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, 516 insertions, 124 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index 1add21160d21..9a969175900e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -25,10 +25,13 @@
 #include <drm/drm_auth.h>
 #include <drm/drm_exec.h>
 #include <linux/pm_runtime.h>
+#include <drm/drm_drv.h>
 
 #include "amdgpu.h"
+#include "amdgpu_reset.h"
 #include "amdgpu_vm.h"
 #include "amdgpu_userq.h"
+#include "amdgpu_hmm.h"
 #include "amdgpu_userq_fence.h"
 
 u32 amdgpu_userq_get_supported_ip_mask(struct amdgpu_device *adev)
@@ -44,10 +47,130 @@ u32 amdgpu_userq_get_supported_ip_mask(struct amdgpu_device *adev)
 	return userq_ip_mask;
 }
 
-int amdgpu_userq_input_va_validate(struct amdgpu_vm *vm, u64 addr,
-				   u64 expected_size)
+static bool amdgpu_userq_is_reset_type_supported(struct amdgpu_device *adev,
+				enum amdgpu_ring_type ring_type, int reset_type)
+{
+
+	if (ring_type < 0 || ring_type >= AMDGPU_RING_TYPE_MAX)
+		return false;
+
+	switch (ring_type) {
+	case AMDGPU_RING_TYPE_GFX:
+		if (adev->gfx.gfx_supported_reset & reset_type)
+			return true;
+		break;
+	case AMDGPU_RING_TYPE_COMPUTE:
+		if (adev->gfx.compute_supported_reset & reset_type)
+			return true;
+		break;
+	case AMDGPU_RING_TYPE_SDMA:
+		if (adev->sdma.supported_reset & reset_type)
+			return true;
+		break;
+	case AMDGPU_RING_TYPE_VCN_DEC:
+	case AMDGPU_RING_TYPE_VCN_ENC:
+		if (adev->vcn.supported_reset & reset_type)
+			return true;
+		break;
+	case AMDGPU_RING_TYPE_VCN_JPEG:
+		if (adev->jpeg.supported_reset & reset_type)
+			return true;
+		break;
+	default:
+		break;
+	}
+	return false;
+}
+
+static void amdgpu_userq_gpu_reset(struct amdgpu_device *adev)
+{
+	if (amdgpu_device_should_recover_gpu(adev)) {
+		amdgpu_reset_domain_schedule(adev->reset_domain,
+					     &adev->userq_reset_work);
+		/* Wait for the reset job to complete */
+		flush_work(&adev->userq_reset_work);
+	}
+}
+
+static int
+amdgpu_userq_detect_and_reset_queues(struct amdgpu_userq_mgr *uq_mgr)
+{
+	struct amdgpu_device *adev = uq_mgr->adev;
+	const int queue_types[] = {
+		AMDGPU_RING_TYPE_COMPUTE,
+		AMDGPU_RING_TYPE_GFX,
+		AMDGPU_RING_TYPE_SDMA
+	};
+	const int num_queue_types = ARRAY_SIZE(queue_types);
+	bool gpu_reset = false;
+	int r = 0;
+	int i;
+
+	/* Warning if current process mutex is not held */
+	WARN_ON(!mutex_is_locked(&uq_mgr->userq_mutex));
+
+	if (unlikely(adev->debug_disable_gpu_ring_reset)) {
+		dev_err(adev->dev, "userq reset disabled by debug mask\n");
+		return 0;
+	}
+
+	/*
+	 * If GPU recovery feature is disabled system-wide,
+	 * skip all reset detection logic
+	 */
+	if (!amdgpu_gpu_recovery)
+		return 0;
+
+	/*
+	 * Iterate through all queue types to detect and reset problematic queues
+	 * Process each queue type in the defined order
+	 */
+	for (i = 0; i < num_queue_types; i++) {
+		int ring_type = queue_types[i];
+		const struct amdgpu_userq_funcs *funcs = adev->userq_funcs[ring_type];
+
+		if (!amdgpu_userq_is_reset_type_supported(adev, ring_type, AMDGPU_RESET_TYPE_PER_QUEUE))
+				continue;
+
+		if (atomic_read(&uq_mgr->userq_count[ring_type]) > 0 &&
+		    funcs && funcs->detect_and_reset) {
+			r = funcs->detect_and_reset(adev, ring_type);
+			if (r) {
+				gpu_reset = true;
+				break;
+			}
+		}
+	}
+
+	if (gpu_reset)
+		amdgpu_userq_gpu_reset(adev);
+
+	return r;
+}
+
+static int amdgpu_userq_buffer_va_list_add(struct amdgpu_usermode_queue *queue,
+					   struct amdgpu_bo_va_mapping *va_map, u64 addr)
+{
+	struct amdgpu_userq_va_cursor *va_cursor;
+	struct userq_va_list;
+
+	va_cursor = kzalloc(sizeof(*va_cursor), GFP_KERNEL);
+	if (!va_cursor)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&va_cursor->list);
+	va_cursor->gpu_addr = addr;
+	atomic_set(&va_map->bo_va->userq_va_mapped, 1);
+	list_add(&va_cursor->list, &queue->userq_va_list);
+
+	return 0;
+}
+
+int amdgpu_userq_input_va_validate(struct amdgpu_usermode_queue *queue,
+				   u64 addr, u64 expected_size)
 {
 	struct amdgpu_bo_va_mapping *va_map;
+	struct amdgpu_vm *vm = queue->vm;
 	u64 user_addr;
 	u64 size;
 	int r = 0;
@@ -67,6 +190,7 @@ int amdgpu_userq_input_va_validate(struct amdgpu_vm *vm, u64 addr,
 	/* Only validate the userq whether resident in the VM mapping range */
 	if (user_addr >= va_map->start  &&
 	    va_map->last - user_addr + 1 >= size) {
+		amdgpu_userq_buffer_va_list_add(queue, va_map, user_addr);
 		amdgpu_bo_unreserve(vm->root.bo);
 		return 0;
 	}
@@ -77,6 +201,76 @@ out_err:
 	return r;
 }
 
+static bool amdgpu_userq_buffer_va_mapped(struct amdgpu_vm *vm, u64 addr)
+{
+	struct amdgpu_bo_va_mapping *mapping;
+	bool r;
+
+	if (amdgpu_bo_reserve(vm->root.bo, false))
+		return false;
+
+	mapping = amdgpu_vm_bo_lookup_mapping(vm, addr);
+	if (!IS_ERR_OR_NULL(mapping) && atomic_read(&mapping->bo_va->userq_va_mapped))
+		r = true;
+	else
+		r = false;
+	amdgpu_bo_unreserve(vm->root.bo);
+
+	return r;
+}
+
+static bool amdgpu_userq_buffer_vas_mapped(struct amdgpu_usermode_queue *queue)
+{
+	struct amdgpu_userq_va_cursor *va_cursor, *tmp;
+	int r = 0;
+
+	list_for_each_entry_safe(va_cursor, tmp, &queue->userq_va_list, list) {
+		r += amdgpu_userq_buffer_va_mapped(queue->vm, va_cursor->gpu_addr);
+		dev_dbg(queue->userq_mgr->adev->dev,
+			"validate the userq mapping:%p va:%llx r:%d\n",
+			queue, va_cursor->gpu_addr, r);
+	}
+
+	if (r != 0)
+		return true;
+
+	return false;
+}
+
+static void amdgpu_userq_buffer_va_list_del(struct amdgpu_bo_va_mapping *mapping,
+					    struct amdgpu_userq_va_cursor *va_cursor)
+{
+	atomic_set(&mapping->bo_va->userq_va_mapped, 0);
+	list_del(&va_cursor->list);
+	kfree(va_cursor);
+}
+
+static int amdgpu_userq_buffer_vas_list_cleanup(struct amdgpu_device *adev,
+						struct amdgpu_usermode_queue *queue)
+{
+	struct amdgpu_userq_va_cursor *va_cursor, *tmp;
+	struct amdgpu_bo_va_mapping *mapping;
+	int r;
+
+	r = amdgpu_bo_reserve(queue->vm->root.bo, false);
+	if (r)
+		return r;
+
+	list_for_each_entry_safe(va_cursor, tmp, &queue->userq_va_list, list) {
+		mapping = amdgpu_vm_bo_lookup_mapping(queue->vm, va_cursor->gpu_addr);
+		if (!mapping) {
+			r = -EINVAL;
+			goto err;
+		}
+		dev_dbg(adev->dev, "delete the userq:%p va:%llx\n",
+			queue, va_cursor->gpu_addr);
+		amdgpu_userq_buffer_va_list_del(mapping, va_cursor);
+	}
+err:
+	amdgpu_bo_unreserve(queue->vm->root.bo);
+	return r;
+}
+
 static int
 amdgpu_userq_preempt_helper(struct amdgpu_userq_mgr *uq_mgr,
 			  struct amdgpu_usermode_queue *queue)
@@ -84,17 +278,22 @@ amdgpu_userq_preempt_helper(struct amdgpu_userq_mgr *uq_mgr,
 	struct amdgpu_device *adev = uq_mgr->adev;
 	const struct amdgpu_userq_funcs *userq_funcs =
 		adev->userq_funcs[queue->queue_type];
+	bool found_hung_queue = false;
 	int r = 0;
 
 	if (queue->state == AMDGPU_USERQ_STATE_MAPPED) {
 		r = userq_funcs->preempt(uq_mgr, queue);
 		if (r) {
 			queue->state = AMDGPU_USERQ_STATE_HUNG;
+			found_hung_queue = true;
 		} else {
 			queue->state = AMDGPU_USERQ_STATE_PREEMPTED;
 		}
 	}
 
+	if (found_hung_queue)
+		amdgpu_userq_detect_and_reset_queues(uq_mgr);
+
 	return r;
 }
 
@@ -126,16 +325,23 @@ amdgpu_userq_unmap_helper(struct amdgpu_userq_mgr *uq_mgr,
 	struct amdgpu_device *adev = uq_mgr->adev;
 	const struct amdgpu_userq_funcs *userq_funcs =
 		adev->userq_funcs[queue->queue_type];
+	bool found_hung_queue = false;
 	int r = 0;
 
 	if ((queue->state == AMDGPU_USERQ_STATE_MAPPED) ||
 		(queue->state == AMDGPU_USERQ_STATE_PREEMPTED)) {
 		r = userq_funcs->unmap(uq_mgr, queue);
-		if (r)
+		if (r) {
 			queue->state = AMDGPU_USERQ_STATE_HUNG;
-		else
+			found_hung_queue = true;
+		} else {
 			queue->state = AMDGPU_USERQ_STATE_UNMAPPED;
+		}
 	}
+
+	if (found_hung_queue)
+		amdgpu_userq_detect_and_reset_queues(uq_mgr);
+
 	return r;
 }
 
@@ -152,26 +358,33 @@ amdgpu_userq_map_helper(struct amdgpu_userq_mgr *uq_mgr,
 		r = userq_funcs->map(uq_mgr, queue);
 		if (r) {
 			queue->state = AMDGPU_USERQ_STATE_HUNG;
+			amdgpu_userq_detect_and_reset_queues(uq_mgr);
 		} else {
 			queue->state = AMDGPU_USERQ_STATE_MAPPED;
 		}
 	}
+
 	return r;
 }
 
-static void
+static int
 amdgpu_userq_wait_for_last_fence(struct amdgpu_userq_mgr *uq_mgr,
 				 struct amdgpu_usermode_queue *queue)
 {
 	struct dma_fence *f = queue->last_fence;
-	int ret;
+	int ret = 0;
 
 	if (f && !dma_fence_is_signaled(f)) {
-		ret = dma_fence_wait_timeout(f, true, msecs_to_jiffies(100));
-		if (ret <= 0)
+		ret = dma_fence_wait_timeout(f, true, MAX_SCHEDULE_TIMEOUT);
+		if (ret <= 0) {
 			drm_file_err(uq_mgr->file, "Timed out waiting for fence=%llu:%llu\n",
 				     f->context, f->seqno);
+			queue->state = AMDGPU_USERQ_STATE_HUNG;
+			return -ETIME;
+		}
 	}
+
+	return ret;
 }
 
 static void
@@ -182,16 +395,27 @@ amdgpu_userq_cleanup(struct amdgpu_userq_mgr *uq_mgr,
 	struct amdgpu_device *adev = uq_mgr->adev;
 	const struct amdgpu_userq_funcs *uq_funcs = adev->userq_funcs[queue->queue_type];
 
+	/* Wait for mode-1 reset to complete */
+	down_read(&adev->reset_domain->sem);
+
+	/* Drop the userq reference. */
+	amdgpu_userq_buffer_vas_list_cleanup(adev, queue);
 	uq_funcs->mqd_destroy(uq_mgr, queue);
 	amdgpu_userq_fence_driver_free(queue);
-	idr_remove(&uq_mgr->userq_idr, queue_id);
+	/* Use interrupt-safe locking since IRQ handlers may access these XArrays */
+	xa_erase_irq(&uq_mgr->userq_mgr_xa, (unsigned long)queue_id);
+	xa_erase_irq(&adev->userq_doorbell_xa, queue->doorbell_index);
+	queue->userq_mgr = NULL;
+	list_del(&queue->userq_va_list);
 	kfree(queue);
+
+	up_read(&adev->reset_domain->sem);
 }
 
 static struct amdgpu_usermode_queue *
 amdgpu_userq_find(struct amdgpu_userq_mgr *uq_mgr, int qid)
 {
-	return idr_find(&uq_mgr->userq_idr, qid);
+	return xa_load(&uq_mgr->userq_mgr_xa, qid);
 }
 
 void
@@ -319,17 +543,6 @@ amdgpu_userq_get_doorbell_index(struct amdgpu_userq_mgr *uq_mgr,
 	case AMDGPU_HW_IP_DMA:
 		db_size = sizeof(u64);
 		break;
-
-	case AMDGPU_HW_IP_VCN_ENC:
-		db_size = sizeof(u32);
-		db_info->doorbell_offset += AMDGPU_NAVI10_DOORBELL64_VCN0_1 << 1;
-		break;
-
-	case AMDGPU_HW_IP_VPE:
-		db_size = sizeof(u32);
-		db_info->doorbell_offset += AMDGPU_NAVI10_DOORBELL64_VPE << 1;
-		break;
-
 	default:
 		drm_file_err(uq_mgr->file, "[Usermode queues] IP %d not support\n",
 			     db_info->queue_type);
@@ -378,10 +591,11 @@ amdgpu_userq_destroy(struct drm_file *filp, int queue_id)
 		amdgpu_bo_unreserve(queue->db_obj.obj);
 	}
 	amdgpu_bo_unref(&queue->db_obj.obj);
-
+	atomic_dec(&uq_mgr->userq_count[queue->queue_type]);
 #if defined(CONFIG_DEBUG_FS)
 	debugfs_remove_recursive(queue->debugfs_queue);
 #endif
+	amdgpu_userq_detect_and_reset_queues(uq_mgr);
 	r = amdgpu_userq_unmap_helper(uq_mgr, queue);
 	/*TODO: It requires a reset for userq hw unmap error*/
 	if (unlikely(r != AMDGPU_USERQ_STATE_UNMAPPED)) {
@@ -391,7 +605,6 @@ amdgpu_userq_destroy(struct drm_file *filp, int queue_id)
 	amdgpu_userq_cleanup(uq_mgr, queue, queue_id);
 	mutex_unlock(&uq_mgr->userq_mutex);
 
-	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
 	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	return r;
@@ -463,8 +676,9 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 	struct amdgpu_db_info db_info;
 	char *queue_name;
 	bool skip_map_queue;
+	u32 qid;
 	uint64_t index;
-	int qid, r = 0;
+	int r = 0;
 	int priority =
 		(args->in.flags & AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_MASK) >>
 		AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_SHIFT;
@@ -487,7 +701,6 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 	 *
 	 * This will also make sure we have a valid eviction fence ready to be used.
 	 */
-	mutex_lock(&adev->userq_mutex);
 	amdgpu_userq_ensure_ev_fence(&fpriv->userq_mgr, &fpriv->evf_mgr);
 
 	uq_funcs = adev->userq_funcs[args->in.ip_type];
@@ -505,14 +718,7 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 		goto unlock;
 	}
 
-	/* Validate the userq virtual address.*/
-	if (amdgpu_userq_input_va_validate(&fpriv->vm, args->in.queue_va, args->in.queue_size) ||
-	    amdgpu_userq_input_va_validate(&fpriv->vm, args->in.rptr_va, AMDGPU_GPU_PAGE_SIZE) ||
-	    amdgpu_userq_input_va_validate(&fpriv->vm, args->in.wptr_va, AMDGPU_GPU_PAGE_SIZE)) {
-		r = -EINVAL;
-		kfree(queue);
-		goto unlock;
-	}
+	INIT_LIST_HEAD(&queue->userq_va_list);
 	queue->doorbell_handle = args->in.doorbell_handle;
 	queue->queue_type = args->in.ip_type;
 	queue->vm = &fpriv->vm;
@@ -523,6 +729,15 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 	db_info.db_obj = &queue->db_obj;
 	db_info.doorbell_offset = args->in.doorbell_offset;
 
+	/* Validate the userq virtual address.*/
+	if (amdgpu_userq_input_va_validate(queue, args->in.queue_va, args->in.queue_size) ||
+	    amdgpu_userq_input_va_validate(queue, args->in.rptr_va, AMDGPU_GPU_PAGE_SIZE) ||
+	    amdgpu_userq_input_va_validate(queue, args->in.wptr_va, AMDGPU_GPU_PAGE_SIZE)) {
+		r = -EINVAL;
+		kfree(queue);
+		goto unlock;
+	}
+
 	/* Convert relative doorbell offset into absolute doorbell index */
 	index = amdgpu_userq_get_doorbell_index(uq_mgr, &db_info, filp);
 	if (index == (uint64_t)-EINVAL) {
@@ -548,16 +763,27 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 		goto unlock;
 	}
 
+	/* Wait for mode-1 reset to complete */
+	down_read(&adev->reset_domain->sem);
+	r = xa_err(xa_store_irq(&adev->userq_doorbell_xa, index, queue, GFP_KERNEL));
+	if (r) {
+		kfree(queue);
+		up_read(&adev->reset_domain->sem);
+		goto unlock;
+	}
 
-	qid = idr_alloc(&uq_mgr->userq_idr, queue, 1, AMDGPU_MAX_USERQ_COUNT, GFP_KERNEL);
-	if (qid < 0) {
+	r = xa_alloc(&uq_mgr->userq_mgr_xa, &qid, queue, XA_LIMIT(1, AMDGPU_MAX_USERQ_COUNT), GFP_KERNEL);
+	if (r) {
 		drm_file_err(uq_mgr->file, "Failed to allocate a queue id\n");
 		amdgpu_userq_fence_driver_free(queue);
 		uq_funcs->mqd_destroy(uq_mgr, queue);
 		kfree(queue);
 		r = -ENOMEM;
+		up_read(&adev->reset_domain->sem);
 		goto unlock;
 	}
+	up_read(&adev->reset_domain->sem);
+	queue->userq_mgr = uq_mgr;
 
 	/* don't map the queue if scheduling is halted */
 	if (adev->userq_halt_for_enforce_isolation &&
@@ -570,7 +796,7 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 		r = amdgpu_userq_map_helper(uq_mgr, queue);
 		if (r) {
 			drm_file_err(uq_mgr->file, "Failed to map Queue\n");
-			idr_remove(&uq_mgr->userq_idr, qid);
+			xa_erase(&uq_mgr->userq_mgr_xa, qid);
 			amdgpu_userq_fence_driver_free(queue);
 			uq_funcs->mqd_destroy(uq_mgr, queue);
 			kfree(queue);
@@ -592,10 +818,10 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 	kfree(queue_name);
 
 	args->out.queue_id = qid;
+	atomic_inc(&uq_mgr->userq_count[queue->queue_type]);
 
 unlock:
 	mutex_unlock(&uq_mgr->userq_mutex);
-	mutex_unlock(&adev->userq_mutex);
 
 	return r;
 }
@@ -693,11 +919,19 @@ static int
 amdgpu_userq_restore_all(struct amdgpu_userq_mgr *uq_mgr)
 {
 	struct amdgpu_usermode_queue *queue;
-	int queue_id;
+	unsigned long queue_id;
 	int ret = 0, r;
 
 	/* Resume all the queues for this process */
-	idr_for_each_entry(&uq_mgr->userq_idr, queue, queue_id) {
+	xa_for_each(&uq_mgr->userq_mgr_xa, queue_id, queue) {
+
+		if (!amdgpu_userq_buffer_vas_mapped(queue)) {
+			drm_file_err(uq_mgr->file,
+				     "trying restore queue without va mapping\n");
+			queue->state = AMDGPU_USERQ_STATE_INVALID_VA;
+			continue;
+		}
+
 		r = amdgpu_userq_restore_helper(uq_mgr, queue);
 		if (r)
 			ret = r;
@@ -760,12 +994,21 @@ static int
 amdgpu_userq_vm_validate(struct amdgpu_userq_mgr *uq_mgr)
 {
 	struct amdgpu_fpriv *fpriv = uq_mgr_to_fpriv(uq_mgr);
+	bool invalidated = false, new_addition = false;
+	struct ttm_operation_ctx ctx = { true, false };
 	struct amdgpu_device *adev = uq_mgr->adev;
+	struct amdgpu_hmm_range *range;
 	struct amdgpu_vm *vm = &fpriv->vm;
+	unsigned long key, tmp_key;
 	struct amdgpu_bo_va *bo_va;
+	struct amdgpu_bo *bo;
 	struct drm_exec exec;
+	struct xarray xa;
 	int ret;
 
+	xa_init(&xa);
+
+retry_lock:
 	drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 0);
 	drm_exec_until_all_locked(&exec) {
 		ret = amdgpu_vm_lock_pd(vm, &exec, 1);
@@ -792,10 +1035,74 @@ amdgpu_userq_vm_validate(struct amdgpu_userq_mgr *uq_mgr)
 			goto unlock_all;
 	}
 
+	if (invalidated) {
+		xa_for_each(&xa, tmp_key, range) {
+			bo = range->bo;
+			amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU);
+			ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+			if (ret)
+				goto unlock_all;
+
+			amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm, range);
+
+			amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
+			ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+			if (ret)
+				goto unlock_all;
+		}
+		invalidated = false;
+	}
+
 	ret = amdgpu_vm_handle_moved(adev, vm, NULL);
 	if (ret)
 		goto unlock_all;
 
+	key = 0;
+	/* Validate User Ptr BOs */
+	list_for_each_entry(bo_va, &vm->done, base.vm_status) {
+		bo = bo_va->base.bo;
+		if (!bo)
+			continue;
+
+		if (!amdgpu_ttm_tt_is_userptr(bo->tbo.ttm))
+			continue;
+
+		range = xa_load(&xa, key);
+		if (range && range->bo != bo) {
+			xa_erase(&xa, key);
+			amdgpu_hmm_range_free(range);
+			range = NULL;
+		}
+
+		if (!range) {
+			range = amdgpu_hmm_range_alloc(bo);
+			if (!range) {
+				ret = -ENOMEM;
+				goto unlock_all;
+			}
+
+			xa_store(&xa, key, range, GFP_KERNEL);
+			new_addition = true;
+		}
+		key++;
+	}
+
+	if (new_addition) {
+		drm_exec_fini(&exec);
+		xa_for_each(&xa, tmp_key, range) {
+			if (!range)
+				continue;
+			bo = range->bo;
+			ret = amdgpu_ttm_tt_get_user_pages(bo, range);
+			if (ret)
+				goto unlock_all;
+		}
+
+		invalidated = true;
+		new_addition = false;
+		goto retry_lock;
+	}
+
 	ret = amdgpu_vm_update_pdes(adev, vm, false);
 	if (ret)
 		goto unlock_all;
@@ -815,6 +1122,13 @@ amdgpu_userq_vm_validate(struct amdgpu_userq_mgr *uq_mgr)
 
 unlock_all:
 	drm_exec_fini(&exec);
+	xa_for_each(&xa, tmp_key, range) {
+		if (!range)
+			continue;
+		bo = range->bo;
+		amdgpu_hmm_range_free(range);
+	}
+	xa_destroy(&xa);
 	return ret;
 }
 
@@ -848,11 +1162,12 @@ static int
 amdgpu_userq_evict_all(struct amdgpu_userq_mgr *uq_mgr)
 {
 	struct amdgpu_usermode_queue *queue;
-	int queue_id;
+	unsigned long queue_id;
 	int ret = 0, r;
 
+	amdgpu_userq_detect_and_reset_queues(uq_mgr);
 	/* Try to unmap all the queues in this process ctx */
-	idr_for_each_entry(&uq_mgr->userq_idr, queue, queue_id) {
+	xa_for_each(&uq_mgr->userq_mgr_xa, queue_id, queue) {
 		r = amdgpu_userq_preempt_helper(uq_mgr, queue);
 		if (r)
 			ret = r;
@@ -863,13 +1178,31 @@ amdgpu_userq_evict_all(struct amdgpu_userq_mgr *uq_mgr)
 	return ret;
 }
 
+void amdgpu_userq_reset_work(struct work_struct *work)
+{
+	struct amdgpu_device *adev = container_of(work, struct amdgpu_device,
+						  userq_reset_work);
+	struct amdgpu_reset_context reset_context;
+
+	memset(&reset_context, 0, sizeof(reset_context));
+
+	reset_context.method = AMD_RESET_METHOD_NONE;
+	reset_context.reset_req_dev = adev;
+	reset_context.src = AMDGPU_RESET_SRC_USERQ;
+	set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
+	/*set_bit(AMDGPU_SKIP_COREDUMP, &reset_context.flags);*/
+
+	amdgpu_device_gpu_recover(adev, NULL, &reset_context);
+}
+
 static int
 amdgpu_userq_wait_for_signal(struct amdgpu_userq_mgr *uq_mgr)
 {
 	struct amdgpu_usermode_queue *queue;
-	int queue_id, ret;
+	unsigned long queue_id;
+	int ret;
 
-	idr_for_each_entry(&uq_mgr->userq_idr, queue, queue_id) {
+	xa_for_each(&uq_mgr->userq_mgr_xa, queue_id, queue) {
 		struct dma_fence *f = queue->last_fence;
 
 		if (!f || dma_fence_is_signaled(f))
@@ -889,22 +1222,19 @@ void
 amdgpu_userq_evict(struct amdgpu_userq_mgr *uq_mgr,
 		   struct amdgpu_eviction_fence *ev_fence)
 {
-	int ret;
 	struct amdgpu_fpriv *fpriv = uq_mgr_to_fpriv(uq_mgr);
 	struct amdgpu_eviction_fence_mgr *evf_mgr = &fpriv->evf_mgr;
+	struct amdgpu_device *adev = uq_mgr->adev;
+	int ret;
 
 	/* Wait for any pending userqueue fence work to finish */
 	ret = amdgpu_userq_wait_for_signal(uq_mgr);
-	if (ret) {
-		drm_file_err(uq_mgr->file, "Not evicting userqueue, timeout waiting for work\n");
-		return;
-	}
+	if (ret)
+		dev_err(adev->dev, "Not evicting userqueue, timeout waiting for work\n");
 
 	ret = amdgpu_userq_evict_all(uq_mgr);
-	if (ret) {
-		drm_file_err(uq_mgr->file, "Failed to evict userqueue\n");
-		return;
-	}
+	if (ret)
+		dev_err(adev->dev, "Failed to evict userqueue\n");
 
 	/* Signal current eviction fence */
 	amdgpu_eviction_fence_signal(evf_mgr, ev_fence);
@@ -922,44 +1252,31 @@ int amdgpu_userq_mgr_init(struct amdgpu_userq_mgr *userq_mgr, struct drm_file *f
 			  struct amdgpu_device *adev)
 {
 	mutex_init(&userq_mgr->userq_mutex);
-	idr_init_base(&userq_mgr->userq_idr, 1);
+	xa_init_flags(&userq_mgr->userq_mgr_xa, XA_FLAGS_ALLOC);
 	userq_mgr->adev = adev;
 	userq_mgr->file = file_priv;
 
-	mutex_lock(&adev->userq_mutex);
-	list_add(&userq_mgr->list, &adev->userq_mgr_list);
-	mutex_unlock(&adev->userq_mutex);
-
 	INIT_DELAYED_WORK(&userq_mgr->resume_work, amdgpu_userq_restore_worker);
 	return 0;
 }
 
 void amdgpu_userq_mgr_fini(struct amdgpu_userq_mgr *userq_mgr)
 {
-	struct amdgpu_device *adev = userq_mgr->adev;
 	struct amdgpu_usermode_queue *queue;
-	struct amdgpu_userq_mgr *uqm, *tmp;
-	uint32_t queue_id;
+	unsigned long queue_id;
 
 	cancel_delayed_work_sync(&userq_mgr->resume_work);
 
-	mutex_lock(&adev->userq_mutex);
 	mutex_lock(&userq_mgr->userq_mutex);
-	idr_for_each_entry(&userq_mgr->userq_idr, queue, queue_id) {
+	amdgpu_userq_detect_and_reset_queues(userq_mgr);
+	xa_for_each(&userq_mgr->userq_mgr_xa, queue_id, queue) {
 		amdgpu_userq_wait_for_last_fence(userq_mgr, queue);
 		amdgpu_userq_unmap_helper(userq_mgr, queue);
 		amdgpu_userq_cleanup(userq_mgr, queue, queue_id);
 	}
 
-	list_for_each_entry_safe(uqm, tmp, &adev->userq_mgr_list, list) {
-		if (uqm == userq_mgr) {
-			list_del(&uqm->list);
-			break;
-		}
-	}
-	idr_destroy(&userq_mgr->userq_idr);
+	xa_destroy(&userq_mgr->userq_mgr_xa);
 	mutex_unlock(&userq_mgr->userq_mutex);
-	mutex_unlock(&adev->userq_mutex);
 	mutex_destroy(&userq_mgr->userq_mutex);
 }
 
@@ -967,57 +1284,51 @@ int amdgpu_userq_suspend(struct amdgpu_device *adev)
 {
 	u32 ip_mask = amdgpu_userq_get_supported_ip_mask(adev);
 	struct amdgpu_usermode_queue *queue;
-	struct amdgpu_userq_mgr *uqm, *tmp;
-	int queue_id;
-	int ret = 0, r;
+	struct amdgpu_userq_mgr *uqm;
+	unsigned long queue_id;
+	int r;
 
 	if (!ip_mask)
 		return 0;
 
