Merge tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "Highlights are usual, more AMD IP blocks for future hw, i915/xe
  changes, Displayport tunnelling support for i915, msm YUV over DP
  changes, new tests for ttm, but its mostly a lot of stuff all over the
  place from lots of people.

  core:
   - EDID cleanups
   - scheduler error handling fixes
   - managed: add drmm_release_action() with tests
   - add ratelimited drm debug print
   - DPCD PSR early transport macro
   - DP tunneling and bandwidth allocation helpers
   - remove built-in edids
   - dp: Avoid AUX transfers on powered-down displays
   - dp: Add VSC SDP helpers

  cross drivers:
   - use new drm print helpers
   - switch to ->read_edid callback
   - gem: add stats for shared buffers plus updates to amdgpu, i915, xe

  syncobj:
   - fixes to waiting and sleeping

  ttm:
   - add tests
   - fix errno codes
   - simply busy-placement handling
   - fix page decryption

  media:
   - tc358743: fix v4l device registration

  video:
   - move all kernel parameters for video behind CONFIG_VIDEO

  sound:
   - remove <drm/drm_edid.h> include from header

  ci:
   - add tests for msm
   - fix apq8016 runner

  efifb:
   - use copy of global screen_info state

  vesafb:
   - use copy of global screen_info state

  simplefb:
   - fix logging

  bridge:
   - ite-6505: fix DP link-training bug
   - samsung-dsim: fix error checking in probe
   - samsung-dsim: add bsh-smm-s2/pro boards
   - tc358767: fix regmap usage
   - imx: add i.MX8MP HDMI PVI plus DT bindings
   - imx: add i.MX8MP HDMI TX plus DT bindings
   - sii902x: fix probing and unregistration
   - tc358767: limit pixel PLL input range
   - switch to new drm_bridge_read_edid() interface

  panel:
   - ltk050h3146w: error-handling fixes
   - panel-edp: support delay between power-on and enable; use put_sync
     in unprepare; support Mediatek MT8173 Chromebooks, BOE NV116WHM-N49
     V8.0, BOE NV122WUM-N41, CSO MNC207QS1-1 plus DT bindings
   - panel-lvds: support EDT ETML0700Z9NDHA plus DT bindings
   - panel-novatek: FRIDA FRD400B25025-A-CTK plus DT bindings
   - add BOE TH101MB31IG002-28A plus DT bindings
   - add EDT ETML1010G3DRA plus DT bindings
   - add Novatek NT36672E LCD DSI plus DT bindings
   - nt36523: support 120Hz timings, fix includes
   - simple: fix display timings on RK32FN48H
   - visionox-vtdr6130: fix initialization
   - add Powkiddy RGB10MAX3 plus DT bindings
   - st7703: support panel rotation plus DT bindings
   - add Himax HX83112A plus DT bindings
   - ltk500hd1829: add support for ltk101b4029w and admatec 9904370
   - simple: add BOE BP082WX1-100 8.2" panel plus DT bindungs

  panel-orientation-quirks:
   - GPD Win Mini

  amdgpu:
   - Validate DMABuf imports in compute VMs
   - Add RAS ACA framework
   - PSP 13 fixes
   - Misc code cleanups
   - Replay fixes
   - Atom interpretor PS, WS bounds checking
   - DML2 fixes
   - Audio fixes
   - DCN 3.5 Z state fixes
   - Remove deprecated ida_simple usage
   - UBSAN fixes
   - RAS fixes
   - Enable seq64 infrastructure
   - DC color block enablement
   - Documentation updates
   - DC documentation updates
   - DMCUB updates
   - ATHUB 4.1 support
   - LSDMA 7.0 support
   - JPEG DPG support
   - IH 7.0 support
   - HDP 7.0 support
   - VCN 5.0 support
   - SMU 13.0.6 updates
   - NBIO 7.11 updates
   - SDMA 6.1 updates
   - MMHUB 3.3 updates
   - DCN 3.5.1 support
   - NBIF 6.3.1 support
   - VPE 6.1.1 support

  amdkfd:
   - Validate DMABuf imports in compute VMs
   - SVM fixes
   - Trap handler updates and enhancements
   - Fix cache size reporting
   - Relocate the trap handler

  radeon:
   - Atom interpretor PS, WS bounds checking
   - Misc code cleanups

  xe:
   - new query for GuC submission version
   - Remove unused persistent exec_queues
   - Add vram frequency sysfs attributes
   - Add the flag XE_VM_BIND_FLAG_DUMPABLE
   - Drop pre-production workarounds
   - Drop kunit tests for unsupported platforms
   - Start pumbling SR-IOV support with memory based interrupts for VF
   - Allow to map BO in GGTT with PAT index corresponding to XE_CACHE_UC
     to work with memory based interrupts
   - Add GuC Doorbells Manager as prep work SR-IOV
   - Implement additional workarounds for xe2 and MTL
   - Program a few registers according to perfomance guide spec for Xe2
   - Fix remaining 32b build issues and enable it back
   - Fix build with CONFIG_DEBUG_FS=n
   - Fix warnings from GuC ABI headers
   - Introduce Relay Communication for SR-IOV for VF <-> GuC <-> PF
   - Release mmap mappings on rpm suspend
   - Disable mid-thread preemption when not properly supported by
     hardware
   - Fix xe_exec by reserving extra fence slot for CPU bind
   - Fix xe_exec with full long running exec queue
   - Canonicalize addresses where needed for Xe2 and add to devcoredum
   - Toggle USM support for Xe2
   - Only allow 1 ufence per exec / bind IOCTL
   - Add GuC firmware loading for Lunar Lake
   - Add XE_VMA_PTE_64K VMA flag

  i915:
   - Add more ADL-N PCI IDs
   - Enable fastboot also on older platforms
   - Early transport for panel replay and PSR
   - New ARL PCI IDs
   - DP TPS4 PHY test pattern support
   - Unify and improve VSC SDP for PSR and non-PSR cases
   - Refactor memory regions and improve debug logging
   - Rework global state serialization
   - Remove unused CDCLK divider fields
   - Unify HDCP connector logging format
   - Use display instead of graphics version in display code
   - Move VBT and opregion debugfs next to the implementation
   - Abstract opregion interface, use opaque type
   - MTL fixes
   - HPD handling fixes
   - Add GuC submission interface version query
   - Atomically invalidate userptr on mmu-notifier
   - Update handling of MMIO triggered reports
   - Don't make assumptions about intel_wakeref_t type
   - Extend driver code of Xe_LPG to Xe_LPG+
   - Add flex arrays to struct i915_syncmap
   - Allow for very slow HuC loading
   - DP tunneling and bandwidth allocation support

  msm:
   - Correct bindings for MSM8976 and SM8650 platforms
   - Start migration of MDP5 platforms to DPU driver
   - X1E80100 MDSS support
   - DPU:
      - Improve DSC allocation, fixing several important corner cases
      - Add support for SDM630/SDM660 platforms
      - Simplify dpu_encoder_phys_ops
      - Apply fixes targeting DSC support with a single DSC encoder
      - Apply fixes for HCTL_EN timing configuration
      - X1E80100 support
      - Add support for YUV420 over DP
   - GPU:
      - fix sc7180 UBWC config
      - fix a7xx LLC config
      - new gpu support: a305B, a750, a702
      - machine support: SM7150 (different power levels than other a618)
      - a7xx devcoredump support

  habanalabs:
   - configure IRQ affinity according to NUMA node
   - move HBM MMU page tables inside the HBM
   - improve device reset
   - check extended PCIe errors

  ivpu:
   - updates to firmware API
   - refactor BO allocation

  imx:
   - use devm_ functions during init

  hisilicon:
   - fix EDID includes

  mgag200:
   - improve ioremap usage
   - convert to struct drm_edid
   - Work around PCI write bursts

  nouveau:
   - disp: use kmemdup()
   - fix EDID includes
   - documentation fixes

  qaic:
   - fixes to BO handling
   - make use of DRM managed release
   - fix order of remove operations

  rockchip:
   - analogix_dp: get encoder port from DT
   - inno_hdmi: support HDMI for RK3128
   - lvds: error-handling fixes

