workqueue: schedule WORK_CPU_UNBOUND work on wq_unbound_cpumask CPUs

WORK_CPU_UNBOUND work items queued to a bound workqueue always run
locally.  This is a good thing normally, but not when the user has
asked us to keep unbound work away from certain CPUs.  Round robin
these to wq_unbound_cpumask CPUs instead, as perturbation avoidance
trumps performance.

tj: Cosmetic and comment changes.  WARN_ON_ONCE() dropped from empty
    (wq_unbound_cpumask AND cpu_online_mask).  If we want that, it
    should be done when config changes.

Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 5e63d3b..0547746 100644 (file)
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -301,7 +301,11 @@ static DEFINE_SPINLOCK(wq_mayday_lock);    /* protects wq->maydays list */
 static LIST_HEAD(workqueues);          /* PR: list of all workqueues */
 static bool workqueue_freezing;                /* PL: have wqs started freezing? */
 
-static cpumask_var_t wq_unbound_cpumask; /* PL: low level cpumask for all unbound wqs */
+/* PL: allowable cpus for unbound wqs and work items */
+static cpumask_var_t wq_unbound_cpumask;
+
+/* CPU where unbound work was last round robin scheduled from this CPU */
+static DEFINE_PER_CPU(int, wq_rr_cpu_last);
 
 /* the per-cpu worker pools */
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS],
@@ -1298,6 +1302,32 @@ static bool is_chained_work(struct workqueue_struct *wq)
        return worker && worker->current_pwq->wq == wq;
 }
 
+/*
+ * When queueing an unbound work item to a wq, prefer local CPU if allowed
+ * by wq_unbound_cpumask.  Otherwise, round robin among the allowed ones to
+ * avoid perturbing sensitive tasks.
+ */
+static int wq_select_unbound_cpu(int cpu)
+{
+       int new_cpu;
+
+       if (cpumask_test_cpu(cpu, wq_unbound_cpumask))
+               return cpu;
+       if (cpumask_empty(wq_unbound_cpumask))
+               return cpu;
+
+       new_cpu = __this_cpu_read(wq_rr_cpu_last);
+       new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask);
+       if (unlikely(new_cpu >= nr_cpu_ids)) {
+               new_cpu = cpumask_first_and(wq_unbound_cpumask, cpu_online_mask);
+               if (unlikely(new_cpu >= nr_cpu_ids))
+                       return cpu;
+       }
+       __this_cpu_write(wq_rr_cpu_last, new_cpu);
+
+       return new_cpu;
+}
+
 static void __queue_work(int cpu, struct workqueue_struct *wq,
                         struct work_struct *work)
 {
@@ -1323,7 +1353,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
                return;
 retry:
        if (req_cpu == WORK_CPU_UNBOUND)
-               cpu = raw_smp_processor_id();
+               cpu = wq_select_unbound_cpu(raw_smp_processor_id());
 
        /* pwq which will be used unless @work is executing elsewhere */
        if (!(wq->flags & WQ_UNBOUND))