Initial commit: Linux kernel 4.19 for Unplugged OS

kernel/cgroup/Makefile

@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-y := cgroup.o rstat.o namespace.o cgroup-v1.o freezer.o
+
+obj-$(CONFIG_CGROUP_FREEZER) += legacy_freezer.o
+obj-$(CONFIG_CGROUP_PIDS) += pids.o
+obj-$(CONFIG_CGROUP_RDMA) += rdma.o
+obj-$(CONFIG_CPUSETS) += cpuset.o
+obj-$(CONFIG_CGROUP_DEBUG) += debug.o

kernel/cgroup/cgroup-internal.h

@@ -0,0 +1,258 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __CGROUP_INTERNAL_H
+#define __CGROUP_INTERNAL_H
+
+#include <linux/cgroup.h>
+#include <linux/kernfs.h>
+#include <linux/workqueue.h>
+#include <linux/list.h>
+#include <linux/refcount.h>
+
+#define TRACE_CGROUP_PATH_LEN 1024
+extern spinlock_t trace_cgroup_path_lock;
+extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN];
+
+/*
+ * cgroup_path() takes a spin lock. It is good practice not to take
+ * spin locks within trace point handlers, as they are mostly hidden
+ * from normal view. As cgroup_path() can take the kernfs_rename_lock
+ * spin lock, it is best to not call that function from the trace event
+ * handler.
+ *
+ * Note: trace_cgroup_##type##_enabled() is a static branch that will only
+ *       be set when the trace event is enabled.
+ */
+#define TRACE_CGROUP_PATH(type, cgrp, ...)				\
+	do {								\
+		if (trace_cgroup_##type##_enabled()) {			\
+			spin_lock(&trace_cgroup_path_lock);		\
+			cgroup_path(cgrp, trace_cgroup_path,		\
+				    TRACE_CGROUP_PATH_LEN);		\
+			trace_cgroup_##type(cgrp, trace_cgroup_path,	\
+					    ##__VA_ARGS__);		\
+			spin_unlock(&trace_cgroup_path_lock);		\
+		}							\
+	} while (0)
+
+/*
+ * A cgroup can be associated with multiple css_sets as different tasks may
+ * belong to different cgroups on different hierarchies.  In the other
+ * direction, a css_set is naturally associated with multiple cgroups.
+ * This M:N relationship is represented by the following link structure
+ * which exists for each association and allows traversing the associations
+ * from both sides.
+ */
+struct cgrp_cset_link {
+	/* the cgroup and css_set this link associates */
+	struct cgroup		*cgrp;
+	struct css_set		*cset;
+
+	/* list of cgrp_cset_links anchored at cgrp->cset_links */
+	struct list_head	cset_link;
+
+	/* list of cgrp_cset_links anchored at css_set->cgrp_links */
+	struct list_head	cgrp_link;
+};
+
+/* used to track tasks and csets during migration */
+struct cgroup_taskset {
+	/* the src and dst cset list running through cset->mg_node */
+	struct list_head	src_csets;
+	struct list_head	dst_csets;
+
+	/* the number of tasks in the set */
+	int			nr_tasks;
+
+	/* the subsys currently being processed */
+	int			ssid;
+
+	/*
+	 * Fields for cgroup_taskset_*() iteration.
+	 *
+	 * Before migration is committed, the target migration tasks are on
+	 * ->mg_tasks of the csets on ->src_csets.  After, on ->mg_tasks of
+	 * the csets on ->dst_csets.  ->csets point to either ->src_csets
+	 * or ->dst_csets depending on whether migration is committed.
+	 *
+	 * ->cur_csets and ->cur_task point to the current task position
+	 * during iteration.
+	 */
+	struct list_head	*csets;
+	struct css_set		*cur_cset;
+	struct task_struct	*cur_task;
+};
+
+/* migration context also tracks preloading */
+struct cgroup_mgctx {
+	/*
+	 * Preloaded source and destination csets.  Used to guarantee
+	 * atomic success or failure on actual migration.
+	 */
+	struct list_head	preloaded_src_csets;
+	struct list_head	preloaded_dst_csets;
+
+	/* tasks and csets to migrate */
+	struct cgroup_taskset	tset;
+
+	/* subsystems affected by migration */
+	u16			ss_mask;
+};
+
+#define CGROUP_TASKSET_INIT(tset)						\
+{										\
+	.src_csets		= LIST_HEAD_INIT(tset.src_csets),		\
+	.dst_csets		= LIST_HEAD_INIT(tset.dst_csets),		\
+	.csets			= &tset.src_csets,				\
+}
+
+#define CGROUP_MGCTX_INIT(name)							\
+{										\
+	LIST_HEAD_INIT(name.preloaded_src_csets),				\
+	LIST_HEAD_INIT(name.preloaded_dst_csets),				\
+	CGROUP_TASKSET_INIT(name.tset),						\
+}
+
+#define DEFINE_CGROUP_MGCTX(name)						\
+	struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name)
+
+struct cgroup_sb_opts {
+	u16 subsys_mask;
+	unsigned int flags;
+	char *release_agent;
+	bool cpuset_clone_children;
+	char *name;
+	/* User explicitly requested empty subsystem */
+	bool none;
+};
+
+extern struct mutex cgroup_mutex;
+extern spinlock_t css_set_lock;
+extern struct cgroup_subsys *cgroup_subsys[];
+extern struct list_head cgroup_roots;
+extern struct file_system_type cgroup_fs_type;
+
+/* iterate across the hierarchies */
+#define for_each_root(root)						\
+	list_for_each_entry((root), &cgroup_roots, root_list)
+
+/**
+ * for_each_subsys - iterate all enabled cgroup subsystems
+ * @ss: the iteration cursor
+ * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
+ */
+#define for_each_subsys(ss, ssid)					\
+	for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT &&		\
+	     (((ss) = cgroup_subsys[ssid]) || true); (ssid)++)
+
+static inline bool cgroup_is_dead(const struct cgroup *cgrp)
+{
+	return !(cgrp->self.flags & CSS_ONLINE);
+}
+
+static inline bool notify_on_release(const struct cgroup *cgrp)
+{
+	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
+}
+
+void put_css_set_locked(struct css_set *cset);
+
+static inline void put_css_set(struct css_set *cset)
+{
+	unsigned long flags;
+
+	/*
+	 * Ensure that the refcount doesn't hit zero while any readers
+	 * can see it. Similar to atomic_dec_and_lock(), but for an
+	 * rwlock
+	 */
+	if (refcount_dec_not_one(&cset->refcount))
+		return;
+
+	spin_lock_irqsave(&css_set_lock, flags);
+	put_css_set_locked(cset);
+	spin_unlock_irqrestore(&css_set_lock, flags);
+}
+
+/*
+ * refcounted get/put for css_set objects
+ */
+static inline void get_css_set(struct css_set *cset)
+{
+	refcount_inc(&cset->refcount);
+}
+
+bool cgroup_ssid_enabled(int ssid);
+bool cgroup_on_dfl(const struct cgroup *cgrp);
+bool cgroup_is_thread_root(struct cgroup *cgrp);
+bool cgroup_is_threaded(struct cgroup *cgrp);
+
+struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root);
+struct cgroup *task_cgroup_from_root(struct task_struct *task,
+				     struct cgroup_root *root);
+struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline);
+void cgroup_kn_unlock(struct kernfs_node *kn);
+int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen,
+			  struct cgroup_namespace *ns);
+
+void cgroup_free_root(struct cgroup_root *root);
+void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts);
+int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask);
+int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask);
+struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
+			       struct cgroup_root *root, unsigned long magic,
+			       struct cgroup_namespace *ns);
+
+int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp);
+void cgroup_migrate_finish(struct cgroup_mgctx *mgctx);
+void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp,
+			    struct cgroup_mgctx *mgctx);
+int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx);
+int cgroup_migrate(struct task_struct *leader, bool threadgroup,
+		   struct cgroup_mgctx *mgctx);
+
+int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
+		       bool threadgroup);
+struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup)
+	__acquires(&cgroup_threadgroup_rwsem);
+void cgroup_procs_write_finish(struct task_struct *task)
+	__releases(&cgroup_threadgroup_rwsem);
+
+void cgroup_lock_and_drain_offline(struct cgroup *cgrp);
+
+int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode);
+int cgroup_rmdir(struct kernfs_node *kn);
+int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
+		     struct kernfs_root *kf_root);
+
+int __cgroup_task_count(const struct cgroup *cgrp);
+int cgroup_task_count(const struct cgroup *cgrp);
+
+/*
+ * rstat.c
+ */
+int cgroup_rstat_init(struct cgroup *cgrp);
+void cgroup_rstat_exit(struct cgroup *cgrp);
+void cgroup_rstat_boot(void);
+void cgroup_base_stat_cputime_show(struct seq_file *seq);
+
+/*
+ * namespace.c
+ */
+extern const struct proc_ns_operations cgroupns_operations;
+
+/*
+ * cgroup-v1.c
+ */
+extern struct cftype cgroup1_base_files[];
+extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops;
+
+int proc_cgroupstats_show(struct seq_file *m, void *v);
+bool cgroup1_ssid_disabled(int ssid);
+void cgroup1_pidlist_destroy_all(struct cgroup *cgrp);
+void cgroup1_release_agent(struct work_struct *work);
+void cgroup1_check_for_release(struct cgroup *cgrp);
+struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
+			     void *data, unsigned long magic,
+			     struct cgroup_namespace *ns);
+
+#endif /* __CGROUP_INTERNAL_H */

kernel/cgroup/debug.c

@@ -0,0 +1,383 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Debug controller
+ *
+ * WARNING: This controller is for cgroup core debugging only.
+ * Its interfaces are unstable and subject to changes at any time.
+ */
+#include <linux/ctype.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+#include "cgroup-internal.h"
+
+static struct cgroup_subsys_state *
+debug_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+	struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
+
+	if (!css)
+		return ERR_PTR(-ENOMEM);
+
+	return css;
+}
+
+static void debug_css_free(struct cgroup_subsys_state *css)
+{
+	kfree(css);
+}
+
+/*
+ * debug_taskcount_read - return the number of tasks in a cgroup.
+ * @cgrp: the cgroup in question
+ */
+static u64 debug_taskcount_read(struct cgroup_subsys_state *css,
+				struct cftype *cft)
+{
+	return cgroup_task_count(css->cgroup);
+}
+
+static int current_css_set_read(struct seq_file *seq, void *v)
+{
+	struct kernfs_open_file *of = seq->private;
+	struct css_set *cset;
+	struct cgroup_subsys *ss;
+	struct cgroup_subsys_state *css;
+	int i, refcnt;
+
+	if (!cgroup_kn_lock_live(of->kn, false))
+		return -ENODEV;
+
+	spin_lock_irq(&css_set_lock);
+	rcu_read_lock();
+	cset = task_css_set(current);
+	refcnt = refcount_read(&cset->refcount);
+	seq_printf(seq, "css_set %pK %d", cset, refcnt);
+	if (refcnt > cset->nr_tasks)
+		seq_printf(seq, " +%d", refcnt - cset->nr_tasks);
+	seq_puts(seq, "\n");
+
+	/*
+	 * Print the css'es stored in the current css_set.
+	 */
+	for_each_subsys(ss, i) {
+		css = cset->subsys[ss->id];
+		if (!css)
+			continue;
+		seq_printf(seq, "%2d: %-4s\t- %lx[%d]\n", ss->id, ss->name,
+			  (unsigned long)css, css->id);
+	}
+	rcu_read_unlock();
+	spin_unlock_irq(&css_set_lock);
+	cgroup_kn_unlock(of->kn);
+	return 0;
+}
+
+static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css,
+					 struct cftype *cft)
+{
+	u64 count;
+
+	rcu_read_lock();
+	count = refcount_read(&task_css_set(current)->refcount);
+	rcu_read_unlock();
+	return count;
+}
+
+static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
+{
+	struct cgrp_cset_link *link;
+	struct css_set *cset;
+	char *name_buf;
+
+	name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL);
+	if (!name_buf)
+		return -ENOMEM;
+
+	spin_lock_irq(&css_set_lock);
+	rcu_read_lock();
+	cset = task_css_set(current);
+	list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
+		struct cgroup *c = link->cgrp;
+
+		cgroup_name(c, name_buf, NAME_MAX + 1);
+		seq_printf(seq, "Root %d group %s\n",
+			   c->root->hierarchy_id, name_buf);
+	}
+	rcu_read_unlock();
+	spin_unlock_irq(&css_set_lock);
+	kfree(name_buf);
+	return 0;
+}
+
+#define MAX_TASKS_SHOWN_PER_CSS 25
+static int cgroup_css_links_read(struct seq_file *seq, void *v)
+{
+	struct cgroup_subsys_state *css = seq_css(seq);
+	struct cgrp_cset_link *link;
+	int dead_cnt = 0, extra_refs = 0, threaded_csets = 0;
+
+	spin_lock_irq(&css_set_lock);
+
+	list_for_each_entry(link, &css->cgroup->cset_links, cset_link) {
+		struct css_set *cset = link->cset;
+		struct task_struct *task;
+		int count = 0;
+		int refcnt = refcount_read(&cset->refcount);
+
+		/*
+		 * Print out the proc_cset and threaded_cset relationship
+		 * and highlight difference between refcount and task_count.
+		 */
+		seq_printf(seq, "css_set %pK", cset);
+		if (rcu_dereference_protected(cset->dom_cset, 1) != cset) {
+			threaded_csets++;
+			seq_printf(seq, "=>%pK", cset->dom_cset);
+		}
+		if (!list_empty(&cset->threaded_csets)) {
+			struct css_set *tcset;
+			int idx = 0;
+
+			list_for_each_entry(tcset, &cset->threaded_csets,
+					    threaded_csets_node) {
+				seq_puts(seq, idx ? "," : "<=");
+				seq_printf(seq, "%pK", tcset);
+				idx++;
+			}
+		} else {
+			seq_printf(seq, " %d", refcnt);
+			if (refcnt - cset->nr_tasks > 0) {
+				int extra = refcnt - cset->nr_tasks;
+
+				seq_printf(seq, " +%d", extra);
+				/*
+				 * Take out the one additional reference in
+				 * init_css_set.
+				 */
+				if (cset == &init_css_set)
+					extra--;
+				extra_refs += extra;
+			}
+		}
+		seq_puts(seq, "\n");
+
+		list_for_each_entry(task, &cset->tasks, cg_list) {
+			if (count++ <= MAX_TASKS_SHOWN_PER_CSS)
+				seq_printf(seq, "  task %d\n",
+					   task_pid_vnr(task));
+		}
+
+		list_for_each_entry(task, &cset->mg_tasks, cg_list) {
+			if (count++ <= MAX_TASKS_SHOWN_PER_CSS)
+				seq_printf(seq, "  task %d\n",
+					   task_pid_vnr(task));
+		}
+		/* show # of overflowed tasks */
+		if (count > MAX_TASKS_SHOWN_PER_CSS)
+			seq_printf(seq, "  ... (%d)\n",
+				   count - MAX_TASKS_SHOWN_PER_CSS);
+
+		if (cset->dead) {
+			seq_puts(seq, "    [dead]\n");
+			dead_cnt++;
+		}
+
+		WARN_ON(count != cset->nr_tasks);
+	}
+	spin_unlock_irq(&css_set_lock);
+
+	if (!dead_cnt && !extra_refs && !threaded_csets)
+		return 0;
+
+	seq_puts(seq, "\n");
+	if (threaded_csets)
+		seq_printf(seq, "threaded css_sets = %d\n", threaded_csets);
+	if (extra_refs)
+		seq_printf(seq, "extra references = %d\n", extra_refs);
+	if (dead_cnt)
+		seq_printf(seq, "dead css_sets = %d\n", dead_cnt);
+
+	return 0;
+}
+
+static int cgroup_subsys_states_read(struct seq_file *seq, void *v)
+{
+	struct kernfs_open_file *of = seq->private;
+	struct cgroup *cgrp;
+	struct cgroup_subsys *ss;
+	struct cgroup_subsys_state *css;
+	char pbuf[16];
+	int i;
+
+	cgrp = cgroup_kn_lock_live(of->kn, false);
+	if (!cgrp)
+		return -ENODEV;
+
+	for_each_subsys(ss, i) {
+		css = rcu_dereference_check(cgrp->subsys[ss->id], true);
+		if (!css)
+			continue;
+
+		pbuf[0] = '\0';
+
+		/* Show the parent CSS if applicable*/
+		if (css->parent)
+			snprintf(pbuf, sizeof(pbuf) - 1, " P=%d",
+				 css->parent->id);
+		seq_printf(seq, "%2d: %-4s\t- %lx[%d] %d%s\n", ss->id, ss->name,
+			  (unsigned long)css, css->id,
+			  atomic_read(&css->online_cnt), pbuf);
+	}
+
+	cgroup_kn_unlock(of->kn);
+	return 0;
+}
+
+static void cgroup_masks_read_one(struct seq_file *seq, const char *name,
+				  u16 mask)
+{
+	struct cgroup_subsys *ss;
+	int ssid;
+	bool first = true;
+
+	seq_printf(seq, "%-17s: ", name);
+	for_each_subsys(ss, ssid) {
+		if (!(mask & (1 << ssid)))
+			continue;
+		if (!first)
+			seq_puts(seq, ", ");
+		seq_puts(seq, ss->name);
+		first = false;
+	}
+	seq_putc(seq, '\n');
+}
+
+static int cgroup_masks_read(struct seq_file *seq, void *v)
+{
+	struct kernfs_open_file *of = seq->private;
+	struct cgroup *cgrp;
+
+	cgrp = cgroup_kn_lock_live(of->kn, false);
+	if (!cgrp)
+		return -ENODEV;
+
+	cgroup_masks_read_one(seq, "subtree_control", cgrp->subtree_control);
+	cgroup_masks_read_one(seq, "subtree_ss_mask", cgrp->subtree_ss_mask);
+
+	cgroup_kn_unlock(of->kn);
+	return 0;
+}
+
+static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	return (!cgroup_is_populated(css->cgroup) &&
+		!css_has_online_children(&css->cgroup->self));
+}
+
+static struct cftype debug_legacy_files[] =  {
+	{
+		.name = "taskcount",
+		.read_u64 = debug_taskcount_read,
+	},
+
+	{
+		.name = "current_css_set",
+		.seq_show = current_css_set_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
+	{
+		.name = "current_css_set_refcount",
+		.read_u64 = current_css_set_refcount_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
+	{
+		.name = "current_css_set_cg_links",
+		.seq_show = current_css_set_cg_links_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
+	{
+		.name = "cgroup_css_links",
+		.seq_show = cgroup_css_links_read,
+	},
+
+	{
+		.name = "cgroup_subsys_states",
+		.seq_show = cgroup_subsys_states_read,
+	},
+
+	{
+		.name = "cgroup_masks",
+		.seq_show = cgroup_masks_read,
+	},
+
+	{
+		.name = "releasable",
+		.read_u64 = releasable_read,
+	},
+
+	{ }	/* terminate */
+};
+
+static struct cftype debug_files[] =  {
+	{
+		.name = "taskcount",
+		.read_u64 = debug_taskcount_read,
+	},
+
+	{
+		.name = "current_css_set",
+		.seq_show = current_css_set_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
+	{
+		.name = "current_css_set_refcount",
+		.read_u64 = current_css_set_refcount_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
+	{
+		.name = "current_css_set_cg_links",
+		.seq_show = current_css_set_cg_links_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
+	{
+		.name = "css_links",
+		.seq_show = cgroup_css_links_read,
+	},
+
+	{
+		.name = "csses",
+		.seq_show = cgroup_subsys_states_read,
+	},
+
+	{
+		.name = "masks",
+		.seq_show = cgroup_masks_read,
+	},
+
+	{ }	/* terminate */
+};
+
+struct cgroup_subsys debug_cgrp_subsys = {
+	.css_alloc	= debug_css_alloc,
+	.css_free	= debug_css_free,
+	.legacy_cftypes	= debug_legacy_files,
+};
+
+/*
+ * On v2, debug is an implicit controller enabled by "cgroup_debug" boot
+ * parameter.
+ */
+static int __init enable_cgroup_debug(char *str)
+{
+	debug_cgrp_subsys.dfl_cftypes = debug_files;
+	debug_cgrp_subsys.implicit_on_dfl = true;
+	debug_cgrp_subsys.threaded = true;
+	return 1;
+}
+__setup("cgroup_debug", enable_cgroup_debug);

kernel/cgroup/freezer.c

@@ -0,0 +1,317 @@
+//SPDX-License-Identifier: GPL-2.0
+#include <linux/cgroup.h>
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/sched/signal.h>
+
+#include "cgroup-internal.h"
+
+/*
+ * Propagate the cgroup frozen state upwards by the cgroup tree.
+ */
+static void cgroup_propagate_frozen(struct cgroup *cgrp, bool frozen)
+{
+	int desc = 1;
+
+	/*
+	 * If the new state is frozen, some freezing ancestor cgroups may change
+	 * their state too, depending on if all their descendants are frozen.
+	 *
+	 * Otherwise, all ancestor cgroups are forced into the non-frozen state.
+	 */
+	while ((cgrp = cgroup_parent(cgrp))) {
+		if (frozen) {
+			cgrp->freezer.nr_frozen_descendants += desc;
+			if (!test_bit(CGRP_FROZEN, &cgrp->flags) &&
+			    test_bit(CGRP_FREEZE, &cgrp->flags) &&
+			    cgrp->freezer.nr_frozen_descendants ==
+			    cgrp->nr_descendants) {
+				set_bit(CGRP_FROZEN, &cgrp->flags);
+				cgroup_file_notify(&cgrp->events_file);
+				desc++;
+			}
+		} else {
+			cgrp->freezer.nr_frozen_descendants -= desc;
+			if (test_bit(CGRP_FROZEN, &cgrp->flags)) {
+				clear_bit(CGRP_FROZEN, &cgrp->flags);
+				cgroup_file_notify(&cgrp->events_file);
+				desc++;
+			}
+		}
+	}
+}
+
+/*
+ * Revisit the cgroup frozen state.
+ * Checks if the cgroup is really frozen and perform all state transitions.
+ */
+void cgroup_update_frozen(struct cgroup *cgrp)
+{
+	bool frozen;
+
+	lockdep_assert_held(&css_set_lock);
+
+	/*
+	 * If the cgroup has to be frozen (CGRP_FREEZE bit set),
+	 * and all tasks are frozen and/or stopped, let's consider
+	 * the cgroup frozen. Otherwise it's not frozen.
+	 */
+	frozen = test_bit(CGRP_FREEZE, &cgrp->flags) &&
+		cgrp->freezer.nr_frozen_tasks == __cgroup_task_count(cgrp);
+
+	if (frozen) {
+		/* Already there? */
+		if (test_bit(CGRP_FROZEN, &cgrp->flags))
+			return;
+
+		set_bit(CGRP_FROZEN, &cgrp->flags);
+	} else {
+		/* Already there? */
+		if (!test_bit(CGRP_FROZEN, &cgrp->flags))
+			return;
+
+		clear_bit(CGRP_FROZEN, &cgrp->flags);
+	}
+	cgroup_file_notify(&cgrp->events_file);
+
+	/* Update the state of ancestor cgroups. */
+	cgroup_propagate_frozen(cgrp, frozen);
+}
+
+/*
+ * Increment cgroup's nr_frozen_tasks.
+ */
+static void cgroup_inc_frozen_cnt(struct cgroup *cgrp)
+{
+	cgrp->freezer.nr_frozen_tasks++;
+}
+
+/*
+ * Decrement cgroup's nr_frozen_tasks.
+ */
+static void cgroup_dec_frozen_cnt(struct cgroup *cgrp)
+{
+	cgrp->freezer.nr_frozen_tasks--;
+	WARN_ON_ONCE(cgrp->freezer.nr_frozen_tasks < 0);
+}
+
+/*
+ * Enter frozen/stopped state, if not yet there. Update cgroup's counters,
+ * and revisit the state of the cgroup, if necessary.
+ */
+void cgroup_enter_frozen(void)
+{
+	struct cgroup *cgrp;
+
+	if (current->frozen)
+		return;
+
+	spin_lock_irq(&css_set_lock);
+	current->frozen = true;
+	cgrp = task_dfl_cgroup(current);
+	cgroup_inc_frozen_cnt(cgrp);
+	cgroup_update_frozen(cgrp);
+	spin_unlock_irq(&css_set_lock);
+}
+
+/*
+ * Conditionally leave frozen/stopped state. Update cgroup's counters,
+ * and revisit the state of the cgroup, if necessary.
+ *
+ * If always_leave is not set, and the cgroup is freezing,
+ * we're racing with the cgroup freezing. In this case, we don't
+ * drop the frozen counter to avoid a transient switch to
+ * the unfrozen state.
+ */
+void cgroup_leave_frozen(bool always_leave)
+{
+	struct cgroup *cgrp;
+
+	spin_lock_irq(&css_set_lock);
+	cgrp = task_dfl_cgroup(current);
+	if (always_leave || !test_bit(CGRP_FREEZE, &cgrp->flags)) {
+		cgroup_dec_frozen_cnt(cgrp);
+		cgroup_update_frozen(cgrp);
+		WARN_ON_ONCE(!current->frozen);
+		current->frozen = false;
+	}
+	spin_unlock_irq(&css_set_lock);
+
+	if (unlikely(current->frozen)) {
+		/*
+		 * If the task remained in the frozen state,
+		 * make sure it won't reach userspace without
+		 * entering the signal handling loop.
+		 */
+		spin_lock_irq(&current->sighand->siglock);
+		recalc_sigpending();
+		spin_unlock_irq(&current->sighand->siglock);
+	}
+}
+
+/*
+ * Freeze or unfreeze the task by setting or clearing the JOBCTL_TRAP_FREEZE
+ * jobctl bit.
+ */
+static void cgroup_freeze_task(struct task_struct *task, bool freeze)
+{
+	unsigned long flags;
+
+	/* If the task is about to die, don't bother with freezing it. */
+	if (!lock_task_sighand(task, &flags))
+		return;
+
+	if (freeze) {
+		task->jobctl |= JOBCTL_TRAP_FREEZE;
+		signal_wake_up(task, false);
+	} else {
+		task->jobctl &= ~JOBCTL_TRAP_FREEZE;
+		wake_up_process(task);
+	}
+
+	unlock_task_sighand(task, &flags);
+}
+
+/*
+ * Freeze or unfreeze all tasks in the given cgroup.
+ */
+static void cgroup_do_freeze(struct cgroup *cgrp, bool freeze)
+{
+	struct css_task_iter it;
+	struct task_struct *task;
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	spin_lock_irq(&css_set_lock);
+	if (freeze)
+		set_bit(CGRP_FREEZE, &cgrp->flags);
+	else
+		clear_bit(CGRP_FREEZE, &cgrp->flags);
+	spin_unlock_irq(&css_set_lock);
+
+	css_task_iter_start(&cgrp->self, 0, &it);
+	while ((task = css_task_iter_next(&it))) {
+		/*
+		 * Ignore kernel threads here. Freezing cgroups containing
+		 * kthreads isn't supported.
+		 */
+		if (task->flags & PF_KTHREAD)
+			continue;
+		cgroup_freeze_task(task, freeze);
+	}
+	css_task_iter_end(&it);
+
+	/*
+	 * Cgroup state should be revisited here to cover empty leaf cgroups
+	 * and cgroups which descendants are already in the desired state.
+	 */
+	spin_lock_irq(&css_set_lock);
+	if (cgrp->nr_descendants == cgrp->freezer.nr_frozen_descendants)
+		cgroup_update_frozen(cgrp);
+	spin_unlock_irq(&css_set_lock);
+}
+
+/*
+ * Adjust the task state (freeze or unfreeze) and revisit the state of
+ * source and destination cgroups.
+ */
+void cgroup_freezer_migrate_task(struct task_struct *task,
+				 struct cgroup *src, struct cgroup *dst)
+{
+	lockdep_assert_held(&css_set_lock);
+
+	/*
+	 * Kernel threads are not supposed to be frozen at all.
+	 */
+	if (task->flags & PF_KTHREAD)
+		return;
+
+	/*
+	 * Adjust counters of freezing and frozen tasks.
+	 * Note, that if the task is frozen, but the destination cgroup is not
+	 * frozen, we bump both counters to keep them balanced.
+	 */
+	if (task->frozen) {
+		cgroup_inc_frozen_cnt(dst);
+		cgroup_dec_frozen_cnt(src);
+	}
+	cgroup_update_frozen(dst);
+	cgroup_update_frozen(src);
+
+	/*
+	 * Force the task to the desired state.
+	 */
+	cgroup_freeze_task(task, test_bit(CGRP_FREEZE, &dst->flags));
+}
+
+void cgroup_freezer_frozen_exit(struct task_struct *task)
+{
+	struct cgroup *cgrp = task_dfl_cgroup(task);
+
+	lockdep_assert_held(&css_set_lock);
+
+	cgroup_dec_frozen_cnt(cgrp);
+	cgroup_update_frozen(cgrp);
+}
+
+void cgroup_freeze(struct cgroup *cgrp, bool freeze)
+{
+	struct cgroup_subsys_state *css;
+	struct cgroup *dsct;
+	bool applied = false;
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	/*
+	 * Nothing changed? Just exit.
+	 */
+	if (cgrp->freezer.freeze == freeze)
+		return;
+
+	cgrp->freezer.freeze = freeze;
+
+	/*
+	 * Propagate changes downwards the cgroup tree.
+	 */
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		dsct = css->cgroup;
+
+		if (cgroup_is_dead(dsct))
+			continue;
+
+		if (freeze) {
+			dsct->freezer.e_freeze++;
+			/*
+			 * Already frozen because of ancestor's settings?
+			 */
+			if (dsct->freezer.e_freeze > 1)
+				continue;
+		} else {
+			dsct->freezer.e_freeze--;
+			/*
+			 * Still frozen because of ancestor's settings?
+			 */
+			if (dsct->freezer.e_freeze > 0)
+				continue;
+
+			WARN_ON_ONCE(dsct->freezer.e_freeze < 0);
+		}
+
+		/*
+		 * Do change actual state: freeze or unfreeze.
+		 */
+		cgroup_do_freeze(dsct, freeze);
+		applied = true;
+	}
+
+	/*
+	 * Even if the actual state hasn't changed, let's notify a user.
+	 * The state can be enforced by an ancestor cgroup: the cgroup
+	 * can already be in the desired state or it can be locked in the
+	 * opposite state, so that the transition will never happen.
+	 * In both cases it's better to notify a user, that there is
+	 * nothing to wait for.
+	 */
+	if (!applied)
+		cgroup_file_notify(&cgrp->events_file);
+}

kernel/cgroup/legacy_freezer.c

@@ -0,0 +1,481 @@
+/*
+ * cgroup_freezer.c -  control group freezer subsystem
+ *
+ * Copyright IBM Corporation, 2007
+ *
+ * Author : Cedric Le Goater <clg@fr.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/cgroup.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/freezer.h>
+#include <linux/seq_file.h>
+#include <linux/mutex.h>
+
+/*
+ * A cgroup is freezing if any FREEZING flags are set.  FREEZING_SELF is
+ * set if "FROZEN" is written to freezer.state cgroupfs file, and cleared
+ * for "THAWED".  FREEZING_PARENT is set if the parent freezer is FREEZING
+ * for whatever reason.  IOW, a cgroup has FREEZING_PARENT set if one of
+ * its ancestors has FREEZING_SELF set.
+ */
+enum freezer_state_flags {
+	CGROUP_FREEZER_ONLINE	= (1 << 0), /* freezer is fully online */
+	CGROUP_FREEZING_SELF	= (1 << 1), /* this freezer is freezing */
+	CGROUP_FREEZING_PARENT	= (1 << 2), /* the parent freezer is freezing */
+	CGROUP_FROZEN		= (1 << 3), /* this and its descendants frozen */
+
+	/* mask for all FREEZING flags */
+	CGROUP_FREEZING		= CGROUP_FREEZING_SELF | CGROUP_FREEZING_PARENT,
+};
+
+struct freezer {
+	struct cgroup_subsys_state	css;
+	unsigned int			state;
+};
+
+static DEFINE_MUTEX(freezer_mutex);
+
+static inline struct freezer *css_freezer(struct cgroup_subsys_state *css)
+{
+	return css ? container_of(css, struct freezer, css) : NULL;
+}
+
+static inline struct freezer *task_freezer(struct task_struct *task)
+{
+	return css_freezer(task_css(task, freezer_cgrp_id));
+}
+
+static struct freezer *parent_freezer(struct freezer *freezer)
+{
+	return css_freezer(freezer->css.parent);
+}
+
+bool cgroup_freezing(struct task_struct *task)
+{
+	bool ret;
+
+	rcu_read_lock();
+	ret = task_freezer(task)->state & CGROUP_FREEZING;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static const char *freezer_state_strs(unsigned int state)
+{
+	if (state & CGROUP_FROZEN)
+		return "FROZEN";
+	if (state & CGROUP_FREEZING)
+		return "FREEZING";
+	return "THAWED";
+};
+
+static struct cgroup_subsys_state *
+freezer_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+	struct freezer *freezer;
+
+	freezer = kzalloc(sizeof(struct freezer), GFP_KERNEL);
+	if (!freezer)
+		return ERR_PTR(-ENOMEM);
+
+	return &freezer->css;
+}
+
+/**
+ * freezer_css_online - commit creation of a freezer css
+ * @css: css being created
+ *
+ * We're committing to creation of @css.  Mark it online and inherit
+ * parent's freezing state while holding both parent's and our
+ * freezer->lock.
+ */
+static int freezer_css_online(struct cgroup_subsys_state *css)
+{
+	struct freezer *freezer = css_freezer(css);
+	struct freezer *parent = parent_freezer(freezer);
+
+	mutex_lock(&freezer_mutex);
+
+	freezer->state |= CGROUP_FREEZER_ONLINE;
+
+	if (parent && (parent->state & CGROUP_FREEZING)) {
+		freezer->state |= CGROUP_FREEZING_PARENT | CGROUP_FROZEN;
+		atomic_inc(&system_freezing_cnt);
+	}
+
+	mutex_unlock(&freezer_mutex);
+	return 0;
+}
+
+/**
+ * freezer_css_offline - initiate destruction of a freezer css
+ * @css: css being destroyed
+ *
+ * @css is going away.  Mark it dead and decrement system_freezing_count if
+ * it was holding one.
+ */
+static void freezer_css_offline(struct cgroup_subsys_state *css)
+{
+	struct freezer *freezer = css_freezer(css);
+
+	mutex_lock(&freezer_mutex);
+
+	if (freezer->state & CGROUP_FREEZING)
+		atomic_dec(&system_freezing_cnt);
+
+	freezer->state = 0;
+
+	mutex_unlock(&freezer_mutex);
+}
+
+static void freezer_css_free(struct cgroup_subsys_state *css)
+{
+	kfree(css_freezer(css));
+}
+
+/*
+ * Tasks can be migrated into a different freezer anytime regardless of its
+ * current state.  freezer_attach() is responsible for making new tasks
+ * conform to the current state.
+ *
+ * Freezer state changes and task migration are synchronized via
+ * @freezer->lock.  freezer_attach() makes the new tasks conform to the
+ * current state and all following state changes can see the new tasks.
+ */
+static void freezer_attach(struct cgroup_taskset *tset)
+{
+	struct task_struct *task;
+	struct cgroup_subsys_state *new_css;
+
+	mutex_lock(&freezer_mutex);
+
+	/*
+	 * Make the new tasks conform to the current state of @new_css.
+	 * For simplicity, when migrating any task to a FROZEN cgroup, we
+	 * revert it to FREEZING and let update_if_frozen() determine the
+	 * correct state later.
+	 *
+	 * Tasks in @tset are on @new_css but may not conform to its
+	 * 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) {
+		struct freezer *freezer = css_freezer(new_css);
+
+		if (!(freezer->state & CGROUP_FREEZING)) {
+			__thaw_task(task);
+		} else {
+			freeze_task(task);
+			/* clear FROZEN and propagate upwards */
+			while (freezer && (freezer->state & CGROUP_FROZEN)) {
+				freezer->state &= ~CGROUP_FROZEN;
+				freezer = parent_freezer(freezer);
+			}
+		}
+	}
+
+	mutex_unlock(&freezer_mutex);
+}
+
+/**
+ * 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;
+
+	/*
+	 * 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 (task_css_is_root(task, freezer_cgrp_id))
+		return;
+
+	mutex_lock(&freezer_mutex);
+	rcu_read_lock();
+
+	freezer = task_freezer(task);
+	if (freezer->state & CGROUP_FREEZING)
+		freeze_task(task);
+
+	rcu_read_unlock();
+	mutex_unlock(&freezer_mutex);
+}
+
+/**
+ * update_if_frozen - update whether a cgroup finished freezing
+ * @css: css of interest
+ *
+ * Once FREEZING is initiated, transition to FROZEN is lazily updated by
+ * calling this function.  If the current state is FREEZING but not FROZEN,
+ * this function checks whether all tasks of this cgroup and the descendant
+ * cgroups finished freezing and, if so, sets FROZEN.
+ *
+ * The caller is responsible for grabbing RCU read lock and calling
+ * update_if_frozen() on all descendants prior to invoking this function.
+ *
+ * Task states and freezer state might disagree while tasks are being
+ * migrated into or out of @css, so we can't verify task states against
+ * @freezer state here.  See freezer_attach() for details.
+ */
+static void update_if_frozen(struct cgroup_subsys_state *css)
+{
+	struct freezer *freezer = css_freezer(css);
+	struct cgroup_subsys_state *pos;
+	struct css_task_iter it;
+	struct task_struct *task;
+
+	lockdep_assert_held(&freezer_mutex);
+
+	if (!(freezer->state & CGROUP_FREEZING) ||
+	    (freezer->state & CGROUP_FROZEN))
+		return;
+
+	/* are all (live) children frozen? */
+	rcu_read_lock();
+	css_for_each_child(pos, css) {
+		struct freezer *child = css_freezer(pos);
+
+		if ((child->state & CGROUP_FREEZER_ONLINE) &&
+		    !(child->state & CGROUP_FROZEN)) {
+			rcu_read_unlock();
+			return;
+		}
+	}
+	rcu_read_unlock();
+
+	/* are all tasks frozen? */
+	css_task_iter_start(css, 0, &it);
+
+	while ((task = css_task_iter_next(&it))) {
+		if (freezing(task)) {
+			/*
+			 * freezer_should_skip() indicates that the task
+			 * should be skipped when determining freezing
+			 * completion.  Consider it frozen in addition to
+			 * the usual frozen condition.
+			 */
+			if (!frozen(task) && !freezer_should_skip(task))
+				goto out_iter_end;
+		}
+	}
+
+	freezer->state |= CGROUP_FROZEN;
+out_iter_end:
+	css_task_iter_end(&it);
+}
+
+static int freezer_read(struct seq_file *m, void *v)
+{
+	struct cgroup_subsys_state *css = seq_css(m), *pos;
+
+	mutex_lock(&freezer_mutex);
+	rcu_read_lock();
+
+	/* update states bottom-up */
+	css_for_each_descendant_post(pos, css) {
+		if (!css_tryget_online(pos))
+			continue;
+		rcu_read_unlock();
+
+		update_if_frozen(pos);
+
+		rcu_read_lock();
+		css_put(pos);
+	}
+
+	rcu_read_unlock();
+	mutex_unlock(&freezer_mutex);
+
+	seq_puts(m, freezer_state_strs(css_freezer(css)->state));
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static void freeze_cgroup(struct freezer *freezer)
+{
+	struct css_task_iter it;
+	struct task_struct *task;
+
+	css_task_iter_start(&freezer->css, 0, &it);
+	while ((task = css_task_iter_next(&it)))
+		freeze_task(task);
+	css_task_iter_end(&it);
+}
+
+static void unfreeze_cgroup(struct freezer *freezer)
+{
+	struct css_task_iter it;
+	struct task_struct *task;
+
+	css_task_iter_start(&freezer->css, 0, &it);
+	while ((task = css_task_iter_next(&it)))
+		__thaw_task(task);
+	css_task_iter_end(&it);
+}
+
+/**
+ * freezer_apply_state - apply state change to a single cgroup_freezer
+ * @freezer: freezer to apply state change to
+ * @freeze: whether to freeze or unfreeze
+ * @state: CGROUP_FREEZING_* flag to set or clear
+ *
+ * Set or clear @state on @cgroup according to @freeze, and perform
+ * freezing or thawing as necessary.
+ */
+static void freezer_apply_state(struct freezer *freezer, bool freeze,
+				unsigned int state)
+{
+	/* also synchronizes against task migration, see freezer_attach() */
+	lockdep_assert_held(&freezer_mutex);
+
+	if (!(freezer->state & CGROUP_FREEZER_ONLINE))
+		return;
+
+	if (freeze) {
+		if (!(freezer->state & CGROUP_FREEZING))
+			atomic_inc(&system_freezing_cnt);
+		freezer->state |= state;
+		freeze_cgroup(freezer);
+	} else {
+		bool was_freezing = freezer->state & CGROUP_FREEZING;
+
+		freezer->state &= ~state;
+
+		if (!(freezer->state & CGROUP_FREEZING)) {
+			if (was_freezing)
+				atomic_dec(&system_freezing_cnt);
+			freezer->state &= ~CGROUP_FROZEN;
+			unfreeze_cgroup(freezer);
+		}
+	}
+}
+
+/**
+ * freezer_change_state - change the freezing state of a cgroup_freezer
+ * @freezer: freezer of interest
+ * @freeze: whether to freeze or thaw
+ *
+ * Freeze or thaw @freezer according to @freeze.  The operations are
+ * recursive - all descendants of @freezer will be affected.
+ */
+static void freezer_change_state(struct freezer *freezer, bool freeze)
+{
+	struct cgroup_subsys_state *pos;
+
+	/*
+	 * Update all its descendants in pre-order traversal.  Each
+	 * descendant will try to inherit its parent's FREEZING state as
+	 * CGROUP_FREEZING_PARENT.
+	 */
+	mutex_lock(&freezer_mutex);
+	rcu_read_lock();
+	css_for_each_descendant_pre(pos, &freezer->css) {
+		struct freezer *pos_f = css_freezer(pos);
+		struct freezer *parent = parent_freezer(pos_f);
+
+		if (!css_tryget_online(pos))
+			continue;
+		rcu_read_unlock();
+
+		if (pos_f == freezer)
+			freezer_apply_state(pos_f, freeze,
+					    CGROUP_FREEZING_SELF);
+		else
+			freezer_apply_state(pos_f,
+					    parent->state & CGROUP_FREEZING,
+					    CGROUP_FREEZING_PARENT);
+
+		rcu_read_lock();
+		css_put(pos);
+	}
+	rcu_read_unlock();
+	mutex_unlock(&freezer_mutex);
+}
+
+static ssize_t freezer_write(struct kernfs_open_file *of,
+			     char *buf, size_t nbytes, loff_t off)
+{
+	bool freeze;
+
+	buf = strstrip(buf);
+
+	if (strcmp(buf, freezer_state_strs(0)) == 0)
+		freeze = false;
+	else if (strcmp(buf, freezer_state_strs(CGROUP_FROZEN)) == 0)
+		freeze = true;
+	else
+		return -EINVAL;
+
+	freezer_change_state(css_freezer(of_css(of)), freeze);
+	return nbytes;
+}
+
+static u64 freezer_self_freezing_read(struct cgroup_subsys_state *css,
+				      struct cftype *cft)
+{
+	struct freezer *freezer = css_freezer(css);
+
+	return (bool)(freezer->state & CGROUP_FREEZING_SELF);
+}
+
+static u64 freezer_parent_freezing_read(struct cgroup_subsys_state *css,
+					struct cftype *cft)
+{
+	struct freezer *freezer = css_freezer(css);
+
+	return (bool)(freezer->state & CGROUP_FREEZING_PARENT);
+}
+
+static struct cftype files[] = {
+	{
+		.name = "state",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = freezer_read,
+		.write = freezer_write,
+	},
+	{
+		.name = "self_freezing",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = freezer_self_freezing_read,
+	},
+	{
+		.name = "parent_freezing",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = freezer_parent_freezing_read,
+	},
+	{ }	/* terminate */
+};
+
+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,
+	.attach		= freezer_attach,
+	.fork		= freezer_fork,
+	.legacy_cftypes	= files,
+};

kernel/cgroup/namespace.c

@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "cgroup-internal.h"
+
+#include <linux/sched/task.h>
+#include <linux/slab.h>
+#include <linux/nsproxy.h>
+#include <linux/proc_ns.h>
+
+
+/* cgroup namespaces */
+
+static struct ucounts *inc_cgroup_namespaces(struct user_namespace *ns)
+{
+	return inc_ucount(ns, current_euid(), UCOUNT_CGROUP_NAMESPACES);
+}
+
+static void dec_cgroup_namespaces(struct ucounts *ucounts)
+{
+	dec_ucount(ucounts, UCOUNT_CGROUP_NAMESPACES);
+}
+
+static struct cgroup_namespace *alloc_cgroup_ns(void)
+{
+	struct cgroup_namespace *new_ns;
+	int ret;
+
+	new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL);
+	if (!new_ns)
+		return ERR_PTR(-ENOMEM);
+	ret = ns_alloc_inum(&new_ns->ns);
+	if (ret) {
+		kfree(new_ns);
+		return ERR_PTR(ret);
+	}
+	refcount_set(&new_ns->count, 1);
+	new_ns->ns.ops = &cgroupns_operations;
+	return new_ns;
+}
+
+void free_cgroup_ns(struct cgroup_namespace *ns)
+{
+	put_css_set(ns->root_cset);
+	dec_cgroup_namespaces(ns->ucounts);
+	put_user_ns(ns->user_ns);
+	ns_free_inum(&ns->ns);
+	kfree(ns);
+}
+EXPORT_SYMBOL(free_cgroup_ns);
+
+struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
+					struct user_namespace *user_ns,
+					struct cgroup_namespace *old_ns)
+{
+	struct cgroup_namespace *new_ns;
+	struct ucounts *ucounts;
+	struct css_set *cset;
+
+	BUG_ON(!old_ns);
+
+	if (!(flags & CLONE_NEWCGROUP)) {
+		get_cgroup_ns(old_ns);
+		return old_ns;
+	}
+
+	/* Allow only sysadmin to create cgroup namespace. */
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	ucounts = inc_cgroup_namespaces(user_ns);
+	if (!ucounts)
+		return ERR_PTR(-ENOSPC);
+
+	/* It is not safe to take cgroup_mutex here */
+	spin_lock_irq(&css_set_lock);
+	cset = task_css_set(current);
+	get_css_set(cset);
+	spin_unlock_irq(&css_set_lock);
+
+	new_ns = alloc_cgroup_ns();
+	if (IS_ERR(new_ns)) {
+		put_css_set(cset);
+		dec_cgroup_namespaces(ucounts);
+		return new_ns;
+	}
+
+	new_ns->user_ns = get_user_ns(user_ns);
+	new_ns->ucounts = ucounts;
+	new_ns->root_cset = cset;
+
+	return new_ns;
+}
+
+static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns)
+{
+	return container_of(ns, struct cgroup_namespace, ns);
+}
+
+static int cgroupns_install(struct nsproxy *nsproxy, struct ns_common *ns)
+{
+	struct cgroup_namespace *cgroup_ns = to_cg_ns(ns);
+
+	if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN) ||
+	    !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* Don't need to do anything if we are attaching to our own cgroupns. */
+	if (cgroup_ns == nsproxy->cgroup_ns)
+		return 0;
+
+	get_cgroup_ns(cgroup_ns);
+	put_cgroup_ns(nsproxy->cgroup_ns);
+	nsproxy->cgroup_ns = cgroup_ns;
+
+	return 0;
+}
+
+static struct ns_common *cgroupns_get(struct task_struct *task)
+{
+	struct cgroup_namespace *ns = NULL;
+	struct nsproxy *nsproxy;
+
+	task_lock(task);
+	nsproxy = task->nsproxy;
+	if (nsproxy) {
+		ns = nsproxy->cgroup_ns;
+		get_cgroup_ns(ns);
+	}
+	task_unlock(task);
+
+	return ns ? &ns->ns : NULL;
+}
+
+static void cgroupns_put(struct ns_common *ns)
+{
+	put_cgroup_ns(to_cg_ns(ns));
+}
+
+static struct user_namespace *cgroupns_owner(struct ns_common *ns)
+{
+	return to_cg_ns(ns)->user_ns;
+}
+
+const struct proc_ns_operations cgroupns_operations = {
+	.name		= "cgroup",
+	.type		= CLONE_NEWCGROUP,
+	.get		= cgroupns_get,
+	.put		= cgroupns_put,
+	.install	= cgroupns_install,
+	.owner		= cgroupns_owner,
+};
+
+static __init int cgroup_namespaces_init(void)
+{
+	return 0;
+}
+subsys_initcall(cgroup_namespaces_init);

kernel/cgroup/pids.c

@@ -0,0 +1,350 @@
+/*
+ * Process number limiting controller for cgroups.
+ *
+ * Used to allow a cgroup hierarchy to stop any new processes from fork()ing
+ * after a certain limit is reached.
+ *
+ * Since it is trivial to hit the task limit without hitting any kmemcg limits
+ * in place, PIDs are a fundamental resource. As such, PID exhaustion must be
+ * preventable in the scope of a cgroup hierarchy by allowing resource limiting
+ * of the number of tasks in a cgroup.
+ *
+ * In order to use the `pids` controller, set the maximum number of tasks in
+ * pids.max (this is not available in the root cgroup for obvious reasons). The
+ * number of processes currently in the cgroup is given by pids.current.
+ * Organisational operations are not blocked by cgroup policies, so it is
+ * possible to have pids.current > pids.max. However, it is not possible to
+ * violate a cgroup policy through fork(). fork() will return -EAGAIN if forking
+ * would cause a cgroup policy to be violated.
+ *
+ * To set a cgroup to have no limit, set pids.max to "max". This is the default
+ * for all new cgroups (N.B. that PID limits are hierarchical, so the most
+ * stringent limit in the hierarchy is followed).
+ *
+ * pids.current tracks all child cgroup hierarchies, so parent/pids.current is
+ * a superset of parent/child/pids.current.
+ *
+ * Copyright (C) 2015 Aleksa Sarai <cyphar@cyphar.com>
+ *
+ * This file is subject to the terms and conditions of version 2 of the GNU
+ * General Public License.  See the file COPYING in the main directory of the
+ * Linux distribution for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/threads.h>
+#include <linux/atomic.h>
+#include <linux/cgroup.h>
+#include <linux/slab.h>
+
+#define PIDS_MAX (PID_MAX_LIMIT + 1ULL)
+#define PIDS_MAX_STR "max"
+
+struct pids_cgroup {
+	struct cgroup_subsys_state	css;
+
+	/*
+	 * Use 64-bit types so that we can safely represent "max" as
+	 * %PIDS_MAX = (%PID_MAX_LIMIT + 1).
+	 */
+	atomic64_t			counter;
+	atomic64_t			limit;
+
+	/* Handle for "pids.events" */
+	struct cgroup_file		events_file;
+
+	/* Number of times fork failed because limit was hit. */
+	atomic64_t			events_limit;
+};
+
+static struct pids_cgroup *css_pids(struct cgroup_subsys_state *css)
+{
+	return container_of(css, struct pids_cgroup, css);
+}
+
+static struct pids_cgroup *parent_pids(struct pids_cgroup *pids)
+{
+	return css_pids(pids->css.parent);
+}
+
+static struct cgroup_subsys_state *
+pids_css_alloc(struct cgroup_subsys_state *parent)
+{
+	struct pids_cgroup *pids;
+
+	pids = kzalloc(sizeof(struct pids_cgroup), GFP_KERNEL);
+	if (!pids)
+		return ERR_PTR(-ENOMEM);
+
+	atomic64_set(&pids->counter, 0);
+	atomic64_set(&pids->limit, PIDS_MAX);
+	atomic64_set(&pids->events_limit, 0);
+	return &pids->css;
+}
+
+static void pids_css_free(struct cgroup_subsys_state *css)
+{
+	kfree(css_pids(css));
+}
+
+/**
+ * pids_cancel - uncharge the local pid count
+ * @pids: the pid cgroup state
+ * @num: the number of pids to cancel
+ *
+ * This function will WARN if the pid count goes under 0, because such a case is
+ * a bug in the pids controller proper.
+ */
+static void pids_cancel(struct pids_cgroup *pids, int num)
+{
+	/*
+	 * A negative count (or overflow for that matter) is invalid,
+	 * and indicates a bug in the `pids` controller proper.
+	 */
+	WARN_ON_ONCE(atomic64_add_negative(-num, &pids->counter));
+}
+
+/**
+ * pids_uncharge - hierarchically uncharge the pid count
+ * @pids: the pid cgroup state
+ * @num: the number of pids to uncharge
+ */
+static void pids_uncharge(struct pids_cgroup *pids, int num)
+{
+	struct pids_cgroup *p;
+
+	for (p = pids; parent_pids(p); p = parent_pids(p))
+		pids_cancel(p, num);
+}
+
+/**
+ * pids_charge - hierarchically charge the pid count
+ * @pids: the pid cgroup state
+ * @num: the number of pids to charge
+ *
+ * This function does *not* follow the pid limit set. It cannot fail and the new
+ * pid count may exceed the limit. This is only used for reverting failed
+ * attaches, where there is no other way out than violating the limit.
+ */
+static void pids_charge(struct pids_cgroup *pids, int num)
+{
+	struct pids_cgroup *p;
+
+	for (p = pids; parent_pids(p); p = parent_pids(p))
+		atomic64_add(num, &p->counter);
+}
+
+/**
+ * pids_try_charge - hierarchically try to charge the pid count
+ * @pids: the pid cgroup state
+ * @num: the number of pids to charge
+ *
+ * This function follows the set limit. It will fail if the charge would cause
+ * the new value to exceed the hierarchical limit. Returns 0 if the charge
+ * succeeded, otherwise -EAGAIN.
+ */
+static int pids_try_charge(struct pids_cgroup *pids, int num)
+{
+	struct pids_cgroup *p, *q;
+
+	for (p = pids; parent_pids(p); p = parent_pids(p)) {
+		int64_t new = atomic64_add_return(num, &p->counter);
+		int64_t limit = atomic64_read(&p->limit);
+
+		/*
+		 * Since new is capped to the maximum number of pid_t, if
+		 * p->limit is %PIDS_MAX then we know that this test will never
+		 * fail.
+		 */
+		if (new > limit)
+			goto revert;
+	}
+
+	return 0;
+
+revert:
+	for (q = pids; q != p; q = parent_pids(q))
+		pids_cancel(q, num);
+	pids_cancel(p, num);
+
+	return -EAGAIN;
+}
+
+static int pids_can_attach(struct cgroup_taskset *tset)
+{
+	struct task_struct *task;
+	struct cgroup_subsys_state *dst_css;
+
+	cgroup_taskset_for_each(task, dst_css, tset) {
+		struct pids_cgroup *pids = css_pids(dst_css);
+		struct cgroup_subsys_state *old_css;
+		struct pids_cgroup *old_pids;
+
+		/*
+		 * No need to pin @old_css between here and cancel_attach()
+		 * because cgroup core protects it from being freed before
+		 * the migration completes or fails.
+		 */
+		old_css = task_css(task, pids_cgrp_id);
+		old_pids = css_pids(old_css);
+
+		pids_charge(pids, 1);
+		pids_uncharge(old_pids, 1);
+	}
+
+	return 0;
+}
+
+static void pids_cancel_attach(struct cgroup_taskset *tset)
+{
+	struct task_struct *task;
+	struct cgroup_subsys_state *dst_css;
+
+	cgroup_taskset_for_each(task, dst_css, tset) {
+		struct pids_cgroup *pids = css_pids(dst_css);
+		struct cgroup_subsys_state *old_css;
+		struct pids_cgroup *old_pids;
+
+		old_css = task_css(task, pids_cgrp_id);
+		old_pids = css_pids(old_css);
+
+		pids_charge(old_pids, 1);
+		pids_uncharge(pids, 1);
+	}
+}
+
+/*
+ * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies
+ * on cgroup_threadgroup_change_begin() held by the copy_process().
+ */
+static int pids_can_fork(struct task_struct *task)
+{
+	struct cgroup_subsys_state *css;
+	struct pids_cgroup *pids;
+	int err;
+
+	css = task_css_check(current, pids_cgrp_id, true);
+	pids = css_pids(css);
+	err = pids_try_charge(pids, 1);
+	if (err) {
+		/* Only log the first time events_limit is incremented. */
+		if (atomic64_inc_return(&pids->events_limit) == 1) {
+			pr_info("cgroup: fork rejected by pids controller in ");
+			pr_cont_cgroup_path(css->cgroup);
+			pr_cont("\n");
+		}
+		cgroup_file_notify(&pids->events_file);
+	}
+	return err;
+}
+
+static void pids_cancel_fork(struct task_struct *task)
+{
+	struct cgroup_subsys_state *css;
+	struct pids_cgroup *pids;
+
+	css = task_css_check(current, pids_cgrp_id, true);
+	pids = css_pids(css);
+	pids_uncharge(pids, 1);
+}
+
+static void pids_release(struct task_struct *task)
+{
+	struct pids_cgroup *pids = css_pids(task_css(task, pids_cgrp_id));
+
+	pids_uncharge(pids, 1);
+}
+
+static ssize_t pids_max_write(struct kernfs_open_file *of, char *buf,
+			      size_t nbytes, loff_t off)
+{
+	struct cgroup_subsys_state *css = of_css(of);
+	struct pids_cgroup *pids = css_pids(css);
+	int64_t limit;
+	int err;
+
+	buf = strstrip(buf);
+	if (!strcmp(buf, PIDS_MAX_STR)) {
+		limit = PIDS_MAX;
+		goto set_limit;
+	}
+
+	err = kstrtoll(buf, 0, &limit);
+	if (err)
+		return err;
+
+	if (limit < 0 || limit >= PIDS_MAX)
+		return -EINVAL;
+
+set_limit:
+	/*
+	 * Limit updates don't need to be mutex'd, since it isn't
+	 * critical that any racing fork()s follow the new limit.
+	 */
+	atomic64_set(&pids->limit, limit);
+	return nbytes;
+}
+
+static int pids_max_show(struct seq_file *sf, void *v)
+{
+	struct cgroup_subsys_state *css = seq_css(sf);
+	struct pids_cgroup *pids = css_pids(css);
+	int64_t limit = atomic64_read(&pids->limit);
+
+	if (limit >= PIDS_MAX)
+		seq_printf(sf, "%s\n", PIDS_MAX_STR);
+	else
+		seq_printf(sf, "%lld\n", limit);
+
+	return 0;
+}
+
+static s64 pids_current_read(struct cgroup_subsys_state *css,
+			     struct cftype *cft)
+{
+	struct pids_cgroup *pids = css_pids(css);
+
+	return atomic64_read(&pids->counter);
+}
+
+static int pids_events_show(struct seq_file *sf, void *v)
+{
+	struct pids_cgroup *pids = css_pids(seq_css(sf));
+
+	seq_printf(sf, "max %lld\n", (s64)atomic64_read(&pids->events_limit));
+	return 0;
+}
+
+static struct cftype pids_files[] = {
+	{
+		.name = "max",
+		.write = pids_max_write,
+		.seq_show = pids_max_show,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "current",
+		.read_s64 = pids_current_read,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "events",
+		.seq_show = pids_events_show,
+		.file_offset = offsetof(struct pids_cgroup, events_file),
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{ }	/* terminate */
+};
+
+struct cgroup_subsys pids_cgrp_subsys = {
+	.css_alloc	= pids_css_alloc,
+	.css_free	= pids_css_free,
+	.can_attach 	= pids_can_attach,
+	.cancel_attach 	= pids_cancel_attach,
+	.can_fork	= pids_can_fork,
+	.cancel_fork	= pids_cancel_fork,
+	.release	= pids_release,
+	.legacy_cftypes	= pids_files,
+	.dfl_cftypes	= pids_files,
+	.threaded	= true,
+};

kernel/cgroup/rdma.c

@@ -0,0 +1,616 @@
+/*
+ * RDMA resource limiting controller for cgroups.
+ *
+ * Used to allow a cgroup hierarchy to stop processes from consuming
+ * additional RDMA resources after a certain limit is reached.
+ *
+ * Copyright (C) 2016 Parav Pandit <pandit.parav@gmail.com>
+ *
+ * This file is subject to the terms and conditions of version 2 of the GNU
+ * General Public License. See the file COPYING in the main directory of the
+ * Linux distribution for more details.
+ */
+
+#include <linux/bitops.h>
+#include <linux/slab.h>
+#include <linux/seq_file.h>
+#include <linux/cgroup.h>
+#include <linux/parser.h>
+#include <linux/cgroup_rdma.h>
+
+#define RDMACG_MAX_STR "max"
+
+/*
+ * Protects list of resource pools maintained on per cgroup basis
+ * and rdma device list.
+ */
+static DEFINE_MUTEX(rdmacg_mutex);
+static LIST_HEAD(rdmacg_devices);
+
+enum rdmacg_file_type {
+	RDMACG_RESOURCE_TYPE_MAX,
+	RDMACG_RESOURCE_TYPE_STAT,
+};
+
+/*
+ * resource table definition as to be seen by the user.
+ * Need to add entries to it when more resources are
+ * added/defined at IB verb/core layer.
+ */
+static char const *rdmacg_resource_names[] = {
+	[RDMACG_RESOURCE_HCA_HANDLE]	= "hca_handle",
+	[RDMACG_RESOURCE_HCA_OBJECT]	= "hca_object",
+};
+
+/* resource tracker for each resource of rdma cgroup */
+struct rdmacg_resource {
+	int max;
+	int usage;
+};
+
+/*
+ * resource pool object which represents per cgroup, per device
+ * resources. There are multiple instances of this object per cgroup,
+ * therefore it cannot be embedded within rdma_cgroup structure. It
+ * is maintained as list.
+ */
+struct rdmacg_resource_pool {
+	struct rdmacg_device	*device;
+	struct rdmacg_resource	resources[RDMACG_RESOURCE_MAX];
+
+	struct list_head	cg_node;
+	struct list_head	dev_node;
+
+	/* count active user tasks of this pool */
+	u64			usage_sum;
+	/* total number counts which are set to max */
+	int			num_max_cnt;
+};
+
+static struct rdma_cgroup *css_rdmacg(struct cgroup_subsys_state *css)
+{
+	return container_of(css, struct rdma_cgroup, css);
+}
+
+static struct rdma_cgroup *parent_rdmacg(struct rdma_cgroup *cg)
+{
+	return css_rdmacg(cg->css.parent);
+}
+
+static inline struct rdma_cgroup *get_current_rdmacg(void)
+{
+	return css_rdmacg(task_get_css(current, rdma_cgrp_id));
+}
+
+static void set_resource_limit(struct rdmacg_resource_pool *rpool,
+			       int index, int new_max)
+{
+	if (new_max == S32_MAX) {
+		if (rpool->resources[index].max != S32_MAX)
+			rpool->num_max_cnt++;
+	} else {
+		if (rpool->resources[index].max == S32_MAX)
+			rpool->num_max_cnt--;
+	}
+	rpool->resources[index].max = new_max;
+}
+
+static void set_all_resource_max_limit(struct rdmacg_resource_pool *rpool)
+{
+	int i;
+
+	for (i = 0; i < RDMACG_RESOURCE_MAX; i++)
+		set_resource_limit(rpool, i, S32_MAX);
+}
+
+static void free_cg_rpool_locked(struct rdmacg_resource_pool *rpool)
+{
+	lockdep_assert_held(&rdmacg_mutex);
+
+	list_del(&rpool->cg_node);
+	list_del(&rpool->dev_node);
+	kfree(rpool);
+}
+
+static struct rdmacg_resource_pool *
+find_cg_rpool_locked(struct rdma_cgroup *cg,
+		     struct rdmacg_device *device)
+
+{
+	struct rdmacg_resource_pool *pool;
+
+	lockdep_assert_held(&rdmacg_mutex);
+
+	list_for_each_entry(pool, &cg->rpools, cg_node)
+		if (pool->device == device)
+			return pool;
+
+	return NULL;
+}
+
+static struct rdmacg_resource_pool *
+get_cg_rpool_locked(struct rdma_cgroup *cg, struct rdmacg_device *device)
+{
+	struct rdmacg_resource_pool *rpool;
+
+	rpool = find_cg_rpool_locked(cg, device);
+	if (rpool)
+		return rpool;
+
+	rpool = kzalloc(sizeof(*rpool), GFP_KERNEL);
+	if (!rpool)
+		return ERR_PTR(-ENOMEM);
+
+	rpool->device = device;
+	set_all_resource_max_limit(rpool);
+
+	INIT_LIST_HEAD(&rpool->cg_node);
+	INIT_LIST_HEAD(&rpool->dev_node);
+	list_add_tail(&rpool->cg_node, &cg->rpools);
+	list_add_tail(&rpool->dev_node, &device->rpools);
+	return rpool;
+}
+
+/**
+ * uncharge_cg_locked - uncharge resource for rdma cgroup
+ * @cg: pointer to cg to uncharge and all parents in hierarchy
+ * @device: pointer to rdmacg device
+ * @index: index of the resource to uncharge in cg (resource pool)
+ *
+ * It also frees the resource pool which was created as part of
+ * charging operation when there are no resources attached to
+ * resource pool.
+ */
+static void
+uncharge_cg_locked(struct rdma_cgroup *cg,
+		   struct rdmacg_device *device,
+		   enum rdmacg_resource_type index)
+{
+	struct rdmacg_resource_pool *rpool;
+
+	rpool = find_cg_rpool_locked(cg, device);
+
+	/*
+	 * rpool cannot be null at this stage. Let kernel operate in case
+	 * if there a bug in IB stack or rdma controller, instead of crashing
+	 * the system.
+	 */
+	if (unlikely(!rpool)) {
+		pr_warn("Invalid device %p or rdma cgroup %p\n", cg, device);
+		return;
+	}
+
+	rpool->resources[index].usage--;
+
+	/*
+	 * A negative count (or overflow) is invalid,
+	 * it indicates a bug in the rdma controller.
+	 */
+	WARN_ON_ONCE(rpool->resources[index].usage < 0);
+	rpool->usage_sum--;
+	if (rpool->usage_sum == 0 &&
+	    rpool->num_max_cnt == RDMACG_RESOURCE_MAX) {
+		/*
+		 * No user of the rpool and all entries are set to max, so
+		 * safe to delete this rpool.
+		 */
+		free_cg_rpool_locked(rpool);
+	}
+}
+
+/**
+ * rdmacg_uncharge_hierarchy - hierarchically uncharge rdma resource count
+ * @device: pointer to rdmacg device
+ * @stop_cg: while traversing hirerchy, when meet with stop_cg cgroup
+ *           stop uncharging
+ * @index: index of the resource to uncharge in cg in given resource pool
+ */
+static void rdmacg_uncharge_hierarchy(struct rdma_cgroup *cg,
+				     struct rdmacg_device *device,
+				     struct rdma_cgroup *stop_cg,
+				     enum rdmacg_resource_type index)
+{
+	struct rdma_cgroup *p;
+
+	mutex_lock(&rdmacg_mutex);
+
+	for (p = cg; p != stop_cg; p = parent_rdmacg(p))
+		uncharge_cg_locked(p, device, index);
+
+	mutex_unlock(&rdmacg_mutex);
+
+	css_put(&cg->css);
+}
+
+/**
+ * rdmacg_uncharge - hierarchically uncharge rdma resource count
+ * @device: pointer to rdmacg device
+ * @index: index of the resource to uncharge in cgroup in given resource pool
+ */
+void rdmacg_uncharge(struct rdma_cgroup *cg,
+		     struct rdmacg_device *device,
+		     enum rdmacg_resource_type index)
+{
+	if (index >= RDMACG_RESOURCE_MAX)
+		return;
+
+	rdmacg_uncharge_hierarchy(cg, device, NULL, index);
+}
+EXPORT_SYMBOL(rdmacg_uncharge);
+
+/**
+ * rdmacg_try_charge - hierarchically try to charge the rdma resource
+ * @rdmacg: pointer to rdma cgroup which will own this resource
+ * @device: pointer to rdmacg device
+ * @index: index of the resource to charge in cgroup (resource pool)
+ *
+ * This function follows charging resource in hierarchical way.
+ * It will fail if the charge would cause the new value to exceed the
+ * hierarchical limit.
+ * Returns 0 if the charge succeded, otherwise -EAGAIN, -ENOMEM or -EINVAL.
+ * Returns pointer to rdmacg for this resource when charging is successful.
+ *
+ * Charger needs to account resources on two criteria.
+ * (a) per cgroup & (b) per device resource usage.
+ * Per cgroup resource usage ensures that tasks of cgroup doesn't cross
+ * the configured limits. Per device provides granular configuration
+ * in multi device usage. It allocates resource pool in the hierarchy
+ * for each parent it come across for first resource. Later on resource
+ * pool will be available. Therefore it will be much faster thereon
+ * to charge/uncharge.
+ */
+int rdmacg_try_charge(struct rdma_cgroup **rdmacg,
+		      struct rdmacg_device *device,
+		      enum rdmacg_resource_type index)
+{
+	struct rdma_cgroup *cg, *p;
+	struct rdmacg_resource_pool *rpool;
+	s64 new;
+	int ret = 0;
+
+	if (index >= RDMACG_RESOURCE_MAX)
+		return -EINVAL;
+
+	/*
+	 * hold on to css, as cgroup can be removed but resource
+	 * accounting happens on css.
+	 */
+	cg = get_current_rdmacg();
+
+	mutex_lock(&rdmacg_mutex);
+	for (p = cg; p; p = parent_rdmacg(p)) {
+		rpool = get_cg_rpool_locked(p, device);
+		if (IS_ERR(rpool)) {
+			ret = PTR_ERR(rpool);
+			goto err;
+		} else {
+			new = rpool->resources[index].usage + 1;
+			if (new > rpool->resources[index].max) {
+				ret = -EAGAIN;
+				goto err;
+			} else {
+				rpool->resources[index].usage = new;
+				rpool->usage_sum++;
+			}
+		}
+	}
+	mutex_unlock(&rdmacg_mutex);
+
+	*rdmacg = cg;
+	return 0;
+
+err:
+	mutex_unlock(&rdmacg_mutex);
+	rdmacg_uncharge_hierarchy(cg, device, p, index);
+	return ret;
+}
+EXPORT_SYMBOL(rdmacg_try_charge);
+
+/**
+ * rdmacg_register_device - register rdmacg device to rdma controller.
+ * @device: pointer to rdmacg device whose resources need to be accounted.
+ *
+ * If IB stack wish a device to participate in rdma cgroup resource
+ * tracking, it must invoke this API to register with rdma cgroup before
+ * any user space application can start using the RDMA resources.
+ * Returns 0 on success or EINVAL when table length given is beyond
+ * supported size.
+ */
+int rdmacg_register_device(struct rdmacg_device *device)
+{
+	INIT_LIST_HEAD(&device->dev_node);
+	INIT_LIST_HEAD(&device->rpools);
+
+	mutex_lock(&rdmacg_mutex);
+	list_add_tail(&device->dev_node, &rdmacg_devices);
+	mutex_unlock(&rdmacg_mutex);
+	return 0;
+}
+EXPORT_SYMBOL(rdmacg_register_device);
+
+/**
+ * rdmacg_unregister_device - unregister rdmacg device from rdma controller.
+ * @device: pointer to rdmacg device which was previously registered with rdma
+ *          controller using rdmacg_register_device().
+ *
+ * IB stack must invoke this after all the resources of the IB device
+ * are destroyed and after ensuring that no more resources will be created
+ * when this API is invoked.
+ */
+void rdmacg_unregister_device(struct rdmacg_device *device)
+{
+	struct rdmacg_resource_pool *rpool, *tmp;
+
+	/*
+	 * Synchronize with any active resource settings,
+	 * usage query happening via configfs.
+	 */
+	mutex_lock(&rdmacg_mutex);
+	list_del_init(&device->dev_node);
+
+	/*
+	 * Now that this device is off the cgroup list, its safe to free
+	 * all the rpool resources.
+	 */
+	list_for_each_entry_safe(rpool, tmp, &device->rpools, dev_node)
+		free_cg_rpool_locked(rpool);
+
+	mutex_unlock(&rdmacg_mutex);
+}
+EXPORT_SYMBOL(rdmacg_unregister_device);
+
+static int parse_resource(char *c, int *intval)
+{
+	substring_t argstr;
+	char *name, *value = c;
+	size_t len;
+	int ret, i;
+
+	name = strsep(&value, "=");
+	if (!name || !value)
+		return -EINVAL;
+
+	i = match_string(rdmacg_resource_names, RDMACG_RESOURCE_MAX, name);
+	if (i < 0)
+		return i;
+
+	len = strlen(value);
+
+	argstr.from = value;
+	argstr.to = value + len;
+
+	ret = match_int(&argstr, intval);
+	if (ret >= 0) {
+		if (*intval < 0)
+			return -EINVAL;
+		return i;
+	}
+	if (strncmp(value, RDMACG_MAX_STR, len) == 0) {
+		*intval = S32_MAX;
+		return i;
+	}
+	return -EINVAL;
+}
+
+static int rdmacg_parse_limits(char *options,
+			       int *new_limits, unsigned long *enables)
+{
+	char *c;
+	int err = -EINVAL;
+
+	/* parse resource options */
+	while ((c = strsep(&options, " ")) != NULL) {
+		int index, intval;
+
+		index = parse_resource(c, &intval);
+		if (index < 0)
+			goto err;
+
+		new_limits[index] = intval;
+		*enables |= BIT(index);
+	}
+	return 0;
+
+err:
+	return err;
+}
+
+static struct rdmacg_device *rdmacg_get_device_locked(const char *name)
+{
+	struct rdmacg_device *device;
+
+	lockdep_assert_held(&rdmacg_mutex);
+
+	list_for_each_entry(device, &rdmacg_devices, dev_node)
+		if (!strcmp(name, device->name))
+			return device;
+
+	return NULL;
+}
+
+static ssize_t rdmacg_resource_set_max(struct kernfs_open_file *of,
+				       char *buf, size_t nbytes, loff_t off)
+{
+	struct rdma_cgroup *cg = css_rdmacg(of_css(of));
+	const char *dev_name;
+	struct rdmacg_resource_pool *rpool;
+	struct rdmacg_device *device;
+	char *options = strstrip(buf);
+	int *new_limits;
+	unsigned long enables = 0;
+	int i = 0, ret = 0;
+
+	/* extract the device name first */
+	dev_name = strsep(&options, " ");
+	if (!dev_name) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	new_limits = kcalloc(RDMACG_RESOURCE_MAX, sizeof(int), GFP_KERNEL);
+	if (!new_limits) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	ret = rdmacg_parse_limits(options, new_limits, &enables);
+	if (ret)
+		goto parse_err;
+
+	/* acquire lock to synchronize with hot plug devices */
+	mutex_lock(&rdmacg_mutex);
+
+	device = rdmacg_get_device_locked(dev_name);
+	if (!device) {
+		ret = -ENODEV;
+		goto dev_err;
+	}
+
+	rpool = get_cg_rpool_locked(cg, device);
+	if (IS_ERR(rpool)) {
+		ret = PTR_ERR(rpool);
+		goto dev_err;
+	}
+
+	/* now set the new limits of the rpool */
+	for_each_set_bit(i, &enables, RDMACG_RESOURCE_MAX)
+		set_resource_limit(rpool, i, new_limits[i]);
+
+	if (rpool->usage_sum == 0 &&
+	    rpool->num_max_cnt == RDMACG_RESOURCE_MAX) {
+		/*
+		 * No user of the rpool and all entries are set to max, so
+		 * safe to delete this rpool.
+		 */
+		free_cg_rpool_locked(rpool);
+	}
+
+dev_err:
+	mutex_unlock(&rdmacg_mutex);
+
+parse_err:
+	kfree(new_limits);
+
+err:
+	return ret ?: nbytes;
+}
+
+static void print_rpool_values(struct seq_file *sf,
+			       struct rdmacg_resource_pool *rpool)
+{
+	enum rdmacg_file_type sf_type;
+	int i;
+	u32 value;
+
+	sf_type = seq_cft(sf)->private;
+
+	for (i = 0; i < RDMACG_RESOURCE_MAX; i++) {
+		seq_puts(sf, rdmacg_resource_names[i]);
+		seq_putc(sf, '=');
+		if (sf_type == RDMACG_RESOURCE_TYPE_MAX) {
+			if (rpool)
+				value = rpool->resources[i].max;
+			else
+				value = S32_MAX;
+		} else {
+			if (rpool)
+				value = rpool->resources[i].usage;
+			else
+				value = 0;
+		}
+
+		if (value == S32_MAX)
+			seq_puts(sf, RDMACG_MAX_STR);
+		else
+			seq_printf(sf, "%d", value);
+		seq_putc(sf, ' ');
+	}
+}
+
+static int rdmacg_resource_read(struct seq_file *sf, void *v)
+{
+	struct rdmacg_device *device;
+	struct rdmacg_resource_pool *rpool;
+	struct rdma_cgroup *cg = css_rdmacg(seq_css(sf));
+
+	mutex_lock(&rdmacg_mutex);
+
+	list_for_each_entry(device, &rdmacg_devices, dev_node) {
+		seq_printf(sf, "%s ", device->name);
+
+		rpool = find_cg_rpool_locked(cg, device);
+		print_rpool_values(sf, rpool);
+
+		seq_putc(sf, '\n');
+	}
+
+	mutex_unlock(&rdmacg_mutex);
+	return 0;
+}
+
+static struct cftype rdmacg_files[] = {
+	{
+		.name = "max",
+		.write = rdmacg_resource_set_max,
+		.seq_show = rdmacg_resource_read,
+		.private = RDMACG_RESOURCE_TYPE_MAX,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "current",
+		.seq_show = rdmacg_resource_read,
+		.private = RDMACG_RESOURCE_TYPE_STAT,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{ }	/* terminate */
+};
+
+static struct cgroup_subsys_state *
+rdmacg_css_alloc(struct cgroup_subsys_state *parent)
+{
+	struct rdma_cgroup *cg;
+
+	cg = kzalloc(sizeof(*cg), GFP_KERNEL);
+	if (!cg)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&cg->rpools);
+	return &cg->css;
+}
+
+static void rdmacg_css_free(struct cgroup_subsys_state *css)
+{
+	struct rdma_cgroup *cg = css_rdmacg(css);
+
+	kfree(cg);
+}
+
+/**
+ * rdmacg_css_offline - cgroup css_offline callback
+ * @css: css of interest
+ *
+ * This function is called when @css is about to go away and responsible
+ * for shooting down all rdmacg associated with @css. As part of that it
+ * marks all the resource pool entries to max value, so that when resources are
+ * uncharged, associated resource pool can be freed as well.
+ */
+static void rdmacg_css_offline(struct cgroup_subsys_state *css)
+{
+	struct rdma_cgroup *cg = css_rdmacg(css);
+	struct rdmacg_resource_pool *rpool;
+
+	mutex_lock(&rdmacg_mutex);
+
+	list_for_each_entry(rpool, &cg->rpools, cg_node)
+		set_all_resource_max_limit(rpool);
+
+	mutex_unlock(&rdmacg_mutex);
+}
+
+struct cgroup_subsys rdma_cgrp_subsys = {
+	.css_alloc	= rdmacg_css_alloc,
+	.css_free	= rdmacg_css_free,
+	.css_offline	= rdmacg_css_offline,
+	.legacy_cftypes	= rdmacg_files,
+	.dfl_cftypes	= rdmacg_files,
+};

kernel/cgroup/rstat.c

@@ -0,0 +1,408 @@
+#include "cgroup-internal.h"
+
+#include <linux/sched/cputime.h>
+
+static DEFINE_SPINLOCK(cgroup_rstat_lock);
+static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock);
+
+static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu);
+
+static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu)
+{
+	return per_cpu_ptr(cgrp->rstat_cpu, cpu);
+}
+
+/**
+ * cgroup_rstat_updated - keep track of updated rstat_cpu
+ * @cgrp: target cgroup
+ * @cpu: cpu on which rstat_cpu was updated
+ *
+ * @cgrp's rstat_cpu on @cpu was updated.  Put it on the parent's matching
+ * rstat_cpu->updated_children list.  See the comment on top of
+ * cgroup_rstat_cpu definition for details.
+ */
+void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
+{
+	raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
+	struct cgroup *parent;
+	unsigned long flags;
+
+	/* nothing to do for root */
+	if (!cgroup_parent(cgrp))
+		return;
+
+	/*
+	 * Speculative already-on-list test. This may race leading to
+	 * temporary inaccuracies, which is fine.
+	 *
+	 * Because @parent's updated_children is terminated with @parent
+	 * instead of NULL, we can tell whether @cgrp is on the list by
+	 * testing the next pointer for NULL.
+	 */
+	if (cgroup_rstat_cpu(cgrp, cpu)->updated_next)
+		return;
+
+	raw_spin_lock_irqsave(cpu_lock, flags);
+
+	/* put @cgrp and all ancestors on the corresponding updated lists */
+	for (parent = cgroup_parent(cgrp); parent;
+	     cgrp = parent, parent = cgroup_parent(cgrp)) {
+		struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
+		struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu);
+
+		/*
+		 * Both additions and removals are bottom-up.  If a cgroup
+		 * is already in the tree, all ancestors are.
+		 */
+		if (rstatc->updated_next)
+			break;
+
+		rstatc->updated_next = prstatc->updated_children;
+		prstatc->updated_children = cgrp;
+	}
+
+	raw_spin_unlock_irqrestore(cpu_lock, flags);
+}
+EXPORT_SYMBOL_GPL(cgroup_rstat_updated);
+
+/**
+ * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree
+ * @pos: current position
+ * @root: root of the tree to traversal
+ * @cpu: target cpu
+ *
+ * Walks the udpated rstat_cpu tree on @cpu from @root.  %NULL @pos starts
+ * the traversal and %NULL return indicates the end.  During traversal,
+ * each returned cgroup is unlinked from the tree.  Must be called with the
+ * matching cgroup_rstat_cpu_lock held.
+ *
+ * The only ordering guarantee is that, for a parent and a child pair
+ * covered by a given traversal, if a child is visited, its parent is
+ * guaranteed to be visited afterwards.
+ */
+static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
+						   struct cgroup *root, int cpu)
+{
+	struct cgroup_rstat_cpu *rstatc;
+
+	if (pos == root)
+		return NULL;
+
+	/*
+	 * We're gonna walk down to the first leaf and visit/remove it.  We
+	 * can pick whatever unvisited node as the starting point.
+	 */
+	if (!pos)
+		pos = root;
+	else
+		pos = cgroup_parent(pos);
+
+	/* walk down to the first leaf */
+	while (true) {
+		rstatc = cgroup_rstat_cpu(pos, cpu);
+		if (rstatc->updated_children == pos)
+			break;
+		pos = rstatc->updated_children;
+	}
+
+	/*
+	 * Unlink @pos from the tree.  As the updated_children list is
+	 * singly linked, we have to walk it to find the removal point.
+	 * However, due to the way we traverse, @pos will be the first
+	 * child in most cases. The only exception is @root.
+	 */
+	if (rstatc->updated_next) {
+		struct cgroup *parent = cgroup_parent(pos);
+		struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu);
+		struct cgroup_rstat_cpu *nrstatc;
+		struct cgroup **nextp;
+
+		nextp = &prstatc->updated_children;
+		while (true) {
+			nrstatc = cgroup_rstat_cpu(*nextp, cpu);
+			if (*nextp == pos)
+				break;
+
+			WARN_ON_ONCE(*nextp == parent);
+			nextp = &nrstatc->updated_next;
+		}
+
+		*nextp = rstatc->updated_next;
+		rstatc->updated_next = NULL;
+
+		return pos;
+	}
+
+	/* only happens for @root */
+	return NULL;
+}
+
+/* see cgroup_rstat_flush() */
+static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep)
+	__releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock)
+{
+	int cpu;
+
+	lockdep_assert_held(&cgroup_rstat_lock);
+
+	for_each_possible_cpu(cpu) {
+		raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock,
+						       cpu);
+		struct cgroup *pos = NULL;
+
+		raw_spin_lock(cpu_lock);
+		while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) {
+			struct cgroup_subsys_state *css;
+
+			cgroup_base_stat_flush(pos, cpu);
+
+			rcu_read_lock();
+			list_for_each_entry_rcu(css, &pos->rstat_css_list,
+						rstat_css_node)
+				css->ss->css_rstat_flush(css, cpu);
+			rcu_read_unlock();
+		}
+		raw_spin_unlock(cpu_lock);
+
+		/* if @may_sleep, play nice and yield if necessary */
+		if (may_sleep && (need_resched() ||
+				  spin_needbreak(&cgroup_rstat_lock))) {
+			spin_unlock_irq(&cgroup_rstat_lock);
+			if (!cond_resched())
+				cpu_relax();
+			spin_lock_irq(&cgroup_rstat_lock);
+		}
+	}
+}
+
+/**
+ * cgroup_rstat_flush - flush stats in @cgrp's subtree
+ * @cgrp: target cgroup
+ *
+ * Collect all per-cpu stats in @cgrp's subtree into the global counters
+ * and propagate them upwards.  After this function returns, all cgroups in
+ * the subtree have up-to-date ->stat.
+ *
+ * This also gets all cgroups in the subtree including @cgrp off the
+ * ->updated_children lists.
+ *
+ * This function may block.
+ */
+void cgroup_rstat_flush(struct cgroup *cgrp)
+{
+	might_sleep();
+
+	spin_lock_irq(&cgroup_rstat_lock);
+	cgroup_rstat_flush_locked(cgrp, true);
+	spin_unlock_irq(&cgroup_rstat_lock);
+}
+
+/**
+ * cgroup_rstat_flush_irqsafe - irqsafe version of cgroup_rstat_flush()
+ * @cgrp: target cgroup
+ *
+ * This function can be called from any context.
+ */
+void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cgroup_rstat_lock, flags);
+	cgroup_rstat_flush_locked(cgrp, false);
+	spin_unlock_irqrestore(&cgroup_rstat_lock, flags);
+}
+
+/**
+ * cgroup_rstat_flush_begin - flush stats in @cgrp's subtree and hold
+ * @cgrp: target cgroup
+ *
+ * Flush stats in @cgrp's subtree and prevent further flushes.  Must be
+ * paired with cgroup_rstat_flush_release().
+ *
+ * This function may block.
+ */
+void cgroup_rstat_flush_hold(struct cgroup *cgrp)
+	__acquires(&cgroup_rstat_lock)
+{
+	might_sleep();
+	spin_lock_irq(&cgroup_rstat_lock);
+	cgroup_rstat_flush_locked(cgrp, true);
+}
+
+/**
+ * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold()
+ */
+void cgroup_rstat_flush_release(void)
+	__releases(&cgroup_rstat_lock)
+{
+	spin_unlock_irq(&cgroup_rstat_lock);
+}
+
+int cgroup_rstat_init(struct cgroup *cgrp)
+{
+	int cpu;
+
+	/* the root cgrp has rstat_cpu preallocated */
+	if (!cgrp->rstat_cpu) {
+		cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu);
+		if (!cgrp->rstat_cpu)
+			return -ENOMEM;
+	}
+
+	/* ->updated_children list is self terminated */
+	for_each_possible_cpu(cpu) {
+		struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
+
+		rstatc->updated_children = cgrp;
+		u64_stats_init(&rstatc->bsync);
+	}
+
+	return 0;
+}
+
+void cgroup_rstat_exit(struct cgroup *cgrp)
+{
+	int cpu;
+
+	cgroup_rstat_flush(cgrp);
+
+	/* sanity check */
+	for_each_possible_cpu(cpu) {
+		struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
+
+		if (WARN_ON_ONCE(rstatc->updated_children != cgrp) ||
+		    WARN_ON_ONCE(rstatc->updated_next))
+			return;
+	}
+
+	free_percpu(cgrp->rstat_cpu);
+	cgrp->rstat_cpu = NULL;
+}
+
+void __init cgroup_rstat_boot(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu));
+
+	BUG_ON(cgroup_rstat_init(&cgrp_dfl_root.cgrp));
+}
+
+/*
+ * Functions for cgroup basic resource statistics implemented on top of
+ * rstat.
+ */
+static void cgroup_base_stat_accumulate(struct cgroup_base_stat *dst_bstat,
+					struct cgroup_base_stat *src_bstat)
+{
+	dst_bstat->cputime.utime += src_bstat->cputime.utime;
+	dst_bstat->cputime.stime += src_bstat->cputime.stime;
+	dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime;
+}
+
+static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
+{
+	struct cgroup *parent = cgroup_parent(cgrp);
+	struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
+	struct task_cputime *last_cputime = &rstatc->last_bstat.cputime;
+	struct task_cputime cputime;
+	struct cgroup_base_stat delta;
+	unsigned seq;
+
+	/* fetch the current per-cpu values */
+	do {
+		seq = __u64_stats_fetch_begin(&rstatc->bsync);
+		cputime = rstatc->bstat.cputime;
+	} while (__u64_stats_fetch_retry(&rstatc->bsync, seq));
+
+	/* calculate the delta to propgate */
+	delta.cputime.utime = cputime.utime - last_cputime->utime;
+	delta.cputime.stime = cputime.stime - last_cputime->stime;
+	delta.cputime.sum_exec_runtime = cputime.sum_exec_runtime -
+					 last_cputime->sum_exec_runtime;
+	*last_cputime = cputime;
+
+	/* transfer the pending stat into delta */
+	cgroup_base_stat_accumulate(&delta, &cgrp->pending_bstat);
+	memset(&cgrp->pending_bstat, 0, sizeof(cgrp->pending_bstat));
+
+	/* propagate delta into the global stat and the parent's pending */
+	cgroup_base_stat_accumulate(&cgrp->bstat, &delta);
+	if (parent)
+		cgroup_base_stat_accumulate(&parent->pending_bstat, &delta);
+}
+
+static struct cgroup_rstat_cpu *
+cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp)
+{
+	struct cgroup_rstat_cpu *rstatc;
+
+	rstatc = get_cpu_ptr(cgrp->rstat_cpu);
+	u64_stats_update_begin(&rstatc->bsync);
+	return rstatc;
+}
+
+static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp,
+						 struct cgroup_rstat_cpu *rstatc)
+{
+	u64_stats_update_end(&rstatc->bsync);
+	cgroup_rstat_updated(cgrp, smp_processor_id());
+	put_cpu_ptr(rstatc);
+}
+
+void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec)
+{
+	struct cgroup_rstat_cpu *rstatc;
+
+	rstatc = cgroup_base_stat_cputime_account_begin(cgrp);
+	rstatc->bstat.cputime.sum_exec_runtime += delta_exec;
+	cgroup_base_stat_cputime_account_end(cgrp, rstatc);
+}
+
+void __cgroup_account_cputime_field(struct cgroup *cgrp,
+				    enum cpu_usage_stat index, u64 delta_exec)
+{
+	struct cgroup_rstat_cpu *rstatc;
+
+	rstatc = cgroup_base_stat_cputime_account_begin(cgrp);
+
+	switch (index) {
+	case CPUTIME_USER:
+	case CPUTIME_NICE:
+		rstatc->bstat.cputime.utime += delta_exec;
+		break;
+	case CPUTIME_SYSTEM:
+	case CPUTIME_IRQ:
+	case CPUTIME_SOFTIRQ:
+		rstatc->bstat.cputime.stime += delta_exec;
+		break;
+	default:
+		break;
+	}
+
+	cgroup_base_stat_cputime_account_end(cgrp, rstatc);
+}
+
+void cgroup_base_stat_cputime_show(struct seq_file *seq)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	u64 usage, utime, stime;
+
+	if (!cgroup_parent(cgrp))
+		return;
+
+	cgroup_rstat_flush_hold(cgrp);
+	usage = cgrp->bstat.cputime.sum_exec_runtime;
+	cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime);
+	cgroup_rstat_flush_release();
+
+	do_div(usage, NSEC_PER_USEC);
+	do_div(utime, NSEC_PER_USEC);
+	do_div(stime, NSEC_PER_USEC);
+
+	seq_printf(seq, "usage_usec %llu\n"
+		   "user_usec %llu\n"
+		   "system_usec %llu\n",
+		   usage, utime, stime);
+}