  ssd130x:
   - support SSD133x plus DT bindings

  tegra:
   - fix error handling

  tilcdc:
   - make use of DRM managed release

  v3d:
   - show memory stats in debugfs
   - Support display MMU page size

  vc4:
   - fix error handling in plane prepare_fb
   - fix framebuffer test in plane helpers

  virtio:
   - add venus capset defines

  vkms:
   - fix OOB access when programming the LUT
   - Kconfig improvements

  vmwgfx:
   - unmap surface before changing plane state
   - fix memory leak in error handling
   - documentation fixes
   - list command SVGA_3D_CMD_DEFINE_GB_SURFACE_V4 as invalid
   - fix null-pointer deref in execbuf
   - refactor display-mode probing
   - fix fencing for creating cursor MOBs
   - fix cursor-memory lifetime

  xlnx:
   - fix live video input for ZynqMP DPSUB

  lima:
   - fix memory leak

  loongson:
   - fail if no VRAM present

  meson:
   - switch to new drm_bridge_read_edid() interface

  renesas:
   - add RZ/G2L DU support plus DT bindings

  mxsfb:
   - Use managed mode config

  sun4i:
   - HDMI: updates to atomic mode setting

  mediatek:
   - Add display driver for MT8188 VDOSYS1
   - DSI driver cleanups
   - Filter modes according to hardware capability
   - Fix a null pointer crash in mtk_drm_crtc_finish_page_flip

  etnaviv:
   - enhancements for NPU and MRT support"

* tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel: (1420 commits)
  drm/amd/display: Removed redundant @ symbol to fix kernel-doc warnings in -next repo
  drm/amd/pm: wait for completion of the EnableGfxImu message
  drm/amdgpu/soc21: add mode2 asic reset for SMU IP v14.0.1
  drm/amdgpu: add smu 14.0.1 support
  drm/amdgpu: add VPE 6.1.1 discovery support
  drm/amdgpu/vpe: add VPE 6.1.1 support
  drm/amdgpu/vpe: don't emit cond exec command under collaborate mode
  drm/amdgpu/vpe: add collaborate mode support for VPE
  drm/amdgpu/vpe: add PRED_EXE and COLLAB_SYNC OPCODE
  drm/amdgpu/vpe: add multi instance VPE support
  drm/amdgpu/discovery: add nbif v6_3_1 ip block
  drm/amdgpu: Add nbif v6_3_1 ip block support
  drm/amdgpu: Add pcie v6_1_0 ip headers (v5)
  drm/amdgpu: Add nbif v6_3_1 ip headers (v5)
  arch/powerpc: Remove <linux/fb.h> from backlight code
  macintosh/via-pmu-backlight: Include <linux/backlight.h>
  fbdev/chipsfb: Include <linux/backlight.h>
  drm/etnaviv: Restore some id values
  drm/amdkfd: make kfd_class constant
  drm/amdgpu: add ring timeout information in devcoredump
  ...

18 files changed, 496 insertions, 125 deletions

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 6627ee07d52d..f84bfed50681 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -693,6 +693,21 @@ int amdgpu_dpm_send_hbm_bad_channel_flag(struct amdgpu_device *adev, uint32_t si
 	return ret;
 }
 
+int amdgpu_dpm_send_rma_reason(struct amdgpu_device *adev)
+{
+	struct smu_context *smu = adev->powerplay.pp_handle;
+	int ret;
+
+	if (!is_support_sw_smu(adev))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&adev->pm.mutex);
+	ret = smu_send_rma_reason(smu);
+	mutex_unlock(&adev->pm.mutex);
+
+	return ret;
+}
+
 int amdgpu_dpm_get_dpm_freq_range(struct amdgpu_device *adev,
 				  enum pp_clock_type type,
 				  uint32_t *min,
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 39c5e1dfa275..f09b9d49297e 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -2034,6 +2034,63 @@ static int ss_bias_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 	return 0;
 }
 
+static int pp_od_clk_voltage_attr_update(struct amdgpu_device *adev, struct amdgpu_device_attr *attr,
+					 uint32_t mask, enum amdgpu_device_attr_states *states)
+{
+	uint32_t gc_ver = amdgpu_ip_version(adev, GC_HWIP, 0);
+
+	*states = ATTR_STATE_SUPPORTED;
+
+	if (!amdgpu_dpm_is_overdrive_supported(adev)) {
+		*states = ATTR_STATE_UNSUPPORTED;
+		return 0;
+	}
+
+	/* Enable pp_od_clk_voltage node for gc 9.4.3 SRIOV/BM support */
+	if (gc_ver == IP_VERSION(9, 4, 3)) {
+		if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+			*states = ATTR_STATE_UNSUPPORTED;
+		return 0;
+	}
+
+	if (!(attr->flags & mask))
+		*states = ATTR_STATE_UNSUPPORTED;
+
+	return 0;
+}
+
+static int pp_dpm_dcefclk_attr_update(struct amdgpu_device *adev, struct amdgpu_device_attr *attr,
+				      uint32_t mask, enum amdgpu_device_attr_states *states)
+{
+	struct device_attribute *dev_attr = &attr->dev_attr;
+	uint32_t gc_ver;
+
+	*states = ATTR_STATE_SUPPORTED;
+
+	if (!(attr->flags & mask)) {
+		*states = ATTR_STATE_UNSUPPORTED;
+		return 0;
+	}
+
+	gc_ver = amdgpu_ip_version(adev, GC_HWIP, 0);
+	/* dcefclk node is not available on gfx 11.0.3 sriov */
+	if ((gc_ver == IP_VERSION(11, 0, 3) && amdgpu_sriov_is_pp_one_vf(adev)) ||
+	    gc_ver < IP_VERSION(9, 0, 0) ||
+	    !amdgpu_device_has_display_hardware(adev))
+		*states = ATTR_STATE_UNSUPPORTED;
+
+	/* SMU MP1 does not support dcefclk level setting,
+	 * setting should not be allowed from VF if not in one VF mode.
+	 */
+	if (gc_ver >= IP_VERSION(10, 0, 0) ||
+	    (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))) {
+		dev_attr->attr.mode &= ~S_IWUGO;
+		dev_attr->store = NULL;
+	}
+
+	return 0;
+}
+
 /* Following items will be read out to indicate current plpd policy:
  *  - -1: none
  *  - 0: disallow
@@ -2113,12 +2170,14 @@ static struct amdgpu_device_attr amdgpu_device_attrs[] = {
 	AMDGPU_DEVICE_ATTR_RW(pp_dpm_vclk1,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
 	AMDGPU_DEVICE_ATTR_RW(pp_dpm_dclk,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
 	AMDGPU_DEVICE_ATTR_RW(pp_dpm_dclk1,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
-	AMDGPU_DEVICE_ATTR_RW(pp_dpm_dcefclk,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
+	AMDGPU_DEVICE_ATTR_RW(pp_dpm_dcefclk,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF,
+			      .attr_update = pp_dpm_dcefclk_attr_update),
 	AMDGPU_DEVICE_ATTR_RW(pp_dpm_pcie,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
 	AMDGPU_DEVICE_ATTR_RW(pp_sclk_od,				ATTR_FLAG_BASIC),
 	AMDGPU_DEVICE_ATTR_RW(pp_mclk_od,				ATTR_FLAG_BASIC),
 	AMDGPU_DEVICE_ATTR_RW(pp_power_profile_mode,			ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
-	AMDGPU_DEVICE_ATTR_RW(pp_od_clk_voltage,			ATTR_FLAG_BASIC),
+	AMDGPU_DEVICE_ATTR_RW(pp_od_clk_voltage,			ATTR_FLAG_BASIC,
+			      .attr_update = pp_od_clk_voltage_attr_update),
 	AMDGPU_DEVICE_ATTR_RO(gpu_busy_percent,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
 	AMDGPU_DEVICE_ATTR_RO(mem_busy_percent,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
 	AMDGPU_DEVICE_ATTR_RO(pcie_bw,					ATTR_FLAG_BASIC),
@@ -2156,17 +2215,9 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 	if (DEVICE_ATTR_IS(pp_dpm_socclk)) {
 		if (gc_ver < IP_VERSION(9, 0, 0))
 			*states = ATTR_STATE_UNSUPPORTED;
-	} else if (DEVICE_ATTR_IS(pp_dpm_dcefclk)) {
-		if (gc_ver < IP_VERSION(9, 0, 0) ||
-		    !amdgpu_device_has_display_hardware(adev))
-			*states = ATTR_STATE_UNSUPPORTED;
 	} else if (DEVICE_ATTR_IS(pp_dpm_fclk)) {
 		if (mp1_ver < IP_VERSION(10, 0, 0))
 			*states = ATTR_STATE_UNSUPPORTED;
-	} else if (DEVICE_ATTR_IS(pp_od_clk_voltage)) {
-		*states = ATTR_STATE_UNSUPPORTED;
-		if (amdgpu_dpm_is_overdrive_supported(adev))
-			*states = ATTR_STATE_SUPPORTED;
 	} else if (DEVICE_ATTR_IS(mem_busy_percent)) {
 		if ((adev->flags & AMD_IS_APU &&
 		     gc_ver != IP_VERSION(9, 4, 3)) ||
@@ -2174,7 +2225,8 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 			*states = ATTR_STATE_UNSUPPORTED;
 	} else if (DEVICE_ATTR_IS(pcie_bw)) {
 		/* PCIe Perf counters won't work on APU nodes */
-		if (adev->flags & AMD_IS_APU)
+		if (adev->flags & AMD_IS_APU ||
+		    !adev->asic_funcs->get_pcie_usage)
 			*states = ATTR_STATE_UNSUPPORTED;
 	} else if (DEVICE_ATTR_IS(unique_id)) {
 		switch (gc_ver) {
@@ -2280,14 +2332,6 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 		break;
 	}
 
