[PATCH 2/2] drm/amdgpu: handle AMDGPU_IB_FLAG_RESET_GDS_MAX_WAVE_ID on gfx10

zhoucm1 zhoucm1 at amd.com
Thu Jun 27 07:50:15 UTC 2019


any reason for not care .emit_ib_size in this one?

-David


On 2019年06月27日 06:35, Marek Olšák wrote:
> From: Marek Olšák <marek.olsak at amd.com>
>
> Signed-off-by: Marek Olšák <marek.olsak at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 17 +++++++++++++++++
>   1 file changed, 17 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
> index 6baaa65a1daa..5b807a19bbbf 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
> @@ -4257,20 +4257,36 @@ static void gfx_v10_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
>   }
>   
>   static void gfx_v10_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
>   					   struct amdgpu_job *job,
>   					   struct amdgpu_ib *ib,
>   					   uint32_t flags)
>   {
>   	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
>   	u32 control = INDIRECT_BUFFER_VALID | ib->length_dw | (vmid << 24);
>   
> +	/* Currently, there is a high possibility to get wave ID mismatch
> +	 * between ME and GDS, leading to a hw deadlock, because ME generates
> +	 * different wave IDs than the GDS expects. This situation happens
> +	 * randomly when at least 5 compute pipes use GDS ordered append.
> +	 * The wave IDs generated by ME are also wrong after suspend/resume.
> +	 * Those are probably bugs somewhere else in the kernel driver.
> +	 *
> +	 * Writing GDS_COMPUTE_MAX_WAVE_ID resets wave ID counters in ME and
> +	 * GDS to 0 for this ring (me/pipe).
> +	 */
> +	if (ib->flags & AMDGPU_IB_FLAG_RESET_GDS_MAX_WAVE_ID) {
> +		amdgpu_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
> +		amdgpu_ring_write(ring, mmGDS_COMPUTE_MAX_WAVE_ID);
> +		amdgpu_ring_write(ring, ring->adev->gds.gds_compute_max_wave_id);
> +	}
> +
>   	amdgpu_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
>   	BUG_ON(ib->gpu_addr & 0x3); /* Dword align */
>   	amdgpu_ring_write(ring,
>   #ifdef __BIG_ENDIAN
>   				(2 << 0) |
>   #endif
>   				lower_32_bits(ib->gpu_addr));
>   	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
>   	amdgpu_ring_write(ring, control);
>   }
> @@ -5103,20 +5119,21 @@ static void gfx_v10_0_set_rlc_funcs(struct amdgpu_device *adev)
>   	}
>   }
>   
>   static void gfx_v10_0_set_gds_init(struct amdgpu_device *adev)
>   {
>   	/* init asic gds info */
>   	switch (adev->asic_type) {
>   	case CHIP_NAVI10:
>   	default:
>   		adev->gds.gds_size = 0x10000;
> +		adev->gds.gds_compute_max_wave_id = 0x4ff;
>   		adev->gds.vgt_gs_max_wave_id = 0x3ff;
>   		break;
>   	}
>   
>   	adev->gds.gws_size = 64;
>   	adev->gds.oa_size = 16;
>   }
>   
>   static void gfx_v10_0_set_user_wgp_inactive_bitmap_per_sh(struct amdgpu_device *adev,
>   							  u32 bitmap)



More information about the amd-gfx mailing list