Merge branch 'fixes-modulesplit' into fixes

82 files changed, 225 insertions, 190 deletions

diff --git a/kernel/async.c b/kernel/async.c
index 4c2843c0043e..80b74b88fefe 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -51,7 +51,7 @@ asynchronous and synchronous parts of the kernel.
 #include <linux/async.h>
 #include <linux/atomic.h>
 #include <linux/ktime.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/wait.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
diff --git a/kernel/audit.c b/kernel/audit.c
index 0a1355ca3d79..09fae2677a45 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -45,7 +45,7 @@
 #include <asm/types.h>
 #include <linux/atomic.h>
 #include <linux/mm.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/kthread.h>
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index ce4b054acee5..47b7fc1ea893 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -48,7 +48,7 @@
 #include <linux/fs.h>
 #include <linux/namei.h>
 #include <linux/mm.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/mount.h>
 #include <linux/socket.h>
diff --git a/kernel/capability.c b/kernel/capability.c
index 283c529f8b1c..b463871a4e69 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -10,7 +10,7 @@
 #include <linux/audit.h>
 #include <linux/capability.h>
 #include <linux/mm.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
 #include <linux/pid_namespace.h>
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 453100a4159d..d9d5648f3cdc 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2027,7 +2027,7 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 		goto out_free_group_list;
 
 	/* prevent changes to the threadgroup list while we take a snapshot. */
-	rcu_read_lock();
+	read_lock(&tasklist_lock);
 	if (!thread_group_leader(leader)) {
 		/*
 		 * a race with de_thread from another thread's exec() may strip
@@ -2036,7 +2036,7 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 		 * throw this task away and try again (from cgroup_procs_write);
 		 * this is "double-double-toil-and-trouble-check locking".
 		 */
-		rcu_read_unlock();
+		read_unlock(&tasklist_lock);
 		retval = -EAGAIN;
 		goto out_free_group_list;
 	}
@@ -2057,7 +2057,7 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 	} while_each_thread(leader, tsk);
 	/* remember the number of threads in the array for later. */
 	group_size = i;
-	rcu_read_unlock();
+	read_unlock(&tasklist_lock);
 
 	/*
 	 * step 1: check that we can legitimately attach to the cgroup.
@@ -2135,14 +2135,17 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 		oldcgrp = task_cgroup_from_root(tsk, root);
 		if (cgrp == oldcgrp)
 			continue;
-		/* attach each task to each subsystem */
-		for_each_subsys(root, ss) {
-			if (ss->attach_task)
-				ss->attach_task(cgrp, tsk);
-		}
 		/* if the thread is PF_EXITING, it can just get skipped. */
 		retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, true);
-		BUG_ON(retval != 0 && retval != -ESRCH);
+		if (retval == 0) {
+			/* attach each task to each subsystem */
+			for_each_subsys(root, ss) {
+				if (ss->attach_task)
+					ss->attach_task(cgrp, tsk);
+			}
+		} else {
+			BUG_ON(retval != -ESRCH);
+		}
 	}
 	/* nothing is sensitive to fork() after this point. */
 
@@ -4880,9 +4883,9 @@ void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
 
 	rcu_assign_pointer(id->css, NULL);
 	rcu_assign_pointer(css->id, NULL);
-	spin_lock(&ss->id_lock);
+	write_lock(&ss->id_lock);
 	idr_remove(&ss->idr, id->id);
-	spin_unlock(&ss->id_lock);
+	write_unlock(&ss->id_lock);
 	kfree_rcu(id, rcu_head);
 }
 EXPORT_SYMBOL_GPL(free_css_id);
@@ -4908,10 +4911,10 @@ static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth)
 		error = -ENOMEM;
 		goto err_out;
 	}
-	spin_lock(&ss->id_lock);
+	write_lock(&ss->id_lock);
 	/* Don't use 0. allocates an ID of 1-65535 */
 	error = idr_get_new_above(&ss->idr, newid, 1, &myid);
-	spin_unlock(&ss->id_lock);
+	write_unlock(&ss->id_lock);
 
 	/* Returns error when there are no free spaces for new ID.*/
 	if (error) {
@@ -4926,9 +4929,9 @@ static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth)
 	return newid;
 remove_idr:
 	error = -ENOSPC;
-	spin_lock(&ss->id_lock);
+	write_lock(&ss->id_lock);
 	idr_remove(&ss->idr, myid);
-	spin_unlock(&ss->id_lock);
+	write_unlock(&ss->id_lock);
 err_out:
 	kfree(newid);
 	return ERR_PTR(error);
@@ -4940,7 +4943,7 @@ static int __init_or_module cgroup_init_idr(struct cgroup_subsys *ss,
 {
 	struct css_id *newid;
 
-	spin_lock_init(&ss->id_lock);
+	rwlock_init(&ss->id_lock);
 	idr_init(&ss->idr);
 
 	newid = get_new_cssid(ss, 0);
@@ -5035,9 +5038,9 @@ css_get_next(struct cgroup_subsys *ss, int id,
 		 * scan next entry from bitmap(tree), tmpid is updated after
 		 * idr_get_next().
 		 */
-		spin_lock(&ss->id_lock);
+		read_lock(&ss->id_lock);
 		tmp = idr_get_next(&ss->idr, &tmpid);
-		spin_unlock(&ss->id_lock);
+		read_unlock(&ss->id_lock);
 
 		if (!tmp)
 			break;
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index e691818d7e45..5e828a2ca8e6 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -14,7 +14,7 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/cgroup.h>
 #include <linux/fs.h>
diff --git a/kernel/compat.c b/kernel/compat.c
index e2435ee9993a..f346cedfe24d 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -21,6 +21,7 @@
 #include <linux/unistd.h>
 #include <linux/security.h>
 #include <linux/timex.h>
+#include <linux/export.h>
 #include <linux/migrate.h>
 #include <linux/posix-timers.h>
 #include <linux/times.h>
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 12b7458f23b1..563f13609470 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -10,11 +10,12 @@
 #include <linux/sched.h>
 #include <linux/unistd.h>
 #include <linux/cpu.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kthread.h>
 #include <linux/stop_machine.h>
 #include <linux/mutex.h>
 #include <linux/gfp.h>
+#include <linux/suspend.h>
 
 #ifdef CONFIG_SMP
 /* Serializes the updates to cpu_online_mask, cpu_present_mask */
@@ -476,6 +477,79 @@ static int alloc_frozen_cpus(void)
 	return 0;
 }
 core_initcall(alloc_frozen_cpus);
+
+/*
+ * Prevent regular CPU hotplug from racing with the freezer, by disabling CPU
+ * hotplug when tasks are about to be frozen. Also, don't allow the freezer
+ * to continue until any currently running CPU hotplug operation gets
+ * completed.
+ * To modify the 'cpu_hotplug_disabled' flag, we need to acquire the
+ * 'cpu_add_remove_lock'. And this same lock is also taken by the regular
+ * CPU hotplug path and released only after it is complete. Thus, we
+ * (and hence the freezer) will block here until any currently running CPU
+ * hotplug operation gets completed.
+ */
+void cpu_hotplug_disable_before_freeze(void)
+{
+	cpu_maps_update_begin();
+	cpu_hotplug_disabled = 1;
+	cpu_maps_update_done();
+}
+
+
+/*
+ * When tasks have been thawed, re-enable regular CPU hotplug (which had been
+ * disabled while beginning to freeze tasks).
+ */
+void cpu_hotplug_enable_after_thaw(void)
+{
+	cpu_maps_update_begin();
+	cpu_hotplug_disabled = 0;
+	cpu_maps_update_done();
+}
+
+/*
+ * When callbacks for CPU hotplug notifications are being executed, we must
+ * ensure that the state of the system with respect to the tasks being frozen
+ * or not, as reported by the notification, remains unchanged *throughout the
+ * duration* of the execution of the callbacks.
+ * Hence we need to prevent the freezer from racing with regular CPU hotplug.
+ *
+ * This synchronization is implemented by mutually excluding regular CPU
+ * hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/
+ * Hibernate notifications.
+ */
+static int
+cpu_hotplug_pm_callback(struct notifier_block *nb,
+			unsigned long action, void *ptr)
+{
+	switch (action) {
+
+	case PM_SUSPEND_PREPARE:
+	case PM_HIBERNATION_PREPARE:
+		cpu_hotplug_disable_before_freeze();
+		break;
+
+	case PM_POST_SUSPEND:
+	case PM_POST_HIBERNATION:
+		cpu_hotplug_enable_after_thaw();
+		break;
+
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+
+int cpu_hotplug_pm_sync_init(void)
+{
+	pm_notifier(cpu_hotplug_pm_callback, 0);
+	return 0;
+}
+core_initcall(cpu_hotplug_pm_sync_init);
+
 #endif /* CONFIG_PM_SLEEP_SMP */
 
 /**
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 10131fdaff70..9fe58c46a426 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -37,7 +37,7 @@
 #include <linux/mempolicy.h>
 #include <linux/mm.h>
 #include <linux/memory.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/pagemap.h>
@@ -949,6 +949,8 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 static void cpuset_change_task_nodemask(struct task_struct *tsk,
 					nodemask_t *newmems)
 {
+	bool masks_disjoint = !nodes_intersects(*newmems, tsk->mems_allowed);
+
 repeat:
 	/*
 	 * Allow tasks that have access to memory reserves because they have
@@ -963,7 +965,6 @@ repeat:
 	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
 	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
 
-
 	/*
 	 * ensure checking ->mems_allowed_change_disable after setting all new
 	 * allowed nodes.
@@ -980,9 +981,11 @@ repeat:
 
 	/*
 	 * Allocation of memory is very fast, we needn't sleep when waiting
-	 * for the read-side.
+	 * for the read-side.  No wait is necessary, however, if at least one
+	 * node remains unchanged.
 	 */
-	while (ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
+	while (masks_disjoint &&
+			ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
 		task_unlock(tsk);
 		if (!task_curr(tsk))
 			yield();
diff --git a/kernel/crash_dump.c b/kernel/crash_dump.c
index 69ebf3380bac..c766ee54c0b1 100644
--- a/kernel/crash_dump.c
+++ b/kernel/crash_dump.c
@@ -2,7 +2,7 @@
 #include <linux/crash_dump.h>
 #include <linux/init.h>
 #include <linux/errno.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 /*
  * If we have booted due to a crash, max_pfn will be a very low value. We need
diff --git a/kernel/cred.c b/kernel/cred.c
index bb55d052d858..5791612a4045 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -8,7 +8,7 @@
  * as published by the Free Software Foundation; either version
  * 2 of the Licence, or (at your option) any later version.
  */
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/cred.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
diff --git a/kernel/debug/kdb/kdb_debugger.c b/kernel/debug/kdb/kdb_debugger.c
index d9ca9aa481ec..8b68ce78ff17 100644
--- a/kernel/debug/kdb/kdb_debugger.c
+++ b/kernel/debug/kdb/kdb_debugger.c
@@ -11,6 +11,7 @@
 #include <linux/kgdb.h>
 #include <linux/kdb.h>
 #include <linux/kdebug.h>
+#include <linux/export.h>
 #include "kdb_private.h"
 #include "../debug_core.h"
 
diff --git a/kernel/dma.c b/kernel/dma.c
index f903189c5304..68a2306522c8 100644
--- a/kernel/dma.c
+++ b/kernel/dma.c
@@ -9,7 +9,7 @@
  *   [It also happened to remove the sizeof(char *) == sizeof(int)
  *   assumption introduced because of those /proc/dma patches. -- Hennus]
  */
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/spinlock.h>
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 12a0287e0358..0e8457da6f95 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -25,11 +25,11 @@
 #include <linux/reboot.h>
 #include <linux/vmstat.h>
 #include <linux/device.h>
+#include <linux/export.h>
 #include <linux/vmalloc.h>
 #include <linux/hardirq.h>
 #include <linux/rculist.h>
 #include <linux/uaccess.h>
-#include <linux/suspend.h>
 #include <linux/syscalls.h>
 #include <linux/anon_inodes.h>
 #include <linux/kernel_stat.h>
@@ -6853,7 +6853,7 @@ static void __cpuinit perf_event_init_cpu(int cpu)
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
-	if (swhash->hlist_refcount > 0 && !swhash->swevent_hlist) {
+	if (swhash->hlist_refcount > 0) {
 		struct swevent_hlist *hlist;
 
 		hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu));
@@ -6942,14 +6942,7 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
 
-	/*
-	 * Ignore suspend/resume action, the perf_pm_notifier will
-	 * take care of that.
-	 */
-	if (action & CPU_TASKS_FROZEN)
-		return NOTIFY_OK;
-
-	switch (action) {
+	switch (action & ~CPU_TASKS_FROZEN) {
 
 	case CPU_UP_PREPARE: