I have some questionmarks how usabilitywise #intelbug will turn out. from what I see it seems the bug can be worked around with heavy performance costs. So: will the workaround be always on?
I suspect that real-world performance hits will depend on the proportion of syscalls in the code being executed. As for permanence of the workaround, I'd guess that we won't know until fixed silicon is seen, and what checks can be made to detect the presence of those chips.
-
-
Not just syscalls. Any user to kernel mode switching, including paging and interrupts.
-
But yeah, other than preliminary
@phoronix results the real impact isn't known (https://www.phoronix.com/scan.php?page=article&item=linux-415-x86pti&num=2 …) - 3 more replies
New conversation -
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.