Dedicated instances are currently disturbed by unnecessary jitter due
to the emulated lapic timers fire on the same pCPUs which vCPUs resident.
There is no hardware virtual timer on Intel for guest like ARM. Both
programming timer in guest and the emulated timer fires incur vmexits.
This patchset tries to avoid vmexit which is incurred by the emulated
timer fires in dedicated instance scenario.
When nohz_full is enabled in dedicated instances scenario, the unpinned
timer will be moved to the nearest busy housekeepers after commit 444969223c8
("sched/nohz: Fix affine unpinned timers mess"). However, KVM always makes
lapic timer pinned to the pCPU which vCPU residents, the reason is explained
by commit 61abdbe0 (kvm: x86: make lapic hrtimer pinned). Actually, these
emulated timers can be offload to the housekeeping cpus since APICv
is really common in recent years. The guest timer interrupt is injected by
posted-interrupt which is delivered by housekeeping cpu once the emulated
timer fires.
The host admin should fine tuned, e.g. dedicated instances scenario w/
nohz_full cover the pCPUs which vCPUs resident, several pCPUs surplus
for housekeeping, disable mwait/hlt/pause vmexits to occupy the pCPUs,
fortunately preemption timer is disabled after mwait is exposed to
guest which makes emulated timer offload can be possible.
3%~5% redis performance benefit can be observed on Skylake server.
v1 -> v2:
* check vcpu_halt_in_guest
* move module parameter from kvm-intel to kvm
* add housekeeping_enabled
* rename apic_timer_expired_pi to kvm_apic_inject_pending_timer_irqs
Wanpeng Li (3):
KVM: LAPIC: Make lapic timer unpinned when timer is injected by
posted-interrupt
KVM: LAPIC: lapic timer interrupt is injected by posted interrupt
KVM: LAPIC: Ignore timer migration when lapic timer is injected by
posted-interrupt
arch/x86/kvm/lapic.c | 55 ++++++++++++++++++++++++++++++++---------
arch/x86/kvm/x86.c | 5 ++++
arch/x86/kvm/x86.h | 7 ++++++
include/linux/sched/isolation.h | 2 ++
kernel/sched/isolation.c | 6 +++++
5 files changed, 63 insertions(+), 12 deletions(-)
--
2.7.4
From: Wanpeng Li <[email protected]>
Make lapic timer unpinned when timer is injected by posted-interrupt,
the emulated timer can be offload to the housekeeping cpus.
The host admin should fine tuned, e.g. dedicated instances scenario
w/ nohz_full cover the pCPUs which vCPUs resident, several pCPUs
surplus for housekeeping, disable mwait/hlt/pause vmexits to occupy
the pCPUs, fortunately preemption timer is disabled after mwait is
exposed to guest which makes emulated timer offload can be possible.
Cc: Paolo Bonzini <[email protected]>
Cc: Radim Krčmář <[email protected]>
Signed-off-by: Wanpeng Li <[email protected]>
---
arch/x86/kvm/lapic.c | 20 ++++++++++++++++----
arch/x86/kvm/x86.c | 5 +++++
arch/x86/kvm/x86.h | 2 ++
include/linux/sched/isolation.h | 2 ++
kernel/sched/isolation.c | 6 ++++++
5 files changed, 31 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index fcf42a3..09b7387 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -127,6 +127,12 @@ static inline u32 kvm_x2apic_id(struct kvm_lapic *apic)
return apic->vcpu->vcpu_id;
}
+static inline bool posted_interrupt_inject_timer_enabled(struct kvm_vcpu *vcpu)
+{
+ return pi_inject_timer && kvm_vcpu_apicv_active(vcpu) &&
+ kvm_mwait_in_guest(vcpu->kvm);
+}
+
static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
u32 dest_id, struct kvm_lapic ***cluster, u16 *mask) {
switch (map->mode) {
@@ -1581,7 +1587,9 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic)
likely(ns > apic->lapic_timer.timer_advance_ns)) {
expire = ktime_add_ns(now, ns);
expire = ktime_sub_ns(expire, ktimer->timer_advance_ns);
- hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_PINNED);
+ hrtimer_start(&ktimer->timer, expire,
+ posted_interrupt_inject_timer_enabled(vcpu) ?
+ HRTIMER_MODE_ABS : HRTIMER_MODE_ABS_PINNED);
} else
apic_timer_expired(apic);
@@ -1683,7 +1691,8 @@ static void start_sw_period(struct kvm_lapic *apic)
hrtimer_start(&apic->lapic_timer.timer,
apic->lapic_timer.target_expiration,
- HRTIMER_MODE_ABS_PINNED);
+ posted_interrupt_inject_timer_enabled(apic->vcpu) ?
+ HRTIMER_MODE_ABS : HRTIMER_MODE_ABS_PINNED);
}
bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu)
@@ -2320,7 +2329,8 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
apic->vcpu = vcpu;
hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
- HRTIMER_MODE_ABS_PINNED);
+ posted_interrupt_inject_timer_enabled(vcpu) ?
+ HRTIMER_MODE_ABS : HRTIMER_MODE_ABS_PINNED);
apic->lapic_timer.timer.function = apic_timer_fn;
if (timer_advance_ns == -1) {
apic->lapic_timer.timer_advance_ns = 1000;
@@ -2509,7 +2519,9 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
timer = &vcpu->arch.apic->lapic_timer.timer;
if (hrtimer_cancel(timer))
- hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
+ hrtimer_start_expires(timer,
+ posted_interrupt_inject_timer_enabled(vcpu) ?
+ HRTIMER_MODE_ABS : HRTIMER_MODE_ABS_PINNED);
}
/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6200d5a..2ef2394 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -54,6 +54,7 @@
#include <linux/kvm_irqfd.h>
#include <linux/irqbypass.h>
#include <linux/sched/stat.h>
+#include <linux/sched/isolation.h>
#include <linux/mem_encrypt.h>
#include <trace/events/kvm.h>
@@ -155,6 +156,9 @@ EXPORT_SYMBOL_GPL(enable_vmware_backdoor);
static bool __read_mostly force_emulation_prefix = false;
module_param(force_emulation_prefix, bool, S_IRUGO);
+bool __read_mostly pi_inject_timer = 0;
+module_param(pi_inject_timer, bool, S_IRUGO | S_IWUSR);
+
#define KVM_NR_SHARED_MSRS 16
struct kvm_shared_msrs_global {
@@ -7030,6 +7034,7 @@ int kvm_arch_init(void *opaque)
host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
kvm_lapic_init();
+ pi_inject_timer = housekeeping_enabled(HK_FLAG_TIMER);
#ifdef CONFIG_X86_64
pvclock_gtod_register_notifier(&pvclock_gtod_notifier);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 275b3b6..aa539d6 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -296,6 +296,8 @@ extern unsigned int min_timer_period_us;
extern bool enable_vmware_backdoor;
+extern bool pi_inject_timer;
+
extern struct static_key kvm_no_apic_vcpu;
static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index b0fb144..6fc5407 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -19,6 +19,7 @@ enum hk_flags {
DECLARE_STATIC_KEY_FALSE(housekeeping_overridden);
extern int housekeeping_any_cpu(enum hk_flags flags);
extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags);
+extern bool housekeeping_enabled(enum hk_flags flags);
extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags);
extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags);
extern void __init housekeeping_init(void);
@@ -38,6 +39,7 @@ static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
static inline void housekeeping_affine(struct task_struct *t,
enum hk_flags flags) { }
static inline void housekeeping_init(void) { }
+static inline bool housekeeping_enabled(enum hk_flags flags) { }
#endif /* CONFIG_CPU_ISOLATION */
static inline bool housekeeping_cpu(int cpu, enum hk_flags flags)
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 123ea07..ccb2808 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -14,6 +14,12 @@ EXPORT_SYMBOL_GPL(housekeeping_overridden);
static cpumask_var_t housekeeping_mask;
static unsigned int housekeeping_flags;
+bool housekeeping_enabled(enum hk_flags flags)
+{
+ return !!(housekeeping_flags & flags);
+}
+EXPORT_SYMBOL_GPL(housekeeping_enabled);
+
int housekeeping_any_cpu(enum hk_flags flags)
{
if (static_branch_unlikely(&housekeeping_overridden))
--
2.7.4
From: Wanpeng Li <[email protected]>
Dedicated instances are currently disturbed by unnecessary jitter due
to the emulated lapic timers fire on the same pCPUs which vCPUs resident.
There is no hardware virtual timer on Intel for guest like ARM. Both
programming timer in guest and the emulated timer fires incur vmexits.
This patch tries to avoid vmexit which is incurred by the emulated
timer fires in dedicated instance scenario.
When nohz_full is enabled in dedicated instances scenario, the emulated
timers can be offload to the nearest busy housekeeping cpus since APICv
is really common in recent years. The guest timer interrupt is injected
by posted-interrupt which is delivered by housekeeping cpu once the emulated
timer fires.
3%~5% redis performance benefit can be observed on Skylake server.
Signed-off-by: Wanpeng Li <[email protected]>
---
arch/x86/kvm/lapic.c | 32 +++++++++++++++++++++++++-------
arch/x86/kvm/x86.h | 5 +++++
2 files changed, 30 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 09b7387..c08e5a8 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -133,6 +133,12 @@ static inline bool posted_interrupt_inject_timer_enabled(struct kvm_vcpu *vcpu)
kvm_mwait_in_guest(vcpu->kvm);
}
+static inline bool can_posted_interrupt_inject_timer(struct kvm_vcpu *vcpu)
+{
+ return posted_interrupt_inject_timer_enabled(vcpu) &&
+ !vcpu_halt_in_guest(vcpu);
+}
+
static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
u32 dest_id, struct kvm_lapic ***cluster, u16 *mask) {
switch (map->mode) {
@@ -1441,6 +1447,19 @@ static void apic_update_lvtt(struct kvm_lapic *apic)
}
}
+static void kvm_apic_inject_pending_timer_irqs(struct kvm_lapic *apic)
+{
+ struct kvm_timer *ktimer = &apic->lapic_timer;
+
+ kvm_apic_local_deliver(apic, APIC_LVTT);
+ if (apic_lvtt_tscdeadline(apic))
+ ktimer->tscdeadline = 0;
+ if (apic_lvtt_oneshot(apic)) {
+ ktimer->tscdeadline = 0;
+ ktimer->target_expiration = 0;
+ }
+}
+
static void apic_timer_expired(struct kvm_lapic *apic)
{
struct kvm_vcpu *vcpu = apic->vcpu;
@@ -1450,6 +1469,11 @@ static void apic_timer_expired(struct kvm_lapic *apic)
if (atomic_read(&apic->lapic_timer.pending))
return;
+ if (unlikely(can_posted_interrupt_inject_timer(apic->vcpu))) {
+ kvm_apic_inject_pending_timer_irqs(apic);
+ return;
+ }
+
atomic_inc(&apic->lapic_timer.pending);
kvm_set_pending_timer(vcpu);
@@ -2386,13 +2410,7 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
struct kvm_lapic *apic = vcpu->arch.apic;
if (atomic_read(&apic->lapic_timer.pending) > 0) {
- kvm_apic_local_deliver(apic, APIC_LVTT);
- if (apic_lvtt_tscdeadline(apic))
- apic->lapic_timer.tscdeadline = 0;
- if (apic_lvtt_oneshot(apic)) {
- apic->lapic_timer.tscdeadline = 0;
- apic->lapic_timer.target_expiration = 0;
- }
+ kvm_apic_inject_pending_timer_irqs(apic);
atomic_set(&apic->lapic_timer.pending, 0);
}
}
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index aa539d6..74c86cb 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -364,4 +364,9 @@ static inline bool kvm_pat_valid(u64 data)
void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu);
void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu);
+static inline bool vcpu_halt_in_guest(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.apf.halted;
+}
+
#endif
--
2.7.4
From: Wanpeng Li <[email protected]>
When lapic timer is injected by posted-interrupt, the emulated timer is
offload to the housekeeping cpu. The timer interrupt will be delivered
properly, no need to migrate timer.
