[RFC PATCH v1 4/6] xentop: collect IRQ and HYP time statistics.

[Volodymyr Babchuk <Volodymyr_Babchuk@xxxxxxxx>]

As scheduler code now collects time spent in IRQ handlers and in
do_softirq(), we can present those values to userspace tools like
xentop, so system administrator can see how system behaves.

We are updating counters only in sched_get_time_correction() function
to minimize number of taken spinlocks. As atomic_t is 32 bit wide, it
is not enough to store time with nanosecond precision. So we need to
use 64 bit variables and protect them with spinlock.

Signed-off-by: Volodymyr Babchuk <volodymyr_babchuk@xxxxxxxx>
---
 xen/common/sched/core.c     | 17 +++++++++++++++++
 xen/common/sysctl.c         |  1 +
 xen/include/public/sysctl.h |  4 +++-
 xen/include/xen/sched.h     |  2 ++
 4 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/xen/common/sched/core.c b/xen/common/sched/core.c
index a7294ff5c3..ee6b1d9161 100644
--- a/xen/common/sched/core.c
+++ b/xen/common/sched/core.c
@@ -95,6 +95,10 @@ static struct scheduler __read_mostly ops;
 
 static bool scheduler_active;
 
+static DEFINE_SPINLOCK(sched_stat_lock);
+s_time_t sched_stat_irq_time;
+s_time_t sched_stat_hyp_time;
+
 static void sched_set_affinity(
     struct sched_unit *unit, const cpumask_t *hard, const cpumask_t *soft);
 
@@ -994,9 +998,22 @@ s_time_t sched_get_time_correction(struct sched_unit *u)
             break;
     }
 
+    spin_lock_irqsave(&sched_stat_lock, flags);
+    sched_stat_irq_time += irq;
+    sched_stat_hyp_time += hyp;
+    spin_unlock_irqrestore(&sched_stat_lock, flags);
+
     return irq + hyp;
 }
 
+void sched_get_time_stats(uint64_t *irq_time, uint64_t *hyp_time)
+{
+    unsigned long flags;
+
+    spin_lock_irqsave(&sched_stat_lock, flags);
+    *irq_time = sched_stat_irq_time;
+    *hyp_time = sched_stat_hyp_time;
+    spin_unlock_irqrestore(&sched_stat_lock, flags);
 }
 
 /*
diff --git a/xen/common/sysctl.c b/xen/common/sysctl.c
index 1c6a817476..00683bc93f 100644
--- a/xen/common/sysctl.c
+++ b/xen/common/sysctl.c
@@ -270,6 +270,7 @@ long do_sysctl(XEN_GUEST_HANDLE_PARAM(xen_sysctl_t) 
u_sysctl)
         pi->scrub_pages = 0;
         pi->cpu_khz = cpu_khz;
         pi->max_mfn = get_upper_mfn_bound();
+        sched_get_time_stats(&pi->irq_time, &pi->hyp_time);
         arch_do_physinfo(pi);
         if ( iommu_enabled )
         {
diff --git a/xen/include/public/sysctl.h b/xen/include/public/sysctl.h
index 3a08c512e8..f320144d40 100644
--- a/xen/include/public/sysctl.h
+++ b/xen/include/public/sysctl.h
@@ -35,7 +35,7 @@
 #include "domctl.h"
 #include "physdev.h"
 
-#define XEN_SYSCTL_INTERFACE_VERSION 0x00000013
+#define XEN_SYSCTL_INTERFACE_VERSION 0x00000014
 
 /*
  * Read console content from Xen buffer ring.
@@ -118,6 +118,8 @@ struct xen_sysctl_physinfo {
     uint64_aligned_t scrub_pages;
     uint64_aligned_t outstanding_pages;
     uint64_aligned_t max_mfn; /* Largest possible MFN on this host */
+    uint64_aligned_t irq_time;
+    uint64_aligned_t hyp_time;
     uint32_t hw_cap[8];
 };
 
diff --git a/xen/include/xen/sched.h b/xen/include/xen/sched.h
index 51dc7c4551..869d4efbd6 100644
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -717,6 +717,8 @@ void vcpu_end_irq_handler(void);
 void vcpu_begin_hyp_task(struct vcpu *v);
 void vcpu_end_hyp_task(struct vcpu *v);
 
+void sched_get_time_stats(uint64_t *irq_time, uint64_t *hyp_time);
+
 /*
  * Force synchronisation of given VCPU's state. If it is currently descheduled,
  * this call will ensure that all its state is committed to memory and that
-- 
2.27.0