On Tue, Aug 6, 2019 at 7:26 AM Christian König ckoenig.leichtzumerken@gmail.com wrote:
Am 06.08.19 um 12:31 schrieb Tao Zhou:
readq/writeq can't be found on arm architecture, implement them with 32 bits operations
Mhm, wasn't the whole point about using readq/writeq that we needed 64bit atomic operations?
It might be better to use atomic64_read/atomic64_set like we do for doorbells.
Alex
Christian.
Signed-off-by: Tao Zhou tao.zhou1@amd.com
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index f62d4f30e810..aaf7f31cf8df 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -29,6 +29,7 @@ #include <linux/kthread.h> #include <linux/console.h> #include <linux/slab.h> +#include <linux/io-64-nonatomic-lo-hi.h> #include <drm/drmP.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_probe_helper.h>
amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx