lkml.org 
[lkml]   [2003]   [Jun]   [14]   [last100]   RSS Feed
Views: [more markup]  [less markup]  [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
DateSat, 14 Jun 2003 04:46:11 -0400
FromSamuel Thibault <>
SubjectRe: [2.5. PATCH] cpufreq: correct initialization on Intel Coppermines
On fri 08 nov 2002 09:30:08 GMT, Dominik Brodowski wrote:
> The detection process for speedstep-enabled Pentium III Coppermines is
> considered proprietary by Intel.

They seem to have changed their mind:

http://www.intel.com/support/processors/sb/cs-003779-prd24.htm

Which looks a bit like what was implemented at first. Here is a patch.
I kept the setup parameter, but it might be removed now?

--- linux-2.5.70-bk12/arch/i386/kernel/cpu/cpufreq/speedstep.c	2003-05-26 21:00:20.000000000 -0400
+++ linux/arch/i386/kernel/cpu/cpufreq/speedstep.c	2003-06-14 04:33:04.000000000 -0400
@@ -503,6 +503,15 @@
 			if (speedstep_coppermine)
 				return SPEEDSTEP_PROCESSOR_PIII_C;
 
+			/* if the processor is a mobile version,
+			 * platform ID has bit 50 set
+			 * it has SpeedStep technology if either
+			 * bit 56 or 57 is set */
+			rdmsr(MSR_IA32_PLATFORM_ID, msr_lo, msr_hi);
+			dprintk(KERN_DEBUG "cpufreq: Coppermine: MSR_IA32_PLATFORM ID is 0x%x, 0x%x\n", msr_lo, msr_hi);
+			if ((msr_hi & (1<<18)) && (msr_hi & (3<<24)))
+				return SPEEDSTEP_PROCESSOR_PIII_C;
+
 			printk(KERN_INFO "cpufreq: in case this is a SpeedStep-capable Intel Pentium III Coppermine\n");
 			printk(KERN_INFO "cpufreq: processor, please pass the boot option or module parameter\n");
 			printk(KERN_INFO "cpufreq: `speedstep_coppermine=1` to the kernel. Thanks!\n");
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
\
 
 \ /
  Last update: 2005-03-22 12:36    [W:0.340 / U:0.040 seconds]
©2003-2008 Jasper Spaans