[RFC 1/7] drm/amdgpu: UAPI for user queue management

[Bas Nieuwenhuizen]

On Fri, Dec 23, 2022 at 8:37 PM Shashank Sharma <shashank.sharma at amd.com> wrote:
>
> From: Alex Deucher <alexander.deucher at amd.com>
>
> This patch intorduces new UAPI/IOCTL for usermode graphics
> queue. The userspace app will fill this structure and request
> the graphics driver to add a graphics work queue for it. The
> output of this UAPI is a queue id.
>
> This UAPI maps the queue into GPU, so the graphics app can start
> submitting work to the queue as soon as the call returns.
>
> Cc: Alex Deucher <alexander.deucher at amd.com>
> Cc: Christian Koenig <christian.koenig at amd.com>
> Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
> Signed-off-by: Shashank Sharma <shashank.sharma at amd.com>
> ---
>  include/uapi/drm/amdgpu_drm.h | 52 +++++++++++++++++++++++++++++++++++
>  1 file changed, 52 insertions(+)
>
> diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
> index 0d93ec132ebb..a3d0dd6f62c5 100644
> --- a/include/uapi/drm/amdgpu_drm.h
> +++ b/include/uapi/drm/amdgpu_drm.h
> @@ -54,6 +54,7 @@ extern "C" {
>  #define DRM_AMDGPU_VM                  0x13
>  #define DRM_AMDGPU_FENCE_TO_HANDLE     0x14
>  #define DRM_AMDGPU_SCHED               0x15
> +#define DRM_AMDGPU_USERQ               0x16
>
>  #define DRM_IOCTL_AMDGPU_GEM_CREATE    DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_CREATE, union drm_amdgpu_gem_create)
>  #define DRM_IOCTL_AMDGPU_GEM_MMAP      DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_MMAP, union drm_amdgpu_gem_mmap)
> @@ -71,6 +72,7 @@ extern "C" {
>  #define DRM_IOCTL_AMDGPU_VM            DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_VM, union drm_amdgpu_vm)
>  #define DRM_IOCTL_AMDGPU_FENCE_TO_HANDLE DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_FENCE_TO_HANDLE, union drm_amdgpu_fence_to_handle)
>  #define DRM_IOCTL_AMDGPU_SCHED         DRM_IOW(DRM_COMMAND_BASE + DRM_AMDGPU_SCHED, union drm_amdgpu_sched)
> +#define DRM_IOCTL_AMDGPU_USERQ         DRM_IOW(DRM_COMMAND_BASE + DRM_AMDGPU_USERQ, union drm_amdgpu_userq)
>
>  /**
>   * DOC: memory domains
> @@ -288,6 +290,56 @@ union drm_amdgpu_ctx {
>         union drm_amdgpu_ctx_out out;
>  };
>
> +/* user queue IOCTL */
> +#define AMDGPU_USERQ_OP_CREATE 1
> +#define AMDGPU_USERQ_OP_FREE   2
> +
> +#define AMDGPU_USERQ_MQD_FLAGS_SECURE  (1 << 0)
> +#define AMDGPU_USERQ_MQD_FLAGS_AQL     (1 << 1)

Can we document what AQL means here?


> +
> +struct drm_amdgpu_userq_mqd {
> +       /** Flags: AMDGPU_USERQ_MQD_FLAGS_* */
> +       __u32   flags;
> +       /** IP type: AMDGPU_HW_IP_* */
> +       __u32   ip_type;
> +       /** GEM object handle */
> +       __u32   doorbell_handle;
> +       /** Doorbell offset in dwords */
> +       __u32   doorbell_offset;

What are the doorbell handle/offset for? I don't see any of them used
in the rest of the series (we only check the handle isn't 0, which
isn't enough validation for a GEM handle to consider it valid), and
the kernel seems to allocate some kind of doorbell index in patch 4.
Does userspace need to know about that one? (similarly use_doorbell in
that patch seems like it is never explicitly written to)

The other questions I have are about how this interacts with memory
management. Does this have access to all BOs allocated with
AMDGPU_GEM_CREATE_VM_ALWAYS_VALID? What about imported BOs? How does
this interact with VA unmap/map operations? (AFAICT we have no way to
tell if pagetable modifying operations are complete from userspace for
now). What happens if we need to spill BOs from VRAM due to
(cross-process) memory pressure?

> +       /** GPU virtual address of the queue */
> +       __u64   queue_va;
> +       /** Size of the queue in bytes */
> +       __u64   queue_size;
> +       /** GPU virtual address of the rptr */
> +       __u64   rptr_va;
> +       /** GPU virtual address of the wptr */
> +       __u64   wptr_va;
> +};
> +
> +struct drm_amdgpu_userq_in {
> +       /** AMDGPU_USERQ_OP_* */
> +       __u32   op;
> +       /** Flags */
> +       __u32   flags;
> +       /** Context handle to associate the queue with */
> +       __u32   ctx_id;
> +       __u32   pad;
> +       /** Queue descriptor */
> +       struct drm_amdgpu_userq_mqd mqd;
> +};
> +
> +struct drm_amdgpu_userq_out {
> +       /** Queue handle */
> +       __u32   q_id;
> +       /** Flags */
> +       __u32   flags;
> +};
> +
> +union drm_amdgpu_userq {
> +       struct drm_amdgpu_userq_in in;
> +       struct drm_amdgpu_userq_out out;
> +};
> +
>  /* vm ioctl */
>  #define AMDGPU_VM_OP_RESERVE_VMID      1
>  #define AMDGPU_VM_OP_UNRESERVE_VMID    2
> --
> 2.34.1
>