Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched, x86: Avoid unnecessary overflow in sched_clock
  sched: Fix buglet in return_cfs_rq_runtime()
  sched: Avoid SMT siblings in select_idle_sibling() if possible
  sched: Set the command name of the idle tasks in SMP kernels
  sched, rt: Provide means of disabling cross-cpu bandwidth sharing
  sched: Document wait_for_completion_*() return values
  sched_fair: Fix a typo in the comment describing update_sd_lb_stats
  sched: Add a comment to effective_load() since it's a pain

4 files changed, 146 insertions, 34 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 0e9344a71be3..d6b149ccf925 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -71,6 +71,7 @@
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
 #include <linux/slab.h>
+#include <linux/init_task.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
@@ -4810,6 +4811,9 @@ EXPORT_SYMBOL(wait_for_completion);
  * This waits for either a completion of a specific task to be signaled or for a
  * specified timeout to expire. The timeout is in jiffies. It is not
  * interruptible.
+ *
+ * The return value is 0 if timed out, and positive (at least 1, or number of
+ * jiffies left till timeout) if completed.
  */
 unsigned long __sched
 wait_for_completion_timeout(struct completion *x, unsigned long timeout)
@@ -4824,6 +4828,8 @@ EXPORT_SYMBOL(wait_for_completion_timeout);
  *
  * This waits for completion of a specific task to be signaled. It is
  * interruptible.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if completed.
  */
 int __sched wait_for_completion_interruptible(struct completion *x)
 {
@@ -4841,6 +4847,9 @@ EXPORT_SYMBOL(wait_for_completion_interruptible);
  *
  * This waits for either a completion of a specific task to be signaled or for a
  * specified timeout to expire. It is interruptible. The timeout is in jiffies.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
+ * positive (at least 1, or number of jiffies left till timeout) if completed.
  */
 long __sched
 wait_for_completion_interruptible_timeout(struct completion *x,
@@ -4856,6 +4865,8 @@ EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
  *
  * This waits to be signaled for completion of a specific task. It can be
  * interrupted by a kill signal.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if completed.
  */
 int __sched wait_for_completion_killable(struct completion *x)
 {
@@ -4874,6 +4885,9 @@ EXPORT_SYMBOL(wait_for_completion_killable);
  * This waits for either a completion of a specific task to be
  * signaled or for a specified timeout to expire. It can be
  * interrupted by a kill signal. The timeout is in jiffies.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
+ * positive (at least 1, or number of jiffies left till timeout) if completed.
  */
 long __sched
 wait_for_completion_killable_timeout(struct completion *x,
@@ -6099,6 +6113,9 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
          */
         idle->sched_class = &idle_sched_class;
         ftrace_graph_init_idle_task(idle, cpu);
+#if defined(CONFIG_SMP)
+        sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
+#endif
 }
 
 /*
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5c9e67923b7c..a78ed2736ba7 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -772,19 +772,32 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
                 list_del_leaf_cfs_rq(cfs_rq);
 }
 
+static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
+{
+        long tg_weight;
+
+        /*
+         * Use this CPU's actual weight instead of the last load_contribution
+         * to gain a more accurate current total weight. See
+         * update_cfs_rq_load_contribution().
+         */
+        tg_weight = atomic_read(&tg->load_weight);
+        tg_weight -= cfs_rq->load_contribution;
+        tg_weight += cfs_rq->load.weight;
+
+        return tg_weight;
+}
+
 static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 {
-        long load_weight, load, shares;
+        long tg_weight, load, shares;
 
+        tg_weight = calc_tg_weight(tg, cfs_rq);
         load = cfs_rq->load.weight;
 
-        load_weight = atomic_read(&tg->load_weight);
-        load_weight += load;
-        load_weight -= cfs_rq->load_contribution;
-
         shares = (tg->shares * load);
-        if (load_weight)
-                shares /= load_weight;
+        if (tg_weight)
+                shares /= tg_weight;
 
         if (shares < MIN_SHARES)
                 shares = MIN_SHARES;
@@ -1743,7 +1756,7 @@ static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 {
-        if (!cfs_rq->runtime_enabled || !cfs_rq->nr_running)
+        if (!cfs_rq->runtime_enabled || cfs_rq->nr_running)
                 return;
 
         __return_cfs_rq_runtime(cfs_rq);
@@ -2036,36 +2049,100 @@ static void task_waking_fair(struct task_struct *p)
  * Adding load to a group doesn't make a group heavier, but can cause movement
  * of group shares between cpus. Assuming the shares were perfectly aligned one
  * can calculate the shift in shares.
+ *
+ * Calculate the effective load difference if @wl is added (subtracted) to @tg
+ * on this @cpu and results in a total addition (subtraction) of @wg to the
+ * total group weight.
+ *
+ * Given a runqueue weight distribution (rw_i) we can compute a shares
+ * distribution (s_i) using:
+ *
+ *   s_i = rw_i / \Sum rw_j                                             (1)
+ *
+ * Suppose we have 4 CPUs and our @tg is a direct child of the root group and
+ * has 7 equal weight tasks, distributed as below (rw_i), with the resulting
+ * shares distribution (s_i):
+ *
+ *   rw_i = {   2,   4,   1,   0 }
+ *   s_i  = { 2/7, 4/7, 1/7,   0 }
+ *
+ * As per wake_affine() we're interested in the load of two CPUs (the CPU the
+ * task used to run on and the CPU the waker is running on), we need to
+ * compute the effect of waking a task on either CPU and, in case of a sync
+ * wakeup, compute the effect of the current task going to sleep.
+ *
+ * So for a change of @wl to the local @cpu with an overall group weight change
+ * of @wl we can compute the new shares distribution (s'_i) using:
+ *
+ *   s'_i = (rw_i + @wl) / (@wg + \Sum rw_j)                            (2)
+ *
+ * Suppose we're interested in CPUs 0 and 1, and want to compute the load
+ * differences in waking a task to CPU 0. The additional task changes the
+ * weight and shares distributions like:
+ *
+ *   rw'_i = {   3,   4,   1,   0 }
+ *   s'_i  = { 3/8, 4/8, 1/8,   0 }
+ *
+ * We can then compute the difference in effective weight by using:
+ *
+ *   dw_i = S * (s'_i - s_i)                                            (3)
+ *
+ * Where 'S' is the group weight as seen by its parent.
+ *
+ * Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7)
+ * times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 -
+ * 4/7) times the weight of the group.