Cc: Paolo Bonzini <[email protected]>
Cc: Radim Krčmář <[email protected]>
Signed-off-by: Wanpeng Li <[email protected]>
---
arch/x86/kvm/lapic.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c08e5a8..a3e4ca8 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2532,7 +2532,8 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
{
struct hrtimer *timer;
- if (!lapic_in_kernel(vcpu))
+ if (!lapic_in_kernel(vcpu) ||
+ posted_interrupt_inject_timer_enabled(vcpu))
return;
timer = &vcpu->arch.apic->lapic_timer.timer;
--
2.7.4
From: Wanpeng Li <[email protected]>
Wait before calling posted-interrupt deliver function directly to add
advance timer support to pi_inject_timer.
Cc: Paolo Bonzini <[email protected]>
Cc: Radim Krčmář <[email protected]>
Signed-off-by: Wanpeng Li <[email protected]>
---
arch/x86/kvm/lapic.c | 6 ++++--
arch/x86/kvm/lapic.h | 2 +-
arch/x86/kvm/svm.c | 2 +-
arch/x86/kvm/vmx/vmx.c | 2 +-
4 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index a3e4ca8..9581817 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1470,6 +1470,8 @@ static void apic_timer_expired(struct kvm_lapic *apic)
return;
if (unlikely(can_posted_interrupt_inject_timer(apic->vcpu))) {
+ if (apic->lapic_timer.timer_advance_ns)
+ kvm_wait_lapic_expire(vcpu, true);
kvm_apic_inject_pending_timer_irqs(apic);
return;
}
@@ -1561,7 +1563,7 @@ static inline void adjust_lapic_timer_advance(struct kvm_vcpu *vcpu,
apic->lapic_timer.timer_advance_ns = timer_advance_ns;
}
-void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
+void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu, bool pi_inject)
{
struct kvm_lapic *apic = vcpu->arch.apic;
u64 guest_tsc, tsc_deadline;
@@ -1569,7 +1571,7 @@ void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
if (apic->lapic_timer.expired_tscdeadline == 0)
return;
- if (!lapic_timer_int_injected(vcpu))
+ if (!lapic_timer_int_injected(vcpu) && !pi_inject)
return;
tsc_deadline = apic->lapic_timer.expired_tscdeadline;
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index f974a3d..16f0500 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -220,7 +220,7 @@ static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu)
bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
-void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu);
+void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu, bool pi_inject);
bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
struct kvm_vcpu **dest_vcpu);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 302cb40..049ba64 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -5648,7 +5648,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
if (lapic_in_kernel(vcpu) &&
vcpu->arch.apic->lapic_timer.timer_advance_ns)
- kvm_wait_lapic_expire(vcpu);
+ kvm_wait_lapic_expire(vcpu, false);
/*
* If this vCPU has touched SPEC_CTRL, restore the guest's value if
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index da24f18..302bac4 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6447,7 +6447,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
if (lapic_in_kernel(vcpu) &&
vcpu->arch.apic->lapic_timer.timer_advance_ns)
- kvm_wait_lapic_expire(vcpu);
+ kvm_wait_lapic_expire(vcpu, false);
/*
* If this vCPU has touched SPEC_CTRL, restore the guest's value if
--
2.7.4
On Thu, 6 Jun 2019 at 13:31, Wanpeng Li <[email protected]> wrote:
>
> Dedicated instances are currently disturbed by unnecessary jitter due
> to the emulated lapic timers fire on the same pCPUs which vCPUs resident.
> There is no hardware virtual timer on Intel for guest like ARM. Both
> programming timer in guest and the emulated timer fires incur vmexits.
> This patchset tries to avoid vmexit which is incurred by the emulated
> timer fires in dedicated instance scenario.
>
> When nohz_full is enabled in dedicated instances scenario, the unpinned
> timer will be moved to the nearest busy housekeepers after commit 444969223c8
> ("sched/nohz: Fix affine unpinned timers mess"). However, KVM always makes
> lapic timer pinned to the pCPU which vCPU residents, the reason is explained
> by commit 61abdbe0 (kvm: x86: make lapic hrtimer pinned). Actually, these
> emulated timers can be offload to the housekeeping cpus since APICv
> is really common in recent years. The guest timer interrupt is injected by
> posted-interrupt which is delivered by housekeeping cpu once the emulated
> timer fires.
