Merge branch 'for-3.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup changes from Tejun Heo:
 "A lot of activities on cgroup side.  The big changes are focused on
  making cgroup hierarchy handling saner.

   - cgroup_rmdir() had peculiar semantics - it allowed cgroup
     destruction to be vetoed by individual controllers and tried to
     drain refcnt synchronously.  The vetoing never worked properly and
     caused good deal of contortions in cgroup.  memcg was the last
     reamining user.  Michal Hocko removed the usage and cgroup_rmdir()
     path has been simplified significantly.  This was done in a
     separate branch so that the memcg people can base further memcg
     changes on top.

   - The above allowed cleaning up cgroup lifecycle management and
     implementation of generic cgroup iterators which are used to
     improve hierarchy support.

   - cgroup_freezer updated to allow migration in and out of a frozen
     cgroup and handle hierarchy.  If a cgroup is frozen, all descendant
     cgroups are frozen.

   - netcls_cgroup and netprio_cgroup updated to handle hierarchy
     properly.

   - Various fixes and cleanups.

   - Two merge commits.  One to pull in memcg and rmdir cleanups (needed
     to build iterators).  The other pulled in cgroup/for-3.7-fixes for
     device_cgroup fixes so that further device_cgroup patches can be
     stacked on top."

Fixed up a trivial conflict in mm/memcontrol.c as per Tejun (due to
commit bea8c150a7 ("memcg: fix hotplugged memory zone oops") in master
touching code close to commit 2ef37d3fe4 ("memcg: Simplify
mem_cgroup_force_empty_list error handling") in for-3.8)

* 'for-3.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (65 commits)
  cgroup: update Documentation/cgroups/00-INDEX
  cgroup_rm_file: don't delete the uncreated files
  cgroup: remove subsystem files when remounting cgroup
  cgroup: use cgroup_addrm_files() in cgroup_clear_directory()
  cgroup: warn about broken hierarchies only after css_online
  cgroup: list_del_init() on removed events
  cgroup: fix lockdep warning for event_control
  cgroup: move list add after list head initilization
  netprio_cgroup: allow nesting and inherit config on cgroup creation
  netprio_cgroup: implement netprio[_set]_prio() helpers
  netprio_cgroup: use cgroup->id instead of cgroup_netprio_state->prioidx
  netprio_cgroup: reimplement priomap expansion
  netprio_cgroup: shorten variable names in extend_netdev_table()
  netprio_cgroup: simplify write_priomap()
  netcls_cgroup: move config inheritance to ->css_online() and remove .broken_hierarchy marking
  cgroup: remove obsolete guarantee from cgroup_task_migrate.
  cgroup: add cgroup->id
  cgroup, cpuset: remove cgroup_subsys->post_clone()
  cgroup: s/CGRP_CLONE_CHILDREN/CGRP_CPUSET_CLONE_CHILDREN/
  cgroup: rename ->create/post_create/pre_destroy/destroy() to ->css_alloc/online/offline/free()
  ...

2 files changed, 125 insertions, 163 deletions

diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 79285a36035..bde53da9cd8 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -27,11 +27,7 @@
 
 #include <linux/fdtable.h>
 
-#define PRIOIDX_SZ 128
-
-static unsigned long prioidx_map[PRIOIDX_SZ];
-static DEFINE_SPINLOCK(prioidx_map_lock);
-static atomic_t max_prioidx = ATOMIC_INIT(0);
+#define PRIOMAP_MIN_SZ		128
 
 static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgrp)
 {
@@ -39,136 +35,157 @@ static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgr
 			    struct cgroup_netprio_state, css);
 }
 
-static int get_prioidx(u32 *prio)
-{
-	unsigned long flags;
-	u32 prioidx;
-
-	spin_lock_irqsave(&prioidx_map_lock, flags);
-	prioidx = find_first_zero_bit(prioidx_map, sizeof(unsigned long) * PRIOIDX_SZ);
-	if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) {
-		spin_unlock_irqrestore(&prioidx_map_lock, flags);
-		return -ENOSPC;
-	}
-	set_bit(prioidx, prioidx_map);
-	if (atomic_read(&max_prioidx) < prioidx)
-		atomic_set(&max_prioidx, prioidx);
-	spin_unlock_irqrestore(&prioidx_map_lock, flags);
-	*prio = prioidx;
-	return 0;
-}
-
-static void put_prioidx(u32 idx)
+/*
+ * Extend @dev->priomap so that it's large enough to accomodate
+ * @target_idx.  @dev->priomap.priomap_len > @target_idx after successful
+ * return.  Must be called under rtnl lock.
+ */
+static int extend_netdev_table(struct net_device *dev, u32 target_idx)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&prioidx_map_lock, flags);
-	clear_bit(idx, prioidx_map);
-	spin_unlock_irqrestore(&prioidx_map_lock, flags);
-}
+	struct netprio_map *old, *new;
+	size_t new_sz, new_len;
 
-static int extend_netdev_table(struct net_device *dev, u32 new_len)
-{
-	size_t new_size = sizeof(struct netprio_map) +
-			   ((sizeof(u32) * new_len));
-	struct netprio_map *new_priomap = kzalloc(new_size, GFP_KERNEL);
-	struct netprio_map *old_priomap;
+	/* is the existing priomap large enough? */
+	old = rtnl_dereference(dev->priomap);
+	if (old && old->priomap_len > target_idx)
+		return 0;
 
-	old_priomap  = rtnl_dereference(dev->priomap);
+	/*
+	 * Determine the new size.  Let's keep it power-of-two.  We start
+	 * from PRIOMAP_MIN_SZ and double it until it's large enough to
+	 * accommodate @target_idx.
+	 */
+	new_sz = PRIOMAP_MIN_SZ;
+	while (true) {
+		new_len = (new_sz - offsetof(struct netprio_map, priomap)) /
+			sizeof(new->priomap[0]);
+		if (new_len > target_idx)
+			break;
+		new_sz *= 2;
+		/* overflowed? */
+		if (WARN_ON(new_sz < PRIOMAP_MIN_SZ))
+			return -ENOSPC;
+	}
 
-	if (!new_priomap) {
+	/* allocate & copy */
+	new = kzalloc(new_sz, GFP_KERNEL);
+	if (!new) {
 		pr_warn("Unable to alloc new priomap!\n");
 		return -ENOMEM;
 	}
 
-	if (old_priomap)
-		memcpy(new_priomap->priomap, old_priomap->priomap,
-		       old_priomap->priomap_len *
-		       sizeof(old_priomap->priomap[0]));
+	if (old)
+		memcpy(new->priomap, old->priomap,
+		       old->priomap_len * sizeof(old->priomap[0]));
 
-	new_priomap->priomap_len = new_len;
+	new->priomap_len = new_len;
 
-	rcu_assign_pointer(dev->priomap, new_priomap);
-	if (old_priomap)
-		kfree_rcu(old_priomap, rcu);
+	/* install the new priomap */
+	rcu_assign_pointer(dev->priomap, new);
+	if (old)
+		kfree_rcu(old, rcu);
 	return 0;
 }
 
-static int write_update_netdev_table(struct net_device *dev)
+/**
+ * netprio_prio - return the effective netprio of a cgroup-net_device pair
+ * @cgrp: cgroup part of the target pair
+ * @dev: net_device part of the target pair
+ *
+ * Should be called under RCU read or rtnl lock.
+ */
+static u32 netprio_prio(struct cgroup *cgrp, struct net_device *dev)
+{
+	struct netprio_map *map = rcu_dereference_rtnl(dev->priomap);
+
+	if (map && cgrp->id < map->priomap_len)
+		return map->priomap[cgrp->id];
+	return 0;
+}
+
+/**
+ * netprio_set_prio - set netprio on a cgroup-net_device pair
+ * @cgrp: cgroup part of the target pair
+ * @dev: net_device part of the target pair
+ * @prio: prio to set
+ *
+ * Set netprio to @prio on @cgrp-@dev pair.  Should be called under rtnl
+ * lock and may fail under memory pressure for non-zero @prio.
+ */
+static int netprio_set_prio(struct cgroup *cgrp, struct net_device *dev,
+			    u32 prio)
 {
-	int ret = 0;
-	u32 max_len;
 	struct netprio_map *map;
+	int ret;
 
