[Xen-devel] [PATCH v1 12/13] x86/PMU: Save VPMU state for PV guests during context switch

[Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>]

Save VPMU state during context switch for both HVM and PV guests unless we
are in VPMU_DOM0 vpmu mode (i.e. dom0 is doing all profiling).

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
---
 xen/arch/x86/domain.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index 36f4192..e74ad5c 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -1416,17 +1416,15 @@ void context_switch(struct vcpu *prev, struct vcpu 
*next)
     }
 
     if (prev != next)
-        update_runstate_area(prev);
-
-    if ( is_hvm_vcpu(prev) )
     {
-        if (prev != next)
+        update_runstate_area(prev);
+        if ( !(vpmu_mode & VPMU_PRIV) || prev->domain != dom0 )
             vpmu_save(prev);
-
-        if ( !list_empty(&prev->arch.hvm_vcpu.tm_list) )
-            pt_save_timer(prev);
     }
 
+    if ( is_hvm_vcpu(prev) && !list_empty(&prev->arch.hvm_vcpu.tm_list) )
+        pt_save_timer(prev);
+
     local_irq_disable();
 
     set_current(next);
@@ -1463,7 +1461,7 @@ void context_switch(struct vcpu *prev, struct vcpu *next)
                            (next->domain->domain_id != 0));
     }
 
-    if (is_hvm_vcpu(next) && (prev != next) )
+    if ( prev != next && !(vpmu_mode & VPMU_PRIV) )
         /* Must be done with interrupts enabled */
         vpmu_load(next);
 
-- 
1.8.1.4


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel