@@ -159,6 +159,23 @@ static void idle_loop(void)
}
}
+/*
+ * Idle loop for siblings of active schedule units.
+ * We don't do any standard idle work like tasklets, page scrubbing or
+ * livepatching.
+ */
+static void guest_idle_loop(void)
+{
+ unsigned int cpu = smp_processor_id();
+
+ for ( ; ; )
+ {
+ if ( !softirq_pending(cpu) )
+ sched_guest_idle(pm_idle, cpu);
+ do_softirq();
+ }
+}
+
void startup_cpu_idle_loop(void)
{
struct vcpu *v = current;
@@ -172,6 +189,10 @@ void startup_cpu_idle_loop(void)
static void noreturn continue_idle_domain(struct vcpu *v)
{
+ /* Idle vcpus might be attached to non-idle units! */
+ if ( !is_idle_domain(v->sched_unit->domain) )
+ reset_stack_and_jump(guest_idle_loop);
+
reset_stack_and_jump(idle_loop);
}
@@ -82,7 +82,18 @@ static struct scheduler __read_mostly ops;
static inline struct vcpu *sched_unit2vcpu_cpu(struct sched_unit *unit,
unsigned int cpu)
{
- return unit->domain->vcpu[unit->unit_id + per_cpu(sched_res_idx, cpu)];
+ unsigned int idx = unit->unit_id + per_cpu(sched_res_idx, cpu);
+ const struct domain *d = unit->domain;
+ struct vcpu *v;
+
+ if ( idx < d->max_vcpus && d->vcpu[idx] )
+ {
+ v = d->vcpu[idx];
+ if ( v->new_state == RUNSTATE_running )
+ return v;
+ }
+
+ return idle_vcpu[cpu];
}
static inline struct scheduler *dom_scheduler(const struct domain *d)
@@ -196,8 +207,11 @@ static inline void vcpu_runstate_change(
trace_runstate_change(v, new_state);
- unit->runstate_cnt[v->runstate.state]--;
- unit->runstate_cnt[new_state]++;
+ if ( !is_idle_vcpu(v) )
+ {
+ unit->runstate_cnt[v->runstate.state]--;
+ unit->runstate_cnt[new_state]++;
+ }
delta = new_entry_time - v->runstate.state_entry_time;
if ( delta > 0 )
@@ -209,19 +223,11 @@ static inline void vcpu_runstate_change(
v->runstate.state = new_state;
}
-static inline void sched_unit_runstate_change(struct sched_unit *unit,
- bool running, s_time_t new_entry_time)
+void sched_guest_idle(void (*idle) (void), unsigned int cpu)
{
- struct vcpu *v;
-
- for_each_sched_unit_vcpu ( unit, v )
- if ( running )
- vcpu_runstate_change(v, v->new_state, new_entry_time);
- else
- vcpu_runstate_change(v,
- ((v->pause_flags & VPF_blocked) ? RUNSTATE_blocked :
- (vcpu_runnable(v) ? RUNSTATE_runnable : RUNSTATE_offline)),
- new_entry_time);
+ atomic_inc(&get_sched_res(cpu)->urgent_count);
+ idle();
+ atomic_dec(&get_sched_res(cpu)->urgent_count);
}
void vcpu_runstate_get(struct vcpu *v, struct vcpu_runstate_info *runstate)
@@ -461,6 +467,7 @@ int sched_init_vcpu(struct vcpu *v)
if ( is_idle_domain(d) )
{
get_sched_res(v->processor)->curr = unit;
+ get_sched_res(v->processor)->sched_unit_idle = unit;
v->is_running = 1;
unit->is_running = 1;
unit->state_entry_time = NOW();
@@ -1637,33 +1644,67 @@ static void sched_switch_units(struct sched_resource *sd,
struct sched_unit *next, struct sched_unit *prev,
s_time_t now)
{
- sd->curr = next;
-
- TRACE_3D(TRC_SCHED_SWITCH_INFPREV, prev->domain->domain_id, prev->unit_id,
- now - prev->state_entry_time);
- TRACE_4D(TRC_SCHED_SWITCH_INFNEXT, next->domain->domain_id, next->unit_id,
- (next->vcpu->runstate.state == RUNSTATE_runnable) ?
- (now - next->state_entry_time) : 0, prev->next_time);
+ int cpu;
ASSERT(unit_running(prev));
- TRACE_4D(TRC_SCHED_SWITCH, prev->domain->domain_id, prev->unit_id,
- next->domain->domain_id, next->unit_id);
+ if ( prev != next )
+ {
+ sd->curr = next;
+ sd->prev = prev;
- sched_unit_runstate_change(prev, false, now);
- prev->last_run_time = now;
+ TRACE_3D(TRC_SCHED_SWITCH_INFPREV, prev->domain->domain_id,
+ prev->unit_id, now - prev->state_entry_time);
+ TRACE_4D(TRC_SCHED_SWITCH_INFNEXT, next->domain->domain_id,
+ next->unit_id,
+ (next->vcpu->runstate.state == RUNSTATE_runnable) ?
+ (now - next->state_entry_time) : 0, prev->next_time);
+ TRACE_4D(TRC_SCHED_SWITCH, prev->domain->domain_id, prev->unit_id,
+ next->domain->domain_id, next->unit_id);
- ASSERT(!unit_running(next));
- sched_unit_runstate_change(next, true, now);
+ prev->last_run_time = now;
- /*
- * NB. Don't add any trace records from here until the actual context
- * switch, else lost_records resume will not work properly.
- */
+ ASSERT(!unit_running(next));
+
+ /*
+ * NB. Don't add any trace records from here until the actual context
+ * switch, else lost_records resume will not work properly.
+ */
- ASSERT(!next->is_running);
- next->vcpu->is_running = 1;
- next->is_running = 1;
+ ASSERT(!next->is_running);
+ next->is_running = 1;
+
+ if ( is_idle_unit(prev) )
+ {
+ prev->runstate_cnt[RUNSTATE_running] = 0;
+ prev->runstate_cnt[RUNSTATE_runnable] = sched_granularity;
+ }
+ if ( is_idle_unit(next) )
+ {
+ next->runstate_cnt[RUNSTATE_running] = sched_granularity;
+ next->runstate_cnt[RUNSTATE_runnable] = 0;
+ }
+ }
+
+ for_each_cpu ( cpu, sd->cpus )
+ {
+ struct vcpu *vprev = get_cpu_current(cpu);
+ struct vcpu *vnext = sched_unit2vcpu_cpu(next, cpu);
+
+ if ( vprev != vnext || vprev->runstate.state != vnext->new_state )
+ {
+ vcpu_runstate_change(vprev,
+ ((vprev->pause_flags & VPF_blocked) ? RUNSTATE_blocked :
+ (vcpu_runnable(vprev) ? RUNSTATE_runnable : RUNSTATE_offline)),
+ now);
+ vcpu_runstate_change(vnext, vnext->new_state, now);
+ }
+
+ vnext->is_running = 1;
+
+ if ( is_idle_vcpu(vnext) )
+ vnext->sched_unit = next;
+ }
}
static bool sched_tasklet_check_cpu(unsigned int cpu)
@@ -1719,25 +1760,25 @@ static struct sched_unit *do_schedule(struct sched_unit *prev, s_time_t now,
if ( prev->next_time >= 0 ) /* -ve means no limit */
set_timer(&sd->s_timer, now + prev->next_time);
- if ( likely(prev != next) )
- sched_switch_units(sd, next, prev, now);
+ sched_switch_units(sd, next, prev, now);
return next;
}
-static void context_saved(struct vcpu *prev)
+static void context_saved(struct sched_unit *unit)
{
- struct sched_unit *unit = prev->sched_unit;
-
unit->is_running = 0;
unit->state_entry_time = NOW();
+ get_sched_res(smp_processor_id())->prev = NULL;
/* Check for migration request /after/ clearing running flag. */
smp_mb();
- sched_context_saved(vcpu_scheduler(prev), unit);
+ sched_context_saved(vcpu_scheduler(unit->vcpu), unit);
- sched_unit_migrate_finish(unit);
+ /* Idle never migrates and idle vcpus might belong to other units. */
+ if ( !is_idle_unit(unit) )
+ sched_unit_migrate_finish(unit);
}
/*
@@ -1754,11 +1795,13 @@ static void context_saved(struct vcpu *prev)
void sched_context_switched(struct vcpu *vprev, struct vcpu *vnext)
{
struct sched_unit *next = vnext->sched_unit;
+ struct sched_resource *sd = get_sched_res(smp_processor_id());
/* Clear running flag /after/ writing context to memory. */
smp_wmb();
- vprev->is_running = 0;
+ if ( vprev != vnext )
+ vprev->is_running = 0;
if ( atomic_read(&next->rendezvous_out_cnt) )
{
@@ -1767,20 +1810,23 @@ void sched_context_switched(struct vcpu *vprev, struct vcpu *vnext)
/* Call context_saved() before releasing other waiters. */
if ( cnt == 1 )
{
- if ( vprev != vnext )
- context_saved(vprev);
+ if ( sd->prev )
+ context_saved(sd->prev);
atomic_set(&next->rendezvous_out_cnt, 0);
}
else
while ( atomic_read(&next->rendezvous_out_cnt) )
cpu_relax();
}
- else if ( vprev != vnext && sched_granularity == 1 )
- context_saved(vprev);
+ else if ( sd->prev )
+ context_saved(sd->prev);
+
+ if ( is_idle_vcpu(vprev) && vprev != vnext )
+ vprev->sched_unit = sd->sched_unit_idle;
}
static void sched_context_switch(struct vcpu *vprev, struct vcpu *vnext,
- s_time_t now)
+ bool reset_idle_unit, s_time_t now)
{
if ( unlikely(vprev == vnext) )
{
@@ -1789,6 +1835,11 @@ static void sched_context_switch(struct vcpu *vprev, struct vcpu *vnext,
now - vprev->runstate.state_entry_time,
vprev->sched_unit->next_time);
sched_context_switched(vprev, vnext);
+
+ if ( reset_idle_unit )
+ vnext->sched_unit =
+ get_sched_res(smp_processor_id())->sched_unit_idle;
+
trace_continue_running(vnext);
return continue_running(vprev);
}
@@ -1870,7 +1921,8 @@ static void sched_slave(void)
pcpu_schedule_unlock_irq(lock, cpu);
- sched_context_switch(vprev, sched_unit2vcpu_cpu(next, cpu), now);
+ sched_context_switch(vprev, sched_unit2vcpu_cpu(next, cpu),
+ is_idle_unit(next) && !is_idle_unit(prev), now);
}
/*
@@ -1930,7 +1982,8 @@ static void schedule(void)
pcpu_schedule_unlock_irq(lock, cpu);
vnext = sched_unit2vcpu_cpu(next, cpu);
- sched_context_switch(vprev, vnext, now);
+ sched_context_switch(vprev, vnext,
+ !is_idle_unit(prev) && is_idle_unit(next), now);
}
/* The scheduler timer: force a run through the scheduler */
@@ -2015,6 +2068,7 @@ static int cpu_schedule_up(unsigned int cpu)
return -ENOMEM;
sd->curr = idle_vcpu[cpu]->sched_unit;
+ sd->sched_unit_idle = idle_vcpu[cpu]->sched_unit;
/*
* We don't want to risk calling xfree() on an sd->sched_priv
@@ -2216,6 +2270,7 @@ void __init scheduler_init(void)
if ( vcpu_create(idle_domain, 0) == NULL )
BUG();
get_sched_res(0)->curr = idle_vcpu[0]->sched_unit;
+ get_sched_res(0)->sched_unit_idle = idle_vcpu[0]->sched_unit;
get_sched_res(0)->sched_priv = sched_alloc_pdata(&ops, 0);
BUG_ON(IS_ERR(get_sched_res(0)->sched_priv));
scheduler_percpu_init(0);
@@ -18,6 +18,7 @@ DECLARE_PER_CPU(struct vcpu *, curr_vcpu);
#define current (this_cpu(curr_vcpu))
#define set_current(vcpu) do { current = (vcpu); } while (0)
+#define get_cpu_current(cpu) (per_cpu(curr_vcpu, cpu))
/* Per-VCPU state that lives at the top of the stack */
struct cpu_info {
@@ -77,6 +77,11 @@ struct cpu_info {
/* get_stack_bottom() must be 16-byte aligned */
};
+static inline struct cpu_info *get_cpu_info_from_stack(unsigned long sp)
+{
+ return (struct cpu_info *)((sp | (STACK_SIZE - 1)) + 1) - 1;
+}
+
static inline struct cpu_info *get_cpu_info(void)
{
#ifdef __clang__
@@ -87,7 +92,7 @@ static inline struct cpu_info *get_cpu_info(void)
register unsigned long sp asm("rsp");
#endif
- return (struct cpu_info *)((sp | (STACK_SIZE - 1)) + 1) - 1;
+ return get_cpu_info_from_stack(sp);
}
#define get_current() (get_cpu_info()->current_vcpu)
@@ -76,6 +76,9 @@ void set_nr_sockets(void);
/* Representing HT and core siblings in each socket. */
extern cpumask_t **socket_cpumask;
+#define get_cpu_current(cpu) \
+ (get_cpu_info_from_stack((unsigned long)stack_base[cpu])->current_vcpu)
+
#endif /* !__ASSEMBLY__ */
#endif
@@ -39,6 +39,8 @@ struct sched_resource {
spinlock_t *schedule_lock,
_lock;
struct sched_unit *curr; /* current task */
+ struct sched_unit *sched_unit_idle;
+ struct sched_unit *prev; /* previous task */
void *sched_priv;
struct timer s_timer; /* scheduling timer */
atomic_t urgent_count; /* how many urgent vcpus */
@@ -168,7 +170,7 @@ static inline void sched_clear_pause_flags_atomic(struct sched_unit *unit,
static inline struct sched_unit *sched_idle_unit(unsigned int cpu)
{
- return idle_vcpu[cpu]->sched_unit;
+ return get_sched_res(cpu)->sched_unit_idle;
}
static inline unsigned int sched_get_resource_cpu(unsigned int cpu)
@@ -921,6 +921,7 @@ int vcpu_pin_override(struct vcpu *v, int cpu);
void vcpu_runstate_get(struct vcpu *v, struct vcpu_runstate_info *runstate);
uint64_t get_cpu_idle_time(unsigned int cpu);
int sched_has_urgent_vcpu(void);
+void sched_guest_idle(void (*idle) (void), unsigned int cpu);
/*
* Used by idle loop to decide whether there is work to do:
When scheduling an unit with multiple vcpus there is no guarantee all vcpus are available (e.g. above maxvcpus or vcpu offline). Fall back to idle vcpu of the current cpu in that case. This requires to store the correct schedule_unit pointer in the idle vcpu as long as it used as fallback vcpu. In order to modify the runstates of the correct vcpus when switching schedule units merge sched_unit_runstate_change() into sched_switch_units() and loop over the affected physical cpus instead of the unit's vcpus. This in turn requires an access function to the current variable of other cpus. Today context_saved() is called in case previous and next vcpus differ when doing a context switch. With an idle vcpu being capable to be a substitute for an offline vcpu this is problematic when switching to an idle scheduling unit. An idle previous vcpu leaves us in doubt which schedule unit was active previously, so save the previous unit pointer in the per-schedule resource area and use its value being non-NULL as a hint whether context_saved() should be called. When running an idle vcpu in a non-idle scheduling unit use a specific guest idle loop not performing any tasklets, memory scrubbing and livepatching in order to avoid populating the cpu caches with memory used by other domains (as far as possible). Softirqs are considered to be save (timers might want to be excluded, but this can be fine-tuned later). Signed-off-by: Juergen Gross <jgross@suse.com> --- RFC V2: new patch (Andrew Cooper) V1: use urgent_count to select correct idle routine (Jan Beulich) --- xen/arch/x86/domain.c | 21 ++++++ xen/common/schedule.c | 155 ++++++++++++++++++++++++++++-------------- xen/include/asm-arm/current.h | 1 + xen/include/asm-x86/current.h | 7 +- xen/include/asm-x86/smp.h | 3 + xen/include/xen/sched-if.h | 4 +- xen/include/xen/sched.h | 1 + 7 files changed, 140 insertions(+), 52 deletions(-)