Re: [PATCH v3 03/14] KVM: x86: use physical LAPIC array for logical x2APIC

From	Nadav Amit <nadav.amit@gmail.com>
Newsgroups	linux.kernel
Subject	Re: [PATCH v3 03/14] KVM: x86: use physical LAPIC array for logical x2APIC
Date	2016-08-02 18:50 +0200
Message-ID	<s1L3d-725-65@gated-at.bofh.it> (permalink)
References	<rUcjT-1np-3@gated-at.bofh.it> <rUcjU-1np-19@gated-at.bofh.it> <s1If0-589-43@gated-at.bofh.it> <s1IRJ-5C1-47@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

Radim Krčmář <rkrcmar@redhat.com> wrote:
> 
> Offending LAPIC marks the logical mapping as unusable, which was
> intended.  kvm_apic_map_get_logical_dest() returns false.
> 
> The main problem is that SDM does not clearly forbid LAPICs in x2APIC
> mode while some xAPIC LAPICs have nonzero LDR, so we should handle it
> somewhat gracefully.
> In combination with our IR-less IOAPIC hack, this would mean that we
> would have to check both interpretations (x2 and xAPIC) of a logical
> address before delivering.  Not to mention that we would also have to
> decide how to handle a case when both interpretations are valid.

My recollection of running Intel tests is that they do leave sometimes
some of the cores in the xAPIC mode while others are in x2APIC mode.
In this case, IIRC they do not generate IPIs from the xAPIC core.

IIRC they do expect broadcast interrupts to be received by all cores,
including those with xAPIC mode. However, I am unsure about this last
point.

Regards,
Nadav

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

Re: [PATCH v3 03/14] KVM: x86: use physical LAPIC array for logical x2APIC Wanpeng Li <kernellwp@gmail.com> - 2016-08-02 15:50 +0200
  Re: [PATCH v3 03/14] KVM: x86: use physical LAPIC array for logical  x2APIC Radim Krčmář <rkrcmar@redhat.com> - 2016-08-02 16:30 +0200
    Re: [PATCH v3 03/14] KVM: x86: use physical LAPIC array for logical x2APIC Nadav Amit <nadav.amit@gmail.com> - 2016-08-02 18:50 +0200

csiph-web