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
|
/*
* IPVS: Source Hashing scheduling module
*
* Authors: Wensong Zhang <wensong@gnuchina.org>
*
* 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:
*
*/
/*
* The sh algorithm is to select server by the hash key of source IP
* address. The pseudo code is as follows:
*
* n <- servernode[src_ip];
* if (n is dead) OR
* (n is overloaded) or (n.weight <= 0) then
* return NULL;
*
* return n;
*
* Notes that servernode is a 256-bucket hash table that maps the hash
* index derived from packet source IP address to the current server
* array. If the sh scheduler is used in cache cluster, it is good to
* combine it with cache_bypass feature. When the statically assigned
* server is dead or overloaded, the load balancer can bypass the cache
* server and send requests to the original server directly.
*
* The weight destination attribute can be used to control the
* distribution of connections to the destinations in servernode. The
* greater the weight, the more connections the destination
* will receive.
*
*/
#define KMSG_COMPONENT "IPVS"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/ip.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <net/ip_vs.h>
#include <net/tcp.h>
#include <linux/udp.h>
#include <linux/sctp.h>
/*
* IPVS SH bucket
*/
struct ip_vs_sh_bucket {
struct ip_vs_dest __rcu *dest; /* real server (cache) */
};
/*
* for IPVS SH entry hash table
*/
#ifndef CONFIG_IP_VS_SH_TAB_BITS
#define CONFIG_IP_VS_SH_TAB_BITS 8
#endif
#define IP_VS_SH_TAB_BITS CONFIG_IP_VS_SH_TAB_BITS
#define IP_VS_SH_TAB_SIZE (1 << IP_VS_SH_TAB_BITS)
#define IP_VS_SH_TAB_MASK (IP_VS_SH_TAB_SIZE - 1)
struct ip_vs_sh_state {
struct rcu_head rcu_head;
struct ip_vs_sh_bucket buckets[IP_VS_SH_TAB_SIZE];
};
/* Helper function to determine if server is unavailable */
static inline bool is_unavailable(struct ip_vs_dest *dest)
{
return atomic_read(&dest->weight) <= 0 ||
dest->flags & IP_VS_DEST_F_OVERLOAD;
}
/*
* Returns hash value for IPVS SH entry
*/
static inline unsigned int
ip_vs_sh_hashkey(int af, const union nf_inet_addr *addr,
__be16 port, unsigned int offset)
{
__be32 addr_fold = addr->ip;
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6)
addr_fold = addr->ip6[0]^addr->ip6[1]^
addr->ip6[2]^addr->ip6[3];
#endif
return (offset + (ntohs(port) + ntohl(addr_fold))*2654435761UL) &
IP_VS_SH_TAB_MASK;
}
/*
* Get ip_vs_dest associated with supplied parameters.
*/
static inline struct ip_vs_dest *
ip_vs_sh_get(struct ip_vs_service *svc, struct ip_vs_sh_state *s,
const union nf_inet_addr *addr, __be16 port)
{
unsigned int hash = ip_vs_sh_hashkey(svc->af, addr, port, 0);
struct ip_vs_dest *dest = rcu_dereference(s->buckets[hash].dest);
return (!dest || is_unavailable(dest)) ? NULL : dest;
}
/* As ip_vs_sh_get, but with fallback if selected server is unavailable
*
* The fallback strategy loops around the table starting from a "random"
* point (in fact, it is chosen to be the original hash value to make the
* algorithm deterministic) to find a new server.
*/
static inline struct ip_vs_dest *
ip_vs_sh_get_fallback(struct ip_vs_service *svc, struct ip_vs_sh_state *s,
const union nf_inet_addr *addr, __be16 port)
{
unsigned int offset, roffset;
unsigned int hash, ihash;
struct ip_vs_dest *dest;
/* first try the dest it's supposed to go to */
ihash = ip_vs_sh_hashkey(svc->af, addr, port, 0);
dest = rcu_dereference(s->buckets[ihash].dest);
if (!dest)
return NULL;
if (!is_unavailable(dest))
return dest;
IP_VS_DBG_BUF(6, "SH: selected unavailable server %s:%d, reselecting",
IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port));
/* if the original dest is unavailable, loop around the table
* starting from ihash to find a new dest
*/
for (offset = 0; offset < IP_VS_SH_TAB_SIZE; offset++) {
roffset = (offset + ihash) % IP_VS_SH_TAB_SIZE;
hash = ip_vs_sh_hashkey(svc->af, addr, port, roffset);
dest = rcu_dereference(s->buckets[hash].dest);
if (!dest)
break;
if (!is_unavailable(dest))
return dest;
IP_VS_DBG_BUF(6, "SH: selected unavailable "
"server %s:%d (offset %d), reselecting",
IP_VS_DBG_ADDR(svc->af, &dest->addr),
ntohs(dest->port), roffset);
}
return NULL;
}
/*
* Assign all the hash buckets of the specified table with the service.
*/
static int
ip_vs_sh_reassign(struct ip_vs_sh_state *s, struct ip_vs_service *svc)
{
int i;
struct ip_vs_sh_bucket *b;
struct list_head *p;
struct ip_vs_dest *dest;
int d_count;
bool empty;
b = &s->buckets[0];
p = &svc->destinations;
empty = list_empty(p);
d_count = 0;
for (i=0; i<IP_VS_SH_TAB_SIZE; i++) {
dest = rcu_dereference_protected(b->dest, 1);
if (dest)
ip_vs_dest_put(dest);
if (empty)
RCU_INIT_POINTER(b->dest, NULL);
else {
if (p == &svc->destinations)
p = p->next;
dest = list_entry(p, struct ip_vs_dest, n_list);
ip_vs_dest_hold(dest);
RCU_INIT_POINTER(b->dest, dest);
IP_VS_DBG_BUF(6, "assigned i: %d dest: %s weight: %d\n",
i, IP_VS_DBG_ADDR(svc->af, &dest->addr),
atomic_read(&dest->weight));
/* Don't move to next dest until filling weight */
if (++d_count >= atomic_read(&dest->weight)) {
p = p->next;
d_count = 0;
}
}
b++;
}
return 0;
}
/*
* Flush all the hash buckets of the specified table.
*/
static void ip_vs_sh_flush(struct ip_vs_sh_state *s)
{
int i;
struct ip_vs_sh_bucket *b;
struct ip_vs_dest *dest;
b = &s->buckets[0];
for (i=0; i<IP_VS_SH_TAB_SIZE; i++) {
dest = rcu_dereference_protected(b->dest, 1);
if (dest) {
ip_vs_dest_put(dest);
RCU_INIT_POINTER(b->dest, NULL);
}
b++;
}
}
static int ip_vs_sh_init_svc(struct ip_vs_service *svc)
{
struct ip_vs_sh_state *s;
/* allocate the SH table for this service */
s = kzalloc(sizeof(struct ip_vs_sh_state), GFP_KERNEL);
if (s == NULL)
return -ENOMEM;
svc->sched_data = s;
IP_VS_DBG(6, "SH hash table (memory=%Zdbytes) allocated for "
"current service\n",
sizeof(struct ip_vs_sh_bucket)*IP_VS_SH_TAB_SIZE);
/* assign the hash buckets with current dests */
ip_vs_sh_reassign(s, svc);
return 0;
}
static void ip_vs_sh_done_svc(struct ip_vs_service *svc)
{
struct ip_vs_sh_state *s = svc->sched_data;
/* got to clean up hash buckets here */
ip_vs_sh_flush(s);
/* release the table itself */
kfree_rcu(s, rcu_head);
IP_VS_DBG(6, "SH hash table (memory=%Zdbytes) released\n",
sizeof(struct ip_vs_sh_bucket)*IP_VS_SH_TAB_SIZE);
}
static int ip_vs_sh_dest_changed(struct ip_vs_service *svc,
struct ip_vs_dest *dest)
{
struct ip_vs_sh_state *s = svc->sched_data;
/* assign the hash buckets with the updated service */
ip_vs_sh_reassign(s, svc);
return 0;
}
/* Helper function to get port number */
static inline __be16
ip_vs_sh_get_port(const struct sk_buff *skb, struct ip_vs_iphdr *iph)
{
__be16 port;
struct tcphdr _tcph, *th;
struct udphdr _udph, *uh;
sctp_sctphdr_t _sctph, *sh;
switch (iph->protocol) {
case IPPROTO_TCP:
th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph);
if (unlikely(th == NULL))
return 0;
port = th->source;
break;
case IPPROTO_UDP:
uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph);
if (unlikely(uh == NULL))
return 0;
port = uh->source;
break;
case IPPROTO_SCTP:
|