From: Sean Christopherson <seanjc@xxxxxxxxxx>
[ Upstream commit 2b01281273738bf2d6551da48d65db2df3f28998 ]
Register /dev/kvm, i.e. expose KVM to userspace, only after all other
setup has completed. Once /dev/kvm is exposed, userspace can start
invoking KVM ioctls, creating VMs, etc... If userspace creates a VM
before KVM is done with its configuration, bad things may happen, e.g.
KVM will fail to properly migrate vCPU state if a VM is created before
KVM has registered preemption notifiers.
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
Message-Id: <20221130230934.1014142-2-seanjc@xxxxxxxxxx>
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
virt/kvm/kvm_main.c | 31 ++++++++++++++++++++++---------
1 file changed, 22 insertions(+), 9 deletions(-)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index c60e88b0b24ec..17e22c654c4e4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -5655,12 +5655,6 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
kvm_vm_fops.owner = module;
kvm_vcpu_fops.owner = module;
- r = misc_register(&kvm_dev);
- if (r) {
- pr_err("kvm: misc device register failed\n");
- goto out_unreg;
- }
-
register_syscore_ops(&kvm_syscore_ops);
kvm_preempt_ops.sched_in = kvm_sched_in;
@@ -5669,11 +5663,24 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
kvm_init_debug();
r = kvm_vfio_ops_init();
- WARN_ON(r);
+ if (WARN_ON_ONCE(r))
+ goto err_vfio;
+
+ /*
+ * Registration _must_ be the very last thing done, as this exposes
+ * /dev/kvm to userspace, i.e. all infrastructure must be setup!
+ */
+ r = misc_register(&kvm_dev);
+ if (r) {
+ pr_err("kvm: misc device register failed\n");
+ goto err_register;
+ }
return 0;
-out_unreg:
+err_register:
+ kvm_vfio_ops_exit();
+err_vfio:
kvm_async_pf_deinit();
out_free_5:
for_each_possible_cpu(cpu)
@@ -5700,8 +5707,14 @@ void kvm_exit(void)
{
int cpu;
- debugfs_remove_recursive(kvm_debugfs_dir);
+ /*
+ * Note, unregistering /dev/kvm doesn't strictly need to come first,
+ * fops_get(), a.k.a. try_module_get(), prevents acquiring references
+ * to KVM while the module is being stopped.
+ */
misc_deregister(&kvm_dev);
+
+ debugfs_remove_recursive(kvm_debugfs_dir);
for_each_possible_cpu(cpu)
free_cpumask_var(per_cpu(cpu_kick_mask, cpu));
kmem_cache_destroy(kvm_vcpu_cache);
--
2.39.2
