Add new features introduced in AMD Fam17h
cover Add new features introduced in AMD Fam17h
Patch1: Add Scalable MCA feature identification
Patch2: Add CLZERO feature
Aravind Gopalakrishnan (2):
x86/mcheck: Add Scalable MCA cpuid bit
x86/cpufeature: Add CLZERO feature
arch/x86/include/asm/cpufeature.h | 5 ++++- arch/x86/include/asm/mce.h | 13 ++++++++++++- arch/x86/kernel/cpu/common.c | 1 + arch/x86/kernel/cpu/mcheck/mce.c | 2 ++ 4 files changed, 19 insertions(+), 2 deletions(-)
Signature · 1 line
2.6.1
PATCH 1/2 x86/mcheck: Add Scalable MCA cpuid bit
Scalable MCA (SMCA) is a new feature in AMD Fam17h processors which indicates presence of MCA extensions.
MCA extensions expands existing register space for the MCE banks and also introduces a new MSR range to accommodate new banks. Future additions to AMD MCE code will first need to detect if SMCA is enabled before enabling the new features.
Adding code to detect if it SMCA is enabled in this patch and store that info in mce_vendor_flags structure.
--- arch/x86/include/asm/mce.h | 13 ++++++++++++- arch/x86/kernel/cpu/mcheck/mce.c | 2 ++ 2 files changed, 14 insertions(+), 1 deletion(-)
arch/x86/include/asm/mce.h +12 -1
@@ -135,7 +135,18 @@ struct mce_vendor_flags {* in HW and deferred error interrupts. */ succor :1 , - __reserved_0 : 62; + +/* +* Scalable MCA: This bit indicates support for MCAX +* (MCA EXtensions) which expands the register space +* for each MCA bank and also increases number of +* banks. Also, to accommodate the new banks and +* registers, the MCA register space is moved to a new +* MSR range +*/ + smca : 1, + + __reserved_0 : 61; };extern struct mce_vendor_flags mce_flags;
arch/x86/kernel/cpu/mcheck/mce.c +2 -0
@@ -1605,6 +1605,8 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)mce_amd_feature_init (c); mce_flags.overflow_recov = !!(ebx &BIT (0 )); mce_flags.succor = !!(ebx &BIT (1 )); + mce_flags.smca = !!(ebx &BIT (3 )); +break ; }
Signature · 1 line
2.6.1
PATCH 2/2 x86/cpufeature: Add CLZERO feature
In reply to Aravind GopalakrishnanCLZERO instruction introduced in AMD Fam17h processors zero's out a 64 byte cache line specified in RAX.
Add the bit here to allow /proc/cpuinfo to list the feature
--- arch/x86/include/asm/cpufeature.h | 5 ++++- arch/x86/kernel/cpu/common.c | 1 + 2 files changed, 5 insertions(+), 1 deletion(-)
arch/x86/include/asm/cpufeature.h +4 -1
@@ -12,7 +12,7 @@#include <asm/disabled-features.h> #endif -#define NCAPINTS 13/* N 32-bit words worth of info */ +#define NCAPINTS 14/* N 32-bit words worth of info */ #define NBUGINTS 1/* N 32-bit bug flags */ /*
@@ -255,6 +255,9 @@/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */ #define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0)/* LLC occupancy monitoring if 1 */ +/* AMD extended feature extension, CPUID level 0x80000008 (ebx), word 13 */ +#define X86_FEATURE_CLZERO (13*32+0)/* CLZERO instruction */ +/* * BUG word(s) */
arch/x86/kernel/cpu/common.c +1 -0
@@ -670,6 +670,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_virt_bits = (eax >>8 ) &0xff ; c->x86_phys_bits = eax &0xff ; + c->x86_capability[13 ] =cpuid_ebx (0x80000008 ); }#ifdef CONFIG_X86_32 else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
Signature · 1 line
2.6.1
Borislav Petkov
maintainerRe: [PATCH 2/2] x86/cpufeature: Add CLZERO feature
Quoted 7 lines · Aravind Gopalakrishnan
CLZERO instruction introduced in AMD Fam17h processors zero's out a 64 byte cache line specified in RAX.
Add the bit here to allow
/proc/cpuinfoto list the featureSigned-off-by Wan Zongshun <[email protected]>Signed-off-by Aravind Gopalakrishnan <[email protected]>
This SOB chain looks wrong - if Vincent is the author and you're only sending the patch, then his "From:" needs to appear before the commit message. git send-email does that correctly, provided the authorship is correctly set in the local branch you're sending the patch from.
Quoted 19 lines
--- arch/x86/include/asm/cpufeature.h | 5 ++++- arch/x86/kernel/cpu/common.c | 1 + 2 files changed, 5 insertions(+), 1 deletion(-)arch/x86/include/asm/cpufeature.h +1
-1@@ -12,7 +12,7 @@#include <asm/disabled-features.h> #endif -#define NCAPINTS 13/* N 32-bit words worth of info */ +#define NCAPINTS 14/* N 32-bit words worth of info */ #define NBUGINTS 1/* N 32-bit bug flags */ /*
arch/x86/include/asm/cpufeature.h line 258
Quoted 4 lines
arch/x86/include/asm/cpufeature.h +1
-0@@ -255,6 +255,9 @@/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */ #define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0)/* LLC occupancy monitoring if 1 */ +/* AMD extended feature extension, CPUID level 0x80000008 (ebx), word 13 */
extended ... extension sounds like a tautology, please sanitize.
Quoted 1 line
arch/x86/include/asm/cpufeature.h +1
-0+#define X86_FEATURE_CLZERO (13*32+0)/* CLZERO instruction */
...
Signature · 5 lines
Regards/Gruss,
Boris.
ECO tip #101: Trim your mails when you reply.
--Re: [PATCH 2/2] x86/cpufeature: Add CLZERO feature
Quoted 4 lines · Borislav Petkov
Quoted 3 lines · Aravind Gopalakrishnan
CLZERO instruction introduced in AMD Fam17h processors zero's out a 64 byte cache line specified in RAX.
Quoted 8 lines
Quoted 4 lines
Add the bit here to allow
/proc/cpuinfoto list the featureSigned-off-by Wan Zongshun <[email protected]>Signed-off-by Aravind Gopalakrishnan <[email protected]>This SOB chain looks wrong - if Vincent is the author and you're only sending the patch, then his "From:" needs to appear before the commit message. git send-email does that correctly, provided the authorship is correctly set in the local branch you're sending the patch from.
For large part yes, wrapped code in patch form with commit message etc. And modified comment a little bit.
Does that still require his address in "From"?
Quoted 8 lines
arch/x86/include/asm/cpufeature.h line 258
Quoted 7 lines
/*
arch/x86/include/asm/cpufeature.h +1
-0@@ -255,6 +255,9 @@/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */ #define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0)/* LLC occupancy monitoring if 1 */ +/* AMD extended feature extension, CPUID level 0x80000008 (ebx), word 13 */ extended ... extension sounds like a tautology, please sanitize.
Haha. True. But looks like that's actually it's name.
If tautologies are not your thing, how about changing comments around 0x80000001,ecx to say "AMD extended features 1" and for 0x80000008, ebx say "AMD extended features 2"?
Thanks,
-Aravind.
Borislav Petkov
maintainerRe: [PATCH 2/2] x86/cpufeature: Add CLZERO feature
Quoted 4 lines · Aravind Gopalakrishnan
For large part yes, wrapped code in patch form with commit message etc. And modified comment a little bit.
Does that still require his address in "From"?
Yes, because it sounds like he was the author of the original patch. Btw, you should read
Documentation/SubmittingPatches
and sections 11 - "Sign your work" up until 14, in particular. That should clear things up for ya.
