Boris Ostrovsky
2011-Oct-06 18:59 UTC
[Xen-devel] [PATCH] x86/AMD: Do not enable ARAT feature on AMD processors below family 0x12
# HG changeset patch
# User Boris Ostrovsky <boris.ostrovsky@amd.com>
# Date 1317915395 14400
# Node ID 4374a261682e78d6bbf3b3fefb1e779b7a1fc3b3
# Parent 0b66e6450ffe6823d8b323ef4248b38fe7372d54
x86/AMD: Do not enable ARAT feature on AMD processors below family 0x12
Determining whether an AMD processor is affected by erratum 400 may
have some corner cases and handling these cases is somewhat complicated.
In the interest of simplicity we won''t claim ARAT support on processor
families below 0x12.
Mirrors Linux commit e9cdd343a5e42c43bcda01e609fa23089e026470
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@amd.com>
diff -r 0b66e6450ffe -r 4374a261682e xen/arch/x86/cpu/amd.c
--- a/xen/arch/x86/cpu/amd.c Tue Oct 04 14:18:30 2011 +0200
+++ b/xen/arch/x86/cpu/amd.c Thu Oct 06 11:36:35 2011 -0400
@@ -495,8 +495,11 @@
}
#endif
- /* As a rule processors have APIC timer running in deep C states */
- if (c->x86 > 0xf && !cpu_has_amd_erratum(c, AMD_ERRATUM_400))
+ /*
+ * Family 0x12 and above processors have APIC timer
+ * running in deep C states.
+ */
+ if (c->x86 > 0x11)
set_bit(X86_FEATURE_ARAT, c->x86_capability);
if (cpuid_edx(0x80000007) & (1 << 10)) {
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xensource.com
http://lists.xensource.com/xen-devel
Jan Beulich
2011-Oct-07 08:39 UTC
Re: [Xen-devel] [PATCH] x86/AMD: Do not enable ARAT feature on AMD processors below family 0x12
>>> On 06.10.11 at 20:59, Boris Ostrovsky <boris.ostrovsky@amd.com> wrote: > # HG changeset patch > # User Boris Ostrovsky <boris.ostrovsky@amd.com> > # Date 1317915395 14400 > # Node ID 4374a261682e78d6bbf3b3fefb1e779b7a1fc3b3 > # Parent 0b66e6450ffe6823d8b323ef4248b38fe7372d54 > x86/AMD: Do not enable ARAT feature on AMD processors below family 0x12 > > Determining whether an AMD processor is affected by erratum 400 may > have some corner cases and handling these cases is somewhat complicated. > In the interest of simplicity we won''t claim ARAT support on processor > families below 0x12. > > Mirrors Linux commit e9cdd343a5e42c43bcda01e609fa23089e026470 > > Signed-off-by: Boris Ostrovsky <boris.ostrovsky@amd.com> > > diff -r 0b66e6450ffe -r 4374a261682e xen/arch/x86/cpu/amd.c > --- a/xen/arch/x86/cpu/amd.c Tue Oct 04 14:18:30 2011 +0200 > +++ b/xen/arch/x86/cpu/amd.c Thu Oct 06 11:36:35 2011 -0400 > @@ -495,8 +495,11 @@ > } > #endif > > - /* As a rule processors have APIC timer running in deep C states */ > - if (c->x86 > 0xf && !cpu_has_amd_erratum(c, AMD_ERRATUM_400)) > + /* > + * Family 0x12 and above processors have APIC timer > + * running in deep C states. > + */ > + if (c->x86 > 0x11) > set_bit(X86_FEATURE_ARAT, c->x86_capability); > > if (cpuid_edx(0x80000007) & (1 << 10)) {Applied, but - couldn''t we do away with the erratum 400 definition now? Or is it reasonable to expect that something else could depend on this (which, following the back-and-forth here, seems to be fuzzy anyway)? (I wouldn''t mind keeping record of it in the example part of the comment preceding the errata definitions, as is already the case.) Jan _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel