@@ -714,8 +714,10 @@ void sched_destroy_domain(struct domain *d)
}
}
-void vcpu_sleep_nosync_locked(struct vcpu *v)
+static void vcpu_sleep_nosync_locked(struct vcpu *v)
{
+ struct sched_unit *unit = v->sched_unit;
+
ASSERT(spin_is_locked(get_sched_res(v->processor)->schedule_lock));
if ( likely(!vcpu_runnable(v)) )
@@ -723,7 +725,14 @@ void vcpu_sleep_nosync_locked(struct vcpu *v)
if ( v->runstate.state == RUNSTATE_runnable )
vcpu_runstate_change(v, RUNSTATE_offline, NOW());
- sched_sleep(vcpu_scheduler(v), v->sched_unit);
+ if ( likely(!unit_runnable(unit)) )
+ sched_sleep(vcpu_scheduler(v), unit);
+ else if ( unit_running(unit) > 1 && v->is_running &&
+ !v->force_context_switch )
+ {
+ v->force_context_switch = true;
+ cpu_raise_softirq(v->processor, SCHED_SLAVE_SOFTIRQ);
+ }
}
}
@@ -755,16 +764,22 @@ void vcpu_wake(struct vcpu *v)
{
unsigned long flags;
spinlock_t *lock;
+ struct sched_unit *unit = v->sched_unit;
TRACE_2D(TRC_SCHED_WAKE, v->domain->domain_id, v->vcpu_id);
- lock = unit_schedule_lock_irqsave(v->sched_unit, &flags);
+ lock = unit_schedule_lock_irqsave(unit, &flags);
if ( likely(vcpu_runnable(v)) )
{
if ( v->runstate.state >= RUNSTATE_blocked )
vcpu_runstate_change(v, RUNSTATE_runnable, NOW());
- sched_wake(vcpu_scheduler(v), v->sched_unit);
+ sched_wake(vcpu_scheduler(v), unit);
+ if ( unit->is_running && !v->is_running && !v->force_context_switch )
+ {
+ v->force_context_switch = true;
+ cpu_raise_softirq(v->processor, SCHED_SLAVE_SOFTIRQ);
+ }
}
else if ( !(v->pause_flags & VPF_blocked) )
{
@@ -772,7 +787,7 @@ void vcpu_wake(struct vcpu *v)
vcpu_runstate_change(v, RUNSTATE_offline, NOW());
}
- unit_schedule_unlock_irqrestore(lock, flags, v->sched_unit);
+ unit_schedule_unlock_irqrestore(lock, flags, unit);
}
void vcpu_unblock(struct vcpu *v)
@@ -1981,6 +1996,62 @@ static void sched_context_switch(struct vcpu *vprev, struct vcpu *vnext,
context_switch(vprev, vnext);
}
+/*
+ * Force a context switch of a single vcpu of an unit.
+ * Might be called either if a vcpu of an already running unit is woken up
+ * or if a vcpu of a running unit is put asleep with other vcpus of the same
+ * unit still running.
+ */
+static struct vcpu *sched_force_context_switch(struct vcpu *vprev,
+ struct vcpu *v,
+ int cpu, s_time_t now)
+{
+ v->force_context_switch = false;
+
+ if ( vcpu_runnable(v) == v->is_running )
+ return NULL;
+
+ if ( vcpu_runnable(v) )
+ {
+ if ( is_idle_vcpu(vprev) )
+ {
+ vcpu_runstate_change(vprev, RUNSTATE_runnable, now);
+ vprev->sched_unit = get_sched_res(cpu)->sched_unit_idle;
+ }
+ vcpu_runstate_change(v, RUNSTATE_running, now);
+ }
+ else
+ {
+ /* Make sure not to switch last vcpu of an unit away. */
+ if ( unit_running(v->sched_unit) == 1 )
+ return NULL;
+
+ v->new_state = vcpu_runstate_blocked(v);
+ vcpu_runstate_change(v, v->new_state, now);
+ v = sched_unit2vcpu_cpu(vprev->sched_unit, cpu);
+ if ( v != vprev )
+ {
+ if ( is_idle_vcpu(vprev) )
+ {
+ vcpu_runstate_change(vprev, RUNSTATE_runnable, now);
+ vprev->sched_unit = get_sched_res(cpu)->sched_unit_idle;
+ }
+ else
+ {
+ v->sched_unit = vprev->sched_unit;
+ vcpu_runstate_change(v, RUNSTATE_running, now);
+ }
+ }
+ }
+
+ v->is_running = 1;
+
+ /* Make sure not to loose another slave call. */
+ raise_softirq(SCHED_SLAVE_SOFTIRQ);
+
+ return v;
+}
+
/*
* Rendezvous before taking a scheduling decision.
