Re: [PATCH v4 4/6] KVM: X86: Implement PV IPIs send hypercall

[Wanpeng Li <kernellwp@xxxxxxxxx>]

On Mon, 23 Jul 2018 at 13:52, Paolo Bonzini <pbonzini@xxxxxxxxxx> wrote:
>
> On 20/07/2018 18:28, Wanpeng Li wrote:
> > +a0: ipi_bitmap low 64 bits
> > +a1: ipi_bitmap high 64 bits
> > +a2: the lowest APIC ID in bitmap
> > +a3: APIC ICR
> > +
> > +The hypercall lets a guest send multicast IPIs at most can handle
> > +128 vCPUs per hypercall on 64-bit machines and 64 vCPUs per hypercall
> > +on 32-bit machines.
> > +
> > +Returns 0 if successfully delivery the IPIs and 1 if discarded.
>
> This description does not mention what happens in 32-bit mode.

Will do in next version.

>
> > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> > index 2b812b3..016c7e2 100644
> > --- a/arch/x86/kvm/x86.c
> > +++ b/arch/x86/kvm/x86.c
> > @@ -6691,6 +6691,41 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
> >       kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL);
> >  }
> >
> > +/*
> > + * Return 0 if successfully added and 1 if discarded.
> > + */
> > +static int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
> > +             unsigned long ipi_bitmap_high, int min, int vector, int op_64_bit)
> > +{
> > +     int i;
> > +     struct kvm_apic_map *map;
> > +     struct kvm_vcpu *vcpu;
> > +     struct kvm_lapic_irq irq = {
> > +             .delivery_mode = APIC_DM_FIXED,
> > +             .vector = vector,
> > +     };
> > +
> > +     rcu_read_lock();
> > +     map = rcu_dereference(kvm->arch.apic_map);
> > +
> > +     for_each_set_bit(i, &ipi_bitmap_low, BITS_PER_LONG) {
> > +             vcpu = map->phys_map[min + i]->vcpu;
> > +             if (!kvm_apic_set_irq(vcpu, &irq, NULL))
> > +                     return 1;
> > +     }
> > +
> > +     if (op_64_bit) {
> > +             for_each_set_bit(i, &ipi_bitmap_high, BITS_PER_LONG) {
> > +                     vcpu = map->phys_map[min + i + BITS_PER_LONG]->vcpu;
> > +                     if (!kvm_apic_set_irq(vcpu, &irq, NULL))
> > +                             return 1;
> > +             }
> > +     }
>
> The second loop processes the second argument, and it should always run,
> even in 32-bit mode.  However, the phys_map index should be min + i + 32
> in 32-bit mode and min + i + 64 in 64-bit mode.  (Using BITS_PER_LONG in
> the for_each_set_bit length is not a bug instead; you could write it
> explicitly as 32 in 32-bit mode, and 64 in 64-bit mode, but I think it's
> a little bit more efficient if it's constant).

Good catch, below should fix it.

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c9dbc2c..c118040 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6701,6 +6701,7 @@ static int kvm_pv_send_ipi(struct kvm *kvm,
unsigned long ipi_bitmap_low,
     struct kvm_apic_map *map;
     struct kvm_vcpu *vcpu;
     struct kvm_lapic_irq irq = {0};
+    int cluster_size = op_64_bit ? 64 : 32;

     switch (icr & APIC_VECTOR_MASK) {
     default:
@@ -6714,18 +6715,16 @@ static int kvm_pv_send_ipi(struct kvm *kvm,
unsigned long ipi_bitmap_low,
     rcu_read_lock();
     map = rcu_dereference(kvm->arch.apic_map);

-    for_each_set_bit(i, &ipi_bitmap_low, BITS_PER_LONG) {
+    for_each_set_bit(i, &ipi_bitmap_low, cluster_size) {
         vcpu = map->phys_map[min + i]->vcpu;
         if (!kvm_apic_set_irq(vcpu, &irq, NULL))
             return 1;
     }

-    if (op_64_bit) {
-        for_each_set_bit(i, &ipi_bitmap_high, BITS_PER_LONG) {
-            vcpu = map->phys_map[min + i + BITS_PER_LONG]->vcpu;
-            if (!kvm_apic_set_irq(vcpu, &irq, NULL))
-                return 1;
-        }
+    for_each_set_bit(i, &ipi_bitmap_high, cluster_size) {
+        vcpu = map->phys_map[min + i + cluster_size]->vcpu;
+        if (!kvm_apic_set_irq(vcpu, &irq, NULL))
+            return 1;
     }

     rcu_read_unlock();