Merge tag 'drm-fixes-2024-10-25' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Weekly drm fixes, mostly amdgpu and xe, with minor bridge and an i915
  Kconfig fix. Nothing too scary and it seems to be pretty quiet.

  amdgpu:
   - ACPI method handling fixes
   - SMU 14.x fixes
   - Display idle optimization fix
   - DP link layer compliance fix
   - SDMA 7.x fix
   - PSR-SU fix
   - SWSMU fix

  i915:
   - Fix DRM_I915_GVT_KVMGT dependencies in Kconfig

  xe:
   - Increase invalidation timeout to avoid errors in some hosts
   - Flush worker on timeout
   - Better handling for force wake failure
   - Improve argument check on user fence creation
   - Don't restart parallel queues multiple times on GT reset

  bridge:
   - aux: Fix assignment of OF node
   - tc358767: Add missing of_node_put() in error path"

* tag 'drm-fixes-2024-10-25' of https://gitlab.freedesktop.org/drm/kernel:
  drm/xe: Don't restart parallel queues multiple times on GT reset
  drm/xe/ufence: Prefetch ufence addr to catch bogus address
  drm/xe: Handle unreliable MMIO reads during forcewake
  drm/xe/guc/ct: Flush g2h worker in case of g2h response timeout
  drm/xe: Enlarge the invalidation timeout from 150 to 500
  drm/amdgpu: handle default profile on on devices without fullscreen 3D
  drm/amd/display: Disable PSR-SU on Parade 08-01 TCON too
  drm/amdgpu: fix random data corruption for sdma 7
  drm/amd/display: temp w/a for DP Link Layer compliance
  drm/amd/display: temp w/a for dGPU to enter idle optimizations
  drm/amd/pm: update deep sleep status on smu v14.0.2/3
  drm/amd/pm: update overdrive function on smu v14.0.2/3
  drm/amd/pm: update the driver-fw interface file for smu v14.0.2/3
  drm/amd: Guard against bad data for ATIF ACPI method
  drm/bridge: tc358767: fix missing of_node_put() in for_each_endpoint_of_node()
  drm/bridge: Fix assignment of the of_node of the parent to aux bridge
  i915: fix DRM_I915_GVT_KVMGT dependencies

17 files changed, 202 insertions, 107 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index f85ace0384d2..1f5a296f5ed2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -147,6 +147,7 @@ static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif,
 					   struct acpi_buffer *params)
 {
 	acpi_status status;
+	union acpi_object *obj;
 	union acpi_object atif_arg_elements[2];
 	struct acpi_object_list atif_arg;
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
@@ -169,16 +170,24 @@ static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif,
 
 	status = acpi_evaluate_object(atif->handle, NULL, &atif_arg,
 				      &buffer);
+	obj = (union acpi_object *)buffer.pointer;
 
-	/* Fail only if calling the method fails and ATIF is supported */
+	/* Fail if calling the method fails and ATIF is supported */
 	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
 		DRM_DEBUG_DRIVER("failed to evaluate ATIF got %s\n",
 				 acpi_format_exception(status));
-		kfree(buffer.pointer);
+		kfree(obj);
 		return NULL;
 	}
 
-	return buffer.pointer;
+	if (obj->type != ACPI_TYPE_BUFFER) {
+		DRM_DEBUG_DRIVER("bad object returned from ATIF: %d\n",
+				 obj->type);
+		kfree(obj);
+		return NULL;
+	}
+
+	return obj;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
index a8763496aed3..9288f37a3cc5 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
@@ -51,6 +51,12 @@ MODULE_FIRMWARE("amdgpu/sdma_7_0_1.bin");
 #define SDMA0_HYP_DEC_REG_END 0x589a
 #define SDMA1_HYP_DEC_REG_OFFSET 0x20
 
+/*define for compression field for sdma7*/
+#define SDMA_PKT_CONSTANT_FILL_HEADER_compress_offset 0
+#define SDMA_PKT_CONSTANT_FILL_HEADER_compress_mask   0x00000001
+#define SDMA_PKT_CONSTANT_FILL_HEADER_compress_shift  16
+#define SDMA_PKT_CONSTANT_FILL_HEADER_COMPRESS(x) (((x) & SDMA_PKT_CONSTANT_FILL_HEADER_compress_mask) << SDMA_PKT_CONSTANT_FILL_HEADER_compress_shift)
+
 static const struct amdgpu_hwip_reg_entry sdma_reg_list_7_0[] = {
 	SOC15_REG_ENTRY_STR(GC, 0, regSDMA0_STATUS_REG),
 	SOC15_REG_ENTRY_STR(GC, 0, regSDMA0_STATUS1_REG),
@@ -1724,7 +1730,8 @@ static void sdma_v7_0_emit_fill_buffer(struct amdgpu_ib *ib,
 				       uint64_t dst_offset,
 				       uint32_t byte_count)
 {
-	ib->ptr[ib->length_dw++] = SDMA_PKT_COPY_LINEAR_HEADER_OP(SDMA_OP_CONST_FILL);
+	ib->ptr[ib->length_dw++] = SDMA_PKT_CONSTANT_FILL_HEADER_OP(SDMA_OP_CONST_FILL) |
+		SDMA_PKT_CONSTANT_FILL_HEADER_COMPRESS(1);
 	ib->ptr[ib->length_dw++] = lower_32_bits(dst_offset);
 	ib->ptr[ib->length_dw++] = upper_32_bits(dst_offset);
 	ib->ptr[ib->length_dw++] = src_data;
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 6b5e2206e687..13421a58210d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -8374,7 +8374,8 @@ static void manage_dm_interrupts(struct amdgpu_device *adev,
 		if (amdgpu_ip_version(adev, DCE_HWIP, 0) <
 		    IP_VERSION(3, 5, 0) ||
 		    acrtc_state->stream->link->psr_settings.psr_version <
-		    DC_PSR_VERSION_UNSUPPORTED) {
+		    DC_PSR_VERSION_UNSUPPORTED ||
+		    !(adev->flags & AMD_IS_APU)) {
 			timing = &acrtc_state->stream->timing;
 
 			/* at least 2 frames */
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 069e0195e50a..eea317dcbe8c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -44,6 +44,7 @@
 
 #include "dm_helpers.h"
 #include "ddc_service_types.h"
+#include "clk_mgr.h"
 
 static u32 edid_extract_panel_id(struct edid *edid)
 {
@@ -1121,6 +1122,8 @@ bool dm_helpers_dp_handle_test_pattern_request(
 	struct pipe_ctx *pipe_ctx = NULL;
 	struct amdgpu_dm_connector *aconnector = link->priv;
 	struct drm_device *dev = aconnector->base.dev;
+	struct dc_state *dc_state = ctx->dc->current_state;
+	struct clk_mgr *clk_mgr = ctx->dc->clk_mgr;
 	int i;
 
 	for (i = 0; i < MAX_PIPES; i++) {
@@ -1221,6 +1224,16 @@ bool dm_helpers_dp_handle_test_pattern_request(
 	pipe_ctx->stream->test_pattern.type = test_pattern;
 	pipe_ctx->stream->test_pattern.color_space = test_pattern_color_space;
 
+	/* Temp W/A for compliance test failure */
+	dc_state->bw_ctx.bw.dcn.clk.p_state_change_support = false;
+	dc_state->bw_ctx.bw.dcn.clk.dramclk_khz = clk_mgr->dc_mode_softmax_enabled ?
+		clk_mgr->bw_params->dc_mode_softmax_memclk : clk_mgr->bw_params->max_memclk_mhz;
+	dc_state->bw_ctx.bw.dcn.clk.idle_dramclk_khz = dc_state->bw_ctx.bw.dcn.clk.dramclk_khz;
+	ctx->dc->clk_mgr->funcs->update_clocks(
+			ctx->dc->clk_mgr,
+			dc_state,
+			false);
+
 	dc_link_dp_set_test_pattern(
 		(struct dc_link *) link,
 		test_pattern,
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
index 3cd52e7a9c77..95838c7ab054 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -841,6 +841,8 @@ bool is_psr_su_specific_panel(struct dc_link *link)
 				isPSRSUSupported = false;
 			else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x03)
 				isPSRSUSupported = false;
+			else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x01)
+				isPSRSUSupported = false;
 			else if (dpcd_caps->psr_info.force_psrsu_cap == 0x1)
 				isPSRSUSupported = true;
 		}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 9ad9cf7a9c98..80e60ea2d11e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1234,6 +1234,14 @@ static void smu_init_xgmi_plpd_mode(struct smu_context *smu)
 	}
 }
 
+static bool smu_is_workload_profile_available(struct smu_context *smu,
+					      u32 profile)
+{
+	if (profile >= PP_SMC_POWER_PROFILE_COUNT)
+		return false;
+	return smu->workload_map && smu->workload_map[profile].valid_mapping;
+}
+
 static int smu_sw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1265,7 +1273,8 @@ static int smu_sw_init(void *handle)
 	smu->workload_prority[PP_SMC_POWER_PROFILE_COMPUTE] = 5;
 	smu->workload_prority[PP_SMC_POWER_PROFILE_CUSTOM] = 6;
 
-	if (smu->is_apu)
+	if (smu->is_apu ||
+	    !smu_is_workload_profile_available(smu, PP_SMC_POWER_PROFILE_FULLSCREEN3D))
 		smu->workload_mask = 1 << smu->workload_prority[PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT];
 	else
 		smu->workload_mask = 1 << smu->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D];
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h
index ee457a6f0813..c2fd0a4a13e5 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h
@@ -25,7 +25,7 @@
 #define SMU14_DRIVER_IF_V14_0_H
 
 //Increment this version if SkuTable_t or BoardTable_t change
-#define PPTABLE_VERSION 0x18
+#define PPTABLE_VERSION 0x1B
 
 #define NUM_GFXCLK_DPM_LEVELS    16
 #define NUM_SOCCLK_DPM_LEVELS    8
@@ -145,7 +145,7 @@ typedef enum {
 } FEATURE_BTC_e;
 
 // Debug Overrides Bitmask
-#define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_VCN_FCLK      0x00000001
+#define DEBUG_OVERRIDE_NOT_USE      				   0x00000001
 #define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_DCN_FCLK      0x00000002
 #define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_MP0_FCLK      0x00000004
 #define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_VCN_DCFCLK    0x00000008
@@ -161,6 +161,7 @@ typedef enum {
 #define DEBUG_OVERRIDE_ENABLE_SOC_VF_BRINGUP_MODE      0x00002000
 #define DEBUG_OVERRIDE_ENABLE_PER_WGP_RESIENCY         0x00004000
 #define DEBUG_OVERRIDE_DISABLE_MEMORY_VOLTAGE_SCALING  0x00008000
+#define DEBUG_OVERRIDE_DFLL_BTC_FCW_LOG                0x00010000
 
 // VR Mapping Bit Defines
 #define VR_MAPPING_VR_SELECT_MASK  0x01
@@ -391,6 +392,21 @@ typedef struct {
   EccInfo_t  EccInfo[24];
 } EccInfoTable_t;
 
+#define EPCS_HIGH_POWER                  600
+#define EPCS_NORMAL_POWER                450
+#define EPCS_LOW_POWER                   300
+#define EPCS_SHORTED_POWER               150
+#define EPCS_NO_BOOTUP                   0
+
+typedef enum{
+  EPCS_SHORTED_LIMIT,
+  EPCS_LOW_POWER_LIMIT,
+  EPCS_NORMAL_POWER_LIMIT,
+  EPCS_HIGH_POWER_LIMIT,
+  EPCS_NOT_CONFIGURED,
+  EPCS_STATUS_COUNT,
+} EPCS_STATUS_e;
+
 //D3HOT sequences
 typedef enum {
   BACO_SEQUENCE,
@@ -662,7 +678,7 @@ typedef enum {
 } PP_GRTAVFS_FW_SEP_FUSE_e;
 
 #define PP_NUM_RTAVFS_PWL_ZONES 5
-
+#define PP_NUM_PSM_DIDT_PWL_ZONES 3
 
 // VBIOS or PPLIB configures telemetry slope and offset. Only slope expected to be set for SVI3
 // Slope Q1.7, Offset Q1.2
@@ -746,10 +762,10 @@ typedef struct {
   uint16_t               Padding;
 
   //Frequency changes
-  int16_t                GfxclkFmin;           // MHz
-  int16_t                GfxclkFmax;           // MHz
-  uint16_t               UclkFmin;             // MHz
-  uint16_t               UclkFmax;             // MHz
+  int16_t                GfxclkFoffset;
+  uint16_t               Padding1;
+  uint16_t               UclkFmin;
+  uint16_t               UclkFmax;
   uint16_t               FclkFmin;
   uint16_t               FclkFmax;
 
@@ -770,19 +786,23 @@ typedef struct {
   uint8_t                MaxOpTemp;
 
   uint8_t                AdvancedOdModeEnabled;
-  uint8_t                Padding1[3];
+  uint8_t                Padding2[3];
 
   uint16_t               GfxVoltageFullCtrlMode;
   uint16_t               SocVoltageFullCtrlMode;
   uint16_t               GfxclkFullCtrlMode;
   uint16_t               UclkFullCtrlMode;
   uint16_t               FclkFullCtrlMode;
-  uint16_t               Padding2;
+  uint16_t               Padding3;
 
   int16_t                GfxEdc;
   int16_t                GfxPccLimitControl;
 
-  uint32_t               Spare[10];
+  uint16_t               GfxclkFmaxVmax;
+  uint8_t                GfxclkFmaxVmaxTemperature;
+  uint8_t                Padding4[1];
+
+  uint32_t               Spare[9];
   uint32_t               MmHubPadding[8]; // SMU internal use. Adding here instead of external as a workaround
 } OverDriveTable_t;
 
@@ -802,8 +822,8 @@ typedef struct {
   uint16_t               VddSocVmax;
 
   //gfxclk
-  int16_t                GfxclkFmin;           // MHz
-  int16_t                GfxclkFmax;           // MHz
+  int16_t                GfxclkFoffset;
+  uint16_t               Padding;
   //uclk
   uint16_t               UclkFmin;             // MHz
   uint16_t               UclkFmax;             // MHz
@@ -828,7 +848,7 @@ typedef struct {
   uint8_t                FanZeroRpmEnable;
   //temperature
   uint8_t                MaxOpTemp;
-  uint8_t                Padding[2];
+  uint8_t                Padding1[2];
 
   //Full Ctrl
   uint16_t               GfxVoltageFullCtrlMode;
@@ -839,7 +859,7 @@ typedef struct {
   //EDC
   int16_t                GfxEdc;
   int16_t                GfxPccLimitControl;
-  int16_t                Padding1;
+  int16_t                Padding2;
 
   uint32_t               Spare[5];
 } OverDriveLimits_t;
@@ -987,8 +1007,9 @@ typedef struct {
   uint16_t BaseClockDc;
   uint16_t GameClockDc;
   uint16_t BoostClockDc;
-
-  uint32_t Reserved[4];
+  uint16_t MaxReportedClock;
+  uint16_t Padding;
+  uint32_t Reserved[3];
 } DriverReportedClocks_t;
 
 typedef struct {
@@ -1132,7 +1153,7 @@ typedef struct {
   uint32_t      DcModeMaxFreq     [PPCLK_COUNT            ];     // In MHz
 
   uint16_t      GfxclkAibFmax;
-  uint16_t      GfxclkFreqCap;
+  uint16_t      GfxDpmPadding;
 
