On Fri, 2006-02-03 at 10:33 +0100, Pavel Troller wrote: > > Isn't there any other way to tell the operating system that the C2/C3 > > states are unusable (e.g. by simply telling they're not there?). This > > looks so obfuscated... > > The problem is that the table (RSDT) has a fixed format and the values have > reserved positions. Putting 0 there would mean zero (unmeasureble) latency, > which would be the best case, of course. So to disable the feature, "out of > range" method was selected. Yes, it would be nice to have some "special" value > there, like FFFF, but it is not a common practice.
Still I don't get it. Current linux acpi implementation suggests there are 8 C states. My laptop says the processor supports 4 C states, my other laptop says it has 3 C states. Do you mean the table always has 8 C entries, and all of the unusable states are marked "unusable"? In that case I would understand.
smime.p7s
Description: S/MIME cryptographic signature