-	mutex_lock(&adev->userq_mutex);
-	list_for_each_entry_safe(uqm, tmp, &adev->userq_mgr_list, list) {
+	xa_for_each(&adev->userq_doorbell_xa, queue_id, queue) {
+		uqm = queue->userq_mgr;
 		cancel_delayed_work_sync(&uqm->resume_work);
-		mutex_lock(&uqm->userq_mutex);
-		idr_for_each_entry(&uqm->userq_idr, queue, queue_id) {
-			if (adev->in_s0ix)
-				r = amdgpu_userq_preempt_helper(uqm, queue);
-			else
-				r = amdgpu_userq_unmap_helper(uqm, queue);
-			if (r)
-				ret = r;
-		}
-		mutex_unlock(&uqm->userq_mutex);
+		guard(mutex)(&uqm->userq_mutex);
+		amdgpu_userq_detect_and_reset_queues(uqm);
+		if (adev->in_s0ix)
+			r = amdgpu_userq_preempt_helper(uqm, queue);
+		else
+			r = amdgpu_userq_unmap_helper(uqm, queue);
+		if (r)
+			return r;
 	}
-	mutex_unlock(&adev->userq_mutex);
-	return ret;
+	return 0;
 }
 
 int amdgpu_userq_resume(struct amdgpu_device *adev)
 {
 	u32 ip_mask = amdgpu_userq_get_supported_ip_mask(adev);
 	struct amdgpu_usermode_queue *queue;
-	struct amdgpu_userq_mgr *uqm, *tmp;
-	int queue_id;
-	int ret = 0, r;
+	struct amdgpu_userq_mgr *uqm;
+	unsigned long queue_id;
+	int r;
 
 	if (!ip_mask)
 		return 0;
 
-	mutex_lock(&adev->userq_mutex);
-	list_for_each_entry_safe(uqm, tmp, &adev->userq_mgr_list, list) {
-		mutex_lock(&uqm->userq_mutex);
-		idr_for_each_entry(&uqm->userq_idr, queue, queue_id) {
-			if (adev->in_s0ix)
-				r = amdgpu_userq_restore_helper(uqm, queue);
-			else
-				r = amdgpu_userq_map_helper(uqm, queue);
-			if (r)
-				ret = r;
-		}
-		mutex_unlock(&uqm->userq_mutex);
+	xa_for_each(&adev->userq_doorbell_xa, queue_id, queue) {
+		uqm = queue->userq_mgr;
+		guard(mutex)(&uqm->userq_mutex);
+		if (adev->in_s0ix)
+			r = amdgpu_userq_restore_helper(uqm, queue);
+		else
+			r = amdgpu_userq_map_helper(uqm, queue);
+		if (r)
+			return r;
 	}
-	mutex_unlock(&adev->userq_mutex);
-	return ret;
+
+	return 0;
 }
 
 int amdgpu_userq_stop_sched_for_enforce_isolation(struct amdgpu_device *adev,
@@ -1025,33 +1336,32 @@ int amdgpu_userq_stop_sched_for_enforce_isolation(struct amdgpu_device *adev,
 {
 	u32 ip_mask = amdgpu_userq_get_supported_ip_mask(adev);
 	struct amdgpu_usermode_queue *queue;
-	struct amdgpu_userq_mgr *uqm, *tmp;
-	int queue_id;
+	struct amdgpu_userq_mgr *uqm;
+	unsigned long queue_id;
 	int ret = 0, r;
 
 	/* only need to stop gfx/compute */
 	if (!(ip_mask & ((1 << AMDGPU_HW_IP_GFX) | (1 << AMDGPU_HW_IP_COMPUTE))))
 		return 0;
 
-	mutex_lock(&adev->userq_mutex);
 	if (adev->userq_halt_for_enforce_isolation)
 		dev_warn(adev->dev, "userq scheduling already stopped!\n");
 	adev->userq_halt_for_enforce_isolation = true;
-	list_for_each_entry_safe(uqm, tmp, &adev->userq_mgr_list, list) {
+	xa_for_each(&adev->userq_doorbell_xa, queue_id, queue) {
+		uqm = queue->userq_mgr;
 		cancel_delayed_work_sync(&uqm->resume_work);
 		mutex_lock(&uqm->userq_mutex);
-		idr_for_each_entry(&uqm->userq_idr, queue, queue_id) {
-			if (((queue->queue_type == AMDGPU_HW_IP_GFX) ||
-			     (queue->queue_type == AMDGPU_HW_IP_COMPUTE)) &&
-			    (queue->xcp_id == idx)) {
-				r = amdgpu_userq_preempt_helper(uqm, queue);
-				if (r)
-					ret = r;
-			}
+		if (((queue->queue_type == AMDGPU_HW_IP_GFX) ||
+		     (queue->queue_type == AMDGPU_HW_IP_COMPUTE)) &&
+		    (queue->xcp_id == idx)) {
+			amdgpu_userq_detect_and_reset_queues(uqm);
+			r = amdgpu_userq_preempt_helper(uqm, queue);
+			if (r)
+				ret = r;
 		}
 		mutex_unlock(&uqm->userq_mutex);
 	}
-	mutex_unlock(&adev->userq_mutex);
+
 	return ret;
 }
 
@@ -1060,21 +1370,20 @@ int amdgpu_userq_start_sched_for_enforce_isolation(struct amdgpu_device *adev,
 {
 	u32 ip_mask = amdgpu_userq_get_supported_ip_mask(adev);
 	struct amdgpu_usermode_queue *queue;
-	struct amdgpu_userq_mgr *uqm, *tmp;
-	int queue_id;
+	struct amdgpu_userq_mgr *uqm;
+	unsigned long queue_id;
 	int ret = 0, r;
 
 	/* only need to stop gfx/compute */
 	if (!(ip_mask & ((1 << AMDGPU_HW_IP_GFX) | (1 << AMDGPU_HW_IP_COMPUTE))))
 		return 0;
 
-	mutex_lock(&adev->userq_mutex);
 	if (!adev->userq_halt_for_enforce_isolation)
 		dev_warn(adev->dev, "userq scheduling already started!\n");
 	adev->userq_halt_for_enforce_isolation = false;
-	list_for_each_entry_safe(uqm, tmp, &adev->userq_mgr_list, list) {
+	xa_for_each(&adev->userq_doorbell_xa, queue_id, queue) {
+		uqm = queue->userq_mgr;
 		mutex_lock(&uqm->userq_mutex);
-		idr_for_each_entry(&uqm->userq_idr, queue, queue_id) {
 			if (((queue->queue_type == AMDGPU_HW_IP_GFX) ||
 			     (queue->queue_type == AMDGPU_HW_IP_COMPUTE)) &&
 			    (queue->xcp_id == idx)) {
@@ -1082,9 +1391,92 @@ int amdgpu_userq_start_sched_for_enforce_isolation(struct amdgpu_device *adev,
 				if (r)
 					ret = r;
 			}
-		}
 		mutex_unlock(&uqm->userq_mutex);
 	}
-	mutex_unlock(&adev->userq_mutex);
+
 	return ret;
 }
+
+int amdgpu_userq_gem_va_unmap_validate(struct amdgpu_device *adev,
+				       struct amdgpu_bo_va_mapping *mapping,
+				       uint64_t saddr)
+{
+	u32 ip_mask = amdgpu_userq_get_supported_ip_mask(adev);
+	struct amdgpu_bo_va *bo_va = mapping->bo_va;
+	struct dma_resv *resv = bo_va->base.bo->tbo.base.resv;
+	int ret = 0;
+
+	if (!ip_mask)
+		return 0;
+
+	dev_warn_once(adev->dev, "now unmapping a vital queue va:%llx\n", saddr);
+	/**
+	 * The userq VA mapping reservation should include the eviction fence,
+	 * if the eviction fence can't signal successfully during unmapping,
+	 * then driver will warn to flag this improper unmap of the userq VA.
+	 * Note: The eviction fence may be attached to different BOs, and this
+	 * unmap is only for one kind of userq VAs, so at this point suppose
+	 * the eviction fence is always unsignaled.
+	 */
+	if (!dma_resv_test_signaled(resv, DMA_RESV_USAGE_BOOKKEEP)) {
+		ret = dma_resv_wait_timeout(resv, DMA_RESV_USAGE_BOOKKEEP, true,
+					    MAX_SCHEDULE_TIMEOUT);
+		if (ret <= 0)
+			return -EBUSY;
+	}
+
+	return 0;
+}
+
+void amdgpu_userq_pre_reset(struct amdgpu_device *adev)
+{
+	const struct amdgpu_userq_funcs *userq_funcs;
+	struct amdgpu_usermode_queue *queue;
+	struct amdgpu_userq_mgr *uqm;
+	unsigned long queue_id;
+
+	xa_for_each(&adev->userq_doorbell_xa, queue_id, queue) {
+		uqm = queue->userq_mgr;
+		cancel_delayed_work_sync(&uqm->resume_work);
+		if (queue->state == AMDGPU_USERQ_STATE_MAPPED) {
+			amdgpu_userq_wait_for_last_fence(uqm, queue);
+			userq_funcs = adev->userq_funcs[queue->queue_type];
+			userq_funcs->unmap(uqm, queue);
+			/* just mark all queues as hung at this point.
+			 * if unmap succeeds, we could map again
+			 * in amdgpu_userq_post_reset() if vram is not lost
+			 */
+			queue->state = AMDGPU_USERQ_STATE_HUNG;
+			amdgpu_userq_fence_driver_force_completion(queue);
+		}
+	}
+}
+
+int amdgpu_userq_post_reset(struct amdgpu_device *adev, bool vram_lost)
+{
+	/* if any queue state is AMDGPU_USERQ_STATE_UNMAPPED
+	 * at this point, we should be able to map it again
+	 * and continue if vram is not lost.
+	 */
+	struct amdgpu_userq_mgr *uqm;
+	struct amdgpu_usermode_queue *queue;
+	const struct amdgpu_userq_funcs *userq_funcs;
+	unsigned long queue_id;
+	int r = 0;
+
+	xa_for_each(&adev->userq_doorbell_xa, queue_id, queue) {
+		uqm = queue->userq_mgr;
+		if (queue->state == AMDGPU_USERQ_STATE_HUNG && !vram_lost) {
+			userq_funcs = adev->userq_funcs[queue->queue_type];
+			/* Re-map queue */
+			r = userq_funcs->map(uqm, queue);
+			if (r) {
+				dev_err(adev->dev, "Failed to remap queue %ld\n", queue_id);
+				continue;
+			}
+			queue->state = AMDGPU_USERQ_STATE_MAPPED;
+		}
+	}
+
+	return r;
+}