[PATCH RT 3/5] KVM: use simple waitqueue for vcpu->wq

From: Steven Rostedt
Date: Thu May 14 2015 - 10:05:04 EST


3.12.40-rt56-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Marcelo Tosatti <mtosatti@xxxxxxxxxx>

The problem:

On -RT, an emulated LAPIC timer instances has the following path:

1) hard interrupt
2) ksoftirqd is scheduled
3) ksoftirqd wakes up vcpu thread
4) vcpu thread is scheduled

This extra context switch introduces unnecessary latency in the
LAPIC path for a KVM guest.

The solution:

Allow waking up vcpu thread from hardirq context,
thus avoiding the need for ksoftirqd to be scheduled.

Normal waitqueues make use of spinlocks, which on -RT
are sleepable locks. Therefore, waking up a waitqueue
waiter involves locking a sleeping lock, which
is not allowed from hard interrupt context.

cyclictest command line:

This patch reduces the average latency in my tests from 14us to 11us.

Cc: stable-rt@xxxxxxxxxxxxxxx
Signed-off-by: Marcelo Tosatti <mtosatti@xxxxxxxxxx>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
Signed-off-by: Steven Rostedt <rostedt@xxxxxxxxxxx>
---
arch/arm/kvm/arm.c | 4 ++--
arch/arm/kvm/psci.c | 4 ++--
arch/powerpc/include/asm/kvm_host.h | 4 ++--
arch/powerpc/kvm/book3s_hv.c | 20 ++++++++++----------
arch/s390/include/asm/kvm_host.h | 2 +-
arch/x86/kvm/lapic.c | 6 +++---
include/linux/kvm_host.h | 4 ++--
virt/kvm/async_pf.c | 4 ++--
virt/kvm/kvm_main.c | 16 ++++++++--------
9 files changed, 32 insertions(+), 32 deletions(-)

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 9c697db2787e..5409d4d7c208 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -491,9 +491,9 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)

static void vcpu_pause(struct kvm_vcpu *vcpu)
{
- wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
+ struct swait_head *wq = kvm_arch_vcpu_wq(vcpu);

- wait_event_interruptible(*wq, !vcpu->arch.pause);
+ swait_event_interruptible(*wq, !vcpu->arch.pause);
}

static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 86a693a02ba3..49aed024ad78 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -35,7 +35,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
{
struct kvm *kvm = source_vcpu->kvm;
struct kvm_vcpu *vcpu;
- wait_queue_head_t *wq;
+ struct swait_head *wq;
unsigned long cpu_id;
phys_addr_t target_pc;

@@ -66,7 +66,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
vcpu->arch.pause = false;
smp_mb(); /* Make sure the above is visible */

- wake_up_interruptible(wq);
+ swait_wake_interruptible(wq);

return KVM_PSCI_RET_SUCCESS;
}
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 33283532e9d8..5fa50fc31ab3 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -290,7 +290,7 @@ struct kvmppc_vcore {
u8 in_guest;
struct list_head runnable_threads;
spinlock_t lock;
- wait_queue_head_t wq;
+ struct swait_head wq;
u64 stolen_tb;
u64 preempt_tb;
struct kvm_vcpu *runner;
@@ -562,7 +562,7 @@ struct kvm_vcpu_arch {
u8 prodded;
u32 last_inst;

- wait_queue_head_t *wqp;
+ struct swait_head *wqp;
struct kvmppc_vcore *vcore;
int ret;
int trap;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 211974a386d6..a4e71ea12cf7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -70,11 +70,11 @@ void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu)
{
int me;
int cpu = vcpu->cpu;
- wait_queue_head_t *wqp;
+ struct swait_head *wqp;

wqp = kvm_arch_vcpu_wq(vcpu);
- if (waitqueue_active(wqp)) {
- wake_up_interruptible(wqp);
+ if (swaitqueue_active(wqp)) {
+ swait_wake_interruptible(wqp);
++vcpu->stat.halt_wakeup;
}

@@ -534,8 +534,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
tvcpu->arch.prodded = 1;
smp_mb();
if (vcpu->arch.ceded) {
- if (waitqueue_active(&vcpu->wq)) {
- wake_up_interruptible(&vcpu->wq);
+ if (swaitqueue_active(&vcpu->wq)) {
+ swait_wake_interruptible(&vcpu->wq);
vcpu->stat.halt_wakeup++;
}
}
@@ -941,7 +941,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
if (vcore) {
INIT_LIST_HEAD(&vcore->runnable_threads);
spin_lock_init(&vcore->lock);
- init_waitqueue_head(&vcore->wq);
+ init_swait_head(&vcore->wq);
vcore->preempt_tb = TB_NIL;
}
kvm->arch.vcores[core] = vcore;
@@ -1312,13 +1312,13 @@ static void kvmppc_wait_for_exec(struct kvm_vcpu *vcpu, int wait_state)
*/
static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
{
- DEFINE_WAIT(wait);
+ DEFINE_SWAITER(wait);

- prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+ swait_prepare(&vc->wq, &wait, TASK_INTERRUPTIBLE);
vc->vcore_state = VCORE_SLEEPING;
spin_unlock(&vc->lock);
schedule();
- finish_wait(&vc->wq, &wait);
+ swait_finish(&vc->wq, &wait);
spin_lock(&vc->lock);
vc->vcore_state = VCORE_INACTIVE;
}
@@ -1360,7 +1360,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
kvmppc_create_dtl_entry(vcpu, vc);
kvmppc_start_thread(vcpu);
} else if (vc->vcore_state == VCORE_SLEEPING) {
- wake_up(&vc->wq);
+ swait_wake(&vc->wq);
}

}
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index e87ecaa2c569..295aab26f605 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -228,7 +228,7 @@ struct kvm_s390_local_interrupt {
atomic_t active;
struct kvm_s390_float_interrupt *float_int;
int timer_due; /* event indicator for waitqueue below */
- wait_queue_head_t *wq;
+ struct swait_head *wq;
atomic_t *cpuflags;
unsigned int action_bits;
};
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 0c4ebde0452f..9644aac4334e 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1546,7 +1546,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic, lapic_timer);
struct kvm_vcpu *vcpu = apic->vcpu;
- wait_queue_head_t *q = &vcpu->wq;
+ struct swait_head *q = &vcpu->wq;

/*
* There is a race window between reading and incrementing, but we do
@@ -1560,8 +1560,8 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
}

- if (waitqueue_active(q))
- wake_up_interruptible(q);
+ if (swaitqueue_active(q))
+ swait_wake_interruptible(q);

if (lapic_is_periodic(apic)) {
hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index e47c7e2f4d04..7bb6c5ac2ad7 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -234,7 +234,7 @@ struct kvm_vcpu {

int fpu_active;
int guest_fpu_loaded, guest_xcr0_loaded;
- wait_queue_head_t wq;
+ struct swait_head wq;
struct pid *pid;
int sigset_active;
sigset_t sigset;
@@ -669,7 +669,7 @@ static inline void kvm_arch_free_vm(struct kvm *kvm)
}
#endif

-static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
+static inline struct swait_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
{
#ifdef __KVM_HAVE_ARCH_WQP
return vcpu->arch.wqp;
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 8a39dda7a325..c8b49a1f9278 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -85,8 +85,8 @@ static void async_pf_execute(struct work_struct *work)

trace_kvm_async_pf_completed(addr, page, gva);

- if (waitqueue_active(&vcpu->wq))
- wake_up_interruptible(&vcpu->wq);
+ if (swaitqueue_active(&vcpu->wq))
+ swait_wake_interruptible(&vcpu->wq);

mmdrop(mm);
kvm_put_kvm(vcpu->kvm);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index b9bf29490b12..efcd02d2a5c6 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -213,7 +213,7 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
vcpu->kvm = kvm;
vcpu->vcpu_id = id;
vcpu->pid = NULL;
- init_waitqueue_head(&vcpu->wq);
+ init_swait_head(&vcpu->wq);
kvm_async_pf_vcpu_init(vcpu);

page = alloc_page(GFP_KERNEL | __GFP_ZERO);
@@ -1672,10 +1672,10 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
*/
void kvm_vcpu_block(struct kvm_vcpu *vcpu)
{
- DEFINE_WAIT(wait);
+ DEFINE_SWAITER(wait);

for (;;) {
- prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+ swait_prepare(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);

if (kvm_arch_vcpu_runnable(vcpu)) {
kvm_make_request(KVM_REQ_UNHALT, vcpu);
@@ -1689,7 +1689,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
schedule();
}

- finish_wait(&vcpu->wq, &wait);
+ swait_finish(&vcpu->wq, &wait);
}

#ifndef CONFIG_S390
@@ -1700,11 +1700,11 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
{
int me;
int cpu = vcpu->cpu;
- wait_queue_head_t *wqp;
+ struct swait_head *wqp;

wqp = kvm_arch_vcpu_wq(vcpu);
- if (waitqueue_active(wqp)) {
- wake_up_interruptible(wqp);
+ if (swaitqueue_active(wqp)) {
+ swait_wake_interruptible(wqp);
++vcpu->stat.halt_wakeup;
}

@@ -1816,7 +1816,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
continue;
if (vcpu == me)
continue;
- if (waitqueue_active(&vcpu->wq))
+ if (swaitqueue_active(&vcpu->wq))
continue;
if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
continue;
--
2.1.4


--
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/