sync with OpenBSD -current

sys/dev/pci/drm/amd/amdgpu/aldebaran.c

@@ -333,6 +333,7 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 {
 	struct list_head *reset_device_list = reset_context->reset_device_list;
 	struct amdgpu_device *tmp_adev = NULL;
+	struct amdgpu_ras *con;
 	int r;
 
 	if (reset_device_list == NULL)
@@ -358,7 +359,30 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 		 */
 		amdgpu_register_gpu_instance(tmp_adev);
 
-		/* Resume RAS */
+		/* Resume RAS, ecc_irq */
+		con = amdgpu_ras_get_context(tmp_adev);
+		if (!amdgpu_sriov_vf(tmp_adev) && con) {
+			if (tmp_adev->sdma.ras &&
+				tmp_adev->sdma.ras->ras_block.ras_late_init) {
+				r = tmp_adev->sdma.ras->ras_block.ras_late_init(tmp_adev,
+						&tmp_adev->sdma.ras->ras_block.ras_comm);
+				if (r) {
+					dev_err(tmp_adev->dev, "SDMA failed to execute ras_late_init! ret:%d\n", r);
+					goto end;
+				}
+			}
+
+			if (tmp_adev->gfx.ras &&
+				tmp_adev->gfx.ras->ras_block.ras_late_init) {
+				r = tmp_adev->gfx.ras->ras_block.ras_late_init(tmp_adev,
+						&tmp_adev->gfx.ras->ras_block.ras_comm);
+				if (r) {
+					dev_err(tmp_adev->dev, "GFX failed to execute ras_late_init! ret:%d\n", r);
+					goto end;
+				}
+			}
+		}
+
 		amdgpu_ras_resume(tmp_adev);
 
 		/* Update PSP FW topology after reset */

sys/dev/pci/drm/amd/amdgpu/amdgpu_amdkfd_fence.c

@@ -90,7 +90,7 @@ struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f)
 		return NULL;
 
 	fence = container_of(f, struct amdgpu_amdkfd_fence, base);
-	if (fence && f->ops == &amdkfd_fence_ops)
+	if (f->ops == &amdkfd_fence_ops)
 		return fence;
 
 	return NULL;

sys/dev/pci/drm/amd/amdgpu/amdgpu_device.c

@@ -1224,6 +1224,7 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev)
 				return true;
 
 			fw_ver = *((uint32_t *)adev->pm.fw->data + 69);
+			release_firmware(adev->pm.fw);
 			if (fw_ver < 0x00160e00)
 				return true;
 		}

sys/dev/pci/drm/amd/amdgpu/amdgpu_gmc.c

@@ -885,21 +885,28 @@ int amdgpu_gmc_vram_checking(struct amdgpu_device *adev)
 	 * seconds, so here, we just pick up three parts for emulation.
 	 */
 	ret = memcmp(vram_ptr, cptr, 10);
-	if (ret)
-		return ret;
+	if (ret) {
+		ret = -EIO;
+		goto release_buffer;
+	}
 
 	ret = memcmp(vram_ptr + (size / 2), cptr, 10);
-	if (ret)
-		return ret;
+	if (ret) {
+		ret = -EIO;
+		goto release_buffer;
+	}
 
 	ret = memcmp(vram_ptr + size - 10, cptr, 10);
-	if (ret)
-		return ret;
+	if (ret) {
+		ret = -EIO;
+		goto release_buffer;
+	}
 
+release_buffer:
 	amdgpu_bo_free_kernel(&vram_bo, &vram_gpu,
 			&vram_ptr);
 
-	return 0;
+	return ret;
 }
 
 static ssize_t current_memory_partition_show(

sys/dev/pci/drm/amd/amdgpu/amdgpu_mes.c

@@ -885,6 +885,11 @@ int amdgpu_mes_set_shader_debugger(struct amdgpu_device *adev,
 	op_input.op = MES_MISC_OP_SET_SHADER_DEBUGGER;
 	op_input.set_shader_debugger.process_context_addr = process_context_addr;
 	op_input.set_shader_debugger.flags.u32all = flags;
+
+	/* use amdgpu mes_flush_shader_debugger instead */
+	if (op_input.set_shader_debugger.flags.process_ctx_flush)
+		return -EINVAL;
+
 	op_input.set_shader_debugger.spi_gdbg_per_vmid_cntl = spi_gdbg_per_vmid_cntl;
 	memcpy(op_input.set_shader_debugger.tcp_watch_cntl, tcp_watch_cntl,
 			sizeof(op_input.set_shader_debugger.tcp_watch_cntl));
@@ -904,6 +909,32 @@ int amdgpu_mes_set_shader_debugger(struct amdgpu_device *adev,
 	return r;
 }
 
+int amdgpu_mes_flush_shader_debugger(struct amdgpu_device *adev,
+				     uint64_t process_context_addr)
+{
+	struct mes_misc_op_input op_input = {0};
+	int r;
+
+	if (!adev->mes.funcs->misc_op) {
+		DRM_ERROR("mes flush shader debugger is not supported!\n");
+		return -EINVAL;
+	}
+
+	op_input.op = MES_MISC_OP_SET_SHADER_DEBUGGER;
+	op_input.set_shader_debugger.process_context_addr = process_context_addr;
+	op_input.set_shader_debugger.flags.process_ctx_flush = true;
+
+	amdgpu_mes_lock(&adev->mes);
+
+	r = adev->mes.funcs->misc_op(&adev->mes, &op_input);
+	if (r)
+		DRM_ERROR("failed to set_shader_debugger\n");
+
+	amdgpu_mes_unlock(&adev->mes);
+
+	return r;
+}
+
 static void
 amdgpu_mes_ring_to_queue_props(struct amdgpu_device *adev,
 			       struct amdgpu_ring *ring,

sys/dev/pci/drm/amd/amdgpu/amdgpu_mes.h

@@ -293,9 +293,10 @@ struct mes_misc_op_input {
 			uint64_t process_context_addr;
 			union {
 				struct {
-					uint64_t single_memop : 1;
-					uint64_t single_alu_op : 1;
-					uint64_t reserved: 30;
+					uint32_t single_memop : 1;
+					uint32_t single_alu_op : 1;
+					uint32_t reserved: 29;
+					uint32_t process_ctx_flush: 1;
 				};
 				uint32_t u32all;
 			} flags;
@@ -371,7 +372,8 @@ int amdgpu_mes_set_shader_debugger(struct amdgpu_device *adev,
 				const uint32_t *tcp_watch_cntl,
 				uint32_t flags,
 				bool trap_en);
-
+int amdgpu_mes_flush_shader_debugger(struct amdgpu_device *adev,
+				uint64_t process_context_addr);
 int amdgpu_mes_add_ring(struct amdgpu_device *adev, int gang_id,
 			int queue_type, int idx,
 			struct amdgpu_mes_ctx_data *ctx_data,

sys/dev/pci/drm/amd/amdgpu/amdgpu_object.c

@@ -1270,19 +1270,15 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
  * amdgpu_bo_move_notify - notification about a memory move
  * @bo: pointer to a buffer object
  * @evict: if this move is evicting the buffer from the graphics address space
- * @new_mem: new information of the bufer object
  *
  * Marks the corresponding &amdgpu_bo buffer object as invalid, also performs
  * bookkeeping.
  * TTM driver callback which is called when ttm moves a buffer.
  */
-void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
-			   bool evict,
-			   struct ttm_resource *new_mem)
+void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 	struct amdgpu_bo *abo;
-	struct ttm_resource *old_mem = bo->resource;
 
 	if (!amdgpu_bo_is_amdgpu_bo(bo))
 		return;
@@ -1301,13 +1297,6 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 	/* remember the eviction */
 	if (evict)
 		atomic64_inc(&adev->num_evictions);
-
-	/* update statistics */
-	if (!new_mem)
-		return;
-
-	/* move_notify is called before move happens */
-	trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
 }
 
 void amdgpu_bo_get_memory(struct amdgpu_bo *bo,

sys/dev/pci/drm/amd/amdgpu/amdgpu_object.h

@@ -345,9 +345,7 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata,
 int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
 			   size_t buffer_size, uint32_t *metadata_size,
 			   uint64_t *flags);
-void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
-			   bool evict,
-			   struct ttm_resource *new_mem);
+void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict);
 void amdgpu_bo_release_notify(struct ttm_buffer_object *bo);
 vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
 void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,

sys/dev/pci/drm/amd/amdgpu/amdgpu_sync.c

@@ -195,7 +195,8 @@ static bool amdgpu_sync_test_fence(struct amdgpu_device *adev,
 
 	/* Never sync to VM updates either. */
 	if (fence_owner == AMDGPU_FENCE_OWNER_VM &&
-	    owner != AMDGPU_FENCE_OWNER_UNDEFINED)
+	    owner != AMDGPU_FENCE_OWNER_UNDEFINED &&
+	    owner != AMDGPU_FENCE_OWNER_KFD)
 		return false;
 
 	/* Ignore fences depending on the sync mode */

sys/dev/pci/drm/amd/amdgpu/amdgpu_ttm.c

@@ -545,10 +545,11 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			return r;
 	}
 
+	trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
 out:
 	/* update statistics */
 	atomic64_add(bo->base.size, &adev->num_bytes_moved);
-	amdgpu_bo_move_notify(bo, evict, new_mem);
+	amdgpu_bo_move_notify(bo, evict);
 	return 0;
 }
 
@@ -1592,7 +1593,7 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo,
 static void
 amdgpu_bo_delete_mem_notify(struct ttm_buffer_object *bo)
 {
-	amdgpu_bo_move_notify(bo, false, NULL);
+	amdgpu_bo_move_notify(bo, false);
 }
 
 static struct ttm_device_funcs amdgpu_bo_driver = {

sys/dev/pci/drm/amd/amdgpu/amdgpu_ucode.c

@@ -1330,9 +1330,13 @@ int amdgpu_ucode_request(struct amdgpu_device *adev, const struct firmware **fw,
 
 	if (err)
 		return -ENODEV;
+
 	err = amdgpu_ucode_validate(*fw);
-	if (err)
+	if (err) {
 		dev_dbg(adev->dev, "\"%s\" failed to validate\n", fw_name);
+		release_firmware(*fw);
+		*fw = NULL;
+	}
 
 	return err;
 }

sys/dev/pci/drm/amd/amdgpu/gfxhub_v1_0.c

@@ -102,7 +102,9 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 		WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 			min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
 
-		if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+		if (adev->apu_flags & (AMD_APU_IS_RAVEN2 |
+				       AMD_APU_IS_RENOIR |
+				       AMD_APU_IS_GREEN_SARDINE))
 		       /*
 			* Raven2 has a HW issue that it is unable to use the
 			* vram which is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR.

sys/dev/pci/drm/amd/amdgpu/gfxhub_v1_2.c

@@ -139,7 +139,9 @@ gfxhub_v1_2_xcc_init_system_aperture_regs(struct amdgpu_device *adev,
 			WREG32_SOC15_RLC(GC, GET_INST(GC, i), regMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 				min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
 
-			if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+			if (adev->apu_flags & (AMD_APU_IS_RAVEN2 |
+					       AMD_APU_IS_RENOIR |
+					       AMD_APU_IS_GREEN_SARDINE))
 			       /*
 				* Raven2 has a HW issue that it is unable to use the
 				* vram which is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR.

sys/dev/pci/drm/amd/amdgpu/gmc_v10_0.c

@@ -1141,6 +1141,10 @@ static int gmc_v10_0_hw_fini(void *handle)
 
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
 
+	if (adev->gmc.ecc_irq.funcs &&
+		amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC))
+		amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
+
 	return 0;
 }
 

sys/dev/pci/drm/amd/amdgpu/gmc_v11_0.c

@@ -974,6 +974,11 @@ static int gmc_v11_0_hw_fini(void *handle)
 	}
 
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
+
+	if (adev->gmc.ecc_irq.funcs &&
+		amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC))
+		amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
+
 	gmc_v11_0_gart_disable(adev);
 
 	return 0;

sys/dev/pci/drm/amd/amdgpu/gmc_v6_0.c

@@ -914,8 +914,8 @@ static int gmc_v6_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v6_0_hw_fini(void *handle)

sys/dev/pci/drm/amd/amdgpu/gmc_v7_0.c

@@ -1103,8 +1103,8 @@ static int gmc_v7_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v7_0_hw_fini(void *handle)

sys/dev/pci/drm/amd/amdgpu/gmc_v8_0.c

@@ -1224,8 +1224,8 @@ static int gmc_v8_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v8_0_hw_fini(void *handle)

sys/dev/pci/drm/amd/amdgpu/gmc_v9_0.c

@@ -2380,8 +2380,8 @@ static int gmc_v9_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 /**
@@ -2420,6 +2420,10 @@ static int gmc_v9_0_hw_fini(void *handle)
 
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
 
+	if (adev->gmc.ecc_irq.funcs &&
+		amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC))
+		amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
+
 	return 0;
 }
 

sys/dev/pci/drm/amd/amdgpu/mmhub_v1_0.c

@@ -96,7 +96,9 @@ static void mmhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 	WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 		     min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
 
-	if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+	if (adev->apu_flags & (AMD_APU_IS_RAVEN2 |
+			       AMD_APU_IS_RENOIR |
+			       AMD_APU_IS_GREEN_SARDINE))
 		/*
 		 * Raven2 has a HW issue that it is unable to use the vram which
 		 * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the

sys/dev/pci/drm/amd/amdkfd/kfd_process_queue_manager.c

@@ -87,6 +87,8 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd)
 		return;
 
 	dev->dqm->ops.process_termination(dev->dqm, &pdd->qpd);
+	if (dev->kfd->shared_resources.enable_mes)
+		amdgpu_mes_flush_shader_debugger(dev->adev, pdd->proc_ctx_gpu_addr);
 	pdd->already_dequeued = true;
 }
 

sys/dev/pci/drm/amd/amdkfd/kfd_svm.c

@@ -391,14 +391,9 @@ static void svm_range_bo_release(struct kref *kref)
 		spin_lock(&svm_bo->list_lock);
 	}
 	spin_unlock(&svm_bo->list_lock);
-	if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base)) {
-		/* We're not in the eviction worker.
-		 * Signal the fence and synchronize with any
-		 * pending eviction work.
-		 */
+	if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base))
+		/* We're not in the eviction worker. Signal the fence. */
 		dma_fence_signal(&svm_bo->eviction_fence->base);
-		cancel_work_sync(&svm_bo->eviction_work);
-	}
 	dma_fence_put(&svm_bo->eviction_fence->base);
 	amdgpu_bo_unref(&svm_bo->bo);
 	kfree(svm_bo);
@@ -2348,8 +2343,10 @@ retry:
 		mutex_unlock(&svms->lock);
 		mmap_write_unlock(mm);
 
-		/* Pairs with mmget in svm_range_add_list_work */
-		mmput(mm);
+		/* Pairs with mmget in svm_range_add_list_work. If dropping the
+		 * last mm refcount, schedule release work to avoid circular locking
+		 */
+		mmput_async(mm);
 
 		spin_lock(&svms->deferred_list_lock);
 	}
@@ -2660,6 +2657,7 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
 {
 	struct vm_area_struct *vma;
 	struct interval_tree_node *node;
+	struct rb_node *rb_node;
 	unsigned long start_limit, end_limit;
 
 	vma = vma_lookup(p->mm, addr << PAGE_SHIFT);
@@ -2679,16 +2677,15 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
 	if (node) {
 		end_limit = min(end_limit, node->start);
 		/* Last range that ends before the fault address */
-		node = container_of(rb_prev(&node->rb),
-				    struct interval_tree_node, rb);
+		rb_node = rb_prev(&node->rb);
 	} else {
 		/* Last range must end before addr because
 		 * there was no range after addr
 		 */
-		node = container_of(rb_last(&p->svms.objects.rb_root),
-				    struct interval_tree_node, rb);
+		rb_node = rb_last(&p->svms.objects.rb_root);
 	}
-	if (node) {
+	if (rb_node) {
+		node = container_of(rb_node, struct interval_tree_node, rb);
 		if (node->last >= addr) {
 			WARN(1, "Overlap with prev node and page fault addr\n");
 			return -EFAULT;
@@ -3424,13 +3421,14 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange,
 
 int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence)
 {
-	if (!fence)
-		return -EINVAL;
-
-	if (dma_fence_is_signaled(&fence->base))
-		return 0;
-
-	if (fence->svm_bo) {
+	/* Dereferencing fence->svm_bo is safe here because the fence hasn't
+	 * signaled yet and we're under the protection of the fence->lock.
+	 * After the fence is signaled in svm_range_bo_release, we cannot get
+	 * here any more.
+	 *
+	 * Reference is dropped in svm_range_evict_svm_bo_worker.
+	 */
+	if (svm_bo_ref_unless_zero(fence->svm_bo)) {
 		WRITE_ONCE(fence->svm_bo->evicting, 1);
 		schedule_work(&fence->svm_bo->eviction_work);
 	}
@@ -3445,8 +3443,6 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 	int r = 0;
 
 	svm_bo = container_of(work, struct svm_range_bo, eviction_work);
-	if (!svm_bo_ref_unless_zero(svm_bo))
-		return; /* svm_bo was freed while eviction was pending */
 
 	if (mmget_not_zero(svm_bo->eviction_fence->mm)) {
 		mm = svm_bo->eviction_fence->mm;

sys/dev/pci/drm/amd/amdkfd/kfd_topology.c

@@ -1452,17 +1452,19 @@ static int kfd_add_peer_prop(struct kfd_topology_device *kdev,
 		/* CPU->CPU  link*/
 		cpu_dev = kfd_topology_device_by_proximity_domain(iolink1->node_to);
 		if (cpu_dev) {
-			list_for_each_entry(iolink3, &cpu_dev->io_link_props, list)
-				if (iolink3->node_to == iolink2->node_to)
-					break;
+			list_for_each_entry(iolink3, &cpu_dev->io_link_props, list) {
+				if (iolink3->node_to != iolink2->node_to)
+					continue;
 
-			props->weight += iolink3->weight;
-			props->min_latency += iolink3->min_latency;
-			props->max_latency += iolink3->max_latency;
-			props->min_bandwidth = min(props->min_bandwidth,
-							iolink3->min_bandwidth);
-			props->max_bandwidth = min(props->max_bandwidth,
-							iolink3->max_bandwidth);
+				props->weight += iolink3->weight;
+				props->min_latency += iolink3->min_latency;
+				props->max_latency += iolink3->max_latency;
+				props->min_bandwidth = min(props->min_bandwidth,
+							   iolink3->min_bandwidth);
+				props->max_bandwidth = min(props->max_bandwidth,
+							   iolink3->max_bandwidth);
+				break;
+			}
 		} else {
 			WARN(1, "CPU node not found");
 		}

sys/dev/pci/drm/amd/display/amdgpu_dm/amdgpu_dm.c

@@ -65,7 +65,6 @@
 #include "amdgpu_dm_debugfs.h"
 #endif
 #include "amdgpu_dm_psr.h"
-#include "amdgpu_dm_replay.h"
 
 #include "ivsrcid/ivsrcid_vislands30.h"
 
@@ -1248,7 +1247,9 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_
 	/* AGP aperture is disabled */
 	if (agp_bot == agp_top) {
 		logical_addr_low = adev->gmc.fb_start >> 18;
-		if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+		if (adev->apu_flags & (AMD_APU_IS_RAVEN2 |
+				       AMD_APU_IS_RENOIR |
+				       AMD_APU_IS_GREEN_SARDINE))
 			/*
 			 * Raven2 has a HW issue that it is unable to use the vram which
 			 * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the
@@ -1260,7 +1261,9 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_
 			logical_addr_high = adev->gmc.fb_end >> 18;
 	} else {
 		logical_addr_low = min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18;
-		if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+		if (adev->apu_flags & (AMD_APU_IS_RAVEN2 |
+				       AMD_APU_IS_RENOIR |
+				       AMD_APU_IS_GREEN_SARDINE))
 			/*
 			 * Raven2 has a HW issue that it is unable to use the vram which
 			 * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the
@@ -4342,7 +4345,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 	enum dc_connection_type new_connection_type = dc_connection_none;
 	const struct dc_plane_cap *plane;
 	bool psr_feature_enabled = false;
-	bool replay_feature_enabled = false;
 	int max_overlay = dm->dc->caps.max_slave_planes;
 
 	dm->display_indexes_num = dm->dc->caps.max_streams;
@@ -4452,20 +4454,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 		}
 	}
 
-	if (!(amdgpu_dc_debug_mask & DC_DISABLE_REPLAY)) {
-		switch (adev->ip_versions[DCE_HWIP][0]) {
-		case IP_VERSION(3, 1, 4):
-		case IP_VERSION(3, 1, 5):
-		case IP_VERSION(3, 1, 6):
-		case IP_VERSION(3, 2, 0):
-		case IP_VERSION(3, 2, 1):
-			replay_feature_enabled = true;
-			break;
-		default:
-			replay_feature_enabled = amdgpu_dc_feature_mask & DC_REPLAY_MASK;
-			break;
-		}
-	}
 	/* loops over all connectors on the board */
 	for (i = 0; i < link_cnt; i++) {
 		struct dc_link *link = NULL;
@@ -4514,12 +4502,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 				amdgpu_dm_update_connector_after_detect(aconnector);
 				setup_backlight_device(dm, aconnector);
 
-				/*
-				 * Disable psr if replay can be enabled
-				 */
-				if (replay_feature_enabled && amdgpu_dm_setup_replay(link, aconnector))
-					psr_feature_enabled = false;
-
 				if (psr_feature_enabled)
 					amdgpu_dm_set_psr_caps(link);
 

sys/dev/pci/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c

@@ -29,7 +29,6 @@
 #include "dc.h"
 #include "amdgpu.h"
 #include "amdgpu_dm_psr.h"
-#include "amdgpu_dm_replay.h"
 #include "amdgpu_dm_crtc.h"
 #include "amdgpu_dm_plane.h"
 #include "amdgpu_dm_trace.h"
@@ -124,12 +123,7 @@ static void vblank_control_worker(struct work_struct *work)
 	 * fill_dc_dirty_rects().
 	 */
 	if (vblank_work->stream && vblank_work->stream->link) {
-		/*
-		 * Prioritize replay, instead of psr
-		 */
-		if (vblank_work->stream->link->replay_settings.replay_feature_enabled)
-			amdgpu_dm_replay_enable(vblank_work->stream, false);
-		else if (vblank_work->enable) {
+		if (vblank_work->enable) {
 			if (vblank_work->stream->link->psr_settings.psr_version < DC_PSR_VERSION_SU_1 &&
 			    vblank_work->stream->link->psr_settings.psr_allow_active)
 				amdgpu_dm_psr_disable(vblank_work->stream);
@@ -138,7 +132,6 @@ static void vblank_control_worker(struct work_struct *work)
 #ifdef CONFIG_DRM_AMD_SECURE_DISPLAY
 			   !amdgpu_dm_crc_window_is_activated(&vblank_work->acrtc->base) &&
 #endif
-			   vblank_work->stream->link->panel_config.psr.disallow_replay &&
 			   vblank_work->acrtc->dm_irq_params.allow_psr_entry) {
 			amdgpu_dm_psr_enable(vblank_work->stream);
 		}

sys/dev/pci/drm/amd/display/dc/core/amdgpu_dc.c

@@ -1948,6 +1948,10 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 		wait_for_no_pipes_pending(dc, context);
 		/* pplib is notified if disp_num changed */
 		dc->hwss.optimize_bandwidth(dc, context);
+		/* Need to do otg sync again as otg could be out of sync due to otg
+		 * workaround applied during clock update
+		 */
+		dc_trigger_sync(dc, context);
 	}
 
 	if (dc->hwss.update_dsc_pg)

sys/dev/pci/drm/amd/display/dc/dc_hw_types.h

@@ -244,7 +244,7 @@ enum pixel_format {
 #define DC_MAX_DIRTY_RECTS 3
 struct dc_flip_addrs {
 	struct dc_plane_address address;
-	unsigned int flip_timestamp_in_us;
+	unsigned long long flip_timestamp_in_us;
 	bool flip_immediate;
 	/* TODO: add flip duration for FreeSync */
 	bool triplebuffer_flips;

sys/dev/pci/drm/amd/display/dc/dce110/dce110_hw_sequencer.c

@@ -2124,7 +2124,8 @@ static void dce110_reset_hw_ctx_wrap(
 				BREAK_TO_DEBUGGER();
 			}
 			pipe_ctx_old->stream_res.tg->funcs->disable_crtc(pipe_ctx_old->stream_res.tg);
-			pipe_ctx_old->stream->link->phy_state.symclk_ref_cnts.otg = 0;
+			if (dc_is_hdmi_tmds_signal(pipe_ctx_old->stream->signal))
+				pipe_ctx_old->stream->link->phy_state.symclk_ref_cnts.otg = 0;
 			pipe_ctx_old->plane_res.mi->funcs->free_mem_input(
 					pipe_ctx_old->plane_res.mi, dc->current_state->stream_count);
 

sys/dev/pci/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c

@@ -1054,7 +1054,8 @@ static void dcn10_reset_back_end_for_pipe(
 		if (pipe_ctx->stream_res.tg->funcs->set_drr)
 			pipe_ctx->stream_res.tg->funcs->set_drr(
 					pipe_ctx->stream_res.tg, NULL);
-		pipe_ctx->stream->link->phy_state.symclk_ref_cnts.otg = 0;
+		if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal))
+			pipe_ctx->stream->link->phy_state.symclk_ref_cnts.otg = 0;
 	}
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++)

sys/dev/pci/drm/amd/display/dc/dcn20/dcn20_hwseq.c

@@ -1792,6 +1792,8 @@ void dcn20_program_front_end_for_ctx(
 	int i;
 	struct dce_hwseq *hws = dc->hwseq;
 	DC_LOGGER_INIT(dc->ctx->logger);
+	unsigned int prev_hubp_count = 0;
+	unsigned int hubp_count = 0;
 
 	/* Carry over GSL groups in case the context is changing. */
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
@@ -1815,6 +1817,20 @@ void dcn20_program_front_end_for_ctx(
 		}
 	}
 
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (dc->current_state->res_ctx.pipe_ctx[i].plane_state)
+			prev_hubp_count++;
+		if (context->res_ctx.pipe_ctx[i].plane_state)
+			hubp_count++;
+	}
+
+	if (prev_hubp_count == 0 && hubp_count > 0) {
+		if (dc->res_pool->hubbub->funcs->force_pstate_change_control)
+			dc->res_pool->hubbub->funcs->force_pstate_change_control(
+					dc->res_pool->hubbub, true, false);
+		udelay(500);
+	}
+
 	/* Set pipe update flags and lock pipes */
 	for (i = 0; i < dc->res_pool->pipe_count; i++)
 		dcn20_detect_pipe_changes(&dc->current_state->res_ctx.pipe_ctx[i],
@@ -1962,6 +1978,10 @@ void dcn20_post_unlock_program_front_end(
 		}
 	}
 
+	if (dc->res_pool->hubbub->funcs->force_pstate_change_control)
+		dc->res_pool->hubbub->funcs->force_pstate_change_control(
+				dc->res_pool->hubbub, false, false);
+
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
 
@@ -2513,7 +2533,8 @@ static void dcn20_reset_back_end_for_pipe(
 		 * the case where the same symclk is shared across multiple otg
 		 * instances
 		 */
-		link->phy_state.symclk_ref_cnts.otg = 0;
+		if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal))
+			link->phy_state.symclk_ref_cnts.otg = 0;
 		if (link->phy_state.symclk_state == SYMCLK_ON_TX_OFF) {
 			link_hwss->disable_link_output(link,
 					&pipe_ctx->link_res, pipe_ctx->stream->signal);

sys/dev/pci/drm/amd/display/dc/dcn31/dcn31_hwseq.c

@@ -523,7 +523,8 @@ static void dcn31_reset_back_end_for_pipe(
 	if (pipe_ctx->stream_res.tg->funcs->set_odm_bypass)
 		pipe_ctx->stream_res.tg->funcs->set_odm_bypass(
 				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
-	pipe_ctx->stream->link->phy_state.symclk_ref_cnts.otg = 0;
+	if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal))
+		pipe_ctx->stream->link->phy_state.symclk_ref_cnts.otg = 0;
 
 	if (pipe_ctx->stream_res.tg->funcs->set_drr)
 		pipe_ctx->stream_res.tg->funcs->set_drr(

sys/dev/pci/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c

@@ -813,6 +813,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 					(v->DRAMSpeedPerState[mode_lib->vba.VoltageLevel] <= MEM_STROBE_FREQ_MHZ ||
 						v->DCFCLKPerState[mode_lib->vba.VoltageLevel] <= DCFCLK_FREQ_EXTRA_PREFETCH_REQ_MHZ) ?
 							mode_lib->vba.ip.min_prefetch_in_strobe_us : 0,
+					mode_lib->vba.PrefetchModePerState[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] > 0 || mode_lib->vba.DRAMClockChangeRequirementFinal == false,
+
 					/* Output */
 					&v->DSTXAfterScaler[k],
 					&v->DSTYAfterScaler[k],
@@ -3317,6 +3319,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							v->SwathHeightCThisState[k], v->TWait,
 							(v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ || v->DCFCLKState[i][j] <= DCFCLK_FREQ_EXTRA_PREFETCH_REQ_MHZ) ?
 									mode_lib->vba.ip.min_prefetch_in_strobe_us : 0,
+							mode_lib->vba.PrefetchModePerState[i][j] > 0 || mode_lib->vba.DRAMClockChangeRequirementFinal == false,
 
