Merge commit 'v2.6.29-rc1' into core/urgent

kernel/Makefile

@@ -9,7 +9,8 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
 	    rcupdate.o extable.o params.o posix-timers.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
-	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o
+	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
+	    async.o
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files

kernel/async.c

@@ -0,0 +1,335 @@
+/*
+ * async.c: Asynchronous function calls for boot performance
+ *
+ * (C) Copyright 2009 Intel Corporation
+ * Author: Arjan van de Ven <arjan@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+
+/*
+
+Goals and Theory of Operation
+
+The primary goal of this feature is to reduce the kernel boot time,
+by doing various independent hardware delays and discovery operations
+decoupled and not strictly serialized.
+
+More specifically, the asynchronous function call concept allows
+certain operations (primarily during system boot) to happen
+asynchronously, out of order, while these operations still
+have their externally visible parts happen sequentially and in-order.
+(not unlike how out-of-order CPUs retire their instructions in order)
+
+Key to the asynchronous function call implementation is the concept of
+a "sequence cookie" (which, although it has an abstracted type, can be
+thought of as a monotonically incrementing number).
+
+The async core will assign each scheduled event such a sequence cookie and
+pass this to the called functions.
+
+The asynchronously called function should before doing a globally visible
+operation, such as registering device numbers, call the
+async_synchronize_cookie() function and pass in its own cookie. The
+async_synchronize_cookie() function will make sure that all asynchronous
+operations that were scheduled prior to the operation corresponding with the
+cookie have completed.
+
+Subsystem/driver initialization code that scheduled asynchronous probe
+functions, but which shares global resources with other drivers/subsystems
+that do not use the asynchronous call feature, need to do a full
+synchronization with the async_synchronize_full() function, before returning
+from their init function. This is to maintain strict ordering between the
+asynchronous and synchronous parts of the kernel.
+
+*/
+
+#include <linux/async.h>
+#include <linux/module.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/kthread.h>
+#include <asm/atomic.h>
+
+static async_cookie_t next_cookie = 1;
+
+#define MAX_THREADS	256
+#define MAX_WORK	32768
+
+static LIST_HEAD(async_pending);
+static LIST_HEAD(async_running);
+static DEFINE_SPINLOCK(async_lock);
+
+static int async_enabled = 0;
+
+struct async_entry {
+	struct list_head list;
+	async_cookie_t   cookie;
+	async_func_ptr	 *func;
+	void             *data;
+	struct list_head *running;
+};
+
+static DECLARE_WAIT_QUEUE_HEAD(async_done);
+static DECLARE_WAIT_QUEUE_HEAD(async_new);
+
+static atomic_t entry_count;
+static atomic_t thread_count;
+
+extern int initcall_debug;
+
+
+/*
+ * MUST be called with the lock held!
+ */
+static async_cookie_t  __lowest_in_progress(struct list_head *running)
+{
+	struct async_entry *entry;
+	if (!list_empty(&async_pending)) {
+		entry = list_first_entry(&async_pending,
+			struct async_entry, list);
+		return entry->cookie;
+	} else if (!list_empty(running)) {
+		entry = list_first_entry(running,
+			struct async_entry, list);
+		return entry->cookie;
+	} else {
+		/* nothing in progress... next_cookie is "infinity" */
+		return next_cookie;
+	}
+
+}
+/*
+ * pick the first pending entry and run it
+ */
+static void run_one_entry(void)
+{
+	unsigned long flags;
+	struct async_entry *entry;
+	ktime_t calltime, delta, rettime;
+
+	/* 1) pick one task from the pending queue */
+
+	spin_lock_irqsave(&async_lock, flags);
+	if (list_empty(&async_pending))
+		goto out;
+	entry = list_first_entry(&async_pending, struct async_entry, list);
+
+	/* 2) move it to the running queue */
+	list_del(&entry->list);
+	list_add_tail(&entry->list, &async_running);
+	spin_unlock_irqrestore(&async_lock, flags);
+
+	/* 3) run it (and print duration)*/
+	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+		printk("calling  %lli_%pF @ %i\n", entry->cookie, entry->func, task_pid_nr(current));
+		calltime = ktime_get();
+	}
+	entry->func(entry->data, entry->cookie);
+	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+		rettime = ktime_get();
+		delta = ktime_sub(rettime, calltime);
+		printk("initcall %lli_%pF returned 0 after %lld usecs\n", entry->cookie,
+			entry->func, ktime_to_ns(delta) >> 10);
+	}
+
+	/* 4) remove it from the running queue */
+	spin_lock_irqsave(&async_lock, flags);
+	list_del(&entry->list);
+
+	/* 5) free the entry  */
+	kfree(entry);
+	atomic_dec(&entry_count);
+
+	spin_unlock_irqrestore(&async_lock, flags);
+
+	/* 6) wake up any waiters. */
+	wake_up(&async_done);
+	return;
+
+out:
+	spin_unlock_irqrestore(&async_lock, flags);
+}
+
+
+static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct list_head *running)
+{
+	struct async_entry *entry;
+	unsigned long flags;
+	async_cookie_t newcookie;
+	
+
+	/* allow irq-off callers */
+	entry = kzalloc(sizeof(struct async_entry), GFP_ATOMIC);
+
+	/*
+	 * If we're out of memory or if there's too much work
+	 * pending already, we execute synchronously.
+	 */
+	if (!async_enabled || !entry || atomic_read(&entry_count) > MAX_WORK) {
+		kfree(entry);
+		spin_lock_irqsave(&async_lock, flags);
+		newcookie = next_cookie++;
+		spin_unlock_irqrestore(&async_lock, flags);
+
+		/* low on memory.. run synchronously */
+		ptr(data, newcookie);
+		return newcookie;
+	}
+	entry->func = ptr;
+	entry->data = data;
+	entry->running = running;
+
+	spin_lock_irqsave(&async_lock, flags);
+	newcookie = entry->cookie = next_cookie++;
+	list_add_tail(&entry->list, &async_pending);
+	atomic_inc(&entry_count);
+	spin_unlock_irqrestore(&async_lock, flags);
+	wake_up(&async_new);
+	return newcookie;
+}
+
+async_cookie_t async_schedule(async_func_ptr *ptr, void *data)
+{
+	return __async_schedule(ptr, data, &async_pending);
+}
+EXPORT_SYMBOL_GPL(async_schedule);
+
+async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *running)
+{
+	return __async_schedule(ptr, data, running);
+}
+EXPORT_SYMBOL_GPL(async_schedule_special);
+
+void async_synchronize_full(void)
+{
+	do {
+		async_synchronize_cookie(next_cookie);
+	} while (!list_empty(&async_running) || !list_empty(&async_pending));
+}
+EXPORT_SYMBOL_GPL(async_synchronize_full);
+
+void async_synchronize_full_special(struct list_head *list)
+{
+	async_synchronize_cookie_special(next_cookie, list);
+}
+EXPORT_SYMBOL_GPL(async_synchronize_full_special);
+
+void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *running)
+{
+	ktime_t starttime, delta, endtime;
+
+	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+		printk("async_waiting @ %i\n", task_pid_nr(current));
+		starttime = ktime_get();
+	}
+
+	wait_event(async_done, __lowest_in_progress(running) >= cookie);
+
+	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+		endtime = ktime_get();
+		delta = ktime_sub(endtime, starttime);
+
+		printk("async_continuing @ %i after %lli usec\n",
+			task_pid_nr(current), ktime_to_ns(delta) >> 10);
+	}
+}
+EXPORT_SYMBOL_GPL(async_synchronize_cookie_special);
+
+void async_synchronize_cookie(async_cookie_t cookie)
+{
+	async_synchronize_cookie_special(cookie, &async_running);
+}
+EXPORT_SYMBOL_GPL(async_synchronize_cookie);
+
+
+static int async_thread(void *unused)
+{
+	DECLARE_WAITQUEUE(wq, current);
+	add_wait_queue(&async_new, &wq);
+
+	while (!kthread_should_stop()) {
+		int ret = HZ;
+		set_current_state(TASK_INTERRUPTIBLE);
+		/*
+		 * check the list head without lock.. false positives
+		 * are dealt with inside run_one_entry() while holding
+		 * the lock.
+		 */
+		rmb();
+		if (!list_empty(&async_pending))
+			run_one_entry();
+		else
+			ret = schedule_timeout(HZ);
+
+		if (ret == 0) {
+			/*
+			 * we timed out, this means we as thread are redundant.
+			 * we sign off and die, but we to avoid any races there
+			 * is a last-straw check to see if work snuck in.
+			 */
+			atomic_dec(&thread_count);
+			wmb(); /* manager must see our departure first */
+			if (list_empty(&async_pending))
+				break;
+			/*
+			 * woops work came in between us timing out and us
+			 * signing off; we need to stay alive and keep working.
+			 */
+			atomic_inc(&thread_count);
+		}
+	}
+	remove_wait_queue(&async_new, &wq);
+
+	return 0;
+}
+
+static int async_manager_thread(void *unused)
+{
+	DECLARE_WAITQUEUE(wq, current);
+	add_wait_queue(&async_new, &wq);
+
+	while (!kthread_should_stop()) {
+		int tc, ec;
+
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		tc = atomic_read(&thread_count);
+		rmb();
+		ec = atomic_read(&entry_count);
+
+		while (tc < ec && tc < MAX_THREADS) {
+			kthread_run(async_thread, NULL, "async/%i", tc);
+			atomic_inc(&thread_count);
+			tc++;
+		}
+
+		schedule();
+	}
+	remove_wait_queue(&async_new, &wq);
+
+	return 0;
+}
+
+static int __init async_init(void)
+{
+	if (async_enabled)
+		kthread_run(async_manager_thread, NULL, "async/mgr");
+	return 0;
+}
+
+static int __init setup_async(char *str)
+{
+	async_enabled = 1;
+	return 1;
+}
+
+__setup("fastboot", setup_async);
+
+
+core_initcall(async_init);

kernel/cgroup.c

@@ -84,7 +84,7 @@ struct cgroupfs_root {
 	/* Tracks how many cgroups are currently defined in hierarchy.*/
 	int number_of_cgroups;
 
-	/* A list running through the mounted hierarchies */
+	/* A list running through the active hierarchies */
 	struct list_head root_list;
 
 	/* Hierarchy-specific flags */
@@ -148,8 +148,8 @@ static int notify_on_release(const struct cgroup *cgrp)
 #define for_each_subsys(_root, _ss) \
 list_for_each_entry(_ss, &_root->subsys_list, sibling)
 
-/* for_each_root() allows you to iterate across the active hierarchies */
-#define for_each_root(_root) \
+/* for_each_active_root() allows you to iterate across the active hierarchies */
+#define for_each_active_root(_root) \
 list_for_each_entry(_root, &roots, root_list)
 
 /* the list of cgroups eligible for automatic release. Protected by
@@ -271,7 +271,7 @@ static void __put_css_set(struct css_set *cg, int taskexit)
 
 	rcu_read_lock();
 	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-		struct cgroup *cgrp = cg->subsys[i]->cgroup;
+		struct cgroup *cgrp = rcu_dereference(cg->subsys[i]->cgroup);
 		if (atomic_dec_and_test(&cgrp->count) &&
 		    notify_on_release(cgrp)) {
 			if (taskexit)
@@ -384,6 +384,25 @@ static int allocate_cg_links(int count, struct list_head *tmp)
 	return 0;
 }
 
+/**
+ * link_css_set - a helper function to link a css_set to a cgroup
+ * @tmp_cg_links: cg_cgroup_link objects allocated by allocate_cg_links()
+ * @cg: the css_set to be linked
+ * @cgrp: the destination cgroup
+ */
+static void link_css_set(struct list_head *tmp_cg_links,
+			 struct css_set *cg, struct cgroup *cgrp)
+{
+	struct cg_cgroup_link *link;
+
+	BUG_ON(list_empty(tmp_cg_links));
+	link = list_first_entry(tmp_cg_links, struct cg_cgroup_link,
+				cgrp_link_list);
+	link->cg = cg;
+	list_move(&link->cgrp_link_list, &cgrp->css_sets);
+	list_add(&link->cg_link_list, &cg->cg_links);
+}
+
 /*
  * find_css_set() takes an existing cgroup group and a
  * cgroup object, and returns a css_set object that's
@@ -399,7 +418,6 @@ static struct css_set *find_css_set(
 	int i;
 
 	struct list_head tmp_cg_links;
-	struct cg_cgroup_link *link;
 
 	struct hlist_head *hhead;
 
