15 files changed, 104 insertions, 63 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index b017887d632f..7bb63eea6eb8 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -302,10 +302,10 @@ static void guarantee_online_cpus(const struct cpuset *cs,
  * are online, with memory.  If none are online with memory, walk
  * up the cpuset hierarchy until we find one that does have some
  * online mems.  If we get all the way to the top and still haven't
- * found any online mems, return node_states[N_HIGH_MEMORY].
+ * found any online mems, return node_states[N_MEMORY].
  *
  * One way or another, we guarantee to return some non-empty subset
- * of node_states[N_HIGH_MEMORY].
+ * of node_states[N_MEMORY].
  *
  * Call with callback_mutex held.
  */
@@ -313,14 +313,14 @@ static void guarantee_online_cpus(const struct cpuset *cs,
 static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask)
 {
         while (cs && !nodes_intersects(cs->mems_allowed,
-                                        node_states[N_HIGH_MEMORY]))
+                                        node_states[N_MEMORY]))
                 cs = cs->parent;
         if (cs)
                 nodes_and(*pmask, cs->mems_allowed,
-                                        node_states[N_HIGH_MEMORY]);
+                                        node_states[N_MEMORY]);
         else
-                *pmask = node_states[N_HIGH_MEMORY];
-        BUG_ON(!nodes_intersects(*pmask, node_states[N_HIGH_MEMORY]));
+                *pmask = node_states[N_MEMORY];
+        BUG_ON(!nodes_intersects(*pmask, node_states[N_MEMORY]));
 }
 
 /*
@@ -1100,7 +1100,7 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
                 return -ENOMEM;
 
         /*
-         * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY];
+         * top_cpuset.mems_allowed tracks node_stats[N_MEMORY];
          * it's read-only
          */
         if (cs == &top_cpuset) {
@@ -1122,7 +1122,7 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
                         goto done;
 
                 if (!nodes_subset(trialcs->mems_allowed,
-                                node_states[N_HIGH_MEMORY])) {
+                                node_states[N_MEMORY])) {
                         retval =  -EINVAL;
                         goto done;
                 }
@@ -2026,7 +2026,7 @@ static struct cpuset *cpuset_next(struct list_head *queue)
  * before dropping down to the next.  It always processes a node before
  * any of its children.
  *
- * In the case of memory hot-unplug, it will remove nodes from N_HIGH_MEMORY
+ * In the case of memory hot-unplug, it will remove nodes from N_MEMORY
  * if all present pages from a node are offlined.
  */
 static void
@@ -2065,7 +2065,7 @@ scan_cpusets_upon_hotplug(struct cpuset *root, enum hotplug_event event)
 
                         /* Continue past cpusets with all mems online */
                         if (nodes_subset(cp->mems_allowed,
-                                        node_states[N_HIGH_MEMORY]))
+                                        node_states[N_MEMORY]))
                                 continue;
 
                         oldmems = cp->mems_allowed;
@@ -2073,7 +2073,7 @@ scan_cpusets_upon_hotplug(struct cpuset *root, enum hotplug_event event)
                         /* Remove offline mems from this cpuset. */
                         mutex_lock(&callback_mutex);
                         nodes_and(cp->mems_allowed, cp->mems_allowed,
-                                                node_states[N_HIGH_MEMORY]);
+                                                node_states[N_MEMORY]);
                         mutex_unlock(&callback_mutex);
 
                         /* Move tasks from the empty cpuset to a parent */
@@ -2126,8 +2126,8 @@ void cpuset_update_active_cpus(bool cpu_online)
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
- * Keep top_cpuset.mems_allowed tracking node_states[N_HIGH_MEMORY].
- * Call this routine anytime after node_states[N_HIGH_MEMORY] changes.
+ * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY].
+ * Call this routine anytime after node_states[N_MEMORY] changes.
  * See cpuset_update_active_cpus() for CPU hotplug handling.
  */
 static int cpuset_track_online_nodes(struct notifier_block *self,
@@ -2140,7 +2140,7 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
         case MEM_ONLINE:
                 oldmems = top_cpuset.mems_allowed;
                 mutex_lock(&callback_mutex);
-                top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
+                top_cpuset.mems_allowed = node_states[N_MEMORY];
                 mutex_unlock(&callback_mutex);
                 update_tasks_nodemask(&top_cpuset, &oldmems, NULL);
                 break;
@@ -2169,7 +2169,7 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
 void __init cpuset_init_smp(void)
 {
         cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
-        top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
+        top_cpuset.mems_allowed = node_states[N_MEMORY];
 
         hotplug_memory_notifier(cpuset_track_online_nodes, 10);
 
@@ -2237,7 +2237,7 @@ void cpuset_init_current_mems_allowed(void)
  *
  * Description: Returns the nodemask_t mems_allowed of the cpuset
  * attached to the specified @tsk.  Guaranteed to return some non-empty
- * subset of node_states[N_HIGH_MEMORY], even if this means going outside the
+ * subset of node_states[N_MEMORY], even if this means going outside the
  * tasks cpuset.
  **/
 
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 29fb60caecb5..691dc2ef9baf 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -428,7 +428,7 @@ int kthreadd(void *unused)
         set_task_comm(tsk, "kthreadd");
         ignore_signals(tsk);
         set_cpus_allowed_ptr(tsk, cpu_all_mask);
-        set_mems_allowed(node_states[N_HIGH_MEMORY]);
+        set_mems_allowed(node_states[N_MEMORY]);
 
         current->flags |= PF_NOFREEZE;
 
diff --git a/kernel/padata.c b/kernel/padata.c
index 89fe3d1b9efb..072f4ee4eb89 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -171,7 +171,7 @@ static struct padata_priv *padata_get_next(struct parallel_data *pd)
 {
         int cpu, num_cpus;
         unsigned int next_nr, next_index;
-        struct padata_parallel_queue *queue, *next_queue;
+        struct padata_parallel_queue *next_queue;
         struct padata_priv *padata;
         struct padata_list *reorder;
 
@@ -204,8 +204,7 @@ static struct padata_priv *padata_get_next(struct parallel_data *pd)
                 goto out;
         }
 
-        queue = per_cpu_ptr(pd->pqueue, smp_processor_id());
-        if (queue->cpu_index == next_queue->cpu_index) {
+        if (__this_cpu_read(pd->pqueue->cpu_index) == next_queue->cpu_index) {
                 padata = ERR_PTR(-ENODATA);
                 goto out;
         }
diff --git a/kernel/pid.c b/kernel/pid.c
index aebd4f5aaf41..fd996c1ed9f8 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -1,8 +1,8 @@
 /*
  * Generic pidhash and scalable, time-bounded PID allocator
  *
- * (C) 2002-2003 William Irwin, IBM
- * (C) 2004 William Irwin, Oracle
+ * (C) 2002-2003 Nadia Yvette Chambers, IBM
+ * (C) 2004 Nadia Yvette Chambers, Oracle
  * (C) 2002-2004 Ingo Molnar, Red Hat
  *
  * pid-structures are backing objects for tasks sharing a given ID to chain
diff --git a/kernel/profile.c b/kernel/profile.c
index 76b8e77773ee..1f391819c42f 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -8,9 +8,10 @@
  *  Scheduler profiling support, Arjan van de Ven and Ingo Molnar,
  *      Red Hat, July 2004
  *  Consolidation of architecture support code for profiling,
- *      William Irwin, Oracle, July 2004
+ *      Nadia Yvette Chambers, Oracle, July 2004
  *  Amortized hit count accounting via per-cpu open-addressed hashtables
- *      to resolve timer interrupt livelocks, William Irwin, Oracle, 2004
+ *      to resolve timer interrupt livelocks, Nadia Yvette Chambers,
+ *      Oracle, 2004
  */
 
 #include <linux/export.h>
@@ -256,7 +257,7 @@ EXPORT_SYMBOL_GPL(unregister_timer_hook);
  * pagetable hash functions, but uses a full hashtable full of finite
  * collision chains, not just pairs of them.
  *
- * -- wli
+ * -- nyc
  */
 static void __profile_flip_buffers(void *unused)
 {
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index ad581aa2369a..3920d593e63c 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -192,25 +192,3 @@ int res_counter_memparse_write_strategy(const char *buf,
         *res = PAGE_ALIGN(*res);
         return 0;
 }
-
-int res_counter_write(struct res_counter *counter, int member,
-                      const char *buf, write_strategy_fn write_strategy)
-{
-        char *end;
-        unsigned long flags;
-        unsigned long long tmp, *val;
-
-        if (write_strategy) {
-                if (write_strategy(buf, &tmp))
-                        return -EINVAL;
-        } else {
-                tmp = simple_strtoull(buf, &end, 10);
-                if (*end != '\0')
-                        return -EINVAL;
-        }
-        spin_lock_irqsave(&counter->lock, flags);
-        val = res_counter_member(counter, member);
-        *val = tmp;
-        spin_unlock_irqrestore(&counter->lock, flags);
-        return 0;
-}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6271b89f87ac..0533496b6228 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -923,6 +923,13 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
                 rq->skip_clock_update = 1;
 }
 
+static ATOMIC_NOTIFIER_HEAD(task_migration_notifier);
+
+void register_task_migration_notifier(struct notifier_block *n)
+{
+        atomic_notifier_chain_register(&task_migration_notifier, n);
+}
+
 #ifdef CONFIG_SMP
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
@@ -953,10 +960,18 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
         trace_sched_migrate_task(p, new_cpu);
 
         if (task_cpu(p) != new_cpu) {
+                struct task_migration_notifier tmn;
+
                 if (p->sched_class->migrate_task_rq)
                         p->sched_class->migrate_task_rq(p, new_cpu);
                 p->se.nr_migrations++;
                 perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
+
+                tmn.task = p;
+                tmn.from_cpu = task_cpu(p);
+                tmn.to_cpu = new_cpu;
+
+                atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn);
         }
 
         __set_task_cpu(p, new_cpu);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 59e072b2db97..756f9f9e8542 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1265,7 +1265,6 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
         }
 
         __update_cfs_rq_tg_load_contrib(cfs_rq, force_update);
-        update_cfs_shares(cfs_rq);
 }
 
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
@@ -1475,8 +1474,9 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
          * Update run-time statistics of the 'current'.
          */
         update_curr(cfs_rq);
-        account_entity_enqueue(cfs_rq, se);
         enqueue_entity_load_avg(cfs_rq, se, flags & ENQUEUE_WAKEUP);
+        account_entity_enqueue(cfs_rq, se);
+        update_cfs_shares(cfs_rq);
 
         if (flags & ENQUEUE_WAKEUP) {
                 place_entity(cfs_rq, se, 0);
@@ -1549,6 +1549,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
          * Update run-time statistics of the 'current'.
          */
         update_curr(cfs_rq);
+        dequeue_entity_load_avg(cfs_rq, se, flags & DEQUEUE_SLEEP);
 
         update_stats_dequeue(cfs_rq, se);
         if (flags & DEQUEUE_SLEEP) {
@@ -1568,8 +1569,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
         if (se != cfs_rq->curr)
                 __dequeue_entity(cfs_rq, se);
+        se->on_rq = 0;
         account_entity_dequeue(cfs_rq, se);
-        dequeue_entity_load_avg(cfs_rq, se, flags & DEQUEUE_SLEEP);
 
         /*
          * Normalize the entity after updating the min_vruntime because the
@@ -1583,7 +1584,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
         return_cfs_rq_runtime(cfs_rq);
 
         update_min_vruntime(cfs_rq);
-        se->on_rq = 0;
+        update_cfs_shares(cfs_rq);
 }
 
 /*
@@ -2595,8 +2596,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
                 if (cfs_rq_throttled(cfs_rq))
                         break;
 
+                update_cfs_shares(cfs_rq);
                 update_entity_load_avg(se, 1);
-                update_cfs_rq_blocked_load(cfs_rq, 0);
         }
 
         if (!se) {
@@ -2656,8 +2657,8 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
                 if (cfs_rq_throttled(cfs_rq))
                         break;
 
+                update_cfs_shares(cfs_rq);
                 update_entity_load_avg(se, 1);
-                update_cfs_rq_blocked_load(cfs_rq, 0);
         }
 
         if (!se) {
@@ -5837,11 +5838,8 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
                 se = tg->se[i];
                 /* Propagate contribution to hierarchy */
                 raw_spin_lock_irqsave(&rq->lock, flags);
-                for_each_sched_entity(se) {
+                for_each_sched_entity(se)
                         update_cfs_shares(group_cfs_rq(se));
-                        /* update contribution to parent */
-                        update_entity_load_avg(se, 1);
-                }
                 raw_spin_unlock_irqrestore(&rq->lock, flags);
         }
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 4c7de02eacdc..cbc6acb0db3f 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -21,6 +21,7 @@
 #include <linux/time.h>
 #include <linux/tick.h>
 #include <linux/stop_machine.h>
+#include <linux/pvclock_gtod.h>
 
 
 static struct timekeeper timekeeper;
@@ -174,6 +175,54 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
         return nsec + arch_gettimeoffset();
 }
 
+static RAW_NOTIFIER_HEAD(pvclock_gtod_chain);
+
+static void update_pvclock_gtod(struct timekeeper *tk)
+{
+        raw_notifier_call_chain(&pvclock_gtod_chain, 0, tk);
+}
+
+/**
+ * pvclock_gtod_register_notifier - register a pvclock timedata update listener
+ *
+ * Must hold write on timekeeper.lock
+ */
+int pvclock_gtod_register_notifier(struct notifier_block *nb)
+{
+        struct timekeeper *tk = &timekeeper;
+        unsigned long flags;
+        int ret;
+
+        write_seqlock_irqsave(&tk->lock, flags);
+        ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb);
+        /* update timekeeping data */
+        update_pvclock_gtod(tk);
+        write_sequnlock_irqrestore(&tk->lock, flags);
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier);
+
+/**
+ * pvclock_gtod_unregister_notifier - unregister a pvclock
+ * timedata update listener
+ *
+ * Must hold write on timekeeper.lock
+ */
+int pvclock_gtod_unregister_notifier(struct notifier_block *nb)
+{
+        struct timekeeper *tk = &timekeeper;
+        unsigned long flags;
+        int ret;
+
+        write_seqlock_irqsave(&tk->lock, flags);
+        ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb);
+        write_sequnlock_irqrestore(&tk->lock, flags);
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);
+
 /* must hold write on timekeeper.lock */
 static void timekeeping_update(struct timekeeper *tk, bool clearntp)
 {
@@ -182,6 +231,7 @@ static void timekeeping_update(struct timekeeper *tk, bool clearntp)
                 ntp_clear();
         }
         update_vsyscall(tk);
+        update_pvclock_gtod(tk);
 }
 
 /**
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 7693aaf324c6..afd092de45b7 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -10,7 +10,7 @@
  * Based on code in the latency_tracer, that is:
  *
  *  Copyright (C) 2004-2006 Ingo Molnar
- *  Copyright (C) 2004 William Lee Irwin III
+ *  Copyright (C) 2004 Nadia Yvette Chambers
  */
 
 #include <linux/stop_machine.h>
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index b69cc380322d..61e081b4ba11 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9,7 +9,7 @@
  *
  * Based on code from the latency_tracer, that is:
  *  Copyright (C) 2004-2006 Ingo Molnar
- *  Copyright (C) 2004 William Lee Irwin III
+ *  Copyright (C) 2004 Nadia Yvette Chambers
  */
 #include <linux/ring_buffer.h>
 #include <generated/utsrelease.h>
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index bb227e380cb5..8e3ad8082ab7 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -7,7 +7,7 @@
  * Based on code from the latency_tracer, that is:
  *
  *  Copyright (C) 2004-2006 Ingo Molnar
- *  Copyright (C) 2004 William Lee Irwin III
+ *  Copyright (C) 2004 Nadia Yvette Chambers
  */
 #include <linux/ring_buffer.h>
 #include <linux/debugfs.h>
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 5ffce7b0f33c..713a2cac4881 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -7,7 +7,7 @@
  * From code in the latency_tracer, that is:
  *
  *  Copyright (C) 2004-2006 Ingo Molnar
- *  Copyright (C) 2004 William Lee Irwin III
+ *  Copyright (C) 2004 Nadia Yvette Chambers
  */
 #include <linux/kallsyms.h>
 #include <linux/debugfs.h>
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index bc64fc137554..9fe45fcefca0 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -7,7 +7,7 @@
  * Based on code from the latency_tracer, that is:
  *
  *  Copyright (C) 2004-2006 Ingo Molnar
- *  Copyright (C) 2004 William Lee Irwin III
+ *  Copyright (C) 2004 Nadia Yvette Chambers
  */
 #include <linux/module.h>
 #include <linux/fs.h>
diff --git a/kernel/wait.c b/kernel/wait.c
index 7fdd9eaca2c3..6698e0c04ead 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -1,7 +1,7 @@
 /*
  * Generic waiting primitives.
  *
- * (C) 2004 William Irwin, Oracle
+ * (C) 2004 Nadia Yvette Chambers, Oracle
  */
 #include <linux/init.h>
 #include <linux/export.h>