Re: 2.6.26, PAT and AMD family 6

[Rene Herman]

On 07-05-08 04:39, Yinghai Lu wrote:

> On Tue, May 6, 2008 at 6:48 PM, Rene Herman <rene.herman@xxxxxxxxxxxx> wrote:

> >  On 2.6.25 and below, my /proc/cpuinfo looks like:
> >
> >  processor       : 0
> >  vendor_id       : AuthenticAMD
> >  cpu family      : 6
> >  model           : 7
> >  model name      : AMD Duron(tm) Processor

[ ... ]

> >  flags           : fpu vme de pse tsc msr pae mce cx8 sep mtrr pge mca cmov
> > pat pse36 mmx fxsr sse syscall mmxext 3dnowext 3dnow ts

> >  while on current mainline PAT and TS (Temperature Sensor) drop from the
> > feature flags:
> >
> >  flags           : fpu vme de pse tsc msr pae mce cx8 sep mtrr pge mca cmov
> > pse36 mmx fxsr sse syscall mmxext 3dnowext 3dnow
> >
> >  With respect to PAT, I guess it's 9307cacad0dfe3749f00303125c6f7f0523e5616,
> > "x86: pat cpu feature bit setting for known cpus" but what's this about?
> >
> > Did my cpuinfo lie upto this point or shouldn't the flag be cleared? The
> > commit message for that change is completely and totally unhelpful.
>
> others like to to whitebox methods, ..., please try attach patch to
> see if duron support PAT.

> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
> index a428ffc..81483ec 100644
> --- a/arch/x86/kernel/cpu/common.c
> +++ b/arch/x86/kernel/cpu/common.c
> @@ -314,6 +314,8 @@ static void __cpuinit early_get_cap(struct cpuinfo_x86 *c)
>  	case X86_VENDOR_AMD:
>  		if (c->x86 >= 0xf && c->x86 <= 0x11)
>  			set_cpu_cap(c, X86_FEATURE_PAT);
> +		if (c->x86 == 6 && c->x86_modes == 7)
> +			set_cpu_cap(c, X86_FEATURE_PAT);
>  		break;
>  	case X86_VENDOR_INTEL:
>  		if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))

s/modes/model/ but, as far as I'm aware, works fine other than that. When I boot
with CONFIG_X86_PAT after applying that, I see:

	x86 PAT enabled: cpu 0, old 0x7040600070406, new 0x7010600070106

and PAT is retained in the feature flags. However, this I do not consider very
surprising. Why is this code doing what it is doing in the first place?

These feature flags are read from hardware in the CPUID instruction. Why is this code
then going "ah, this CPU may _claim_ PAT but we won't actually believe it unless it's
model foo, bar or baz". Is that feature flag buggy?

That is, why is the attached not the better fix? Works fine for me as well and will
retain the PAT feature flag also for for example the AMD family 6, model 1 and model
4 that both also advertise PAT in their feature flags, but wil have lost them now as
well in the same way.

If for some or other reason this explicit PAT white listing is in fact necessary, in
addition to the above, it seems you also need/want the same in generic_identify() in
that same file.

And what it definitely wanted was a changelog...

Rene.
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 35b4f6a..45d8738 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -307,20 +307,6 @@ static void __cpuinit early_get_cap(struct cpuinfo_x86 *c)
 		}
 
 	}
-
-	clear_cpu_cap(c, X86_FEATURE_PAT);
-
-	switch (c->x86_vendor) {
-	case X86_VENDOR_AMD:
-		if (c->x86 >= 0xf && c->x86 <= 0x11)
-			set_cpu_cap(c, X86_FEATURE_PAT);
-		break;
-	case X86_VENDOR_INTEL:
-		if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
-			set_cpu_cap(c, X86_FEATURE_PAT);
-		break;
-	}
-
 }
 
 /*
@@ -408,19 +394,6 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
 
 		init_scattered_cpuid_features(c);
 	}
-
-	clear_cpu_cap(c, X86_FEATURE_PAT);
-
-	switch (c->x86_vendor) {
-	case X86_VENDOR_AMD:
-		if (c->x86 >= 0xf && c->x86 <= 0x11)
-			set_cpu_cap(c, X86_FEATURE_PAT);
-		break;
-	case X86_VENDOR_INTEL:
-		if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
-			set_cpu_cap(c, X86_FEATURE_PAT);
-		break;
-	}
 }
 
 static void __cpuinit squash_the_stupid_serial_number(struct cpuinfo_x86 *c)