Merge the two loops, loosen the restriction for big allocations.
This reduces the CPU overhead in the good case, but increases
it a bit under memory pressure.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-and-Tested-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>