Merge tag 'drm-fixes-2024-01-05' of git://anongit.freedesktop.org/drm/drm

Pull more drm fixes from Dave Airlie:
 "The amdgpu ones are fairly normal, the one that is a bit large is a
  fix for a newly introduced IP in 6.7 so unlikely to cause regressions.

  The nouveau ones are mostly memory leaks and debugging cleanups from
  the GSP (new nvidia firmware) enablement. There are some GSP changes
  to the message passing code and a subsequent fix for eDP panel turn
  on, that means my laptop can turn on the panel in GSP mode. These are
  fairly low chance of disrupting things since GSP is new in 6.7. The
  final not all in GSP fix is a deadlock seen with i915/nouveau when GSP
  is used where the the fence and irq paths have locking inversions,
  I've pushed some irq enablement out to a workqueue, and this has seen
  some fairly decent testing.

  amdgpu:
   - DP MST fix
   - SMU 13.0.6 fixes
   - fix displays on macbooks using vega12
   - fix VSC and colorimetry on DP/eDP

  nouveau:
   - fix deadlock between fence signalling and irq paths
   - fix GSP memory leaks
   - fix GSP leftover debug
   - hide some GSP callback messages
   - fix GSP display disable path
   - fix GSP ACPI interaction
   - handle errors in ctrl messages
   - use errors info to fix DP link training"

* tag 'drm-fixes-2024-01-05' of git://anongit.freedesktop.org/drm/drm:
  drm/nouveau/dp: Honor GSP link training retry timeouts
  nouveau: push event block/allowing out of the fence context
  nouveau/gsp: always free the alloc messages on r535
  nouveau/gsp: don't free ctrl messages on errors
  nouveau/gsp: convert gsp errors to generic errors
  drm/nouveau/gsp: Fix ACPI MXDM/MXDS method invocations
  nouveau/gsp: free userd allocation.
  nouveau/gsp: free acpi object after use
  nouveau: fix disp disabling with GSP
  nouveau/gsp: drop some acpi related debug
  nouveau/gsp: add three notifier callbacks that we see in normal operation (v2)
  drm/amd/pm: Use gpu_metrics_v1_5 for SMUv13.0.6
  drm/amd/pm: Add gpu_metrics_v1_5
  drm/amd/pm: Add mem_busy_percent for GCv9.4.3 apu
  drm/amd/display: Fix sending VSC (+ colorimetry) packets for DP/eDP displays without PSR
  drm/amdgpu: skip gpu_info fw loading on navi12
  drm/amd/display: add nv12 bounding box
  drm/amd/pm: Update metric table for jpeg/vcn data
  drm/amd/pm: Use separate metric table for APU
  drm/amd/display: pbn_div need be updated for hotplug event

16 files changed, 603 insertions, 196 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 8dee52ce26d0..93cf73d6fa11 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2188,15 +2188,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 
 	adev->firmware.gpu_info_fw = NULL;
 
-	if (adev->mman.discovery_bin) {
-		/*
-		 * FIXME: The bounding box is still needed by Navi12, so
-		 * temporarily read it from gpu_info firmware. Should be dropped
-		 * when DAL no longer needs it.
-		 */
-		if (adev->asic_type != CHIP_NAVI12)
-			return 0;
-	}
+	if (adev->mman.discovery_bin)
+		return 0;
 
 	switch (adev->asic_type) {
 	default:
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 c8c00c2a5224..4e82ee4d74ac 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -6170,8 +6170,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 
 	if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
 		mod_build_hf_vsif_infopacket(stream, &stream->vsp_infopacket);
-
-	if (stream->link->psr_settings.psr_feature_enabled || stream->link->replay_settings.replay_feature_enabled) {
+	else if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT ||
+			 stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST ||
+			 stream->signal == SIGNAL_TYPE_EDP) {
 		//
 		// should decide stream support vsc sdp colorimetry capability
 		// before building vsc info packet
@@ -6187,8 +6188,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 		if (stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22)
 			tf = TRANSFER_FUNC_GAMMA_22;
 		mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf);
-		aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
 
+		if (stream->link->psr_settings.psr_feature_enabled)
+			aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
 	}
 finish:
 	dc_sink_release(sink);
@@ -6914,8 +6916,7 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder,
 	if (IS_ERR(mst_state))
 		return PTR_ERR(mst_state);
 
-	if (!mst_state->pbn_div)
-		mst_state->pbn_div = dm_mst_get_pbn_divider(aconnector->mst_root->dc_link);
+	mst_state->pbn_div = dm_mst_get_pbn_divider(aconnector->mst_root->dc_link);
 
 	if (!state->duplicated) {
 		int max_bpc = conn_state->max_requested_bpc;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index ec77b2b41ba3..d2271e308fa0 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -440,7 +440,115 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = {
 	.use_urgent_burst_bw = 0
 };
 
-struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { 0 };
+struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = {
+	.clock_limits = {
+		{
+			.state = 0,
+			.dcfclk_mhz = 560.0,
+			.fabricclk_mhz = 560.0,
+			.dispclk_mhz = 513.0,
+			.dppclk_mhz = 513.0,
+			.phyclk_mhz = 540.0,
+			.socclk_mhz = 560.0,
+			.dscclk_mhz = 171.0,
+			.dram_speed_mts = 1069.0,
+		},
+		{
+			.state = 1,
+			.dcfclk_mhz = 694.0,
+			.fabricclk_mhz = 694.0,
+			.dispclk_mhz = 642.0,
+			.dppclk_mhz = 642.0,
+			.phyclk_mhz = 600.0,
+			.socclk_mhz = 694.0,
+			.dscclk_mhz = 214.0,
+			.dram_speed_mts = 1324.0,
+		},
+		{
+			.state = 2,
+			.dcfclk_mhz = 875.0,
+			.fabricclk_mhz = 875.0,
+			.dispclk_mhz = 734.0,
+			.dppclk_mhz = 734.0,
+			.phyclk_mhz = 810.0,
+			.socclk_mhz = 875.0,
+			.dscclk_mhz = 245.0,
+			.dram_speed_mts = 1670.0,
+		},
+		{
+			.state = 3,
+			.dcfclk_mhz = 1000.0,
+			.fabricclk_mhz = 1000.0,
+			.dispclk_mhz = 1100.0,
+			.dppclk_mhz = 1100.0,
+			.phyclk_mhz = 810.0,
+			.socclk_mhz = 1000.0,
+			.dscclk_mhz = 367.0,
+			.dram_speed_mts = 2000.0,
+		},
+		{
+			.state = 4,
+			.dcfclk_mhz = 1200.0,
+			.fabricclk_mhz = 1200.0,
+			.dispclk_mhz = 1284.0,
+			.dppclk_mhz = 1284.0,
+			.phyclk_mhz = 810.0,
+			.socclk_mhz = 1200.0,
+			.dscclk_mhz = 428.0,
+			.dram_speed_mts = 2000.0,
+		},
+		{
+			.state = 5,
+			.dcfclk_mhz = 1200.0,
+			.fabricclk_mhz = 1200.0,
+			.dispclk_mhz = 1284.0,
+			.dppclk_mhz = 1284.0,
+			.phyclk_mhz = 810.0,
+			.socclk_mhz = 1200.0,
+			.dscclk_mhz = 428.0,
+			.dram_speed_mts = 2000.0,
+		},
+	},
+
+	.num_states = 5,
+	.sr_exit_time_us = 1.9,
+	.sr_enter_plus_exit_time_us = 4.4,
+	.urgent_latency_us = 3.0,
+	.urgent_latency_pixel_data_only_us = 4.0,
+	.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
+	.urgent_latency_vm_data_only_us = 4.0,
+	.urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096,
+	.urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096,
+	.urgent_out_of_order_return_per_channel_vm_only_bytes = 4096,
+	.pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 40.0,
+	.pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 40.0,
+	.pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0,
+	.max_avg_sdp_bw_use_normal_percent = 40.0,
+	.max_avg_dram_bw_use_normal_percent = 40.0,
+	.writeback_latency_us = 12.0,
+	.ideal_dram_bw_after_urgent_percent = 40.0,
+	.max_request_size_bytes = 256,
+	.dram_channel_width_bytes = 16,
+	.fabric_datapath_to_dcn_data_return_bytes = 64,
+	.dcn_downspread_percent = 0.5,
+	.downspread_percent = 0.5,
+	.dram_page_open_time_ns = 50.0,
+	.dram_rw_turnaround_time_ns = 17.5,
+	.dram_return_buffer_per_channel_bytes = 8192,
+	.round_trip_ping_latency_dcfclk_cycles = 131,
+	.urgent_out_of_order_return_per_channel_bytes = 4096,
+	.channel_interleave_bytes = 256,
+	.num_banks = 8,
+	.num_chans = 16,
+	.vmm_page_size_bytes = 4096,
+	.dram_clock_change_latency_us = 45.0,
+	.writeback_dram_clock_change_latency_us = 23.0,
+	.return_bus_width_bytes = 64,
+	.dispclk_dppclk_vco_speed_mhz = 3850,
+	.xfc_bus_transport_time_us = 20,
+	.xfc_xbuf_latency_tolerance_us = 50,
+	.use_urgent_burst_bw = 0,
+};
 
 struct _vcs_dpi_ip_params_st dcn2_1_ip = {
 	.odm_capable = 1,
diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
index 84f9b412a4f1..738ee763f24a 100644
--- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
+++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
@@ -147,12 +147,15 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 	}
 
 	/* VSC packet set to 4 for PSR-SU, or 2 for PSR1 */
-	if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1)
-		vsc_packet_revision = vsc_packet_rev4;
-	else if (stream->link->replay_settings.config.replay_supported)
+	if (stream->link->psr_settings.psr_feature_enabled) {
+		if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1)
+			vsc_packet_revision = vsc_packet_rev4;
+		else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1)
+			vsc_packet_revision = vsc_packet_rev2;
+	}
+
+	if (stream->link->replay_settings.config.replay_supported)
 		vsc_packet_revision = vsc_packet_rev4;
-	else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1)
-		vsc_packet_revision = vsc_packet_rev2;
 
 	/* Update to revision 5 for extended colorimetry support */
 	if (stream->use_vsc_sdp_for_colorimetry)
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index 1c5049e894e3..c2ccf3724e37 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -318,6 +318,7 @@ enum pp_xgmi_plpd_mode {
 #define MAX_GFX_CLKS 8
 #define MAX_CLKS 4
 #define NUM_VCN 4
+#define NUM_JPEG_ENG 32
 
 struct seq_file;
 enum amd_pp_clock_type;
@@ -774,6 +775,85 @@ struct gpu_metrics_v1_4 {
 	uint16_t			padding;
 };
 
+struct gpu_metrics_v1_5 {
+	struct metrics_table_header	common_header;
+
+	/* Temperature (Celsius) */
+	uint16_t			temperature_hotspot;
+	uint16_t			temperature_mem;
+	uint16_t			temperature_vrsoc;
+
+	/* Power (Watts) */
+	uint16_t			curr_socket_power;
+
+	/* Utilization (%) */
+	uint16_t			average_gfx_activity;
+	uint16_t			average_umc_activity; // memory controller
+	uint16_t			vcn_activity[NUM_VCN];
+	uint16_t			jpeg_activity[NUM_JPEG_ENG];
+
+	/* Energy (15.259uJ (2^-16) units) */
+	uint64_t			energy_accumulator;
+
+	/* Driver attached timestamp (in ns) */
+	uint64_t			system_clock_counter;
+
+	/* Throttle status */
+	uint32_t			throttle_status;
+
+	/* Clock Lock Status. Each bit corresponds to clock instance */
+	uint32_t			gfxclk_lock_status;
+
+	/* Link width (number of lanes) and speed (in 0.1 GT/s) */
+	uint16_t			pcie_link_width;
+	uint16_t			pcie_link_speed;
+
+	/* XGMI bus width and bitrate (in Gbps) */
+	uint16_t			xgmi_link_width;
+	uint16_t			xgmi_link_speed;
+
+	/* Utilization Accumulated (%) */
+	uint32_t			gfx_activity_acc;
+	uint32_t			mem_activity_acc;
+
+	/*PCIE accumulated bandwidth (GB/sec) */
+	uint64_t			pcie_bandwidth_acc;
+
+	/*PCIE instantaneous bandwidth (GB/sec) */
+	uint64_t			pcie_bandwidth_inst;
+
+	/* PCIE L0 to recovery state transition accumulated count */
+	uint64_t			pcie_l0_to_recov_count_acc;
+
+	/* PCIE replay accumulated count */
+	uint64_t			pcie_replay_count_acc;
+
+	/* PCIE replay rollover accumulated count */
+	uint64_t			pcie_replay_rover_count_acc;
+
+	/* PCIE NAK sent  accumulated count */
+	uint32_t			pcie_nak_sent_count_acc;
+
+	/* PCIE NAK received accumulated count */
+	uint32_t			pcie_nak_rcvd_count_acc;
+
+	/* XGMI accumulated data transfer size(KiloBytes) */
+	uint64_t			xgmi_read_data_acc[NUM_XGMI_LINKS];
+	uint64_t			xgmi_write_data_acc[NUM_XGMI_LINKS];
+
+	/* PMFW attached timestamp (10ns resolution) */
+	uint64_t			firmware_timestamp;
+
+	/* Current clocks (Mhz) */
+	uint16_t			current_gfxclk[MAX_GFX_CLKS];
+	uint16_t			current_socclk[MAX_CLKS];
+	uint16_t			current_vclk0[MAX_CLKS];
+	uint16_t			current_dclk0[MAX_CLKS];
+	uint16_t			current_uclk;
+
+	uint16_t			padding;
+};
+
 /*
  * gpu_metrics_v2_0 is not recommended as it's not naturally aligned.
  * Use gpu_metrics_v2_1 or later instead.
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 49028dde0f87..20c53eefd680 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -2128,7 +2128,9 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 		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, 0, 1))
+		if ((adev->flags & AMD_IS_APU &&
+		     gc_ver != IP_VERSION(9, 4, 3)) ||
+		    gc_ver == IP_VERSION(9, 0, 1))
 			*states = ATTR_STATE_UNSUPPORTED;
 	} else if (DEVICE_ATTR_IS(pcie_bw)) {
 		/* PCIe Perf counters won't work on APU nodes */
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h
index fef2d290f3f2..7b812b9994d7 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h
@@ -123,7 +123,7 @@ typedef enum {
   VOLTAGE_GUARDBAND_COUNT
 } GFX_GUARDBAND_e;
 
-#define SMU_METRICS_TABLE_VERSION 0x9
+#define SMU_METRICS_TABLE_VERSION 0xB
 
 typedef struct __attribute__((packed, aligned(4))) {
   uint32_t AccumulationCounter;
@@ -219,7 +219,103 @@ typedef struct __attribute__((packed, aligned(4))) {
   uint32_t PCIenReplayARolloverCountAcc;  // The Pcie counter itself is accumulated
   uint32_t PCIeNAKSentCountAcc;           // The Pcie counter itself is accumulated
   uint32_t PCIeNAKReceivedCountAcc;       // The Pcie counter itself is accumulated
-} MetricsTable_t;
+
+  // VCN/JPEG ACTIVITY
+  uint32_t VcnBusy[4];
+  uint32_t JpegBusy[32];
+} MetricsTableX_t;
+
+typedef struct __attribute__((packed, aligned(4))) {
+  uint32_t AccumulationCounter;
+
+  //TEMPERATURE
+  uint32_t MaxSocketTemperature;
+  uint32_t MaxVrTemperature;
+  uint32_t MaxHbmTemperature;
+  uint64_t MaxSocketTemperatureAcc;
+  uint64_t MaxVrTemperatureAcc;
+  uint64_t MaxHbmTemperatureAcc;
+
+  //POWER
+  uint32_t SocketPowerLimit;
+  uint32_t MaxSocketPowerLimit;
+  uint32_t SocketPower;
+
+  //ENERGY
+  uint64_t Timestamp;
+  uint64_t SocketEnergyAcc;
+  uint64_t CcdEnergyAcc;
+  uint64_t XcdEnergyAcc;
+  uint64_t AidEnergyAcc;
+  uint64_t HbmEnergyAcc;
+
+  //FREQUENCY
+  uint32_t CclkFrequencyLimit;
+  uint32_t GfxclkFrequencyLimit;
+  uint32_t FclkFrequency;
+  uint32_t UclkFrequency;
+  uint32_t SocclkFrequency[4];
+  uint32_t VclkFrequency[4];
+  uint32_t DclkFrequency[4];
+  uint32_t LclkFrequency[4];
+  uint64_t GfxclkFrequencyAcc[8];
+  uint64_t CclkFrequencyAcc[96];
+
+  //FREQUENCY RANGE
+  uint32_t MaxCclkFrequency;
+  uint32_t MinCclkFrequency;
+  uint32_t MaxGfxclkFrequency;
+  uint32_t MinGfxclkFrequency;
+  uint32_t FclkFrequencyTable[4];
+  uint32_t UclkFrequencyTable[4];
+  uint32_t SocclkFrequencyTable[4];
+  uint32_t VclkFrequencyTable[4];
+  uint32_t DclkFrequencyTable[4];
+  uint32_t LclkFrequencyTable[4];
+  uint32_t MaxLclkDpmRange;
+  uint32_t MinLclkDpmRange;
+
+  //XGMI
+  uint32_t XgmiWidth;
+  uint32_t XgmiBitrate;
+  uint64_t XgmiReadBandwidthAcc[8];
+  uint64_t XgmiWriteBandwidthAcc[8];
+
+  //ACTIVITY
+  uint32_t SocketC0Residency;
+  uint32_t SocketGfxBusy;
+  uint32_t DramBandwidthUtilization;
+  uint64_t SocketC0ResidencyAcc;
+  uint64_t SocketGfxBusyAcc;
+  uint64_t DramBandwidthAcc;
+  uint32_t MaxDramBandwidth;
+  uint64_t DramBandwidthUtilizationAcc;
+  uint64_t PcieBandwidthAcc[4];
+
+  //THROTTLERS
+  uint32_t ProchotResidencyAcc;
+  uint32_t PptResidencyAcc;
+  uint32_t SocketThmResidencyAcc;
+  uint32_t VrThmResidencyAcc;
+  uint32_t HbmThmResidencyAcc;
+  uint32_t GfxLockXCDMak;
+
+  // New Items at end to maintain driver compatibility
+  uint32_t GfxclkFrequency[8];
+
+  //PSNs
+  uint64_t PublicSerialNumber_AID[4];
+  uint64_t PublicSerialNumber_XCD[8];
+  uint64_t PublicSerialNumber_CCD[12];
+
+  //XGMI Data tranfser size
+  uint64_t XgmiReadDataSizeAcc[8];//in KByte
+  uint64_t XgmiWriteDataSizeAcc[8];//in KByte
+
+  // VCN/JPEG ACTIVITY
+  uint32_t VcnBusy[4];
+  uint32_t JpegBusy[32];
+} MetricsTableA_t;
 
 #define SMU_VF_METRICS_TABLE_VERSION 0x3
 
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 900a2d9e6d85..b64e07b75937 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
@@ -245,6 +245,8 @@ struct PPTable_t {
 #define SMUQ10_TO_UINT(x) ((x) >> 10)
 #define SMUQ10_FRAC(x) ((x) & 0x3ff)
 #define SMUQ10_ROUND(x) ((SMUQ10_TO_UINT(x)) + ((SMUQ10_FRAC(x)) >= 0x200))
+#define GET_METRIC_FIELD(field) ((adev->flags & AMD_IS_APU) ?\
+		(metrics_a->field) : (metrics_x->field))
 
 struct smu_v13_0_6_dpm_map {
 	enum smu_clk_type clk_type;
@@ -327,7 +329,8 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu)
 		SMU_TABLE_INIT(tables, SMU_TABLE_PMSTATUSLOG, SMU13_TOOL_SIZE,
 			       PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
 
-	SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(MetricsTable_t),
+	SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS,
+		       max(sizeof(MetricsTableX_t), sizeof(MetricsTableA_t)),
 		       PAGE_SIZE,
 		       AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT);
 
@@ -335,12 +338,13 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu)
 		       PAGE_SIZE,
 		       AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT);
 
-	smu_table->metrics_table = kzalloc(sizeof(MetricsTable_t), GFP_KERNEL);
+	smu_table->metrics_table = kzalloc(max(sizeof(MetricsTableX_t),
+		       sizeof(MetricsTableA_t)), GFP_KERNEL);
 	if (!smu_table->metrics_table)
 		return -ENOMEM;
 	smu_table->metrics_time = 0;
 
-	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_4);
+	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_5);
 	smu_table->gpu_metrics_table =
 		kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL);
 	if (!smu_table->gpu_metrics_table) {
@@ -431,9 +435,11 @@ static int smu_v13_0_6_get_metrics_table(struct smu_context *smu,
 static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	MetricsTable_t *metrics = (MetricsTable_t *)smu_table->metrics_table;
+	MetricsTableX_t *metrics_x = (MetricsTableX_t *)smu_table->metrics_table;
+	MetricsTableA_t *metrics_a = (MetricsTableA_t *)smu_table->metrics_table;
 	struct PPTable_t *pptable =
 		(struct PPTable_t *)smu_table->driver_pptable;
+	struct amdgpu_device *adev = smu->adev;
 	int ret, i, retry = 100;
 
 	/* Store one-time values in driver PPTable */
@@ -444,7 +450,7 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu)
 				return ret;
 
 			/* Ensure that metrics have been updated */
-			if (metrics->AccumulationCounter)
+			if (GET_METRIC_FIELD(AccumulationCounter))
 				break;
 
 			usleep_range(1000, 1100);
@@ -454,29 +460,29 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu)
 			return -ETIME;
 
 		pptable->MaxSocketPowerLimit =
-			SMUQ10_ROUND(metrics->MaxSocketPowerLimit);
+			SMUQ10_ROUND(GET_METRIC_FIELD(MaxSocketPowerLimit));
 		pptable->MaxGfxclkFrequency =
-			SMUQ10_ROUND(metrics->MaxGfxclkFrequency);
+			SMUQ10_ROUND(GET_METRIC_FIELD(MaxGfxclkFrequency));
 		pptable->MinGfxclkFrequency =
-			SMUQ10_ROUND(metrics->MinGfxclkFrequency);
+			SMUQ10_ROUND(GET_METRIC_FIELD(MinGfxclkFrequency));
 
 		for (i = 0; i < 4; ++i) {
 			pptable->FclkFrequencyTable[i] =
-				SMUQ10_ROUND(metrics->FclkFrequencyTable[i]);
+				SMUQ10_ROUND(GET_METRIC_FIELD(FclkFrequencyTable)[i]);
 			pptable->UclkFrequencyTable[i] =
-				SMUQ10_ROUND(metrics->UclkFrequencyTable[i]);
+				SMUQ10_ROUND(GET_METRIC_FIELD(UclkFrequencyTable)[i]);
 			pptable->SocclkFrequencyTable[i] = SMUQ10_ROUND(
-				metrics->SocclkFrequencyTable[i]);
+				GET_METRIC_FIELD(SocclkFrequencyTable)[i]);
 			pptable->VclkFrequencyTable[i] =
-				SMUQ10_ROUND(metrics->VclkFrequencyTable[i]);
+				SMUQ10_ROUND(GET_METRIC_FIELD(VclkFrequencyTable)[i]);
 			pptable->DclkFrequencyTable[i] =
-				SMUQ10_ROUND(metrics->DclkFrequencyTable[i]);
+				SMUQ10_ROUND(GET_METRIC_FIELD(DclkFrequencyTable)[i]);
 			pptable->LclkFrequencyTable[i] =
-				SMUQ10_ROUND(metrics->LclkFrequencyTable[i]);
+				SMUQ10_ROUND(GET_METRIC_FIELD(LclkFrequencyTable)[i]);
 		}
 
