diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index c05b39438663..d0102cfc8efb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -81,6 +81,23 @@
 #include "amdgpu_bo_list.h"
 #include "amdgpu_gem.h"
 
+#define MAX_GPU_INSTANCE		16
+
+struct amdgpu_gpu_instance
+{
+	struct amdgpu_device		*adev;
+	int				mgpu_fan_enabled;
+};
+
+struct amdgpu_mgpu_info
+{
+	struct amdgpu_gpu_instance	gpu_ins[MAX_GPU_INSTANCE];
+	struct mutex			mutex;
+	uint32_t			num_gpu;
+	uint32_t			num_dgpu;
+	uint32_t			num_apu;
+};
+
 /*
  * Modules parameters.
  */
@@ -134,6 +151,7 @@ extern int amdgpu_compute_multipipe;
 extern int amdgpu_gpu_recovery;
 extern int amdgpu_emu_mode;
 extern uint amdgpu_smu_memory_pool_size;
+extern struct amdgpu_mgpu_info mgpu_info;
 
 #ifdef CONFIG_DRM_AMDGPU_SI
 extern int amdgpu_si_support;
@@ -598,31 +616,6 @@ void amdgpu_benchmark(struct amdgpu_device *adev, int test_number);
  */
 void amdgpu_test_moves(struct amdgpu_device *adev);
 
-
-/*
- * amdgpu smumgr functions
- */
-struct amdgpu_smumgr_funcs {
-	int (*check_fw_load_finish)(struct amdgpu_device *adev, uint32_t fwtype);
-	int (*request_smu_load_fw)(struct amdgpu_device *adev);
-	int (*request_smu_specific_fw)(struct amdgpu_device *adev, uint32_t fwtype);
-};
-
-/*
- * amdgpu smumgr
- */
-struct amdgpu_smumgr {
-	struct amdgpu_bo *toc_buf;
-	struct amdgpu_bo *smu_buf;
-	/* asic priv smu data */
-	void *priv;
-	spinlock_t smu_lock;
-	/* smumgr functions */
-	const struct amdgpu_smumgr_funcs *smumgr_funcs;
-	/* ucode loading complete flag */
-	uint32_t fw_flags;
-};
-
 /*
  * ASIC specific register table accessible by UMD
  */
@@ -958,9 +951,6 @@ struct amdgpu_device {
 	u32				cg_flags;
 	u32				pg_flags;
 
-	/* amdgpu smumgr */
-	struct amdgpu_smumgr smu;
-
 	/* gfx */
 	struct amdgpu_gfx		gfx;
 
@@ -1025,6 +1015,9 @@ struct amdgpu_device {
 	bool has_hw_reset;
 	u8				reset_magic[AMDGPU_RESET_MAGIC_NUM];
 
+	/* s3/s4 mask */
+	bool                            in_suspend;
+
 	/* record last mm index being written through WREG32*/
 	unsigned long last_mm_index;
 	bool                            in_gpu_reset;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 6488e90ec948..7f0afc526419 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -359,7 +359,9 @@ out:
  *
  * Checks the acpi event and if it matches an atif event,
  * handles it.
- * Returns NOTIFY code
+ *
+ * Returns:
+ * NOTIFY_BAD or NOTIFY_DONE, depending on the event.
  */
 static int amdgpu_atif_handler(struct amdgpu_device *adev,
 			       struct acpi_bus_event *event)
@@ -373,11 +375,16 @@ static int amdgpu_atif_handler(struct amdgpu_device *adev,
 	if (strcmp(event->device_class, ACPI_VIDEO_CLASS) != 0)
 		return NOTIFY_DONE;
 
+	/* Is this actually our event? */
 	if (!atif ||
 	    !atif->notification_cfg.enabled ||
-	    event->type != atif->notification_cfg.command_code)
-		/* Not our event */
-		return NOTIFY_DONE;
+	    event->type != atif->notification_cfg.command_code) {
+		/* These events will generate keypresses otherwise */
+		if (event->type == ACPI_VIDEO_NOTIFY_PROBE)
+			return NOTIFY_BAD;
+		else
+			return NOTIFY_DONE;
+	}
 
 	if (atif->functions.sbios_requests) {
 		struct atif_sbios_requests req;
@@ -386,7 +393,7 @@ static int amdgpu_atif_handler(struct amdgpu_device *adev,
 		count = amdgpu_atif_get_sbios_requests(atif, &req);
 
 		if (count <= 0)
-			return NOTIFY_DONE;
+			return NOTIFY_BAD;
 
 		DRM_DEBUG_DRIVER("ATIF: %d pending SBIOS requests\n", count);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index bd79d0a31942..1e4dd09a5072 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1525,6 +1525,92 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+static int amdgpu_device_ip_hw_init_phase1(struct amdgpu_device *adev)
+{
+	int i, r;
+
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_blocks[i].status.sw)
+			continue;
+		if (adev->ip_blocks[i].status.hw)
+			continue;
+		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON ||
+		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH) {
+			r = adev->ip_blocks[i].version->funcs->hw_init(adev);
+			if (r) {
+				DRM_ERROR("hw_init of IP block <%s> failed %d\n",
+					  adev->ip_blocks[i].version->funcs->name, r);
+				return r;
+			}
+			adev->ip_blocks[i].status.hw = true;
+		}
+	}
+
+	return 0;
+}
+
+static int amdgpu_device_ip_hw_init_phase2(struct amdgpu_device *adev)
+{
+	int i, r;
+
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_blocks[i].status.sw)
+			continue;
+		if (adev->ip_blocks[i].status.hw)
+			continue;
+		r = adev->ip_blocks[i].version->funcs->hw_init(adev);
+		if (r) {
+			DRM_ERROR("hw_init of IP block <%s> failed %d\n",
+				  adev->ip_blocks[i].version->funcs->name, r);
+			return r;
+		}
+		adev->ip_blocks[i].status.hw = true;
+	}
+
+	return 0;
+}
+
+static int amdgpu_device_fw_loading(struct amdgpu_device *adev)
+{
+	int r = 0;
+	int i;
+
+	if (adev->asic_type >= CHIP_VEGA10) {
+		for (i = 0; i < adev->num_ip_blocks; i++) {
+			if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP) {
+				if (adev->in_gpu_reset || adev->in_suspend) {
+					if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset)
+						break; /* sriov gpu reset, psp need to do hw_init before IH because of hw limit */
+					r = adev->ip_blocks[i].version->funcs->resume(adev);
+					if (r) {
+						DRM_ERROR("resume of IP block <%s> failed %d\n",
+							  adev->ip_blocks[i].version->funcs->name, r);
+						return r;
+					}
+				} else {
+					r = adev->ip_blocks[i].version->funcs->hw_init(adev);
+					if (r) {
+						DRM_ERROR("hw_init of IP block <%s> failed %d\n",
+						  adev->ip_blocks[i].version->funcs->name, r);
+						return r;
+					}
+				}
+				adev->ip_blocks[i].status.hw = true;
+			}
+		}
+	}
+
+	if (adev->powerplay.pp_funcs->load_firmware) {
+		r = adev->powerplay.pp_funcs->load_firmware(adev->powerplay.pp_handle);
+		if (r) {
+			pr_err("firmware loading failed\n");
+			return r;
+		}
+	}
+
+	return 0;
+}
+
 /**
  * amdgpu_device_ip_init - run init for hardware IPs
  *
@@ -1581,19 +1667,21 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 		}
 	}
 
-	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_blocks[i].status.sw)
-			continue;
-		if (adev->ip_blocks[i].status.hw)
-			continue;
-		r = adev->ip_blocks[i].version->funcs->hw_init((void *)adev);
-		if (r) {
-			DRM_ERROR("hw_init of IP block <%s> failed %d\n",
-				  adev->ip_blocks[i].version->funcs->name, r);
-			return r;
-		}
-		adev->ip_blocks[i].status.hw = true;
-	}
+	r = amdgpu_ucode_create_bo(adev); /* create ucode bo when sw_init complete*/
+	if (r)
+		return r;
+
+	r = amdgpu_device_ip_hw_init_phase1(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_device_fw_loading(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_device_ip_hw_init_phase2(adev);
+	if (r)
+		return r;
 
 	amdgpu_xgmi_add_device(adev);
 	amdgpu_amdkfd_device_init(adev);
@@ -1656,7 +1744,7 @@ static int amdgpu_device_set_cg_state(struct amdgpu_device *adev,
 
 	for (j = 0; j < adev->num_ip_blocks; j++) {
 		i = state == AMD_CG_STATE_GATE ? j : adev->num_ip_blocks - j - 1;
-		if (!adev->ip_blocks[i].status.valid)
+		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
 		/* skip CG for VCE/UVD, it's handled specially */
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
@@ -1686,7 +1774,7 @@ static int amdgpu_device_set_pg_state(struct amdgpu_device *adev, enum amd_power
 
 	for (j = 0; j < adev->num_ip_blocks; j++) {
 		i = state == AMD_PG_STATE_GATE ? j : adev->num_ip_blocks - j - 1;
-		if (!adev->ip_blocks[i].status.valid)
+		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
 		/* skip CG for VCE/UVD, it's handled specially */
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
@@ -1723,7 +1811,7 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 	int i = 0, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_blocks[i].status.valid)
+		if (!adev->ip_blocks[i].status.hw)
 			continue;
 		if (adev->ip_blocks[i].version->funcs->late_init) {
 			r = adev->ip_blocks[i].version->funcs->late_init((void *)adev);
@@ -1732,8 +1820,8 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 					  adev->ip_blocks[i].version->funcs->name, r);
 				return r;
 			}
-			adev->ip_blocks[i].status.late_initialized = true;
 		}
+		adev->ip_blocks[i].status.late_initialized = true;
 	}
 
 	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_GATE);
@@ -1803,6 +1891,7 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 			continue;
 
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
+			amdgpu_ucode_free_bo(adev);
 			amdgpu_free_static_csa(adev);
 			amdgpu_device_wb_fini(adev);
 			amdgpu_device_vram_scratch_fini(adev);
@@ -1833,6 +1922,43 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 	return 0;
 }
 
+static int amdgpu_device_enable_mgpu_fan_boost(void)
+{
+	struct amdgpu_gpu_instance *gpu_ins;
+	struct amdgpu_device *adev;
+	int i, ret = 0;
+
+	mutex_lock(&mgpu_info.mutex);
+
+	/*
+	 * MGPU fan boost feature should be enabled
+	 * only when there are two or more dGPUs in
+	 * the system
+	 */
+	if (mgpu_info.num_dgpu < 2)
+		goto out;
+
+	for (i = 0; i < mgpu_info.num_dgpu; i++) {
+		gpu_ins = &(mgpu_info.gpu_ins[i]);
+		adev = gpu_ins->adev;
+		if (!(adev->flags & AMD_IS_APU) &&
+		    !gpu_ins->mgpu_fan_enabled &&
+		    adev->powerplay.pp_funcs &&
+		    adev->powerplay.pp_funcs->enable_mgpu_fan_boost) {
+			ret = amdgpu_dpm_enable_mgpu_fan_boost(adev);
+			if (ret)
+				break;
+
+			gpu_ins->mgpu_fan_enabled = 1;
+		}
+	}
+
+out:
+	mutex_unlock(&mgpu_info.mutex);
+
+	return ret;
+}
+
 /**
  * amdgpu_device_ip_late_init_func_handler - work handler for ib test
  *
@@ -1847,6 +1973,10 @@ static void amdgpu_device_ip_late_init_func_handler(struct work_struct *work)
 	r = amdgpu_ib_ring_tests(adev);
 	if (r)
 		DRM_ERROR("ib ring test failed (%d).\n", r);
+
+	r = amdgpu_device_enable_mgpu_fan_boost();
+	if (r)
+		DRM_ERROR("enable mgpu fan boost failed (%d).\n", r);
 }
 
 static void amdgpu_device_delay_enable_gfx_off(struct work_struct *work)
@@ -2082,7 +2212,8 @@ static int amdgpu_device_ip_resume_phase2(struct amdgpu_device *adev)
 			continue;
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON ||
 		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC ||
-		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH)
+		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH ||
+		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP)
 			continue;
 		r = adev->ip_blocks[i].version->funcs->resume(adev);
 		if (r) {
@@ -2114,6 +2245,11 @@ static int amdgpu_device_ip_resume(struct amdgpu_device *adev)
 	r = amdgpu_device_ip_resume_phase1(adev);
 	if (r)
 		return r;
+
+	r = amdgpu_device_fw_loading(adev);
+	if (r)
+		return r;
+
 	r = amdgpu_device_ip_resume_phase2(adev);
 
 	return r;
@@ -2608,6 +2744,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
+	adev->in_suspend = true;
 	drm_kms_helper_poll_disable(dev);
 
 	if (fbcon)
@@ -2793,6 +2930,8 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 #ifdef CONFIG_PM
 	dev->dev->power.disable_depth--;
 #endif
+	adev->in_suspend = false;
+
 	return 0;
 }
 
@@ -3061,6 +3200,10 @@ retry:
 			if (r)
 				goto out;
 
+			r = amdgpu_device_fw_loading(adev);
+			if (r)
+				return r;
+
 			r = amdgpu_device_ip_resume_phase2(adev);
 			if (r)
 				goto out;
@@ -3117,6 +3260,10 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	/* we need recover gart prior to run SMC/CP/SDMA resume */
 	amdgpu_gtt_mgr_recover(&adev->mman.bdev.man[TTM_PL_TT]);
 
+	r = amdgpu_device_fw_loading(adev);
+	if (r)
+		return r;
+
 	/* now we are okay to resume SMC/CP/SDMA */
 	r = amdgpu_device_ip_reinit_late_sriov(adev);
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
index ff24e1cc5b65..f972cd156795 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
@@ -278,6 +278,9 @@ enum amdgpu_pcie_gen {
 #define amdgpu_dpm_get_fan_speed_rpm(adev, s) \
 		((adev)->powerplay.pp_funcs->get_fan_speed_rpm)((adev)->powerplay.pp_handle, (s))
 
+#define amdgpu_dpm_set_fan_speed_rpm(adev, s) \
+		((adev)->powerplay.pp_funcs->set_fan_speed_rpm)((adev)->powerplay.pp_handle, (s))
+
 #define amdgpu_dpm_get_sclk(adev, l) \
 		((adev)->powerplay.pp_funcs->get_sclk((adev)->powerplay.pp_handle, (l)))
 
@@ -357,6 +360,10 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->odn_edit_dpm_table(\
 			(adev)->powerplay.pp_handle, type, parameter, size))
 
+#define amdgpu_dpm_enable_mgpu_fan_boost(adev) \
+		((adev)->powerplay.pp_funcs->enable_mgpu_fan_boost(\
+			(adev)->powerplay.pp_handle))
+
 struct amdgpu_dpm {
 	struct amdgpu_ps        *ps;
 	/* number of valid power states */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 723f0f7754bd..28781414d71c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -127,6 +127,9 @@ int amdgpu_compute_multipipe = -1;
 int amdgpu_gpu_recovery = -1; /* auto */
 int amdgpu_emu_mode = 0;
 uint amdgpu_smu_memory_pool_size = 0;
+struct amdgpu_mgpu_info mgpu_info = {
+	.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
+};
 
 /**
  * DOC: vramlimit (int)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index f172e92c463c..b61b5c11aead 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -297,8 +297,7 @@ struct amdgpu_gfx {
 	/* reset mask */
 	uint32_t                        grbm_soft_reset;
 	uint32_t                        srbm_soft_reset;
-	/* s3/s4 mask */
-	bool                            in_suspend;
+
 	/* NGG */
 	struct amdgpu_ngg		ngg;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 9a5b252784a1..d73367cab4f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -146,6 +146,8 @@ void amdgpu_gmc_gart_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc)
 {
 	const uint64_t four_gb = 0x100000000ULL;
 	u64 size_af, size_bf;
+	/*To avoid the hole, limit the max mc address to AMDGPU_GMC_HOLE_START*/
+	u64 max_mc_address = min(adev->gmc.mc_mask, AMDGPU_GMC_HOLE_START - 1);
 
 	mc->gart_size += adev->pm.smu_prv_buffer_size;
 
@@ -153,7 +155,7 @@ void amdgpu_gmc_gart_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc)
 	 * the GART base on a 4GB boundary as well.
 	 */
 	size_bf = mc->fb_start;
-	size_af = adev->gmc.mc_mask + 1 - ALIGN(mc->fb_end + 1, four_gb);
+	size_af = max_mc_address + 1 - ALIGN(mc->fb_end + 1, four_gb);
 
 	if (mc->gart_size > max(size_bf, size_af)) {
 		dev_warn(adev->dev, "limiting GART\n");
@@ -164,7 +166,7 @@ void amdgpu_gmc_gart_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc)
 	    (size_af < mc->gart_size))
 		mc->gart_start = 0;
 	else
-		mc->gart_start = mc->mc_mask - mc->gart_size + 1;
+		mc->gart_start = max_mc_address - mc->gart_size + 1;
 
 	mc->gart_start &= ~(four_gb - 1);
 	mc->gart_end = mc->gart_start + mc->gart_size - 1;
@@ -200,16 +202,13 @@ void amdgpu_gmc_agp_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc)
 	}
 
 	if (size_bf > size_af) {
-		mc->agp_start = mc->fb_start > mc->gart_start ?
-			mc->gart_end + 1 : 0;
+		mc->agp_start = (mc->fb_start - size_bf) & sixteen_gb_mask;
 		mc->agp_size = size_bf;
 	} else {
-		mc->agp_start = (mc->fb_start > mc->gart_start ?
-			mc->fb_end : mc->gart_end) + 1,
+		mc->agp_start = ALIGN(mc->fb_end + 1, sixteen_gb);
 		mc->agp_size = size_af;
 	}
 
-	mc->agp_start = ALIGN(mc->agp_start, sixteen_gb);
 	mc->agp_end = mc->agp_start + mc->agp_size - 1;
 	dev_info(adev->dev, "AGP: %lluM 0x%016llX - 0x%016llX\n",
 			mc->agp_size >> 20, mc->agp_start, mc->agp_end);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 47817e00f54f..b8963b725dfa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -354,6 +354,14 @@ int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
 		if (!ring || !ring->ready)
 			continue;
 
+		/* skip IB tests for KIQ in general for the below reasons:
+		 * 1. We never submit IBs to the KIQ
+		 * 2. KIQ doesn't use the EOP interrupts,
+		 *    we use some other CP interrupt.
+		 */
+		if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
+			continue;
+
 		/* MM engine need more time */
 		if (ring->funcs->type == AMDGPU_RING_TYPE_UVD ||
 			ring->funcs->type == AMDGPU_RING_TYPE_VCE ||
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index a64056dadc58..81732a84c2ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -40,6 +40,30 @@
 #include "amdgpu_gem.h"
 #include "amdgpu_display.h"
 
+static void amdgpu_unregister_gpu_instance(struct amdgpu_device *adev)
+{
+	struct amdgpu_gpu_instance *gpu_instance;
+	int i;
+
+	mutex_lock(&mgpu_info.mutex);
+
+	for (i = 0; i < mgpu_info.num_gpu; i++) {
+		gpu_instance = &(mgpu_info.gpu_ins[i]);
+		if (gpu_instance->adev == adev) {
+			mgpu_info.gpu_ins[i] =
+				mgpu_info.gpu_ins[mgpu_info.num_gpu - 1];
+			mgpu_info.num_gpu--;
+			if (adev->flags & AMD_IS_APU)
+				mgpu_info.num_apu--;
+			else
+				mgpu_info.num_dgpu--;
+			break;
+		}
+	}
+
+	mutex_unlock(&mgpu_info.mutex);
+}
+
 /**
  * amdgpu_driver_unload_kms - Main unload function for KMS.
  *
@@ -55,6 +79,8 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)
 	if (adev == NULL)
 		return;
 
+	amdgpu_unregister_gpu_instance(adev);
+
 	if (adev->rmmio == NULL)
 		goto done_free;
 
@@ -75,6 +101,31 @@ done_free:
 	dev->dev_private = NULL;
 }
 
+static void amdgpu_register_gpu_instance(struct amdgpu_device *adev)
+{
+	struct amdgpu_gpu_instance *gpu_instance;
+
+	mutex_lock(&mgpu_info.mutex);
+
+	if (mgpu_info.num_gpu >= MAX_GPU_INSTANCE) {
+		DRM_ERROR("Cannot register more gpu instance\n");
+		mutex_unlock(&mgpu_info.mutex);
+		return;
+	}
+
+	gpu_instance = &(mgpu_info.gpu_ins[mgpu_info.num_gpu]);
+	gpu_instance->adev = adev;
+	gpu_instance->mgpu_fan_enabled = 0;
+
+	mgpu_info.num_gpu++;
+	if (adev->flags & AMD_IS_APU)
+		mgpu_info.num_apu++;
+	else
+		mgpu_info.num_dgpu++;
+
+	mutex_unlock(&mgpu_info.mutex);
+}
+
 /**
  * amdgpu_driver_load_kms - Main load function for KMS.
  *
@@ -169,6 +220,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 		pm_runtime_put_autosuspend(dev->dev);
 	}
 
+	amdgpu_register_gpu_instance(adev);
 out:
 	if (r) {
 		/* balance pm_runtime_get_sync in amdgpu_driver_unload_kms */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 18d989e0e362..94055a485e01 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -1120,12 +1120,19 @@ static ssize_t amdgpu_hwmon_set_pwm1(struct device *dev,
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	int err;
 	u32 value;
+	u32 pwm_mode;
 
 	/* Can't adjust fan when the card is off */
 	if  ((adev->flags & AMD_IS_PX) &&
 	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
 		return -EINVAL;
 
+	pwm_mode = amdgpu_dpm_get_fan_control_mode(adev);
+	if (pwm_mode != AMD_FAN_CTRL_MANUAL) {
+		pr_info("manual fan speed control should be enabled first\n");
+		return -EINVAL;
+	}
+
 	err = kstrtou32(buf, 10, &value);
 	if (err)
 		return err;
@@ -1187,6 +1194,148 @@ static ssize_t amdgpu_hwmon_get_fan1_input(struct device *dev,
 	return sprintf(buf, "%i\n", speed);
 }
 
+static ssize_t amdgpu_hwmon_get_fan1_min(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct amdgpu_device *adev = dev_get_drvdata(dev);
+	u32 min_rpm = 0;
+	u32 size = sizeof(min_rpm);
+	int r;
+
+	if (!adev->powerplay.pp_funcs->read_sensor)
+		return -EINVAL;
+
+	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_MIN_FAN_RPM,
+				   (void *)&min_rpm, &size);
+	if (r)
+		return r;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", min_rpm);
+}
+
+static ssize_t amdgpu_hwmon_get_fan1_max(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct amdgpu_device *adev = dev_get_drvdata(dev);
+	u32 max_rpm = 0;
+	u32 size = sizeof(max_rpm);
+	int r;
+
+	if (!adev->powerplay.pp_funcs->read_sensor)
+		return -EINVAL;
+
+	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_MAX_FAN_RPM,
+				   (void *)&max_rpm, &size);
+	if (r)
+		return r;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", max_rpm);
+}
+
+static ssize_t amdgpu_hwmon_get_fan1_target(struct device *dev,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	struct amdgpu_device *adev = dev_get_drvdata(dev);
+	int err;
+	u32 rpm = 0;
+
+	/* Can't adjust fan when the card is off */
+	if  ((adev->flags & AMD_IS_PX) &&
+	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return -EINVAL;
+
+	if (adev->powerplay.pp_funcs->get_fan_speed_rpm) {
+		err = amdgpu_dpm_get_fan_speed_rpm(adev, &rpm);
+		if (err)
+			return err;
+	}
+
+	return sprintf(buf, "%i\n", rpm);
+}
+
+static ssize_t amdgpu_hwmon_set_fan1_target(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	struct amdgpu_device *adev = dev_get_drvdata(dev);
+	int err;
+	u32 value;
+	u32 pwm_mode;
+
+	pwm_mode = amdgpu_dpm_get_fan_control_mode(adev);
+	if (pwm_mode != AMD_FAN_CTRL_MANUAL)
+		return -ENODATA;
+
+	/* Can't adjust fan when the card is off */
+	if  ((adev->flags & AMD_IS_PX) &&
+	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return -EINVAL;
+
+	err = kstrtou32(buf, 10, &value);
+	if (err)
+		return err;
+
+	if (adev->powerplay.pp_funcs->set_fan_speed_rpm) {
+		err = amdgpu_dpm_set_fan_speed_rpm(adev, value);
+		if (err)
+			return err;
+	}
+
+	return count;
+}
+
+static ssize_t amdgpu_hwmon_get_fan1_enable(struct device *dev,
+					    struct device_attribute *attr,
+					    char *buf)
+{
+	struct amdgpu_device *adev = dev_get_drvdata(dev);
+	u32 pwm_mode = 0;
+
+	if (!adev->powerplay.pp_funcs->get_fan_control_mode)
+		return -EINVAL;
+
+	pwm_mode = amdgpu_dpm_get_fan_control_mode(adev);
+
+	return sprintf(buf, "%i\n", pwm_mode == AMD_FAN_CTRL_AUTO ? 0 : 1);
+}
+
+static ssize_t amdgpu_hwmon_set_fan1_enable(struct device *dev,
+					    struct device_attribute *attr,
+					    const char *buf,
+					    size_t count)
+{
+	struct amdgpu_device *adev = dev_get_drvdata(dev);
+	int err;
+	int value;
+	u32 pwm_mode;
+
+	/* Can't adjust fan when the card is off */
+	if  ((adev->flags & AMD_IS_PX) &&
+	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return -EINVAL;
+
+	if (!adev->powerplay.pp_funcs->set_fan_control_mode)
+		return -EINVAL;
+
+	err = kstrtoint(buf, 10, &value);
+	if (err)
+		return err;
+
+	if (value == 0)
+		pwm_mode = AMD_FAN_CTRL_AUTO;
+	else if (value == 1)
+		pwm_mode = AMD_FAN_CTRL_MANUAL;
+	else
+		return -EINVAL;
+
+	amdgpu_dpm_set_fan_control_mode(adev, pwm_mode);
+
+	return count;
+}
+
 static ssize_t amdgpu_hwmon_show_vddgfx(struct device *dev,
 					struct device_attribute *attr,
 					char *buf)
@@ -1406,8 +1555,16 @@ static ssize_t amdgpu_hwmon_set_power_cap(struct device *dev,
  *
  * - pwm1_max: pulse width modulation fan control maximum level (255)
  *
+ * - fan1_min: an minimum value Unit: revolution/min (RPM)
+ *
+ * - fan1_max: an maxmum value Unit: revolution/max (RPM)
+ *
  * - fan1_input: fan speed in RPM
  *
+ * - fan[1-*]_target: Desired fan speed Unit: revolution/min (RPM)
+ *
+ * - fan[1-*]_enable: Enable or disable the sensors.1: Enable 0: Disable
+ *
  * You can use hwmon tools like sensors to view this information on your system.
  *
  */
@@ -1420,6 +1577,10 @@ static SENSOR_DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR, amdgpu_hwmon_get_pwm1_
 static SENSOR_DEVICE_ATTR(pwm1_min, S_IRUGO, amdgpu_hwmon_get_pwm1_min, NULL, 0);
 static SENSOR_DEVICE_ATTR(pwm1_max, S_IRUGO, amdgpu_hwmon_get_pwm1_max, NULL, 0);
 static SENSOR_DEVICE_ATTR(fan1_input, S_IRUGO, amdgpu_hwmon_get_fan1_input, NULL, 0);
+static SENSOR_DEVICE_ATTR(fan1_min, S_IRUGO, amdgpu_hwmon_get_fan1_min, NULL, 0);
+static SENSOR_DEVICE_ATTR(fan1_max, S_IRUGO, amdgpu_hwmon_get_fan1_max, NULL, 0);
+static SENSOR_DEVICE_ATTR(fan1_target, S_IRUGO | S_IWUSR, amdgpu_hwmon_get_fan1_target, amdgpu_hwmon_set_fan1_target, 0);
+static SENSOR_DEVICE_ATTR(fan1_enable, S_IRUGO | S_IWUSR, amdgpu_hwmon_get_fan1_enable, amdgpu_hwmon_set_fan1_enable, 0);
 static SENSOR_DEVICE_ATTR(in0_input, S_IRUGO, amdgpu_hwmon_show_vddgfx, NULL, 0);
 static SENSOR_DEVICE_ATTR(in0_label, S_IRUGO, amdgpu_hwmon_show_vddgfx_label, NULL, 0);
 static SENSOR_DEVICE_ATTR(in1_input, S_IRUGO, amdgpu_hwmon_show_vddnb, NULL, 0);
@@ -1438,6 +1599,10 @@ static struct attribute *hwmon_attributes[] = {
 	&sensor_dev_attr_pwm1_min.dev_attr.attr,
 	&sensor_dev_attr_pwm1_max.dev_attr.attr,
 	&sensor_dev_attr_fan1_input.dev_attr.attr,
+	&sensor_dev_attr_fan1_min.dev_attr.attr,
+	&sensor_dev_attr_fan1_max.dev_attr.attr,
+	&sensor_dev_attr_fan1_target.dev_attr.attr,
+	&sensor_dev_attr_fan1_enable.dev_attr.attr,
 	&sensor_dev_attr_in0_input.dev_attr.attr,
 	&sensor_dev_attr_in0_label.dev_attr.attr,
 	&sensor_dev_attr_in1_input.dev_attr.attr,
@@ -1456,13 +1621,16 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	umode_t effective_mode = attr->mode;
 
