n",
@@ -2333,8 +2342,10 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
 			}
 
 			/* Disable VLAN filtering when only VLAN 0 is left */
-			if (!ice_vsi_has_non_zero_vlans(vsi))
+			if (!ice_vsi_has_non_zero_vlans(vsi)) {
+				vsi->inner_vlan_ops.dis_tx_filtering(vsi);
 				vsi->inner_vlan_ops.dis_rx_filtering(vsi);
+			}
 
 			if (vlan_promisc)
 				ice_vf_dis_vlan_promisc(vsi, &vlan);
@@ -2838,6 +2849,13 @@ ice_vc_del_vlans(struct ice_vf *vf, struct ice_vsi *vsi,
 
 			if (vlan_promisc)
 				ice_vf_dis_vlan_promisc(vsi, &vlan);
+
+			/* Disable VLAN filtering when only VLAN 0 is left */
+			if (!ice_vsi_has_non_zero_vlans(vsi) && ice_is_dvm_ena(&vsi->back->hw)) {
+				err = vsi->outer_vlan_ops.dis_tx_filtering(vsi);
+				if (err)
+					return err;
+			}
 		}
 
 		vc_vlan = &vlan_fltr->inner;
@@ -2853,8 +2871,17 @@ ice_vc_del_vlans(struct ice_vf *vf, struct ice_vsi *vsi,
 			/* no support for VLAN promiscuous on inner VLAN unless
 			 * we are in Single VLAN Mode (SVM)
 			 */
-			if (!ice_is_dvm_ena(&vsi->back->hw) && vlan_promisc)
-				ice_vf_dis_vlan_promisc(vsi, &vlan);
+			if (!ice_is_dvm_ena(&vsi->back->hw)) {
+				if (vlan_promisc)
+					ice_vf_dis_vlan_promisc(vsi, &vlan);
+
+				/* Disable VLAN filtering when only VLAN 0 is left */
+				if (!ice_vsi_has_non_zero_vlans(vsi)) {
+					err = vsi->inner_vlan_ops.dis_tx_filtering(vsi);
+					if (err)
+						return err;
+				}
+			}
 		}
 	}
 
@@ -2931,6 +2958,13 @@ ice_vc_add_vlans(struct ice_vf *vf, struct ice_vsi *vsi,
 				if (err)
 					return err;
 			}
+
+			/* Enable VLAN filtering on first non-zero VLAN */
+			if (vf->spoofchk && vlan.vid && ice_is_dvm_ena(&vsi->back->hw)) {
+				err = vsi->outer_vlan_ops.ena_tx_filtering(vsi);
+				if (err)
+					return err;
+			}
 		}
 
 		vc_vlan = &vlan_fltr->inner;
@@ -2946,10 +2980,19 @@ ice_vc_add_vlans(struct ice_vf *vf, struct ice_vsi *vsi,
 			/* no support for VLAN promiscuous on inner VLAN unless
 			 * we are in Single VLAN Mode (SVM)
 			 */
-			if (!ice_is_dvm_ena(&vsi->back->hw) && vlan_promisc) {
-				err = ice_vf_ena_vlan_promisc(vsi, &vlan);
-				if (err)
-					return err;
+			if (!ice_is_dvm_ena(&vsi->back->hw)) {
+				if (vlan_promisc) {
+					err = ice_vf_ena_vlan_promisc(vsi, &vlan);
+					if (err)
+						return err;
+				}
+
+				/* Enable VLAN filtering on first non-zero VLAN */
+				if (vf->spoofchk && vlan.vid) {
+					err = vsi->inner_vlan_ops.ena_tx_filtering(vsi);
+					if (err)
+						return err;
+				}
 			}
 		}
 	}
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 2d3daf022651..015b78144114 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -664,6 +664,8 @@ struct igb_adapter {
 	struct igb_mac_addr *mac_table;
 	struct vf_mac_filter vf_macs;
 	struct vf_mac_filter *vf_mac_list;
+	/* lock for VF resources */
+	spinlock_t vfs_lock;
 };
 
 /* flags controlling PTP/1588 function */
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index d8b836a85cc3..2796e81d2726 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -3637,6 +3637,7 @@ static int igb_disable_sriov(struct pci_dev *pdev)
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	unsigned long flags;
 
 	/* reclaim resources allocated to VFs */
 	if (adapter->vf_data) {
@@ -3649,12 +3650,13 @@ static int igb_disable_sriov(struct pci_dev *pdev)
 			pci_disable_sriov(pdev);
 			msleep(500);
 		}
-
+		spin_lock_irqsave(&adapter->vfs_lock, flags);
 		kfree(adapter->vf_mac_list);
 		adapter->vf_mac_list = NULL;
 		kfree(adapter->vf_data);
 		adapter->vf_data = NULL;
 		adapter->vfs_allocated_count = 0;
+		spin_unlock_irqrestore(&adapter->vfs_lock, flags);
 		wr32(E1000_IOVCTL, E1000_IOVCTL_REUSE_VFQ);
 		wrfl();
 		msleep(100);
@@ -3814,7 +3816,9 @@ static void igb_remove(struct pci_dev *pdev)
 	igb_release_hw_control(adapter);
 
 #ifdef CONFIG_PCI_IOV
+	rtnl_lock();
 	igb_disable_sriov(pdev);
+	rtnl_unlock();
 #endif
 
 	unregister_netdev(netdev);
@@ -3974,6 +3978,9 @@ static int igb_sw_init(struct igb_adapter *adapter)
 
 	spin_lock_init(&adapter->nfc_lock);
 	spin_lock_init(&adapter->stats64_lock);
+
+	/* init spinlock to avoid concurrency of VF resources */
+	spin_lock_init(&adapter->vfs_lock);
 #ifdef CONFIG_PCI_IOV
 	switch (hw->mac.type) {
 	case e1000_82576:
@@ -7958,8 +7965,10 @@ unlock:
 static void igb_msg_task(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
+	unsigned long flags;
 	u32 vf;
 
+	spin_lock_irqsave(&adapter->vfs_lock, flags);
 	for (vf = 0; vf < adapter->vfs_allocated_count; vf++) {
 		/* process any reset requests */
 		if (!igb_check_for_rst(hw, vf))
@@ -7973,6 +7982,7 @@ static void igb_msg_task(struct igb_adapter *adapter)
 		if (!igb_check_for_ack(hw, vf))
 			igb_rcv_ack_from_vf(adapter, vf);
 	}
+	spin_unlock_irqrestore(&adapter->vfs_lock, flags);
 }
 
 /**
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index d9426b01f462..8aff4c0c28bd 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1732,7 +1732,7 @@ static u32 mtk_xdp_run(struct mtk_eth *eth, struct mtk_rx_ring *ring,
 	case XDP_TX: {
 		struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
 
-		if (mtk_xdp_submit_frame(eth, xdpf, dev, false)) {
+		if (!xdpf || mtk_xdp_submit_frame(eth, xdpf, dev, false)) {
 			count = &hw_stats->xdp_stats.rx_xdp_tx_errors;
 			act = XDP_DROP;
 			break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 4c1599de652c..0c66774a1720 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -696,6 +696,13 @@ static int mlx5e_init_rep(struct mlx5_core_dev *mdev,
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
+	priv->fs = mlx5e_fs_init(priv->profile, mdev,
+				 !test_bit(MLX5E_STATE_DESTROYING, &priv->state));
+	if (!priv->fs) {
+		netdev_err(priv->netdev, "FS allocation failed\n");
+		return -ENOMEM;
+	}
+
 	mlx5e_build_rep_params(netdev);
 	mlx5e_timestamp_init(priv);
 
@@ -708,12 +715,21 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev,
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	int err;
 
+	priv->fs = mlx5e_fs_init(priv->profile, mdev,
+				 !test_bit(MLX5E_STATE_DESTROYING, &priv->state));
+	if (!priv->fs) {
+		netdev_err(priv->netdev, "FS allocation failed\n");
+		return -ENOMEM;
+	}
+
 	err = mlx5e_ipsec_init(priv);
 	if (err)
 		mlx5_core_err(mdev, "Uplink rep IPsec initialization failed, %d\n", err);
 
 	mlx5e_vxlan_set_netdev_info(priv);
-	return mlx5e_init_rep(mdev, netdev);
+	mlx5e_build_rep_params(netdev);
+	mlx5e_timestamp_init(priv);
+	return 0;
 }
 
 static void mlx5e_cleanup_rep(struct mlx5e_priv *priv)
@@ -836,13 +852,6 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
-	priv->fs = mlx5e_fs_init(priv->profile, mdev,
-				 !test_bit(MLX5E_STATE_DESTROYING, &priv->state));
-	if (!priv->fs) {
-		netdev_err(priv->netdev, "FS allocation failed\n");
-		return -ENOMEM;
-	}
-
 	priv->rx_res = mlx5e_rx_res_alloc();
 	if (!priv->rx_res) {
 		err = -ENOMEM;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 3548fe1df7c8..987fe5c9d5a3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -21,7 +21,6 @@
 #define MLXSW_THERMAL_ASIC_TEMP_HOT	105000	/* 105C */
 #define MLXSW_THERMAL_HYSTERESIS_TEMP	5000	/* 5C */
 #define MLXSW_THERMAL_MODULE_TEMP_SHIFT	(MLXSW_THERMAL_HYSTERESIS_TEMP * 2)
-#define MLXSW_THERMAL_TEMP_SCORE_MAX	GENMASK(31, 0)
 #define MLXSW_THERMAL_MAX_STATE	10
 #define MLXSW_THERMAL_MIN_STATE	2
 #define MLXSW_THERMAL_MAX_DUTY	255
@@ -101,8 +100,6 @@ struct mlxsw_thermal {
 	struct thermal_cooling_device *cdevs[MLXSW_MFCR_PWMS_MAX];
 	u8 cooling_levels[MLXSW_THERMAL_MAX_STATE + 1];
 	struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
-	unsigned int tz_highest_score;
-	struct thermal_zone_device *tz_highest_dev;
 	struct mlxsw_thermal_area line_cards[];
 };
 
@@ -193,34 +190,6 @@ mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core,
 	return 0;
 }
 
-static void mlxsw_thermal_tz_score_update(struct mlxsw_thermal *thermal,
-					  struct thermal_zone_device *tzdev,
-					  struct mlxsw_thermal_trip *trips,
-					  int temp)
-{
-	struct mlxsw_thermal_trip *trip = trips;
-	unsigned int score, delta, i, shift = 1;
-
-	/* Calculate thermal zone score, if temperature is above the hot
-	 * threshold score is set to MLXSW_THERMAL_TEMP_SCORE_MAX.
-	 */
-	score = MLXSW_THERMAL_TEMP_SCORE_MAX;
-	for (i = MLXSW_THERMAL_TEMP_TRIP_NORM; i < MLXSW_THERMAL_NUM_TRIPS;
-	     i++, trip++) {
-		if (temp < trip->temp) {
-			delta = DIV_ROUND_CLOSEST(temp, trip->temp - temp);
-			score = delta * shift;
-			break;
-		}
-		shift *= 256;
-	}
-
-	if (score > thermal->tz_highest_score) {
-		thermal->tz_highest_score = score;
-		thermal->tz_highest_dev = tzdev;
-	}
-}
-
 static int mlxsw_thermal_bind(struct thermal_zone_device *tzdev,
 			      struct thermal_cooling_device *cdev)
 {
@@ -286,9 +255,6 @@ static int mlxsw_thermal_get_temp(struct thermal_zone_device *tzdev,
 		return err;
 	}
 	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL, NULL, NULL);
-	if (temp > 0)
-		mlxsw_thermal_tz_score_update(thermal, tzdev, thermal->trips,
-					      temp);
 
 	*p_temp = temp;
 	return 0;
@@ -349,21 +315,6 @@ static int mlxsw_thermal_set_trip_hyst(struct thermal_zone_device *tzdev,
 	return 0;
 }
 
-static int mlxsw_thermal_trend_get(struct thermal_zone_device *tzdev,
-				   int trip, enum thermal_trend *trend)
-{
-	struct mlxsw_thermal *thermal = tzdev->devdata;
-
-	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
-		return -EINVAL;
-
-	if (tzdev == thermal->tz_highest_dev)
-		return 1;
-
-	*trend = THERMAL_TREND_STABLE;
-	return 0;
-}
-
 static struct thermal_zone_params mlxsw_thermal_params = {
 	.no_hwmon = true,
 };
@@ -377,7 +328,6 @@ static struct thermal_zone_device_ops mlxsw_thermal_ops = {
 	.set_trip_temp	= mlxsw_thermal_set_trip_temp,
 	.get_trip_hyst	= mlxsw_thermal_get_trip_hyst,
 	.set_trip_hyst	= mlxsw_thermal_set_trip_hyst,
-	.get_trend	= mlxsw_thermal_trend_get,
 };
 
 static int mlxsw_thermal_module_bind(struct thermal_zone_device *tzdev,
@@ -463,7 +413,6 @@ static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
 	int temp, crit_temp, emerg_temp;
 	struct device *dev;
 	u16 sensor_index;
-	int err;
 
 	dev = thermal->bus_info->dev;
 	sensor_index = MLXSW_REG_MTMP_MODULE_INDEX_MIN + tz->module;
@@ -479,10 +428,8 @@ static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
 		return 0;
 
 	/* Update trip points. */
-	err = mlxsw_thermal_module_trips_update(dev, thermal->core, tz,
-						crit_temp, emerg_temp);
-	if (!err && temp > 0)
-		mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
+	mlxsw_thermal_module_trips_update(dev, thermal->core, tz,
+					  crit_temp, emerg_temp);
 
 	return 0;
 }
@@ -546,22 +493,6 @@ mlxsw_thermal_module_trip_hyst_set(struct thermal_zone_device *tzdev, int trip,
 	return 0;
 }
 
-static int mlxsw_thermal_module_trend_get(struct thermal_zone_device *tzdev,
-					  int trip, enum thermal_trend *trend)
-{
-	struct mlxsw_thermal_module *tz = tzdev->devdata;
-	struct mlxsw_thermal *thermal = tz->parent;
-
-	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
-		return -EINVAL;
-
-	if (tzdev == thermal->tz_highest_dev)
-		return 1;
-
-	*trend = THERMAL_TREND_STABLE;
-	return 0;
-}
-
 static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
 	.bind		= mlxsw_thermal_module_bind,
 	.unbind		= mlxsw_thermal_module_unbind,
@@ -571,7 +502,6 @@ static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
 	.set_trip_temp	= mlxsw_thermal_module_trip_temp_set,
 	.get_trip_hyst	= mlxsw_thermal_module_trip_hyst_get,
 	.set_trip_hyst	= mlxsw_thermal_module_trip_hyst_set,
-	.get_trend	= mlxsw_thermal_module_trend_get,
 };
 
 static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
@@ -592,8 +522,6 @@ static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
 		return err;
 
 	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL, NULL, NULL);
-	if (temp > 0)
-		mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
 
 	*p_temp = temp;
 	return 0;
@@ -608,7 +536,6 @@ static struct thermal_zone_device_ops mlxsw_thermal_gearbox_ops = {
 	.set_trip_temp	= mlxsw_thermal_module_trip_temp_set,
 	.get_trip_hyst	= mlxsw_thermal_module_trip_hyst_get,
 	.set_trip_hyst	= mlxsw_thermal_module_trip_hyst_set,
-	.get_trend	= mlxsw_thermal_module_trend_get,
 };
 
 static int mlxsw_thermal_get_max_state(struct thermal_cooling_device *cdev,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 1e240cdd9cbd..30c7b0e15721 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1897,9 +1897,9 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u16 local_port)
 
 	cancel_delayed_work_sync(&mlxsw_sp_port->periodic_hw_stats.update_dw);
 	cancel_delayed_work_sync(&mlxsw_sp_port->ptp.shaper_dw);
-	mlxsw_sp_port_ptp_clear(mlxsw_sp_port);
 	mlxsw_core_port_clear(mlxsw_sp->core, local_port, mlxsw_sp);
 	unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
+	mlxsw_sp_port_ptp_clear(mlxsw_sp_port);
 	mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, true, true);
 	mlxsw_sp->ports[local_port] = NULL;
 	mlxsw_sp_port_vlan_flush(mlxsw_sp_port, true);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
index 2e0b704b8a31..7b01b9c20722 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
@@ -46,6 +46,7 @@ struct mlxsw_sp2_ptp_state {
 					  * enabled.
 					  */
 	struct hwtstamp_config config;
+	struct mutex lock; /* Protects 'config' and HW configuration. */
 };
 
 struct mlxsw_sp1_ptp_key {
@@ -1374,6 +1375,7 @@ struct mlxsw_sp_ptp_state *mlxsw_sp2_ptp_init(struct mlxsw_sp *mlxsw_sp)
 		goto err_ptp_traps_set;
 
 	refcount_set(&ptp_state->ptp_port_enabled_ref, 0);
+	mutex_init(&ptp_state->lock);
 	return &ptp_state->common;
 
 err_ptp_traps_set:
@@ -1388,6 +1390,7 @@ void mlxsw_sp2_ptp_fini(struct mlxsw_sp_ptp_state *ptp_state_common)
 
 	ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp);
 
+	mutex_destroy(&ptp_state->lock);
 	mlxsw_sp_ptp_traps_unset(mlxsw_sp);
 	kfree(ptp_state);
 }
@@ -1461,7 +1464,10 @@ int mlxsw_sp2_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp_port->mlxsw_sp);
 
+	mutex_lock(&ptp_state->lock);
 	*config = ptp_state->config;
+	mutex_unlock(&ptp_state->lock);
+
 	return 0;
 }
 
@@ -1523,6 +1529,9 @@ mlxsw_sp2_ptp_get_message_types(const struct hwtstamp_config *config,
 		return -EINVAL;
 	}
 
+	if ((ing_types && !egr_types) || (!ing_types && egr_types))
+		return -EINVAL;
+
 	*p_ing_types = ing_types;
 	*p_egr_types = egr_types;
 	return 0;
@@ -1574,8 +1583,6 @@ static int mlxsw_sp2_ptp_configure_port(struct mlxsw_sp_port *mlxsw_sp_port,
 	struct mlxsw_sp2_ptp_state *ptp_state;
 	int err;
 
-	ASSERT_RTNL();
-
 	ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp_port->mlxsw_sp);
 
 	if (refcount_inc_not_zero(&ptp_state->ptp_port_enabled_ref))
@@ -1597,8 +1604,6 @@ static int mlxsw_sp2_ptp_deconfigure_port(struct mlxsw_sp_port *mlxsw_sp_port,
 	struct mlxsw_sp2_ptp_state *ptp_state;
 	int err;
 
-	ASSERT_RTNL();
-
 	ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp_port->mlxsw_sp);
 
 	if (!refcount_dec_and_test(&ptp_state->ptp_port_enabled_ref))
@@ -1618,16 +1623,20 @@ err_ptp_disable:
 int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 			       struct hwtstamp_config *config)
 {
+	struct mlxsw_sp2_ptp_state *ptp_state;
 	enum hwtstamp_rx_filters rx_filter;
 	struct hwtstamp_config new_config;
 	u16 new_ing_types, new_egr_types;
 	bool ptp_enabled;
 	int err;
 
+	ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp_port->mlxsw_sp);
+	mutex_lock(&ptp_state->lock);
+
 	err = mlxsw_sp2_ptp_get_message_types(config, &new_ing_types,
 					      &new_egr_types, &rx_filter);
 	if (err)
-		return err;
+		goto err_get_message_types;
 
 	new_config.flags = config->flags;
 	new_config.tx_type = config->tx_type;
@@ -1640,11 +1649,11 @@ int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 		err = mlxsw_sp2_ptp_configure_port(mlxsw_sp_port, new_ing_types,
 						   new_egr_types, new_config);
 		if (err)
-			return err;
+			goto err_configure_port;
 	} else if (!new_ing_types && !new_egr_types && ptp_enabled) {
 		err = mlxsw_sp2_ptp_deconfigure_port(mlxsw_sp_port, new_config);
 		if (err)
-			return err;
+			goto err_deconfigure_port;
 	}
 
 	mlxsw_sp_port->ptp.ing_types = new_ing_types;
@@ -1652,8 +1661,15 @@ int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	/* Notify the ioctl caller what we are actually timestamping. */
 	config->rx_filter = rx_filter;
+	mutex_unlock(&ptp_state->lock);
 
 	return 0;
+
+err_deconfigure_port:
+err_configure_port:
+err_get_message_types:
+	mutex_unlock(&ptp_state->lock);
+	return err;
 }
 
 int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
index 2d1628fdefc1..a8b88230959a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
@@ -171,10 +171,11 @@ static inline void mlxsw_sp1_get_stats(struct mlxsw_sp_port *mlxsw_sp_port,
 {
 }
 
-int mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-				 struct mlxsw_sp_port *mlxsw_sp_port,
-				 struct sk_buff *skb,
-				 const struct mlxsw_tx_info *tx_info)
+static inline int
+mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
+			     struct mlxsw_sp_port *mlxsw_sp_port,
+			     struct sk_buff *skb,
+			     const struct mlxsw_tx_info *tx_info)
 {
 	return -EOPNOTSUPP;
 }
@@ -231,10 +232,11 @@ static inline int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
 	return mlxsw_sp_ptp_get_ts_info_noptp(info);
 }
 
-int mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-				  struct mlxsw_sp_port *mlxsw_sp_port,
-				  struct sk_buff *skb,
-				  const struct mlxsw_tx_info *tx_info)
+static inline int
+mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
+			      struct mlxsw_sp_port *mlxsw_sp_port,
+			      struct sk_buff *skb,
+			      const struct mlxsw_tx_info *tx_info)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index 1d6e3b641b2e..d928b75f3780 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -710,7 +710,7 @@ static void lan966x_cleanup_ports(struct lan966x *lan966x)
 	disable_irq(lan966x->xtr_irq);
 	lan966x->xtr_irq = -ENXIO;
 
-	if (lan966x->ana_irq) {
+	if (lan966x->ana_irq > 0) {
 		disable_irq(lan966x->ana_irq);
 		lan966x->ana_irq = -ENXIO;
 	}
@@ -718,10 +718,10 @@ static void lan966x_cleanup_ports(struct lan966x *lan966x)
 	if (lan966x->fdma)
 		devm_free_irq(lan966x->dev, lan966x->fdma_irq, lan966x);
 
-	if (lan966x->ptp_irq)
+	if (lan966x->ptp_irq > 0)
 		devm_free_irq(lan966x->dev, lan966x->ptp_irq, lan966x);
 
-	if (lan966x->ptp_ext_irq)
+	if (lan966x->ptp_ext_irq > 0)
 		devm_free_irq(lan966x->dev, lan966x->ptp_ext_irq, lan966x);
 }
 
@@ -1049,7 +1049,7 @@ static int lan966x_probe(struct platform_device *pdev)
 	}
 
 	lan966x->ana_irq = platform_get_irq_byname(pdev, "ana");
-	if (lan966x->ana_irq) {
+	if (lan966x->ana_irq > 0) {
 		err = devm_request_threaded_irq(&pdev->dev, lan966x->ana_irq, NULL,
 						lan966x_ana_irq_handler, IRQF_ONESHOT,
 						"ana irq", lan966x);
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index a3214a762e4b..19009a6bd33a 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -62,9 +62,6 @@ static int moxart_set_mac_address(struct net_device *ndev, void *addr)
 {
 	struct sockaddr *address = addr;
 
-	if (!is_valid_ether_addr(address->sa_data))
-		return -EADDRNOTAVAIL;
-
 	eth_hw_addr_set(ndev, address->sa_data);
 	moxart_update_mac_address(ndev);
 
@@ -77,7 +74,7 @@ static void moxart_mac_free_memory(struct net_device *ndev)
 	int i;
 
 	for (i = 0; i < RX_DESC_NUM; i++)
-		dma_unmap_single(&ndev->dev, priv->rx_mapping[i],
+		dma_unmap_single(&priv->pdev->dev, priv->rx_mapping[i],
 				 priv->rx_buf_size, DMA_FROM_DEVICE);
 
 	if (priv->tx_desc_base)
@@ -147,11 +144,11 @@ static void moxart_mac_setup_desc_ring(struct net_device *ndev)
 		       desc + RX_REG_OFFSET_DESC1);
 
 		priv->rx_buf[i] = priv->rx_buf_base + priv->rx_buf_size * i;
-		priv->rx_mapping[i] = dma_map_single(&ndev->dev,
+		priv->rx_mapping[i] = dma_map_single(&priv->pdev->dev,
 						     priv->rx_buf[i],
 						     priv->rx_buf_size,
 						     DMA_FROM_DEVICE);
-		if (dma_mapping_error(&ndev->dev, priv->rx_mapping[i]))
+		if (dma_mapping_error(&priv->pdev->dev, priv->rx_mapping[i]))
 			netdev_err(ndev, "DMA mapping error\n");
 
 		moxart_desc_write(priv->rx_mapping[i],
@@ -172,9 +169,6 @@ static int moxart_mac_open(struct net_device *ndev)
 {
 	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
 
-	if (!is_valid_ether_addr(ndev->dev_addr))
-		return -EADDRNOTAVAIL;
-
 	napi_enable(&priv->napi);
 
 	moxart_mac_reset(ndev);
@@ -240,7 +234,7 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget)
 		if (len > RX_BUF_SIZE)
 			len = RX_BUF_SIZE;
 
-		dma_sync_single_for_cpu(&ndev->dev,
+		dma_sync_single_for_cpu(&priv->pdev->dev,
 					priv->rx_mapping[rx_head],
 					priv->rx_buf_size, DMA_FROM_DEVICE);
 		skb = netdev_alloc_skb_ip_align(ndev, len);
@@ -294,7 +288,7 @@ static void moxart_tx_finished(struct net_device *ndev)
 	unsigned int tx_tail = priv->tx_tail;
 
 	while (tx_tail != tx_head) {
-		dma_unmap_single(&ndev->dev, priv->tx_mapping[tx_tail],
+		dma_unmap_single(&priv->pdev->dev, priv->tx_mapping[tx_tail],
 				 priv->tx_len[tx_tail], DMA_TO_DEVICE);
 
 		ndev->stats.tx_packets++;
@@ -358,9 +352,9 @@ static netdev_tx_t moxart_mac_start_xmit(struct sk_buff *skb,
 
 	len = skb->len > TX_BUF_SIZE ? TX_BUF_SIZE : skb->len;
 
-	priv->tx_mapping[tx_head] = dma_map_single(&ndev->dev, skb->data,
+	priv->tx_mapping[tx_head] = dma_map_single(&priv->pdev->dev, skb->data,
 						   len, DMA_TO_DEVICE);
-	if (dma_mapping_error(&ndev->dev, priv->tx_mapping[tx_head])) {
+	if (dma_mapping_error(&priv->pdev->dev, priv->tx_mapping[tx_head])) {
 		netdev_err(ndev, "DMA mapping error\n");
 		goto out_unlock;
 	}
@@ -379,7 +373,7 @@ static netdev_tx_t moxart_mac_start_xmit(struct sk_buff *skb,
 		len = ETH_ZLEN;
 	}
 
-	dma_sync_single_for_device(&ndev->dev, priv->tx_mapping[tx_head],
+	dma_sync_single_for_device(&priv->pdev->dev, priv->tx_mapping[tx_head],
 				   priv->tx_buf_size, DMA_TO_DEVICE);
 
 	txdes1 = TX_DESC1_LTS | TX_DESC1_FTS | (len & TX_DESC1_BUF_SIZE_MASK);
@@ -488,12 +482,19 @@ static int moxart_mac_probe(struct platform_device *pdev)
 	}
 	ndev->base_addr = res->start;
 
+	ret = platform_get_ethdev_address(p_dev, ndev);
+	if (ret == -EPROBE_DEFER)
+		goto init_fail;
+	if (ret)
+		eth_hw_addr_random(ndev);
+	moxart_update_mac_address(ndev);
+
 	spin_lock_init(&priv->txlock);
 
 	priv->tx_buf_size = TX_BUF_SIZE;
 	priv->rx_buf_size = RX_BUF_SIZE;
 
-	priv->tx_desc_base = dma_alloc_coherent(&pdev->dev, TX_REG_DESC_SIZE *
+	priv->tx_desc_base = dma_alloc_coherent(p_dev, TX_REG_DESC_SIZE *
 						TX_DESC_NUM, &priv->tx_base,
 						GFP_DMA | GFP_KERNEL);
 	if (!priv->tx_desc_base) {
@@ -501,7 +502,7 @@ static int moxart_mac_probe(struct platform_device *pdev)
 		goto init_fail;
 	}
 
-	priv->rx_desc_base = dma_alloc_coherent(&pdev->dev, RX_REG_DESC_SIZE *
+	priv->rx_desc_base = dma_alloc_coherent(p_dev, RX_REG_DESC_SIZE *
 						RX_DESC_NUM, &priv->rx_base,
 						GFP_DMA | GFP_KERNEL);
 	if (!priv->rx_desc_base) {
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index d4649e4ee0e7..306026e6aa11 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1860,16 +1860,20 @@ void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data)
 	if (sset != ETH_SS_STATS)
 		return;
 
-	for (i = 0; i < ocelot->num_stats; i++)
+	for (i = 0; i < OCELOT_NUM_STATS; i++) {
+		if (ocelot->stats_layout[i].name[0] == '\0')
+			continue;
+
 		memcpy(data + i * ETH_GSTRING_LEN, ocelot->stats_layout[i].name,
 		       ETH_GSTRING_LEN);
+	}
 }
 EXPORT_SYMBOL(ocelot_get_strings);
 
 /* Caller must hold &ocelot->stats_lock */
 static int ocelot_port_update_stats(struct ocelot *ocelot, int port)
 {
-	unsigned int idx = port * ocelot->num_stats;
+	unsigned int idx = port * OCELOT_NUM_STATS;
 	struct ocelot_stats_region *region;
 	int err, j;
 
@@ -1877,9 +1881,8 @@ static int ocelot_port_update_stats(struct ocelot *ocelot, int port)
 	ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(port), SYS_STAT_CFG);
 
 	list_for_each_entry(region, &ocelot->stats_regions, node) {
-		err = ocelot_bulk_read_rix(ocelot, SYS_COUNT_RX_OCTETS,
-					   region->offset, region->buf,
-					   region->count);
+		err = ocelot_bulk_read(ocelot, region->base, region->buf,
+				       region->count);
 		if (err)
 			return err;
 
@@ -1906,13 +1909,13 @@ static void ocelot_check_stats_work(struct work_struct *work)
 					     stats_work);
 	int i, err;
 
-	mutex_lock(&ocelot->stats_lock);
+	spin_lock(&ocelot->stats_lock);
 	for (i = 0; i < ocelot->num_phys_ports; i++) {
 		err = ocelot_port_update_stats(ocelot, i);
 		if (err)
 			break;
 	}
-	mutex_unlock(&ocelot->stats_lock);
+	spin_unlock(&ocelot->stats_lock);
 
 	if (err)
 		dev_err(ocelot->dev, "Error %d updating ethtool stats\n",  err);
@@ -1925,16 +1928,22 @@ void ocelot_get_ethtool_stats(struct ocelot *ocelot, int port, u64 *data)
 {
 	int i, err;
 
-	mutex_lock(&ocelot->stats_lock);
+	spin_lock(&ocelot->stats_lock);
 
 	/* check and update now */
 	err = ocelot_port_update_stats(ocelot, port);
 
-	/* Copy all counters */
-	for (i = 0; i < ocelot->num_stats; i++)
-		*data++ = ocelot->stats[port * ocelot->num_stats + i];
+	/* Copy all supported counters */
+	for (i = 0; i < OCELOT_NUM_STATS; i++) {
+		int index = port * OCELOT_NUM_STATS + i;
+
+		if (ocelot->stats_layout[i].name[0] == '\0')
+			continue;
+
+		*data++ = ocelot->stats[index];
+	}
 
-	mutex_unlock(&ocelot->stats_lock);
+	spin_unlock(&ocelot->stats_lock);
 
 	if (err)
 		dev_err(ocelot->dev, "Error %d updating ethtool stats\n", err);
@@ -1943,10 +1952,16 @@ EXPORT_SYMBOL(ocelot_get_ethtool_stats);
 
 int ocelot_get_sset_count(struct ocelot *ocelot, int port, int sset)
 {
+	int i, num_stats = 0;
+
 	if (sset != ETH_SS_STATS)
 		return -EOPNOTSUPP;
 
-	return ocelot->num_stats;
+	for (i = 0; i < OCELOT_NUM_STATS; i++)
+		if (ocelot->stats_layout[i].name[0] != '\0')
+			num_stats++;
+
+	return num_stats;
 }
 EXPORT_SYMBOL(ocelot_get_sset_count);
 
@@ -1958,8 +1973,11 @@ static int ocelot_prepare_stats_regions(struct ocelot *ocelot)
 
 	INIT_LIST_HEAD(&ocelot->stats_regions);
 
-	for (i = 0; i < ocelot->num_stats; i++) {
-		if (region && ocelot->stats_layout[i].offset == last + 1) {
+	for (i = 0; i < OCELOT_NUM_STATS; i++) {
+		if (ocelot->stats_layout[i].name[0] == '\0')
+			continue;
+
+		if (region && ocelot->stats_layout[i].reg == last + 4) {
 			region->count++;
 		} else {
 			region = devm_kzalloc(ocelot->dev, sizeof(*region),
@@ -1967,12 +1985,12 @@ static int ocelot_prepare_stats_regions(struct ocelot *ocelot)
 			if (!region)
 				return -ENOMEM;
 
-			region->offset = ocelot->stats_layout[i].offset;
+			region->base = ocelot->stats_layout[i].reg;
 			region->count = 1;
 			list_add_tail(&region->node, &ocelot->stats_regions);
 		}
 
-		last = ocelot->stats_layout[i].offset;
+		last = ocelot->stats_layout[i].reg;
 	}
 
 	list_for_each_entry(region, &ocelot->stats_regions, node) {
@@ -3340,7 +3358,6 @@ static void ocelot_detect_features(struct ocelot *ocelot)
 
 int ocelot_init(struct ocelot *ocelot)
 {
-	const struct ocelot_stat_layout *stat;
 	char queue_name[32];
 	int i, ret;
 	u32 port;
@@ -3353,17 +3370,13 @@ int ocelot_init(struct ocelot *ocelot)
 		}
 	}
 
-	ocelot->num_stats = 0;
-	for_each_stat(ocelot, stat)
-		ocelot->num_stats++;
-
 	ocelot->stats = devm_kcalloc(ocelot->dev,
-				     ocelot->num_phys_ports * ocelot->num_stats,
+				     ocelot->num_phys_ports * OCELOT_NUM_STATS,
 				     sizeof(u64), GFP_KERNEL);
 	if (!ocelot->stats)
 		return -ENOMEM;
 
-	mutex_init(&ocelot->stats_lock);
+	spin_lock_init(&ocelot->stats_lock);
 	mutex_init(&ocelot->ptp_lock);
 	mutex_init(&ocelot->mact_lock);
 	mutex_init(&ocelot->fwd_domain_lock);
@@ -3511,7 +3524,6 @@ void ocelot_deinit(struct ocelot *ocelot)
 	cancel_delayed_work(&ocelot->stats_work);
 	destroy_workqueue(ocelot->stats_queue);
 	destroy_workqueue(ocelot->owq);
-	mutex_destroy(&ocelot->stats_lock);
 }
 EXPORT_SYMBOL(ocelot_deinit);
 
diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c
index 5e6136e80282..330d30841cdc 100644
--- a/drivers/net/ethernet/mscc/ocelot_net.c
+++ b/drivers/net/ethernet/mscc/ocelot_net.c
@@ -725,37 +725,42 @@ static void ocelot_get_stats64(struct net_device *dev,
 	struct ocelot_port_private *priv = netdev_priv(dev);
 	struct ocelot *ocelot = priv->port.ocelot;
 	int port = priv->port.index;
+	u64 *s;
 
-	/* Configure the port to read the stats from */
-	ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(port),
-		     SYS_STAT_CFG);
+	spin_lock(&ocelot->stats_lock);
+
+	s = &ocelot->stats[port * OCELOT_NUM_STATS];
 
 	/* Get Rx stats */
-	stats->rx_bytes = ocelot_read(ocelot, SYS_COUNT_RX_OCTETS);
-	stats->rx_packets = ocelot_read(ocelot, SYS_COUNT_RX_SHORTS) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_FRAGMENTS) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_JABBERS) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_LONGS) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_64) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_65_127) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_128_255) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_256_1023) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_1024_1526) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_1527_MAX);
-	stats->multicast = ocelot_read(ocelot, SYS_COUNT_RX_MULTICAST);
+	stats->rx_bytes = s[OCELOT_STAT_RX_OCTETS];
+	stats->rx_packets = s[OCELOT_STAT_RX_SHORTS] +
+			    s[OCELOT_STAT_RX_FRAGMENTS] +
+			    s[OCELOT_STAT_RX_JABBERS] +
+			    s[OCELOT_STAT_RX_LONGS] +
+			    s[OCELOT_STAT_RX_64] +
+			    s[OCELOT_STAT_RX_65_127] +
+			    s[OCELOT_STAT_RX_128_255] +
+			    s[OCELOT_STAT_RX_256_511] +
+			    s[OCELOT_STAT_RX_512_1023] +
+			    s[OCELOT_STAT_RX_1024_1526] +
+			    s[OCELOT_STAT_RX_1527_MAX];
+	stats->multicast = s[OCELOT_STAT_RX_MULTICAST];
 	stats->rx_dropped = dev->stats.rx_dropped;
 
 	/* Get Tx stats */
-	stats->tx_bytes = ocelot_read(ocelot, SYS_COUNT_TX_OCTETS);
-	stats->tx_packets = ocelot_read(ocelot, SYS_COUNT_TX_64) +
-			    ocelot_read(ocelot, SYS_COUNT_TX_65_127) +
-			    ocelot_read(ocelot, SYS_COUNT_TX_128_511) +
-			    ocelot_read(ocelot, SYS_COUNT_TX_512_1023) +
-			    ocelot_read(ocelot, SYS_COUNT_TX_1024_1526) +
-			    ocelot_read(ocelot, SYS_COUNT_TX_1527_MAX);
-	stats->tx_dropped = ocelot_read(ocelot, SYS_COUNT_TX_DROPS) +
-			    ocelot_read(ocelot, SYS_COUNT_TX_AGING);
-	stats->collisions = ocelot_read(ocelot, SYS_COUNT_TX_COLLISION);
+	stats->tx_bytes = s[OCELOT_STAT_TX_OCTETS];
+	stats->tx_packets = s[OCELOT_STAT_TX_64] +
+			    s[OCELOT_STAT_TX_65_127] +
+			    s[OCELOT_STAT_TX_128_255] +
+			    s[OCELOT_STAT_TX_256_511] +
+			    s[OCELOT_STAT_TX_512_1023] +
+			    s[OCELOT_STAT_TX_1024_1526] +
+			    s[OCELOT_STAT_TX_1527_MAX];
+	stats->tx_dropped = s[OCELOT_STAT_TX_DROPS] +
+			    s[OCELOT_STAT_TX_AGED];
+	stats->collisions = s[OCELOT_STAT_TX_COLLISION];
+
+	spin_unlock(&ocelot->stats_lock);
 }
 
 static int ocelot_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index 961f803aca19..9c488953f541 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -96,101 +96,379 @@ static const struct reg_field ocelot_regfields[REGFIELD_MAX] = {
 	[SYS_PAUSE_CFG_PAUSE_ENA] = REG_FIELD_ID(SYS_PAUSE_CFG, 0, 1, 12, 4),
 };
 
-static const struct ocelot_stat_layout ocelot_stats_layout[] = {
-	{ .name = "rx_octets", .offset = 0x00, },
-	{ .name = "rx_unicast", .offset = 0x01, },
-	{ .name = "rx_multicast", .offset = 0x02, },
-	{ .name = "rx_broadcast", .offset = 0x03, },
-	{ .name = "rx_shorts", .offset = 0x04, },
-	{ .name = "rx_fragments", .offset = 0x05, },
-	{ .name = "rx_jabbers", .offset = 0x06, },
-	{ .name = "rx_crc_align_errs", .offset = 0x07, },
-	{ .name = "rx_sym_errs", .offset = 0x08, },
-	{ .name = "rx_frames_below_65_octets", .offset = 0x09, },
-	{ .name = "rx_frames_65_to_127_octets", .offset = 0x0A, },
-	{ .name = "rx_frames_128_to_255_octets", .offset = 0x0B, },
-	{ .name = "rx_frames_256_to_511_octets", .offset = 0x0C, },
-	{ .name = "rx_frames_512_to_1023_octets", .offset = 0x0D, },
-	{ .name = "rx_frames_1024_to_1526_octets", .offset = 0x0E, },
-	{ .name = "rx_frames_over_1526_octets", .offset = 0x0F, },
-	{ .name = "rx_pause", .offset = 0x10, },
-	{ .name = "rx_control", .offset = 0x11, },
-	{ .name = "rx_longs", .offset = 0x12, },
-	{ .name = "rx_classified_drops", .offset = 0x13, },
-	{ .name = "rx_red_prio_0", .offset = 0x14, },
-	{ .name = "rx_red_prio_1", .offset = 0x15, },
-	{ .name = "rx_red_prio_2", .offset = 0x16, },
-	{ .name = "rx_red_prio_3", .offset = 0x17, },
-	{ .name = "rx_red_prio_4", .offset = 0x18, },
-	{ .name = "rx_red_prio_5", .offset = 0x19, },
-	{ .name = "rx_red_prio_6", .offset = 0x1A, },
-	{ .name = "rx_red_prio_7", .offset = 0x1B, },
-	{ .name = "rx_yellow_prio_0", .offset = 0x1C, },
-	{ .name = "rx_yellow_prio_1", .offset = 0x1D, },
-	{ .name = "rx_yellow_prio_2", .offset = 0x1E, },
-	{ .name = "rx_yellow_prio_3", .offset = 0x1F, },
-	{ .name = "rx_yellow_prio_4", .offset = 0x20, },
-	{ .name = "rx_yellow_prio_5", .offset = 0x21, },
-	{ .name = "rx_yellow_prio_6", .offset = 0x22, },
-	{ .name = "rx_yellow_prio_7", .offset = 0x23, },
-	{ .name = "rx_green_prio_0", .offset = 0x24, },
-	{ .name = "rx_green_prio_1", .offset = 0x25, },
-	{ .name = "rx_green_prio_2", .offset = 0x26, },
-	{ .name = "rx_green_prio_3", .offset = 0x27, },
-	{ .name = "rx_green_prio_4", .offset = 0x28, },
-	{ .name = "rx_green_prio_5", .offset = 0x29, },
-	{ .name = "rx_green_prio_6", .offset = 0x2A, },
-	{ .name = "rx_green_prio_7", .offset = 0x2B, },
-	{ .name = "tx_octets", .offset = 0x40, },
-	{ .name = "tx_unicast", .offset = 0x41, },
-	{ .name = "tx_multicast", .offset = 0x42, },
-	{ .name = "tx_broadcast", .offset = 0x43, },
-	{ .name = "tx_collision", .offset = 0x44, },
-	{ .name = "tx_drops", .offset = 0x45, },
-	{ .name = "tx_pause", .offset = 0x46, },
-	{ .name = "tx_frames_below_65_octets", .offset = 0x47, },
-	{ .name = "tx_frames_65_to_127_octets", .offset = 0x48, },
-	{ .name = "tx_frames_128_255_octets", .offset = 0x49, },
-	{ .name = "tx_frames_256_511_octets", .offset = 0x4A, },
-	{ .name = "tx_frames_512_1023_octets", .offset = 0x4B, },
-	{ .name = "tx_frames_1024_1526_octets", .offset = 0x4C, },
-	{ .name = "tx_frames_over_1526_octets", .offset = 0x4D, },
-	{ .name = "tx_yellow_prio_0", .offset = 0x4E, },
-	{ .name = "tx_yellow_prio_1", .offset = 0x4F, },
-	{ .name = "tx_yellow_prio_2", .offset = 0x50, },
-	{ .name = "tx_yellow_prio_3", .offset = 0x51, },
-	{ .name = "tx_yellow_prio_4", .offset = 0x52, },
-	{ .name = "tx_yellow_prio_5", .offset = 0x53, },
-	{ .name = "tx_yellow_prio_6", .offset = 0x54, },
-	{ .name = "tx_yellow_prio_7", .offset = 0x55, },
-	{ .name = "tx_green_prio_0", .offset = 0x56, },
-	{ .name = "tx_green_prio_1", .offset = 0x57, },
-	{ .name = "tx_green_prio_2", .offset = 0x58, },
-	{ .name = "tx_green_prio_3", .offset = 0x59, },
-	{ .name = "tx_green_prio_4", .offset = 0x5A, },
-	{ .name = "tx_green_prio_5", .offset = 0x5B, },
-	{ .name = "tx_green_prio_6", .offset = 0x5C, },
-	{ .name = "tx_green_prio_7", .offset = 0x5D, },
-	{ .name = "tx_aged", .offset = 0x5E, },
-	{ .name = "drop_local", .offset = 0x80, },
-	{ .name = "drop_tail", .offset = 0x81, },
-	{ .name = "drop_yellow_prio_0", .offset = 0x82, },
-	{ .name = "drop_yellow_prio_1", .offset = 0x83, },
-	{ .name = "drop_yellow_prio_2", .offset = 0x84, },
-	{ .name = "drop_yellow_prio_3", .offset = 0x85, },
-	{ .name = "drop_yellow_prio_4", .offset = 0x86, },
-	{ .name = "drop_yellow_prio_5", .offset = 0x87, },
-	{ .name = "drop_yellow_prio_6", .offset = 0x88, },
-	{ .name = "drop_yellow_prio_7", .offset = 0x89, },
-	{ .name = "drop_green_prio_0", .offset = 0x8A, },
-	{ .name = "drop_green_prio_1", .offset = 0x8B, },
-	{ .name = "drop_green_prio_2", .offset = 0x8C, },
-	{ .name = "drop_green_prio_3", .offset = 0x8D, },
-	{ .name = "drop_green_prio_4", .offset = 0x8E, },
-	{ .name = "drop_green_prio_5", .offset = 0x8F, },
-	{ .name = "drop_green_prio_6", .offset = 0x90, },
-	{ .name = "drop_green_prio_7", .offset = 0x91, },
-	OCELOT_STAT_END
+static const struct ocelot_stat_layout ocelot_stats_layout[OCELOT_NUM_STATS] = {
+	[OCELOT_STAT_RX_OCTETS] = {
+		.name = "rx_octets",
+		.reg = SYS_COUNT_RX_OCTETS,
+	},
+	[OCELOT_STAT_RX_UNICAST] = {
+		.name = "rx_unicast",
+		.reg = SYS_COUNT_RX_UNICAST,
+	},
+	[OCELOT_STAT_RX_MULTICAST] = {
+		.name = "rx_multicast",
+		.reg = SYS_COUNT_RX_MULTICAST,
+	},
+	[OCELOT_STAT_RX_BROADCAST] = {
+		.name = "rx_broadcast",
+		.reg = SYS_COUNT_RX_BROADCAST,
+	},
+	[OCELOT_STAT_RX_SHORTS] = {
+		.name = "rx_shorts",
+		.reg = SYS_COUNT_RX_SHORTS,
+	},
+	[OCELOT_STAT_RX_FRAGMENTS] = {
+		.name = "rx_fragments",
+		.reg = SYS_COUNT_RX_FRAGMENTS,
+	},
+	[OCELOT_STAT_RX_JABBERS] = {
+		.name = "rx_jabbers",
+		.reg = SYS_COUNT_RX_JABBERS,
+	},
+	[OCELOT_STAT_RX_CRC_ALIGN_ERRS] = {
+		.name = "rx_crc_align_errs",
+		.reg = SYS_COUNT_RX_CRC_ALIGN_ERRS,
+	},
+	[OCELOT_STAT_RX_SYM_ERRS] = {
+		.name = "rx_sym_errs",
+		.reg = SYS_COUNT_RX_SYM_ERRS,
+	},
+	[OCELOT_STAT_RX_64] = {
+		.name = "rx_frames_below_65_octets",
+		.reg = SYS_COUNT_RX_64,
+	},
+	[OCELOT_STAT_RX_65_127] = {
+		.name = "rx_frames_65_to_127_octets",
+		.reg = SYS_COUNT_RX_65_127,
+	},
+	[OCELOT_STAT_RX_128_255] = {
+		.name = "rx_frames_128_to_255_octets",
+		.reg = SYS_COUNT_RX_128_255,
+	},
+	[OCELOT_STAT_RX_256_511] = {
+		.name = "rx_frames_256_to_511_octets",
+		.reg = SYS_COUNT_RX_256_511,
+	},
+	[OCELOT_STAT_RX_512_1023] = {
+		.name = "rx_frames_512_to_1023_octets",
+		.reg = SYS_COUNT_RX_512_1023,
+	},
+	[OCELOT_STAT_RX_1024_1526] = {
+		.name = "rx_frames_1024_to_1526_octets",
+		.reg = SYS_COUNT_RX_1024_1526,
+	},
+	[OCELOT_STAT_RX_1527_MAX] = {
+		.name = "rx_frames_over_1526_octets",
+		.reg = SYS_COUNT_RX_1527_MAX,
+	},
+	[OCELOT_STAT_RX_PAUSE] = {
+		.name = "rx_pause",
+		.reg = SYS_COUNT_RX_PAUSE,
+	},
+	[OCELOT_STAT_RX_CONTROL] = {
+		.name = "rx_control",
+		.reg = SYS_COUNT_RX_CONTROL,
+	},
+	[OCELOT_STAT_RX_LONGS] = {
+		.name = "rx_longs",
+		.reg = SYS_COUNT_RX_LONGS,
+	},
+	[OCELOT_STAT_RX_CLASSIFIED_DROPS] = {
+		.name = "rx_classified_drops",
+		.reg = SYS_COUNT_RX_CLASSIFIED_DROPS,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_0] = {
+		.name = "rx_red_prio_0",
+		.reg = SYS_COUNT_RX_RED_PRIO_0,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_1] = {
+		.name = "rx_red_prio_1",
+		.reg = SYS_COUNT_RX_RED_PRIO_1,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_2] = {
+		.name = "rx_red_prio_2",
+		.reg = SYS_COUNT_RX_RED_PRIO_2,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_3] = {
+		.name = "rx_red_prio_3",
+		.reg = SYS_COUNT_RX_RED_PRIO_3,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_4] = {
+		.name = "rx_red_prio_4",
+		.reg = SYS_COUNT_RX_RED_PRIO_4,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_5] = {
+		.name = "rx_red_prio_5",
+		.reg = SYS_COUNT_RX_RED_PRIO_5,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_6] = {
+		.name = "rx_red_prio_6",
+		.reg = SYS_COUNT_RX_RED_PRIO_6,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_7] = {
+		.name = "rx_red_prio_7",
+		.reg = SYS_COUNT_RX_RED_PRIO_7,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_0] = {
+		.name = "rx_yellow_prio_0",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_1] = {
+		.name = "rx_yellow_prio_1",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_2] = {
+		.name = "rx_yellow_prio_2",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_3] = {
+		.name = "rx_yellow_prio_3",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_4] = {
+		.name = "rx_yellow_prio_4",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_5] = {
+		.name = "rx_yellow_prio_5",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_6] = {
+		.name = "rx_yellow_prio_6",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_7] = {
+		.name = "rx_yellow_prio_7",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_0] = {
+		.name = "rx_green_prio_0",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_1] = {
+		.name = "rx_green_prio_1",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_2] = {
+		.name = "rx_green_prio_2",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_3] = {
+		.name = "rx_green_prio_3",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_4] = {
+		.name = "rx_green_prio_4",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_5] = {
+		.name = "rx_green_prio_5",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_6] = {
+		.name = "rx_green_prio_6",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_7] = {
+		.name = "rx_green_prio_7",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_7,
+	},
+	[OCELOT_STAT_TX_OCTETS] = {
+		.name = "tx_octets",
+		.reg = SYS_COUNT_TX_OCTETS,
+	},
+	[OCELOT_STAT_TX_UNICAST] = {
+		.name = "tx_unicast",
+		.reg = SYS_COUNT_TX_UNICAST,
+	},
+	[OCELOT_STAT_TX_MULTICAST] = {
+		.name = "tx_multicast",
+		.reg = SYS_COUNT_TX_MULTICAST,
+	},
+	[OCELOT_STAT_TX_BROADCAST] = {
+		.name = "tx_broadcast",
+		.reg = SYS_COUNT_TX_BROADCAST,
+	},
+	[OCELOT_STAT_TX_COLLISION] = {
+		.name = "tx_collision",
+		.reg = SYS_COUNT_TX_COLLISION,
+	},
+	[OCELOT_STAT_TX_DROPS] = {
+		.name = "tx_drops",
+		.reg = SYS_COUNT_TX_DROPS,
+	},
+	[OCELOT_STAT_TX_PAUSE] = {
+		.name = "tx_pause",
+		.reg = SYS_COUNT_TX_PAUSE,
+	},
+	[OCELOT_STAT_TX_64] = {
+		.name = "tx_frames_below_65_octets",
+		.reg = SYS_COUNT_TX_64,
+	},
+	[OCELOT_STAT_TX_65_127] = {
+		.name = "tx_frames_65_to_127_octets",
+		.reg = SYS_COUNT_TX_65_127,
+	},
+	[OCELOT_STAT_TX_128_255] = {
+		.name = "tx_frames_128_255_octets",
+		.reg = SYS_COUNT_TX_128_255,
+	},
+	[OCELOT_STAT_TX_256_511] = {
+		.name = "tx_frames_256_511_octets",
+		.reg = SYS_COUNT_TX_256_511,
+	},
+	[OCELOT_STAT_TX_512_1023] = {
+		.name = "tx_frames_512_1023_octets",
+		.reg = SYS_COUNT_TX_512_1023,
+	},
+	[OCELOT_STAT_TX_1024_1526] = {
+		.name = "tx_frames_1024_1526_octets",
+		.reg = SYS_COUNT_TX_1024_1526,
+	},
+	[OCELOT_STAT_TX_1527_MAX] = {
+		.name = "tx_frames_over_1526_octets",
+		.reg = SYS_COUNT_TX_1527_MAX,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_0] = {
+		.name = "tx_yellow_prio_0",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_1] = {
+		.name = "tx_yellow_prio_1",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_2] = {
+		.name = "tx_yellow_prio_2",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_3] = {
+		.name = "tx_yellow_prio_3",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_4] = {
+		.name = "tx_yellow_prio_4",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_5] = {
+		.name = "tx_yellow_prio_5",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_6] = {
+		.name = "tx_yellow_prio_6",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_7] = {
+		.name = "tx_yellow_prio_7",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_0] = {
+		.name = "tx_green_prio_0",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_1] = {
+		.name = "tx_green_prio_1",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_2] = {
+		.name = "tx_green_prio_2",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_3] = {
+		.name = "tx_green_prio_3",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_4] = {
+		.name = "tx_green_prio_4",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_5] = {
+		.name = "tx_green_prio_5",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_6] = {
+		.name = "tx_green_prio_6",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_7] = {
+		.name = "tx_green_prio_7",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_7,
+	},
+	[OCELOT_STAT_TX_AGED] = {
+		.name = "tx_aged",
+		.reg = SYS_COUNT_TX_AGING,
+	},
+	[OCELOT_STAT_DROP_LOCAL] = {
+		.name = "drop_local",
+		.reg = SYS_COUNT_DROP_LOCAL,
+	},
+	[OCELOT_STAT_DROP_TAIL] = {
+		.name = "drop_tail",
+		.reg = SYS_COUNT_DROP_TAIL,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_0] = {
+		.name = "drop_yellow_prio_0",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_1] = {
+		.name = "drop_yellow_prio_1",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_2] = {
+		.name = "drop_yellow_prio_2",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_3] = {
+		.name = "drop_yellow_prio_3",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_4] = {
+		.name = "drop_yellow_prio_4",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_5] = {
+		.name = "drop_yellow_prio_5",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_6] = {
+		.name = "drop_yellow_prio_6",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_7] = {
+		.name = "drop_yellow_prio_7",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_0] = {
+		.name = "drop_green_prio_0",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_1] = {
+		.name = "drop_green_prio_1",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_2] = {
+		.name = "drop_green_prio_2",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_3] = {
+		.name = "drop_green_prio_3",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_4] = {
+		.name = "drop_green_prio_4",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_5] = {
+		.name = "drop_green_prio_5",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_6] = {
+		.name = "drop_green_prio_6",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_7] = {
+		.name = "drop_green_prio_7",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_7,
+	},
 };
 
 static void ocelot_pll5_init(struct ocelot *ocelot)
diff --git a/drivers/net/ethernet/mscc/vsc7514_regs.c b/drivers/net/ethernet/mscc/vsc7514_regs.c
index c2af4eb8ca5d..9cf82ecf191c 100644
--- a/drivers/net/ethernet/mscc/vsc7514_regs.c
+++ b/drivers/net/ethernet/mscc/vsc7514_regs.c
@@ -180,13 +180,38 @@ const u32 vsc7514_sys_regmap[] = {
 	REG(SYS_COUNT_RX_64,				0x000024),
 	REG(SYS_COUNT_RX_65_127,			0x000028),
 	REG(SYS_COUNT_RX_128_255,			0x00002c),
-	REG(SYS_COUNT_RX_256_1023,			0x000030),
-	REG(SYS_COUNT_RX_1024_1526,			0x000034),
-	REG(SYS_COUNT_RX_1527_MAX,			0x000038),
-	REG(SYS_COUNT_RX_PAUSE,				0x00003c),
-	REG(SYS_COUNT_RX_CONTROL,			0x000040),
-	REG(SYS_COUNT_RX_LONGS,				0x000044),
-	REG(SYS_COUNT_RX_CLASSIFIED_DROPS,		0x000048),
+	REG(SYS_COUNT_RX_256_511,			0x000030),
+	REG(SYS_COUNT_RX_512_1023,			0x000034),
+	REG(SYS_COUNT_RX_1024_1526,			0x000038),
+	REG(SYS_COUNT_RX_1527_MAX,			0x00003c),
+	REG(SYS_COUNT_RX_PAUSE,				0x000040),
+	REG(SYS_COUNT_RX_CONTROL,			0x000044),
+	REG(SYS_COUNT_RX_LONGS,				0x000048),
+	REG(SYS_COUNT_RX_CLASSIFIED_DROPS,		0x00004c),
+	REG(SYS_COUNT_RX_RED_PRIO_0,			0x000050),
+	REG(SYS_COUNT_RX_RED_PRIO_1,			0x000054),
+	REG(SYS_COUNT_RX_RED_PRIO_2,			0x000058),
+	REG(SYS_COUNT_RX_RED_PRIO_3,			0x00005c),
+	REG(SYS_COUNT_RX_RED_PRIO_4,			0x000060),
+	REG(SYS_COUNT_RX_RED_PRIO_5,			0x000064),
+	REG(SYS_COUNT_RX_RED_PRIO_6,			0x000068),
+	REG(SYS_COUNT_RX_RED_PRIO_7,			0x00006c),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_0,			0x000070),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_1,			0x000074),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_2,			0x000078),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_3,			0x00007c),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_4,			0x000080),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_5,			0x000084),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_6,			0x000088),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_7,			0x00008c),
+	REG(SYS_COUNT_RX_GREEN_PRIO_0,			0x000090),
+	REG(SYS_COUNT_RX_GREEN_PRIO_1,			0x000094),
+	REG(SYS_COUNT_RX_GREEN_PRIO_2,			0x000098),
+	REG(SYS_COUNT_RX_GREEN_PRIO_3,			0x00009c),
+	REG(SYS_COUNT_RX_GREEN_PRIO_4,			0x0000a0),
+	REG(SYS_COUNT_RX_GREEN_PRIO_5,			0x0000a4),
+	REG(SYS_COUNT_RX_GREEN_PRIO_6,			0x0000a8),
+	REG(SYS_COUNT_RX_GREEN_PRIO_7,			0x0000ac),
 	REG(SYS_COUNT_TX_OCTETS,			0x000100),
 	REG(SYS_COUNT_TX_UNICAST,			0x000104),
 	REG(SYS_COUNT_TX_MULTICAST,			0x000108),
@@ -196,11 +221,46 @@ const u32 vsc7514_sys_regmap[] = {
 	REG(SYS_COUNT_TX_PAUSE,				0x000118),
 	REG(SYS_COUNT_TX_64,				0x00011c),
 	REG(SYS_COUNT_TX_65_127,			0x000120),
-	REG(SYS_COUNT_TX_128_511,			0x000124),
-	REG(SYS_COUNT_TX_512_1023,			0x000128),
-	REG(SYS_COUNT_TX_1024_1526,			0x00012c),
-	REG(SYS_COUNT_TX_1527_MAX,			0x000130),
-	REG(SYS_COUNT_TX_AGING,				0x000170),
+	REG(SYS_COUNT_TX_128_255,			0x000124),
+	REG(SYS_COUNT_TX_256_511,			0x000128),
+	REG(SYS_COUNT_TX_512_1023,			0x00012c),
+	REG(SYS_COUNT_TX_1024_1526,			0x000130),
+	REG(SYS_COUNT_TX_1527_MAX,			0x000134),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_0,			0x000138),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_1,			0x00013c),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_2,			0x000140),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_3,			0x000144),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_4,			0x000148),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_5,			0x00014c),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_6,			0x000150),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_7,			0x000154),
+	REG(SYS_COUNT_TX_GREEN_PRIO_0,			0x000158),
+	REG(SYS_COUNT_TX_GREEN_PRIO_1,			0x00015c),
+	REG(SYS_COUNT_TX_GREEN_PRIO_2,			0x000160),
+	REG(SYS_COUNT_TX_GREEN_PRIO_3,			0x000164),
+	REG(SYS_COUNT_TX_GREEN_PRIO_4,			0x000168),
+	REG(SYS_COUNT_TX_GREEN_PRIO_5,			0x00016c),
+	REG(SYS_COUNT_TX_GREEN_PRIO_6,			0x000170),
+	REG(SYS_COUNT_TX_GREEN_PRIO_7,			0x000174),
+	REG(SYS_COUNT_TX_AGING,				0x000178),
+	REG(SYS_COUNT_DROP_LOCAL,			0x000200),
+	REG(SYS_COUNT_DROP_TAIL,			0x000204),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_0,		0x000208),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_1,		0x00020c),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_2,		0x000210),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_3,		0x000214),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_4,		0x000218),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_5,		0x00021c),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_6,		0x000220),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_7,		0x000214),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_0,		0x000218),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_1,		0x00021c),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_2,		0x000220),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_3,		0x000224),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_4,		0x000228),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_5,		0x00022c),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_6,		0x000230),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_7,		0x000234),
 	REG(SYS_RESET_CFG,				0x000508),
 	REG(SYS_CMID,					0x00050c),
 	REG(SYS_VLAN_ETYPE_CFG,				0x000510),
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 52f9ed8db9c9..4f2b82a884b9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -1134,6 +1134,7 @@ static void intel_eth_pci_remove(struct pci_dev *pdev)
 
 	stmmac_dvr_remove(&pdev->dev);
 
+	clk_disable_unprepare(priv->plat->stmmac_clk);
 	clk_unregister_fixed_rate(priv->plat->stmmac_clk);
 
 	pcim_iounmap_regions(pdev, BIT(0));
diff --git a/drivers/net/fddi/skfp/h/hwmtm.h b/drivers/net/fddi/skfp/h/hwmtm.h
index 76c4a709d73d..e97db826cdd4 100644
--- a/drivers/net/fddi/skfp/h/hwmtm.h
+++ b/drivers/net/fddi/skfp/h/hwmtm.h
@@ -348,7 +348,7 @@ do {									\
  *		This macro is invoked by the OS-specific before it left the
  *		function mac_drv_rx_complete. This macro calls mac_drv_fill_rxd
  *		if the number of used RxDs is equal or lower than the
- *		the given low water mark.
+ *		given low water mark.
  *
  * para	low_water	low water mark of used RxD's
  *
diff --git a/drivers/net/ipa/ipa_reg.h b/drivers/net/ipa/ipa_reg.h
index a5b355384d4a..6f35438cda89 100644
--- a/drivers/net/ipa/ipa_reg.h
+++ b/drivers/net/ipa/ipa_reg.h
@@ -48,7 +48,7 @@ struct ipa;
  *
  * The offset of registers related to resource types is computed by a macro
  * that is supplied a parameter "rt".  The "rt" represents a resource type,
- * which is is a member of the ipa_resource_type_src enumerated type for
+ * which is a member of the ipa_resource_type_src enumerated type for
  * source endpoint resources or the ipa_resource_type_dst enumerated type
  * for destination endpoint resources.
  *
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d934774e9733..9cce7dec7366 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1211,7 +1211,7 @@ static void virtio_skb_set_hash(const struct virtio_net_hdr_v1_hash *hdr_hash,
 	if (!hdr_hash || !skb)
 		return;
 
-	switch ((int)hdr_hash->hash_report) {
+	switch (__le16_to_cpu(hdr_hash->hash_report)) {
 	case VIRTIO_NET_HASH_REPORT_TCPv4:
 	case VIRTIO_NET_HASH_REPORT_UDPv4:
 	case VIRTIO_NET_HASH_REPORT_TCPv6:
@@ -1229,7 +1229,7 @@ static void virtio_skb_set_hash(const struct virtio_net_hdr_v1_hash *hdr_hash,
 	default:
 		rss_hash_type = PKT_HASH_TYPE_NONE;
 	}
-	skb_set_hash(skb, (unsigned int)hdr_hash->hash_value, rss_hash_type);
+	skb_set_hash(skb, __le32_to_cpu(hdr_hash->hash_value), rss_hash_type);
 }
 
 static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
@@ -3432,29 +3432,6 @@ static unsigned int mergeable_min_buf_len(struct virtnet_info *vi, struct virtqu
 		   (unsigned int)GOOD_PACKET_LEN);
 }
 
-static void virtnet_config_sizes(struct virtnet_info *vi, u32 *sizes)
-{
-	u32 i, rx_size, tx_size;
-
-	if (vi->speed == SPEED_UNKNOWN || vi->speed < SPEED_10000) {
-		rx_size = 1024;
-		tx_size = 1024;
-
-	} else if (vi->speed < SPEED_40000) {
-		rx_size = 1024 * 4;
-		tx_size = 1024 * 4;
-
-	} else {
-		rx_size = 1024 * 8;
-		tx_size = 1024 * 8;
-	}
-
-	for (i = 0; i < vi->max_queue_pairs; i++) {
-		sizes[rxq2vq(i)] = rx_size;
-		sizes[txq2vq(i)] = tx_size;
-	}
-}
-
 static int virtnet_find_vqs(struct virtnet_info *vi)
 {
 	vq_callback_t **callbacks;
@@ -3462,7 +3439,6 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 	int ret = -ENOMEM;
 	int i, total_vqs;
 	const char **names;
-	u32 *sizes;
 	bool *ctx;
 
 	/* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by
@@ -3490,15 +3466,10 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 		ctx = NULL;
 	}
 
-	sizes = kmalloc_array(total_vqs, sizeof(*sizes), GFP_KERNEL);
-	if (!sizes)
-		goto err_sizes;
-
 	/* Parameters for control virtqueue, if any */
 	if (vi->has_cvq) {
 		callbacks[total_vqs - 1] = NULL;
 		names[total_vqs - 1] = "control";
-		sizes[total_vqs - 1] = 64;
 	}
 
 	/* Allocate/initialize parameters for send/receive virtqueues */
@@ -3513,10 +3484,8 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 			ctx[rxq2vq(i)] = true;
 	}
 
-	virtnet_config_sizes(vi, sizes);
-
-	ret = virtio_find_vqs_ctx_size(vi->vdev, total_vqs, vqs, callbacks,
-				       names, sizes, ctx, NULL);
+	ret = virtio_find_vqs_ctx(vi->vdev, total_vqs, vqs, callbacks,
+				  names, ctx, NULL);
 	if (ret)
 		goto err_find;
 
@@ -3536,8 +3505,6 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 
 
 err_find:
-	kfree(sizes);
-err_sizes:
 	kfree(ctx);
 err_ctx:
 	kfree(names);
@@ -3897,9 +3864,6 @@ static int virtnet_probe(struct virtio_device *vdev)
 		vi->curr_queue_pairs = num_online_cpus();
 	vi->max_queue_pairs = max_queue_pairs;
 
-	virtnet_init_settings(dev);
-	virtnet_update_settings(vi);
-
 	/* Allocate/initialize the rx/tx queues, and invoke find_vqs */
 	err = init_vqs(vi);
 	if (err)
@@ -3912,6 +3876,8 @@ static int virtnet_probe(struct virtio_device *vdev)
 	netif_set_real_num_tx_queues(dev, vi->curr_queue_pairs);
 	netif_set_real_num_rx_queues(dev, vi->curr_queue_pairs);
 
+	virtnet_init_settings(dev);
+
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_STANDBY)) {
 		vi->failover = net_failover_create(vi->dev);
 		if (IS_ERR(vi->failover)) {
diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c
index 342778782359..2c20b0de8cb0 100644
--- a/drivers/perf/riscv_pmu_legacy.c
+++ b/drivers/perf/riscv_pmu_legacy.c
@@ -72,7 +72,7 @@ static void pmu_legacy_ctr_start(struct perf_event *event, u64 ival)
 	local64_set(&hwc->prev_count, initial_val);
 }
 
-/**
+/*
  * This is just a simple implementation to allow legacy implementations
  * compatible with new RISC-V PMU driver framework.
  * This driver only allows reading two counters i.e CYCLE & INSTRET.
diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c
index 8be13d416f48..1ae3c56b66b0 100644
--- a/drivers/platform/mellanox/mlxbf-tmfifo.c
+++ b/drivers/platform/mellanox/mlxbf-tmfifo.c
@@ -928,7 +928,6 @@ static int mlxbf_tmfifo_virtio_find_vqs(struct virtio_device *vdev,
 					struct virtqueue *vqs[],
 					vq_callback_t *callbacks[],
 					const char * const names[],
-					u32 sizes[],
 					const bool *ctx,
 					struct irq_affinity *desc)
 {
diff --git a/drivers/platform/x86/serial-multi-instantiate.c b/drivers/platform/x86/serial-multi-instantiate.c
index 67feed25c9db..5362f1a7b77c 100644
--- a/drivers/platform/x86/serial-multi-instantiate.c
+++ b/drivers/platform/x86/serial-multi-instantiate.c
@@ -328,6 +328,7 @@ static const struct acpi_device_id smi_acpi_ids[] = {
 	{ "INT3515", (unsigned long)&int3515_data },
 	/* Non-conforming _HID for Cirrus Logic already released */
 	{ "CLSA0100", (unsigned long)&cs35l41_hda },
+	{ "CLSA0101", (unsigned long)&cs35l41_hda },
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, smi_acpi_ids);
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 7150b1d0159e..d8373cb04f90 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -4784,10 +4784,10 @@ int regulator_bulk_get(struct device *dev, int num_consumers,
 		consumers[i].consumer = regulator_get(dev,
 						      consumers[i].supply);
 		if (IS_ERR(consumers[i].consumer)) {
-			consumers[i].consumer = NULL;
 			ret = dev_err_probe(dev, PTR_ERR(consumers[i].consumer),
 					    "Failed to get supply '%s'",
 					    consumers[i].supply);
+			consumers[i].consumer = NULL;
 			goto err;
 		}
 
diff --git a/drivers/regulator/max8973-regulator.c b/drivers/regulator/max8973-regulator.c
index fdcb0f508984..596cc36aaff6 100644
--- a/drivers/regulator/max8973-regulator.c
+++ b/drivers/regulator/max8973-regulator.c
@@ -434,9 +434,9 @@ static int max8973_init_dcdc(struct max8973_chip *max,
 	return ret;
 }
 
-static int max8973_thermal_read_temp(void *data, int *temp)
+static int max8973_thermal_read_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct max8973_chip *mchip = data;
+	struct max8973_chip *mchip = tz->devdata;
 	unsigned int val;
 	int ret;
 
@@ -465,7 +465,7 @@ static irqreturn_t max8973_thermal_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static const struct thermal_zone_of_device_ops max77621_tz_ops = {
+static const struct thermal_zone_device_ops max77621_tz_ops = {
 	.get_temp = max8973_thermal_read_temp,
 };
 
@@ -479,8 +479,8 @@ static int max8973_thermal_init(struct max8973_chip *mchip)
 	if (mchip->id != MAX77621)
 		return 0;
 
-	tzd = devm_thermal_zone_of_sensor_register(mchip->dev, 0, mchip,
-						   &max77621_tz_ops);
+	tzd = devm_thermal_of_zone_register(mchip->dev, 0, mchip,
+					    &max77621_tz_ops);
 	if (IS_ERR(tzd)) {
 		ret = PTR_ERR(tzd);
 		dev_err(mchip->dev, "Failed to register thermal sensor: %d\n",
diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c
index 81c4f5776109..0f7706e23eb9 100644
--- a/drivers/remoteproc/remoteproc_virtio.c
+++ b/drivers/remoteproc/remoteproc_virtio.c
@@ -158,7 +158,6 @@ static int rproc_virtio_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 				 struct virtqueue *vqs[],
 				 vq_callback_t *callbacks[],
 				 const char * const names[],
-				 u32 sizes[],
 				 const bool * ctx,
 				 struct irq_affinity *desc)
 {
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 8f1d1cf23d44..59ac98f2bd27 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -2086,6 +2086,9 @@ static inline void ap_scan_adapter(int ap)
  */
 static bool ap_get_configuration(void)
 {
+	if (!ap_qci_info)	/* QCI not supported */
+		return false;
+
 	memcpy(ap_qci_info_old, ap_qci_info, sizeof(*ap_qci_info));
 	ap_fetch_qci_info(ap_qci_info);
 
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 0c40af157df2..0f17933954fb 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -148,12 +148,16 @@ struct ap_driver {
 	/*
 	 * Called at the start of the ap bus scan function when
 	 * the crypto config information (qci) has changed.
+	 * This callback is not invoked if there is no AP
+	 * QCI support available.
 	 */
 	void (*on_config_changed)(struct ap_config_info *new_config_info,
 				  struct ap_config_info *old_config_info);
 	/*
 	 * Called at the end of the ap bus scan function when
 	 * the crypto config information (qci) has changed.
+	 * This callback is not invoked if there is no AP
+	 * QCI support available.
 	 */
 	void (*on_scan_complete)(struct ap_config_info *new_config_info,
 				 struct ap_config_info *old_config_info);
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index 896896e32664..a10dbe632ef9 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -637,7 +637,6 @@ static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 			       struct virtqueue *vqs[],
 			       vq_callback_t *callbacks[],
 			       const char * const names[],
-			       u32 sizes[],
 			       const bool *ctx,
 			       struct irq_affinity *desc)
 {
diff --git a/drivers/spi/spi-meson-spicc.c b/drivers/spi/spi-meson-spicc.c
index 0bc7daa7afc8..e4cb52e1fe26 100644
--- a/drivers/spi/spi-meson-spicc.c
+++ b/drivers/spi/spi-meson-spicc.c
@@ -156,6 +156,7 @@ struct meson_spicc_device {
 	void __iomem			*base;
 	struct clk			*core;
 	struct clk			*pclk;
+	struct clk_divider		pow2_div;
 	struct clk			*clk;
 	struct spi_message		*message;
 	struct spi_transfer		*xfer;
@@ -168,6 +169,8 @@ struct meson_spicc_device {
 	unsigned long			xfer_remain;
 };
 
+#define pow2_clk_to_spicc(_div) container_of(_div, struct meson_spicc_device, pow2_div)
+
 static void meson_spicc_oen_enable(struct meson_spicc_device *spicc)
 {
 	u32 conf;
@@ -421,7 +424,7 @@ static int meson_spicc_prepare_message(struct spi_master *master,
 {
 	struct meson_spicc_device *spicc = spi_master_get_devdata(master);
 	struct spi_device *spi = message->spi;
-	u32 conf = 0;
+	u32 conf = readl_relaxed(spicc->base + SPICC_CONREG) & SPICC_DATARATE_MASK;
 
 	/* Store current message */
 	spicc->message = message;
@@ -458,8 +461,6 @@ static int meson_spicc_prepare_message(struct spi_master *master,
 	/* Select CS */
 	conf |= FIELD_PREP(SPICC_CS_MASK, spi->chip_select);
 
-	/* Default Clock rate core/4 */
-
 	/* Default 8bit word */
 	conf |= FIELD_PREP(SPICC_BITLENGTH_MASK, 8 - 1);
 
@@ -476,12 +477,16 @@ static int meson_spicc_prepare_message(struct spi_master *master,
 static int meson_spicc_unprepare_transfer(struct spi_master *master)
 {
 	struct meson_spicc_device *spicc = spi_master_get_devdata(master);
+	u32 conf = readl_relaxed(spicc->base + SPICC_CONREG) & SPICC_DATARATE_MASK;
 
 	/* Disable all IRQs */
 	writel(0, spicc->base + SPICC_INTREG);
 
 	device_reset_optional(&spicc->pdev->dev);
 
+	/* Set default configuration, keeping datarate field */
+	writel_relaxed(conf, spicc->base + SPICC_CONREG);
+
 	return 0;
 }
 
@@ -518,14 +523,60 @@ static void meson_spicc_cleanup(struct spi_device *spi)
  * Clk path for G12A series:
  *    pclk -> pow2 fixed div -> pow2 div -> mux -> out
  *    pclk -> enh fixed div -> enh div -> mux -> out
+ *
+ * The pow2 divider is tied to the controller HW state, and the
+ * divider is only valid when the controller is initialized.
+ *
+ * A set of clock ops is added to make sure we don't read/set this
+ * clock rate while the controller is in an unknown state.
  */
 
-static int meson_spicc_clk_init(struct meson_spicc_device *spicc)
+static unsigned long meson_spicc_pow2_recalc_rate(struct clk_hw *hw,
+						  unsigned long parent_rate)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	struct meson_spicc_device *spicc = pow2_clk_to_spicc(divider);
+
+	if (!spicc->master->cur_msg || !spicc->master->busy)
+		return 0;
+
+	return clk_divider_ops.recalc_rate(hw, parent_rate);
+}
+
+static int meson_spicc_pow2_determine_rate(struct clk_hw *hw,
+					   struct clk_rate_request *req)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	struct meson_spicc_device *spicc = pow2_clk_to_spicc(divider);
+
+	if (!spicc->master->cur_msg || !spicc->master->busy)
+		return -EINVAL;
+
+	return clk_divider_ops.determine_rate(hw, req);
+}
+
+static int meson_spicc_pow2_set_rate(struct clk_hw *hw, unsigned long rate,
+				     unsigned long parent_rate)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	struct meson_spicc_device *spicc = pow2_clk_to_spicc(divider);
+
+	if (!spicc->master->cur_msg || !spicc->master->busy)
+		return -EINVAL;
+
+	return clk_divider_ops.set_rate(hw, rate, parent_rate);
+}
+
+const struct clk_ops meson_spicc_pow2_clk_ops = {
+	.recalc_rate = meson_spicc_pow2_recalc_rate,
+	.determine_rate = meson_spicc_pow2_determine_rate,
+	.set_rate = meson_spicc_pow2_set_rate,
+};
+
+static int meson_spicc_pow2_clk_init(struct meson_spicc_device *spicc)
 {
 	struct device *dev = &spicc->pdev->dev;
-	struct clk_fixed_factor *pow2_fixed_div, *enh_fixed_div;
-	struct clk_divider *pow2_div, *enh_div;
-	struct clk_mux *mux;
+	struct clk_fixed_factor *pow2_fixed_div;
 	struct clk_init_data init;
 	struct clk *clk;
 	struct clk_parent_data parent_data[2];
@@ -560,31 +611,45 @@ static int meson_spicc_clk_init(struct meson_spicc_device *spicc)
 	if (WARN_ON(IS_ERR(clk)))
 		return PTR_ERR(clk);
 
-	pow2_div = devm_kzalloc(dev, sizeof(*pow2_div), GFP_KERNEL);
-	if (!pow2_div)
-		return -ENOMEM;
-
 	snprintf(name, sizeof(name), "%s#pow2_div", dev_name(dev));
 	init.name = name;
-	init.ops = &clk_divider_ops;
-	init.flags = CLK_SET_RATE_PARENT;
+	init.ops = &meson_spicc_pow2_clk_ops;
+	/*
+	 * Set NOCACHE here to make sure we read the actual HW value
+	 * since we reset the HW after each transfer.
+	 */
+	init.flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE;
 	parent_data[0].hw = &pow2_fixed_div->hw;
 	init.num_parents = 1;
 
-	pow2_div->shift = 16,
-	pow2_div->width = 3,
-	pow2_div->flags = CLK_DIVIDER_POWER_OF_TWO,
-	pow2_div->reg = spicc->base + SPICC_CONREG;
-	pow2_div->hw.init = &init;
+	spicc->pow2_div.shift = 16,
+	spicc->pow2_div.width = 3,
+	spicc->pow2_div.flags = CLK_DIVIDER_POWER_OF_TWO,
+	spicc->pow2_div.reg = spicc->base + SPICC_CONREG;
+	spicc->pow2_div.hw.init = &init;
 
-	clk = devm_clk_register(dev, &pow2_div->hw);
-	if (WARN_ON(IS_ERR(clk)))
-		return PTR_ERR(clk);
+	spicc->clk = devm_clk_register(dev, &spicc->pow2_div.hw);
+	if (WARN_ON(IS_ERR(spicc->clk)))
+		return PTR_ERR(spicc->clk);
 
-	if (!spicc->data->has_enhance_clk_div) {
-		spicc->clk = clk;
-		return 0;
-	}
+	return 0;
+}
+
+static int meson_spicc_enh_clk_init(struct meson_spicc_device *spicc)
+{
+	struct device *dev = &spicc->pdev->dev;
+	struct clk_fixed_factor *enh_fixed_div;
+	struct clk_divider *enh_div;
+	struct clk_mux *mux;
+	struct clk_init_data init;
+	struct clk *clk;
+	struct clk_parent_data parent_data[2];
+	char name[64];
+
+	memset(&init, 0, sizeof(init));
+	memset(&parent_data, 0, sizeof(parent_data));
+
+	init.parent_data = parent_data;
 
 	/* algorithm for enh div: rate = freq / 2 / (N + 1) */
 
@@ -637,7 +702,7 @@ static int meson_spicc_clk_init(struct meson_spicc_device *spicc)
 	snprintf(name, sizeof(name), "%s#sel", dev_name(dev));
 	init.name = name;
 	init.ops = &clk_mux_ops;
-	parent_data[0].hw = &pow2_div->hw;
+	parent_data[0].hw = &spicc->pow2_div.hw;
 	parent_data[1].hw = &enh_div->hw;
 	init.num_parents = 2;
 	init.flags = CLK_SET_RATE_PARENT;
@@ -754,12 +819,20 @@ static int meson_spicc_probe(struct platform_device *pdev)
 
 	meson_spicc_oen_enable(spicc);
 
-	ret = meson_spicc_clk_init(spicc);
+	ret = meson_spicc_pow2_clk_init(spicc);
 	if (ret) {
-		dev_err(&pdev->dev, "clock registration failed\n");
+		dev_err(&pdev->dev, "pow2 clock registration failed\n");
 		goto out_clk;
 	}
 
+	if (spicc->data->has_enhance_clk_div) {
+		ret = meson_spicc_enh_clk_init(spicc);
+		if (ret) {
+			dev_err(&pdev->dev, "clock registration failed\n");
+			goto out_clk;
+		}
+	}
+
 	ret = devm_spi_register_master(&pdev->dev, master);
 	if (ret) {
 		dev_err(&pdev->dev, "spi master registration failed\n");
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 8f97a3eacdea..83da8862b8f2 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -95,7 +95,7 @@ static ssize_t driver_override_show(struct device *dev,
 }
 static DEVICE_ATTR_RW(driver_override);
 
-static struct spi_statistics *spi_alloc_pcpu_stats(struct device *dev)
+static struct spi_statistics __percpu *spi_alloc_pcpu_stats(struct device *dev)
 {
 	struct spi_statistics __percpu *pcpu_stats;
 
@@ -162,7 +162,7 @@ static struct device_attribute dev_attr_spi_device_##field = {		\
 }
 
 #define SPI_STATISTICS_SHOW_NAME(name, file, field)			\
-static ssize_t spi_statistics_##name##_show(struct spi_statistics *stat, \
+static ssize_t spi_statistics_##name##_show(struct spi_statistics __percpu *stat, \
 					    char *buf)			\
 {									\
 	ssize_t len;							\
@@ -309,7 +309,7 @@ static const struct attribute_group *spi_master_groups[] = {
 	NULL,
 };
 
-static void spi_statistics_add_transfer_stats(struct spi_statistics *pcpu_stats,
+static void spi_statistics_add_transfer_stats(struct spi_statistics __percpu *pcpu_stats,
 					      struct spi_transfer *xfer,
 					      struct spi_controller *ctlr)
 {
@@ -1275,8 +1275,8 @@ static int spi_transfer_wait(struct spi_controller *ctlr,
 			     struct spi_message *msg,
 			     struct spi_transfer *xfer)
 {
-	struct spi_statistics *statm = ctlr->pcpu_statistics;
-	struct spi_statistics *stats = msg->spi->pcpu_statistics;
+	struct spi_statistics __percpu *statm = ctlr->pcpu_statistics;
+	struct spi_statistics __percpu *stats = msg->spi->pcpu_statistics;
 	u32 speed_hz = xfer->speed_hz;
 	unsigned long long ms;
 
@@ -1432,8 +1432,8 @@ static int spi_transfer_one_message(struct spi_controller *ctlr,
 	struct spi_transfer *xfer;
 	bool keep_cs = false;
 	int ret = 0;
-	struct spi_statistics *statm = ctlr->pcpu_statistics;
-	struct spi_statistics *stats = msg->spi->pcpu_statistics;
+	struct spi_statistics __percpu *statm = ctlr->pcpu_statistics;
+	struct spi_statistics __percpu *stats = msg->spi->pcpu_statistics;
 
 	spi_set_cs(msg->spi, true, false);
 
diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
index f2b1bcefcadd..1175f3a46859 100644
--- a/drivers/tee/tee_shm.c
+++ b/drivers/tee/tee_shm.c
@@ -326,6 +326,9 @@ struct tee_shm *tee_shm_register_user_buf(struct tee_context *ctx,
 	void *ret;
 	int id;
 
+	if (!access_ok((void __user *)addr, length))
+		return ERR_PTR(-EFAULT);
+
 	mutex_lock(&teedev->mutex);
 	id = idr_alloc(&teedev->idr, NULL, 1, 0, GFP_KERNEL);
 	mutex_unlock(&teedev->mutex);
diff --git a/drivers/thermal/amlogic_thermal.c b/drivers/thermal/amlogic_thermal.c
index e61b91d14ad1..d30cb791e63c 100644
--- a/drivers/thermal/amlogic_thermal.c
+++ b/drivers/thermal/amlogic_thermal.c
@@ -179,12 +179,12 @@ static int amlogic_thermal_disable(struct amlogic_thermal *data)
 	return 0;
 }
 
-static int amlogic_thermal_get_temp(void *data, int *temp)
+static int amlogic_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
 	unsigned int tval;
-	struct amlogic_thermal *pdata = data;
+	struct amlogic_thermal *pdata = tz->devdata;
 
-	if (!data)
+	if (!pdata)
 		return -EINVAL;
 
 	regmap_read(pdata->regmap, TSENSOR_STAT0, &tval);
@@ -195,7 +195,7 @@ static int amlogic_thermal_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops amlogic_thermal_ops = {
+static const struct thermal_zone_device_ops amlogic_thermal_ops = {
 	.get_temp	= amlogic_thermal_get_temp,
 };
 
@@ -276,10 +276,10 @@ static int amlogic_thermal_probe(struct platform_device *pdev)
 		return PTR_ERR(pdata->sec_ao_map);
 	}
 
-	pdata->tzd = devm_thermal_zone_of_sensor_register(&pdev->dev,
-							  0,
-							  pdata,
-							  &amlogic_thermal_ops);
+	pdata->tzd = devm_thermal_of_zone_register(&pdev->dev,
+						   0,
+						   pdata,
+						   &amlogic_thermal_ops);
 	if (IS_ERR(pdata->tzd)) {
 		ret = PTR_ERR(pdata->tzd);
 		dev_err(dev, "Failed to register tsensor: %d\n", ret);
diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index c2ebfb5be4b3..52d63b3997fe 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -420,9 +420,9 @@ static struct thermal_zone_device_ops legacy_ops = {
 	.get_temp = armada_get_temp_legacy,
 };
 
-static int armada_get_temp(void *_sensor, int *temp)
+static int armada_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct armada_thermal_sensor *sensor = _sensor;
+	struct armada_thermal_sensor *sensor = tz->devdata;
 	struct armada_thermal_priv *priv = sensor->priv;
 	int ret;
 
@@ -450,7 +450,7 @@ unlock_mutex:
 	return ret;
 }
 
-static const struct thermal_zone_of_device_ops of_ops = {
+static const struct thermal_zone_device_ops of_ops = {
 	.get_temp = armada_get_temp,
 };
 
@@ -928,9 +928,9 @@ static int armada_thermal_probe(struct platform_device *pdev)
 		/* Register the sensor */
 		sensor->priv = priv;
 		sensor->id = sensor_id;
-		tz = devm_thermal_zone_of_sensor_register(&pdev->dev,
-							  sensor->id, sensor,
-							  &of_ops);
+		tz = devm_thermal_of_zone_register(&pdev->dev,
+						   sensor->id, sensor,
+						   &of_ops);
 		if (IS_ERR(tz)) {
 			dev_info(&pdev->dev, "Thermal sensor %d unavailable\n",
 				 sensor_id);
diff --git a/drivers/thermal/broadcom/bcm2711_thermal.c b/drivers/thermal/broadcom/bcm2711_thermal.c
index e9bef5c3414b..1f8651d15160 100644
--- a/drivers/thermal/broadcom/bcm2711_thermal.c
+++ b/drivers/thermal/broadcom/bcm2711_thermal.c
@@ -31,11 +31,11 @@ struct bcm2711_thermal_priv {
 	struct thermal_zone_device *thermal;
 };
 
-static int bcm2711_get_temp(void *data, int *temp)
+static int bcm2711_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct bcm2711_thermal_priv *priv = data;
-	int slope = thermal_zone_get_slope(priv->thermal);
-	int offset = thermal_zone_get_offset(priv->thermal);
+	struct bcm2711_thermal_priv *priv = tz->devdata;
+	int slope = thermal_zone_get_slope(tz);
+	int offset = thermal_zone_get_offset(tz);
 	u32 val;
 	int ret;
 
@@ -54,7 +54,7 @@ static int bcm2711_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops bcm2711_thermal_of_ops = {
+static const struct thermal_zone_device_ops bcm2711_thermal_of_ops = {
 	.get_temp	= bcm2711_get_temp,
 };
 
@@ -88,8 +88,8 @@ static int bcm2711_thermal_probe(struct platform_device *pdev)
 	}
 	priv->regmap = regmap;
 
-	thermal = devm_thermal_zone_of_sensor_register(dev, 0, priv,
-						       &bcm2711_thermal_of_ops);
+	thermal = devm_thermal_of_zone_register(dev, 0, priv,
+						&bcm2711_thermal_of_ops);
 	if (IS_ERR(thermal)) {
 		ret = PTR_ERR(thermal);
 		dev_err(dev, "could not register sensor: %d\n", ret);
diff --git a/drivers/thermal/broadcom/bcm2835_thermal.c b/drivers/thermal/broadcom/bcm2835_thermal.c
index c8e4344d5a3d..2c67841a1115 100644
--- a/drivers/thermal/broadcom/bcm2835_thermal.c
+++ b/drivers/thermal/broadcom/bcm2835_thermal.c
@@ -88,9 +88,9 @@ static int bcm2835_thermal_temp2adc(int temp, int offset, int slope)
 	return temp;
 }
 
-static int bcm2835_thermal_get_temp(void *d, int *temp)
+static int bcm2835_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct bcm2835_thermal_data *data = d;
+	struct bcm2835_thermal_data *data = tz->devdata;
 	u32 val = readl(data->regs + BCM2835_TS_TSENSSTAT);
 
 	if (!(val & BCM2835_TS_TSENSSTAT_VALID))
@@ -135,7 +135,7 @@ static void bcm2835_thermal_debugfs(struct platform_device *pdev)
 	debugfs_create_regset32("regset", 0444, data->debugfsdir, regset);
 }
 
-static const struct thermal_zone_of_device_ops bcm2835_thermal_ops = {
+static const struct thermal_zone_device_ops bcm2835_thermal_ops = {
 	.get_temp = bcm2835_thermal_get_temp,
 };
 
@@ -206,8 +206,8 @@ static int bcm2835_thermal_probe(struct platform_device *pdev)
 			 data->clk, rate);
 
 	/* register of thermal sensor and get info from DT */
-	tz = thermal_zone_of_sensor_register(&pdev->dev, 0, data,
-					     &bcm2835_thermal_ops);
+	tz = devm_thermal_of_zone_register(&pdev->dev, 0, data,
+					   &bcm2835_thermal_ops);
 	if (IS_ERR(tz)) {
 		err = PTR_ERR(tz);
 		dev_err(&pdev->dev,
@@ -277,7 +277,7 @@ static int bcm2835_thermal_probe(struct platform_device *pdev)
 
 	return 0;
 err_tz:
-	thermal_zone_of_sensor_unregister(&pdev->dev, tz);
+	thermal_of_zone_unregister(tz);
 err_clk:
 	clk_disable_unprepare(data->clk);
 
@@ -290,7 +290,7 @@ static int bcm2835_thermal_remove(struct platform_device *pdev)
 	struct thermal_zone_device *tz = data->tz;
 
 	debugfs_remove_recursive(data->debugfsdir);
-	thermal_zone_of_sensor_unregister(&pdev->dev, tz);
+	thermal_of_zone_unregister(tz);
 	clk_disable_unprepare(data->clk);
 
 	return 0;
diff --git a/drivers/thermal/broadcom/brcmstb_thermal.c b/drivers/thermal/broadcom/brcmstb_thermal.c
index 0cedb8b4f00a..c79c6cfdd74d 100644
--- a/drivers/thermal/broadcom/brcmstb_thermal.c
+++ b/drivers/thermal/broadcom/brcmstb_thermal.c
@@ -105,7 +105,7 @@ static struct avs_tmon_trip avs_tmon_trips[] = {
 struct brcmstb_thermal_params {
 	unsigned int offset;
 	unsigned int mult;
-	const struct thermal_zone_of_device_ops *of_ops;
+	const struct thermal_zone_device_ops *of_ops;
 };
 
 struct brcmstb_thermal_priv {
@@ -150,9 +150,9 @@ static inline u32 avs_tmon_temp_to_code(struct brcmstb_thermal_priv *priv,
 		return (u32)((offset - temp) / mult);
 }
 
-static int brcmstb_get_temp(void *data, int *temp)
+static int brcmstb_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct brcmstb_thermal_priv *priv = data;
+	struct brcmstb_thermal_priv *priv = tz->devdata;
 	u32 val;
 	long t;
 
@@ -260,9 +260,9 @@ static irqreturn_t brcmstb_tmon_irq_thread(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int brcmstb_set_trips(void *data, int low, int high)
+static int brcmstb_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	struct brcmstb_thermal_priv *priv = data;
+	struct brcmstb_thermal_priv *priv = tz->devdata;
 
 	dev_dbg(priv->dev, "set trips %d <--> %d\n", low, high);
 
@@ -288,7 +288,7 @@ static int brcmstb_set_trips(void *data, int low, int high)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops brcmstb_16nm_of_ops = {
+static const struct thermal_zone_device_ops brcmstb_16nm_of_ops = {
 	.get_temp	= brcmstb_get_temp,
 };
 
@@ -298,7 +298,7 @@ static const struct brcmstb_thermal_params brcmstb_16nm_params = {
 	.of_ops	= &brcmstb_16nm_of_ops,
 };
 
-static const struct thermal_zone_of_device_ops brcmstb_28nm_of_ops = {
+static const struct thermal_zone_device_ops brcmstb_28nm_of_ops = {
 	.get_temp	= brcmstb_get_temp,
 	.set_trips	= brcmstb_set_trips,
 };
@@ -318,7 +318,7 @@ MODULE_DEVICE_TABLE(of, brcmstb_thermal_id_table);
 
 static int brcmstb_thermal_probe(struct platform_device *pdev)
 {
-	const struct thermal_zone_of_device_ops *of_ops;
+	const struct thermal_zone_device_ops *of_ops;
 	struct thermal_zone_device *thermal;
 	struct brcmstb_thermal_priv *priv;
 	struct resource *res;
@@ -341,8 +341,8 @@ static int brcmstb_thermal_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, priv);
 	of_ops = priv->temp_params->of_ops;
 
-	thermal = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, priv,
-						       of_ops);
+	thermal = devm_thermal_of_zone_register(&pdev->dev, 0, priv,
+						of_ops);
 	if (IS_ERR(thermal)) {
 		ret = PTR_ERR(thermal);
 		dev_err(&pdev->dev, "could not register sensor: %d\n", ret);
diff --git a/drivers/thermal/broadcom/ns-thermal.c b/drivers/thermal/broadcom/ns-thermal.c
index c9468ba9d449..07a8a3f49bd0 100644
--- a/drivers/thermal/broadcom/ns-thermal.c
+++ b/drivers/thermal/broadcom/ns-thermal.c
@@ -14,19 +14,14 @@
 #define PVTMON_CONTROL0_SEL_TEST_MODE			0x0000000e
 #define PVTMON_STATUS					0x08
 
-struct ns_thermal {
-	struct thermal_zone_device *tz;
-	void __iomem *pvtmon;
-};
-
-static int ns_thermal_get_temp(void *data, int *temp)
+static int ns_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct ns_thermal *ns_thermal = data;
-	int offset = thermal_zone_get_offset(ns_thermal->tz);
-	int slope = thermal_zone_get_slope(ns_thermal->tz);
+	void __iomem *pvtmon = tz->devdata;
+	int offset = thermal_zone_get_offset(tz);
+	int slope = thermal_zone_get_slope(tz);
 	u32 val;
 
-	val = readl(ns_thermal->pvtmon + PVTMON_CONTROL0);
+	val = readl(pvtmon + PVTMON_CONTROL0);
 	if ((val & PVTMON_CONTROL0_SEL_MASK) != PVTMON_CONTROL0_SEL_TEMP_MONITOR) {
 		/* Clear current mode selection */
 		val &= ~PVTMON_CONTROL0_SEL_MASK;
@@ -34,50 +29,47 @@ static int ns_thermal_get_temp(void *data, int *temp)
 		/* Set temp monitor mode (it's the default actually) */
 		val |= PVTMON_CONTROL0_SEL_TEMP_MONITOR;
 
-		writel(val, ns_thermal->pvtmon + PVTMON_CONTROL0);
+		writel(val, pvtmon + PVTMON_CONTROL0);
 	}
 
-	val = readl(ns_thermal->pvtmon + PVTMON_STATUS);
+	val = readl(pvtmon + PVTMON_STATUS);
 	*temp = slope * val + offset;
 
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops ns_thermal_ops = {
+static const struct thermal_zone_device_ops ns_thermal_ops = {
 	.get_temp = ns_thermal_get_temp,
 };
 
 static int ns_thermal_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct ns_thermal *ns_thermal;
-
-	ns_thermal = devm_kzalloc(dev, sizeof(*ns_thermal), GFP_KERNEL);
-	if (!ns_thermal)
-		return -ENOMEM;
+	struct thermal_zone_device *tz;
+	void __iomem *pvtmon;
 
-	ns_thermal->pvtmon = of_iomap(dev_of_node(dev), 0);
-	if (WARN_ON(!ns_thermal->pvtmon))
+	pvtmon = of_iomap(dev_of_node(dev), 0);
+	if (WARN_ON(!pvtmon))
 		return -ENOENT;
 
-	ns_thermal->tz = devm_thermal_zone_of_sensor_register(dev, 0,
-							      ns_thermal,
-							      &ns_thermal_ops);
-	if (IS_ERR(ns_thermal->tz)) {
-		iounmap(ns_thermal->pvtmon);
-		return PTR_ERR(ns_thermal->tz);
+	tz = devm_thermal_of_zone_register(dev, 0,
+					   pvtmon,
+					   &ns_thermal_ops);
+	if (IS_ERR(tz)) {
+		iounmap(pvtmon);
+		return PTR_ERR(tz);
 	}
 
-	platform_set_drvdata(pdev, ns_thermal);
+	platform_set_drvdata(pdev, pvtmon);
 
 	return 0;
 }
 
 static int ns_thermal_remove(struct platform_device *pdev)
 {
-	struct ns_thermal *ns_thermal = platform_get_drvdata(pdev);
+	void __iomem *pvtmon = platform_get_drvdata(pdev);
 
-	iounmap(ns_thermal->pvtmon);
+	iounmap(pvtmon);
 
 	return 0;
 }
diff --git a/drivers/thermal/broadcom/sr-thermal.c b/drivers/thermal/broadcom/sr-thermal.c
index 85ab9edd580c..2b93502543ff 100644
--- a/drivers/thermal/broadcom/sr-thermal.c
+++ b/drivers/thermal/broadcom/sr-thermal.c
@@ -19,7 +19,6 @@
 #define SR_TMON_MAX_LIST        6
 
 struct sr_tmon {
-	struct thermal_zone_device *tz;
 	unsigned int crit_temp;
 	unsigned int tmon_id;
 	struct sr_thermal *priv;
@@ -31,9 +30,9 @@ struct sr_thermal {
 	struct sr_tmon tmon[SR_TMON_MAX_LIST];
 };
 
-static int sr_get_temp(void *data, int *temp)
+static int sr_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct sr_tmon *tmon = data;
+	struct sr_tmon *tmon = tz->devdata;
 	struct sr_thermal *sr_thermal = tmon->priv;
 
 	*temp = readl(sr_thermal->regs + SR_TMON_TEMP_BASE(tmon->tmon_id));
@@ -41,13 +40,14 @@ static int sr_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops sr_tz_ops = {
+static const struct thermal_zone_device_ops sr_tz_ops = {
 	.get_temp = sr_get_temp,
 };
 
 static int sr_thermal_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	struct thermal_zone_device *tz;
 	struct sr_thermal *sr_thermal;
 	struct sr_tmon *tmon;
 	struct resource *res;
@@ -84,10 +84,10 @@ static int sr_thermal_probe(struct platform_device *pdev)
 		writel(0, sr_thermal->regs + SR_TMON_TEMP_BASE(i));
 		tmon->tmon_id = i;
 		tmon->priv = sr_thermal;
-		tmon->tz = devm_thermal_zone_of_sensor_register(dev, i, tmon,
-								&sr_tz_ops);
-		if (IS_ERR(tmon->tz))
-			return PTR_ERR(tmon->tz);
+		tz = devm_thermal_of_zone_register(dev, i, tmon,
+						   &sr_tz_ops);
+		if (IS_ERR(tz))
+			return PTR_ERR(tz);
 
 		dev_dbg(dev, "thermal sensor %d registered\n", i);
 	}
diff --git a/drivers/thermal/db8500_thermal.c b/drivers/thermal/db8500_thermal.c
index 121cf853e545..cb10e280681f 100644
--- a/drivers/thermal/db8500_thermal.c
+++ b/drivers/thermal/db8500_thermal.c
@@ -58,9 +58,9 @@ struct db8500_thermal_zone {
 };
 
 /* Callback to get current temperature */
-static int db8500_thermal_get_temp(void *data, int *temp)
+static int db8500_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct db8500_thermal_zone *th = data;
+	struct db8500_thermal_zone *th = tz->devdata;
 
 	/*
 	 * TODO: There is no PRCMU interface to get temperature data currently,
@@ -72,7 +72,7 @@ static int db8500_thermal_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static struct thermal_zone_of_device_ops thdev_ops = {
+static const struct thermal_zone_device_ops thdev_ops = {
 	.get_temp = db8500_thermal_get_temp,
 };
 
@@ -182,7 +182,7 @@ static int db8500_thermal_probe(struct platform_device *pdev)
 	}
 
 	/* register of thermal sensor and get info from DT */
-	th->tz = devm_thermal_zone_of_sensor_register(dev, 0, th, &thdev_ops);
+	th->tz = devm_thermal_of_zone_register(dev, 0, th, &thdev_ops);
 	if (IS_ERR(th->tz)) {
 		dev_err(dev, "register thermal zone sensor failed\n");
 		return PTR_ERR(th->tz);
diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c
index 991a1c54296d..a08bbe33be96 100644
--- a/drivers/thermal/gov_bang_bang.c
+++ b/drivers/thermal/gov_bang_bang.c
@@ -31,8 +31,6 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip)
 				trip, trip_temp, tz->temperature,
 				trip_hyst);
 
-	mutex_lock(&tz->lock);
-
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
 		if (instance->trip != trip)
 			continue;
@@ -65,8 +63,6 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip)
 		instance->cdev->updated = false; /* cdev needs update */
 		mutex_unlock(&instance->cdev->lock);
 	}
-
-	mutex_unlock(&tz->lock);
 }
 
 /**
@@ -100,15 +96,13 @@ static int bang_bang_control(struct thermal_zone_device *tz, int trip)
 {
 	struct thermal_instance *instance;
 
-	thermal_zone_trip_update(tz, trip);
+	lockdep_assert_held(&tz->lock);
 
-	mutex_lock(&tz->lock);
+	thermal_zone_trip_update(tz, trip);
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node)
 		thermal_cdev_update(instance->cdev);
 
-	mutex_unlock(&tz->lock);
-
 	return 0;
 }
 
diff --git a/drivers/thermal/gov_fair_share.c b/drivers/thermal/gov_fair_share.c
index 6a2abcfc648f..a4ee4661e9cc 100644
--- a/drivers/thermal/gov_fair_share.c
+++ b/drivers/thermal/gov_fair_share.c
@@ -82,7 +82,7 @@ static int fair_share_throttle(struct thermal_zone_device *tz, int trip)
 	int total_instance = 0;
 	int cur_trip_level = get_trip_level(tz);
 
-	mutex_lock(&tz->lock);
+	lockdep_assert_held(&tz->lock);
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
 		if (instance->trip != trip)
@@ -112,7 +112,6 @@ static int fair_share_throttle(struct thermal_zone_device *tz, int trip)
 		mutex_unlock(&cdev->lock);
 	}
 
-	mutex_unlock(&tz->lock);
 	return 0;
 }
 
diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index 1d5052470967..2d1aeaba38a8 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -392,8 +392,6 @@ static int allocate_power(struct thermal_zone_device *tz,
 	int i, num_actors, total_weight, ret = 0;
 	int trip_max_desired_temperature = params->trip_max_desired_temperature;
 
-	mutex_lock(&tz->lock);
-
 	num_actors = 0;
 	total_weight = 0;
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
@@ -404,10 +402,8 @@ static int allocate_power(struct thermal_zone_device *tz,
 		}
 	}
 
-	if (!num_actors) {
-		ret = -ENODEV;
-		goto unlock;
-	}
+	if (!num_actors)
+		return -ENODEV;
 
 	/*
 	 * We need to allocate five arrays of the same size:
@@ -421,10 +417,8 @@ static int allocate_power(struct thermal_zone_device *tz,
 	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*extra_actor_power));
 	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*weighted_req_power));
 	req_power = kcalloc(num_actors * 5, sizeof(*req_power), GFP_KERNEL);
-	if (!req_power) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	if (!req_power)
+		return -ENOMEM;
 
 	max_power = &req_power[num_actors];
 	granted_power = &req_power[2 * num_actors];
@@ -496,8 +490,6 @@ static int allocate_power(struct thermal_zone_device *tz,
 				      control_temp - tz->temperature);
 
 	kfree(req_power);
-unlock:
-	mutex_unlock(&tz->lock);
 
 	return ret;
 }
@@ -576,7 +568,6 @@ static void allow_maximum_power(struct thermal_zone_device *tz, bool update)
 	struct power_allocator_params *params = tz->governor_data;
 	u32 req_power;
 
-	mutex_lock(&tz->lock);
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
 		struct thermal_cooling_device *cdev = instance->cdev;
 
@@ -598,7 +589,6 @@ static void allow_maximum_power(struct thermal_zone_device *tz, bool update)
 
 		mutex_unlock(&instance->cdev->lock);
 	}
-	mutex_unlock(&tz->lock);
 }
 
 /**
@@ -712,6 +702,8 @@ static int power_allocator_throttle(struct thermal_zone_device *tz, int trip)
 	struct power_allocator_params *params = tz->governor_data;
 	bool update;
 
+	lockdep_assert_held(&tz->lock);
+
 	/*
 	 * We get called for every trip point but we only need to do
 	 * our calculations once
diff --git a/drivers/thermal/gov_step_wise.c b/drivers/thermal/gov_step_wise.c
index 9729b46d0258..cdd3354bc27f 100644
--- a/drivers/thermal/gov_step_wise.c
+++ b/drivers/thermal/gov_step_wise.c
@@ -117,8 +117,6 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip)
 	dev_dbg(&tz->device, "Trip%d[type=%d,temp=%d]:trend=%d,throttle=%d\n",
 				trip, trip_type, trip_temp, trend, throttle);
 
-	mutex_lock(&tz->lock);
-
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
 		if (instance->trip != trip)
 			continue;
@@ -145,8 +143,6 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip)
 		instance->cdev->updated = false; /* cdev needs update */
 		mutex_unlock(&instance->cdev->lock);
 	}
-
-	mutex_unlock(&tz->lock);
 }
 
 /**
@@ -164,15 +160,13 @@ static int step_wise_throttle(struct thermal_zone_device *tz, int trip)
 {
 	struct thermal_instance *instance;
 
-	thermal_zone_trip_update(tz, trip);
+	lockdep_assert_held(&tz->lock);
 
-	mutex_lock(&tz->lock);
+	thermal_zone_trip_update(tz, trip);
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node)
 		thermal_cdev_update(instance->cdev);
 
-	mutex_unlock(&tz->lock);
-
 	return 0;
 }
 
diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c
index 19a242c69ce6..d6974db7aaf7 100644
--- a/drivers/thermal/hisi_thermal.c
+++ b/drivers/thermal/hisi_thermal.c
@@ -434,9 +434,9 @@ static int hi3660_thermal_probe(struct hisi_thermal_data *data)
 	return 0;
 }
 
-static int hisi_thermal_get_temp(void *__data, int *temp)
+static int hisi_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct hisi_thermal_sensor *sensor = __data;
+	struct hisi_thermal_sensor *sensor = tz->devdata;
 	struct hisi_thermal_data *data = sensor->data;
 
 	*temp = data->ops->get_temp(sensor);
@@ -447,7 +447,7 @@ static int hisi_thermal_get_temp(void *__data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops hisi_of_thermal_ops = {
+static const struct thermal_zone_device_ops hisi_of_thermal_ops = {
 	.get_temp = hisi_thermal_get_temp,
 };
 
@@ -459,7 +459,7 @@ static irqreturn_t hisi_thermal_alarm_irq_thread(int irq, void *dev)
 
 	data->ops->irq_handler(sensor);
 
-	hisi_thermal_get_temp(sensor, &temp);
+	temp = data->ops->get_temp(sensor);
 
 	if (temp >= sensor->thres_temp) {
 		dev_crit(&data->pdev->dev,
@@ -484,9 +484,9 @@ static int hisi_thermal_register_sensor(struct platform_device *pdev,
 	int ret, i;
 	const struct thermal_trip *trip;
 
-	sensor->tzd = devm_thermal_zone_of_sensor_register(&pdev->dev,
-							   sensor->id, sensor,
-							   &hisi_of_thermal_ops);
+	sensor->tzd = devm_thermal_of_zone_register(&pdev->dev,
+						    sensor->id, sensor,
+						    &hisi_of_thermal_ops);
 	if (IS_ERR(sensor->tzd)) {
 		ret = PTR_ERR(sensor->tzd);
 		sensor->tzd = NULL;
diff --git a/drivers/thermal/imx8mm_thermal.c b/drivers/thermal/imx8mm_thermal.c
index af666bd9e8d4..e2c2673025a7 100644
--- a/drivers/thermal/imx8mm_thermal.c
+++ b/drivers/thermal/imx8mm_thermal.c
@@ -96,15 +96,15 @@ static int imx8mp_tmu_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static int tmu_get_temp(void *data, int *temp)
+static int tmu_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct tmu_sensor *sensor = data;
+	struct tmu_sensor *sensor = tz->devdata;
 	struct imx8mm_tmu *tmu = sensor->priv;
 
-	return tmu->socdata->get_temp(data, temp);
+	return tmu->socdata->get_temp(sensor, temp);
 }
 
-static struct thermal_zone_of_device_ops tmu_tz_ops = {
+static const struct thermal_zone_device_ops tmu_tz_ops = {
 	.get_temp = tmu_get_temp,
 };
 
@@ -165,9 +165,9 @@ static int imx8mm_tmu_probe(struct platform_device *pdev)
 	for (i = 0; i < data->num_sensors; i++) {
 		tmu->sensors[i].priv = tmu;
 		tmu->sensors[i].tzd =
-			devm_thermal_zone_of_sensor_register(&pdev->dev, i,
-							     &tmu->sensors[i],
-							     &tmu_tz_ops);
+			devm_thermal_of_zone_register(&pdev->dev, i,
+						      &tmu->sensors[i],
+						      &tmu_tz_ops);
 		if (IS_ERR(tmu->sensors[i].tzd)) {
 			ret = PTR_ERR(tmu->sensors[i].tzd);
 			dev_err(&pdev->dev,
diff --git a/drivers/thermal/imx_sc_thermal.c b/drivers/thermal/imx_sc_thermal.c
index 331a241eb0ef..10bfa6507eb4 100644
--- a/drivers/thermal/imx_sc_thermal.c
+++ b/drivers/thermal/imx_sc_thermal.c
@@ -43,11 +43,11 @@ struct imx_sc_msg_misc_get_temp {
 	} data;
 } __packed __aligned(4);
 
