I wonder whether having the language know about array bounds (i.e. memory safety) makes it easier to deploy mitigations against Spectre…
-
-
The first thing that came to mind was .get(i).cloned() - it's easier when it's a panic or abort, but you can just as well go through libraries and rely on optimizations to place the instructions close together.
-
I’m not sure what you’re saying here. Presumably .get(i) would also load without speculation, right?
- 5 more replies
New conversation -
-
-
Have you seen the ARM whitepaper and the new CSDB insn? It seems related to this but I'm still trying to wrap my head around it.
-
In particular, I'm a little unclear on how a compiler would figure out how/where to insert their workarounds in the general case for e.g. C code, but as part of a check-and-load gadget it might be a simpler problem?
- 2 more replies
New conversation -
-
-
apparently on Intel CPUs there is a way to stop speculation for indirect branches: https://lkml.org/lkml/2018/1/3/770 …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.