Quoted 1 line
Haha. True. But looks like that's actually it's name.
No one said hw people can name stuff properly.
Quoted 1 line
If tautologies are not your thing,
My thing is catching sloppiness in patches.
Quoted 3 lines
how about changing comments around 0x80000001,ecx to say "AMD extended features 1" and for
0x80000008, ebx say "AMD extended features 2"?
No, I think you should add that bit to init_scattered_cpuid_features() instead.
And btw, those Intel QoS single bit defines and the XSAVE stuff there should move to that function too - that's a pure waste having them in the cap_flags array. I'll fix that.
Signature · 5 lines
Regards/Gruss,
Boris.
ECO tip #101: Trim your mails when you reply.
--Borislav Petkov
maintainerRFC PATCH 1/1 x86/cpu: Move sparsely used bit leafs into scattered features (was: Re: [PATCH 2/2] x86/cpufeature: Add CLZERO feature)
Quoted 3 lines · Borislav Petkov
And btw, those Intel QoS single bit defines and the XSAVE stuff there should move to that function too - that's a pure waste having them in the
cap_flagsarray. I'll fix that.
I.e., something like that (I'm jetlagged and I can't sleep, bah :-\).
So this one builds but no further guarantees. It looks straightforward though.
---
arch/x86/include/asm/cpufeature.h +10 -13
@@ -12,7 +12,7 @@#include <asm/disabled-features.h> #endif -#define NCAPINTS 13/* N 32-bit words worth of info */ +#define NCAPINTS 10/* N 32-bit words worth of info */ #define NBUGINTS 1/* N 32-bit bug flags */ /*
@@ -198,6 +198,15 @@#define X86_FEATURE_HWP_EPP ( 7*32+13)/* Intel HWP_EPP */ #define X86_FEATURE_HWP_PKG_REQ ( 7*32+14)/* Intel HWP_PKG_REQ */ #define X86_FEATURE_INTEL_PT ( 7*32+15)/* Intel Processor Trace */ +/* Extended state features, CPUID level 0x0000000d:1 (eax) */ +#define X86_FEATURE_XSAVEOPT (7*32+ 16)/* XSAVEOPT */ +#define X86_FEATURE_XSAVEC (7*32+ 17)/* XSAVEC */ +#define X86_FEATURE_XGETBV1 (7*32+ 18)/* XGETBV with ECX = 1 */ +#define X86_FEATURE_XSAVES (7*32+ 19)/* XSAVES/XRSTORS */ +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx) */ +#define X86_FEATURE_CQM_LLC (7*32+ 20)/* LLC QoS if 1 */ +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx) */ +#define X86_FEATURE_CQM_OCCUP_LLC (7*32+ 21)/* LLC occupancy monitoring if 1 */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0)/* Intel TPR Shadow */
@@ -243,18 +252,6 @@#define X86_FEATURE_AVX512CD ( 9*32+28)/* AVX-512 Conflict Detection */ #define X86_FEATURE_SHA_NI ( 9*32+29)/* SHA1/SHA256 Instruction Extensions */ -/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */ -#define X86_FEATURE_XSAVEOPT (10*32+ 0)/* XSAVEOPT */ -#define X86_FEATURE_XSAVEC (10*32+ 1)/* XSAVEC */ -#define X86_FEATURE_XGETBV1 (10*32+ 2)/* XGETBV with ECX = 1 */ -#define X86_FEATURE_XSAVES (10*32+ 3)/* XSAVES/XRSTORS */ - -/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */ -#define X86_FEATURE_CQM_LLC (11*32+ 1)/* LLC QoS if 1 */ - -/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */ -#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0)/* LLC occupancy monitoring if 1 */ -/* * BUG word(s) */
arch/x86/kernel/cpu/common.c +0 -11