-	max_len = atomic_read(&max_prioidx) + 1;
+	/* avoid extending priomap for zero writes */
 	map = rtnl_dereference(dev->priomap);
-	if (!map || map->priomap_len < max_len)
-		ret = extend_netdev_table(dev, max_len);
+	if (!prio && (!map || map->priomap_len <= cgrp->id))
+		return 0;
 
-	return ret;
+	ret = extend_netdev_table(dev, cgrp->id);
+	if (ret)
+		return ret;
+
+	map = rtnl_dereference(dev->priomap);
+	map->priomap[cgrp->id] = prio;
+	return 0;
 }
 
-static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp)
 {
 	struct cgroup_netprio_state *cs;
-	int ret = -EINVAL;
 
 	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
 
-	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx)
-		goto out;
-
-	ret = get_prioidx(&cs->prioidx);
-	if (ret < 0) {
-		pr_warn("No space in priority index array\n");
-		goto out;
-	}
-
 	return &cs->css;
-out:
-	kfree(cs);
-	return ERR_PTR(ret);
 }
 
-static void cgrp_destroy(struct cgroup *cgrp)
+static int cgrp_css_online(struct cgroup *cgrp)
 {
-	struct cgroup_netprio_state *cs;
+	struct cgroup *parent = cgrp->parent;
 	struct net_device *dev;
-	struct netprio_map *map;
+	int ret = 0;
+
+	if (!parent)
+		return 0;
 
-	cs = cgrp_netprio_state(cgrp);
 	rtnl_lock();
+	/*
+	 * Inherit prios from the parent.  As all prios are set during
+	 * onlining, there is no need to clear them on offline.
+	 */
 	for_each_netdev(&init_net, dev) {
-		map = rtnl_dereference(dev->priomap);
-		if (map && cs->prioidx < map->priomap_len)
-			map->priomap[cs->prioidx] = 0;
+		u32 prio = netprio_prio(parent, dev);
+
+		ret = netprio_set_prio(cgrp, dev, prio);
+		if (ret)
+			break;
 	}
 	rtnl_unlock();
-	put_prioidx(cs->prioidx);
-	kfree(cs);
+	return ret;
+}
+
+static void cgrp_css_free(struct cgroup *cgrp)
+{
+	kfree(cgrp_netprio_state(cgrp));
 }
 
 static u64 read_prioidx(struct cgroup *cgrp, struct cftype *cft)
 {
-	return (u64)cgrp_netprio_state(cgrp)->prioidx;
+	return cgrp->id;
 }
 
 static int read_priomap(struct cgroup *cont, struct cftype *cft,
 			struct cgroup_map_cb *cb)
 {
 	struct net_device *dev;
-	u32 prioidx = cgrp_netprio_state(cont)->prioidx;
-	u32 priority;
-	struct netprio_map *map;
 
 	rcu_read_lock();
-	for_each_netdev_rcu(&init_net, dev) {
-		map = rcu_dereference(dev->priomap);
-		priority = (map && prioidx < map->priomap_len) ? map->priomap[prioidx] : 0;
-		cb->fill(cb, dev->name, priority);
-	}
+	for_each_netdev_rcu(&init_net, dev)
+		cb->fill(cb, dev->name, netprio_prio(cont, dev));
 	rcu_read_unlock();
 	return 0;
 }
@@ -176,66 +193,24 @@ static int read_priomap(struct cgroup *cont, struct cftype *cft,
 static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
 			 const char *buffer)
 {
-	char *devname = kstrdup(buffer, GFP_KERNEL);
-	int ret = -EINVAL;
-	u32 prioidx = cgrp_netprio_state(cgrp)->prioidx;
-	unsigned long priority;
-	char *priostr;
+	char devname[IFNAMSIZ + 1];
 	struct net_device *dev;
-	struct netprio_map *map;
-
-	if (!devname)
-		return -ENOMEM;
-
-	/*
-	 * Minimally sized valid priomap string
-	 */
-	if (strlen(devname) < 3)
-		goto out_free_devname;
-
-	priostr = strstr(devname, " ");
-	if (!priostr)
-		goto out_free_devname;
-
-	/*
-	 *Separate the devname from the associated priority
-	 *and advance the priostr pointer to the priority value
-	 */
-	*priostr = '\0';
-	priostr++;
-
-	/*
-	 * If the priostr points to NULL, we're at the end of the passed
-	 * in string, and its not a valid write
-	 */
-	if (*priostr == '\0')
-		goto out_free_devname;
-
-	ret = kstrtoul(priostr, 10, &priority);
-	if (ret < 0)
-		goto out_free_devname;
+	u32 prio;
+	int ret;
 
-	ret = -ENODEV;
+	if (sscanf(buffer, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2)
+		return -EINVAL;
 
 	dev = dev_get_by_name(&init_net, devname);
 	if (!dev)
-		goto out_free_devname;
+		return -ENODEV;
 
 	rtnl_lock();
-	ret = write_update_netdev_table(dev);
-	if (ret < 0)
-		goto out_put_dev;
 
-	map = rtnl_dereference(dev->priomap);
-	if (map)
-		map->priomap[prioidx] = priority;
+	ret = netprio_set_prio(cgrp, dev, prio);
 
-out_put_dev:
 	rtnl_unlock();
 	dev_put(dev);
-
-out_free_devname:
-	kfree(devname);
 	return ret;
 }
 
@@ -276,22 +251,13 @@ static struct cftype ss_files[] = {
 
 struct cgroup_subsys net_prio_subsys = {
 	.name		= "net_prio",
-	.create		= cgrp_create,
-	.destroy	= cgrp_destroy,
+	.css_alloc	= cgrp_css_alloc,
+	.css_online	= cgrp_css_online,
+	.css_free	= cgrp_css_free,
 	.attach		= net_prio_attach,
 	.subsys_id	= net_prio_subsys_id,
 	.base_cftypes	= ss_files,
 	.module		= THIS_MODULE,
-
-	/*
-	 * net_prio has artificial limit on the number of cgroups and
-	 * disallows nesting making it impossible to co-mount it with other
-	 * hierarchical subsystems.  Remove the artificially low PRIOIDX_SZ
-	 * limit and properly nest configuration such that children follow
-	 * their parents' configurations by default and are allowed to
-	 * override and remove the following.
-	 */
-	.broken_hierarchy = true,
 };
 
 static int netprio_device_event(struct notifier_block *unused,
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 2ecde225ae6..31f06b63357 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -34,21 +34,25 @@ static inline struct cgroup_cls_state *task_cls_state(struct task_struct *p)
 			    struct cgroup_cls_state, css);
 }
 
-static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp)
 {
 	struct cgroup_cls_state *cs;
 
 	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
+	return &cs->css;
+}
 
+static int cgrp_css_online(struct cgroup *cgrp)
+{
 	if (cgrp->parent)
-		cs->classid = cgrp_cls_state(cgrp->parent)->classid;
-
-	return &cs->css;
+		cgrp_cls_state(cgrp)->classid =
+			cgrp_cls_state(cgrp->parent)->classid;
+	return 0;
 }
 
-static void cgrp_destroy(struct cgroup *cgrp)
+static void cgrp_css_free(struct cgroup *cgrp)
 {
 	kfree(cgrp_cls_state(cgrp));
 }
@@ -75,20 +79,12 @@ static struct cftype ss_files[] = {
 
 struct cgroup_subsys net_cls_subsys = {
 	.name		= "net_cls",
-	.create		= cgrp_create,
-	.destroy	= cgrp_destroy,
+	.css_alloc	= cgrp_css_alloc,
+	.css_online	= cgrp_css_online,
+	.css_free	= cgrp_css_free,
 	.subsys_id	= net_cls_subsys_id,
 	.base_cftypes	= ss_files,
 	.module		= THIS_MODULE,
-
-	/*
-	 * While net_cls cgroup has the rudimentary hierarchy support of
-	 * inheriting the parent's classid on cgroup creation, it doesn't
-	 * properly propagates config changes in ancestors to their
-	 * descendents.  A child should follow the parent's configuration
-	 * but be allowed to override it.  Fix it and remove the following.
-	 */
-	.broken_hierarchy = true,
 };
 
 struct cls_cgroup_head {