[PATCH 2/2] drm/amdgpu: Implement gfx9 patch functions for resubmission

[Alex Deucher]

Series is:
Acked-by: Alex Deucher <alexander.deucher at amd.com>

On Thu, May 25, 2023 at 9:19 PM <jiadong.zhu at amd.com> wrote:
>
> From: Jiadong Zhu <Jiadong.Zhu at amd.com>
>
> Patch the packages including CONTEXT_CONTROL and WRITE_DATA for gfx9
> during the resubmission scenario.
>
> Signed-off-by: Jiadong Zhu <Jiadong.Zhu at amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 80 +++++++++++++++++++++++++++
>  1 file changed, 80 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> index cbcf6126cce5..4fbeb9b5752c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> @@ -5172,9 +5172,83 @@ static void gfx_v9_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
>  #endif
>                 lower_32_bits(ib->gpu_addr));
>         amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
> +       amdgpu_ring_ib_on_emit_cntl(ring);
>         amdgpu_ring_write(ring, control);
>  }
>
> +static void gfx_v9_0_ring_patch_cntl(struct amdgpu_ring *ring,
> +                                    unsigned offset)
> +{
> +       u32 control = ring->ring[offset];
> +
> +       control |= INDIRECT_BUFFER_PRE_RESUME(1);
> +       ring->ring[offset] = control;
> +}
> +
> +static void gfx_v9_0_ring_patch_ce_meta(struct amdgpu_ring *ring,
> +                                       unsigned offset)
> +{
> +       struct amdgpu_device *adev = ring->adev;
> +       void *ce_payload_cpu_addr;
> +       uint64_t payload_offset, payload_size;
> +
> +       payload_size = sizeof(struct v9_ce_ib_state);
> +
> +       if (ring->is_mes_queue) {
> +               payload_offset = offsetof(struct amdgpu_mes_ctx_meta_data,
> +                                         gfx[0].gfx_meta_data) +
> +                       offsetof(struct v9_gfx_meta_data, ce_payload);
> +               ce_payload_cpu_addr =
> +                       amdgpu_mes_ctx_get_offs_cpu_addr(ring, payload_offset);
> +       } else {
> +               payload_offset = offsetof(struct v9_gfx_meta_data, ce_payload);
> +               ce_payload_cpu_addr = adev->virt.csa_cpu_addr + payload_offset;
> +       }
> +
> +       if (offset + (payload_size >> 2) <= ring->buf_mask + 1) {
> +               memcpy((void *)&ring->ring[offset], ce_payload_cpu_addr, payload_size);
> +       } else {
> +               memcpy((void *)&ring->ring[offset], ce_payload_cpu_addr,
> +                      (ring->buf_mask + 1 - offset) << 2);
> +               payload_size -= (ring->buf_mask + 1 - offset) << 2;
> +               memcpy((void *)&ring->ring[0],
> +                      ce_payload_cpu_addr + ((ring->buf_mask + 1 - offset) << 2),
> +                      payload_size);
> +       }
> +}
> +
> +static void gfx_v9_0_ring_patch_de_meta(struct amdgpu_ring *ring,
> +                                       unsigned offset)
> +{
> +       struct amdgpu_device *adev = ring->adev;
> +       void *de_payload_cpu_addr;
> +       uint64_t payload_offset, payload_size;
> +
> +       payload_size = sizeof(struct v9_de_ib_state);
> +
> +       if (ring->is_mes_queue) {
> +               payload_offset = offsetof(struct amdgpu_mes_ctx_meta_data,
> +                                         gfx[0].gfx_meta_data) +
> +                       offsetof(struct v9_gfx_meta_data, de_payload);
> +               de_payload_cpu_addr =
> +                       amdgpu_mes_ctx_get_offs_cpu_addr(ring, payload_offset);
> +       } else {
> +               payload_offset = offsetof(struct v9_gfx_meta_data, de_payload);
> +               de_payload_cpu_addr = adev->virt.csa_cpu_addr + payload_offset;
> +       }
> +
> +       if (offset + (payload_size >> 2) <= ring->buf_mask + 1) {
> +               memcpy((void *)&ring->ring[offset], de_payload_cpu_addr, payload_size);
> +       } else {
> +               memcpy((void *)&ring->ring[offset], de_payload_cpu_addr,
> +                      (ring->buf_mask + 1 - offset) << 2);
> +               payload_size -= (ring->buf_mask + 1 - offset) << 2;
> +               memcpy((void *)&ring->ring[0],
> +                      de_payload_cpu_addr + ((ring->buf_mask + 1 - offset) << 2),
> +                      payload_size);
> +       }
> +}
> +
>  static void gfx_v9_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
>                                           struct amdgpu_job *job,
>                                           struct amdgpu_ib *ib,
> @@ -5370,6 +5444,8 @@ static void gfx_v9_0_ring_emit_ce_meta(struct amdgpu_ring *ring, bool resume)
>         amdgpu_ring_write(ring, lower_32_bits(ce_payload_gpu_addr));
>         amdgpu_ring_write(ring, upper_32_bits(ce_payload_gpu_addr));
>
> +       amdgpu_ring_ib_on_emit_ce(ring);
> +
>         if (resume)
>                 amdgpu_ring_write_multiple(ring, ce_payload_cpu_addr,
>                                            sizeof(ce_payload) >> 2);
> @@ -5481,6 +5557,7 @@ static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume, bo
>         amdgpu_ring_write(ring, lower_32_bits(de_payload_gpu_addr));
>         amdgpu_ring_write(ring, upper_32_bits(de_payload_gpu_addr));
>
> +       amdgpu_ring_ib_on_emit_de(ring);
>         if (resume)
>                 amdgpu_ring_write_multiple(ring, de_payload_cpu_addr,
>                                            sizeof(de_payload) >> 2);
> @@ -6891,6 +6968,9 @@ static const struct amdgpu_ring_funcs gfx_v9_0_sw_ring_funcs_gfx = {
>         .emit_reg_write_reg_wait = gfx_v9_0_ring_emit_reg_write_reg_wait,
>         .soft_recovery = gfx_v9_0_ring_soft_recovery,
>         .emit_mem_sync = gfx_v9_0_emit_mem_sync,
> +       .patch_cntl = gfx_v9_0_ring_patch_cntl,
> +       .patch_de = gfx_v9_0_ring_patch_de_meta,
> +       .patch_ce = gfx_v9_0_ring_patch_ce_meta,
>  };
>
>  static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = {
> --
> 2.25.1
>