amdgpu_amdkfd_restore_userptr_worker() and svm_range_restore_work() reschedule themselves when validation fails with evicted objects pending. After a surprise removal the restore paths fail with -ENODEV permanently, so rescheduling just spins the worker uselessly until cancel_delayed_work_sync() in fini finally stops it - which can take a while, since process teardown itself is delayed by the dead device.
Treat -ENODEV as terminal in both workers and also stop setting evicted_bos after it. Cc: Xiaogang Chen <[email protected]> Signed-off-by: Olivier Kaloudoff <[email protected]> --- Changes in v5: - none Changes in v4: - moved the svm_range_restore_work() change here from the SVM migration patch (Felix Kuehling) - assign ret on the evicted_bos-mismatch and confirm_valid-WARN paths, fixing a latent uninitialized read introduced in v2 Changes in v3: - retitled; now covers both restore workers Changes in v2: - new --- diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index d668816..2ad6777 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -2827,6 +2827,7 @@ static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work) struct task_struct *usertask; struct mm_struct *mm; uint32_t evicted_bos; + int ret; mutex_lock(&process_info->notifier_lock); evicted_bos = process_info->evicted_bos; @@ -2846,14 +2847,16 @@ static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work) mutex_lock(&process_info->lock); - if (update_invalid_user_pages(process_info, mm)) + ret = update_invalid_user_pages(process_info, mm); + if (ret) goto unlock_out; /* userptr_inval_list can be empty if all evicted userptr BOs * have been freed. In that case there is nothing to validate * and we can just restart the queues. */ if (!list_empty(&process_info->userptr_inval_list)) { - if (validate_invalid_user_pages(process_info)) + ret = validate_invalid_user_pages(process_info); + if (ret) goto unlock_out; } /* Final check for concurrent evicton and atomic update. If @@ -2862,11 +2865,14 @@ static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work) * reference counting inside KFD will handle this case. */ mutex_lock(&process_info->notifier_lock); - if (process_info->evicted_bos != evicted_bos) + if (process_info->evicted_bos != evicted_bos) { + ret = -EAGAIN; goto unlock_notifier_out; + } if (confirm_valid_user_pages_locked(process_info)) { WARN(1, "User pages unexpectedly invalid"); + ret = -EINVAL; goto unlock_notifier_out; } @@ -2884,8 +2890,10 @@ unlock_notifier_out: unlock_out: mutex_unlock(&process_info->lock); - /* If validation failed, reschedule another attempt */ - if (evicted_bos) { + /* If validation failed, reschedule another attempt, unless the + * device is gone for good + */ + if (evicted_bos && ret != -ENODEV) { queue_delayed_work(system_freezable_wq, &process_info->restore_userptr_work, msecs_to_jiffies(AMDGPU_USERPTR_RESTORE_DELAY_MS)); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index fa4054d..3dab456 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -2013,8 +2013,10 @@ out_reschedule: mmap_write_unlock(mm); mutex_unlock(&process_info->lock); - /* If validation failed, reschedule another attempt */ - if (evicted_ranges) { + /* If validation failed, reschedule another attempt, unless the + * device is gone for good + */ + if (evicted_ranges && r != -ENODEV) { pr_debug("reschedule to restore svm range\n"); queue_delayed_work(system_freezable_wq, &svms->restore_work, msecs_to_jiffies(AMDGPU_SVM_RANGE_RESTORE_DELAY_MS)); -- 2.47.3
