Messages in this thread |  | | | Date | Tue, 18 Aug 1998 15:41:51 +0200 (CEST) | | From | Andrea Arcangeli <> | | Subject | Re: ANNOUNCE: Pset (sysmp) 0.58 for Linux/SMP now available |
| |
On 17 Aug 1998, Andi Kleen wrote:
>> Could you explian me how could be more secure? > >For example if you compute a cryptographic algorithm in the root >process then some information leaks over thread/process boundaries >(e.g. cycle counters, or cache line information etc.) and could be
The only thing you should be able to read as normal user in i386 is the tsc that say you how many tick the CPU got until boot.
>Search the web for 'side-chanel cryptoanalysis' or 'timing attacks' >for more information about this. e.g. http://www.counterpane.com/side_channel.html
Also the power consumation can be an useful data for the attakker reading the doc. I think that if somebody need such kind of security is better to allow only trusted users to login on its machine instead of run its process on a single CPU.
>Note that the leaking of the cycle counters on Intel could be easily
Which cycle counter? The tsc? The tsc can' t be used by other process to take timings from your process and the other i386 profiling counters are accessible only as root.
Andrea[s] Arcangeli
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html
|  |