aboutsummaryrefslogtreecommitdiff
path: root/net/ceph/messenger.c
blob: 0e8157ee5d4382a32992f34c2b1cf0d78f2868b4 (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
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
#include <linux/ceph/ceph_debug.h>

#include <linux/crc32c.h>
#include <linux/ctype.h>
#include <linux/highmem.h>
#include <linux/inet.h>
#include <linux/kthread.h>
#include <linux/net.h>
#include <linux/slab.h>
#include <linux/socket.h>
#include <linux/string.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <net/tcp.h>

#include <linux/ceph/libceph.h>
#include <linux/ceph/messenger.h>
#include <linux/ceph/decode.h>
#include <linux/ceph/pagelist.h>

/*
 * Ceph uses the messenger to exchange ceph_msg messages with other
 * hosts in the system.  The messenger provides ordered and reliable
 * delivery.  We tolerate TCP disconnects by reconnecting (with
 * exponential backoff) in the case of a fault (disconnection, bad
 * crc, protocol error).  Acks allow sent messages to be discarded by
 * the sender.
 */

/* static tag bytes (protocol control messages) */
static char tag_msg = CEPH_MSGR_TAG_MSG;
static char tag_ack = CEPH_MSGR_TAG_ACK;
static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE;

#ifdef CONFIG_LOCKDEP
static struct lock_class_key socket_class;
#endif


static void queue_con(struct ceph_connection *con);
static void con_work(struct work_struct *);
static void ceph_fault(struct ceph_connection *con);

/*
 * nicely render a sockaddr as a string.
 */
#define MAX_ADDR_STR 20
#define MAX_ADDR_STR_LEN 60
static char addr_str[MAX_ADDR_STR][MAX_ADDR_STR_LEN];
static DEFINE_SPINLOCK(addr_str_lock);
static int last_addr_str;

const char *ceph_pr_addr(const struct sockaddr_storage *ss)
{
	int i;
	char *s;
	struct sockaddr_in *in4 = (void *)ss;
	struct sockaddr_in6 *in6 = (void *)ss;

	spin_lock(&addr_str_lock);
	i = last_addr_str++;
	if (last_addr_str == MAX_ADDR_STR)
		last_addr_str = 0;
	spin_unlock(&addr_str_lock);
	s = addr_str[i];

	switch (ss->ss_family) {
	case AF_INET:
		snprintf(s, MAX_ADDR_STR_LEN, "%pI4:%u", &in4->sin_addr,
			 (unsigned int)ntohs(in4->sin_port));
		break;

	case AF_INET6:
		snprintf(s, MAX_ADDR_STR_LEN, "[%pI6c]:%u", &in6->sin6_addr,
			 (unsigned int)ntohs(in6->sin6_port));
		break;

	default:
		sprintf(s, "(unknown sockaddr family %d)", (int)ss->ss_family);
	}

	return s;
}
EXPORT_SYMBOL(ceph_pr_addr);

static void encode_my_addr(struct ceph_messenger *msgr)
{
	memcpy(&msgr->my_enc_addr, &msgr->inst.addr, sizeof(msgr->my_enc_addr));
	ceph_encode_addr(&msgr->my_enc_addr);
}

/*
 * work queue for all reading and writing to/from the socket.
 */
struct workqueue_struct *ceph_msgr_wq;

int ceph_msgr_init(void)
{
	ceph_msgr_wq = create_workqueue("ceph-msgr");
	if (IS_ERR(ceph_msgr_wq)) {
		int ret = PTR_ERR(ceph_msgr_wq);
		pr_err("msgr_init failed to create workqueue: %d\n", ret);
		ceph_msgr_wq = NULL;
		return ret;
	}
	return 0;
}
EXPORT_SYMBOL(ceph_msgr_init);

void ceph_msgr_exit(void)
{
	destroy_workqueue(ceph_msgr_wq);
}
EXPORT_SYMBOL(ceph_msgr_exit);

void ceph_msgr_flush(void)
{
	flush_workqueue(ceph_msgr_wq);
}
EXPORT_SYMBOL(ceph_msgr_flush);


/*
 * socket callback functions
 */

/* data available on socket, or listen socket received a connect */
static void ceph_data_ready(struct sock *sk, int count_unused)
{
	struct ceph_connection *con =
		(struct ceph_connection *)sk->sk_user_data;
	if (sk->sk_state != TCP_CLOSE_WAIT) {
		dout("ceph_data_ready on %p state = %lu, queueing work\n",
		     con, con->state);
		queue_con(con);
	}
}

/* socket has buffer space for writing */
static void ceph_write_space(struct sock *sk)
{
	struct ceph_connection *con =
		(struct ceph_connection *)sk->sk_user_data;

	/* only queue to workqueue if there is data we want to write. */
	if (test_bit(WRITE_PENDING, &con->state)) {
		dout("ceph_write_space %p queueing write work\n", con);
		queue_con(con);
	} else {
		dout("ceph_write_space %p nothing to write\n", con);
	}

	/* since we have our own write_space, clear the SOCK_NOSPACE flag */
	clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
}

/* socket's state has changed */
static void ceph_state_change(struct sock *sk)
{
	struct ceph_connection *con =
		(struct ceph_connection *)sk->sk_user_data;

	dout("ceph_state_change %p state = %lu sk_state = %u\n",
	     con, con->state, sk->sk_state);

	if (test_bit(CLOSED, &con->state))
		return;

	switch (sk->sk_state) {
	case TCP_CLOSE:
		dout("ceph_state_change TCP_CLOSE\n");
	case TCP_CLOSE_WAIT:
		dout("ceph_state_change TCP_CLOSE_WAIT\n");
		if (test_and_set_bit(SOCK_CLOSED, &con->state) == 0) {
			if (test_bit(CONNECTING, &con->state))
				con->error_msg = "connection failed";
			else
				con->error_msg = "socket closed";
			queue_con(con);
		}
		break;
	case TCP_ESTABLISHED:
		dout("ceph_state_change TCP_ESTABLISHED\n");
		queue_con(con);
		break;
	}
}

/*
 * set up socket callbacks
 */
static void set_sock_callbacks(struct socket *sock,
			       struct ceph_connection *con)
{
	struct sock *sk = sock->sk;
	sk->sk_user_data = (void *)con;
	sk->sk_data_ready = ceph_data_ready;
	sk->sk_write_space = ceph_write_space;
	sk->sk_state_change = ceph_state_change;
}


/*
 * socket helpers
 */

/*
 * initiate connection to a remote socket.
 */
static struct socket *ceph_tcp_connect(struct ceph_connection *con)
{
	struct sockaddr_storage *paddr = &con->peer_addr.in_addr;
	struct socket *sock;
	int ret;

	BUG_ON(con->sock);
	ret = sock_create_kern(con->peer_addr.in_addr.ss_family, SOCK_STREAM,
			       IPPROTO_TCP, &sock);
	if (ret)
		return ERR_PTR(ret);
	con->sock = sock;
	sock->sk->sk_allocation = GFP_NOFS;

#ifdef CONFIG_LOCKDEP
	lockdep_set_class(&sock->sk->sk_lock, &socket_class);
#endif

	set_sock_callbacks(sock, con);

	dout("connect %s\n", ceph_pr_addr(&con->peer_addr.in_addr));

	ret = sock->ops->connect(sock, (struct sockaddr *)paddr, sizeof(*paddr),
				 O_NONBLOCK);
	if (ret == -EINPROGRESS) {
		dout("connect %s EINPROGRESS sk_state = %u\n",
		     ceph_pr_addr(&con->peer_addr.in_addr),
		     sock->sk->sk_state);
		ret = 0;
	}
	if (ret < 0) {
		pr_err("connect %s error %d\n",
		       ceph_pr_addr(&con->peer_addr.in_addr), ret);
		sock_release(sock);
		con->sock = NULL;
		con->error_msg = "connect error";
	}

	if (ret < 0)
		return ERR_PTR(ret);
	return sock;
}

static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len)
{
	struct kvec iov = {buf, len};
	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };

	return kernel_recvmsg(sock, &msg, &iov, 1, len, msg.msg_flags);
}

/*
 * write something.  @more is true if caller will be sending more data
 * shortly.
 */
static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
		     size_t kvlen, size_t len, int more)
{
	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };

	if (more)
		msg.msg_flags |= MSG_MORE;
	else
		msg.msg_flags |= MSG_EOR;  /* superfluous, but what the hell */

	return kernel_sendmsg(sock, &msg, iov, kvlen, len);
}


/*
 * Shutdown/close the socket for the given connection.
 */
static int con_close_socket(struct ceph_connection *con)
{
	int rc;

	dout("con_close_socket on %p sock %p\n", con, con->sock);
	if (!con->sock)
		return 0;
	set_bit(SOCK_CLOSED, &con->state);
	rc = con->sock->ops->shutdown(con->sock, SHUT_RDWR);
	sock_release(con->sock);
	con->sock = NULL;
	clear_bit(SOCK_CLOSED, &con->state);
	return rc;
}

/*
 * Reset a connection.  Discard all incoming and outgoing messages
 * and clear *_seq state.
 */
static void ceph_msg_remove(struct ceph_msg *msg)
{
	list_del_init(&msg->list_head);
	ceph_msg_put(msg);
}
static void ceph_msg_remove_list(struct list_head *head)
{
	while (!list_empty(head)) {
		struct ceph_msg *msg = list_first_entry(head, struct ceph_msg,
							list_head);
		ceph_msg_remove(msg);
	}
}

static void reset_connection(struct ceph_connection *con)
{
	/* reset connection, out_queue, msg_ and connect_seq */
	/* discard existing out_queue and msg_seq */
	ceph_msg_remove_list(&con->out_queue);
	ceph_msg_remove_list(&con->out_sent);

	if (con->in_msg) {
		ceph_msg_put(con->in_msg);
		con->in_msg = NULL;
	}

	con->connect_seq = 0;
	con->out_seq = 0;
	if (con->out_msg) {
		ceph_msg_put(con->out_msg);
		con->out_msg = NULL;
	}
	con->out_keepalive_pending = false;
	con->in_seq = 0;
	con->in_seq_acked = 0;
}

/*
 * mark a peer down.  drop any open connections.
 */
void ceph_con_close(struct ceph_connection *con)
{
	dout("con_close %p peer %s\n", con,
	     ceph_pr_addr(&con->peer_addr.in_addr));
	set_bit(CLOSED, &con->state);  /* in case there's queued work */
	clear_bit(STANDBY, &con->state);  /* avoid connect_seq bump */
	clear_bit(LOSSYTX, &con->state);  /* so we retry next connect */
	clear_bit(KEEPALIVE_PENDING, &con->state);
	clear_bit(WRITE_PENDING, &con->state);
	mutex_lock(&con->mutex);
	reset_connection(con);
	con->peer_global_seq = 0;
	cancel_delayed_work(&con->work);
	mutex_unlock(&con->mutex);
	queue_con(con);
}
EXPORT_SYMBOL(ceph_con_close);

/*
 * Reopen a closed connection, with a new peer address.
 */
void ceph_con_open(struct ceph_connection *con, struct ceph_entity_addr *addr)
{
	dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr));
	set_bit(OPENING, &con->state);
	clear_bit(CLOSED, &con->state);
	memcpy(&con->peer_addr, addr, sizeof(*addr));
	con->delay = 0;      /* reset backoff memory */
	queue_con(con);
}
EXPORT_SYMBOL(ceph_con_open);

/*
 * return true if this connection ever successfully opened
 */
bool ceph_con_opened(struct ceph_connection *con)
{
	return con->connect_seq > 0;
}

/*
 * generic get/put
 */
struct ceph_connection *ceph_con_get(struct ceph_connection *con)
{
	dout("con_get %p nref = %d -> %d\n", con,
	     atomic_read(&con->nref), atomic_read(&con->nref) + 1);
	if (atomic_inc_not_zero(&con->nref))
		return con;
	return NULL;
}

void ceph_con_put(struct ceph_connection *con)
{
	dout("con_put %p nref = %d -> %d\n", con,
	     atomic_read(&con->nref), atomic_read(&con->nref) - 1);
	BUG_ON(atomic_read(&con->nref) == 0);
	if (atomic_dec_and_test(&con->nref)) {
		BUG_ON(con->sock);
		kfree(con);
	}
}

/*
 * initialize a new connection.
 */
void ceph_con_init(struct ceph_messenger *msgr, struct ceph_connection *con)
{
	dout("con_init %p\n", con);
	memset(con, 0, sizeof(*con));
	atomic_set(&con->nref, 1);
	con->msgr = msgr;
	mutex_init(&con->mutex);
	INIT_LIST_HEAD(&con->out_queue);
	INIT_LIST_HEAD(&con->out_sent);
	INIT_DELAYED_WORK(&con->work, con_work);
}
EXPORT_SYMBOL(ceph_con_init);


/*
 * We maintain a global counter to order connection attempts.  Get
 * a unique seq greater than @gt.
 */
static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt)
{
	u32 ret;

	spin_lock(&msgr->global_seq_lock);
	if (msgr->global_seq < gt)
		msgr->global_seq = gt;
	ret = ++msgr->global_seq;
	spin_unlock(&msgr->global_seq_lock);
	return ret;
}


/*
 * Prepare footer for currently outgoing message, and finish things
 * off.  Assumes out_kvec* are already valid.. we just add on to the end.
 */
static void prepare_write_message_footer(struct ceph_connection *con, int v)
{
	struct ceph_msg *m = con->out_msg;

	dout("prepare_write_message_footer %p\n", con);
	con->out_kvec_is_msg = true;
	con->out_kvec[v].iov_base = &m->footer;
	con->out_kvec[v].iov_len = sizeof(m->footer);
	con->out_kvec_bytes += sizeof(m->footer);
	con->out_kvec_left++;
	con->out_more = m->more_to_follow;
	con->out_msg_done = true;
}

/*
 * Prepare headers for the next outgoing message.
 */
static void prepare_write_message(struct ceph_connection *con)
{
	struct ceph_msg *m;
	int v = 0;

	con->out_kvec_bytes = 0;
	con->out_kvec_is_msg = true;
	con->out_msg_done = false;

	/* Sneak an ack in there first?  If we can get it into the same
	 * TCP packet that's a good thing. */
	if (con->in_seq > con->in_seq_acked) {
		con->in_seq_acked = con->in_seq;
		con->out_kvec[v].iov_base = &tag_ack;
		con->out_kvec[v++].iov_len = 1;
		con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
		con->out_kvec[v].iov_base = &con->out_temp_ack;
		con->out_kvec[v++].iov_len = sizeof(con->out_temp_ack);
		con->out_kvec_bytes = 1 + sizeof(con->out_temp_ack);
	}

	m = list_first_entry(&con->out_queue,
		       struct ceph_msg, list_head);
	con->out_msg = m;
	if (test_bit(LOSSYTX, &con->state)) {
		list_del_init(&m->list_head);
	} else {
		/* put message on sent list */
		ceph_msg_get(m);
		list_move_tail(&m->list_head, &con->out_sent);
	}

	/*
	 * only assign outgoing seq # if we haven't sent this message
	 * yet.  if it is requeued, resend with it's original seq.
	 */
	if (m->needs_out_seq) {
		m->hdr.seq = cpu_to_le64(++con->out_seq);
		m->needs_out_seq = false;
	}

	dout("prepare_write_message %p seq %lld type %d len %d+%d+%d %d pgs\n",
	     m, con->out_seq, le16_to_cpu(m->hdr.type),
	     le32_to_cpu(m->hdr.front_len), le32_to_cpu(m->hdr.middle_len),
	     le32_to_cpu(m->hdr.data_len),
	     m->nr_pages);
	BUG_ON(le32_to_cpu(m->hdr.front_len) != m->front.iov_len);

	/* tag + hdr + front + middle */
	con->out_kvec[v].iov_base = &tag_msg;
	con->out_kvec[v++].iov_len = 1;
	con->out_kvec[v].iov_base = &m->hdr;
	con->out_kvec[v++].iov_len = sizeof(m->hdr);
	con->out_kvec[v++] = m->front;
	if (m->middle)
		con->out_kvec[v++] = m->middle->vec;
	con->out_kvec_left = v;
	con->out_kvec_bytes += 1 + sizeof(m->hdr) + m->front.iov_len +
		(m->middle ? m->middle->vec.iov_len : 0);
	con->out_kvec_cur = con->out_kvec;

	/* fill in crc (except data pages), footer */
	con->out_msg->hdr.crc =
		cpu_to_le32(crc32c(0, (void *)&m->hdr,
				      sizeof(m->hdr) - sizeof(m->hdr.crc)));
	con->out_msg->footer.flags = CEPH_MSG_FOOTER_COMPLETE;
	con->out_msg->footer.front_crc =
		cpu_to_le32(crc32c(0, m->front.iov_base, m->front.iov_len));
	if (m->middle)
		con->out_msg->footer.middle_crc =
			cpu_to_le32(crc32c(0, m->middle->vec.iov_base,
					   m->middle->vec.iov_len));
	else
		con->out_msg->footer.middle_crc = 0;
	con->out_msg->footer.data_crc = 0;
	dout("prepare_write_message front_crc %u data_crc %u\n",
	     le32_to_cpu(con->out_msg->footer.front_crc),
	     le32_to_cpu(con->out_msg->footer.middle_crc));

	/* is there a data payload? */
	if (le32_to_cpu(m->hdr.data_len) > 0) {
		/* initialize page iterator */
		con->out_msg_pos.page = 0;
		if (m->pages)
			con->out_msg_pos.page_pos =
				le16_to_cpu(m->hdr.data_off) & ~PAGE_MASK;
		else
			con->out_msg_pos.page_pos = 0;
		con->out_msg_pos.data_pos = 0;
		con->out_msg_pos.did_page_crc = 0;
		con->out_more = 1;  /* data + footer will follow */
	} else {
		/* no, queue up footer too and be done */
		prepare_write_message_footer(con, v);
	}

	set_bit(WRITE_PENDING, &con->state);
}

/*
 * Prepare an ack.
 */
static void prepare_write_ack(struct ceph_connection *con)
{
	dout("prepare_write_ack %p %llu -> %llu\n", con,
	     con->in_seq_acked, con->in_seq);
	con->in_seq_acked = con->in_seq;

	con->out_kvec[0].iov_base = &tag_ack;
	con->out_kvec[0].iov_len = 1;
	con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
	con->out_kvec[1].iov_base = &con->out_temp_ack;
	con->out_kvec[1].iov_len = sizeof(con->out_temp_ack);
	con->out_kvec_left = 2;
	con->out_kvec_bytes = 1 + sizeof(con->out_temp_ack);
	con->out_kvec_cur = con->out_kvec;
	con->out_more = 1;  /* more will follow.. eventually.. */
	set_bit(WRITE_PENDING, &con->state);
}

/*
 * Prepare to write keepalive byte.
 */
static void prepare_write_keepalive(struct ceph_connection *con)
{
	dout("prepare_write_keepalive %p\n", con);
	con->out_kvec[0].iov_base = &tag_keepalive;
	con->out_kvec[0].iov_len = 1;
	con->out_kvec_left = 1;
	con->out_kvec_bytes = 1;
	con->out_kvec_cur = con->out_kvec;
	set_bit(WRITE_PENDING, &con->state);
}

/*
 * Connection negotiation.
 */

static void prepare_connect_authorizer(struct ceph_connection *con)
{
	void *auth_buf;
	int auth_len = 0;
	int auth_protocol = 0;

	mutex_unlock(&con->mutex);
	if (con->ops->get_authorizer)
		con->ops->get_authorizer(con, &auth_buf, &auth_len,
					 &auth_protocol, &con->auth_reply_buf,
					 &con->auth_reply_buf_len,
					 con->auth_retry);
	mutex_lock(&con->mutex);

	con->out_connect.authorizer_protocol = cpu_to_le32(auth_protocol);
	con->out_connect.authorizer_len = cpu_to_le32(auth_len);

	con->out_kvec[con->out_kvec_left].iov_base = auth_buf;
	con->out_kvec[con->out_kvec_left].iov_len = auth_len;
	con->out_kvec_left++;
	con->out_kvec_bytes += auth_len;
}

/*
 * We connected to a peer and are saying hello.
 */
static void prepare_write_banner(struct ceph_messenger *msgr,
				 struct ceph_connection *con)
{
	int len = strlen(CEPH_BANNER);

	con->out_kvec[0].iov_base = CEPH_BANNER;
	con->out_kvec[0].iov_len = len;
	con->out_kvec[1].iov_base = &msgr->my_enc_addr;
	con->out_kvec[1].iov_len = sizeof(msgr->my_enc_addr);
	con->out_kvec_left = 2;
	con->out_kvec_bytes = len + sizeof(msgr->my_enc_addr);
	con->out_kvec_cur = con->out_kvec;
	con->out_more = 0;
	set_bit(WRITE_PENDING, &con->state);
}

static void prepare_write_connect(struct ceph_messenger *msgr,
				  struct ceph_connection *con,
				  int after_banner)
{
	unsigned global_seq = get_global_seq(con->msgr, 0);
	int proto;

	switch (con->peer_name.type) {
	case CEPH_ENTITY_TYPE_MON:
		proto = CEPH_MONC_PROTOCOL;
		break;
	case CEPH_ENTITY_TYPE_OSD:
		proto = CEPH_OSDC_PROTOCOL;
		break;
	case CEPH_ENTITY_TYPE_MDS:
		proto = CEPH_MDSC_PROTOCOL;
		break;
	default:
		BUG();
	}

	dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con,
	     con->connect_seq, global_seq, proto);

	con->out_connect.features = cpu_to_le64(msgr->supported_features);
	con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT);
	con->out_connect.connect_seq = cpu_to_le32(con->connect_seq);
	con->out_connect.global_seq = cpu_to_le32(global_seq);
	con->out_connect.protocol_version = cpu_to_le32(proto);
	con->out_connect.flags = 0;

	if (!after_banner) {
		con->out_kvec_left = 0;
		con->out_kvec_bytes = 0;
	}
	con->out_kvec[con->out_kvec_left].iov_base = &con->out_connect;
	con->out_kvec[con->out_kvec_left].iov_len = sizeof(con->out_connect);
	con->out_kvec_left++;
	con->out_kvec_bytes += sizeof(con->out_connect);
	con->out_kvec_cur = con->out_kvec;
	con->out_more = 0;
	set_bit(WRITE_PENDING, &con->state);

	prepare_connect_authorizer(con);
}


/*
 * write as much of pending kvecs to the socket as we can.
 *  1 -> done
 *  0 -> socket full, but more to do
 * <0 -> error
 */
static int write_partial_kvec(struct ceph_connection *con)
{
	int ret;

	dout("write_partial_kvec %p %d left\n", con, con->out_kvec_bytes);
	while (con->out_kvec_bytes > 0) {
		ret = ceph_tcp_sendmsg(con->sock, con->out_kvec_cur,
				       con->out_kvec_left, con->out_kvec_bytes,
				       con->out_more);
		if (ret <= 0)
			goto out;
		con->out_kvec_bytes -= ret;
		if (con->out_kvec_bytes == 0)
			break;            /* done */
		while (ret > 0) {
			if (ret >= con->out_kvec_cur->iov_len) {
				ret -= con->out_kvec_cur->iov_len;
				con->out_kvec_cur++;
				con->out_kvec_left--;
			} else {
				con->out_kvec_cur->iov_len -= ret;
				con->out_kvec_cur->iov_base += ret;
				ret = 0;
				break;
			}
		}
	}
	con->out_kvec_left = 0;
	con->out_kvec_is_msg = false;
	ret = 1;
out:
	dout("write_partial_kvec %p %d left in %d kvecs ret = %d\n", con,
	     con->out_kvec_bytes, con->out_kvec_left, ret);
	return ret;  /* done! */
}

#ifdef CONFIG_BLOCK
static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg)
{
	if (!bio) {
		*iter = NULL;
		*seg = 0;
		return;
	}
	*iter = bio;
	*seg = bio->bi_idx;
}

static void iter_bio_next(struct bio **bio_iter, int *seg)
{
	if (*bio_iter == NULL)
		return;

	BUG_ON(*seg >= (*bio_iter)->bi_vcnt);

	(*seg)++;
	if (*seg == (*bio_iter)->bi_vcnt)
		init_bio_iter((*bio_iter)->bi_next, bio_iter, seg);
}
#endif

/*
 * Write as much message data payload as we can.  If we finish, queue
 * up the footer.
 *  1 -> done, footer is now queued in out_kvec[].
 *  0 -> socket full, but more to do
 * <0 -> error
 */
static int write_partial_msg_pages(struct ceph_connection *con)
{
	struct ceph_msg *msg = con->out_msg;
	unsigned data_len = le32_to_cpu(msg->hdr.data_len);
	size_t len;
	int crc = con->msgr->nocrc;
	int ret;
	int total_max_write;
	int in_trail = 0;
	size_t trail_len = (msg->trail ? msg->trail->length : 0);

	dout("write_partial_msg_pages %p msg %p page %d/%d offset %d\n",
	     con, con->out_msg, con->out_msg_pos.page, con->out_msg->nr_pages,
	     con->out_msg_pos.page_pos);

#ifdef CONFIG_BLOCK
	if (msg->bio && !msg->bio_iter)
		init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg);
#endif

	while (data_len > con->out_msg_pos.data_pos) {
		struct page *page = NULL;
		void *kaddr = NULL;
		int max_write = PAGE_SIZE;
		int page_shift = 0;

		total_max_write = data_len - trail_len -
			con->out_msg_pos.data_pos;

		/*
		 * if we are calculating the data crc (the default), we need
		 * to map the page.  if our pages[] has been revoked, use the
		 * zero page.
		 */

		/* have we reached the trail part of the data? */
		if (con->out_msg_pos.data_pos >= data_len - trail_len) {
			in_trail = 1;

			total_max_write = data_len - con->out_msg_pos.data_pos;

			page = list_first_entry(&msg->trail->head,
						struct page, lru);
			if (crc)
				kaddr = kmap(page);
			max_write = PAGE_SIZE;
		} else if (msg->pages) {
			page = msg->pages[con->out_msg_pos.page];
			if (crc)
				kaddr = kmap(page);
		} else if (msg->pagelist) {
			page = list_first_entry(&msg->pagelist->head,
						struct page, lru);
			if (crc)
				kaddr = kmap(page);
#ifdef CONFIG_BLOCK
		} else if (msg->bio) {
			struct bio_vec *bv;

			bv = bio_iovec_idx(msg->bio_iter, msg->bio_seg);
			page = bv->bv_page;
			page_shift = bv->bv_offset;
			if (crc)
				kaddr = kmap(page) + page_shift;
			max_write = bv->bv_len;
#endif
		} else {
			page = con->msgr->zero_page;
			if (crc)
				kaddr = page_address(con->msgr->zero_page);
		}
		len = min_t(int, max_write - con->out_msg_pos.page_pos,
			    total_max_write);

		if (crc && !con->out_msg_pos.did_page_crc) {
			void *base = kaddr + con->out_msg_pos.page_pos;
			u32 tmpcrc = le32_to_cpu(con->out_msg->footer.data_crc);

