[RFC PATCH 3/3] kvm: use yield_to instead of sleep inkvm_vcpu_on_spin

[Rik van Riel]

Instead of sleeping in kvm_vcpu_on_spin, which can cause gigantic
slowdowns of certain workloads, we instead use yield_to to hand
the rest of our timeslice to another vcpu in the same KVM guest.

Signed-off-by: Rik van Riel <riel@xxxxxxxxxx>
Signed-off-by: Marcelo Tosatti <mtosatti@xxxxxxxxxx>

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c011ba3..7637dd3 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -90,6 +90,7 @@ struct kvm_vcpu {
 	int fpu_active;
 	int guest_fpu_loaded;
 	wait_queue_head_t wq;
+	int spinning;
 	int sigset_active;
 	sigset_t sigset;
 	struct kvm_vcpu_stat stat;
@@ -185,6 +186,7 @@ struct kvm {
 #endif
 	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
 	atomic_t online_vcpus;
+	int last_boosted_vcpu;
 	struct list_head vm_list;
 	struct mutex lock;
 	struct kvm_io_bus *buses[KVM_NR_BUSES];
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 80f17db..a6eeafc 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1880,18 +1880,53 @@ void kvm_resched(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_resched);
 
-void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu)
+void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 {
-	ktime_t expires;
-	DEFINE_WAIT(wait);
+	struct kvm *kvm = me->kvm;
+	struct kvm_vcpu *vcpu;
+	int last_boosted_vcpu = me->kvm->last_boosted_vcpu;
+	int first_round = 1;
+	int i;
 
-	prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+	me->spinning = 1;
+
+	/*
+	 * We boost the priority of a VCPU that is runnable but not
+	 * currently running, because it got preempted by something
+	 * else and called schedule in __vcpu_run.  Hopefully that
+	 * VCPU is holding the lock that we need and will release it.
+	 * We approximate round-robin by starting at the last boosted VCPU.
+	 */
+ again:
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		struct task_struct *task = vcpu->task;
+		if (first_round && i < last_boosted_vcpu) {
+			i = last_boosted_vcpu;
+			continue;
+		} else if (!first_round && i > last_boosted_vcpu)
+			break;
+		if (vcpu == me)
+			continue;
+		if (vcpu->spinning)
+			continue;
+		if (!task)
+			continue;
+		if (waitqueue_active(&vcpu->wq))
+			continue;
+		if (task->flags & PF_VCPU)
+			continue;
+		kvm->last_boosted_vcpu = i;
+		yield_to(task);
+		break;
+	}
 
-	/* Sleep for 100 us, and hope lock-holder got scheduled */
-	expires = ktime_add_ns(ktime_get(), 100000UL);
-	schedule_hrtimeout(&expires, HRTIMER_MODE_ABS);
+	if (first_round && last_boosted_vcpu == kvm->last_boosted_vcpu) {
+		/* We have not found anyone yet. */
+		first_round = 0;
+		goto again;
+	}
 
-	finish_wait(&vcpu->wq, &wait);
+	me->spinning = 0;
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin);
 


-- 
All rights reversed.
--
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/