Merge tag 'drm-next-2025-12-03' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "There was a rather late merge of a new color pipeline feature, that
  some userspace projects are blocked on, and has seen a lot of work in
  amdgpu. This should have seen some time in -next. There is additional
  support for this for Intel, that if it arrives in the next day or two
  I'll pass it on in another pull request and you can decide if you want
  to take it.

  Highlights:
   - Arm Ethos NPU accelerator driver
   - new DRM color pipeline support
   - amdgpu will now run discrete SI/CIK cards instead of radeon, which
     enables vulkan support in userspace
   - msm gets gen8 gpu support
   - initial Xe3P support in xe

  Full detail summary:

  New driver:
   - Arm Ethos-U65/U85 accel driver

  Core:
   - support the drm color pipeline in vkms/amdgfx
   - add support for drm colorop pipeline
   - add COLOR PIPELINE plane property
   - add DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE
   - throttle dirty worker with vblank
   - use drm_for_each_bridge_in_chain_scoped in drm's bridge code
   - Ensure drm_client_modeset tests are enabled in UML
   - add simulated vblank interrupt - use in drivers
   - dumb buffer sizing helper
   - move freeing of drm client memory to driver
   - crtc sharpness strength property
   - stop using system_wq in scheduler/drivers
   - support emergency restore in drm-client

  Rust:
   - make slice::as_flattened usable on all supported rustc
   - add FromBytes::from_bytes_prefix() method
   - remove redundant device ptr from Rust GEM object
   - Change how AlwaysRefCounted is implemented for GEM objects

  gpuvm:
   - Add deferred vm_bo cleanup to GPUVM (for rust)

  atomic:
   - cleanup and improve state handling interfaces

  buddy:
   - optimize block management

  dma-buf:
   - heaps: Create heap per CMA reserved location
   - improve userspace documentation

  dp:
   - add POST_LT_ADJ_REQ training sequence
   - DPCD dSC quirk for synaptics panamera devices
   - helpers to query branch DSC max throughput

  ttm:
   - Rename ttm_bo_put to ttm_bo_fini
   - allow page protection flags on risc-v
   - rework pipelined eviction fence handling

  amdgpu:
   - enable amdgpu by default for SI/CI dGPUs
   - enable DC by default on SI
   - refactor CIK/SI enablement
   - add ABM KMS property
   - Re-enable DM idle optimizations
   - DC Analog encoders support
   - Powerplay fixes for fiji/iceland
   - Enable DC on bonaire by default
   - HMM cleanup
   - Add new RAS framework
   - DML2.1 updates
   - YCbCr420 fixes
   - DC FP fixes
   - DMUB fixes
   - LTTPR fixes
   - DTBCLK fixes
   - DMU cursor offload handling
   - Userq validation improvements
   - Unify shutdown callback handling
   - Suspend improvements
   - Power limit code cleanup
   - SR-IOV fixes
   - AUX backlight fixes
   - DCN 3.5 fixes
   - HDMI compliance fixes
   - DCN 4.0.1 cursor updates
   - DCN interrupt fix
   - DC KMS full update improvements
   - Add additional HDCP traces
   - DCN 3.2 fixes
   - DP MST fixes
   - Add support for new SR-IOV mailbox interface
   - UQ reset support
   - HDP flush rework
   - VCE1 support

  amdkfd:
   - HMM cleanups
   - Relax checks on save area overallocations
   - Fix GPU mappings after prefetch

  radeon:
   - refactor CIK/SI enablement

  xe:
   - Initial Xe3P support
   - panic support on VRAM for display
   - fix stolen size check
   - Loosen used tracking restriction
   - New SR-IOV debugfs structure and debugfs updates
   - Hide the GPU madvise flag behind a VM_BIND flag
   - Always expose VRAM provisioning data on discrete GPUs
   - Allow VRAM mappings for userptr when used with SVM
   - Allow pinning of p2p dma-buf
   - Use per-tile debugfs where appropriate
   - Add documentation for Execution Queues
   - PF improvements
   - VF migration recovery redesign work
   - User / Kernel VRAM partitioning
   - Update Tile-based messages
   - Allow configfs to disable specific GT types
   - VF provisioning and migration improvements
   - use SVM range helpers in PT layer
   - Initial CRI support
   - access VF registers using dedicated MMIO view
   - limit number of jobs per exec queue
   - add sriov_admin sysfs tree
   - more crescent island specific support
   - debugfs residency counter
   - SRIOV migration work
   - runtime registers for GFX 35

