Messages in this thread | | | Date | Tue, 19 May 1998 00:15:44 -0400 (EDT) | From | "Phil's Kernel Account" <> | Subject | Re: Cyrix 6x86MX and Centaur C6 CPUs in 2.1.102 |
| |
On Mon, 18 May 1998, Vojtech Pavlik wrote:
#*sigh* And this would also mean that my joystick driver will fallback into #PIT timing mode on a Cyrix, though it could safely use the TSC timer, since #there isn't a chance of the CPU getting a HLT instruction while it is timing #the joystick input ...
Thank you SO much Vojtech. I've been trying to remember something that REALLY relies on the TSC to support my suggestion all day. Now I can reply to Linus' mail! Yay! }:)
#If I could suggest a solution, add a bug flag for this behaviour, and check #for presence of TSC and absence of the bug in do_fast_gettimeofday. The TSC #simply is there, though not suitable for all uses.
Perhaps, perhaps not. There IS a way to address it correctly in ALL situations, I just don't remember it.
#Also, it'd be neat if the kernel had some public variable containing the #real TSC increment speed for each CPU, say in ticks per second or #microsecond, so that drivers using the TSC wouldn't need to calibrate it.
Oooo, that WOULD be *VERY* handy. Instant-sync. I like. :)
-Phil R. Jaenke (kernel@nls.net / prj@nls.net) TheGuyInCharge(tm), Ketyra Designs - We get paid to break stuff :) Linux pkrea.ketyra.INT 2.0.33 #15 Sat Apr 18 00:40:21 EDT 1998 i586 Linux eiterra.nls.net 2.0.33 #15 Fri Apr 17 00:22:13 EDT 1998 i586 - Linus says for 'brave people only.' I say 'keep a backup.' - :)
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu
| |