提交 86c2b790 编写于 作者: J Jammy Zhou 提交者: Alex Deucher

drm/amdgpu: rewording some left radeons

Signed-off-by: NJammy Zhou <Jammy.Zhou@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
上级 c65444fe
......@@ -2164,7 +2164,7 @@ static inline struct amdgpu_fence *to_amdgpu_fence(struct fence *f)
static inline void amdgpu_ring_write(struct amdgpu_ring *ring, uint32_t v)
{
if (ring->count_dw <= 0)
DRM_ERROR("radeon: writing more dwords to the ring than expected!\n");
DRM_ERROR("amdgpu: writing more dwords to the ring than expected!\n");
ring->ring[ring->wptr++] = v;
ring->wptr &= ring->ptr_mask;
ring->count_dw--;
......
......@@ -193,13 +193,13 @@ static bool amdgpu_fence_activity(struct amdgpu_ring *ring)
* xchg of the current process.
*
* More over for this to go in infinite loop there need to be
* continuously new fence signaled ie radeon_fence_read needs
* continuously new fence signaled ie amdgpu_fence_read needs
* to return a different value each time for both the currently
* polling process and the other process that xchg the last_seq
* btw atomic read and xchg of the current process. And the
* value the other process set as last seq must be higher than
* the seq value we just read. Which means that current process
* need to be interrupted after radeon_fence_read and before
* need to be interrupted after amdgpu_fence_read and before
* atomic xchg.
*
* To be even more safe we count the number of time we loop and
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册