   //GFX Idle Power Settings
   uint16_t      GfxclkFgfxoffEntry;   // Entry in RLC stage (PLL), in Mhz
@@ -1172,8 +1193,7 @@ typedef struct {
   uint32_t        DvoFmaxLowScaler; //Unitless float
 
   // GFX DCS
-  uint16_t      DcsGfxOffVoltage;     //Voltage in mV(Q2) applied to VDDGFX when entering DCS GFXOFF phase
-  uint16_t      PaddingDcs;
+  uint32_t      PaddingDcs;
 
   uint16_t      DcsMinGfxOffTime;     //Minimum amount of time PMFW shuts GFX OFF as part of GFX DCS phase
   uint16_t      DcsMaxGfxOffTime;      //Maximum amount of time PMFW can shut GFX OFF as part of GFX DCS phase at a stretch.
@@ -1205,8 +1225,7 @@ typedef struct {
   uint16_t      DalDcModeMaxUclkFreq;
   uint8_t       PaddingsMem[2];
   //FCLK Section
-  uint16_t      FclkDpmDisallowPstateFreq;  //Frequency which FW will target when indicated that display config cannot support P-state. Set to 0 use FW calculated value
-  uint16_t      PaddingFclk;
+  uint32_t      PaddingFclk;
 
   // Link DPM Settings
   uint8_t       PcieGenSpeed[NUM_LINK_LEVELS];           ///< 0:PciE-gen1 1:PciE-gen2 2:PciE-gen3 3:PciE-gen4 4:PciE-gen5
@@ -1215,12 +1234,19 @@ typedef struct {
 
   // SECTION: VDD_GFX AVFS
   uint8_t       OverrideGfxAvfsFuses;
-  uint8_t       GfxAvfsPadding[3];
+  uint8_t       GfxAvfsPadding[1];
+  uint16_t      DroopGBStDev;
 
   uint32_t      SocHwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT];   //new added for Soc domain
   uint32_t      GfxL2HwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT]; //see fusedoc for encoding
   //uint32_t      GfxSeHwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT];
-  uint32_t      spare_HwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT];
+
+  uint16_t      PsmDidt_Vcross[PP_NUM_PSM_DIDT_PWL_ZONES-1];
+  uint32_t      PsmDidt_StaticDroop_A[PP_NUM_PSM_DIDT_PWL_ZONES];
+  uint32_t      PsmDidt_StaticDroop_B[PP_NUM_PSM_DIDT_PWL_ZONES];
+  uint32_t      PsmDidt_DynDroop_A[PP_NUM_PSM_DIDT_PWL_ZONES];
+  uint32_t      PsmDidt_DynDroop_B[PP_NUM_PSM_DIDT_PWL_ZONES];
+  uint32_t      spare_HwRtAvfsFuses[19];
 
   uint32_t      SocCommonRtAvfs[PP_GRTAVFS_FW_COMMON_FUSE_COUNT];
   uint32_t      GfxCommonRtAvfs[PP_GRTAVFS_FW_COMMON_FUSE_COUNT];
@@ -1246,11 +1272,7 @@ typedef struct {
   uint32_t      dGbV_dT_vmin;
   uint32_t      dGbV_dT_vmax;
 
-  //Unused: PMFW-9370
-  uint32_t      V2F_vmin_range_low;
-  uint32_t      V2F_vmin_range_high;
-  uint32_t      V2F_vmax_range_low;
-  uint32_t      V2F_vmax_range_high;
+  uint32_t      PaddingV2F[4];
 
   AvfsDcBtcParams_t DcBtcGfxParams;
   QuadraticInt_t    SSCurve_GFX;
@@ -1327,18 +1349,18 @@ typedef struct {
   uint16_t        PsmDidtReleaseTimer;
   uint32_t        PsmDidtStallPattern; //Will be written to both pattern 1 and didt_static_level_prog
   // CAC EDC
-  uint32_t        Leakage_C0; // in IEEE float
-  uint32_t        Leakage_C1; // in IEEE float
-  uint32_t        Leakage_C2; // in IEEE float
-  uint32_t        Leakage_C3; // in IEEE float
-  uint32_t        Leakage_C4; // in IEEE float
-  uint32_t        Leakage_C5; // in IEEE float
-  uint32_t        GFX_CLK_SCALAR; // in IEEE float
-  uint32_t        GFX_CLK_INTERCEPT; // in IEEE float
-  uint32_t        GFX_CAC_M; // in IEEE float
-  uint32_t        GFX_CAC_B; // in IEEE float
-  uint32_t        VDD_GFX_CurrentLimitGuardband; // in IEEE float
-  uint32_t        DynToTotalCacScalar; // in IEEE
+  uint32_t        CacEdcCacLeakageC0;
+  uint32_t        CacEdcCacLeakageC1;
+  uint32_t        CacEdcCacLeakageC2;
+  uint32_t        CacEdcCacLeakageC3;
+  uint32_t        CacEdcCacLeakageC4;
+  uint32_t        CacEdcCacLeakageC5;
+  uint32_t        CacEdcGfxClkScalar;
+  uint32_t        CacEdcGfxClkIntercept;
+  uint32_t        CacEdcCac_m;
+  uint32_t        CacEdcCac_b;
+  uint32_t        CacEdcCurrLimitGuardband;
+  uint32_t        CacEdcDynToTotalCacRatio;
   // GFX EDC XVMIN
   uint32_t        XVmin_Gfx_EdcThreshScalar;
   uint32_t        XVmin_Gfx_EdcEnableFreq;
@@ -1467,7 +1489,7 @@ typedef struct {
   uint8_t      VddqOffEnabled;
   uint8_t      PaddingUmcFlags[2];
 
-  uint32_t    PostVoltageSetBacoDelay; // in microseconds. Amount of time FW will wait after power good is established or PSI0 command is issued
+  uint32_t    Paddign1;
   uint32_t    BacoEntryDelay; // in milliseconds. Amount of time FW will wait to trigger BACO entry after receiving entry notification from OS
 
   uint8_t     FuseWritePowerMuxPresent;
@@ -1530,7 +1552,7 @@ typedef struct {
   int16_t     FuzzyFan_ErrorSetDelta;
   int16_t     FuzzyFan_ErrorRateSetDelta;
   int16_t     FuzzyFan_PwmSetDelta;
-  uint16_t    FuzzyFan_Reserved;
+  uint16_t    FanPadding2;
 
   uint16_t    FwCtfLimit[TEMP_COUNT];
 
@@ -1547,9 +1569,10 @@ typedef struct {
   uint16_t    FanSpare[1];
   uint8_t     FanIntakeSensorSupport;
   uint8_t     FanIntakePadding;
-  uint32_t    FanAmbientPerfBoostThreshold;
   uint32_t    FanSpare2[12];
 
+  uint32_t ODFeatureCtrlMask;
+
   uint16_t TemperatureLimit_Hynix; // In degrees Celsius. Memory temperature limit associated with Hynix
   uint16_t TemperatureLimit_Micron; // In degrees Celsius. Memory temperature limit associated with Micron
   uint16_t TemperatureFwCtfLimit_Hynix;
@@ -1637,7 +1660,7 @@ typedef struct {
   uint16_t AverageDclk0Frequency  ;
   uint16_t AverageVclk1Frequency  ;
   uint16_t AverageDclk1Frequency  ;
-  uint16_t PCIeBusy               ;
+  uint16_t AveragePCIeBusy        ;
   uint16_t dGPU_W_MAX             ;
   uint16_t padding                ;
 
@@ -1665,12 +1688,12 @@ typedef struct {
 
   uint16_t AverageGfxActivity    ;
   uint16_t AverageUclkActivity   ;
-  uint16_t Vcn0ActivityPercentage  ;
+  uint16_t AverageVcn0ActivityPercentage;
   uint16_t Vcn1ActivityPercentage  ;
 
   uint32_t EnergyAccumulator;
   uint16_t AverageSocketPower;
-  uint16_t MovingAverageTotalBoardPower;
+  uint16_t AverageTotalBoardPower;
 
   uint16_t AvgTemperature[TEMP_COUNT];
   uint16_t AvgTemperatureFanIntake;
@@ -1684,7 +1707,8 @@ typedef struct {
 
 
   uint8_t  ThrottlingPercentage[THROTTLER_COUNT];
-  uint8_t  padding1[3];
+  uint8_t  VmaxThrottlingPercentage;
+  uint8_t  padding1[2];
 
   //metrics for D3hot entry/exit and driver ARM msgs
   uint32_t D3HotEntryCountPerMode[D3HOT_SEQUENCE_COUNT];
@@ -1693,7 +1717,7 @@ typedef struct {
 
   uint16_t ApuSTAPMSmartShiftLimit;
   uint16_t ApuSTAPMLimit;
-  uint16_t MovingAvgApuSocketPower;
+  uint16_t AvgApuSocketPower;
 
   uint16_t AverageUclkActivity_MAX;
 
@@ -1823,6 +1847,17 @@ typedef struct {
 #define TABLE_TRANSFER_FAILED     0xFF
 #define TABLE_TRANSFER_PENDING    0xAB
 
