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:

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

Daniel writes:
Paolo asked for numbers from kvm-unit-tests/tscdeadline_latency
benchmark on mainline. The test was run 1000 times on
tip/sched/core 4.4.0-rc8-01134-g0905f04:

  ./x86-run x86/tscdeadline_latency.flat -cpu host

with idle=poll.

The test seems not to deliver really stable numbers though most of
them are smaller. Paolo write:

"Anything above ~10000 cycles means that the host went to C1 or
lower---the number means more or less nothing in that case.

The mean shows an improvement indeed."

Before:

               min             max         mean           std
count  1000.000000     1000.000000  1000.000000   1000.000000
mean   5162.596000  2019270.084000  5824.491541  20681.645558
std      75.431231   622607.723969    89.575700   6492.272062
min    4466.000000    23928.000000  5537.926500    585.864966
25%    5163.000000  1613252.750000  5790.132275  16683.745433
50%    5175.000000  2281919.000000  5834.654000  23151.990026
75%    5190.000000  2382865.750000  5861.412950  24148.206168
max    5228.000000  4175158.000000  6254.827300  46481.048691

After
               min            max         mean           std
count  1000.000000     1000.00000  1000.000000   1000.000000
mean   5143.511000  2076886.10300  5813.312474  21207.357565
std      77.668322   610413.09583    86.541500   6331.915127
min    4427.000000    25103.00000  5529.756600    559.187707
25%    5148.000000  1691272.75000  5784.889825  17473.518244
50%    5160.000000  2308328.50000  5832.025000  23464.837068
75%    5172.000000  2393037.75000  5853.177675  24223.969976
max    5222.000000  3922458.00000  6186.720500  42520.379830

[Patch was originaly based on the swait implementation found in the -rt
 tree. Daniel ported it to mainline's version and gathered the
 benchmark numbers for tscdeadline_latency test.]

Signed-off-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: linux-rt-users@vger.kernel.org
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1455871601-27484-4-git-send-email-wagi@monom.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

2 files changed, 13 insertions, 14 deletions

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 9d08d8cbed1a..c98afa538b3a 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -289,7 +289,7 @@ struct kvmppc_vcore {
 	struct list_head runnable_threads;
 	struct list_head preempt_list;
 	spinlock_t lock;
-	wait_queue_head_t wq;
+	struct swait_queue_head wq;
 	spinlock_t stoltb_lock;	/* protects stolen_tb and preempt_tb */
 	u64 stolen_tb;
 	u64 preempt_tb;
@@ -629,7 +629,7 @@ struct kvm_vcpu_arch {
 	u8 prodded;
 	u32 last_inst;
 
-	wait_queue_head_t *wqp;
+	struct swait_queue_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 baeddb06811d..f1187bb6dd4d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -114,11 +114,11 @@ static bool kvmppc_ipi_thread(int cpu)
 static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 {
 	int cpu;
-	wait_queue_head_t *wqp;
+	struct swait_queue_head *wqp;
 
 	wqp = kvm_arch_vcpu_wq(vcpu);
-	if (waitqueue_active(wqp)) {
-		wake_up_interruptible(wqp);
+	if (swait_active(wqp)) {
+		swake_up(wqp);
 		++vcpu->stat.halt_wakeup;
 	}
 
@@ -701,8 +701,8 @@ 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 (swait_active(&vcpu->wq)) {
+				swake_up(&vcpu->wq);
 				vcpu->stat.halt_wakeup++;
 			}
 		}
@@ -1459,7 +1459,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
 	INIT_LIST_HEAD(&vcore->runnable_threads);
 	spin_lock_init(&vcore->lock);
 	spin_lock_init(&vcore->stoltb_lock);
-	init_waitqueue_head(&vcore->wq);
+	init_swait_queue_head(&vcore->wq);
 	vcore->preempt_tb = TB_NIL;
 	vcore->lpcr = kvm->arch.lpcr;
 	vcore->first_vcpuid = core * threads_per_subcore;
@@ -2531,10 +2531,9 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 {
 	struct kvm_vcpu *vcpu;
 	int do_sleep = 1;
+	DECLARE_SWAITQUEUE(wait);
 
-	DEFINE_WAIT(wait);
-
-	prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+	prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
 
 	/*
 	 * Check one last time for pending exceptions and ceded state after
@@ -2548,7 +2547,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	}
 
 	if (!do_sleep) {
-		finish_wait(&vc->wq, &wait);
+		finish_swait(&vc->wq, &wait);
 		return;
 	}
 
@@ -2556,7 +2555,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	trace_kvmppc_vcore_blocked(vc, 0);
 	spin_unlock(&vc->lock);
 	schedule();
-	finish_wait(&vc->wq, &wait);
+	finish_swait(&vc->wq, &wait);
 	spin_lock(&vc->lock);
 	vc->vcore_state = VCORE_INACTIVE;
 	trace_kvmppc_vcore_blocked(vc, 1);
@@ -2612,7 +2611,7 @@ 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) {
-			wake_up(&vc->wq);
+			swake_up(&vc->wq);
 		}
 
 	}