KVM: PPC: Implement existing and add new halt polling vcpu stats

vcpu stats are used to collect information about a vcpu which can be viewed
in the debugfs. For example halt_attempted_poll and halt_successful_poll
are used to keep track of the number of times the vcpu attempts to and
successfully polls. These stats are currently not used on powerpc.

Implement incrementation of the halt_attempted_poll and
halt_successful_poll vcpu stats for powerpc. Since these stats are summed
over all the vcpus for all running guests it doesn't matter which vcpu
they are attributed to, thus we choose the current runner vcpu of the
vcore.

Also add new vcpu stats: halt_poll_success_ns, halt_poll_fail_ns and
halt_wait_ns to be used to accumulate the total time spend polling
successfully, polling unsuccessfully and waiting respectively, and
halt_successful_wait to accumulate the number of times the vcpu waits.
Given that halt_poll_success_ns, halt_poll_fail_ns and halt_wait_ns are
expressed in nanoseconds it is necessary to represent these as 64-bit
quantities, otherwise they would overflow after only about 4 seconds.

Given that the total time spend either polling or waiting will be known and
the number of times that each was done, it will be possible to determine
the average poll and wait times. This will give the ability to tune the kvm
module parameters based on the calculated average wait and poll times.
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Reviewed-by: David Matlack <dmatlack@google.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>

arch/powerpc/include/asm/kvm_host.h

@@ -116,8 +116,12 @@ struct kvm_vcpu_stat {
 	u64 emulated_inst_exits;
 	u64 dec_exits;
 	u64 ext_intr_exits;
+	u64 halt_poll_success_ns;
+	u64 halt_poll_fail_ns;
+	u64 halt_wait_ns;
 	u64 halt_successful_poll;
 	u64 halt_attempted_poll;
+	u64 halt_successful_wait;
 	u64 halt_poll_invalid;
 	u64 halt_wakeup;
 	u64 dbell_exits;

arch/powerpc/kvm/book3s.c

@@ -52,8 +52,12 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "dec",         VCPU_STAT(dec_exits) },
 	{ "ext_intr",    VCPU_STAT(ext_intr_exits) },
 	{ "queue_intr",  VCPU_STAT(queue_intr) },
+	{ "halt_poll_success_ns",	VCPU_STAT(halt_poll_success_ns) },
+	{ "halt_poll_fail_ns",		VCPU_STAT(halt_poll_fail_ns) },
+	{ "halt_wait_ns",		VCPU_STAT(halt_wait_ns) },
 	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll), },
 	{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll), },
+	{ "halt_successful_wait",	VCPU_STAT(halt_successful_wait) },
 	{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
 	{ "pf_storage",  VCPU_STAT(pf_storage) },

arch/powerpc/kvm/book3s_hv.c

@@ -2680,15 +2680,16 @@ static int kvmppc_vcore_check_block(struct kvmppc_vcore *vc)
  */
 static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 {
+	ktime_t cur, start_poll, start_wait;
 	int do_sleep = 1;
-	ktime_t cur, start;
 	u64 block_ns;
 	DECLARE_SWAITQUEUE(wait);
 
 	/* Poll for pending exceptions and ceded state */
-	cur = start = ktime_get();
+	cur = start_poll = ktime_get();
 	if (vc->halt_poll_ns) {
-		ktime_t stop = ktime_add_ns(start, vc->halt_poll_ns);
+		ktime_t stop = ktime_add_ns(start_poll, vc->halt_poll_ns);
+		++vc->runner->stat.halt_attempted_poll;
 
 		vc->vcore_state = VCORE_POLLING;
 		spin_unlock(&vc->lock);
@@ -2704,8 +2705,10 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 		spin_lock(&vc->lock);
 		vc->vcore_state = VCORE_INACTIVE;
 
-		if (!do_sleep)
+		if (!do_sleep) {
+			++vc->runner->stat.halt_successful_poll;
 			goto out;
+		}
 	}
 
 	prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
@@ -2713,9 +2716,14 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	if (kvmppc_vcore_check_block(vc)) {
 		finish_swait(&vc->wq, &wait);
 		do_sleep = 0;
+		/* If we polled, count this as a successful poll */
+		if (vc->halt_poll_ns)
+			++vc->runner->stat.halt_successful_poll;
 		goto out;
 	}
 
+	start_wait = ktime_get();
+
 	vc->vcore_state = VCORE_SLEEPING;
 	trace_kvmppc_vcore_blocked(vc, 0);
 	spin_unlock(&vc->lock);
@@ -2724,11 +2732,29 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	spin_lock(&vc->lock);
 	vc->vcore_state = VCORE_INACTIVE;
 	trace_kvmppc_vcore_blocked(vc, 1);
+	++vc->runner->stat.halt_successful_wait;
 
 	cur = ktime_get();
 
 out:
-	block_ns = ktime_to_ns(cur) - ktime_to_ns(start);
+	block_ns = ktime_to_ns(cur) - ktime_to_ns(start_poll);
+
+	/* Attribute wait time */
+	if (do_sleep) {
+		vc->runner->stat.halt_wait_ns +=
+			ktime_to_ns(cur) - ktime_to_ns(start_wait);
+		/* Attribute failed poll time */
+		if (vc->halt_poll_ns)
+			vc->runner->stat.halt_poll_fail_ns +=
+				ktime_to_ns(start_wait) -
+				ktime_to_ns(start_poll);
+	} else {
+		/* Attribute successful poll time */
+		if (vc->halt_poll_ns)
+			vc->runner->stat.halt_poll_success_ns +=
+				ktime_to_ns(cur) -
+				ktime_to_ns(start_poll);
+	}
 
 	/* Adjust poll time */
 	if (halt_poll_max_ns) {