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 8577370fb0cb
("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>
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 93493f0..7f59c47 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/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;