This probably kills 5 9s of performance whereas timer interrupt every 100ns to clobber BTB would only kill 4...
So that one code path in the victim process can't be coerced into leaking unrelated parts of the process's own memory. That's what Spectre v1 is.
-
-
The only mitigation without new Si is to turn off speculative execution across branches, and cpu vendors won't give us an MSR for that (because perf hit looks bad on them), so forcibly prevent branch prediction instead using HT.
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.