Merge tag 'amd-drm-next-6.15-2025-03-21' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.15-2025-03-21:

amdgpu:
- Refine nomodeset handling
- RAS fixes
- DCN 3.x fixes
- DMUB fixes
- eDP fixes
- SMU 14.0.2 fixes
- SMU 13.0.6 fixes
- SMU 13.0.12 fixes
- SDMA engine reset fixes
- Enforce Isolation fixes
- Runtime workload profile ref count fixes
- Documentation fixes
- SR-IOV fixes
- MES fixes
- GC 11.5 cleaner shader support
- SDMA VM invalidation fixes
- IP discovery improvements for GC based chips

amdkfd:
- Dequeue wait count fixes
- Precise memops fixes

radeon:
- Code cleanup

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250321210909.2809595-1-alexander.deucher@amd.com

Author: airlied

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

@@ -1194,9 +1194,15 @@ struct amdgpu_device {
 	bool                            debug_exp_resets;
 	bool                            debug_disable_gpu_ring_reset;
 
-	bool				enforce_isolation[MAX_XCP];
-	/* Added this mutex for cleaner shader isolation between GFX and compute processes */
+	/* Protection for the following isolation structure */
 	struct mutex                    enforce_isolation_mutex;
+	bool				enforce_isolation[MAX_XCP];
+	struct amdgpu_isolation {
+		void			*owner;
+		struct dma_fence	*spearhead;
+		struct amdgpu_sync	active;
+		struct amdgpu_sync	prev;
+	} isolation[MAX_XCP];
 
 	struct amdgpu_init_level *init_lvl;
 
@@ -1482,6 +1488,9 @@ void amdgpu_device_pcie_port_wreg(struct amdgpu_device *adev,
 struct dma_fence *amdgpu_device_get_gang(struct amdgpu_device *adev);
 struct dma_fence *amdgpu_device_switch_gang(struct amdgpu_device *adev,
 					    struct dma_fence *gang);
+struct dma_fence *amdgpu_device_enforce_isolation(struct amdgpu_device *adev,
+						  struct amdgpu_ring *ring,
+						  struct amdgpu_job *job);
 bool amdgpu_device_has_display_hardware(struct amdgpu_device *adev);
 ssize_t amdgpu_get_soft_full_reset_mask(struct amdgpu_ring *ring);
 ssize_t amdgpu_show_reset_mask(char *buf, uint32_t supported_reset);

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

@@ -391,6 +391,7 @@ static void aca_banks_generate_cper(struct amdgpu_device *adev,
 {
 	struct aca_bank_node *node;
 	struct aca_bank *bank;
+	int r;
 
 	if (!adev->cper.enabled)
 		return;
@@ -402,11 +403,27 @@ static void aca_banks_generate_cper(struct amdgpu_device *adev,
 
 	/* UEs must be encoded into separate CPER entries */
 	if (type == ACA_SMU_TYPE_UE) {
+		struct aca_banks de_banks;
+
+		aca_banks_init(&de_banks);
 		list_for_each_entry(node, &banks->list, node) {
 			bank = &node->bank;
-			if (amdgpu_cper_generate_ue_record(adev, bank))
-				dev_warn(adev->dev, "fail to generate ue cper records\n");
+			if (bank->aca_err_type == ACA_ERROR_TYPE_DEFERRED) {
+				r = aca_banks_add_bank(&de_banks, bank);
+				if (r)
+					dev_warn(adev->dev, "fail to add de banks, ret = %d\n", r);
+			} else {
+				if (amdgpu_cper_generate_ue_record(adev, bank))
+					dev_warn(adev->dev, "fail to generate ue cper records\n");
+			}
+		}
+
+		if (!list_empty(&de_banks.list)) {
+			if (amdgpu_cper_generate_ce_records(adev, &de_banks, de_banks.nr_banks))
+				dev_warn(adev->dev, "fail to generate de cper records\n");
 		}
+
+		aca_banks_release(&de_banks);
 	} else {
 		/*
 		 * SMU_TYPE_CE banks are combined into 1 CPER entries,
@@ -541,6 +558,10 @@ static int __aca_get_error_data(struct amdgpu_device *adev, struct aca_handle *h
 	if (ret)
 		return ret;
 
+	/* DEs may contain in CEs or UEs */
+	if (type != ACA_ERROR_TYPE_DEFERRED)
+		aca_log_aca_error(handle, ACA_ERROR_TYPE_DEFERRED, err_data);
+
 	return aca_log_aca_error(handle, type, err_data);
 }
 

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

@@ -76,11 +76,17 @@ struct ras_query_context;
 #define mmSMNAID_XCD1_MCA_SMU		0x38430400	/* SMN AID XCD1 */
 #define mmSMNXCD_XCD0_MCA_SMU		0x40430400	/* SMN XCD XCD0 */
 
-#define ACA_BANK_ERR_CE_DE_DECODE(bank)                                  \
-	((ACA_REG__STATUS__POISON((bank)->regs[ACA_REG_IDX_STATUS]) ||   \
-	  ACA_REG__STATUS__DEFERRED((bank)->regs[ACA_REG_IDX_STATUS])) ? \
-		ACA_ERROR_TYPE_DEFERRED :                                \
-		ACA_ERROR_TYPE_CE)
+#define ACA_BANK_ERR_IS_DEFFERED(bank)                                \
+	(ACA_REG__STATUS__POISON((bank)->regs[ACA_REG_IDX_STATUS]) || \
+	 ACA_REG__STATUS__DEFERRED((bank)->regs[ACA_REG_IDX_STATUS]))
+
+#define ACA_BANK_ERR_CE_DE_DECODE(bank)                             \
+	(ACA_BANK_ERR_IS_DEFFERED(bank) ? ACA_ERROR_TYPE_DEFERRED : \
+					  ACA_ERROR_TYPE_CE)
+
+#define ACA_BANK_ERR_UE_DE_DECODE(bank)                             \
+	(ACA_BANK_ERR_IS_DEFFERED(bank) ? ACA_ERROR_TYPE_DEFERRED : \
+					  ACA_ERROR_TYPE_UE)
 
 enum aca_reg_idx {
 	ACA_REG_IDX_CTL			= 0,

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

@@ -491,7 +491,7 @@ static int vm_update_pds(struct amdgpu_vm *vm, struct amdgpu_sync *sync)
 	if (ret)
 		return ret;
 
-	return amdgpu_sync_fence(sync, vm->last_update);
+	return amdgpu_sync_fence(sync, vm->last_update, GFP_KERNEL);
 }
 
 static uint64_t get_pte_flags(struct amdgpu_device *adev, struct kgd_mem *mem)
@@ -1249,7 +1249,7 @@ static int unmap_bo_from_gpuvm(struct kgd_mem *mem,
 
 	(void)amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update);
 
-	(void)amdgpu_sync_fence(sync, bo_va->last_pt_update);
+	(void)amdgpu_sync_fence(sync, bo_va->last_pt_update, GFP_KERNEL);
 
 	return 0;
 }
@@ -1273,7 +1273,7 @@ static int update_gpuvm_pte(struct kgd_mem *mem,
 		return ret;
 	}
 
-	return amdgpu_sync_fence(sync, bo_va->last_pt_update);
+	return amdgpu_sync_fence(sync, bo_va->last_pt_update, GFP_KERNEL);
 }
 
 static int map_bo_to_gpuvm(struct kgd_mem *mem,
@@ -2913,7 +2913,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
 		}
 		dma_resv_for_each_fence(&cursor, bo->tbo.base.resv,
 					DMA_RESV_USAGE_KERNEL, fence) {
-			ret = amdgpu_sync_fence(&sync_obj, fence);
+			ret = amdgpu_sync_fence(&sync_obj, fence, GFP_KERNEL);
 			if (ret) {
 				pr_debug("Memory eviction: Sync BO fence failed. Try again\n");
 				goto validate_map_fail;

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

@@ -455,10 +455,10 @@ static u32 amdgpu_cper_ring_get_ent_sz(struct amdgpu_ring *ring, u64 pos)
 		return umin(rec_len, chunk);
 }
 
-void amdgpu_cper_ring_write(struct amdgpu_ring *ring,
-					      void *src, int count)
+void amdgpu_cper_ring_write(struct amdgpu_ring *ring, void *src, int count)
 {
 	u64 pos, wptr_old, rptr = *ring->rptr_cpu_addr & ring->ptr_mask;
+	int rec_cnt_dw = count >> 2;
 	u32 chunk, ent_sz;
 	u8 *s = (u8 *)src;
 
@@ -485,6 +485,9 @@ void amdgpu_cper_ring_write(struct amdgpu_ring *ring,
 		s += chunk;
 	}
 
+	if (ring->count_dw < rec_cnt_dw)
+		ring->count_dw = 0;
+
 	/* the buffer is overflow, adjust rptr */
 	if (((wptr_old < rptr) && (rptr <= ring->wptr)) ||
 	    ((ring->wptr < wptr_old) && (wptr_old < rptr)) ||
@@ -501,12 +504,10 @@ void amdgpu_cper_ring_write(struct amdgpu_ring *ring,
 			pos = rptr;
 		} while (!amdgpu_cper_is_hdr(ring, rptr));
 	}
-	mutex_unlock(&ring->adev->cper.ring_lock);
 
-	if (ring->count_dw >= (count >> 2))
-		ring->count_dw -= (count >> 2);
-	else
-		ring->count_dw = 0;
+	if (ring->count_dw >= rec_cnt_dw)
+		ring->count_dw -= rec_cnt_dw;
+	mutex_unlock(&ring->adev->cper.ring_lock);
 }
 
 static u64 amdgpu_cper_ring_get_rptr(struct amdgpu_ring *ring)

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

@@ -428,7 +428,7 @@ static int amdgpu_cs_p2_dependencies(struct amdgpu_cs_parser *p,
 			dma_fence_put(old);
 		}
 
-		r = amdgpu_sync_fence(&p->sync, fence);
+		r = amdgpu_sync_fence(&p->sync, fence, GFP_KERNEL);
 		dma_fence_put(fence);
 		if (r)
 			return r;
@@ -450,7 +450,7 @@ static int amdgpu_syncobj_lookup_and_add(struct amdgpu_cs_parser *p,
 		return r;
 	}
 
-	r = amdgpu_sync_fence(&p->sync, fence);
+	r = amdgpu_sync_fence(&p->sync, fence, GFP_KERNEL);
 	dma_fence_put(fence);
 	return r;
 }
@@ -1111,7 +1111,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 			struct drm_gpu_scheduler *sched = entity->rq->sched;
 			struct amdgpu_ring *ring = to_amdgpu_ring(sched);
 
-			if (amdgpu_vmid_uses_reserved(adev, vm, ring->vm_hub))
+			if (amdgpu_vmid_uses_reserved(vm, ring->vm_hub))
 				return -EINVAL;
 		}
 	}
@@ -1124,7 +1124,8 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = amdgpu_sync_fence(&p->sync, fpriv->prt_va->last_pt_update);
+	r = amdgpu_sync_fence(&p->sync, fpriv->prt_va->last_pt_update,
+			      GFP_KERNEL);
 	if (r)
 		return r;
 
@@ -1135,7 +1136,8 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 		if (r)
 			return r;
 
-		r = amdgpu_sync_fence(&p->sync, bo_va->last_pt_update);
+		r = amdgpu_sync_fence(&p->sync, bo_va->last_pt_update,
+				      GFP_KERNEL);
 		if (r)
 			return r;
 	}
@@ -1154,7 +1156,8 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 		if (r)
 			return r;
 
-		r = amdgpu_sync_fence(&p->sync, bo_va->last_pt_update);
+		r = amdgpu_sync_fence(&p->sync, bo_va->last_pt_update,
+				      GFP_KERNEL);
 		if (r)
 			return r;
 	}
@@ -1167,7 +1170,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = amdgpu_sync_fence(&p->sync, vm->last_update);
+	r = amdgpu_sync_fence(&p->sync, vm->last_update, GFP_KERNEL);
 	if (r)
 		return r;
 
@@ -1248,7 +1251,8 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p)
 			continue;
 		}
 
-		r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence);
+		r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence,
+				      GFP_KERNEL);
 		dma_fence_put(fence);
 		if (r)
 			return r;