On Tue, Jul 25, 2017 at 1:08 AM, Paolo Bonzini <pbonzini@xxxxxxxxxx> wrote: > On 28/04/2017 07:13, fanwenyi0529@xxxxxxxxx wrote: >> From: Wincy Van <fanwenyi0529@xxxxxxxxx> >> >> The nested/non-nested PI vector is the same currently, this is wrong >> since the non-nested PI may not be recognized if dest vcpu is in L2. >> >> This patch series introduce a new vector for nested PI to solve the >> problem. >> >> Wincy Van (2): >> x86: irq: Define a global vector for nested posted interrupts >> KVM: nVMX: Fix posted intr delivery when vcpu is in guest mode >> >> arch/x86/entry/entry_64.S | 1 + >> arch/x86/include/asm/entry_arch.h | 2 ++ >> arch/x86/include/asm/hardirq.h | 1 + >> arch/x86/include/asm/hw_irq.h | 2 ++ >> arch/x86/include/asm/irq_vectors.h | 1 + >> arch/x86/kernel/irq.c | 13 +++++++++++++ >> arch/x86/kernel/irqinit.c | 2 ++ >> arch/x86/kvm/vmx.c | 22 +++++++++++----------- >> 8 files changed, 33 insertions(+), 11 deletions(-) >> > > Belatedly applying this, with this change: > > diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c > index e3d4718faa95..6b85958ea2ec 100644 > --- a/arch/x86/kernel/irq.c > +++ b/arch/x86/kernel/irq.c > @@ -155,6 +155,12 @@ int arch_show_interrupts(struct seq_file *p, int prec) > seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis); > seq_puts(p, " Posted-interrupt notification event\n"); > > + seq_printf(p, "%*s: ", prec, "NPI"); > + for_each_online_cpu(j) > + seq_printf(p, "%10u ", > + irq_stats(j)->kvm_posted_intr_nested_ipis); > + seq_puts(p, " Nested posted-interrupt wakeup event\n"); > + > seq_printf(p, "%*s: ", prec, "PIW"); > for_each_online_cpu(j) > seq_printf(p, "%10u ", > > on top of patch 1. > It's nice, thank you :) Wincy