 		/* use AID0 serial number by default */
-		pptable->PublicSerialNumber_AID = metrics->PublicSerialNumber_AID[0];
+		pptable->PublicSerialNumber_AID = GET_METRIC_FIELD(PublicSerialNumber_AID)[0];
 
 		pptable->Init = true;
 	}
@@ -778,7 +784,8 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu,
 					    uint32_t *value)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	MetricsTable_t *metrics = (MetricsTable_t *)smu_table->metrics_table;
+	MetricsTableX_t *metrics_x = (MetricsTableX_t *)smu_table->metrics_table;
+	MetricsTableA_t *metrics_a = (MetricsTableA_t *)smu_table->metrics_table;
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 	int xcc_id;
@@ -793,50 +800,50 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu,
 	case METRICS_AVERAGE_GFXCLK:
 		if (smu->smc_fw_version >= 0x552F00) {
 			xcc_id = GET_INST(GC, 0);
-			*value = SMUQ10_ROUND(metrics->GfxclkFrequency[xcc_id]);
+			*value = SMUQ10_ROUND(GET_METRIC_FIELD(GfxclkFrequency)[xcc_id]);
 		} else {
 			*value = 0;
 		}
 		break;
 	case METRICS_CURR_SOCCLK:
 	case METRICS_AVERAGE_SOCCLK:
-		*value = SMUQ10_ROUND(metrics->SocclkFrequency[0]);
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(SocclkFrequency)[0]);
 		break;
 	case METRICS_CURR_UCLK:
 	case METRICS_AVERAGE_UCLK:
-		*value = SMUQ10_ROUND(metrics->UclkFrequency);
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(UclkFrequency));
 		break;
 	case METRICS_CURR_VCLK:
-		*value = SMUQ10_ROUND(metrics->VclkFrequency[0]);
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(VclkFrequency)[0]);
 		break;
 	case METRICS_CURR_DCLK:
-		*value = SMUQ10_ROUND(metrics->DclkFrequency[0]);
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(DclkFrequency)[0]);
 		break;
 	case METRICS_CURR_FCLK:
-		*value = SMUQ10_ROUND(metrics->FclkFrequency);
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(FclkFrequency));
 		break;
 	case METRICS_AVERAGE_GFXACTIVITY:
-		*value = SMUQ10_ROUND(metrics->SocketGfxBusy);
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(SocketGfxBusy));
 		break;
 	case METRICS_AVERAGE_MEMACTIVITY:
-		*value = SMUQ10_ROUND(metrics->DramBandwidthUtilization);
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(DramBandwidthUtilization));
 		break;
 	case METRICS_CURR_SOCKETPOWER:
-		*value = SMUQ10_ROUND(metrics->SocketPower) << 8;
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(SocketPower)) << 8;
 		break;
 	case METRICS_TEMPERATURE_HOTSPOT:
-		*value = SMUQ10_ROUND(metrics->MaxSocketTemperature) *
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(MaxSocketTemperature)) *
 			 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
 	case METRICS_TEMPERATURE_MEM:
-		*value = SMUQ10_ROUND(metrics->MaxHbmTemperature) *
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(MaxHbmTemperature)) *
 			 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
 	/* This is the max of all VRs and not just SOC VR.
 	 * No need to define another data type for the same.
 	 */
 	case METRICS_TEMPERATURE_VRSOC:
-		*value = SMUQ10_ROUND(metrics->MaxVrTemperature) *
+		*value = SMUQ10_ROUND(GET_METRIC_FIELD(MaxVrTemperature)) *
 			 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
 	default:
@@ -2022,67 +2029,70 @@ static int smu_v13_0_6_get_current_pcie_link_speed(struct smu_context *smu)
 static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	struct gpu_metrics_v1_4 *gpu_metrics =
-		(struct gpu_metrics_v1_4 *)smu_table->gpu_metrics_table;
+	struct gpu_metrics_v1_5 *gpu_metrics =
+		(struct gpu_metrics_v1_5 *)smu_table->gpu_metrics_table;
 	struct amdgpu_device *adev = smu->adev;
-	int ret = 0, xcc_id, inst, i;
-	MetricsTable_t *metrics;
+	int ret = 0, xcc_id, inst, i, j;
+	MetricsTableX_t *metrics_x;
+	MetricsTableA_t *metrics_a;
 	u16 link_width_level;
 
-	metrics = kzalloc(sizeof(MetricsTable_t), GFP_KERNEL);
-	ret = smu_v13_0_6_get_metrics_table(smu, metrics, true);
+	metrics_x = kzalloc(max(sizeof(MetricsTableX_t), sizeof(MetricsTableA_t)), GFP_KERNEL);
+	ret = smu_v13_0_6_get_metrics_table(smu, metrics_x, true);
 	if (ret) {
-		kfree(metrics);
+		kfree(metrics_x);
 		return ret;
 	}
 
-	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 4);
+	metrics_a = (MetricsTableA_t *)metrics_x;
+
+	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 5);
 
 	gpu_metrics->temperature_hotspot =
-		SMUQ10_ROUND(metrics->MaxSocketTemperature);
+		SMUQ10_ROUND(GET_METRIC_FIELD(MaxSocketTemperature));
 	/* Individual HBM stack temperature is not reported */
 	gpu_metrics->temperature_mem =
-		SMUQ10_ROUND(metrics->MaxHbmTemperature);
+		SMUQ10_ROUND(GET_METRIC_FIELD(MaxHbmTemperature));
 	/* Reports max temperature of all voltage rails */
 	gpu_metrics->temperature_vrsoc =
-		SMUQ10_ROUND(metrics->MaxVrTemperature);
+		SMUQ10_ROUND(GET_METRIC_FIELD(MaxVrTemperature));
 
 	gpu_metrics->average_gfx_activity =
-		SMUQ10_ROUND(metrics->SocketGfxBusy);
+		SMUQ10_ROUND(GET_METRIC_FIELD(SocketGfxBusy));
 	gpu_metrics->average_umc_activity =
-		SMUQ10_ROUND(metrics->DramBandwidthUtilization);
+		SMUQ10_ROUND(GET_METRIC_FIELD(DramBandwidthUtilization));
 
 	gpu_metrics->curr_socket_power =
-		SMUQ10_ROUND(metrics->SocketPower);
+		SMUQ10_ROUND(GET_METRIC_FIELD(SocketPower));
 	/* Energy counter reported in 15.259uJ (2^-16) units */
-	gpu_metrics->energy_accumulator = metrics->SocketEnergyAcc;
+	gpu_metrics->energy_accumulator = GET_METRIC_FIELD(SocketEnergyAcc);
 
 	for (i = 0; i < MAX_GFX_CLKS; i++) {
 		xcc_id = GET_INST(GC, i);
 		if (xcc_id >= 0)
 			gpu_metrics->current_gfxclk[i] =
-				SMUQ10_ROUND(metrics->GfxclkFrequency[xcc_id]);
+				SMUQ10_ROUND(GET_METRIC_FIELD(GfxclkFrequency)[xcc_id]);
 
 		if (i < MAX_CLKS) {
 			gpu_metrics->current_socclk[i] =
-				SMUQ10_ROUND(metrics->SocclkFrequency[i]);
+				SMUQ10_ROUND(GET_METRIC_FIELD(SocclkFrequency)[i]);
 			inst = GET_INST(VCN, i);
 			if (inst >= 0) {
 				gpu_metrics->current_vclk0[i] =
-					SMUQ10_ROUND(metrics->VclkFrequency[inst]);
+					SMUQ10_ROUND(GET_METRIC_FIELD(VclkFrequency)[inst]);
 				gpu_metrics->current_dclk0[i] =
-					SMUQ10_ROUND(metrics->DclkFrequency[inst]);
+					SMUQ10_ROUND(GET_METRIC_FIELD(DclkFrequency)[inst]);
 			}
 		}
 	}
 
-	gpu_metrics->current_uclk = SMUQ10_ROUND(metrics->UclkFrequency);
+	gpu_metrics->current_uclk = SMUQ10_ROUND(GET_METRIC_FIELD(UclkFrequency));
 
 	/* Throttle status is not reported through metrics now */
 	gpu_metrics->throttle_status = 0;
 
 	/* Clock Lock Status. Each bit corresponds to each GFXCLK instance */
-	gpu_metrics->gfxclk_lock_status = metrics->GfxLockXCDMak >> GET_INST(GC, 0);
+	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);
@@ -2094,38 +2104,57 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 		gpu_metrics->pcie_link_speed =
 			smu_v13_0_6_get_current_pcie_link_speed(smu);
 		gpu_metrics->pcie_bandwidth_acc =
-				SMUQ10_ROUND(metrics->PcieBandwidthAcc[0]);
+				SMUQ10_ROUND(metrics_x->PcieBandwidthAcc[0]);
 		gpu_metrics->pcie_bandwidth_inst =
-				SMUQ10_ROUND(metrics->PcieBandwidth[0]);
+				SMUQ10_ROUND(metrics_x->PcieBandwidth[0]);
 		gpu_metrics->pcie_l0_to_recov_count_acc =
-				metrics->PCIeL0ToRecoveryCountAcc;
+				metrics_x->PCIeL0ToRecoveryCountAcc;
 		gpu_metrics->pcie_replay_count_acc =
-				metrics->PCIenReplayAAcc;
+				metrics_x->PCIenReplayAAcc;
 		gpu_metrics->pcie_replay_rover_count_acc =
-				metrics->PCIenReplayARolloverCountAcc;
+				metrics_x->PCIenReplayARolloverCountAcc;
+		gpu_metrics->pcie_nak_sent_count_acc =
+				metrics_x->PCIeNAKSentCountAcc;
+		gpu_metrics->pcie_nak_rcvd_count_acc =
+				metrics_x->PCIeNAKReceivedCountAcc;
 	}
 
 	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();
 
 	gpu_metrics->gfx_activity_acc =
-		SMUQ10_ROUND(metrics->SocketGfxBusyAcc);
+		SMUQ10_ROUND(GET_METRIC_FIELD(SocketGfxBusyAcc));
 	gpu_metrics->mem_activity_acc =
-		SMUQ10_ROUND(metrics->DramBandwidthUtilizationAcc);
+		SMUQ10_ROUND(GET_METRIC_FIELD(DramBandwidthUtilizationAcc));
 
 	for (i = 0; i < NUM_XGMI_LINKS; i++) {
 		gpu_metrics->xgmi_read_data_acc[i] =
-			SMUQ10_ROUND(metrics->XgmiReadDataSizeAcc[i]);
+			SMUQ10_ROUND(GET_METRIC_FIELD(XgmiReadDataSizeAcc)[i]);
 		gpu_metrics->xgmi_write_data_acc[i] =
-			SMUQ10_ROUND(metrics->XgmiWriteDataSizeAcc[i]);
+			SMUQ10_ROUND(GET_METRIC_FIELD(XgmiWriteDataSizeAcc)[i]);
+	}
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		inst = GET_INST(JPEG, i);
+		for (j = 0; j < adev->jpeg.num_jpeg_rings; ++j) {
+			gpu_metrics->jpeg_activity[(i * adev->jpeg.num_jpeg_rings) + j] =
+				SMUQ10_ROUND(GET_METRIC_FIELD(JpegBusy)
+				[(inst * adev->jpeg.num_jpeg_rings) + j]);
+		}
+	}
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		inst = GET_INST(VCN, i);
+		gpu_metrics->vcn_activity[i] =
+			SMUQ10_ROUND(GET_METRIC_FIELD(VcnBusy)[inst]);
 	}
 
-	gpu_metrics->xgmi_link_width = SMUQ10_ROUND(metrics->XgmiWidth);
-	gpu_metrics->xgmi_link_speed = SMUQ10_ROUND(metrics->XgmiBitrate);
+	gpu_metrics->xgmi_link_width = SMUQ10_ROUND(GET_METRIC_FIELD(XgmiWidth));
+	gpu_metrics->xgmi_link_speed = SMUQ10_ROUND(GET_METRIC_FIELD(XgmiBitrate));
 
-	gpu_metrics->firmware_timestamp = metrics->Timestamp;
+	gpu_metrics->firmware_timestamp = GET_METRIC_FIELD(Timestamp);
 
 	*table = (void *)gpu_metrics;
-	kfree(metrics);
+	kfree(metrics_x);
 
 	return sizeof(*gpu_metrics);
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index 001a5cf09657..00cd615bbcdc 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -989,6 +989,9 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev)
 	case METRICS_VERSION(1, 4):
 		structure_size = sizeof(struct gpu_metrics_v1_4);
 		break;
+	case METRICS_VERSION(1, 5):
+		structure_size = sizeof(struct gpu_metrics_v1_5);
+		break;
 	case METRICS_VERSION(2, 0):
 		structure_size = sizeof(struct gpu_metrics_v2_0);
 		break;
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index 2fa0445d8928..d1437c08645f 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -187,7 +187,7 @@ struct nvkm_gsp {
 		void (*rpc_done)(struct nvkm_gsp *gsp, void *repv);
 
 		void *(*rm_ctrl_get)(struct nvkm_gsp_object *, u32 cmd, u32 argc);
-		void *(*rm_ctrl_push)(struct nvkm_gsp_object *, void *argv, u32 repc);
+		int (*rm_ctrl_push)(struct nvkm_gsp_object *, void **argv, u32 repc);
 		void (*rm_ctrl_done)(struct nvkm_gsp_object *, void *repv);
 
 		void *(*rm_alloc_get)(struct nvkm_gsp_object *, u32 oclass, u32 argc);
@@ -265,7 +265,7 @@ nvkm_gsp_rm_ctrl_get(struct nvkm_gsp_object *object, u32 cmd, u32 argc)
 	return object->client->gsp->rm->rm_ctrl_get(object, cmd, argc);
 }
 
-static inline void *
+static inline int
 nvkm_gsp_rm_ctrl_push(struct nvkm_gsp_object *object, void *argv, u32 repc)
 {
 	return object->client->gsp->rm->rm_ctrl_push(object, argv, repc);
@@ -275,21 +275,24 @@ static inline void *
 nvkm_gsp_rm_ctrl_rd(struct nvkm_gsp_object *object, u32 cmd, u32 repc)
 {
 	void *argv = nvkm_gsp_rm_ctrl_get(object, cmd, repc);
+	int ret;
 
 	if (IS_ERR(argv))
 		return argv;
 
-	return nvkm_gsp_rm_ctrl_push(object, argv, repc);
+	ret = nvkm_gsp_rm_ctrl_push(object, &argv, repc);
+	if (ret)
+		return ERR_PTR(ret);
+	return argv;
 }
 
 static inline int
 nvkm_gsp_rm_ctrl_wr(struct nvkm_gsp_object *object, void *argv)
 {
-	void *repv = nvkm_gsp_rm_ctrl_push(object, argv, 0);
-
-	if (IS_ERR(repv))
-		return PTR_ERR(repv);
+	int ret = nvkm_gsp_rm_ctrl_push(object, &argv, 0);
 
+	if (ret)
+		return ret;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index ca762ea55413..5057d976fa57 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -62,7 +62,7 @@ nouveau_fence_signal(struct nouveau_fence *fence)
 	if (test_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags)) {
 		struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
 
-		if (!--fctx->notify_ref)
+		if (atomic_dec_and_test(&fctx->notify_ref))
 			drop = 1;
 	}
 
@@ -103,6 +103,7 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error)
 void
 nouveau_fence_context_del(struct nouveau_fence_chan *fctx)
 {
+	cancel_work_sync(&fctx->allow_block_work);
 	nouveau_fence_context_kill(fctx, 0);
 	nvif_event_dtor(&fctx->event);
 	fctx->dead = 1;
@@ -167,6 +168,18 @@ nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc
 	return ret;
 }
 
+static void
+nouveau_fence_work_allow_block(struct work_struct *work)
+{
+	struct nouveau_fence_chan *fctx = container_of(work, struct nouveau_fence_chan,
+						       allow_block_work);
+
+	if (atomic_read(&fctx->notify_ref) == 0)
+		nvif_event_block(&fctx->event);
+	else
+		nvif_event_allow(&fctx->event);
+}
+
 void
 nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_chan *fctx)
 {
@@ -178,6 +191,7 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha
 	} args;
 	int ret;
 
+	INIT_WORK(&fctx->allow_block_work, nouveau_fence_work_allow_block);
 	INIT_LIST_HEAD(&fctx->flip);
 	INIT_LIST_HEAD(&fctx->pending);
 	spin_lock_init(&fctx->lock);
@@ -521,15 +535,19 @@ static bool nouveau_fence_enable_signaling(struct dma_fence *f)
 	struct nouveau_fence *fence = from_fence(f);
 	struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
 	bool ret;
+	bool do_work;
 
