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 8577370fb0
("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>
This commit is contained in:
Davidlohr Bueso 2020-04-23 22:48:37 -07:00 committed by Paolo Bonzini
parent 191a43be61
commit da4ad88cab
11 changed files with 38 additions and 43 deletions

View File

@ -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;
}

View File

@ -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;

View File

@ -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;

View File

@ -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;

View File

@ -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;

View File

@ -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);

View File

@ -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
}

View File

@ -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);
/*

View File

@ -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. */

View File

@ -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);

View File

@ -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 @@ out:
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))