Re:Researchers have significantly increased the scope of the...
by kibwen on Sunday December 02, 2018 @08:41PM
(#18585779)
I wonder if having a separate stick of RAM exclusively dedicated to kernelspace would provide any mitigation against privelige escalation via rowhammer. Are we considering a future where every "ring" is literally a separate set of CPU, RAM, etc in order to stymie side channels, or is that just too crazy?
[ Parent
| on HN ]
Re:Researchers have significantly increased the scope of the...
by ghthor on Sunday December 02, 2018 @09:01PM
(#18585845)
Sounds good to me, would be fun to piece that together and pick different types of parts for each different function.
Re:Researchers have significantly increased the scope of the...
by saati on Monday December 03, 2018 @06:41AM
(#18588016)
Wouldn't help against rowhammer via ethernet[1].
[1] https://www.cs.vu.nl/~herbertb/download/papers/throwhammer_a...
Re:Researchers have significantly increased the scope of the...
by paulryanrogers on Sunday December 02, 2018 @09:05PM
(#18585866)
If kernel space were relatively small this might be practical as a motherboard feature, possibly soldered in place. Though I doubt it'll become standard unless there are no other alternatives since it seems like a very specialized solution.
Re:Researchers have significantly increased the scope of the...
by Insequent on Monday December 03, 2018 @12:54AM
(#18586648)
The kernel's memory usage is typically pretty small, unless you're considering the page cache to be part of it.
Although: I once investigated a soft freeze on a realtime-patched Linux system that turned out to be caused by a vendor's software somehow managing to indefinitely stall an RCU grace period, eventually consuming all available memory on the system. The kernel core dump being over 4GB in size was a bit of a give-away.