[PATCH 05/12] xen: yield to IPI target if necessary

From: Jeremy Fitzhardinge
Date: Mon Oct 15 2007 - 17:49:36 EST


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

Signed-off-by: Jeremy Fitzhardinge <jeremy@xxxxxxxxxxxxx>

---
arch/x86/xen/smp.c | 14 ++++++++++----
arch/x86/xen/time.c | 6 ++++++
arch/x86/xen/xen-ops.h | 2 ++
3 files changed, 18 insertions(+), 4 deletions(-)

===================================================================
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -360,7 +360,8 @@ int xen_smp_call_function_mask(cpumask_t
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
/* 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 ||
===================================================================
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -103,6 +103,12 @@ static void get_runstate_snapshot(struct
*res = *state;
barrier();
} 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)
===================================================================
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -27,6 +27,8 @@ int xen_set_wallclock(unsigned long time
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);

DECLARE_PER_CPU(enum paravirt_lazy_mode, xen_lazy_mode);

--

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/