patches/KVM-use-simple-waitqueue-for-vcpu-wq.patch

From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Wed, 8 Apr 2015 20:33:24 -0300
Subject: KVM: use simple waitqueue for vcpu->wq

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:
# cyclictest -m -n -q -p99 -l 1000000 -h60  -D 1m

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

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 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        |   23 +++++++++++------------
 arch/s390/include/asm/kvm_host.h    |    2 +-
 arch/s390/kvm/interrupt.c           |    8 ++++----
 arch/x86/kvm/lapic.c                |    6 +++---
 include/linux/kvm_host.h            |    4 ++--
 virt/kvm/async_pf.c                 |    4 ++--
 virt/kvm/kvm_main.c                 |   16 ++++++++--------
 10 files changed, 37 insertions(+), 38 deletions(-)

--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -474,9 +474,9 @@ bool kvm_arch_intc_initialized(struct kv
 
 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)
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -68,7 +68,7 @@ static unsigned long kvm_psci_vcpu_on(st
 {
 	struct kvm *kvm = source_vcpu->kvm;
 	struct kvm_vcpu *vcpu = NULL;
-	wait_queue_head_t *wq;
+	struct swait_head *wq;
 	unsigned long cpu_id;
 	unsigned long context_id;
 	phys_addr_t target_pc;
@@ -117,7 +117,7 @@ static unsigned long kvm_psci_vcpu_on(st
 	smp_mb();		/* Make sure the above is visible */
 
 	wq = kvm_arch_vcpu_wq(vcpu);
-	wake_up_interruptible(wq);
+	swait_wake_interruptible(wq);
 
 	return PSCI_RET_SUCCESS;
 }
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -280,7 +280,7 @@ struct kvmppc_vcore {
 	u8 in_guest;
 	struct list_head runnable_threads;
 	spinlock_t lock;
-	wait_queue_head_t wq;
+	struct swait_head wq;
 	spinlock_t stoltb_lock;	/* protects stolen_tb and preempt_tb */
 	u64 stolen_tb;
 	u64 preempt_tb;
@@ -613,7 +613,7 @@ 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;
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -115,11 +115,11 @@ static bool kvmppc_ipi_thread(int cpu)
 static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 {
 	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;
 	}
 
@@ -686,8 +686,8 @@ int kvmppc_pseries_do_hcall(struct kvm_v
 		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++;
 			}
 		}
@@ -1426,7 +1426,7 @@ static struct kvmppc_vcore *kvmppc_vcore
 	INIT_LIST_HEAD(&vcore->runnable_threads);
 	spin_lock_init(&vcore->lock);
 	spin_lock_init(&vcore->stoltb_lock);
-	init_waitqueue_head(&vcore->wq);
+	init_swait_head(&vcore->wq);
 	vcore->preempt_tb = TB_NIL;
 	vcore->lpcr = kvm->arch.lpcr;
 	vcore->first_vcpuid = core * threads_per_subcore;
@@ -2073,10 +2073,9 @@ static void kvmppc_vcore_blocked(struct
 {
 	struct kvm_vcpu *vcpu;
 	int do_sleep = 1;
+	DEFINE_SWAITER(wait);
 
-	DEFINE_WAIT(wait);
-
-	prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+	swait_prepare(&vc->wq, &wait, TASK_INTERRUPTIBLE);
 
 	/*
 	 * Check one last time for pending exceptions and ceded state after
@@ -2090,7 +2089,7 @@ static void kvmppc_vcore_blocked(struct
 	}
 
 	if (!do_sleep) {
-		finish_wait(&vc->wq, &wait);
+		swait_finish(&vc->wq, &wait);
 		return;
 	}
 
@@ -2098,7 +2097,7 @@ static void kvmppc_vcore_blocked(struct
 	trace_kvmppc_vcore_blocked(vc, 0);
 	spin_unlock(&vc->lock);
 	schedule();
-	finish_wait(&vc->wq, &wait);
+	swait_finish(&vc->wq, &wait);
 	spin_lock(&vc->lock);
 	vc->vcore_state = VCORE_INACTIVE;
 	trace_kvmppc_vcore_blocked(vc, 1);
@@ -2142,7 +2141,7 @@ static int kvmppc_run_vcpu(struct kvm_ru
 			kvmppc_start_thread(vcpu);
 			trace_kvm_guest_enter(vcpu);
 		} else if (vc->vcore_state == VCORE_SLEEPING) {
-			wake_up(&vc->wq);
+			swait_wake(&vc->wq);
 		}
 
 	}
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -419,7 +419,7 @@ struct kvm_s390_irq_payload {
 struct kvm_s390_local_interrupt {
 	spinlock_t lock;
 	struct kvm_s390_float_interrupt *float_int;
-	wait_queue_head_t *wq;
+	struct swait_head *wq;
 	atomic_t *cpuflags;
 	DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS);
 	struct kvm_s390_irq_payload irq;
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -875,13 +875,13 @@ int kvm_s390_handle_wait(struct kvm_vcpu
 
 void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 {
-	if (waitqueue_active(&vcpu->wq)) {
+	if (swaitqueue_active(&vcpu->wq)) {
 		/*
 		 * The vcpu gave up the cpu voluntarily, mark it as a good
 		 * yield-candidate.
 		 */
 		vcpu->preempted = true;
-		wake_up_interruptible(&vcpu->wq);
+		swait_wake_interruptible(&vcpu->wq);
 		vcpu->stat.halt_wakeup++;
 	}
 }
@@ -987,7 +987,7 @@ int kvm_s390_inject_program_int(struct k
 	spin_lock(&li->lock);
 	irq.u.pgm.code = code;
 	__inject_prog(vcpu, &irq);
-	BUG_ON(waitqueue_active(li->wq));
+	BUG_ON(swaitqueue_active(li->wq));
 	spin_unlock(&li->lock);
 	return 0;
 }
@@ -1006,7 +1006,7 @@ int kvm_s390_inject_prog_irq(struct kvm_
 	spin_lock(&li->lock);
 	irq.u.pgm = *pgm_info;
 	rc = __inject_prog(vcpu, &irq);
-	BUG_ON(waitqueue_active(li->wq));
+	BUG_ON(swaitqueue_active(li->wq));
 	spin_unlock(&li->lock);
 	return rc;
 }
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1104,7 +1104,7 @@ static void apic_update_lvtt(struct kvm_
 static void apic_timer_expired(struct kvm_lapic *apic)
 {
 	struct kvm_vcpu *vcpu = apic->vcpu;
-	wait_queue_head_t *q = &vcpu->wq;
+	struct swait_head *q = &vcpu->wq;
 	struct kvm_timer *ktimer = &apic->lapic_timer;
 
 	if (atomic_read(&apic->lapic_timer.pending))
@@ -1113,8 +1113,8 @@ static void apic_timer_expired(struct kv
 	atomic_inc(&apic->lapic_timer.pending);
 	kvm_set_pending_timer(vcpu);
 
-	if (waitqueue_active(q))
-		wake_up_interruptible(q);
+	if (swaitqueue_active(q))
+		swait_wake_interruptible(q);
 
 	if (apic_lvtt_tscdeadline(apic))
 		ktimer->expired_tscdeadline = ktimer->tscdeadline;
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -230,7 +230,7 @@ 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;
@@ -690,7 +690,7 @@ static inline bool kvm_arch_has_noncoher
 }
 #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;
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -94,8 +94,8 @@ static void async_pf_execute(struct work
 
 	trace_kvm_async_pf_completed(addr, gva);
 
-	if (waitqueue_active(&vcpu->wq))
-		wake_up_interruptible(&vcpu->wq);
+	if (swaitqueue_active(&vcpu->wq))
+		swait_wake_interruptible(&vcpu->wq);
 
 	mmput(mm);
 	kvm_put_kvm(vcpu->kvm);
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -218,7 +218,7 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu,
 	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);
@@ -1779,7 +1779,7 @@ static int kvm_vcpu_check_block(struct k
 void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 {
 	ktime_t start, cur;
-	DEFINE_WAIT(wait);
+	DEFINE_SWAITER(wait);
 	bool waited = false;
 
 	start = cur = ktime_get();
@@ -1800,7 +1800,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcp
 	}
 
 	for (;;) {
-		prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+		swait_prepare(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
 		if (kvm_vcpu_check_block(vcpu) < 0)
 			break;
@@ -1809,7 +1809,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcp
 		schedule();
 	}
 
-	finish_wait(&vcpu->wq, &wait);
+	swait_finish(&vcpu->wq, &wait);
 	cur = ktime_get();
 
 out:
@@ -1825,11 +1825,11 @@ 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;
 	}
 
@@ -1930,7 +1930,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *m
 				continue;
 			if (vcpu == me)
 				continue;
-			if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
+			if (swaitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
 				continue;
 			if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
 				continue;