@@ -621,29 +621,18 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[9 ] = ebx; } -/* Extended state features: level 0x0000000d */ -if (c->cpuid_level >=0x0000000d ) { -u32 eax, ebx, ecx, edx; - -cpuid_count (0x0000000d ,1 , &eax, &ebx, &ecx, &edx); - - c->x86_capability[10 ] = eax; - } -/* Additional Intel-defined flags: level 0x0000000F */ if (c->cpuid_level >=0x0000000F ) {u32 eax, ebx, ecx, edx;/* QoS sub-leaf, EAX=0Fh, ECX=0 */ cpuid_count (0x0000000F ,0 , &eax, &ebx, &ecx, &edx); - c->x86_capability[11 ] = edx;if (cpu_has (c,X86_FEATURE_CQM_LLC )) {/* will be overridden if occupancy monitoring exists */ c->x86_cache_max_rmid = ebx;/* QoS sub-leaf, EAX=0Fh, ECX=1 */ cpuid_count (0x0000000F ,1 , &eax, &ebx, &ecx, &edx); - c->x86_capability[12 ] = edx;if (cpu_has (c,X86_FEATURE_CQM_OCCUP_LLC )) { c->x86_cache_max_rmid = ecx; c->x86_cache_occ_scale = ebx;
arch/x86/kernel/cpu/scattered.c +7 -1
@@ -41,9 +41,15 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) { X86_FEATURE_HWP_ACT_WINDOW, CR_EAX, 9, 0x00000006, 0 }, { X86_FEATURE_HWP_EPP, CR_EAX,10, 0x00000006, 0 }, { X86_FEATURE_HWP_PKG_REQ, CR_EAX,11, 0x00000006, 0 }, - { X86_FEATURE_INTEL_PT, CR_EBX,25, 0x00000007, 0 }, { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, + { X86_FEATURE_INTEL_PT, CR_EBX,25, 0x00000007, 0 }, + { X86_FEATURE_XSAVEOPT, CR_EAX, 0, 0x0000000d, 1 }, + { X86_FEATURE_XSAVEC, CR_EAX, 1, 0x0000000d, 1 }, + { X86_FEATURE_XGETBV1, CR_EAX, 2, 0x0000000d, 1 }, + { X86_FEATURE_XSAVES, CR_EAX, 3, 0x0000000d, 1 }, + { X86_FEATURE_CQM_LLC, CR_EDX, 1, 0x0000000f, 0 }, + { X86_FEATURE_CQM_OCCUP_LLC, CR_EDX, 0, 0x0000000f, 1 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CR_EDX,11, 0x80000007, 0 },
Signature · 5 lines
Regards/Gruss,
Boris.
ECO tip #101: Trim your mails when you reply.
--Re: [RFC PATCH] x86/cpu: Move sparsely used bit leafs into scattered features (was: Re: [PATCH 2/2] x86/cpufeature: Add CLZERO feature)
Quoted 27 lines · Borislav Petkov
Quoted 3 lines · Borislav Petkov
And btw, those Intel QoS single bit defines and the XSAVE stuff there should move to that function too - that's a pure waste having them in the
cap_flagsarray. I'll fix that.I.e., something like that (I'm jetlagged and I can't sleep, bah :-\).
So this one builds but no further guarantees. It looks straightforward though.
Not-yet-signed-off-by Borislav Petkov <[email protected]>---
arch/x86/include/asm/cpufeature.h +1
-1@@ -12,7 +12,7 @@#include <asm/disabled-features.h> #endif -#define NCAPINTS 13/* N 32-bit words worth of info */ +#define NCAPINTS 10/* N 32-bit words worth of info */ #define NBUGINTS 1/* N 32-bit bug flags */ /*
arch/x86/include/asm/cpufeature.h line 205
Quoted 8 lines
arch/x86/include/asm/cpufeature.h +5
-0@@ -198,6 +198,15 @@#define X86_FEATURE_HWP_EPP ( 7*32+13)/* Intel HWP_EPP */ #define X86_FEATURE_HWP_PKG_REQ ( 7*32+14)/* Intel HWP_PKG_REQ */ #define X86_FEATURE_INTEL_PT ( 7*32+15)/* Intel Processor Trace */ +/* Extended state features, CPUID level 0x0000000d:1 (eax) */ +#define X86_FEATURE_XSAVEOPT (7*32+ 16)/* XSAVEOPT */ +#define X86_FEATURE_XSAVEC (7*32+ 17)/* XSAVEC */ +#define X86_FEATURE_XGETBV1 (7*32+ 18)/* XGETBV with ECX = 1 */ +#define X86_FEATURE_XSAVES (7*32+ 19)/* XSAVES/XRSTORS */
How few features in one leaf do we need before calling it scattered makes sense? These four might make sense to keep as is...
arch/x86/include/asm/cpufeature.h line 210
Quoted 5 lines
arch/x86/include/asm/cpufeature.h +4
-0+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx) */ +#define X86_FEATURE_CQM_LLC (7*32+ 20)/* LLC QoS if 1 */ +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx) */ +#define X86_FEATURE_CQM_OCCUP_LLC (7*32+ 21)/* LLC occupancy monitoring if 1 */
...whereas this looks totally reasonable.
FWIW, we have a ton of thses things. Would it make sense to convert this to a text file giving features and their CPUID positions that generates the defines and the code to enumerate them?
--Andy
Borislav Petkov
maintainerRe: [RFC PATCH] x86/cpu: Move sparsely used bit leafs into scattered features (was: Re: [PATCH 2/2] x86/cpufeature: Add CLZERO feature)
Quoted 2 lines · Andy Lutomirski
How few features in one leaf do we need before calling it scattered makes sense? These four might make sense to keep as is...
Actually, according to hpa, all those leafs will be filled out gradually as they're apparently going to be used for hw features. And it looks like the AMD leaf is of the same type. So those all will be fleshed out with time and we can keep them here, in cpufeature.h.
Quoted 5 lines
...whereas this looks totally reasonable.
FWIW, we have a ton of thses things. Would it make sense to convert this to a text file giving features and their CPUID positions that generates the defines and the code to enumerate them?
Yeah, maybe. I'm not that really bothered by the current form too, though.
Signature · 5 lines
Regards/Gruss,
Boris.
ECO tip #101: Trim your mails when you reply.
--Re: [PATCH 2/2] x86/cpufeature: Add CLZERO feature
In reply to Borislav PetkovQuoted 6 lines · Borislav Petkov
Quoted 4 lines · Aravind Gopalakrishnan
For large part yes, wrapped code in patch form with commit message etc. And modified comment a little bit.
Does that still require his address in "From"?
Yes, because it sounds like he was the author of the original patch.
Okay, will fix that in V2.
Quoted 7 lines
No, I think you should add that bit to
init_scattered_cpuid_features()instead.And btw, those Intel QoS single bit defines and the XSAVE stuff there should move to that function too - that's a pure waste having them in the
cap_flagsarray. I'll fix that.
Ok, I added it to init_scattered_cpuid_features() on top of your RFC patch and it seems to work fine.
How do you prefer a V2 for this to be sent though- Shall I wait until your fixes are in tip.git and resend? Or send a V2 on top of current tip.git?
Thanks,
-Aravind.
Borislav Petkov
maintainerRe: [PATCH 2/2] x86/cpufeature: Add CLZERO feature
Quoted 3 lines · Aravind Gopalakrishnan
How do you prefer a V2 for this to be sent though- Shall I wait until your fixes are in tip.git and resend? Or send a V2 on top of current tip.git?
Actually, I just showed it to hpa and he says those CPUID leafs are going to be filled at some point so no need to add them to the scattered features list.
If that AMD CPUID leaf 0x80000008 is going to be containing more CPUID feature bits - and it sounded like it will because you called it "AMD extended features 2" - then those should really go into into the x86_capability array, i.e., like you've done it in your initial version.
This also means, that the scattered features would need to get stuff moved over to the x86_capability array too, but that's for later.
So please fix the SOB chain of your initial patch and send that one out.
Thanks.
Signature · 5 lines
Regards/Gruss,
Boris.
ECO tip #101: Trim your mails when you reply.
--Re: [PATCH 2/2] x86/cpufeature: Add CLZERO feature
Quoted 8 lines · Borislav Petkov
Quoted 3 lines · Aravind Gopalakrishnan
How do you prefer a V2 for this to be sent though- Shall I wait until your fixes are in tip.git and resend? Or send a V2 on top of current tip.git?
Actually, I just showed it to hpa and he says those CPUID leafs are going to be filled at some point so no need to add them to the scattered features list.
Quoted 7 lines
If that AMD CPUID leaf
0x80000008is going to be containing more CPUID feature bits - and it sounded like it will because you called it "AMD extended features 2" - then those should really go into into thex86_capabilityarray, i.e., like you've done it in your initial version.So please fix the SOB chain of your initial patch and send that one out.
Okay, Will do.
Thanks,
-Aravind.
Re: [PATCH 2/2] x86/cpufeature: Add CLZERO feature
In reply to Borislav PetkovQuoted 7 lines · Borislav Petkov
you called it "AMD
extended features 2" - then those should really go into into thex86_capabilityarray, i.e., like you've done it in your initial version.So please fix the SOB chain of your initial patch and send that one out.
Forgot to ask earlier about this-
Shall I still sanitize the comments to say "AMD extended features 1" for 0x80000001,ecx and "AMD extended features 2" for 0x80000008, ebx?
Or let it be as in initial version?
Thanks,
-Aravind.
Borislav Petkov
maintainerRe: [PATCH 2/2] x86/cpufeature: Add CLZERO feature
Quoted 4 lines · Aravind Gopalakrishnan
Forgot to ask earlier about this-
Shall I still sanitize the comments to say "AMD extended features 1" for 0x80000001,ecx
and "AMD extended features 2" for0x80000008, ebx?
Just use the cpufeature.h nomenclature:
/* AMD-defined CPU features, CPUID level 0x80000008, word 13 */
or so...
Thanks.
Signature · 5 lines
Regards/Gruss,
Boris.
ECO tip #101: Trim your mails when you reply.
--Re: [PATCH 2/2] x86/cpufeature: Add CLZERO feature
In reply to Borislav Petkov(removing [email protected] as email bounced)
Quoted 4 lines · Borislav Petkov
Quoted 3 lines · Aravind Gopalakrishnan
CLZERO instruction introduced in AMD Fam17h processors zero's out a 64 byte cache line specified in RAX.
Quoted 8 lines
Quoted 4 lines
Add the bit here to allow
/proc/cpuinfoto list the featureSigned-off-by Wan Zongshun <[email protected]>Signed-off-by Aravind Gopalakrishnan <[email protected]>This SOB chain looks wrong - if Vincent is the author and you're only sending the patch, then his "From:" needs to appear before the commit message. git send-email does that correctly, provided the authorship is correctly set in the local branch you're sending the patch from.
For large part yes, wrapped code in patch form with commit message etc. And modified comment a little bit.
Does that still require his address in "From"?
Quoted 8 lines
arch/x86/include/asm/cpufeature.h line 258
Quoted 7 lines
/*
arch/x86/include/asm/cpufeature.h +1
-0@@ -255,6 +255,9 @@/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */ #define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0)/* LLC occupancy monitoring if 1 */ +/* AMD extended feature extension, CPUID level 0x80000008 (ebx), word 13 */ extended ... extension sounds like a tautology, please sanitize.
Haha. True. But looks like that's actually it's name.
If tautologies are not your thing, how about changing comments around 0x80000001,ecx to say "AMD extended features 1" and for 0x80000008, ebx say "AMD extended features 2"?
Thanks,
-Aravind.