credit2: fix credit reset happening too few times

There is a bug in commit 5e4b419966 ("xen: credit2: only reset
credit on reset condition"). In fact, the aim of that commit was to
make sure that we do not perform too many credit reset operations
(which are not super cheap, and in an hot-path). But the check used
to determine whether a reset is necessary was the wrong one.

In fact, knowing just that some vCPUs have been skipped, while
traversing the runqueue (in runq_candidate()), is not enough. We
need to check explicitly whether the first vCPU in the runqueue
has a negative amount of credit.

Since a trace record is changed, this patch updates xentrace format file
and xenalyze as well

This should be backported.

Signed-off-by: Dario Faggioli <dfaggioli@suse.com>
Acked-by: George Dunlap <george.dunlap@citrix.com>
master commit: dae7b62e97
master date: 2020-04-03 10:46:53 +0200

tools/xentrace/formats

@@ -67,7 +67,7 @@
 0x00022210  CPU%(cpu)d  %(tsc)d (+%(reltsc)8d)  csched2:load_check     [ lrq_id[16]:orq_id[16] = 0x%(1)08x, delta = %(2)d ]
 0x00022211  CPU%(cpu)d  %(tsc)d (+%(reltsc)8d)  csched2:load_balance   [ l_bavgload = 0x%(2)08x%(1)08x, o_bavgload = 0x%(4)08x%(3)08x, lrq_id[16]:orq_id[16] = 0x%(5)08x ]
 0x00022212  CPU%(cpu)d  %(tsc)d (+%(reltsc)8d)  csched2:pick_cpu       [ b_avgload = 0x%(2)08x%(1)08x, dom:vcpu = 0x%(3)08x, rq_id[16]:new_cpu[16] = %(4)d ]
-0x00022213  CPU%(cpu)d  %(tsc)d (+%(reltsc)8d)  csched2:runq_candidate [ dom:vcpu = 0x%(1)08x, credit = %(4)d, skipped_vcpus = %(3)d, tickled_cpu = %(2)d ]
+0x00022213  CPU%(cpu)d  %(tsc)d (+%(reltsc)8d)  csched2:runq_candidate [ dom:vcpu = 0x%(1)08x, credit = %(3)d, tickled_cpu = %(2)d ]
 0x00022214  CPU%(cpu)d  %(tsc)d (+%(reltsc)8d)  csched2:schedule       [ rq:cpu = 0x%(1)08x, tasklet[8]:idle[8]:smt_idle[8]:tickled[8] = %(2)08x ]
 0x00022215  CPU%(cpu)d  %(tsc)d (+%(reltsc)8d)  csched2:ratelimit      [ dom:vcpu = 0x%(1)08x, runtime = %(2)d ]
 0x00022216  CPU%(cpu)d  %(tsc)d (+%(reltsc)8d)  csched2:runq_cand_chk  [ dom:vcpu = 0x%(1)08x ]

tools/xentrace/xenalyze.c

@@ -7855,14 +7855,12 @@ void sched_process(struct pcpu_info *p)
             if (opt.dump_all) {
                 struct {
                     unsigned vcpuid:16, domid:16;
-                    unsigned tickled_cpu, skipped;
+                    unsigned tickled_cpu;
                     int credit;
                 } *r = (typeof(r))ri->d;
 
-                printf(" %s csched2:runq_candidate d%uv%u, credit = %d, "
-                       "%u vcpus skipped, ",
-                       ri->dump_header, r->domid, r->vcpuid,
-                       r->credit, r->skipped);
+                printf(" %s csched2:runq_candidate d%uv%u, credit = %d, ",
+                       ri->dump_header, r->domid, r->vcpuid, r->credit);
                 if (r->tickled_cpu == (unsigned)-1)
                     printf("no cpu was tickled\n");
                 else

xen/common/sched_credit2.c

@@ -3265,16 +3265,13 @@ csched2_runtime(const struct scheduler *ops, int cpu,
 static struct csched2_vcpu *
 runq_candidate(struct csched2_runqueue_data *rqd,
                struct csched2_vcpu *scurr,
-               int cpu, s_time_t now,
-               unsigned int *skipped)
+               int cpu, s_time_t now)
 {
     struct list_head *iter, *temp;
     struct csched2_vcpu *snext = NULL;
     struct csched2_private *prv = csched2_priv(per_cpu(scheduler, cpu));
     bool yield = false, soft_aff_preempt = false;
 
-    *skipped = 0;
-
     if ( unlikely(is_idle_vcpu(scurr->vcpu)) )
     {
         snext = scurr;
@@ -3371,10 +3368,7 @@ runq_candidate(struct csched2_runqueue_data *rqd,
 
         /* Only consider vcpus that are allowed to run on this processor. */
         if ( !cpumask_test_cpu(cpu, svc->vcpu->cpu_hard_affinity) )
-        {
-            (*skipped)++;
             continue;
-        }
 
         /*
          * If a vcpu is meant to be picked up by another processor, and such
@@ -3383,7 +3377,6 @@ runq_candidate(struct csched2_runqueue_data *rqd,
         if ( svc->tickled_cpu != -1 && svc->tickled_cpu != cpu &&
              cpumask_test_cpu(svc->tickled_cpu, &rqd->tickled) )
         {
-            (*skipped)++;
             SCHED_STAT_CRANK(deferred_to_tickled_cpu);
             continue;
         }
@@ -3395,7 +3388,6 @@ runq_candidate(struct csched2_runqueue_data *rqd,
         if ( svc->vcpu->processor != cpu
              && snext->credit + CSCHED2_MIGRATE_RESIST > svc->credit )
         {
-            (*skipped)++;
             SCHED_STAT_CRANK(migrate_resisted);
             continue;
         }
@@ -3418,14 +3410,13 @@ runq_candidate(struct csched2_runqueue_data *rqd,
     {
         struct {
             unsigned vcpu:16, dom:16;
-            unsigned tickled_cpu, skipped;
+            unsigned tickled_cpu;
             int credit;
         } d;
         d.dom = snext->vcpu->domain->domain_id;
         d.vcpu = snext->vcpu->vcpu_id;
         d.credit = snext->credit;
         d.tickled_cpu = snext->tickled_cpu;
-        d.skipped = *skipped;
         __trace_var(TRC_CSCHED2_RUNQ_CANDIDATE, 1,
                     sizeof(d),
                     (unsigned char *)&d);
@@ -3456,7 +3447,6 @@ csched2_schedule(
     struct csched2_runqueue_data *rqd;
     struct csched2_vcpu * const scurr = csched2_vcpu(current);
     struct csched2_vcpu *snext = NULL;
-    unsigned int skipped_vcpus = 0;
     struct task_slice ret;
     bool tickled;
 
@@ -3534,7 +3524,7 @@ csched2_schedule(
         snext = csched2_vcpu(idle_vcpu[cpu]);
     }
     else
-        snext = runq_candidate(rqd, scurr, cpu, now, &skipped_vcpus);
+        snext = runq_candidate(rqd, scurr, cpu, now);
 
     /* If switching from a non-idle runnable vcpu, put it
      * back on the runqueue. */
@@ -3548,6 +3538,8 @@ csched2_schedule(
     /* Accounting for non-idle tasks */
     if ( !is_idle_vcpu(snext->vcpu) )
     {
+        int top_credit;
+
         /* If switching, remove this from the runqueue and mark it scheduled */
         if ( snext != scurr )
         {
@@ -3568,11 +3560,15 @@ csched2_schedule(
          *  2) no other vcpu with higher credits wants to run.
          *
          * Here, where we want to check for reset, we need to make sure the
-         * proper vcpu is being used. In fact, runqueue_candidate() may have
-         * not returned the first vcpu in the runqueue, for various reasons
+         * proper vcpu is being used. In fact, runq_candidate() may have not
+         * returned the first vcpu in the runqueue, for various reasons
          * (e.g., affinity). Only trigger a reset when it does.
          */
-        if ( skipped_vcpus == 0 && snext->credit <= CSCHED2_CREDIT_RESET )
+        if ( list_empty(&rqd->runq) )
+            top_credit = snext->credit;
+        else
+            top_credit = max(snext->credit, runq_elem(rqd->runq.next)->credit);
+        if ( top_credit <= CSCHED2_CREDIT_RESET )
         {
             reset_credit(ops, cpu, now, snext);
             balance_load(ops, cpu, now);