We do track the current steal time of the host CPUs. Let us use
this value to disable halt polling if the steal time goes beyond
a configured value.
Signed-off-by: Christian Borntraeger <borntraeger@xxxxxxxxxx>
Acked-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Reviewed-by: Cornelia Huck <cohuck@xxxxxxxxxx>
Signed-off-by: Christian Borntraeger <borntraeger@xxxxxxxxxx>
---
arch/s390/include/asm/kvm_host.h | 1 +
arch/s390/kvm/Kconfig | 1 +
arch/s390/kvm/kvm-s390.c | 17 +++++++++++++++++
3 files changed, 19 insertions(+)
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index e224246ff93c..bdbc81b5bc91 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -313,6 +313,7 @@ struct kvm_vcpu_stat {
u64 halt_successful_poll;
u64 halt_attempted_poll;
u64 halt_poll_invalid;
+ u64 halt_no_poll_steal;
u64 halt_wakeup;
u64 instruction_lctl;
u64 instruction_lctlg;
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 767453faacfc..e987e73738b5 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -31,6 +31,7 @@ config KVM
select HAVE_KVM_IRQFD
select HAVE_KVM_IRQ_ROUTING
select HAVE_KVM_INVALID_WAKEUPS
+ select HAVE_KVM_NO_POLL
select SRCU
select KVM_VFIO
---help---
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index eb68ada1334b..ed280a4fea07 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -75,6 +75,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
+ { "halt_no_poll_steal", VCPU_STAT(halt_no_poll_steal) },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
@@ -177,6 +178,11 @@ static int hpage;
module_param(hpage, int, 0444);
MODULE_PARM_DESC(hpage, "1m huge page backing support");
+/* maximum percentage of steal time for polling. >100 is treated like 100 */
+static u8 halt_poll_max_steal = 10;
+module_param(halt_poll_max_steal, byte, 0644);
+MODULE_PARM_DESC(hpage, "Maximum percentage of steal time to allow polling");
+
/*
* For now we handle at most 16 double words as this is what the s390 base
* kernel handles and stores in the prefix page. If we ever need to go beyond
@@ -3166,6 +3172,17 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
}
}
+bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
+{
+ /* do not poll with more than halt_poll_max_steal percent of steal time */
+ if (S390_lowcore.avg_steal_timer * 100 / (TICK_USEC << 12) >=
+ halt_poll_max_steal) {
+ vcpu->stat.halt_no_poll_steal++;
+ return true;
+ }
+ return false;
+}
+
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
/* kvm common code refers to this, but never calls it */
--
2.19.1
