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