 							/* Output */
 							&v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTXAfterScaler[k],

sys/dev/pci/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c

@@ -3423,6 +3423,7 @@ bool dml32_CalculatePrefetchSchedule(
 		unsigned int SwathHeightC,
 		double TWait,
 		double TPreReq,
+		bool ExtendPrefetchIfPossible,
 		/* Output */
 		double   *DSTXAfterScaler,
 		double   *DSTYAfterScaler,
@@ -3892,12 +3893,32 @@ bool dml32_CalculatePrefetchSchedule(
 			/* Clamp to oto for bandwidth calculation */
 			LinesForPrefetchBandwidth = dst_y_prefetch_oto;
 		} else {
-			*DestinationLinesForPrefetch = dst_y_prefetch_equ;
-			TimeForFetchingMetaPTE = Tvm_equ;
-			TimeForFetchingRowInVBlank = Tr0_equ;
-			*PrefetchBandwidth = prefetch_bw_equ;
-			/* Clamp to equ for bandwidth calculation */
-			LinesForPrefetchBandwidth = dst_y_prefetch_equ;
+			/* For mode programming we want to extend the prefetch as much as possible
+			 * (up to oto, or as long as we can for equ) if we're not already applying
+			 * the 60us prefetch requirement. This is to avoid intermittent underflow
+			 * issues during prefetch.
+			 *
+			 * The prefetch extension is applied under the following scenarios:
+			 * 1. We're in prefetch mode > 0 (i.e. we don't support MCLK switch in blank)
+			 * 2. We're using subvp or drr methods of p-state switch, in which case we
+			 *    we don't care if prefetch takes up more of the blanking time
+			 *
+			 * Mode programming typically chooses the smallest prefetch time possible
+			 * (i.e. highest bandwidth during prefetch) presumably to create margin between
+			 * p-states / c-states that happen in vblank and prefetch. Therefore we only
+			 * apply this prefetch extension when p-state in vblank is not required (UCLK
+			 * p-states take up the most vblank time).
+			 */
+			if (ExtendPrefetchIfPossible && TPreReq == 0 && VStartup < MaxVStartup) {
+				MyError = true;
+			} else {
+				*DestinationLinesForPrefetch = dst_y_prefetch_equ;
+				TimeForFetchingMetaPTE = Tvm_equ;
+				TimeForFetchingRowInVBlank = Tr0_equ;
+				*PrefetchBandwidth = prefetch_bw_equ;
+				/* Clamp to equ for bandwidth calculation */
+				LinesForPrefetchBandwidth = dst_y_prefetch_equ;
+			}
 		}
 
 		*DestinationLinesToRequestVMInVBlank = dml_ceil(4.0 * TimeForFetchingMetaPTE / LineTime, 1.0) / 4.0;

sys/dev/pci/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h

@@ -747,6 +747,7 @@ bool dml32_CalculatePrefetchSchedule(
 		unsigned int SwathHeightC,
 		double TWait,
 		double TPreReq,
+		bool ExtendPrefetchIfPossible,
 		/* Output */
 		double   *DSTXAfterScaler,
 		double   *DSTYAfterScaler,

sys/dev/pci/drm/amd/display/dc/link/link_dpms.c

@@ -1059,18 +1059,21 @@ static struct fixed31_32 get_pbn_from_bw_in_kbps(uint64_t kbps)
 	uint32_t denominator = 1;
 
 	/*
-	 * margin 5300ppm + 300ppm ~ 0.6% as per spec, factor is 1.006
+	 * The 1.006 factor (margin 5300ppm + 300ppm ~ 0.6% as per spec) is not
+	 * required when determining PBN/time slot utilization on the link between
+	 * us and the branch, since that overhead is already accounted for in
+	 * the get_pbn_per_slot function.
+	 *
 	 * The unit of 54/64Mbytes/sec is an arbitrary unit chosen based on
 	 * common multiplier to render an integer PBN for all link rate/lane
 	 * counts combinations
 	 * calculate
-	 * peak_kbps *= (1006/1000)
 	 * peak_kbps *= (64/54)
-	 * peak_kbps *= 8    convert to bytes
+	 * peak_kbps /= (8 * 1000) convert to bytes
 	 */
 
-	numerator = 64 * PEAK_FACTOR_X1000;
-	denominator = 54 * 8 * 1000 * 1000;
+	numerator = 64;
+	denominator = 54 * 8 * 1000;
 	kbps *= numerator;
 	peak_kbps = dc_fixpt_from_fraction(kbps, denominator);
 

sys/dev/pci/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c

@@ -50,6 +50,7 @@ static bool get_bw_alloc_proceed_flag(struct dc_link *tmp)
 			&& tmp->hpd_status
 			&& tmp->dpia_bw_alloc_config.bw_alloc_enabled);
 }
+
 static void reset_bw_alloc_struct(struct dc_link *link)
 {
 	link->dpia_bw_alloc_config.bw_alloc_enabled = false;
@@ -59,6 +60,11 @@ static void reset_bw_alloc_struct(struct dc_link *link)
 	link->dpia_bw_alloc_config.bw_granularity = 0;
 	link->dpia_bw_alloc_config.response_ready = false;
 }
+
+#define BW_GRANULARITY_0 4 // 0.25 Gbps
+#define BW_GRANULARITY_1 2 // 0.5 Gbps
+#define BW_GRANULARITY_2 1 // 1 Gbps
+
 static uint8_t get_bw_granularity(struct dc_link *link)
 {
 	uint8_t bw_granularity = 0;
@@ -71,16 +77,20 @@ static uint8_t get_bw_granularity(struct dc_link *link)
 
 	switch (bw_granularity & 0x3) {
 	case 0:
-		bw_granularity = 4;
+		bw_granularity = BW_GRANULARITY_0;
 		break;
 	case 1:
+		bw_granularity = BW_GRANULARITY_1;
+		break;
+	case 2:
 	default:
-		bw_granularity = 2;
+		bw_granularity = BW_GRANULARITY_2;
 		break;
 	}
 
 	return bw_granularity;
 }
+
 static int get_estimated_bw(struct dc_link *link)
 {
 	uint8_t bw_estimated_bw = 0;
@@ -93,31 +103,7 @@ static int get_estimated_bw(struct dc_link *link)
 
 	return bw_estimated_bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity);
 }
-static bool allocate_usb4_bw(int *stream_allocated_bw, int bw_needed, struct dc_link *link)
-{
-	if (bw_needed > 0)
-		*stream_allocated_bw += bw_needed;
 
-	return true;
-}
-static bool deallocate_usb4_bw(int *stream_allocated_bw, int bw_to_dealloc, struct dc_link *link)
-{
-	bool ret = false;
-
-	if (*stream_allocated_bw > 0) {
-		*stream_allocated_bw -= bw_to_dealloc;
-		ret = true;
-	} else {
-		//Do nothing for now
-		ret = true;
-	}
-
-	// Unplug so reset values
-	if (!link->hpd_status)
-		reset_bw_alloc_struct(link);
-
-	return ret;
-}
 /*
  * Read all New BW alloc configuration ex: estimated_bw, allocated_bw,
  * granuality, Driver_ID, CM_Group, & populate the BW allocation structs
@@ -128,7 +114,12 @@ static void init_usb4_bw_struct(struct dc_link *link)
 	// Init the known values
 	link->dpia_bw_alloc_config.bw_granularity = get_bw_granularity(link);
 	link->dpia_bw_alloc_config.estimated_bw = get_estimated_bw(link);
+
+	DC_LOG_DEBUG("%s: bw_granularity(%d), estimated_bw(%d)\n",
+		__func__, link->dpia_bw_alloc_config.bw_granularity,
+		link->dpia_bw_alloc_config.estimated_bw);
 }
+
 static uint8_t get_lowest_dpia_index(struct dc_link *link)
 {
 	const struct dc *dc_struct = link->dc;
@@ -141,12 +132,15 @@ static uint8_t get_lowest_dpia_index(struct dc_link *link)
 				dc_struct->links[i]->ep_type != DISPLAY_ENDPOINT_USB4_DPIA)
 			continue;
 
-		if (idx > dc_struct->links[i]->link_index)
+		if (idx > dc_struct->links[i]->link_index) {
 			idx = dc_struct->links[i]->link_index;
+			break;
+		}
 	}
 
 	return idx;
 }
+
 /*
  * Get the Max Available BW or Max Estimated BW for each Host Router
  *
@@ -186,6 +180,7 @@ static int get_host_router_total_bw(struct dc_link *link, uint8_t type)
 
 	return total_bw;
 }
+
 /*
  * Cleanup function for when the dpia is unplugged to reset struct
  * and perform any required clean up
@@ -194,42 +189,50 @@ static int get_host_router_total_bw(struct dc_link *link, uint8_t type)
  *
  * return: none
  */
-static bool dpia_bw_alloc_unplug(struct dc_link *link)
+static void dpia_bw_alloc_unplug(struct dc_link *link)
 {
-	if (!link)
-		return true;
-
-	return deallocate_usb4_bw(&link->dpia_bw_alloc_config.sink_allocated_bw,
-			link->dpia_bw_alloc_config.sink_allocated_bw, link);
+	if (link) {
+		DC_LOG_DEBUG("%s: resetting bw alloc config for link(%d)\n",
+			__func__, link->link_index);
+		link->dpia_bw_alloc_config.sink_allocated_bw = 0;
+		reset_bw_alloc_struct(link);
+	}
 }
+
 static void set_usb4_req_bw_req(struct dc_link *link, int req_bw)
 {
 	uint8_t requested_bw;
 	uint32_t temp;
 
-	// 1. Add check for this corner case #1
-	if (req_bw > link->dpia_bw_alloc_config.estimated_bw)
+	/* Error check whether request bw greater than allocated */
+	if (req_bw > link->dpia_bw_alloc_config.estimated_bw) {
+		DC_LOG_ERROR("%s: Request bw greater than estimated bw for link(%d)\n",
+			__func__, link->link_index);
 		req_bw = link->dpia_bw_alloc_config.estimated_bw;
+	}
 
 	temp = req_bw * link->dpia_bw_alloc_config.bw_granularity;
 	requested_bw = temp / Kbps_TO_Gbps;
 
-	// Always make sure to add more to account for floating points
+	/* Always make sure to add more to account for floating points */
 	if (temp % Kbps_TO_Gbps)
 		++requested_bw;
 
-	// 2. Add check for this corner case #2
+	/* Error check whether requested and allocated are equal */
 	req_bw = requested_bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity);
-	if (req_bw == link->dpia_bw_alloc_config.sink_allocated_bw)
-		return;
+	if (req_bw == link->dpia_bw_alloc_config.sink_allocated_bw) {
+		DC_LOG_ERROR("%s: Request bw equals to allocated bw for link(%d)\n",
+			__func__, link->link_index);
+	}
 
-	if (core_link_write_dpcd(
+	link->dpia_bw_alloc_config.response_ready = false; // Reset flag
+	core_link_write_dpcd(
 		link,
 		REQUESTED_BW,
 		&requested_bw,
-		sizeof(uint8_t)) == DC_OK)
-		link->dpia_bw_alloc_config.response_ready = false; // Reset flag
+		sizeof(uint8_t));
 }
+
 /*
  * Return the response_ready flag from dc_link struct
  *
@@ -241,6 +244,7 @@ static bool get_cm_response_ready_flag(struct dc_link *link)
 {
 	return link->dpia_bw_alloc_config.response_ready;
 }
+
 // ------------------------------------------------------------------
 //					PUBLIC FUNCTIONS
 // ------------------------------------------------------------------
@@ -277,27 +281,27 @@ bool link_dp_dpia_set_dptx_usb4_bw_alloc_support(struct dc_link *link)
 				DPTX_BW_ALLOCATION_MODE_CONTROL,
 				&response,
 				sizeof(uint8_t)) != DC_OK) {
-			DC_LOG_DEBUG("%s: **** FAILURE Enabling DPtx BW Allocation Mode Support ***\n",
-					__func__);
+			DC_LOG_DEBUG("%s: FAILURE Enabling DPtx BW Allocation Mode Support for link(%d)\n",
+				__func__, link->link_index);
 		} else {
 			// SUCCESS Enabled DPtx BW Allocation Mode Support
-			link->dpia_bw_alloc_config.bw_alloc_enabled = true;
-			DC_LOG_DEBUG("%s: **** SUCCESS Enabling DPtx BW Allocation Mode Support ***\n",
-					__func__);
+			DC_LOG_DEBUG("%s: SUCCESS Enabling DPtx BW Allocation Mode Support for link(%d)\n",
+				__func__, link->link_index);
 
 			ret = true;
 			init_usb4_bw_struct(link);
+			link->dpia_bw_alloc_config.bw_alloc_enabled = true;
 		}
 	}
 
 out:
 	return ret;
 }
+
 void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t result)
 {
 	int bw_needed = 0;
 	int estimated = 0;
-	int host_router_total_estimated_bw = 0;
 
 	if (!get_bw_alloc_proceed_flag((link)))
 		return;
@@ -306,14 +310,22 @@ void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t res
 
 	case DPIA_BW_REQ_FAILED:
 
-		DC_LOG_DEBUG("%s: *** *** BW REQ FAILURE for DP-TX Request *** ***\n", __func__);
+		/*
+		 * Ideally, we shouldn't run into this case as we always validate available
+		 * bandwidth and request within that limit
+		 */
+		estimated = bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity);
 
-		// Update the new Estimated BW value updated by CM
-		link->dpia_bw_alloc_config.estimated_bw =
-				bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity);
+		DC_LOG_ERROR("%s: BW REQ FAILURE for DP-TX Request for link(%d)\n",
+			__func__, link->link_index);
+		DC_LOG_ERROR("%s: current estimated_bw(%d), new estimated_bw(%d)\n",
+			__func__, link->dpia_bw_alloc_config.estimated_bw, estimated);
 
+		/* Update the new Estimated BW value updated by CM */
+		link->dpia_bw_alloc_config.estimated_bw = estimated;
+
+		/* Allocate the previously requested bandwidth */
 		set_usb4_req_bw_req(link, link->dpia_bw_alloc_config.estimated_bw);
-		link->dpia_bw_alloc_config.response_ready = false;
 
 		/*
 		 * If FAIL then it is either:
@@ -326,68 +338,34 @@ void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t res
 
 	case DPIA_BW_REQ_SUCCESS:
 
-		DC_LOG_DEBUG("%s: *** BW REQ SUCCESS for DP-TX Request ***\n", __func__);
-
-		// 1. SUCCESS 1st time before any Pruning is done
-		// 2. SUCCESS after prev. FAIL before any Pruning is done
-		// 3. SUCCESS after Pruning is done but before enabling link
-
 		bw_needed = bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity);
 
-		// 1.
-		if (!link->dpia_bw_alloc_config.sink_allocated_bw) {
+		DC_LOG_DEBUG("%s: BW REQ SUCCESS for DP-TX Request for link(%d)\n",
+			__func__, link->link_index);
+		DC_LOG_DEBUG("%s: current allocated_bw(%d), new allocated_bw(%d)\n",
+			__func__, link->dpia_bw_alloc_config.sink_allocated_bw, bw_needed);
 
-			allocate_usb4_bw(&link->dpia_bw_alloc_config.sink_allocated_bw, bw_needed, link);
-			link->dpia_bw_alloc_config.sink_verified_bw =
-					link->dpia_bw_alloc_config.sink_allocated_bw;
-
-			// SUCCESS from first attempt
-			if (link->dpia_bw_alloc_config.sink_allocated_bw >
-			link->dpia_bw_alloc_config.sink_max_bw)
-				link->dpia_bw_alloc_config.sink_verified_bw =
-						link->dpia_bw_alloc_config.sink_max_bw;
-		}
-		// 3.
-		else if (link->dpia_bw_alloc_config.sink_allocated_bw) {
-
-			// Find out how much do we need to de-alloc
-			if (link->dpia_bw_alloc_config.sink_allocated_bw > bw_needed)
-				deallocate_usb4_bw(&link->dpia_bw_alloc_config.sink_allocated_bw,
-						link->dpia_bw_alloc_config.sink_allocated_bw - bw_needed, link);
-			else
-				allocate_usb4_bw(&link->dpia_bw_alloc_config.sink_allocated_bw,
-						bw_needed - link->dpia_bw_alloc_config.sink_allocated_bw, link);
-		}
-
-		// 4. If this is the 2nd sink then any unused bw will be reallocated to master DPIA
-		// => check if estimated_bw changed
+		link->dpia_bw_alloc_config.sink_allocated_bw = bw_needed;
 
 		link->dpia_bw_alloc_config.response_ready = true;
 		break;
 
 	case DPIA_EST_BW_CHANGED:
 
-		DC_LOG_DEBUG("%s: *** ESTIMATED BW CHANGED for DP-TX Request ***\n", __func__);
-
 		estimated = bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity);
-		host_router_total_estimated_bw = get_host_router_total_bw(link, HOST_ROUTER_BW_ESTIMATED);
 
-		// 1. If due to unplug of other sink
-		if (estimated == host_router_total_estimated_bw) {
-			// First update the estimated & max_bw fields
-			if (link->dpia_bw_alloc_config.estimated_bw < estimated)
-				link->dpia_bw_alloc_config.estimated_bw = estimated;
-		}
-		// 2. If due to realloc bw btw 2 dpia due to plug OR realloc unused Bw
-		else {
-			// We lost estimated bw usually due to plug event of other dpia
-			link->dpia_bw_alloc_config.estimated_bw = estimated;
-		}
+		DC_LOG_DEBUG("%s: ESTIMATED BW CHANGED for link(%d)\n",
+			__func__, link->link_index);
+		DC_LOG_DEBUG("%s: current estimated_bw(%d), new estimated_bw(%d)\n",
+			__func__, link->dpia_bw_alloc_config.estimated_bw, estimated);
+
+		link->dpia_bw_alloc_config.estimated_bw = estimated;
 		break;
 
 	case DPIA_BW_ALLOC_CAPS_CHANGED:
 
-		DC_LOG_DEBUG("%s: *** BW ALLOC CAPABILITY CHANGED for DP-TX Request ***\n", __func__);
+		DC_LOG_ERROR("%s: BW ALLOC CAPABILITY CHANGED to Disabled for link(%d)\n",
+			__func__, link->link_index);
 		link->dpia_bw_alloc_config.bw_alloc_enabled = false;
 		break;
 	}
@@ -409,11 +387,11 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea
 		set_usb4_req_bw_req(link, link->dpia_bw_alloc_config.sink_max_bw);
 
 		do {
-			if (!(timeout > 0))
+			if (timeout > 0)
 				timeout--;
 			else
 				break;
-			fsleep(10 * 1000);
+			drm_msleep(10);
 		} while (!get_cm_response_ready_flag(link));
 
 		if (!timeout)
@@ -428,37 +406,36 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea
 out:
 	return ret;
 }
-int link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int req_bw)
+
+bool link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int req_bw)
 {
-	int ret = 0;
+	bool ret = false;
 	uint8_t timeout = 10;
 
+	DC_LOG_DEBUG("%s: ENTER: link(%d), hpd_status(%d), current allocated_bw(%d), req_bw(%d)\n",
+		__func__, link->link_index, link->hpd_status,
+		link->dpia_bw_alloc_config.sink_allocated_bw, req_bw);
+
 	if (!get_bw_alloc_proceed_flag(link))
 		goto out;
 
-	/*
-	 * Sometimes stream uses same timing parameters as the already
-	 * allocated max sink bw so no need to re-alloc
-	 */
-	if (req_bw != link->dpia_bw_alloc_config.sink_allocated_bw) {
-		set_usb4_req_bw_req(link, req_bw);
-		do {
-			if (!(timeout > 0))
-				timeout--;
-			else
-				break;
-			udelay(10 * 1000);
-		} while (!get_cm_response_ready_flag(link));
+	set_usb4_req_bw_req(link, req_bw);
+	do {
+		if (timeout > 0)
+			timeout--;
+		else
+			break;
+		drm_msleep(10);
+	} while (!get_cm_response_ready_flag(link));
 
-		if (!timeout)
-			ret = 0;// ERROR TIMEOUT waiting for response for allocating bw
-		else if (link->dpia_bw_alloc_config.sink_allocated_bw > 0)
-			ret = get_host_router_total_bw(link, HOST_ROUTER_BW_ALLOCATED);
-	}
+	if (timeout)
+		ret = true;
 
 out:
+	DC_LOG_DEBUG("%s: EXIT: timeout(%d), ret(%d)\n", __func__, timeout, ret);
 	return ret;
 }
+
 bool dpia_validate_usb4_bw(struct dc_link **link, int *bw_needed_per_dpia, const unsigned int num_dpias)
 {
 	bool ret = true;

sys/dev/pci/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h

@@ -59,9 +59,9 @@ bool link_dp_dpia_set_dptx_usb4_bw_alloc_support(struct dc_link *link);
  * @link: pointer to the dc_link struct instance
  * @req_bw: Bw requested by the stream
  *
- * return: allocated bw else return 0
+ * return: true if allocated successfully
  */
-int link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int req_bw);
+bool link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int req_bw);
 
 /*
  * Handle the USB4 BW Allocation related functionality here:

sys/dev/pci/drm/amd/include/amd_shared.h

@@ -240,7 +240,6 @@ enum DC_FEATURE_MASK {
 	DC_DISABLE_LTTPR_DP2_0 = (1 << 6), //0x40, disabled by default
 	DC_PSR_ALLOW_SMU_OPT = (1 << 7), //0x80, disabled by default
 	DC_PSR_ALLOW_MULTI_DISP_OPT = (1 << 8), //0x100, disabled by default
-	DC_REPLAY_MASK = (1 << 9), //0x200, disabled by default for dcn < 3.1.4
 };
 
 enum DC_DEBUG_MASK {
@@ -251,7 +250,6 @@ enum DC_DEBUG_MASK {
 	DC_DISABLE_PSR = 0x10,
 	DC_FORCE_SUBVP_MCLK_SWITCH = 0x20,
 	DC_DISABLE_MPO = 0x40,
-	DC_DISABLE_REPLAY = 0x50,
 	DC_ENABLE_DPIA_TRACE = 0x80,
 };
 

sys/dev/pci/drm/amd/include/mes_v11_api_def.h

@@ -571,7 +571,8 @@ struct SET_SHADER_DEBUGGER {
 		struct {
 			uint32_t single_memop : 1;  /* SQ_DEBUG.single_memop */
 			uint32_t single_alu_op : 1; /* SQ_DEBUG.single_alu_op */
-			uint32_t reserved : 30;
+			uint32_t reserved : 29;
+			uint32_t process_ctx_flush : 1;
 		};
 		uint32_t u32all;
 	} flags;

sys/dev/pci/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c

@@ -200,7 +200,7 @@ static int get_platform_power_management_table(
 		struct pp_hwmgr *hwmgr,
 		ATOM_Tonga_PPM_Table *atom_ppm_table)
 {
-	struct phm_ppm_table *ptr = kzalloc(sizeof(ATOM_Tonga_PPM_Table), GFP_KERNEL);
+	struct phm_ppm_table *ptr = kzalloc(sizeof(*ptr), GFP_KERNEL);
 	struct phm_ppt_v1_information *pp_table_information =
 		(struct phm_ppt_v1_information *)(hwmgr->pptable);
 

sys/dev/pci/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c

@@ -3999,6 +3999,7 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 	uint32_t sclk, mclk, activity_percent;
 	uint32_t offset, val_vid;
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	/* size must be at least 4 bytes for all sensors */
 	if (*size < 4)
@@ -4042,7 +4043,21 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 		*size = 4;
 		return 0;
 	case AMDGPU_PP_SENSOR_GPU_INPUT_POWER:
-		return smu7_get_gpu_power(hwmgr, (uint32_t *)value);
+		if ((adev->asic_type != CHIP_HAWAII) &&
+		    (adev->asic_type != CHIP_BONAIRE) &&
+		    (adev->asic_type != CHIP_FIJI) &&
+		    (adev->asic_type != CHIP_TONGA))
+			return smu7_get_gpu_power(hwmgr, (uint32_t *)value);
+		else
+			return -EOPNOTSUPP;
+	case AMDGPU_PP_SENSOR_GPU_AVG_POWER:
+		if ((adev->asic_type != CHIP_HAWAII) &&
+		    (adev->asic_type != CHIP_BONAIRE) &&
+		    (adev->asic_type != CHIP_FIJI) &&
+		    (adev->asic_type != CHIP_TONGA))
+			return -EOPNOTSUPP;
+		else
+			return smu7_get_gpu_power(hwmgr, (uint32_t *)value);
 	case AMDGPU_PP_SENSOR_VDDGFX:
 		if ((data->vr_config & VRCONF_VDDGFX_MASK) ==
 		    (VR_SVI2_PLANE_2 << VRCONF_VDDGFX_SHIFT))

sys/dev/pci/drm/drm_file.c

@@ -994,7 +994,7 @@ void drm_show_memory_stats(struct drm_printer *p, struct drm_file *file)
 {
 	struct drm_gem_object *obj;
 	struct drm_memory_stats status = {};
-	enum drm_gem_object_status supported_status;
+	enum drm_gem_object_status supported_status = 0;
 	int id;
 
 	spin_lock(&file->table_lock);

sys/dev/pci/drm/drm_framebuffer.c

@@ -570,7 +570,7 @@ int drm_mode_getfb2_ioctl(struct drm_device *dev,
 	struct drm_mode_fb_cmd2 *r = data;
 	struct drm_framebuffer *fb;
 	unsigned int i;
-	int ret;
+	int ret = 0;
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EINVAL;

sys/dev/pci/drm/drm_mipi_dsi.c

@@ -353,7 +353,8 @@ static int mipi_dsi_remove_device_fn(struct device *dev, void *priv)
 {
 	struct mipi_dsi_device *dsi = to_mipi_dsi_device(dev);
 
-	mipi_dsi_detach(dsi);
+	if (dsi->attached)
+		mipi_dsi_detach(dsi);
 	mipi_dsi_device_unregister(dsi);
 
 	return 0;
@@ -378,11 +379,18 @@ EXPORT_SYMBOL(mipi_dsi_host_unregister);
 int mipi_dsi_attach(struct mipi_dsi_device *dsi)
 {
 	const struct mipi_dsi_host_ops *ops = dsi->host->ops;
+	int ret;
 
 	if (!ops || !ops->attach)
 		return -ENOSYS;
 
-	return ops->attach(dsi->host, dsi);
+	ret = ops->attach(dsi->host, dsi);
+	if (ret)
+		return ret;
+
+	dsi->attached = true;
+
+	return 0;
 }
 EXPORT_SYMBOL(mipi_dsi_attach);
 
@@ -394,9 +402,14 @@ int mipi_dsi_detach(struct mipi_dsi_device *dsi)
 {
 	const struct mipi_dsi_host_ops *ops = dsi->host->ops;
 
+	if (WARN_ON(!dsi->attached))
+		return -EINVAL;
+
 	if (!ops || !ops->detach)
 		return -ENOSYS;
 
+	dsi->attached = false;
+
 	return ops->detach(dsi->host, dsi);
 }
 EXPORT_SYMBOL(mipi_dsi_detach);

sys/dev/pci/drm/include/drm/drm_color_mgmt.h

@@ -24,6 +24,7 @@
 #define __DRM_COLOR_MGMT_H__
 
 #include <linux/ctype.h>
+#include <linux/math64.h>
 #include <drm/drm_property.h>
 
 struct drm_crtc;

sys/dev/pci/drm/include/drm/drm_mipi_dsi.h

@@ -27,6 +27,7 @@ struct mipi_dsi_device {
 	uint32_t channel;
 	uint32_t mode_flags;
 #define MIPI_DSI_MODE_LPM	(1 << 0)
+	bool attached;
 };
 
 struct mipi_dsi_msg {