-
 	/* Skip fan attributes if fan is not present */
 	if (adev->pm.no_fan && (attr == &sensor_dev_attr_pwm1.dev_attr.attr ||
 	    attr == &sensor_dev_attr_pwm1_enable.dev_attr.attr ||
 	    attr == &sensor_dev_attr_pwm1_max.dev_attr.attr ||
 	    attr == &sensor_dev_attr_pwm1_min.dev_attr.attr ||
-	    attr == &sensor_dev_attr_fan1_input.dev_attr.attr))
+	    attr == &sensor_dev_attr_fan1_input.dev_attr.attr ||
+	    attr == &sensor_dev_attr_fan1_min.dev_attr.attr ||
+	    attr == &sensor_dev_attr_fan1_max.dev_attr.attr ||
+	    attr == &sensor_dev_attr_fan1_target.dev_attr.attr ||
+	    attr == &sensor_dev_attr_fan1_enable.dev_attr.attr))
 		return 0;
 
 	/* Skip limit attributes if DPM is not enabled */
@@ -1472,7 +1640,12 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 	     attr == &sensor_dev_attr_pwm1.dev_attr.attr ||
 	     attr == &sensor_dev_attr_pwm1_enable.dev_attr.attr ||
 	     attr == &sensor_dev_attr_pwm1_max.dev_attr.attr ||
-	     attr == &sensor_dev_attr_pwm1_min.dev_attr.attr))
+	     attr == &sensor_dev_attr_pwm1_min.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_input.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_min.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_max.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_target.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_enable.dev_attr.attr))
 		return 0;
 
 	/* mask fan attributes if we have no bindings for this asic to expose */
@@ -1497,10 +1670,18 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 	/* hide max/min values if we can't both query and manage the fan */
 	if ((!adev->powerplay.pp_funcs->set_fan_speed_percent &&
 	     !adev->powerplay.pp_funcs->get_fan_speed_percent) &&
+	     (!adev->powerplay.pp_funcs->set_fan_speed_rpm &&
+	     !adev->powerplay.pp_funcs->get_fan_speed_rpm) &&
 	    (attr == &sensor_dev_attr_pwm1_max.dev_attr.attr ||
 	     attr == &sensor_dev_attr_pwm1_min.dev_attr.attr))
 		return 0;
 
+	if ((!adev->powerplay.pp_funcs->set_fan_speed_rpm &&
+	     !adev->powerplay.pp_funcs->get_fan_speed_rpm) &&
+	    (attr == &sensor_dev_attr_fan1_max.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_min.dev_attr.attr))
+		return 0;
+
 	/* only APUs have vddnb */
 	if (!(adev->flags & AMD_IS_APU) &&
 	    (attr == &sensor_dev_attr_in1_input.dev_attr.attr ||
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index bd397d2916fb..25d2f3e757f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -452,8 +452,6 @@ static int psp_hw_fini(void *handle)
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP)
 		return 0;
 
-	amdgpu_ucode_fini_bo(adev);
-
 	psp_ring_destroy(psp, PSP_RING_TYPE__KM);
 
 	amdgpu_bo_free_kernel(&psp->tmr_bo, &psp->tmr_mc_addr, &psp->tmr_buf);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
index d17503f0df8e..500113ec65ca 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
@@ -46,10 +46,6 @@ struct amdgpu_sdma_instance {
 
 struct amdgpu_sdma {
 	struct amdgpu_sdma_instance instance[AMDGPU_MAX_SDMA_INSTANCES];
-#ifdef CONFIG_DRM_AMDGPU_SI
-	//SI DMA has a difference trap irq number for the second engine
-	struct amdgpu_irq_src	trap_irq_1;
-#endif
 	struct amdgpu_irq_src	trap_irq;
 	struct amdgpu_irq_src	illegal_inst_irq;
 	int			num_instances;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 1fa8bc337859..7b33867036e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -297,10 +297,7 @@ amdgpu_ucode_get_load_type(struct amdgpu_device *adev, int load_type)
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
 	case CHIP_VEGAM:
-		if (!load_type)
-			return AMDGPU_FW_LOAD_DIRECT;
-		else
-			return AMDGPU_FW_LOAD_SMU;
+		return AMDGPU_FW_LOAD_SMU;
 	case CHIP_VEGA10:
 	case CHIP_RAVEN:
 	case CHIP_VEGA12:
@@ -423,32 +420,41 @@ static int amdgpu_ucode_patch_jt(struct amdgpu_firmware_info *ucode,
 	return 0;
 }
 
+int amdgpu_ucode_create_bo(struct amdgpu_device *adev)
+{
+	if (adev->firmware.load_type != AMDGPU_FW_LOAD_DIRECT) {
+		amdgpu_bo_create_kernel(adev, adev->firmware.fw_size, PAGE_SIZE,
+			amdgpu_sriov_vf(adev) ? AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
+			&adev->firmware.fw_buf,
+			&adev->firmware.fw_buf_mc,
+			&adev->firmware.fw_buf_ptr);
+		if (!adev->firmware.fw_buf) {
+			dev_err(adev->dev, "failed to create kernel buffer for firmware.fw_buf\n");
+			return -ENOMEM;
+		} else if (amdgpu_sriov_vf(adev)) {
+			memset(adev->firmware.fw_buf_ptr, 0, adev->firmware.fw_size);
+		}
+	}
+	return 0;
+}
+
+void amdgpu_ucode_free_bo(struct amdgpu_device *adev)
+{
+	if (adev->firmware.load_type != AMDGPU_FW_LOAD_DIRECT)
+		amdgpu_bo_free_kernel(&adev->firmware.fw_buf,
+		&adev->firmware.fw_buf_mc,
+		&adev->firmware.fw_buf_ptr);
+}
+
 int amdgpu_ucode_init_bo(struct amdgpu_device *adev)
 {
 	uint64_t fw_offset = 0;
-	int i, err;
+	int i;
 	struct amdgpu_firmware_info *ucode = NULL;
-	const struct common_firmware_header *header = NULL;
 
-	if (!adev->firmware.fw_size) {
-		dev_warn(adev->dev, "No ip firmware need to load\n");
+ /* for baremetal, the ucode is allocated in gtt, so don't need to fill the bo when reset/suspend */
+	if (!amdgpu_sriov_vf(adev) && (adev->in_gpu_reset || adev->in_suspend))
 		return 0;
-	}
-
-	if (!adev->in_gpu_reset) {
-		err = amdgpu_bo_create_kernel(adev, adev->firmware.fw_size, PAGE_SIZE,
-					amdgpu_sriov_vf(adev) ? AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
-					&adev->firmware.fw_buf,
-					&adev->firmware.fw_buf_mc,
-					&adev->firmware.fw_buf_ptr);
-		if (err) {
-			dev_err(adev->dev, "failed to create kernel buffer for firmware.fw_buf\n");
-			goto failed;
-		}
-	}
-
-	memset(adev->firmware.fw_buf_ptr, 0, adev->firmware.fw_size);
-
 	/*
 	 * if SMU loaded firmware, it needn't add SMC, UVD, and VCE
 	 * ucode info here
@@ -465,7 +471,6 @@ int amdgpu_ucode_init_bo(struct amdgpu_device *adev)
 	for (i = 0; i < adev->firmware.max_ucodes; i++) {
 		ucode = &adev->firmware.ucode[i];
 		if (ucode->fw) {
-			header = (const struct common_firmware_header *)ucode->fw->data;
 			amdgpu_ucode_init_single_fw(adev, ucode, adev->firmware.fw_buf_mc + fw_offset,
 						    adev->firmware.fw_buf_ptr + fw_offset);
 			if (i == AMDGPU_UCODE_ID_CP_MEC1 &&
@@ -480,33 +485,4 @@ int amdgpu_ucode_init_bo(struct amdgpu_device *adev)
 		}
 	}
 	return 0;
-
-failed:
-	if (err)
-		adev->firmware.load_type = AMDGPU_FW_LOAD_DIRECT;
-
-	return err;
-}
-
-int amdgpu_ucode_fini_bo(struct amdgpu_device *adev)
-{
-	int i;
-	struct amdgpu_firmware_info *ucode = NULL;
-
-	if (!adev->firmware.fw_size)
-		return 0;
-
-	for (i = 0; i < adev->firmware.max_ucodes; i++) {
-		ucode = &adev->firmware.ucode[i];
-		if (ucode->fw) {
-			ucode->mc_addr = 0;
-			ucode->kaddr = NULL;
-		}
-	}
-
-	amdgpu_bo_free_kernel(&adev->firmware.fw_buf,
-				&adev->firmware.fw_buf_mc,
-				&adev->firmware.fw_buf_ptr);
-
-	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index 8f3f1117728c..aa6641b944a0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -276,8 +276,10 @@ void amdgpu_ucode_print_gpu_info_hdr(const struct common_firmware_header *hdr);
 int amdgpu_ucode_validate(const struct firmware *fw);
 bool amdgpu_ucode_hdr_version(union amdgpu_firmware_header *hdr,
 				uint16_t hdr_major, uint16_t hdr_minor);
+
 int amdgpu_ucode_init_bo(struct amdgpu_device *adev);
-int amdgpu_ucode_fini_bo(struct amdgpu_device *adev);
+int amdgpu_ucode_create_bo(struct amdgpu_device *adev);
+void amdgpu_ucode_free_bo(struct amdgpu_device *adev);
 
 enum amdgpu_firmware_load_type
 amdgpu_ucode_get_load_type(struct amdgpu_device *adev, int load_type);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 64e527b1c02f..27da13df2f11 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -121,8 +121,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 			version_major, version_minor, family_id);
 	}
 
-	bo_size = AMDGPU_VCN_STACK_SIZE + AMDGPU_VCN_HEAP_SIZE
-		  +  AMDGPU_VCN_SESSION_SIZE * 40;
+	bo_size = AMDGPU_VCN_STACK_SIZE + AMDGPU_VCN_CONTEXT_SIZE;
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP)
 		bo_size += AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8);
 	r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE,
@@ -263,7 +262,7 @@ static int amdgpu_vcn_pause_dpg_mode(struct amdgpu_device *adev,
 
 				ring = &adev->vcn.ring_dec;
 				WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR,
-					     lower_32_bits(ring->wptr) | 0x80000000);
+						   RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2));
 				SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
 						   UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON,
 						   UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
@@ -309,18 +308,21 @@ static int amdgpu_vcn_pause_dpg_mode(struct amdgpu_device *adev,
 				/* Restore */
 				ring = &adev->vcn.ring_jpeg;
 				WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
-				WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, 0x00000001L | 0x00000002L);
+				WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL,
+							UVD_JRBC_RB_CNTL__RB_NO_FETCH_MASK |
+							UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK);
 				WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW,
-					     lower_32_bits(ring->gpu_addr));
+							lower_32_bits(ring->gpu_addr));
 				WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH,
-					     upper_32_bits(ring->gpu_addr));
+							upper_32_bits(ring->gpu_addr));
 				WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR, ring->wptr);
 				WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, ring->wptr);
-				WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, 0x00000002L);
+				WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL,
+							UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK);
 
 				ring = &adev->vcn.ring_dec;
 				WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR,
-					     lower_32_bits(ring->wptr) | 0x80000000);
+						   RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2));
 				SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
 						   UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON,
 						   UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 0b88a4672da5..a0ad19af9080 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -24,9 +24,9 @@
 #ifndef __AMDGPU_VCN_H__
 #define __AMDGPU_VCN_H__
 
-#define AMDGPU_VCN_STACK_SIZE		(200*1024)
-#define AMDGPU_VCN_HEAP_SIZE		(256*1024)
-#define AMDGPU_VCN_SESSION_SIZE		(50*1024)
+#define AMDGPU_VCN_STACK_SIZE		(128*1024)
+#define AMDGPU_VCN_CONTEXT_SIZE	(512*1024)
+
 #define AMDGPU_VCN_FIRMWARE_OFFSET	256
 #define AMDGPU_VCN_MAX_ENC_RINGS	3
 
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 78ab939ae5d8..f41f5f57e9f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -2002,6 +2002,8 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &cik_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v7_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &cik_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v7_2_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
 		if (amdgpu_dpm == -1)
 			amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		else
@@ -2014,8 +2016,6 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 #endif
 		else
 			amdgpu_device_ip_block_add(adev, &dce_v8_2_ip_block);
-		amdgpu_device_ip_block_add(adev, &gfx_v7_2_ip_block);
-		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
 		amdgpu_device_ip_block_add(adev, &uvd_v4_2_ip_block);
 		amdgpu_device_ip_block_add(adev, &vce_v2_0_ip_block);
 		break;
@@ -2023,6 +2023,8 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &cik_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v7_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &cik_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v7_3_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
 		if (amdgpu_dpm == -1)
 			amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		else
@@ -2035,8 +2037,6 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 #endif
 		else
 			amdgpu_device_ip_block_add(adev, &dce_v8_5_ip_block);
-		amdgpu_device_ip_block_add(adev, &gfx_v7_3_ip_block);
-		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
 		amdgpu_device_ip_block_add(adev, &uvd_v4_2_ip_block);
 		amdgpu_device_ip_block_add(adev, &vce_v2_0_ip_block);
 		break;
@@ -2044,6 +2044,8 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &cik_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v7_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &cik_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v7_1_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
 		amdgpu_device_ip_block_add(adev, &kv_smu_ip_block);
 		if (adev->enable_virtual_display)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -2053,8 +2055,7 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 #endif
 		else
 			amdgpu_device_ip_block_add(adev, &dce_v8_1_ip_block);
-		amdgpu_device_ip_block_add(adev, &gfx_v7_1_ip_block);
-		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
+
 		amdgpu_device_ip_block_add(adev, &uvd_v4_2_ip_block);
 		amdgpu_device_ip_block_add(adev, &vce_v2_0_ip_block);
 		break;
@@ -2063,6 +2064,8 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &cik_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v7_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &cik_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v7_2_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
 		amdgpu_device_ip_block_add(adev, &kv_smu_ip_block);
 		if (adev->enable_virtual_display)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -2072,8 +2075,6 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 #endif
 		else
 			amdgpu_device_ip_block_add(adev, &dce_v8_3_ip_block);
-		amdgpu_device_ip_block_add(adev, &gfx_v7_2_ip_block);
-		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
 		amdgpu_device_ip_block_add(adev, &uvd_v4_2_ip_block);
 		amdgpu_device_ip_block_add(adev, &vce_v2_0_ip_block);
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 2aeef2bb93a4..3d0f277a6523 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -1173,64 +1173,61 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev)
 		}
 	}
 
-	if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU) {
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_PFP];
-		info->ucode_id = AMDGPU_UCODE_ID_CP_PFP;
-		info->fw = adev->gfx.pfp_fw;
-		header = (const struct common_firmware_header *)info->fw->data;
-		adev->firmware.fw_size +=
-			ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
+	info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_PFP];
+	info->ucode_id = AMDGPU_UCODE_ID_CP_PFP;
+	info->fw = adev->gfx.pfp_fw;
+	header = (const struct common_firmware_header *)info->fw->data;
+	adev->firmware.fw_size +=
+		ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
 
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_ME];
-		info->ucode_id = AMDGPU_UCODE_ID_CP_ME;
-		info->fw = adev->gfx.me_fw;
-		header = (const struct common_firmware_header *)info->fw->data;
-		adev->firmware.fw_size +=
-			ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
+	info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_ME];
+	info->ucode_id = AMDGPU_UCODE_ID_CP_ME;
+	info->fw = adev->gfx.me_fw;
+	header = (const struct common_firmware_header *)info->fw->data;
+	adev->firmware.fw_size +=
+		ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
 
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_CE];
-		info->ucode_id = AMDGPU_UCODE_ID_CP_CE;
-		info->fw = adev->gfx.ce_fw;
-		header = (const struct common_firmware_header *)info->fw->data;
-		adev->firmware.fw_size +=
-			ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
+	info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_CE];
+	info->ucode_id = AMDGPU_UCODE_ID_CP_CE;
+	info->fw = adev->gfx.ce_fw;
+	header = (const struct common_firmware_header *)info->fw->data;
+	adev->firmware.fw_size +=
+		ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
 
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_G];
-		info->ucode_id = AMDGPU_UCODE_ID_RLC_G;
-		info->fw = adev->gfx.rlc_fw;
-		header = (const struct common_firmware_header *)info->fw->data;
-		adev->firmware.fw_size +=
-			ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
+	info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_G];
+	info->ucode_id = AMDGPU_UCODE_ID_RLC_G;
+	info->fw = adev->gfx.rlc_fw;
+	header = (const struct common_firmware_header *)info->fw->data;
+	adev->firmware.fw_size +=
+		ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
 
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1];
-		info->ucode_id = AMDGPU_UCODE_ID_CP_MEC1;
+	info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1];
+	info->ucode_id = AMDGPU_UCODE_ID_CP_MEC1;
+	info->fw = adev->gfx.mec_fw;
+	header = (const struct common_firmware_header *)info->fw->data;
+	adev->firmware.fw_size +=
+		ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
+
+	/* we need account JT in */
+	cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
+	adev->firmware.fw_size +=
+		ALIGN(le32_to_cpu(cp_hdr->jt_size) << 2, PAGE_SIZE);
+
+	if (amdgpu_sriov_vf(adev)) {
+		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_STORAGE];
+		info->ucode_id = AMDGPU_UCODE_ID_STORAGE;
 		info->fw = adev->gfx.mec_fw;
+		adev->firmware.fw_size +=
+			ALIGN(le32_to_cpu(64 * PAGE_SIZE), PAGE_SIZE);
+	}
+
+	if (adev->gfx.mec2_fw) {
+		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC2];
+		info->ucode_id = AMDGPU_UCODE_ID_CP_MEC2;
+		info->fw = adev->gfx.mec2_fw;
 		header = (const struct common_firmware_header *)info->fw->data;
 		adev->firmware.fw_size +=
 			ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
-
-		/* we need account JT in */
-		cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
-		adev->firmware.fw_size +=
-			ALIGN(le32_to_cpu(cp_hdr->jt_size) << 2, PAGE_SIZE);
-
-		if (amdgpu_sriov_vf(adev)) {
-			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_STORAGE];
-			info->ucode_id = AMDGPU_UCODE_ID_STORAGE;
-			info->fw = adev->gfx.mec_fw;
-			adev->firmware.fw_size +=
-				ALIGN(le32_to_cpu(64 * PAGE_SIZE), PAGE_SIZE);
-		}
-
-		if (adev->gfx.mec2_fw) {
-			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC2];
-			info->ucode_id = AMDGPU_UCODE_ID_CP_MEC2;
-			info->fw = adev->gfx.mec2_fw;
-			header = (const struct common_firmware_header *)info->fw->data;
-			adev->firmware.fw_size +=
-				ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
-		}
-
 	}
 
 out:
@@ -2048,11 +2045,6 @@ static int gfx_v8_0_sw_init(void *handle)
 	adev->gfx.mec.num_pipe_per_mec = 4;
 	adev->gfx.mec.num_queue_per_pipe = 8;
 
-	/* KIQ event */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_INT_IB2, &adev->gfx.kiq.irq);
-	if (r)
-		return r;
-
 	/* EOP Event */
 	r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_END_OF_PIPE, &adev->gfx.eop_irq);
 	if (r)
@@ -4181,45 +4173,11 @@ static void gfx_v8_0_rlc_start(struct amdgpu_device *adev)
 	udelay(50);
 }
 
-static int gfx_v8_0_rlc_load_microcode(struct amdgpu_device *adev)
-{
-	const struct rlc_firmware_header_v2_0 *hdr;
-	const __le32 *fw_data;
-	unsigned i, fw_size;
-
-	if (!adev->gfx.rlc_fw)
-		return -EINVAL;
-
-	hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
-	amdgpu_ucode_print_rlc_hdr(&hdr->header);
-
-	fw_data = (const __le32 *)(adev->gfx.rlc_fw->data +
-			   le32_to_cpu(hdr->header.ucode_array_offset_bytes));
-	fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
-
-	WREG32(mmRLC_GPM_UCODE_ADDR, 0);
-	for (i = 0; i < fw_size; i++)
-		WREG32(mmRLC_GPM_UCODE_DATA, le32_to_cpup(fw_data++));
-	WREG32(mmRLC_GPM_UCODE_ADDR, adev->gfx.rlc_fw_version);
-
-	return 0;
-}
-
 static int gfx_v8_0_rlc_resume(struct amdgpu_device *adev)
 {
-	int r;
-
 	gfx_v8_0_rlc_stop(adev);
 	gfx_v8_0_rlc_reset(adev);
 	gfx_v8_0_init_pg(adev);
-
-	if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
-		/* legacy rlc firmware loading */
-		r = gfx_v8_0_rlc_load_microcode(adev);
-		if (r)
-			return r;
-	}
-
 	gfx_v8_0_rlc_start(adev);
 
 	return 0;
@@ -4245,63 +4203,6 @@ static void gfx_v8_0_cp_gfx_enable(struct amdgpu_device *adev, bool enable)
 	udelay(50);
 }
 
-static int gfx_v8_0_cp_gfx_load_microcode(struct amdgpu_device *adev)
-{
-	const struct gfx_firmware_header_v1_0 *pfp_hdr;
-	const struct gfx_firmware_header_v1_0 *ce_hdr;
-	const struct gfx_firmware_header_v1_0 *me_hdr;
-	const __le32 *fw_data;
-	unsigned i, fw_size;
-
-	if (!adev->gfx.me_fw || !adev->gfx.pfp_fw || !adev->gfx.ce_fw)
-		return -EINVAL;
-
-	pfp_hdr = (const struct gfx_firmware_header_v1_0 *)
-		adev->gfx.pfp_fw->data;
-	ce_hdr = (const struct gfx_firmware_header_v1_0 *)
-		adev->gfx.ce_fw->data;
-	me_hdr = (const struct gfx_firmware_header_v1_0 *)
-		adev->gfx.me_fw->data;
-
-	amdgpu_ucode_print_gfx_hdr(&pfp_hdr->header);
-	amdgpu_ucode_print_gfx_hdr(&ce_hdr->header);
-	amdgpu_ucode_print_gfx_hdr(&me_hdr->header);
-
-	gfx_v8_0_cp_gfx_enable(adev, false);
-
-	/* PFP */
-	fw_data = (const __le32 *)
-		(adev->gfx.pfp_fw->data +
-		 le32_to_cpu(pfp_hdr->header.ucode_array_offset_bytes));
-	fw_size = le32_to_cpu(pfp_hdr->header.ucode_size_bytes) / 4;
-	WREG32(mmCP_PFP_UCODE_ADDR, 0);
-	for (i = 0; i < fw_size; i++)
-		WREG32(mmCP_PFP_UCODE_DATA, le32_to_cpup(fw_data++));
-	WREG32(mmCP_PFP_UCODE_ADDR, adev->gfx.pfp_fw_version);
-
-	/* CE */
-	fw_data = (const __le32 *)
-		(adev->gfx.ce_fw->data +
-		 le32_to_cpu(ce_hdr->header.ucode_array_offset_bytes));
-	fw_size = le32_to_cpu(ce_hdr->header.ucode_size_bytes) / 4;
-	WREG32(mmCP_CE_UCODE_ADDR, 0);
-	for (i = 0; i < fw_size; i++)
-		WREG32(mmCP_CE_UCODE_DATA, le32_to_cpup(fw_data++));
-	WREG32(mmCP_CE_UCODE_ADDR, adev->gfx.ce_fw_version);
-
-	/* ME */
-	fw_data = (const __le32 *)
-		(adev->gfx.me_fw->data +
-		 le32_to_cpu(me_hdr->header.ucode_array_offset_bytes));
-	fw_size = le32_to_cpu(me_hdr->header.ucode_size_bytes) / 4;
-	WREG32(mmCP_ME_RAM_WADDR, 0);
-	for (i = 0; i < fw_size; i++)
-		WREG32(mmCP_ME_RAM_DATA, le32_to_cpup(fw_data++));
-	WREG32(mmCP_ME_RAM_WADDR, adev->gfx.me_fw_version);
-
-	return 0;
-}
-
 static u32 gfx_v8_0_get_csb_size(struct amdgpu_device *adev)
 {
 	u32 count = 0;
@@ -4501,52 +4402,6 @@ static void gfx_v8_0_cp_compute_enable(struct amdgpu_device *adev, bool enable)
 	udelay(50);
 }
 
