Merge branches 'core-urgent-for-linus', 'perf-urgent-for-linus' and 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  debugobjects: Fix boot crash when kmemleak and debugobjects enabled

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  jump_label: Fix jump_label update for modules
  oprofile, x86: Fix race in nmi handler while starting counters

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  sched: Disable (revert) SCHED_LOAD_SCALE increase
  sched, cgroups: Fix MIN_SHARES on 64-bit boxen

arch/x86/oprofile/nmi_int.c

@@ -112,8 +112,10 @@ static void nmi_cpu_start(void *dummy)
 static int nmi_start(void)
 {
 	get_online_cpus();
-	on_each_cpu(nmi_cpu_start, NULL, 1);
 	ctr_running = 1;
+	/* make ctr_running visible to the nmi handler: */
+	smp_mb();
+	on_each_cpu(nmi_cpu_start, NULL, 1);
 	put_online_cpus();
 	return 0;
 }
@@ -504,15 +506,18 @@ static int nmi_setup(void)
 
 	nmi_enabled = 0;
 	ctr_running = 0;
-	barrier();
+	/* make variables visible to the nmi handler: */
+	smp_mb();
 	err = register_die_notifier(&profile_exceptions_nb);
 	if (err)
 		goto fail;
 
 	get_online_cpus();
 	register_cpu_notifier(&oprofile_cpu_nb);
-	on_each_cpu(nmi_cpu_setup, NULL, 1);
 	nmi_enabled = 1;
+	/* make nmi_enabled visible to the nmi handler: */
+	smp_mb();
+	on_each_cpu(nmi_cpu_setup, NULL, 1);
 	put_online_cpus();
 
 	return 0;
@@ -531,7 +536,8 @@ static void nmi_shutdown(void)
 	nmi_enabled = 0;
 	ctr_running = 0;
 	put_online_cpus();
-	barrier();
+	/* make variables visible to the nmi handler: */
+	smp_mb();
 	unregister_die_notifier(&profile_exceptions_nb);
 	msrs = &get_cpu_var(cpu_msrs);
 	model->shutdown(msrs);

include/linux/sched.h

@@ -808,7 +808,7 @@ enum cpu_idle_type {
  * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the
  * increased costs.
  */
-#if BITS_PER_LONG > 32
+#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load  */
 # define SCHED_LOAD_RESOLUTION	10
 # define scale_load(w)		((w) << SCHED_LOAD_RESOLUTION)
 # define scale_load_down(w)	((w) >> SCHED_LOAD_RESOLUTION)

kernel/jump_label.c

@@ -375,15 +375,19 @@ int jump_label_text_reserved(void *start, void *end)
 
 static void jump_label_update(struct jump_label_key *key, int enable)
 {
-	struct jump_entry *entry = key->entries;
-
-	/* if there are no users, entry can be NULL */
-	if (entry)
-		__jump_label_update(key, entry, __stop___jump_table, enable);
+	struct jump_entry *entry = key->entries, *stop = __stop___jump_table;
 
 #ifdef CONFIG_MODULES
+	struct module *mod = __module_address((jump_label_t)key);
+
 	__jump_label_mod_update(key, enable);
+
+	if (mod)
+		stop = mod->jump_entries + mod->num_jump_entries;
 #endif
+	/* if there are no users, entry can be NULL */
+	if (entry)
+		__jump_label_update(key, entry, stop, enable);
 }
 
 #endif

kernel/sched.c

@@ -292,8 +292,8 @@ static DEFINE_SPINLOCK(task_group_lock);
  * (The default weight is 1024 - so there's no practical
  *  limitation from this.)
  */
-#define MIN_SHARES	2
-#define MAX_SHARES	(1UL << (18 + SCHED_LOAD_RESOLUTION))
+#define MIN_SHARES	(1UL <<  1)
+#define MAX_SHARES	(1UL << 18)
 
 static int root_task_group_load = ROOT_TASK_GROUP_LOAD;
 #endif
@@ -8450,10 +8450,7 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 	if (!tg->se[0])
 		return -EINVAL;
 
-	if (shares < MIN_SHARES)
-		shares = MIN_SHARES;
-	else if (shares > MAX_SHARES)
-		shares = MAX_SHARES;
+	shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES));
 
 	mutex_lock(&shares_mutex);
 	if (tg->shares == shares)

lib/debugobjects.c

@@ -198,7 +198,7 @@ static void free_object(struct debug_obj *obj)
 	 * initialized:
 	 */
 	if (obj_pool_free > ODEBUG_POOL_SIZE && obj_cache)
-		sched = !work_pending(&debug_obj_work);
+		sched = keventd_up() && !work_pending(&debug_obj_work);
 	hlist_add_head(&obj->node, &obj_pool);
 	obj_pool_free++;
 	obj_pool_used--;