Loading...
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 | /*
* ip_vs_proto.c: transport protocol load balancing support for IPVS
*
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
* Julian Anastasov <ja@ssi.bg>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Changes:
*
*/
#define KMSG_COMPONENT "IPVS"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/gfp.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <net/protocol.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <linux/stat.h>
#include <linux/proc_fs.h>
#include <net/ip_vs.h>
/*
* IPVS protocols can only be registered/unregistered when the ipvs
* module is loaded/unloaded, so no lock is needed in accessing the
* ipvs protocol table.
*/
#define IP_VS_PROTO_TAB_SIZE 32 /* must be power of 2 */
#define IP_VS_PROTO_HASH(proto) ((proto) & (IP_VS_PROTO_TAB_SIZE-1))
static struct ip_vs_protocol *ip_vs_proto_table[IP_VS_PROTO_TAB_SIZE];
/*
* register an ipvs protocol
*/
static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp)
{
unsigned int hash = IP_VS_PROTO_HASH(pp->protocol);
pp->next = ip_vs_proto_table[hash];
ip_vs_proto_table[hash] = pp;
if (pp->init != NULL)
pp->init(pp);
return 0;
}
/*
* register an ipvs protocols netns related data
*/
static int
register_ip_vs_proto_netns(struct netns_ipvs *ipvs, struct ip_vs_protocol *pp)
{
unsigned int hash = IP_VS_PROTO_HASH(pp->protocol);
struct ip_vs_proto_data *pd =
kzalloc(sizeof(struct ip_vs_proto_data), GFP_KERNEL);
if (!pd)
return -ENOMEM;
pd->pp = pp; /* For speed issues */
pd->next = ipvs->proto_data_table[hash];
ipvs->proto_data_table[hash] = pd;
atomic_set(&pd->appcnt, 0); /* Init app counter */
if (pp->init_netns != NULL) {
int ret = pp->init_netns(ipvs, pd);
if (ret) {
/* unlink an free proto data */
ipvs->proto_data_table[hash] = pd->next;
kfree(pd);
return ret;
}
}
return 0;
}
/*
* unregister an ipvs protocol
*/
static int unregister_ip_vs_protocol(struct ip_vs_protocol *pp)
{
struct ip_vs_protocol **pp_p;
unsigned int hash = IP_VS_PROTO_HASH(pp->protocol);
pp_p = &ip_vs_proto_table[hash];
for (; *pp_p; pp_p = &(*pp_p)->next) {
if (*pp_p == pp) {
*pp_p = pp->next;
if (pp->exit != NULL)
pp->exit(pp);
return 0;
}
}
return -ESRCH;
}
/*
* unregister an ipvs protocols netns data
*/
static int
unregister_ip_vs_proto_netns(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd)
{
struct ip_vs_proto_data **pd_p;
unsigned int hash = IP_VS_PROTO_HASH(pd->pp->protocol);
pd_p = &ipvs->proto_data_table[hash];
for (; *pd_p; pd_p = &(*pd_p)->next) {
if (*pd_p == pd) {
*pd_p = pd->next;
if (pd->pp->exit_netns != NULL)
pd->pp->exit_netns(ipvs, pd);
kfree(pd);
return 0;
}
}
return -ESRCH;
}
/*
* get ip_vs_protocol object by its proto.
*/
struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto)
{
struct ip_vs_protocol *pp;
unsigned int hash = IP_VS_PROTO_HASH(proto);
for (pp = ip_vs_proto_table[hash]; pp; pp = pp->next) {
if (pp->protocol == proto)
return pp;
}
return NULL;
}
EXPORT_SYMBOL(ip_vs_proto_get);
/*
* get ip_vs_protocol object data by netns and proto
*/
struct ip_vs_proto_data *
ip_vs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto)
{
struct ip_vs_proto_data *pd;
unsigned int hash = IP_VS_PROTO_HASH(proto);
for (pd = ipvs->proto_data_table[hash]; pd; pd = pd->next) {
if (pd->pp->protocol == proto)
return pd;
}
return NULL;
}
EXPORT_SYMBOL(ip_vs_proto_data_get);
/*
* Propagate event for state change to all protocols
*/
void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags)
{
struct ip_vs_proto_data *pd;
int i;
for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) {
for (pd = ipvs->proto_data_table[i]; pd; pd = pd->next) {
if (pd->pp->timeout_change)
pd->pp->timeout_change(pd, flags);
}
}
}
int *
ip_vs_create_timeout_table(int *table, int size)
{
return kmemdup(table, size, GFP_KERNEL);
}
/*
* Set timeout value for state specified by name
*/
int
ip_vs_set_state_timeout(int *table, int num, const char *const *names,
const char *name, int to)
{
int i;
if (!table || !name || !to)
return -EINVAL;
for (i = 0; i < num; i++) {
if (strcmp(names[i], name))
continue;
table[i] = to * HZ;
return 0;
}
return -ENOENT;
}
const char * ip_vs_state_name(__u16 proto, int state)
{
struct ip_vs_protocol *pp = ip_vs_proto_get(proto);
if (pp == NULL || pp->state_name == NULL)
return (IPPROTO_IP == proto) ? "NONE" : "ERR!";
return pp->state_name(state);
}
static void
ip_vs_tcpudp_debug_packet_v4(struct ip_vs_protocol *pp,
const struct sk_buff *skb,
int offset,
const char *msg)
{
char buf[128];
struct iphdr _iph, *ih;
ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph);
if (ih == NULL)
sprintf(buf, "TRUNCATED");
else if (ih->frag_off & htons(IP_OFFSET))
sprintf(buf, "%pI4->%pI4 frag", &ih->saddr, &ih->daddr);
else {
__be16 _ports[2], *pptr;
pptr = skb_header_pointer(skb, offset + ih->ihl*4,
sizeof(_ports), _ports);
if (pptr == NULL)
sprintf(buf, "TRUNCATED %pI4->%pI4",
&ih->saddr, &ih->daddr);
else
sprintf(buf, "%pI4:%u->%pI4:%u",
&ih->saddr, ntohs(pptr[0]),
&ih->daddr, ntohs(pptr[1]));
}
pr_debug("%s: %s %s\n", msg, pp->name, buf);
}
#ifdef CONFIG_IP_VS_IPV6
static void
ip_vs_tcpudp_debug_packet_v6(struct ip_vs_protocol *pp,
const struct sk_buff *skb,
int offset,
const char *msg)
{
char buf[192];
struct ipv6hdr _iph, *ih;
ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph);
if (ih == NULL)
sprintf(buf, "TRUNCATED");
else if (ih->nexthdr == IPPROTO_FRAGMENT)
sprintf(buf, "%pI6c->%pI6c frag", &ih->saddr, &ih->daddr);
else {
__be16 _ports[2], *pptr;
pptr = skb_header_pointer(skb, offset + sizeof(struct ipv6hdr),
sizeof(_ports), _ports);
if (pptr == NULL)
sprintf(buf, "TRUNCATED %pI6c->%pI6c",
&ih->saddr, &ih->daddr);
else
sprintf(buf, "%pI6c:%u->%pI6c:%u",
&ih->saddr, ntohs(pptr[0]),
&ih->daddr, ntohs(pptr[1]));
}
pr_debug("%s: %s %s\n", msg, pp->name, buf);
}
#endif
void
ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
const struct sk_buff *skb,
int offset,
const char *msg)
{
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6)
ip_vs_tcpudp_debug_packet_v6(pp, skb, offset, msg);
else
#endif
ip_vs_tcpudp_debug_packet_v4(pp, skb, offset, msg);
}
/*
* per network name-space init
*/
int __net_init ip_vs_protocol_net_init(struct netns_ipvs *ipvs)
{
int i, ret;
static struct ip_vs_protocol *protos[] = {
#ifdef CONFIG_IP_VS_PROTO_TCP
&ip_vs_protocol_tcp,
#endif
#ifdef CONFIG_IP_VS_PROTO_UDP
&ip_vs_protocol_udp,
#endif
#ifdef CONFIG_IP_VS_PROTO_SCTP
&ip_vs_protocol_sctp,
#endif
#ifdef CONFIG_IP_VS_PROTO_AH
&ip_vs_protocol_ah,
#endif
#ifdef CONFIG_IP_VS_PROTO_ESP
&ip_vs_protocol_esp,
#endif
};
for (i = 0; i < ARRAY_SIZE(protos); i++) {
ret = register_ip_vs_proto_netns(ipvs, protos[i]);
if (ret < 0)
goto cleanup;
}
return 0;
cleanup:
ip_vs_protocol_net_cleanup(ipvs);
return ret;
}
void __net_exit ip_vs_protocol_net_cleanup(struct netns_ipvs *ipvs)
{
struct ip_vs_proto_data *pd;
int i;
/* unregister all the ipvs proto data for this netns */
for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) {
while ((pd = ipvs->proto_data_table[i]) != NULL)
unregister_ip_vs_proto_netns(ipvs, pd);
}
}
int __init ip_vs_protocol_init(void)
{
char protocols[64];
#define REGISTER_PROTOCOL(p) \
do { \
register_ip_vs_protocol(p); \
strcat(protocols, ", "); \
strcat(protocols, (p)->name); \
} while (0)
protocols[0] = '\0';
protocols[2] = '\0';
#ifdef CONFIG_IP_VS_PROTO_TCP
REGISTER_PROTOCOL(&ip_vs_protocol_tcp);
#endif
#ifdef CONFIG_IP_VS_PROTO_UDP
REGISTER_PROTOCOL(&ip_vs_protocol_udp);
#endif
#ifdef CONFIG_IP_VS_PROTO_SCTP
REGISTER_PROTOCOL(&ip_vs_protocol_sctp);
#endif
#ifdef CONFIG_IP_VS_PROTO_AH
REGISTER_PROTOCOL(&ip_vs_protocol_ah);
#endif
#ifdef CONFIG_IP_VS_PROTO_ESP
REGISTER_PROTOCOL(&ip_vs_protocol_esp);
#endif
pr_info("Registered protocols (%s)\n", &protocols[2]);
return 0;
}
void ip_vs_protocol_cleanup(void)
{
struct ip_vs_protocol *pp;
int i;
/* unregister all the ipvs protocols */
for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) {
while ((pp = ip_vs_proto_table[i]) != NULL)
unregister_ip_vs_protocol(pp);
}
}
|