drm/amdgpu: Fix off-by-one errors in amdgpu_vm_bo_map
authorFelix Kuehling <Felix.Kuehling@amd.com>
Mon, 23 Nov 2015 22:43:48 +0000 (17:43 -0500)
committerAlex Deucher <alexander.deucher@amd.com>
Mon, 21 Dec 2015 21:39:14 +0000 (16:39 -0500)
commit005ae95e6ec119c64e2d16eb65a94c49e1dcf9f0
tree8739151b1ce8a4d1645e980a9297abe9a4936bc8
parent42ef344c0994cc453477afdc7a8eadc578ed0257
drm/amdgpu: Fix off-by-one errors in amdgpu_vm_bo_map

eaddr is sometimes treated as the last address inside the address
range, and sometimes as the first address outside the range. This
was resulting in errors when a test filled up the entire address
space. Make it consistent to always be the last address within the
range.

Signed-off-by: Felix.Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Cc: stable@vger.kernel.org
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c