[PATCH for-4.22? 1/9] sched: introduce specialization of "running only" vcpu_runstate_get()

[Jan Beulich <jbeulich@xxxxxxxx>]

About half the callers of vcpu_runstate_get() are solely after the
"running" time of a vCPU. Introduce a specialization with a smaller
read critical section and thus reduced risk of a need for retries.

Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
---
The function name was chosen such that grep-ing for "vcpu_runstate_get"
would still turn up all uses. If that was deemed largely irrelevant, a
better name might be e.g. vcpu_get_running_time().

--- a/xen/common/domctl.c
+++ b/xen/common/domctl.c
@@ -56,7 +56,6 @@ void getdomaininfo(struct domain *d, str
     struct vcpu *v;
     u64 cpu_time = 0;
     int flags = XEN_DOMINF_blocked;
-    struct vcpu_runstate_info runstate;
 
     memset(info, 0, sizeof(*info));
 
@@ -69,8 +68,7 @@ void getdomaininfo(struct domain *d, str
      */
     for_each_vcpu ( d, v )
     {
-        vcpu_runstate_get(v, &runstate);
-        cpu_time += runstate.time[RUNSTATE_running];
+        cpu_time += vcpu_runstate_get_running(v);
         info->max_vcpu_id = v->vcpu_id;
         if ( !(v->pause_flags & VPF_down) )
         {
@@ -829,8 +827,7 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xe
 
     case XEN_DOMCTL_getvcpuinfo:
     {
-        struct vcpu   *v;
-        struct vcpu_runstate_info runstate;
+        const struct vcpu *v;
 
         ret = -EINVAL;
         if ( op->u.getvcpuinfo.vcpu >= d->max_vcpus )
@@ -840,12 +837,10 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xe
         if ( (v = d->vcpu[op->u.getvcpuinfo.vcpu]) == NULL )
             break;
 
-        vcpu_runstate_get(v, &runstate);
-
         op->u.getvcpuinfo.online   = !(v->pause_flags & VPF_down);
         op->u.getvcpuinfo.blocked  = !!(v->pause_flags & VPF_blocked);
         op->u.getvcpuinfo.running  = v->is_running;
-        op->u.getvcpuinfo.cpu_time = runstate.time[RUNSTATE_running];
+        op->u.getvcpuinfo.cpu_time = vcpu_runstate_get_running(v);
         op->u.getvcpuinfo.cpu      = v->processor;
         ret = 0;
         copyback = 1;
--- a/xen/common/sched/core.c
+++ b/xen/common/sched/core.c
@@ -325,15 +325,35 @@ void vcpu_runstate_get(const struct vcpu
     }
 }
 
-uint64_t get_cpu_idle_time(unsigned int cpu)
+uint64_t vcpu_runstate_get_running(const struct vcpu *v)
 {
-    struct vcpu_runstate_info state = { 0 };
-    const struct vcpu *v = idle_vcpu[cpu];
+    struct seqcount seq = SEQCNT_ZERO();
+    const struct seqcount *s = v == current ? &seq : &v->runstate_seq;
+    unsigned int count;
+    uint64_t running;
+    s_time_t delta;
+
+    do {
+        count = read_seqcount_begin(s);
+
+        running = v->runstate.time[RUNSTATE_running];
+        delta = v->runstate.state == RUNSTATE_running
+                ? NOW() - v->runstate.state_entry_time
+                : 0;
+    } while ( read_seqcount_retry(s, count) );
+
+    if ( delta > 0 )
+        running += delta;
 
+    return running;
+}
+
+uint64_t get_cpu_idle_time(unsigned int cpu)
+{
     if ( cpu_online(cpu) && get_sched_res(cpu) )
-        vcpu_runstate_get(v, &state);
+        return vcpu_runstate_get_running(idle_vcpu[cpu]);
 
-    return state.time[RUNSTATE_running];
+    return 0;
 }
 
 /*
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -1121,6 +1121,7 @@ int vcpu_affinity_domctl(struct domain *
 
 void vcpu_runstate_get(const struct vcpu *v,
                        struct vcpu_runstate_info *runstate);
+uint64_t vcpu_runstate_get_running(const struct vcpu *v);
 uint64_t get_cpu_idle_time(unsigned int cpu);
 void sched_guest_idle(void (*idle) (void), unsigned int cpu);
 void scheduler_enable(void);