  i915:
   - add initial Xe3p_LPD display version 35 support
   - Enable LNL+ content adaptive sharpness filter
   - Use optimized VRR guardband
   - Enable Xe3p LT PHY
   - enable FBC support for Xe3p_LPD display
   - add display 30.02 firmware support
   - refactor SKL+ watermark latency setup
   - refactor fbdev handling
   - call i915/xe runtime PM via function pointers
   - refactor i915/xe stolen memory/display interfaces
   - use display version instead of gfx version in display code
   - extend i915_display_info with Type-C port details
   - lots of display cleanups/refactorings
   - set O_LARGEFILE in __create_shmem
   - skuip guc communication warning on reset
   - fix time conversions
   - defeature DRRS on LNL+
   - refactor intel_frontbuffer split between i915/xe/display
   - convert inteL_rom interfaces to struct drm_device
   - unify display register polling interfaces
   - aovid lock inversion when pinning to GGTT on CHV/BXT+VTD

  panel:
   - Add KD116N3730A08/A12, chromebook mt8189
   - JT101TM023, LQ079L1SX01,
   - GLD070WX3-SL01 MIPI DSI
   - Samsung LTL106AL0, Samsung LTL106AL01
   - Raystar RFF500F-AWH-DNN
   - Winstar WF70A8SYJHLNGA
   - Wanchanglong w552946aaa
   - Samsung SOFEF00
   - Lenovo X13s panel
   - ilitek-ili9881c - add rpi 5" support
   - visionx-rm69299 - add backlight support
   - edp - support AUI B116XAN02.0

  bridge:
   - improve ref counting
   - ti-sn65dsi86 - add support for DP mode with HPD
   - synopsis: support CEC, init timer with correct freq
   - ASL CS5263 DP-to-HDMI bridge support

  nova-core:
   - introduce bitfield! macro
   - introduce safe integer converters
   - GSP inits to fully booted state on Ampere
   - Use more future-proof register for GPU identification

  nova-drm:
   - select NOVA_CORE
   - 64-bit only

  nouveau:
   - improve reclocking on tegra 186+
   - add large page and compression support

  msm:
   - GPU:
      - Gen8 support: A840 (Kaanapali) and X2-85 (Glymur)
      - A612 support
   - MDSS:
      - Added support for Glymur and QCS8300 platforms
   - DPU:
      - Enabled Quad-Pipe support, unlocking higher resolutions support
      - Added support for Glymur platform
      - Documented DPU on QCS8300 platform as supported
   - DisplayPort:
      - Added support for Glymur platform
      - Added support lame remapping inside DP block
      - Documented DisplayPort controller on QCS8300 and SM6150/QCS615
        as supported

  tegra:
   - NVJPG driver

  panfrost:
   - display JM contexts over debugfs
   - export JM contexts to userspace
   - improve error and job handling

  panthor:
   - support custom ASN_HASH for mt8196
   - support mali-G1 GPU
   - flush shmem write before mapping buffers uncached
   - make timeout per-queue instead of per-job

  mediatek:
   - MT8195/88 HDMIv2/DDCv2 support

  rockchip:
   - dsi: add support for RK3368

  amdxdna:
   - enhance runtime PM
   - last hardware error reading uapi
   - support firmware debug output
   - add resource and telemetry data uapi
   - preemption support

  imx:
   - add driver for HDMI TX Parallel audio interface

  ivpu:
   - add support for user-managed preemption buffer
   - add userptr support
   - update JSM firware API to 3.33.0
   - add better alloc/free warnings
   - fix page fault in unbind all bos
   - rework bind/unbind of imported buffers
   - enable MCA ECC signalling
   - split fw runtime and global memory buffers
   - add fdinfo memory statistics

  tidss:
   - convert to drm logging
   - logging cleanup

  ast:
   - refactor generation init paths
   - add per chip generation detect_tx_chip
   - set quirks for each chip model

  atmel-hlcdc:
   - set LCDC_ATTRE register in plane disable
   - set correct values for plane scaler

  solomon:
   - use drm helper for get_modes and move_valid

  sitronix:
   - fix output position when clearing screens

  qaic:
   - support dma-buf exports
   - support new firmware's READ_DATA implementation
   - sahara AIC200 image table update
   - add sysfs support
   - add coredump support
   - add uevents support
   - PM support

  sun4i:
   - layer refactors to decouple plane from output
   - improve DE33 support

  vc4:
   - switch to generic CEC helpers

  komeda:
   - use drm_ logging functions

  vkms:
   - configfs support for display configuration

  vgem:
   - fix fence timer deadlock

  etnaviv:
   - add HWDB entry for GC8000 Nano Ultra VIP r6205"

* tag 'drm-next-2025-12-03' of https://gitlab.freedesktop.org/drm/kernel: (1869 commits)
  Revert "drm/amd: Skip power ungate during suspend for VPE"
  drm/amdgpu: use common defines for HUB faults
  drm/amdgpu/gmc12: add amdgpu_vm_handle_fault() handling
  drm/amdgpu/gmc11: add amdgpu_vm_handle_fault() handling
  drm/amdgpu: use static ids for ACP platform devs
  drm/amdgpu/sdma6: Update SDMA 6.0.3 FW version to include UMQ protected-fence fix
  drm/amdgpu: Forward VMID reservation errors
  drm/amdgpu/gmc8: Delegate VM faults to soft IRQ handler ring
  drm/amdgpu/gmc7: Delegate VM faults to soft IRQ handler ring
  drm/amdgpu/gmc6: Delegate VM faults to soft IRQ handler ring
  drm/amdgpu/gmc6: Cache VM fault info
  drm/amdgpu/gmc6: Don't print MC client as it's unknown
  drm/amdgpu/cz_ih: Enable soft IRQ handler ring
  drm/amdgpu/tonga_ih: Enable soft IRQ handler ring
  drm/amdgpu/iceland_ih: Enable soft IRQ handler ring
  drm/amdgpu/cik_ih: Enable soft IRQ handler ring
  drm/amdgpu/si_ih: Enable soft IRQ handler ring
  drm/amd/display: fix typo in display_mode_core_structs.h
  drm/amd/display: fix Smart Power OLED not working after S4
  drm/amd/display: Move RGB-type check for audio sync to DCE HW sequence
  ...

1 files changed, 284 insertions, 134 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 96b6738e6252..a1817b4b5173 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -71,6 +71,7 @@
 
 #include "amdgpu_xgmi.h"
 #include "amdgpu_ras.h"
+#include "amdgpu_ras_mgr.h"
 #include "amdgpu_pmu.h"
 #include "amdgpu_fru_eeprom.h"
 #include "amdgpu_reset.h"
@@ -179,6 +180,10 @@ struct amdgpu_init_level amdgpu_init_minimal_xgmi = {
 		BIT(AMD_IP_BLOCK_TYPE_PSP)
 };
 
+static int amdgpu_device_ip_resume_phase1(struct amdgpu_device *adev);
+static int amdgpu_device_ip_resume_phase2(struct amdgpu_device *adev);
+static int amdgpu_device_ip_resume_phase3(struct amdgpu_device *adev);
+
 static void amdgpu_device_load_switch_state(struct amdgpu_device *adev);
 
 static inline bool amdgpu_ip_member_of_hwini(struct amdgpu_device *adev,
@@ -2387,7 +2392,7 @@ int amdgpu_device_ip_wait_for_idle(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_device_ip_is_valid - is the hardware IP enabled
+ * amdgpu_device_ip_is_hw - is the hardware IP enabled
  *
  * @adev: amdgpu_device pointer
  * @block_type: Type of hardware IP (SMU, GFX, UVD, etc.)
@@ -2395,6 +2400,27 @@ int amdgpu_device_ip_wait_for_idle(struct amdgpu_device *adev,
  * Check if the hardware IP is enable or not.
  * Returns true if it the IP is enable, false if not.
  */
+bool amdgpu_device_ip_is_hw(struct amdgpu_device *adev,
+			    enum amd_ip_block_type block_type)
+{
+	int i;
+
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (adev->ip_blocks[i].version->type == block_type)
+			return adev->ip_blocks[i].status.hw;
+	}
+	return false;
+}
+
+/**
+ * amdgpu_device_ip_is_valid - is the hardware IP valid
+ *
+ * @adev: amdgpu_device pointer
+ * @block_type: Type of hardware IP (SMU, GFX, UVD, etc.)
+ *
+ * Check if the hardware IP is valid or not.
+ * Returns true if it the IP is valid, false if not.
+ */
 bool amdgpu_device_ip_is_valid(struct amdgpu_device *adev,
 			       enum amd_ip_block_type block_type)
 {
@@ -2473,6 +2499,7 @@ static const char *ip_block_names[] = {
 	[AMD_IP_BLOCK_TYPE_VPE] = "vpe",
 	[AMD_IP_BLOCK_TYPE_UMSCH_MM] = "umsch_mm",
 	[AMD_IP_BLOCK_TYPE_ISP] = "isp",
+	[AMD_IP_BLOCK_TYPE_RAS] = "ras",
 };
 
 static const char *ip_block_name(struct amdgpu_device *adev, enum amd_ip_block_type type)
@@ -2633,12 +2660,12 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 		chip_name = "arcturus";
 		break;
 	case CHIP_NAVI12:
-		if (adev->mman.discovery_bin)
+		if (adev->discovery.bin)
 			return 0;
 		chip_name = "navi12";
 		break;
 	case CHIP_CYAN_SKILLFISH:
-		if (adev->mman.discovery_bin)
+		if (adev->discovery.bin)
 			return 0;
 		chip_name = "cyan_skillfish";
 		break;
@@ -2763,6 +2790,10 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 		r = amdgpu_virt_request_full_gpu(adev, true);
 		if (r)
 			return r;
+
+		r = amdgpu_virt_init_critical_region(adev);
+		if (r)
+			return r;
 	}
 
 	switch (adev->asic_type) {
@@ -3652,6 +3683,20 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev)
 				"failed to release exclusive mode on fini\n");
 	}
 
+	/*
+	 * Driver reload on the APU can fail due to firmware validation because
+	 * the PSP is always running, as it is shared across the whole SoC.
+	 * This same issue does not occur on dGPU because it has a mechanism
+	 * that checks whether the PSP is running. A solution for those issues
+	 * in the APU is to trigger a GPU reset, but this should be done during
+	 * the unload phase to avoid adding boot latency and screen flicker.
+	 */
+	if ((adev->flags & AMD_IS_APU) && !adev->gmc.is_app_apu) {
+		r = amdgpu_asic_reset(adev);
+		if (r)
+			dev_err(adev->dev, "asic reset on %s failed\n", __func__);
+	}
+
 	return 0;
 }
 
@@ -3762,7 +3807,7 @@ static void amdgpu_device_delay_enable_gfx_off(struct work_struct *work)
  */
 static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
 {
-	int i, r;
+	int i, r, rec;
 
 	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
 	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
@@ -3783,13 +3828,25 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_DCE)
 			continue;
 
-		/* XXX handle errors */
 		r = amdgpu_ip_block_suspend(&adev->ip_blocks[i]);
 		if (r)
-			return r;
+			goto unwind;
 	}
 
 	return 0;
+unwind:
+	rec = amdgpu_device_ip_resume_phase3(adev);
+	if (rec)
+		dev_err(adev->dev,
+			"amdgpu_device_ip_resume_phase3 failed during unwind: %d\n",
+			rec);
+
+	amdgpu_dpm_set_df_cstate(adev, DF_CSTATE_ALLOW);
+
+	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_GATE);
+	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_GATE);
+
+	return r;
 }
 
 /**
@@ -3805,7 +3862,7 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
  */
 static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 {
-	int i, r;
+	int i, r, rec;
 
 	if (adev->in_s0ix)
 		amdgpu_dpm_gfx_state_change(adev, sGpuChangeState_D3Entry);
@@ -3866,9 +3923,9 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP)
 			continue;
 
-		/* XXX handle errors */
 		r = amdgpu_ip_block_suspend(&adev->ip_blocks[i]);
-		adev->ip_blocks[i].status.hw = false;
+		if (r)
+			goto unwind;
 
 		/* handle putting the SMC in the appropriate state */
 		if (!amdgpu_sriov_vf(adev)) {
@@ -3878,13 +3935,40 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 					dev_err(adev->dev,
 						"SMC failed to set mp1 state %d, %d\n",
 						adev->mp1_state, r);
-					return r;
+					goto unwind;
 				}
 			}
 		}
 	}
 
 	return 0;
+unwind:
+	/* suspend phase 2 = resume phase 1 + resume phase 2 */
+	rec = amdgpu_device_ip_resume_phase1(adev);
+	if (rec) {
+		dev_err(adev->dev,
+			"amdgpu_device_ip_resume_phase1 failed during unwind: %d\n",
+			rec);
+		return r;
+	}
+
+	rec = amdgpu_device_fw_loading(adev);
+	if (rec) {
+		dev_err(adev->dev,
+			"amdgpu_device_fw_loading failed during unwind: %d\n",
+			rec);
+		return r;
+	}
+
+	rec = amdgpu_device_ip_resume_phase2(adev);
+	if (rec) {
+		dev_err(adev->dev,
+			"amdgpu_device_ip_resume_phase2 failed during unwind: %d\n",
+			rec);
+		return r;
+	}
+
+	return r;
 }
 
 /**
@@ -3898,7 +3982,7 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
  * in each IP into a state suitable for suspend.
  * Returns 0 on success, negative error code on failure.
  */
-int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
+static int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
 {
 	int r;
 
@@ -4182,25 +4266,13 @@ bool amdgpu_device_asic_has_dc_support(struct pci_dev *pdev,
 	case CHIP_PITCAIRN:
 	case CHIP_VERDE:
 	case CHIP_OLAND:
-		/*
-		 * We have systems in the wild with these ASICs that require
-		 * LVDS and VGA support which is not supported with DC.
-		 *
-		 * Fallback to the non-DC driver here by default so as not to
-		 * cause regressions.
-		 */
-#if defined(CONFIG_DRM_AMD_DC_SI)
-		return amdgpu_dc > 0;
-#else
-		return false;
-#endif
-	case CHIP_BONAIRE:
+		return amdgpu_dc != 0 && IS_ENABLED(CONFIG_DRM_AMD_DC_SI);
 	case CHIP_KAVERI:
 	case CHIP_KABINI:
 	case CHIP_MULLINS:
 		/*
 		 * We have systems in the wild with these ASICs that require
-		 * VGA support which is not supported with DC.
+		 * TRAVIS and NUTMEG support which is not supported with DC.
 		 *
 		 * Fallback to the non-DC driver here by default so as not to
 		 * cause regressions.
@@ -4288,58 +4360,53 @@ static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
 	long timeout;
 	int ret = 0;
 
-	/*
-	 * By default timeout for jobs is 10 sec
-	 */
-	adev->compute_timeout = adev->gfx_timeout = msecs_to_jiffies(10000);
-	adev->sdma_timeout = adev->video_timeout = adev->gfx_timeout;
+	/* By default timeout for all queues is 2 sec */
+	adev->gfx_timeout = adev->compute_timeout = adev->sdma_timeout =
+		adev->video_timeout = msecs_to_jiffies(2000);
 
-	if (strnlen(input, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH)) {
-		while ((timeout_setting = strsep(&input, ",")) &&
-				strnlen(timeout_setting, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH)) {
-			ret = kstrtol(timeout_setting, 0, &timeout);
-			if (ret)
-				return ret;
+	if (!strnlen(input, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH))
+		return 0;
 
-			if (timeout == 0) {
-				index++;
-				continue;
-			} else if (timeout < 0) {
-				timeout = MAX_SCHEDULE_TIMEOUT;
-				dev_warn(adev->dev, "lockup timeout disabled");
-				add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK);
-			} else {
-				timeout = msecs_to_jiffies(timeout);
-			}
+	while ((timeout_setting = strsep(&input, ",")) &&
+	       strnlen(timeout_setting, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH)) {
+		ret = kstrtol(timeout_setting, 0, &timeout);
+		if (ret)
+			return ret;
 
-			switch (index++) {
-			case 0:
-				adev->gfx_timeout = timeout;
-				break;
-			case 1:
-				adev->compute_timeout = timeout;
-				break;
-			case 2:
-				adev->sdma_timeout = timeout;
-				break;
-			case 3:
-				adev->video_timeout = timeout;
-				break;
-			default:
-				break;
-			}
+		if (timeout == 0) {
+			index++;
+			continue;
+		} else if (timeout < 0) {
+			timeout = MAX_SCHEDULE_TIMEOUT;
+			dev_warn(adev->dev, "lockup timeout disabled");
+			add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK);
+		} else {
+			timeout = msecs_to_jiffies(timeout);
 		}
-		/*
-		 * There is only one value specified and
-		 * it should apply to all non-compute jobs.
-		 */
-		if (index == 1) {
-			adev->sdma_timeout = adev->video_timeout = adev->gfx_timeout;
-			if (amdgpu_sriov_vf(adev) || amdgpu_passthrough(adev))
-				adev->compute_timeout = adev->gfx_timeout;
+
+		switch (index++) {
+		case 0:
+			adev->gfx_timeout = timeout;
+			break;
+		case 1:
+			adev->compute_timeout = timeout;
+			break;
+		case 2:
+			adev->sdma_timeout = timeout;
+			break;
+		case 3:
+			adev->video_timeout = timeout;
+			break;
+		default:
+			break;
 		}
 	}
 
+	/* When only one value specified apply it to all queues. */
+	if (index == 1)
+		adev->gfx_timeout = adev->compute_timeout = adev->sdma_timeout =
+			adev->video_timeout = timeout;
+
 	return ret;
 }
 
@@ -4394,6 +4461,55 @@ static void amdgpu_device_set_mcbp(struct amdgpu_device *adev)
 		dev_info(adev->dev, "MCBP is enabled\n");
 }
 
