[PATCH 1/3] drm/amdgpu: Optimize a function called by every IB sheduling

[zhoucm1]

On 2017年05月31日 05:47, Alex Xie wrote:
>    Move several if statements and a loop statment from
>    run time to initialization time.
>
> Signed-off-by: Alex Xie <AlexBin.Xie at amd.com>
nice, Reviewed-by: Chunming Zhou <david1.zhou at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 33 ++++++++++++++++++++++++++++++++
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h |  6 ++++++
>   drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c   | 28 +--------------------------
>   3 files changed, 40 insertions(+), 27 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
> index 6a85db0..7d95435 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
> @@ -153,6 +153,36 @@ void amdgpu_ring_undo(struct amdgpu_ring *ring)
>   }
>   
>   /**
> + * amdgpu_ring_check_compute_vm_bug - check whether this ring has compute vm bug
> + *
> + * @adev: amdgpu_device pointer
> + * @ring: amdgpu_ring structure holding ring information
> + */
> +static void amdgpu_ring_check_compute_vm_bug(struct amdgpu_device *adev,
> +					struct amdgpu_ring *ring)
> +{
> +	const struct amdgpu_ip_block *ip_block;
> +
> +	ring->has_compute_vm_bug = false;
> +
> +	if (ring->funcs->type != AMDGPU_RING_TYPE_COMPUTE)
> +		/* only compute rings */
> +		return;
> +
> +	ip_block = amdgpu_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GFX);
> +	if (!ip_block)
> +		return;
> +
> +	/* Compute ring has a VM bug for GFX version < 7.
> +           And compute ring has a VM bug for GFX 8 MEC firmware version < 673.*/
> +	if (ip_block->version->major <= 7) {
> +		ring->has_compute_vm_bug = true;
> +	} else if (ip_block->version->major == 8)
> +		if (adev->gfx.mec_fw_version < 673)
> +			ring->has_compute_vm_bug = true;
> +}
> +
> +/**
>    * amdgpu_ring_init - init driver ring struct.
>    *
>    * @adev: amdgpu_device pointer
> @@ -257,6 +287,9 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
>   	if (amdgpu_debugfs_ring_init(adev, ring)) {
>   		DRM_ERROR("Failed to register debugfs file for rings !\n");
>   	}
> +
> +	amdgpu_ring_check_compute_vm_bug(adev, ring);
> +
>   	return 0;
>   }
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
> index a9223a8..334307e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
> @@ -185,6 +185,7 @@ struct amdgpu_ring {
>   	u64			cond_exe_gpu_addr;
>   	volatile u32		*cond_exe_cpu_addr;
>   	unsigned		vm_inv_eng;
> +	bool			has_compute_vm_bug;
>   #if defined(CONFIG_DEBUG_FS)
>   	struct dentry *ent;
>   #endif
> @@ -207,4 +208,9 @@ static inline void amdgpu_ring_clear_ring(struct amdgpu_ring *ring)
>   
>   }
>   
> +static inline bool amdgpu_ring_has_compute_vm_bug(struct amdgpu_ring *ring)
> +{
> +	return ring->has_compute_vm_bug;
> +}
> +
>   #endif
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> index b2384b8..7a323f9 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> @@ -656,32 +656,6 @@ static int amdgpu_vm_alloc_reserved_vmid(struct amdgpu_device *adev,
>   	return r;
>   }
>   
> -static bool amdgpu_vm_ring_has_compute_vm_bug(struct amdgpu_ring *ring)
> -{
> -	struct amdgpu_device *adev = ring->adev;
> -	const struct amdgpu_ip_block *ip_block;
> -
> -	if (ring->funcs->type != AMDGPU_RING_TYPE_COMPUTE)
> -		/* only compute rings */
> -		return false;
> -
> -	ip_block = amdgpu_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GFX);
> -	if (!ip_block)
> -		return false;
> -
> -	if (ip_block->version->major <= 7) {
> -		/* gfx7 has no workaround */
> -		return true;
> -	} else if (ip_block->version->major == 8) {
> -		if (adev->gfx.mec_fw_version >= 673)
> -			/* gfx8 is fixed in MEC firmware 673 */
> -			return false;
> -		else
> -			return true;
> -	}
> -	return false;
> -}
> -
>   bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
>   				  struct amdgpu_job *job)
>   {
> @@ -691,7 +665,7 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
>   	struct amdgpu_vm_id *id;
>   	bool gds_switch_needed;
>   	bool vm_flush_needed = job->vm_needs_flush ||
> -		amdgpu_vm_ring_has_compute_vm_bug(ring);
> +		amdgpu_ring_has_compute_vm_bug(ring);
>   
>   	if (job->vm_id == 0)
>   		return false;