summaryrefslogtreecommitdiff
path: root/net/core/flow.c
blob: f7f5d1932a2720767dd31f4033f196815ff08447 (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
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
/* flow.c: Generic flow cache.
 *
 * Copyright (C) 2003 Alexey N. Kuznetsov (kuznet@ms2.inr.ac.ru)
 * Copyright (C) 2003 David S. Miller (davem@redhat.com)
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/list.h>
#include <linux/jhash.h>
#include <linux/interrupt.h>
#include <linux/mm.h>
#include <linux/random.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/completion.h>
#include <linux/percpu.h>
#include <linux/bitops.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/mutex.h>
#include <net/flow.h>
#include <linux/atomic.h>
#include <linux/security.h>
#include <net/net_namespace.h>

struct flow_cache_entry {
	union {
		struct hlist_node	hlist;
		struct list_head	gc_list;
	} u;
	struct net			*net;
	u16				family;
	u8				dir;
	u32				genid;
	struct flowi			key;
	struct flow_cache_object	*object;
};

struct flow_flush_info {
	struct flow_cache		*cache;
	atomic_t			cpuleft;
	struct completion		completion;
};

static struct kmem_cache *flow_cachep __read_mostly;

#define flow_cache_hash_size(cache)	(1U << (cache)->hash_shift)
#define FLOW_HASH_RND_PERIOD		(10 * 60 * HZ)

static void flow_cache_new_hashrnd(unsigned long arg)
{
	struct flow_cache *fc = (void *) arg;
	int i;

	for_each_possible_cpu(i)
		per_cpu_ptr(fc->percpu, i)->hash_rnd_recalc = 1;

	fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD;
	add_timer(&fc->rnd_timer);
}

static int flow_entry_valid(struct flow_cache_entry *fle,
				struct netns_xfrm *xfrm)
{
	if (atomic_read(&xfrm->flow_cache_genid) != fle->genid)
		return 0;
	if (fle->object && !fle->object->ops->check(fle->object))
		return 0;
	return 1;
}

static void flow_entry_kill(struct flow_cache_entry *fle,
				struct netns_xfrm *xfrm)
{
	if (fle->object)
		fle->object->ops->delete(fle->object);
	kmem_cache_free(flow_cachep, fle);
}

static void flow_cache_gc_task(struct work_struct *work)
{
	struct list_head gc_list;
	struct flow_cache_entry *fce, *n;
	struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
						flow_cache_gc_work);

	INIT_LIST_HEAD(&gc_list);
	spin_lock_bh(&xfrm->flow_cache_gc_lock);
	list_splice_tail_init(&xfrm->flow_cache_gc_list, &gc_list);
	spin_unlock_bh(&xfrm->flow_cache_gc_lock);

	list_for_each_entry_safe(fce, n, &gc_list, u.gc_list) {
		flow_entry_kill(fce, xfrm);
		atomic_dec(&xfrm->flow_cache_gc_count);
	}
}

static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
				     unsigned int deleted,
				     struct list_head *gc_list,
				     struct netns_xfrm *xfrm)
{
	if (deleted) {
		atomic_add(deleted, &xfrm->flow_cache_gc_count);
		fcp->hash_count -= deleted;
		spin_lock_bh(&xfrm->flow_cache_gc_lock);
		list_splice_tail(gc_list, &xfrm->flow_cache_gc_list);
		spin_unlock_bh(&xfrm->flow_cache_gc_lock);
		schedule_work(&xfrm->flow_cache_gc_work);
	}
}

static void __flow_cache_shrink(struct flow_cache *fc,
				struct flow_cache_percpu *fcp,
				unsigned int shrink_to)
{
	struct flow_cache_entry *fle;
	struct hlist_node *tmp;
	LIST_HEAD(gc_list);
	unsigned int deleted = 0;
	struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
						flow_cache_global);
	unsigned int i;

	for (i = 0; i < flow_cache_hash_size(fc); i++) {
		unsigned int saved = 0;

		hlist_for_each_entry_safe(fle, tmp,
					  &fcp->hash_table[i], u.hlist) {
			if (saved < shrink_to &&
			    flow_entry_valid(fle, xfrm)) {
				saved++;
			} else {
				deleted++;
				hlist_del(&fle->u.hlist);
				list_add_tail(&fle->u.gc_list, &gc_list);
			}
		}
	}

	flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);
}

static void flow_cache_shrink(struct flow_cache *fc,
			      struct flow_cache_percpu *fcp)
{
	unsigned int shrink_to = fc->low_watermark / flow_cache_hash_size(fc);

	__flow_cache_shrink(fc, fcp, shrink_to);
}

static void flow_new_hash_rnd(struct flow_cache *fc,
			      struct flow_cache_percpu *fcp)
{
	get_random_bytes(&fcp->hash_rnd, sizeof(u32));
	fcp->hash_rnd_recalc = 0;
	__flow_cache_shrink(fc, fcp, 0);
}

static u32 flow_hash_code(struct flow_cache *fc,
			  struct flow_cache_percpu *fcp,
			  const struct flowi *key,
			  unsigned int keysize)
{
	const u32 *k = (const u32 *) key;
	const u32 length = keysize * sizeof(flow_compare_t) / sizeof(u32);

	return jhash2(k, length, fcp->hash_rnd)
		& (flow_cache_hash_size(fc) - 1);
}

/* I hear what you're saying, use memcmp.  But memcmp cannot make
 * important assumptions that we can here, such as alignment.
 */
static int flow_key_compare(const struct flowi *key1, const struct flowi *key2,
			    unsigned int keysize)
{
	const flow_compare_t *k1, *k1_lim, *k2;

	k1 = (const flow_compare_t *) key1;
	k1_lim = k1 + keysize;

	k2 = (const flow_compare_t *) key2;

	do {
		if (*k1++ != *k2++)
			return 1;
	} while (k1 < k1_lim);

	return 0;
}

struct flow_cache_object *
flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
		  flow_resolve_t resolver, void *ctx)
{
	struct flow_cache *fc = &net->xfrm.flow_cache_global;
	struct flow_cache_percpu *fcp;
	struct flow_cache_entry *fle, *tfle;
	struct flow_cache_object *flo;
	unsigned int keysize;
	unsigned int hash;

	local_bh_disable();
	fcp = this_cpu_ptr(fc->percpu);

	fle = NULL;
	flo = NULL;

	keysize = flow_key_size(family);
	if (!keysize)
		goto nocache;

	/* Packet really early in init?  Making flow_cache_init a
	 * pre-smp initcall would solve this.  --RR */
	if (!fcp->hash_table)
		goto nocache;

	if (fcp->hash_rnd_recalc)
		flow_new_hash_rnd(fc, fcp);

	hash = flow_hash_code(fc, fcp, key, keysize);
	hlist_for_each_entry(tfle, &fcp->hash_table[hash], u.hlist) {
		if (tfle->net == net &&
		    tfle->family == family &&
		    tfle->dir == dir &&
		    flow_key_compare(key, &tfle->key, keysize) == 0) {
			fle = tfle;
			break;
		}
	}

	if (unlikely(!fle)) {
		if (fcp->hash_count > fc->high_watermark)
			flow_cache_shrink(fc, fcp);

		if (atomic_read(&net->xfrm.flow_cache_gc_count) >
		    2 * num_online_cpus() * fc->high_watermark) {
			flo = ERR_PTR(-ENOBUFS);
			goto ret_object;
		}

		fle = kmem_cache_alloc(flow_cachep, GFP_ATOMIC);
		if (fle) {
			fle->net = net;
			fle->family = family;
			fle->dir = dir;
			memcpy(&fle->key, key, keysize * sizeof(flow_compare_t));
			fle->object = NULL;
			hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]);
			fcp->hash_count++;
		}
	} else if (likely(fle->genid == atomic_read(&net->xfrm.flow_cache_genid))) {
		flo = fle->object;
		if (!flo)
			goto ret_object;
		flo = flo->ops->get(flo);
		if (flo)
			goto ret_object;
	} else if (fle->object) {
	        flo = fle->object;
	        flo->ops->delete(flo);
	        fle->object = NULL;
	}

nocache:
	flo = NULL;
	if (fle) {
		flo = fle->object;
		fle->object = NULL;
	}
	flo = resolver(net, key, family, dir, flo, ctx);
	if (fle) {
		fle->genid = atomic_read(&net->xfrm.flow_cache_genid);
		if (!IS_ERR(flo))
			fle->object = flo;
		else
			fle->genid--;
	} else {
		if (!IS_ERR_OR_NULL(flo))
			flo->ops->delete(flo);
	}
ret_object:
	local_bh_enable();
	return flo;
}
EXPORT_SYMBOL(flow_cache_lookup);

static void flow_cache_flush_tasklet(unsigned long data)
{
	struct flow_flush_info *info = (void *)data;
	struct flow_cache *fc = info->cache;
	struct flow_cache_percpu *fcp;
	struct flow_cache_entry *fle;
	struct hlist_node *tmp;
	LIST_HEAD(gc_list);
	unsigned int deleted = 0;
	struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
						flow_cache_global);
	unsigned int i;

	fcp = this_cpu_ptr(fc->percpu);
	for (i = 0; i < flow_cache_hash_size(fc); i++) {
		hlist_for_each_entry_safe(fle, tmp,
					  &fcp->hash_table[i], u.hlist) {
			if (flow_entry_valid(fle, xfrm))
				continue;

			deleted++;
			hlist_del(&fle->u.hlist);
			list_add_tail(&fle->u.gc_list, &gc_list);
		}
	}

	flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);

	if (atomic_dec_and_test(&info->cpuleft))
		complete(&info->completion);
}

/*
 * Return whether a cpu needs flushing.  Conservatively, we assume
 * the presence of any entries means the core may require flushing,
 * since the flow_cache_ops.check() function may assume it's running
 * on the same core as the per-cpu cache component.
 */
static int flow_cache_percpu_empty(struct flow_cache *fc, int cpu)
{
	struct flow_cache_percpu *fcp;
	unsigned int i;

	fcp = per_cpu_ptr(fc->percpu, cpu);
	for (i = 0; i < flow_cache_hash_size(fc); i++)
		if (!hlist_empty(&fcp->hash_table[i]))
			return 0;
	return 1;
}

static void flow_cache_flush_per_cpu(void *data)
{
	struct flow_flush_info *info = data;
	struct tasklet_struct *tasklet;

	tasklet = &this_cpu_ptr(info->cache->percpu)->flush_tasklet;
	tasklet->data = (unsigned long)info;
	tasklet_schedule(tasklet);
}

void flow_cache_flush(struct net *net)
{
	struct flow_flush_info info;
	cpumask_var_t mask;
	int i, self;

	/* Track which cpus need flushing to avoid disturbing all cores. */
	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
		return;
	cpumask_clear(mask);

	/* Don't want cpus going down or up during this. */
	get_online_cpus();
	mutex_lock(&net->xfrm.flow_flush_sem);
	info.cache = &net->xfrm.flow_cache_global;
	for_each_online_cpu(i)
		if (!flow_cache_percpu_empty(info.cache, i))
			cpumask_set_cpu(i, mask);
	atomic_set(&info.cpuleft, cpumask_weight(mask));
	if (atomic_read(&info.cpuleft) == 0)
		goto done;

	init_completion(&info.completion);

	local_bh_disable();
	self = cpumask_test_and_clear_cpu(smp_processor_id(), mask);
	on_each_cpu_mask(mask, flow_cache_flush_per_cpu, &info, 0);
	if (self)
		flow_cache_flush_tasklet((unsigned long)&info);
	local_bh_enable();

	wait_for_completion(&info.completion);

done:
	mutex_unlock(&net->xfrm.flow_flush_sem);
	put_online_cpus();
	free_cpumask_var(mask);
}

static void flow_cache_flush_task(struct work_struct *work)
{
	struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
						flow_cache_flush_work);
	struct net *net = container_of(xfrm, struct net, xfrm);

	flow_cache_flush(net);
}

void flow_cache_flush_deferred(struct net *net)
{
	schedule_work(&net->xfrm.flow_cache_flush_work);
}

static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
{
	struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
	unsigned int sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc);

	if (!fcp->hash_table) {
		fcp->hash_table = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
		if (!fcp->hash_table) {
			pr_err("NET: failed to allocate flow cache sz %u\n", sz);
			return -ENOMEM;
		}
		fcp->hash_rnd_recalc = 1;
		fcp->hash_count = 0;
		tasklet_init(&fcp->flush_tasklet, flow_cache_flush_tasklet, 0);
	}
	return 0;
}

static int flow_cache_cpu_up_prep(unsigned int cpu, struct hlist_node *node)
{
	struct flow_cache *fc = hlist_entry_safe(node, struct flow_cache, node);

	return flow_cache_cpu_prepare(fc, cpu);
}

static int flow_cache_cpu_dead(unsigned int cpu, struct hlist_node *node)
{
	struct flow_cache *fc = hlist_entry_safe(node, struct flow_cache, node);
	struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);

	__flow_cache_shrink(fc, fcp, 0);
	return 0;
}

int flow_cache_init(struct net *net)
{
	int i;
	struct flow_cache *fc = &net->xfrm.flow_cache_global;

	if (!flow_cachep)
		flow_cachep = kmem_cache_create("flow_cache",
						sizeof(struct flow_cache_entry),
						0, SLAB_PANIC, NULL);
	spin_lock_init(&net->xfrm.flow_cache_gc_lock);
	INIT_LIST_HEAD(&net->xfrm.flow_cache_gc_list);
	INIT_WORK(&net->xfrm.flow_cache_gc_work, flow_cache_gc_task);
	INIT_WORK(&net->xfrm.flow_cache_flush_work, flow_cache_flush_task);
	mutex_init(&net->xfrm.flow_flush_sem);
	atomic_set(&net->xfrm.flow_cache_gc_count, 0);

	fc->hash_shift = 10;
	fc->low_watermark = 2 * flow_cache_hash_size(fc);
	fc->high_watermark = 4 * flow_cache_hash_size(fc);

	fc->percpu = alloc_percpu(struct flow_cache_percpu);
	if (!fc->percpu)
		return -ENOMEM;

	if (cpuhp_state_add_instance(CPUHP_NET_FLOW_PREPARE, &fc->node))
		goto err;

	setup_timer(&fc->rnd_timer, flow_cache_new_hashrnd,
		    (unsigned long) fc);
	fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD;
	add_timer(&fc->rnd_timer);

	return 0;

err:
	for_each_possible_cpu(i) {
		struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i);
		kfree(fcp->hash_table);
		fcp->hash_table = NULL;
	}

	free_percpu(fc->percpu);
	fc->percpu = NULL;

	return -ENOMEM;
}
EXPORT_SYMBOL(flow_cache_init);

void flow_cache_fini(struct net *net)
{
	int i;
	struct flow_cache *fc = &net->xfrm.flow_cache_global;

	del_timer_sync(&fc->rnd_timer);

	cpuhp_state_remove_instance_nocalls(CPUHP_NET_FLOW_PREPARE, &fc->node);

	for_each_possible_cpu(i) {
		struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i);
		kfree(fcp->hash_table);
		fcp->hash_table = NULL;
	}

	free_percpu(fc->percpu);
	fc->percpu = NULL;
}
EXPORT_SYMBOL(flow_cache_fini);

void __init flow_cache_hp_init(void)
{
	int ret;

	ret = cpuhp_setup_state_multi(CPUHP_NET_FLOW_PREPARE,
				      "net/flow:prepare",
				      flow_cache_cpu_up_prep,
				      flow_cache_cpu_dead);
	WARN_ON(ret < 0);
}