+static int amdgpu_device_sys_interface_init(struct amdgpu_device *adev)
+{
+	int r;
+
+	r = amdgpu_atombios_sysfs_init(adev);
+	if (r)
+		drm_err(&adev->ddev,
+			"registering atombios sysfs failed (%d).\n", r);
+
+	r = amdgpu_pm_sysfs_init(adev);
+	if (r)
+		dev_err(adev->dev, "registering pm sysfs failed (%d).\n", r);
+
+	r = amdgpu_ucode_sysfs_init(adev);
+	if (r) {
+		adev->ucode_sysfs_en = false;
+		dev_err(adev->dev, "Creating firmware sysfs failed (%d).\n", r);
+	} else
+		adev->ucode_sysfs_en = true;
+
+	r = amdgpu_device_attr_sysfs_init(adev);
+	if (r)
+		dev_err(adev->dev, "Could not create amdgpu device attr\n");
+
+	r = devm_device_add_group(adev->dev, &amdgpu_board_attrs_group);
+	if (r)
+		dev_err(adev->dev,
+			"Could not create amdgpu board attributes\n");
+
+	amdgpu_fru_sysfs_init(adev);
+	amdgpu_reg_state_sysfs_init(adev);
+	amdgpu_xcp_sysfs_init(adev);
+
+	return r;
+}
+
+static void amdgpu_device_sys_interface_fini(struct amdgpu_device *adev)
+{
+	if (adev->pm.sysfs_initialized)
+		amdgpu_pm_sysfs_fini(adev);
+	if (adev->ucode_sysfs_en)
+		amdgpu_ucode_sysfs_fini(adev);
+	amdgpu_device_attr_sysfs_fini(adev);
+	amdgpu_fru_sysfs_fini(adev);
+
+	amdgpu_reg_state_sysfs_fini(adev);
+	amdgpu_xcp_sysfs_fini(adev);
+}
+
 /**
  * amdgpu_device_init - initialize the driver
  *
@@ -4493,7 +4609,6 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	mutex_init(&adev->gfx.userq_sch_mutex);
 	mutex_init(&adev->gfx.workload_profile_mutex);
 	mutex_init(&adev->vcn.workload_profile_mutex);
-	mutex_init(&adev->userq_mutex);
 
 	amdgpu_device_init_apu_flags(adev);
 
@@ -4521,7 +4636,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 
 	INIT_LIST_HEAD(&adev->pm.od_kobj_list);
 
-	INIT_LIST_HEAD(&adev->userq_mgr_list);
+	xa_init(&adev->userq_doorbell_xa);
 
 	INIT_DELAYED_WORK(&adev->delayed_init_work,
 			  amdgpu_device_delayed_init_work_handler);
@@ -4544,6 +4659,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	}
 
 	INIT_WORK(&adev->xgmi_reset_work, amdgpu_device_xgmi_reset_func);
+	INIT_WORK(&adev->userq_reset_work, amdgpu_userq_reset_work);
 
 	adev->gfx.gfx_off_req_count = 1;
 	adev->gfx.gfx_off_residency = 0;
@@ -4817,39 +4933,14 @@ fence_driver_init:
 		flush_delayed_work(&adev->delayed_init_work);
 	}
 
+	if (adev->init_lvl->level == AMDGPU_INIT_LEVEL_MINIMAL_XGMI)
+		amdgpu_xgmi_reset_on_init(adev);
 	/*
 	 * Place those sysfs registering after `late_init`. As some of those
 	 * operations performed in `late_init` might affect the sysfs
 	 * interfaces creating.
 	 */
-	r = amdgpu_atombios_sysfs_init(adev);
-	if (r)
-		drm_err(&adev->ddev,
-			"registering atombios sysfs failed (%d).\n", r);
-
-	r = amdgpu_pm_sysfs_init(adev);
-	if (r)
-		dev_err(adev->dev, "registering pm sysfs failed (%d).\n", r);
-
-	r = amdgpu_ucode_sysfs_init(adev);
-	if (r) {
-		adev->ucode_sysfs_en = false;
-		dev_err(adev->dev, "Creating firmware sysfs failed (%d).\n", r);
-	} else
-		adev->ucode_sysfs_en = true;
-
-	r = amdgpu_device_attr_sysfs_init(adev);
-	if (r)
-		dev_err(adev->dev, "Could not create amdgpu device attr\n");
-
-	r = devm_device_add_group(adev->dev, &amdgpu_board_attrs_group);
-	if (r)
-		dev_err(adev->dev,
-			"Could not create amdgpu board attributes\n");
-
-	amdgpu_fru_sysfs_init(adev);
-	amdgpu_reg_state_sysfs_init(adev);
-	amdgpu_xcp_sysfs_init(adev);
+	r = amdgpu_device_sys_interface_init(adev);
 
 	if (IS_ENABLED(CONFIG_PERF_EVENTS))
 		r = amdgpu_pmu_init(adev);
@@ -4877,9 +4968,6 @@ fence_driver_init:
 	if (px)
 		vga_switcheroo_init_domain_pm_ops(adev->dev, &adev->vga_pm_domain);
 
-	if (adev->init_lvl->level == AMDGPU_INIT_LEVEL_MINIMAL_XGMI)
-		amdgpu_xgmi_reset_on_init(adev);
-
 	amdgpu_device_check_iommu_direct_map(adev);
 
 	adev->pm_nb.notifier_call = amdgpu_device_pm_notifier;
@@ -4971,15 +5059,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 	}
 	amdgpu_fence_driver_hw_fini(adev);
 
-	if (adev->pm.sysfs_initialized)
-		amdgpu_pm_sysfs_fini(adev);
-	if (adev->ucode_sysfs_en)
-		amdgpu_ucode_sysfs_fini(adev);
-	amdgpu_device_attr_sysfs_fini(adev);
-	amdgpu_fru_sysfs_fini(adev);
-
-	amdgpu_reg_state_sysfs_fini(adev);
-	amdgpu_xcp_sysfs_fini(adev);
+	amdgpu_device_sys_interface_fini(adev);
 
 	/* disable ras feature must before hw fini */
 	amdgpu_ras_pre_fini(adev);
@@ -5054,7 +5134,7 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 
 	if (IS_ENABLED(CONFIG_PERF_EVENTS))
 		amdgpu_pmu_fini(adev);
-	if (adev->mman.discovery_bin)
+	if (adev->discovery.bin)
 		amdgpu_discovery_fini(adev);
 
 	amdgpu_reset_put_reset_domain(adev->reset_domain);
@@ -5202,7 +5282,7 @@ void amdgpu_device_complete(struct drm_device *dev)
 int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients)
 {
 	struct amdgpu_device *adev = drm_to_adev(dev);
-	int r = 0;
+	int r, rec;
 
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
@@ -5218,35 +5298,92 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients)
 			return r;
 	}
 
-	if (amdgpu_acpi_smart_shift_update(adev, AMDGPU_SS_DEV_D3))
-		dev_warn(adev->dev, "smart shift update failed\n");
+	r = amdgpu_acpi_smart_shift_update(adev, AMDGPU_SS_DEV_D3);
+	if (r)
+		goto unwind_sriov;
 
 	if (notify_clients)
-		drm_client_dev_suspend(adev_to_drm(adev), false);
+		drm_client_dev_suspend(adev_to_drm(adev));
 
 	cancel_delayed_work_sync(&adev->delayed_init_work);
 
 	amdgpu_ras_suspend(adev);
 
-	amdgpu_device_ip_suspend_phase1(adev);
+	r = amdgpu_device_ip_suspend_phase1(adev);
+	if (r)
+		goto unwind_smartshift;
 
 	amdgpu_amdkfd_suspend(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm);
-	amdgpu_userq_suspend(adev);
+	r = amdgpu_userq_suspend(adev);
+	if (r)
+		goto unwind_ip_phase1;
 
 	r = amdgpu_device_evict_resources(adev);
 	if (r)
-		return r;
+		goto unwind_userq;
 
 	amdgpu_ttm_set_buffer_funcs_status(adev, false);
 
 	amdgpu_fence_driver_hw_fini(adev);
 
-	amdgpu_device_ip_suspend_phase2(adev);
+	r = amdgpu_device_ip_suspend_phase2(adev);
+	if (r)
+		goto unwind_evict;
 
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_release_full_gpu(adev, false);
 
 	return 0;
+
+unwind_evict:
+	if (adev->mman.buffer_funcs_ring->sched.ready)
+		amdgpu_ttm_set_buffer_funcs_status(adev, true);
+	amdgpu_fence_driver_hw_init(adev);
+
+unwind_userq:
+	rec = amdgpu_userq_resume(adev);
+	if (rec) {
+		dev_warn(adev->dev, "failed to re-initialize user queues: %d\n", rec);
+		return r;
+	}
+	rec = amdgpu_amdkfd_resume(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm);
+	if (rec) {
+		dev_warn(adev->dev, "failed to re-initialize kfd: %d\n", rec);
+		return r;
+	}
+
+unwind_ip_phase1:
+	/* suspend phase 1 = resume phase 3 */
+	rec = amdgpu_device_ip_resume_phase3(adev);
+	if (rec) {
+		dev_warn(adev->dev, "failed to re-initialize IPs phase1: %d\n", rec);
+		return r;
+	}
+
+unwind_smartshift:
+	rec = amdgpu_acpi_smart_shift_update(adev, AMDGPU_SS_DEV_D0);
+	if (rec) {
+		dev_warn(adev->dev, "failed to re-update smart shift: %d\n", rec);
+		return r;
+	}
+
+	if (notify_clients)
+		drm_client_dev_resume(adev_to_drm(adev));
+
+	amdgpu_ras_resume(adev);
+
+unwind_sriov:
+	if (amdgpu_sriov_vf(adev)) {
+		rec = amdgpu_virt_request_full_gpu(adev, true);
+		if (rec) {
+			dev_warn(adev->dev, "failed to reinitialize sriov: %d\n", rec);
+			return r;
+		}
+	}
+
+	adev->in_suspend = adev->in_s0ix = adev->in_s3 = false;
+
+	return r;
 }
 
 static inline int amdgpu_virt_resume(struct amdgpu_device *adev)
@@ -5352,7 +5489,7 @@ exit:
 	flush_delayed_work(&adev->delayed_init_work);
 
 	if (notify_clients)
-		drm_client_dev_resume(adev_to_drm(adev), false);
+		drm_client_dev_resume(adev_to_drm(adev));
 
 	amdgpu_ras_resume(adev);
 
@@ -5808,11 +5945,6 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
-		/* Clear job fence from fence drv to avoid force_completion
-		 * leave NULL and vm flush fence in fence drv
-		 */
-		amdgpu_fence_driver_clear_job_fences(ring);
-
 		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
 		amdgpu_fence_driver_force_completion(ring);
 	}
@@ -5957,7 +6089,11 @@ int amdgpu_device_reinit_after_reset(struct amdgpu_reset_context *reset_context)
 				if (r)
 					goto out;
 
-				drm_client_dev_resume(adev_to_drm(tmp_adev), false);
+				r = amdgpu_userq_post_reset(tmp_adev, vram_lost);
+				if (r)
+					goto out;
+
+				drm_client_dev_resume(adev_to_drm(tmp_adev));
 
 				/*
 				 * The GPU enters bad state once faulty pages
@@ -6179,6 +6315,7 @@ static inline void amdgpu_device_stop_pending_resets(struct amdgpu_device *adev)
 	if (!amdgpu_sriov_vf(adev))
 		cancel_work(&adev->reset_work);
 #endif
+	cancel_work(&adev->userq_reset_work);
 
 	if (adev->kfd.dev)
 		cancel_work(&adev->kfd.reset_work);
@@ -6292,13 +6429,15 @@ static void amdgpu_device_halt_activities(struct amdgpu_device *adev,
 		 */
 		amdgpu_unregister_gpu_instance(tmp_adev);
 
-		drm_client_dev_suspend(adev_to_drm(tmp_adev), false);
+		drm_client_dev_suspend(adev_to_drm(tmp_adev));
 
 		/* disable ras on ALL IPs */
 		if (!need_emergency_restart && !amdgpu_reset_in_dpc(adev) &&
 		    amdgpu_device_ip_need_full_reset(tmp_adev))
 			amdgpu_ras_suspend(tmp_adev);
 
+		amdgpu_userq_pre_reset(tmp_adev);
+
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = tmp_adev->rings[i];
 
@@ -6528,6 +6667,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 			goto end_reset;
 	}
 
+	/* Cannot be called after locking reset domain */
+	amdgpu_ras_pre_reset(adev, &device_list);
+
 	/* We need to lock reset domain only once both for XGMI and single device */
 	amdgpu_device_recovery_get_reset_lock(adev, &device_list);
 
@@ -6541,7 +6683,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	 *
 	 * job->base holds a reference to parent fence
 	 */
-	if (job && dma_fence_is_signaled(&job->hw_fence.base)) {
+	if (job && dma_fence_is_signaled(&job->hw_fence->base)) {
 		job_signaled = true;
 		dev_info(adev->dev, "Guilty job already signaled, skipping HW reset");
 		goto skip_hw_reset;
@@ -6558,6 +6700,7 @@ skip_sched_resume:
 	amdgpu_device_gpu_resume(adev, &device_list, need_emergency_restart);
 reset_unlock:
 	amdgpu_device_recovery_put_reset_lock(adev, &device_list);
+	amdgpu_ras_post_reset(adev, &device_list);
 end_reset:
 	if (hive) {
 		mutex_unlock(&hive->hive_lock);
@@ -7285,10 +7428,17 @@ void amdgpu_device_flush_hdp(struct amdgpu_device *adev,
 	if (adev->gmc.xgmi.connected_to_cpu)
 		return;
 
-	if (ring && ring->funcs->emit_hdp_flush)
+	if (ring && ring->funcs->emit_hdp_flush) {
 		amdgpu_ring_emit_hdp_flush(ring);
-	else
-		amdgpu_asic_flush_hdp(adev, ring);
+		return;
+	}
+
+	if (!ring && amdgpu_sriov_runtime(adev)) {
+		if (!amdgpu_kiq_hdp_flush(adev))
+			return;
+	}
+
+	amdgpu_hdp_flush(adev, ring);
 }
 
 void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev,
@@ -7301,7 +7451,7 @@ void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev,
 	if (adev->gmc.xgmi.connected_to_cpu)
 		return;
 
-	amdgpu_asic_invalidate_hdp(adev, ring);
+	amdgpu_hdp_invalidate(adev, ring);
 }
 
 int amdgpu_in_reset(struct amdgpu_device *adev)