| Message ID | 20200226202221.6555-11-andrew.cooper3@citrix.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | x86: Default vs Max policies | expand |
On 26.02.2020 21:22, Andrew Cooper wrote: > Memory Protection eXtension support has been dropped from GCC and Linux, and > will be dropped from future Intel CPUs. > > With all other default/max pieces in place, move MPX from default to max. > This means that VMs won't be offered it by default, but can explicitly opt > into using it via cpuid="host,mpx=1" in their vm.cfg file. > > The difference as visible to the guest is: > > diff --git a/default b/mpx > index 0e91765d6b..c8c33cd584 100644 > --- a/default > +++ b/mpx > @@ -13,15 +13,17 @@ Native cpuid: > 00000004:00000004 -> 00000000:00000000:00000000:00000000 > 00000005:ffffffff -> 00000000:00000000:00000000:00000000 > 00000006:ffffffff -> 00000000:00000000:00000000:00000000 > - 00000007:00000000 -> 00000000:009c2fbb:00000000:9c000400 > + 00000007:00000000 -> 00000000:009c6fbb:00000000:9c000400 > 00000008:ffffffff -> 00000000:00000000:00000000:00000000 > 00000009:ffffffff -> 00000000:00000000:00000000:00000000 > 0000000a:ffffffff -> 00000000:00000000:00000000:00000000 > 0000000b:ffffffff -> 00000000:00000000:00000000:00000000 > 0000000c:ffffffff -> 00000000:00000000:00000000:00000000 > - 0000000d:00000000 -> 00000007:00000240:00000340:00000000 > + 0000000d:00000000 -> 0000001f:00000240:00000440:00000000 > 0000000d:00000001 -> 0000000f:00000240:00000000:00000000 > 0000000d:00000002 -> 00000100:00000240:00000000:00000000 > + 0000000d:00000003 -> 00000040:000003c0:00000000:00000000 > + 0000000d:00000004 -> 00000040:00000400:00000000:00000000 > 40000000:ffffffff -> 40000005:566e6558:65584d4d:4d4d566e > 40000001:ffffffff -> 0004000e:00000000:00000000:00000000 > 40000002:ffffffff -> 00000001:40000000:00000000:00000000 > > Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> Reviewed-by: Jan Beulich <jbeulich@suse.com>
diff --git a/xen/include/public/arch-x86/cpufeatureset.h b/xen/include/public/arch-x86/cpufeatureset.h index d79a53befe..81e4c2950f 100644 --- a/xen/include/public/arch-x86/cpufeatureset.h +++ b/xen/include/public/arch-x86/cpufeatureset.h @@ -207,7 +207,7 @@ XEN_CPUFEATURE(INVPCID, 5*32+10) /*H Invalidate Process Context ID */ XEN_CPUFEATURE(RTM, 5*32+11) /*A Restricted Transactional Memory */ XEN_CPUFEATURE(PQM, 5*32+12) /* Platform QoS Monitoring */ XEN_CPUFEATURE(NO_FPU_SEL, 5*32+13) /*! FPU CS/DS stored as zero */ -XEN_CPUFEATURE(MPX, 5*32+14) /*S Memory Protection Extensions */ +XEN_CPUFEATURE(MPX, 5*32+14) /*s Memory Protection Extensions */ XEN_CPUFEATURE(PQE, 5*32+15) /* Platform QoS Enforcement */ XEN_CPUFEATURE(AVX512F, 5*32+16) /*A AVX-512 Foundation Instructions */ XEN_CPUFEATURE(AVX512DQ, 5*32+17) /*A AVX-512 Doubleword & Quadword Instrs */
Memory Protection eXtension support has been dropped from GCC and Linux, and will be dropped from future Intel CPUs. With all other default/max pieces in place, move MPX from default to max. This means that VMs won't be offered it by default, but can explicitly opt into using it via cpuid="host,mpx=1" in their vm.cfg file. The difference as visible to the guest is: diff --git a/default b/mpx index 0e91765d6b..c8c33cd584 100644 --- a/default +++ b/mpx @@ -13,15 +13,17 @@ Native cpuid: 00000004:00000004 -> 00000000:00000000:00000000:00000000 00000005:ffffffff -> 00000000:00000000:00000000:00000000 00000006:ffffffff -> 00000000:00000000:00000000:00000000 - 00000007:00000000 -> 00000000:009c2fbb:00000000:9c000400 + 00000007:00000000 -> 00000000:009c6fbb:00000000:9c000400 00000008:ffffffff -> 00000000:00000000:00000000:00000000 00000009:ffffffff -> 00000000:00000000:00000000:00000000 0000000a:ffffffff -> 00000000:00000000:00000000:00000000 0000000b:ffffffff -> 00000000:00000000:00000000:00000000 0000000c:ffffffff -> 00000000:00000000:00000000:00000000 - 0000000d:00000000 -> 00000007:00000240:00000340:00000000 + 0000000d:00000000 -> 0000001f:00000240:00000440:00000000 0000000d:00000001 -> 0000000f:00000240:00000000:00000000 0000000d:00000002 -> 00000100:00000240:00000000:00000000 + 0000000d:00000003 -> 00000040:000003c0:00000000:00000000 + 0000000d:00000004 -> 00000040:00000400:00000000:00000000 40000000:ffffffff -> 40000005:566e6558:65584d4d:4d4d566e 40000001:ffffffff -> 0004000e:00000000:00000000:00000000 40000002:ffffffff -> 00000001:40000000:00000000:00000000 Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> --- CC: Jan Beulich <JBeulich@suse.com> CC: Wei Liu <wl@xen.org> CC: Roger Pau Monné <roger.pau@citrix.com> XXX - One moving piece (the migration series) is still in review on xen-devel. I won't commit this change until that is sorted, and I can double check the backwards compatibility for VMs from previous versions of Xen. The main purpose of posting this patch now is to illustrate the effects of the previous patches in the series. --- xen/include/public/arch-x86/cpufeatureset.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)