[Xen-changelog] Remove the spin on VCPUF_running from context_switch().

[Xen patchbot -unstable <patchbot-unstable@xxxxxxxxxxxxxxxxxxx>]

# HG changeset patch
# User kaf24@xxxxxxxxxxxxxxxxxxxx
# Node ID af7e4ce4665399f9468e85839013ce9c441edd53
# Parent  1b7d6c2ae2f7626facde3dc61aa899204ada2da8
Remove the spin on VCPUF_running from context_switch().
It doesn't work because we already set VCPUF_running
locally, and the scheduler should not pick another CPU's
VCPUF_running VCPU anyway, since it mustn't modify the 
processor field.

Instead just add a simple assertion to the scheduler to
ensure the scheduling algorithm is not picking an
inappropriate VCPU.

Signed-off-by: Keir Fraser <keir@xxxxxxxxxxxxx>

diff -r 1b7d6c2ae2f7 -r af7e4ce46653 xen/arch/x86/domain.c
--- a/xen/arch/x86/domain.c     Tue Jan 17 12:25:30 2006
+++ b/xen/arch/x86/domain.c     Tue Jan 17 13:24:42 2006
@@ -738,9 +738,6 @@
     ASSERT(cpus_weight(dirty_mask) <= 1);
     if ( unlikely(!cpu_isset(cpu, dirty_mask) && !cpus_empty(dirty_mask)) )
     {
-        /* Make sure the next VCPU is not in a scheduling tail. */
-        while ( test_bit(_VCPUF_running, &next->vcpu_flags) )
-            cpu_relax();
         /* Other cpus call __sync_lazy_execstate from flush ipi handler. */
         if ( !cpus_empty(next->vcpu_dirty_cpumask) )
             flush_tlb_mask(next->vcpu_dirty_cpumask);
diff -r 1b7d6c2ae2f7 -r af7e4ce46653 xen/common/schedule.c
--- a/xen/common/schedule.c     Tue Jan 17 12:25:30 2006
+++ b/xen/common/schedule.c     Tue Jan 17 13:24:42 2006
@@ -420,6 +420,7 @@
     }
 #endif
 
+    ASSERT(!test_bit(_VCPUF_running, &next->vcpu_flags));
     set_bit(_VCPUF_running, &next->vcpu_flags);
 
     spin_unlock_irq(&schedule_data[cpu].schedule_lock);

_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-changelog