KVM: kvm_io_bus_unregister_dev() should never fail

No caller currently checks the return value of
kvm_io_bus_unregister_dev(). This is evil, as all callers silently go on
freeing their device. A stale reference will remain in the io_bus,
getting at least used again, when the iobus gets teared down on
kvm_destroy_vm() - leading to use after free errors.

There is nothing the callers could do, except retrying over and over
again.

So let's simply remove the bus altogether, print an error and make
sure no one can access this broken bus again (returning -ENOMEM on any
attempt to access it).

Fixes: e93f8a0f821e ("KVM: convert io_bus to SRCU")
Cc: stable@vger.kernel.org # 3.4+
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 25 insertions, 17 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7445566fadc1..ef1aa7f1ed7a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -728,7 +728,8 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	spin_unlock(&kvm_lock);
 	kvm_free_irq_routing(kvm);
 	for (i = 0; i < KVM_NR_BUSES; i++) {
-		kvm_io_bus_destroy(kvm->buses[i]);
+		if (kvm->buses[i])
+			kvm_io_bus_destroy(kvm->buses[i]);
 		kvm->buses[i] = NULL;
 	}
 	kvm_coalesced_mmio_free(kvm);
@@ -3476,6 +3477,8 @@ int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 	};
 
 	bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+	if (!bus)
+		return -ENOMEM;
 	r = __kvm_io_bus_write(vcpu, bus, &range, val);
 	return r < 0 ? r : 0;
 }
@@ -3493,6 +3496,8 @@ int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx,
 	};
 
 	bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+	if (!bus)
+		return -ENOMEM;
 
 	/* First try the device referenced by cookie. */
 	if ((cookie >= 0) && (cookie < bus->dev_count) &&
@@ -3543,6 +3548,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 	};
 
 	bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+	if (!bus)
+		return -ENOMEM;
 	r = __kvm_io_bus_read(vcpu, bus, &range, val);
 	return r < 0 ? r : 0;
 }
@@ -3555,6 +3562,9 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm->buses[bus_idx];
+	if (!bus)
+		return -ENOMEM;
+
 	/* exclude ioeventfd which is limited by maximum fd */
 	if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1)
 		return -ENOSPC;
@@ -3574,45 +3584,41 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 }
 
 /* Caller must hold slots_lock. */
-int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
-			      struct kvm_io_device *dev)
+void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+			       struct kvm_io_device *dev)
 {
-	int i, r;
+	int i;
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm->buses[bus_idx];
-
-	/*
-	 * It's possible the bus being released before hand. If so,
-	 * we're done here.
-	 */
 	if (!bus)
-		return 0;
+		return;
 
-	r = -ENOENT;
 	for (i = 0; i < bus->dev_count; i++)
 		if (bus->range[i].dev == dev) {
-			r = 0;
 			break;
 		}
 
-	if (r)
-		return r;
+	if (i == bus->dev_count)
+		return;
 
 	new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count - 1) *
 			  sizeof(struct kvm_io_range)), GFP_KERNEL);
-	if (!new_bus)
-		return -ENOMEM;
+	if (!new_bus)  {
+		pr_err("kvm: failed to shrink bus, removing it completely\n");
+		goto broken;
+	}
 
 	memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
 	new_bus->dev_count--;
 	memcpy(new_bus->range + i, bus->range + i + 1,
 	       (new_bus->dev_count - i) * sizeof(struct kvm_io_range));
 
+broken:
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
 	kfree(bus);
-	return r;
+	return;
 }
 
 struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
@@ -3625,6 +3631,8 @@ struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 
 	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
+	if (!bus)
+		goto out_unlock;
 
 	dev_idx = kvm_io_bus_get_first_dev(bus, addr, 1);
 	if (dev_idx < 0)