[Lima] [PATCH v7 2/2] drm/lima: driver for ARM Mali4xx GPUs

[Dave Airlie]

> +#endif
> diff --git a/include/uapi/drm/lima_drm.h b/include/uapi/drm/lima_drm.h
> new file mode 100644
> index 000000000000..05f8c910d7fb
> --- /dev/null
> +++ b/include/uapi/drm/lima_drm.h
> @@ -0,0 +1,164 @@
> +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */
> +/* Copyright 2017-2018 Qiang Yu <yuq825 at gmail.com> */
> +
> +#ifndef __LIMA_DRM_H__
> +#define __LIMA_DRM_H__
> +
> +#include "drm.h"
> +
> +#if defined(__cplusplus)
> +extern "C" {
> +#endif
> +
> +enum drm_lima_param_gpu_id {
> +       DRM_LIMA_PARAM_GPU_ID_UNKNOWN,
> +       DRM_LIMA_PARAM_GPU_ID_MALI400,
> +       DRM_LIMA_PARAM_GPU_ID_MALI450,
> +};
> +
> +enum drm_lima_param {
> +       DRM_LIMA_PARAM_GPU_ID,
> +       DRM_LIMA_PARAM_NUM_PP,
> +       DRM_LIMA_PARAM_GP_VERSION,
> +       DRM_LIMA_PARAM_PP_VERSION,
> +};
> +
> +/**
> + * get various information of the GPU
> + */
> +struct drm_lima_get_param {
> +       __u32 param; /* in, value in enum drm_lima_param */
> +       __u32 pad;   /* pad, must be zero */
> +       __u64 value; /* out, parameter value */
> +};
> +
> +/**
> + * create a buffer for used by GPU
> + */
> +struct drm_lima_gem_create {
> +       __u32 size;    /* in, buffer size */
> +       __u32 flags;   /* in, currently no flags, must be zero */
> +       __u32 handle;  /* out, GEM buffer handle */
> +       __u32 pad;     /* pad, must be zero */
> +};
> +
> +/**
> + * get information of a buffer
> + */
> +struct drm_lima_gem_info {
> +       __u32 handle;  /* in, GEM buffer handle */
> +       __u32 va;      /* out, virtual address mapped into GPU MMU */
> +       __u64 offset;  /* out, used to mmap this buffer to CPU */
> +};
> +
> +#define LIMA_SUBMIT_BO_READ   0x01
> +#define LIMA_SUBMIT_BO_WRITE  0x02
> +
> +/* buffer information used by one task */
> +struct drm_lima_gem_submit_bo {
> +       __u32 handle;  /* in, GEM buffer handle */
> +       __u32 flags;   /* in, buffer read/write by GPU */
> +};
> +
> +#define LIMA_GP_FRAME_REG_NUM 6
> +
> +/* frame used to setup GP for each task */
> +struct drm_lima_gp_frame {
> +       __u32 frame[LIMA_GP_FRAME_REG_NUM];
> +};
> +
> +#define LIMA_PP_FRAME_REG_NUM 23
> +#define LIMA_PP_WB_REG_NUM 12
> +
> +/* frame used to setup mali400 GPU PP for each task */
> +struct drm_lima_m400_pp_frame {
> +       __u32 frame[LIMA_PP_FRAME_REG_NUM];
> +       __u32 num_pp;
> +       __u32 wb[3 * LIMA_PP_WB_REG_NUM];
> +       __u32 plbu_array_address[4];
> +       __u32 fragment_stack_address[4];
> +};
> +
> +/* frame used to setup mali450 GPU PP for each task */
> +struct drm_lima_m450_pp_frame {
> +       __u32 frame[LIMA_PP_FRAME_REG_NUM];
> +       __u32 num_pp;
> +       __u32 wb[3 * LIMA_PP_WB_REG_NUM];
> +       __u32 use_dlbu;
> +       __u32 _pad;
> +       union {
> +               __u32 plbu_array_address[8];
> +               __u32 dlbu_regs[4];
> +       };
> +       __u32 fragment_stack_address[8];
> +};
> +
> +#define LIMA_PIPE_GP  0x00
> +#define LIMA_PIPE_PP  0x01
> +
> +#define LIMA_SUBMIT_FLAG_EXPLICIT_FENCE (1 << 0)
> +
> +/**
> + * submit a task to GPU
> + */
> +struct drm_lima_gem_submit {
> +       __u32 ctx;         /* in, context handle task is submitted to */
> +       __u32 pipe;        /* in, which pipe to use, GP/PP */
> +       __u32 nr_bos;      /* in, array length of bos field */
> +       __u32 frame_size;  /* in, size of frame field */
> +       __u64 bos;         /* in, array of drm_lima_gem_submit_bo */
> +       __u64 frame;       /* in, GP/PP frame */
> +       __u32 flags;       /* in, submit flags */
> +       __u32 out_sync;    /* in, drm_syncobj handle used to wait task finish after submission */
> +       __u32 in_sync[2];  /* in, drm_syncobj handle used to wait before start this task */
> +};

This seems a bit limited, is there a reason it's two, at least in
Vulkan drivers we'd want more than two I suspect (Vulkan may not work
on this hw anyways), but it might be required in the future to make
this extensible.

At least a comment stating why 2 was picked is sufficient for current use cases.

Thanks,
Dave