Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (29 commits)
  sched: Export account_system_vtime()
  sched: Call tick_check_idle before __irq_enter
  sched: Remove irq time from available CPU power
  sched: Do not account irq time to current task
  x86: Add IRQ_TIME_ACCOUNTING
  sched: Add IRQ_TIME_ACCOUNTING, finer accounting of irq time
  sched: Add a PF flag for ksoftirqd identification
  sched: Consolidate account_system_vtime extern declaration
  sched: Fix softirq time accounting
  sched: Drop group_capacity to 1 only if local group has extra capacity
  sched: Force balancing on newidle balance if local group has capacity
  sched: Set group_imb only a task can be pulled from the busiest cpu
  sched: Do not consider SCHED_IDLE tasks to be cache hot
  sched: Drop all load weight manipulation for RT tasks
  sched: Create special class for stop/migrate work
  sched: Unindent labels
  sched: Comment updates: fix default latency and granularity numbers
  tracing/sched: Add sched_pi_setprio tracepoint
  sched: Give CPU bound RT tasks preference
  sched: Try not to migrate higher priority RT tasks
  ...

4 files changed, 61 insertions, 6 deletions

diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 1f4517d55b19..96c323ac44df 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -64,6 +64,8 @@
 #define HARDIRQ_OFFSET  (1UL << HARDIRQ_SHIFT)
 #define NMI_OFFSET      (1UL << NMI_SHIFT)
 
+#define SOFTIRQ_DISABLE_OFFSET  (2 * SOFTIRQ_OFFSET)
+
 #ifndef PREEMPT_ACTIVE
 #define PREEMPT_ACTIVE_BITS     1
 #define PREEMPT_ACTIVE_SHIFT    (NMI_SHIFT + NMI_BITS)
@@ -82,10 +84,13 @@
 /*
  * Are we doing bottom half or hardware interrupt processing?
  * Are we in a softirq context? Interrupt context?
+ * in_softirq - Are we currently processing softirq or have bh disabled?
+ * in_serving_softirq - Are we currently processing softirq?
  */
 #define in_irq()                (hardirq_count())
 #define in_softirq()            (softirq_count())
 #define in_interrupt()          (irq_count())
+#define in_serving_softirq()    (softirq_count() & SOFTIRQ_OFFSET)
 
 /*
  * Are we in NMI context?
@@ -132,10 +137,12 @@ extern void synchronize_irq(unsigned int irq);
 
 struct task_struct;
 
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING)
 static inline void account_system_vtime(struct task_struct *tsk)
 {
 }
+#else
+extern void account_system_vtime(struct task_struct *tsk);
 #endif
 
 #if defined(CONFIG_NO_HZ)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 61b4ecf1da50..0383601a927c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -875,6 +875,7 @@ enum sched_domain_level {
         SD_LV_NONE = 0,
         SD_LV_SIBLING,
         SD_LV_MC,
+        SD_LV_BOOK,
         SD_LV_CPU,
         SD_LV_NODE,
         SD_LV_ALLNODES,
@@ -1690,8 +1691,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 /*
  * Per process flags
  */
-#define PF_ALIGNWARN    0x00000001      /* Print alignment warning msgs */
-                                        /* Not implemented yet, only for 486*/
+#define PF_KSOFTIRQD    0x00000001      /* I am ksoftirqd */
 #define PF_STARTING     0x00000002      /* being created */
 #define PF_EXITING      0x00000004      /* getting shut down */
 #define PF_EXITPIDONE   0x00000008      /* pi exit done on shut down */
@@ -1837,6 +1837,19 @@ extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
 #endif
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+/*
+ * An i/f to runtime opt-in for irq time accounting based off of sched_clock.
+ * The reason for this explicit opt-in is not to have perf penalty with
+ * slow sched_clocks.
+ */
+extern void enable_sched_clock_irqtime(void);
+extern void disable_sched_clock_irqtime(void);
+#else
+static inline void enable_sched_clock_irqtime(void) {}
+static inline void disable_sched_clock_irqtime(void) {}
+#endif
+
 extern unsigned long long
 task_sched_runtime(struct task_struct *task);
 extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
@@ -2378,9 +2391,9 @@ extern int __cond_resched_lock(spinlock_t *lock);
 
 extern int __cond_resched_softirq(void);
 
-#define cond_resched_softirq() ({                               \
-        __might_sleep(__FILE__, __LINE__, SOFTIRQ_OFFSET);      \
-        __cond_resched_softirq();                               \
+#define cond_resched_softirq() ({                                       \
+        __might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET);      \
+        __cond_resched_softirq();                                       \
 })
 
 /*
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 64e084ff5e5c..b91a40e847d2 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -201,6 +201,12 @@ int arch_update_cpu_topology(void);
         .balance_interval       = 64,                                   \
 }
 
+#ifdef CONFIG_SCHED_BOOK
+#ifndef SD_BOOK_INIT
+#error Please define an appropriate SD_BOOK_INIT in include/asm/topology.h!!!
+#endif
+#endif /* CONFIG_SCHED_BOOK */
+
 #ifdef CONFIG_NUMA
 #ifndef SD_NODE_INIT
 #error Please define an appropriate SD_NODE_INIT in include/asm/topology.h!!!
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 9208c92aeab5..f6334782a593 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -362,6 +362,35 @@ TRACE_EVENT(sched_stat_runtime,
                         (unsigned long long)__entry->vruntime)
 );
 
+/*
+ * Tracepoint for showing priority inheritance modifying a tasks
+ * priority.
+ */
+TRACE_EVENT(sched_pi_setprio,
+
+        TP_PROTO(struct task_struct *tsk, int newprio),
+
+        TP_ARGS(tsk, newprio),
+
+        TP_STRUCT__entry(
+                __array( char,  comm,   TASK_COMM_LEN   )
+                __field( pid_t, pid                     )
+                __field( int,   oldprio                 )
+                __field( int,   newprio                 )
+        ),
+
+        TP_fast_assign(
+                memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+                __entry->pid            = tsk->pid;
+                __entry->oldprio        = tsk->prio;
+                __entry->newprio        = newprio;
+        ),
+
+        TP_printk("comm=%s pid=%d oldprio=%d newprio=%d",
+                        __entry->comm, __entry->pid,
+                        __entry->oldprio, __entry->newprio)
+);
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */