Parse vcpus for VMX guest. Vcpus are passed to device model and vmx domain builder. Signed-off-by: Yan Li <yanx.li@intel.com> Signed-off-by: Xin Li <xin.b.li@intel.com> _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
>Why does ioemu need to know the number of vcpus? I see the patch adds >this option to ioemu, but you don''t add any code that actually uses it >(yet). Do you have plans to? >Yes, IOAPIC should use it for SMP VMX guest interrupt injection. -Xin _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Why does ioemu need to know the number of vcpus? I see the patch adds this option to ioemu, but you don''t add any code that actually uses it (yet). Do you have plans to? -- Keir On 20 Sep 2005, at 16:40, Li, Xin B wrote:> Parse vcpus for VMX guest. > > Vcpus are passed to device model and vmx domain builder. > > Signed-off-by: Yan Li <yanx.li@intel.com> > Signed-off-by: Xin Li <xin.b.li@intel.com> > <vmx_parse_vcpus.patch>_______________________________________________ > Xen-devel mailing list > Xen-devel@lists.xensource.com > http://lists.xensource.com/xen-devel_______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Keir Fraser wrote:> Why does ioemu need to know the number of vcpus? I see the patch adds > this option to ioemu, but you don''t add any code that actually uses it > (yet). Do you have plans to? > > -- Keir >Yes, we do. We have code for local APIC (mostly in Xen) and IO APIC device models (in qemu-dm) in preparation for SMP VMX guests. Since guests don''t explicitly send EOI to IO APIC upon timer interrupts, we are also hoping it would reduce the traffic between qemu-dm. We''ll send out the patch shortly once more testing is done.> On 20 Sep 2005, at 16:40, Li, Xin B wrote: > >> Parse vcpus for VMX guest. >> >> Vcpus are passed to device model and vmx domain builder. >> >> Signed-off-by: Yan Li <yanx.li@intel.com> >> Signed-off-by: Xin Li <xin.b.li@intel.com> >><vmx_parse_vcpus.patch>_______________________________________________ Jun --- Intel Open Source Technology Center _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Jiang, Yunhong
2005-Sep-21 02:00 UTC
RE: [Xen-devel] [PATCH][VT] parse vcpus for VMX guest
Nakajima, Jun wrote:> Keir Fraser wrote: >> Why does ioemu need to know the number of vcpus? I see the patch adds >> this option to ioemu, but you don''t add any code that actually uses >> it (yet). Do you have plans to? >> >> -- Keir >> > > Yes, we do. We have code for local APIC (mostly in Xen) and IO APIC > device models (in qemu-dm) in preparation for SMP VMX guests. Since > guests don''t explicitly send EOI to IO APIC upon timer interrupts, we > are also hoping it would reduce the traffic between qemu-dm. We''ll > send out the patch shortly once more testing is done.I think one more possible reason is, the qemu-dm may need to know the vcpu number to get the io request. Thanks Yunhong Jiang> >> On 20 Sep 2005, at 16:40, Li, Xin B wrote: >> >>> Parse vcpus for VMX guest. >>> >>> Vcpus are passed to device model and vmx domain builder. >>> >>> Signed-off-by: Yan Li <yanx.li@intel.com> >>> Signed-off-by: Xin Li <xin.b.li@intel.com> >>> > <vmx_parse_vcpus.patch>_______________________________________________ > > Jun > --- > Intel Open Source Technology Center > > _______________________________________________ > Xen-devel mailing list > Xen-devel@lists.xensource.com > http://lists.xensource.com/xen-devel_______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel