A question that pops up in my mind is: is there a mapping of all physical memory inside the kernels supported by Genode (and for which kernel is this true, besides Linux)?
One of the things mentioned in the paper:
We focus on addresses that are mapped within the at- tacker’s process, i.e., the user-accessible user space ad- dresses as well as the user-inaccessible kernel space ad- dresses. Note that attacks targeting code that is executed within the context (i.e., address space) of another process are possible [19], but out of scope in this work, since all physical memory (including the memory of other pro- cesses) can be read through the kernel address space any- way.
In other words, is it possible for the meltdown attack on genode to leak memory of other user-level components?