From 906ea0086b70c146e1871a773430d7574391bf84 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 30 Nov 2022 23:08:45 +0000 Subject: [PATCH] KVM: Register /dev/kvm as the _very_ last thing during initialization commit 2b01281273738bf2d6551da48d65db2df3f28998 upstream. 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@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20221130230934.1014142-2-seanjc@google.com> Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- 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 9c60384b5ae0..07aae60288f9 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5995,12 +5995,6 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, kvm_chardev_ops.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; @@ -6009,11 +6003,24 @@ 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_4: for_each_possible_cpu(cpu) @@ -6039,8 +6046,14 @@ 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);