Merge tag 'amd-drm-next-6.19-2025-11-07' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.19-2025-11-07:

amdgpu:
- Misc fixes
- HMM cleanup
- HDP flush rework
- RAS updates
- SMU 13.x updates
- SI DPM cleanup
- Suspend rework
- UQ reset support
- Replay/PSR fixes
- HDCP updates
- DC PMO fixes
- DC pstate fixes
- DCN4 fixes
- GPUVM fixes
- SMU 13 parition metrics
- Fix possible fence leak in job cleanup
- Hibernation fix
- MST fix

amdkfd:
- HMM cleanup
- Process cleanup fix

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patch.msgid.link/20251107145938.26669-1-alexander.deucher@amd.com

Author: airlied

MAINTAINERS

@@ -1080,7 +1080,7 @@ M:	Austin Zheng <austin.zheng@amd.com>
 M:	Jun Lei <jun.lei@amd.com>
 S:	Supported
 F:	drivers/gpu/drm/amd/display/dc/dml/
-F:	drivers/gpu/drm/amd/display/dc/dml2/
+F:	drivers/gpu/drm/amd/display/dc/dml2_0/
 
 AMD FAM15H PROCESSOR POWER MONITORING DRIVER
 M:	Huang Rui <ray.huang@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -1316,6 +1316,7 @@ struct amdgpu_device {
 	bool                            apu_prefer_gtt;
 
 	bool                            userq_halt_for_enforce_isolation;
+	struct work_struct              userq_reset_work;
 	struct amdgpu_uid *uid_info;
 
 	/* KFD
@@ -1539,11 +1540,6 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 #define amdgpu_asic_read_bios_from_rom(adev, b, l) (adev)->asic_funcs->read_bios_from_rom((adev), (b), (l))
 #define amdgpu_asic_read_register(adev, se, sh, offset, v)((adev)->asic_funcs->read_register((adev), (se), (sh), (offset), (v)))
 #define amdgpu_asic_get_config_memsize(adev) (adev)->asic_funcs->get_config_memsize((adev))
-#define amdgpu_asic_flush_hdp(adev, r) \
-	((adev)->asic_funcs->flush_hdp ? (adev)->asic_funcs->flush_hdp((adev), (r)) : (adev)->hdp.funcs->flush_hdp((adev), (r)))
-#define amdgpu_asic_invalidate_hdp(adev, r) \
-	((adev)->asic_funcs->invalidate_hdp ? (adev)->asic_funcs->invalidate_hdp((adev), (r)) : \
-	 ((adev)->hdp.funcs->invalidate_hdp ? (adev)->hdp.funcs->invalidate_hdp((adev), (r)) : (void)0))
 #define amdgpu_asic_need_full_reset(adev) (adev)->asic_funcs->need_full_reset((adev))
 #define amdgpu_asic_init_doorbell_index(adev) (adev)->asic_funcs->init_doorbell_index((adev))
 #define amdgpu_asic_get_pcie_usage(adev, cnt0, cnt1) ((adev)->asic_funcs->get_pcie_usage((adev), (cnt0), (cnt1)))

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

@@ -1274,6 +1274,10 @@ static int unmap_bo_from_gpuvm(struct kgd_mem *mem,
 
 	(void)amdgpu_vm_bo_unmap(adev, bo_va, entry->va);
 
+	/* VM entity stopped if process killed, don't clear freed pt bo */
+	if (!amdgpu_vm_ready(vm))
+		return 0;
+
 	(void)amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update);
 
 	(void)amdgpu_sync_fence(sync, bo_va->last_pt_update, GFP_KERNEL);

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,
@@ -2494,6 +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)
@@ -3784,7 +3790,7 @@ 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);
@@ -3807,10 +3813,23 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
 
 		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;
 }
 
 /**
@@ -3826,7 +3845,7 @@ 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);
@@ -3889,7 +3908,7 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 
 		r = amdgpu_ip_block_suspend(&adev->ip_blocks[i]);
 		if (r)
-			return r;
+			goto unwind;
 
 		/* handle putting the SMC in the appropriate state */
 		if (!amdgpu_sriov_vf(adev)) {
@@ -3899,13 +3918,40 @@ 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;
 }
 
 /**
@@ -4607,6 +4653,7 @@ 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;
@@ -5229,7 +5276,7 @@ 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;
@@ -5245,8 +5292,9 @@ 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));
@@ -5257,33 +5305,79 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients)
 
 	r = amdgpu_device_ip_suspend_phase1(adev);
 	if (r)
-		return r;
+		goto unwind_smartshift;
 
 	amdgpu_amdkfd_suspend(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm);
 	r = amdgpu_userq_suspend(adev);
 	if (r)
-		return 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);
 
 	r = amdgpu_device_ip_suspend_phase2(adev);
 	if (r)
-		return r;
+		goto unwind_evict;
 
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_release_full_gpu(adev, false);
 
-	r = amdgpu_dpm_notify_rlc_state(adev, false);
-	if (r)
+	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;
+	}
 
-	return 0;
+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)
@@ -5989,6 +6083,10 @@ int amdgpu_device_reinit_after_reset(struct amdgpu_reset_context *reset_context)
 				if (r)
 					goto out;
 
+				r = amdgpu_userq_post_reset(tmp_adev, vram_lost);
+				if (r)
+					goto out;
+
 				drm_client_dev_resume(adev_to_drm(tmp_adev));
 
 				/*
@@ -6211,6 +6309,7 @@ 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);
@@ -6331,6 +6430,8 @@ static void amdgpu_device_halt_activities(struct amdgpu_device *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];
 
@@ -6560,6 +6661,9 @@ 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);
 
@@ -6590,6 +6694,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	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);
@@ -7327,7 +7432,7 @@ void amdgpu_device_flush_hdp(struct amdgpu_device *adev,
 			return;
 	}
 
-	amdgpu_asic_flush_hdp(adev, ring);
+	amdgpu_hdp_flush(adev, ring);
 }
 
 void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev,
@@ -7340,7 +7445,7 @@ 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)

drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c

@@ -81,13 +81,20 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
 	struct drm_gem_object *obj = dmabuf->priv;
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+	int r;
 
 	if (!amdgpu_dmabuf_is_xgmi_accessible(attach_adev, bo) &&
 	    pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
 		attach->peer2peer = false;
 
+	r = dma_resv_lock(bo->tbo.base.resv, NULL);
+	if (r)
+		return r;
+
 	amdgpu_vm_bo_update_shared(bo);
 
+	dma_resv_unlock(bo->tbo.base.resv);
+
 	return 0;
 }
 

drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c

@@ -2625,9 +2625,14 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
+	int r;
 
-	if (amdgpu_acpi_should_gpu_reset(adev))
-		return amdgpu_asic_reset(adev);
+	if (amdgpu_acpi_should_gpu_reset(adev)) {
+		amdgpu_device_lock_reset_domain(adev->reset_domain);
+		r = amdgpu_asic_reset(adev);
+		amdgpu_device_unlock_reset_domain(adev->reset_domain);
+		return r;
+	}
 
 	return 0;
 }

drivers/gpu/drm/amd/amdgpu/amdgpu_hdp.c

@@ -66,3 +66,19 @@ void amdgpu_hdp_generic_flush(struct amdgpu_device *adev,
 				      0);
 	}
 }
+
+void amdgpu_hdp_invalidate(struct amdgpu_device *adev, struct amdgpu_ring *ring)
+{
+	if (adev->asic_funcs && adev->asic_funcs->invalidate_hdp)
+		adev->asic_funcs->invalidate_hdp(adev, ring);
+	else if (adev->hdp.funcs && adev->hdp.funcs->invalidate_hdp)
+		adev->hdp.funcs->invalidate_hdp(adev, ring);
+}
+
+void amdgpu_hdp_flush(struct amdgpu_device *adev, struct amdgpu_ring *ring)
+{
+	if (adev->asic_funcs && adev->asic_funcs->flush_hdp)
+		adev->asic_funcs->flush_hdp(adev, ring);
+	else if (adev->hdp.funcs && adev->hdp.funcs->flush_hdp)
+		adev->hdp.funcs->flush_hdp(adev, ring);
+}