[PATCH RFC V4 0/3] kvm: Improving directed yield in PLE handler

From: Raghavendra K T

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

V2 was:
Reviewed-by: Rik van Riel

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
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

From: Raghavendra K T

Currently, on a large vcpu guests, there is a high probability of
yielding to the same vcpu who had recently done a pause-loop exit or
cpu relax intercepted. Such a yield can lead to the vcpu spinning
again and hence degrade the performance.

The patchset keeps track of the pause loop exit/cpu relax interception
and gives chance to a vcpu which:
(a) Has not done pause loop exit or cpu relax intercepted at all
(probably he is preempted lock-holder)
(b) Was skipped in last iteration because it did pause loop exit or
cpu relax intercepted, and probably has become eligible now
(next eligible lock holder)

Signed-off-by: Raghavendra K T

V2 was:
Reviewed-by: Rik van Riel

include/linux/kvm_host.h | 5 +++++
virt/kvm/kvm_main.c | 35 +++++++++++++++++++++++++++++++++++
2 files changed, 40 insertions(+), 0 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index fa353bd..cfb38a2 100644
a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -925,6 +925,11 @@ static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
{
}

+static inline bool kvm_vcpu_check_and_update_eligible(struct kvm_vcpu *vcpu)
+{
+ return true;
+}
+
#endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */

#endif
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index c50213f..6a82580 100644
a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1571,6 +1571,39 @@ bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
}
EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);

+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
+/*
+ * Helper that checks whether a VCPU is eligible for directed yield.
+ * Most eligible candidate to yield is decided by following heuristics:
+ *
+ * (a) VCPU which has not done pl-exit or cpu relax intercepted recently
+ * (preempted lock holder), indicated by @cpu_relax_intercepted.
+ * Set at the beiginning and cleared at the end of interception/PLE handler.
+ *
+ * (b) VCPU which has done pl-exit/ cpu relax intercepted but did not get
+ * chance last time (mostly it has become eligible now since we have probably
+ * yielded to lockholder in last iteration. This is done by toggling
+ * @dy_eligible each time a VCPU checked for eligibility.)
+ *
+ * Yielding to a recently pl-exited/cpu relax intercepted VCPU before yielding
+ * to preempted lock-holder could result in wrong VCPU selection and CPU
+ * burning. Giving priority for a potential lock-holder increases lock
+ * progress.
+ */
+bool kvm_vcpu_check_and_update_eligible(struct kvm_vcpu *vcpu)
+{
+ bool eligible;
+
+ eligible = !vcpu->ple.cpu_relax_intercepted ||
+ (vcpu->ple.cpu_relax_intercepted &&
+ vcpu->ple.dy_eligible);
+
+ if (vcpu->ple.cpu_relax_intercepted)
+ vcpu->ple.dy_eligible = !vcpu->ple.dy_eligible;
+
+ return eligible;
+}
+#endif
void kvm_vcpu_on_spin(struct kvm_vcpu *me)
{
struct kvm *kvm = me->kvm;
@@ -1599,6 +1632,8 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
continue;
if (waitqueue_active(&vcpu->wq))
continue;
+ if (!kvm_vcpu_check_and_update_eligible(vcpu))
+ continue;
if (kvm_vcpu_yield_to(vcpu)) {
kvm->last_boosted_vcpu = i;
yielded = 1;

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

From: Raghavendra K T

Suggested-by: Avi Kivity
Signed-off-by: Raghavendra K T

arch/s390/kvm/Kconfig | 1 +
arch/x86/kvm/Kconfig | 1 +
virt/kvm/Kconfig | 3 +++
3 files changed, 5 insertions(+), 0 deletions(-)

diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 78eb984..a6e2677 100644
a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -21,6 +21,7 @@ config KVM
depends on HAVE_KVM && EXPERIMENTAL
select PREEMPT_NOTIFIERS
select ANON_INODES
+ select HAVE_KVM_CPU_RELAX_INTERCEPT
help
Support hosting paravirtualized guest machines using the SIE
virtualization capability on the mainframe. This should work
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index a28f338..45c044f 100644
a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -37,6 +37,7 @@ config KVM
select TASK_DELAY_ACCT
select PERF_EVENTS
select HAVE_KVM_MSI
+ select HAVE_KVM_CPU_RELAX_INTERCEPT
help
Support hosting fully virtualized guest machines using hardware
virtualization extensions. You will need a fairly recent
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 28694f4..d01b24b 100644
a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -21,3 +21,6 @@ config KVM_ASYNC_PF

config HAVE_KVM_MSI
bool
+
+config HAVE_KVM_CPU_RELAX_INTERCEPT
+ bool

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

On 07/16/2012 11:25 AM, Raghavendra K T wrote:

From: Raghavendra K T

Currently, on a large vcpu guests, there is a high probability of
yielding to the same vcpu who had recently done a pause-loop exit or
cpu relax intercepted. Such a yield can lead to the vcpu spinning
again and hence degrade the performance.

The patchset keeps track of the pause loop exit/cpu relax interception
and gives chance to a vcpu which:
(a) Has not done pause loop exit or cpu relax intercepted at all
(probably he is preempted lock-holder)
(b) Was skipped in last iteration because it did pause loop exit or
cpu relax intercepted, and probably has become eligible now
(next eligible lock holder)



+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
+/*
+ * Helper that checks whether a VCPU is eligible for directed yield.
+ * Most eligible candidate to yield is decided by following heuristics:
+ *
+ * (a) VCPU which has not done pl-exit or cpu relax intercepted recently
+ * (preempted lock holder), indicated by @cpu_relax_intercepted.
+ * Set at the beiginning and cleared at the end of interception/PLE handler.
+ *
+ * (b) VCPU which has done pl-exit/ cpu relax intercepted but did not get
+ * chance last time (mostly it has become eligible now since we have probably
+ * yielded to lockholder in last iteration. This is done by toggling
+ * @dy_eligible each time a VCPU checked for eligibility.)
+ *
+ * Yielding to a recently pl-exited/cpu relax intercepted VCPU before yielding
+ * to preempted lock-holder could result in wrong VCPU selection and CPU
+ * burning. Giving priority for a potential lock-holder increases lock
+ * progress.
+ */
+bool kvm_vcpu_check_and_update_eligible(struct kvm_vcpu *vcpu)

Predicates' names should give a hint as to what true and false returns
mean. For example vcpu_eligible_for_directed_yield().

+{
+ bool eligible;
+
+ eligible = !vcpu->ple.cpu_relax_intercepted ||
+ (vcpu->ple.cpu_relax_intercepted &&
+ vcpu->ple.dy_eligible);
+
+ if (vcpu->ple.cpu_relax_intercepted)
+ vcpu->ple.dy_eligible = !vcpu->ple.dy_eligible;

Probably should assign 'true', since the previous value is essentially
random.

+
+ return eligible;
+}

You're accessing another vcpu's data structures without any locking.
This is probably okay since we're not basing any life or death decisions
on this, but a comment would be good to explain to readers that this has
been considered and is okay (and why).




error compiling committee.c: too many arguments to function


To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

On 07/16/2012 11:25 AM, Raghavendra K T wrote:

From: Raghavendra K T

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

V2 was:
Reviewed-by: Rik van Riel

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;

Naming:

- ple is the x86 name, but this is common code. I'd call it spin_loop.
- cpu_relax_intercepted: can call it in_spin_loop, the original name can
me "are we intercepting cpu_relax or not" which may be useful at one
point (when we know we aren't overcommitted)
- dy_eligible: I'd like to understand the algorithm more and would want
the name to reflect it, will come to this later if I have a better idea.

+#endif

blank line.

struct kvm_vcpu_arch arch;
};

error compiling committee.c: too many arguments to function


To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/