diff options
| author | Christian König <christian.koenig@amd.com> | 2024-10-08 18:23:22 +0300 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2024-10-28 23:32:03 +0300 |
| commit | 57e92d991e31ee237774aa9390586fad83630634 (patch) | |
| tree | e34e26711f597ddb5f2b2e4160e60fc2aabb729c /drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | |
| parent | dac64cb3e029e9ae9ca251798bcb9cdb118d68d5 (diff) | |
| download | linux-57e92d991e31ee237774aa9390586fad83630634.tar.xz | |
drm/amdgpu: drop volatile from ring buffer
Volatile only prevents the compiler from re-ordering reads and writes.
Since we always only modify the ring buffer from one CPU thread and have
an explicit barrier before signaling the HW this should have no effect at
all and just prevents compiler optimisations.
While at it drop the local variables as well.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Sunil Khatri <sunil.khatri@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 11 |
1 files changed, 4 insertions, 7 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 574336d6714a..36fc9578c53c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -246,7 +246,7 @@ struct amdgpu_ring { struct drm_gpu_scheduler sched; struct amdgpu_bo *ring_obj; - volatile uint32_t *ring; + uint32_t *ring; unsigned rptr_offs; u64 rptr_gpu_addr; volatile u32 *rptr_cpu_addr; @@ -288,7 +288,7 @@ struct amdgpu_ring { u64 cond_exe_gpu_addr; volatile u32 *cond_exe_cpu_addr; unsigned int set_q_mode_offs; - volatile u32 *set_q_mode_ptr; + u32 *set_q_mode_ptr; u64 set_q_mode_token; unsigned vm_hub; unsigned vm_inv_eng; @@ -386,10 +386,8 @@ static inline void amdgpu_ring_write_multiple(struct amdgpu_ring *ring, void *src, int count_dw) { unsigned occupied, chunk1, chunk2; - void *dst; occupied = ring->wptr & ring->buf_mask; - dst = (void *)&ring->ring[occupied]; chunk1 = ring->buf_mask + 1 - occupied; chunk1 = (chunk1 >= count_dw) ? count_dw : chunk1; chunk2 = count_dw - chunk1; @@ -397,12 +395,11 @@ static inline void amdgpu_ring_write_multiple(struct amdgpu_ring *ring, chunk2 <<= 2; if (chunk1) - memcpy(dst, src, chunk1); + memcpy(&ring->ring[occupied], src, chunk1); if (chunk2) { src += chunk1; - dst = (void *)ring->ring; - memcpy(dst, src, chunk2); + memcpy(ring->ring, src, chunk2); } ring->wptr += count_dw; |