xref: /kernel/linux/linux-5.10/net/ipv4/inetpeer.c (revision 8c2ecf20)
1/*
2 *		INETPEER - A storage for permanent information about peers
3 *
4 *  This source is covered by the GNU GPL, the same as all kernel sources.
5 *
6 *  Authors:	Andrey V. Savochkin <saw@msu.ru>
7 */
8
9#include <linux/cache.h>
10#include <linux/module.h>
11#include <linux/types.h>
12#include <linux/slab.h>
13#include <linux/interrupt.h>
14#include <linux/spinlock.h>
15#include <linux/random.h>
16#include <linux/timer.h>
17#include <linux/time.h>
18#include <linux/kernel.h>
19#include <linux/mm.h>
20#include <linux/net.h>
21#include <linux/workqueue.h>
22#include <net/ip.h>
23#include <net/inetpeer.h>
24#include <net/secure_seq.h>
25
26/*
27 *  Theory of operations.
28 *  We keep one entry for each peer IP address.  The nodes contains long-living
29 *  information about the peer which doesn't depend on routes.
30 *
31 *  Nodes are removed only when reference counter goes to 0.
32 *  When it's happened the node may be removed when a sufficient amount of
33 *  time has been passed since its last use.  The less-recently-used entry can
34 *  also be removed if the pool is overloaded i.e. if the total amount of
35 *  entries is greater-or-equal than the threshold.
36 *
37 *  Node pool is organised as an RB tree.
38 *  Such an implementation has been chosen not just for fun.  It's a way to
39 *  prevent easy and efficient DoS attacks by creating hash collisions.  A huge
40 *  amount of long living nodes in a single hash slot would significantly delay
41 *  lookups performed with disabled BHs.
42 *
43 *  Serialisation issues.
44 *  1.  Nodes may appear in the tree only with the pool lock held.
45 *  2.  Nodes may disappear from the tree only with the pool lock held
46 *      AND reference count being 0.
47 *  3.  Global variable peer_total is modified under the pool lock.
48 *  4.  struct inet_peer fields modification:
49 *		rb_node: pool lock
50 *		refcnt: atomically against modifications on other CPU;
51 *		   usually under some other lock to prevent node disappearing
52 *		daddr: unchangeable
53 */
54
55static struct kmem_cache *peer_cachep __ro_after_init;
56
57void inet_peer_base_init(struct inet_peer_base *bp)
58{
59	bp->rb_root = RB_ROOT;
60	seqlock_init(&bp->lock);
61	bp->total = 0;
62}
63EXPORT_SYMBOL_GPL(inet_peer_base_init);
64
65#define PEER_MAX_GC 32
66
67/* Exported for sysctl_net_ipv4.  */
68int inet_peer_threshold __read_mostly = 65536 + 128;	/* start to throw entries more
69					 * aggressively at this stage */
70int inet_peer_minttl __read_mostly = 120 * HZ;	/* TTL under high load: 120 sec */
71int inet_peer_maxttl __read_mostly = 10 * 60 * HZ;	/* usual time to live: 10 min */
72
73/* Called from ip_output.c:ip_init  */
74void __init inet_initpeers(void)
75{
76	struct sysinfo si;
77
78	/* Use the straight interface to information about memory. */
79	si_meminfo(&si);
80	/* The values below were suggested by Alexey Kuznetsov
81	 * <kuznet@ms2.inr.ac.ru>.  I don't have any opinion about the values
82	 * myself.  --SAW
83	 */
84	if (si.totalram <= (32768*1024)/PAGE_SIZE)
85		inet_peer_threshold >>= 1; /* max pool size about 1MB on IA32 */
86	if (si.totalram <= (16384*1024)/PAGE_SIZE)
87		inet_peer_threshold >>= 1; /* about 512KB */
88	if (si.totalram <= (8192*1024)/PAGE_SIZE)
89		inet_peer_threshold >>= 2; /* about 128KB */