* Called with schedule lock held, so all accesses to the rendezvous counter
@@ -1996,6 +2067,7 @@ static struct sched_unit *sched_wait_rendezvous_in(struct sched_unit *prev,
s_time_t now)
{
struct sched_unit *next;
+ struct vcpu *v;
if ( !--prev->rendezvous_in_cnt )
{
@@ -2004,8 +2076,28 @@ static struct sched_unit *sched_wait_rendezvous_in(struct sched_unit *prev,
return next;
}
+ v = unit2vcpu_cpu(prev, cpu);
while ( prev->rendezvous_in_cnt )
{
+ if ( v && v->force_context_switch )
+ {
+ struct vcpu *vprev = current;
+
+ v = sched_force_context_switch(vprev, v, cpu, now);
+
+ if ( v )
+ {
+ /* We'll come back another time, so adjust rendezvous_in_cnt. */
+ prev->rendezvous_in_cnt++;
+ atomic_set(&prev->rendezvous_out_cnt, 0);
+
+ pcpu_schedule_unlock_irq(*lock, cpu);
+
+ sched_context_switch(vprev, v, false, now);
+ }
+
+ v = unit2vcpu_cpu(prev, cpu);
+ }
/*
* Coming from idle might need to do tasklet work.
* In order to avoid deadlocks we can't do that here, but have to
@@ -2038,10 +2130,11 @@ static struct sched_unit *sched_wait_rendezvous_in(struct sched_unit *prev,
static void sched_slave(void)
{
- struct vcpu *vprev = current;
+ struct vcpu *v, *vprev = current;
struct sched_unit *prev = vprev->sched_unit, *next;
s_time_t now;
spinlock_t *lock;
+ bool do_softirq = false;
int cpu = smp_processor_id();
ASSERT_NOT_IN_ATOMIC();
@@ -2050,9 +2143,29 @@ static void sched_slave(void)
now = NOW();
+ v = unit2vcpu_cpu(prev, cpu);
+ if ( v && v->force_context_switch )
+ {
+ v = sched_force_context_switch(vprev, v, cpu, now);
+
+ if ( v )
+ {
+ pcpu_schedule_unlock_irq(lock, cpu);
+
+ sched_context_switch(vprev, v, false, now);
+ }
+
+ do_softirq = true;
+ }
+
if ( !prev->rendezvous_in_cnt )
{
pcpu_schedule_unlock_irq(lock, cpu);
+
+ /* Check for failed forced context switch. */
+ if ( do_softirq )
+ raise_softirq(SCHEDULE_SOFTIRQ);
+
return;
}
@@ -99,6 +99,11 @@ static inline bool unit_runnable(const struct sched_unit *unit)
return false;
}
+static inline int vcpu_runstate_blocked(struct vcpu *v)
+{
+ return (v->pause_flags & VPF_blocked) ? RUNSTATE_blocked : RUNSTATE_offline;
+}
+
static inline bool unit_runnable_state(const struct sched_unit *unit)
{
struct vcpu *v;
@@ -111,9 +116,7 @@ static inline bool unit_runnable_state(const struct sched_unit *unit)
{
runnable = vcpu_runnable(v);
- v->new_state = runnable ? RUNSTATE_running
- : (v->pause_flags & VPF_blocked)
- ? RUNSTATE_blocked : RUNSTATE_offline;
+ v->new_state = runnable ? RUNSTATE_running : vcpu_runstate_blocked(v);
if ( runnable )
ret = true;
@@ -186,6 +186,8 @@ struct vcpu
bool is_running;
/* VCPU should wake fast (do not deep sleep the CPU). */
bool is_urgent;
+ /* VCPU must context_switch without scheduling unit. */
+ bool force_context_switch;
#ifdef VCPU_TRAP_LAST
#define VCPU_TRAP_NONE 0
vcpu_wake() and vcpu_sleep() need to be made core scheduling aware: they might need to switch a single vcpu of an already scheduled unit between running and not running. Especially when vcpu_sleep() for a vcpu is being called by a vcpu of the same scheduling unit special care must be taken in order to avoid a deadlock: the vcpu to be put asleep must be forced through a context switch without doing so for the calling vcpu. For this purpose add a vcpu flag handled in sched_slave() and in sched_wait_rendezvous_in() allowing a vcpu of the currently running unit to switch state at a higher priority than a normal schedule event. Use the same mechanism when waking up a vcpu of a currently active unit. While at it make vcpu_sleep_nosync_locked() static as it is used in schedule.c only. Signed-off-by: Juergen Gross <jgross@suse.com> --- RFC V2: add vcpu_sleep() handling and force_context_switch flag V2: fix runstate change in sched_force_context_switch() --- xen/common/schedule.c | 125 ++++++++++++++++++++++++++++++++++++++++++--- xen/include/xen/sched-if.h | 9 ++-- xen/include/xen/sched.h | 2 + 3 files changed, 127 insertions(+), 9 deletions(-)