diff mbox series

[12/44] KVM: VMX: Do _all_ initialization before exposing /dev/kvm to userspace

Message ID 20221102231911.3107438-13-seanjc@google.com
State New
Headers
Series KVM: Rework kvm_init() and hardware enabling |

Commit Message

Sean Christopherson Nov. 2, 2022, 11:18 p.m. UTC 
  Call kvm_init() only after _all_ setup is complete, as kvm_init() exposes
/dev/kvm to userspace and thus allows userspace to create VMs (and call
other ioctls).  E.g. KVM will encounter a NULL pointer when attempting to
add a vCPU to the per-CPU loaded_vmcss_on_cpu list if userspace is able to
create a VM before vmx_init() configures said list.

 BUG: kernel NULL pointer dereference, address: 0000000000000008
 #PF: supervisor write access in kernel mode
 #PF: error_code(0x0002) - not-present page
 PGD 0 P4D 0
 Oops: 0002 [#1] SMP
 CPU: 6 PID: 1143 Comm: stable Not tainted 6.0.0-rc7+ #988
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
 RIP: 0010:vmx_vcpu_load_vmcs+0x68/0x230 [kvm_intel]
  <TASK>
  vmx_vcpu_load+0x16/0x60 [kvm_intel]
  kvm_arch_vcpu_load+0x32/0x1f0 [kvm]
  vcpu_load+0x2f/0x40 [kvm]
  kvm_arch_vcpu_create+0x231/0x310 [kvm]
  kvm_vm_ioctl+0x79f/0xe10 [kvm]
  ? handle_mm_fault+0xb1/0x220
  __x64_sys_ioctl+0x80/0xb0
  do_syscall_64+0x2b/0x50
  entry_SYSCALL_64_after_hwframe+0x46/0xb0
 RIP: 0033:0x7f5a6b05743b
  </TASK>
 Modules linked in: vhost_net vhost vhost_iotlb tap kvm_intel(+) kvm irqbypass

Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/vmx.c | 38 +++++++++++++++++++++++---------------
 1 file changed, 23 insertions(+), 15 deletions(-)
diff mbox series

Patch

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 118d9b29b339..6adb60485839 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -8493,21 +8493,25 @@  static void vmx_cleanup_l1d_flush(void)
 	l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
 }
 
-static void vmx_exit(void)
+static void __vmx_exit(void)
 {
+	allow_smaller_maxphyaddr = false;
+
 #ifdef CONFIG_KEXEC_CORE
 	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
 	synchronize_rcu();
 #endif
-
-	kvm_exit();
-	kvm_x86_vendor_exit();
-
-	hv_cleanup_evmcs();
-
 	vmx_cleanup_l1d_flush();
+}
 
-	allow_smaller_maxphyaddr = false;
+static void vmx_exit(void)
+{
+	kvm_exit();
+	kvm_x86_vendor_exit();
+
+	__vmx_exit();
+
+	hv_cleanup_evmcs();
 }
 module_exit(vmx_exit);
 
@@ -8521,11 +8525,6 @@  static int __init vmx_init(void)
 	if (r)
 		goto err_x86_init;
 
-	r = kvm_init(&vmx_init_ops, sizeof(struct vcpu_vmx),
-		     __alignof__(struct vcpu_vmx), THIS_MODULE);
-	if (r)
-		goto err_kvm_init;
-
 	/*
 	 * Must be called after common x86 init so enable_ept is properly set
 	 * up. Hand the parameter mitigation value in which was stored in
@@ -8559,11 +8558,20 @@  static int __init vmx_init(void)
 	if (!enable_ept)
 		allow_smaller_maxphyaddr = true;
 
+	/*
+	 * Common KVM initialization _must_ come last, after this, /dev/kvm is
+	 * exposed to userspace!
+	 */
+	r = kvm_init(&vmx_init_ops, sizeof(struct vcpu_vmx),
+		     __alignof__(struct vcpu_vmx), THIS_MODULE);
+	if (r)
+		goto err_kvm_init;
+
 	return 0;
 
-err_l1d_flush:
-	vmx_exit();
 err_kvm_init:
+	__vmx_exit();
+err_l1d_flush:
 	kvm_x86_vendor_exit();
 err_x86_init:
 	hv_cleanup_evmcs();