kvm: Replace vcpu->swait with rcuwait

The use of any sort of waitqueue (simple or regular) for
wait/waking vcpus has always been an overkill and semantically
wrong. Because this is per-vcpu (which is blocked) there is
only ever a single waiting vcpu, thus no need for any sort of
queue.

As such, make use of the rcuwait primitive, with the following
considerations:

  - rcuwait already provides the proper barriers that serialize
  concurrent waiter and waker.

  - Task wakeup is done in rcu read critical region, with a
  stable task pointer.

  - Because there is no concurrency among waiters, we need
  not worry about rcuwait_wait_event() calls corrupting
  the wait->task. As a consequence, this saves the locking
  done in swait when modifying the queue. This also applies
  to per-vcore wait for powerpc kvm-hv.

The x86 tscdeadline_latency test mentioned in 8577370f
("KVM: Use simple waitqueue for vcpu->wq") shows that, on avg,
latency is reduced by around 15-20% with this change.

Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: kvmarm@lists.cs.columbia.edu
Cc: linux-mips@vger.kernel.org
Reviewed-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Message-Id: <20200424054837.5138-6-dave@stgolabs.net>
[Avoid extra logic changes. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/mips/kvm/mips.c

@@ -283,8 +283,7 @@ static enum hrtimer_restart kvm_mips_comparecount_wakeup(struct hrtimer *timer)
 	kvm_mips_callbacks->queue_timer_int(vcpu);
 
 	vcpu->arch.wait = 0;
-	if (swq_has_sleeper(&vcpu->wq))
-		swake_up_one(&vcpu->wq);
+	rcuwait_wake_up(&vcpu->wait);
 
 	return kvm_mips_count_timeout(vcpu);
 }
@@ -511,8 +510,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 
 	dvcpu->arch.wait = 0;
 
-	if (swq_has_sleeper(&dvcpu->wq))
-		swake_up_one(&dvcpu->wq);
+	rcuwait_wake_up(&dvcpu->wait);
 
 	return 0;
 }

arch/powerpc/include/asm/kvm_book3s.h

@@ -78,7 +78,7 @@ struct kvmppc_vcore {
 	struct kvm_vcpu *runnable_threads[MAX_SMT_THREADS];
 	struct list_head preempt_list;
 	spinlock_t lock;
-	struct swait_queue_head wq;
+	struct rcuwait wait;
 	spinlock_t stoltb_lock;	/* protects stolen_tb and preempt_tb */
 	u64 stolen_tb;
 	u64 preempt_tb;

arch/powerpc/include/asm/kvm_host.h

@@ -751,7 +751,7 @@ struct kvm_vcpu_arch {
 	u8 irq_pending; /* Used by XIVE to signal pending guest irqs */
 	u32 last_inst;
 
-	struct swait_queue_head *wqp;
+	struct rcuwait *waitp;
 	struct kvmppc_vcore *vcore;
 	int ret;
 	int trap;

arch/powerpc/kvm/book3s_hv.c

@@ -230,13 +230,11 @@ static bool kvmppc_ipi_thread(int cpu)
 static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 {
 	int cpu;
-	struct swait_queue_head *wqp;
+	struct rcuwait *waitp;
 
-	wqp = kvm_arch_vcpu_wq(vcpu);
-	if (swq_has_sleeper(wqp)) {
-		swake_up_one(wqp);
+	waitp = kvm_arch_vcpu_get_wait(vcpu);
+	if (rcuwait_wake_up(waitp))
 		++vcpu->stat.halt_wakeup;
-	}
 
 	cpu = READ_ONCE(vcpu->arch.thread_cpu);
 	if (cpu >= 0 && kvmppc_ipi_thread(cpu))
@@ -2125,7 +2123,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int id)
 
 	spin_lock_init(&vcore->lock);
 	spin_lock_init(&vcore->stoltb_lock);
-	init_swait_queue_head(&vcore->wq);
+	rcuwait_init(&vcore->wait);
 	vcore->preempt_tb = TB_NIL;
 	vcore->lpcr = kvm->arch.lpcr;
 	vcore->first_vcpuid = id;
@@ -3784,7 +3782,6 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	ktime_t cur, start_poll, start_wait;
 	int do_sleep = 1;
 	u64 block_ns;
-	DECLARE_SWAITQUEUE(wait);
 
 	/* Poll for pending exceptions and ceded state */
 	cur = start_poll = ktime_get();
@@ -3812,10 +3809,10 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 		}
 	}
 
-	prepare_to_swait_exclusive(&vc->wq, &wait, TASK_INTERRUPTIBLE);
-
+	prepare_to_rcuwait(&vc->wait);
+	set_current_state(TASK_INTERRUPTIBLE);
 	if (kvmppc_vcore_check_block(vc)) {
-		finish_swait(&vc->wq, &wait);
+		finish_rcuwait(&vc->wait);
 		do_sleep = 0;
 		/* If we polled, count this as a successful poll */
 		if (vc->halt_poll_ns)
@@ -3829,7 +3826,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	trace_kvmppc_vcore_blocked(vc, 0);
 	spin_unlock(&vc->lock);
 	schedule();
-	finish_swait(&vc->wq, &wait);
+	finish_rcuwait(&vc->wait);
 	spin_lock(&vc->lock);
 	vc->vcore_state = VCORE_INACTIVE;
 	trace_kvmppc_vcore_blocked(vc, 1);
@@ -3940,7 +3937,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 			kvmppc_start_thread(vcpu, vc);
 			trace_kvm_guest_enter(vcpu);
 		} else if (vc->vcore_state == VCORE_SLEEPING) {
-			swake_up_one(&vc->wq);
+		        rcuwait_wake_up(&vc->wait);
 		}
 
 	}
@@ -4279,7 +4276,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	}
 	user_vrsave = mfspr(SPRN_VRSAVE);
 
-	vcpu->arch.wqp = &vcpu->arch.vcore->wq;
+	vcpu->arch.waitp = &vcpu->arch.vcore->wait;
 	vcpu->arch.pgdir = kvm->mm->pgd;
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
 

arch/powerpc/kvm/powerpc.c

@@ -752,7 +752,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	if (err)
 		goto out_vcpu_uninit;
 
-	vcpu->arch.wqp = &vcpu->wq;
+	vcpu->arch.waitp = &vcpu->wait;
 	kvmppc_create_vcpu_debugfs(vcpu, vcpu->vcpu_id);
 	return 0;
 

arch/x86/kvm/lapic.c

@@ -1861,7 +1861,7 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
 	/* If the preempt notifier has already run, it also called apic_timer_expired */
 	if (!apic->lapic_timer.hv_timer_in_use)
 		goto out;
-	WARN_ON(swait_active(&vcpu->wq));
+	WARN_ON(rcuwait_active(&vcpu->wait));
 	cancel_hv_timer(apic);
 	apic_timer_expired(apic);
 

include/linux/kvm_host.h

@@ -23,7 +23,7 @@
 #include <linux/irqflags.h>
 #include <linux/context_tracking.h>
 #include <linux/irqbypass.h>
-#include <linux/swait.h>
+#include <linux/rcuwait.h>
 #include <linux/refcount.h>
 #include <linux/nospec.h>
 #include <asm/signal.h>
@@ -277,7 +277,7 @@ struct kvm_vcpu {
 	struct mutex mutex;
 	struct kvm_run *run;
 
-	struct swait_queue_head wq;
+	struct rcuwait wait;
 	struct pid __rcu *pid;
 	int sigset_active;
 	sigset_t sigset;
@@ -960,12 +960,12 @@ static inline bool kvm_arch_has_assigned_device(struct kvm *kvm)
 }
 #endif
 
-static inline struct swait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
+static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu)
 {
 #ifdef __KVM_HAVE_ARCH_WQP
-	return vcpu->arch.wqp;
+	return vcpu->arch.waitp;
 #else
-	return &vcpu->wq;
+	return &vcpu->wait;
 #endif
 }
 

virt/kvm/arm/arch_timer.c

@@ -571,6 +571,7 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = vcpu_timer(vcpu);
 	struct timer_map map;
+	struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu);
 
 	if (unlikely(!timer->enabled))
 		return;
@@ -593,7 +594,7 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 	if (map.emul_ptimer)
 		soft_timer_cancel(&map.emul_ptimer->hrtimer);
 
-	if (swait_active(kvm_arch_vcpu_wq(vcpu)))
+	if (rcuwait_active(wait))
 		kvm_timer_blocking(vcpu);
 
 	/*

virt/kvm/arm/arm.c

@@ -579,16 +579,17 @@ void kvm_arm_resume_guest(struct kvm *kvm)
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		vcpu->arch.pause = false;
-		swake_up_one(kvm_arch_vcpu_wq(vcpu));
+		rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu));
 	}
 }
 
 static void vcpu_req_sleep(struct kvm_vcpu *vcpu)
 {
-	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
+	struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu);
 
-	swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) &&
-				       (!vcpu->arch.pause)));
+	rcuwait_wait_event(wait,
+			   (!vcpu->arch.power_off) &&(!vcpu->arch.pause),
+			   TASK_INTERRUPTIBLE);
 
 	if (vcpu->arch.power_off || vcpu->arch.pause) {
 		/* Awaken to handle a signal, request we sleep again later. */

virt/kvm/async_pf.c

@@ -80,8 +80,7 @@ static void async_pf_execute(struct work_struct *work)
 
 	trace_kvm_async_pf_completed(addr, cr2_or_gpa);
 
-	if (swq_has_sleeper(&vcpu->wq))
-		swake_up_one(&vcpu->wq);
+	rcuwait_wake_up(&vcpu->wait);
 
 	mmput(mm);
 	kvm_put_kvm(vcpu->kvm);

virt/kvm/kvm_main.c

@@ -349,7 +349,7 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 	vcpu->kvm = kvm;
 	vcpu->vcpu_id = id;
 	vcpu->pid = NULL;
-	init_swait_queue_head(&vcpu->wq);
+	rcuwait_init(&vcpu->wait);
 	kvm_async_pf_vcpu_init(vcpu);
 
 	vcpu->pre_pcpu = -1;
@@ -2678,7 +2678,6 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu)
 void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 {
 	ktime_t start, cur;
-	DECLARE_SWAITQUEUE(wait);
 	bool waited = false;
 	u64 block_ns;
 
@@ -2704,8 +2703,9 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 		} while (single_task_running() && ktime_before(cur, stop));
 	}
 
+	prepare_to_rcuwait(&vcpu->wait);
 	for (;;) {
-		prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+		set_current_state(TASK_INTERRUPTIBLE);
 
 		if (kvm_vcpu_check_block(vcpu) < 0)
 			break;
@@ -2713,8 +2713,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 		waited = true;
 		schedule();
 	}
-
-	finish_swait(&vcpu->wq, &wait);
+	finish_rcuwait(&vcpu->wait);
 	cur = ktime_get();
 out:
 	kvm_arch_vcpu_unblocking(vcpu);
@@ -2746,11 +2745,10 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_block);
 
 bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
 {
-	struct swait_queue_head *wqp;
+	struct rcuwait *waitp;
 
-	wqp = kvm_arch_vcpu_wq(vcpu);
-	if (swq_has_sleeper(wqp)) {
-		swake_up_one(wqp);
+	waitp = kvm_arch_vcpu_get_wait(vcpu);
+	if (rcuwait_wake_up(waitp)) {
 		WRITE_ONCE(vcpu->ready, true);
 		++vcpu->stat.halt_wakeup;
 		return true;
@@ -2892,7 +2890,8 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 				continue;
 			if (vcpu == me)
 				continue;
-			if (swait_active(&vcpu->wq) && !vcpu_dy_runnable(vcpu))
+			if (rcuwait_active(&vcpu->wait) &&
+			    !vcpu_dy_runnable(vcpu))
 				continue;
 			if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode &&
 				!kvm_arch_vcpu_in_kernel(vcpu))