All of lore.kernel.org
 help / color / mirror / Atom feed
* powernow-k8 patch
@ 2004-08-19 17:35 mark.langsdorf
  2004-08-19 18:25 ` Ari Pollak
  0 siblings, 1 reply; 9+ messages in thread
From: mark.langsdorf @ 2004-08-19 17:35 UTC (permalink / raw)
  To: cpufreq; +Cc: davej

[-- Attachment #1: Type: text/plain, Size: 488 bytes --]

AMD recently errata'd the definition of the PSB/PST
for recent Athlon 64 and Opteron parts.  The errata
allows for a second, identical PST for those parts.
The current powernow-k8 driver will not work in 
PST/PSB mode on those parts because it requires 
there be 1 and only 1 PST.

This patch adjusts the powernow-k8 driver to 
work with that errata.

Mark Langsdorf
Advanced Micro Devices        mark.langsdorf@amd.com
5204 E. Ben White Blvd        Phone: 512.602.3756
Austin, TX 78704


[-- Attachment #2: powernow-k8-new-cpus-2.6.8.1.patch --]
[-- Type: application/octet-stream, Size: 1209 bytes --]

--- arch/i386/kernel/cpu/cpufreq/powernow-k8.c.orig	2004-08-14 05:55:33.000000000 -0500
+++ arch/i386/kernel/cpu/cpufreq/powernow-k8.c	2004-08-18 14:33:56.953872328 -0500
@@ -39,7 +39,7 @@
 
 #define PFX "powernow-k8: "
 #define BFX PFX "BIOS error: "
-#define VERSION "version 1.00.09b"
+#define VERSION "version 1.00.09e"
 #include "powernow-k8.h"
 
 /* serialize freq changes  */
@@ -596,6 +596,8 @@ static int find_psb_table(struct powerno
 	unsigned int i;
 	u32 mvs;
 	u8 maxvid;
+	u32 cpst = 0;
+	u32 thiscpuid;
 
 	for (i = 0xc0000; i < 0xffff0; i += 0x10) {
 		/* Scan BIOS looking for the signature. */
@@ -634,7 +636,14 @@ static int find_psb_table(struct powerno
 		dprintk(KERN_INFO PFX "maximum voltage step: %d - 0x%x\n", mvs, data->vidmvs);
 
 		dprintk(KERN_DEBUG PFX "numpst: 0x%x\n", psb->numpst);
-		if (psb->numpst != 1) {
+		cpst = psb->numpst;
+		if ((psb->cpuid == 0x00000fc0) || (psb->cpuid == 0x00000fe0) ){
+			thiscpuid = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);
+			if ((thiscpuid == 0x00000fc0) || (thiscpuid == 0x00000fe0) ) {
+				cpst = 1;
+			}
+		}
+		if (cpst != 1) {
 			printk(KERN_ERR BFX "numpst must be 1\n");
 			return -ENODEV;
 		}

[-- Attachment #3: Type: text/plain, Size: 143 bytes --]

_______________________________________________
Cpufreq mailing list
Cpufreq@www.linux.org.uk
http://www.linux.org.uk/mailman/listinfo/cpufreq

^ permalink raw reply	[flat|nested] 9+ messages in thread
* RE: powernow-k8 patch
@ 2004-08-19 18:32 mark.langsdorf
  2004-08-19 19:00 ` Ari Pollak
  0 siblings, 1 reply; 9+ messages in thread
From: mark.langsdorf @ 2004-08-19 18:32 UTC (permalink / raw)
  To: ajp, cpufreq

Ari Pollak wrote:
> mark.langsdorf@amd.com wrote:
> > AMD recently errata'd the definition of the PSB/PST
> > for recent Athlon 64 and Opteron parts.  The errata
> > allows for a second, identical PST for those parts.
> > The current powernow-k8 driver will not work in
> > PST/PSB mode on those parts because it requires 
> > there be 1 and only 1 PST.
> > 
> > This patch adjusts the powernow-k8 driver to
> > work with that errata.

> Does that happen to fix the bug I reported earlier in powernow-k8?

No.  Your problem is caused by a malformed PST table
that has too many "low" frequency entries and by a 
PSB header that isn't the correct revision (1.4).  
Complain to your BIOS vendor.  Tell them that their 
BIOS does not support PN! on Win2K.

I'm curious as to why it doesn't work under ACPI.  
Can you instantiate the ACPI version and give me the
debug messages?

-Mark Langsdorf
AMD, Inc.

^ permalink raw reply	[flat|nested] 9+ messages in thread
* RE: powernow-k8 patch
@ 2004-08-19 19:26 mark.langsdorf
  2004-08-19 19:33 ` Ari Pollak
                   ` (2 more replies)
  0 siblings, 3 replies; 9+ messages in thread
From: mark.langsdorf @ 2004-08-19 19:26 UTC (permalink / raw)
  To: ajp, cpufreq

>  > No.  Your problem is caused by a malformed PST table
>  > that has too many "low" frequency entries and by a
>  > PSB header that isn't the correct revision (1.4).
>  > Complain to your BIOS vendor.  Tell them that their
>  > BIOS does not support PN! on Win2K.
>
> That's interesting, since IIRC AMD distributed a similar MSI 
> motherboard as a demo/reference. Maybe there's some obscure
> BIOS setting I'm missing.

No comment.
 
>  > I'm curious as to why it doesn't work under ACPI.
>  > Can you instantiate the ACPI version and give me the
>  > debug messages?

> I'm also wondering why powernow-k8 doesn't fallback to retrieving 
> information from ACPI, which is what the documentation says it's 
> supposed to do.
 
> Not sure if this is what you want, but here's the ACPI 
> debugging stuff 

Actually, I meant the powernow-k8 information.  If it failed
to load, it should give some reason why.

> and after I try to load the acpi module:
> ACPI: Processor [CPU1] (supports C1)
> acpi_processor_perf-0301 [30] acpi_cpufreq_cpu_init : Unsupported 
> address space [127, 127]

It looks like there's something wrong with the ACPI module,
but I don't know what that means.

-Mark Langsdorf
AMD, Inc.

^ permalink raw reply	[flat|nested] 9+ messages in thread
end of thread, other threads:[~2004-08-23 15:45 UTC | newest]

Thread overview: 9+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2004-08-19 17:35 powernow-k8 patch mark.langsdorf
2004-08-19 18:25 ` Ari Pollak
  -- strict thread matches above, loose matches on Subject: below --
2004-08-19 18:32 mark.langsdorf
2004-08-19 19:00 ` Ari Pollak
2004-08-19 19:26 mark.langsdorf
2004-08-19 19:33 ` Ari Pollak
2004-08-19 19:33 ` Ari Pollak
2004-08-23 15:39 ` Bruno Ducrot
2004-08-23 15:45   ` Ari Pollak

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.