[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1438200012.13460.74.camel@redhat.com>
Date: Wed, 29 Jul 2015 14:00:12 -0600
From: Alex Williamson <alex.williamson@...hat.com>
To: Paolo Bonzini <pbonzini@...hat.com>
Cc: linux-kernel@...r.kernel.org, kvm@...r.kernel.org,
yang.z.zhang@...el.com, srutherford@...el.com
Subject: Re: [PATCH 0/2] KVM: x86: limit interactions between IOAPIC and
LAPIC
On Wed, 2015-07-29 at 15:37 +0200, Paolo Bonzini wrote:
> Inspired by the split irqchip patches, this series limits the
> IOAPIC<->LAPIC to the EOI exit bitmap that is inferred from the
> redirection table.
>
> TMR is entirely handled within the local APIC, and no global copy
> of the IOAPIC-handled vectors is necessary anymore. This makes
> it simpler to introduce a userspace IOAPIC.
>
> Tested with ioapic.flat for now, planning to do more complete tests
> tomorrow. The most interesting test to do here is an assigned device
> that uses INTX, so I am CCing Alex Williamson for a heads up.
Tested Windows and Linux guests with assigned devices restricted to INTx
mode, no obvious regression. Thanks,
Alex
> Paolo Bonzini (2):
> KVM: x86: set TMR when the interrupt is accepted
> KVM: x86: store IOAPIC-handled vectors in each VCPU
>
> arch/x86/include/asm/kvm_host.h | 3 ++-
> arch/x86/kvm/ioapic.c | 27 ++++-----------------------
> arch/x86/kvm/ioapic.h | 11 +----------
> arch/x86/kvm/lapic.c | 29 ++++++++++++++++++-----------
> arch/x86/kvm/lapic.h | 1 -
> arch/x86/kvm/svm.c | 2 +-
> arch/x86/kvm/vmx.c | 3 ++-
> arch/x86/kvm/x86.c | 11 +++--------
> 8 files changed, 31 insertions(+), 56 deletions(-)
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists