Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

 * Fix include order for bison/flex-generated C files, from Ben Hutchings

 * Build fixes and documentation corrections from David Ahern

 * Group parsing support, from Jiri Olsa

 * UI/gtk refactorings and improvements from Namhyung Kim

 * NULL deref fix for perf script, from Namhyung Kim

 * Assorted cleanups from Robert Richter

 * Let O= makes handle relative paths, from Steven Rostedt

 * perf script python fixes, from Feng Tang.

 * Improve 'perf lock' error message when the needed tracepoints
   are not present, from David Ahern.

 * Initial bash completion support, from Frederic Weisbecker

 * Allow building without libelf, from Namhyung Kim.

 * Support DWARF CFI based unwind to have callchains when %bp
   based unwinding is not possible, from Jiri Olsa.

 * Symbol resolution fixes, while fixing support PPC64 files with an .opt ELF
   section was the end goal, several fixes for code that handles all
   architectures and cleanups are included, from Cody Schafer.

 * Add a description for the JIT interface, from Andi Kleen.

 * Assorted fixes for Documentation and build in 32 bit, from Robert Richter

 * Add support for non-tracepoint events in perf script python, from Feng Tang

 * Cache the libtraceevent event_format associated to each evsel early, so that we
   avoid relookups, i.e. calling pevent_find_event repeatedly when processing
   tracepoint events.

   [ This is to reduce the surface contact with libtraceevents and make clear what
     is that the perf tools needs from that lib: so far parsing the common and per
     event fields. ]

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

55 files changed, 2399 insertions, 1516 deletions

diff --git a/kernel/async.c b/kernel/async.c
index bd0c168a3bb..9d311838485 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -62,8 +62,10 @@ static async_cookie_t next_cookie = 1;
 #define MAX_WORK	32768
 
 static LIST_HEAD(async_pending);
-static LIST_HEAD(async_running);
+static ASYNC_DOMAIN(async_running);
+static LIST_HEAD(async_domains);
 static DEFINE_SPINLOCK(async_lock);
+static DEFINE_MUTEX(async_register_mutex);
 
 struct async_entry {
 	struct list_head	list;
@@ -71,7 +73,7 @@ struct async_entry {
 	async_cookie_t		cookie;
 	async_func_ptr		*func;
 	void			*data;
-	struct list_head	*running;
+	struct async_domain	*running;
 };
 
 static DECLARE_WAIT_QUEUE_HEAD(async_done);
@@ -82,13 +84,12 @@ static atomic_t entry_count;
 /*
  * MUST be called with the lock held!
  */
-static async_cookie_t  __lowest_in_progress(struct list_head *running)
+static async_cookie_t  __lowest_in_progress(struct async_domain *running)
 {
 	struct async_entry *entry;
 
-	if (!list_empty(running)) {
-		entry = list_first_entry(running,
-			struct async_entry, list);
+	if (!list_empty(&running->domain)) {
+		entry = list_first_entry(&running->domain, typeof(*entry), list);
 		return entry->cookie;
 	}
 
@@ -99,7 +100,7 @@ static async_cookie_t  __lowest_in_progress(struct list_head *running)
 	return next_cookie;	/* "infinity" value */
 }
 
-static async_cookie_t  lowest_in_progress(struct list_head *running)
+static async_cookie_t  lowest_in_progress(struct async_domain *running)
 {
 	unsigned long flags;
 	async_cookie_t ret;
@@ -119,10 +120,11 @@ static void async_run_entry_fn(struct work_struct *work)
 		container_of(work, struct async_entry, work);
 	unsigned long flags;
 	ktime_t uninitialized_var(calltime), delta, rettime;
+	struct async_domain *running = entry->running;
 
 	/* 1) move self to the running queue */
 	spin_lock_irqsave(&async_lock, flags);
-	list_move_tail(&entry->list, entry->running);
+	list_move_tail(&entry->list, &running->domain);
 	spin_unlock_irqrestore(&async_lock, flags);
 
 	/* 2) run (and print duration) */
@@ -145,6 +147,8 @@ static void async_run_entry_fn(struct work_struct *work)
 	/* 3) remove self from the running queue */
 	spin_lock_irqsave(&async_lock, flags);
 	list_del(&entry->list);
+	if (running->registered && --running->count == 0)
+		list_del_init(&running->node);
 
 	/* 4) free the entry */
 	kfree(entry);
@@ -156,7 +160,7 @@ static void async_run_entry_fn(struct work_struct *work)
 	wake_up(&async_done);
 }
 
-static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct list_head *running)
+static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct async_domain *running)
 {
 	struct async_entry *entry;
 	unsigned long flags;
@@ -187,6 +191,8 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct l
 	spin_lock_irqsave(&async_lock, flags);
 	newcookie = entry->cookie = next_cookie++;
 	list_add_tail(&entry->list, &async_pending);
+	if (running->registered && running->count++ == 0)
+		list_add_tail(&running->node, &async_domains);
 	atomic_inc(&entry_count);
 	spin_unlock_irqrestore(&async_lock, flags);
 
@@ -223,7 +229,7 @@ EXPORT_SYMBOL_GPL(async_schedule);
  * Note: This function may be called from atomic or non-atomic contexts.
  */
 async_cookie_t async_schedule_domain(async_func_ptr *ptr, void *data,
-				     struct list_head *running)
+				     struct async_domain *running)
 {
 	return __async_schedule(ptr, data, running);
 }
@@ -236,22 +242,52 @@ EXPORT_SYMBOL_GPL(async_schedule_domain);
  */
 void async_synchronize_full(void)
 {
+	mutex_lock(&async_register_mutex);
 	do {
-		async_synchronize_cookie(next_cookie);
-	} while (!list_empty(&async_running) || !list_empty(&async_pending));
+		struct async_domain *domain = NULL;
+
+		spin_lock_irq(&async_lock);
+		if (!list_empty(&async_domains))
+			domain = list_first_entry(&async_domains, typeof(*domain), node);
+		spin_unlock_irq(&async_lock);
+
+		async_synchronize_cookie_domain(next_cookie, domain);
+	} while (!list_empty(&async_domains));
+	mutex_unlock(&async_register_mutex);
 }
 EXPORT_SYMBOL_GPL(async_synchronize_full);
 
 /**
+ * async_unregister_domain - ensure no more anonymous waiters on this domain
+ * @domain: idle domain to flush out of any async_synchronize_full instances
+ *
+ * async_synchronize_{cookie|full}_domain() are not flushed since callers
+ * of these routines should know the lifetime of @domain
+ *
+ * Prefer ASYNC_DOMAIN_EXCLUSIVE() declarations over flushing
+ */
+void async_unregister_domain(struct async_domain *domain)
+{
+	mutex_lock(&async_register_mutex);
+	spin_lock_irq(&async_lock);
+	WARN_ON(!domain->registered || !list_empty(&domain->node) ||
+		!list_empty(&domain->domain));
+	domain->registered = 0;
+	spin_unlock_irq(&async_lock);
+	mutex_unlock(&async_register_mutex);
+}
+EXPORT_SYMBOL_GPL(async_unregister_domain);
+
+/**
  * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain
- * @list: running list to synchronize on
+ * @domain: running list to synchronize on
  *
  * This function waits until all asynchronous function calls for the
- * synchronization domain specified by the running list @list have been done.
+ * synchronization domain specified by the running list @domain have been done.
  */
-void async_synchronize_full_domain(struct list_head *list)
+void async_synchronize_full_domain(struct async_domain *domain)
 {
-	async_synchronize_cookie_domain(next_cookie, list);
+	async_synchronize_cookie_domain(next_cookie, domain);
 }
 EXPORT_SYMBOL_GPL(async_synchronize_full_domain);
 
@@ -261,14 +297,16 @@ EXPORT_SYMBOL_GPL(async_synchronize_full_domain);
  * @running: running list to synchronize on
  *
  * This function waits until all asynchronous function calls for the
- * synchronization domain specified by the running list @list submitted
+ * synchronization domain specified by running list @running submitted
  * prior to @cookie have been done.
  */
-void async_synchronize_cookie_domain(async_cookie_t cookie,
-				     struct list_head *running)
+void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain *running)
 {
 	ktime_t uninitialized_var(starttime), delta, endtime;
 
+	if (!running)
+		return;
+
 	if (initcall_debug && system_state == SYSTEM_BOOTING) {
 		printk(KERN_DEBUG "async_waiting @ %i\n", task_pid_nr(current));
 		starttime = ktime_get();
diff --git a/kernel/audit.c b/kernel/audit.c
index 1c7f2c61416..ea3b7b6191c 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -384,7 +384,7 @@ static void audit_hold_skb(struct sk_buff *skb)
 static void audit_printk_skb(struct sk_buff *skb)
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(skb);
-	char *data = NLMSG_DATA(nlh);
+	char *data = nlmsg_data(nlh);
 
 	if (nlh->nlmsg_type != AUDIT_EOE) {
 		if (printk_ratelimit())
@@ -516,14 +516,15 @@ struct sk_buff *audit_make_reply(int pid, int seq, int type, int done,
 	if (!skb)
 		return NULL;
 
-	nlh	= NLMSG_NEW(skb, pid, seq, t, size, flags);
-	data	= NLMSG_DATA(nlh);
+	nlh	= nlmsg_put(skb, pid, seq, t, size, flags);
+	if (!nlh)
+		goto out_kfree_skb;
+	data = nlmsg_data(nlh);
 	memcpy(data, payload, size);
 	return skb;
 
-nlmsg_failure:			/* Used by NLMSG_NEW */
-	if (skb)
-		kfree_skb(skb);
+out_kfree_skb:
+	kfree_skb(skb);
 	return NULL;
 }
 
@@ -680,7 +681,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	sessionid = audit_get_sessionid(current);
 	security_task_getsecid(current, &sid);
 	seq  = nlh->nlmsg_seq;
-	data = NLMSG_DATA(nlh);
+	data = nlmsg_data(nlh);
 
 	switch (msg_type) {
 	case AUDIT_GET:
@@ -961,14 +962,17 @@ static void audit_receive(struct sk_buff  *skb)
 static int __init audit_init(void)
 {
 	int i;
+	struct netlink_kernel_cfg cfg = {
+		.input	= audit_receive,
+	};
 
 	if (audit_initialized == AUDIT_DISABLED)
 		return 0;
 
 	printk(KERN_INFO "audit: initializing netlink socket (%s)\n",
 	       audit_default ? "enabled" : "disabled");
-	audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, 0,
-					   audit_receive, NULL, THIS_MODULE);
+	audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT,
+					   THIS_MODULE, &cfg);
 	if (!audit_sock)
 		audit_panic("cannot initialize netlink socket");
 	else
@@ -1060,13 +1064,15 @@ static struct audit_buffer * audit_buffer_alloc(struct audit_context *ctx,
 
 	ab->skb = nlmsg_new(AUDIT_BUFSIZ, gfp_mask);
 	if (!ab->skb)
-		goto nlmsg_failure;
+		goto err;
 
-	nlh = NLMSG_NEW(ab->skb, 0, 0, type, 0, 0);
+	nlh = nlmsg_put(ab->skb, 0, 0, type, 0, 0);
+	if (!nlh)
+		goto out_kfree_skb;
 
 	return ab;
 
-nlmsg_failure:                  /* Used by NLMSG_NEW */
+out_kfree_skb:
 	kfree_skb(ab->skb);
 	ab->skb = NULL;
 err:
@@ -1450,6 +1456,27 @@ void audit_log_key(struct audit_buffer *ab, char *key)
 }
 
 /**
+ * audit_log_link_denied - report a link restriction denial
+ * @operation: specific link opreation
+ * @link: the path that triggered the restriction
+ */
+void audit_log_link_denied(const char *operation, struct path *link)
+{
+	struct audit_buffer *ab;
+
+	ab = audit_log_start(current->audit_context, GFP_KERNEL,
+			     AUDIT_ANOM_LINK);
+	audit_log_format(ab, "op=%s action=denied", operation);
+	audit_log_format(ab, " pid=%d comm=", current->pid);
+	audit_log_untrustedstring(ab, current->comm);
+	audit_log_d_path(ab, " path=", link);
+	audit_log_format(ab, " dev=");
+	audit_log_untrustedstring(ab, link->dentry->d_inode->i_sb->s_id);
+	audit_log_format(ab, " ino=%lu", link->dentry->d_inode->i_ino);
+	audit_log_end(ab);
+}
+
+/**
  * audit_log_end - end one audit record
  * @ab: the audit_buffer
  *
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 5bf0790497e..3a5ca582ba1 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -595,7 +595,7 @@ void audit_trim_trees(void)
 
 		root_mnt = collect_mounts(&path);
 		path_put(&path);
-		if (!root_mnt)
+		if (IS_ERR(root_mnt))
 			goto skip_it;
 
 		spin_lock(&hash_lock);
@@ -669,8 +669,8 @@ int audit_add_tree_rule(struct audit_krule *rule)
 		goto Err;
 	mnt = collect_mounts(&path);
 	path_put(&path);
-	if (!mnt) {
-		err = -ENOMEM;
+	if (IS_ERR(mnt)) {
+		err = PTR_ERR(mnt);
 		goto Err;
 	}
 
@@ -719,8 +719,8 @@ int audit_tag_tree(char *old, char *new)
 		return err;
 	tagged = collect_mounts(&path2);
 	path_put(&path2);
-	if (!tagged)
-		return -ENOMEM;
+	if (IS_ERR(tagged))
+		return PTR_ERR(tagged);
 
 	err = kern_path(old, 0, &path1);
 	if (err) {
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index e683869365d..3823281401b 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -355,34 +355,15 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
 /* Get path information necessary for adding watches. */
 static int audit_get_nd(struct audit_watch *watch, struct path *parent)
 {
-	struct nameidata nd;
-	struct dentry *d;
-	int err;
-
-	err = kern_path_parent(watch->path, &nd);
-	if (err)
-		return err;
-
-	if (nd.last_type != LAST_NORM) {
-		path_put(&nd.path);
-		return -EINVAL;
-	}
-
-	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
-	d = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
-	if (IS_ERR(d)) {
-		mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
-		path_put(&nd.path);
+	struct dentry *d = kern_path_locked(watch->path, parent);
+	if (IS_ERR(d))
 		return PTR_ERR(d);
-	}
+	mutex_unlock(&parent->dentry->d_inode->i_mutex);
 	if (d->d_inode) {
 		/* update watch filter fields */
 		watch->dev = d->d_inode->i_sb->s_dev;
 		watch->ino = d->d_inode->i_ino;
 	}
-	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
-
-	*parent = nd.path;
 	dput(d);
 	return 0;
 }
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b303dfc7dce..79818507e44 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -822,7 +822,7 @@ EXPORT_SYMBOL_GPL(cgroup_unlock);
  */
 
 static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
-static struct dentry *cgroup_lookup(struct inode *, struct dentry *, struct nameidata *);
+static struct dentry *cgroup_lookup(struct inode *, struct dentry *, unsigned int);
 static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
 static int cgroup_populate_dir(struct cgroup *cgrp);
 static const struct inode_operations cgroup_dir_inode_operations;
@@ -954,7 +954,7 @@ static int cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
 
 		dget(d);
 		d_delete(d);
-		simple_unlink(d->d_inode, d);
+		simple_unlink(cgrp->dentry->d_inode, d);
 		list_del_init(&cfe->node);
 		dput(d);
 
@@ -1068,28 +1068,24 @@ 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_move(&ss->sibling, &root->subsys_list);
 			ss->root = root;
 			if (ss->bind)
 				ss->bind(cgrp);
-			mutex_unlock(&ss->hierarchy_mutex);
 			/* refcount was already taken, and we're keeping it */
 		} else if (bit & removed_bits) {
 			/* We're removing this subsystem */
 			BUG_ON(ss == NULL);
 			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(dummytop);
 			dummytop->subsys[i]->cgroup = dummytop;
 			cgrp->subsys[i] = NULL;
 			subsys[i]->root = &rootnode;
 			list_move(&ss->sibling, &rootnode.subsys_list);
-			mutex_unlock(&ss->hierarchy_mutex);
 			/* subsystem is now free - drop reference on module */
 			module_put(ss->module);
 		} else if (bit & final_bits) {
@@ -1587,7 +1583,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 	opts.new_root = new_root;
 
 	/* Locate an existing or new sb for this hierarchy */
-	sb = sget(fs_type, cgroup_test_super, cgroup_set_super, &opts);
+	sb = sget(fs_type, cgroup_test_super, cgroup_set_super, 0, &opts);
 	if (IS_ERR(sb)) {
 		ret = PTR_ERR(sb);
 		cgroup_drop_root(opts.new_root);
@@ -2570,7 +2566,7 @@ static const struct inode_operations cgroup_dir_inode_operations = {
 	.rename = cgroup_rename,
 };
 
-static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 {
 	if (dentry->d_name.len > NAME_MAX)
 		return ERR_PTR(-ENAMETOOLONG);
@@ -3915,37 +3911,6 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 		set_bit(CSS_CLEAR_CSS_REFS, &css->flags);
 }
 
-static void cgroup_lock_hierarchy(struct cgroupfs_root *root)
-{
-	/* We need to take each hierarchy_mutex in a consistent order */
-	int i;
-
-	/*
-	 * No worry about a race with rebind_subsystems that might mess up the
-	 * locking order, since both parties are under cgroup_mutex.
-	 */
-	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-		struct cgroup_subsys *ss = subsys[i];
-		if (ss == NULL)
-			continue;
-		if (ss->root == root)
-			mutex_lock(&ss->hierarchy_mutex);
-	}
-}
-
-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 == NULL)
-			continue;
-		if (ss->root == root)
-			mutex_unlock(&ss->hierarchy_mutex);
-	}
-}
-
 /*
  * cgroup_create - create a cgroup
  * @parent: cgroup that will be parent of the new cgroup
@@ -4006,9 +3971,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 			ss->post_clone(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);
@@ -4035,9 +3998,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
  err_remove:
 
-	cgroup_lock_hierarchy(root);
 	list_del(&cgrp->sibling);
-	cgroup_unlock_hierarchy(root);
 	root->number_of_cgroups--;
 
  err_destroy:
@@ -4245,10 +4206,8 @@ again:
 		list_del_init(&cgrp->release_list);
 	raw_spin_unlock(&release_list_lock);
 
-	cgroup_lock_hierarchy(cgrp->root);
 	/* delete this cgroup from parent->children */
 	list_del_init(&cgrp->sibling);
-	cgroup_unlock_hierarchy(cgrp->root);
 
 	list_del_init(&cgrp->allcg_node);
 
@@ -4322,8 +4281,6 @@ 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);
-	lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
 	ss->active = 1;
 
 	/* this function shouldn't be used with modular subsystems, since they
@@ -4450,8 +4407,6 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	}
 	write_unlock(&css_set_lock);
 
-	mutex_init(&ss->hierarchy_mutex);
-	lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
 	ss->active = 1;
 
 	/* success! */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index a4eb5227a19..14d32588ccc 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -416,7 +416,7 @@ int __cpuinit cpu_up(unsigned int cpu)
 
 	if (pgdat->node_zonelists->_zonerefs->zone == NULL) {
 		mutex_lock(&zonelists_mutex);
-		build_all_zonelists(NULL);
+		build_all_zonelists(NULL, NULL);
 		mutex_unlock(&zonelists_mutex);
 	}
 #endif
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 8c8bd652dd1..f33c7153b6d 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -147,6 +147,12 @@ typedef enum {
 	CS_SPREAD_SLAB,
 } cpuset_flagbits_t;
 
+/* the type of hotplug event */
+enum hotplug_event {
+	CPUSET_CPU_OFFLINE,
+	CPUSET_MEM_OFFLINE,
+};
+
 /* convenient tests for these bits */
 static inline int is_cpu_exclusive(const struct cpuset *cs)
 {
@@ -1990,8 +1996,36 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
 }
 
 /*
- * Walk the specified cpuset subtree and look for empty cpusets.
- * The tasks of such cpuset must be moved to a parent cpuset.
+ * Helper function to traverse cpusets.
+ * It can be used to walk the cpuset tree from top to bottom, completing
+ * one layer before dropping down to the next (thus always processing a
+ * node before any of its children).
+ */
+static struct cpuset *cpuset_next(struct list_head *queue)
+{
+	struct cpuset *cp;
+	struct cpuset *child;	/* scans child cpusets of cp */
+	struct cgroup *cont;
+
+	if (list_empty(queue))
+		return NULL;
+
+	cp = list_first_entry(queue, struct cpuset, stack_list);
+	list_del(queue->next);
+	list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
+		child = cgroup_cs(cont);
+		list_add_tail(&child->stack_list, queue);
+	}
+
+	return cp;
+}
+
+
+/*
+ * Walk the specified cpuset subtree upon a hotplug operation (CPU/Memory
+ * online/offline) and update the cpusets accordingly.
+ * For regular CPU/Mem hotplug, look for empty cpusets; the tasks of such
+ * cpuset must be moved to a parent cpuset.
  *
  * Called with cgroup_mutex held.  We take callback_mutex to modify
  * cpus_allowed and mems_allowed.
@@ -2000,50 +2034,61 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
  * before dropping down to the next.  It always processes a node before
  * any of its children.
  *
- * For now, since we lack memory hot unplug, we'll never see a cpuset
- * that has tasks along with an empty 'mems'.  But if we did see such
- * a cpuset, we'd handle it just like we do if its 'cpus' was empty.
+ * In the case of memory hot-unplug, it will remove nodes from N_HIGH_MEMORY
+ * if all present pages from a node are offlined.
  */
-static void scan_for_empty_cpusets(struct cpuset *root)
+static void
+scan_cpusets_upon_hotplug(struct cpuset *root, enum hotplug_event event)
 {
 	LIST_HEAD(queue);
-	struct cpuset *cp;	/* scans cpusets being updated */
-	struct cpuset *child;	/* scans child cpusets of cp */
-	struct cgroup *cont;
+	struct cpuset *cp;		/* scans cpusets being updated */
 	static nodemask_t oldmems;	/* protected by cgroup_mutex */
 
 	list_add_tail((struct list_head *)&root->stack_list, &queue);
 
-	while (!list_empty(&queue)) {
-		cp = list_first_entry(&queue, struct cpuset, stack_list);
-		list_del(queue.next);
-		list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
-			child = cgroup_cs(cont);
-			list_add_tail(&child->stack_list, &queue);
+	switch (event) {
+	case CPUSET_CPU_OFFLINE:
+		while ((cp = cpuset_next(&queue)) != NULL) {
+
+			/* Continue past cpusets with all cpus online */
+			if (cpumask_subset(cp->cpus_allowed, cpu_active_mask))
+				continue;
+
+			/* Re