KVM: let kvm_destroy_vm_debugfs clean up vCPU debugfs directories

After commit 63d0434 ("KVM: x86: move kvm_create_vcpu_debugfs after
last failure point") we are creating the pre-vCPU debugfs files
after the creation of the vCPU file descriptor.  This makes it
possible for userspace to reach kvm_vcpu_release before
kvm_create_vcpu_debugfs has finished.  The vcpu->debugfs_dentry
then does not have any associated inode anymore, and this causes
a NULL-pointer dereference in debugfs_create_file.

The solution is simply to avoid removing the files; they are
cleaned up when the VM file descriptor is closed (and that must be
after KVM_CREATE_VCPU returns).  We can stop storing the dentry
in struct kvm_vcpu too, because it is not needed anywhere after
kvm_create_vcpu_debugfs returns.

Reported-by: syzbot+705f4401d5a93a59b87d@syzkaller.appspotmail.com
Fixes: 63d0434837 ("KVM: x86: move kvm_create_vcpu_debugfs after last failure point")
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This commit is contained in:
Paolo Bonzini
2020-06-04 15:16:52 +02:00
parent 6929f71e46
commit d56f5136b0
4 changed files with 10 additions and 16 deletions

View File

@@ -318,7 +318,6 @@ struct kvm_vcpu {
bool preempted;
bool ready;
struct kvm_vcpu_arch arch;
struct dentry *debugfs_dentry;
};
static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
@@ -888,7 +887,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS
void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu);
void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry);
#endif
int kvm_arch_hardware_enable(void);