It turns out that if userspace creates a pseries-type VM without
in-kernel XICS (interrupt controller) emulation, and then connects
an eventfd to the VM as an irqfd, and the eventfd gets signalled,
that the code will try to deliver an interrupt via the non-existent
XICS object and crash the host kernel with a NULL pointer dereference.
To fix this, we check for the presence of the XICS object before
trying to deliver the interrupt, and return with an error if not.
Signed-off-by: Paul Mackerras <paulus@xxxxxxxxxx>
---
arch/powerpc/kvm/book3s_xics.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index a75ba38..d5de902 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -1252,6 +1252,8 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
{
struct kvmppc_xics *xics = kvm->arch.xics;
+ if (!xics)
+ return -ENODEV;
return ics_deliver_irq(xics, irq, level);
}
--
2.8.1
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
