summaryrefslogtreecommitdiffstats
path: root/kernel/bpf/cgroup_iter.c
blob: d57ccb02477f8576b94751631a8ed54e3a1e97dd (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
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2022 Google */
#include <linux/bpf.h>
#include <linux/btf_ids.h>
#include <linux/cgroup.h>
#include <linux/kernel.h>
#include <linux/seq_file.h>

#include "../cgroup/cgroup-internal.h"  /* cgroup_mutex and cgroup_is_dead */

/* cgroup_iter provides four modes of traversal to the cgroup hierarchy.
 *
 *  1. Walk the descendants of a cgroup in pre-order.
 *  2. Walk the descendants of a cgroup in post-order.
 *  3. Walk the ancestors of a cgroup.
 *  4. Show the given cgroup only.
 *
 * For walking descendants, cgroup_iter can walk in either pre-order or
 * post-order. For walking ancestors, the iter walks up from a cgroup to
 * the root.
 *
 * The iter program can terminate the walk early by returning 1. Walk
 * continues if prog returns 0.
 *
 * The prog can check (seq->num == 0) to determine whether this is
 * the first element. The prog may also be passed a NULL cgroup,
 * which means the walk has completed and the prog has a chance to
 * do post-processing, such as outputting an epilogue.
 *
 * Note: the iter_prog is called with cgroup_mutex held.
 *
 * Currently only one session is supported, which means, depending on the
 * volume of data bpf program intends to send to user space, the number
 * of cgroups that can be walked is limited. For example, given the current
 * buffer size is 8 * PAGE_SIZE, if the program sends 64B data for each
 * cgroup, assuming PAGE_SIZE is 4kb, the total number of cgroups that can
 * be walked is 512. This is a limitation of cgroup_iter. If the output data
 * is larger than the kernel buffer size, after all data in the kernel buffer
 * is consumed by user space, the subsequent read() syscall will signal
 * EOPNOTSUPP. In order to work around, the user may have to update their
 * program to reduce the volume of data sent to output. For example, skip
 * some uninteresting cgroups.
 */

struct bpf_iter__cgroup {
	__bpf_md_ptr(struct bpf_iter_meta *, meta);
	__bpf_md_ptr(struct cgroup *, cgroup);
};

struct cgroup_iter_priv {
	struct cgroup_subsys_state *start_css;
	bool visited_all;
	bool terminate;
	int order;
};

static void *cgroup_iter_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct cgroup_iter_priv *p = seq->private;

	cgroup_lock();

	/* cgroup_iter doesn't support read across multiple sessions. */
	if (*pos > 0) {
		if (p->visited_all)
			return NULL;

		/* Haven't visited all, but because cgroup_mutex has dropped,
		 * return -EOPNOTSUPP to indicate incomplete iteration.
		 */
		return ERR_PTR(-EOPNOTSUPP);
	}

	++*pos;
	p->terminate = false;
	p->visited_all = false;
	if (p->order == BPF_CGROUP_ITER_DESCENDANTS_PRE)
		return css_next_descendant_pre(NULL, p->start_css);
	else if (p->order == BPF_CGROUP_ITER_DESCENDANTS_POST)
		return css_next_descendant_post(NULL, p->start_css);
	else /* BPF_CGROUP_ITER_SELF_ONLY and BPF_CGROUP_ITER_ANCESTORS_UP */
		return p->start_css;
}

static int __cgroup_iter_seq_show(struct seq_file *seq,
				  struct cgroup_subsys_state *css, int in_stop);

static void cgroup_iter_seq_stop(struct seq_file *seq, void *v)
{
	struct cgroup_iter_priv *p = seq->private;

	cgroup_unlock();

	/* pass NULL to the prog for post-processing */
	if (!v) {
		__cgroup_iter_seq_show(seq, NULL, true);
		p->visited_all = true;
	}
}

static void *cgroup_iter_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct cgroup_subsys_state *curr = (struct cgroup_subsys_state *)v;
	struct cgroup_iter_priv *p = seq->private;

	++*pos;
	if (p->terminate)
		return NULL;

	if (p->order == BPF_CGROUP_ITER_DESCENDANTS_PRE)
		return css_next_descendant_pre(curr, p->start_css);
	else if (p->order == BPF_CGROUP_ITER_DESCENDANTS_POST)
		return css_next_descendant_post(curr, p->start_css);
	else if (p->order == BPF_CGROUP_ITER_ANCESTORS_UP)
		return curr->parent;
	else  /* BPF_CGROUP_ITER_SELF_ONLY */
		return NULL;
}

static int __cgroup_iter_seq_show(struct seq_file *seq,
				  struct cgroup_subsys_state *css, int in_stop)
{
	struct cgroup_iter_priv *p = seq->private;
	struct bpf_iter__cgroup ctx;
	struct bpf_iter_meta meta;
	struct bpf_prog *prog;
	int ret = 0;

	/* cgroup is dead, skip this element */
	if (css && cgroup_is_dead(css->cgroup))
		return 0;

	ctx.meta = &meta;
	ctx.cgroup = css ? css->cgroup : NULL;
	meta.seq = seq;
	prog = bpf_iter_get_info(&meta, in_stop);
	if (prog)
		ret = bpf_iter_run_prog(prog, &ctx);

	/* if prog returns > 0, terminate after this element. */
	if (ret != 0)
		p->terminate = true;

	return 0;
}

static int cgroup_iter_seq_show(struct seq_file *seq, void *v)
{
	return __cgroup_iter_seq_show(seq, (struct cgroup_subsys_state *)v,
				      false);
}

static const struct seq_operations cgroup_iter_seq_ops = {
	.start  = cgroup_iter_seq_start,
	.next   = cgroup_iter_seq_next,
	.stop   = cgroup_iter_seq_stop,
	.show   = cgroup_iter_seq_show,
};

BTF_ID_LIST_SINGLE(bpf_cgroup_btf_id, struct, cgroup)

static int cgroup_iter_seq_init(void *priv, struct bpf_iter_aux_info *aux)
{
	struct cgroup_iter_priv *p = (struct cgroup_iter_priv *)priv;
	struct cgroup *cgrp = aux->cgroup.start;

	/* bpf_iter_attach_cgroup() has already acquired an extra reference
	 * for the start cgroup, but the reference may be released after
	 * cgroup_iter_seq_init(), so acquire another reference for the
	 * start cgroup.
	 */
	p->start_css = &cgrp->self;
	css_get(p->start_css);
	p->terminate = false;
	p->visited_all = false;
	p->order = aux->cgroup.order;
	return 0;
}

static void cgroup_iter_seq_fini(void *priv)
{
	struct cgroup_iter_priv *p = (struct cgroup_iter_priv *)priv;

	css_put(p->start_css);
}

static const struct bpf_iter_seq_info cgroup_iter_seq_info = {
	.seq_ops		= &cgroup_iter_seq_ops,
	.init_seq_private	= cgroup_iter_seq_init,
	.fini_seq_private	= cgroup_iter_seq_fini,
	.seq_priv_size		= sizeof(struct cgroup_iter_priv),
};

static int bpf_iter_attach_cgroup(struct bpf_prog *prog,
				  union bpf_iter_link_info *linfo,
				  struct bpf_iter_aux_info *aux)
{
	int fd = linfo->cgroup.cgroup_fd;
	u64 id = linfo->cgroup.cgroup_id;
	int order = linfo->cgroup.order;
	struct cgroup *cgrp;

	if (order != BPF_CGROUP_ITER_DESCENDANTS_PRE &&
	    order != BPF_CGROUP_ITER_DESCENDANTS_POST &&
	    order != BPF_CGROUP_ITER_ANCESTORS_UP &&
	    order != BPF_CGROUP_ITER_SELF_ONLY)
		return -EINVAL;

	if (fd && id)
		return -EINVAL;

	if (fd)
		cgrp = cgroup_v1v2_get_from_fd(fd);
	else if (id)
		cgrp = cgroup_get_from_id(id);
	else /* walk the entire hierarchy by default. */
		cgrp = cgroup_get_from_path("/");

	if (IS_ERR(cgrp))
		return PTR_ERR(cgrp);

	aux->cgroup.start = cgrp;
	aux->cgroup.order = order;
	return 0;
}

static void bpf_iter_detach_cgroup(struct bpf_iter_aux_info *aux)
{
	cgroup_put(aux->cgroup.start);
}

static void bpf_iter_cgroup_show_fdinfo(const struct bpf_iter_aux_info *aux,
					struct seq_file *seq)
{
	char *buf;

	buf = kzalloc(PATH_MAX, GFP_KERNEL);
	if (!buf) {
		seq_puts(seq, "cgroup_path:\t<unknown>\n");
		goto show_order;
	}

	/* If cgroup_path_ns() fails, buf will be an empty string, cgroup_path
	 * will print nothing.
	 *
	 * Path is in the calling process's cgroup namespace.
	 */
	cgroup_path_ns(aux->cgroup.start, buf, PATH_MAX,
		       current->nsproxy->cgroup_ns);
	seq_printf(seq, "cgroup_path:\t%s\n", buf);
	kfree(buf);

show_order:
	if (aux->cgroup.order == BPF_CGROUP_ITER_DESCENDANTS_PRE)
		seq_puts(seq, "order: descendants_pre\n");
	else if (aux->cgroup.order == BPF_CGROUP_ITER_DESCENDANTS_POST)
		seq_puts(seq, "order: descendants_post\n");
	else if (aux->cgroup.order == BPF_CGROUP_ITER_ANCESTORS_UP)
		seq_puts(seq, "order: ancestors_up\n");
	else /* BPF_CGROUP_ITER_SELF_ONLY */
		seq_puts(seq, "order: self_only\n");
}

static int bpf_iter_cgroup_fill_link_info(const struct bpf_iter_aux_info *aux,
					  struct bpf_link_info *info)
{
	info->iter.cgroup.order = aux->cgroup.order;
	info->iter.cgroup.cgroup_id = cgroup_id(aux->cgroup.start);
	return 0;
}

DEFINE_BPF_ITER_FUNC(cgroup, struct bpf_iter_meta *meta,
		     struct cgroup *cgroup)

static struct bpf_iter_reg bpf_cgroup_reg_info = {
	.target			= "cgroup",
	.feature		= BPF_ITER_RESCHED,
	.attach_target		= bpf_iter_attach_cgroup,
	.detach_target		= bpf_iter_detach_cgroup,
	.show_fdinfo		= bpf_iter_cgroup_show_fdinfo,
	.fill_link_info		= bpf_iter_cgroup_fill_link_info,
	.ctx_arg_info_size	= 1,
	.ctx_arg_info		= {
		{ offsetof(struct bpf_iter__cgroup, cgroup),
		  PTR_TO_BTF_ID_OR_NULL },
	},
	.seq_info		= &cgroup_iter_seq_info,
};

static int __init bpf_cgroup_iter_init(void)
{
	bpf_cgroup_reg_info.ctx_arg_info[0].btf_id = bpf_cgroup_btf_id[0];
	return bpf_iter_reg_target(&bpf_cgroup_reg_info);
}

late_initcall(bpf_cgroup_iter_init);