KVM: Ensure new code that references immediate_exit gets extra scrutiny

Ensure that any new KVM code that references immediate_exit gets extra
scrutiny by renaming it to immediate_exit__unsafe in kernel code.

All fields in struct kvm_run are subject to TOCTOU races since they are
mapped into userspace, which may be malicious or buggy. To protect KVM,
introduces a new macro that appends __unsafe to select field names in
struct kvm_run, hinting to developers and reviewers that accessing such
fields must be done carefully.

Apply the new macro to immediate_exit, since userspace can make
immediate_exit inconsistent with vcpu->wants_to_run, i.e. accessing
immediate_exit directly could lead to unexpected bugs in the future.

Signed-off-by: David Matlack <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
[sean: massage changelog]
Signed-off-by: Sean Christopherson <[email protected]>

Author: dmatlack

include/uapi/linux/kvm.h

@@ -192,11 +192,24 @@ struct kvm_xen_exit {
 /* Flags that describe what fields in emulation_failure hold valid data. */
 #define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0)
 
+/*
+ * struct kvm_run can be modified by userspace at any time, so KVM must be
+ * careful to avoid TOCTOU bugs. In order to protect KVM, HINT_UNSAFE_IN_KVM()
+ * renames fields in struct kvm_run from <symbol> to <symbol>__unsafe when
+ * compiled into the kernel, ensuring that any use within KVM is obvious and
+ * gets extra scrutiny.
+ */
+#ifdef __KERNEL__
+#define HINT_UNSAFE_IN_KVM(_symbol) _symbol##__unsafe
+#else
+#define HINT_UNSAFE_IN_KVM(_symbol) _symbol
+#endif
+
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
 	/* in */
 	__u8 request_interrupt_window;
-	__u8 immediate_exit;
+	__u8 HINT_UNSAFE_IN_KVM(immediate_exit);
 	__u8 padding1[6];
 
 	/* out */

virt/kvm/kvm_main.c

@@ -4435,7 +4435,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
 				synchronize_rcu();
 			put_pid(oldpid);
 		}
-		vcpu->wants_to_run = !READ_ONCE(vcpu->run->immediate_exit);
+		vcpu->wants_to_run = !READ_ONCE(vcpu->run->immediate_exit__unsafe);
 		r = kvm_arch_vcpu_ioctl_run(vcpu);
 		vcpu->wants_to_run = false;