12 files changed, 336 insertions, 249 deletions

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 4badde179b18..f560325c444f 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -134,13 +134,16 @@ static inline void task_name(struct seq_file *m, struct task_struct *p)
  * simple bit tests.
  */
 static const char *task_state_array[] = {
-        "R (running)",          /*  0 */
-        "S (sleeping)",         /*  1 */
-        "D (disk sleep)",       /*  2 */
-        "T (stopped)",          /*  4 */
-        "T (tracing stop)",     /*  8 */
-        "Z (zombie)",           /* 16 */
-        "X (dead)"              /* 32 */
+        "R (running)",          /*   0 */
+        "S (sleeping)",         /*   1 */
+        "D (disk sleep)",       /*   2 */
+        "T (stopped)",          /*   4 */
+        "t (tracing stop)",     /*   8 */
+        "Z (zombie)",           /*  16 */
+        "X (dead)",             /*  32 */
+        "x (dead)",             /*  64 */
+        "K (wakekill)",         /* 128 */
+        "W (waking)",           /* 256 */
 };
 
 static inline const char *get_task_state(struct task_struct *tsk)
@@ -148,6 +151,8 @@ static inline const char *get_task_state(struct task_struct *tsk)
         unsigned int state = (tsk->state & TASK_REPORT) | tsk->exit_state;
         const char **p = &task_state_array[0];
 
+        BUILD_BUG_ON(1 + ilog2(TASK_STATE_MAX) != ARRAY_SIZE(task_state_array));
+
         while (state) {
                 p++;
                 state >>= 1;
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index c4ba9a78721e..96cc307ed9f4 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -101,4 +101,9 @@ static inline void exit_rcu(void)
 {
 }
 
+static inline int rcu_preempt_depth(void)
+{
+        return 0;
+}
+
 #endif /* __LINUX_RCUTINY_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index c93eee5911b0..8044b1b94333 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -45,6 +45,12 @@ extern void __rcu_read_unlock(void);
 extern void synchronize_rcu(void);
 extern void exit_rcu(void);
 
+/*
+ * Defined as macro as it is a very low level header
+ * included from areas that don't even know about current
+ */
+#define rcu_preempt_depth() (current->rcu_read_lock_nesting)
+
 #else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
 static inline void __rcu_read_lock(void)
@@ -63,6 +69,11 @@ static inline void exit_rcu(void)
 {
 }
 
+static inline int rcu_preempt_depth(void)
+{
+        return 0;
+}
+
 #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
 
 static inline void __rcu_read_lock_bh(void)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e89857812be6..f2f842db03ce 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -192,6 +192,12 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 #define TASK_DEAD               64
 #define TASK_WAKEKILL           128
 #define TASK_WAKING             256
+#define TASK_STATE_MAX          512
+
+#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW"
+
+extern char ___assert_task_state[1 - 2*!!(
+                sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
 
 /* Convenience macros for the sake of set_task_state */
 #define TASK_KILLABLE           (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
@@ -1091,7 +1097,8 @@ struct sched_class {
                               enum cpu_idle_type idle);
         void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
         void (*post_schedule) (struct rq *this_rq);
-        void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
+        void (*task_waking) (struct rq *this_rq, struct task_struct *task);
+        void (*task_woken) (struct rq *this_rq, struct task_struct *task);
 
         void (*set_cpus_allowed)(struct task_struct *p,
                                  const struct cpumask *newmask);
@@ -1115,7 +1122,7 @@ struct sched_class {
                                          struct task_struct *task);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-        void (*moved_group) (struct task_struct *p);
+        void (*moved_group) (struct task_struct *p, int on_rq);
 #endif
 };
 
@@ -2594,8 +2601,6 @@ static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
 }
 #endif /* CONFIG_MM_OWNER */
 
-#define TASK_STATE_TO_CHAR_STR "RSDTtZX"
-
 #endif /* __KERNEL__ */
 
 #endif
diff --git a/init/main.c b/init/main.c
index c3db4a98b369..dac44a9356a5 100644
--- a/init/main.c
+++ b/init/main.c
@@ -369,12 +369,6 @@ static void __init smp_init(void)
 {
         unsigned int cpu;
 
-        /*
-         * Set up the current CPU as possible to migrate to.
-         * The other ones will be done by cpu_up/cpu_down()
-         */
-        set_cpu_active(smp_processor_id(), true);
-
         /* FIXME: This should be done in userspace --RR */
         for_each_present_cpu(cpu) {
                 if (num_online_cpus() >= setup_max_cpus)
@@ -486,6 +480,7 @@ static void __init boot_cpu_init(void)
         int cpu = smp_processor_id();
         /* Mark the boot cpu "present", "online" etc for SMP and UP case */
         set_cpu_online(cpu, true);
+        set_cpu_active(cpu, true);
         set_cpu_present(cpu, true);
         set_cpu_possible(cpu, true);
 }
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 291ac586f37f..1c8ddd6ee940 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -209,6 +209,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
                 return -ENOMEM;
 
         cpu_hotplug_begin();
+        set_cpu_active(cpu, false);
         err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
                                         hcpu, -1, &nr_calls);
         if (err == NOTIFY_BAD) {
@@ -280,18 +281,6 @@ int __ref cpu_down(unsigned int cpu)
                 goto out;
         }
 
-        set_cpu_active(cpu, false);
-
-        /*
-         * Make sure the all cpus did the reschedule and are not
-         * using stale version of the cpu_active_mask.
-         * This is not strictly necessary becuase stop_machine()
-         * that we run down the line already provides the required
-         * synchronization. But it's really a side effect and we do not
-         * want to depend on the innards of the stop_machine here.
-         */
-        synchronize_sched();
-
         err = _cpu_down(cpu, 0);
 
 out:
@@ -382,19 +371,12 @@ int disable_nonboot_cpus(void)
                 return error;
         cpu_maps_update_begin();
         first_cpu = cpumask_first(cpu_online_mask);
-        /* We take down all of the non-boot CPUs in one shot to avoid races
+        /*
+         * We take down all of the non-boot CPUs in one shot to avoid races
          * with the userspace trying to use the CPU hotplug at the same time