Merge tag 'amd-drm-fixes-7.1-2026-05-06' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-7.1-2026-05-06:

amdgpu:
- GFX9 fixes
- Hawaii SMU fixes
- SDMA4 fix
- GART fix
- Userq fixes

amdkfd:
- GPUVM TLB flush fix
- Hotplug fix

radeon:
- Hawaii SMU fixes

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patch.msgid.link/20260506154631.1733034-1-alexander.deucher@amd.com

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

@@ -3149,11 +3149,7 @@ static int __init amdgpu_init(void)
 
 	r = amdgpu_sync_init();
 	if (r)
-		goto error_sync;
-
-	r = amdgpu_userq_fence_slab_init();
-	if (r)
-		goto error_fence;
+		return r;
 
 	amdgpu_register_atpx_handler();
 	amdgpu_acpi_detect();
@@ -3161,7 +3157,7 @@ static int __init amdgpu_init(void)
 	/* Ignore KFD init failures when CONFIG_HSA_AMD is not set. */
 	r = amdgpu_amdkfd_init();
 	if (r && r != -ENOENT)
-		goto error_fence;
+		goto error_fini_sync;
 
 	if (amdgpu_pp_feature_mask & PP_OVERDRIVE_MASK) {
 		add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
@@ -3172,10 +3168,8 @@ static int __init amdgpu_init(void)
 	/* let modprobe override vga console setting */
 	return pci_register_driver(&amdgpu_kms_pci_driver);
 
-error_fence:
+error_fini_sync:
 	amdgpu_sync_fini();
-
-error_sync:
 	return r;
 }
 
@@ -3186,7 +3180,6 @@ static void __exit amdgpu_exit(void)
 	amdgpu_unregister_atpx_handler();
 	amdgpu_acpi_release();
 	amdgpu_sync_fini();
-	amdgpu_userq_fence_slab_fini();
 	mmu_notifier_synchronize();
 	amdgpu_xcp_drv_release();
 }

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

@@ -262,12 +262,19 @@ void amdgpu_gart_table_ram_free(struct amdgpu_device *adev)
  */
 int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev)
 {
+	int r;
+
 	if (adev->gart.bo != NULL)
 		return 0;
 
-	return amdgpu_bo_create_kernel(adev,  adev->gart.table_size, PAGE_SIZE,
-				       AMDGPU_GEM_DOMAIN_VRAM, &adev->gart.bo,
-				       NULL, (void *)&adev->gart.ptr);
+	r = amdgpu_bo_create_kernel(adev,  adev->gart.table_size, PAGE_SIZE,
+				    AMDGPU_GEM_DOMAIN_VRAM, &adev->gart.bo,
+				    NULL, (void *)&adev->gart.ptr);
+	if (r)
+		return r;
+
+	memset_io(adev->gart.ptr, adev->gart.gart_pte_flags, adev->gart.table_size);
+	return 0;
 }
 
 /**

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

@@ -32,29 +32,9 @@
 #include "amdgpu.h"
 #include "amdgpu_userq_fence.h"
 
-static const struct dma_fence_ops amdgpu_userq_fence_ops;
-static struct kmem_cache *amdgpu_userq_fence_slab;
-
 #define AMDGPU_USERQ_MAX_HANDLES	(1U << 16)
 
-int amdgpu_userq_fence_slab_init(void)
-{
-	amdgpu_userq_fence_slab = kmem_cache_create("amdgpu_userq_fence",
-						    sizeof(struct amdgpu_userq_fence),
-						    0,
-						    SLAB_HWCACHE_ALIGN,
-						    NULL);
-	if (!amdgpu_userq_fence_slab)
-		return -ENOMEM;
-
-	return 0;
-}
-
-void amdgpu_userq_fence_slab_fini(void)
-{
-	rcu_barrier();
-	kmem_cache_destroy(amdgpu_userq_fence_slab);
-}
+static const struct dma_fence_ops amdgpu_userq_fence_ops;
 
 static inline struct amdgpu_userq_fence *to_amdgpu_userq_fence(struct dma_fence *f)
 {
@@ -231,7 +211,7 @@ void amdgpu_userq_fence_driver_put(struct amdgpu_userq_fence_driver *fence_drv)
 
 static int amdgpu_userq_fence_alloc(struct amdgpu_userq_fence **userq_fence)
 {
-	*userq_fence = kmem_cache_alloc(amdgpu_userq_fence_slab, GFP_ATOMIC);
+	*userq_fence = kmalloc(sizeof(**userq_fence), GFP_KERNEL);
 	return *userq_fence ? 0 : -ENOMEM;
 }
 
@@ -342,7 +322,7 @@ static void amdgpu_userq_fence_free(struct rcu_head *rcu)
 	amdgpu_userq_fence_driver_put(fence_drv);
 
 	kvfree(userq_fence->fence_drv_array);
-	kmem_cache_free(amdgpu_userq_fence_slab, userq_fence);
+	kfree(userq_fence);
 }
 
 static void amdgpu_userq_fence_release(struct dma_fence *f)
@@ -545,7 +525,7 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data,
 	r = amdgpu_userq_fence_create(queue, userq_fence, wptr, &fence);
 	if (r) {
 		mutex_unlock(&userq_mgr->userq_mutex);
-		kmem_cache_free(amdgpu_userq_fence_slab, userq_fence);
+		kfree(userq_fence);
 		goto put_gobj_write;
 	}
 

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

@@ -58,9 +58,6 @@ struct amdgpu_userq_fence_driver {
 	char timeline_name[TASK_COMM_LEN];
 };
 
-int amdgpu_userq_fence_slab_init(void);
-void amdgpu_userq_fence_slab_fini(void);
-
 void amdgpu_userq_fence_driver_get(struct amdgpu_userq_fence_driver *fence_drv);
 void amdgpu_userq_fence_driver_put(struct amdgpu_userq_fence_driver *fence_drv);
 int amdgpu_userq_fence_driver_alloc(struct amdgpu_device *adev,

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -5660,9 +5660,6 @@ static void gfx_v9_0_ring_emit_fence_kiq(struct amdgpu_ring *ring, u64 addr,
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	/* we only allocate 32bit for each seq wb address */
-	BUG_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
-
 	/* write fence seq to the "addr" */
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
 	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |

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

@@ -30,34 +30,6 @@
 #define AMDGPU_USERQ_PROC_CTX_SZ PAGE_SIZE
 #define AMDGPU_USERQ_GANG_CTX_SZ PAGE_SIZE
 
-static int
-mes_userq_map_gtt_bo_to_gart(struct amdgpu_bo *bo)
-{
-	int ret;
-
-	ret = amdgpu_bo_reserve(bo, true);
-	if (ret) {
-		DRM_ERROR("Failed to reserve bo. ret %d\n", ret);
-		goto err_reserve_bo_failed;
-	}
-
-	ret = amdgpu_ttm_alloc_gart(&bo->tbo);
-	if (ret) {
-		DRM_ERROR("Failed to bind bo to GART. ret %d\n", ret);
-		goto err_map_bo_gart_failed;
-	}
-
-	amdgpu_bo_unreserve(bo);
-	bo = amdgpu_bo_ref(bo);
-
-	return 0;
-
-err_map_bo_gart_failed:
-	amdgpu_bo_unreserve(bo);
-err_reserve_bo_failed:
-	return ret;
-}
-
 static int
 mes_userq_create_wptr_mapping(struct amdgpu_device *adev,
 			      struct amdgpu_userq_mgr *uq_mgr,
@@ -65,55 +37,62 @@ mes_userq_create_wptr_mapping(struct amdgpu_device *adev,
 			      uint64_t wptr)
 {
 	struct amdgpu_bo_va_mapping *wptr_mapping;
-	struct amdgpu_vm *wptr_vm;
 	struct amdgpu_userq_obj *wptr_obj = &queue->wptr_obj;
+	struct amdgpu_bo *obj;
+	struct amdgpu_vm *vm = queue->vm;
+	struct drm_exec exec;
 	int ret;
 
-	wptr_vm = queue->vm;
-	ret = amdgpu_bo_reserve(wptr_vm->root.bo, false);
-	if (ret)
-		return ret;
-
 	wptr &= AMDGPU_GMC_HOLE_MASK;
-	wptr_mapping = amdgpu_vm_bo_lookup_mapping(wptr_vm, wptr >> PAGE_SHIFT);
-	amdgpu_bo_unreserve(wptr_vm->root.bo);
-	if (!wptr_mapping) {
-		DRM_ERROR("Failed to lookup wptr bo\n");
-		return -EINVAL;
+
+	drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 2);
+	drm_exec_until_all_locked(&exec) {
+		ret = amdgpu_vm_lock_pd(vm, &exec, 1);
+		drm_exec_retry_on_contention(&exec);
+		if (unlikely(ret))
+			goto fail_lock;
+
+		wptr_mapping = amdgpu_vm_bo_lookup_mapping(vm, wptr >> PAGE_SHIFT);
+		if (!wptr_mapping) {
+			ret = -EINVAL;
+			goto fail_lock;
+		}
+
+		obj = wptr_mapping->bo_va->base.bo;
+		ret = drm_exec_lock_obj(&exec, &obj->tbo.base);
+		drm_exec_retry_on_contention(&exec);
+		if (unlikely(ret))
+			goto fail_lock;
 	}
 
-	wptr_obj->obj = wptr_mapping->bo_va->base.bo;
+	wptr_obj->obj = amdgpu_bo_ref(wptr_mapping->bo_va->base.bo);
 	if (wptr_obj->obj->tbo.base.size > PAGE_SIZE) {
-		DRM_ERROR("Requested GART mapping for wptr bo larger than one page\n");
-		return -EINVAL;
-	}
-
-	ret = mes_userq_map_gtt_bo_to_gart(wptr_obj->obj);
-	if (ret) {
-		DRM_ERROR("Failed to map wptr bo to GART\n");
-		return ret;
-	}
-
-	ret = amdgpu_bo_reserve(wptr_obj->obj, true);
-	if (ret) {
-		DRM_ERROR("Failed to reserve wptr bo\n");
-		return ret;
+		ret = -EINVAL;
+		goto fail_map;
 	}
 
 	/* TODO use eviction fence instead of pinning. */
 	ret = amdgpu_bo_pin(wptr_obj->obj, AMDGPU_GEM_DOMAIN_GTT);
 	if (ret) {
-		drm_file_err(uq_mgr->file, "[Usermode queues] Failed to pin wptr bo\n");
-		goto unresv_bo;
+		DRM_ERROR("Failed to pin wptr bo. ret %d\n", ret);
+		goto fail_map;
+	}
+
+	ret = amdgpu_ttm_alloc_gart(&wptr_obj->obj->tbo);
+	if (ret) {
+		DRM_ERROR("Failed to bind bo to GART. ret %d\n", ret);
+		goto fail_map;
 	}
 
 	queue->wptr_obj.gpu_addr = amdgpu_bo_gpu_offset(wptr_obj->obj);
-	amdgpu_bo_unreserve(wptr_obj->obj);
 
+	drm_exec_fini(&exec);
 	return 0;
 
-unresv_bo:
-	amdgpu_bo_unreserve(wptr_obj->obj);
+fail_map:
+	amdgpu_bo_unref(&wptr_obj->obj);
+fail_lock:
+	drm_exec_fini(&exec);
 	return ret;
 
 }

drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c

@@ -889,7 +889,7 @@ static void sdma_v4_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se
 	/* write the fence */
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_FENCE));
 	/* zero in first two bits */
-	BUG_ON(addr & 0x3);
+	WARN_ON(addr & 0x3);
 	amdgpu_ring_write(ring, lower_32_bits(addr));
 	amdgpu_ring_write(ring, upper_32_bits(addr));
 	amdgpu_ring_write(ring, lower_32_bits(seq));
@@ -899,7 +899,7 @@ static void sdma_v4_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se
 		addr += 4;
 		amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_FENCE));
 		/* zero in first two bits */
-		BUG_ON(addr & 0x3);
+		WARN_ON(addr & 0x3);
 		amdgpu_ring_write(ring, lower_32_bits(addr));
 		amdgpu_ring_write(ring, upper_32_bits(addr));
 		amdgpu_ring_write(ring, upper_32_bits(seq));

drivers/gpu/drm/amd/amdkfd/kfd_chardev.c

@@ -1360,7 +1360,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 		peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]);
 		if (WARN_ON_ONCE(!peer_pdd))
 			continue;
-		kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY);
+		kfd_flush_tlb(peer_pdd);
 	}
 	kfree(devices_arr);
 
@@ -1455,7 +1455,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 		if (WARN_ON_ONCE(!peer_pdd))
 			continue;
 		if (flush_tlb)
-			kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT);
+			kfd_flush_tlb(peer_pdd);
 
 		/* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */
 		err = amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv);

drivers/gpu/drm/amd/amdkfd/kfd_device.c

@@ -1737,37 +1737,6 @@ bool kgd2kfd_vmfault_fast_path(struct amdgpu_device *adev, struct amdgpu_iv_entr
 	return false;
 }
 
-/* check if there is kfd process still uses adev */
-static bool kgd2kfd_check_device_idle(struct amdgpu_device *adev)
-{
-	struct kfd_process *p;
-	struct hlist_node *p_temp;
-	unsigned int temp;
-	struct kfd_node *dev;
-
-	mutex_lock(&kfd_processes_mutex);
-
-	if (hash_empty(kfd_processes_table)) {
-		mutex_unlock(&kfd_processes_mutex);
-		return true;
-	}
-
-	/* check if there is device still use adev */
-	hash_for_each_safe(kfd_processes_table, temp, p_temp, p, kfd_processes) {
-		for (int i = 0; i < p->n_pdds; i++) {
-			dev = p->pdds[i]->dev;
-			if (dev->adev == adev) {
-				mutex_unlock(&kfd_processes_mutex);
-				return false;
-			}
-		}
-	}
-
-	mutex_unlock(&kfd_processes_mutex);
-
-	return true;
-}
-
 /** kgd2kfd_teardown_processes - gracefully tear down existing
  *  kfd processes that use adev
  *
@@ -1800,7 +1769,7 @@ void kgd2kfd_teardown_processes(struct amdgpu_device *adev)
 	mutex_unlock(&kfd_processes_mutex);
 
 	/* wait all kfd processes use adev terminate */
-	while (!kgd2kfd_check_device_idle(adev))
+	while (!!atomic_read(&adev->kfd.dev->kfd_processes_count))
 		cond_resched();
 }
 

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c

@@ -572,7 +572,7 @@ static int allocate_vmid(struct device_queue_manager *dqm,
 			qpd->vmid,
 			qpd->page_table_base);
 	/* invalidate the VM context after pasid and vmid mapping is set up */
-	kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY);
+	kfd_flush_tlb(qpd_to_pdd(qpd));
 
 	if (dqm->dev->kfd2kgd->set_scratch_backing_va)
 		dqm->dev->kfd2kgd->set_scratch_backing_va(dqm->dev->adev,
@@ -610,7 +610,7 @@ static void deallocate_vmid(struct device_queue_manager *dqm,
 		if (flush_texture_cache_nocpsch(q->device, qpd))
 			dev_err(dev, "Failed to flush TC\n");
 
-	kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY);
+	kfd_flush_tlb(qpd_to_pdd(qpd));
 
 	/* Release the vmid mapping */
 	set_pasid_vmid_mapping(dqm, 0, qpd->vmid);
@@ -1284,7 +1284,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 				dqm->dev->adev,
 				qpd->vmid,
 				qpd->page_table_base);
-		kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY);
+		kfd_flush_tlb(pdd);
 	}
 
 	/* Take a safe reference to the mm_struct, which may otherwise

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

@@ -1554,13 +1554,13 @@ void kfd_signal_reset_event(struct kfd_node *dev);
 void kfd_signal_poison_consumed_event(struct kfd_node *dev, u32 pasid);
 void kfd_signal_process_terminate_event(struct kfd_process *p);
 
-static inline void kfd_flush_tlb(struct kfd_process_device *pdd,
-				 enum TLB_FLUSH_TYPE type)
+static inline void kfd_flush_tlb(struct kfd_process_device *pdd)
 {
 	struct amdgpu_device *adev = pdd->dev->adev;
 	struct amdgpu_vm *vm = drm_priv_to_vm(pdd->drm_priv);
 
-	amdgpu_vm_flush_compute_tlb(adev, vm, type, pdd->dev->xcc_mask);
+	amdgpu_vm_flush_compute_tlb(adev, vm, TLB_FLUSH_HEAVYWEIGHT,
+				    pdd->dev->xcc_mask);
 }
 
 static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev)

drivers/gpu/drm/amd/amdkfd/kfd_svm.c

@@ -1424,7 +1424,7 @@ svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start,
 			if (r)
 				break;
 		}
-		kfd_flush_tlb(pdd, TLB_FLUSH_HEAVYWEIGHT);
+		kfd_flush_tlb(pdd);
 	}
 
 	return r;
@@ -1571,7 +1571,7 @@ svm_range_map_to_gpus(struct svm_range *prange, unsigned long offset,
 			}
 		}
 
-		kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY);
+		kfd_flush_tlb(pdd);
 	}
 
 	return r;

drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c

@@ -1333,12 +1333,13 @@ static int ci_populate_all_memory_levels(struct pp_hwmgr *hwmgr)
 
 	dev_id = adev->pdev->device;
 
-	if ((dpm_table->mclk_table.count >= 2)
-		&& ((dev_id == 0x67B0) ||  (dev_id == 0x67B1))) {
-		smu_data->smc_state_table.MemoryLevel[1].MinVddci =
-				smu_data->smc_state_table.MemoryLevel[0].MinVddci;
-		smu_data->smc_state_table.MemoryLevel[1].MinMvdd =
-				smu_data->smc_state_table.MemoryLevel[0].MinMvdd;
+	if ((dpm_table->mclk_table.count >= 2) &&
+	    ((dev_id == 0x67B0) ||  (dev_id == 0x67B1)) &&
+	    (adev->pdev->revision == 0)) {
+		smu_data->smc_state_table.MemoryLevel[1].MinVddc =
+				smu_data->smc_state_table.MemoryLevel[0].MinVddc;
+		smu_data->smc_state_table.MemoryLevel[1].MinVddcPhases =
+				smu_data->smc_state_table.MemoryLevel[0].MinVddcPhases;
 	}
 	smu_data->smc_state_table.MemoryLevel[0].ActivityLevel = 0x1F;
 	CONVERT_FROM_HOST_TO_SMC_US(smu_data->smc_state_table.MemoryLevel[0].ActivityLevel);

drivers/gpu/drm/radeon/ci_dpm.c

@@ -2461,7 +2461,8 @@ static void ci_register_patching_mc_arb(struct radeon_device *rdev,
 
 	if (patch &&
 	    ((rdev->pdev->device == 0x67B0) ||
-	     (rdev->pdev->device == 0x67B1))) {
+	     (rdev->pdev->device == 0x67B1)) &&
+	    (rdev->pdev->revision == 0)) {
 		if ((memory_clock > 100000) && (memory_clock <= 125000)) {
 			tmp2 = (((0x31 * engine_clock) / 125000) - 1) & 0xff;
 			*dram_timimg2 &= ~0x00ff0000;
@@ -3304,7 +3305,8 @@ static int ci_populate_all_memory_levels(struct radeon_device *rdev)
 	pi->smc_state_table.MemoryLevel[0].EnabledForActivity = 1;
 
 	if ((dpm_table->mclk_table.count >= 2) &&
-	    ((rdev->pdev->device == 0x67B0) || (rdev->pdev->device == 0x67B1))) {
+	    ((rdev->pdev->device == 0x67B0) || (rdev->pdev->device == 0x67B1)) &&
+	    (rdev->pdev->revision == 0)) {
 		pi->smc_state_table.MemoryLevel[1].MinVddc =
 			pi->smc_state_table.MemoryLevel[0].MinVddc;
 		pi->smc_state_table.MemoryLevel[1].MinVddcPhases =
@@ -4493,7 +4495,8 @@ static int ci_register_patching_mc_seq(struct radeon_device *rdev,
 
 	if (patch &&
 	    ((rdev->pdev->device == 0x67B0) ||
-	     (rdev->pdev->device == 0x67B1))) {
+	     (rdev->pdev->device == 0x67B1)) &&
+	    (rdev->pdev->revision == 0)) {
 		for (i = 0; i < table->last; i++) {
 			if (table->last >= SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;