>
> The host admin should fine tuned, e.g. dedicated instances scenario w/
> nohz_full cover the pCPUs which vCPUs resident, several pCPUs surplus
> for housekeeping, disable mwait/hlt/pause vmexits to occupy the pCPUs,
> fortunately preemption timer is disabled after mwait is exposed to
> guest which makes emulated timer offload can be possible.
> 3%~5% redis performance benefit can be observed on Skylake server.
w/o patchset:
VM-EXIT Samples Samples% Time%
Min Time Max Time Avg time
EXTERNAL_INTERRUPT 42916 49.43% 39.30% 0.47us
106.09us 0.71us ( +- 1.09% )
w/ patchset:
VM-EXIT Samples Samples% Time%
Min Time Max Time Avg time
EXTERNAL_INTERRUPT 6871 9.29% 2.96% 0.44us
57.88us 0.72us ( +- 4.02% )
Regards,
Wanpeng Li
2019-06-06 13:31+0800, Wanpeng Li:
> From: Wanpeng Li <[email protected]>
>
> Dedicated instances are currently disturbed by unnecessary jitter due
> to the emulated lapic timers fire on the same pCPUs which vCPUs resident.
> There is no hardware virtual timer on Intel for guest like ARM. Both
> programming timer in guest and the emulated timer fires incur vmexits.
> This patch tries to avoid vmexit which is incurred by the emulated
> timer fires in dedicated instance scenario.
>
> When nohz_full is enabled in dedicated instances scenario, the emulated
> timers can be offload to the nearest busy housekeeping cpus since APICv
> is really common in recent years. The guest timer interrupt is injected
> by posted-interrupt which is delivered by housekeeping cpu once the emulated
> timer fires.
>
> 3%~5% redis performance benefit can be observed on Skylake server.
>
> Signed-off-by: Wanpeng Li <[email protected]>
> ---
> arch/x86/kvm/lapic.c | 32 +++++++++++++++++++++++++-------
> arch/x86/kvm/x86.h | 5 +++++
> 2 files changed, 30 insertions(+), 7 deletions(-)
>
> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> index 09b7387..c08e5a8 100644
> --- a/arch/x86/kvm/lapic.c
> +++ b/arch/x86/kvm/lapic.c
> @@ -133,6 +133,12 @@ static inline bool posted_interrupt_inject_timer_enabled(struct kvm_vcpu *vcpu)
> kvm_mwait_in_guest(vcpu->kvm);
> }
>
> +static inline bool can_posted_interrupt_inject_timer(struct kvm_vcpu *vcpu)
> +{
> + return posted_interrupt_inject_timer_enabled(vcpu) &&
> + !vcpu_halt_in_guest(vcpu);
It would make more sense to have a condition for general blocking in
KVM, but keep in mind that we're not running on the same cpu anymore, so
any code like that has to be properly protected against VM entries under
our hands. (The VCPU could appear halted here, but before we get make
the timer pending, the VCPU would enter and potentially never check the
interrupt.)
I think we should be able to simply do
if (posted_interrupt_inject_timer_enabled(vcpu))
kvm_inject_apic_timer_irqs();
directly in the apic_timer_expired() as the injection will wake up the
target if necessary. It's going to be a bit slow for timer callback in
those (too slow to warrant special handling?), but there hopefully
aren't any context restrictions in place.
Thanks.
2019-06-06 13:31+0800, Wanpeng Li:
> From: Wanpeng Li <[email protected]>
>
> Make lapic timer unpinned when timer is injected by posted-interrupt,
> the emulated timer can be offload to the housekeeping cpus.
>
> The host admin should fine tuned, e.g. dedicated instances scenario
> w/ nohz_full cover the pCPUs which vCPUs resident, several pCPUs
> surplus for housekeeping, disable mwait/hlt/pause vmexits to occupy
> the pCPUs, fortunately preemption timer is disabled after mwait is
> exposed to guest which makes emulated timer offload can be possible.
>
> Cc: Paolo Bonzini <[email protected]>
> Cc: Radim Krčmář <[email protected]>
> Signed-off-by: Wanpeng Li <[email protected]>
> ---
> arch/x86/kvm/lapic.c | 20 ++++++++++++++++----
> arch/x86/kvm/x86.c | 5 +++++
> arch/x86/kvm/x86.h | 2 ++
> include/linux/sched/isolation.h | 2 ++
> kernel/sched/isolation.c | 6 ++++++
> 5 files changed, 31 insertions(+), 4 deletions(-)
>
> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> index fcf42a3..09b7387 100644
> --- a/arch/x86/kvm/lapic.c
> +++ b/arch/x86/kvm/lapic.c
> @@ -127,6 +127,12 @@ static inline u32 kvm_x2apic_id(struct kvm_lapic *apic)
> return apic->vcpu->vcpu_id;
> }
>
> +static inline bool posted_interrupt_inject_timer_enabled(struct kvm_vcpu *vcpu)
> +{
> + return pi_inject_timer && kvm_vcpu_apicv_active(vcpu) &&
> + kvm_mwait_in_guest(vcpu->kvm);
I'm torn about the mwait dependency. It covers a lot of the targeted
user base, but the relation is convoluted and not fitting perfectly.
What do you think about making posted_interrupt_inject_timer_enabled()
just
pi_inject_timer && kvm_vcpu_apicv_active(vcpu)
and disarming the vmx preemption timer when
posted_interrupt_inject_timer_enabled(), just like we do with mwait now?
Thanks.
On Tue, 11 Jun 2019 at 00:51, Radim Krčmář <[email protected]> wrote:
>
> 2019-06-06 13:31+0800, Wanpeng Li:
> > From: Wanpeng Li <[email protected]>
> >
> > Dedicated instances are currently disturbed by unnecessary jitter due
> > to the emulated lapic timers fire on the same pCPUs which vCPUs resident.
> > There is no hardware virtual timer on Intel for guest like ARM. Both
> > programming timer in guest and the emulated timer fires incur vmexits.
> > This patch tries to avoid vmexit which is incurred by the emulated
> > timer fires in dedicated instance scenario.
> >
> > When nohz_full is enabled in dedicated instances scenario, the emulated
> > timers can be offload to the nearest busy housekeeping cpus since APICv
> > is really common in recent years. The guest timer interrupt is injected
> > by posted-interrupt which is delivered by housekeeping cpu once the emulated
> > timer fires.
> >
> > 3%~5% redis performance benefit can be observed on Skylake server.
> >
> > Signed-off-by: Wanpeng Li <[email protected]>
> > ---
> > arch/x86/kvm/lapic.c | 32 +++++++++++++++++++++++++-------
> > arch/x86/kvm/x86.h | 5 +++++
> > 2 files changed, 30 insertions(+), 7 deletions(-)
> >
> > diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> > index 09b7387..c08e5a8 100644
> > --- a/arch/x86/kvm/lapic.c
> > +++ b/arch/x86/kvm/lapic.c
> > @@ -133,6 +133,12 @@ static inline bool posted_interrupt_inject_timer_enabled(struct kvm_vcpu *vcpu)
> > kvm_mwait_in_guest(vcpu->kvm);
> > }
> >
> > +static inline bool can_posted_interrupt_inject_timer(struct kvm_vcpu *vcpu)
> > +{
> > + return posted_interrupt_inject_timer_enabled(vcpu) &&
> > + !vcpu_halt_in_guest(vcpu);
>
> It would make more sense to have a condition for general blocking in
> KVM, but keep in mind that we're not running on the same cpu anymore, so
> any code like that has to be properly protected against VM entries under
> our hands. (The VCPU could appear halted here, but before we get make
> the timer pending, the VCPU would enter and potentially never check the
> interrupt.)
>
> I think we should be able to simply do
>
> if (posted_interrupt_inject_timer_enabled(vcpu))
> kvm_inject_apic_timer_irqs();
>
> directly in the apic_timer_expired() as the injection will wake up the
> target if necessary. It's going to be a bit slow for timer callback in
> those (too slow to warrant special handling?), but there hopefully
> aren't any context restrictions in place.