-	if (!fctx->notify_ref++)
-		nvif_event_allow(&fctx->event);
+	if (atomic_inc_return(&fctx->notify_ref) == 0)
+		do_work = true;
 
 	ret = nouveau_fence_no_signaling(f);
 	if (ret)
 		set_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags);
-	else if (!--fctx->notify_ref)
-		nvif_event_block(&fctx->event);
+	else if (atomic_dec_and_test(&fctx->notify_ref))
+		do_work = true;
+
+	if (do_work)
+		schedule_work(&fctx->allow_block_work);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index 64d33ae7f356..28f5cf013b89 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -3,6 +3,7 @@
 #define __NOUVEAU_FENCE_H__
 
 #include <linux/dma-fence.h>
+#include <linux/workqueue.h>
 #include <nvif/event.h>
 
 struct nouveau_drm;
@@ -45,7 +46,9 @@ struct nouveau_fence_chan {
 	char name[32];
 
 	struct nvif_event event;
-	int notify_ref, dead, killed;
+	struct work_struct allow_block_work;
+	atomic_t notify_ref;
+	int dead, killed;
 };
 
 struct nouveau_fence_priv {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c
index 457ec5db794d..b24eb1e560bc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c
@@ -209,7 +209,7 @@ nvkm_disp_dtor(struct nvkm_engine *engine)
 		nvkm_head_del(&head);
 	}
 
-	if (disp->func->dtor)
+	if (disp->func && disp->func->dtor)
 		disp->func->dtor(disp);
 
 	return data;
@@ -243,8 +243,10 @@ nvkm_disp_new_(const struct nvkm_disp_func *func, struct nvkm_device *device,
 	spin_lock_init(&disp->client.lock);
 
 	ret = nvkm_engine_ctor(&nvkm_disp, device, type, inst, true, &disp->engine);
-	if (ret)
+	if (ret) {
+		disp->func = NULL;
 		return ret;
+	}
 
 	if (func->super) {
 		disp->super.wq = create_singlethread_workqueue("nvkm-disp");
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c
index 298035070b3a..6a0a4d3b8902 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c
@@ -282,7 +282,7 @@ r535_sor_bl_get(struct nvkm_ior *sor)
 {
 	struct nvkm_disp *disp = sor->disp;
 	NV0073_CTRL_SPECIFIC_BACKLIGHT_BRIGHTNESS_PARAMS *ctrl;
-	int lvl;
+	int ret, lvl;
 
 	ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom,
 				    NV0073_CTRL_CMD_SPECIFIC_GET_BACKLIGHT_BRIGHTNESS,
@@ -292,9 +292,11 @@ r535_sor_bl_get(struct nvkm_ior *sor)
 
 	ctrl->displayId = BIT(sor->asy.outp->index);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
 	lvl = ctrl->brightness;
 	nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
@@ -649,9 +651,11 @@ r535_conn_new(struct nvkm_disp *disp, u32 id)
 	ctrl->subDeviceInstance = 0;
 	ctrl->displayId = BIT(id);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return (void *)ctrl;
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ERR_PTR(ret);
+	}
 
 	list_for_each_entry(conn, &disp->conns, head) {
 		if (conn->index == ctrl->data[0].index) {
@@ -686,7 +690,7 @@ r535_outp_acquire(struct nvkm_outp *outp, bool hda)
 	struct nvkm_disp *disp = outp->disp;
 	struct nvkm_ior *ior;
 	NV0073_CTRL_DFP_ASSIGN_SOR_PARAMS *ctrl;
-	int or;
+	int ret, or;
 
 	ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom,
 				    NV0073_CTRL_CMD_DFP_ASSIGN_SOR, sizeof(*ctrl));
@@ -699,9 +703,11 @@ r535_outp_acquire(struct nvkm_outp *outp, bool hda)
 	if (hda)
 		ctrl->flags |= NVDEF(NV0073_CTRL, DFP_ASSIGN_SOR_FLAGS, AUDIO, OPTIMAL);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
 	for (or = 0; or < ARRAY_SIZE(ctrl->sorAssignListWithTag); or++) {
 		if (ctrl->sorAssignListWithTag[or].displayMask & BIT(outp->index)) {
@@ -727,6 +733,7 @@ static int
 r535_disp_head_displayid(struct nvkm_disp *disp, int head, u32 *displayid)
 {
 	NV0073_CTRL_SYSTEM_GET_ACTIVE_PARAMS *ctrl;
+	int ret;
 
 	ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom,
 				    NV0073_CTRL_CMD_SYSTEM_GET_ACTIVE, sizeof(*ctrl));
@@ -736,9 +743,11 @@ r535_disp_head_displayid(struct nvkm_disp *disp, int head, u32 *displayid)
 	ctrl->subDeviceInstance = 0;
 	ctrl->head = head;
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
 	*displayid = ctrl->displayId;
 	nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
@@ -772,9 +781,11 @@ r535_outp_inherit(struct nvkm_outp *outp)
 			ctrl->subDeviceInstance = 0;
 			ctrl->displayId = displayid;
 
-			ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-			if (IS_ERR(ctrl))
+			ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+			if (ret) {
+				nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
 				return NULL;
+			}
 
 			id = ctrl->index;
 			proto = ctrl->protocol;
@@ -825,6 +836,7 @@ r535_outp_dfp_get_info(struct nvkm_outp *outp)
 {
 	NV0073_CTRL_DFP_GET_INFO_PARAMS *ctrl;
 	struct nvkm_disp *disp = outp->disp;
+	int ret;
 
 	ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DFP_GET_INFO, sizeof(*ctrl));
 	if (IS_ERR(ctrl))
@@ -832,9 +844,11 @@ r535_outp_dfp_get_info(struct nvkm_outp *outp)
 
 	ctrl->displayId = BIT(outp->index);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
 	nvkm_debug(&disp->engine.subdev, "DFP %08x: flags:%08x flags2:%08x\n",
 		   ctrl->displayId, ctrl->flags, ctrl->flags2);
@@ -858,9 +872,11 @@ r535_outp_detect(struct nvkm_outp *outp)
 	ctrl->subDeviceInstance = 0;
 	ctrl->displayMask = BIT(outp->index);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
 	if (ctrl->displayMask & BIT(outp->index)) {
 		ret = r535_outp_dfp_get_info(outp);
@@ -895,6 +911,7 @@ r535_dp_mst_id_get(struct nvkm_outp *outp, u32 *pid)
 {
 	NV0073_CTRL_CMD_DP_TOPOLOGY_ALLOCATE_DISPLAYID_PARAMS *ctrl;
 	struct nvkm_disp *disp = outp->disp;
+	int ret;
 
 	ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom,
 				    NV0073_CTRL_CMD_DP_TOPOLOGY_ALLOCATE_DISPLAYID,
@@ -904,9 +921,11 @@ r535_dp_mst_id_get(struct nvkm_outp *outp, u32 *pid)
 
 	ctrl->subDeviceInstance = 0;
 	ctrl->displayId = BIT(outp->index);
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
 	*pid = ctrl->displayIdAssigned;
 	nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
@@ -938,38 +957,60 @@ r535_dp_train_target(struct nvkm_outp *outp, u8 target, bool mst, u8 link_nr, u8
 {
 	struct nvkm_disp *disp = outp->disp;
 	NV0073_CTRL_DP_CTRL_PARAMS *ctrl;
-	int ret;
-
-	ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_CTRL, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	int ret, retries;
+	u32 cmd, data;
 
