From b8f67b9ddf4f8fe6dd536590712b5912ad78f99c Mon Sep 17 00:00:00 2001 From: Shashank Sharma Date: Thu, 18 Jan 2024 20:15:42 +0100 Subject: drm/amdgpu: change vm->task_info handling This patch changes the handling and lifecycle of vm->task_info object. The major changes are: - vm->task_info is a dynamically allocated ptr now, and its uasge is reference counted. - introducing two new helper funcs for task_info lifecycle management - amdgpu_vm_get_task_info: reference counts up task_info before returning this info - amdgpu_vm_put_task_info: reference counts down task_info - last put to task_info() frees task_info from the vm. This patch also does logistical changes required for existing usage of vm->task_info. V2: Do not block all the prints when task_info not found (Felix) V3: Fixed review comments from Felix - Fix wrong indentation - No debug message for -ENOMEM - Add NULL check for task_info - Do not duplicate the debug messages (ti vs no ti) - Get first reference of task_info in vm_init(), put last in vm_fini() V4: Fixed review comments from Felix - fix double reference increment in create_task_info - change amdgpu_vm_get_task_info_pasid - additional changes in amdgpu_gem.c while porting Cc: Christian Koenig Cc: Alex Deucher Cc: Felix Kuehling Reviewed-by: Felix Kuehling Signed-off-by: Shashank Sharma Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c') diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 969a9e867170..d20e5f20ee31 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -1445,18 +1445,24 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev, gmc_v8_0_set_fault_enable_default(adev, false); if (printk_ratelimit()) { - struct amdgpu_task_info task_info; + struct amdgpu_task_info *task_info; - memset(&task_info, 0, sizeof(struct amdgpu_task_info)); - amdgpu_vm_get_task_info(adev, entry->pasid, &task_info); + dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n", + entry->src_id, entry->src_data[0]); + + task_info = amdgpu_vm_get_task_info_pasid(adev, entry->pasid); + if (task_info) { + dev_err(adev->dev, " for process %s pid %d thread %s pid %d\n", + task_info->process_name, task_info->tgid, + task_info->task_name, task_info->pid); + amdgpu_vm_put_task_info(task_info); + } - dev_err(adev->dev, "GPU fault detected: %d 0x%08x for process %s pid %d thread %s pid %d\n", - entry->src_id, entry->src_data[0], task_info.process_name, - task_info.tgid, task_info.task_name, task_info.pid); dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n", - addr); + addr); dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n", status); + gmc_v8_0_vm_decode_fault(adev, status, addr, mc_client, entry->pasid); } -- cgit v1.2.3