-	if (DEVICE_ATTR_IS(pp_dpm_dcefclk)) {
-		/* SMU MP1 does not support dcefclk level setting */
-		if (gc_ver >= IP_VERSION(10, 0, 0)) {
-			dev_attr->attr.mode &= ~S_IWUGO;
-			dev_attr->store = NULL;
-		}
-	}
-
 	/* setting should not be allowed from VF if not in one VF mode */
 	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev)) {
 		dev_attr->attr.mode &= ~S_IWUGO;
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index 3047ffe7f244..621200e0823f 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -450,6 +450,7 @@ int amdgpu_pm_load_smu_firmware(struct amdgpu_device *adev, uint32_t *smu_versio
 int amdgpu_dpm_handle_passthrough_sbr(struct amdgpu_device *adev, bool enable);
 int amdgpu_dpm_send_hbm_bad_pages_num(struct amdgpu_device *adev, uint32_t size);
 int amdgpu_dpm_send_hbm_bad_channel_flag(struct amdgpu_device *adev, uint32_t size);
+int amdgpu_dpm_send_rma_reason(struct amdgpu_device *adev);
 int amdgpu_dpm_get_dpm_freq_range(struct amdgpu_device *adev,
 				       enum pp_clock_type type,
 				       uint32_t *min,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c
index f503e61faa60..b1b4c09c3467 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c
@@ -226,7 +226,7 @@ int atomctrl_set_engine_dram_timings_rv770(
 
 	return amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, DynamicMemorySettings),
-			(uint32_t *)&engine_clock_parameters);
+			(uint32_t *)&engine_clock_parameters, sizeof(engine_clock_parameters));
 }
 
 /*
@@ -297,7 +297,7 @@ int atomctrl_get_memory_pll_dividers_si(
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 		 GetIndexIntoMasterTable(COMMAND, ComputeMemoryClockParam),
-		(uint32_t *)&mpll_parameters);
+		(uint32_t *)&mpll_parameters, sizeof(mpll_parameters));
 
 	if (0 == result) {
 		mpll_param->mpll_fb_divider.clk_frac =
@@ -345,7 +345,7 @@ int atomctrl_get_memory_pll_dividers_vi(struct pp_hwmgr *hwmgr,
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ComputeMemoryClockParam),
-			(uint32_t *)&mpll_parameters);
+			(uint32_t *)&mpll_parameters, sizeof(mpll_parameters));
 
 	if (!result)
 		mpll_param->mpll_post_divider =
@@ -366,7 +366,7 @@ int atomctrl_get_memory_pll_dividers_ai(struct pp_hwmgr *hwmgr,
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ComputeMemoryClockParam),
-			(uint32_t *)&mpll_parameters);
+			(uint32_t *)&mpll_parameters, sizeof(mpll_parameters));
 
 	/* VEGAM's mpll takes sometime to finish computing */
 	udelay(10);
@@ -396,7 +396,7 @@ int atomctrl_get_engine_pll_dividers_kong(struct pp_hwmgr *hwmgr,
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 		 GetIndexIntoMasterTable(COMMAND, ComputeMemoryEnginePLL),
-		(uint32_t *)&pll_parameters);
+		(uint32_t *)&pll_parameters, sizeof(pll_parameters));
 
 	if (0 == result) {
 		dividers->pll_post_divider = pll_parameters.ucPostDiv;
@@ -420,7 +420,7 @@ int atomctrl_get_engine_pll_dividers_vi(
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 		 GetIndexIntoMasterTable(COMMAND, ComputeMemoryEnginePLL),
-		(uint32_t *)&pll_patameters);
+		(uint32_t *)&pll_patameters, sizeof(pll_patameters));
 
 	if (0 == result) {
 		dividers->pll_post_divider =
@@ -457,7 +457,7 @@ int atomctrl_get_engine_pll_dividers_ai(struct pp_hwmgr *hwmgr,
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 		 GetIndexIntoMasterTable(COMMAND, ComputeMemoryEnginePLL),
-		(uint32_t *)&pll_patameters);
+		(uint32_t *)&pll_patameters, sizeof(pll_patameters));
 
 	if (0 == result) {
 		dividers->usSclk_fcw_frac     = le16_to_cpu(pll_patameters.usSclk_fcw_frac);
@@ -490,7 +490,7 @@ int atomctrl_get_dfs_pll_dividers_vi(
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 		 GetIndexIntoMasterTable(COMMAND, ComputeMemoryEnginePLL),
-		(uint32_t *)&pll_patameters);
+		(uint32_t *)&pll_patameters, sizeof(pll_patameters));
 
 	if (0 == result) {
 		dividers->pll_post_divider =
@@ -773,7 +773,7 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			(uint32_t *)&sOutput_FuseValues);
+			(uint32_t *)&sOutput_FuseValues, sizeof(sOutput_FuseValues));
 
 	if (result)
 		return result;
@@ -794,7 +794,7 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			(uint32_t *)&sOutput_FuseValues);
+			(uint32_t *)&sOutput_FuseValues, sizeof(sOutput_FuseValues));
 
 	if (result)
 		return result;
@@ -814,7 +814,7 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			(uint32_t *)&sOutput_FuseValues);
+			(uint32_t *)&sOutput_FuseValues, sizeof(sOutput_FuseValues));
 
 	if (result)
 		return result;
@@ -835,7 +835,7 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			(uint32_t *)&sOutput_FuseValues);
+			(uint32_t *)&sOutput_FuseValues, sizeof(sOutput_FuseValues));
 
 	if (result)
 		return result;
@@ -857,7 +857,7 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			(uint32_t *)&sOutput_FuseValues);
+			(uint32_t *)&sOutput_FuseValues, sizeof(sOutput_FuseValues));
 	if (result)
 		return result;
 
@@ -878,7 +878,7 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			(uint32_t *)&sOutput_FuseValues);
+			(uint32_t *)&sOutput_FuseValues, sizeof(sOutput_FuseValues));
 
 	if (result)
 		return result;
@@ -909,7 +909,7 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			(uint32_t *)&sOutput_FuseValues);
+			(uint32_t *)&sOutput_FuseValues, sizeof(sOutput_FuseValues));
 
 	if (result)
 		return result;
@@ -1134,7 +1134,7 @@ int atomctrl_get_voltage_evv_on_sclk(
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, GetVoltageInfo),
-			(uint32_t *)&get_voltage_info_param_space);
+			(uint32_t *)&get_voltage_info_param_space, sizeof(get_voltage_info_param_space));
 
