summaryrefslogtreecommitdiff
path: root/kernel/sched/autogroup.c
blob: da39489d2d80e9b8f6781610e97c23ec0014f45b (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
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
#include "sched.h"

#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/kallsyms.h>
#include <linux/utsname.h>
#include <linux/security.h>
#include <linux/export.h>

unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
static struct autogroup autogroup_default;
static atomic_t autogroup_seq_nr;

void __init autogroup_init(struct task_struct *init_task)
{
	autogroup_default.tg = &root_task_group;
	kref_init(&autogroup_default.kref);
	init_rwsem(&autogroup_default.lock);
	init_task->signal->autogroup = &autogroup_default;
}

void autogroup_free(struct task_group *tg)
{
	kfree(tg->autogroup);
}

static inline void autogroup_destroy(struct kref *kref)
{
	struct autogroup *ag = container_of(kref, struct autogroup, kref);

#ifdef CONFIG_RT_GROUP_SCHED
	/* We've redirected RT tasks to the root task group... */
	ag->tg->rt_se = NULL;
	ag->tg->rt_rq = NULL;
#endif
	sched_offline_group(ag->tg);
	sched_destroy_group(ag->tg);
}

static inline void autogroup_kref_put(struct autogroup *ag)
{
	kref_put(&ag->kref, autogroup_destroy);
}

static inline struct autogroup *autogroup_kref_get(struct autogroup *ag)
{
	kref_get(&ag->kref);
	return ag;
}

static inline struct autogroup *autogroup_task_get(struct task_struct *p)
{
	struct autogroup *ag;
	unsigned long flags;

	if (!lock_task_sighand(p, &flags))
		return autogroup_kref_get(&autogroup_default);

	ag = autogroup_kref_get(p->signal->autogroup);
	unlock_task_sighand(p, &flags);

	return ag;
}

static inline struct autogroup *autogroup_create(void)
{
	struct autogroup *ag = kzalloc(sizeof(*ag), GFP_KERNEL);
	struct task_group *tg;

	if (!ag)
		goto out_fail;

	tg = sched_create_group(&root_task_group);

	if (IS_ERR(tg))
		goto out_free;

	kref_init(&ag->kref);
	init_rwsem(&ag->lock);
	ag->id = atomic_inc_return(&autogroup_seq_nr);
	ag->tg = tg;
#ifdef CONFIG_RT_GROUP_SCHED
	/*
	 * Autogroup RT tasks are redirected to the root task group
	 * so we don't have to move tasks around upon policy change,
	 * or flail around trying to allocate bandwidth on the fly.
	 * A bandwidth exception in __sched_setscheduler() allows
	 * the policy change to proceed.
	 */
	free_rt_sched_group(tg);
	tg->rt_se = root_task_group.rt_se;
	tg->rt_rq = root_task_group.rt_rq;
#endif
	tg->autogroup = ag;

	sched_online_group(tg, &root_task_group);
	return ag;

out_free:
	kfree(ag);
out_fail:
	if (printk_ratelimit()) {
		printk(KERN_WARNING "autogroup_create: %s failure.\n",
			ag ? "sched_create_group()" : "kmalloc()");
	}

	return autogroup_kref_get(&autogroup_default);
}

bool task_wants_autogroup(struct task_struct *p, struct task_group *tg)
{
	if (tg != &root_task_group)
		return false;
	/*
	 * If we race with autogroup_move_group() the caller can use the old
	 * value of signal->autogroup but in this case sched_move_task() will
	 * be called again before autogroup_kref_put().
	 *
	 * However, there is no way sched_autogroup_exit_task() could tell us
	 * to avoid autogroup->tg, so we abuse PF_EXITING flag for this case.
	 */
	if (p->flags & PF_EXITING)
		return false;

	return true;
}

void sched_autogroup_exit_task(struct task_struct *p)
{
	/*
	 * We are going to call exit_notify() and autogroup_move_group() can't
	 * see this thread after that: we can no longer use signal->autogroup.
	 * See the PF_EXITING check in task_wants_autogroup().
	 */
	sched_move_task(p);
}

static void
autogroup_move_group(struct task_struct *p, struct autogroup *ag)
{
	struct autogroup *prev;
	struct task_struct *t;
	unsigned long flags;

	BUG_ON(!lock_task_sighand(p, &flags));

	prev = p->signal->autogroup;
	if (prev == ag) {
		unlock_task_sighand(p, &flags);
		return;
	}

	p->signal->autogroup = autogroup_kref_get(ag);
	/*
	 * We can't avoid sched_move_task() after we changed signal->autogroup,
	 * this process can already run with task_group() == prev->tg or we can
	 * race with cgroup code which can read autogroup = prev under rq->lock.
	 * In the latter case for_each_thread() can not miss a migrating thread,
	 * cpu_cgroup_attach() must not be possible after cgroup_exit() and it
	 * can't be removed from thread list, we hold ->siglock.
	 *
	 * If an exiting thread was already removed from thread list we rely on
	 * sched_autogroup_exit_task().
	 */
	for_each_thread(p, t)
		sched_move_task(t);

	unlock_task_sighand(p, &flags);
	autogroup_kref_put(prev);
}

/* Allocates GFP_KERNEL, cannot be called under any spinlock */
void sched_autogroup_create_attach(struct task_struct *p)
{
	struct autogroup *ag = autogroup_create();

	autogroup_move_group(p, ag);
	/* drop extra reference added by autogroup_create() */
	autogroup_kref_put(ag);
}
EXPORT_SYMBOL(sched_autogroup_create_attach);

/* Cannot be called under siglock.  Currently has no users */
void sched_autogroup_detach(struct task_struct *p)
{
	autogroup_move_group(p, &autogroup_default);
}
EXPORT_SYMBOL(sched_autogroup_detach);

void sched_autogroup_fork(struct signal_struct *sig)
{
	sig->autogroup = autogroup_task_get(current);
}

void sched_autogroup_exit(struct signal_struct *sig)
{
	autogroup_kref_put(sig->autogroup);
}

static int __init setup_autogroup(char *str)
{
	sysctl_sched_autogroup_enabled = 0;

	return 1;
}

__setup("noautogroup", setup_autogroup);

#ifdef CONFIG_PROC_FS

int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
{
	static unsigned long next = INITIAL_JIFFIES;
	struct autogroup *ag;
	unsigned long shares;
	int err;

	if (nice < MIN_NICE || nice > MAX_NICE)
		return -EINVAL;

	err = security_task_setnice(current, nice);
	if (err)
		return err;

	if (nice < 0 && !can_nice(current, nice))
		return -EPERM;

	/* this is a heavy operation taking global locks.. */
	if (!capable(CAP_SYS_ADMIN) && time_before(jiffies, next))
		return -EAGAIN;

	next = HZ / 10 + jiffies;
	ag = autogroup_task_get(p);
	shares = scale_load(sched_prio_to_weight[nice + 20]);

	down_write(&ag->lock);
	err = sched_group_set_shares(ag->tg, shares);
	if (!err)
		ag->nice = nice;
	up_write(&ag->lock);

	autogroup_kref_put(ag);

	return err;
}

void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
{
	struct autogroup *ag = autogroup_task_get(p);

	if (!task_group_is_autogroup(ag->tg))
		goto out;

	down_read(&ag->lock);
	seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice);
	up_read(&ag->lock);

out:
	autogroup_kref_put(ag);
}
#endif /* CONFIG_PROC_FS */

#ifdef CONFIG_SCHED_DEBUG
int autogroup_path(struct task_group *tg, char *buf, int buflen)
{
	if (!task_group_is_autogroup(tg))
		return 0;

	return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id);
}
#endif /* CONFIG_SCHED_DEBUG */