+#define TABLE_PPT_FAILED                          0x100
+#define TABLE_TDC_FAILED                          0x200
+#define TABLE_TEMP_FAILED                         0x400
+#define TABLE_FAN_TARGET_TEMP_FAILED              0x800
+#define TABLE_FAN_STOP_TEMP_FAILED               0x1000
+#define TABLE_FAN_START_TEMP_FAILED              0x2000
+#define TABLE_FAN_PWM_MIN_FAILED                 0x4000
+#define TABLE_ACOUSTIC_TARGET_RPM_FAILED         0x8000
+#define TABLE_ACOUSTIC_LIMIT_RPM_FAILED         0x10000
+#define TABLE_MGPU_ACOUSTIC_TARGET_RPM_FAILED   0x20000
+
 // Table types
 #define TABLE_PPTABLE            0
 #define TABLE_COMBO_PPTABLE           1
@@ -1849,5 +1884,6 @@ typedef struct {
 #define IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING  0x7
 #define IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL        0x8
 #define IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY        0x9
+#define IH_INTERRUPT_CONTEXT_ID_DYNAMIC_TABLE       0xA
 
 #endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
index 46b456590a08..727d5b405435 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
@@ -28,7 +28,7 @@
 #define SMU14_DRIVER_IF_VERSION_INV 0xFFFFFFFF
 #define SMU14_DRIVER_IF_VERSION_SMU_V14_0_0 0x7
 #define SMU14_DRIVER_IF_VERSION_SMU_V14_0_1 0x6
-#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_2 0x26
+#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_2 0x2E
 
 #define FEATURE_MASK(feature) (1ULL << feature)
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index 5899d01fa73d..e83ea2bc7f9c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -1077,12 +1077,9 @@ static void smu_v14_0_2_get_od_setting_limits(struct smu_context *smu,
 
 	switch (od_feature_bit) {
 	case PP_OD_FEATURE_GFXCLK_FMIN:
-		od_min_setting = overdrive_lowerlimits->GfxclkFmin;
-		od_max_setting = overdrive_upperlimits->GfxclkFmin;
-		break;
 	case PP_OD_FEATURE_GFXCLK_FMAX:
-		od_min_setting = overdrive_lowerlimits->GfxclkFmax;
-		od_max_setting = overdrive_upperlimits->GfxclkFmax;
+		od_min_setting = overdrive_lowerlimits->GfxclkFoffset;
+		od_max_setting = overdrive_upperlimits->GfxclkFoffset;
 		break;
 	case PP_OD_FEATURE_UCLK_FMIN:
 		od_min_setting = overdrive_lowerlimits->UclkFmin;
@@ -1269,10 +1266,16 @@ static int smu_v14_0_2_print_clk_levels(struct smu_context *smu,
 							 PP_OD_FEATURE_GFXCLK_BIT))
 			break;
 
-		size += sysfs_emit_at(buf, size, "OD_SCLK:\n");
-		size += sysfs_emit_at(buf, size, "0: %uMhz\n1: %uMhz\n",
-					od_table->OverDriveTable.GfxclkFmin,
-					od_table->OverDriveTable.GfxclkFmax);
+		PPTable_t *pptable = smu->smu_table.driver_pptable;
+		const OverDriveLimits_t * const overdrive_upperlimits =
+					&pptable->SkuTable.OverDriveLimitsBasicMax;
+		const OverDriveLimits_t * const overdrive_lowerlimits =
+					&pptable->SkuTable.OverDriveLimitsBasicMin;
+
+		size += sysfs_emit_at(buf, size, "OD_SCLK_OFFSET:\n");
+		size += sysfs_emit_at(buf, size, "0: %dMhz\n1: %uMhz\n",
+					overdrive_lowerlimits->GfxclkFoffset,
+					overdrive_upperlimits->GfxclkFoffset);
 		break;
 
 	case SMU_OD_MCLK:
@@ -1414,7 +1417,7 @@ static int smu_v14_0_2_print_clk_levels(struct smu_context *smu,
 							  PP_OD_FEATURE_GFXCLK_FMAX,
 							  NULL,
 							  &max_value);
-			size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "SCLK_OFFSET: %7dMhz %10uMhz\n",
 					      min_value, max_value);
 		}
 
@@ -1796,7 +1799,7 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu,
 	DpmActivityMonitorCoeffInt_t *activity_monitor =
 		&(activity_monitor_external.DpmActivityMonitorCoeffInt);
 	int workload_type, ret = 0;
-
+	uint32_t current_profile_mode = smu->power_profile_mode;
 	smu->power_profile_mode = input[size];
 
 	if (smu->power_profile_mode >= PP_SMC_POWER_PROFILE_COUNT) {
@@ -1854,6 +1857,11 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu,
 		}
 	}
 
+	if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE)
+		smu_v14_0_deep_sleep_control(smu, false);
+	else if (current_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE)
+		smu_v14_0_deep_sleep_control(smu, true);
+
 	/* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */
 	workload_type = smu_cmn_to_asic_specific_index(smu,
 						       CMN2ASIC_MAPPING_WORKLOAD,
@@ -2158,7 +2166,7 @@ static ssize_t smu_v14_0_2_get_gpu_metrics(struct smu_context *smu,
 
 	gpu_metrics->average_gfx_activity = metrics->AverageGfxActivity;
 	gpu_metrics->average_umc_activity = metrics->AverageUclkActivity;
-	gpu_metrics->average_mm_activity = max(metrics->Vcn0ActivityPercentage,
+	gpu_metrics->average_mm_activity = max(metrics->AverageVcn0ActivityPercentage,
 					       metrics->Vcn1ActivityPercentage);
 
 	gpu_metrics->average_socket_power = metrics->AverageSocketPower;
@@ -2217,8 +2225,7 @@ static void smu_v14_0_2_dump_od_table(struct smu_context *smu,
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	dev_dbg(adev->dev, "OD: Gfxclk: (%d, %d)\n", od_table->OverDriveTable.GfxclkFmin,
-						     od_table->OverDriveTable.GfxclkFmax);
+	dev_dbg(adev->dev, "OD: Gfxclk offset: (%d)\n", od_table->OverDriveTable.GfxclkFoffset);
 	dev_dbg(adev->dev, "OD: Uclk: (%d, %d)\n", od_table->OverDriveTable.UclkFmin,
 						   od_table->OverDriveTable.UclkFmax);
 }
@@ -2309,10 +2316,8 @@ static int smu_v14_0_2_set_default_od_settings(struct smu_context *smu)
 		memcpy(user_od_table,
 		       boot_od_table,
 		       sizeof(OverDriveTableExternal_t));
-		user_od_table->OverDriveTable.GfxclkFmin =
-				user_od_table_bak.OverDriveTable.GfxclkFmin;
-		user_od_table->OverDriveTable.GfxclkFmax =
-				user_od_table_bak.OverDriveTable.GfxclkFmax;
+		user_od_table->OverDriveTable.GfxclkFoffset =
+				user_od_table_bak.OverDriveTable.GfxclkFoffset;
 		user_od_table->OverDriveTable.UclkFmin =
 				user_od_table_bak.OverDriveTable.UclkFmin;
 		user_od_table->OverDriveTable.UclkFmax =
@@ -2441,22 +2446,6 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu,
 			}
 
 			switch (input[i]) {
-			case 0:
-				smu_v14_0_2_get_od_setting_limits(smu,
-								  PP_OD_FEATURE_GFXCLK_FMIN,
-								  &minimum,
-								  &maximum);
-				if (input[i + 1] < minimum ||
-				    input[i + 1] > maximum) {
-					dev_info(adev->dev, "GfxclkFmin (%ld) must be within [%u, %u]!\n",
-						input[i + 1], minimum, maximum);
-					return -EINVAL;
-				}
-
-				od_table->OverDriveTable.GfxclkFmin = input[i + 1];
-				od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFXCLK_BIT;
-				break;
-
 			case 1:
 				smu_v14_0_2_get_od_setting_limits(smu,
 								  PP_OD_FEATURE_GFXCLK_FMAX,
@@ -2469,7 +2458,7 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu,
 					return -EINVAL;
 				}
 
-				od_table->OverDriveTable.GfxclkFmax = input[i + 1];
+				od_table->OverDriveTable.GfxclkFoffset = input[i + 1];
 				od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFXCLK_BIT;
 				break;
 
@@ -2480,13 +2469,6 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu,
 			}
 		}
 
-		if (od_table->OverDriveTable.GfxclkFmin > od_table->OverDriveTable.GfxclkFmax) {
-			dev_err(adev->dev,
-				"Invalid setting: GfxclkFmin(%u) is bigger than GfxclkFmax(%u)\n",
-				(uint32_t)od_table->OverDriveTable.GfxclkFmin,
-				(uint32_t)od_table->OverDriveTable.GfxclkFmax);
-			return -EINVAL;
-		}
 		break;
 
 	case PP_OD_EDIT_MCLK_VDDC_TABLE:
diff --git a/drivers/gpu/drm/bridge/aux-bridge.c b/drivers/gpu/drm/bridge/aux-bridge.c
index b29980f95379..295e9d031e2d 100644
--- a/drivers/gpu/drm/bridge/aux-bridge.c
+++ b/drivers/gpu/drm/bridge/aux-bridge.c
@@ -58,9 +58,10 @@ int drm_aux_bridge_register(struct device *parent)
 	adev->id = ret;
 	adev->name = "aux_bridge";
 	adev->dev.parent = parent;
-	adev->dev.of_node = of_node_get(parent->of_node);
 	adev->dev.release = drm_aux_bridge_release;
 
+	device_set_of_node_from_dev(&adev->dev, parent);
+
 	ret = auxiliary_device_init(adev);
 	if (ret) {
 		ida_free(&drm_aux_bridge_ida, adev->id);
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index 290e2532fab1..f3afdab55c11 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -2391,6 +2391,7 @@ static int tc_probe_bridge_endpoint(struct tc_data *tc)
 			if (tc->pre_emphasis[0] < 0 || tc->pre_emphasis[0] > 2 ||
 			    tc->pre_emphasis[1] < 0 || tc->pre_emphasis[1] > 2) {
 				dev_err(dev, "Incorrect Pre-Emphasis setting, use either 0=0dB 1=3.5dB 2=6dB\n");
+				of_node_put(node);
 				return -EINVAL;
 			}
 		}
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index faa253b27664..14ac351fd76d 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -123,9 +123,8 @@ config DRM_I915_USERPTR
 config DRM_I915_GVT_KVMGT
 	tristate "Enable KVM host support Intel GVT-g graphics virtualization"
 	depends on DRM_I915
-	depends on X86
+	depends on KVM_X86
 	depends on 64BIT
-	depends on KVM
 	depends on VFIO
 	select DRM_I915_GVT
 	select KVM_EXTERNAL_WRITE_TRACKING
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 0a9ffc19e92f..10fd4601b9f2 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -890,7 +890,7 @@ void xe_device_l2_flush(struct xe_device *xe)
 	spin_lock(&gt->global_invl_lock);
 	xe_mmio_write32(gt, XE2_GLOBAL_INVAL, 0x1);
 
-	if (xe_mmio_wait32(gt, XE2_GLOBAL_INVAL, 0x1, 0x0, 150, NULL, true))
+	if (xe_mmio_wait32(gt, XE2_GLOBAL_INVAL, 0x1, 0x0, 500, NULL, true))
 		xe_gt_err_once(gt, "Global invalidation timeout\n");
 	spin_unlock(&gt->global_invl_lock);
 
diff --git a/drivers/gpu/drm/xe/xe_force_wake.c b/drivers/gpu/drm/xe/xe_force_wake.c
index b263fff15273..7d9fc489dcb8 100644
--- a/drivers/gpu/drm/xe/xe_force_wake.c
+++ b/drivers/gpu/drm/xe/xe_force_wake.c
@@ -115,9 +115,15 @@ static int __domain_wait(struct xe_gt *gt, struct xe_force_wake_domain *domain,
 			     XE_FORCE_WAKE_ACK_TIMEOUT_MS * USEC_PER_MSEC,
 			     &value, true);
 	if (ret)
-		xe_gt_notice(gt, "Force wake domain %d failed to ack %s (%pe) reg[%#x] = %#x\n",
-			     domain->id, str_wake_sleep(wake), ERR_PTR(ret),
-			     domain->reg_ack.addr, value);
+		xe_gt_err(gt, "Force wake domain %d failed to ack %s (%pe) reg[%#x] = %#x\n",
+			  domain->id, str_wake_sleep(wake), ERR_PTR(ret),
+			  domain->reg_ack.addr, value);
+	if (value == ~0) {
+		xe_gt_err(gt,
+			  "Force wake domain %d: %s. MMIO unreliable (forcewake register returns 0xFFFFFFFF)!\n",
+			  domain->id, str_wake_sleep(wake));
+		ret = -EIO;
+	}
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index d16eb9ab49fb..17986bfd8818 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -898,6 +898,24 @@ retry_same_fence:
 	ret = wait_event_timeout(ct->g2h_fence_wq, g2h_fence.done, HZ);
 
 	/*
+	 * Occasionally it is seen that the G2H worker starts running after a delay of more than
+	 * a second even after being queued and activated by the Linux workqueue subsystem. This
+	 * leads to G2H timeout error. The root cause of issue lies with scheduling latency of
+	 * Lunarlake Hybrid CPU. Issue dissappears if we disable Lunarlake atom cores from BIOS
+	 * and this is beyond xe kmd.
+	 *
+	 * TODO: Drop this change once workqueue scheduling delay issue is fixed on LNL Hybrid CPU.
+	 */
+	if (!ret) {
+		flush_work(&ct->g2h_worker);
+		if (g2h_fence.done) {
+			xe_gt_warn(gt, "G2H fence %u, action %04x, done\n",
+				   g2h_fence.seqno, action[0]);
+			ret = 1;
+		}
+	}
+
+	/*
 	 * Ensure we serialize with completion side to prevent UAF with fence going out of scope on
 	 * the stack, since we have no clue if it will fire after the timeout before we can erase
 	 * from the xa. Also we have some dependent loads and stores below for which we need the
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 8a9254e5af6e..d333be9c4227 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1726,8 +1726,13 @@ void xe_guc_submit_stop(struct xe_guc *guc)
 
 	mutex_lock(&guc->submission_state.lock);
 
-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+		/* Prevent redundant attempts to stop parallel queues */
+		if (q->guc->id != index)
+			continue;
+
 		guc_exec_queue_stop(guc, q);
+	}
 
 	mutex_unlock(&guc->submission_state.lock);
 
@@ -1765,8 +1770,13 @@ int xe_guc_submit_start(struct xe_guc *guc)
 
 	mutex_lock(&guc->submission_state.lock);
 	atomic_dec(&guc->submission_state.stopped);
-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+		/* Prevent redundant attempts to start parallel queues */
+		if (q->guc->id != index)
+			continue;
+
 		guc_exec_queue_start(q);
+	}
 	mutex_unlock(&guc->submission_state.lock);
 
 	wake_up_all(&guc->ct.wq);
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index c6cf227ead40..2e72c06fd40d 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -54,8 +54,9 @@ static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr,
 {
 	struct xe_user_fence *ufence;
 	u64 __user *ptr = u64_to_user_ptr(addr);
+	u64 __maybe_unused prefetch_val;
 
-	if (!access_ok(ptr, sizeof(*ptr)))
+	if (get_user(prefetch_val, ptr))
 		return ERR_PTR(-EFAULT);
 
 	ufence = kzalloc(sizeof(*ufence), GFP_KERNEL);