 	*voltage = result ? 0 :
 			le16_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 *)
@@ -1179,7 +1179,7 @@ int atomctrl_get_voltage_evv(struct pp_hwmgr *hwmgr,
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, GetVoltageInfo),
-			(uint32_t *)&get_voltage_info_param_space);
+			(uint32_t *)&get_voltage_info_param_space, sizeof(get_voltage_info_param_space));
 
 	if (0 != result)
 		return result;
@@ -1359,7 +1359,7 @@ int atomctrl_read_efuse(struct pp_hwmgr *hwmgr, uint16_t start_index,
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			(uint32_t *)&efuse_param);
+			(uint32_t *)&efuse_param, sizeof(efuse_param));
 	*efuse = result ? 0 : le32_to_cpu(efuse_param.ulEfuseValue) & mask;
 
 	return result;
@@ -1380,7 +1380,7 @@ int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock,
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 		 GetIndexIntoMasterTable(COMMAND, DynamicMemorySettings),
-		(uint32_t *)&memory_clock_parameters);
+		(uint32_t *)&memory_clock_parameters, sizeof(memory_clock_parameters));
 
 	return result;
 }
@@ -1399,7 +1399,7 @@ int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, GetVoltageInfo),
-			(uint32_t *)&get_voltage_info_param_space);
+			(uint32_t *)&get_voltage_info_param_space, sizeof(get_voltage_info_param_space));
 
 	*voltage = result ? 0 :
 		le32_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)(&get_voltage_info_param_space))->ulVoltageLevel);
@@ -1526,7 +1526,7 @@ int atomctrl_get_leakage_id_from_efuse(struct pp_hwmgr *hwmgr, uint16_t *virtual
 
 	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, SetVoltage),
-			(uint32_t *)voltage_parameters);
+			(uint32_t *)voltage_parameters, sizeof(*voltage_parameters));
 
 	*virtual_voltage_id = voltage_parameters->usVoltageLevel;
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c
index a47a47238e2b..82d540334318 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c
@@ -258,7 +258,7 @@ int pp_atomfwctrl_get_gpu_pll_dividers_vega10(struct pp_hwmgr *hwmgr,
 	idx = GetIndexIntoMasterCmdTable(computegpuclockparam);
 
 	if (amdgpu_atom_execute_table(
-		adev->mode_info.atom_context, idx, (uint32_t *)&pll_parameters))
+		adev->mode_info.atom_context, idx, (uint32_t *)&pll_parameters, sizeof(pll_parameters)))
 		return -EINVAL;
 
 	pll_output = (struct compute_gpu_clock_output_parameter_v1_8 *)
@@ -505,7 +505,7 @@ int pp_atomfwctrl_get_clk_information_by_clkid(struct pp_hwmgr *hwmgr,
 	ix = GetIndexIntoMasterCmdTable(getsmuclockinfo);
 
 	if (amdgpu_atom_execute_table(
-		adev->mode_info.atom_context, ix, (uint32_t *)&parameters))
+		adev->mode_info.atom_context, ix, (uint32_t *)&parameters, sizeof(parameters)))
 		return -EINVAL;
 
 	output = (struct atom_get_smu_clock_info_output_parameters_v3_1 *)&parameters;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 0ad947df777a..246b211b1e85 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -712,6 +712,7 @@ static int smu_set_funcs(struct amdgpu_device *adev)
 		smu_v13_0_7_set_ppt_funcs(smu);
 		break;
 	case IP_VERSION(14, 0, 0):
+	case IP_VERSION(14, 0, 1):
 		smu_v14_0_0_set_ppt_funcs(smu);
 		break;
 	default:
@@ -751,6 +752,7 @@ static int smu_early_init(void *handle)
 
 static int smu_set_default_dpm_table(struct smu_context *smu)
 {
+	struct amdgpu_device *adev = smu->adev;
 	struct smu_power_context *smu_power = &smu->smu_power;
 	struct smu_power_gate *power_gate = &smu_power->power_gate;
 	int vcn_gate, jpeg_gate;
@@ -759,25 +761,34 @@ static int smu_set_default_dpm_table(struct smu_context *smu)
 	if (!smu->ppt_funcs->set_default_dpm_table)
 		return 0;
 
-	vcn_gate = atomic_read(&power_gate->vcn_gated);
-	jpeg_gate = atomic_read(&power_gate->jpeg_gated);
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN)
+		vcn_gate = atomic_read(&power_gate->vcn_gated);
+	if (adev->pg_flags & AMD_PG_SUPPORT_JPEG)
+		jpeg_gate = atomic_read(&power_gate->jpeg_gated);
 
-	ret = smu_dpm_set_vcn_enable(smu, true);
-	if (ret)
-		return ret;
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN) {
+		ret = smu_dpm_set_vcn_enable(smu, true);
+		if (ret)
+			return ret;
+	}
 
-	ret = smu_dpm_set_jpeg_enable(smu, true);
-	if (ret)
-		goto err_out;
+	if (adev->pg_flags & AMD_PG_SUPPORT_JPEG) {
+		ret = smu_dpm_set_jpeg_enable(smu, true);
+		if (ret)
+			goto err_out;
+	}
 
 	ret = smu->ppt_funcs->set_default_dpm_table(smu);
 	if (ret)
 		dev_err(smu->adev->dev,
 			"Failed to setup default dpm clock tables!\n");
 
-	smu_dpm_set_jpeg_enable(smu, !jpeg_gate);
+	if (adev->pg_flags & AMD_PG_SUPPORT_JPEG)
+		smu_dpm_set_jpeg_enable(smu, !jpeg_gate);
 err_out:
-	smu_dpm_set_vcn_enable(smu, !vcn_gate);
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN)
+		smu_dpm_set_vcn_enable(smu, !vcn_gate);
+
 	return ret;
 }
 
@@ -1885,6 +1896,7 @@ static int smu_disable_dpms(struct smu_context *smu)
 		case IP_VERSION(13, 0, 4):
 		case IP_VERSION(13, 0, 11):
 		case IP_VERSION(14, 0, 0):
+		case IP_VERSION(14, 0, 1):
 			return 0;
 		default:
 			break;
@@ -3669,3 +3681,13 @@ int smu_send_hbm_bad_channel_flag(struct smu_context *smu, uint32_t size)
 
 	return ret;
 }
+
+int smu_send_rma_reason(struct smu_context *smu)
+{
+	int ret = 0;
+
+	if (smu->ppt_funcs && smu->ppt_funcs->send_rma_reason)
+		ret = smu->ppt_funcs->send_rma_reason(smu);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 66e84defd0b6..a870bdd49a4e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -1342,6 +1342,11 @@ struct pptable_funcs {
 	int (*send_hbm_bad_pages_num)(struct smu_context *smu, uint32_t size);
 
 	/**
+	 * @send_rma_reason: message rma reason event to SMU.
+	 */
+	int (*send_rma_reason)(struct smu_context *smu);
+
+	/**
 	 * @get_ecc_table:  message SMU to get ECC INFO table.
 	 */
 	ssize_t (*get_ecc_info)(struct smu_context *smu, void *table);
@@ -1588,5 +1593,6 @@ int smu_stb_collect_info(struct smu_context *smu, void *buff, uint32_t size);
 void amdgpu_smu_stb_debug_fs_init(struct amdgpu_device *adev);
 int smu_send_hbm_bad_pages_num(struct smu_context *smu, uint32_t size);
 int smu_send_hbm_bad_channel_flag(struct smu_context *smu, uint32_t size);
+int smu_send_rma_reason(struct smu_context *smu);
 #endif
 #endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h
index 509e3cd483fb..86758051cb93 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h
@@ -91,7 +91,8 @@
 #define PPSMC_MSG_QueryValidMcaCeCount              0x3A
 #define PPSMC_MSG_McaBankCeDumpDW                   0x3B
 #define PPSMC_MSG_SelectPLPDMode                    0x40
-#define PPSMC_Message_Count                         0x41
+#define PPSMC_MSG_RmaDueToBadPageThreshold          0x43
+#define PPSMC_Message_Count                         0x44
 
