Quoting Chris Wilson (2017-11-07 21:31:20) > The handling of contexts are peculiar. Instead of tieing their vma to > activity, we pin the context. This means that we cannot simply unbind > the context object itself at will (which would normally cause us to wait > for the vma to be idle), but must manually idle the GPU and retire > requests first. > > A consequence of this peculiarity is when doing a last desperate attempt > to recover memory. If the memory is tied up inside active context > objects, we will fail to recover any memory simply by trying to unbind > the objects without first doing a wait-for-idle. However, we are totally not allowed to use ordinary allocs here, making sending a request next to impossible. We'll just have to wait for idle and nothing more. Alternatively we have a specially crafted request just for the shrinker... Ugh. -Chris _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
