drm/amdgpu: use LRU mapping policy for SDMA engines

Spreading the load across multiple SDMA engines can increase memory
transfer performance.

Signed-off-by: Andres Rodriguez <andresx7@gmail.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 1 insertions, 1 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
index 9a14c27d99d7..befc09b68543 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
@@ -276,7 +276,6 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 
         switch (mapper->hw_ip) {
         case AMDGPU_HW_IP_GFX:
-        case AMDGPU_HW_IP_DMA:
         case AMDGPU_HW_IP_UVD:
         case AMDGPU_HW_IP_VCE:
         case AMDGPU_HW_IP_UVD_ENC:
@@ -284,6 +283,7 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
         case AMDGPU_HW_IP_VCN_ENC:
                 r = amdgpu_identity_map(adev, mapper, ring, out_ring);
                 break;
+        case AMDGPU_HW_IP_DMA:
         case AMDGPU_HW_IP_COMPUTE:
                 r = amdgpu_lru_map(adev, mapper, ring, out_ring);
                 break;