 //PPSMC Reset Types for driver msg argument
 #define PPSMC_RESET_TYPE_DRIVER_MODE_1_RESET        0x1
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
index 953a767613b1..a941fdbf78b6 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
@@ -261,7 +261,8 @@
 	__SMU_DUMMY_MAP(SetSoftMaxVpe),	\
 	__SMU_DUMMY_MAP(SetSoftMinVpe), \
 	__SMU_DUMMY_MAP(GetMetricsVersion), \
-	__SMU_DUMMY_MAP(EnableUCLKShadow),
+	__SMU_DUMMY_MAP(EnableUCLKShadow), \
+	__SMU_DUMMY_MAP(RmaDueToBadPageThreshold),
 
 #undef __SMU_DUMMY_MAP
 #define __SMU_DUMMY_MAP(type)	SMU_MSG_##type
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index bcad42534da4..1d96eb274d72 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -2272,8 +2272,8 @@ static uint16_t arcturus_get_current_pcie_link_speed(struct smu_context *smu)
 
 	/* TODO: confirm this on real target */
 	esm_ctrl = RREG32_PCIE(smnPCIE_ESM_CTRL);
-	if ((esm_ctrl >> 15) & 0x1FFFF)
-		return (uint16_t)(((esm_ctrl >> 8) & 0x3F) + 128);
+	if ((esm_ctrl >> 15) & 0x1)
+		return (uint16_t)(((esm_ctrl >> 8) & 0x7F) + 128);
 
 	return smu_v11_0_get_current_pcie_link_speed(smu);
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index c7bfa68bf00f..f6545093bfc1 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -514,7 +514,7 @@ static int smu_v11_0_atom_get_smu_clockinfo(struct amdgpu_device *adev,
 					    getsmuclockinfo);
 
 	ret = amdgpu_atom_execute_table(adev->mode_info.atom_context, index,
-					(uint32_t *)&input);
+					(uint32_t *)&input, sizeof(input));
 	if (ret)
 		return -EINVAL;
 
@@ -1432,24 +1432,24 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev,
 		dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU HW CTF!\n");
 		orderly_poweroff(true);
 	} else if (client_id == SOC15_IH_CLIENTID_MP1) {
-		if (src_id == 0xfe) {
+		if (src_id == SMU_IH_INTERRUPT_ID_TO_DRIVER) {
 			/* ACK SMUToHost interrupt */
 			data = RREG32_SOC15(MP1, 0, mmMP1_SMN_IH_SW_INT_CTRL);
 			data = REG_SET_FIELD(data, MP1_SMN_IH_SW_INT_CTRL, INT_ACK, 1);
 			WREG32_SOC15(MP1, 0, mmMP1_SMN_IH_SW_INT_CTRL, data);
 
 			switch (ctxid) {
-			case 0x3:
+			case SMU_IH_INTERRUPT_CONTEXT_ID_AC:
 				dev_dbg(adev->dev, "Switched to AC mode!\n");
 				schedule_work(&smu->interrupt_work);
 				adev->pm.ac_power = true;
 				break;
-			case 0x4:
+			case SMU_IH_INTERRUPT_CONTEXT_ID_DC:
 				dev_dbg(adev->dev, "Switched to DC mode!\n");
 				schedule_work(&smu->interrupt_work);
 				adev->pm.ac_power = false;
 				break;
-			case 0x7:
+			case SMU_IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING:
 				/*
 				 * Increment the throttle interrupt counter
 				 */
@@ -1462,6 +1462,10 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev,
 					schedule_work(&smu->throttling_logging_work);
 
 				break;
+			default:
+				dev_dbg(adev->dev, "Unhandled context id %d from client:%d!\n",
+									ctxid, client_id);
+				break;
 			}
 		}
 	}
@@ -1504,7 +1508,7 @@ int smu_v11_0_register_irq_handler(struct smu_context *smu)
 		return ret;
 
 	ret = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_MP1,
-				0xfe,
+				SMU_IH_INTERRUPT_ID_TO_DRIVER,
 				irq_src);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
index 5e408a195860..ed15f5a0fd11 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
@@ -301,7 +301,7 @@ static int smu_v12_0_atom_get_smu_clockinfo(struct amdgpu_device *adev,
 					    getsmuclockinfo);
 
 	ret = amdgpu_atom_execute_table(adev->mode_info.atom_context, index,
-					(uint32_t *)&input);
+					(uint32_t *)&input, sizeof(input));
 	if (ret)
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index dd9bcbd630a1..f41ac6465f2a 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -1682,8 +1682,8 @@ static int aldebaran_get_current_pcie_link_speed(struct smu_context *smu)
 
 	/* TODO: confirm this on real target */
 	esm_ctrl = RREG32_PCIE(smnPCIE_ESM_CTRL);
-	if ((esm_ctrl >> 15) & 0x1FFFF)
-		return (((esm_ctrl >> 8) & 0x3F) + 128);
+	if ((esm_ctrl >> 15) & 0x1)
+		return (((esm_ctrl >> 8) & 0x7F) + 128);
 
 	return smu_v13_0_get_current_pcie_link_speed(smu);
 }
@@ -1746,10 +1746,12 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu,
 
 	gpu_metrics->current_fan_speed = 0;
 
-	gpu_metrics->pcie_link_width =
-		smu_v13_0_get_current_pcie_link_width(smu);
-	gpu_metrics->pcie_link_speed =
-		aldebaran_get_current_pcie_link_speed(smu);
+	if (!amdgpu_sriov_vf(smu->adev)) {
+		gpu_metrics->pcie_link_width =
+			smu_v13_0_get_current_pcie_link_width(smu);
+		gpu_metrics->pcie_link_speed =
+			aldebaran_get_current_pcie_link_speed(smu);
+	}
 
 	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index c486182ff275..48170bb5112e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -1369,24 +1369,24 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev,
 		dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU HW CTF!\n");
 		orderly_poweroff(true);
 	} else if (client_id == SOC15_IH_CLIENTID_MP1) {
-		if (src_id == 0xfe) {
+		if (src_id == SMU_IH_INTERRUPT_ID_TO_DRIVER) {
 			/* ACK SMUToHost interrupt */
 			data = RREG32_SOC15(MP1, 0, regMP1_SMN_IH_SW_INT_CTRL);
 			data = REG_SET_FIELD(data, MP1_SMN_IH_SW_INT_CTRL, INT_ACK, 1);
 			WREG32_SOC15(MP1, 0, regMP1_SMN_IH_SW_INT_CTRL, data);
 
 			switch (ctxid) {
-			case 0x3:
+			case SMU_IH_INTERRUPT_CONTEXT_ID_AC:
 				dev_dbg(adev->dev, "Switched to AC mode!\n");
 				smu_v13_0_ack_ac_dc_interrupt(smu);
 				adev->pm.ac_power = true;
 				break;
-			case 0x4:
+			case SMU_IH_INTERRUPT_CONTEXT_ID_DC:
 				dev_dbg(adev->dev, "Switched to DC mode!\n");
 				smu_v13_0_ack_ac_dc_interrupt(smu);
 				adev->pm.ac_power = false;
 				break;
-			case 0x7:
+			case SMU_IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING:
 				/*
 				 * Increment the throttle interrupt counter
 				 */
@@ -1399,7 +1399,7 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev,
 					schedule_work(&smu->throttling_logging_work);
 
 				break;
-			case 0x8:
+			case SMU_IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL:
 				high = smu->thermal_range.software_shutdown_temp +
 					smu->thermal_range.software_shutdown_temp_offset;
 				high = min_t(typeof(high),
@@ -1416,7 +1416,7 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev,
 				data = data & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK);
 				WREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL, data);
 				break;
-			case 0x9:
+			case SMU_IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY:
 				high = min_t(typeof(high),
 					     SMU_THERMAL_MAXIMUM_ALERT_TEMP,
 					     smu->thermal_range.software_shutdown_temp);
@@ -1429,6 +1429,10 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev,
 				data = data & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK);
 				WREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL, data);
 				break;
+			default:
+				dev_dbg(adev->dev, "Unhandled context id %d from client:%d!\n",
+									ctxid, client_id);
+				break;
 			}
 		}
 	}
@@ -1473,7 +1477,7 @@ int smu_v13_0_register_irq_handler(struct smu_context *smu)
 		return ret;
 
 	ret = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_MP1,
-				0xfe,
+				SMU_IH_INTERRUPT_ID_TO_DRIVER,
 				irq_src);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 7e1941cf1796..3957af057d54 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -45,6 +45,7 @@
 #include <linux/pci.h>
 #include "amdgpu_ras.h"
 #include "amdgpu_mca.h"
+#include "amdgpu_aca.h"
 #include "smu_cmn.h"
 #include "mp/mp_13_0_6_offset.h"
 #include "mp/mp_13_0_6_sh_mask.h"
@@ -171,6 +172,7 @@ static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COU
 	MSG_MAP(McaBankDumpDW,                       PPSMC_MSG_McaBankDumpDW,                   0),
 	MSG_MAP(McaBankCeDumpDW,                     PPSMC_MSG_McaBankCeDumpDW,                 0),
 	MSG_MAP(SelectPLPDMode,                      PPSMC_MSG_SelectPLPDMode,                  0),
+	MSG_MAP(RmaDueToBadPageThreshold,            PPSMC_MSG_RmaDueToBadPageThreshold,        0),
 };
 
 // clang-format on
@@ -1438,7 +1440,10 @@ static int smu_v13_0_6_irq_process(struct amdgpu_device *adev,
 							entry->src_data[1]);
 					schedule_work(&smu->throttling_logging_work);
 				}
-
+				break;
+			default:
+				dev_dbg(adev->dev, "Unhandled context id %d from client:%d!\n",
+									ctxid, client_id);
 				break;
 			}
 		}
@@ -1574,6 +1579,8 @@ static int smu_v13_0_6_set_performance_level(struct smu_context *smu,
 	struct smu_13_0_dpm_context *dpm_context = smu_dpm->dpm_context;
 	struct smu_13_0_dpm_table *gfx_table =
 		&dpm_context->dpm_tables.gfx_table;
+	struct smu_13_0_dpm_table *uclk_table =
+		&dpm_context->dpm_tables.uclk_table;
 	struct smu_umd_pstate_table *pstate_table = &smu->pstate_table;
 	int ret;
 
@@ -1589,17 +1596,27 @@ static int smu_v13_0_6_set_performance_level(struct smu_context *smu,
 		return 0;
 
 	case AMD_DPM_FORCED_LEVEL_AUTO:
-		if ((gfx_table->min == pstate_table->gfxclk_pstate.curr.min) &&
-		    (gfx_table->max == pstate_table->gfxclk_pstate.curr.max))
-			return 0;
+		if ((gfx_table->min != pstate_table->gfxclk_pstate.curr.min) ||
+		    (gfx_table->max != pstate_table->gfxclk_pstate.curr.max)) {
+			ret = smu_v13_0_6_set_gfx_soft_freq_limited_range(
+				smu, gfx_table->min, gfx_table->max);
+			if (ret)
+				return ret;
 
-		ret = smu_v13_0_6_set_gfx_soft_freq_limited_range(
-			smu, gfx_table->min, gfx_table->max);
-		if (ret)
-			return ret;
+			pstate_table->gfxclk_pstate.curr.min = gfx_table->min;
+			pstate_table->gfxclk_pstate.curr.max = gfx_table->max;
+		}
+
+		if (uclk_table->max != pstate_table->uclk_pstate.curr.max) {
+			/* Min UCLK is not expected to be changed */
+			ret = smu_v13_0_set_soft_freq_limited_range(
+				smu, SMU_UCLK, 0, uclk_table->max);
+			if (ret)
+				return ret;
+			pstate_table->uclk_pstate.curr.max = uclk_table->max;
+		}
+		pstate_table->uclk_pstate.custom.max = 0;
 
-		pstate_table->gfxclk_pstate.curr.min = gfx_table->min;
-		pstate_table->gfxclk_pstate.curr.max = gfx_table->max;
 		return 0;
 	case AMD_DPM_FORCED_LEVEL_MANUAL:
 		return 0;
@@ -1622,7 +1639,8 @@ static int smu_v13_0_6_set_soft_freq_limited_range(struct smu_context *smu,
 	uint32_t max_clk;
 	int ret = 0;
 
-	if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK)
+	if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK &&
+	    clk_type != SMU_UCLK)
 		return -EINVAL;
 
 	if ((smu_dpm->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL) &&
@@ -1632,18 +1650,31 @@ static int smu_v13_0_6_set_soft_freq_limited_range(struct smu_context *smu,
 	if (smu_dpm->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
 		if (min >= max) {
 			dev_err(smu->adev->dev,
-				"Minimum GFX clk should be less than the maximum allowed clock\n");
+				"Minimum clk should be less than the maximum allowed clock\n");
 			return -EINVAL;
 		}
 
-		if ((min == pstate_table->gfxclk_pstate.curr.min) &&
-		    (max == pstate_table->gfxclk_pstate.curr.max))
-			return 0;
+		if (clk_type == SMU_GFXCLK) {
+			if ((min == pstate_table->gfxclk_pstate.curr.min) &&
+			    (max == pstate_table->gfxclk_pstate.curr.max))
+				return 0;
 
-		ret = smu_v13_0_6_set_gfx_soft_freq_limited_range(smu, min, max);
-		if (!ret) {
-			pstate_table->gfxclk_pstate.curr.min = min;
-			pstate_table->gfxclk_pstate.curr.max = max;
+			ret = smu_v13_0_6_set_gfx_soft_freq_limited_range(
+				smu, min, max);
+			if (!ret) {
+				pstate_table->gfxclk_pstate.curr.min = min;
+				pstate_table->gfxclk_pstate.curr.max = max;
+			}
+		}
+
+		if (clk_type == SMU_UCLK) {
+			if (max == pstate_table->uclk_pstate.curr.max)
+				return 0;
+			/* Only max clock limiting is allowed for UCLK */
+			ret = smu_v13_0_set_soft_freq_limited_range(
+				smu, SMU_UCLK, 0, max);
+			if (!ret)
+				pstate_table->uclk_pstate.curr.max = max;
 		}
 
 		return ret;
@@ -1736,6 +1767,40 @@ static int smu_v13_0_6_usr_edit_dpm_table(struct smu_context *smu,
 			return -EINVAL;
 		}
 		break;
+	case PP_OD_EDIT_MCLK_VDDC_TABLE:
+		if (size != 2) {
+			dev_err(smu->adev->dev,
+				"Input parameter number not correct\n");
+			return -EINVAL;
+		}
+
+		if (!smu_cmn_feature_is_enabled(smu,
+						SMU_FEATURE_DPM_UCLK_BIT)) {
+			dev_warn(smu->adev->dev,
+				 "UCLK_LIMITS setting not supported!\n");
+			return -EOPNOTSUPP;
+		}
+
+		if (input[0] == 0) {
+			dev_info(smu->adev->dev,
+				 "Setting min UCLK level is not supported");
+			return -EINVAL;
+		} else if (input[0] == 1) {
+			if (input[1] > dpm_context->dpm_tables.uclk_table.max) {
+				dev_warn(
+					smu->adev->dev,
+					"Maximum UCLK (%ld) MHz specified is greater than the maximum allowed (%d) MHz\n",
+					input[1],
+					dpm_context->dpm_tables.uclk_table.max);
+				pstate_table->uclk_pstate.custom.max =
+					pstate_table->uclk_pstate.curr.max;
+				return -EINVAL;
+			}
+
+			pstate_table->uclk_pstate.custom.max = input[1];
+		}
+		break;
+
 	case PP_OD_RESTORE_DEFAULT_TABLE:
 		if (size != 0) {
 			dev_err(smu->adev->dev,
@@ -1746,8 +1811,19 @@ static int smu_v13_0_6_usr_edit_dpm_table(struct smu_context *smu,
 			min_clk = dpm_context->dpm_tables.gfx_table.min;
 			max_clk = dpm_context->dpm_tables.gfx_table.max;
 
-			return smu_v13_0_6_set_soft_freq_limited_range(
+			ret = smu_v13_0_6_set_soft_freq_limited_range(
 				smu, SMU_GFXCLK, min_clk, max_clk);
+
+			if (ret)
+				return ret;
+
+			min_clk = dpm_context->dpm_tables.uclk_table.min;
+			max_clk = dpm_context->dpm_tables.uclk_table.max;
+			ret = smu_v13_0_6_set_soft_freq_limited_range(
+				smu, SMU_UCLK, min_clk, max_clk);
+			if (ret)
+				return ret;
+			pstate_table->uclk_pstate.custom.max = 0;
 		}
 		break;
 	case PP_OD_COMMIT_DPM_TABLE:
@@ -1767,8 +1843,19 @@ static int smu_v13_0_6_usr_edit_dpm_table(struct smu_context *smu,
 			min_clk = pstate_table->gfxclk_pstate.custom.min;
 			max_clk = pstate_table->gfxclk_pstate.custom.max;
 
