sched: don't let XEN_RUNSTATE_UPDATE leak into vcpu_runstate_get()

vcpu_runstate_get() should never return a state entry time with
XEN_RUNSTATE_UPDATE set. To avoid this let update_runstate_area()
operate on a local runstate copy.

As it is required to first set the XEN_RUNSTATE_UPDATE indicator in
guest memory, then update all the runstate data, and then at last
clear the XEN_RUNSTATE_UPDATE again it is much less effort to have
a local copy of the runstate data instead of keeping only a copy of
state_entry_time.

This problem was introduced with commit 2529c850ea48f036 ("add update
indicator to vcpu_runstate_info").

Reported-by: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Julien Grall <julien.grall@arm.com>

1 files changed, 10 insertions, 7 deletions

diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index c0faf68852..c7fa224c89 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -1600,21 +1600,24 @@ bool update_runstate_area(struct vcpu *v)
     bool rc;
     struct guest_memory_policy policy = { .nested_guest_mode = false };
     void __user *guest_handle = NULL;
+    struct vcpu_runstate_info runstate;
 
     if ( guest_handle_is_null(runstate_guest(v)) )
         return true;
 
     update_guest_memory_policy(v, &policy);
 
+    memcpy(&runstate, &v->runstate, sizeof(runstate));
+
     if ( VM_ASSIST(v->domain, runstate_update_flag) )
     {
         guest_handle = has_32bit_shinfo(v->domain)
             ? &v->runstate_guest.compat.p->state_entry_time + 1
             : &v->runstate_guest.native.p->state_entry_time + 1;
         guest_handle--;
-        v->runstate.state_entry_time |= XEN_RUNSTATE_UPDATE;
+        runstate.state_entry_time |= XEN_RUNSTATE_UPDATE;
         __raw_copy_to_guest(guest_handle,
-                            (void *)(&v->runstate.state_entry_time + 1) - 1, 1);
+                            (void *)(&runstate.state_entry_time + 1) - 1, 1);
         smp_wmb();
     }
 
@@ -1622,20 +1625,20 @@ bool update_runstate_area(struct vcpu *v)
     {
         struct compat_vcpu_runstate_info info;
 
-        XLAT_vcpu_runstate_info(&info, &v->runstate);
+        XLAT_vcpu_runstate_info(&info, &runstate);
         __copy_to_guest(v->runstate_guest.compat, &info, 1);
         rc = true;
     }
     else
-        rc = __copy_to_guest(runstate_guest(v), &v->runstate, 1) !=
-             sizeof(v->runstate);
+        rc = __copy_to_guest(runstate_guest(v), &runstate, 1) !=
+             sizeof(runstate);
 
     if ( guest_handle )
     {
-        v->runstate.state_entry_time &= ~XEN_RUNSTATE_UPDATE;
+        runstate.state_entry_time &= ~XEN_RUNSTATE_UPDATE;
         smp_wmb();
         __raw_copy_to_guest(guest_handle,
-                            (void *)(&v->runstate.state_entry_time + 1) - 1, 1);
+                            (void *)(&runstate.state_entry_time + 1) - 1, 1);
     }
 
     update_guest_memory_policy(v, &policy);