1 files changed, 26 insertions, 9 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index e9f0e0a1b41c..908081c85de1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -852,8 +852,8 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p,
 
 	if (type == KFD_EVENT_TYPE_MEMORY) {
 		dev_warn(kfd_device,
-			"Sending SIGSEGV to HSA Process with PID %d ",
-				p->lead_thread->pid);
+			"Sending SIGSEGV to process %d (pasid 0x%x)",
+				p->lead_thread->pid, p->pasid);
 		send_sig(SIGSEGV, p->lead_thread, 0);
 	}
 
@@ -861,13 +861,13 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p,
 	if (send_signal) {
 		if (send_sigterm) {
 			dev_warn(kfd_device,
-				"Sending SIGTERM to HSA Process with PID %d ",
-					p->lead_thread->pid);
+				"Sending SIGTERM to process %d (pasid 0x%x)",
+					p->lead_thread->pid, p->pasid);
 			send_sig(SIGTERM, p->lead_thread, 0);
 		} else {
 			dev_err(kfd_device,
-				"HSA Process (PID %d) got unhandled exception",
-				p->lead_thread->pid);
+				"Process %d (pasid 0x%x) got unhandled exception",
+				p->lead_thread->pid, p->pasid);
 		}
 	}
 }
@@ -936,7 +936,8 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
 	/* Workaround on Raven to not kill the process when memory is freed
 	 * before IOMMU is able to finish processing all the excessive PPRs
 	 */
-	if (dev->device_info->asic_family != CHIP_RAVEN) {
+	if (dev->device_info->asic_family != CHIP_RAVEN &&
+	    dev->device_info->asic_family != CHIP_RENOIR) {
 		mutex_lock(&p->event_mutex);
 
 		/* Lookup events by type and signal them */
@@ -983,7 +984,7 @@ void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
 		return; /* Presumably process exited. */
 	memset(&memory_exception_data, 0, sizeof(memory_exception_data));
 	memory_exception_data.gpu_id = dev->id;
-	memory_exception_data.failure.imprecise = 1;
+	memory_exception_data.failure.imprecise = true;
 	/* Set failure reason */
 	if (info) {
 		memory_exception_data.va = (info->page_addr) << PAGE_SHIFT;
@@ -1011,25 +1012,41 @@ void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
 void kfd_signal_reset_event(struct kfd_dev *dev)
 {
 	struct kfd_hsa_hw_exception_data hw_exception_data;
+	struct kfd_hsa_memory_exception_data memory_exception_data;
 	struct kfd_process *p;
 	struct kfd_event *ev;
 	unsigned int temp;
 	uint32_t id, idx;
+	int reset_cause = atomic_read(&dev->sram_ecc_flag) ?
+			KFD_HW_EXCEPTION_ECC :
+			KFD_HW_EXCEPTION_GPU_HANG;
 
 	/* Whole gpu reset caused by GPU hang and memory is lost */
 	memset(&hw_exception_data, 0, sizeof(hw_exception_data));
 	hw_exception_data.gpu_id = dev->id;
 	hw_exception_data.memory_lost = 1;
+	hw_exception_data.reset_cause = reset_cause;
+
+	memset(&memory_exception_data, 0, sizeof(memory_exception_data));
+	memory_exception_data.ErrorType = KFD_MEM_ERR_SRAM_ECC;
+	memory_exception_data.gpu_id = dev->id;
+	memory_exception_data.failure.imprecise = true;
 
 	idx = srcu_read_lock(&kfd_processes_srcu);
 	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
 		mutex_lock(&p->event_mutex);
 		id = KFD_FIRST_NONSIGNAL_EVENT_ID;
-		idr_for_each_entry_continue(&p->event_idr, ev, id)
+		idr_for_each_entry_continue(&p->event_idr, ev, id) {
 			if (ev->type == KFD_EVENT_TYPE_HW_EXCEPTION) {
 				ev->hw_exception_data = hw_exception_data;
 				set_event(ev);
 			}
+			if (ev->type == KFD_EVENT_TYPE_MEMORY &&
+			    reset_cause == KFD_HW_EXCEPTION_ECC) {
+				ev->memory_exception_data = memory_exception_data;
+				set_event(ev);
+			}
+		}
 		mutex_unlock(&p->event_mutex);
 	}
 	srcu_read_unlock(&kfd_processes_srcu, idx);