-	ctrl->subDeviceInstance = 0;
-	ctrl->displayId = BIT(outp->index);
-	ctrl->cmd = NVDEF(NV0073_CTRL, DP_CMD, SET_LANE_COUNT, TRUE) |
-		    NVDEF(NV0073_CTRL, DP_CMD, SET_LINK_BW, TRUE) |
-		    NVDEF(NV0073_CTRL, DP_CMD, TRAIN_PHY_REPEATER, YES);
-	ctrl->data = NVVAL(NV0073_CTRL, DP_DATA, SET_LANE_COUNT, link_nr) |
-		     NVVAL(NV0073_CTRL, DP_DATA, SET_LINK_BW, link_bw) |
-		     NVVAL(NV0073_CTRL, DP_DATA, TARGET, target);
+	cmd = NVDEF(NV0073_CTRL, DP_CMD, SET_LANE_COUNT, TRUE) |
+	      NVDEF(NV0073_CTRL, DP_CMD, SET_LINK_BW, TRUE) |
+	      NVDEF(NV0073_CTRL, DP_CMD, TRAIN_PHY_REPEATER, YES);
+	data = NVVAL(NV0073_CTRL, DP_DATA, SET_LANE_COUNT, link_nr) |
+	       NVVAL(NV0073_CTRL, DP_DATA, SET_LINK_BW, link_bw) |
+	       NVVAL(NV0073_CTRL, DP_DATA, TARGET, target);
 
 	if (mst)
-		ctrl->cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_FORMAT_MODE, MULTI_STREAM);
+		cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_FORMAT_MODE, MULTI_STREAM);
 
 	if (outp->dp.dpcd[DPCD_RC02] & DPCD_RC02_ENHANCED_FRAME_CAP)
-		ctrl->cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_ENHANCED_FRAMING, TRUE);
+		cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_ENHANCED_FRAMING, TRUE);
 
 	if (target == 0 &&
 	     (outp->dp.dpcd[DPCD_RC02] & 0x20) &&
 	    !(outp->dp.dpcd[DPCD_RC03] & DPCD_RC03_TPS4_SUPPORTED))
-	    ctrl->cmd |= NVDEF(NV0073_CTRL, DP_CMD, POST_LT_ADJ_REQ_GRANTED, YES);
+		cmd |= NVDEF(NV0073_CTRL, DP_CMD, POST_LT_ADJ_REQ_GRANTED, YES);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	/* We should retry up to 3 times, but only if GSP asks politely */
+	for (retries = 0; retries < 3; ++retries) {
+		ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_CTRL,
+					    sizeof(*ctrl));
+		if (IS_ERR(ctrl))
+			return PTR_ERR(ctrl);
+
+		ctrl->subDeviceInstance = 0;
+		ctrl->displayId = BIT(outp->index);
+		ctrl->retryTimeMs = 0;
+		ctrl->cmd = cmd;
+		ctrl->data = data;
+
+		ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+		if (ret == -EAGAIN && ctrl->retryTimeMs) {
+			/*
+			 * Device (likely an eDP panel) isn't ready yet, wait for the time specified
+			 * by GSP before retrying again
+			 */
+			nvkm_debug(&disp->engine.subdev,
+				   "Waiting %dms for GSP LT panel delay before retrying\n",
+				   ctrl->retryTimeMs);
+			msleep(ctrl->retryTimeMs);
+			nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		} else {
+			/* GSP didn't say to retry, or we were successful */
+			if (ctrl->err)
+				ret = -EIO;
+			nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+			break;
+		}
+	}
 
-	ret = ctrl->err ? -EIO : 0;
-	nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
 	return ret;
 }
 
@@ -1036,9 +1077,11 @@ r535_dp_aux_xfer(struct nvkm_outp *outp, u8 type, u32 addr, u8 *data, u8 *psize)
 	ctrl->size = !ctrl->bAddrOnly ? (size - 1) : 0;
 	memcpy(ctrl->data, data, size);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
 		return PTR_ERR(ctrl);
+	}
 
 	memcpy(data, ctrl->data, size);
 	*psize = ctrl->size;
@@ -1111,10 +1154,13 @@ r535_tmds_edid_get(struct nvkm_outp *outp, u8 *data, u16 *psize)
 	ctrl->subDeviceInstance = 0;
 	ctrl->displayId = BIT(outp->index);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
+	ret = -E2BIG;
 	if (ctrl->bufferSize <= *psize) {
 		memcpy(data, ctrl->edidBuffer, ctrl->bufferSize);
 		*psize = ctrl->bufferSize;
@@ -1153,9 +1199,11 @@ r535_outp_new(struct nvkm_disp *disp, u32 id)
 	ctrl->subDeviceInstance = 0;
 	ctrl->displayId = BIT(id);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+	if (ret) {
+		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		return ret;
+	}
 
 	switch (ctrl->type) {
 	case NV0073_CTRL_SPECIFIC_OR_TYPE_NONE:
@@ -1229,9 +1277,11 @@ r535_outp_new(struct nvkm_disp *disp, u32 id)
 
 		ctrl->sorIndex = ~0;
 
-		ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl));
-		if (IS_ERR(ctrl))
-			return PTR_ERR(ctrl);
+		ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+		if (ret) {
+			nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+			return ret;
+		}
 
 		switch (NVVAL_GET(ctrl->maxLinkRate, NV0073_CTRL_CMD, DP_GET_CAPS, MAX_LINK_RATE)) {
 		case NV0073_CTRL_CMD_DP_GET_CAPS_MAX_LINK_RATE_1_62:
@@ -1465,8 +1515,6 @@ r535_disp_oneinit(struct nvkm_disp *disp)
 				bool nvhg = acpi_check_dsm(handle, &NVHG_DSM_GUID, NVHG_DSM_REV,
 						           1ULL << 0x00000014);
 
-				printk(KERN_ERR "bl: nbci:%d nvhg:%d\n", nbci, nvhg);
-
 				if (nbci || nvhg) {
 					union acpi_object argv4 = {
 						.buffer.type    = ACPI_TYPE_BUFFER,
@@ -1479,9 +1527,6 @@ r535_disp_oneinit(struct nvkm_disp *disp)
 					if (!obj) {
 						acpi_handle_info(handle, "failed to evaluate _DSM\n");
 					} else {
-						printk(KERN_ERR "bl: obj type %d\n", obj->type);
-						printk(KERN_ERR "bl: obj len %d\n", obj->package.count);
-
 						for (int i = 0; i < obj->package.count; i++) {
 							union acpi_object *elt = &obj->package.elements[i];
 							u32 size;
@@ -1491,12 +1536,10 @@ r535_disp_oneinit(struct nvkm_disp *disp)
 							else
 								size = 4;
 
-							printk(KERN_ERR "elt %03d: type %d size %d\n", i, elt->type, size);
 							memcpy(&ctrl->backLightData[ctrl->backLightDataSize], &elt->integer.value, size);
 							ctrl->backLightDataSize += size;
 						}
 
-						printk(KERN_ERR "bl: data size %d\n", ctrl->backLightDataSize);
 						ctrl->status = 0;
 						ACPI_FREE(obj);
 					}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c
index d088e636edc3..b903785056b5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c
@@ -242,6 +242,7 @@ r535_chan_id_put(struct nvkm_chan *chan)
 				nvkm_memory_unref(&userd->mem);
 				nvkm_chid_put(runl->chid, userd->chid, &chan->cgrp->lock);
 				list_del(&userd->head);
+				kfree(userd);
 			}
 
 			break;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index 44fb86841c05..9ee58e2a0eb2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -70,6 +70,20 @@ struct r535_gsp_msg {
 
 #define GSP_MSG_HDR_SIZE offsetof(struct r535_gsp_msg, data)
 
+static int
+r535_rpc_status_to_errno(uint32_t rpc_status)
+{
+	switch (rpc_status) {
+	case 0x55: /* NV_ERR_NOT_READY */
+	case 0x66: /* NV_ERR_TIMEOUT_RETRY */
+		return -EAGAIN;
+	case 0x51: /* NV_ERR_NO_MEMORY */
+		return -ENOMEM;
+	default:
+		return -EINVAL;
+	}
+}
+
 static void *
 r535_gsp_msgq_wait(struct nvkm_gsp *gsp, u32 repc, u32 *prepc, int *ptime)
 {
@@ -298,7 +312,8 @@ retry:
 		struct nvkm_gsp_msgq_ntfy *ntfy = &gsp->msgq.ntfy[i];
 
 		if (ntfy->fn == msg->function) {
-			ntfy->func(ntfy->priv, ntfy->fn, msg->data, msg->length - sizeof(*msg));
+			if (ntfy->func)
+				ntfy->func(ntfy->priv, ntfy->fn, msg->data, msg->length - sizeof(*msg));
 			break;
 		}
 	}
@@ -583,14 +598,14 @@ r535_gsp_rpc_rm_alloc_push(struct nvkm_gsp_object *object, void *argv, u32 repc)
 		return rpc;
 
 	if (rpc->status) {
-		nvkm_error(&gsp->subdev, "RM_ALLOC: 0x%x\n", rpc->status);
-		ret = ERR_PTR(-EINVAL);
+		ret = ERR_PTR(r535_rpc_status_to_errno(rpc->status));
+		if (PTR_ERR(ret) != -EAGAIN)
+			nvkm_error(&gsp->subdev, "RM_ALLOC: 0x%x\n", rpc->status);
 	} else {
 		ret = repc ? rpc->params : NULL;
 	}
 
-	if (IS_ERR_OR_NULL(ret))
-		nvkm_gsp_rpc_done(gsp, rpc);
+	nvkm_gsp_rpc_done(gsp, rpc);
 
 	return ret;
 }
@@ -623,29 +638,34 @@ r535_gsp_rpc_rm_ctrl_done(struct nvkm_gsp_object *object, void *repv)
 {
 	rpc_gsp_rm_control_v03_00 *rpc = container_of(repv, typeof(*rpc), params);
 
+	if (!repv)
+		return;
 	nvkm_gsp_rpc_done(object->client->gsp, rpc);
 }
 
-static void *
-r535_gsp_rpc_rm_ctrl_push(struct nvkm_gsp_object *object, void *argv, u32 repc)
+static int
+r535_gsp_rpc_rm_ctrl_push(struct nvkm_gsp_object *object, void **argv, u32 repc)
 {
-	rpc_gsp_rm_control_v03_00 *rpc = container_of(argv, typeof(*rpc), params);
+	rpc_gsp_rm_control_v03_00 *rpc = container_of((*argv), typeof(*rpc), params);
 	struct nvkm_gsp *gsp = object->client->gsp;
-	void *ret;
+	int ret = 0;
 
 	rpc = nvkm_gsp_rpc_push(gsp, rpc, true, repc);
-	if (IS_ERR_OR_NULL(rpc))
-		return rpc;
+	if (IS_ERR_OR_NULL(rpc)) {
+		*argv = NULL;
+		return PTR_ERR(rpc);
+	}
 
 	if (rpc->status) {
-		nvkm_error(&gsp->subdev, "cli:0x%08x obj:0x%08x ctrl cmd:0x%08x failed: 0x%08x\n",
-			   object->client->object.handle, object->handle, rpc->cmd, rpc->status);
-		ret = ERR_PTR(-EINVAL);
-	} else {
-		ret = repc ? rpc->params : NULL;
+		ret = r535_rpc_status_to_errno(rpc->status);
+		if (ret != -EAGAIN)
+			nvkm_error(&gsp->subdev, "cli:0x%08x obj:0x%08x ctrl cmd:0x%08x failed: 0x%08x\n",
+				   object->client->object.handle, object->handle, rpc->cmd, rpc->status);
 	}
 
-	if (IS_ERR_OR_NULL(ret))
+	if (repc)
+		*argv = rpc->params;
+	else
 		nvkm_gsp_rpc_done(gsp, rpc);
 
 	return ret;
@@ -843,9 +863,11 @@ r535_gsp_intr_get_table(struct nvkm_gsp *gsp)
 	if (IS_ERR(ctrl))
 		return PTR_ERR(ctrl);
 
-	ctrl = nvkm_gsp_rm_ctrl_push(&gsp->internal.device.subdevice, ctrl, sizeof(*ctrl));
-	if (WARN_ON(IS_ERR(ctrl)))
-		return PTR_ERR(ctrl);
+	ret = nvkm_gsp_rm_ctrl_push(&gsp->internal.device.subdevice, &ctrl, sizeof(*ctrl));
+	if (WARN_ON(ret)) {
+		nvkm_gsp_rm_ctrl_done(&gsp->internal.device.subdevice, ctrl);
+		return ret;
+	}
 
 	for (unsigned i = 0; i < ctrl->tableLen; i++) {
 		enum nvkm_subdev_type type;
@@ -1099,16 +1121,12 @@ r535_gsp_acpi_caps(acpi_handle handle, CAPS_METHOD_DATA *caps)
 	if (!obj)
 		return;
 
-	printk(KERN_ERR "nvop: obj type %d\n", obj->type);
-	printk(KERN_ERR "nvop: obj len %d\n", obj->buffer.length);
-
 	if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) ||
 	    WARN_ON(obj->buffer.length != 4))
 		return;
 
 	caps->status = 0;
 	caps->optimusCaps = *(u32 *)obj->buffer.pointer;
-	printk(KERN_ERR "nvop: caps %08x\n", caps->optimusCaps);
 
 	ACPI_FREE(obj);
 
@@ -1135,9 +1153,6 @@ r535_gsp_acpi_jt(acpi_handle handle, JT_METHOD_DATA *jt)
 	if (!obj)
 		return;
 
-	printk(KERN_ERR "jt: obj type %d\n", obj->type);
-	printk(KERN_ERR "jt: obj len %d\n", obj->buffer.length);
-
 	if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) ||
 	    WARN_ON(obj->buffer.length != 4))
 		return;
@@ -1146,7 +1161,6 @@ r535_gsp_acpi_jt(acpi_handle handle, JT_METHOD_DATA *jt)
 	jt->jtCaps = *(u32 *)obj->buffer.pointer;
 	jt->jtRevId = (jt->jtCaps & 0xfff00000) >> 20;
 	jt->bSBIOSCaps = 0;
-	printk(KERN_ERR "jt: caps %08x rev:%04x\n", jt->jtCaps, jt->jtRevId);
 
 	ACPI_FREE(obj);
 
@@ -1157,6 +1171,8 @@ static void
 r535_gsp_acpi_mux_id(acpi_handle handle, u32 id, MUX_METHOD_DATA_ELEMENT *mode,
 						 MUX_METHOD_DATA_ELEMENT *part)
 {
+	union acpi_object mux_arg = { ACPI_TYPE_INTEGER };
+	struct acpi_object_list input = { 1, &mux_arg };
 	acpi_handle iter = NULL, handle_mux = NULL;
 	acpi_status status;
 	unsigned long long value;
@@ -1179,14 +1195,18 @@ r535_gsp_acpi_mux_id(acpi_handle handle, u32 id, MUX_METHOD_DATA_ELEMENT *mode,
 	if (!handle_mux)
 		return;
 
-	status = acpi_evaluate_integer(handle_mux, "MXDM", NULL, &value);
+	/* I -think- 0 means "acquire" according to nvidia's driver source */
+	input.pointer->integer.type = ACPI_TYPE_INTEGER;
+	input.pointer->integer.value = 0;
+
+	status = acpi_evaluate_integer(handle_mux, "MXDM", &input, &value);
 	if (ACPI_SUCCESS(status)) {
 		mode->acpiId = id;
 		mode->mode   = value;
 		mode->status = 0;
 	}
 
-	status = acpi_evaluate_integer(handle_mux, "MXDS", NULL, &value);
+	status = acpi_evaluate_integer(handle_mux, "MXDS", &input, &value);
 	if (ACPI_SUCCESS(status)) {
 		part->acpiId = id;
 		part->mode   = value;
@@ -1232,8 +1252,8 @@ r535_gsp_acpi_dod(acpi_handle handle, DOD_METHOD_DATA *dod)
 		dod->acpiIdListLen += sizeof(dod->acpiIdList[0]);
 	}
 
-	printk(KERN_ERR "_DOD: ok! len:%d\n", dod->acpiIdListLen);
 	dod->status = 0;
+	kfree(output.pointer);
 }
 #endif
 
@@ -2186,7 +2206,9 @@ r535_gsp_oneinit(struct nvkm_gsp *gsp)
 	r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_MMU_FAULT_QUEUED,
 			      r535_gsp_msg_mmu_fault_queued, gsp);
 	r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_OS_ERROR_LOG, r535_gsp_msg_os_error_log, gsp);
-
+	r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_PERF_BRIDGELESS_INFO_UPDATE, NULL, NULL);
+	r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_UCODE_LIBOS_PRINT, NULL, NULL);
+	r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_GSP_SEND_USER_SHARED_DATA, NULL, NULL);
 	ret = r535_gsp_rm_boot_ctor(gsp);
 	if (ret)
 		return ret;