90
91	peer_cachep = kmem_cache_create("inet_peer_cache",
92			sizeof(struct inet_peer),
93			0, SLAB_HWCACHE_ALIGN | SLAB_PANIC,
94			NULL);
95}
96
97/* Called with rcu_read_lock() or base->lock held */
98static struct inet_peer *lookup(const struct inetpeer_addr *daddr,
99				struct inet_peer_base *base,
100				unsigned int seq,
101				struct inet_peer *gc_stack[],
102				unsigned int *gc_cnt,
103				struct rb_node **parent_p,
104				struct rb_node ***pp_p)
105{
106	struct rb_node **pp, *parent, *next;
107	struct inet_peer *p;
108
109	pp = &base->rb_root.rb_node;
110	parent = NULL;
111	while (1) {
112		int cmp;
113
114		next = rcu_dereference_raw(*pp);
115		if (!next)
116			break;
117		parent = next;
118		p = rb_entry(parent, struct inet_peer, rb_node);
119		cmp = inetpeer_addr_cmp(daddr, &p->daddr);
120		if (cmp == 0) {
121			if (!refcount_inc_not_zero(&p->refcnt))
122				break;
123			return p;
124		}
125		if (gc_stack) {
126			if (*gc_cnt < PEER_MAX_GC)
127				gc_stack[(*gc_cnt)++] = p;
128		} else if (unlikely(read_seqretry(&base->lock, seq))) {
129			break;
130		}
131		if (cmp == -1)
132			pp = &next->rb_left;
133		else
134			pp = &next->rb_right;
135	}
136	*parent_p = parent;
137	*pp_p = pp;
138	return NULL;
139}
140
141static void inetpeer_free_rcu(struct rcu_head *head)
142{
143	kmem_cache_free(peer_cachep, container_of(head, struct inet_peer, rcu));
144}
145
146/* perform garbage collect on all items stacked during a lookup */
147static void inet_peer_gc(struct inet_peer_base *base,
148			 struct inet_peer *gc_stack[],
149			 unsigned int gc_cnt)
150{
151	int peer_threshold, peer_maxttl, peer_minttl;
152	struct inet_peer *p;
153	__u32 delta, ttl;
154	int i;
155
156	peer_threshold = READ_ONCE(inet_peer_threshold);
157	peer_maxttl = READ_ONCE(inet_peer_maxttl);
158	peer_minttl = READ_ONCE(inet_peer_minttl);
159
160	if (base->total >= peer_threshold)
161		ttl = 0; /* be aggressive */
162	else
163		ttl = peer_maxttl - (peer_maxttl - peer_minttl) / HZ *
164			base->total / peer_threshold * HZ;
165	for (i = 0; i < gc_cnt; i++) {
166		p = gc_stack[i];
167
168		/* The READ_ONCE() pairs with the WRITE_ONCE()
169		 * in inet_putpeer()
170		 */
171		delta = (__u32)jiffies - READ_ONCE(p->dtime);
172
173		if (delta < ttl || !refcount_dec_if_one(&p->refcnt))
174			gc_stack[i] = NULL;
175	}
176	for (i = 0; i < gc_cnt; i++) {
177		p = gc_stack[i];
178		if (p) {
179			rb_erase(&p->rb_node, &base->rb_root);
180			base->total--;
181			call_rcu(&p->rcu, inetpeer_free_rcu);
182		}
183	}
184}
185
186struct inet_peer *inet_getpeer(struct inet_peer_base *base,
187			       const struct inetpeer_addr *daddr,
188			       int create)
189{
190	struct inet_peer *p, *gc_stack[PEER_MAX_GC];
191	struct rb_node **pp, *parent;
192	unsigned int gc_cnt, seq;
193	int invalidated;
194
195	/* Attempt a lockless lookup first.
196	 * Because of a concurrent writer, we might not find an existing entry.
197	 */
198	rcu_read_lock();
199	seq = read_seqbegin(&base->lock);
200	p = lookup(daddr, base, seq, NULL, &gc_cnt, &parent, &pp);
201	invalidated = read_seqretry(&base->lock, seq);
202	rcu_read_unlock();
203
204	if (p)
205		return p;
206
207	/* If no writer did a change during our lookup, we can return early. */
208	if (!create && !invalidated)
209		return NULL;
210
211	/* retry an exact lookup, taking the lock before.
212	 * At least, nodes should be hot in our cache.
213	 */
214	parent = NULL;
215	write_seqlock_bh(&base->lock);
216
217	gc_cnt = 0;
218	p = lookup(daddr, base, seq, gc_stack, &gc_cnt, &parent, &pp);
219	if (!p && create) {
220		p = kmem_cache_alloc(peer_cachep, GFP_ATOMIC);
221		if (p) {
222			p->daddr = *daddr;
223			p->dtime = (__u32)jiffies;
224			refcount_set(&p->refcnt, 2);
225			atomic_set(&p->rid, 0);
226			p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
227			p->rate_tokens = 0;
228			p->n_redirects = 0;
229			/* 60*HZ is arbitrary, but chosen enough high so that the first
230			 * calculation of tokens is at its maximum.
231			 */
232			p->rate_last = jiffies - 60*HZ;
233
234			rb_link_node(&p->rb_node, parent, pp);
235			rb_insert_color(&p->rb_node, &base->rb_root);
236			base->total++;
237		}
238	}
239	if (gc_cnt)
240		inet_peer_gc(base, gc_stack, gc_cnt);
241	write_sequnlock_bh(&base->lock);
242
243	return p;
244}
245EXPORT_SYMBOL_GPL(inet_getpeer);
246
247void inet_putpeer(struct inet_peer *p)
248{
249	/* The WRITE_ONCE() pairs with itself (we run lockless)
250	 * and the READ_ONCE() in inet_peer_gc()
251	 */
252	WRITE_ONCE(p->dtime, (__u32)jiffies);
253
254	if (refcount_dec_and_test(&p->refcnt))
255		call_rcu(&p->rcu, inetpeer_free_rcu);
256}
257EXPORT_SYMBOL_GPL(inet_putpeer);
258
259/*
260 *	Check transmit rate limitation for given message.
261 *	The rate information is held in the inet_peer entries now.
262 *	This function is generic and could be used for other purposes
263 *	too. It uses a Token bucket filter as suggested by Alexey Kuznetsov.
264 *
265 *	Note that the same inet_peer fields are modified by functions in
266 *	route.c too, but these work for packet destinations while xrlim_allow
267 *	works for icmp destinations. This means the rate limiting information
268 *	for one "ip object" is shared - and these ICMPs are twice limited:
269 *	by source and by destination.
270 *
271 *	RFC 1812: 4.3.2.8 SHOULD be able to limit error message rate
272 *			  SHOULD allow setting of rate limits
273 *
274 * 	Shared between ICMPv4 and ICMPv6.
275 */
276#define XRLIM_BURST_FACTOR 6
277bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout)
278{
279	unsigned long now, token;
280	bool rc = false;
281
282	if (!peer)
283		return true;
284
285	token = peer->rate_tokens;
286	now = jiffies;
287	token += now - peer->rate_last;
288	peer->rate_last = now;
289	if (token > XRLIM_BURST_FACTOR * timeout)
290		token = XRLIM_BURST_FACTOR * timeout;
291	if (token >= timeout) {
292		token -= timeout;
293		rc = true;
294	}
295	peer->rate_tokens = token;
296	return rc;
297}
298EXPORT_SYMBOL(inet_peer_xrlim_allow);
299
300void inetpeer_invalidate_tree(struct inet_peer_base *base)
301{
302	struct rb_node *p = rb_first(&base->rb_root);
303
304	while (p) {
305		struct inet_peer *peer = rb_entry(p, struct inet_peer, rb_node);
306
307		p = rb_next(p);
308		rb_erase(&peer->rb_node, &base->rb_root);
309		inet_putpeer(peer);
310		cond_resched();
311	}
312
313	base->total = 0;
314}
315EXPORT_SYMBOL(inetpeer_invalidate_tree);
316