The vCPU halt status is used to handle non-PV apf notification aware
guest which is pointed out by Paolo.
https://lkml.org/lkml/2019/6/5/436 The vCPU will not re-vmentry w/
timer interrupt even if there is a kick since vcpu->arch.apf.halted is
true and it can't escape from kvm_vcpu_check_block().
Regards,
Wanpeng Li
On Tue, 11 Jun 2019 at 01:11, Radim Krčmář <[email protected]> wrote:
>
> 2019-06-06 13:31+0800, Wanpeng Li:
> > From: Wanpeng Li <[email protected]>
> >
> > Make lapic timer unpinned when timer is injected by posted-interrupt,
> > the emulated timer can be offload to the housekeeping cpus.
> >
> > The host admin should fine tuned, e.g. dedicated instances scenario
> > w/ nohz_full cover the pCPUs which vCPUs resident, several pCPUs
> > surplus for housekeeping, disable mwait/hlt/pause vmexits to occupy
> > the pCPUs, fortunately preemption timer is disabled after mwait is
> > exposed to guest which makes emulated timer offload can be possible.
> >
> > Cc: Paolo Bonzini <[email protected]>
> > Cc: Radim Krčmář <[email protected]>
> > Signed-off-by: Wanpeng Li <[email protected]>
> > ---
> > arch/x86/kvm/lapic.c | 20 ++++++++++++++++----
> > arch/x86/kvm/x86.c | 5 +++++
> > arch/x86/kvm/x86.h | 2 ++
> > include/linux/sched/isolation.h | 2 ++
> > kernel/sched/isolation.c | 6 ++++++
> > 5 files changed, 31 insertions(+), 4 deletions(-)
> >
> > diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> > index fcf42a3..09b7387 100644
> > --- a/arch/x86/kvm/lapic.c
> > +++ b/arch/x86/kvm/lapic.c
> > @@ -127,6 +127,12 @@ static inline u32 kvm_x2apic_id(struct kvm_lapic *apic)
> > return apic->vcpu->vcpu_id;
> > }
> >
> > +static inline bool posted_interrupt_inject_timer_enabled(struct kvm_vcpu *vcpu)
> > +{
> > + return pi_inject_timer && kvm_vcpu_apicv_active(vcpu) &&
> > + kvm_mwait_in_guest(vcpu->kvm);
>
> I'm torn about the mwait dependency. It covers a lot of the targeted
> user base, but the relation is convoluted and not fitting perfectly.
>
> What do you think about making posted_interrupt_inject_timer_enabled()
> just
>
> pi_inject_timer && kvm_vcpu_apicv_active(vcpu)
>
> and disarming the vmx preemption timer when
> posted_interrupt_inject_timer_enabled(), just like we do with mwait now?
Agreed, thanks for the review. :)
Regards,
Wanpeng Li
On 06/06/19 07:31, Wanpeng Li wrote:
> +static inline bool can_posted_interrupt_inject_timer(struct kvm_vcpu *vcpu)
> +{
> + return posted_interrupt_inject_timer_enabled(vcpu) &&
> + !vcpu_halt_in_guest(vcpu);
> +}
> +
I agree with Radim, what you want here is just use kvm_hlt_in_guest.
I'll post shortly a prerequisite patch to block APF artificial halt when
kvm_hlt_in_guest is true.
Paolo
On Tue, 11 Jun 2019 at 19:40, Paolo Bonzini <[email protected]> wrote:
>
> On 06/06/19 07:31, Wanpeng Li wrote:
> > +static inline bool can_posted_interrupt_inject_timer(struct kvm_vcpu *vcpu)
> > +{
> > + return posted_interrupt_inject_timer_enabled(vcpu) &&
> > + !vcpu_halt_in_guest(vcpu);
> > +}
> > +
>
> I agree with Radim, what you want here is just use kvm_hlt_in_guest.
Do it in v3.
>
> I'll post shortly a prerequisite patch to block APF artificial halt when
> kvm_hlt_in_guest is true.
Thanks Paolo!
Regards,
Wanpeng Li