-static int gfx_v8_0_cp_compute_load_microcode(struct amdgpu_device *adev)
-{
-	const struct gfx_firmware_header_v1_0 *mec_hdr;
-	const __le32 *fw_data;
-	unsigned i, fw_size;
-
-	if (!adev->gfx.mec_fw)
-		return -EINVAL;
-
-	gfx_v8_0_cp_compute_enable(adev, false);
-
-	mec_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
-	amdgpu_ucode_print_gfx_hdr(&mec_hdr->header);
-
-	fw_data = (const __le32 *)
-		(adev->gfx.mec_fw->data +
-		 le32_to_cpu(mec_hdr->header.ucode_array_offset_bytes));
-	fw_size = le32_to_cpu(mec_hdr->header.ucode_size_bytes) / 4;
-
-	/* MEC1 */
-	WREG32(mmCP_MEC_ME1_UCODE_ADDR, 0);
-	for (i = 0; i < fw_size; i++)
-		WREG32(mmCP_MEC_ME1_UCODE_DATA, le32_to_cpup(fw_data+i));
-	WREG32(mmCP_MEC_ME1_UCODE_ADDR, adev->gfx.mec_fw_version);
-
-	/* Loading MEC2 firmware is only necessary if MEC2 should run different microcode than MEC1. */
-	if (adev->gfx.mec2_fw) {
-		const struct gfx_firmware_header_v1_0 *mec2_hdr;
-
-		mec2_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec2_fw->data;
-		amdgpu_ucode_print_gfx_hdr(&mec2_hdr->header);
-
-		fw_data = (const __le32 *)
-			(adev->gfx.mec2_fw->data +
-			 le32_to_cpu(mec2_hdr->header.ucode_array_offset_bytes));
-		fw_size = le32_to_cpu(mec2_hdr->header.ucode_size_bytes) / 4;
-
-		WREG32(mmCP_MEC_ME2_UCODE_ADDR, 0);
-		for (i = 0; i < fw_size; i++)
-			WREG32(mmCP_MEC_ME2_UCODE_DATA, le32_to_cpup(fw_data+i));
-		WREG32(mmCP_MEC_ME2_UCODE_ADDR, adev->gfx.mec2_fw_version);
-	}
-
-	return 0;
-}
-
 /* KIQ functions */
 static void gfx_v8_0_kiq_setting(struct amdgpu_ring *ring)
 {
@@ -4872,7 +4727,7 @@ static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring)
 	struct vi_mqd *mqd = ring->mqd_ptr;
 	int mqd_idx = ring - &adev->gfx.compute_ring[0];
 
-	if (!adev->in_gpu_reset && !adev->gfx.in_suspend) {
+	if (!adev->in_gpu_reset && !adev->in_suspend) {
 		memset((void *)mqd, 0, sizeof(struct vi_mqd_allocation));
 		((struct vi_mqd_allocation *)mqd)->dynamic_cu_mask = 0xFFFFFFFF;
 		((struct vi_mqd_allocation *)mqd)->dynamic_rb_mask = 0xFFFFFFFF;
@@ -4980,17 +4835,6 @@ static int gfx_v8_0_cp_resume(struct amdgpu_device *adev)
 	if (!(adev->flags & AMD_IS_APU))
 		gfx_v8_0_enable_gui_idle_interrupt(adev, false);
 
-	if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
-			/* legacy firmware loading */
-		r = gfx_v8_0_cp_gfx_load_microcode(adev);
-		if (r)
-			return r;
-
-		r = gfx_v8_0_cp_compute_load_microcode(adev);
-		if (r)
-			return r;
-	}
-
 	r = gfx_v8_0_kiq_resume(adev);
 	if (r)
 		return r;
@@ -5142,19 +4986,12 @@ static int gfx_v8_0_hw_fini(void *handle)
 
 static int gfx_v8_0_suspend(void *handle)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	adev->gfx.in_suspend = true;
-	return gfx_v8_0_hw_fini(adev);
+	return gfx_v8_0_hw_fini(handle);
 }
 
 static int gfx_v8_0_resume(void *handle)
 {
-	int r;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	r = gfx_v8_0_hw_init(adev);
-	adev->gfx.in_suspend = false;
-	return r;
+	return gfx_v8_0_hw_init(handle);
 }
 
 static bool gfx_v8_0_check_soft_reset(void *handle)
@@ -7025,52 +6862,6 @@ static int gfx_v8_0_sq_irq(struct amdgpu_device *adev,
 	return 0;
 }
 
-static int gfx_v8_0_kiq_set_interrupt_state(struct amdgpu_device *adev,
-					    struct amdgpu_irq_src *src,
-					    unsigned int type,
-					    enum amdgpu_interrupt_state state)
-{
-	struct amdgpu_ring *ring = &(adev->gfx.kiq.ring);
-
-	switch (type) {
-	case AMDGPU_CP_KIQ_IRQ_DRIVER0:
-		WREG32_FIELD(CPC_INT_CNTL, GENERIC2_INT_ENABLE,
-			     state == AMDGPU_IRQ_STATE_DISABLE ? 0 : 1);
-		if (ring->me == 1)
-			WREG32_FIELD_OFFSET(CP_ME1_PIPE0_INT_CNTL,
-				     ring->pipe,
-				     GENERIC2_INT_ENABLE,
-				     state == AMDGPU_IRQ_STATE_DISABLE ? 0 : 1);
-		else
-			WREG32_FIELD_OFFSET(CP_ME2_PIPE0_INT_CNTL,
-				     ring->pipe,
-				     GENERIC2_INT_ENABLE,
-				     state == AMDGPU_IRQ_STATE_DISABLE ? 0 : 1);
-		break;
-	default:
-		BUG(); /* kiq only support GENERIC2_INT now */
-		break;
-	}
-	return 0;
-}
-
-static int gfx_v8_0_kiq_irq(struct amdgpu_device *adev,
-			    struct amdgpu_irq_src *source,
-			    struct amdgpu_iv_entry *entry)
-{
-	u8 me_id, pipe_id, queue_id;
-	struct amdgpu_ring *ring = &(adev->gfx.kiq.ring);
-
-	me_id = (entry->ring_id & 0x0c) >> 2;
-	pipe_id = (entry->ring_id & 0x03) >> 0;
-	queue_id = (entry->ring_id & 0x70) >> 4;
-	DRM_DEBUG("IH: CPC GENERIC2_INT, me:%d, pipe:%d, queue:%d\n",
-		   me_id, pipe_id, queue_id);
-
-	amdgpu_fence_process(ring);
-	return 0;
-}
-
 static const struct amd_ip_funcs gfx_v8_0_ip_funcs = {
 	.name = "gfx_v8_0",
 	.early_init = gfx_v8_0_early_init,
@@ -7221,11 +7012,6 @@ static const struct amdgpu_irq_src_funcs gfx_v8_0_priv_inst_irq_funcs = {
 	.process = gfx_v8_0_priv_inst_irq,
 };
 
-static const struct amdgpu_irq_src_funcs gfx_v8_0_kiq_irq_funcs = {
-	.set = gfx_v8_0_kiq_set_interrupt_state,
-	.process = gfx_v8_0_kiq_irq,
-};
-
 static const struct amdgpu_irq_src_funcs gfx_v8_0_cp_ecc_error_irq_funcs = {
 	.set = gfx_v8_0_set_cp_ecc_int_state,
 	.process = gfx_v8_0_cp_ecc_error_irq,
@@ -7247,9 +7033,6 @@ static void gfx_v8_0_set_irq_funcs(struct amdgpu_device *adev)
 	adev->gfx.priv_inst_irq.num_types = 1;
 	adev->gfx.priv_inst_irq.funcs = &gfx_v8_0_priv_inst_irq_funcs;
 
-	adev->gfx.kiq.irq.num_types = AMDGPU_CP_KIQ_IRQ_LAST;
-	adev->gfx.kiq.irq.funcs = &gfx_v8_0_kiq_irq_funcs;
-
 	adev->gfx.cp_ecc_error_irq.num_types = 1;
 	adev->gfx.cp_ecc_error_irq.funcs = &gfx_v8_0_cp_ecc_error_irq_funcs;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 261bb051b14d..e61f6a3ca241 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -133,7 +133,10 @@ static const struct soc15_reg_golden golden_settings_gc_9_0_vg10[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_UTCL1_CNTL2, 0x00030000, 0x00020000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1, 0x0000000f, 0x01000107),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x00001800, 0x00000800),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmWD_UTCL1_CNTL, 0x08000000, 0x08000080)
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmWD_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC1_F32_INT_DIS, 0x00000000, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC2_F32_INT_DIS, 0x00000000, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_DEBUG, 0x00000000, 0x00008000)
 };
 
 static const struct soc15_reg_golden golden_settings_gc_9_0_vg20[] =
@@ -173,7 +176,10 @@ static const struct soc15_reg_golden golden_settings_gc_9_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_LO, 0xffffffff, 0x00003120),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_CACHE_INVALIDATION, 0x3fff3af3, 0x19200000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_GS_MAX_WAVE_ID, 0x00000fff, 0x000000ff),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmWD_UTCL1_CNTL, 0x08000000, 0x08000080)
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmWD_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC1_F32_INT_DIS, 0x00000000, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC2_F32_INT_DIS, 0x00000000, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_DEBUG, 0x00000000, 0x00008000)
 };
 
 static const struct soc15_reg_golden golden_settings_gc_9_1_rv1[] =
@@ -247,7 +253,10 @@ static const struct soc15_reg_golden golden_settings_gc_9_2_1_vg12[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1, 0xffff03ff, 0x01000107),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_HI, 0xffffffff, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_LO, 0xffffffff, 0x76325410),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x01bd9f33, 0x01000000)
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x01bd9f33, 0x01000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC1_F32_INT_DIS, 0x00000000, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC2_F32_INT_DIS, 0x00000000, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_DEBUG, 0x00000000, 0x00008000)
 };
 
 static const u32 GFX_RLC_SRM_INDEX_CNTL_ADDR_OFFSETS[] =
@@ -908,6 +917,50 @@ static void gfx_v9_0_get_csb_buffer(struct amdgpu_device *adev,
 	buffer[count++] = cpu_to_le32(0);
 }
 
+static void gfx_v9_0_init_always_on_cu_mask(struct amdgpu_device *adev)
+{
+	struct amdgpu_cu_info *cu_info = &adev->gfx.cu_info;
+	uint32_t pg_always_on_cu_num = 2;
+	uint32_t always_on_cu_num;
+	uint32_t i, j, k;
+	uint32_t mask, cu_bitmap, counter;
+
+	if (adev->flags & AMD_IS_APU)
+		always_on_cu_num = 4;
+	else if (adev->asic_type == CHIP_VEGA12)
+		always_on_cu_num = 8;
+	else
+		always_on_cu_num = 12;
+
+	mutex_lock(&adev->grbm_idx_mutex);
+	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
+		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
+			mask = 1;
+			cu_bitmap = 0;
+			counter = 0;
+			gfx_v9_0_select_se_sh(adev, i, j, 0xffffffff);
+
+			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k ++) {
+				if (cu_info->bitmap[i][j] & mask) {
+					if (counter == pg_always_on_cu_num)
+						WREG32_SOC15(GC, 0, mmRLC_PG_ALWAYS_ON_CU_MASK, cu_bitmap);
+					if (counter < always_on_cu_num)
+						cu_bitmap |= mask;
+					else
+						break;
+					counter++;
+				}
+				mask <<= 1;
+			}
+
+			WREG32_SOC15(GC, 0, mmRLC_LB_ALWAYS_ACTIVE_CU_MASK, cu_bitmap);
+			cu_info->ao_cu_bitmap[i][j] = cu_bitmap;
+		}
+	}
+	gfx_v9_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+	mutex_unlock(&adev->grbm_idx_mutex);
+}
+
 static void gfx_v9_0_init_lbpw(struct amdgpu_device *adev)
 {
 	uint32_t data;
@@ -941,8 +994,10 @@ static void gfx_v9_0_init_lbpw(struct amdgpu_device *adev)
 	data |= 0x00C00000;
 	WREG32_SOC15(GC, 0, mmRLC_GPM_GENERAL_7, data);
 
-	/* set RLC_LB_ALWAYS_ACTIVE_CU_MASK = 0xFFF */
-	WREG32_SOC15(GC, 0, mmRLC_LB_ALWAYS_ACTIVE_CU_MASK, 0xFFF);
+	/*
+	 * RLC_LB_ALWAYS_ACTIVE_CU_MASK = 0xF (4 CUs AON for Raven),
+	 * programmed in gfx_v9_0_init_always_on_cu_mask()
+	 */
 
 	/* set RLC_LB_CNTL = 0x8000_0095, 31 bit is reserved,
 	 * but used for RLC_LB_CNTL configuration */
@@ -951,6 +1006,57 @@ static void gfx_v9_0_init_lbpw(struct amdgpu_device *adev)
 	data |= REG_SET_FIELD(data, RLC_LB_CNTL, RESERVED, 0x80000);
 	WREG32_SOC15(GC, 0, mmRLC_LB_CNTL, data);
 	mutex_unlock(&adev->grbm_idx_mutex);
+
+	gfx_v9_0_init_always_on_cu_mask(adev);
+}
+
+static void gfx_v9_4_init_lbpw(struct amdgpu_device *adev)
+{
+	uint32_t data;
+
+	/* set mmRLC_LB_THR_CONFIG_1/2/3/4 */
+	WREG32_SOC15(GC, 0, mmRLC_LB_THR_CONFIG_1, 0x0000007F);
+	WREG32_SOC15(GC, 0, mmRLC_LB_THR_CONFIG_2, 0x033388F8);
+	WREG32_SOC15(GC, 0, mmRLC_LB_THR_CONFIG_3, 0x00000077);
+	WREG32_SOC15(GC, 0, mmRLC_LB_THR_CONFIG_4, (0x10 | 0x27 << 8 | 0x02FA << 16));
+
+	/* set mmRLC_LB_CNTR_INIT = 0x0000_0000 */
+	WREG32_SOC15(GC, 0, mmRLC_LB_CNTR_INIT, 0x00000000);
+
+	/* set mmRLC_LB_CNTR_MAX = 0x0000_0500 */
+	WREG32_SOC15(GC, 0, mmRLC_LB_CNTR_MAX, 0x00000800);
+
+	mutex_lock(&adev->grbm_idx_mutex);
+	/* set mmRLC_LB_INIT_CU_MASK thru broadcast mode to enable all SE/SH*/
+	gfx_v9_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+	WREG32_SOC15(GC, 0, mmRLC_LB_INIT_CU_MASK, 0xffffffff);
+
+	/* set mmRLC_LB_PARAMS = 0x003F_1006 */
+	data = REG_SET_FIELD(0, RLC_LB_PARAMS, FIFO_SAMPLES, 0x0003);
+	data |= REG_SET_FIELD(data, RLC_LB_PARAMS, PG_IDLE_SAMPLES, 0x0010);
+	data |= REG_SET_FIELD(data, RLC_LB_PARAMS, PG_IDLE_SAMPLE_INTERVAL, 0x033F);
+	WREG32_SOC15(GC, 0, mmRLC_LB_PARAMS, data);
+
+	/* set mmRLC_GPM_GENERAL_7[31-16] = 0x00C0 */
+	data = RREG32_SOC15(GC, 0, mmRLC_GPM_GENERAL_7);
+	data &= 0x0000FFFF;
+	data |= 0x00C00000;
+	WREG32_SOC15(GC, 0, mmRLC_GPM_GENERAL_7, data);
+
+	/*
+	 * RLC_LB_ALWAYS_ACTIVE_CU_MASK = 0xFFF (12 CUs AON),
+	 * programmed in gfx_v9_0_init_always_on_cu_mask()
+	 */
+
+	/* set RLC_LB_CNTL = 0x8000_0095, 31 bit is reserved,
+	 * but used for RLC_LB_CNTL configuration */
+	data = RLC_LB_CNTL__LB_CNT_SPIM_ACTIVE_MASK;
+	data |= REG_SET_FIELD(data, RLC_LB_CNTL, CU_MASK_USED_OFF_HYST, 0x09);
+	data |= REG_SET_FIELD(data, RLC_LB_CNTL, RESERVED, 0x80000);
+	WREG32_SOC15(GC, 0, mmRLC_LB_CNTL, data);
+	mutex_unlock(&adev->grbm_idx_mutex);
+
+	gfx_v9_0_init_always_on_cu_mask(adev);
 }
 
 static void gfx_v9_0_enable_lbpw(struct amdgpu_device *adev, bool enable)
@@ -1084,8 +1190,17 @@ static int gfx_v9_0_rlc_init(struct amdgpu_device *adev)
 		rv_init_cp_jump_table(adev);
 		amdgpu_bo_kunmap(adev->gfx.rlc.cp_table_obj);
 		amdgpu_bo_unreserve(adev->gfx.rlc.cp_table_obj);
+	}
 
+	switch (adev->asic_type) {
+	case CHIP_RAVEN:
 		gfx_v9_0_init_lbpw(adev);
+		break;
+	case CHIP_VEGA20:
+		gfx_v9_4_init_lbpw(adev);
+		break;
+	default:
+		break;
 	}
 
 	return 0;
@@ -1605,11 +1720,6 @@ static int gfx_v9_0_sw_init(void *handle)
 	adev->gfx.mec.num_pipe_per_mec = 4;
 	adev->gfx.mec.num_queue_per_pipe = 8;
 
-	/* KIQ event */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, GFX_9_0__SRCID__CP_IB2_INTERRUPT_PKT, &adev->gfx.kiq.irq);
-	if (r)
-		return r;
-
 	/* EOP Event */
 	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, GFX_9_0__SRCID__CP_EOP_INTERRUPT, &adev->gfx.eop_irq);
 	if (r)
@@ -2403,7 +2513,8 @@ static int gfx_v9_0_rlc_resume(struct amdgpu_device *adev)
 			return r;
 	}
 
-	if (adev->asic_type == CHIP_RAVEN) {
+	if (adev->asic_type == CHIP_RAVEN ||
+	    adev->asic_type == CHIP_VEGA20) {
 		if (amdgpu_lbpw != 0)
 			gfx_v9_0_enable_lbpw(adev, true);
 		else
@@ -3091,7 +3202,7 @@ static int gfx_v9_0_kcq_init_queue(struct amdgpu_ring *ring)
 	struct v9_mqd *mqd = ring->mqd_ptr;
 	int mqd_idx = ring - &adev->gfx.compute_ring[0];
 
-	if (!adev->in_gpu_reset && !adev->gfx.in_suspend) {
+	if (!adev->in_gpu_reset && !adev->in_suspend) {
 		memset((void *)mqd, 0, sizeof(struct v9_mqd_allocation));
 		((struct v9_mqd_allocation *)mqd)->dynamic_cu_mask = 0xFFFFFFFF;
 		((struct v9_mqd_allocation *)mqd)->dynamic_rb_mask = 0xFFFFFFFF;
@@ -3310,7 +3421,7 @@ static int gfx_v9_0_hw_fini(void *handle)
 	/* Use deinitialize sequence from CAIL when unbinding device from driver,
 	 * otherwise KIQ is hanging when binding back
 	 */
-	if (!adev->in_gpu_reset && !adev->gfx.in_suspend) {
+	if (!adev->in_gpu_reset && !adev->in_suspend) {
 		mutex_lock(&adev->srbm_mutex);
 		soc15_grbm_select(adev, adev->gfx.kiq.ring.me,
 				adev->gfx.kiq.ring.pipe,
@@ -3330,20 +3441,12 @@ static int gfx_v9_0_hw_fini(void *handle)
 
 static int gfx_v9_0_suspend(void *handle)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	adev->gfx.in_suspend = true;
-	return gfx_v9_0_hw_fini(adev);
+	return gfx_v9_0_hw_fini(handle);
 }
 
 static int gfx_v9_0_resume(void *handle)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	int r;
-
-	r = gfx_v9_0_hw_init(adev);
-	adev->gfx.in_suspend = false;
-	return r;
+	return gfx_v9_0_hw_init(handle);
 }
 
 static bool gfx_v9_0_is_idle(void *handle)
@@ -4609,68 +4712,6 @@ static int gfx_v9_0_priv_inst_irq(struct amdgpu_device *adev,
 	return 0;
 }
 
-static int gfx_v9_0_kiq_set_interrupt_state(struct amdgpu_device *adev,
-					    struct amdgpu_irq_src *src,
-					    unsigned int type,
-					    enum amdgpu_interrupt_state state)
-{
-	uint32_t tmp, target;
-	struct amdgpu_ring *ring = &(adev->gfx.kiq.ring);
-
-	if (ring->me == 1)
-		target = SOC15_REG_OFFSET(GC, 0, mmCP_ME1_PIPE0_INT_CNTL);
-	else
-		target = SOC15_REG_OFFSET(GC, 0, mmCP_ME2_PIPE0_INT_CNTL);
-	target += ring->pipe;
-
-	switch (type) {
-	case AMDGPU_CP_KIQ_IRQ_DRIVER0:
-		if (state == AMDGPU_IRQ_STATE_DISABLE) {
-			tmp = RREG32_SOC15(GC, 0, mmCPC_INT_CNTL);
-			tmp = REG_SET_FIELD(tmp, CPC_INT_CNTL,
-						 GENERIC2_INT_ENABLE, 0);
-			WREG32_SOC15(GC, 0, mmCPC_INT_CNTL, tmp);
-
-			tmp = RREG32(target);
-			tmp = REG_SET_FIELD(tmp, CP_ME2_PIPE0_INT_CNTL,
-						 GENERIC2_INT_ENABLE, 0);
-			WREG32(target, tmp);
-		} else {
-			tmp = RREG32_SOC15(GC, 0, mmCPC_INT_CNTL);
-			tmp = REG_SET_FIELD(tmp, CPC_INT_CNTL,
-						 GENERIC2_INT_ENABLE, 1);
-			WREG32_SOC15(GC, 0, mmCPC_INT_CNTL, tmp);
-
-			tmp = RREG32(target);
-			tmp = REG_SET_FIELD(tmp, CP_ME2_PIPE0_INT_CNTL,
-						 GENERIC2_INT_ENABLE, 1);
-			WREG32(target, tmp);
-		}
-		break;
-	default:
-		BUG(); /* kiq only support GENERIC2_INT now */
-		break;
-	}
-	return 0;
-}
-
-static int gfx_v9_0_kiq_irq(struct amdgpu_device *adev,
-			    struct amdgpu_irq_src *source,
-			    struct amdgpu_iv_entry *entry)
-{
-	u8 me_id, pipe_id, queue_id;
-	struct amdgpu_ring *ring = &(adev->gfx.kiq.ring);
-
-	me_id = (entry->ring_id & 0x0c) >> 2;
-	pipe_id = (entry->ring_id & 0x03) >> 0;
-	queue_id = (entry->ring_id & 0x70) >> 4;
-	DRM_DEBUG("IH: CPC GENERIC2_INT, me:%d, pipe:%d, queue:%d\n",
-		   me_id, pipe_id, queue_id);
-
-	amdgpu_fence_process(ring);
-	return 0;
-}
-
 static const struct amd_ip_funcs gfx_v9_0_ip_funcs = {
 	.name = "gfx_v9_0",
 	.early_init = gfx_v9_0_early_init,
@@ -4819,11 +4860,6 @@ static void gfx_v9_0_set_ring_funcs(struct amdgpu_device *adev)
 		adev->gfx.compute_ring[i].funcs = &gfx_v9_0_ring_funcs_compute;
 }
 
-static const struct amdgpu_irq_src_funcs gfx_v9_0_kiq_irq_funcs = {
-	.set = gfx_v9_0_kiq_set_interrupt_state,
-	.process = gfx_v9_0_kiq_irq,
-};
-
 static const struct amdgpu_irq_src_funcs gfx_v9_0_eop_irq_funcs = {
 	.set = gfx_v9_0_set_eop_interrupt_state,
 	.process = gfx_v9_0_eop_irq,
@@ -4849,9 +4885,6 @@ static void gfx_v9_0_set_irq_funcs(struct amdgpu_device *adev)
 
 	adev->gfx.priv_inst_irq.num_types = 1;
 	adev->gfx.priv_inst_irq.funcs = &gfx_v9_0_priv_inst_irq_funcs;
-
-	adev->gfx.kiq.irq.num_types = AMDGPU_CP_KIQ_IRQ_LAST;
-	adev->gfx.kiq.irq.funcs = &gfx_v9_0_kiq_irq_funcs;
 }
 
 static void gfx_v9_0_set_rlc_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index 9217af00bc8d..3f3fac2d50cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -306,11 +306,8 @@ static int psp_v11_0_ring_stop(struct psp_context *psp,
 			      enum psp_ring_type ring_type)
 {
 	int ret = 0;
-	struct psp_ring *ring;
 	struct amdgpu_device *adev = psp->adev;
 
-	ring = &psp->km_ring;
-
 	/* Write the ring destroy command to C2PMSG_64 */
 	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_64, GFX_CTRL_CMD_ID_DESTROY_RINGS);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index cd781abc4953..2d4770e173dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -504,41 +504,6 @@ static int sdma_v2_4_rlc_resume(struct amdgpu_device *adev)
 	return 0;
 }
 
-/**
- * sdma_v2_4_load_microcode - load the sDMA ME ucode
- *
- * @adev: amdgpu_device pointer
- *
- * Loads the sDMA0/1 ucode.
- * Returns 0 for success, -EINVAL if the ucode is not available.
- */
-static int sdma_v2_4_load_microcode(struct amdgpu_device *adev)
-{
-	const struct sdma_firmware_header_v1_0 *hdr;
-	const __le32 *fw_data;
-	u32 fw_size;
-	int i, j;
-
-	/* halt the MEs */
-	sdma_v2_4_enable(adev, false);
-
-	for (i = 0; i < adev->sdma.num_instances; i++) {
-		if (!adev->sdma.instance[i].fw)
-			return -EINVAL;
-		hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data;
-		amdgpu_ucode_print_sdma_hdr(&hdr->header);
-		fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
-		fw_data = (const __le32 *)
-			(adev->sdma.instance[i].fw->data +
-			 le32_to_cpu(hdr->header.ucode_array_offset_bytes));
-		WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0);
-		for (j = 0; j < fw_size; j++)
-			WREG32(mmSDMA0_UCODE_DATA + sdma_offsets[i], le32_to_cpup(fw_data++));
-		WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma.instance[i].fw_version);
-	}
-
-	return 0;
-}
 
 /**
  * sdma_v2_4_start - setup and start the async dma engines
@@ -552,13 +517,6 @@ static int sdma_v2_4_start(struct amdgpu_device *adev)
 {
 	int r;
 
-
-	if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
-		r = sdma_v2_4_load_microcode(adev);
-		if (r)
-			return r;
-	}
-
 	/* halt the engine before programing */
 	sdma_v2_4_enable(adev, false);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 6d5c8ac64874..6fb3edaba0ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -318,14 +318,13 @@ static int sdma_v3_0_init_microcode(struct amdgpu_device *adev)
 		if (adev->sdma.instance[i].feature_version >= 20)
 			adev->sdma.instance[i].burst_nop = true;
 
-		if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU) {
-			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i];
-			info->ucode_id = AMDGPU_UCODE_ID_SDMA0 + i;
-			info->fw = adev->sdma.instance[i].fw;
-			header = (const struct common_firmware_header *)info->fw->data;
-			adev->firmware.fw_size +=
-				ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
-		}
+		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i];
+		info->ucode_id = AMDGPU_UCODE_ID_SDMA0 + i;
+		info->fw = adev->sdma.instance[i].fw;
+		header = (const struct common_firmware_header *)info->fw->data;
+		adev->firmware.fw_size +=
+			ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
+
 	}
 out:
 	if (err) {
@@ -777,42 +776,6 @@ static int sdma_v3_0_rlc_resume(struct amdgpu_device *adev)
 	return 0;
 }
 
-/**
- * sdma_v3_0_load_microcode - load the sDMA ME ucode
- *
- * @adev: amdgpu_device pointer
- *
- * Loads the sDMA0/1 ucode.
- * Returns 0 for success, -EINVAL if the ucode is not available.
- */
-static int sdma_v3_0_load_microcode(struct amdgpu_device *adev)
-{
-	const struct sdma_firmware_header_v1_0 *hdr;
-	const __le32 *fw_data;
-	u32 fw_size;
-	int i, j;
-
-	/* halt the MEs */
-	sdma_v3_0_enable(adev, false);
-
-	for (i = 0; i < adev->sdma.num_instances; i++) {
-		if (!adev->sdma.instance[i].fw)
-			return -EINVAL;
-		hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data;
-		amdgpu_ucode_print_sdma_hdr(&hdr->header);
-		fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
-		fw_data = (const __le32 *)
-			(adev->sdma.instance[i].fw->data +
-				le32_to_cpu(hdr->header.ucode_array_offset_bytes));
-		WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0);
-		for (j = 0; j < fw_size; j++)
-			WREG32(mmSDMA0_UCODE_DATA + sdma_offsets[i], le32_to_cpup(fw_data++));
-		WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma.instance[i].fw_version);
-	}
-
-	return 0;
-}
-
 /**
  * sdma_v3_0_start - setup and start the async dma engines
  *
@@ -825,12 +788,6 @@ static int sdma_v3_0_start(struct amdgpu_device *adev)
 {
 	int r;
 
-	if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
-		r = sdma_v3_0_load_microcode(adev);
-		if (r)
-			return r;
-	}
-
 	/* disable sdma engine before programing it */
 	sdma_v3_0_ctx_switch_enable(adev, false);
 	sdma_v3_0_enable(adev, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index a3e2ed15fff2..c20d413f277c 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -818,7 +818,7 @@ sdma_v4_1_update_power_gating(struct amdgpu_device *adev, bool enable)
 	uint32_t def, data;
 
 	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_SDMA)) {
-		/* disable idle interrupt */
+		/* enable idle interrupt */
 		def = data = RREG32(SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_CNTL));
 		data |= SDMA0_CNTL__CTXEMPTY_INT_ENABLE_MASK;
 
@@ -1364,6 +1364,9 @@ static int sdma_v4_0_hw_init(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs->set_powergating_by_smu)
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_SDMA, false);
+
 	sdma_v4_0_init_golden_registers(adev);
 
 	r = sdma_v4_0_start(adev);
@@ -1381,6 +1384,9 @@ static int sdma_v4_0_hw_fini(void *handle)
 	sdma_v4_0_ctx_switch_enable(adev, false);
 	sdma_v4_0_enable(adev, false);
 
+	if (adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs->set_powergating_by_smu)
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_SDMA, true);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index c364ef94cc36..f8408f88cd37 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -2057,13 +2057,13 @@ int si_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &si_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v6_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &si_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v6_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &si_dma_ip_block);
 		amdgpu_device_ip_block_add(adev, &si_smu_ip_block);
 		if (adev->enable_virtual_display)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 		else
 			amdgpu_device_ip_block_add(adev, &dce_v6_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &gfx_v6_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &si_dma_ip_block);
 		/* amdgpu_device_ip_block_add(adev, &uvd_v3_1_ip_block); */
 		/* amdgpu_device_ip_block_add(adev, &vce_v1_0_ip_block); */
 		break;
@@ -2071,13 +2071,14 @@ int si_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &si_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v6_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &si_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v6_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &si_dma_ip_block);
 		amdgpu_device_ip_block_add(adev, &si_smu_ip_block);
 		if (adev->enable_virtual_display)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 		else
 			amdgpu_device_ip_block_add(adev, &dce_v6_4_ip_block);
-		amdgpu_device_ip_block_add(adev, &gfx_v6_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &si_dma_ip_block);
+
 		/* amdgpu_device_ip_block_add(adev, &uvd_v3_1_ip_block); */
 		/* amdgpu_device_ip_block_add(adev, &vce_v1_0_ip_block); */
 		break;
@@ -2085,11 +2086,11 @@ int si_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &si_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v6_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &si_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v6_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &si_dma_ip_block);
 		amdgpu_device_ip_block_add(adev, &si_smu_ip_block);
 		if (adev->enable_virtual_display)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
-		amdgpu_device_ip_block_add(adev, &gfx_v6_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &si_dma_ip_block);
 		break;
 	default:
 		BUG();
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c
index d4ceaf440f26..adbaea6da0d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dma.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c
@@ -502,12 +502,14 @@ static int si_dma_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* DMA0 trap event */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, 224, &adev->sdma.trap_irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, 224,
+			      &adev->sdma.trap_irq);
 	if (r)
 		return r;
 
 	/* DMA1 trap event */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, 244, &adev->sdma.trap_irq_1);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, 244,
+			      &adev->sdma.trap_irq);
 	if (r)
 		return r;
 
@@ -649,17 +651,10 @@ static int si_dma_process_trap_irq(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
 {
-	amdgpu_fence_process(&adev->sdma.instance[0].ring);
-
-	return 0;
-}
-
-static int si_dma_process_trap_irq_1(struct amdgpu_device *adev,
-				      struct amdgpu_irq_src *source,
-				      struct amdgpu_iv_entry *entry)
-{
-	amdgpu_fence_process(&adev->sdma.instance[1].ring);
-
+	if (entry->src_id == 224)
+		amdgpu_fence_process(&adev->sdma.instance[0].ring);
+	else
+		amdgpu_fence_process(&adev->sdma.instance[1].ring);
 	return 0;
 }
 
@@ -786,11 +781,6 @@ static const struct amdgpu_irq_src_funcs si_dma_trap_irq_funcs = {
 	.process = si_dma_process_trap_irq,
 };
 
-static const struct amdgpu_irq_src_funcs si_dma_trap_irq_funcs_1 = {
-	.set = si_dma_set_trap_irq_state,
-	.process = si_dma_process_trap_irq_1,
-};
-
 static const struct amdgpu_irq_src_funcs si_dma_illegal_inst_irq_funcs = {
 	.process = si_dma_process_illegal_inst_irq,
 };
@@ -799,7 +789,6 @@ static void si_dma_set_irq_funcs(struct amdgpu_device *adev)
 {
 	adev->sdma.trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST;
 	adev->sdma.trap_irq.funcs = &si_dma_trap_irq_funcs;
-	adev->sdma.trap_irq_1.funcs = &si_dma_trap_irq_funcs_1;
 	adev->sdma.illegal_inst_irq.funcs = &si_dma_illegal_inst_irq_funcs;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index fb26039beeba..bf5e6a413dee 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -529,6 +529,8 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block);
 		else
 			amdgpu_device_ip_block_add(adev, &psp_v3_1_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
 		if (!amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
@@ -539,8 +541,6 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 #else
 #	warning "Enable CONFIG_DRM_AMD_DC for display support on SOC15."
 #endif
-		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
 		if (!(adev->asic_type == CHIP_VEGA20 && amdgpu_sriov_vf(adev))) {
 			amdgpu_device_ip_block_add(adev, &uvd_v7_0_ip_block);
 			amdgpu_device_ip_block_add(adev, &vce_v4_0_ip_block);
@@ -551,6 +551,8 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gmc_v9_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &vega10_ih_ip_block);
 		amdgpu_device_ip_block_add(adev, &psp_v10_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -560,8 +562,6 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 #else
 #	warning "Enable CONFIG_DRM_AMD_DC for display support on SOC15."
 #endif
-		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &vcn_v1_0_ip_block);
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 8ef4a5392112..7a5b40275e8e 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -274,7 +274,7 @@ err:
  */
 static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring,
 					uint32_t handle,
-					bool direct, struct dma_fence **fence)
+					struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
@@ -310,11 +310,7 @@ static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (direct)
-		r = amdgpu_job_submit_direct(job, ring, &f);
-	else
-		r = amdgpu_job_submit(job, &ring->adev->vce.entity,
-				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
@@ -345,7 +341,7 @@ static int uvd_v6_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 		goto error;
 	}
 
-	r = uvd_v6_0_enc_get_destroy_msg(ring, 1, true, &fence);
+	r = uvd_v6_0_enc_get_destroy_msg(ring, 1, &fence);
 	if (r) {
 		DRM_ERROR("amdgpu: failed to get destroy ib (%ld).\n", r);
 		goto error;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index a289f6a20b6b..58b39afcfb86 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -280,8 +280,8 @@ err:
  *
  * Close up a stream for HW test or if userspace failed to do so
  */
-int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
-				 bool direct, struct dma_fence **fence)
+static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
+				struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
@@ -317,11 +317,7 @@ int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (direct)
-		r = amdgpu_job_submit_direct(job, ring, &f);
-	else
-		r = amdgpu_job_submit(job, &ring->adev->vce.entity,
-				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
@@ -352,7 +348,7 @@ static int uvd_v7_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 		goto error;
 	}
 
-	r = uvd_v7_0_enc_get_destroy_msg(ring, 1, true, &fence);
+	r = uvd_v7_0_enc_get_destroy_msg(ring, 1, &fence);
 	if (r) {
 		DRM_ERROR("amdgpu: (%d)failed to get destroy ib (%ld).\n", ring->me, r);
 		goto error;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 63d7f97e81b7..e9282415c24f 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -278,6 +278,7 @@ static void vcn_v1_0_mc_resume_spg_mode(struct amdgpu_device *adev)
 	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
 	uint32_t offset;
 
+	/* cache window 0: fw */
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 		WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
 			     (adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_lo));
@@ -297,20 +298,21 @@ static void vcn_v1_0_mc_resume_spg_mode(struct amdgpu_device *adev)
 
 	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE0, size);
 
+	/* cache window 1: stack */
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW,
 		     lower_32_bits(adev->vcn.gpu_addr + offset));
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH,
 		     upper_32_bits(adev->vcn.gpu_addr + offset));
 	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET1, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE1, AMDGPU_VCN_HEAP_SIZE);
+	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE1, AMDGPU_VCN_STACK_SIZE);
 
+	/* cache window 2: context */
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW,
-		     lower_32_bits(adev->vcn.gpu_addr + offset + AMDGPU_VCN_HEAP_SIZE));
+		     lower_32_bits(adev->vcn.gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH,
-		     upper_32_bits(adev->vcn.gpu_addr + offset + AMDGPU_VCN_HEAP_SIZE));
+		     upper_32_bits(adev->vcn.gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
 	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET2, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE2,
-			AMDGPU_VCN_STACK_SIZE + (AMDGPU_VCN_SESSION_SIZE * 40));
+	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE2, AMDGPU_VCN_CONTEXT_SIZE);
 
 	WREG32_SOC15(UVD, 0, mmUVD_UDEC_ADDR_CONFIG,
 			adev->gfx.config.gb_addr_config);
@@ -325,6 +327,7 @@ static void vcn_v1_0_mc_resume_dpg_mode(struct amdgpu_device *adev)
 	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
 	uint32_t offset;
 
+	/* cache window 0: fw */
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 		WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
 			     (adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_lo),
@@ -347,24 +350,25 @@ static void vcn_v1_0_mc_resume_dpg_mode(struct amdgpu_device *adev)
 
 	WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_VCPU_CACHE_SIZE0, size, 0xFFFFFFFF, 0);
 
+	/* cache window 1: stack */
 	WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW,
 		     lower_32_bits(adev->vcn.gpu_addr + offset), 0xFFFFFFFF, 0);
 	WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH,
 		     upper_32_bits(adev->vcn.gpu_addr + offset), 0xFFFFFFFF, 0);
 	WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_VCPU_CACHE_OFFSET1, 0,
 			     0xFFFFFFFF, 0);
-	WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_VCPU_CACHE_SIZE1, AMDGPU_VCN_HEAP_SIZE,
+	WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_VCPU_CACHE_SIZE1, AMDGPU_VCN_STACK_SIZE,
 			     0xFFFFFFFF, 0);
 
+	/* cache window 2: context */
 	WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW,
-		     lower_32_bits(adev->vcn.gpu_addr + offset + AMDGPU_VCN_HEAP_SIZE),
+		     lower_32_bits(adev->vcn.gpu_addr + offset + AMDGPU_VCN_STACK_SIZE),
 			     0xFFFFFFFF, 0);
 	WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH,
-		     upper_32_bits(adev->vcn.gpu_addr + offset + AMDGPU_VCN_HEAP_SIZE),
+		     upper_32_bits(adev->vcn.gpu_addr + offset + AMDGPU_VCN_STACK_SIZE),
 			     0xFFFFFFFF, 0);
 	WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_VCPU_CACHE_OFFSET2, 0, 0xFFFFFFFF, 0);
-	WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_VCPU_CACHE_SIZE2,
-			AMDGPU_VCN_STACK_SIZE + (AMDGPU_VCN_SESSION_SIZE * 40),
+	WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_VCPU_CACHE_SIZE2, AMDGPU_VCN_CONTEXT_SIZE,
 			     0xFFFFFFFF, 0);
 
 	WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_UDEC_ADDR_CONFIG,
@@ -601,8 +605,6 @@ static void vcn_v1_0_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t s
 		reg_data = 0 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
 	reg_data |= 1 << UVD_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
 	reg_data |= 4 << UVD_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
-	WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_CGC_CTRL, reg_data, 0xFFFFFFFF, sram_sel);
-
 	reg_data &= ~(UVD_CGC_CTRL__UDEC_RE_MODE_MASK |
 		 UVD_CGC_CTRL__UDEC_CM_MODE_MASK |
 		 UVD_CGC_CTRL__UDEC_IT_MODE_MASK |
@@ -812,12 +814,12 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev)
 
 		for (j = 0; j < 100; ++j) {
 			status = RREG32_SOC15(UVD, 0, mmUVD_STATUS);
-			if (status & 2)
+			if (status & UVD_STATUS__IDLE)
 				break;
 			mdelay(10);
 		}
 		r = 0;
-		if (status & 2)
+		if (status & UVD_STATUS__IDLE)
 			break;
 
 		DRM_ERROR("VCN decode not responding, trying to reset the VCPU!!!\n");
@@ -875,6 +877,8 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev)
 	/* Initialize the ring buffer's read and write pointers */
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR, 0);
 
+	WREG32_SOC15(UVD, 0, mmUVD_SCRATCH2, 0);
+
 	ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR);
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR,
 			lower_32_bits(ring->wptr));
@@ -898,12 +902,13 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev)
 
 	ring = &adev->vcn.ring_jpeg;
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, (0x00000001L | 0x00000002L));
+	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, UVD_JRBC_RB_CNTL__RB_NO_FETCH_MASK |
+			UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK);
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr));
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH, upper_32_bits(ring->gpu_addr));
 	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR, 0);
 	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, 0x00000002L);
+	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK);
 
 	/* initialize wptr */
 	ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
@@ -1051,6 +1056,8 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
 	/* Initialize the ring buffer's read and write pointers */
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR, 0);
 
+	WREG32_SOC15(UVD, 0, mmUVD_SCRATCH2, 0);
+
 	ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR);
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR,
 								lower_32_bits(ring->wptr));
@@ -1120,8 +1127,9 @@ static int vcn_v1_0_stop_dpg_mode(struct amdgpu_device *adev)
 {
 	int ret_code;
 
-	/* Wait for power status to be 1 */
-	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS, 0x1,
+	/* Wait for power status to be UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF */
+	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
+			UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF,
 			UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
 
 	/* disable dynamic power gating mode */
@@ -1147,7 +1155,7 @@ static bool vcn_v1_0_is_idle(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	return (RREG32_SOC15(VCN, 0, mmUVD_STATUS) == 0x2);
+	return (RREG32_SOC15(VCN, 0, mmUVD_STATUS) == UVD_STATUS__IDLE);
 }
 
 static int vcn_v1_0_wait_for_idle(void *handle)
@@ -1155,7 +1163,8 @@ static int vcn_v1_0_wait_for_idle(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int ret = 0;
 
-	SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_STATUS, 0x2, 0x2, ret);
+	SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_STATUS, UVD_STATUS__IDLE,
+		UVD_STATUS__IDLE, ret);
 
 	return ret;
 }
@@ -1217,6 +1226,10 @@ static void vcn_v1_0_dec_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		WREG32_SOC15(UVD, 0, mmUVD_SCRATCH2,
+			lower_32_bits(ring->wptr) | 0x80000000);
+
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr));
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 88b57a5e9489..07880d35e9de 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1596,16 +1596,18 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &vi_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v7_4_ip_block);
 		amdgpu_device_ip_block_add(adev, &iceland_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v2_4_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
-		amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &sdma_v2_4_ip_block);
 		break;
 	case CHIP_FIJI:
 		amdgpu_device_ip_block_add(adev, &vi_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v8_5_ip_block);
 		amdgpu_device_ip_block_add(adev, &tonga_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -1615,8 +1617,6 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 #endif
 		else
 			amdgpu_device_ip_block_add(adev, &dce_v10_1_ip_block);
-		amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		if (!amdgpu_sriov_vf(adev)) {
 			amdgpu_device_ip_block_add(adev, &uvd_v6_0_ip_block);
 			amdgpu_device_ip_block_add(adev, &vce_v3_0_ip_block);
@@ -1626,6 +1626,8 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &vi_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v8_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &tonga_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -1635,8 +1637,6 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 #endif
 		else
 			amdgpu_device_ip_block_add(adev, &dce_v10_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		if (!amdgpu_sriov_vf(adev)) {
 			amdgpu_device_ip_block_add(adev, &uvd_v5_0_ip_block);
 			amdgpu_device_ip_block_add(adev, &vce_v3_0_ip_block);
@@ -1649,6 +1649,8 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &vi_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v8_1_ip_block);
 		amdgpu_device_ip_block_add(adev, &tonga_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v3_1_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -1658,8 +1660,6 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 #endif
 		else
 			amdgpu_device_ip_block_add(adev, &dce_v11_2_ip_block);
-		amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &sdma_v3_1_ip_block);
 		amdgpu_device_ip_block_add(adev, &uvd_v6_3_ip_block);
 		amdgpu_device_ip_block_add(adev, &vce_v3_4_ip_block);
 		break;
@@ -1667,6 +1667,8 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &vi_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v8_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &cz_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -1676,8 +1678,6 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 #endif
 		else
 			amdgpu_device_ip_block_add(adev, &dce_v11_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &uvd_v6_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &vce_v3_1_ip_block);
 #if defined(CONFIG_DRM_AMD_ACP)
@@ -1688,6 +1688,8 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &vi_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v8_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &cz_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v8_1_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		if (adev->enable_virtual_display)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -1697,8 +1699,6 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 #endif
 		else
 			amdgpu_device_ip_block_add(adev, &dce_v11_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &gfx_v8_1_ip_block);
-		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &uvd_v6_2_ip_block);
 		amdgpu_device_ip_block_add(adev, &vce_v3_4_ip_block);
 #if defined(CONFIG_DRM_AMD_ACP)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index d6af31ccf0ee..a3b933967171 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -358,8 +358,8 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 					struct queue *q,
 					struct qcm_process_device *qpd)
 {
-	int retval;
 	struct mqd_manager *mqd_mgr;
+	int retval;
 
 	mqd_mgr = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_COMPUTE);
 	if (!mqd_mgr)
@@ -387,8 +387,12 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 	if (!q->properties.is_active)
 		return 0;
 
-	retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue,
-			&q->properties, q->process->mm);
+	if (WARN(q->process->mm != current->mm,
+		 "should only run in user thread"))
+		retval = -EFAULT;
+	else
+		retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue,
+					   &q->properties, current->mm);
 	if (retval)
 		goto out_uninit_mqd;
 
@@ -545,9 +549,15 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 		retval = map_queues_cpsch(dqm);
 	else if (q->properties.is_active &&
 		 (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
-		  q->properties.type == KFD_QUEUE_TYPE_SDMA))
-		retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue,
-				       &q->properties, q->process->mm);
+		  q->properties.type == KFD_QUEUE_TYPE_SDMA)) {
+		if (WARN(q->process->mm != current->mm,
+			 "should only run in user thread"))
+			retval = -EFAULT;
+		else
+			retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd,
+						   q->pipe, q->queue,
+						   &q->properties, current->mm);
+	}
 
 out_unlock:
 	dqm_unlock(dqm);
@@ -653,6 +663,7 @@ out:
 static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 					  struct qcm_process_device *qpd)
 {
+	struct mm_struct *mm = NULL;
 	struct queue *q;
 	struct mqd_manager *mqd_mgr;
 	struct kfd_process_device *pdd;
@@ -686,6 +697,15 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 		kfd_flush_tlb(pdd);
 	}
 
+	/* Take a safe reference to the mm_struct, which may otherwise
+	 * disappear even while the kfd_process is still referenced.
+	 */
+	mm = get_task_mm(pdd->process->lead_thread);
+	if (!mm) {
+		retval = -EFAULT;
+		goto out;
+	}
+
 	/* activate all active queues on the qpd */
 	list_for_each_entry(q, &qpd->queues_list, list) {
 		if (!q->properties.is_evicted)
@@ -700,14 +720,15 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 		q->properties.is_evicted = false;
 		q->properties.is_active = true;
 		retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe,
-				       q->queue, &q->properties,
-				       q->process->mm);
+				       q->queue, &q->properties, mm);
 		if (retval)
 			goto out;
 		dqm->queue_count++;
 	}
 	qpd->evicted = 0;
 out:
+	if (mm)
+		mmput(mm);
 	dqm_unlock(dqm);
 	return retval;
 }
@@ -1343,9 +1364,6 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 {
 	int retval;
 	struct mqd_manager *mqd_mgr;
-	bool preempt_all_queues;
-
-	preempt_all_queues = false;
 
 	retval = 0;
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 6a2342d72742..e224f23e2215 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4740,12 +4740,18 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 	}
 	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
 
-	/* Signal HW programming completion */
-	drm_atomic_helper_commit_hw_done(state);
 
 	if (wait_for_vblank)
 		drm_atomic_helper_wait_for_flip_done(dev, state);
 
+	/*
+	 * FIXME:
+	 * Delay hw_done() until flip_done() is signaled. This is to block
+	 * another commit from freeing the CRTC state while we're still
+	 * waiting on flip_done.
+	 */
+	drm_atomic_helper_commit_hw_done(state);
+
 	drm_atomic_helper_cleanup_planes(dev, state);
 
 	/*
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index a910f01838ab..a212178f2edc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -36,17 +36,13 @@
  * Private declarations.
  *****************************************************************************/
 
-struct handler_common_data {
+struct amdgpu_dm_irq_handler_data {
 	struct list_head list;
 	interrupt_handler handler;
 	void *handler_arg;
 
 	/* DM which this handler belongs to */
 	struct amdgpu_display_manager *dm;
-};
-
-struct amdgpu_dm_irq_handler_data {
-	struct handler_common_data hcd;
 	/* DAL irq source which registered for this interrupt. */
 	enum dc_irq_source irq_source;
 };
@@ -61,7 +57,7 @@ struct amdgpu_dm_irq_handler_data {
  * Private functions.
  *****************************************************************************/
 
-static void init_handler_common_data(struct handler_common_data *hcd,
+static void init_handler_common_data(struct amdgpu_dm_irq_handler_data *hcd,
 				     void (*ih)(void *),
 				     void *args,
 				     struct amdgpu_display_manager *dm)
@@ -85,11 +81,9 @@ static void dm_irq_work_func(struct work_struct *work)
 	struct amdgpu_dm_irq_handler_data *handler_data;
 
 	list_for_each(entry, handler_list) {
-		handler_data =
-			list_entry(
-				entry,
-				struct amdgpu_dm_irq_handler_data,
-				hcd.list);
+		handler_data = list_entry(entry,
+					  struct amdgpu_dm_irq_handler_data,
+					  list);
 
 		DRM_DEBUG_KMS("DM_IRQ: work_func: for dal_src=%d\n",
 				handler_data->irq_source);
@@ -97,7 +91,7 @@ static void dm_irq_work_func(struct work_struct *work)
 		DRM_DEBUG_KMS("DM_IRQ: schedule_work: for dal_src=%d\n",
 			handler_data->irq_source);
 
-		handler_data->hcd.handler(handler_data->hcd.handler_arg);
+		handler_data->handler(handler_data->handler_arg);
 	}
 
 	/* Call a DAL subcomponent which registered for interrupt notification
@@ -137,11 +131,11 @@ static struct list_head *remove_irq_handler(struct amdgpu_device *adev,
 	list_for_each_safe(entry, tmp, hnd_list) {
 
 		handler = list_entry(entry, struct amdgpu_dm_irq_handler_data,
-				hcd.list);
+				     list);
 
 		if (ih == handler) {
 			/* Found our handler. Remove it from the list. */
-			list_del(&handler->hcd.list);
+			list_del(&handler->list);
 			handler_removed = true;
 			break;
 		}
@@ -230,8 +224,7 @@ void *amdgpu_dm_irq_register_interrupt(struct amdgpu_device *adev,
 
 	memset(handler_data, 0, sizeof(*handler_data));
 
-	init_handler_common_data(&handler_data->hcd, ih, handler_args,
-			&adev->dm);
+	init_handler_common_data(handler_data, ih, handler_args, &adev->dm);
 
 	irq_source = int_params->irq_source;
 
@@ -250,7 +243,7 @@ void *amdgpu_dm_irq_register_interrupt(struct amdgpu_device *adev,
 		break;
 	}
 
-	list_add_tail(&handler_data->hcd.list, hnd_list);
+	list_add_tail(&handler_data->list, hnd_list);
 
 	DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags);
 
@@ -462,15 +455,13 @@ static void amdgpu_dm_irq_immediate_work(struct amdgpu_device *adev,
 		entry,
 		&adev->dm.irq_handler_list_high_tab[irq_source]) {
 
-		handler_data =
-			list_entry(
-				entry,
-				struct amdgpu_dm_irq_handler_data,
-				hcd.list);
+		handler_data = list_entry(entry,
+					  struct amdgpu_dm_irq_handler_data,
+					  list);
 
 		/* Call a subcomponent which registered for immediate
 		 * interrupt notification */
-		handler_data->hcd.handler(handler_data->hcd.handler_arg);
+		handler_data->handler(handler_data->handler_arg);
 	}
 
