Merge branch 'for-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq

Pull workqueue changes from Tejun Heo:
 "Surprisingly, Lai and I didn't break too many things implementing
  custom pools and stuff last time around and there aren't any follow-up
  changes necessary at this point.

  The only change in this pull request is Viresh's patches to make some
  per-cpu workqueues to behave as unbound workqueues dependent on a boot
  param whose default can be configured via a config option.  This leads
  to higher processing overhead / lower bandwidth as more work items are
  bounced across CPUs; however, it can lead to noticeable powersave in
  certain configurations - ~10% w/ idlish constant workload on a
  big.LITTLE configuration according to Viresh.

  This is because per-cpu workqueues interfere with how the scheduler
  perceives whether or not each CPU is idle by forcing pinned tasks on
  them, which makes the scheduler's power-aware scheduling decisions
  less effective.

  Its effectiveness is likely less pronounced on homogenous
  configurations and this type of optimization can probably be made
  automatic; however, the changes are pretty minimal and the affected
  workqueues are clearly marked, so it's an easy gain for some
  configurations for the time being with pretty unintrusive changes."

* 'for-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
  fbcon: queue work on power efficient wq
  block: queue work on power efficient wq
  PHYLIB: queue work on system_power_efficient_wq
  workqueue: Add system wide power_efficient workqueues
  workqueues: Introduce new flag WQ_POWER_EFFICIENT for power oriented workqueues

2 files changed, 45 insertions, 1 deletions

diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 9c39de095ba9..d444c4e834f4 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -262,6 +262,26 @@ config PM_GENERIC_DOMAINS
         bool
         depends on PM
 
+config WQ_POWER_EFFICIENT_DEFAULT
+        bool "Enable workqueue power-efficient mode by default"
+        depends on PM
+        default n
+        help
+          Per-cpu workqueues are generally preferred because they show
+          better performance thanks to cache locality; unfortunately,
+          per-cpu workqueues tend to be more power hungry than unbound
+          workqueues.
+
+          Enabling workqueue.power_efficient kernel parameter makes the
+          per-cpu workqueues which were observed to contribute
+          significantly to power consumption unbound, leading to measurably
+          lower power usage at the cost of small performance overhead.
+
+          This config option determines whether workqueue.power_efficient
+          is enabled by default.
+
+          If in doubt, say N.
+
 config PM_GENERIC_DOMAINS_SLEEP
         def_bool y
         depends on PM_SLEEP && PM_GENERIC_DOMAINS
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ee8e29a2320c..f02c4a4a0c3c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -272,6 +272,15 @@ static cpumask_var_t *wq_numa_possible_cpumask;
 static bool wq_disable_numa;
 module_param_named(disable_numa, wq_disable_numa, bool, 0444);
 
+/* see the comment above the definition of WQ_POWER_EFFICIENT */
+#ifdef CONFIG_WQ_POWER_EFFICIENT_DEFAULT
+static bool wq_power_efficient = true;
+#else
+static bool wq_power_efficient;
+#endif
+
+module_param_named(power_efficient, wq_power_efficient, bool, 0444);
+
 static bool wq_numa_enabled;            /* unbound NUMA affinity enabled */
 
 /* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */
@@ -305,6 +314,10 @@ struct workqueue_struct *system_unbound_wq __read_mostly;
 EXPORT_SYMBOL_GPL(system_unbound_wq);
 struct workqueue_struct *system_freezable_wq __read_mostly;
 EXPORT_SYMBOL_GPL(system_freezable_wq);
+struct workqueue_struct *system_power_efficient_wq __read_mostly;
+EXPORT_SYMBOL_GPL(system_power_efficient_wq);
+struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly;
+EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq);
 
 static int worker_thread(void *__worker);
 static void copy_workqueue_attrs(struct workqueue_attrs *to,
@@ -4086,6 +4099,10 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
         struct workqueue_struct *wq;
         struct pool_workqueue *pwq;
 
+        /* see the comment above the definition of WQ_POWER_EFFICIENT */
+        if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
+                flags |= WQ_UNBOUND;
+
         /* allocate wq and format name */
         if (flags & WQ_UNBOUND)
                 tbl_size = wq_numa_tbl_len * sizeof(wq->numa_pwq_tbl[0]);
@@ -4985,8 +5002,15 @@ static int __init init_workqueues(void)
                                             WQ_UNBOUND_MAX_ACTIVE);
         system_freezable_wq = alloc_workqueue("events_freezable",
                                               WQ_FREEZABLE, 0);
+        system_power_efficient_wq = alloc_workqueue("events_power_efficient",
+                                              WQ_POWER_EFFICIENT, 0);
+        system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient",
+                                              WQ_FREEZABLE | WQ_POWER_EFFICIENT,
+                                              0);
         BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq ||
-               !system_unbound_wq || !system_freezable_wq);
+               !system_unbound_wq || !system_freezable_wq ||
+               !system_power_efficient_wq ||
+               !system_freezable_power_efficient_wq);
         return 0;
 }
 early_initcall(init_workqueues);