Quoting Thomas Hellström (Intel) (2020-07-27 19:19:19) > > On 7/15/20 1:51 PM, Chris Wilson wrote: > > It is illegal to wait on an another vma while holding the vm->mutex, as > > that easily leads to ABBA deadlocks (we wait on a second vma that waits > > on us to release the vm->mutex). So while the vm->mutex exists, move the > > waiting outside of the lock into the async binding pipeline. > > Why is it we don't just move the fence binding to a separate loop after > unlocking the vm->mutex in eb_reserve_vm()? That is what is done. The work is called immediately when possible. Just the loop may be deferred if the what we need to unbind are still active. -Chris _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