@@ -444,26 +462,11 @@ static struct css_set *find_css_set(
 		 * only do it for the first subsystem in each
 		 * hierarchy
 		 */
-		if (ss->root->subsys_list.next == &ss->sibling) {
-			BUG_ON(list_empty(&tmp_cg_links));
-			link = list_entry(tmp_cg_links.next,
-					  struct cg_cgroup_link,
-					  cgrp_link_list);
-			list_del(&link->cgrp_link_list);
-			list_add(&link->cgrp_link_list, &cgrp->css_sets);
-			link->cg = res;
-			list_add(&link->cg_link_list, &res->cg_links);
-		}
-	}
-	if (list_empty(&rootnode.subsys_list)) {
-		link = list_entry(tmp_cg_links.next,
-				  struct cg_cgroup_link,
-				  cgrp_link_list);
-		list_del(&link->cgrp_link_list);
-		list_add(&link->cgrp_link_list, &dummytop->css_sets);
-		link->cg = res;
-		list_add(&link->cg_link_list, &res->cg_links);
+		if (ss->root->subsys_list.next == &ss->sibling)
+			link_css_set(&tmp_cg_links, res, cgrp);
 	}
+	if (list_empty(&rootnode.subsys_list))
+		link_css_set(&tmp_cg_links, res, dummytop);
 
 	BUG_ON(!list_empty(&tmp_cg_links));
 
@@ -586,11 +589,18 @@ static void cgroup_call_pre_destroy(struct cgroup *cgrp)
 {
 	struct cgroup_subsys *ss;
 	for_each_subsys(cgrp->root, ss)
-		if (ss->pre_destroy && cgrp->subsys[ss->subsys_id])
+		if (ss->pre_destroy)
 			ss->pre_destroy(ss, cgrp);
 	return;
 }
 
+static void free_cgroup_rcu(struct rcu_head *obj)
+{
+	struct cgroup *cgrp = container_of(obj, struct cgroup, rcu_head);
+
+	kfree(cgrp);
+}
+
 static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 {
 	/* is dentry a directory ? if so, kfree() associated cgroup */
@@ -610,19 +620,19 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		/*
 		 * Release the subsystem state objects.
 		 */
-		for_each_subsys(cgrp->root, ss) {
-			if (cgrp->subsys[ss->subsys_id])
-				ss->destroy(ss, cgrp);
-		}
+		for_each_subsys(cgrp->root, ss)
+			ss->destroy(ss, cgrp);
 
 		cgrp->root->number_of_cgroups--;
 		mutex_unlock(&cgroup_mutex);
 
-		/* Drop the active superblock reference that we took when we
-		 * created the cgroup */
+		/*
+		 * Drop the active superblock reference that we took when we
+		 * created the cgroup
+		 */
 		deactivate_super(cgrp->root->sb);
 
-		kfree(cgrp);
+		call_rcu(&cgrp->rcu_head, free_cgroup_rcu);
 	}
 	iput(inode);
 }
@@ -712,23 +722,26 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 			BUG_ON(cgrp->subsys[i]);
 			BUG_ON(!dummytop->subsys[i]);
 			BUG_ON(dummytop->subsys[i]->cgroup != dummytop);
+			mutex_lock(&ss->hierarchy_mutex);
 			cgrp->subsys[i] = dummytop->subsys[i];
 			cgrp->subsys[i]->cgroup = cgrp;
-			list_add(&ss->sibling, &root->subsys_list);
-			rcu_assign_pointer(ss->root, root);
+			list_move(&ss->sibling, &root->subsys_list);
+			ss->root = root;
 			if (ss->bind)
 				ss->bind(ss, cgrp);
-
+			mutex_unlock(&ss->hierarchy_mutex);
 		} else if (bit & removed_bits) {
 			/* We're removing this subsystem */
 			BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]);
 			BUG_ON(cgrp->subsys[i]->cgroup != cgrp);
+			mutex_lock(&ss->hierarchy_mutex);
 			if (ss->bind)
 				ss->bind(ss, dummytop);
 			dummytop->subsys[i]->cgroup = dummytop;
 			cgrp->subsys[i] = NULL;
-			rcu_assign_pointer(subsys[i]->root, &rootnode);
-			list_del(&ss->sibling);
+			subsys[i]->root = &rootnode;
+			list_move(&ss->sibling, &rootnode.subsys_list);
+			mutex_unlock(&ss->hierarchy_mutex);
 		} else if (bit & final_bits) {
 			/* Subsystem state should already exist */
 			BUG_ON(!cgrp->subsys[i]);
@@ -990,7 +1003,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 		root = NULL;
 	} else {
 		/* New superblock */
-		struct cgroup *cgrp = &root->top_cgroup;
+		struct cgroup *root_cgrp = &root->top_cgroup;
 		struct inode *inode;
 		int i;
 
@@ -1031,7 +1044,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 		list_add(&root->root_list, &roots);
 		root_count++;
 
-		sb->s_root->d_fsdata = &root->top_cgroup;
+		sb->s_root->d_fsdata = root_cgrp;
 		root->top_cgroup.dentry = sb->s_root;
 
 		/* Link the top cgroup in this hierarchy into all
@@ -1042,29 +1055,18 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 			struct hlist_node *node;
 			struct css_set *cg;
 
-			hlist_for_each_entry(cg, node, hhead, hlist) {
-				struct cg_cgroup_link *link;
-
-				BUG_ON(list_empty(&tmp_cg_links));
-				link = list_entry(tmp_cg_links.next,
-						  struct cg_cgroup_link,
-						  cgrp_link_list);
-				list_del(&link->cgrp_link_list);
-				link->cg = cg;
-				list_add(&link->cgrp_link_list,
-					 &root->top_cgroup.css_sets);
-				list_add(&link->cg_link_list, &cg->cg_links);
-			}
+			hlist_for_each_entry(cg, node, hhead, hlist)
+				link_css_set(&tmp_cg_links, cg, root_cgrp);
 		}
 		write_unlock(&css_set_lock);
 
 		free_cg_links(&tmp_cg_links);
 
-		BUG_ON(!list_empty(&cgrp->sibling));
-		BUG_ON(!list_empty(&cgrp->children));
+		BUG_ON(!list_empty(&root_cgrp->sibling));
+		BUG_ON(!list_empty(&root_cgrp->children));
 		BUG_ON(root->number_of_cgroups != 1);
 
-		cgroup_populate_dir(cgrp);
+		cgroup_populate_dir(root_cgrp);
 		mutex_unlock(&inode->i_mutex);
 		mutex_unlock(&cgroup_mutex);
 	}
@@ -1113,10 +1115,9 @@ static void cgroup_kill_sb(struct super_block *sb) {
 	}
 	write_unlock(&css_set_lock);
 
-	if (!list_empty(&root->root_list)) {
-		list_del(&root->root_list);
-		root_count--;
-	}
+	list_del(&root->root_list);
+	root_count--;
+
 	mutex_unlock(&cgroup_mutex);
 
 	kfree(root);
@@ -1145,14 +1146,16 @@ static inline struct cftype *__d_cft(struct dentry *dentry)
  * @buf: the buffer to write the path into
  * @buflen: the length of the buffer
  *
- * Called with cgroup_mutex held. Writes path of cgroup into buf.
- * Returns 0 on success, -errno on error.
+ * Called with cgroup_mutex held or else with an RCU-protected cgroup
+ * reference.  Writes path of cgroup into buf.  Returns 0 on success,
+ * -errno on error.
  */
 int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 {
 	char *start;
+	struct dentry *dentry = rcu_dereference(cgrp->dentry);
 
-	if (cgrp == dummytop) {
+	if (!dentry || cgrp == dummytop) {
 		/*
 		 * Inactive subsystems have no dentry for their root
 		 * cgroup
@@ -1165,13 +1168,14 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 
 	*--start = '\0';
 	for (;;) {
-		int len = cgrp->dentry->d_name.len;
+		int len = dentry->d_name.len;
 		if ((start -= len) < buf)
 			return -ENAMETOOLONG;
 		memcpy(start, cgrp->dentry->d_name.name, len);
 		cgrp = cgrp->parent;
 		if (!cgrp)
 			break;
+		dentry = rcu_dereference(cgrp->dentry);
 		if (!cgrp->parent)
 			continue;
 		if (--start < buf)
@@ -1216,7 +1220,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	int retval = 0;
 	struct cgroup_subsys *ss;
 	struct cgroup *oldcgrp;
-	struct css_set *cg = tsk->cgroups;
+	struct css_set *cg;
 	struct css_set *newcg;
 	struct cgroupfs_root *root = cgrp->root;
 	int subsys_id;
@@ -1236,11 +1240,16 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 		}
 	}
 
+	task_lock(tsk);
+	cg = tsk->cgroups;
+	get_css_set(cg);
+	task_unlock(tsk);
 	/*
 	 * Locate or allocate a new css_set for this task,
 	 * based on its final set of cgroups
 	 */
 	newcg = find_css_set(cg, cgrp);
+	put_css_set(cg);
 	if (!newcg)
 		return -ENOMEM;
 
@@ -1445,7 +1454,7 @@ static ssize_t cgroup_file_write(struct file *file, const char __user *buf,
 	struct cftype *cft = __d_cft(file->f_dentry);
 	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
 
-	if (!cft || cgroup_is_removed(cgrp))
+	if (cgroup_is_removed(cgrp))
 		return -ENODEV;
 	if (cft->write)
 		return cft->write(cgrp, cft, file, buf, nbytes, ppos);
@@ -1490,7 +1499,7 @@ static ssize_t cgroup_file_read(struct file *file, char __user *buf,
 	struct cftype *cft = __d_cft(file->f_dentry);
 	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
 
-	if (!cft || cgroup_is_removed(cgrp))
+	if (cgroup_is_removed(cgrp))
 		return -ENODEV;
 
 	if (cft->read)
@@ -1554,10 +1563,8 @@ static int cgroup_file_open(struct inode *inode, struct file *file)
 	err = generic_file_open(inode, file);
 	if (err)
 		return err;
-
 	cft = __d_cft(file->f_dentry);
-	if (!cft)
-		return -ENODEV;
+
 	if (cft->read_map || cft->read_seq_string) {
 		struct cgroup_seqfile_state *state =
 			kzalloc(sizeof(*state), GFP_USER);
@@ -1671,7 +1678,7 @@ static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry,
 	if (!error) {
 		dentry->d_fsdata = cgrp;
 		inc_nlink(parent->d_inode);
-		cgrp->dentry = dentry;
+		rcu_assign_pointer(cgrp->dentry, dentry);
 		dget(dentry);
 	}
 	dput(dentry);
@@ -1812,6 +1819,7 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
 {
 	struct task_struct *res;
 	struct list_head *l = it->task;
+	struct cg_cgroup_link *link;
 
 	/* If the iterator cg is NULL, we have no tasks */
 	if (!it->cg_link)
@@ -1819,7 +1827,8 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
 	res = list_entry(l, struct task_struct, cg_list);
 	/* Advance iterator to find next entry */
 	l = l->next;
-	if (l == &res->cgroups->tasks) {
+	link = list_entry(it->cg_link, struct cg_cgroup_link, cgrp_link_list);
+	if (l == &link->cg->tasks) {
 		/* We reached the end of this task list - move on to
 		 * the next cg_cgroup_link */
 		cgroup_advance_iter(cgrp, it);
@@ -2013,14 +2022,16 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
  */
 static int pid_array_load(pid_t *pidarray, int npids, struct cgroup *cgrp)
 {
-	int n = 0;
+	int n = 0, pid;
 	struct cgroup_iter it;
 	struct task_struct *tsk;
 	cgroup_iter_start(cgrp, &it);
 	while ((tsk = cgroup_iter_next(cgrp, &it))) {
 		if (unlikely(n == npids))
 			break;
-		pidarray[n++] = task_pid_vnr(tsk);
+		pid = task_pid_vnr(tsk);
+		if (pid > 0)
+			pidarray[n++] = pid;
 	}
 	cgroup_iter_end(cgrp, &it);
 	return n;
@@ -2052,7 +2063,6 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 
 	ret = 0;
 	cgrp = dentry->d_fsdata;
-	rcu_read_lock();
 
 	cgroup_iter_start(cgrp, &it);
 	while ((tsk = cgroup_iter_next(cgrp, &it))) {
@@ -2077,7 +2087,6 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 	}
 	cgroup_iter_end(cgrp, &it);
 
-	rcu_read_unlock();
 err:
 	return ret;
 }
@@ -2324,7 +2333,7 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 			       struct cgroup *cgrp)
 {
 	css->cgroup = cgrp;
-	atomic_set(&css->refcnt, 0);
+	atomic_set(&css->refcnt, 1);
 	css->flags = 0;
 	if (cgrp == dummytop)
 		set_bit(CSS_ROOT, &css->flags);
@@ -2332,6 +2341,29 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 	cgrp->subsys[ss->subsys_id] = css;
 }
 
+static void cgroup_lock_hierarchy(struct cgroupfs_root *root)
+{
+	/* We need to take each hierarchy_mutex in a consistent order */
+	int i;
+
+	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+		struct cgroup_subsys *ss = subsys[i];
+		if (ss->root == root)
+			mutex_lock_nested(&ss->hierarchy_mutex, i);
+	}
+}
+
+static void cgroup_unlock_hierarchy(struct cgroupfs_root *root)
+{
+	int i;
+
+	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+		struct cgroup_subsys *ss = subsys[i];
+		if (ss->root == root)
+			mutex_unlock(&ss->hierarchy_mutex);
+	}
+}
+
 /*
  * cgroup_create - create a cgroup
  * @parent: cgroup that will be parent of the new cgroup
@@ -2380,7 +2412,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 		init_cgroup_css(css, ss, cgrp);
 	}
 
+	cgroup_lock_hierarchy(root);
 	list_add(&cgrp->sibling, &cgrp->parent->children);
+	cgroup_unlock_hierarchy(root);
 	root->number_of_cgroups++;
 
 	err = cgroup_create_dir(cgrp, dentry, mode);
@@ -2431,7 +2465,7 @@ static int cgroup_has_css_refs(struct cgroup *cgrp)
 {
 	/* Check the reference count on each subsystem. Since we
 	 * already established that there are no tasks in the
-	 * cgroup, if the css refcount is also 0, then there should
+	 * cgroup, if the css refcount is also 1, then there should
 	 * be no outstanding references, so the subsystem is safe to
 	 * destroy. We scan across all subsystems rather than using
 	 * the per-hierarchy linked list of mounted subsystems since
@@ -2452,19 +2486,67 @@ static int cgroup_has_css_refs(struct cgroup *cgrp)
 		 * matter, since it can only happen if the cgroup
 		 * has been deleted and hence no longer needs the
 		 * release agent to be called anyway. */
-		if (css && atomic_read(&css->refcnt))
+		if (css && (atomic_read(&css->refcnt) > 1))
 			return 1;
 	}
 	return 0;
 }
 
+/*
+ * Atomically mark all (or else none) of the cgroup's CSS objects as
+ * CSS_REMOVED. Return true on success, or false if the cgroup has
+ * busy subsystems. Call with cgroup_mutex held
+ */
+
+static int cgroup_clear_css_refs(struct cgroup *cgrp)
+{
+	struct cgroup_subsys *ss;
+	unsigned long flags;
+	bool failed = false;
+	local_irq_save(flags);
+	for_each_subsys(cgrp->root, ss) {
+		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+		int refcnt;
+		do {
+			/* We can only remove a CSS with a refcnt==1 */
+			refcnt = atomic_read(&css->refcnt);
+			if (refcnt > 1) {
+				failed = true;
+				goto done;
+			}
+			BUG_ON(!refcnt);
+			/*
+			 * Drop the refcnt to 0 while we check other
+			 * subsystems. This will cause any racing
+			 * css_tryget() to spin until we set the
+			 * CSS_REMOVED bits or abort
+			 */
+		} while (atomic_cmpxchg(&css->refcnt, refcnt, 0) != refcnt);
+	}
+ done:
+	for_each_subsys(cgrp->root, ss) {
+		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+		if (failed) {
+			/*
+			 * Restore old refcnt if we previously managed
+			 * to clear it from 1 to 0
+			 */
+			if (!atomic_read(&css->refcnt))
+				atomic_set(&css->refcnt, 1);
+		} else {
+			/* Commit the fact that the CSS is removed */
+			set_bit(CSS_REMOVED, &css->flags);
+		}
+	}
+	local_irq_restore(flags);
+	return !failed;
+}
+
 static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 {
 	struct cgroup *cgrp = dentry->d_fsdata;
 	struct dentry *d;
 	struct cgroup *parent;
-	struct super_block *sb;
-	struct cgroupfs_root *root;
 
 	/* the vfs holds both inode->i_mutex already */
 
@@ -2487,12 +2569,10 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 
 	mutex_lock(&cgroup_mutex);
 	parent = cgrp->parent;
-	root = cgrp->root;
-	sb = root->sb;
 
 	if (atomic_read(&cgrp->count)
 	    || !list_empty(&cgrp->children)
-	    || cgroup_has_css_refs(cgrp)) {
+	    || !cgroup_clear_css_refs(cgrp)) {
 		mutex_unlock(&cgroup_mutex);
 		return -EBUSY;
 	}
@@ -2502,8 +2582,12 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	if (!list_empty(&cgrp->release_list))
 		list_del(&cgrp->release_list);
 	spin_unlock(&release_list_lock);
-	/* delete my sibling from parent->children */
+
+	cgroup_lock_hierarchy(cgrp->root);
+	/* delete this cgroup from parent->children */
 	list_del(&cgrp->sibling);
+	cgroup_unlock_hierarchy(cgrp->root);
+
 	spin_lock(&cgrp->dentry->d_lock);
 	d = dget(cgrp->dentry);
 	spin_unlock(&d->d_lock);
@@ -2525,6 +2609,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name);
 
 	/* Create the top cgroup state for this subsystem */
+	list_add(&ss->sibling, &rootnode.subsys_list);
 	ss->root = &rootnode;
 	css = ss->create(ss, dummytop);
 	/* We don't handle early failures gracefully */
@@ -2544,6 +2629,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	 * need to invoke fork callbacks here. */
 	BUG_ON(!list_empty(&init_task.tasks));
 
+	mutex_init(&ss->hierarchy_mutex);
 	ss->active = 1;
 }
 
@@ -2562,7 +2648,6 @@ int __init cgroup_init_early(void)
 	INIT_HLIST_NODE(&init_css_set.hlist);
 	css_set_count = 1;
 	init_cgroup_root(&rootnode);
-	list_add(&rootnode.root_list, &roots);
 	root_count = 1;
 	init_task.cgroups = &init_css_set;
 
@@ -2669,15 +2754,12 @@ static int proc_cgroup_show(struct seq_file *m, void *v)
 
 	mutex_lock(&cgroup_mutex);
 
-	for_each_root(root) {
+	for_each_active_root(root) {
 		struct cgroup_subsys *ss;
 		struct cgroup *cgrp;
 		int subsys_id;
 		int count = 0;
 
-		/* Skip this hierarchy if it has no active subsystems */
-		if (!root->actual_subsys_bits)
-			continue;
 		seq_printf(m, "%lu:", root->subsys_bits);
 		for_each_subsys(root, ss)
 			seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
@@ -2800,8 +2882,10 @@ void cgroup_post_fork(struct task_struct *child)
 {
 	if (use_task_css_set_links) {
 		write_lock(&css_set_lock);
+		task_lock(child);
 		if (list_empty(&child->cg_list))
 			list_add(&child->cg_list, &child->cgroups->tasks);
+		task_unlock(child);
 		write_unlock(&css_set_lock);
 	}
 }
@@ -2907,6 +2991,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 		mutex_unlock(&cgroup_mutex);
 		return 0;
 	}
+	task_lock(tsk);
 	cg = tsk->cgroups;
 	parent = task_cgroup(tsk, subsys->subsys_id);
 
@@ -2919,6 +3004,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 
 	/* Keep the cgroup alive */
 	get_css_set(cg);
+	task_unlock(tsk);
 	mutex_unlock(&cgroup_mutex);
 
 	/* Now do the VFS work to create a cgroup */
@@ -2937,7 +3023,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 	}
 
 	/* Create the cgroup directory, which also creates the cgroup */
-	ret = vfs_mkdir(inode, dentry, S_IFDIR | 0755);
+	ret = vfs_mkdir(inode, dentry, 0755);
 	child = __d_cgrp(dentry);
 	dput(dentry);
 	if (ret) {
@@ -2947,13 +3033,6 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 		goto out_release;
 	}
 
-	if (!child) {
-		printk(KERN_INFO
-		       "Couldn't find new cgroup %s\n", nodename);
-		ret = -ENOMEM;
-		goto out_release;
-	}
-
 	/* The cgroup now exists. Retake cgroup_mutex and check
 	 * that we're still in the same state that we thought we
 	 * were. */
@@ -3049,7 +3128,8 @@ void __css_put(struct cgroup_subsys_state *css)
 {
 	struct cgroup *cgrp = css->cgroup;
 	rcu_read_lock();
-	if (atomic_dec_and_test(&css->refcnt) && notify_on_release(cgrp)) {
+	if ((atomic_dec_return(&css->refcnt) == 1) &&
+	    notify_on_release(cgrp)) {
 		set_bit(CGRP_RELEASABLE, &cgrp->flags);
 		check_for_release(cgrp);
 	}

kernel/cpuset.c

@@ -84,7 +84,7 @@ struct cpuset {
 	struct cgroup_subsys_state css;
 
 	unsigned long flags;		/* "unsigned long" so bitops work */
-	cpumask_t cpus_allowed;		/* CPUs allowed to tasks in cpuset */
+	cpumask_var_t cpus_allowed;	/* CPUs allowed to tasks in cpuset */
 	nodemask_t mems_allowed;	/* Memory Nodes allowed to tasks */
 
 	struct cpuset *parent;		/* my parent */
@@ -195,8 +195,6 @@ static int cpuset_mems_generation;
 
 static struct cpuset top_cpuset = {
 	.flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)),
-	.cpus_allowed = CPU_MASK_ALL,
-	.mems_allowed = NODE_MASK_ALL,
 };
 
 /*
@@ -278,7 +276,7 @@ static struct file_system_type cpuset_fs_type = {
 };
 
 /*
- * Return in *pmask the portion of a cpusets's cpus_allowed that
+ * Return in pmask the portion of a cpusets's cpus_allowed that
  * are online.  If none are online, walk up the cpuset hierarchy
  * until we find one that does have some online cpus.  If we get
  * all the way to the top and still haven't found any online cpus,
@@ -291,15 +289,16 @@ static struct file_system_type cpuset_fs_type = {
  * Call with callback_mutex held.
  */
 
-static void guarantee_online_cpus(const struct cpuset *cs, cpumask_t *pmask)
+static void guarantee_online_cpus(const struct cpuset *cs,
+				  struct cpumask *pmask)
 {
-	while (cs && !cpus_intersects(cs->cpus_allowed, cpu_online_map))
+	while (cs && !cpumask_intersects(cs->cpus_allowed, cpu_online_mask))
 		cs = cs->parent;
 	if (cs)
-		cpus_and(*pmask, cs->cpus_allowed, cpu_online_map);
+		cpumask_and(pmask, cs->cpus_allowed, cpu_online_mask);
 	else
-		*pmask = cpu_online_map;
-	BUG_ON(!cpus_intersects(*pmask, cpu_online_map));
+		cpumask_copy(pmask, cpu_online_mask);
+	BUG_ON(!cpumask_intersects(pmask, cpu_online_mask));
 }
 
 /*
@@ -375,14 +374,9 @@ void cpuset_update_task_memory_state(void)
 	struct task_struct *tsk = current;
 	struct cpuset *cs;
 
-	if (task_cs(tsk) == &top_cpuset) {
-		/* Don't need rcu for top_cpuset.  It's never freed. */
-		my_cpusets_mem_gen = top_cpuset.mems_generation;
-	} else {
-		rcu_read_lock();
-		my_cpusets_mem_gen = task_cs(tsk)->mems_generation;
-		rcu_read_unlock();
-	}
+	rcu_read_lock();
+	my_cpusets_mem_gen = task_cs(tsk)->mems_generation;
+	rcu_read_unlock();
 
 	if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
 		mutex_lock(&callback_mutex);
@@ -414,12 +408,43 @@ void cpuset_update_task_memory_state(void)
 
 static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
 {
-	return	cpus_subset(p->cpus_allowed, q->cpus_allowed) &&
+	return	cpumask_subset(p->cpus_allowed, q->cpus_allowed) &&
 		nodes_subset(p->mems_allowed, q->mems_allowed) &&
 		is_cpu_exclusive(p) <= is_cpu_exclusive(q) &&
 		is_mem_exclusive(p) <= is_mem_exclusive(q);
 }
 
+/**
+ * alloc_trial_cpuset - allocate a trial cpuset
+ * @cs: the cpuset that the trial cpuset duplicates
+ */
+static struct cpuset *alloc_trial_cpuset(const struct cpuset *cs)
+{
+	struct cpuset *trial;
+
+	trial = kmemdup(cs, sizeof(*cs), GFP_KERNEL);
+	if (!trial)
+		return NULL;
+
+	if (!alloc_cpumask_var(&trial->cpus_allowed, GFP_KERNEL)) {
+		kfree(trial);
+		return NULL;
+	}
+	cpumask_copy(trial->cpus_allowed, cs->cpus_allowed);
+
+	return trial;
+}
+
+/**
+ * free_trial_cpuset - free the trial cpuset
+ * @trial: the trial cpuset to be freed
+ */
+static void free_trial_cpuset(struct cpuset *trial)
+{
+	free_cpumask_var(trial->cpus_allowed);
+	kfree(trial);
+}
+
 /*
  * validate_change() - Used to validate that any proposed cpuset change
  *		       follows the structural rules for cpusets.
@@ -469,7 +494,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
 		c = cgroup_cs(cont);
 		if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
 		    c != cur &&
-		    cpus_intersects(trial->cpus_allowed, c->cpus_allowed))
+		    cpumask_intersects(trial->cpus_allowed, c->cpus_allowed))
 			return -EINVAL;
 		if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
 		    c != cur &&
@@ -479,7 +504,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
 
 	/* Cpusets with tasks can't have empty cpus_allowed or mems_allowed */
 	if (cgroup_task_count(cur->css.cgroup)) {
-		if (cpus_empty(trial->cpus_allowed) ||
+		if (cpumask_empty(trial->cpus_allowed) ||
 		    nodes_empty(trial->mems_allowed)) {
 			return -ENOSPC;
 		}
@@ -494,7 +519,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
  */
 static int cpusets_overlap(struct cpuset *a, struct cpuset *b)
 {
-	return cpus_intersects(a->cpus_allowed, b->cpus_allowed);
+	return cpumask_intersects(a->cpus_allowed, b->cpus_allowed);
 }
 
 static void
@@ -519,7 +544,7 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c)
 		cp = list_first_entry(&q, struct cpuset, stack_list);
 		list_del(q.next);
 
-		if (cpus_empty(cp->cpus_allowed))
+		if (cpumask_empty(cp->cpus_allowed))
 			continue;
 
 		if (is_sched_load_balance(cp))
@@ -586,7 +611,8 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c)
  *	element of the partition (one sched domain) to be passed to
  *	partition_sched_domains().
  */
-static int generate_sched_domains(cpumask_t **domains,
+/* FIXME: see the FIXME in partition_sched_domains() */
+static int generate_sched_domains(struct cpumask **domains,
 			struct sched_domain_attr **attributes)
 {
 	LIST_HEAD(q);		/* queue of cpusets to be scanned */
@@ -594,10 +620,10 @@ static int generate_sched_domains(cpumask_t **domains,
 	struct cpuset **csa;	/* array of all cpuset ptrs */
 	int csn;		/* how many cpuset ptrs in csa so far */
 	int i, j, k;		/* indices for partition finding loops */
-	cpumask_t *doms;	/* resulting partition; i.e. sched domains */
+	struct cpumask *doms;	/* resulting partition; i.e. sched domains */
 	struct sched_domain_attr *dattr;  /* attributes for custom domains */
 	int ndoms = 0;		/* number of sched domains in result */
-	int nslot;		/* next empty doms[] cpumask_t slot */
+	int nslot;		/* next empty doms[] struct cpumask slot */
 
 	doms = NULL;
 	dattr = NULL;
@@ -605,7 +631,7 @@ static int generate_sched_domains(cpumask_t **domains,
 
 	/* Special case for the 99% of systems with one, full, sched domain */
 	if (is_sched_load_balance(&top_cpuset)) {
-		doms = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
+		doms = kmalloc(cpumask_size(), GFP_KERNEL);
 		if (!doms)
 			goto done;
 
@@ -614,7 +640,7 @@ static int generate_sched_domains(cpumask_t **domains,
 			*dattr = SD_ATTR_INIT;
 			update_domain_attr_tree(dattr, &top_cpuset);
 		}
-		*doms = top_cpuset.cpus_allowed;
+		cpumask_copy(doms, top_cpuset.cpus_allowed);
 
 		ndoms = 1;
 		goto done;
@@ -633,7 +659,7 @@ static int generate_sched_domains(cpumask_t **domains,
 		cp = list_first_entry(&q, struct cpuset, stack_list);
 		list_del(q.next);
 
-		if (cpus_empty(cp->cpus_allowed))
+		if (cpumask_empty(cp->cpus_allowed))
 			continue;
 
 		/*
@@ -684,7 +710,7 @@ restart:
 	 * Now we know how many domains to create.
 	 * Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
 	 */
-	doms = kmalloc(ndoms * sizeof(cpumask_t), GFP_KERNEL);
+	doms = kmalloc(ndoms * cpumask_size(), GFP_KERNEL);
 	if (!doms)
 		goto done;
 
@@ -696,7 +722,7 @@ restart:
 
 	for (nslot = 0, i = 0; i < csn; i++) {
 		struct cpuset *a = csa[i];
-		cpumask_t *dp;
+		struct cpumask *dp;
 		int apn = a->pn;
 
 		if (apn < 0) {
@@ -719,14 +745,14 @@ restart:
 			continue;
 		}
 
-		cpus_clear(*dp);
+		cpumask_clear(dp);
 		if (dattr)
 			*(dattr + nslot) = SD_ATTR_INIT;
 		for (j = i; j < csn; j++) {
 			struct cpuset *b = csa[j];
 
 			if (apn == b->pn) {
-				cpus_or(*dp, *dp, b->cpus_allowed);
+				cpumask_or(dp, dp, b->cpus_allowed);
 				if (dattr)
 					update_domain_attr_tree(dattr + nslot, b);
 
@@ -766,7 +792,7 @@ done:
 static void do_rebuild_sched_domains(struct work_struct *unused)
 {
 	struct sched_domain_attr *attr;
-	cpumask_t *doms;
+	struct cpumask *doms;
 	int ndoms;
 
 	get_online_cpus();
@@ -835,7 +861,7 @@ void rebuild_sched_domains(void)
 static int cpuset_test_cpumask(struct task_struct *tsk,
 			       struct cgroup_scanner *scan)
 {
-	return !cpus_equal(tsk->cpus_allowed,
+	return !cpumask_equal(&tsk->cpus_allowed,
 			(cgroup_cs(scan->cg))->cpus_allowed);
 }
 
@@ -853,7 +879,7 @@ static int cpuset_test_cpumask(struct task_struct *tsk,
 static void cpuset_change_cpumask(struct task_struct *tsk,
 				  struct cgroup_scanner *scan)
 {
-	set_cpus_allowed_ptr(tsk, &((cgroup_cs(scan->cg))->cpus_allowed));
+	set_cpus_allowed_ptr(tsk, ((cgroup_cs(scan->cg))->cpus_allowed));
 }
 
 /**
@@ -885,10 +911,10 @@ static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap)
  * @cs: the cpuset to consider
  * @buf: buffer of cpu numbers written to this cpuset
  */
-static int update_cpumask(struct cpuset *cs, const char *buf)
+static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
+			  const char *buf)
 {
 	struct ptr_heap heap;
-	struct cpuset trialcs;
 	int retval;
 	int is_load_balanced;
 
@@ -896,8 +922,6 @@ static int update_cpumask(struct cpuset *cs, const char *buf)
 	if (cs == &top_cpuset)
 		return -EACCES;
 
-	trialcs = *cs;
-
 	/*
 	 * An empty cpus_allowed is ok only if the cpuset has no tasks.
 	 * Since cpulist_parse() fails on an empty mask, we special case
@@ -905,31 +929,31 @@ static int update_cpumask(struct cpuset *cs, const char *buf)
 	 * with tasks have cpus.
 	 */
 	if (!*buf) {
-		cpus_clear(trialcs.cpus_allowed);
+		cpumask_clear(trialcs->cpus_allowed);
 	} else {
-		retval = cpulist_parse(buf, &trialcs.cpus_allowed);
+		retval = cpulist_parse(buf, trialcs->cpus_allowed);
 		if (retval < 0)
 			return retval;
 
-		if (!cpus_subset(trialcs.cpus_allowed, cpu_online_map))
+		if (!cpumask_subset(trialcs->cpus_allowed, cpu_online_mask))
 			return -EINVAL;
 	}
-	retval = validate_change(cs, &trialcs);
+	retval = validate_change(cs, trialcs);
 	if (retval < 0)
 		return retval;
 
 	/* Nothing to do if the cpus didn't change */
-	if (cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed))
+	if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed))
 		return 0;
 
 	retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
 	if (retval)
 		return retval;
 
-	is_load_balanced = is_sched_load_balance(&trialcs);
+	is_load_balanced = is_sched_load_balance(trialcs);
 
 	mutex_lock(&callback_mutex);
-	cs->cpus_allowed = trialcs.cpus_allowed;
+	cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
 	mutex_unlock(&callback_mutex);
 
 	/*
@@ -1017,7 +1041,7 @@ static int update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem)
 	cpuset_being_rebound = cs;		/* causes mpol_dup() rebind */
 
 	fudge = 10;				/* spare mmarray[] slots */
-	fudge += cpus_weight(cs->cpus_allowed);	/* imagine one fork-bomb/cpu */
+	fudge += cpumask_weight(cs->cpus_allowed);/* imagine 1 fork-bomb/cpu */
 	retval = -ENOMEM;
 
 	/*
@@ -1104,9 +1128,9 @@ done:
  * lock each such tasks mm->mmap_sem, scan its vma's and rebind
  * their mempolicies to the cpusets new mems_allowed.
  */
-static int update_nodemask(struct cpuset *cs, const char *buf)
+static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
+			   const char *buf)
 {
-	struct cpuset trialcs;
 	nodemask_t oldmem;
 	int retval;
 
@@ -1117,8 +1141,6 @@ static int update_nodemask(struct cpuset *cs, const char *buf)
 	if (cs == &top_cpuset)
 		return -EACCES;
 
-	trialcs = *cs;
-
 	/*
 	 * An empty mems_allowed is ok iff there are no tasks in the cpuset.
 	 * Since nodelist_parse() fails on an empty mask, we special case
@@ -1126,27 +1148,27 @@ static int update_nodemask(struct cpuset *cs, const char *buf)
 	 * with tasks have memory.
 	 */
 	if (!*buf) {
-		nodes_clear(trialcs.mems_allowed);
+		nodes_clear(trialcs->mems_allowed);
 	} else {
-		retval = nodelist_parse(buf, trialcs.mems_allowed);
+		retval = nodelist_parse(buf, trialcs->mems_allowed);
 		if (retval < 0)
 			goto done;
 
-		if (!nodes_subset(trialcs.mems_allowed,
+		if (!nodes_subset(trialcs->mems_allowed,
 				node_states[N_HIGH_MEMORY]))
 			return -EINVAL;
 	}
 	oldmem = cs->mems_allowed;
-	if (nodes_equal(oldmem, trialcs.mems_allowed)) {
+	if (nodes_equal(oldmem, trialcs->mems_allowed)) {
 		retval = 0;		/* Too easy - nothing to do */
 		goto done;
 	}
-	retval = validate_change(cs, &trialcs);
+	retval = validate_change(cs, trialcs);
 	if (retval < 0)
 		goto done;
 
 	mutex_lock(&callback_mutex);
-	cs->mems_allowed = trialcs.mems_allowed;
+	cs->mems_allowed = trialcs->mems_allowed;
 	cs->mems_generation = cpuset_mems_generation++;
 	mutex_unlock(&callback_mutex);
 
@@ -1167,7 +1189,8 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val)
 
 	if (val != cs->relax_domain_level) {
 		cs->relax_domain_level = val;
-		if (!cpus_empty(cs->cpus_allowed) && is_sched_load_balance(cs))
+		if (!cpumask_empty(cs->cpus_allowed) &&
+		    is_sched_load_balance(cs))
 			async_rebuild_sched_domains();
 	}
 
@@ -1186,31 +1209,36 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val)
 static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
 		       int turning_on)
 {
-	struct cpuset trialcs;
+	struct cpuset *trialcs;
 	int err;
 	int balance_flag_changed;
 
-	trialcs = *cs;
-	if (turning_on)
-		set_bit(bit, &trialcs.flags);
-	else
-		clear_bit(bit, &trialcs.flags);
+	trialcs = alloc_trial_cpuset(cs);
+	if (!trialcs)
+		return -ENOMEM;
 
-	err = validate_change(cs, &trialcs);
+	if (turning_on)
+		set_bit(bit, &trialcs->flags);
+	else
+		clear_bit(bit, &trialcs->flags);
+
+	err = validate_change(cs, trialcs);
 	if (err < 0)
-		return err;
+		goto out;
 
 	balance_flag_changed = (is_sched_load_balance(cs) !=
-		 			is_sched_load_balance(&trialcs));
+				is_sched_load_balance(trialcs));
 
 	mutex_lock(&callback_mutex);
-	cs->flags = trialcs.flags;
+	cs->flags = trialcs->flags;
 	mutex_unlock(&callback_mutex);
 
-	if (!cpus_empty(trialcs.cpus_allowed) && balance_flag_changed)
+	if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed)
 		async_rebuild_sched_domains();
 
-	return 0;
+out:
+	free_trial_cpuset(trialcs);
+	return err;
 }
 
 /*
@@ -1311,42 +1339,47 @@ static int fmeter_getrate(struct fmeter *fmp)
 	return val;
 }
 
+/* Protected by cgroup_lock */
+static cpumask_var_t cpus_attach;
+
 /* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */
 static int cpuset_can_attach(struct cgroup_subsys *ss,
 			     struct cgroup *cont, struct task_struct *tsk)
 {
 	struct cpuset *cs = cgroup_cs(cont);
+	int ret = 0;
 
-	if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
+	if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
 		return -ENOSPC;
-	if (tsk->flags & PF_THREAD_BOUND) {
-		cpumask_t mask;
 
+	if (tsk->flags & PF_THREAD_BOUND) {
 		mutex_lock(&callback_mutex);
-		mask = cs->cpus_allowed;
+		if (!cpumask_equal(&tsk->cpus_allowed, cs->cpus_allowed))
+			ret = -EINVAL;
 		mutex_unlock(&callback_mutex);
-		if (!cpus_equal(tsk->cpus_allowed, mask))
-			return -EINVAL;
 	}
 
-	return security_task_setscheduler(tsk, 0, NULL);
+	return ret < 0 ? ret : security_task_setscheduler(tsk, 0, NULL);
 }
 
 static void cpuset_attach(struct cgroup_subsys *ss,
 			  struct cgroup *cont, struct cgroup *oldcont,
 			  struct task_struct *tsk)
 {
-	cpumask_t cpus;
 	nodemask_t from, to;
 	struct mm_struct *mm;
 	struct cpuset *cs = cgroup_cs(cont);
 	struct cpuset *oldcs = cgroup_cs(oldcont);
 	int err;
 
-	mutex_lock(&callback_mutex);
-	guarantee_online_cpus(cs, &cpus);
-	err = set_cpus_allowed_ptr(tsk, &cpus);
-	mutex_unlock(&callback_mutex);
+	if (cs == &top_cpuset) {
+		cpumask_copy(cpus_attach, cpu_possible_mask);
+	} else {
+		mutex_lock(&callback_mutex);
+		guarantee_online_cpus(cs, cpus_attach);
+		mutex_unlock(&callback_mutex);
+	}
+	err = set_cpus_allowed_ptr(tsk, cpus_attach);
 	if (err)
 		return;
 
@@ -1359,7 +1392,6 @@ static void cpuset_attach(struct cgroup_subsys *ss,
 			cpuset_migrate_mm(mm, &from, &to);
 		mmput(mm);
 	}
-
 }
 
 /* The various types of files and directories in a cpuset file system */
@@ -1454,21 +1486,29 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
 				const char *buf)
 {
 	int retval = 0;
+	struct cpuset *cs = cgroup_cs(cgrp);
+	struct cpuset *trialcs;
 
 	if (!cgroup_lock_live_group(cgrp))
 		return -ENODEV;
 
+	trialcs = alloc_trial_cpuset(cs);
+	if (!trialcs)
+		return -ENOMEM;
+
 	switch (cft->private) {
 	case FILE_CPULIST:
-		retval = update_cpumask(cgroup_cs(cgrp), buf);
+		retval = update_cpumask(cs, trialcs, buf);
 		break;
 	case FILE_MEMLIST:
-		retval = update_nodemask(cgroup_cs(cgrp), buf);
+		retval = update_nodemask(cs, trialcs, buf);
 		break;
 	default:
 		retval = -EINVAL;
 		break;
 	}
+
+	free_trial_cpuset(trialcs);
 	cgroup_unlock();
 	return retval;
 }
@@ -1487,13 +1527,13 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
 
 static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
 {
-	cpumask_t mask;
+	int ret;
 
 	mutex_lock(&callback_mutex);
-	mask = cs->cpus_allowed;
+	ret = cpulist_scnprintf(page, PAGE_SIZE, cs->cpus_allowed);
 	mutex_unlock(&callback_mutex);
 
-	return cpulist_scnprintf(page, PAGE_SIZE, &mask);
+	return ret;
 }
 
 static int cpuset_sprintf_memlist(char *page, struct cpuset *cs)
@@ -1729,7 +1769,7 @@ static void cpuset_post_clone(struct cgroup_subsys *ss,
 	parent_cs = cgroup_cs(parent);
 
 	cs->mems_allowed = parent_cs->mems_allowed;
-	cs->cpus_allowed = parent_cs->cpus_allowed;
+	cpumask_copy(cs->cpus_allowed, parent_cs->cpus_allowed);
 	return;
 }
 
@@ -1755,6 +1795,10 @@ static struct cgroup_subsys_state *cpuset_create(
 	cs = kmalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
+	if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL)) {
+		kfree(cs);
+		return ERR_PTR(-ENOMEM);
+	}
 
 	cpuset_update_task_memory_state();
 	cs->flags = 0;
@@ -1763,7 +1807,7 @@ static struct cgroup_subsys_state *cpuset_create(
 	if (is_spread_slab(parent))
 		set_bit(CS_SPREAD_SLAB, &cs->flags);
 	set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
-	cpus_clear(cs->cpus_allowed);
+	cpumask_clear(cs->cpus_allowed);
 	nodes_clear(cs->mems_allowed);
 	cs->mems_generation = cpuset_mems_generation++;
 	fmeter_init(&cs->fmeter);
@@ -1790,6 +1834,7 @@ static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
 		update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
 
 	number_of_cpusets--;
+	free_cpumask_var(cs->cpus_allowed);
 	kfree(cs);
 }
 
@@ -1813,6 +1858,8 @@ struct cgroup_subsys cpuset_subsys = {
 
 int __init cpuset_init_early(void)
 {
+	alloc_bootmem_cpumask_var(&top_cpuset.cpus_allowed);
+
 	top_cpuset.mems_generation = cpuset_mems_generation++;
 	return 0;
 }
@@ -1828,7 +1875,7 @@ int __init cpuset_init(void)
 {
 	int err = 0;
 
-	cpus_setall(top_cpuset.cpus_allowed);
+	cpumask_setall(top_cpuset.cpus_allowed);
 	nodes_setall(top_cpuset.mems_allowed);
 
 	fmeter_init(&top_cpuset.fmeter);
@@ -1840,6 +1887,9 @@ int __init cpuset_init(void)
 	if (err < 0)
 		return err;
 
+	if (!alloc_cpumask_var(&cpus_attach, GFP_KERNEL))
+		BUG();
+
 	number_of_cpusets = 1;
 	return 0;
 }
@@ -1914,7 +1964,7 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
 	 * has online cpus, so can't be empty).
 	 */
 	parent = cs->parent;
-	while (cpus_empty(parent->cpus_allowed) ||
+	while (cpumask_empty(parent->cpus_allowed) ||
 			nodes_empty(parent->mems_allowed))
 		parent = parent->parent;
 
@@ -1955,7 +2005,7 @@ static void scan_for_empty_cpusets(struct cpuset *root)
 		}
 
 		/* Continue past cpusets with all cpus, mems online */
-		if (cpus_subset(cp->cpus_allowed, cpu_online_map) &&
+		if (cpumask_subset(cp->cpus_allowed, cpu_online_mask) &&
 		    nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY]))
 			continue;
 
@@ -1963,13 +2013,14 @@ static void scan_for_empty_cpusets(struct cpuset *root)
 
 		/* Remove offline cpus and mems from this cpuset. */
 		mutex_lock(&callback_mutex);
-		cpus_and(cp->cpus_allowed, cp->cpus_allowed, cpu_online_map);
+		cpumask_and(cp->cpus_allowed, cp->cpus_allowed,
+			    cpu_online_mask);
 		nodes_and(cp->mems_allowed, cp->mems_allowed,
 						node_states[N_HIGH_MEMORY]);
 		mutex_unlock(&callback_mutex);
 
 		/* Move tasks from the empty cpuset to a parent */
-		if (cpus_empty(cp->cpus_allowed) ||
+		if (cpumask_empty(cp->cpus_allowed) ||
 		     nodes_empty(cp->mems_allowed))
 			remove_tasks_in_empty_cpuset(cp);
 		else {
@@ -1995,7 +2046,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 				unsigned long phase, void *unused_cpu)
 {
 	struct sched_domain_attr *attr;
-	cpumask_t *doms;
+	struct cpumask *doms;
 	int ndoms;
 
 	switch (phase) {
@@ -2010,7 +2061,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 	}
 
 	cgroup_lock();
-	top_cpuset.cpus_allowed = cpu_online_map;
+	cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask);
 	scan_for_empty_cpusets(&top_cpuset);
 	ndoms = generate_sched_domains(&doms, &attr);
 	cgroup_unlock();
@@ -2055,7 +2106,7 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
 
 void __init cpuset_init_smp(void)
 {
-	top_cpuset.cpus_allowed = cpu_online_map;
+	cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask);
 	top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 
 	hotcpu_notifier(cpuset_track_online_cpus, 0);
@@ -2065,15 +2116,15 @@ void __init cpuset_init_smp(void)
 /**
  * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset.
  * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
- * @pmask: pointer to cpumask_t variable to receive cpus_allowed set.
+ * @pmask: pointer to struct cpumask variable to receive cpus_allowed set.
  *
- * Description: Returns the cpumask_t cpus_allowed of the cpuset
+ * Description: Returns the cpumask_var_t cpus_allowed of the cpuset
  * attached to the specified @tsk.  Guaranteed to return some non-empty
  * subset of cpu_online_map, even if this means going outside the
  * tasks cpuset.
  **/
 
-void cpuset_cpus_allowed(struct task_struct *tsk, cpumask_t *pmask)
+void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 {
 	mutex_lock(&callback_mutex);
 	cpuset_cpus_allowed_locked(tsk, pmask);
@@ -2084,7 +2135,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, cpumask_t *pmask)
  * cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset.
  * Must be called with callback_mutex held.
  **/
-void cpuset_cpus_allowed_locked(struct task_struct *tsk, cpumask_t *pmask)
+void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask)
 {
 	task_lock(tsk);
 	guarantee_online_cpus(task_cs(tsk), pmask);

kernel/cred.c

@@ -372,7 +372,8 @@ int commit_creds(struct cred *new)
 	    old->fsuid != new->fsuid ||
 	    old->fsgid != new->fsgid ||
 	    !cap_issubset(new->cap_permitted, old->cap_permitted)) {
-		set_dumpable(task->mm, suid_dumpable);
+		if (task->mm)
+			set_dumpable(task->mm, suid_dumpable);
 		task->pdeath_signal = 0;
 		smp_wmb();
 	}
@@ -506,6 +507,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 	else
 		old = get_cred(&init_cred);
 
+	*new = *old;
 	get_uid(new->user);
 	get_group_info(new->group_info);
 
@@ -529,6 +531,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 
 error:
 	put_cred(new);
+	put_cred(old);
 	return NULL;
 }
 EXPORT_SYMBOL(prepare_kernel_cred);

kernel/fork.c

@@ -1126,12 +1126,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	if (pid != &init_struct_pid) {
 		retval = -ENOMEM;
-		pid = alloc_pid(task_active_pid_ns(p));
+		pid = alloc_pid(p->nsproxy->pid_ns);
 		if (!pid)
 			goto bad_fork_cleanup_io;
 
 		if (clone_flags & CLONE_NEWPID) {
-			retval = pid_ns_prepare_proc(task_active_pid_ns(p));
+			retval = pid_ns_prepare_proc(p->nsproxy->pid_ns);
 			if (retval < 0)
 				goto bad_fork_free_pid;
 		}
@@ -1481,12 +1481,10 @@ void __init proc_caches_init(void)
 	fs_cachep = kmem_cache_create("fs_cache",
 			sizeof(struct fs_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
-	vm_area_cachep = kmem_cache_create("vm_area_struct",
-			sizeof(struct vm_area_struct), 0,
-			SLAB_PANIC, NULL);
 	mm_cachep = kmem_cache_create("mm_struct",
 			sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+	mmap_init();
 }
 
 /*

kernel/irq/autoprobe.c

@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
+#include <linux/async.h>
 
 #include "internals.h"
 
@@ -34,6 +35,10 @@ unsigned long probe_irq_on(void)
 	unsigned int status;
 	int i;
 
+	/*
+	 * quiesce the kernel, or at least the asynchronous portion
+	 */
+	async_synchronize_full();
 	mutex_lock(&probing_active);
 	/*
 	 * something may have generated an irq long ago and we want to

kernel/module.c

@@ -50,6 +50,7 @@
 #include <asm/sections.h>
 #include <linux/tracepoint.h>
 #include <linux/ftrace.h>
+#include <linux/async.h>
 
 #if 0
 #define DEBUGP printk
@@ -816,6 +817,7 @@ sys_delete_module(const char __user *name_user, unsigned int flags)
 		mod->exit();
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_GOING, mod);
+	async_synchronize_full();
 	mutex_lock(&module_mutex);
 	/* Store the name of the last unloaded module for diagnostic purposes */
 	strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module));

kernel/ns_cgroup.c

@@ -13,7 +13,6 @@
 
 struct ns_cgroup {
 	struct cgroup_subsys_state css;
-	spinlock_t lock;
 };
 
 struct cgroup_subsys ns_subsys;
@@ -84,7 +83,6 @@ static struct cgroup_subsys_state *ns_create(struct cgroup_subsys *ss,
 	ns_cgroup = kzalloc(sizeof(*ns_cgroup), GFP_KERNEL);
 	if (!ns_cgroup)
 		return ERR_PTR(-ENOMEM);
-	spin_lock_init(&ns_cgroup->lock);
 	return &ns_cgroup->css;
 }
 

kernel/pid.c

@@ -474,6 +474,12 @@ pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
 }
 EXPORT_SYMBOL(task_session_nr_ns);
 
+struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
+{
+	return ns_of_pid(task_pid(tsk));
+}
+EXPORT_SYMBOL_GPL(task_active_pid_ns);
+
 /*
  * Used by proc to find the first pid that is greater than or equal to nr.
  *

kernel/power/disk.c

@@ -258,12 +258,12 @@ int hibernation_snapshot(int platform_mode)
 {
 	int error;
 
-	/* Free memory before shutting down devices. */
-	error = swsusp_shrink_memory();
+	error = platform_begin(platform_mode);
 	if (error)
 		return error;
 
-	error = platform_begin(platform_mode);
+	/* Free memory before shutting down devices. */
+	error = swsusp_shrink_memory();
 	if (error)
 		goto Close;
 

kernel/power/snapshot.c

@@ -25,6 +25,7 @@
 #include <linux/syscalls.h>
 #include <linux/console.h>
 #include <linux/highmem.h>
+#include <linux/list.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -192,12 +193,6 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
 	return ret;
 }
 
-static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
-{
-	free_list_of_pages(ca->chain, clear_page_nosave);
-	memset(ca, 0, sizeof(struct chain_allocator));
-}
-
 /**
  *	Data types related to memory bitmaps.
  *
@@ -233,7 +228,7 @@ static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
 #define BM_BITS_PER_BLOCK	(PAGE_SIZE << 3)
 
 struct bm_block {
-	struct bm_block *next;		/* next element of the list */
+	struct list_head hook;	/* hook into a list of bitmap blocks */
 	unsigned long start_pfn;	/* pfn represented by the first bit */
 	unsigned long end_pfn;	/* pfn represented by the last bit plus 1 */
 	unsigned long *data;	/* bitmap representing pages */
@@ -244,24 +239,15 @@ static inline unsigned long bm_block_bits(struct bm_block *bb)
 	return bb->end_pfn - bb->start_pfn;
 }
 
-struct zone_bitmap {
-	struct zone_bitmap *next;	/* next element of the list */
-	unsigned long start_pfn;	/* minimal pfn in this zone */
-	unsigned long end_pfn;		/* maximal pfn in this zone plus 1 */
-	struct bm_block *bm_blocks;	/* list of bitmap blocks */
-	struct bm_block *cur_block;	/* recently used bitmap block */
-};
-
 /* strcut bm_position is used for browsing memory bitmaps */
 
 struct bm_position {
-	struct zone_bitmap *zone_bm;
 	struct bm_block *block;
 	int bit;
 };
 
 struct memory_bitmap {
-	struct zone_bitmap *zone_bm_list;	/* list of zone bitmaps */
+	struct list_head blocks;	/* list of bitmap blocks */
 	struct linked_page *p_list;	/* list of pages used to store zone
 					 * bitmap objects and bitmap block
 					 * objects
@@ -273,11 +259,7 @@ struct memory_bitmap {
 
 static void memory_bm_position_reset(struct memory_bitmap *bm)
 {
-	struct zone_bitmap *zone_bm;
-
-	zone_bm = bm->zone_bm_list;
-	bm->cur.zone_bm = zone_bm;
-	bm->cur.block = zone_bm->bm_blocks;
+	bm->cur.block = list_entry(bm->blocks.next, struct bm_block, hook);
 	bm->cur.bit = 0;
 }
 
@@ -285,151 +267,184 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free);
 
 /**
  *	create_bm_block_list - create a list of block bitmap objects
+ *	@nr_blocks - number of blocks to allocate
+ *	@list - list to put the allocated blocks into
+ *	@ca - chain allocator to be used for allocating memory
  */
-
-static inline struct bm_block *
-create_bm_block_list(unsigned int nr_blocks, struct chain_allocator *ca)
+static int create_bm_block_list(unsigned long pages,
+				struct list_head *list,
+				struct chain_allocator *ca)
 {
-	struct bm_block *bblist = NULL;
+	unsigned int nr_blocks = DIV_ROUND_UP(pages, BM_BITS_PER_BLOCK);
 
 	while (nr_blocks-- > 0) {
 		struct bm_block *bb;
 
 		bb = chain_alloc(ca, sizeof(struct bm_block));
 		if (!bb)
-			return NULL;
-
-		bb->next = bblist;
-		bblist = bb;
+			return -ENOMEM;
+		list_add(&bb->hook, list);
+	}
+
+	return 0;
+}
+
+struct mem_extent {
+	struct list_head hook;
+	unsigned long start;
+	unsigned long end;
+};
+
+/**
+ *	free_mem_extents - free a list of memory extents
+ *	@list - list of extents to empty
+ */
+static void free_mem_extents(struct list_head *list)
+{
+	struct mem_extent *ext, *aux;
+
+	list_for_each_entry_safe(ext, aux, list, hook) {
+		list_del(&ext->hook);
+		kfree(ext);
 	}
-	return bblist;
 }
 
 /**
- *	create_zone_bm_list - create a list of zone bitmap objects
+ *	create_mem_extents - create a list of memory extents representing
+ *	                     contiguous ranges of PFNs
+ *	@list - list to put the extents into
+ *	@gfp_mask - mask to use for memory allocations
  */
-
-static inline struct zone_bitmap *
-create_zone_bm_list(unsigned int nr_zones, struct chain_allocator *ca)
+static int create_mem_extents(struct list_head *list, gfp_t gfp_mask)
 {
-	struct zone_bitmap *zbmlist = NULL;
+	struct zone *zone;
 
-	while (nr_zones-- > 0) {
-		struct zone_bitmap *zbm;
+	INIT_LIST_HEAD(list);
 
-		zbm = chain_alloc(ca, sizeof(struct zone_bitmap));
-		if (!zbm)
-			return NULL;
+	for_each_zone(zone) {
+		unsigned long zone_start, zone_end;
+		struct mem_extent *ext, *cur, *aux;
 
-		zbm->next = zbmlist;
-		zbmlist = zbm;
+		if (!populated_zone(zone))
+			continue;
+
+		zone_start = zone->zone_start_pfn;
+		zone_end = zone->zone_start_pfn + zone->spanned_pages;
+
+		list_for_each_entry(ext, list, hook)
+			if (zone_start <= ext->end)
+				break;
+
+		if (&ext->hook == list || zone_end < ext->start) {
+			/* New extent is necessary */
+			struct mem_extent *new_ext;
+
+			new_ext = kzalloc(sizeof(struct mem_extent), gfp_mask);
+			if (!new_ext) {
+				free_mem_extents(list);
+				return -ENOMEM;
+			}
+			new_ext->start = zone_start;
+			new_ext->end = zone_end;
+			list_add_tail(&new_ext->hook, &ext->hook);
+			continue;
+		}
+
+		/* Merge this zone's range of PFNs with the existing one */
+		if (zone_start < ext->start)
+			ext->start = zone_start;
+		if (zone_end > ext->end)
+			ext->end = zone_end;
+
+		/* More merging may be possible */
+		cur = ext;
+		list_for_each_entry_safe_continue(cur, aux, list, hook) {
+			if (zone_end < cur->start)
+				break;
+			if (zone_end < cur->end)
+				ext->end = cur->end;
+			list_del(&cur->hook);
+			kfree(cur);
+		}
 	}
-	return zbmlist;
+
+	return 0;
 }
 
 /**
   *	memory_bm_create - allocate memory for a memory bitmap
   */
-
 static int
 memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed)
 {
 	struct chain_allocator ca;
-	struct zone *zone;
-	struct zone_bitmap *zone_bm;
-	struct bm_block *bb;
-	unsigned int nr;
+	struct list_head mem_extents;
+	struct mem_extent *ext;
+	int error;
 
 	chain_init(&ca, gfp_mask, safe_needed);
+	INIT_LIST_HEAD(&bm->blocks);
 
-	/* Compute the number of zones */
-	nr = 0;
-	for_each_zone(zone)
-		if (populated_zone(zone))
-			nr++;
+	error = create_mem_extents(&mem_extents, gfp_mask);
+	if (error)
+		return error;
 
-	/* Allocate the list of zones bitmap objects */
-	zone_bm = create_zone_bm_list(nr, &ca);
-	bm->zone_bm_list = zone_bm;
-	if (!zone_bm) {
-		chain_free(&ca, PG_UNSAFE_CLEAR);
-		return -ENOMEM;
-	}
+	list_for_each_entry(ext, &mem_extents, hook) {
+		struct bm_block *bb;
+		unsigned long pfn = ext->start;
+		unsigned long pages = ext->end - ext->start;
 
-	/* Initialize the zone bitmap objects */
-	for_each_zone(zone) {
-		unsigned long pfn;
+		bb = list_entry(bm->blocks.prev, struct bm_block, hook);
 
-		if (!populated_zone(zone))
-			continue;
+		error = create_bm_block_list(pages, bm->blocks.prev, &ca);
+		if (error)
+			goto Error;
 
-		zone_bm->start_pfn = zone->zone_start_pfn;
-		zone_bm->end_pfn = zone->zone_start_pfn + zone->spanned_pages;
-		/* Allocate the list of bitmap block objects */
-		nr = DIV_ROUND_UP(zone->spanned_pages, BM_BITS_PER_BLOCK);
-		bb = create_bm_block_list(nr, &ca);
-		zone_bm->bm_blocks = bb;
-		zone_bm->cur_block = bb;
-		if (!bb)
-			goto Free;
-
-		nr = zone->spanned_pages;
-		pfn = zone->zone_start_pfn;
-		/* Initialize the bitmap block objects */
-		while (bb) {
-			unsigned long *ptr;
-
-			ptr = get_image_page(gfp_mask, safe_needed);
-			bb->data = ptr;
-			if (!ptr)
-				goto Free;
+		list_for_each_entry_continue(bb, &bm->blocks, hook) {
+			bb->data = get_image_page(gfp_mask, safe_needed);
+			if (!bb->data) {
+				error = -ENOMEM;
+				goto Error;
+			}
 
 			bb->start_pfn = pfn;
-			if (nr >= BM_BITS_PER_BLOCK) {
+			if (pages >= BM_BITS_PER_BLOCK) {
 				pfn += BM_BITS_PER_BLOCK;
-				nr -= BM_BITS_PER_BLOCK;
+				pages -= BM_BITS_PER_BLOCK;
 			} else {
 				/* This is executed only once in the loop */
-				pfn += nr;
+				pfn += pages;
 			}
 			bb->end_pfn = pfn;
-			bb = bb->next;
 		}
-		zone_bm = zone_bm->next;
 	}
+
 	bm->p_list = ca.chain;
 	memory_bm_position_reset(bm);
-	return 0;
+ Exit:
+	free_mem_extents(&mem_extents);
+	return error;
 
- Free:
+ Error:
 	bm->p_list = ca.chain;
 	memory_bm_free(bm, PG_UNSAFE_CLEAR);
-	return -ENOMEM;
+	goto Exit;
 }
 
 /**
   *	memory_bm_free - free memory occupied by the memory bitmap @bm
   */
-
 static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free)
 {
-	struct zone_bitmap *zone_bm;
+	struct bm_block *bb;
 
-	/* Free the list of bit blocks for each zone_bitmap object */
-	zone_bm = bm->zone_bm_list;
-	while (zone_bm) {
-		struct bm_block *bb;
+	list_for_each_entry(bb, &bm->blocks, hook)
+		if (bb->data)
+			free_image_page(bb->data, clear_nosave_free);
 
-		bb = zone_bm->bm_blocks;
-		while (bb) {
-			if (bb->data)
-				free_image_page(bb->data, clear_nosave_free);
-			bb = bb->next;
-		}
-		zone_bm = zone_bm->next;
-	}
 	free_list_of_pages(bm->p_list, clear_nosave_free);
-	bm->zone_bm_list = NULL;
+
+	INIT_LIST_HEAD(&bm->blocks);
 }
 
 /**
@@ -437,38 +452,33 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free)
  *	to given pfn.  The cur_zone_bm member of @bm and the cur_block member
  *	of @bm->cur_zone_bm are updated.
  */
-
 static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
 				void **addr, unsigned int *bit_nr)
 {
-	struct zone_bitmap *zone_bm;
 	struct bm_block *bb;
 
-	/* Check if the pfn is from the current zone */
-	zone_bm = bm->cur.zone_bm;
-	if (pfn < zone_bm->start_pfn || pfn >= zone_bm->end_pfn) {
-		zone_bm = bm->zone_bm_list;
-		/* We don't assume that the zones are sorted by pfns */
-		while (pfn < zone_bm->start_pfn || pfn >= zone_bm->end_pfn) {
-			zone_bm = zone_bm->next;
-
-			if (!zone_bm)
-				return -EFAULT;
-		}
-		bm->cur.zone_bm = zone_bm;
-	}
-	/* Check if the pfn corresponds to the current bitmap block */
-	bb = zone_bm->cur_block;
+	/*
+	 * Check if the pfn corresponds to the current bitmap block and find
+	 * the block where it fits if this is not the case.
+	 */
+	bb = bm->cur.block;
 	if (pfn < bb->start_pfn)
-		bb = zone_bm->bm_blocks;
+		list_for_each_entry_continue_reverse(bb, &bm->blocks, hook)
+			if (pfn >= bb->start_pfn)
+				break;
 
-	while (pfn >= bb->end_pfn) {
-		bb = bb->next;
+	if (pfn >= bb->end_pfn)
+		list_for_each_entry_continue(bb, &bm->blocks, hook)
+			if (pfn >= bb->start_pfn && pfn < bb->end_pfn)
+				break;
 
-		BUG_ON(!bb);
-	}
-	zone_bm->cur_block = bb;
+	if (&bb->hook == &bm->blocks)
+		return -EFAULT;
+
+	/* The block has been found */
+	bm->cur.block = bb;
 	pfn -= bb->start_pfn;
+	bm->cur.bit = pfn + 1;
 	*bit_nr = pfn;
 	*addr = bb->data;
 	return 0;
@@ -519,6 +529,14 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
 	return test_bit(bit, addr);
 }
 
+static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn)
+{
+	void *addr;
+	unsigned int bit;
+
+	return !memory_bm_find_bit(bm, pfn, &addr, &bit);
+}
+
 /**
  *	memory_bm_next_pfn - find the pfn that corresponds to the next set bit
  *	in the bitmap @bm.  If the pfn cannot be found, BM_END_OF_MAP is
@@ -530,29 +548,21 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
 
 static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm)
 {
-	struct zone_bitmap *zone_bm;
 	struct bm_block *bb;
 	int bit;
 
+	bb = bm->cur.block;
 	do {
-		bb = bm->cur.block;
-		do {
-			bit = bm->cur.bit;
-			bit = find_next_bit(bb->data, bm_block_bits(bb), bit);
-			if (bit < bm_block_bits(bb))
-				goto Return_pfn;
+		bit = bm->cur.bit;
+		bit = find_next_bit(bb->data, bm_block_bits(bb), bit);
+		if (bit < bm_block_bits(bb))
+			goto Return_pfn;
+
+		bb = list_entry(bb->hook.next, struct bm_block, hook);
+		bm->cur.block = bb;
+		bm->cur.bit = 0;
+	} while (&bb->hook != &bm->blocks);
 
-			bb = bb->next;
-			bm->cur.block = bb;
-			bm->cur.bit = 0;
-		} while (bb);
-		zone_bm = bm->cur.zone_bm->next;
-		if (zone_bm) {
-			bm->cur.zone_bm = zone_bm;
-			bm->cur.block = zone_bm->bm_blocks;
-			bm->cur.bit = 0;
-		}
-	} while (zone_bm);
 	memory_bm_position_reset(bm);
 	return BM_END_OF_MAP;
 
@@ -808,8 +818,7 @@ static unsigned int count_free_highmem_pages(void)
  *	We should save the page if it isn't Nosave or NosaveFree, or Reserved,
  *	and it isn't a part of a free chunk of pages.
  */
-
-static struct page *saveable_highmem_page(unsigned long pfn)
+static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn)
 {
 	struct page *page;
 
@@ -817,6 +826,8 @@ static struct page *saveable_highmem_page(unsigned long pfn)
 		return NULL;
 
 	page = pfn_to_page(pfn);
+	if (page_zone(page) != zone)
+		return NULL;
 
 	BUG_ON(!PageHighMem(page));
 
@@ -846,13 +857,16 @@ unsigned int count_highmem_pages(void)
 		mark_free_pages(zone);
 		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
 		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
-			if (saveable_highmem_page(pfn))
+			if (saveable_highmem_page(zone, pfn))
 				n++;
 	}
 	return n;
 }
 #else
-static inline void *saveable_highmem_page(unsigned long pfn) { return NULL; }
+static inline void *saveable_highmem_page(struct zone *z, unsigned long p)
+{
+	return NULL;
+}
 #endif /* CONFIG_HIGHMEM */
 
 /**
@@ -863,8 +877,7 @@ static inline void *saveable_highmem_page(unsigned long pfn) { return NULL; }
  *	of pages statically defined as 'unsaveable', and it isn't a part of
  *	a free chunk of pages.
  */
-
-static struct page *saveable_page(unsigned long pfn)
+static struct page *saveable_page(struct zone *zone, unsigned long pfn)
 {
 	struct page *page;
 
@@ -872,6 +885,8 @@ static struct page *saveable_page(unsigned long pfn)
 		return NULL;
 
 	page = pfn_to_page(pfn);
+	if (page_zone(page) != zone)
+		return NULL;
 
 	BUG_ON(PageHighMem(page));
 
@@ -903,7 +918,7 @@ unsigned int count_data_pages(void)
 		mark_free_pages(zone);
 		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
 		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
-			if(saveable_page(pfn))
+			if (saveable_page(zone, pfn))
 				n++;
 	}
 	return n;
@@ -944,7 +959,7 @@ static inline struct page *
 page_is_saveable(struct zone *zone, unsigned long pfn)
 {
 	return is_highmem(zone) ?
-			saveable_highmem_page(pfn) : saveable_page(pfn);
+		saveable_highmem_page(zone, pfn) : saveable_page(zone, pfn);
 }
 
 static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
@@ -966,7 +981,7 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 			 * data modified by kmap_atomic()
 			 */
 			safe_copy_page(buffer, s_page);
-			dst = kmap_atomic(pfn_to_page(dst_pfn), KM_USER0);
+			dst = kmap_atomic(d_page, KM_USER0);
 			memcpy(dst, buffer, PAGE_SIZE);
 			kunmap_atomic(dst, KM_USER0);
 		} else {
@@ -975,7 +990,7 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 	}
 }
 #else
-#define page_is_saveable(zone, pfn)	saveable_page(pfn)
+#define page_is_saveable(zone, pfn)	saveable_page(zone, pfn)
 
 static inline void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 {
@@ -1459,9 +1474,7 @@ load_header(struct swsusp_info *info)
  *	unpack_orig_pfns - for each element of @buf[] (1 page at a time) set
  *	the corresponding bit in the memory bitmap @bm
  */
-
-static inline void
-unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
+static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
 {
 	int j;
 
@@ -1469,8 +1482,13 @@ unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
 		if (unlikely(buf[j] == BM_END_OF_MAP))
 			break;
 
-		memory_bm_set_bit(bm, buf[j]);
+		if (memory_bm_pfn_present(bm, buf[j]))
+			memory_bm_set_bit(bm, buf[j]);
+		else
+			return -EFAULT;
 	}
+
+	return 0;
 }
 
 /* List of "safe" pages that may be used to store data loaded from the suspend
@@ -1608,7 +1626,7 @@ get_highmem_page_buffer(struct page *page, struct chain_allocator *ca)
 	pbe = chain_alloc(ca, sizeof(struct highmem_pbe));
 	if (!pbe) {
 		swsusp_free();
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	pbe->orig_page = page;
 	if (safe_highmem_pages > 0) {
@@ -1677,7 +1695,7 @@ prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p)
 static inline void *
 get_highmem_page_buffer(struct page *page, struct chain_allocator *ca)
 {
-	return NULL;
+	return ERR_PTR(-EINVAL);
 }
 
 static inline void copy_last_highmem_page(void) {}
@@ -1788,8 +1806,13 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
 static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
 {
 	struct pbe *pbe;
-	struct page *page = pfn_to_page(memory_bm_next_pfn(bm));
+	struct page *page;
+	unsigned long pfn = memory_bm_next_pfn(bm);
 
+	if (pfn == BM_END_OF_MAP)
+		return ERR_PTR(-EFAULT);
+
+	page = pfn_to_page(pfn);
 	if (PageHighMem(page))
 		return get_highmem_page_buffer(page, ca);
 
@@ -1805,7 +1828,7 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
 	pbe = chain_alloc(ca, sizeof(struct pbe));
 	if (!pbe) {
 		swsusp_free();
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	pbe->orig_address = page_address(page);
 	pbe->address = safe_pages_list;
@@ -1868,7 +1891,10 @@ int snapshot_write_next(struct snapshot_handle *handle, size_t count)
 				return error;
 
 		} else if (handle->prev <= nr_meta_pages) {
-			unpack_orig_pfns(buffer, &copy_bm);
+			error = unpack_orig_pfns(buffer, &copy_bm);
+			if (error)
+				return error;
+
 			if (handle->prev == nr_meta_pages) {
 				error = prepare_image(&orig_bm, &copy_bm);
 				if (error)
@@ -1879,12 +1905,14 @@ int snapshot_write_next(struct snapshot_handle *handle, size_t count)
 				restore_pblist = NULL;
 				handle->buffer = get_buffer(&orig_bm, &ca);
 				handle->sync_read = 0;
-				if (!handle->buffer)
-					return -ENOMEM;
+				if (IS_ERR(handle->buffer))
+					return PTR_ERR(handle->buffer);
 			}
 		} else {
 			copy_last_highmem_page();
 			handle->buffer = get_buffer(&orig_bm, &ca);
+			if (IS_ERR(handle->buffer))
+				return PTR_ERR(handle->buffer);
 			if (handle->buffer != buffer)
 				handle->sync_read = 0;
 		}

kernel/power/swsusp.c

@@ -262,3 +262,125 @@ int swsusp_shrink_memory(void)
 
 	return 0;
 }
+
+/*
+ * Platforms, like ACPI, may want us to save some memory used by them during
+ * hibernation and to restore the contents of this memory during the subsequent
+ * resume.  The code below implements a mechanism allowing us to do that.
+ */
+
+struct nvs_page {
+	unsigned long phys_start;
+	unsigned int size;
+	void *kaddr;
+	void *data;
+	struct list_head node;
+};
+
+static LIST_HEAD(nvs_list);
+
+/**
+ *	hibernate_nvs_register - register platform NVS memory region to save
+ *	@start - physical address of the region
+ *	@size - size of the region
+ *
+ *	The NVS region need not be page-aligned (both ends) and we arrange
+ *	things so that the data from page-aligned addresses in this region will
+ *	be copied into separate RAM pages.
+ */
+int hibernate_nvs_register(unsigned long start, unsigned long size)
+{
+	struct nvs_page *entry, *next;
+
+	while (size > 0) {
+		unsigned int nr_bytes;
+
+		entry = kzalloc(sizeof(struct nvs_page), GFP_KERNEL);
+		if (!entry)
+			goto Error;
+
+		list_add_tail(&entry->node, &nvs_list);
+		entry->phys_start = start;
+		nr_bytes = PAGE_SIZE - (start & ~PAGE_MASK);
+		entry->size = (size < nr_bytes) ? size : nr_bytes;
+
+		start += entry->size;
+		size -= entry->size;
+	}
+	return 0;
+
+ Error:
+	list_for_each_entry_safe(entry, next, &nvs_list, node) {
+		list_del(&entry->node);
+		kfree(entry);
+	}
+	return -ENOMEM;
+}
+
+/**
+ *	hibernate_nvs_free - free data pages allocated for saving NVS regions
+ */
+void hibernate_nvs_free(void)
+{
+	struct nvs_page *entry;
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data) {
+			free_page((unsigned long)entry->data);
+			entry->data = NULL;
+			if (entry->kaddr) {
+				iounmap(entry->kaddr);
+				entry->kaddr = NULL;
+			}
+		}
+}
+
+/**
+ *	hibernate_nvs_alloc - allocate memory necessary for saving NVS regions
+ */
+int hibernate_nvs_alloc(void)
+{
+	struct nvs_page *entry;
+
+	list_for_each_entry(entry, &nvs_list, node) {
+		entry->data = (void *)__get_free_page(GFP_KERNEL);
+		if (!entry->data) {
+			hibernate_nvs_free();
+			return -ENOMEM;
+		}
+	}
+	return 0;
+}
+
+/**
+ *	hibernate_nvs_save - save NVS memory regions
+ */
+void hibernate_nvs_save(void)
+{
+	struct nvs_page *entry;
+
+	printk(KERN_INFO "PM: Saving platform NVS memory\n");
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data) {
+			entry->kaddr = ioremap(entry->phys_start, entry->size);
+			memcpy(entry->data, entry->kaddr, entry->size);
+		}
+}
+
+/**
+ *	hibernate_nvs_restore - restore NVS memory regions
+ *
+ *	This function is going to be called with interrupts disabled, so it
+ *	cannot iounmap the virtual addresses used to access the NVS region.
+ */
+void hibernate_nvs_restore(void)
+{
+	struct nvs_page *entry;
+
+	printk(KERN_INFO "PM: Restoring platform NVS memory\n");
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data)
+			memcpy(entry->kaddr, entry->data, entry->size);
+}

kernel/res_counter.c

@@ -15,10 +15,11 @@
 #include <linux/uaccess.h>
 #include <linux/mm.h>
 
-void res_counter_init(struct res_counter *counter)
+void res_counter_init(struct res_counter *counter, struct res_counter *parent)
 {
 	spin_lock_init(&counter->lock);
 	counter->limit = (unsigned long long)LLONG_MAX;
+	counter->parent = parent;
 }
 
 int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
@@ -34,14 +35,34 @@ int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
 	return 0;
 }
 
-int res_counter_charge(struct res_counter *counter, unsigned long val)
+int res_counter_charge(struct res_counter *counter, unsigned long val,
+			struct res_counter **limit_fail_at)
 {
 	int ret;
 	unsigned long flags;
+	struct res_counter *c, *u;
 
-	spin_lock_irqsave(&counter->lock, flags);
-	ret = res_counter_charge_locked(counter, val);
-	spin_unlock_irqrestore(&counter->lock, flags);
+	*limit_fail_at = NULL;
+	local_irq_save(flags);
+	for (c = counter; c != NULL; c = c->parent) {
+		spin_lock(&c->lock);
+		ret = res_counter_charge_locked(c, val);
+		spin_unlock(&c->lock);
+		if (ret < 0) {
+			*limit_fail_at = c;
+			goto undo;
+		}
+	}
+	ret = 0;
+	goto done;
+undo:
+	for (u = counter; u != c; u = u->parent) {
+		spin_lock(&u->lock);
+		res_counter_uncharge_locked(u, val);
+		spin_unlock(&u->lock);
+	}
+done:
+	local_irq_restore(flags);
 	return ret;
 }
 
@@ -56,10 +77,15 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
 void res_counter_uncharge(struct res_counter *counter, unsigned long val)
 {
 	unsigned long flags;
+	struct res_counter *c;
 
-	spin_lock_irqsave(&counter->lock, flags);
-	res_counter_uncharge_locked(counter, val);
-	spin_unlock_irqrestore(&counter->lock, flags);
+	local_irq_save(flags);
+	for (c = counter; c != NULL; c = c->parent) {
+		spin_lock(&c->lock);
+		res_counter_uncharge_locked(c, val);
+		spin_unlock(&c->lock);
+	}
+	local_irq_restore(flags);
 }
 
 

kernel/resource.c

@@ -623,7 +623,7 @@ resource_size_t resource_alignment(struct resource *res)
  */
 struct resource * __request_region(struct resource *parent,
 				   resource_size_t start, resource_size_t n,
-				   const char *name)
+				   const char *name, int flags)
 {
 	struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL);
 
@@ -634,6 +634,7 @@ struct resource * __request_region(struct resource *parent,
 	res->start = start;
 	res->end = start + n - 1;
 	res->flags = IORESOURCE_BUSY;
+	res->flags |= flags;
 
 	write_lock(&resource_lock);
 
@@ -679,7 +680,7 @@ int __check_region(struct resource *parent, resource_size_t start,
 {
 	struct resource * res;
 
-	res = __request_region(parent, start, n, "check-region");
+	res = __request_region(parent, start, n, "check-region", 0);
 	if (!res)
 		return -EBUSY;
 
@@ -776,7 +777,7 @@ struct resource * __devm_request_region(struct device *dev,
 	dr->start = start;
 	dr->n = n;
 
-	res = __request_region(parent, start, n, name);
+	res = __request_region(parent, start, n, name, 0);
 	if (res)
 		devres_add(dev, dr);
 	else
@@ -876,3 +877,57 @@ int iomem_map_sanity_check(resource_size_t addr, unsigned long size)
 
 	return err;
 }
+
+#ifdef CONFIG_STRICT_DEVMEM
+static int strict_iomem_checks = 1;
+#else
+static int strict_iomem_checks;
+#endif
+
+/*
+ * check if an address is reserved in the iomem resource tree
+ * returns 1 if reserved, 0 if not reserved.
+ */
+int iomem_is_exclusive(u64 addr)
+{
+	struct resource *p = &iomem_resource;
+	int err = 0;
+	loff_t l;
+	int size = PAGE_SIZE;
+
+	if (!strict_iomem_checks)
+		return 0;
+
+	addr = addr & PAGE_MASK;
+
+	read_lock(&resource_lock);
+	for (p = p->child; p ; p = r_next(NULL, p, &l)) {
+		/*
+		 * We can probably skip the resources without
+		 * IORESOURCE_IO attribute?
+		 */
+		if (p->start >= addr + size)
+			break;
+		if (p->end < addr)
+			continue;
+		if (p->flags & IORESOURCE_BUSY &&
+		     p->flags & IORESOURCE_EXCLUSIVE) {
+			err = 1;
+			break;
+		}
+	}
+	read_unlock(&resource_lock);
+
+	return err;
+}
+
+static int __init strict_iomem(char *str)
+{
+	if (strstr(str, "relaxed"))
+		strict_iomem_checks = 0;
+	if (strstr(str, "strict"))
+		strict_iomem_checks = 1;
+	return 1;
+}
+
+__setup("iomem=", strict_iomem);

kernel/sched.c

@@ -3728,8 +3728,13 @@ redo:
 		}
 
 		double_unlock_balance(this_rq, busiest);
+		/*
+		 * Should not call ttwu while holding a rq->lock
+		 */
+		spin_unlock(&this_rq->lock);
 		if (active_balance)
 			wake_up_process(busiest->migration_thread);
+		spin_lock(&this_rq->lock);
 
 	} else
 		sd->nr_balance_failed = 0;

kernel/sched_fair.c

@@ -1617,8 +1617,6 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 	}
 }
 
-#define swap(a, b) do { typeof(a) tmp = (a); (a) = (b); (b) = tmp; } while (0)
-
 /*
  * Share the fairness runtime between parent and child, thus the
  * total amount of pressure for CPU stays equal - new tasks

kernel/sysctl.c

@@ -82,6 +82,9 @@ extern int percpu_pagelist_fraction;
 extern int compat_log;
 extern int latencytop_enabled;
 extern int sysctl_nr_open_min, sysctl_nr_open_max;
+#ifndef CONFIG_MMU
+extern int sysctl_nr_trim_pages;
+#endif
 #ifdef CONFIG_RCU_TORTURE_TEST
 extern int rcutorture_runnable;
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
@@ -1102,6 +1105,17 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec
 	},
+#else
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "nr_trim_pages",
+		.data		= &sysctl_nr_trim_pages,
+		.maxlen		= sizeof(sysctl_nr_trim_pages),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+	},
 #endif
 	{
 		.ctl_name	= VM_LAPTOP_MODE,

kernel/trace/ring_buffer.c

@@ -168,7 +168,13 @@ rb_event_length(struct ring_buffer_event *event)
  */
 unsigned ring_buffer_event_length(struct ring_buffer_event *event)
 {
-	return rb_event_length(event);
+	unsigned length = rb_event_length(event);
+	if (event->type != RINGBUF_TYPE_DATA)
+		return length;
+	length -= RB_EVNT_HDR_SIZE;
+	if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0]))
+                length -= sizeof(event->array[0]);
+	return length;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_event_length);