-			return smu_v13_0_6_set_soft_freq_limited_range(
+			ret = smu_v13_0_6_set_soft_freq_limited_range(
 				smu, SMU_GFXCLK, min_clk, max_clk);
+
+			if (ret)
+				return ret;
+
+			if (!pstate_table->uclk_pstate.custom.max)
+				return 0;
+
+			min_clk = pstate_table->uclk_pstate.curr.min;
+			max_clk = pstate_table->uclk_pstate.custom.max;
+			return smu_v13_0_6_set_soft_freq_limited_range(
+				smu, SMU_UCLK, min_clk, max_clk);
 		}
 		break;
 	default:
@@ -2060,8 +2147,8 @@ static int smu_v13_0_6_get_current_pcie_link_speed(struct smu_context *smu)
 
 	/* TODO: confirm this on real target */
 	esm_ctrl = RREG32_PCIE(smnPCIE_ESM_CTRL);
-	if ((esm_ctrl >> 15) & 0x1FFFF)
-		return (((esm_ctrl >> 8) & 0x3F) + 128);
+	if ((esm_ctrl >> 15) & 0x1)
+		return (((esm_ctrl >> 8) & 0x7F) + 128);
 
 	speed_level = (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) &
 		PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK)
@@ -2141,14 +2228,16 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 	gpu_metrics->gfxclk_lock_status = GET_METRIC_FIELD(GfxLockXCDMak) >> GET_INST(GC, 0);
 
 	if (!(adev->flags & AMD_IS_APU)) {
-		link_width_level = smu_v13_0_6_get_current_pcie_link_width_level(smu);
-		if (link_width_level > MAX_LINK_WIDTH)
-			link_width_level = 0;
-
-		gpu_metrics->pcie_link_width =
-			DECODE_LANE_WIDTH(link_width_level);
-		gpu_metrics->pcie_link_speed =
-			smu_v13_0_6_get_current_pcie_link_speed(smu);
+		if (!amdgpu_sriov_vf(adev)) {
+			link_width_level = smu_v13_0_6_get_current_pcie_link_width_level(smu);
+			if (link_width_level > MAX_LINK_WIDTH)
+				link_width_level = 0;
+
+			gpu_metrics->pcie_link_width =
+				DECODE_LANE_WIDTH(link_width_level);
+			gpu_metrics->pcie_link_speed =
+				smu_v13_0_6_get_current_pcie_link_speed(smu);
+		}
 		gpu_metrics->pcie_bandwidth_acc =
 				SMUQ10_ROUND(metrics_x->PcieBandwidthAcc[0]);
 		gpu_metrics->pcie_bandwidth_inst =
@@ -2219,8 +2308,8 @@ static int smu_v13_0_6_mode2_reset(struct smu_context *smu)
 	ret = smu_cmn_send_msg_without_waiting(smu, (uint16_t)index,
 					       SMU_RESET_MODE_2);
 
-	/* This is similar to FLR, wait till max FLR timeout */
-	msleep(100);
+	/* Reset takes a bit longer, wait for 200ms. */
+	msleep(200);
 
 	dev_dbg(smu->adev->dev, "restore config space...\n");
 	/* Restore the config space saved during init */
@@ -2376,6 +2465,24 @@ static int smu_v13_0_6_smu_send_hbm_bad_page_num(struct smu_context *smu,
 	return ret;
 }
 
+static int smu_v13_0_6_send_rma_reason(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+	int ret;
+
+	/* NOTE: the message is only valid on dGPU with pmfw 85.90.0 and above */
+	if ((adev->flags & AMD_IS_APU) || smu->smc_fw_version < 0x00555a00)
+		return 0;
+
+	ret = smu_cmn_send_smc_msg(smu, SMU_MSG_RmaDueToBadPageThreshold, NULL);
+	if (ret)
+		dev_err(smu->adev->dev,
+			"[%s] failed to send BadPageThreshold event to SMU\n",
+			__func__);
+
+	return ret;
+}
+
 static int mca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable)
 {
 	struct smu_context *smu = adev->powerplay.pp_handle;
@@ -2547,18 +2654,22 @@ static int mca_umc_mca_get_err_count(const struct mca_ras_info *mca_ras, struct
 				     enum amdgpu_mca_error_type type, struct mca_bank_entry *entry, uint32_t *count)
 {
 	uint64_t status0;
+	uint32_t ext_error_code;
+	uint32_t odecc_err_cnt;
 
 	status0 = entry->regs[MCA_REG_IDX_STATUS];
+	ext_error_code = MCA_REG__STATUS__ERRORCODEEXT(status0);
+	odecc_err_cnt = MCA_REG__MISC0__ERRCNT(entry->regs[MCA_REG_IDX_MISC0]);
 
 	if (!REG_GET_FIELD(status0, MCMP1_STATUST0, Val)) {
 		*count = 0;
 		return 0;
 	}
 
-	if (type == AMDGPU_MCA_ERROR_TYPE_UE && umc_v12_0_is_uncorrectable_error(adev, status0))
-		*count = 1;
-	else if (type == AMDGPU_MCA_ERROR_TYPE_CE && umc_v12_0_is_correctable_error(adev, status0))
-		*count = 1;
+	if (umc_v12_0_is_deferred_error(adev, status0) ||
+	    umc_v12_0_is_uncorrectable_error(adev, status0) ||
+	    umc_v12_0_is_correctable_error(adev, status0))
+		*count = (ext_error_code == 0) ? odecc_err_cnt : 1;
 
 	return 0;
 }
@@ -2857,6 +2968,143 @@ static const struct amdgpu_mca_smu_funcs smu_v13_0_6_mca_smu_funcs = {
 	.mca_get_valid_mca_count = mca_smu_get_valid_mca_count,
 };
 
+static int aca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable)
+{
+	struct smu_context *smu = adev->powerplay.pp_handle;
+
+	return smu_v13_0_6_mca_set_debug_mode(smu, enable);
+}
+
+static int smu_v13_0_6_get_valid_aca_count(struct smu_context *smu, enum aca_error_type type, u32 *count)
+{
+	uint32_t msg;
+	int ret;
+
+	if (!count)
+		return -EINVAL;
+
+	switch (type) {
+	case ACA_ERROR_TYPE_UE:
+		msg = SMU_MSG_QueryValidMcaCount;
+		break;
+	case ACA_ERROR_TYPE_CE:
+		msg = SMU_MSG_QueryValidMcaCeCount;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = smu_cmn_send_smc_msg(smu, msg, count);
+	if (ret) {
+		*count = 0;
+		return ret;
+	}
+
+	return 0;
+}
+
+static int aca_smu_get_valid_aca_count(struct amdgpu_device *adev,
+				       enum aca_error_type type, u32 *count)
+{
+	struct smu_context *smu = adev->powerplay.pp_handle;
+	int ret;
+
+	switch (type) {
+	case ACA_ERROR_TYPE_UE:
+	case ACA_ERROR_TYPE_CE:
+		ret = smu_v13_0_6_get_valid_aca_count(smu, type, count);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static int __smu_v13_0_6_aca_bank_dump(struct smu_context *smu, enum aca_error_type type,
+				       int idx, int offset, u32 *val)
+{
+	uint32_t msg, param;
+
+	switch (type) {
+	case ACA_ERROR_TYPE_UE:
+		msg = SMU_MSG_McaBankDumpDW;
+		break;
+	case ACA_ERROR_TYPE_CE:
+		msg = SMU_MSG_McaBankCeDumpDW;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	param = ((idx & 0xffff) << 16) | (offset & 0xfffc);
+
+	return smu_cmn_send_smc_msg_with_param(smu, msg, param, (uint32_t *)val);
+}
+
+static int smu_v13_0_6_aca_bank_dump(struct smu_context *smu, enum aca_error_type type,
+				     int idx, int offset, u32 *val, int count)
+{
+	int ret, i;
+
+	if (!val)
+		return -EINVAL;
+
+	for (i = 0; i < count; i++) {
+		ret = __smu_v13_0_6_aca_bank_dump(smu, type, idx, offset + (i << 2), &val[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int aca_bank_read_reg(struct amdgpu_device *adev, enum aca_error_type type,
+			     int idx, int reg_idx, u64 *val)
+{
+	struct smu_context *smu = adev->powerplay.pp_handle;
+	u32 data[2] = {0, 0};
+	int ret;
+
+	if (!val || reg_idx >= ACA_REG_IDX_COUNT)
+		return -EINVAL;
+
+	ret = smu_v13_0_6_aca_bank_dump(smu, type, idx, reg_idx * 8, data, ARRAY_SIZE(data));
+	if (ret)
+		return ret;
+
+	*val = (u64)data[1] << 32 | data[0];
+
+	dev_dbg(adev->dev, "mca read bank reg: type:%s, index: %d, reg_idx: %d, val: 0x%016llx\n",
+		type == ACA_ERROR_TYPE_UE ? "UE" : "CE", idx, reg_idx, *val);
+
+	return 0;
+}
+
+static int aca_smu_get_valid_aca_bank(struct amdgpu_device *adev,
+				      enum aca_error_type type, int idx, struct aca_bank *bank)
+{
+	int i, ret, count;
+
+	count = min_t(int, 16, ARRAY_SIZE(bank->regs));
+	for (i = 0; i < count; i++) {
+		ret = aca_bank_read_reg(adev, type, idx, i, &bank->regs[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static const struct aca_smu_funcs smu_v13_0_6_aca_smu_funcs = {
+	.max_ue_bank_count = 12,
+	.max_ce_bank_count = 12,
+	.set_debug_mode = aca_smu_set_debug_mode,
+	.get_valid_aca_count = aca_smu_get_valid_aca_count,
+	.get_valid_aca_bank = aca_smu_get_valid_aca_bank,
+};
+
 static int smu_v13_0_6_select_xgmi_plpd_policy(struct smu_context *smu,
 					       enum pp_xgmi_plpd_mode mode)
 {
@@ -2895,13 +3143,6 @@ static int smu_v13_0_6_select_xgmi_plpd_policy(struct smu_context *smu,
 	return ret;
 }
 
-static ssize_t smu_v13_0_6_get_ecc_info(struct smu_context *smu,
-			void *table)
-{
-	/* Support ecc info by default */
-	return 0;
-}
-
 static const struct pptable_funcs smu_v13_0_6_ppt_funcs = {
 	/* init dpm */
 	.get_allowed_feature_mask = smu_v13_0_6_get_allowed_feature_mask,
@@ -2956,7 +3197,7 @@ static const struct pptable_funcs smu_v13_0_6_ppt_funcs = {
 	.i2c_init = smu_v13_0_6_i2c_control_init,
 	.i2c_fini = smu_v13_0_6_i2c_control_fini,
 	.send_hbm_bad_pages_num = smu_v13_0_6_smu_send_hbm_bad_page_num,
-	.get_ecc_info = smu_v13_0_6_get_ecc_info,
+	.send_rma_reason = smu_v13_0_6_send_rma_reason,
 };
 
 void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu)
@@ -2969,4 +3210,5 @@ void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu)
 	smu->smc_driver_if_version = SMU13_0_6_DRIVER_IF_VERSION;
 	smu_v13_0_set_smu_mailbox_registers(smu);
 	amdgpu_mca_smu_init_funcs(smu->adev, &smu_v13_0_6_mca_smu_funcs);
+	amdgpu_aca_set_smu_funcs(smu->adev, &smu_v13_0_6_aca_smu_funcs);
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index 6dae5ad74ff0..b06a3cc43305 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -53,6 +53,8 @@
 
 MODULE_FIRMWARE("amdgpu/smu_14_0_2.bin");
 
+#define ENABLE_IMU_ARG_GFXOFF_ENABLE		1
+
 int smu_v14_0_init_microcode(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
@@ -231,6 +233,10 @@ int smu_v14_0_check_fw_version(struct smu_context *smu)
 	case IP_VERSION(14, 0, 0):
 		smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_0;
 		break;
+	case IP_VERSION(14, 0, 1):
+		smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_0;
+		break;
+
 	default:
 		dev_err(adev->dev, "smu unsupported IP version: 0x%x.\n",
 			amdgpu_ip_version(adev, MP1_HWIP, 0));
@@ -734,6 +740,7 @@ int smu_v14_0_gfx_off_control(struct smu_context *smu, bool enable)
 	switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
 	case IP_VERSION(14, 0, 2):
 	case IP_VERSION(14, 0, 0):
+	case IP_VERSION(14, 0, 1):
 		if (!(adev->pm.pp_feature & PP_GFXOFF_MASK))
 			return 0;
 		if (enable)
@@ -890,7 +897,7 @@ int smu_v14_0_register_irq_handler(struct smu_context *smu)
 	// TODO: THM related
 
 	ret = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_MP1,
-				0xfe,
+				SMU_IH_INTERRUPT_ID_TO_DRIVER,
 				irq_src);
 	if (ret)
 		return ret;
@@ -1628,11 +1635,16 @@ int smu_v14_0_baco_exit(struct smu_context *smu)
 int smu_v14_0_set_gfx_power_up_by_imu(struct smu_context *smu)
 {
 	uint16_t index;
+	struct amdgpu_device *adev = smu->adev;
+
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+		return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_EnableGfxImu,
+						       ENABLE_IMU_ARG_GFXOFF_ENABLE, NULL);
+	}
 
 	index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_MSG,
 					       SMU_MSG_EnableGfxImu);
-	/* Param 1 to tell PMFW to enable GFXOFF feature */
-	return smu_cmn_send_msg_without_waiting(smu, index, 1);
+	return smu_cmn_send_msg_without_waiting(smu, index, ENABLE_IMU_ARG_GFXOFF_ENABLE);
 }
 
 int smu_v14_0_set_default_dpm_tables(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index 00cd615bbcdc..b8dbd4e25348 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -378,8 +378,15 @@ int smu_cmn_send_smc_msg_with_param(struct smu_context *smu,
 	res = __smu_cmn_reg2errno(smu, reg);
 	if (res != 0)
 		__smu_cmn_reg_print_error(smu, reg, index, param, msg);
-	if (read_arg)
+	if (read_arg) {
 		smu_cmn_read_arg(smu, read_arg);
+		dev_dbg(adev->dev, "smu send message: %s(%d) param: 0x%08x, resp: 0x%08x,\
+			readval: 0x%08x\n",
+			smu_get_message_name(smu, msg), index, param, reg, *read_arg);
+	} else {
+		dev_dbg(adev->dev, "smu send message: %s(%d) param: 0x%08x, resp: 0x%08x\n",
+			smu_get_message_name(smu, msg), index, param, reg);
+	}
 Out:
 	if (unlikely(adev->pm.smu_debug_mask & SMU_DEBUG_HALT_ON_ERROR) && res) {
 		amdgpu_device_halt(adev);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
index cc590e27d88a..81bfce1406e5 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
@@ -30,6 +30,16 @@
 #define FDO_PWM_MODE_STATIC  1
 #define FDO_PWM_MODE_STATIC_RPM 5
 
+#define SMU_IH_INTERRUPT_ID_TO_DRIVER                   0xFE
+#define SMU_IH_INTERRUPT_CONTEXT_ID_BACO                0x2
+#define SMU_IH_INTERRUPT_CONTEXT_ID_AC                  0x3
+#define SMU_IH_INTERRUPT_CONTEXT_ID_DC                  0x4
+#define SMU_IH_INTERRUPT_CONTEXT_ID_AUDIO_D0            0x5
+#define SMU_IH_INTERRUPT_CONTEXT_ID_AUDIO_D3            0x6
+#define SMU_IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING  0x7
+#define SMU_IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL        0x8
+#define SMU_IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY        0x9
+
 extern const int link_speed[];
 
 /* Helper to Convert from PCIE Gen 1/2/3/4/5/6 to 0.1 GT/s speed units */