Merge branch 'for-3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:
 "A lot updates for cgroup:

   - The biggest one is cgroup's conversion to kernfs.  cgroup took
     after the long abandoned vfs-entangled sysfs implementation and
     made it even more convoluted over time.  cgroup's internal objects
     were fused with vfs objects which also brought in vfs locking and
     object lifetime rules.  Naturally, there are places where vfs rules
     don't fit and nasty hacks, such as credential switching or lock
     dance interleaving inode mutex and cgroup_mutex with object serial
     number comparison thrown in to decide whether the operation is
     actually necessary, needed to be employed.

     After conversion to kernfs, internal object lifetime and locking
     rules are mostly isolated from vfs interactions allowing shedding
     of several nasty hacks and overall simplification.  This will also
     allow implmentation of operations which may affect multiple cgroups
     which weren't possible before as it would have required nesting
     i_mutexes.

   - Various simplifications including dropping of module support,
     easier cgroup name/path handling, simplified cgroup file type
     handling and task_cg_lists optimization.

   - Prepatory changes for the planned unified hierarchy, which is still
     a patchset away from being actually operational.  The dummy
     hierarchy is updated to serve as the default unified hierarchy.
     Controllers which aren't claimed by other hierarchies are
     associated with it, which BTW was what the dummy hierarchy was for
     anyway.

   - Various fixes from Li and others.  This pull request includes some
     patches to add missing slab.h to various subsystems.  This was
     triggered xattr.h include removal from cgroup.h.  cgroup.h
     indirectly got included a lot of files which brought in xattr.h
     which brought in slab.h.

  There are several merge commits - one to pull in kernfs updates
  necessary for converting cgroup (already in upstream through
  driver-core), others for interfering changes in the fixes branch"

* 'for-3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (74 commits)
  cgroup: remove useless argument from cgroup_exit()
  cgroup: fix spurious lockdep warning in cgroup_exit()
  cgroup: Use RCU_INIT_POINTER(x, NULL) in cgroup.c
  cgroup: break kernfs active_ref protection in cgroup directory operations
  cgroup: fix cgroup_taskset walking order
  cgroup: implement CFTYPE_ONLY_ON_DFL
  cgroup: make cgrp_dfl_root mountable
  cgroup: drop const from @buffer of cftype->write_string()
  cgroup: rename cgroup_dummy_root and related names
  cgroup: move ->subsys_mask from cgroupfs_root to cgroup
  cgroup: treat cgroup_dummy_root as an equivalent hierarchy during rebinding
  cgroup: remove NULL checks from [pr_cont_]cgroup_{name|path}()
  cgroup: use cgroup_setup_root() to initialize cgroup_dummy_root
  cgroup: reorganize cgroup bootstrapping
  cgroup: relocate setting of CGRP_DEAD
  cpuset: use rcu_read_lock() to protect task_cs()
  cgroup_freezer: document freezer_fork() subtleties
  cgroup: update cgroup_transfer_tasks() to either succeed or fail
  cgroup: drop task_lock() protection around task->cgroups
  cgroup: update how a newly forked task gets associated with css_set
  ...

arch/sparc/kernel/leon_pci_grpci2.c

@@ -8,6 +8,7 @@
 #include <linux/of_device.h>
 #include <linux/kernel.h>
 #include <linux/pci.h>
+#include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <asm/io.h>

arch/sparc/kernel/sun4m_irq.c

@@ -9,6 +9,8 @@
  *  Copyright (C) 1996 Dave Redman (djhr@tadpole.co.uk)
  */
 
+#include <linux/slab.h>
+
 #include <asm/timer.h>
 #include <asm/traps.h>
 #include <asm/pgalloc.h>

block/blk-cgroup.c

@@ -894,7 +894,7 @@ static int blkcg_can_attach(struct cgroup_subsys_state *css,
 	int ret = 0;
 
 	/* task_lock() is needed to avoid races with exit_io_context() */
-	cgroup_taskset_for_each(task, css, tset) {
+	cgroup_taskset_for_each(task, tset) {
 		task_lock(task);
 		ioc = task->io_context;
 		if (ioc && atomic_read(&ioc->nr_tasks) > 1)
@@ -906,17 +906,14 @@ static int blkcg_can_attach(struct cgroup_subsys_state *css,
 	return ret;
 }
 
-struct cgroup_subsys blkio_subsys = {
-	.name = "blkio",
+struct cgroup_subsys blkio_cgrp_subsys = {
 	.css_alloc = blkcg_css_alloc,
 	.css_offline = blkcg_css_offline,
 	.css_free = blkcg_css_free,
 	.can_attach = blkcg_can_attach,
-	.subsys_id = blkio_subsys_id,
 	.base_cftypes = blkcg_files,
-	.module = THIS_MODULE,
 };
-EXPORT_SYMBOL_GPL(blkio_subsys);
+EXPORT_SYMBOL_GPL(blkio_cgrp_subsys);
 
 /**
  * blkcg_activate_policy - activate a blkcg policy on a request_queue
@@ -1106,7 +1103,7 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 
 	/* everything is in place, add intf files for the new policy */
 	if (pol->cftypes)
-		WARN_ON(cgroup_add_cftypes(&blkio_subsys, pol->cftypes));
+		WARN_ON(cgroup_add_cftypes(&blkio_cgrp_subsys, pol->cftypes));
 	ret = 0;
 out_unlock:
 	mutex_unlock(&blkcg_pol_mutex);

block/blk-cgroup.h

@@ -186,7 +186,7 @@ static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css)
 
 static inline struct blkcg *task_blkcg(struct task_struct *tsk)
 {
-	return css_to_blkcg(task_css(tsk, blkio_subsys_id));
+	return css_to_blkcg(task_css(tsk, blkio_cgrp_id));
 }
 
 static inline struct blkcg *bio_blkcg(struct bio *bio)
@@ -241,12 +241,16 @@ static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd)
  */
 static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
 {
-	int ret;
+	char *p;
 
-	ret = cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
-	if (ret)
+	p = cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
+	if (!p) {
 		strncpy(buf, "<unavailable>", buflen);
-	return ret;
+		return -ENAMETOOLONG;
+	}
+
+	memmove(buf, p, buf + buflen - p);
+	return 0;
 }
 
 /**

block/blk-throttle.c

@@ -1408,13 +1408,13 @@ static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
 }
 
 static int tg_set_conf_u64(struct cgroup_subsys_state *css, struct cftype *cft,
-			   const char *buf)
+			   char *buf)
 {
 	return tg_set_conf(css, cft, buf, true);
 }
 
 static int tg_set_conf_uint(struct cgroup_subsys_state *css, struct cftype *cft,
-			    const char *buf)
+			    char *buf)
 {
 	return tg_set_conf(css, cft, buf, false);
 }
@@ -1425,28 +1425,24 @@ static struct cftype throtl_files[] = {
 		.private = offsetof(struct throtl_grp, bps[READ]),
 		.seq_show = tg_print_conf_u64,
 		.write_string = tg_set_conf_u64,
-		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.write_bps_device",
 		.private = offsetof(struct throtl_grp, bps[WRITE]),
 		.seq_show = tg_print_conf_u64,
 		.write_string = tg_set_conf_u64,
-		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.read_iops_device",
 		.private = offsetof(struct throtl_grp, iops[READ]),
 		.seq_show = tg_print_conf_uint,
 		.write_string = tg_set_conf_uint,
-		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.write_iops_device",
 		.private = offsetof(struct throtl_grp, iops[WRITE]),
 		.seq_show = tg_print_conf_uint,
 		.write_string = tg_set_conf_uint,
-		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.io_service_bytes",

block/cfq-iosched.c

@@ -1701,13 +1701,13 @@ static int __cfqg_set_weight_device(struct cgroup_subsys_state *css,
 }
 
 static int cfqg_set_weight_device(struct cgroup_subsys_state *css,
-				  struct cftype *cft, const char *buf)
+				  struct cftype *cft, char *buf)
 {
 	return __cfqg_set_weight_device(css, cft, buf, false);
 }
 
 static int cfqg_set_leaf_weight_device(struct cgroup_subsys_state *css,
-				       struct cftype *cft, const char *buf)
+				       struct cftype *cft, char *buf)
 {
 	return __cfqg_set_weight_device(css, cft, buf, true);
 }
@@ -1838,7 +1838,6 @@ static struct cftype cfq_blkcg_files[] = {
 		.flags = CFTYPE_ONLY_ON_ROOT,
 		.seq_show = cfqg_print_leaf_weight_device,
 		.write_string = cfqg_set_leaf_weight_device,
-		.max_write_len = 256,
 	},
 	{
 		.name = "weight",
@@ -1853,7 +1852,6 @@ static struct cftype cfq_blkcg_files[] = {
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = cfqg_print_weight_device,
 		.write_string = cfqg_set_weight_device,
-		.max_write_len = 256,
 	},
 	{
 		.name = "weight",
@@ -1866,7 +1864,6 @@ static struct cftype cfq_blkcg_files[] = {
 		.name = "leaf_weight_device",
 		.seq_show = cfqg_print_leaf_weight_device,
 		.write_string = cfqg_set_leaf_weight_device,
-		.max_write_len = 256,
 	},
 	{
 		.name = "leaf_weight",

fs/bio.c

@@ -1969,7 +1969,7 @@ int bio_associate_current(struct bio *bio)
 
 	/* associate blkcg if exists */
 	rcu_read_lock();
-	css = task_css(current, blkio_subsys_id);
+	css = task_css(current, blkio_cgrp_id);
 	if (css && css_tryget(css))
 		bio->bi_css = css;
 	rcu_read_unlock();

fs/kernfs/dir.c

@@ -112,6 +112,7 @@ char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen)
 	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
 	return p;
 }
+EXPORT_SYMBOL_GPL(kernfs_path);
 
 /**
  * pr_cont_kernfs_name - pr_cont name of a kernfs_node

include/linux/cgroup_subsys.h

@@ -3,51 +3,51 @@
  *
  * DO NOT ADD ANY SUBSYSTEM WITHOUT EXPLICIT ACKS FROM CGROUP MAINTAINERS.
  */
-#if IS_SUBSYS_ENABLED(CONFIG_CPUSETS)
+#if IS_ENABLED(CONFIG_CPUSETS)
 SUBSYS(cpuset)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_DEBUG)
+#if IS_ENABLED(CONFIG_CGROUP_DEBUG)
 SUBSYS(debug)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_SCHED)
-SUBSYS(cpu_cgroup)
+#if IS_ENABLED(CONFIG_CGROUP_SCHED)
+SUBSYS(cpu)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_CPUACCT)
+#if IS_ENABLED(CONFIG_CGROUP_CPUACCT)
 SUBSYS(cpuacct)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_MEMCG)
-SUBSYS(mem_cgroup)
+#if IS_ENABLED(CONFIG_MEMCG)
+SUBSYS(memory)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_DEVICE)
+#if IS_ENABLED(CONFIG_CGROUP_DEVICE)
 SUBSYS(devices)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_FREEZER)
+#if IS_ENABLED(CONFIG_CGROUP_FREEZER)
 SUBSYS(freezer)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_NET_CLASSID)
+#if IS_ENABLED(CONFIG_CGROUP_NET_CLASSID)
 SUBSYS(net_cls)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_BLK_CGROUP)
+#if IS_ENABLED(CONFIG_BLK_CGROUP)
 SUBSYS(blkio)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_PERF)
-SUBSYS(perf)
+#if IS_ENABLED(CONFIG_CGROUP_PERF)
+SUBSYS(perf_event)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_NET_PRIO)
+#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
 SUBSYS(net_prio)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_HUGETLB)
+#if IS_ENABLED(CONFIG_CGROUP_HUGETLB)
 SUBSYS(hugetlb)
 #endif
 /*

include/linux/hugetlb_cgroup.h

@@ -49,7 +49,7 @@ int set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg)
 
 static inline bool hugetlb_cgroup_disabled(void)
 {
-	if (hugetlb_subsys.disabled)
+	if (hugetlb_cgrp_subsys.disabled)
 		return true;
 	return false;
 }

include/linux/memcontrol.h

@@ -162,7 +162,7 @@ extern int do_swap_account;
 
 static inline bool mem_cgroup_disabled(void)
 {
-	if (mem_cgroup_subsys.disabled)
+	if (memory_cgrp_subsys.disabled)
 		return true;
 	return false;
 }

include/net/cls_cgroup.h

@@ -34,7 +34,7 @@ static inline u32 task_cls_classid(struct task_struct *p)
 		return 0;
 
 	rcu_read_lock();
-	classid = container_of(task_css(p, net_cls_subsys_id),
+	classid = container_of(task_css(p, net_cls_cgrp_id),
 			       struct cgroup_cls_state, css)->classid;
 	rcu_read_unlock();
 

include/net/netprio_cgroup.h

@@ -27,32 +27,17 @@ struct netprio_map {
 
 void sock_update_netprioidx(struct sock *sk);
 
-#if IS_BUILTIN(CONFIG_CGROUP_NET_PRIO)
 static inline u32 task_netprioidx(struct task_struct *p)
 {
 	struct cgroup_subsys_state *css;
 	u32 idx;
 
 	rcu_read_lock();
-	css = task_css(p, net_prio_subsys_id);
+	css = task_css(p, net_prio_cgrp_id);
 	idx = css->cgroup->id;
 	rcu_read_unlock();
 	return idx;
 }
-#elif IS_MODULE(CONFIG_CGROUP_NET_PRIO)
-static inline u32 task_netprioidx(struct task_struct *p)
-{
-	struct cgroup_subsys_state *css;
-	u32 idx = 0;
-
-	rcu_read_lock();
-	css = task_css(p, net_prio_subsys_id);
-	if (css)
-		idx = css->cgroup->id;
-	rcu_read_unlock();
-	return idx;
-}
-#endif
 #else /* !CONFIG_CGROUP_NET_PRIO */
 static inline u32 task_netprioidx(struct task_struct *p)
 {

init/Kconfig

@@ -854,6 +854,7 @@ config NUMA_BALANCING
 
 menuconfig CGROUPS
 	boolean "Control Group support"
+	select KERNFS
 	help
 	  This option adds support for grouping sets of processes together, for
 	  use with process control subsystems such as Cpusets, CFS, memory

kernel/cgroup_freezer.c

@@ -52,7 +52,7 @@ static inline struct freezer *css_freezer(struct cgroup_subsys_state *css)
 
 static inline struct freezer *task_freezer(struct task_struct *task)
 {
-	return css_freezer(task_css(task, freezer_subsys_id));
+	return css_freezer(task_css(task, freezer_cgrp_id));
 }
 
 static struct freezer *parent_freezer(struct freezer *freezer)
@@ -84,8 +84,6 @@ static const char *freezer_state_strs(unsigned int state)
 	return "THAWED";
 };
 
-struct cgroup_subsys freezer_subsys;
-
 static struct cgroup_subsys_state *
 freezer_css_alloc(struct cgroup_subsys_state *parent_css)
 {
@@ -189,7 +187,7 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
 	 * current state before executing the following - !frozen tasks may
 	 * be visible in a FROZEN cgroup and frozen tasks in a THAWED one.
 	 */
-	cgroup_taskset_for_each(task, new_css, tset) {
+	cgroup_taskset_for_each(task, tset) {
 		if (!(freezer->state & CGROUP_FREEZING)) {
 			__thaw_task(task);
 		} else {
@@ -216,6 +214,16 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
 	}
 }
 
+/**
+ * freezer_fork - cgroup post fork callback
+ * @task: a task which has just been forked
+ *
+ * @task has just been created and should conform to the current state of
+ * the cgroup_freezer it belongs to.  This function may race against
+ * freezer_attach().  Losing to freezer_attach() means that we don't have
+ * to do anything as freezer_attach() will put @task into the appropriate
+ * state.
+ */
 static void freezer_fork(struct task_struct *task)
 {
 	struct freezer *freezer;
@@ -224,14 +232,26 @@ static void freezer_fork(struct task_struct *task)
 	freezer = task_freezer(task);
 
 	/*
-	 * The root cgroup is non-freezable, so we can skip the
-	 * following check.
+	 * The root cgroup is non-freezable, so we can skip locking the
+	 * freezer.  This is safe regardless of race with task migration.
+	 * If we didn't race or won, skipping is obviously the right thing
+	 * to do.  If we lost and root is the new cgroup, noop is still the
+	 * right thing to do.
 	 */
 	if (!parent_freezer(freezer))
 		goto out;
 
+	/*
+	 * Grab @freezer->lock and freeze @task after verifying @task still
+	 * belongs to @freezer and it's freezing.  The former is for the
+	 * case where we have raced against task migration and lost and
+	 * @task is already in a different cgroup which may not be frozen.
+	 * This isn't strictly necessary as freeze_task() is allowed to be
+	 * called spuriously but let's do it anyway for, if nothing else,
+	 * documentation.
+	 */
 	spin_lock_irq(&freezer->lock);
-	if (freezer->state & CGROUP_FREEZING)
+	if (freezer == task_freezer(task) && (freezer->state & CGROUP_FREEZING))
 		freeze_task(task);
 	spin_unlock_irq(&freezer->lock);
 out:
@@ -422,7 +442,7 @@ static void freezer_change_state(struct freezer *freezer, bool freeze)
 }
 
 static int freezer_write(struct cgroup_subsys_state *css, struct cftype *cft,
-			 const char *buffer)
+			 char *buffer)
 {
 	bool freeze;
 
@@ -473,13 +493,11 @@ static struct cftype files[] = {
 	{ }	/* terminate */
 };
 
-struct cgroup_subsys freezer_subsys = {
-	.name		= "freezer",
+struct cgroup_subsys freezer_cgrp_subsys = {
 	.css_alloc	= freezer_css_alloc,
 	.css_online	= freezer_css_online,
 	.css_offline	= freezer_css_offline,
 	.css_free	= freezer_css_free,
-	.subsys_id	= freezer_subsys_id,
 	.attach		= freezer_attach,
 	.fork		= freezer_fork,
 	.base_cftypes	= files,

kernel/events/core.c

@@ -361,7 +361,7 @@ struct perf_cgroup {
 static inline struct perf_cgroup *
 perf_cgroup_from_task(struct task_struct *task)
 {
-	return container_of(task_css(task, perf_subsys_id),
+	return container_of(task_css(task, perf_event_cgrp_id),
 			    struct perf_cgroup, css);
 }
 
@@ -389,11 +389,6 @@ perf_cgroup_match(struct perf_event *event)
 				    event->cgrp->css.cgroup);
 }
 
-static inline bool perf_tryget_cgroup(struct perf_event *event)
-{
-	return css_tryget(&event->cgrp->css);
-}
-
 static inline void perf_put_cgroup(struct perf_event *event)
 {
 	css_put(&event->cgrp->css);
@@ -612,9 +607,7 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 	if (!f.file)
 		return -EBADF;
 
-	rcu_read_lock();
-
-	css = css_from_dir(f.file->f_dentry, &perf_subsys);
+	css = css_tryget_from_dir(f.file->f_dentry, &perf_event_cgrp_subsys);
 	if (IS_ERR(css)) {
 		ret = PTR_ERR(css);
 		goto out;
@@ -623,13 +616,6 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 	cgrp = container_of(css, struct perf_cgroup, css);
 	event->cgrp = cgrp;
 
-	/* must be done before we fput() the file */
-	if (!perf_tryget_cgroup(event)) {
-		event->cgrp = NULL;
-		ret = -ENOENT;
-		goto out;
-	}
-
 	/*
 	 * all events in a group must monitor
 	 * the same cgroup because a task belongs
@@ -640,7 +626,6 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 		ret = -EINVAL;
 	}
 out:
-	rcu_read_unlock();
 	fdput(f);
 	return ret;
 }
@@ -8053,7 +8038,7 @@ static void perf_cgroup_attach(struct cgroup_subsys_state *css,
 {
 	struct task_struct *task;
 
-	cgroup_taskset_for_each(task, css, tset)
+	cgroup_taskset_for_each(task, tset)
 		task_function_call(task, __perf_cgroup_move, task);
 }
 
@@ -8072,9 +8057,7 @@ static void perf_cgroup_exit(struct cgroup_subsys_state *css,
 	task_function_call(task, __perf_cgroup_move, task);
 }
 
-struct cgroup_subsys perf_subsys = {
-	.name		= "perf_event",
-	.subsys_id	= perf_subsys_id,
+struct cgroup_subsys perf_event_cgrp_subsys = {
 	.css_alloc	= perf_cgroup_css_alloc,
 	.css_free	= perf_cgroup_css_free,
 	.exit		= perf_cgroup_exit,

kernel/exit.c

@@ -797,7 +797,7 @@ void do_exit(long code)
 	 */
 	perf_event_exit_task(tsk);
 
-	cgroup_exit(tsk, 1);
+	cgroup_exit(tsk);
 
 	if (group_dead)
 		disassociate_ctty(1);