add update indicator to vcpu_runstate_info

There has been a report about incorrect vruntime accounting in Linux
guests under Xen. A Linux kernel with CONFIG_PARAVIRT_TIME_ACCOUNTING
set is capable to do correct vruntime accounting, but this would
require the kernel to be able to read the runstate data of other cpus.

A guest mapping vcpu_runstate_info into its memory can't read this
information from another cpu but the one the data is referring to.
Reason is there is no reliable way for the guest to detect a concurrent
data update by the hypervisor. In order to support reading another
vcpu's mapped vcpu_runstate_info an indicator for an occurring update
of the runstate information is needed.

Add the possibility to activate setting this indicator in the highest
bit of state_entry_time via a vm_assist hypercall. When activated the
update indicator will be set before the runstate information is
modified in guest memory and it will be reset after modification is
done. As state_entry_time is guaranteed to be different after each
update the guest can detect any update (either in progress or while
reading the runstate data) by comparing state_entry_time before and
after reading runstate data: in case the values differ or the update
indicator was set the data might be inconsistent and should be reread.

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

xen/arch/arm/domain.c

@@ -239,10 +239,30 @@ static void ctxt_switch_to(struct vcpu *n)
 /* Update per-VCPU guest runstate shared memory area (if registered). */
 static void update_runstate_area(struct vcpu *v)
 {
+    void __user *guest_handle = NULL;
+
     if ( guest_handle_is_null(runstate_guest(v)) )
         return;
 
+    if ( VM_ASSIST(v->domain, runstate_update_flag) )
+    {
+        guest_handle = &v->runstate_guest.p->state_entry_time + 1;
+        guest_handle--;
+        v->runstate.state_entry_time |= XEN_RUNSTATE_UPDATE;
+        __raw_copy_to_guest(guest_handle,
+                            (void *)(&v->runstate.state_entry_time + 1) - 1, 1);
+        smp_wmb();
+    }
+
     __copy_to_guest(runstate_guest(v), &v->runstate, 1);
+
+    if ( guest_handle )
+    {
+        v->runstate.state_entry_time &= ~XEN_RUNSTATE_UPDATE;
+        smp_wmb();
+        __raw_copy_to_guest(guest_handle,
+                            (void *)(&v->runstate.state_entry_time + 1) - 1, 1);
+    }
 }
 
 static void schedule_tail(struct vcpu *prev)

xen/arch/x86/domain.c

@@ -1926,12 +1926,25 @@ bool_t update_runstate_area(struct vcpu *v)
 {
     bool_t rc;
     smap_check_policy_t smap_policy;
+    void __user *guest_handle = NULL;
 
     if ( guest_handle_is_null(runstate_guest(v)) )
         return 1;
 
     smap_policy = smap_policy_change(v, SMAP_CHECK_ENABLED);
 
+    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;
+        __raw_copy_to_guest(guest_handle,
+                            (void *)(&v->runstate.state_entry_time + 1) - 1, 1);
+        smp_wmb();
+    }
+
     if ( has_32bit_shinfo(v->domain) )
     {
         struct compat_vcpu_runstate_info info;
@@ -1944,6 +1957,14 @@ bool_t update_runstate_area(struct vcpu *v)
         rc = __copy_to_guest(runstate_guest(v), &v->runstate, 1) !=
              sizeof(v->runstate);
 
+    if ( guest_handle )
+    {
+        v->runstate.state_entry_time &= ~XEN_RUNSTATE_UPDATE;
+        smp_wmb();
+        __raw_copy_to_guest(guest_handle,
+                            (void *)(&v->runstate.state_entry_time + 1) - 1, 1);
+    }
+
     smap_policy_change(v, smap_policy);
 
     return rc;

xen/include/asm-arm/config.h

@@ -199,7 +199,7 @@ extern unsigned long frametable_virt_end;
 #define watchdog_disable() ((void)0)
 #define watchdog_enable()  ((void)0)
 
-#define VM_ASSIST_VALID          (0)
+#define VM_ASSIST_VALID          (1UL << VMASST_TYPE_runstate_update_flag)
 
 #endif /* __ARM_CONFIG_H__ */
 /*

xen/include/asm-x86/config.h

@@ -332,6 +332,7 @@ extern unsigned long xen_phys_start;
                                   (1UL << VMASST_TYPE_writable_pagetables) | \
                                   (1UL << VMASST_TYPE_pae_extended_cr3)    | \
                                   (1UL << VMASST_TYPE_architectural_iopl)  | \
+                                  (1UL << VMASST_TYPE_runstate_update_flag)| \
                                   (1UL << VMASST_TYPE_m2p_strict))
 #define VM_ASSIST_VALID          NATIVE_VM_ASSIST_VALID
 #define COMPAT_VM_ASSIST_VALID   (NATIVE_VM_ASSIST_VALID & \

xen/include/public/vcpu.h

@@ -83,6 +83,12 @@ struct vcpu_runstate_info {
     int      state;
     /* When was current state entered (system time, ns)? */
     uint64_t state_entry_time;
+    /*
+     * Update indicator set in state_entry_time:
+     * When activated via VMASST_TYPE_runstate_update_flag, set during
+     * updates in guest memory mapped copy of vcpu_runstate_info.
+     */
+#define XEN_RUNSTATE_UPDATE          (1ULL << 63)
     /*
      * Time spent in each RUNSTATE_* (ns). The sum of these times is
      * guaranteed not to drift from system time.

xen/include/public/xen.h

@@ -509,6 +509,13 @@ DEFINE_XEN_GUEST_HANDLE(mmuext_op_t);
  */
 #define VMASST_TYPE_architectural_iopl   4
 
+/*
+ * All guests: activate update indicator in vcpu_runstate_info
+ * Enable setting the XEN_RUNSTATE_UPDATE flag in guest memory mapped
+ * vcpu_runstate_info during updates of the runstate information.
+ */
+#define VMASST_TYPE_runstate_update_flag 5
+
 /*
  * x86/64 guests: strictly hide M2P from user mode.
  * This allows the guest to control respective hypervisor behavior: