summaryrefslogtreecommitdiffstats
path: root/kernel/cgroup/cgroup-internal.h
blob: 793565c057426656312ab7b31471f6c523b7ae59 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
#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>

/*
 * 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 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);

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 ref_flags);
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);

bool cgroup_may_migrate_to(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);
ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
			     size_t nbytes, loff_t off, bool threadgroup);
ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes,
			   loff_t off);

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);

/*
 * namespace.c
 */
extern const struct proc_ns_operations cgroupns_operations;

/*
 * cgroup-v1.c
 */
extern struct cftype cgroup1_base_files[];
extern const struct file_operations proc_cgroupstats_operations;
extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops;

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 */