xen: yield to IPI target if necessary

When sending a call-function IPI to a vcpu, yield if the vcpu isn't
running.

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>

3 files changed, 18 insertions, 4 deletions

diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 557b8e24706a..865953e6f341 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -360,7 +360,8 @@ int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *),
                                void *info, int wait)
 {
         struct call_data_struct data;
-        int cpus;
+        int cpus, cpu;
+        bool yield;
 
         /* Holding any lock stops cpus from going down. */
         spin_lock(&call_lock);
@@ -389,9 +390,14 @@ int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *),
         /* Send a message to other CPUs and wait for them to respond */
         xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR);
 
-        /* Make sure other vcpus get a chance to run.
-           XXX too severe?  Maybe we should check the other CPU's states? */
-        HYPERVISOR_sched_op(SCHEDOP_yield, 0);
+        /* Make sure other vcpus get a chance to run if they need to. */
+        yield = false;
+        for_each_cpu_mask(cpu, mask)
+                if (xen_vcpu_stolen(cpu))
+                        yield = true;
+
+        if (yield)
+                HYPERVISOR_sched_op(SCHEDOP_yield, 0);
 
         /* Wait for response */
         while (atomic_read(&data.started) != cpus ||
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index dfd6db69ead5..d083ff5ef088 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -105,6 +105,12 @@ static void get_runstate_snapshot(struct vcpu_runstate_info *res)
         } while (get64(&state->state_entry_time) != state_time);
 }
 
+/* return true when a vcpu could run but has no real cpu to run on */
+bool xen_vcpu_stolen(int vcpu)
+{
+        return per_cpu(runstate, vcpu).state == RUNSTATE_runnable;
+}
+
 static void setup_runstate_info(int cpu)
 {
         struct vcpu_register_runstate_memory_area area;
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index b5697bae52d0..3847eed0bb09 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -27,6 +27,8 @@ unsigned long xen_get_wallclock(void);
 int xen_set_wallclock(unsigned long time);
 unsigned long long xen_sched_clock(void);
 
+bool xen_vcpu_stolen(int vcpu);
+
 void xen_mark_init_mm_pinned(void);
 
 void __init xen_fill_possible_map(void);