[PATCH RFC V4 2/3] kvm: Note down when cpu relax intercepted or pause loop exited

From: Raghavendra K T
Date: Mon Jul 16 2012 - 04:27:25 EST


From: Raghavendra K T <raghavendra.kt@xxxxxxxxxxxxxxxxxx>

Noting pause loop exited vcpu or cpu relax intercepted helps in
filtering right candidate to yield. Wrong selection of vcpu;
i.e., a vcpu that just did a pl-exit or cpu relax intercepted may
contribute to performance degradation.

Signed-off-by: Raghavendra K T <raghavendra.kt@xxxxxxxxxxxxxxxxxx>
---
V2 was:
Reviewed-by: Rik van Riel <riel@xxxxxxxxxx>

include/linux/kvm_host.h | 37 +++++++++++++++++++++++++++++++++++++
virt/kvm/kvm_main.c | 5 +++++
2 files changed, 42 insertions(+), 0 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c446435..fa353bd 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -183,6 +183,18 @@ struct kvm_vcpu {
} async_pf;
#endif

+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
+ /*
+ * Cpu relax intercept or pause loop exit optimization
+ * cpu_relax_intercepted: set when a vcpu does a pause loop exit
+ * or cpu relax intercepted.
+ * dy_eligible: indicates whether vcpu is eligible for directed yield.
+ */
+ struct {
+ bool cpu_relax_intercepted;
+ bool dy_eligible;
+ } ple;
+#endif
struct kvm_vcpu_arch arch;
};

@@ -890,5 +902,30 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
}
}

+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
+
+static inline void kvm_vcpu_set_cpu_relax_intercepted(struct kvm_vcpu *vcpu,
+ bool val)
+{
+ vcpu->ple.cpu_relax_intercepted = val;
+}
+static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
+{
+ vcpu->ple.dy_eligible = val;
+}
+
+#else /* !CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
+
+static inline void kvm_vcpu_set_cpu_relax_intercepted(struct kvm_vcpu *vcpu,
+ bool val)
+{
+}
+
+static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
+{
+}
+
+#endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
+
#endif

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7e14068..c50213f 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -236,6 +236,9 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
}
vcpu->run = page_address(page);

+ kvm_vcpu_set_cpu_relax_intercepted(vcpu, false);
+ kvm_vcpu_set_dy_eligible(vcpu, false);
+
r = kvm_arch_vcpu_init(vcpu);
if (r < 0)
goto fail_free_run;
@@ -1577,6 +1580,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
int pass;
int i;

+ kvm_vcpu_set_cpu_relax_intercepted(me, true);
/*
* We boost the priority of a VCPU that is runnable but not
* currently running, because it got preempted by something
@@ -1602,6 +1606,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
}
}
}
+ kvm_vcpu_set_cpu_relax_intercepted(me, false);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin);


--
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/