-static int imx_sc_thermal_get_temp(void *data, int *temp)
+static int imx_sc_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
 	struct imx_sc_msg_misc_get_temp msg;
 	struct imx_sc_rpc_msg *hdr = &msg.hdr;
-	struct imx_sc_sensor *sensor = data;
+	struct imx_sc_sensor *sensor = tz->devdata;
 	int ret;
 
 	msg.data.req.resource_id = sensor->resource_id;
@@ -70,7 +70,7 @@ static int imx_sc_thermal_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops imx_sc_thermal_ops = {
+static const struct thermal_zone_device_ops imx_sc_thermal_ops = {
 	.get_temp = imx_sc_thermal_get_temp,
 };
 
@@ -109,10 +109,10 @@ static int imx_sc_thermal_probe(struct platform_device *pdev)
 			break;
 		}
 
-		sensor->tzd = devm_thermal_zone_of_sensor_register(&pdev->dev,
-								   sensor->resource_id,
-								   sensor,
-								   &imx_sc_thermal_ops);
+		sensor->tzd = devm_thermal_of_zone_register(&pdev->dev,
+							    sensor->resource_id,
+							    sensor,
+							    &imx_sc_thermal_ops);
 		if (IS_ERR(sensor->tzd)) {
 			dev_err(&pdev->dev, "failed to register thermal zone\n");
 			ret = PTR_ERR(sensor->tzd);
diff --git a/drivers/thermal/k3_bandgap.c b/drivers/thermal/k3_bandgap.c
index 5d0b3ffc6f46..22c9bcb899c3 100644
--- a/drivers/thermal/k3_bandgap.c
+++ b/drivers/thermal/k3_bandgap.c
@@ -139,9 +139,9 @@ static int k3_bgp_read_temp(struct k3_thermal_data *devdata,
 	return 0;
 }
 
-static int k3_thermal_get_temp(void *devdata, int *temp)
+static int k3_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct k3_thermal_data *data = devdata;
+	struct k3_thermal_data *data = tz->devdata;
 	int ret = 0;
 
 	ret = k3_bgp_read_temp(data, temp);
@@ -151,7 +151,7 @@ static int k3_thermal_get_temp(void *devdata, int *temp)
 	return ret;
 }
 
-static const struct thermal_zone_of_device_ops k3_of_thermal_ops = {
+static const struct thermal_zone_device_ops k3_of_thermal_ops = {
 	.get_temp = k3_thermal_get_temp,
 };
 
@@ -213,9 +213,9 @@ static int k3_bandgap_probe(struct platform_device *pdev)
 		writel(val, data[id].bgp->base + data[id].ctrl_offset);
 
 		data[id].tzd =
-		devm_thermal_zone_of_sensor_register(dev, id,
-						     &data[id],
-						     &k3_of_thermal_ops);
+		devm_thermal_of_zone_register(dev, id,
+					      &data[id],
+					      &k3_of_thermal_ops);
 		if (IS_ERR(data[id].tzd)) {
 			dev_err(dev, "thermal zone device is NULL\n");
 			ret = PTR_ERR(data[id].tzd);
diff --git a/drivers/thermal/k3_j72xx_bandgap.c b/drivers/thermal/k3_j72xx_bandgap.c
index 115a44eb4fbf..16b6bcf1bf4f 100644
--- a/drivers/thermal/k3_j72xx_bandgap.c
+++ b/drivers/thermal/k3_j72xx_bandgap.c
@@ -247,9 +247,9 @@ static inline int k3_bgp_read_temp(struct k3_thermal_data *devdata,
 }
 
 /* Get temperature callback function for thermal zone */
-static int k3_thermal_get_temp(void *devdata, int *temp)
+static int k3_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct k3_thermal_data *data = devdata;
+	struct k3_thermal_data *data = tz->devdata;
 	int ret = 0;
 
 	ret = k3_bgp_read_temp(data, temp);
@@ -259,7 +259,7 @@ static int k3_thermal_get_temp(void *devdata, int *temp)
 	return ret;
 }
 
-static const struct thermal_zone_of_device_ops k3_of_thermal_ops = {
+static const struct thermal_zone_device_ops k3_of_thermal_ops = {
 	.get_temp = k3_thermal_get_temp,
 };
 
@@ -474,10 +474,8 @@ static int k3_j72xx_bandgap_probe(struct platform_device *pdev)
 		writel(val, data[id].bgp->cfg2_base + data[id].ctrl_offset);
 
 		bgp->ts_data[id] = &data[id];
-		ti_thermal =
-		devm_thermal_zone_of_sensor_register(bgp->dev, id,
-						     &data[id],
-						     &k3_of_thermal_ops);
+		ti_thermal = devm_thermal_of_zone_register(bgp->dev, id, &data[id],
+							   &k3_of_thermal_ops);
 		if (IS_ERR(ti_thermal)) {
 			dev_err(bgp->dev, "thermal zone device is NULL\n");
 			ret = PTR_ERR(ti_thermal);
diff --git a/drivers/thermal/max77620_thermal.c b/drivers/thermal/max77620_thermal.c
index 82d06c7411eb..6451a55eb582 100644
--- a/drivers/thermal/max77620_thermal.c
+++ b/drivers/thermal/max77620_thermal.c
@@ -44,9 +44,9 @@ struct max77620_therm_info {
  * Return 0 on success otherwise error number to show reason of failure.
  */
 
-static int max77620_thermal_read_temp(void *data, int *temp)
+static int max77620_thermal_read_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct max77620_therm_info *mtherm = data;
+	struct max77620_therm_info *mtherm = tz->devdata;
 	unsigned int val;
 	int ret;
 
@@ -66,7 +66,7 @@ static int max77620_thermal_read_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops max77620_thermal_ops = {
+static const struct thermal_zone_device_ops max77620_thermal_ops = {
 	.get_temp = max77620_thermal_read_temp,
 };
 
@@ -114,7 +114,7 @@ static int max77620_thermal_probe(struct platform_device *pdev)
 	 */
 	device_set_of_node_from_dev(&pdev->dev, pdev->dev.parent);
 
-	mtherm->tz_device = devm_thermal_zone_of_sensor_register(&pdev->dev, 0,
+	mtherm->tz_device = devm_thermal_of_zone_register(&pdev->dev, 0,
 				mtherm, &max77620_thermal_ops);
 	if (IS_ERR(mtherm->tz_device)) {
 		ret = PTR_ERR(mtherm->tz_device);
diff --git a/drivers/thermal/mtk_thermal.c b/drivers/thermal/mtk_thermal.c
index ede94eadddda..8440692e3890 100644
--- a/drivers/thermal/mtk_thermal.c
+++ b/drivers/thermal/mtk_thermal.c
@@ -679,9 +679,9 @@ static int mtk_thermal_bank_temperature(struct mtk_thermal_bank *bank)
 	return max;
 }
 
-static int mtk_read_temp(void *data, int *temperature)
+static int mtk_read_temp(struct thermal_zone_device *tz, int *temperature)
 {
-	struct mtk_thermal *mt = data;
+	struct mtk_thermal *mt = tz->devdata;
 	int i;
 	int tempmax = INT_MIN;
 
@@ -700,7 +700,7 @@ static int mtk_read_temp(void *data, int *temperature)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops mtk_thermal_ops = {
+static const struct thermal_zone_device_ops mtk_thermal_ops = {
 	.get_temp = mtk_read_temp,
 };
 
@@ -1082,8 +1082,8 @@ static int mtk_thermal_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, mt);
 
-	tzdev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, mt,
-						     &mtk_thermal_ops);
+	tzdev = devm_thermal_of_zone_register(&pdev->dev, 0, mt,
+					      &mtk_thermal_ops);
 	if (IS_ERR(tzdev)) {
 		ret = PTR_ERR(tzdev);
 		goto err_disable_clk_peri_therm;
diff --git a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c
index 073943cbcc2b..af68adf720cc 100644
--- a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c
+++ b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c
@@ -357,9 +357,9 @@ static irqreturn_t adc_tm5_gen2_isr(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int adc_tm5_get_temp(void *data, int *temp)
+static int adc_tm5_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct adc_tm5_channel *channel = data;
+	struct adc_tm5_channel *channel = tz->devdata;
 	int ret;
 
 	if (!channel || !channel->iio)
@@ -639,9 +639,9 @@ config_fail:
 	return ret;
 }
 
-static int adc_tm5_set_trips(void *data, int low, int high)
+static int adc_tm5_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	struct adc_tm5_channel *channel = data;
+	struct adc_tm5_channel *channel = tz->devdata;
 	struct adc_tm5_chip *chip;
 	int ret;
 
@@ -660,7 +660,7 @@ static int adc_tm5_set_trips(void *data, int low, int high)
 	return ret;
 }
 
-static struct thermal_zone_of_device_ops adc_tm5_thermal_ops = {
+static const struct thermal_zone_device_ops adc_tm5_thermal_ops = {
 	.get_temp = adc_tm5_get_temp,
 	.set_trips = adc_tm5_set_trips,
 };
@@ -672,11 +672,10 @@ static int adc_tm5_register_tzd(struct adc_tm5_chip *adc_tm)
 
 	for (i = 0; i < adc_tm->nchannels; i++) {
 		adc_tm->channels[i].chip = adc_tm;
-
-		tzd = devm_thermal_zone_of_sensor_register(adc_tm->dev,
-							   adc_tm->channels[i].channel,
-							   &adc_tm->channels[i],
-							   &adc_tm5_thermal_ops);
+		tzd = devm_thermal_of_zone_register(adc_tm->dev,
+						    adc_tm->channels[i].channel,
+						    &adc_tm->channels[i],
+						    &adc_tm5_thermal_ops);
 		if (IS_ERR(tzd)) {
 			if (PTR_ERR(tzd) == -ENODEV) {
 				dev_warn(adc_tm->dev, "thermal sensor on channel %d is not used\n",
@@ -1026,10 +1025,8 @@ static int adc_tm5_probe(struct platform_device *pdev)
 	adc_tm->base = reg;
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "get_irq failed: %d\n", irq);
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = adc_tm5_get_dt_data(adc_tm, node);
 	if (ret) {
diff --git a/drivers/thermal/qcom/qcom-spmi-temp-alarm.c b/drivers/thermal/qcom/qcom-spmi-temp-alarm.c
index 770f82cc9bca..be785ab37e53 100644
--- a/drivers/thermal/qcom/qcom-spmi-temp-alarm.c
+++ b/drivers/thermal/qcom/qcom-spmi-temp-alarm.c
@@ -186,9 +186,9 @@ static int qpnp_tm_update_temp_no_adc(struct qpnp_tm_chip *chip)
 	return 0;
 }
 
-static int qpnp_tm_get_temp(void *data, int *temp)
+static int qpnp_tm_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct qpnp_tm_chip *chip = data;
+	struct qpnp_tm_chip *chip = tz->devdata;
 	int ret, mili_celsius;
 
 	if (!temp)
@@ -263,9 +263,9 @@ skip:
 	return qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
 }
 
-static int qpnp_tm_set_trip_temp(void *data, int trip, int temp)
+static int qpnp_tm_set_trip_temp(struct thermal_zone_device *tz, int trip, int temp)
 {
-	struct qpnp_tm_chip *chip = data;
+	struct qpnp_tm_chip *chip = tz->devdata;
 	const struct thermal_trip *trip_points;
 	int ret;
 
@@ -283,7 +283,7 @@ static int qpnp_tm_set_trip_temp(void *data, int trip, int temp)
 	return ret;
 }
 
-static const struct thermal_zone_of_device_ops qpnp_tm_sensor_ops = {
+static const struct thermal_zone_device_ops qpnp_tm_sensor_ops = {
 	.get_temp = qpnp_tm_get_temp,
 	.set_trip_temp = qpnp_tm_set_trip_temp,
 };
@@ -446,7 +446,7 @@ static int qpnp_tm_probe(struct platform_device *pdev)
 	 * read the trip points. get_temp() returns the default temperature
 	 * before the hardware initialization is completed.
 	 */
-	chip->tz_dev = devm_thermal_zone_of_sensor_register(
+	chip->tz_dev = devm_thermal_of_zone_register(
 		&pdev->dev, 0, chip, &qpnp_tm_sensor_ops);
 	if (IS_ERR(chip->tz_dev)) {
 		dev_err(&pdev->dev, "failed to register sensor\n");
diff --git a/drivers/thermal/qcom/tsens.c b/drivers/thermal/qcom/tsens.c
index e49f58e83513..b1b10005fb28 100644
--- a/drivers/thermal/qcom/tsens.c
+++ b/drivers/thermal/qcom/tsens.c
@@ -532,9 +532,9 @@ static irqreturn_t tsens_irq_thread(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int tsens_set_trips(void *_sensor, int low, int high)
+static int tsens_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	struct tsens_sensor *s = _sensor;
+	struct tsens_sensor *s = tz->devdata;
 	struct tsens_priv *priv = s->priv;
 	struct device *dev = priv->dev;
 	struct tsens_irq_data d;
@@ -925,9 +925,9 @@ err_put_device:
 	return ret;
 }
 
-static int tsens_get_temp(void *data, int *temp)
+static int tsens_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct tsens_sensor *s = data;
+	struct tsens_sensor *s = tz->devdata;
 	struct tsens_priv *priv = s->priv;
 
 	return priv->ops->get_temp(s, temp);
@@ -991,7 +991,7 @@ static const struct of_device_id tsens_table[] = {
 };
 MODULE_DEVICE_TABLE(of, tsens_table);
 
-static const struct thermal_zone_of_device_ops tsens_of_ops = {
+static const struct thermal_zone_device_ops tsens_of_ops = {
 	.get_temp = tsens_get_temp,
 	.set_trips = tsens_set_trips,
 };
@@ -1044,9 +1044,9 @@ static int tsens_register(struct tsens_priv *priv)
 
 	for (i = 0;  i < priv->num_sensors; i++) {
 		priv->sensor[i].priv = priv;
-		tzd = devm_thermal_zone_of_sensor_register(priv->dev, priv->sensor[i].hw_id,
-							   &priv->sensor[i],
-							   &tsens_of_ops);
+		tzd = devm_thermal_of_zone_register(priv->dev, priv->sensor[i].hw_id,
+						    &priv->sensor[i],
+						    &tsens_of_ops);
 		if (IS_ERR(tzd))
 			continue;
 		priv->sensor[i].tzd = tzd;
diff --git a/drivers/thermal/qoriq_thermal.c b/drivers/thermal/qoriq_thermal.c
index 73049f9bea25..d111e218f362 100644
--- a/drivers/thermal/qoriq_thermal.c
+++ b/drivers/thermal/qoriq_thermal.c
@@ -82,9 +82,9 @@ static struct qoriq_tmu_data *qoriq_sensor_to_data(struct qoriq_sensor *s)
 	return container_of(s, struct qoriq_tmu_data, sensor[s->id]);
 }
 
-static int tmu_get_temp(void *p, int *temp)
+static int tmu_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct qoriq_sensor *qsensor = p;
+	struct qoriq_sensor *qsensor = tz->devdata;
 	struct qoriq_tmu_data *qdata = qoriq_sensor_to_data(qsensor);
 	u32 val;
 	/*
@@ -122,7 +122,7 @@ static int tmu_get_temp(void *p, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops tmu_tz_ops = {
+static const struct thermal_zone_device_ops tmu_tz_ops = {
 	.get_temp = tmu_get_temp,
 };
 
@@ -146,9 +146,9 @@ static int qoriq_tmu_register_tmu_zone(struct device *dev,
 
 		sensor->id = id;
 
-		tzd = devm_thermal_zone_of_sensor_register(dev, id,
-							   sensor,
-							   &tmu_tz_ops);
+		tzd = devm_thermal_of_zone_register(dev, id,
+						    sensor,
+						    &tmu_tz_ops);
 		ret = PTR_ERR_OR_ZERO(tzd);
 		if (ret) {
 			if (ret == -ENODEV)
diff --git a/drivers/thermal/rcar_gen3_thermal.c b/drivers/thermal/rcar_gen3_thermal.c
index cda7c52f2319..4c1c6f89aa2f 100644
--- a/drivers/thermal/rcar_gen3_thermal.c
+++ b/drivers/thermal/rcar_gen3_thermal.c
@@ -164,9 +164,9 @@ static int rcar_gen3_thermal_round(int temp)
 	return result * RCAR3_THERMAL_GRAN;
 }
 
-static int rcar_gen3_thermal_get_temp(void *devdata, int *temp)
+static int rcar_gen3_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct rcar_gen3_thermal_tsc *tsc = devdata;
+	struct rcar_gen3_thermal_tsc *tsc = tz->devdata;
 	int mcelsius, val;
 	int reg;
 
@@ -203,9 +203,9 @@ static int rcar_gen3_thermal_mcelsius_to_temp(struct rcar_gen3_thermal_tsc *tsc,
 	return INT_FIXPT(val);
 }
 
-static int rcar_gen3_thermal_set_trips(void *devdata, int low, int high)
+static int rcar_gen3_thermal_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	struct rcar_gen3_thermal_tsc *tsc = devdata;
+	struct rcar_gen3_thermal_tsc *tsc = tz->devdata;
 	u32 irqmsk = 0;
 
 	if (low != -INT_MAX) {
@@ -225,7 +225,7 @@ static int rcar_gen3_thermal_set_trips(void *devdata, int low, int high)
 	return 0;
 }
 
-static struct thermal_zone_of_device_ops rcar_gen3_tz_of_ops = {
+static struct thermal_zone_device_ops rcar_gen3_tz_of_ops = {
 	.get_temp	= rcar_gen3_thermal_get_temp,
 	.set_trips	= rcar_gen3_thermal_set_trips,
 };
@@ -508,8 +508,8 @@ static int rcar_gen3_thermal_probe(struct platform_device *pdev)
 	for (i = 0; i < priv->num_tscs; i++) {
 		struct rcar_gen3_thermal_tsc *tsc = priv->tscs[i];
 
-		zone = devm_thermal_zone_of_sensor_register(dev, i, tsc,
-							    &rcar_gen3_tz_of_ops);
+		zone = devm_thermal_of_zone_register(dev, i, tsc,
+						     &rcar_gen3_tz_of_ops);
 		if (IS_ERR(zone)) {
 			dev_err(dev, "Sensor %u: Can't register thermal zone\n", i);
 			ret = PTR_ERR(zone);
@@ -560,7 +560,7 @@ static int __maybe_unused rcar_gen3_thermal_resume(struct device *dev)
 
 		priv->thermal_init(tsc);
 		if (zone->ops->set_trips)
-			rcar_gen3_thermal_set_trips(tsc, zone->prev_low_trip,
+			rcar_gen3_thermal_set_trips(zone, zone->prev_low_trip,
 						    zone->prev_high_trip);
 	}
 
diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c
index 1d729ed4d685..4df42d70d867 100644
--- a/drivers/thermal/rcar_thermal.c
+++ b/drivers/thermal/rcar_thermal.c
@@ -271,13 +271,6 @@ static int rcar_thermal_get_current_temp(struct rcar_thermal_priv *priv,
 	return 0;
 }
 
-static int rcar_thermal_of_get_temp(void *data, int *temp)
-{
-	struct rcar_thermal_priv *priv = data;
-
-	return rcar_thermal_get_current_temp(priv, temp);
-}
-
 static int rcar_thermal_get_temp(struct thermal_zone_device *zone, int *temp)
 {
 	struct rcar_thermal_priv *priv = rcar_zone_to_priv(zone);
@@ -323,8 +316,8 @@ static int rcar_thermal_get_trip_temp(struct thermal_zone_device *zone,
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops rcar_thermal_zone_of_ops = {
-	.get_temp	= rcar_thermal_of_get_temp,
+static struct thermal_zone_device_ops rcar_thermal_zone_of_ops = {
+	.get_temp	= rcar_thermal_get_temp,
 };
 
 static struct thermal_zone_device_ops rcar_thermal_zone_ops = {
@@ -534,7 +527,7 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 			goto error_unregister;
 
 		if (chip->use_of_thermal) {
-			priv->zone = devm_thermal_zone_of_sensor_register(
+			priv->zone = devm_thermal_of_zone_register(
 						dev, i, priv,
 						&rcar_thermal_zone_of_ops);
 		} else {
diff --git a/drivers/thermal/rockchip_thermal.c b/drivers/thermal/rockchip_thermal.c
index dc3a9c276a09..819e059cde71 100644
--- a/drivers/thermal/rockchip_thermal.c
+++ b/drivers/thermal/rockchip_thermal.c
@@ -1211,9 +1211,9 @@ static irqreturn_t rockchip_thermal_alarm_irq_thread(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
-static int rockchip_thermal_set_trips(void *_sensor, int low, int high)
+static int rockchip_thermal_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	struct rockchip_thermal_sensor *sensor = _sensor;
+	struct rockchip_thermal_sensor *sensor = tz->devdata;
 	struct rockchip_thermal_data *thermal = sensor->thermal;
 	const struct rockchip_tsadc_chip *tsadc = thermal->chip;
 
@@ -1224,9 +1224,9 @@ static int rockchip_thermal_set_trips(void *_sensor, int low, int high)
 				     sensor->id, thermal->regs, high);
 }
 
-static int rockchip_thermal_get_temp(void *_sensor, int *out_temp)
+static int rockchip_thermal_get_temp(struct thermal_zone_device *tz, int *out_temp)
 {
-	struct rockchip_thermal_sensor *sensor = _sensor;
+	struct rockchip_thermal_sensor *sensor = tz->devdata;
 	struct rockchip_thermal_data *thermal = sensor->thermal;
 	const struct rockchip_tsadc_chip *tsadc = sensor->thermal->chip;
 	int retval;
@@ -1239,7 +1239,7 @@ static int rockchip_thermal_get_temp(void *_sensor, int *out_temp)
 	return retval;
 }
 
-static const struct thermal_zone_of_device_ops rockchip_of_thermal_ops = {
+static const struct thermal_zone_device_ops rockchip_of_thermal_ops = {
 	.get_temp = rockchip_thermal_get_temp,
 	.set_trips = rockchip_thermal_set_trips,
 };
@@ -1326,8 +1326,8 @@ rockchip_thermal_register_sensor(struct platform_device *pdev,
 
 	sensor->thermal = thermal;
 	sensor->id = id;
-	sensor->tzd = devm_thermal_zone_of_sensor_register(&pdev->dev, id,
-					sensor, &rockchip_of_thermal_ops);
+	sensor->tzd = devm_thermal_of_zone_register(&pdev->dev, id, sensor,
+						    &rockchip_of_thermal_ops);
 	if (IS_ERR(sensor->tzd)) {
 		error = PTR_ERR(sensor->tzd);
 		dev_err(&pdev->dev, "failed to register sensor %d: %d\n",
diff --git a/drivers/thermal/rzg2l_thermal.c b/drivers/thermal/rzg2l_thermal.c
index 51ae80eda6af..2e0649f38506 100644
--- a/drivers/thermal/rzg2l_thermal.c
+++ b/drivers/thermal/rzg2l_thermal.c
@@ -73,9 +73,9 @@ static inline void rzg2l_thermal_write(struct rzg2l_thermal_priv *priv, u32 reg,
 	iowrite32(data, priv->base + reg);
 }
 
-static int rzg2l_thermal_get_temp(void *devdata, int *temp)
+static int rzg2l_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct rzg2l_thermal_priv *priv = devdata;
+	struct rzg2l_thermal_priv *priv = tz->devdata;
 	u32 result = 0, dsensor, ts_code_ave;
 	int val, i;
 
@@ -114,7 +114,7 @@ static int rzg2l_thermal_get_temp(void *devdata, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops rzg2l_tz_of_ops = {
+static const struct thermal_zone_device_ops rzg2l_tz_of_ops = {
 	.get_temp = rzg2l_thermal_get_temp,
 };
 
@@ -207,8 +207,8 @@ static int rzg2l_thermal_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	zone = devm_thermal_zone_of_sensor_register(dev, 0, priv,
-						    &rzg2l_tz_of_ops);
+	zone = devm_thermal_of_zone_register(dev, 0, priv,
+					     &rzg2l_tz_of_ops);
 	if (IS_ERR(zone)) {
 		dev_err(dev, "Can't register thermal zone");
 		ret = PTR_ERR(zone);
diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c
index f4ab4c5b4b62..51874d0a284c 100644
--- a/drivers/thermal/samsung/exynos_tmu.c
+++ b/drivers/thermal/samsung/exynos_tmu.c
@@ -650,9 +650,9 @@ static void exynos7_tmu_control(struct platform_device *pdev, bool on)
 	writel(con, data->base + EXYNOS_TMU_REG_CONTROL);
 }
 
-static int exynos_get_temp(void *p, int *temp)
+static int exynos_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct exynos_tmu_data *data = p;
+	struct exynos_tmu_data *data = tz->devdata;
 	int value, ret = 0;
 
 	if (!data || !data->tmu_read)
@@ -728,9 +728,9 @@ static void exynos4412_tmu_set_emulation(struct exynos_tmu_data *data,
 	writel(val, data->base + emul_con);
 }
 
-static int exynos_tmu_set_emulation(void *drv_data, int temp)
+static int exynos_tmu_set_emulation(struct thermal_zone_device *tz, int temp)
 {
-	struct exynos_tmu_data *data = drv_data;
+	struct exynos_tmu_data *data = tz->devdata;
 	int ret = -EINVAL;
 
 	if (data->soc == SOC_ARCH_EXYNOS4210)
@@ -750,7 +750,7 @@ out:
 }
 #else
 #define exynos4412_tmu_set_emulation NULL
-static int exynos_tmu_set_emulation(void *drv_data, int temp)
+static int exynos_tmu_set_emulation(struct thermal_zone_device *tz, int temp)
 	{ return -EINVAL; }
 #endif /* CONFIG_THERMAL_EMULATION */
 
@@ -997,7 +997,7 @@ static int exynos_map_dt_data(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops exynos_sensor_ops = {
+static const struct thermal_zone_device_ops exynos_sensor_ops = {
 	.get_temp = exynos_get_temp,
 	.set_emul_temp = exynos_tmu_set_emulation,
 };
@@ -1091,8 +1091,8 @@ static int exynos_tmu_probe(struct platform_device *pdev)
 	 * data->tzd must be registered before calling exynos_tmu_initialize(),
 	 * requesting irq and calling exynos_tmu_control().
 	 */
-	data->tzd = thermal_zone_of_sensor_register(&pdev->dev, 0, data,
-						    &exynos_sensor_ops);
+	data->tzd = devm_thermal_of_zone_register(&pdev->dev, 0, data,
+						  &exynos_sensor_ops);
 	if (IS_ERR(data->tzd)) {
 		ret = PTR_ERR(data->tzd);
 		if (ret != -EPROBE_DEFER)
@@ -1104,21 +1104,19 @@ static int exynos_tmu_probe(struct platform_device *pdev)
 	ret = exynos_tmu_initialize(pdev);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to initialize TMU\n");
-		goto err_thermal;
+		goto err_sclk;
 	}
 
 	ret = devm_request_irq(&pdev->dev, data->irq, exynos_tmu_irq,
 		IRQF_TRIGGER_RISING | IRQF_SHARED, dev_name(&pdev->dev), data);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to request irq: %d\n", data->irq);
-		goto err_thermal;
+		goto err_sclk;
 	}
 
 	exynos_tmu_control(pdev, true);
 	return 0;
 
-err_thermal:
-	thermal_zone_of_sensor_unregister(&pdev->dev, data->tzd);
 err_sclk:
 	clk_disable_unprepare(data->sclk);
 err_clk:
@@ -1136,9 +1134,7 @@ err_sensor:
 static int exynos_tmu_remove(struct platform_device *pdev)
 {
 	struct exynos_tmu_data *data = platform_get_drvdata(pdev);
-	struct thermal_zone_device *tzd = data->tzd;
 
-	thermal_zone_of_sensor_unregister(&pdev->dev, tzd);
 	exynos_tmu_control(pdev, false);
 
 	clk_disable_unprepare(data->sclk);
diff --git a/drivers/thermal/sprd_thermal.c b/drivers/thermal/sprd_thermal.c
index fff80fc18002..ac884514f116 100644
--- a/drivers/thermal/sprd_thermal.c
+++ b/drivers/thermal/sprd_thermal.c
@@ -204,9 +204,9 @@ static int sprd_thm_temp_to_rawdata(int temp, struct sprd_thermal_sensor *sen)
 	return clamp(val, val, (u32)(SPRD_THM_RAW_DATA_HIGH - 1));
 }
 
-static int sprd_thm_read_temp(void *devdata, int *temp)
+static int sprd_thm_read_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct sprd_thermal_sensor *sen = devdata;
+	struct sprd_thermal_sensor *sen = tz->devdata;
 	u32 data;
 
 	data = readl(sen->data->base + SPRD_THM_TEMP(sen->id)) &
@@ -217,7 +217,7 @@ static int sprd_thm_read_temp(void *devdata, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops sprd_thm_ops = {
+static const struct thermal_zone_device_ops sprd_thm_ops = {
 	.get_temp = sprd_thm_read_temp,
 };
 
@@ -408,10 +408,10 @@ static int sprd_thm_probe(struct platform_device *pdev)
 
 		sprd_thm_sensor_init(thm, sen);
 
-		sen->tzd = devm_thermal_zone_of_sensor_register(sen->dev,
-								sen->id,
-								sen,
-								&sprd_thm_ops);
+		sen->tzd = devm_thermal_of_zone_register(sen->dev,
+							 sen->id,
+							 sen,
+							 &sprd_thm_ops);
 		if (IS_ERR(sen->tzd)) {
 			dev_err(&pdev->dev, "register thermal zone failed %d\n",
 				sen->id);
@@ -523,8 +523,8 @@ static int sprd_thm_remove(struct platform_device *pdev)
 
 	for (i = 0; i < thm->nr_sensors; i++) {
 		sprd_thm_toggle_sensor(thm->sensor[i], false);
-		devm_thermal_zone_of_sensor_unregister(&pdev->dev,
-						       thm->sensor[i]->tzd);
+		devm_thermal_of_zone_unregister(&pdev->dev,
+						thm->sensor[i]->tzd);
 	}
 
 	clk_disable_unprepare(thm->clk);
diff --git a/drivers/thermal/st/stm_thermal.c b/drivers/thermal/st/stm_thermal.c
index 5fd3fb8912a6..78feb802a87d 100644
--- a/drivers/thermal/st/stm_thermal.c
+++ b/drivers/thermal/st/stm_thermal.c
@@ -302,9 +302,9 @@ static int stm_disable_irq(struct stm_thermal_sensor *sensor)
 	return 0;
 }
 
-static int stm_thermal_set_trips(void *data, int low, int high)
+static int stm_thermal_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	struct stm_thermal_sensor *sensor = data;
+	struct stm_thermal_sensor *sensor = tz->devdata;
 	u32 itr1, th;
 	int ret;
 
@@ -350,9 +350,9 @@ static int stm_thermal_set_trips(void *data, int low, int high)
 }
 
 /* Callback to get temperature from HW */
-static int stm_thermal_get_temp(void *data, int *temp)
+static int stm_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct stm_thermal_sensor *sensor = data;
+	struct stm_thermal_sensor *sensor = tz->devdata;
 	u32 periods;
 	int freqM, ret;
 
@@ -474,7 +474,7 @@ static int stm_thermal_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(stm_thermal_pm_ops,
 			 stm_thermal_suspend, stm_thermal_resume);
 
-static const struct thermal_zone_of_device_ops stm_tz_ops = {
+static const struct thermal_zone_device_ops stm_tz_ops = {
 	.get_temp	= stm_thermal_get_temp,
 	.set_trips	= stm_thermal_set_trips,
 };
@@ -539,9 +539,9 @@ static int stm_thermal_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	sensor->th_dev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0,
-							      sensor,
-							      &stm_tz_ops);
+	sensor->th_dev = devm_thermal_of_zone_register(&pdev->dev, 0,
+						       sensor,
+						       &stm_tz_ops);
 
 	if (IS_ERR(sensor->th_dev)) {
 		dev_err(&pdev->dev, "%s: thermal zone sensor registering KO\n",
@@ -572,7 +572,6 @@ static int stm_thermal_probe(struct platform_device *pdev)
 	return 0;
 
 err_tz:
-	thermal_zone_of_sensor_unregister(&pdev->dev, sensor->th_dev);
 	return ret;
 }
 
@@ -582,7 +581,6 @@ static int stm_thermal_remove(struct platform_device *pdev)
 
 	stm_thermal_sensor_off(sensor);
 	thermal_remove_hwmon_sysfs(sensor->th_dev);
-	thermal_zone_of_sensor_unregister(&pdev->dev, sensor->th_dev);
 
 	return 0;
 }
diff --git a/drivers/thermal/sun8i_thermal.c b/drivers/thermal/sun8i_thermal.c
index 212c87e63a66..e64d06d1328c 100644
--- a/drivers/thermal/sun8i_thermal.c
+++ b/drivers/thermal/sun8i_thermal.c
@@ -108,9 +108,9 @@ static int sun50i_h5_calc_temp(struct ths_device *tmdev,
 		return -1590 * reg / 10 + 276000;
 }
 
-static int sun8i_ths_get_temp(void *data, int *temp)
+static int sun8i_ths_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct tsensor *s = data;
+	struct tsensor *s = tz->devdata;
 	struct ths_device *tmdev = s->tmdev;
 	int val = 0;
 
@@ -135,7 +135,7 @@ static int sun8i_ths_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops ths_ops = {
+static const struct thermal_zone_device_ops ths_ops = {
 	.get_temp = sun8i_ths_get_temp,
 };
 
@@ -468,10 +468,10 @@ static int sun8i_ths_register(struct ths_device *tmdev)
 		tmdev->sensor[i].tmdev = tmdev;
 		tmdev->sensor[i].id = i;
 		tmdev->sensor[i].tzd =
-			devm_thermal_zone_of_sensor_register(tmdev->dev,
-							     i,
-							     &tmdev->sensor[i],
-							     &ths_ops);
+			devm_thermal_of_zone_register(tmdev->dev,
+						      i,
+						      &tmdev->sensor[i],
+						      &ths_ops);
 		if (IS_ERR(tmdev->sensor[i].tzd))
 			return PTR_ERR(tmdev->sensor[i].tzd);
 
diff --git a/drivers/thermal/tegra/soctherm.c b/drivers/thermal/tegra/soctherm.c
index 825eab526619..1efe470f31e9 100644
--- a/drivers/thermal/tegra/soctherm.c
+++ b/drivers/thermal/tegra/soctherm.c
@@ -421,9 +421,9 @@ static int translate_temp(u16 val)
 	return t;
 }
 
-static int tegra_thermctl_get_temp(void *data, int *out_temp)
+static int tegra_thermctl_get_temp(struct thermal_zone_device *tz, int *out_temp)
 {
-	struct tegra_thermctl_zone *zone = data;
+	struct tegra_thermctl_zone *zone = tz->devdata;
 	u32 val;
 
 	val = readl(zone->reg);
@@ -582,10 +582,9 @@ static int tsensor_group_thermtrip_get(struct tegra_soctherm *ts, int id)
 	return temp;
 }
 
-static int tegra_thermctl_set_trip_temp(void *data, int trip, int temp)
+static int tegra_thermctl_set_trip_temp(struct thermal_zone_device *tz, int trip, int temp)
 {
-	struct tegra_thermctl_zone *zone = data;
-	struct thermal_zone_device *tz = zone->tz;
+	struct tegra_thermctl_zone *zone = tz->devdata;
 	struct tegra_soctherm *ts = zone->ts;
 	const struct tegra_tsensor_group *sg = zone->sg;
 	struct device *dev = zone->dev;
@@ -657,9 +656,9 @@ static void thermal_irq_disable(struct tegra_thermctl_zone *zn)
 	mutex_unlock(&zn->ts->thermctl_lock);
 }
 
-static int tegra_thermctl_set_trips(void *data, int lo, int hi)
+static int tegra_thermctl_set_trips(struct thermal_zone_device *tz, int lo, int hi)
 {
-	struct tegra_thermctl_zone *zone = data;
+	struct tegra_thermctl_zone *zone = tz->devdata;
 	u32 r;
 
 	thermal_irq_disable(zone);
@@ -682,7 +681,7 @@ static int tegra_thermctl_set_trips(void *data, int lo, int hi)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops tegra_of_thermal_ops = {
+static const struct thermal_zone_device_ops tegra_of_thermal_ops = {
 	.get_temp = tegra_thermctl_get_temp,
 	.set_trip_temp = tegra_thermctl_set_trip_temp,
 	.set_trips = tegra_thermctl_set_trips,
@@ -2194,9 +2193,9 @@ static int tegra_soctherm_probe(struct platform_device *pdev)
 		zone->sg = soc->ttgs[i];
 		zone->ts = tegra;
 
-		z = devm_thermal_zone_of_sensor_register(&pdev->dev,
-							 soc->ttgs[i]->id, zone,
-							 &tegra_of_thermal_ops);
+		z = devm_thermal_of_zone_register(&pdev->dev,
+						  soc->ttgs[i]->id, zone,
+						  &tegra_of_thermal_ops);
 		if (IS_ERR(z)) {
 			err = PTR_ERR(z);
 			dev_err(&pdev->dev, "failed to register sensor: %d\n",
diff --git a/drivers/thermal/tegra/tegra-bpmp-thermal.c b/drivers/thermal/tegra/tegra-bpmp-thermal.c
index 5affc3d196be..eb84f0b9dc7c 100644
--- a/drivers/thermal/tegra/tegra-bpmp-thermal.c
+++ b/drivers/thermal/tegra/tegra-bpmp-thermal.c
@@ -30,9 +30,9 @@ struct tegra_bpmp_thermal {
 	struct tegra_bpmp_thermal_zone **zones;
 };
 
-static int tegra_bpmp_thermal_get_temp(void *data, int *out_temp)
+static int __tegra_bpmp_thermal_get_temp(struct tegra_bpmp_thermal_zone *zone,
+					 int *out_temp)
 {
-	struct tegra_bpmp_thermal_zone *zone = data;
 	struct mrq_thermal_host_to_bpmp_request req;
 	union mrq_thermal_bpmp_to_host_response reply;
 	struct tegra_bpmp_message msg;
@@ -60,9 +60,14 @@ static int tegra_bpmp_thermal_get_temp(void *data, int *out_temp)
 	return 0;
 }
 
-static int tegra_bpmp_thermal_set_trips(void *data, int low, int high)
+static int tegra_bpmp_thermal_get_temp(struct thermal_zone_device *tz, int *out_temp)
 {
-	struct tegra_bpmp_thermal_zone *zone = data;
+	return __tegra_bpmp_thermal_get_temp(tz->devdata, out_temp);
+}
+
+static int tegra_bpmp_thermal_set_trips(struct thermal_zone_device *tz, int low, int high)
+{
+	struct tegra_bpmp_thermal_zone *zone = tz->devdata;
 	struct mrq_thermal_host_to_bpmp_request req;
 	struct tegra_bpmp_message msg;
 	int err;
@@ -157,7 +162,7 @@ static int tegra_bpmp_thermal_get_num_zones(struct tegra_bpmp *bpmp,
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops tegra_bpmp_of_thermal_ops = {
+static const struct thermal_zone_device_ops tegra_bpmp_of_thermal_ops = {
 	.get_temp = tegra_bpmp_thermal_get_temp,
 	.set_trips = tegra_bpmp_thermal_set_trips,
 };
@@ -200,13 +205,13 @@ static int tegra_bpmp_thermal_probe(struct platform_device *pdev)
 		zone->idx = i;
 		zone->tegra = tegra;
 
-		err = tegra_bpmp_thermal_get_temp(zone, &temp);
+		err = __tegra_bpmp_thermal_get_temp(zone, &temp);
 		if (err < 0) {
 			devm_kfree(&pdev->dev, zone);
 			continue;
 		}
 
-		tzd = devm_thermal_zone_of_sensor_register(
+		tzd = devm_thermal_of_zone_register(
 			&pdev->dev, i, zone, &tegra_bpmp_of_thermal_ops);
 		if (IS_ERR(tzd)) {
 			if (PTR_ERR(tzd) == -EPROBE_DEFER)
diff --git a/drivers/thermal/tegra/tegra30-tsensor.c b/drivers/thermal/tegra/tegra30-tsensor.c
index 05886684f429..c34501287e96 100644
--- a/drivers/thermal/tegra/tegra30-tsensor.c
+++ b/drivers/thermal/tegra/tegra30-tsensor.c
@@ -159,9 +159,9 @@ static void devm_tegra_tsensor_hw_disable(void *data)
 	tegra_tsensor_hw_disable(ts);
 }
 
-static int tegra_tsensor_get_temp(void *data, int *temp)
+static int tegra_tsensor_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	const struct tegra_tsensor_channel *tsc = data;
+	const struct tegra_tsensor_channel *tsc = tz->devdata;
 	const struct tegra_tsensor *ts = tsc->ts;
 	int err, c1, c2, c3, c4, counter;
 	u32 val;
@@ -217,9 +217,9 @@ static int tegra_tsensor_temp_to_counter(const struct tegra_tsensor *ts, int tem
 	return DIV_ROUND_CLOSEST(c2 * 1000000 - ts->calib.b, ts->calib.a);
 }
 
-static int tegra_tsensor_set_trips(void *data, int low, int high)
+static int tegra_tsensor_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	const struct tegra_tsensor_channel *tsc = data;
+	const struct tegra_tsensor_channel *tsc = tz->devdata;
 	const struct tegra_tsensor *ts = tsc->ts;
 	u32 val;
 
@@ -240,7 +240,7 @@ static int tegra_tsensor_set_trips(void *data, int low, int high)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops ops = {
+static const struct thermal_zone_device_ops ops = {
 	.get_temp = tegra_tsensor_get_temp,
 	.set_trips = tegra_tsensor_set_trips,
 };
@@ -516,7 +516,7 @@ static int tegra_tsensor_register_channel(struct tegra_tsensor *ts,
 	tsc->id = id;
 	tsc->regs = ts->regs + 0x40 * (hw_id + 1);
 
-	tsc->tzd = devm_thermal_zone_of_sensor_register(ts->dev, id, tsc, &ops);
+	tsc->tzd = devm_thermal_of_zone_register(ts->dev, id, tsc, &ops);
 	if (IS_ERR(tsc->tzd)) {
 		if (PTR_ERR(tsc->tzd) != -ENODEV)
 			return dev_err_probe(ts->dev, PTR_ERR(tsc->tzd),
diff --git a/drivers/thermal/thermal-generic-adc.c b/drivers/thermal/thermal-generic-adc.c
index 73665c3ccfe0..323e273e3298 100644
--- a/drivers/thermal/thermal-generic-adc.c
+++ b/drivers/thermal/thermal-generic-adc.c
@@ -52,9 +52,9 @@ static int gadc_thermal_adc_to_temp(struct gadc_thermal_info *gti, int val)
 	return temp;
 }
 
-static int gadc_thermal_get_temp(void *data, int *temp)
+static int gadc_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct gadc_thermal_info *gti = data;
+	struct gadc_thermal_info *gti = tz->devdata;
 	int val;
 	int ret;
 
@@ -68,7 +68,7 @@ static int gadc_thermal_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops gadc_thermal_ops = {
+static const struct thermal_zone_device_ops gadc_thermal_ops = {
 	.get_temp = gadc_thermal_get_temp,
 };
 
@@ -143,8 +143,8 @@ static int gadc_thermal_probe(struct platform_device *pdev)
 	gti->dev = &pdev->dev;
 	platform_set_drvdata(pdev, gti);
 
-	gti->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, gti,
-							   &gadc_thermal_ops);
+	gti->tz_dev = devm_thermal_of_zone_register(&pdev->dev, 0, gti,
+						    &gadc_thermal_ops);
 	if (IS_ERR(gti->tz_dev)) {
 		ret = PTR_ERR(gti->tz_dev);
 		if (ret != -EPROBE_DEFER)
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 50d50cec7774..99c0c19fa5a6 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -295,27 +295,14 @@ static void thermal_zone_device_set_polling(struct thermal_zone_device *tz,
 		cancel_delayed_work(&tz->poll_queue);
 }
 
-static inline bool should_stop_polling(struct thermal_zone_device *tz)
-{
-	return !thermal_zone_device_is_enabled(tz);
-}
-
 static void monitor_thermal_zone(struct thermal_zone_device *tz)
 {
-	bool stop;
-
-	stop = should_stop_polling(tz);
-
-	mutex_lock(&tz->lock);
-
-	if (!stop && tz->passive)
+	if (tz->mode != THERMAL_DEVICE_ENABLED)
+		thermal_zone_device_set_polling(tz, 0);
+	else if (tz->passive)
 		thermal_zone_device_set_polling(tz, tz->passive_delay_jiffies);
-	else if (!stop && tz->polling_delay_jiffies)
+	else if (tz->polling_delay_jiffies)
 		thermal_zone_device_set_polling(tz, tz->polling_delay_jiffies);
-	else
-		thermal_zone_device_set_polling(tz, 0);
-
-	mutex_unlock(&tz->lock);
 }
 
 static void handle_non_critical_trips(struct thermal_zone_device *tz, int trip)
@@ -383,18 +370,13 @@ static void handle_thermal_trip(struct thermal_zone_device *tz, int trip)
 		handle_critical_trips(tz, trip, trip_temp, type);
 	else
 		handle_non_critical_trips(tz, trip);
-	/*
-	 * Alright, we handled this trip successfully.
-	 * So, start monitoring again.
-	 */
-	monitor_thermal_zone(tz);
 }
 
 static void update_temperature(struct thermal_zone_device *tz)
 {
 	int temp, ret;
 
-	ret = thermal_zone_get_temp(tz, &temp);
+	ret = __thermal_zone_get_temp(tz, &temp);
 	if (ret) {
 		if (ret != -EAGAIN)
 			dev_warn(&tz->device,
@@ -403,10 +385,8 @@ static void update_temperature(struct thermal_zone_device *tz)
 		return;
 	}
 
-	mutex_lock(&tz->lock);
 	tz->last_temperature = tz->temperature;
 	tz->temperature = temp;
-	mutex_unlock(&tz->lock);
 
 	trace_thermal_temperature(tz);
 
@@ -469,15 +449,9 @@ EXPORT_SYMBOL_GPL(thermal_zone_device_disable);
 
 int thermal_zone_device_is_enabled(struct thermal_zone_device *tz)
 {
-	enum thermal_device_mode mode;
+	lockdep_assert_held(&tz->lock);
 
-	mutex_lock(&tz->lock);
-
-	mode = tz->mode;
-
-	mutex_unlock(&tz->lock);
-
-	return mode == THERMAL_DEVICE_ENABLED;
+	return tz->mode == THERMAL_DEVICE_ENABLED;
 }
 
 void thermal_zone_device_update(struct thermal_zone_device *tz,
@@ -485,9 +459,6 @@ void thermal_zone_device_update(struct thermal_zone_device *tz,
 {
 	int count;
 
-	if (should_stop_polling(tz))
-		return;
-
 	if (atomic_read(&in_suspend))
 		return;
 
@@ -495,14 +466,23 @@ void thermal_zone_device_update(struct thermal_zone_device *tz,
 		      "'get_temp' ops set\n", __func__))
 		return;
 
+	mutex_lock(&tz->lock);
+
+	if (!thermal_zone_device_is_enabled(tz))
+		goto out;
+
 	update_temperature(tz);
 
-	thermal_zone_set_trips(tz);
+	__thermal_zone_set_trips(tz);
 
 	tz->notify_event = event;
 
 	for (count = 0; count < tz->num_trips; count++)
 		handle_thermal_trip(tz, count);
+
+	monitor_thermal_zone(tz);
+out:
+	mutex_unlock(&tz->lock);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_device_update);
 
@@ -1458,9 +1438,6 @@ static int thermal_pm_notify(struct notifier_block *nb,
 	case PM_POST_SUSPEND:
 		atomic_set(&in_suspend, 0);
 		list_for_each_entry(tz, &thermal_tz_list, node) {
-			if (!thermal_zone_device_is_enabled(tz))
-				continue;
-
 			thermal_zone_device_init(tz);
 			thermal_zone_device_update(tz,
 						   THERMAL_EVENT_UNSPECIFIED);
@@ -1492,10 +1469,6 @@ static int __init thermal_init(void)
 	if (result)
 		goto unregister_governors;
 
-	result = of_parse_thermal_zones();
-	if (result)
-		goto unregister_class;
-
 	result = register_pm_notifier(&thermal_pm_nb);
 	if (result)
 		pr_warn("Thermal: Can not register suspend notifier, return %d\n",
@@ -1503,8 +1476,6 @@ static int __init thermal_init(void)
 
 	return 0;
 
-unregister_class:
-	class_unregister(&thermal_class);
 unregister_governors:
 	thermal_unregister_governors();
 error:
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index c991bb290512..1571917bd3c8 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -112,6 +112,8 @@ int thermal_build_list_of_policies(char *buf);
 
 /* Helpers */
 void thermal_zone_set_trips(struct thermal_zone_device *tz);
+void __thermal_zone_set_trips(struct thermal_zone_device *tz);
+int __thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp);
 
 /* sysfs I/F */
 int thermal_zone_create_device_groups(struct thermal_zone_device *, int);
@@ -135,13 +137,11 @@ thermal_cooling_device_stats_update(struct thermal_cooling_device *cdev,
 
 /* device tree support */
 #ifdef CONFIG_THERMAL_OF
-int of_parse_thermal_zones(void);
 int of_thermal_get_ntrips(struct thermal_zone_device *);
 bool of_thermal_is_trip_valid(struct thermal_zone_device *, int);
 const struct thermal_trip *
 of_thermal_get_trip_points(struct thermal_zone_device *);
 #else
-static inline int of_parse_thermal_zones(void) { return 0; }
 static inline int of_thermal_get_ntrips(struct thermal_zone_device *tz)
 {
 	return 0;
diff --git a/drivers/thermal/thermal_helpers.c b/drivers/thermal/thermal_helpers.c
index 690890f054a3..c65cdce8f856 100644
--- a/drivers/thermal/thermal_helpers.c
+++ b/drivers/thermal/thermal_helpers.c
@@ -64,27 +64,17 @@ get_thermal_instance(struct thermal_zone_device *tz,
 }
 EXPORT_SYMBOL(get_thermal_instance);
 
-/**
- * thermal_zone_get_temp() - returns the temperature of a thermal zone
- * @tz: a valid pointer to a struct thermal_zone_device
- * @temp: a valid pointer to where to store the resulting temperature.
- *
- * When a valid thermal zone reference is passed, it will fetch its
- * temperature and fill @temp.
- *
- * Return: On success returns 0, an error code otherwise
- */
-int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp)
+int __thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp)
 {
 	int ret = -EINVAL;
 	int count;
 	int crit_temp = INT_MAX;
 	enum thermal_trip_type type;
 
-	if (!tz || IS_ERR(tz) || !tz->ops->get_temp)
-		goto exit;
+	lockdep_assert_held(&tz->lock);
 
-	mutex_lock(&tz->lock);
+	if (!tz || IS_ERR(tz) || !tz->ops->get_temp)
+		return -EINVAL;
 
 	ret = tz->ops->get_temp(tz, temp);
 
@@ -107,35 +97,42 @@ int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp)
 			*temp = tz->emul_temperature;
 	}
 
-	mutex_unlock(&tz->lock);
-exit:
 	return ret;
 }
-EXPORT_SYMBOL_GPL(thermal_zone_get_temp);
 
 /**
- * thermal_zone_set_trips - Computes the next trip points for the driver
- * @tz: a pointer to a thermal zone device structure
+ * thermal_zone_get_temp() - returns the temperature of a thermal zone
+ * @tz: a valid pointer to a struct thermal_zone_device
+ * @temp: a valid pointer to where to store the resulting temperature.
  *
- * The function computes the next temperature boundaries by browsing
- * the trip points. The result is the closer low and high trip points
- * to the current temperature. These values are passed to the backend
- * driver to let it set its own notification mechanism (usually an
- * interrupt).
+ * When a valid thermal zone reference is passed, it will fetch its
+ * temperature and fill @temp.
  *
- * It does not return a value
+ * Return: On success returns 0, an error code otherwise
  */
-void thermal_zone_set_trips(struct thermal_zone_device *tz)
+int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp)
+{
+	int ret;
+
+	mutex_lock(&tz->lock);
+	ret = __thermal_zone_get_temp(tz, temp);
+	mutex_unlock(&tz->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(thermal_zone_get_temp);
+
+void __thermal_zone_set_trips(struct thermal_zone_device *tz)
 {
 	int low = -INT_MAX;
 	int high = INT_MAX;
 	int trip_temp, hysteresis;
 	int i, ret;
 
-	mutex_lock(&tz->lock);
+	lockdep_assert_held(&tz->lock);
 
 	if (!tz->ops->set_trips || !tz->ops->get_trip_hyst)
-		goto exit;
+		return;
 
 	for (i = 0; i < tz->num_trips; i++) {
 		int trip_low;
@@ -154,7 +151,7 @@ void thermal_zone_set_trips(struct thermal_zone_device *tz)
 
 	/* No need to change trip points */
 	if (tz->prev_low_trip == low && tz->prev_high_trip == high)
-		goto exit;
+		return;
 
 	tz->prev_low_trip = low;
 	tz->prev_high_trip = high;
@@ -169,8 +166,24 @@ void thermal_zone_set_trips(struct thermal_zone_device *tz)
 	ret = tz->ops->set_trips(tz, low, high);
 	if (ret)
 		dev_err(&tz->device, "Failed to set trips: %d\n", ret);
+}
 
-exit:
+/**
+ * thermal_zone_set_trips - Computes the next trip points for the driver
+ * @tz: a pointer to a thermal zone device structure
+ *
+ * The function computes the next temperature boundaries by browsing
+ * the trip points. The result is the closer low and high trip points
+ * to the current temperature. These values are passed to the backend
+ * driver to let it set its own notification mechanism (usually an
+ * interrupt).
+ *
+ * It does not return a value
+ */
+void thermal_zone_set_trips(struct thermal_zone_device *tz)
+{
+	mutex_lock(&tz->lock);
+	__thermal_zone_set_trips(tz);
 	mutex_unlock(&tz->lock);
 }
 
diff --git a/drivers/thermal/thermal_mmio.c b/drivers/thermal/thermal_mmio.c
index 360b0dfdc3b0..1bf1a16533da 100644
--- a/drivers/thermal/thermal_mmio.c
+++ b/drivers/thermal/thermal_mmio.c
@@ -20,11 +20,10 @@ static u32 thermal_mmio_readb(void __iomem *mmio_base)
 	return readb(mmio_base);
 }
 
-static int thermal_mmio_get_temperature(void *private, int *temp)
+static int thermal_mmio_get_temperature(struct thermal_zone_device *tz, int *temp)
 {
 	int t;
-	struct thermal_mmio *sensor =
-		(struct thermal_mmio *)private;
+	struct thermal_mmio *sensor = tz->devdata;
 
 	t = sensor->read_mmio(sensor->mmio_base) & sensor->mask;
 	t *= sensor->factor;
@@ -34,7 +33,7 @@ static int thermal_mmio_get_temperature(void *private, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops thermal_mmio_ops = {
+static const struct thermal_zone_device_ops thermal_mmio_ops = {
 	.get_temp = thermal_mmio_get_temperature,
 };
 
@@ -68,10 +67,10 @@ static int thermal_mmio_probe(struct platform_device *pdev)
 		}
 	}
 
-	thermal_zone = devm_thermal_zone_of_sensor_register(&pdev->dev,
-							    0,
-							    sensor,
-							    &thermal_mmio_ops);
+	thermal_zone = devm_thermal_of_zone_register(&pdev->dev,
+						     0,
+						     sensor,
+						     &thermal_mmio_ops);
 	if (IS_ERR(thermal_zone)) {
 		dev_err(&pdev->dev,
 			"failed to register sensor (%ld)\n",
@@ -79,7 +78,7 @@ static int thermal_mmio_probe(struct platform_device *pdev)
 		return PTR_ERR(thermal_zone);
 	}
 
-	thermal_mmio_get_temperature(sensor, &temperature);
+	thermal_mmio_get_temperature(thermal_zone, &temperature);
 	dev_info(&pdev->dev,
 		 "thermal mmio sensor %s registered, current temperature: %d\n",
 		 pdev->name, temperature);
diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c
index 802c30b72a92..fd2fb84bf246 100644
--- a/drivers/thermal/thermal_of.c
+++ b/drivers/thermal/thermal_of.c
@@ -19,93 +19,6 @@
 
 #include "thermal_core.h"
 
-/***   Private data structures to represent thermal device tree data ***/
-
-/**
- * struct __thermal_cooling_bind_param - a cooling device for a trip point
- * @cooling_device: a pointer to identify the referred cooling device
- * @min: minimum cooling state used at this trip point
- * @max: maximum cooling state used at this trip point
- */
-
-struct __thermal_cooling_bind_param {
-	struct device_node *cooling_device;
-	unsigned long min;
-	unsigned long max;
-};
-
-/**
- * struct __thermal_bind_params - a match between trip and cooling device
- * @tcbp: a pointer to an array of cooling devices
- * @count: number of elements in array
- * @trip_id: the trip point index
- * @usage: the percentage (from 0 to 100) of cooling contribution
- */
-
-struct __thermal_bind_params {
-	struct __thermal_cooling_bind_param *tcbp;
-	unsigned int count;
-	unsigned int trip_id;
-	unsigned int usage;
-};
-
-/**
- * struct __thermal_zone - internal representation of a thermal zone
- * @passive_delay: polling interval while passive cooling is activated
- * @polling_delay: zone polling interval
- * @slope: slope of the temperature adjustment curve
- * @offset: offset of the temperature adjustment curve
- * @ntrips: number of trip points
- * @trips: an array of trip points (0..ntrips - 1)
- * @num_tbps: number of thermal bind params
- * @tbps: an array of thermal bind params (0..num_tbps - 1)
- * @sensor_data: sensor private data used while reading temperature and trend
- * @ops: set of callbacks to handle the thermal zone based on DT
- */
-
-struct __thermal_zone {
-	int passive_delay;
-	int polling_delay;
-	int slope;
-	int offset;
-
-	/* trip data */
-	int ntrips;
-	struct thermal_trip *trips;
-
-	/* cooling binding data */
-	int num_tbps;
-	struct __thermal_bind_params *tbps;
-
-	/* sensor interface */
-	void *sensor_data;
-	const struct thermal_zone_of_device_ops *ops;
-};
-
-/***   DT thermal zone device callbacks   ***/
-
-static int of_thermal_get_temp(struct thermal_zone_device *tz,
-			       int *temp)
-{
-	struct __thermal_zone *data = tz->devdata;
-
-	if (!data->ops || !data->ops->get_temp)
-		return -EINVAL;
-
-	return data->ops->get_temp(data->sensor_data, temp);
-}
-
-static int of_thermal_set_trips(struct thermal_zone_device *tz,
-				int low, int high)
-{
-	struct __thermal_zone *data = tz->devdata;
-
-	if (!data->ops || !data->ops->set_trips)
-		return -EINVAL;
-
-	return data->ops->set_trips(data->sensor_data, low, high);
-}
-
 /**
  * of_thermal_get_ntrips - function to export number of available trip
  *			   points.
@@ -158,114 +71,6 @@ of_thermal_get_trip_points(struct thermal_zone_device *tz)
 }
 EXPORT_SYMBOL_GPL(of_thermal_get_trip_points);
 
-/**
- * of_thermal_set_emul_temp - function to set emulated temperature
- *
- * @tz:	pointer to a thermal zone
- * @temp:	temperature to set
- *
- * This function gives the ability to set emulated value of temperature,
- * which is handy for debugging
- *
- * Return: zero on success, error code otherwise
- */
-static int of_thermal_set_emul_temp(struct thermal_zone_device *tz,
-				    int temp)
-{
-	struct __thermal_zone *data = tz->devdata;
-
-	if (!data->ops || !data->ops->set_emul_temp)
-		return -EINVAL;
-
-	return data->ops->set_emul_temp(data->sensor_data, temp);
-}
-
-static int of_thermal_get_trend(struct thermal_zone_device *tz, int trip,
-				enum thermal_trend *trend)
-{
-	struct __thermal_zone *data = tz->devdata;
-
-	if (!data->ops || !data->ops->get_trend)
-		return -EINVAL;
-
-	return data->ops->get_trend(data->sensor_data, trip, trend);
-}
-
-static int of_thermal_change_mode(struct thermal_zone_device *tz,
-				enum thermal_device_mode mode)
-{
-	struct __thermal_zone *data = tz->devdata;
-
-	return data->ops->change_mode(data->sensor_data, mode);
-}
-
-static int of_thermal_bind(struct thermal_zone_device *thermal,
-			   struct thermal_cooling_device *cdev)
-{
-	struct __thermal_zone *data = thermal->devdata;
-	struct __thermal_bind_params *tbp;
-	struct __thermal_cooling_bind_param *tcbp;
-	int i, j;
-
-	if (!data || IS_ERR(data))
-		return -ENODEV;
-
-	/* find where to bind */
-	for (i = 0; i < data->num_tbps; i++) {
-		tbp = data->tbps + i;
-
-		for (j = 0; j < tbp->count; j++) {
-			tcbp = tbp->tcbp + j;
-
-			if (tcbp->cooling_device == cdev->np) {
-				int ret;
-
-				ret = thermal_zone_bind_cooling_device(thermal,
-						tbp->trip_id, cdev,
-						tcbp->max,
-						tcbp->min,
-						tbp->usage);
-				if (ret)
-					return ret;
-			}
-		}
-	}
-
-	return 0;
-}
-
-static int of_thermal_unbind(struct thermal_zone_device *thermal,
-			     struct thermal_cooling_device *cdev)
-{
-	struct __thermal_zone *data = thermal->devdata;
-	struct __thermal_bind_params *tbp;
-	struct __thermal_cooling_bind_param *tcbp;
-	int i, j;
-
-	if (!data || IS_ERR(data))
-		return -ENODEV;
-
-	/* find where to unbind */
-	for (i = 0; i < data->num_tbps; i++) {
-		tbp = data->tbps + i;
-
-		for (j = 0; j < tbp->count; j++) {
-			tcbp = tbp->tcbp + j;
-
-			if (tcbp->cooling_device == cdev->np) {
-				int ret;
-
-				ret = thermal_zone_unbind_cooling_device(thermal,
-							tbp->trip_id, cdev);
-				if (ret)
-					return ret;
-			}
-		}
-	}
-
-	return 0;
-}
-
 static int of_thermal_get_trip_type(struct thermal_zone_device *tz, int trip,
 				    enum thermal_trip_type *type)
 {
@@ -288,28 +93,6 @@ static int of_thermal_get_trip_temp(struct thermal_zone_device *tz, int trip,
 	return 0;
 }
 
-static int of_thermal_set_trip_temp(struct thermal_zone_device *tz, int trip,
-				    int temp)
-{
-	struct __thermal_zone *data = tz->devdata;
-
-	if (trip >= tz->num_trips || trip < 0)
-		return -EDOM;
-
-	if (data->ops && data->ops->set_trip_temp) {
-		int ret;
-
-		ret = data->ops->set_trip_temp(data->sensor_data, trip, temp);
-		if (ret)
-			return ret;
-	}
-
-	/* thermal framework should take care of data->mask & (1 << trip) */
-	tz->trips[trip].temperature = temp;
-
-	return 0;
-}
-
 static int of_thermal_get_trip_hyst(struct thermal_zone_device *tz, int trip,
 				    int *hyst)
 {
@@ -347,62 +130,6 @@ static int of_thermal_get_crit_temp(struct thermal_zone_device *tz,
 	return -EINVAL;
 }
 
-static struct thermal_zone_device_ops of_thermal_ops = {
-	.get_trip_type = of_thermal_get_trip_type,
-	.get_trip_temp = of_thermal_get_trip_temp,
-	.set_trip_temp = of_thermal_set_trip_temp,
-	.get_trip_hyst = of_thermal_get_trip_hyst,
-	.set_trip_hyst = of_thermal_set_trip_hyst,
-	.get_crit_temp = of_thermal_get_crit_temp,
-
-	.bind = of_thermal_bind,
-	.unbind = of_thermal_unbind,
-};
-
-/***   sensor API   ***/
-
-static struct thermal_zone_device *
-thermal_zone_of_add_sensor(struct device_node *zone,
-			   struct device_node *sensor, void *data,
-			   const struct thermal_zone_of_device_ops *ops)
-{
-	struct thermal_zone_device *tzd;
-	struct __thermal_zone *tz;
-
-	tzd = thermal_zone_get_zone_by_name(zone->name);
-	if (IS_ERR(tzd))
-		return ERR_PTR(-EPROBE_DEFER);
-
-	tz = tzd->devdata;
-
-	if (!ops)
-		return ERR_PTR(-EINVAL);
-
-	mutex_lock(&tzd->lock);
-	tz->ops = ops;
-	tz->sensor_data = data;
-
-	tzd->ops->get_temp = of_thermal_get_temp;
-	tzd->ops->get_trend = of_thermal_get_trend;
-
-	/*
-	 * The thermal zone core will calculate the window if they have set the
-	 * optional set_trips pointer.
-	 */
-	if (ops->set_trips)
-		tzd->ops->set_trips = of_thermal_set_trips;
-
-	if (ops->set_emul_temp)
-		tzd->ops->set_emul_temp = of_thermal_set_emul_temp;
-
-	if (ops->change_mode)
-		tzd->ops->change_mode = of_thermal_change_mode;
-
-	mutex_unlock(&tzd->lock);
-
-	return tzd;
-}
-
 /**
  * thermal_zone_of_get_sensor_id - get sensor ID from a DT thermal zone
  * @tz_np: a valid thermal zone device node.
@@ -447,207 +174,6 @@ int thermal_zone_of_get_sensor_id(struct device_node *tz_np,
 }
 EXPORT_SYMBOL_GPL(thermal_zone_of_get_sensor_id);
 
-/**
- * thermal_zone_of_sensor_register - registers a sensor to a DT thermal zone
- * @dev: a valid struct device pointer of a sensor device. Must contain
- *       a valid .of_node, for the sensor node.
- * @sensor_id: a sensor identifier, in case the sensor IP has more
- *             than one sensors
- * @data: a private pointer (owned by the caller) that will be passed
- *        back, when a temperature reading is needed.
- * @ops: struct thermal_zone_of_device_ops *. Must contain at least .get_temp.
- *
- * This function will search the list of thermal zones described in device
- * tree and look for the zone that refer to the sensor device pointed by
- * @dev->of_node as temperature providers. For the zone pointing to the
- * sensor node, the sensor will be added to the DT thermal zone device.
- *
- * The thermal zone temperature is provided by the @get_temp function
- * pointer. When called, it will have the private pointer @data back.
- *
- * The thermal zone temperature trend is provided by the @get_trend function
- * pointer. When called, it will have the private pointer @data back.
- *
- * TODO:
- * 01 - This function must enqueue the new sensor instead of using
- * it as the only source of temperature values.
- *
- * 02 - There must be a way to match the sensor with all thermal zones
- * that refer to it.
- *
- * Return: On success returns a valid struct thermal_zone_device,
- * otherwise, it returns a corresponding ERR_PTR(). Caller must
- * check the return value with help of IS_ERR() helper.
- */
-struct thermal_zone_device *
-thermal_zone_of_sensor_register(struct device *dev, int sensor_id, void *data,
-				const struct thermal_zone_of_device_ops *ops)
-{
-	struct device_node *np, *child, *sensor_np;
-	struct thermal_zone_device *tzd = ERR_PTR(-ENODEV);
-
-	np = of_find_node_by_name(NULL, "thermal-zones");
-	if (!np)
-		return ERR_PTR(-ENODEV);
-
-	if (!dev || !dev->of_node) {
-		of_node_put(np);
-		return ERR_PTR(-ENODEV);
-	}
-
-	sensor_np = of_node_get(dev->of_node);
-
-	for_each_available_child_of_node(np, child) {
-		int ret, id;
-
-		/* For now, thermal framework supports only 1 sensor per zone */
-		ret = thermal_zone_of_get_sensor_id(child, sensor_np, &id);
-		if (ret)
-			continue;
-
-		if (id == sensor_id) {
-			tzd = thermal_zone_of_add_sensor(child, sensor_np,
-							 data, ops);
-			if (!IS_ERR(tzd))
-				thermal_zone_device_enable(tzd);
-
-			of_node_put(child);
-			goto exit;
-		}
-	}
-exit:
-	of_node_put(sensor_np);
-	of_node_put(np);
-
-	return tzd;
-}
-EXPORT_SYMBOL_GPL(thermal_zone_of_sensor_register);
-
-/**
- * thermal_zone_of_sensor_unregister - unregisters a sensor from a DT thermal zone
- * @dev: a valid struct device pointer of a sensor device. Must contain
- *       a valid .of_node, for the sensor node.
- * @tzd: a pointer to struct thermal_zone_device where the sensor is registered.
- *
- * This function removes the sensor callbacks and private data from the
- * thermal zone device registered with thermal_zone_of_sensor_register()
- * API. It will also silent the zone by remove the .get_temp() and .get_trend()
- * thermal zone device callbacks.
- *
- * TODO: When the support to several sensors per zone is added, this
- * function must search the sensor list based on @dev parameter.
- *
- */
-void thermal_zone_of_sensor_unregister(struct device *dev,
-				       struct thermal_zone_device *tzd)
-{
-	struct __thermal_zone *tz;
-
-	if (!dev || !tzd || !tzd->devdata)
-		return;
-
-	tz = tzd->devdata;
-
-	/* no __thermal_zone, nothing to be done */
-	if (!tz)
-		return;
-
-	/* stop temperature polling */
-	thermal_zone_device_disable(tzd);
-
-	mutex_lock(&tzd->lock);
-	tzd->ops->get_temp = NULL;
-	tzd->ops->get_trend = NULL;
-	tzd->ops->set_emul_temp = NULL;
-	tzd->ops->change_mode = NULL;
-
-	tz->ops = NULL;
-	tz->sensor_data = NULL;
-	mutex_unlock(&tzd->lock);
-}
-EXPORT_SYMBOL_GPL(thermal_zone_of_sensor_unregister);
-
-static void devm_thermal_zone_of_sensor_release(struct device *dev, void *res)
-{
-	thermal_zone_of_sensor_unregister(dev,
-					  *(struct thermal_zone_device **)res);
-}
-
-static int devm_thermal_zone_of_sensor_match(struct device *dev, void *res,
-					     void *data)
-{
-	struct thermal_zone_device **r = res;
-
-	if (WARN_ON(!r || !*r))
-		return 0;
-
-	return *r == data;
-}
-
-/**
- * devm_thermal_zone_of_sensor_register - Resource managed version of
- *				thermal_zone_of_sensor_register()
- * @dev: a valid struct device pointer of a sensor device. Must contain
- *       a valid .of_node, for the sensor node.
- * @sensor_id: a sensor identifier, in case the sensor IP has more
- *	       than one sensors
- * @data: a private pointer (owned by the caller) that will be passed
- *	  back, when a temperature reading is needed.
- * @ops: struct thermal_zone_of_device_ops *. Must contain at least .get_temp.
- *
- * Refer thermal_zone_of_sensor_register() for more details.
- *
- * Return: On success returns a valid struct thermal_zone_device,
- * otherwise, it returns a corresponding ERR_PTR(). Caller must
- * check the return value with help of IS_ERR() helper.
- * Registered thermal_zone_device device will automatically be
- * released when device is unbounded.
- */
-struct thermal_zone_device *devm_thermal_zone_of_sensor_register(
-	struct device *dev, int sensor_id,
-	void *data, const struct thermal_zone_of_device_ops *ops)
-{
-	struct thermal_zone_device **ptr, *tzd;
-
-	ptr = devres_alloc(devm_thermal_zone_of_sensor_release, sizeof(*ptr),
-			   GFP_KERNEL);
-	if (!ptr)
-		return ERR_PTR(-ENOMEM);
-
-	tzd = thermal_zone_of_sensor_register(dev, sensor_id, data, ops);
-	if (IS_ERR(tzd)) {
-		devres_free(ptr);
-		return tzd;
-	}
-
-	*ptr = tzd;
-	devres_add(dev, ptr);
-
-	return tzd;
-}
-EXPORT_SYMBOL_GPL(devm_thermal_zone_of_sensor_register);
-
-/**
- * devm_thermal_zone_of_sensor_unregister - Resource managed version of
- *				thermal_zone_of_sensor_unregister().
- * @dev: Device for which which resource was allocated.
- * @tzd: a pointer to struct thermal_zone_device where the sensor is registered.
- *
- * This function removes the sensor callbacks and private data from the
- * thermal zone device registered with devm_thermal_zone_of_sensor_register()
- * API. It will also silent the zone by remove the .get_temp() and .get_trend()
- * thermal zone device callbacks.
- * Normally this function will not need to be called and the resource
- * management code will ensure that the resource is freed.
- */
-void devm_thermal_zone_of_sensor_unregister(struct device *dev,
-					    struct thermal_zone_device *tzd)
-{
-	WARN_ON(devres_release(dev, devm_thermal_zone_of_sensor_release,
-			       devm_thermal_zone_of_sensor_match, tzd));
-}
-EXPORT_SYMBOL_GPL(devm_thermal_zone_of_sensor_unregister);
-
 /***   functions parsing device tree nodes   ***/
 
 static int of_find_trip_id(struct device_node *np, struct device_node *trip)
@@ -679,98 +205,6 @@ out:
 	return i;
 }
 
-/**
- * thermal_of_populate_bind_params - parse and fill cooling map data
- * @np: DT node containing a cooling-map node
- * @__tbp: data structure to be filled with cooling map info
- * @trips: array of thermal zone trip points
- * @ntrips: number of trip points inside trips.
- *
- * This function parses a cooling-map type of node represented by
- * @np parameter and fills the read data into @__tbp data structure.
- * It needs the already parsed array of trip points of the thermal zone
- * in consideration.
- *
- * Return: 0 on success, proper error code otherwise
- */
-static int thermal_of_populate_bind_params(struct device_node *tz_np,
-					   struct device_node *np,
-					   struct __thermal_bind_params *__tbp)
-{
-	struct of_phandle_args cooling_spec;
-	struct __thermal_cooling_bind_param *__tcbp;
-	struct device_node *trip;
-	int ret, i, count;
-	int trip_id;
-	u32 prop;
-
-	/* Default weight. Usage is optional */
-	__tbp->usage = THERMAL_WEIGHT_DEFAULT;
-	ret = of_property_read_u32(np, "contribution", &prop);
-	if (ret == 0)
-		__tbp->usage = prop;
-
-	trip = of_parse_phandle(np, "trip", 0);
-	if (!trip) {
-		pr_err("missing trip property\n");
-		return -ENODEV;
-	}
-
-	trip_id = of_find_trip_id(tz_np, trip);
-	if (trip_id < 0) {
-		ret = trip_id;
-		goto end;
-	}
-
-	__tbp->trip_id = trip_id;
-
-	count = of_count_phandle_with_args(np, "cooling-device",
-					   "#cooling-cells");
-	if (count <= 0) {
-		pr_err("Add a cooling_device property with at least one device\n");
-		ret = -ENOENT;
-		goto end;
-	}
-
-	__tcbp = kcalloc(count, sizeof(*__tcbp), GFP_KERNEL);
-	if (!__tcbp) {
-		ret = -ENOMEM;
-		goto end;
-	}
-
-	for (i = 0; i < count; i++) {
-		ret = of_parse_phandle_with_args(np, "cooling-device",
-				"#cooling-cells", i, &cooling_spec);
-		if (ret < 0) {
-			pr_err("Invalid cooling-device entry\n");
-			goto free_tcbp;
-		}
-
-		__tcbp[i].cooling_device = cooling_spec.np;
-
-		if (cooling_spec.args_count >= 2) { /* at least min and max */
-			__tcbp[i].min = cooling_spec.args[0];
-			__tcbp[i].max = cooling_spec.args[1];
-		} else {
-			pr_err("wrong reference to cooling device, missing limits\n");
-		}
-	}
-
-	__tbp->tcbp = __tcbp;
-	__tbp->count = count;
-
-	goto end;
-
-free_tcbp:
-	for (i = i - 1; i >= 0; i--)
-		of_node_put(__tcbp[i].cooling_device);
-	kfree(__tcbp);
-end:
-	of_node_put(trip);
-
-	return ret;
-}
-
 /*
  * It maps 'enum thermal_trip_type' found in include/linux/thermal.h
  * into the device tree binding of 'trip', property type.
@@ -811,16 +245,6 @@ static int thermal_of_get_trip_type(struct device_node *np,
 	return -ENODEV;
 }
 
-/**
- * thermal_of_populate_trip - parse and fill one trip point data
- * @np: DT node containing a trip point node
- * @trip: trip point data structure to be filled up
- *
- * This function parses a trip point type of node represented by
- * @np parameter and fills the read data into @trip data structure.
- *
- * Return: 0 on success, proper error code otherwise
- */
 static int thermal_of_populate_trip(struct device_node *np,
 				    struct thermal_trip *trip)
 {
@@ -897,258 +321,458 @@ out_of_node_put:
 	return ERR_PTR(ret);
 }
 
-/**
- * thermal_of_build_thermal_zone - parse and fill one thermal zone data
- * @np: DT node containing a thermal zone node
- *
- * This function parses a thermal zone type of node represented by
- * @np parameter and fills the read data into a __thermal_zone data structure
- * and return this pointer.
- *
- * TODO: Missing properties to parse: thermal-sensor-names
- *
- * Return: On success returns a valid struct __thermal_zone,
- * otherwise, it returns a corresponding ERR_PTR(). Caller must
- * check the return value with help of IS_ERR() helper.
- */
-static struct __thermal_zone
-__init *thermal_of_build_thermal_zone(struct device_node *np)
+static struct device_node *of_thermal_zone_find(struct device_node *sensor, int id)
 {
-	struct device_node *child = NULL, *gchild;
-	struct __thermal_zone *tz;
-	int ret, i;
-	u32 prop, coef[2];
+	struct device_node *np, *tz;
+	struct of_phandle_args sensor_specs;
 
+	np = of_find_node_by_name(NULL, "thermal-zones");
 	if (!np) {
-		pr_err("no thermal zone np\n");
-		return ERR_PTR(-EINVAL);
+		pr_debug("No thermal zones description\n");
+		return ERR_PTR(-ENODEV);
 	}
 
-	tz = kzalloc(sizeof(*tz), GFP_KERNEL);
-	if (!tz)
-		return ERR_PTR(-ENOMEM);
+	/*
+	 * Search for each thermal zone, a defined sensor
+	 * corresponding to the one passed as parameter
+	 */
+	for_each_available_child_of_node(np, tz) {
+
+		int count, i;
+
+		count = of_count_phandle_with_args(tz, "thermal-sensors",
+						   "#thermal-sensor-cells");
+		if (count <= 0) {
+			pr_err("%pOFn: missing thermal sensor\n", tz);
+			tz = ERR_PTR(-EINVAL);
+			goto out;
+		}
+
+		for (i = 0; i < count; i++) {
+
+			int ret;
 
-	ret = of_property_read_u32(np, "polling-delay-passive", &prop);
+			ret = of_parse_phandle_with_args(tz, "thermal-sensors",
+							 "#thermal-sensor-cells",
+							 i, &sensor_specs);
+			if (ret < 0) {
+				pr_err("%pOFn: Failed to read thermal-sensors cells: %d\n", tz, ret);
+				tz = ERR_PTR(ret);
+				goto out;
+			}
+
+			if ((sensor == sensor_specs.np) && id == (sensor_specs.args_count ?
+								  sensor_specs.args[0] : 0)) {
+				pr_debug("sensor %pOFn id=%d belongs to %pOFn\n", sensor, id, tz);
+				goto out;
+			}
+		}
+	}
+	tz = ERR_PTR(-ENODEV);
+out:
+	of_node_put(np);
+	return tz;
+}
+
+static int thermal_of_monitor_init(struct device_node *np, int *delay, int *pdelay)
+{
+	int ret;
+
+	ret = of_property_read_u32(np, "polling-delay-passive", pdelay);
 	if (ret < 0) {
 		pr_err("%pOFn: missing polling-delay-passive property\n", np);
-		goto free_tz;
+		return ret;
 	}
-	tz->passive_delay = prop;
 
-	ret = of_property_read_u32(np, "polling-delay", &prop);
+	ret = of_property_read_u32(np, "polling-delay", delay);
 	if (ret < 0) {
 		pr_err("%pOFn: missing polling-delay property\n", np);
-		goto free_tz;
+		return ret;
 	}
-	tz->polling_delay = prop;
+
+	return 0;
+}
+
+static struct thermal_zone_params *thermal_of_parameters_init(struct device_node *np)
+{
+	struct thermal_zone_params *tzp;
+	int coef[2];
+	int ncoef = ARRAY_SIZE(coef);
+	int prop, ret;
+
+	tzp = kzalloc(sizeof(*tzp), GFP_KERNEL);
+	if (!tzp)
+		return ERR_PTR(-ENOMEM);
+
+	tzp->no_hwmon = true;
+
+	if (!of_property_read_u32(np, "sustainable-power", &prop))
+		tzp->sustainable_power = prop;
 
 	/*
-	 * REVIST: for now, the thermal framework supports only
-	 * one sensor per thermal zone. Thus, we are considering
-	 * only the first two values as slope and offset.
+	 * For now, the thermal framework supports only one sensor per
+	 * thermal zone. Thus, we are considering only the first two
+	 * values as slope and offset.
 	 */
-	ret = of_property_read_u32_array(np, "coefficients", coef, 2);
-	if (ret == 0) {
-		tz->slope = coef[0];
-		tz->offset = coef[1];
-	} else {
-		tz->slope = 1;
-		tz->offset = 0;
+	ret = of_property_read_u32_array(np, "coefficients", coef, ncoef);
+	if (ret) {
+		coef[0] = 1;
+		coef[1] = 0;
+	}
+
+	tzp->slope = coef[0];
+	tzp->offset = coef[1];
+
+	return tzp;
+}
+
+static struct device_node *thermal_of_zone_get_by_name(struct thermal_zone_device *tz)
+{
+	struct device_node *np, *tz_np;
+
+	np = of_find_node_by_name(NULL, "thermal-zones");
+	if (!np)
+		return ERR_PTR(-ENODEV);
+
+	tz_np = of_get_child_by_name(np, tz->type);
+
+	of_node_put(np);
+
+	if (!tz_np)
+		return ERR_PTR(-ENODEV);
+
+	return tz_np;
+}
+
+static int __thermal_of_unbind(struct device_node *map_np, int index, int trip_id,
+			       struct thermal_zone_device *tz, struct thermal_cooling_device *cdev)
+{
+	struct of_phandle_args cooling_spec;
+	int ret;
+
+	ret = of_parse_phandle_with_args(map_np, "cooling-device", "#cooling-cells",
+					 index, &cooling_spec);
+
+	of_node_put(cooling_spec.np);
+
+	if (ret < 0) {
+		pr_err("Invalid cooling-device entry\n");
+		return ret;
 	}
 
-	tz->trips = thermal_of_trips_init(np, &tz->ntrips);
-	if (IS_ERR(tz->trips)) {
-		ret = PTR_ERR(tz->trips);
-		goto finish;
+	if (cooling_spec.args_count < 2) {
+		pr_err("wrong reference to cooling device, missing limits\n");
+		return -EINVAL;
 	}
 
-	/* cooling-maps */
-	child = of_get_child_by_name(np, "cooling-maps");
+	if (cooling_spec.np != cdev->np)
+		return 0;
 
-	/* cooling-maps not provided */
-	if (!child)
-		goto finish;
+	ret = thermal_zone_unbind_cooling_device(tz, trip_id, cdev);
+	if (ret)
+		pr_err("Failed to unbind '%s' with '%s': %d\n", tz->type, cdev->type, ret);
 
-	tz->num_tbps = of_get_child_count(child);
-	if (tz->num_tbps == 0)
-		goto finish;
+	return ret;
+}
 
-	tz->tbps = kcalloc(tz->num_tbps, sizeof(*tz->tbps), GFP_KERNEL);
-	if (!tz->tbps) {
-		ret = -ENOMEM;
-		goto free_trips;
+static int __thermal_of_bind(struct device_node *map_np, int index, int trip_id,
+			     struct thermal_zone_device *tz, struct thermal_cooling_device *cdev)
+{
+	struct of_phandle_args cooling_spec;
+	int ret, weight = THERMAL_WEIGHT_DEFAULT;
+
+	of_property_read_u32(map_np, "contribution", &weight);
+
+	ret = of_parse_phandle_with_args(map_np, "cooling-device", "#cooling-cells",
+					 index, &cooling_spec);
+
+	of_node_put(cooling_spec.np);
+
+	if (ret < 0) {
+		pr_err("Invalid cooling-device entry\n");
+		return ret;
 	}
 
-	i = 0;
-	for_each_child_of_node(child, gchild) {
-		ret = thermal_of_populate_bind_params(np, gchild, &tz->tbps[i++]);
-		if (ret) {
-			of_node_put(gchild);
-			goto free_tbps;
-		}
+	if (cooling_spec.args_count < 2) {
+		pr_err("wrong reference to cooling device, missing limits\n");
+		return -EINVAL;
 	}
 
-finish:
-	of_node_put(child);
+	if (cooling_spec.np != cdev->np)
+		return 0;
+
+	ret = thermal_zone_bind_cooling_device(tz, trip_id, cdev, cooling_spec.args[1],
+					       cooling_spec.args[0],
+					       weight);
+	if (ret)
+		pr_err("Failed to bind '%s' with '%s': %d\n", tz->type, cdev->type, ret);
 
-	return tz;
+	return ret;
+}
 
-free_tbps:
-	for (i = i - 1; i >= 0; i--) {
-		struct __thermal_bind_params *tbp = tz->tbps + i;
-		int j;
+static int thermal_of_for_each_cooling_device(struct device_node *tz_np, struct device_node *map_np,
+					      struct thermal_zone_device *tz, struct thermal_cooling_device *cdev,
+					      int (*action)(struct device_node *, int, int,
+							    struct thermal_zone_device *, struct thermal_cooling_device *))
+{
+	struct device_node *tr_np;
+	int count, i, trip_id;
 
-		for (j = 0; j < tbp->count; j++)
-			of_node_put(tbp->tcbp[j].cooling_device);
+	tr_np = of_parse_phandle(map_np, "trip", 0);
+	if (!tr_np)
+		return -ENODEV;
 
-		kfree(tbp->tcbp);
+	trip_id = of_find_trip_id(tz_np, tr_np);
+	if (trip_id < 0)
+		return trip_id;
+
+	count = of_count_phandle_with_args(map_np, "cooling-device", "#cooling-cells");
+	if (count <= 0) {
+		pr_err("Add a cooling_device property with at least one device\n");
+		return -ENOENT;
 	}
 
-	kfree(tz->tbps);
-free_trips:
-	kfree(tz->trips);
-free_tz:
-	kfree(tz);
-	of_node_put(child);
+	/*
+	 * At this point, we don't want to bail out when there is an
+	 * error, we will try to bind/unbind as many as possible
+	 * cooling devices
+	 */
+	for (i = 0; i < count; i++)
+		action(map_np, i, trip_id, tz, cdev);
 
-	return ERR_PTR(ret);
+	return 0;
 }
 
-static __init void of_thermal_free_zone(struct __thermal_zone *tz)
+static int thermal_of_for_each_cooling_maps(struct thermal_zone_device *tz,
+					    struct thermal_cooling_device *cdev,
+					    int (*action)(struct device_node *, int, int,
+							  struct thermal_zone_device *, struct thermal_cooling_device *))
 {
-	struct __thermal_bind_params *tbp;
-	int i, j;
+	struct device_node *tz_np, *cm_np, *child;
+	int ret = 0;
 
-	for (i = 0; i < tz->num_tbps; i++) {
-		tbp = tz->tbps + i;
+	tz_np = thermal_of_zone_get_by_name(tz);
+	if (IS_ERR(tz_np)) {
+		pr_err("Failed to get node tz by name\n");
+		return PTR_ERR(tz_np);
+	}
 
-		for (j = 0; j < tbp->count; j++)
-			of_node_put(tbp->tcbp[j].cooling_device);
+	cm_np = of_get_child_by_name(tz_np, "cooling-maps");
+	if (!cm_np)
+		goto out;
 
-		kfree(tbp->tcbp);
+	for_each_child_of_node(cm_np, child) {
+		ret = thermal_of_for_each_cooling_device(tz_np, child, tz, cdev, action);
+		if (ret)
+			break;
 	}
 
-	kfree(tz->tbps);
-	kfree(tz->trips);
-	kfree(tz);
+	of_node_put(cm_np);
+out:
+	of_node_put(tz_np);
+
+	return ret;
+}
+
+static int thermal_of_bind(struct thermal_zone_device *tz,
+			   struct thermal_cooling_device *cdev)
+{
+	return thermal_of_for_each_cooling_maps(tz, cdev, __thermal_of_bind);
+}
+
+static int thermal_of_unbind(struct thermal_zone_device *tz,
+			     struct thermal_cooling_device *cdev)
+{
+	return thermal_of_for_each_cooling_maps(tz, cdev, __thermal_of_unbind);
 }
 
 /**
- * of_thermal_destroy_zones - remove all zones parsed and allocated resources
+ * thermal_of_zone_unregister - Cleanup the specific allocated ressources
  *
- * Finds all zones parsed and added to the thermal framework and remove them
- * from the system, together with their resources.
+ * This function disables the thermal zone and frees the different
+ * ressources allocated specific to the thermal OF.
  *
+ * @tz: a pointer to the thermal zone structure
  */
-static __init void of_thermal_destroy_zones(void)
+void thermal_of_zone_unregister(struct thermal_zone_device *tz)
 {
-	struct device_node *np, *child;
+	struct thermal_trip *trips = tz->trips;
+	struct thermal_zone_params *tzp = tz->tzp;
+	struct thermal_zone_device_ops *ops = tz->ops;
 
-	np = of_find_node_by_name(NULL, "thermal-zones");
-	if (!np) {
-		pr_debug("unable to find thermal zones\n");
-		return;
+	thermal_zone_device_disable(tz);
+	thermal_zone_device_unregister(tz);
+	kfree(trips);
+	kfree(tzp);
+	kfree(ops);
+}
+EXPORT_SYMBOL_GPL(thermal_of_zone_unregister);
+
+/**
+ * thermal_of_zone_register - Register a thermal zone with device node
+ * sensor
+ *
+ * The thermal_of_zone_register() parses a device tree given a device
+ * node sensor and identifier. It searches for the thermal zone
+ * associated to the couple sensor/id and retrieves all the thermal
+ * zone properties and registers new thermal zone with those
+ * properties.
+ *
+ * @sensor: A device node pointer corresponding to the sensor in the device tree
+ * @id: An integer as sensor identifier
+ * @data: A private data to be stored in the thermal zone dedicated private area
+ * @ops: A set of thermal sensor ops
+ *
+ * Return: a valid thermal zone structure pointer on success.
+ * 	- EINVAL: if the device tree thermal description is malformed
+ *	- ENOMEM: if one structure can not be allocated
+ *	- Other negative errors are returned by the underlying called functions
+ */
+struct thermal_zone_device *thermal_of_zone_register(struct device_node *sensor, int id, void *data,
+						     const struct thermal_zone_device_ops *ops)
+{
+	struct thermal_zone_device *tz;
+	struct thermal_trip *trips;
+	struct thermal_zone_params *tzp;
+	struct thermal_zone_device_ops *of_ops;
+	struct device_node *np;
+	int delay, pdelay;
+	int ntrips, mask;
+	int ret;
+
+	of_ops = kmemdup(ops, sizeof(*ops), GFP_KERNEL);
+	if (!of_ops)
+		return ERR_PTR(-ENOMEM);
+
+	np = of_thermal_zone_find(sensor, id);
+	if (IS_ERR(np)) {
+		if (PTR_ERR(np) != -ENODEV)
+			pr_err("Failed to find thermal zone for %pOFn id=%d\n", sensor, id);
+		return ERR_CAST(np);
 	}
 
-	for_each_available_child_of_node(np, child) {
-		struct thermal_zone_device *zone;
+	trips = thermal_of_trips_init(np, &ntrips);
+	if (IS_ERR(trips)) {
+		pr_err("Failed to find trip points for %pOFn id=%d\n", sensor, id);
+		return ERR_CAST(trips);
+	}
 
-		zone = thermal_zone_get_zone_by_name(child->name);
-		if (IS_ERR(zone))
-			continue;
+	ret = thermal_of_monitor_init(np, &delay, &pdelay);
+	if (ret) {
+		pr_err("Failed to initialize monitoring delays from %pOFn\n", np);
+		goto out_kfree_trips;
+	}
 
-		thermal_zone_device_unregister(zone);
-		kfree(zone->tzp);
-		kfree(zone->ops);
-		of_thermal_free_zone(zone->devdata);
+	tzp = thermal_of_parameters_init(np);
+	if (IS_ERR(tzp)) {
+		ret = PTR_ERR(tzp);
+		pr_err("Failed to initialize parameter from %pOFn: %d\n", np, ret);
+		goto out_kfree_trips;
 	}
-	of_node_put(np);
+
+	of_ops->get_trip_type = of_ops->get_trip_type ? : of_thermal_get_trip_type;
+	of_ops->get_trip_temp = of_ops->get_trip_temp ? : of_thermal_get_trip_temp;
+	of_ops->get_trip_hyst = of_ops->get_trip_hyst ? : of_thermal_get_trip_hyst;
+	of_ops->set_trip_hyst = of_ops->set_trip_hyst ? : of_thermal_set_trip_hyst;
+	of_ops->get_crit_temp = of_ops->get_crit_temp ? : of_thermal_get_crit_temp;
+	of_ops->bind = thermal_of_bind;
+	of_ops->unbind = thermal_of_unbind;
+
+	mask = GENMASK_ULL((ntrips) - 1, 0);
+
+	tz = thermal_zone_device_register_with_trips(np->name, trips, ntrips,
+						     mask, data, of_ops, tzp,
+						     pdelay, delay);
+	if (IS_ERR(tz)) {
+		ret = PTR_ERR(tz);
+		pr_err("Failed to register thermal zone %pOFn: %d\n", np, ret);
+		goto out_kfree_tzp;
+	}
+
+	ret = thermal_zone_device_enable(tz);
+	if (ret) {
+		pr_err("Failed to enabled thermal zone '%s', id=%d: %d\n",
+		       tz->type, tz->id, ret);
+		thermal_of_zone_unregister(tz);
+		return ERR_PTR(ret);
+	}
+
+	return tz;
+
+out_kfree_tzp:
+	kfree(tzp);
+out_kfree_trips:
+	kfree(trips);
+
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(thermal_of_zone_register);
+
+static void devm_thermal_of_zone_release(struct device *dev, void *res)
+{
+	thermal_of_zone_unregister(*(struct thermal_zone_device **)res);
+}
+
+static int devm_thermal_of_zone_match(struct device *dev, void *res,
+				      void *data)
+{
+	struct thermal_zone_device **r = res;
+
+	if (WARN_ON(!r || !*r))
+		return 0;
+
+	return *r == data;
 }
 
 /**
- * of_parse_thermal_zones - parse device tree thermal data
+ * devm_thermal_of_zone_register - register a thermal tied with the sensor life cycle
  *
- * Initialization function that can be called by machine initialization
- * code to parse thermal data and populate the thermal framework
- * with hardware thermal zones info. This function only parses thermal zones.
- * Cooling devices and sensor devices nodes are supposed to be parsed
- * by their respective drivers.
- *
- * Return: 0 on success, proper error code otherwise
+ * This function is the device version of the thermal_of_zone_register() function.
  *
+ * @dev: a device structure pointer to sensor to be tied with the thermal zone OF life cycle
+ * @sensor_id: the sensor identifier
+ * @data: a pointer to a private data to be stored in the thermal zone 'devdata' field
+ * @ops: a pointer to the ops structure associated with the sensor
  */
-int __init of_parse_thermal_zones(void)
+struct thermal_zone_device *devm_thermal_of_zone_register(struct device *dev, int sensor_id, void *data,
+							  const struct thermal_zone_device_ops *ops)
 {
-	struct device_node *np, *child;
-	struct __thermal_zone *tz;
-	struct thermal_zone_device_ops *ops;
-
-	np = of_find_node_by_name(NULL, "thermal-zones");
-	if (!np) {
-		pr_debug("unable to find thermal zones\n");
-		return 0; /* Run successfully on systems without thermal DT */
-	}
-
-	for_each_available_child_of_node(np, child) {
-		struct thermal_zone_device *zone;
-		struct thermal_zone_params *tzp;
-		int i, mask = 0;
-		u32 prop;
-
-		tz = thermal_of_build_thermal_zone(child);
-		if (IS_ERR(tz)) {
-			pr_err("failed to build thermal zone %pOFn: %ld\n",
-			       child,
-			       PTR_ERR(tz));
-			continue;
-		}
-
-		ops = kmemdup(&of_thermal_ops, sizeof(*ops), GFP_KERNEL);
-		if (!ops)
-			goto exit_free;
+	struct thermal_zone_device **ptr, *tzd;
 
-		tzp = kzalloc(sizeof(*tzp), GFP_KERNEL);
-		if (!tzp) {
-			kfree(ops);
-			goto exit_free;
-		}
+	ptr = devres_alloc(devm_thermal_of_zone_release, sizeof(*ptr),
+			   GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
 
-		/* No hwmon because there might be hwmon drivers registering */
-		tzp->no_hwmon = true;
-
-		if (!of_property_read_u32(child, "sustainable-power", &prop))
-			tzp->sustainable_power = prop;
-
-		for (i = 0; i < tz->ntrips; i++)
-			mask |= 1 << i;
-
-		/* these two are left for temperature drivers to use */
-		tzp->slope = tz->slope;
-		tzp->offset = tz->offset;
-
-		zone = thermal_zone_device_register_with_trips(child->name, tz->trips, tz->ntrips,
-							       mask, tz, ops, tzp, tz->passive_delay,
-							       tz->polling_delay);
-		if (IS_ERR(zone)) {
-			pr_err("Failed to build %pOFn zone %ld\n", child,
-			       PTR_ERR(zone));
-			kfree(tzp);
-			kfree(ops);
-			of_thermal_free_zone(tz);
-			/* attempting to build remaining zones still */
-		}
+	tzd = thermal_of_zone_register(dev->of_node, sensor_id, data, ops);
+	if (IS_ERR(tzd)) {
+		devres_free(ptr);
+		return tzd;
 	}
-	of_node_put(np);
-
-	return 0;
 
-exit_free:
-	of_node_put(child);
-	of_node_put(np);
-	of_thermal_free_zone(tz);
+	*ptr = tzd;
+	devres_add(dev, ptr);
 
-	/* no memory available, so free what we have built */
-	of_thermal_destroy_zones();
+	return tzd;
+}
+EXPORT_SYMBOL_GPL(devm_thermal_of_zone_register);
 
-	return -ENOMEM;
+/**
+ * devm_thermal_of_zone_unregister - Resource managed version of
+ *				thermal_of_zone_unregister().
+ * @dev: Device for which which resource was allocated.
+ * @tz: a pointer to struct thermal_zone where the sensor is registered.
+ *
+ * This function removes the sensor callbacks and private data from the
+ * thermal zone device registered with devm_thermal_zone_of_sensor_register()
+ * API. It will also silent the zone by remove the .get_temp() and .get_trend()
+ * thermal zone device callbacks.
+ * Normally this function will not need to be called and the resource
+ * management code will ensure that the resource is freed.
+ */
+void devm_thermal_of_zone_unregister(struct device *dev, struct thermal_zone_device *tz)
+{
+	WARN_ON(devres_release(dev, devm_thermal_of_zone_release,
+			       devm_thermal_of_zone_match, tz));
 }
+EXPORT_SYMBOL_GPL(devm_thermal_of_zone_unregister);
diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c
index 3a8d6e747c25..78c5841bdfae 100644
--- a/drivers/thermal/thermal_sysfs.c
+++ b/drivers/thermal/thermal_sysfs.c
@@ -49,7 +49,11 @@ static ssize_t
 mode_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct thermal_zone_device *tz = to_thermal_zone(dev);
-	int enabled = thermal_zone_device_is_enabled(tz);
+	int enabled;
+
+	mutex_lock(&tz->lock);
+	enabled = thermal_zone_device_is_enabled(tz);
+	mutex_unlock(&tz->lock);
 
 	return sprintf(buf, "%s\n", enabled ? "enabled" : "disabled");
 }
@@ -115,7 +119,7 @@ trip_point_temp_store(struct device *dev, struct device_attribute *attr,
 	int temperature, hyst = 0;
 	enum thermal_trip_type type;
 
-	if (!tz->ops->set_trip_temp)
+	if (!tz->ops->set_trip_temp && !tz->trips)
 		return -EPERM;
 
 	if (sscanf(attr->attr.name, "trip_point_%d_temp", &trip) != 1)
@@ -128,6 +132,9 @@ trip_point_temp_store(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
+	if (tz->trips)
+		tz->trips[trip].temperature = temperature;
+
 	if (tz->ops->get_trip_hyst) {
 		ret = tz->ops->get_trip_hyst(tz, trip, &hyst);
 		if (ret)
diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
index 703039d8b937..8a9055bd376e 100644
--- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
+++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
@@ -65,10 +65,10 @@ static inline int ti_thermal_hotspot_temperature(int t, int s, int c)
 
 /* thermal zone ops */
 /* Get temperature callback function for thermal zone */
-static inline int __ti_thermal_get_temp(void *devdata, int *temp)
+static inline int __ti_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
 	struct thermal_zone_device *pcb_tz = NULL;
-	struct ti_thermal_data *data = devdata;
+	struct ti_thermal_data *data = tz->devdata;
 	struct ti_bandgap *bgp;
 	const struct ti_temp_sensor *s;
 	int ret, tmp, slope, constant;
@@ -85,8 +85,8 @@ static inline int __ti_thermal_get_temp(void *devdata, int *temp)
 		return ret;
 
 	/* Default constants */
-	slope = thermal_zone_get_slope(data->ti_thermal);
-	constant = thermal_zone_get_offset(data->ti_thermal);
+	slope = thermal_zone_get_slope(tz);
+	constant = thermal_zone_get_offset(tz);
 
 	pcb_tz = data->pcb_tz;
 	/* In case pcb zone is available, use the extrapolation rule with it */
@@ -107,9 +107,9 @@ static inline int __ti_thermal_get_temp(void *devdata, int *temp)
 	return ret;
 }
 
-static int __ti_thermal_get_trend(void *p, int trip, enum thermal_trend *trend)
+static int __ti_thermal_get_trend(struct thermal_zone_device *tz, int trip, enum thermal_trend *trend)
 {
-	struct ti_thermal_data *data = p;
+	struct ti_thermal_data *data = tz->devdata;
 	struct ti_bandgap *bgp;
 	int id, tr, ret = 0;
 
@@ -130,7 +130,7 @@ static int __ti_thermal_get_trend(void *p, int trip, enum thermal_trend *trend)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops ti_of_thermal_ops = {
+static const struct thermal_zone_device_ops ti_of_thermal_ops = {
 	.get_temp = __ti_thermal_get_temp,
 	.get_trend = __ti_thermal_get_trend,
 };
@@ -170,7 +170,7 @@ int ti_thermal_expose_sensor(struct ti_bandgap *bgp, int id,
 		return -EINVAL;
 
 	/* in case this is specified by DT */
-	data->ti_thermal = devm_thermal_zone_of_sensor_register(bgp->dev, id,
+	data->ti_thermal = devm_thermal_of_zone_register(bgp->dev, id,
 					data, &ti_of_thermal_ops);
 	if (IS_ERR(data->ti_thermal)) {
 		dev_err(bgp->dev, "thermal zone device is NULL\n");
diff --git a/drivers/thermal/uniphier_thermal.c b/drivers/thermal/uniphier_thermal.c
index 4cae5561a2a3..4111d99ef50e 100644
--- a/drivers/thermal/uniphier_thermal.c
+++ b/drivers/thermal/uniphier_thermal.c
@@ -187,9 +187,9 @@ static void uniphier_tm_disable_sensor(struct uniphier_tm_dev *tdev)
 	usleep_range(1000, 2000);	/* The spec note says at least 1ms */
 }
 
-static int uniphier_tm_get_temp(void *data, int *out_temp)
+static int uniphier_tm_get_temp(struct thermal_zone_device *tz, int *out_temp)
 {
-	struct uniphier_tm_dev *tdev = data;
+	struct uniphier_tm_dev *tdev = tz->devdata;
 	struct regmap *map = tdev->regmap;
 	int ret;
 	u32 temp;
@@ -204,7 +204,7 @@ static int uniphier_tm_get_temp(void *data, int *out_temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops uniphier_of_thermal_ops = {
+static const struct thermal_zone_device_ops uniphier_of_thermal_ops = {
 	.get_temp = uniphier_tm_get_temp,
 };
 
@@ -289,8 +289,8 @@ static int uniphier_tm_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, tdev);
 
-	tdev->tz_dev = devm_thermal_zone_of_sensor_register(dev, 0, tdev,
-						&uniphier_of_thermal_ops);
+	tdev->tz_dev = devm_thermal_of_zone_register(dev, 0, tdev,
+						     &uniphier_of_thermal_ops);
 	if (IS_ERR(tdev->tz_dev)) {
 		dev_err(dev, "failed to register sensor device\n");
 		return PTR_ERR(tdev->tz_dev);
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index c492a57531c6..3ff746e3f24a 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -360,7 +360,7 @@ static void vm_synchronize_cbs(struct virtio_device *vdev)
 
 static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int index,
 				  void (*callback)(struct virtqueue *vq),
-				  const char *name, u32 size, bool ctx)
+				  const char *name, bool ctx)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
 	struct virtio_mmio_vq_info *info;
@@ -395,11 +395,8 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int in
 		goto error_new_virtqueue;
 	}
 
-	if (!size || size > num)
-		size = num;
-
 	/* Create the vring */
-	vq = vring_create_virtqueue(index, size, VIRTIO_MMIO_VRING_ALIGN, vdev,
+	vq = vring_create_virtqueue(index, num, VIRTIO_MMIO_VRING_ALIGN, vdev,
 				 true, true, ctx, vm_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;
@@ -477,7 +474,6 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 		       struct virtqueue *vqs[],
 		       vq_callback_t *callbacks[],
 		       const char * const names[],
-		       u32 sizes[],
 		       const bool *ctx,
 		       struct irq_affinity *desc)
 {
@@ -503,7 +499,6 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 		}
 
 		vqs[i] = vm_setup_vq(vdev, queue_idx++, callbacks[i], names[i],
-				     sizes ? sizes[i] : 0,
 				     ctx ? ctx[i] : false);
 		if (IS_ERR(vqs[i])) {
 			vm_del_vqs(vdev);
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 00ad476a815d..ad258a9d3b9f 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -174,7 +174,6 @@ error:
 static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned int index,
 				     void (*callback)(struct virtqueue *vq),
 				     const char *name,
-				     u32 size,
 				     bool ctx,
 				     u16 msix_vec)
 {
@@ -187,7 +186,7 @@ static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned int in
 	if (!info)
 		return ERR_PTR(-ENOMEM);
 
-	vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, size, ctx,
+	vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, ctx,
 			      msix_vec);
 	if (IS_ERR(vq))
 		goto out_info;
@@ -284,7 +283,7 @@ void vp_del_vqs(struct virtio_device *vdev)
 
 static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], u32 sizes[], bool per_vq_vectors,
+		const char * const names[], bool per_vq_vectors,
 		const bool *ctx,
 		struct irq_affinity *desc)
 {
@@ -327,8 +326,8 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs,
 		else
 			msix_vec = VP_MSIX_VQ_VECTOR;
 		vqs[i] = vp_setup_vq(vdev, queue_idx++, callbacks[i], names[i],
-				     sizes ? sizes[i] : 0,
-				     ctx ? ctx[i] : false, msix_vec);
+				     ctx ? ctx[i] : false,
+				     msix_vec);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
 			goto error_find;
@@ -358,7 +357,7 @@ error_find:
 
 static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], u32 sizes[], const bool *ctx)
+		const char * const names[], const bool *ctx)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	int i, err, queue_idx = 0;
@@ -380,7 +379,6 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs,
 			continue;
 		}
 		vqs[i] = vp_setup_vq(vdev, queue_idx++, callbacks[i], names[i],
-				     sizes ? sizes[i] : 0,
 				     ctx ? ctx[i] : false,
 				     VIRTIO_MSI_NO_VECTOR);
 		if (IS_ERR(vqs[i])) {
@@ -398,21 +396,21 @@ out_del_vqs:
 /* the config->find_vqs() implementation */
 int vp_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], u32 sizes[], const bool *ctx,
+		const char * const names[], const bool *ctx,
 		struct irq_affinity *desc)
 {
 	int err;
 
 	/* Try MSI-X with one vector per queue. */
-	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, sizes, true, ctx, desc);
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, true, ctx, desc);
 	if (!err)
 		return 0;
 	/* Fallback: MSI-X with one vector for config, one shared for queues. */
-	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, sizes, false, ctx, desc);
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false, ctx, desc);
 	if (!err)
 		return 0;
 	/* Finally fall back to regular interrupts. */
-	return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names, sizes, ctx);
+	return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names, ctx);
 }
 
 const char *vp_bus_name(struct virtio_device *vdev)
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index c0448378b698..23112d84218f 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -80,7 +80,6 @@ struct virtio_pci_device {
 				      unsigned int idx,
 				      void (*callback)(struct virtqueue *vq),
 				      const char *name,
-				      u32 size,
 				      bool ctx,
 				      u16 msix_vec);
 	void (*del_vq)(struct virtio_pci_vq_info *info);
@@ -111,7 +110,7 @@ void vp_del_vqs(struct virtio_device *vdev);
 /* the config->find_vqs() implementation */
 int vp_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], u32 sizes[], const bool *ctx,
+		const char * const names[], const bool *ctx,
 		struct irq_affinity *desc);
 const char *vp_bus_name(struct virtio_device *vdev);
 
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index d75e5c4e637f..2257f1b3d8ae 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -112,7 +112,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 				  unsigned int index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
-				  u32 size,
 				  bool ctx,
 				  u16 msix_vec)
 {
@@ -126,13 +125,10 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	if (!num || vp_legacy_get_queue_enable(&vp_dev->ldev, index))
 		return ERR_PTR(-ENOENT);
 
-	if (!size || size > num)
-		size = num;
-
 	info->msix_vector = msix_vec;
 
 	/* create the vring */
-	vq = vring_create_virtqueue(index, size,
+	vq = vring_create_virtqueue(index, num,
 				    VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
 				    true, false, ctx,
 				    vp_notify, callback, name);
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index f7965c5dd36b..c3b9f2761849 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -293,7 +293,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 				  unsigned int index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
-				  u32 size,
 				  bool ctx,
 				  u16 msix_vec)
 {
@@ -311,18 +310,15 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	if (!num || vp_modern_get_queue_enable(mdev, index))
 		return ERR_PTR(-ENOENT);
 
-	if (!size || size > num)
-		size = num;
-
-	if (size & (size - 1)) {
-		dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", size);
+	if (num & (num - 1)) {
+		dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", num);
 		return ERR_PTR(-EINVAL);
 	}
 
 	info->msix_vector = msix_vec;
 
 	/* create the vring */
-	vq = vring_create_virtqueue(index, size,
+	vq = vring_create_virtqueue(index, num,
 				    SMP_CACHE_BYTES, &vp_dev->vdev,
 				    true, true, ctx,
 				    vp_notify, callback, name);
@@ -351,15 +347,12 @@ err:
 static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 			      struct virtqueue *vqs[],
 			      vq_callback_t *callbacks[],
-			      const char * const names[],
-			      u32 sizes[],
-			      const bool *ctx,
+			      const char * const names[], const bool *ctx,
 			      struct irq_affinity *desc)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	struct virtqueue *vq;
-	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, sizes, ctx,
-			     desc);
+	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, ctx, desc);
 
 	if (rc)
 		return rc;
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index d66c8e6d0ef3..4620e9d79dde 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -2426,6 +2426,14 @@ static inline bool more_used(const struct vring_virtqueue *vq)
 	return vq->packed_ring ? more_used_packed(vq) : more_used_split(vq);
 }
 
+/**
+ * vring_interrupt - notify a virtqueue on an interrupt
+ * @irq: the IRQ number (ignored)
+ * @_vq: the struct virtqueue to notify
+ *
+ * Calls the callback function of @_vq to process the virtqueue
+ * notification.
+ */
 irqreturn_t vring_interrupt(int irq, void *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c
index 9bc4d110b800..9670cc79371d 100644
--- a/drivers/virtio/virtio_vdpa.c
+++ b/drivers/virtio/virtio_vdpa.c
@@ -131,7 +131,7 @@ static irqreturn_t virtio_vdpa_virtqueue_cb(void *private)
 static struct virtqueue *
 virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index,
 		     void (*callback)(struct virtqueue *vq),
-		     const char *name, u32 size, bool ctx)
+		     const char *name, bool ctx)
 {
 	struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev);
 	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
@@ -168,17 +168,14 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index,
 		goto error_new_virtqueue;
 	}
 
-	if (!size || size > max_num)
-		size = max_num;
-
 	if (ops->get_vq_num_min)
 		min_num = ops->get_vq_num_min(vdpa);
 
-	may_reduce_num = (size == min_num) ? false : true;
+	may_reduce_num = (max_num == min_num) ? false : true;
 
 	/* Create the vring */
 	align = ops->get_vq_align(vdpa);
-	vq = vring_create_virtqueue(index, size, align, vdev,
+	vq = vring_create_virtqueue(index, max_num, align, vdev,
 				    true, may_reduce_num, ctx,
 				    virtio_vdpa_notify, callback, name);
 	if (!vq) {
@@ -272,7 +269,6 @@ static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 				struct virtqueue *vqs[],
 				vq_callback_t *callbacks[],
 				const char * const names[],
-				u32 sizes[],
 				const bool *ctx,
 				struct irq_affinity *desc)
 {
@@ -288,9 +284,9 @@ static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 			continue;
 		}
 
-		vqs[i] = virtio_vdpa_setup_vq(vdev, queue_idx++, callbacks[i],
-						  names[i], sizes ? sizes[i] : 0,
-						  ctx ? ctx[i] : false);
+		vqs[i] = virtio_vdpa_setup_vq(vdev, queue_idx++,
+					      callbacks[i], names[i], ctx ?
+					      ctx[i] : false);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
 			goto err_setup_vq;