On 4/30/25 17:48, Alex Deucher wrote:
> Query the status of the user queue, currently whether
> the queue is hung and whether or not VRAM is lost.
>
> Reviewed-by: Sunil Khatri <sunil.kha...@amd.com>
> Signed-off-by: Alex Deucher <alexander.deuc...@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c | 47 ++++++++++++++++++++++-
> drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h | 1 +
> 2 files changed, 47 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
> index 4be46fa76ceba..e56fae10400db 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
> @@ -460,6 +460,7 @@ amdgpu_userq_create(struct drm_file *filp, union
> drm_amdgpu_userq *args)
> queue->queue_type = args->in.ip_type;
> queue->vm = &fpriv->vm;
> queue->priority = priority;
> + queue->generation = amdgpu_vm_generation(adev, &fpriv->vm);
>
> db_info.queue_type = queue->queue_type;
> db_info.doorbell_handle = queue->doorbell_handle;
> @@ -532,6 +533,34 @@ amdgpu_userq_create(struct drm_file *filp, union
> drm_amdgpu_userq *args)
> return r;
> }
>
> +static int
> +amdgpu_userq_query_status(struct drm_file *filp, union drm_amdgpu_userq
> *args)
> +{
> + struct amdgpu_fpriv *fpriv = filp->driver_priv;
> + struct amdgpu_userq_mgr *uq_mgr = &fpriv->userq_mgr;
> + struct amdgpu_device *adev = uq_mgr->adev;
> + struct amdgpu_usermode_queue *queue;
> + int queue_id = args->in.queue_id;
> +
> + mutex_lock(&uq_mgr->userq_mutex);
> +
> + queue = amdgpu_userq_find(uq_mgr, queue_id);
> + if (!queue) {
> + dev_err(adev->dev, "Invalid queue id to query\n");
Using dev_err is probably not justified, this is more debug level.
> + mutex_unlock(&uq_mgr->userq_mutex);
> + return -EINVAL;
> + }
> + args->out_qs.flags = 0;
> + if (queue->state == AMDGPU_USERQ_STATE_HUNG)
> + args->out_qs.flags |= AMDGPU_USERQ_QUERY_STATUS_FLAGS_HUNG;
> + if (queue->generation != amdgpu_vm_generation(adev, &fpriv->vm))
> + args->out_qs.flags |= AMDGPU_USERQ_QUERY_STATUS_FLAGS_VRAMLOST;
> +
> + mutex_unlock(&uq_mgr->userq_mutex);
> +
> + return 0;
> +}
> +
> int amdgpu_userq_ioctl(struct drm_device *dev, void *data,
> struct drm_file *filp)
> {
> @@ -565,7 +594,23 @@ int amdgpu_userq_ioctl(struct drm_device *dev, void
> *data,
> if (r)
> DRM_ERROR("Failed to destroy usermode queue\n");
> break;
> -
> + case AMDGPU_USERQ_OP_QUERY_STATUS:
> + if (args->in.ip_type ||
> + args->in.doorbell_handle ||
> + args->in.doorbell_offset ||
> + args->in.flags ||
> + args->in.queue_va ||
> + args->in.queue_size ||
> + args->in.rptr_va ||
> + args->in.wptr_va ||
> + args->in.wptr_va ||
> + args->in.mqd ||
> + args->in.mqd_size)
> + return -EINVAL;
We can't expect those fields to be initialized for this operation. So checking
them is probably not a good idea.
> + r = amdgpu_userq_query_status(filp, args);
> + if (r)
> + DRM_ERROR("Failed to query usermode queue status\n");
That message is overkill we already have the message inside
amdgpu_userq_query_status().
Regards,
Christian.
> + break;
> default:
> DRM_DEBUG_DRIVER("Invalid user queue op specified: %d\n",
> args->in.op);
> return -EINVAL;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
> index 6ede08dd821d2..35a08ee59d893 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
> @@ -65,6 +65,7 @@ struct amdgpu_usermode_queue {
> struct dma_fence *last_fence;
> u32 xcp_id;
> int priority;
> + uint64_t generation;
> };
>
> struct amdgpu_userq_funcs {
