Op 29-01-2021 om 14:16 schreef Chris Wilson: > Quoting Maarten Lankhorst (2021-01-29 13:11:37) >> In reloc_iomap we swallow the -EDEADLK error, but this needs to >> be returned for -EDEADLK handling. Add the missing check to >> make bsw pass again. > What lock? You already have the pages reserved, why are we not just using > the earlier reservation. > -Chris
We start taking locks on the vm ggtt objects, this is going to break with the object mm lock removal break. So easiest fix is to add missing -EDEADLK here. Any pinning operation may fail with -EDEADLK, it's something we should always handle. ~Maarten _______________________________________________ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/intel-gfx