 	DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 76fe5a9af3bf..7c491c91465f 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -60,6 +60,7 @@
 #define DC_LOGGER \
 	dc->ctx->logger
 
+const static char DC_BUILD_ID[] = "production-build";
 
 /*******************************************************************************
  * Private functions
@@ -758,6 +759,8 @@ struct dc *dc_create(const struct dc_init_data *init_params)
 
 	dc->config = init_params->flags;
 
+	dc->build_id = DC_BUILD_ID;
+
 	DC_LOG_DC("Display Core initialized\n");
 
 
@@ -1110,32 +1113,6 @@ static bool is_surface_in_context(
 	return false;
 }
 
-static unsigned int pixel_format_to_bpp(enum surface_pixel_format format)
-{
-	switch (format) {
-	case SURFACE_PIXEL_FORMAT_VIDEO_420_YCbCr:
-	case SURFACE_PIXEL_FORMAT_VIDEO_420_YCrCb:
-		return 12;
-	case SURFACE_PIXEL_FORMAT_GRPH_ARGB1555:
-	case SURFACE_PIXEL_FORMAT_GRPH_RGB565:
-	case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr:
-	case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb:
-		return 16;
-	case SURFACE_PIXEL_FORMAT_GRPH_ARGB8888:
-	case SURFACE_PIXEL_FORMAT_GRPH_ABGR8888:
-	case SURFACE_PIXEL_FORMAT_GRPH_ARGB2101010:
-	case SURFACE_PIXEL_FORMAT_GRPH_ABGR2101010:
-		return 32;
-	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
-	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F:
-	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F:
-		return 64;
-	default:
-		ASSERT_CRITICAL(false);
-		return -1;
-	}
-}
-
 static enum surface_update_type get_plane_info_update_type(const struct dc_surface_update *u)
 {
 	union surface_update_flags *update_flags = &u->surface->update_flags;
@@ -1169,8 +1146,8 @@ static enum surface_update_type get_plane_info_update_type(const struct dc_surfa
 			|| u->plane_info->dcc.grph.meta_pitch != u->surface->dcc.grph.meta_pitch)
 		update_flags->bits.dcc_change = 1;
 
-	if (pixel_format_to_bpp(u->plane_info->format) !=
-			pixel_format_to_bpp(u->surface->format))
+	if (resource_pixel_format_to_bpp(u->plane_info->format) !=
+			resource_pixel_format_to_bpp(u->surface->format))
 		/* different bytes per element will require full bandwidth
 		 * and DML calculation
 		 */
@@ -1859,3 +1836,16 @@ void dc_link_remove_remote_sink(struct dc_link *link, struct dc_sink *sink)
 		}
 	}
 }
+
+void get_clock_requirements_for_state(struct dc_state *state, struct AsicStateEx *info)
+{
+	info->displayClock				= (unsigned int)state->bw.dcn.clk.dispclk_khz;
+	info->engineClock				= (unsigned int)state->bw.dcn.clk.dcfclk_khz;
+	info->memoryClock				= (unsigned int)state->bw.dcn.clk.dramclk_khz;
+	info->maxSupportedDppClock		= (unsigned int)state->bw.dcn.clk.max_supported_dppclk_khz;
+	info->dppClock					= (unsigned int)state->bw.dcn.clk.dppclk_khz;
+	info->socClock					= (unsigned int)state->bw.dcn.clk.socclk_khz;
+	info->dcfClockDeepSleep			= (unsigned int)state->bw.dcn.clk.dcfclk_deep_sleep_khz;
+	info->fClock					= (unsigned int)state->bw.dcn.clk.fclk_khz;
+	info->phyClock					= (unsigned int)state->bw.dcn.clk.phyclk_khz;
+}
\ No newline at end of file
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 2d6a4300bfa4..b6fe29b9fb65 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1975,6 +1975,9 @@ static void calculate_phy_pix_clks(struct dc_stream_state *stream)
 	else
 		stream->phy_pix_clk =
 			stream->timing.pix_clk_khz;
+
+	if (stream->timing.timing_3d_format == TIMING_3D_FORMAT_HW_FRAME_PACKING)
+		stream->phy_pix_clk *= 2;
 }
 
 enum dc_status resource_map_pool_resources(
@@ -2096,6 +2099,14 @@ enum dc_status dc_validate_global_state(
 			if (pipe_ctx->stream != stream)
 				continue;
 
+			if (dc->res_pool->funcs->get_default_swizzle_mode &&
+					pipe_ctx->plane_state &&
+					pipe_ctx->plane_state->tiling_info.gfx9.swizzle == DC_SW_UNKNOWN) {
+				result = dc->res_pool->funcs->get_default_swizzle_mode(pipe_ctx->plane_state);
+				if (result != DC_OK)
+					return result;
+			}
+
 			/* Switch to dp clock source only if there is
 			 * no non dp stream that shares the same timing
 			 * with the dp stream.
@@ -2885,3 +2896,32 @@ enum dc_status dc_validate_plane(struct dc *dc, const struct dc_plane_state *pla
 
 	return res;
 }
+
+unsigned int resource_pixel_format_to_bpp(enum surface_pixel_format format)
+{
+	switch (format) {
+	case SURFACE_PIXEL_FORMAT_GRPH_PALETA_256_COLORS:
+		return 8;
+	case SURFACE_PIXEL_FORMAT_VIDEO_420_YCbCr:
+	case SURFACE_PIXEL_FORMAT_VIDEO_420_YCrCb:
+		return 12;
+	case SURFACE_PIXEL_FORMAT_GRPH_ARGB1555:
+	case SURFACE_PIXEL_FORMAT_GRPH_RGB565:
+	case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr:
+	case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb:
+		return 16;
+	case SURFACE_PIXEL_FORMAT_GRPH_ARGB8888:
+	case SURFACE_PIXEL_FORMAT_GRPH_ABGR8888:
+	case SURFACE_PIXEL_FORMAT_GRPH_ARGB2101010:
+	case SURFACE_PIXEL_FORMAT_GRPH_ABGR2101010:
+	case SURFACE_PIXEL_FORMAT_GRPH_ABGR2101010_XR_BIAS:
+		return 32;
+	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
+	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F:
+	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F:
+		return 64;
+	default:
+		ASSERT_CRITICAL(false);
+		return -1;
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 11ea2a226952..199527171100 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,13 +38,12 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.67"
+#define DC_VER "3.1.68"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
 #define MAX_SINKS_PER_LINK 4
 
-
 /*******************************************************************************
  * Display Core Interfaces
  ******************************************************************************/
@@ -208,6 +207,7 @@ struct dc_clocks {
 	int dcfclk_deep_sleep_khz;
 	int fclk_khz;
 	int phyclk_khz;
+	int dramclk_khz;
 };
 
 struct dc_debug_options {
@@ -315,6 +315,8 @@ struct dc {
 	struct compressor *fbc_compressor;
 
 	struct dc_debug_data debug_data;
+
+	const char *build_id;
 };
 
 enum frame_buffer_mode {
@@ -599,6 +601,8 @@ struct dc_validation_set {
 
 enum dc_status dc_validate_plane(struct dc *dc, const struct dc_plane_state *plane_state);
 
+void get_clock_requirements_for_state(struct dc_state *state, struct AsicStateEx *info);
+
 enum dc_status dc_validate_global_state(
 		struct dc *dc,
 		struct dc_state *new_ctx);
diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index 57f57cf0fe2a..7825e4b5e97c 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -289,7 +289,8 @@ enum swizzle_mode_values {
 	DC_SW_VAR_S_X = 29,
 	DC_SW_VAR_D_X = 30,
 	DC_SW_VAR_R_X = 31,
-	DC_SW_MAX
+	DC_SW_MAX = 32,
+	DC_SW_UNKNOWN = DC_SW_MAX
 };
 
 union dc_tiling_info {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 4fb62780a696..6e12d640d020 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -659,4 +659,16 @@ enum i2c_mot_mode {
 	I2C_MOT_FALSE
 };
 
+struct AsicStateEx {
+	unsigned int memoryClock;
+	unsigned int displayClock;
+	unsigned int engineClock;
+	unsigned int maxSupportedDppClock;
+	unsigned int dppClock;
+	unsigned int socClock;
+	unsigned int dcfClockDeepSleep;
+	unsigned int fClock;
+	unsigned int phyClock;
+};
+
 #endif /* DC_TYPES_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
index 3f5b2e6f7553..aaeb7faac0c4 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -312,7 +312,7 @@ static void process_channel_reply(
 
 	/* in case HPD is LOW, exit AUX transaction */
 	if ((sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
-		reply->status = AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON;
+		reply->status = AUX_TRANSACTION_REPLY_HPD_DISCON;
 		return;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index d42afa081452..d89a097ba936 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -664,6 +664,11 @@ static void dce_update_clocks(struct dccg *dccg,
 			bool safe_to_lower)
 {
 	struct dm_pp_power_level_change_request level_change_req;
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(dccg);
+
+	/* TODO: Investigate why this is needed to fix display corruption. */
+	if (!clk_dce->dfs_bypass_active)
+		new_clocks->dispclk_khz = new_clocks->dispclk_khz * 115 / 100;
 
 	level_change_req.power_level = dce_get_required_clocks_state(dccg, new_clocks);
 	/* get max clock state from PPLIB */
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
index 4942590e8b9c..366bc8c2c643 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
@@ -662,21 +662,10 @@ bool dce110_link_encoder_validate_dp_output(
 	const struct dce110_link_encoder *enc110,
 	const struct dc_crtc_timing *crtc_timing)
 {
-	/* default RGB only */
-	if (crtc_timing->pixel_encoding == PIXEL_ENCODING_RGB)
-		return true;
+	if (crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+		return false;
 
-	if (enc110->base.features.flags.bits.IS_YCBCR_CAPABLE)
-		return true;
-
-	/* for DCE 8.x or later DP Y-only feature,
-	 * we need ASIC cap + FeatureSupportDPYonly, not support 666 */
-	if (crtc_timing->flags.Y_ONLY &&
-		enc110->base.features.flags.bits.IS_YCBCR_CAPABLE &&
-		crtc_timing->display_color_depth != COLOR_DEPTH_666)
-		return true;
-
-	return false;
+	return true;
 }
 
 void dce110_link_encoder_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index b1cc38827f09..14754a87156c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -551,8 +551,7 @@ static const struct encoder_feature_support link_enc_feature = {
 		.max_hdmi_deep_color = COLOR_DEPTH_121212,
 		.max_hdmi_pixel_clock = 300000,
 		.flags.bits.IS_HBR2_CAPABLE = true,
-		.flags.bits.IS_TPS3_CAPABLE = true,
-		.flags.bits.IS_YCBCR_CAPABLE = true
+		.flags.bits.IS_TPS3_CAPABLE = true
 };
 
 struct link_encoder *dce100_link_encoder_create(
@@ -690,7 +689,9 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+	}
 
+	for (i = 0; i < pool->base.res_cap->num_ddc; i++) {
 		if (pool->base.engines[i] != NULL)
 			dce110_engine_destroy(&pool->base.engines[i]);
 		if (pool->base.hw_i2cs[i] != NULL) {
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index b44cc7042249..de190935f0a4 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -570,8 +570,7 @@ static const struct encoder_feature_support link_enc_feature = {
 		.max_hdmi_deep_color = COLOR_DEPTH_121212,
 		.max_hdmi_pixel_clock = 594000,
 		.flags.bits.IS_HBR2_CAPABLE = true,
-		.flags.bits.IS_TPS3_CAPABLE = true,
-		.flags.bits.IS_YCBCR_CAPABLE = true
+		.flags.bits.IS_TPS3_CAPABLE = true
 };
 
 static struct link_encoder *dce110_link_encoder_create(
@@ -720,7 +719,9 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+	}
 
+	for (i = 0; i < pool->base.res_cap->num_ddc; i++) {
 		if (pool->base.engines[i] != NULL)
 			dce110_engine_destroy(&pool->base.engines[i]);
 		if (pool->base.hw_i2cs[i] != NULL) {
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 0f8332ea1160..3ce79c208ddf 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -555,8 +555,7 @@ static const struct encoder_feature_support link_enc_feature = {
 		.flags.bits.IS_HBR2_CAPABLE = true,
 		.flags.bits.IS_HBR3_CAPABLE = true,
 		.flags.bits.IS_TPS3_CAPABLE = true,
-		.flags.bits.IS_TPS4_CAPABLE = true,
-		.flags.bits.IS_YCBCR_CAPABLE = true
+		.flags.bits.IS_TPS4_CAPABLE = true
 };
 
 struct link_encoder *dce112_link_encoder_create(
@@ -694,9 +693,6 @@ static void destruct(struct dce110_resource_pool *pool)
 		if (pool->base.opps[i] != NULL)
 			dce110_opp_destroy(&pool->base.opps[i]);
 
-		if (pool->base.engines[i] != NULL)
-			dce110_engine_destroy(&pool->base.engines[i]);
-
 		if (pool->base.transforms[i] != NULL)
 			dce112_transform_destroy(&pool->base.transforms[i]);
 
@@ -712,6 +708,11 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+	}
+
+	for (i = 0; i < pool->base.res_cap->num_ddc; i++) {
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
 		if (pool->base.hw_i2cs[i] != NULL) {
 			kfree(pool->base.hw_i2cs[i]);
 			pool->base.hw_i2cs[i] = NULL;
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index 59055801af44..79ab5f9f9115 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -533,7 +533,9 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+	}
 
+	for (i = 0; i < pool->base.res_cap->num_ddc; i++) {
 		if (pool->base.engines[i] != NULL)
 			dce110_engine_destroy(&pool->base.engines[i]);
 		if (pool->base.hw_i2cs[i] != NULL) {
@@ -609,7 +611,6 @@ static const struct encoder_feature_support link_enc_feature = {
 		.flags.bits.IS_HBR3_CAPABLE = true,
 		.flags.bits.IS_TPS3_CAPABLE = true,
 		.flags.bits.IS_TPS4_CAPABLE = true,
-		.flags.bits.IS_YCBCR_CAPABLE = true
 };
 
 static struct link_encoder *dce120_link_encoder_create(
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index 1dc590ccc5f9..d68f951f9869 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -650,8 +650,7 @@ static const struct encoder_feature_support link_enc_feature = {
 		.max_hdmi_deep_color = COLOR_DEPTH_121212,
 		.max_hdmi_pixel_clock = 297000,
 		.flags.bits.IS_HBR2_CAPABLE = true,
-		.flags.bits.IS_TPS3_CAPABLE = true,
-		.flags.bits.IS_YCBCR_CAPABLE = true
+		.flags.bits.IS_TPS3_CAPABLE = true
 };
 
 struct link_encoder *dce80_link_encoder_create(
@@ -739,7 +738,9 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+	}
 
+	for (i = 0; i < pool->base.res_cap->num_ddc; i++) {
 		if (pool->base.engines[i] != NULL)
 			dce110_engine_destroy(&pool->base.engines[i]);
 		if (pool->base.hw_i2cs[i] != NULL) {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
index 1ea91e153d3a..4254e7e1a509 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
@@ -87,6 +87,23 @@ void hubbub1_wm_read_state(struct hubbub *hubbub,
 	s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D);
 }
 
+void hubbub1_disable_allow_self_refresh(struct hubbub *hubbub)
+{
+	REG_UPDATE(DCHUBBUB_ARB_DRAM_STATE_CNTL,
+			DCHUBBUB_ARB_ALLOW_SELF_REFRESH_FORCE_ENABLE, 0);
+}
+
+bool hububu1_is_allow_self_refresh_enabled(struct hubbub *hubbub)
+{
+	uint32_t enable = 0;
+
+	REG_GET(DCHUBBUB_ARB_DRAM_STATE_CNTL,
+			DCHUBBUB_ARB_ALLOW_SELF_REFRESH_FORCE_ENABLE, &enable);
+
+	return true ? false : enable;
+}
+
+
 bool hubbub1_verify_allow_pstate_change_high(
 	struct hubbub *hubbub)
 {
@@ -116,7 +133,43 @@ bool hubbub1_verify_allow_pstate_change_high(
 		forced_pstate_allow = false;
 	}
 
-	/* RV1:
+	/* RV2:
+	 * dchubbubdebugind, at: 0xB
+	 * description
+	 * 0:     Pipe0 Plane0 Allow Pstate Change
+	 * 1:     Pipe0 Plane1 Allow Pstate Change
+	 * 2:     Pipe0 Cursor0 Allow Pstate Change
+	 * 3:     Pipe0 Cursor1 Allow Pstate Change
+	 * 4:     Pipe1 Plane0 Allow Pstate Change
+	 * 5:     Pipe1 Plane1 Allow Pstate Change
+	 * 6:     Pipe1 Cursor0 Allow Pstate Change
+	 * 7:     Pipe1 Cursor1 Allow Pstate Change
+	 * 8:     Pipe2 Plane0 Allow Pstate Change
+	 * 9:     Pipe2 Plane1 Allow Pstate Change
+	 * 10:    Pipe2 Cursor0 Allow Pstate Change
+	 * 11:    Pipe2 Cursor1 Allow Pstate Change
+	 * 12:    Pipe3 Plane0 Allow Pstate Change
+	 * 13:    Pipe3 Plane1 Allow Pstate Change
+	 * 14:    Pipe3 Cursor0 Allow Pstate Change
+	 * 15:    Pipe3 Cursor1 Allow Pstate Change
+	 * 16:    Pipe4 Plane0 Allow Pstate Change
+	 * 17:    Pipe4 Plane1 Allow Pstate Change
+	 * 18:    Pipe4 Cursor0 Allow Pstate Change
+	 * 19:    Pipe4 Cursor1 Allow Pstate Change
+	 * 20:    Pipe5 Plane0 Allow Pstate Change
+	 * 21:    Pipe5 Plane1 Allow Pstate Change
+	 * 22:    Pipe5 Cursor0 Allow Pstate Change
+	 * 23:    Pipe5 Cursor1 Allow Pstate Change
+	 * 24:    Pipe6 Plane0 Allow Pstate Change
+	 * 25:    Pipe6 Plane1 Allow Pstate Change
+	 * 26:    Pipe6 Cursor0 Allow Pstate Change
+	 * 27:    Pipe6 Cursor1 Allow Pstate Change
+	 * 28:    WB0 Allow Pstate Change
+	 * 29:    WB1 Allow Pstate Change
+	 * 30:    Arbiter's allow_pstate_change
+	 * 31:    SOC pstate change request"
+	 *
+	 * RV1:
 	 * dchubbubdebugind, at: 0x7
 	 * description "3-0:   Pipe0 cursor0 QOS
 	 * 7-4:   Pipe1 cursor0 QOS
@@ -140,7 +193,6 @@ bool hubbub1_verify_allow_pstate_change_high(
 	 * 31:    SOC pstate change request
 	 */
 
-
 	REG_WRITE(DCHUBBUB_TEST_DEBUG_INDEX, hubbub->debug_test_index_pstate);
 
 	for (i = 0; i < pstate_wait_timeout_us; i++) {
@@ -802,5 +854,9 @@ void hubbub1_construct(struct hubbub *hubbub,
 	hubbub->masks = hubbub_mask;
 
 	hubbub->debug_test_index_pstate = 0x7;
+#if defined(CONFIG_DRM_AMD_DC_DCN1_01)
+	if (ctx->dce_version == DCN_VERSION_1_01)
+		hubbub->debug_test_index_pstate = 0xB;
+#endif
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
index d6e596eef4c5..d0f03d152913 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
@@ -203,6 +203,10 @@ void hubbub1_program_watermarks(
 		unsigned int refclk_mhz,
 		bool safe_to_lower);
 
+void hubbub1_disable_allow_self_refresh(struct hubbub *hubbub);
+
+bool hububu1_is_allow_self_refresh_enabled(struct hubbub *hubub);
+
 void hubbub1_toggle_watermark_change_req(
 		struct hubbub *hubbub);
 
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 a881ff5559ec..193184affefb 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
@@ -997,7 +997,21 @@ static void dcn10_init_hw(struct dc *dc)
 	} else {
 
 		if (!dcb->funcs->is_accelerated_mode(dcb)) {
+			bool allow_self_fresh_force_enable =
+					hububu1_is_allow_self_refresh_enabled(dc->res_pool->hubbub);
+
 			bios_golden_init(dc);
+
+			/* WA for making DF sleep when idle after resume from S0i3.
+			 * DCHUBBUB_ARB_ALLOW_SELF_REFRESH_FORCE_ENABLE is set to 1 by
+			 * command table, if DCHUBBUB_ARB_ALLOW_SELF_REFRESH_FORCE_ENABLE = 0
+			 * before calling command table and it changed to 1 after,
+			 * it should be set back to 0.
+			 */
+			if (allow_self_fresh_force_enable == false &&
+					hububu1_is_allow_self_refresh_enabled(dc->res_pool->hubbub))
+				hubbub1_disable_allow_self_refresh(dc->res_pool->hubbub);
+
 			disable_vga(dc->hwseq);
 		}
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
index 6f675206a136..ba6a8686062f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
@@ -606,22 +606,10 @@ bool dcn10_link_encoder_validate_dp_output(
 	const struct dcn10_link_encoder *enc10,
 	const struct dc_crtc_timing *crtc_timing)
 {
-	/* default RGB only */
-	if (crtc_timing->pixel_encoding == PIXEL_ENCODING_RGB)
-		return true;
+	if (crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+		return false;
 
-	if (enc10->base.features.flags.bits.IS_YCBCR_CAPABLE)
-		return true;
-
-	/* for DCE 8.x or later DP Y-only feature,
-	 * we need ASIC cap + FeatureSupportDPYonly, not support 666
-	 */
-	if (crtc_timing->flags.Y_ONLY &&
-		enc10->base.features.flags.bits.IS_YCBCR_CAPABLE &&
-		crtc_timing->display_color_depth != COLOR_DEPTH_666)
-		return true;
-
-	return false;
+	return true;
 }
 
 void dcn10_link_encoder_construct(
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 411f89218e01..54626682bab2 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
@@ -98,7 +98,6 @@ static uint32_t get_start_vline(struct timing_generator *optc, const struct dc_c
 	struct dc_crtc_timing patched_crtc_timing;
 	int vesa_sync_start;
 	int asic_blank_end;
-	int interlace_factor;
 	int vertical_line_start;
 
 	patched_crtc_timing = *dc_crtc_timing;
@@ -112,16 +111,13 @@ static uint32_t get_start_vline(struct timing_generator *optc, const struct dc_c
 			vesa_sync_start -
 			patched_crtc_timing.h_border_left;
 
-	interlace_factor = patched_crtc_timing.flags.INTERLACE ? 2 : 1;
-
 	vesa_sync_start = patched_crtc_timing.v_addressable +
 			patched_crtc_timing.v_border_bottom +
 			patched_crtc_timing.v_front_porch;
 
 	asic_blank_end = (patched_crtc_timing.v_total -
 			vesa_sync_start -
-			patched_crtc_timing.v_border_top)
-			* interlace_factor;
+			patched_crtc_timing.v_border_top);
 
 	vertical_line_start = asic_blank_end - optc->dlg_otg_param.vstartup_start + 1;
 	if (vertical_line_start < 0) {
@@ -154,7 +150,7 @@ void optc1_program_vline_interrupt(
 		req_delta_lines--;
 
 	if (req_delta_lines > vsync_line)
-		start_line = dc_crtc_timing->v_total - (req_delta_lines - vsync_line) - 1;
+		start_line = dc_crtc_timing->v_total - (req_delta_lines - vsync_line) + 2;
 	else
 		start_line = vsync_line - req_delta_lines;
 
@@ -186,7 +182,6 @@ void optc1_program_timing(
 	uint32_t v_sync_end;
 	uint32_t v_init, v_fp2;
 	uint32_t h_sync_polarity, v_sync_polarity;
-	uint32_t interlace_factor;
 	uint32_t start_point = 0;
 	uint32_t field_num = 0;
 	uint32_t h_div_2;
@@ -237,16 +232,8 @@ void optc1_program_timing(
 	REG_UPDATE(OTG_H_SYNC_A_CNTL,
 			OTG_H_SYNC_A_POL, h_sync_polarity);
 
-	/* Load vertical timing */
+	v_total = patched_crtc_timing.v_total - 1;
 
-	/* CRTC_V_TOTAL = v_total - 1 */
-	if (patched_crtc_timing.flags.INTERLACE) {
-		interlace_factor = 2;
-		v_total = 2 * patched_crtc_timing.v_total;
-	} else {
-		interlace_factor = 1;
-		v_total = patched_crtc_timing.v_total - 1;
-	}
 	REG_SET(OTG_V_TOTAL, 0,
 			OTG_V_TOTAL, v_total);
 
@@ -259,7 +246,7 @@ void optc1_program_timing(
 		OTG_V_TOTAL_MIN, v_total);
 
 	/* v_sync_start = 0, v_sync_end = v_sync_width */
-	v_sync_end = patched_crtc_timing.v_sync_width * interlace_factor;
+	v_sync_end = patched_crtc_timing.v_sync_width;
 
 	REG_UPDATE_2(OTG_V_SYNC_A,
 			OTG_V_SYNC_A_START, 0,
@@ -271,15 +258,13 @@ void optc1_program_timing(
 
 	asic_blank_end = (patched_crtc_timing.v_total -
 			vesa_sync_start -
-			patched_crtc_timing.v_border_top)
-			* interlace_factor;
+			patched_crtc_timing.v_border_top);
 
 	/* v_blank_start = v_blank_end + v_active */
 	asic_blank_start = asic_blank_end +
 			(patched_crtc_timing.v_border_top +
 			patched_crtc_timing.v_addressable +
-			patched_crtc_timing.v_border_bottom)
-			* interlace_factor;
+			patched_crtc_timing.v_border_bottom);
 
 	REG_UPDATE_2(OTG_V_BLANK_START_END,
 			OTG_V_BLANK_START, asic_blank_start,
@@ -301,7 +286,7 @@ void optc1_program_timing(
 			0 : 1;
 
 	REG_UPDATE(OTG_V_SYNC_A_CNTL,
-			OTG_V_SYNC_A_POL, v_sync_polarity);
+		OTG_V_SYNC_A_POL, v_sync_polarity);
 
 	v_init = asic_blank_start;
 	if (optc->dlg_otg_param.signal == SIGNAL_TYPE_DISPLAY_PORT ||
@@ -532,7 +517,6 @@ bool optc1_validate_timing(
 	struct timing_generator *optc,
 	const struct dc_crtc_timing *timing)
 {
-	uint32_t interlace_factor;
 	uint32_t v_blank;
 	uint32_t h_blank;
 	uint32_t min_v_blank;
@@ -540,10 +524,8 @@ bool optc1_validate_timing(
 
 	ASSERT(timing != NULL);
 
-	interlace_factor = timing->flags.INTERLACE ? 2 : 1;
 	v_blank = (timing->v_total - timing->v_addressable -
-					timing->v_border_top - timing->v_border_bottom) *
-					interlace_factor;
+					timing->v_border_top - timing->v_border_bottom);
 
 	h_blank = (timing->h_total - timing->h_addressable -
 		timing->h_border_right -
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index cb1b134b8fcb..a71453a15ae3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -507,6 +507,18 @@ static const struct resource_caps res_cap = {
 		.num_ddc = 4,
 };
 
+#if defined(CONFIG_DRM_AMD_DC_DCN1_01)
+static const struct resource_caps rv2_res_cap = {
+		.num_timing_generator = 3,
+		.num_opp = 3,
+		.num_video_plane = 3,
+		.num_audio = 3,
+		.num_stream_encoder = 3,
+		.num_pll = 3,
+		.num_ddc = 3,
+};
+#endif
+
 static const struct dc_debug_options debug_defaults_drv = {
 		.sanity_checks = true,
 		.disable_dmcu = true,
@@ -711,8 +723,7 @@ static const struct encoder_feature_support link_enc_feature = {
 		.flags.bits.IS_HBR2_CAPABLE = true,
 		.flags.bits.IS_HBR3_CAPABLE = true,
 		.flags.bits.IS_TPS3_CAPABLE = true,
-		.flags.bits.IS_TPS4_CAPABLE = true,
-		.flags.bits.IS_YCBCR_CAPABLE = true
+		.flags.bits.IS_TPS4_CAPABLE = true
 };
 
 struct link_encoder *dcn10_link_encoder_create(
@@ -897,7 +908,9 @@ static void destruct(struct dcn10_resource_pool *pool)
 			kfree(DCN10TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+	}
 
+	for (i = 0; i < pool->base.res_cap->num_ddc; i++) {
 		if (pool->base.engines[i] != NULL)
 			pool->base.engines[i]->funcs->destroy_engine(&pool->base.engines[i]);
 		if (pool->base.hw_i2cs[i] != NULL) {
@@ -1119,6 +1132,24 @@ static enum dc_status dcn10_validate_plane(const struct dc_plane_state *plane_st
 	return DC_OK;
 }
 
+static enum dc_status dcn10_get_default_swizzle_mode(struct dc_plane_state *plane_state)
+{
+	enum dc_status result = DC_OK;
+
+	enum surface_pixel_format surf_pix_format = plane_state->format;
+	unsigned int bpp = resource_pixel_format_to_bpp(surf_pix_format);
+
+	enum swizzle_mode_values swizzle = DC_SW_LINEAR;
+
+	if (bpp == 64)
+		swizzle = DC_SW_64KB_D;
+	else
+		swizzle = DC_SW_64KB_S;
+
+	plane_state->tiling_info.gfx9.swizzle = swizzle;
+	return result;
+}
+
 static const struct dc_cap_funcs cap_funcs = {
 	.get_dcc_compression_cap = dcn10_get_dcc_compression_cap
 };
@@ -1129,7 +1160,8 @@ static const struct resource_funcs dcn10_res_pool_funcs = {
 	.validate_bandwidth = dcn_validate_bandwidth,
 	.acquire_idle_pipe_for_layer = dcn10_acquire_idle_pipe_for_layer,
 	.validate_plane = dcn10_validate_plane,
-	.add_stream_to_ctx = dcn10_add_stream_to_ctx
+	.add_stream_to_ctx = dcn10_add_stream_to_ctx,
+	.get_default_swizzle_mode = dcn10_get_default_swizzle_mode
 };
 
 static uint32_t read_pipe_fuses(struct dc_context *ctx)
@@ -1152,7 +1184,12 @@ static bool construct(
 
 	ctx->dc_bios->regs = &bios_regs;
 
-	pool->base.res_cap = &res_cap;
+#if defined(CONFIG_DRM_AMD_DC_DCN1_01)
+	if (ctx->dce_version == DCN_VERSION_1_01)
+		pool->base.res_cap = &rv2_res_cap;
+	else
+#endif
+		pool->base.res_cap = &res_cap;
 	pool->base.funcs = &dcn10_res_pool_funcs;
 
 	/*
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
index 8eee8ace1259..59c3ed43d609 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
@@ -346,7 +346,7 @@ static void process_channel_reply(
 
 	/* in case HPD is LOW, exit AUX transaction */
 	if ((sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
-		reply->status = AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON;
+		reply->status = AUX_TRANSACTION_REPLY_HPD_DISCON;
 		return;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index 831a1bdf622c..c1976c175b57 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -120,6 +120,9 @@ struct resource_funcs {
 				struct dc *dc,
 				struct dc_state *new_ctx,
 				struct dc_stream_state *stream);
+	enum dc_status (*get_default_swizzle_mode)(
+			struct dc_plane_state *plane_state);
+
 };
 
 struct audio_support{
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
index 58818920ed41..e28e9770e0a3 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
@@ -58,7 +58,6 @@ struct encoder_feature_support {
 			uint32_t IS_HBR3_CAPABLE:1;
 			uint32_t IS_TPS3_CAPABLE:1;
 			uint32_t IS_TPS4_CAPABLE:1;
-			uint32_t IS_YCBCR_CAPABLE:1;
 			uint32_t HDMI_6GB_EN:1;
 		} bits;
 		uint32_t raw;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index 76d00c6dbca9..33b99e3ab10d 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -172,4 +172,7 @@ void update_audio_usage(
 		const struct resource_pool *pool,
 		struct audio *audio,
 		bool acquired);
+
+unsigned int resource_pixel_format_to_bpp(enum surface_pixel_format format);
+
 #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_INC_RESOURCE_H_ */
diff --git a/drivers/gpu/drm/amd/display/include/signal_types.h b/drivers/gpu/drm/amd/display/include/signal_types.h
index 03476b142d8e..f56d2891475f 100644
--- a/drivers/gpu/drm/amd/display/include/signal_types.h
+++ b/drivers/gpu/drm/amd/display/include/signal_types.h
@@ -102,4 +102,9 @@ static inline bool dc_is_audio_capable_signal(enum signal_type signal)
 		dc_is_hdmi_signal(signal));
 }
 
+static inline bool dc_is_virtual_signal(enum signal_type signal)
+{
+	return (signal == SIGNAL_TYPE_VIRTUAL);
+}
+
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h
index 4ce090db7ef7..529b37db274c 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h
@@ -2449,6 +2449,8 @@
 #define mmCP_ECC_FIRSTOCCURRENCE_RING2_BASE_IDX                                                        0
 #define mmGB_EDC_MODE                                                                                  0x107e
 #define mmGB_EDC_MODE_BASE_IDX                                                                         0
+#define mmCP_DEBUG                                                                                     0x107f
+#define mmCP_DEBUG_BASE_IDX                                                                            0
 #define mmCP_CPF_DEBUG                                                                                 0x1080
 #define mmCP_PQ_WPTR_POLL_CNTL                                                                         0x1083
 #define mmCP_PQ_WPTR_POLL_CNTL_BASE_IDX                                                                0
diff --git a/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_9_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_9_0_offset.h
index efd2704d0f8f..0d6891095f62 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_9_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_9_0_offset.h
@@ -175,4 +175,7 @@
 #define mmSMUSVI0_PLANE0_CURRENTVID_BASE_IDX                                                           0
 #define mmSMUSVI0_PLANE0_CURRENTVID                                                                    0x0013
 
+#define mmSMUSVI0_TEL_PLANE0_BASE_IDX                                                                  0
+#define mmSMUSVI0_TEL_PLANE0                                                                           0x0004
+
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_9_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_9_0_sh_mask.h
index 2487ab9621e9..b1d9d8be1119 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_9_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_9_0_sh_mask.h
@@ -258,4 +258,7 @@
 #define SMUSVI0_PLANE0_CURRENTVID__CURRENT_SVI0_PLANE0_VID__SHIFT                                             0x18
 #define SMUSVI0_PLANE0_CURRENTVID__CURRENT_SVI0_PLANE0_VID_MASK                                               0xFF000000L
 
+#define SMUSVI0_TEL_PLANE0__SVI0_PLANE0_VDDCOR__SHIFT                                                         0x10
+#define SMUSVI0_TEL_PLANE0__SVI0_PLANE0_VDDCOR_MASK                                                           0x01FF0000L
+
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_offset.h b/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_offset.h
index 510ec3c70626..a9eb57a53e59 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_offset.h
@@ -26,6 +26,18 @@
 #define mmCG_MULT_THERMAL_STATUS                                                                       0x005f
 #define mmCG_MULT_THERMAL_STATUS_BASE_IDX                                                              0
 
+#define mmCG_FDO_CTRL0                                                                                 0x0067
+#define mmCG_FDO_CTRL0_BASE_IDX                                                                        0
+
+#define mmCG_FDO_CTRL1                                                                                 0x0068
+#define mmCG_FDO_CTRL1_BASE_IDX                                                                        0
+
+#define mmCG_FDO_CTRL2                                                                                 0x0069
+#define mmCG_FDO_CTRL2_BASE_IDX                                                                        0
+
+#define mmCG_TACH_CTRL                                                                                 0x006a
+#define mmCG_TACH_CTRL_BASE_IDX                                                                        0
+
 #define mmTHM_THERMAL_INT_ENA                                                                          0x000a
 #define mmTHM_THERMAL_INT_ENA_BASE_IDX                                                                 0
 #define mmTHM_THERMAL_INT_CTRL                                                                         0x000b
diff --git a/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_sh_mask.h
index f69533fa6abf..d130d92aee19 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/thm/thm_11_0_2_sh_mask.h
@@ -28,6 +28,16 @@
 #define CG_MULT_THERMAL_STATUS__CTF_TEMP__SHIFT                                                               0x9
 #define CG_MULT_THERMAL_STATUS__ASIC_MAX_TEMP_MASK                                                            0x000001FFL
 #define CG_MULT_THERMAL_STATUS__CTF_TEMP_MASK                                                                 0x0003FE00L
+#define CG_FDO_CTRL2__TMIN__SHIFT                                                                             0x0
+#define CG_FDO_CTRL2__TMIN_MASK                                                                               0x000000FFL
+#define CG_FDO_CTRL2__FDO_PWM_MODE__SHIFT                                                                     0xb
+#define CG_FDO_CTRL2__FDO_PWM_MODE_MASK                                                                       0x00003800L
+#define CG_FDO_CTRL1__FMAX_DUTY100__SHIFT                                                                     0x0
+#define CG_FDO_CTRL1__FMAX_DUTY100_MASK                                                                       0x000000FFL
+#define CG_FDO_CTRL0__FDO_STATIC_DUTY__SHIFT                                                                  0x0
+#define CG_FDO_CTRL0__FDO_STATIC_DUTY_MASK                                                                    0x000000FFL
+#define CG_TACH_CTRL__TARGET_PERIOD__SHIFT                                                                    0x3
+#define CG_TACH_CTRL__TARGET_PERIOD_MASK                                                                      0xFFFFFFF8L
 
 //THM_THERMAL_INT_ENA
 #define THM_THERMAL_INT_ENA__THERM_INTH_SET__SHIFT                                                            0x0
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index bd7404532029..980e696989b1 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -114,6 +114,8 @@ enum amd_pp_sensors {
 	AMDGPU_PP_SENSOR_STABLE_PSTATE_SCLK,
 	AMDGPU_PP_SENSOR_STABLE_PSTATE_MCLK,
 	AMDGPU_PP_SENSOR_ENABLED_SMC_FEATURES_MASK,
+	AMDGPU_PP_SENSOR_MIN_FAN_RPM,
+	AMDGPU_PP_SENSOR_MAX_FAN_RPM,
 };
 
 enum amd_pp_task {
@@ -228,6 +230,7 @@ struct amd_pm_funcs {
 	enum amd_dpm_forced_level (*get_performance_level)(void *handle);
 	enum amd_pm_state_type (*get_current_power_state)(void *handle);
 	int (*get_fan_speed_rpm)(void *handle, uint32_t *rpm);
+	int (*set_fan_speed_rpm)(void *handle, uint32_t rpm);
 	int (*get_pp_num_states)(void *handle, struct pp_states_info *data);
 	int (*get_pp_table)(void *handle, char **table);
 	int (*set_pp_table)(void *handle, const char *buf, size_t size);
@@ -272,6 +275,7 @@ struct amd_pm_funcs {
 	int (*get_display_mode_validation_clocks)(void *handle,
 		struct amd_pp_simple_clock_info *clocks);
 	int (*notify_smu_enable_pwe)(void *handle);
+	int (*enable_mgpu_fan_boost)(void *handle);
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index da4ebff5b74d..75b56ae032ce 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -109,11 +109,8 @@ static int pp_sw_fini(void *handle)
 
 	hwmgr_sw_fini(hwmgr);
 
-	if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU) {
-		release_firmware(adev->pm.fw);
-		adev->pm.fw = NULL;
-		amdgpu_ucode_fini_bo(adev);
-	}
+	release_firmware(adev->pm.fw);
+	adev->pm.fw = NULL;
 
 	return 0;
 }
@@ -124,9 +121,6 @@ static int pp_hw_init(void *handle)
 	struct amdgpu_device *adev = handle;
 	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
 
-	if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU)
-		amdgpu_ucode_init_bo(adev);
-
 	ret = hwmgr_hw_init(hwmgr);
 
 	if (ret)
@@ -273,8 +267,23 @@ const struct amdgpu_ip_block_version pp_smu_ip_block =
 	.funcs = &pp_ip_funcs,
 };
 
+/* This interface only be supported On Vi,
+ * because only smu7/8 can help to load gfx/sdma fw,
+ * smu need to be enabled before load other ip's fw.
+ * so call start smu to load smu7 fw and other ip's fw
+ */
 static int pp_dpm_load_fw(void *handle)
 {
+	struct pp_hwmgr *hwmgr = handle;
+
+	if (!hwmgr || !hwmgr->smumgr_funcs || !hwmgr->smumgr_funcs->start_smu)
+		return -EINVAL;
+
+	if (hwmgr->smumgr_funcs->start_smu(hwmgr)) {
+		pr_err("fw load failed\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -576,6 +585,24 @@ static int pp_dpm_get_fan_speed_rpm(void *handle, uint32_t *rpm)
 	return ret;
 }
 
+static int pp_dpm_set_fan_speed_rpm(void *handle, uint32_t rpm)
+{
+	struct pp_hwmgr *hwmgr = handle;
+	int ret = 0;
+
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
+
+	if (hwmgr->hwmgr_func->set_fan_speed_rpm == NULL) {
+		pr_info("%s was not implemented.\n", __func__);
+		return 0;
+	}
+	mutex_lock(&hwmgr->smu_lock);
+	ret = hwmgr->hwmgr_func->set_fan_speed_rpm(hwmgr, rpm);
+	mutex_unlock(&hwmgr->smu_lock);
+	return ret;
+}
+
 static int pp_dpm_get_pp_num_states(void *handle,
 		struct pp_states_info *data)
 {
@@ -813,6 +840,12 @@ static int pp_dpm_read_sensor(void *handle, int idx,
 	case AMDGPU_PP_SENSOR_STABLE_PSTATE_MCLK:
 		*((uint32_t *)value) = hwmgr->pstate_mclk;
 		return 0;
+	case AMDGPU_PP_SENSOR_MIN_FAN_RPM:
+		*((uint32_t *)value) = hwmgr->thermal_controller.fanInfo.ulMinRPM;
+		return 0;
+	case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
+		*((uint32_t *)value) = hwmgr->thermal_controller.fanInfo.ulMaxRPM;
+		return 0;
 	default:
 		mutex_lock(&hwmgr->smu_lock);
 		ret = hwmgr->hwmgr_func->read_sensor(hwmgr, idx, value, size);
@@ -1196,6 +1229,21 @@ static void pp_dpm_powergate_acp(void *handle, bool gate)
 	hwmgr->hwmgr_func->powergate_acp(hwmgr, gate);
 }
 
+static void pp_dpm_powergate_sdma(void *handle, bool gate)
+{
+	struct pp_hwmgr *hwmgr = handle;
+
+	if (!hwmgr)
+		return;
+
+	if (hwmgr->hwmgr_func->powergate_sdma == NULL) {
+		pr_info("%s was not implemented.\n", __func__);
+		return;
+	}
+
+	hwmgr->hwmgr_func->powergate_sdma(hwmgr, gate);
+}
+
 static int pp_set_powergating_by_smu(void *handle,
 				uint32_t block_type, bool gate)
 {
@@ -1218,6 +1266,9 @@ static int pp_set_powergating_by_smu(void *handle,
 	case AMD_IP_BLOCK_TYPE_ACP:
 		pp_dpm_powergate_acp(handle, gate);
 		break;
+	case AMD_IP_BLOCK_TYPE_SDMA:
+		pp_dpm_powergate_sdma(handle, gate);
+		break;
 	default:
 		break;
 	}
@@ -1243,6 +1294,24 @@ static int pp_notify_smu_enable_pwe(void *handle)
 	return 0;
 }
 
+static int pp_enable_mgpu_fan_boost(void *handle)
+{
+	struct pp_hwmgr *hwmgr = handle;
+
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
+
+	if (hwmgr->hwmgr_func->enable_mgpu_fan_boost == NULL) {
+		return 0;
+	}
+
+	mutex_lock(&hwmgr->smu_lock);
+	hwmgr->hwmgr_func->enable_mgpu_fan_boost(hwmgr);
+	mutex_unlock(&hwmgr->smu_lock);
+
+	return 0;
+}
+
 static const struct amd_pm_funcs pp_dpm_funcs = {
 	.load_firmware = pp_dpm_load_fw,
 	.wait_for_fw_loading_complete = pp_dpm_fw_loading_complete,
@@ -1255,6 +1324,7 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.set_fan_speed_percent = pp_dpm_set_fan_speed_percent,
 	.get_fan_speed_percent = pp_dpm_get_fan_speed_percent,
 	.get_fan_speed_rpm = pp_dpm_get_fan_speed_rpm,
+	.set_fan_speed_rpm = pp_dpm_set_fan_speed_rpm,
 	.get_pp_num_states = pp_dpm_get_pp_num_states,
 	.get_pp_table = pp_dpm_get_pp_table,
 	.set_pp_table = pp_dpm_set_pp_table,
@@ -1287,4 +1357,5 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.display_clock_voltage_request = pp_display_clock_voltage_request,
 	.get_display_mode_validation_clocks = pp_get_display_mode_validation_clocks,
 	.notify_smu_enable_pwe = pp_notify_smu_enable_pwe,
+	.enable_mgpu_fan_boost = pp_enable_mgpu_fan_boost,
 };
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index 7500a3e61dba..47ac92369739 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -89,7 +89,6 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 	hwmgr_init_default_caps(hwmgr);
 	hwmgr_set_user_specify_caps(hwmgr);
 	hwmgr->fan_ctrl_is_in_default_mode = true;
-	hwmgr->reload_fw = 1;
 	hwmgr_init_workload_prority(hwmgr);
 
 	switch (hwmgr->chip_family) {
@@ -209,17 +208,6 @@ int hwmgr_hw_init(struct pp_hwmgr *hwmgr)
 {
 	int ret = 0;
 
-	if (!hwmgr || !hwmgr->smumgr_funcs)
-		return -EINVAL;
-
-	if (hwmgr->smumgr_funcs->start_smu) {
-		ret = hwmgr->smumgr_funcs->start_smu(hwmgr);
-		if (ret) {
-			pr_err("smc start failed\n");
-			return -EINVAL;
-		}
-	}
-
 	if (!hwmgr->pm_en)
 		return 0;
 
@@ -320,13 +308,6 @@ int hwmgr_resume(struct pp_hwmgr *hwmgr)
 	if (!hwmgr)
 		return -EINVAL;
 
-	if (hwmgr->smumgr_funcs && hwmgr->smumgr_funcs->start_smu) {
-		if (hwmgr->smumgr_funcs->start_smu(hwmgr)) {
-			pr_err("smc start failed\n");
-			return -EINVAL;
-		}
-	}
-
 	if (!hwmgr->pm_en)
 		return 0;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index 5d1dae25a466..dd18cb710391 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
@@ -1153,6 +1153,14 @@ static int smu10_powergate_mmhub(struct pp_hwmgr *hwmgr)
 	return smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PowerGateMmHub);
 }
 
+static int smu10_powergate_sdma(struct pp_hwmgr *hwmgr, bool gate)
+{
+	if (gate)
+		return smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PowerDownSdma);
+	else
+		return smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PowerUpSdma);
+}
+
 static void smu10_powergate_vcn(struct pp_hwmgr *hwmgr, bool bgate)
 {
 	if (bgate) {
@@ -1208,6 +1216,7 @@ static const struct pp_hwmgr_func smu10_hwmgr_funcs = {
 	.smus_notify_pwe = smu10_smus_notify_pwe,
 	.display_clock_voltage_request = smu10_display_clock_voltage_request,
 	.powergate_gfx = smu10_gfx_off_control,
+	.powergate_sdma = smu10_powergate_sdma,
 };
 
 int smu10_init_function_pointers(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_thermal.c
index 44527755e747..5bdc0df5a9f4 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_thermal.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_thermal.c
@@ -260,6 +260,7 @@ int smu7_fan_ctrl_set_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t speed)
 	if (hwmgr->thermal_controller.fanInfo.bNoFan ||
 			(hwmgr->thermal_controller.fanInfo.
 			ucTachometerPulsesPerRevolution == 0) ||
+			speed == 0 ||
 			(speed < hwmgr->thermal_controller.fanInfo.ulMinRPM) ||
 			(speed > hwmgr->thermal_controller.fanInfo.ulMaxRPM))
 		return 0;
@@ -272,7 +273,7 @@ int smu7_fan_ctrl_set_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t speed)
 	tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed);
 
 	PHM_WRITE_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
-				CG_TACH_STATUS, TACH_PERIOD, tach_period);
+				CG_TACH_CTRL, TARGET_PERIOD, tach_period);
 
 	return smu7_fan_ctrl_set_static_mode(hwmgr, FDO_PWM_MODE_STATIC_RPM);
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
index 53cf787560f7..fef111ddb736 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
@@ -1228,14 +1228,17 @@ static int smu8_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 
 static int smu8_dpm_powerdown_uvd(struct pp_hwmgr *hwmgr)
 {
-	if (PP_CAP(PHM_PlatformCaps_UVDPowerGating))
+	if (PP_CAP(PHM_PlatformCaps_UVDPowerGating)) {
+		smu8_nbdpm_pstate_enable_disable(hwmgr, true, true);
 		return smum_send_msg_to_smc(hwmgr, PPSMC_MSG_UVDPowerOFF);
+	}
 	return 0;
 }
 
 static int smu8_dpm_powerup_uvd(struct pp_hwmgr *hwmgr)
 {
 	if (PP_CAP(PHM_PlatformCaps_UVDPowerGating)) {
+		smu8_nbdpm_pstate_enable_disable(hwmgr, false, true);
 		return smum_send_msg_to_smc_with_parameter(
 			hwmgr,
 			PPSMC_MSG_UVDPowerON,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
index 8ad4e6960efd..4714b5b59825 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
@@ -39,6 +39,50 @@ uint16_t convert_to_vddc(uint8_t vid)
 	return (uint16_t) ((6200 - (vid * 25)) / VOLTAGE_SCALE);
 }
 
+int phm_copy_clock_limits_array(
+	struct pp_hwmgr *hwmgr,
+	uint32_t **pptable_info_array,
+	const uint32_t *pptable_array,
+	uint32_t power_saving_clock_count)
+{
+	uint32_t array_size, i;
+	uint32_t *table;
+
+	array_size = sizeof(uint32_t) * power_saving_clock_count;
+	table = kzalloc(array_size, GFP_KERNEL);
+	if (NULL == table)
+		return -ENOMEM;
+
+	for (i = 0; i < power_saving_clock_count; i++)
+		table[i] = le32_to_cpu(pptable_array[i]);
+
+	*pptable_info_array = table;
+
+	return 0;
+}
+
+int phm_copy_overdrive_settings_limits_array(
+	struct pp_hwmgr *hwmgr,
+	uint32_t **pptable_info_array,
+	const uint32_t *pptable_array,
+	uint32_t od_setting_count)
+{
+	uint32_t array_size, i;
+	uint32_t *table;
+
+	array_size = sizeof(uint32_t) * od_setting_count;
+	table = kzalloc(array_size, GFP_KERNEL);
+	if (NULL == table)
+		return -ENOMEM;
+
+	for (i = 0; i < od_setting_count; i++)
+		table[i] = le32_to_cpu(pptable_array[i]);
+
+	*pptable_info_array = table;
+
+	return 0;
+}
+
 uint32_t phm_set_field_to_u32(u32 offset, u32 original_data, u32 field, u32 size)
 {
 	u32 mask = 0;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
index 5454289d5226..ad33983a8064 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
@@ -47,6 +47,18 @@ struct watermarks {
 	uint32_t     padding[7];
 };
 
+int phm_copy_clock_limits_array(
+	struct pp_hwmgr *hwmgr,
+	uint32_t **pptable_info_array,
+	const uint32_t *pptable_array,
+	uint32_t power_saving_clock_count);
+
+int phm_copy_overdrive_settings_limits_array(
+	struct pp_hwmgr *hwmgr,
+	uint32_t **pptable_info_array,
+	const uint32_t *pptable_array,
+	uint32_t od_setting_count);
+
 extern int phm_wait_for_register_unequal(struct pp_hwmgr *hwmgr,
 					uint32_t index,
 					uint32_t value, uint32_t mask);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_processpptables.c
index 16b1a9cf6cf0..b8747a5c9204 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_processpptables.c
@@ -451,23 +451,23 @@ static int get_tdp_table(
 					le16_to_cpu(power_tune_table_v2->usLoadLineResistance);
 	} else {
 		power_tune_table_v3 = (ATOM_Vega10_PowerTune_Table_V3 *)table;
-		tdp_table->usMaximumPowerDeliveryLimit   = power_tune_table_v3->usSocketPowerLimit;
-		tdp_table->usTDC                         = power_tune_table_v3->usTdcLimit;
-		tdp_table->usEDCLimit                    = power_tune_table_v3->usEdcLimit;
-		tdp_table->usSoftwareShutdownTemp        = power_tune_table_v3->usSoftwareShutdownTemp;
-		tdp_table->usTemperatureLimitTedge       = power_tune_table_v3->usTemperatureLimitTedge;
-		tdp_table->usTemperatureLimitHotspot     = power_tune_table_v3->usTemperatureLimitHotSpot;
-		tdp_table->usTemperatureLimitLiquid1     = power_tune_table_v3->usTemperatureLimitLiquid1;
-		tdp_table->usTemperatureLimitLiquid2     = power_tune_table_v3->usTemperatureLimitLiquid2;
-		tdp_table->usTemperatureLimitHBM         = power_tune_table_v3->usTemperatureLimitHBM;
-		tdp_table->usTemperatureLimitVrVddc      = power_tune_table_v3->usTemperatureLimitVrSoc;
-		tdp_table->usTemperatureLimitVrMvdd      = power_tune_table_v3->usTemperatureLimitVrMem;
-		tdp_table->usTemperatureLimitPlx         = power_tune_table_v3->usTemperatureLimitPlx;
+		tdp_table->usMaximumPowerDeliveryLimit   = le16_to_cpu(power_tune_table_v3->usSocketPowerLimit);
+		tdp_table->usTDC                         = le16_to_cpu(power_tune_table_v3->usTdcLimit);
+		tdp_table->usEDCLimit                    = le16_to_cpu(power_tune_table_v3->usEdcLimit);
+		tdp_table->usSoftwareShutdownTemp        = le16_to_cpu(power_tune_table_v3->usSoftwareShutdownTemp);
+		tdp_table->usTemperatureLimitTedge       = le16_to_cpu(power_tune_table_v3->usTemperatureLimitTedge);
+		tdp_table->usTemperatureLimitHotspot     = le16_to_cpu(power_tune_table_v3->usTemperatureLimitHotSpot);
+		tdp_table->usTemperatureLimitLiquid1     = le16_to_cpu(power_tune_table_v3->usTemperatureLimitLiquid1);
+		tdp_table->usTemperatureLimitLiquid2     = le16_to_cpu(power_tune_table_v3->usTemperatureLimitLiquid2);
+		tdp_table->usTemperatureLimitHBM         = le16_to_cpu(power_tune_table_v3->usTemperatureLimitHBM);
+		tdp_table->usTemperatureLimitVrVddc      = le16_to_cpu(power_tune_table_v3->usTemperatureLimitVrSoc);
+		tdp_table->usTemperatureLimitVrMvdd      = le16_to_cpu(power_tune_table_v3->usTemperatureLimitVrMem);
+		tdp_table->usTemperatureLimitPlx         = le16_to_cpu(power_tune_table_v3->usTemperatureLimitPlx);
 		tdp_table->ucLiquid1_I2C_address         = power_tune_table_v3->ucLiquid1_I2C_address;
 		tdp_table->ucLiquid2_I2C_address         = power_tune_table_v3->ucLiquid2_I2C_address;
-		tdp_table->usBoostStartTemperature       = power_tune_table_v3->usBoostStartTemperature;
-		tdp_table->usBoostStopTemperature        = power_tune_table_v3->usBoostStopTemperature;
-		tdp_table->ulBoostClock                  = power_tune_table_v3->ulBoostClock;
+		tdp_table->usBoostStartTemperature       = le16_to_cpu(power_tune_table_v3->usBoostStartTemperature);
+		tdp_table->usBoostStopTemperature        = le16_to_cpu(power_tune_table_v3->usBoostStopTemperature);
+		tdp_table->ulBoostClock                  = le32_to_cpu(power_tune_table_v3->ulBoostClock);
 
 		get_scl_sda_value(power_tune_table_v3->ucLiquid_I2C_Line, &scl, &sda);
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c
index 407762b36901..3f807d6c95ce 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c
@@ -312,6 +312,7 @@ int vega10_fan_ctrl_set_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t speed)
 	int result = 0;
 
 	if (hwmgr->thermal_controller.fanInfo.bNoFan ||
+	    speed == 0 ||
 	    (speed < hwmgr->thermal_controller.fanInfo.ulMinRPM) ||
 	    (speed > hwmgr->thermal_controller.fanInfo.ulMaxRPM))
 		return -1;
@@ -322,9 +323,9 @@ int vega10_fan_ctrl_set_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t speed)
 	if (!result) {
 		crystal_clock_freq = amdgpu_asic_get_xclk((struct amdgpu_device *)hwmgr->adev);
 		tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed);
-		WREG32_SOC15(THM, 0, mmCG_TACH_STATUS,
-				REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_TACH_STATUS),
-					CG_TACH_STATUS, TACH_PERIOD,
+		WREG32_SOC15(THM, 0, mmCG_TACH_CTRL,
+				REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_TACH_CTRL),
+					CG_TACH_CTRL, TARGET_PERIOD,
 					tach_period));
 	}
 	return vega10_fan_ctrl_set_static_mode(hwmgr, FDO_PWM_MODE_STATIC_RPM);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
index cb3a5b1737c8..9817f7a5ed29 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
@@ -99,50 +99,6 @@ static int set_platform_caps(struct pp_hwmgr *hwmgr, uint32_t powerplay_caps)
 	return 0;
 }
 
-static int copy_clock_limits_array(
-	struct pp_hwmgr *hwmgr,
-	uint32_t **pptable_info_array,
-	const uint32_t *pptable_array)
-{
-	uint32_t array_size, i;
-	uint32_t *table;
-
-	array_size = sizeof(uint32_t) * ATOM_VEGA12_PPCLOCK_COUNT;
-
-	table = kzalloc(array_size, GFP_KERNEL);
-	if (NULL == table)
-		return -ENOMEM;
-
-	for (i = 0; i < ATOM_VEGA12_PPCLOCK_COUNT; i++)
-		table[i] = pptable_array[i];
-
-	*pptable_info_array = table;
-
-	return 0;
-}
-
-static int copy_overdrive_settings_limits_array(
-		struct pp_hwmgr *hwmgr,
-		uint32_t **pptable_info_array,
-		const uint32_t *pptable_array)
-{
-	uint32_t array_size, i;
-	uint32_t *table;
-
-	array_size = sizeof(uint32_t) * ATOM_VEGA12_ODSETTING_COUNT;
-
-	table = kzalloc(array_size, GFP_KERNEL);
-	if (NULL == table)
-		return -ENOMEM;
-
-	for (i = 0; i < ATOM_VEGA12_ODSETTING_COUNT; i++)
-		table[i] = pptable_array[i];
-
-	*pptable_info_array = table;
-
-	return 0;
-}
-
 static int append_vbios_pptable(struct pp_hwmgr *hwmgr, PPTable_t *ppsmc_pptable)
 {
 	struct pp_atomfwctrl_smc_dpm_parameters smc_dpm_table;
@@ -250,14 +206,22 @@ static int init_powerplay_table_information(
 
 	phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_MicrocodeFanControl);
 
-	if (powerplay_table->ODSettingsMax[ATOM_VEGA12_ODSETTING_GFXCLKFMAX] > VEGA12_ENGINECLOCK_HARDMAX)
+	if (le32_to_cpu(powerplay_table->ODSettingsMax[ATOM_VEGA12_ODSETTING_GFXCLKFMAX]) > VEGA12_ENGINECLOCK_HARDMAX)
 		hwmgr->platform_descriptor.overdriveLimit.engineClock = VEGA12_ENGINECLOCK_HARDMAX;
 	else
-		hwmgr->platform_descriptor.overdriveLimit.engineClock = powerplay_table->ODSettingsMax[ATOM_VEGA12_ODSETTING_GFXCLKFMAX];
-	hwmgr->platform_descriptor.overdriveLimit.memoryClock = powerplay_table->ODSettingsMax[ATOM_VEGA12_ODSETTING_UCLKFMAX];
+		hwmgr->platform_descriptor.overdriveLimit.engineClock =
+			le32_to_cpu(powerplay_table->ODSettingsMax[ATOM_VEGA12_ODSETTING_GFXCLKFMAX]);
+	hwmgr->platform_descriptor.overdriveLimit.memoryClock =
+		le32_to_cpu(powerplay_table->ODSettingsMax[ATOM_VEGA12_ODSETTING_UCLKFMAX]);
 
-	copy_overdrive_settings_limits_array(hwmgr, &pptable_information->od_settings_max, powerplay_table->ODSettingsMax);
-	copy_overdrive_settings_limits_array(hwmgr, &pptable_information->od_settings_min, powerplay_table->ODSettingsMin);
+	phm_copy_overdrive_settings_limits_array(hwmgr,
+						 &pptable_information->od_settings_max,
+						 powerplay_table->ODSettingsMax,
+						 ATOM_VEGA12_ODSETTING_COUNT);
+	phm_copy_overdrive_settings_limits_array(hwmgr,
+						 &pptable_information->od_settings_min,
+						 powerplay_table->ODSettingsMin,
+						 ATOM_VEGA12_ODSETTING_COUNT);
 
 	/* hwmgr->platformDescriptor.minOverdriveVDDC = 0;
 	hwmgr->platformDescriptor.maxOverdriveVDDC = 0;
@@ -267,15 +231,15 @@ static int init_powerplay_table_information(
 		&& hwmgr->platform_descriptor.overdriveLimit.memoryClock > 0)
 		phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_ACOverdriveSupport);
 
-	pptable_information->us_small_power_limit1 = powerplay_table->usSmallPowerLimit1;
-	pptable_information->us_small_power_limit2 = powerplay_table->usSmallPowerLimit2;
-	pptable_information->us_boost_power_limit = powerplay_table->usBoostPowerLimit;
-	pptable_information->us_od_turbo_power_limit = powerplay_table->usODTurboPowerLimit;
-	pptable_information->us_od_powersave_power_limit = powerplay_table->usODPowerSavePowerLimit;
+	pptable_information->us_small_power_limit1 = le16_to_cpu(powerplay_table->usSmallPowerLimit1);
+	pptable_information->us_small_power_limit2 = le16_to_cpu(powerplay_table->usSmallPowerLimit2);
+	pptable_information->us_boost_power_limit = le16_to_cpu(powerplay_table->usBoostPowerLimit);
+	pptable_information->us_od_turbo_power_limit = le16_to_cpu(powerplay_table->usODTurboPowerLimit);
+	pptable_information->us_od_powersave_power_limit = le16_to_cpu(powerplay_table->usODPowerSavePowerLimit);
 
-	pptable_information->us_software_shutdown_temp = powerplay_table->usSoftwareShutdownTemp;
+	pptable_information->us_software_shutdown_temp = le16_to_cpu(powerplay_table->usSoftwareShutdownTemp);
 
-	hwmgr->platform_descriptor.TDPODLimit = (uint16_t)powerplay_table->ODSettingsMax[ATOM_VEGA12_ODSETTING_POWERPERCENTAGE];
+	hwmgr->platform_descriptor.TDPODLimit = le32_to_cpu(powerplay_table->ODSettingsMax[ATOM_VEGA12_ODSETTING_POWERPERCENTAGE]);
 
 	disable_power_control = 0;
 	if (!disable_power_control) {
@@ -285,8 +249,8 @@ static int init_powerplay_table_information(
 				PHM_PlatformCaps_PowerControl);
 	}
 
-	copy_clock_limits_array(hwmgr, &pptable_information->power_saving_clock_max, powerplay_table->PowerSavingClockMax);
-	copy_clock_limits_array(hwmgr, &pptable_information->power_saving_clock_min, powerplay_table->PowerSavingClockMin);
+	phm_copy_clock_limits_array(hwmgr, &pptable_information->power_saving_clock_max, powerplay_table->PowerSavingClockMax, ATOM_VEGA12_PPCLOCK_COUNT);
+	phm_copy_clock_limits_array(hwmgr, &pptable_information->power_saving_clock_min, powerplay_table->PowerSavingClockMin, ATOM_VEGA12_PPCLOCK_COUNT);
 
 	pptable_information->smc_pptable = (PPTable_t *)kmalloc(sizeof(PPTable_t), GFP_KERNEL);
 	if (pptable_information->smc_pptable == NULL)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
index 2a554f9edcda..958af7b48827 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
@@ -46,6 +46,9 @@
 #include "ppinterrupt.h"
 #include "pp_overdriver.h"
 #include "pp_thermal.h"
+#include "soc15_common.h"
+#include "smuio/smuio_9_0_offset.h"
+#include "smuio/smuio_9_0_sh_mask.h"
 
 static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr)
 {
@@ -1474,6 +1477,19 @@ static int vega20_init_max_sustainable_clocks(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static int vega20_enable_mgpu_fan_boost(struct pp_hwmgr *hwmgr)
+{
+	int result;
+
+	result = smum_send_msg_to_smc(hwmgr,
+		PPSMC_MSG_SetMGpuFanBoostLimitRpm);
+	PP_ASSERT_WITH_CODE(!result,
+			"[EnableMgpuFan] Failed to enable mgpu fan boost!",
+			return result);
+
+	return 0;
+}
+
 static void vega20_init_powergate_state(struct pp_hwmgr *hwmgr)
 {
 	struct vega20_hwmgr *data =
@@ -1544,6 +1560,14 @@ static int vega20_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 			"[EnableDPMTasks] Failed to populate umdpstate clocks!",
 			return result);
 
+	result = smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetPptLimit,
+			POWER_SOURCE_AC << 16);
+	PP_ASSERT_WITH_CODE(!result,
+			"[GetPptLimit] get default PPT limit failed!",
+			return result);
+	hwmgr->power_limit =
+		hwmgr->default_power_limit = smum_get_argument(hwmgr);
+
 	return 0;
 }
 
@@ -1907,6 +1931,8 @@ static int vega20_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 			      void *value, int *size)
 {
 	struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend);
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t val_vid;
 	int ret = 0;
 
 	switch (idx) {
@@ -1941,6 +1967,13 @@ static int vega20_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 		*size = 16;
 		ret = vega20_get_gpu_power(hwmgr, (uint32_t *)value);
 		break;
+	case AMDGPU_PP_SENSOR_VDDGFX:
+		val_vid = (RREG32_SOC15(SMUIO, 0, mmSMUSVI0_TEL_PLANE0) &
+			SMUSVI0_TEL_PLANE0__SVI0_PLANE0_VDDCOR_MASK) >>
+			SMUSVI0_TEL_PLANE0__SVI0_PLANE0_VDDCOR__SHIFT;
+		*((uint32_t *)value) =
+			(uint32_t)convert_to_vddc((uint8_t)val_vid);
+		break;
 	case AMDGPU_PP_SENSOR_ENABLED_SMC_FEATURES_MASK:
 		ret = vega20_get_enabled_smc_features(hwmgr, (uint64_t *)value);
 		if (!ret)
@@ -2269,6 +2302,25 @@ static uint32_t vega20_get_fan_control_mode(struct pp_hwmgr *hwmgr)
 		return AMD_FAN_CTRL_AUTO;
 }
 
+static void vega20_set_fan_control_mode(struct pp_hwmgr *hwmgr, uint32_t mode)
+{
+	switch (mode) {
+	case AMD_FAN_CTRL_NONE:
+		vega20_fan_ctrl_set_fan_speed_percent(hwmgr, 100);
+		break;
+	case AMD_FAN_CTRL_MANUAL:
+		if (PP_CAP(PHM_PlatformCaps_MicrocodeFanControl))
+			vega20_fan_ctrl_stop_smc_fan_control(hwmgr);
+		break;
+	case AMD_FAN_CTRL_AUTO:
+		if (PP_CAP(PHM_PlatformCaps_MicrocodeFanControl))
+			vega20_fan_ctrl_start_smc_fan_control(hwmgr);
+		break;
+	default:
+		break;
+	}
+}
+
 static int vega20_get_dal_power_level(struct pp_hwmgr *hwmgr,
 		struct amd_pp_simple_clock_info *info)
 {
@@ -3165,7 +3217,7 @@ static int vega20_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 				"[GetPowerProfile] Failed to get activity monitor!",
 				return result);
 
-		size += sprintf(buf + size, "%2d(%14s%s)\n",
+		size += sprintf(buf + size, "%2d %14s%s:\n",
 			i, profile_name[i], (i == hwmgr->power_profile_mode) ? "*" : " ");
 
 		size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
@@ -3432,15 +3484,25 @@ static const struct pp_hwmgr_func vega20_hwmgr_funcs = {
 	.disable_smc_firmware_ctf =
 		vega20_thermal_disable_alert,
 	/* fan control related */
+	.get_fan_speed_percent =
+		vega20_fan_ctrl_get_fan_speed_percent,
+	.set_fan_speed_percent =
+		vega20_fan_ctrl_set_fan_speed_percent,
 	.get_fan_speed_info =
 		vega20_fan_ctrl_get_fan_speed_info,
 	.get_fan_speed_rpm =
 		vega20_fan_ctrl_get_fan_speed_rpm,
+	.set_fan_speed_rpm =
+		vega20_fan_ctrl_set_fan_speed_rpm,
 	.get_fan_control_mode =
 		vega20_get_fan_control_mode,
+	.set_fan_control_mode =
+		vega20_set_fan_control_mode,
 	/* smu memory related */
 	.notify_cac_buffer_info =
 		vega20_notify_cac_buffer_info,
+	.enable_mgpu_fan_boost =
+		vega20_enable_mgpu_fan_boost,
 };
 
 int vega20_hwmgr_init(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_processpptables.c
index 5f1f7a32ac24..32fe38452094 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_processpptables.c
@@ -661,50 +661,6 @@ static int set_platform_caps(struct pp_hwmgr *hwmgr, uint32_t powerplay_caps)
 	return 0;
 }
 
-static int copy_clock_limits_array(
-	struct pp_hwmgr *hwmgr,
-	uint32_t **pptable_info_array,
-	const uint32_t *pptable_array,
-	uint32_t power_saving_clock_count)
-{
-	uint32_t array_size, i;
-	uint32_t *table;
-
-	array_size = sizeof(uint32_t) * power_saving_clock_count;
-	table = kzalloc(array_size, GFP_KERNEL);
-	if (NULL == table)
-		return -ENOMEM;
-
-	for (i = 0; i < power_saving_clock_count; i++)
-		table[i] = pptable_array[i];
-
-	*pptable_info_array = table;
-
-	return 0;
-}
-
-static int copy_overdrive_settings_limits_array(
-		struct pp_hwmgr *hwmgr,
-		uint32_t **pptable_info_array,
-		const uint32_t *pptable_array,
-		uint32_t od_setting_count)
-{
-	uint32_t array_size, i;
-	uint32_t *table;
-
-	array_size = sizeof(uint32_t) * od_setting_count;
-	table = kzalloc(array_size, GFP_KERNEL);
-	if (NULL == table)
-		return -ENOMEM;
-
-	for (i = 0; i < od_setting_count; i++)
-		table[i] = pptable_array[i];
-
-	*pptable_info_array = table;
-
-	return 0;
-}
-
 static int copy_overdrive_feature_capabilities_array(
 		struct pp_hwmgr *hwmgr,
 		uint8_t **pptable_info_array,
@@ -721,7 +677,7 @@ static int copy_overdrive_feature_capabilities_array(
 		return -ENOMEM;
 
 	for (i = 0; i < od_feature_count; i++) {
-		table[i] = pptable_array[i];
+		table[i] = le32_to_cpu(pptable_array[i]);
 		if (table[i])
 			od_supported = true;
 	}
@@ -834,6 +790,8 @@ static int init_powerplay_table_information(
 
 	hwmgr->thermal_controller.ucType = powerplay_table->ucThermalControllerType;
 	pptable_information->uc_thermal_controller_type = powerplay_table->ucThermalControllerType;
+	hwmgr->thermal_controller.fanInfo.ulMinRPM = 0;
+	hwmgr->thermal_controller.fanInfo.ulMaxRPM = powerplay_table->smcPPTable.FanMaximumRpm;
 
 	set_hw_cap(hwmgr,
 		ATOM_VEGA20_PP_THERMALCONTROLLER_NONE != hwmgr->thermal_controller.ucType,
@@ -842,34 +800,40 @@ static int init_powerplay_table_information(
 	phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_MicrocodeFanControl);
 
 	if (powerplay_table->OverDrive8Table.ucODTableRevision == 1) {
-		od_feature_count = (powerplay_table->OverDrive8Table.ODFeatureCount > ATOM_VEGA20_ODFEATURE_COUNT) ?
-				ATOM_VEGA20_ODFEATURE_COUNT : powerplay_table->OverDrive8Table.ODFeatureCount;
-		od_setting_count = (powerplay_table->OverDrive8Table.ODSettingCount > ATOM_VEGA20_ODSETTING_COUNT) ?
-				ATOM_VEGA20_ODSETTING_COUNT : powerplay_table->OverDrive8Table.ODSettingCount;
+		od_feature_count =
+			(le32_to_cpu(powerplay_table->OverDrive8Table.ODFeatureCount) >
+			 ATOM_VEGA20_ODFEATURE_COUNT) ?
+			ATOM_VEGA20_ODFEATURE_COUNT :
+			le32_to_cpu(powerplay_table->OverDrive8Table.ODFeatureCount);
+		od_setting_count =
+			(le32_to_cpu(powerplay_table->OverDrive8Table.ODSettingCount) >
+			 ATOM_VEGA20_ODSETTING_COUNT) ?
+			ATOM_VEGA20_ODSETTING_COUNT :
+			le32_to_cpu(powerplay_table->OverDrive8Table.ODSettingCount);
 
 		copy_overdrive_feature_capabilities_array(hwmgr,
 				&pptable_information->od_feature_capabilities,
 				powerplay_table->OverDrive8Table.ODFeatureCapabilities,
 				od_feature_count);
-		copy_overdrive_settings_limits_array(hwmgr,
+		phm_copy_overdrive_settings_limits_array(hwmgr,
 				&pptable_information->od_settings_max,
 				powerplay_table->OverDrive8Table.ODSettingsMax,
 				od_setting_count);
-		copy_overdrive_settings_limits_array(hwmgr,
+		phm_copy_overdrive_settings_limits_array(hwmgr,
 				&pptable_information->od_settings_min,
 				powerplay_table->OverDrive8Table.ODSettingsMin,
 				od_setting_count);
 	}
 
-	pptable_information->us_small_power_limit1 = powerplay_table->usSmallPowerLimit1;
-	pptable_information->us_small_power_limit2 = powerplay_table->usSmallPowerLimit2;
-	pptable_information->us_boost_power_limit = powerplay_table->usBoostPowerLimit;
-	pptable_information->us_od_turbo_power_limit = powerplay_table->usODTurboPowerLimit;
-	pptable_information->us_od_powersave_power_limit = powerplay_table->usODPowerSavePowerLimit;
+	pptable_information->us_small_power_limit1 = le16_to_cpu(powerplay_table->usSmallPowerLimit1);
+	pptable_information->us_small_power_limit2 = le16_to_cpu(powerplay_table->usSmallPowerLimit2);
+	pptable_information->us_boost_power_limit = le16_to_cpu(powerplay_table->usBoostPowerLimit);
+	pptable_information->us_od_turbo_power_limit = le16_to_cpu(powerplay_table->usODTurboPowerLimit);
+	pptable_information->us_od_powersave_power_limit = le16_to_cpu(powerplay_table->usODPowerSavePowerLimit);
 
-	pptable_information->us_software_shutdown_temp = powerplay_table->usSoftwareShutdownTemp;
+	pptable_information->us_software_shutdown_temp = le16_to_cpu(powerplay_table->usSoftwareShutdownTemp);
 
-	hwmgr->platform_descriptor.TDPODLimit = (uint16_t)powerplay_table->OverDrive8Table.ODSettingsMax[ATOM_VEGA20_ODSETTING_POWERPERCENTAGE];
+	hwmgr->platform_descriptor.TDPODLimit = le32_to_cpu(powerplay_table->OverDrive8Table.ODSettingsMax[ATOM_VEGA20_ODSETTING_POWERPERCENTAGE]);
 
 	disable_power_control = 0;
 	if (!disable_power_control && hwmgr->platform_descriptor.TDPODLimit)
@@ -877,13 +841,16 @@ static int init_powerplay_table_information(
 		phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_PowerControl);
 
 	if (powerplay_table->PowerSavingClockTable.ucTableRevision == 1) {
-		power_saving_clock_count = (powerplay_table->PowerSavingClockTable.PowerSavingClockCount >= ATOM_VEGA20_PPCLOCK_COUNT) ?
-				ATOM_VEGA20_PPCLOCK_COUNT : powerplay_table->PowerSavingClockTable.PowerSavingClockCount;
-		copy_clock_limits_array(hwmgr,
+		power_saving_clock_count =
+			(le32_to_cpu(powerplay_table->PowerSavingClockTable.PowerSavingClockCount) >=
+			 ATOM_VEGA20_PPCLOCK_COUNT) ?
+			ATOM_VEGA20_PPCLOCK_COUNT :
+			le32_to_cpu(powerplay_table->PowerSavingClockTable.PowerSavingClockCount);
+		phm_copy_clock_limits_array(hwmgr,
 				&pptable_information->power_saving_clock_max,
 				powerplay_table->PowerSavingClockTable.PowerSavingClockMax,
 				power_saving_clock_count);
-		copy_clock_limits_array(hwmgr,
+		phm_copy_clock_limits_array(hwmgr,
 				&pptable_information->power_saving_clock_min,
 				powerplay_table->PowerSavingClockTable.PowerSavingClockMin,
 				power_saving_clock_count);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c
index 1c951a5d827d..ede54e87e287 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c
@@ -29,6 +29,78 @@
 #include "soc15_common.h"
 #include "pp_debug.h"
 
+static int vega20_disable_fan_control_feature(struct pp_hwmgr *hwmgr)
+{
+	struct vega20_hwmgr *data = hwmgr->backend;
+	int ret = 0;
+
+	if (data->smu_features[GNLD_FAN_CONTROL].supported) {
+		ret = vega20_enable_smc_features(
+				hwmgr, false,
+				data->smu_features[GNLD_FAN_CONTROL].
+				smu_feature_bitmap);
+		PP_ASSERT_WITH_CODE(!ret,
+				"Disable FAN CONTROL feature Failed!",
+				return ret);
+		data->smu_features[GNLD_FAN_CONTROL].enabled = false;
+	}
+
+	return ret;
+}
+
+int vega20_fan_ctrl_stop_smc_fan_control(struct pp_hwmgr *hwmgr)
+{
+	struct vega20_hwmgr *data = hwmgr->backend;
+
+	if (data->smu_features[GNLD_FAN_CONTROL].supported)
+		return vega20_disable_fan_control_feature(hwmgr);
+
+	return 0;
+}
+
+static int vega20_enable_fan_control_feature(struct pp_hwmgr *hwmgr)
+{
+	struct vega20_hwmgr *data = hwmgr->backend;
+	int ret = 0;
+
+	if (data->smu_features[GNLD_FAN_CONTROL].supported) {
+		ret = vega20_enable_smc_features(
+				hwmgr, true,
+				data->smu_features[GNLD_FAN_CONTROL].
+				smu_feature_bitmap);
+		PP_ASSERT_WITH_CODE(!ret,
+				"Enable FAN CONTROL feature Failed!",
+				return ret);
+		data->smu_features[GNLD_FAN_CONTROL].enabled = true;
+	}
+
+	return ret;
+}
+
+int vega20_fan_ctrl_start_smc_fan_control(struct pp_hwmgr *hwmgr)
+{
+	struct vega20_hwmgr *data = hwmgr->backend;
+
+	if (data->smu_features[GNLD_FAN_CONTROL].supported)
+		return vega20_enable_fan_control_feature(hwmgr);
+
+	return 0;
+}
+
+static int vega20_fan_ctrl_set_static_mode(struct pp_hwmgr *hwmgr, uint32_t mode)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL2,
+			REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL2),
+				CG_FDO_CTRL2, TMIN, 0));
+	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL2,
+			REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL2),
+				CG_FDO_CTRL2, FDO_PWM_MODE, mode));
+
+	return 0;
+}
+
 static int vega20_get_current_rpm(struct pp_hwmgr *hwmgr, uint32_t *current_rpm)
 {
 	int ret = 0;
@@ -42,12 +114,62 @@ static int vega20_get_current_rpm(struct pp_hwmgr *hwmgr, uint32_t *current_rpm)
 	return 0;
 }
 
+int vega20_fan_ctrl_get_fan_speed_percent(struct pp_hwmgr *hwmgr,
+		uint32_t *speed)
+{
+	struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend);
+	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
+	uint32_t current_rpm, percent = 0;
+	int ret = 0;
+
+	ret = vega20_get_current_rpm(hwmgr, &current_rpm);
+	if (ret)
+		return ret;
+
+	percent = current_rpm * 100 / pp_table->FanMaximumRpm;
+
+	*speed = percent > 100 ? 100 : percent;
+
+	return 0;
+}
+
+int vega20_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
+		uint32_t speed)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t duty100;
+	uint32_t duty;
+	uint64_t tmp64;
+
+	if (speed > 100)
+		speed = 100;
+
+	if (PP_CAP(PHM_PlatformCaps_MicrocodeFanControl))
+		vega20_fan_ctrl_stop_smc_fan_control(hwmgr);
+
+	duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1),
+				    CG_FDO_CTRL1, FMAX_DUTY100);
+
+	if (duty100 == 0)
+		return -EINVAL;
+
+	tmp64 = (uint64_t)speed * duty100;
+	do_div(tmp64, 100);
+	duty = (uint32_t)tmp64;
+
+	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL0,
+		REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL0),
+			CG_FDO_CTRL0, FDO_STATIC_DUTY, duty));
+
+	return vega20_fan_ctrl_set_static_mode(hwmgr, FDO_PWM_MODE_STATIC);
+}
+
 int vega20_fan_ctrl_get_fan_speed_info(struct pp_hwmgr *hwmgr,
 		struct phm_fan_speed_info *fan_speed_info)
 {
 	memset(fan_speed_info, 0, sizeof(*fan_speed_info));
-	fan_speed_info->supports_percent_read = false;
-	fan_speed_info->supports_percent_write = false;
+	fan_speed_info->supports_percent_read = true;
+	fan_speed_info->supports_percent_write = true;
 	fan_speed_info->supports_rpm_read = true;
 	fan_speed_info->supports_rpm_write = true;
 
@@ -61,6 +183,31 @@ int vega20_fan_ctrl_get_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t *speed)
 	return vega20_get_current_rpm(hwmgr, speed);
 }
 
+int vega20_fan_ctrl_set_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t speed)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t tach_period, crystal_clock_freq;
+	int result = 0;
+
+	if (!speed)
+		return -EINVAL;
+
+	if (PP_CAP(PHM_PlatformCaps_MicrocodeFanControl)) {
+		result = vega20_fan_ctrl_stop_smc_fan_control(hwmgr);
+		if (result)
+			return result;
+	}
+
+	crystal_clock_freq = amdgpu_asic_get_xclk((struct amdgpu_device *)hwmgr->adev);
+	tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed);
+	WREG32_SOC15(THM, 0, mmCG_TACH_CTRL,
+			REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_TACH_CTRL),
+				CG_TACH_CTRL, TARGET_PERIOD,
+				tach_period));
+
+	return vega20_fan_ctrl_set_static_mode(hwmgr, FDO_PWM_MODE_STATIC_RPM);
+}
+
 /**
 * Reads the remote temperature from the SIslands thermal controller.
 *
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.h
index 2a6d49fec4e0..2d1769bbd24e 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.h
@@ -50,15 +50,22 @@ struct vega20_temperature {
 #define FDO_PWM_MODE_STATIC_RPM 5
 
 extern int vega20_thermal_get_temperature(struct pp_hwmgr *hwmgr);
-extern int vega20_thermal_stop_thermal_controller(struct pp_hwmgr *hwmgr);
 extern int vega20_fan_ctrl_get_fan_speed_info(struct pp_hwmgr *hwmgr,
 		struct phm_fan_speed_info *fan_speed_info);
-extern int vega20_fan_ctrl_reset_fan_speed_to_default(struct pp_hwmgr *hwmgr);
 extern int vega20_fan_ctrl_get_fan_speed_rpm(struct pp_hwmgr *hwmgr,
 		uint32_t *speed);
+extern int vega20_fan_ctrl_set_fan_speed_rpm(struct pp_hwmgr *hwmgr,
+		uint32_t speed);
+extern int vega20_fan_ctrl_get_fan_speed_percent(struct pp_hwmgr *hwmgr,
+		uint32_t *speed);
+extern int vega20_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
+		uint32_t speed);
+extern int vega20_fan_ctrl_stop_smc_fan_control(struct pp_hwmgr *hwmgr);
+extern int vega20_fan_ctrl_start_smc_fan_control(struct pp_hwmgr *hwmgr);
 extern int vega20_thermal_disable_alert(struct pp_hwmgr *hwmgr);
 extern int vega20_start_thermal_controller(struct pp_hwmgr *hwmgr,
 				struct PP_TemperatureRange *range);
+extern int vega20_thermal_stop_thermal_controller(struct pp_hwmgr *hwmgr);
 
 #endif
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index a6d92128b19c..e5a60aa44b5d 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -328,6 +328,8 @@ struct pp_hwmgr_func {
 	int (*set_power_limit)(struct pp_hwmgr *hwmgr, uint32_t n);
 	int (*powergate_mmhub)(struct pp_hwmgr *hwmgr);
 	int (*smus_notify_pwe)(struct pp_hwmgr *hwmgr);
+	int (*powergate_sdma)(struct pp_hwmgr *hwmgr, bool bgate);
+	int (*enable_mgpu_fan_boost)(struct pp_hwmgr *hwmgr);
 };
 
 struct pp_table_func {
@@ -732,7 +734,6 @@ struct pp_hwmgr {
 	void *smu_backend;
 	const struct pp_smumgr_func *smumgr_funcs;
 	bool is_kicker;
-	bool reload_fw;
 
 	enum PP_DAL_POWERLEVEL dal_power_level;
 	struct phm_dynamic_state_info dyn_state;
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h
index 71191deb4e76..a002021414ff 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h
@@ -268,6 +268,12 @@ typedef enum {
   PPCLK_COUNT,
 } PPCLK_e;
 
+typedef enum {
+  POWER_SOURCE_AC,
+  POWER_SOURCE_DC,
+  POWER_SOURCE_COUNT,
+} POWER_SOURCE_e;
+
 typedef enum {
   VOLTAGE_MODE_AVFS = 0,
   VOLTAGE_MODE_AVFS_SS,
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
index 18643e06bc6f..669bd0c2a16c 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
@@ -2269,11 +2269,13 @@ static uint32_t ci_get_offsetof(uint32_t type, uint32_t member)
 		case DRAM_LOG_BUFF_SIZE:
 			return offsetof(SMU7_SoftRegisters, DRAM_LOG_BUFF_SIZE);
 		}
+		break;
 	case SMU_Discrete_DpmTable:
 		switch (member) {
 		case LowSclkInterruptThreshold:
 			return offsetof(SMU7_Discrete_DpmTable, LowSclkInterruptT);
 		}
+		break;
 	}
 	pr_debug("can't get the offset of type %x member %x\n", type, member);
 	return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
index ec14798e87b6..bc8375cbf297 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
@@ -302,16 +302,6 @@ static int fiji_start_smu(struct pp_hwmgr *hwmgr)
 			hwmgr->avfs_supported = false;
 	}
 
-	/* To initialize all clock gating before RLC loaded and running.*/
-	amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
-			AMD_IP_BLOCK_TYPE_GFX, AMD_CG_STATE_GATE);
-	amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
-			AMD_IP_BLOCK_TYPE_GMC, AMD_CG_STATE_GATE);
-	amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
-			AMD_IP_BLOCK_TYPE_SDMA, AMD_CG_STATE_GATE);
-	amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
-			AMD_IP_BLOCK_TYPE_COMMON, AMD_CG_STATE_GATE);
-
 	/* Setup SoftRegsStart here for register lookup in case
 	 * DummyBackEnd is used and ProcessFirmwareHeader is not executed
 	 */
@@ -2331,6 +2321,7 @@ static uint32_t fiji_get_offsetof(uint32_t type, uint32_t member)
 		case DRAM_LOG_BUFF_SIZE:
 			return offsetof(SMU73_SoftRegisters, DRAM_LOG_BUFF_SIZE);
 		}
+		break;
 	case SMU_Discrete_DpmTable:
 		switch (member) {
 		case UvdBootLevel:
@@ -2340,6 +2331,7 @@ static uint32_t fiji_get_offsetof(uint32_t type, uint32_t member)
 		case LowSclkInterruptThreshold:
 			return offsetof(SMU73_Discrete_DpmTable, LowSclkInterruptThreshold);
 		}
+		break;
 	}
 	pr_warn("can't get the offset of type %x member %x\n", type, member);
 	return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c
index 73aa368a454e..375ccf6ff5f2 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c
@@ -232,26 +232,25 @@ static int iceland_request_smu_load_specific_fw(struct pp_hwmgr *hwmgr,
 
 static int iceland_start_smu(struct pp_hwmgr *hwmgr)
 {
+	struct iceland_smumgr *priv = hwmgr->smu_backend;
 	int result;
 
-	result = iceland_smu_upload_firmware_image(hwmgr);
-	if (result)
-		return result;
-	result = iceland_smu_start_smc(hwmgr);
-	if (result)
-		return result;
-
 	if (!smu7_is_smc_ram_running(hwmgr)) {
-		pr_info("smu not running, upload firmware again \n");
 		result = iceland_smu_upload_firmware_image(hwmgr);
 		if (result)
 			return result;
 
-		result = iceland_smu_start_smc(hwmgr);
-		if (result)
-			return result;
+		iceland_smu_start_smc(hwmgr);
 	}
 
+	/* Setup SoftRegsStart here to visit the register UcodeLoadStatus
+	 * to check fw loading state
+	 */
+	smu7_read_smc_sram_dword(hwmgr,
+			SMU71_FIRMWARE_HEADER_LOCATION +
+			offsetof(SMU71_Firmware_Header, SoftRegisters),
+			&(priv->smu7_data.soft_regs_start), 0x40000);
+
 	result = smu7_request_smu_load_fw(hwmgr);
 
 	return result;
@@ -2237,11 +2236,13 @@ static uint32_t iceland_get_offsetof(uint32_t type, uint32_t member)
 		case DRAM_LOG_BUFF_SIZE:
 			return offsetof(SMU71_SoftRegisters, DRAM_LOG_BUFF_SIZE);
 		}
+		break;
 	case SMU_Discrete_DpmTable:
 		switch (member) {
 		case LowSclkInterruptThreshold:
 			return offsetof(SMU71_Discrete_DpmTable, LowSclkInterruptThreshold);
 		}
+		break;
 	}
 	pr_warn("can't get the offset of type %x member %x\n", type, member);
 	return 0;
@@ -2662,7 +2663,7 @@ const struct pp_smumgr_func iceland_smu_funcs = {
 	.smu_fini = &smu7_smu_fini,
 	.start_smu = &iceland_start_smu,
 	.check_fw_load_finish = &smu7_check_fw_load_finish,
-	.request_smu_load_fw = &smu7_reload_firmware,
+	.request_smu_load_fw = &smu7_request_smu_load_fw,
 	.request_smu_load_specific_fw = &iceland_request_smu_load_specific_fw,
 	.send_msg_to_smc = &smu7_send_msg_to_smc,
 	.send_msg_to_smc_with_parameter = &smu7_send_msg_to_smc_with_parameter,
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
index 6f961dec2088..d0eb8ab50148 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
@@ -186,40 +186,12 @@ static int smu10_verify_smc_interface(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-/* sdma is disabled by default in vbios, need to re-enable in driver */
-static void smu10_smc_enable_sdma(struct pp_hwmgr *hwmgr)
-{
-	smu10_send_msg_to_smc(hwmgr,
-			PPSMC_MSG_PowerUpSdma);
-}
-
-static void smu10_smc_disable_sdma(struct pp_hwmgr *hwmgr)
-{
-	smu10_send_msg_to_smc(hwmgr,
-			PPSMC_MSG_PowerDownSdma);
-}
-
-/* vcn is disabled by default in vbios, need to re-enable in driver */
-static void smu10_smc_enable_vcn(struct pp_hwmgr *hwmgr)
-{
-	smu10_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_PowerUpVcn, 0);
-}
-
-static void smu10_smc_disable_vcn(struct pp_hwmgr *hwmgr)
-{
-	smu10_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_PowerDownVcn, 0);
-}
-
 static int smu10_smu_fini(struct pp_hwmgr *hwmgr)
 {
 	struct smu10_smumgr *priv =
 			(struct smu10_smumgr *)(hwmgr->smu_backend);
 
 	if (priv) {
-		smu10_smc_disable_sdma(hwmgr);
-		smu10_smc_disable_vcn(hwmgr);
 		amdgpu_bo_free_kernel(&priv->smu_tables.entry[SMU10_WMTABLE].handle,
 					&priv->smu_tables.entry[SMU10_WMTABLE].mc_addr,
 					&priv->smu_tables.entry[SMU10_WMTABLE].table);
@@ -243,8 +215,7 @@ static int smu10_start_smu(struct pp_hwmgr *hwmgr)
 
 	if (smu10_verify_smc_interface(hwmgr))
 		return -EINVAL;
-	smu10_smc_enable_sdma(hwmgr);
-	smu10_smc_enable_vcn(hwmgr);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
index 186dafc7f166..3f51d545e8ff 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
@@ -302,44 +302,6 @@ int smu7_write_smc_sram_dword(struct pp_hwmgr *hwmgr, uint32_t smc_addr, uint32_
 	return 0;
 }
 
-/* Convert the firmware type to SMU type mask. For MEC, we need to check all MEC related type */
-
-static uint32_t smu7_get_mask_for_firmware_type(uint32_t fw_type)
-{
-	uint32_t result = 0;
-
-	switch (fw_type) {
-	case UCODE_ID_SDMA0:
-		result = UCODE_ID_SDMA0_MASK;
-		break;
-	case UCODE_ID_SDMA1:
-		result = UCODE_ID_SDMA1_MASK;
-		break;
-	case UCODE_ID_CP_CE:
-		result = UCODE_ID_CP_CE_MASK;
-		break;
-	case UCODE_ID_CP_PFP:
-		result = UCODE_ID_CP_PFP_MASK;
-		break;
-	case UCODE_ID_CP_ME:
-		result = UCODE_ID_CP_ME_MASK;
-		break;
-	case UCODE_ID_CP_MEC:
-	case UCODE_ID_CP_MEC_JT1:
-	case UCODE_ID_CP_MEC_JT2:
-		result = UCODE_ID_CP_MEC_MASK;
-		break;
-	case UCODE_ID_RLC_G:
-		result = UCODE_ID_RLC_G_MASK;
-		break;
-	default:
-		pr_info("UCode type is out of range! \n");
-		result = 0;
-	}
-
-	return result;
-}
-
 static int smu7_populate_single_firmware_entry(struct pp_hwmgr *hwmgr,
 						uint32_t fw_type,
 						struct SMU_Entry *entry)
@@ -381,10 +343,7 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 	uint32_t fw_to_load;
 	int r = 0;
 
-	if (!hwmgr->reload_fw) {
-		pr_info("skip reloading...\n");
-		return 0;
-	}
+	amdgpu_ucode_init_bo(hwmgr->adev);
 
 	if (smu_data->soft_regs_start)
 		cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
@@ -467,10 +426,13 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 	smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_HI, upper_32_bits(smu_data->header_buffer.mc_addr));
 	smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_LO, lower_32_bits(smu_data->header_buffer.mc_addr));
 
-	if (smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_LoadUcodes, fw_to_load))
-		pr_err("Fail to Request SMU Load uCode");
+	smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_LoadUcodes, fw_to_load);
 
-	return r;
+	r = smu7_check_fw_load_finish(hwmgr, fw_to_load);
+	if (!r)
+		return 0;
+
+	pr_err("SMU load firmware failed\n");
 
 failed:
 	kfree(smu_data->toc);
@@ -482,13 +444,12 @@ failed:
 int smu7_check_fw_load_finish(struct pp_hwmgr *hwmgr, uint32_t fw_type)
 {
 	struct smu7_smumgr *smu_data = (struct smu7_smumgr *)(hwmgr->smu_backend);
-	uint32_t fw_mask = smu7_get_mask_for_firmware_type(fw_type);
 	uint32_t ret;
 
 	ret = phm_wait_on_indirect_register(hwmgr, mmSMC_IND_INDEX_11,
 					smu_data->soft_regs_start + smum_get_offsetof(hwmgr,
 					SMU_SoftRegisters, UcodeLoadStatus),
-					fw_mask, fw_mask);
+					fw_type, fw_type);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
index a74c5be1ec18..f836d30fdd44 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
@@ -658,11 +658,10 @@ static int smu8_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 {
 	struct smu8_smumgr *smu8_smu = hwmgr->smu_backend;
 	uint32_t smc_address;
+	uint32_t fw_to_check = 0;
+	int ret;
 
-	if (!hwmgr->reload_fw) {
-		pr_info("skip reloading...\n");
-		return 0;
-	}
+	amdgpu_ucode_init_bo(hwmgr->adev);
 
 	smu8_smu_populate_firmware_entries(hwmgr);
 
@@ -689,15 +688,39 @@ static int smu8_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 	smu8_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_ExecuteJob,
 				smu8_smu->toc_entry_power_profiling_index);
 
-	return smu8_send_msg_to_smc_with_parameter(hwmgr,
+	smu8_send_msg_to_smc_with_parameter(hwmgr,
 					PPSMC_MSG_ExecuteJob,
 					smu8_smu->toc_entry_initialize_index);
+
+	fw_to_check = UCODE_ID_RLC_G_MASK |
+			UCODE_ID_SDMA0_MASK |
+			UCODE_ID_SDMA1_MASK |
+			UCODE_ID_CP_CE_MASK |
+			UCODE_ID_CP_ME_MASK |
+			UCODE_ID_CP_PFP_MASK |
+			UCODE_ID_CP_MEC_JT1_MASK |
+			UCODE_ID_CP_MEC_JT2_MASK;
+
+	if (hwmgr->chip_id == CHIP_STONEY)
+		fw_to_check &= ~(UCODE_ID_SDMA1_MASK | UCODE_ID_CP_MEC_JT2_MASK);
+
+	ret = smu8_check_fw_load_finish(hwmgr, fw_to_check);
+	if (ret) {
+		pr_err("SMU firmware load failed\n");
+		return ret;
+	}
+
+	ret = smu8_load_mec_firmware(hwmgr);
+	if (ret) {
+		pr_err("Mec Firmware load failed\n");
+		return ret;
+	}
+
+	return 0;
 }
 
 static int smu8_start_smu(struct pp_hwmgr *hwmgr)
 {
-	int ret = 0;
-	uint32_t fw_to_check = 0;
 	struct amdgpu_device *adev = hwmgr->adev;
 
 	uint32_t index = SMN_MP1_SRAM_START_ADDR +
@@ -712,31 +735,7 @@ static int smu8_start_smu(struct pp_hwmgr *hwmgr)
 	hwmgr->smu_version = cgs_read_register(hwmgr->device, mmMP0PUB_IND_DATA);
 	adev->pm.fw_version = hwmgr->smu_version >> 8;
 
-	fw_to_check = UCODE_ID_RLC_G_MASK |
-			UCODE_ID_SDMA0_MASK |
-			UCODE_ID_SDMA1_MASK |
-			UCODE_ID_CP_CE_MASK |
-			UCODE_ID_CP_ME_MASK |
-			UCODE_ID_CP_PFP_MASK |
-			UCODE_ID_CP_MEC_JT1_MASK |
-			UCODE_ID_CP_MEC_JT2_MASK;
-
-	if (hwmgr->chip_id == CHIP_STONEY)
-		fw_to_check &= ~(UCODE_ID_SDMA1_MASK | UCODE_ID_CP_MEC_JT2_MASK);
-
-	smu8_request_smu_load_fw(hwmgr);
-
-	ret = smu8_check_fw_load_finish(hwmgr, fw_to_check);
-	if (ret) {
-		pr_err("SMU firmware load failed\n");
-		return ret;
-	}
-
-	ret = smu8_load_mec_firmware(hwmgr);
-	if (ret)
-		pr_err("Mec Firmware load failed\n");
-
-	return ret;
+	return smu8_request_smu_load_fw(hwmgr);
 }
 
 static int smu8_smu_init(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
index ae8378ed32ee..3ed6c5f1e5cf 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
@@ -192,6 +192,7 @@ static int tonga_start_in_non_protection_mode(struct pp_hwmgr *hwmgr)
 
 static int tonga_start_smu(struct pp_hwmgr *hwmgr)
 {
+	struct tonga_smumgr *priv = hwmgr->smu_backend;
 	int result;
 
 	/* Only start SMC if SMC RAM is not running */
@@ -209,6 +210,14 @@ static int tonga_start_smu(struct pp_hwmgr *hwmgr)
 		}
 	}
 
+	/* Setup SoftRegsStart here to visit the register UcodeLoadStatus
+	 * to check fw loading state
+	 */
+	smu7_read_smc_sram_dword(hwmgr,
+			SMU72_FIRMWARE_HEADER_LOCATION +
+			offsetof(SMU72_Firmware_Header, SoftRegisters),
+			&(priv->smu7_data.soft_regs_start), 0x40000);
+
 	result = smu7_request_smu_load_fw(hwmgr);
 
 	return result;
@@ -2619,6 +2628,7 @@ static uint32_t tonga_get_offsetof(uint32_t type, uint32_t member)
 		case DRAM_LOG_BUFF_SIZE:
 			return offsetof(SMU72_SoftRegisters, DRAM_LOG_BUFF_SIZE);
 		}
+		break;
 	case SMU_Discrete_DpmTable:
 		switch (member) {
 		case UvdBootLevel:
@@ -2628,6 +2638,7 @@ static uint32_t tonga_get_offsetof(uint32_t type, uint32_t member)
 		case LowSclkInterruptThreshold:
 			return offsetof(SMU72_Discrete_DpmTable, LowSclkInterruptThreshold);
 		}
+		break;
 	}
 	pr_warn("can't get the offset of type %x member %x\n", type, member);
 	return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
index 3d415fabbd93..9f71512b2510 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
@@ -2185,6 +2185,7 @@ static uint32_t vegam_get_offsetof(uint32_t type, uint32_t member)
 		case DRAM_LOG_BUFF_SIZE:
 			return offsetof(SMU75_SoftRegisters, DRAM_LOG_BUFF_SIZE);
 		}
+		break;
 	case SMU_Discrete_DpmTable:
 		switch (member) {
 		case UvdBootLevel:
@@ -2194,6 +2195,7 @@ static uint32_t vegam_get_offsetof(uint32_t type, uint32_t member)
 		case LowSclkInterruptThreshold:
 			return offsetof(SMU75_Discrete_DpmTable, LowSclkInterruptThreshold);
 		}
+		break;
 	}
 	pr_warn("can't get the offset of type %x member %x\n", type, member);
 	return 0;
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 54324330b91f..f471537c852f 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -2416,7 +2416,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 				size = radeon_get_ib_value(p, idx+1+(i*8)+1);
 				if (p->rdev && (size + offset) > radeon_bo_size(reloc->robj)) {
 					/* force size to size of the buffer */
-					dev_warn(p->dev, "vbo resource seems too big for the bo\n");
+					dev_warn_ratelimited(p->dev, "vbo resource seems too big for the bo\n");
 					ib[idx+1+(i*8)+1] = radeon_bo_size(reloc->robj) - offset;
 				}
 
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 4e5e95c0cab5..3e22a54a99c2 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -467,8 +467,7 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity)
 	struct dma_fence *fence;
 	struct drm_sched_rq *rq;
 
-	if (!spsc_queue_count(&entity->job_queue) == 0 ||
-	    entity->num_rq_list <= 1)
+	if (spsc_queue_count(&entity->job_queue) || entity->num_rq_list <= 1)
 		return;
 
 	fence = READ_ONCE(entity->last_scheduled);
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index b2a33bf1ef10..26b889f86670 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -247,20 +247,6 @@ void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo,
 }
 EXPORT_SYMBOL(ttm_bo_move_to_lru_tail);
 
-static void ttm_list_move_bulk_tail(struct list_head *list,
-				    struct list_head *first,
-				    struct list_head *last)
-{
-	first->prev->next = last->next;
-	last->next->prev = first->prev;
-
-	list->prev->next = first;
-	first->prev = list->prev;
-
-	last->next = list;
-	list->prev = last;
-}
-
 void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk)
 {
 	unsigned i;
@@ -276,8 +262,8 @@ void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk)
 		reservation_object_assert_held(pos->last->resv);
 
 		man = &pos->first->bdev->man[TTM_PL_TT];
-		ttm_list_move_bulk_tail(&man->lru[i], &pos->first->lru,
-					&pos->last->lru);
+		list_bulk_move_tail(&man->lru[i], &pos->first->lru,
+				    &pos->last->lru);
 	}
 
 	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) {
@@ -291,8 +277,8 @@ void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk)
 		reservation_object_assert_held(pos->last->resv);
 
 		man = &pos->first->bdev->man[TTM_PL_VRAM];
-		ttm_list_move_bulk_tail(&man->lru[i], &pos->first->lru,
-					&pos->last->lru);
+		list_bulk_move_tail(&man->lru[i], &pos->first->lru,
+				    &pos->last->lru);
 	}
 
 	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) {
@@ -306,8 +292,7 @@ void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk)
 		reservation_object_assert_held(pos->last->resv);
 
 		lru = &pos->first->bdev->glob->swap_lru[i];
-		ttm_list_move_bulk_tail(lru, &pos->first->swap,
-					&pos->last->swap);
+		list_bulk_move_tail(lru, &pos->first->swap, &pos->last->swap);
 	}
 }
 EXPORT_SYMBOL(ttm_bo_bulk_move_lru_tail);
diff --git a/include/linux/list.h b/include/linux/list.h
index de04cc5ed536..edb7628e46ed 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -183,6 +183,29 @@ static inline void list_move_tail(struct list_head *list,
 	list_add_tail(list, head);
 }
 
+/**
+ * list_bulk_move_tail - move a subsection of a list to its tail
+ * @head: the head that will follow our entry
+ * @first: first entry to move
+ * @last: last entry to move, can be the same as first
+ *
+ * Move all entries between @first and including @last before @head.
+ * All three entries must belong to the same linked list.
+ */
+static inline void list_bulk_move_tail(struct list_head *head,
+				       struct list_head *first,
+				       struct list_head *last)
+{
+	first->prev->next = last->next;
+	last->next->prev = first->prev;
+
+	head->prev->next = first;
+	first->prev = head->prev;
+
+	last->next = head;
+	head->prev = last;
+}
+
 /**
  * list_is_last - tests whether @list is the last entry in list @head
  * @list: the entry to test