From: David Matlack <dmatlack@xxxxxxxxxx>
commit 5f6de5cbebee925a612856fce6f9182bb3eee0db upstream.
Tie the lifetime the KVM module to the lifetime of each VM via
kvm.users_count. This way anything that grabs a reference to the VM via
kvm_get_kvm() cannot accidentally outlive the KVM module.
Prior to this commit, the lifetime of the KVM module was tied to the
lifetime of /dev/kvm file descriptors, VM file descriptors, and vCPU
file descriptors by their respective file_operations "owner" field.
This approach is insufficient because references grabbed via
kvm_get_kvm() do not prevent closing any of the aforementioned file
descriptors.
This fixes a long standing theoretical bug in KVM that at least affects
async page faults. kvm_setup_async_pf() grabs a reference via
kvm_get_kvm(), and drops it in an asynchronous work callback. Nothing
prevents the VM file descriptor from being closed and the KVM module
from being unloaded before this callback runs.
Fixes: af585b921e5d ("KVM: Halt vcpu if page it tries to access is swapped out")
Fixes: 3d3aab1b973b ("KVM: set owner of cpu and vm file operations")
Cc: stable@xxxxxxxxxxxxxxx
Suggested-by: Ben Gardon <bgardon@xxxxxxxxxx>
[ Based on a patch from Ben implemented for Google's kernel. ]
Signed-off-by: David Matlack <dmatlack@xxxxxxxxxx>
Message-Id: <20220303183328.1499189-2-dmatlack@xxxxxxxxxx>
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
virt/kvm/kvm_main.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -107,6 +107,8 @@ EXPORT_SYMBOL_GPL(kvm_debugfs_dir);
static int kvm_debugfs_num_entries;
static const struct file_operations *stat_fops_per_vm[];
+static struct file_operations kvm_chardev_ops;
+
static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
unsigned long arg);
#ifdef CONFIG_KVM_COMPAT
@@ -714,6 +716,16 @@ static struct kvm *kvm_create_vm(unsigne
preempt_notifier_inc();
+ /*
+ * When the fd passed to this ioctl() is opened it pins the module,
+ * but try_module_get() also prevents getting a reference if the module
+ * is in MODULE_STATE_GOING (e.g. if someone ran "rmmod --wait").
+ */
+ if (!try_module_get(kvm_chardev_ops.owner)) {
+ r = -ENODEV;
+ goto out_err;
+ }
+
return kvm;
out_err:
@@ -798,6 +810,7 @@ static void kvm_destroy_vm(struct kvm *k
preempt_notifier_dec();
hardware_disable_all();
mmdrop(mm);
+ module_put(kvm_chardev_ops.owner);
}
void kvm_get_kvm(struct kvm *kvm)