			BUG_ON(kaddr == NULL);
			con->out_msg->footer.data_crc =
				cpu_to_le32(crc32c(tmpcrc, base, len));
			con->out_msg_pos.did_page_crc = 1;
		}
		ret = kernel_sendpage(con->sock, page,
				      con->out_msg_pos.page_pos + page_shift,
				      len,
				      MSG_DONTWAIT | MSG_NOSIGNAL |
				      MSG_MORE);

		if (crc &&
		    (msg->pages || msg->pagelist || msg->bio || in_trail))
			kunmap(page);

		if (ret <= 0)
			goto out;

		con->out_msg_pos.data_pos += ret;
		con->out_msg_pos.page_pos += ret;
		if (ret == len) {
			con->out_msg_pos.page_pos = 0;
			con->out_msg_pos.page++;
			con->out_msg_pos.did_page_crc = 0;
			if (in_trail)
				list_move_tail(&page->lru,
					       &msg->trail->head);
			else if (msg->pagelist)
				list_move_tail(&page->lru,
					       &msg->pagelist->head);
#ifdef CONFIG_BLOCK
			else if (msg->bio)
				iter_bio_next(&msg->bio_iter, &msg->bio_seg);
#endif
		}
	}

	dout("write_partial_msg_pages %p msg %p done\n", con, msg);

	/* prepare and queue up footer, too */
	if (!crc)
		con->out_msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
	con->out_kvec_bytes = 0;
	con->out_kvec_left = 0;
	con->out_kvec_cur = con->out_kvec;
	prepare_write_message_footer(con, 0);
	ret = 1;
out:
	return ret;
}

/*
 * write some zeros
 */
static int write_partial_skip(struct ceph_connection *con)
{
	int ret;

	while (con->out_skip > 0) {
		struct kvec iov = {
			.iov_base = page_address(con->msgr->zero_page),
			.iov_len = min(con->out_skip, (int)PAGE_CACHE_SIZE)
		};

		ret = ceph_tcp_sendmsg(con->sock, &iov, 1, iov.iov_len, 1);
		if (ret <= 0)
			goto out;
		con->out_skip -= ret;
	}
	ret = 1;
out:
	return ret;
}

/*
 * Prepare to read connection handshake, or an ack.
 */
static void prepare_read_banner(struct ceph_connection *con)
{
	dout("prepare_read_banner %p\n", con);
	con->in_base_pos = 0;
}

static void prepare_read_connect(struct ceph_connection *con)
{
	dout("prepare_read_connect %p\n", con);
	con->in_base_pos = 0;
}

static void prepare_read_ack(struct ceph_connection *con)
{
	dout("prepare_read_ack %p\n", con);
	con->in_base_pos = 0;
}

static void prepare_read_tag(struct ceph_connection *con)
{
	dout("prepare_read_tag %p\n", con);
	con->in_base_pos = 0;
	con->in_tag = CEPH_MSGR_TAG_READY;
}

/*
 * Prepare to read a message.
 */
static int prepare_read_message(struct ceph_connection *con)
{
	dout("prepare_read_message %p\n", con);
	BUG_ON(con->in_msg != NULL);
	con->in_base_pos = 0;
	con->in_front_crc = con->in_middle_crc = con->in_data_crc = 0;
	return 0;
}


static int read_partial(struct ceph_connection *con,
			int *to, int size, void *object)
{
	*to += size;
	while (con->in_base_pos < *to) {
		int left = *to - con->in_base_pos;
		int have = size - left;
		int ret = ceph_tcp_recvmsg(con->sock, object + have, left);
		if (ret <= 0)
			return ret;
		con->in_base_pos += ret;
	}
	return 1;
}


/*
 * Read all or part of the connect-side handshake on a new connection
 */
static int read_partial_banner(struct ceph_connection *con)
{
	int ret, to = 0;

	dout("read_partial_banner %p at %d\n", con, con->in_base_pos);

	/* peer's banner */
	ret = read_partial(con, &to, strlen(CEPH_BANNER), con->in_banner);
	if (ret <= 0)
		goto out;
	ret = read_partial(con, &to, sizeof(con->actual_peer_addr),
			   &con->actual_peer_addr);
	if (ret <= 0)
		goto out;
	ret = read_partial(con, &to, sizeof(con->peer_addr_for_me),
			   &con->peer_addr_for_me);
	if (ret <= 0)
		goto out;
out:
	return ret;
}

static int read_partial_connect(struct ceph_connection *con)
{
	int ret, to = 0;

	dout("read_partial_connect %p at %d\n", con, con->in_base_pos);

	ret = read_partial(con, &to, sizeof(con->in_reply), &con->in_reply);
	if (ret <= 0)
		goto out;
	ret = read_partial(con, &to, le32_to_cpu(con->in_reply.authorizer_len),
			   con->auth_reply_buf);
	if (ret <= 0)
		goto out;

	dout("read_partial_connect %p tag %d, con_seq = %u, g_seq = %u\n",
	     con, (int)con->in_reply.tag,
	     le32_to_cpu(con->in_reply.connect_seq),
	     le32_to_cpu(con->in_reply.global_seq));
out:
	return ret;

}

/*
 * Verify the hello banner looks okay.
 */
static int verify_hello(struct ceph_connection *con)
{
	if (memcmp(con->in_banner, CEPH_BANNER, strlen(CEPH_BANNER))) {
		pr_err("connect to %s got bad banner\n",
		       ceph_pr_addr(&con->peer_addr.in_addr));
		con->error_msg = "protocol error, bad banner";
		return -1;
	}
	return 0;
}

static bool addr_is_blank(struct sockaddr_storage *ss)
{
	switch (ss->ss_family) {
	case AF_INET:
		return ((struct sockaddr_in *)ss)->sin_addr.s_addr == 0;
	case AF_INET6:
		return
		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[0] == 0 &&
		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[1] == 0 &&
		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[2] == 0 &&
		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[3] == 0;
	}
	return false;
}

static int addr_port(struct sockaddr_storage *ss)
{
	switch (ss->ss_family) {
	case AF_INET:
		return ntohs(((struct sockaddr_in *)ss)->sin_port);
	case AF_INET6:
		return ntohs(((struct sockaddr_in6 *)ss)->sin6_port);
	}
	return 0;
}

static void addr_set_port(struct sockaddr_storage *ss, int p)
{
	switch (ss->ss_family) {
	case AF_INET:
		((struct sockaddr_in *)ss)->sin_port = htons(p);
	case AF_INET6:
		((struct sockaddr_in6 *)ss)->sin6_port = htons(p);
	}
}

/*
 * Parse an ip[:port] list into an addr array.  Use the default
 * monitor port if a port isn't specified.
 */
int ceph_parse_ips(const char *c, const char *end,
		   struct ceph_entity_addr *addr,
		   int max_count, int *count)
{
	int i;
	const char *p = c;

	dout("parse_ips on '%.*s'\n", (int)(end-c), c);
	for (i = 0; i < max_count; i++) {
		const char *ipend;
		struct sockaddr_storage *ss = &addr[i].in_addr;
		struct sockaddr_in *in4 = (void *)ss;
		struct sockaddr_in6 *in6 = (void *)ss;
		int port;
		char delim = ',';

		if (*p == '[') {
			delim = ']';
			p++;
		}

		memset(ss, 0, sizeof(*ss));
		if (in4_pton(p, end - p, (u8 *)&in4->sin_addr.s_addr,
			     delim, &ipend))
			ss->ss_family = AF_INET;
		else if (in6_pton(p, end - p, (u8 *)&in6->sin6_addr.s6_addr,
				  delim, &ipend))
			ss->ss_family = AF_INET6;
		else
			goto bad;
		p = ipend;

		if (delim == ']') {
			if (*p != ']') {
				dout("missing matching ']'\n");
				goto bad;
			}
			p++;
		}

		/* port? */
		if (p < end && *p == ':') {
			port = 0;
			p++;
			while (p < end && *p >= '0' && *p <= '9') {
				port = (port * 10) + (*p - '0');
				p++;
			}
			if (port > 65535 || port == 0)
				goto bad;
		} else {
			port = CEPH_MON_PORT;
		}

		addr_set_port(ss, port);

		dout("parse_ips got %s\n", ceph_pr_addr(ss));

		if (p == end)
			break;
		if (*p != ',')
			goto bad;
		p++;
	}

	if (p != end)
		goto bad;

	if (count)
		*count = i + 1;
	return 0;

bad:
	pr_err("parse_ips bad ip '%.*s'\n", (int)(end - c), c);
	return -EINVAL;
}
EXPORT_SYMBOL(ceph_parse_ips);

static int process_banner(struct ceph_connection *con)
{
	dout("process_banner on %p\n", con);

	if (verify_hello(con) < 0)
		return -1;

	ceph_decode_addr(&con->actual_peer_addr);
	ceph_decode_addr(&con->peer_addr_for_me);

	/*
	 * Make sure the other end is who we wanted.  note that the other
	 * end may not yet know their ip address, so if it's 0.0.0.0, give
	 * them the benefit of the doubt.
	 */
	if (memcmp(&con->peer_addr, &con->actual_peer_addr,
		   sizeof(con->peer_addr)) != 0 &&
	    !(addr_is_blank(&con->actual_peer_addr.in_addr) &&
	      con->actual_peer_addr.nonce == con->peer_addr.nonce)) {
		pr_warning("wrong peer, want %s/%d, got %s/%d\n",
			   ceph_pr_addr(&con->peer_addr.in_addr),
			   (int)le32_to_cpu(con->peer_addr.nonce),
			   ceph_pr_addr(&con->actual_peer_addr.in_addr),
			   (int)le32_to_cpu(con->actual_peer_addr.nonce));
		con->error_msg = "wrong peer at address";
		return -1;
	}

	/*
	 * did we learn our address?
	 */
	if (addr_is_blank(&con->msgr->inst.addr.in_addr)) {
		int port = addr_port(&con->msgr->inst.addr.in_addr);

		memcpy(&con->msgr->inst.addr.in_addr,
		       &con->peer_addr_for_me.in_addr,
		       sizeof(con->peer_addr_for_me.in_addr));
		addr_set_port(&con->msgr->inst.addr.in_addr, port);
		encode_my_addr(con->msgr);
		dout("process_banner learned my addr is %s\n",
		     ceph_pr_addr(&con->msgr->inst.addr.in_addr));
	}

	set_bit(NEGOTIATING, &con->state);
	prepare_read_connect(con);
	return 0;
}

static void fail_protocol(struct ceph_connection *con)
{
	reset_connection(con);
	set_bit(CLOSED, &con->state);  /* in case there's queued work */

	mutex_unlock(&con->mutex);
	if (con->ops->bad_proto)
		con->ops->bad_proto(con);
	mutex_lock(&con->mutex);
}

static int process_connect(struct ceph_connection *con)
{
	u64 sup_feat = con->msgr->supported_features;
	u64 req_feat = con->msgr->required_features;
	u64 server_feat = le64_to_cpu(con->in_reply.features);

	dout("process_connect on %p tag %d\n", con, (int)con->in_tag);

	switch (con->in_reply.tag) {
	case CEPH_MSGR_TAG_FEATURES:
		pr_err("%s%lld %s feature set mismatch,"
		       " my %llx < server's %llx, missing %llx\n",
		       ENTITY_NAME(con->peer_name),
		       ceph_pr_addr(&con->peer_addr.in_addr),
		       sup_feat, server_feat, server_feat & ~sup_feat);
		con->error_msg = "missing required protocol features";
		fail_protocol(con);
		return -1;

	case CEPH_MSGR_TAG_BADPROTOVER:
		pr_err("%s%lld %s protocol version mismatch,"
		       " my %d != server's %d\n",
		       ENTITY_NAME(con->peer_name),
		       ceph_pr_addr(&con->peer_addr.in_addr),
		       le32_to_cpu(con->out_connect.protocol_version),
		       le32_to_cpu(con->in_reply.protocol_version));
		con->error_msg = "protocol version mismatch";
		fail_protocol(con);
		return -1;

	case CEPH_MSGR_TAG_BADAUTHORIZER:
		con->auth_retry++;
		dout("process_connect %p got BADAUTHORIZER attempt %d\n", con,
		     con->auth_retry);
		if (con->auth_retry == 2) {
			con->error_msg = "connect authorization failure";
			reset_connection(con);
			set_bit(CLOSED, &con->state);
			return -1;
		}
		con->auth_retry = 1;
		prepare_write_connect(con->msgr, con, 0);
		prepare_read_connect(con);
		break;

	case CEPH_MSGR_TAG_RESETSESSION:
		/*
		 * If we connected with a large connect_seq but the peer
		 * has no record of a session with us (no connection, or
		 * connect_seq == 0), they will send RESETSESION to indicate
		 * that they must have reset their session, and may have
		 * dropped messages.
		 */
		dout("process_connect got RESET peer seq %u\n",
		     le32_to_cpu(con->in_connect.connect_seq));
		pr_err("%s%lld %s connection reset\n",
		       ENTITY_NAME(con->peer_name),
		       ceph_pr_addr(&con->peer_addr.in_addr));
		reset_connection(con);
		prepare_write_connect(con->msgr, con, 0);
		prepare_read_connect(con);

		/* Tell ceph about it. */
		mutex_unlock(&con->mutex);
		pr_info("reset on %s%lld\n", ENTITY_NAME(con->peer_name));
		if (con->ops->peer_reset)
			con->ops->peer_reset(con);
		mutex_lock(&con->mutex);
		break;

	case CEPH_MSGR_TAG_RETRY_SESSION:
		/*
		 * If we sent a smaller connect_seq than the peer has, try
		 * again with a larger value.
		 */
		dout("process_connect got RETRY my seq = %u, peer_seq = %u\n",
		     le32_to_cpu(con->out_connect.connect_seq),
		     le32_to_cpu(con->in_connect.connect_seq));
		con->connect_seq = le32_to_cpu(con->in_connect.connect_seq);
		prepare_write_connect(con->msgr, con, 0);
		prepare_read_connect(con);
		break;

	case CEPH_MSGR_TAG_RETRY_GLOBAL:
		/*
		 * If we sent a smaller global_seq than the peer has, try
		 * again with a larger value.
		 */
		dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n",
		     con->peer_global_seq,
		     le32_to_cpu(con->in_connect.global_seq));
		get_global_seq(con->msgr,
			       le32_to_cpu(con->in_connect.global_seq));
		prepare_write_connect(con->msgr, con, 0);
		prepare_read_connect(con);
		break;

	case CEPH_MSGR_TAG_READY:
		if (req_feat & ~server_feat) {
			pr_err("%s%lld %s protocol feature mismatch,"
			       " my required %llx > server's %llx, need %llx\n",
			       ENTITY_NAME(con->peer_name),
			       ceph_pr_addr(&con->peer_addr.in_addr),
			       req_feat, server_feat, req_feat & ~server_feat);
			con->error_msg = "missing required protocol features";
			fail_protocol(con);
			return -1;
		}
		clear_bit(CONNECTING, &con->state);
		con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq);
		con->connect_seq++;
		con->peer_features = server_feat;
		dout("process_connect got READY gseq %d cseq %d (%d)\n",
		     con->peer_global_seq,
		     le32_to_cpu(con->in_reply.connect_seq),
		     con->connect_seq);
		WARN_ON(con->connect_seq !=
			le32_to_cpu(con->in_reply.connect_seq));

		if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY)
			set_bit(LOSSYTX, &con->state);

		prepare_read_tag(con);
		break;

	case CEPH_MSGR_TAG_WAIT:
		/*
		 * If there is a connection race (we are opening
		 * connections to each other), one of us may just have
		 * to WAIT.  This shouldn't happen if we are the
		 * client.
		 */
		pr_err("process_connect peer connecting WAIT\n");

	default:
		pr_err("connect protocol error, will retry\n");
		con->error_msg = "protocol error, garbage tag during connect";
		return -1;
	}
	return 0;
}


/*
 * read (part of) an ack
 */
static int read_partial_ack(struct ceph_connection *con)
{
	int to = 0;

	return read_partial(con, &to, sizeof(con->in_temp_ack),
			    &con->in_temp_ack);
}


/*
 * We can finally discard anything that's been acked.
 */
static void process_ack(struct ceph_connection *con)
{
	struct ceph_msg *m;
	u64 ack = le64_to_cpu(con->in_temp_ack);
	u64 seq;

	while (!list_empty(&con->out_sent)) {
		m = list_first_entry(&con->out_sent, struct ceph_msg,
				     list_head);
		seq = le64_to_cpu(m->hdr.seq);
		if (seq > ack)
			break;
		dout("got ack for seq %llu type %d at %p\n", seq,
		     le16_to_cpu(m->hdr.type), m);
		ceph_msg_remove(m);
	}
	prepare_read_tag(con);
}




static int read_partial_message_section(struct ceph_connection *con,
					struct kvec *section,
					unsigned int sec_len, u32 *crc)
{
	int ret, left;

	BUG_ON(!section);

	while (section->iov_len < sec_len) {
		BUG_ON(section->iov_base == NULL);
		left = sec_len - section->iov_len;
		ret = ceph_tcp_recvmsg(con->sock, (char *)section->iov_base +
				       section->iov_len, left);
		if (ret <= 0)
			return ret;
		section->iov_len += ret;
		if (section->iov_len == sec_len)
			*crc = crc32c(0, section->iov_base,
				      section->iov_len);
	}

	return 1;
}

static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
				struct ceph_msg_header *hdr,
				int *skip);


static int read_partial_message_pages(struct ceph_connection *con,
				      struct page **pages,
				      unsigned data_len, int datacrc)
{
	void *p;
	int ret;
	int left;

	left = min((int)(data_len - con->in_msg_pos.data_pos),
		   (int)(PAGE_SIZE - con->in_msg_pos.page_pos));
	/* (page) data */
	BUG_ON(pages == NULL);
	p = kmap(pages[con->in_msg_pos.page]);
	ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos,
			       left);
	if (ret > 0 && datacrc)
		con->in_data_crc =
			crc32c(con->in_data_crc,
				  p + con->in_msg_pos.page_pos, ret);
	kunmap(pages[con->in_msg_pos.page]);
	if (ret <= 0)
		return ret;
	con->in_msg_pos.data_pos += ret;
	con->in_msg_pos.page_pos += ret;
	if (con->in_msg_pos.page_pos == PAGE_SIZE) {
		con->in_msg_pos.page_pos = 0;
		con->in_msg_pos.page++;
	}

	return ret;
}

#ifdef CONFIG_BLOCK
static int read_partial_message_bio(struct ceph_connection *con,
				    struct bio **bio_iter, int *bio_seg,
				    unsigned data_len, int datacrc)
{
	struct bio_vec *bv = bio_iovec_idx(*bio_iter, *bio_seg);
	void *p;
	int ret, left;

	if (IS_ERR(bv))
		return PTR_ERR(bv);

	left = min((int)(data_len - con->in_msg_pos.data_pos),
		   (int)(bv->bv_len - con->in_msg_pos.page_pos));

	p = kmap(bv->bv_page) + bv->bv_offset;

	ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos,
			       left);
	if (ret > 0 && datacrc)
		con->in_data_crc =
			crc32c(con->in_data_crc,
				  p + con->in_msg_pos.page_pos, ret);
	kunmap(bv->bv_page);
	if (ret <= 0)
		return ret;
	con->in_msg_pos.data_pos += ret;
	con->in_msg_pos.page_pos += ret;
	if (con->in_msg_pos.page_pos == bv->bv_len) {
		con->in_msg_pos.page_pos = 0;
		iter_bio_next(bio_iter, bio_seg);
	}

	return ret;
}
#endif

/*
 * read (part of) a message.
 */
static int read_partial_message(struct ceph_connection *con)
{
	struct ceph_msg *m = con->in_msg;
	int ret;
	int to, left;
	unsigned front_len, middle_len, data_len, data_off;
	int datacrc = con->msgr->nocrc;
	int skip;
	u64 seq;

	dout("read_partial_message con %p msg %p\n", con, m);

	/* header */
	while (con->in_base_pos < sizeof(con->in_hdr)) {
		left = sizeof(con->in_hdr) - con->in_base_pos;
		ret = ceph_tcp_recvmsg(con->sock,
				       (char *)&con->in_hdr + con->in_base_pos,
				       left);
		if (ret <= 0)
			return ret;
		con->in_base_pos += ret;
		if (con->in_base_pos == sizeof(con->in_hdr)) {
			u32 crc = crc32c(0, (void *)&con->in_hdr,
				 sizeof(con->in_hdr) - sizeof(con->in_hdr.crc));
			if (crc != le32_to_cpu(con->in_hdr.crc)) {
				pr_err("read_partial_message bad hdr "
				       " crc %u != expected %u\n",
				       crc, con->in_hdr.crc);
				return -EBADMSG;
			}
		}
	}
	front_len = le32_to_cpu(con->in_hdr.front_len);
	if (front_len > CEPH_MSG_MAX_FRONT_LEN)
		return -EIO;
	middle_len = le32_to_cpu(con->in_hdr.middle_len);
	if (middle_len > CEPH_MSG_MAX_DATA_LEN)
		return -EIO;
	data_len = le32_to_cpu(con->in_hdr.data_len);
	if (data_len > CEPH_MSG_MAX_DATA_LEN)
		return -EIO;
	data_off = le16_to_cpu(con->in_hdr.data_off);

	/* verify seq# */
	seq = le64_to_cpu(con->in_hdr.seq);
	if ((s64)seq - (s64)con->in_seq < 1) {
		pr_info("skipping %s%lld %s seq %lld, expected %lld\n",
			ENTITY_NAME(con->peer_name),
			ceph_pr_addr(&con->peer_addr.in_addr),
			seq, con->in_seq + 1);
		con->in_base_pos = -front_len - middle_len - data_len -
			sizeof(m->footer);
		con->in_tag = CEPH_MSGR_TAG_READY;
		con->in_seq++;
		return 0;
	} else if ((s64)seq - (s64)con->in_seq > 1) {
		pr_err("read_partial_message bad seq %lld expected %lld\n",
		       seq, con->in_seq + 1);
		con->error_msg = "bad message sequence # for incoming message";
		return -EBADMSG;
	}

	/* allocate message? */
	if (!con->in_msg) {
		dout("got hdr type %d front %d data %d\n", con->in_hdr.type,
		     con->in_hdr.front_len, con->in_hdr.data_len);
		skip = 0;
		con->in_msg = ceph_alloc_msg(con, &con->in_hdr, &skip);
		if (skip) {
			/* skip this message */
			dout("alloc_msg said skip message\n");
			BUG_ON(con->in_msg);
			con->in_base_pos = -front_len - middle_len - data_len -
				sizeof(m->footer);
			con->in_tag = CEPH_MSGR_TAG_READY;
			con->in_seq++;
			return 0;
		}
		if (!con->in_msg) {
			con->error_msg =
				"error allocating memory for incoming message";
			return -ENOMEM;
		}
		m = con->in_msg;
		m->front.iov_len = 0;    /* haven't read it yet */
		if (m->middle)
			m->middle->vec.iov_len = 0;

		con->in_msg_pos.page = 0;
		if (m->pages)
			con->in_msg_pos.page_pos = data_off & ~PAGE_MASK;
		else
			con->in_msg_pos.page_pos = 0;
		con->in_msg_pos.data_pos = 0;
	}

	/* front */
	ret = read_partial_message_section(con, &m->front, front_len,
					   &con->in_front_crc);
	if (ret <= 0)
		return ret;

	/* middle */
	if (m->middle) {
		ret = read_partial_message_section(con, &m->middle->vec,
						   middle_len,
						   &con->in_middle_crc);
		if (ret <= 0)
			return ret;
	}
#ifdef CONFIG_BLOCK
	if (m->bio && !m->bio_iter)
		init_bio_iter(m->bio, &m->bio_iter, &m->bio_seg);
#endif

	/* (page) data */
	while (con->in_msg_pos.data_pos < data_len) {
		if (m->pages) {
			ret = read_partial_message_pages(con, m->pages,
						 data_len, datacrc);
			if (ret <= 0)
				return ret;
#ifdef CONFIG_BLOCK
		} else if (m->bio) {

			ret = read_partial_message_bio(con,
						 &m->bio_iter, &m->bio_seg,
						 data_len, datacrc);
			if (ret <= 0)
				return ret;
#endif
		} else {
			BUG_ON(1);
		}
	}

	/* footer */
	to = sizeof(m->hdr) + sizeof(m->footer);
	while (con->in_base_pos < to) {
		left = to - con->in_base_pos;
		ret = ceph_tcp_recvmsg(con->sock, (char *)&m->footer +
				       (con->in_base_pos - sizeof(m->hdr)),
				       left);
		if (ret <= 0)
			return ret;
		con->in_base_pos += ret;
	}
	dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n",
	     m, front_len, m->footer.front_crc, middle_len,
	     m->footer.middle_crc, data_len, m->footer.data_crc);

	/* crc ok? */
	if (con->in_front_crc != le32_to_cpu(m->footer.front_crc)) {
		pr_err("read_partial_message %p front crc %u != exp. %u\n",
		       m, con->in_front_crc, m->footer.front_crc);
		return -EBADMSG;
	}
	if (con->in_middle_crc != le32_to_cpu(m->footer.middle_crc)) {
		pr_err("read_partial_message %p middle crc %u != exp %u\n",
		       m, con->in_middle_crc, m->footer.middle_crc);
		return -EBADMSG;
	}
	if (datacrc &&
	    (m->footer.flags & CEPH_MSG_FOOTER_NOCRC) == 0 &&
	    con->in_data_crc != le32_to_cpu(m->footer.data_crc)) {
		pr_err("read_partial_message %p data crc %u != exp. %u\n", m,
		       con->in_data_crc, le32_to_cpu(m->footer.data_crc));
		return -EBADMSG;
	}

	return 1; /* done! */
}

/*
 * Process message.  This happens in the worker thread.  The callback should
 * be careful not to do anything that waits on other incoming messages or it
 * may deadlock.
 */
static void process_message(struct ceph_connection *con)
{
	struct ceph_msg *msg;

	msg = con->in_msg;
	con->in_msg = NULL;

	/* if first message, set peer_name */
	if (con->peer_name.type == 0)
		con->peer_name = msg->hdr.src;

	con->in_seq++;
	mutex_unlock(&con->mutex);

	dout("===== %p %llu from %s%lld %d=%s len %d+%d (%u %u %u) =====\n",
	     msg, le64_to_cpu(msg->hdr.seq),
	     ENTITY_NAME(msg->hdr.src),
	     le16_to_cpu(msg->hdr.type),
	     ceph_msg_type_name(le16_to_cpu(msg->hdr.type)),
	     le32_to_cpu(msg->hdr.front_len),
	     le32_to_cpu(msg->hdr.data_len),
	     con->in_front_crc, con->in_middle_crc, con->in_data_crc);
	con->ops->dispatch(con, msg);

	mutex_lock(&con->mutex);
	prepare_read_tag(con);
}


/*
 * Write something to the socket.  Called in a worker thread when the
 * socket appears to be writeable and we have something ready to send.
 */
static int try_write(struct ceph_connection *con)
{
	struct ceph_messenger *msgr = con->msgr;
	int ret = 1;

	dout("try_write start %p state %lu nref %d\n", con, con->state,
	     atomic_read(&con->nref));

more:
	dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes);

	/* open the socket first? */
	if (con->sock == NULL) {
		/*
		 * if we were STANDBY and are reconnecting _this_
		 * connection, bump connect_seq now.  Always bump
		 * global_seq.
		 */
		if (test_and_clear_bit(STANDBY, &con->state))
			con->connect_seq++;

		prepare_write_banner(msgr, con);
		prepare_write_connect(msgr, con, 1);
		prepare_read_banner(con);
		set_bit(CONNECTING, &con->state);
		clear_bit(NEGOTIATING, &con->state);

		BUG_ON(con->in_msg);
		con->in_tag = CEPH_MSGR_TAG_READY;
		dout("try_write initiating connect on %p new state %lu\n",
		     con, con->state);
		con->sock = ceph_tcp_connect(con);
		if (IS_ERR(con->sock)) {
			con->sock = NULL;
			con->error_msg = "connect error";
			ret = -1;
			goto out;
		}
	}

more_kvec:
	/* kvec data queued? */
	if (con->out_skip) {
		ret = write_partial_skip(con);
		if (ret <= 0)
			goto done;
		if (ret < 0) {
			dout("try_write write_partial_skip err %d\n", ret);
			goto done;
		}
	}
	if (con->out_kvec_left) {
		ret = write_partial_kvec(con);
		if (ret <= 0)
			goto done;
	}

	/* msg pages? */
	if (con->out_msg) {
		if (con->out_msg_done) {
			ceph_msg_put(con->out_msg);
			con->out_msg = NULL;   /* we're done with this one */
			goto do_next;
		}

		ret = write_partial_msg_pages(con);
		if (ret == 1)
			goto more_kvec;  /* we need to send the footer, too! */
		if (ret == 0)
			goto done;
		if (ret < 0) {
			dout("try_write write_partial_msg_pages err %d\n",
			     ret);
			goto done;
		}
	}

do_next:
	if (!test_bit(CONNECTING, &con->state)) {
		/* is anything else pending? */
		if (!list_empty(&con->out_queue)) {
			prepare_write_message(con);
			goto more;
		}
		if (con->in_seq > con->in_seq_acked) {
			prepare_write_ack(con);
			goto more;
		}
		if (test_and_clear_bit(KEEPALIVE_PENDING, &con->state)) {
			prepare_write_keepalive(con);
			goto more;
		}
	}

	/* Nothing to do! */
	clear_bit(WRITE_PENDING, &con->state);
	dout("try_write nothing else to write.\n");
done:
	ret = 0;
out:
	dout("try_write done on %p\n", con);
	return ret;
}



/*
 * Read what we can from the socket.
 */
static int try_read(struct ceph_connection *con)
{
	int ret = -1;

	if (!con->sock)
		return 0;

	if (test_bit(STANDBY, &con->state))
		return 0;

	dout("try_read start on %p\n", con);

more:
	dout("try_read tag %d in_base_pos %d\n", (int)con->in_tag,
	     con->in_base_pos);
	if (test_bit(CONNECTING, &con->state)) {
		if (!test_bit(NEGOTIATING, &con->state)) {
			dout("try_read connecting\n");
			ret = read_partial_banner(con);
			if (ret <= 0)
				goto done;
			if (process_banner(con) < 0) {
				ret = -1;
				goto out;
			}
		}
		ret = read_partial_connect(con);
		if (ret <= 0)
			goto done;
		if (process_connect(con) < 0) {
			ret = -1;
			goto out;
		}
		goto more;
	}

	if (con->in_base_pos < 0) {
		/*
		 * skipping + discarding content.
		 *
		 * FIXME: there must be a better way to do this!
		 */
		static char buf[1024];
		int skip = min(1024, -con->in_base_pos);
		dout("skipping %d / %d bytes\n", skip, -con->in_base_pos);
		ret = ceph_tcp_recvmsg(con->sock, buf, skip);
		if (ret <= 0)
			goto done;
		con->in_base_pos += ret;
		if (con->in_base_pos)
			goto more;
	}
	if (con->in_tag == CEPH_MSGR_TAG_READY) {
		/*
		 * what's next?
		 */
		ret = ceph_tcp_recvmsg(con->sock, &con->in_tag, 1);
		if (ret <= 0)
			goto done;
		dout("try_read got tag %d\n", (int)con->in_tag);
		switch (con->in_tag) {
		case CEPH_MSGR_TAG_MSG:
			prepare_read_message(con);
			break;
		case CEPH_MSGR_TAG_ACK:
			prepare_read_ack(con);
			break;
		case CEPH_MSGR_TAG_CLOSE:
			set_bit(CLOSED, &con->state);   /* fixme */
			goto done;
		default:
			goto bad_tag;
		}
	}
	if (con->in_tag == CEPH_MSGR_TAG_MSG) {
		ret = read_partial_message(con);
		if (ret <= 0) {
			switch (ret) {
			case -EBADMSG:
				con->error_msg = "bad crc";
				ret = -EIO;
				goto out;
			case -EIO:
				con->error_msg = "io error";
				goto out;
			default:
				goto done;
			}
		}
		if (con->in_tag == CEPH_MSGR_TAG_READY)
			goto more;
		process_message(con);
		goto more;
	}
	if (con->in_tag == CEPH_MSGR_TAG_ACK) {
		ret = read_partial_ack(con);
		if (ret <= 0)
			goto done;
		process_ack(con);
		goto more;
	}

done:
	ret = 0;
out:
	dout("try_read done on %p\n", con);
	return ret;

bad_tag:
	pr_err("try_read bad con->in_tag = %d\n", (int)con->in_tag);
	con->error_msg = "protocol error, garbage tag";
	ret = -1;
	goto out;
}


/*
 * Atomically queue work on a connection.  Bump @con reference to
 * avoid races with connection teardown.
 *
 * There is some trickery going on with QUEUED and BUSY because we
 * only want a _single_ thread operating on each connection at any
 * point in time, but we want to use all available CPUs.
 *
 * The worker thread only proceeds if it can atomically set BUSY.  It
 * clears QUEUED and does it's thing.  When it thinks it's done, it
 * clears BUSY, then rechecks QUEUED.. if it's set again, it loops
 * (tries again to set BUSY).
 *
 * To queue work, we first set QUEUED, _then_ if BUSY isn't set, we
 * try to queue work.  If that fails (work is already queued, or BUSY)
 * we give up (work also already being done or is queued) but leave QUEUED
 * set so that the worker thread will loop if necessary.
 */
static void queue_con(struct ceph_connection *con)
{
	if (test_bit(DEAD, &con->state)) {
		dout("queue_con %p ignoring: DEAD\n",
		     con);
		return;
	}

	if (!con->ops->get(con)) {
		dout("queue_con %p ref count 0\n", con);
		return;
	}

	set_bit(QUEUED, &con->state);
	if (test_bit(BUSY, &con->state)) {
		dout("queue_con %p - already BUSY\n", con);
		con->ops->put(con);
	} else if (!queue_work(ceph_msgr_wq, &con->work.work)) {
		dout("queue_con %p - already queued\n", con);
		con->ops->put(con);
	} else {
		dout("queue_con %p\n", con);
	}
}

/*
 * Do some work on a connection.  Drop a connection ref when we're done.
 */
static void con_work(struct work_struct *work)
{
	struct ceph_connection *con = container_of(work, struct ceph_connection,
						   work.work);
	int backoff = 0;

more:
	if (test_and_set_bit(BUSY, &con->state) != 0) {
		dout("con_work %p BUSY already set\n", con);
		goto out;
	}
	dout("con_work %p start, clearing QUEUED\n", con);
	clear_bit(QUEUED, &con->state);

	mutex_lock(&con->mutex);

	if (test_bit(CLOSED, &con->state)) { /* e.g. if we are replaced */
		dout("con_work CLOSED\n");
		con_close_socket(con);
		goto done;
	}
	if (test_and_clear_bit(OPENING, &con->state)) {
		/* reopen w/ new peer */
		dout("con_work OPENING\n");
		con_close_socket(con);
	}

	if (test_and_clear_bit(SOCK_CLOSED, &con->state) ||
	    try_read(con) < 0 ||
	    try_write(con) < 0) {
		mutex_unlock(&con->mutex);
		backoff = 1;
		ceph_fault(con);     /* error/fault path */
		goto done_unlocked;
	}

done:
	mutex_unlock(&con->mutex);

done_unlocked:
	clear_bit(BUSY, &con->state);
	dout("con->state=%lu\n", con->state);
	if (test_bit(QUEUED, &con->state)) {
		if (!backoff || test_bit(OPENING, &con->state)) {
			dout("con_work %p QUEUED reset, looping\n", con);
			goto more;
		}
		dout("con_work %p QUEUED reset, but just faulted\n", con);
		clear_bit(QUEUED, &con->state);
	}
	dout("con_work %p done\n", con);

out:
	con->ops->put(con);
}


/*
 * Generic error/fault handler.  A retry mechanism is used with
 * exponential backoff
 */
static void ceph_fault(struct ceph_connection *con)
{
	pr_err("%s%lld %s %s\n", ENTITY_NAME(con->peer_name),
	       ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg);
	dout("fault %p state %lu to peer %s\n",
	     con, con->state, ceph_pr_addr(&con->peer_addr.in_addr));

	if (test_bit(LOSSYTX, &con->state)) {
		dout("fault on LOSSYTX channel\n");
		goto out;
	}

	mutex_lock(&con->mutex);
	if (test_bit(CLOSED, &con->state))
		goto out_unlock;

	con_close_socket(con);

	if (con->in_msg) {
		ceph_msg_put(con->in_msg);
		con->in_msg = NULL;
	}

	/* Requeue anything that hasn't been acked */
	list_splice_init(&con->out_sent, &con->out_queue);

	/* If there are no messages in the queue, place the connection
	 * in a STANDBY state (i.e., don't try to reconnect just yet). */
	if (list_empty(&con->out_queue) && !con->out_keepalive_pending) {
		dout("fault setting STANDBY\n");
		set_bit(STANDBY, &con->state);
	} else {
		/* retry after a delay. */
		if (con->delay == 0)
			con->delay = BASE_DELAY_INTERVAL;
		else if (con->delay < MAX_DELAY_INTERVAL)
			con->delay *= 2;
		dout("fault queueing %p delay %lu\n", con, con->delay);
		con->ops->get(con);
		if (queue_delayed_work(ceph_msgr_wq, &con->work,
				       round_jiffies_relative(con->delay)) == 0)
			con->ops->put(con);
	}

out_unlock:
	mutex_unlock(&con->mutex);
out:
	/*
	 * in case we faulted due to authentication, invalidate our
	 * current tickets so that we can get new ones.
	 */
	if (con->auth_retry && con->ops->invalidate_authorizer) {
		dout("calling invalidate_authorizer()\n");
		con->ops->invalidate_authorizer(con);
	}

	if (con->ops->fault)
		con->ops->fault(con);
}



/*
 * create a new messenger instance
 */
struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr,
					     u32 supported_features,
					     u32 required_features)
{
	struct ceph_messenger *msgr;

	msgr = kzalloc(sizeof(*msgr), GFP_KERNEL);
	if (msgr == NULL)
		return ERR_PTR(-ENOMEM);

	msgr->supported_features = supported_features;
	msgr->required_features = required_features;

	spin_lock_init(&msgr->global_seq_lock);

	/* the zero page is needed if a request is "canceled" while the message
	 * is being written over the socket */
	msgr->zero_page = __page_cache_alloc(GFP_KERNEL | __GFP_ZERO);
	if (!msgr->zero_page) {
		kfree(msgr);
		return ERR_PTR(-ENOMEM);
	}
	kmap(msgr->zero_page);

	if (myaddr)
		msgr->inst.addr = *myaddr;

	/* select a random nonce */
	msgr->inst.addr.type = 0;
	get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce));
	encode_my_addr(msgr);

	dout("messenger_create %p\n", msgr);
	return msgr;
}
EXPORT_SYMBOL(ceph_messenger_create);

void ceph_messenger_destroy(struct ceph_messenger *msgr)
{
	dout("destroy %p\n", msgr);
	kunmap(msgr->zero_page);
	__free_page(msgr->zero_page);
	kfree(msgr);
	dout("destroyed messenger %p\n", msgr);
}
EXPORT_SYMBOL(ceph_messenger_destroy);

/*
 * Queue up an outgoing message on the given connection.
 */
void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
{
	if (test_bit(CLOSED, &con->state)) {
		dout("con_send %p closed, dropping %p\n", con, msg);
		ceph_msg_put(msg);
		return;
	}

	/* set src+dst */
	msg->hdr.src = con->msgr->inst.name;

	BUG_ON(msg->front.iov_len != le32_to_cpu(msg->hdr.front_len));

	msg->needs_out_seq = true;

	/* queue */
	mutex_lock(&con->mutex);
	BUG_ON(!list_empty(&msg->list_head));
	list_add_tail(&msg->list_head, &con->out_queue);
	dout("----- %p to %s%lld %d=%s len %d+%d+%d -----\n", msg,
	     ENTITY_NAME(con->peer_name), le16_to_cpu(msg->hdr.type),
	     ceph_msg_type_name(le16_to_cpu(msg->hdr.type)),
	     le32_to_cpu(msg->hdr.front_len),
	     le32_to_cpu(msg->hdr.middle_len),
	     le32_to_cpu(msg->hdr.data_len));
	mutex_unlock(&con->mutex);

	/* if there wasn't anything waiting to send before, queue
	 * new work */
	if (test_and_set_bit(WRITE_PENDING, &con->state) == 0)
		queue_con(con);
}
EXPORT_SYMBOL(ceph_con_send);

/*
 * Revoke a message that was previously queued for send
 */
void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg)
{
	mutex_lock(&con->mutex);
	if (!list_empty(&msg->list_head)) {
		dout("con_revoke %p msg %p - was on queue\n", con, msg);
		list_del_init(&msg->list_head);
		ceph_msg_put(msg);
		msg->hdr.seq = 0;
	}
	if (con->out_msg == msg) {
		dout("con_revoke %p msg %p - was sending\n", con, msg);
		con->out_msg = NULL;
		if (con->out_kvec_is_msg) {
			con->out_skip = con->out_kvec_bytes;
			con->out_kvec_is_msg = false;
		}
		ceph_msg_put(msg);
		msg->hdr.seq = 0;
	}
	mutex_unlock(&con->mutex);
}

/*
 * Revoke a message that we may be reading data into
 */
void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg)
{
	mutex_lock(&con->mutex);
	if (con->in_msg && con->in_msg == msg) {
		unsigned front_len = le32_to_cpu(con->in_hdr.front_len);
		unsigned middle_len = le32_to_cpu(con->in_hdr.middle_len);
		unsigned data_len = le32_to_cpu(con->in_hdr.data_len);

		/* skip rest of message */
		dout("con_revoke_pages %p msg %p revoked\n", con, msg);
			con->in_base_pos = con->in_base_pos -
				sizeof(struct ceph_msg_header) -
				front_len -
				middle_len -
				data_len -
				sizeof(struct ceph_msg_footer);
		ceph_msg_put(con->in_msg);
		con->in_msg = NULL;
		con->in_tag = CEPH_MSGR_TAG_READY;
		con->in_seq++;
	} else {
		dout("con_revoke_pages %p msg %p pages %p no-op\n",
		     con, con->in_msg, msg);
	}
	mutex_unlock(&con->mutex);
}

/*
 * Queue a keepalive byte to ensure the tcp connection is alive.
 */
void ceph_con_keepalive(struct ceph_connection *con)
{
	if (test_and_set_bit(KEEPALIVE_PENDING, &con->state) == 0 &&
	    test_and_set_bit(WRITE_PENDING, &con->state) == 0)
		queue_con(con);
}
EXPORT_SYMBOL(ceph_con_keepalive);


/*
 * construct a new message with given type, size
 * the new msg has a ref count of 1.
 */
struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags)
{
	struct ceph_msg *m;

	m = kmalloc(sizeof(*m), flags);
	if (m == NULL)
		goto out;
	kref_init(&m->kref);
	INIT_LIST_HEAD(&m->list_head);

	m->hdr.tid = 0;
	m->hdr.type = cpu_to_le16(type);
	m->hdr.priority = cpu_to_le16(CEPH_MSG_PRIO_DEFAULT);
	m->hdr.version = 0;
	m->hdr.front_len = cpu_to_le32(front_len);
	m->hdr.middle_len = 0;
	m->hdr.data_len = 0;
	m->hdr.data_off = 0;
	m->hdr.reserved = 0;
	m->footer.front_crc = 0;
	m->footer.middle_crc = 0;
	m->footer.data_crc = 0;
	m->footer.flags = 0;
	m->front_max = front_len;
	m->front_is_vmalloc = false;
	m->more_to_follow = false;
	m->pool = NULL;

	/* front */
	if (front_len) {
		if (front_len > PAGE_CACHE_SIZE) {
			m->front.iov_base = __vmalloc(front_len, flags,
						      PAGE_KERNEL);
			m->front_is_vmalloc = true;
		} else {
			m->front.iov_base = kmalloc(front_len, flags);
		}
		if (m->front.iov_base == NULL) {
			pr_err("msg_new can't allocate %d bytes\n",
			     front_len);
			goto out2;
		}
	} else {
		m->front.iov_base = NULL;
	}
	m->front.iov_len = front_len;

	/* middle */
	m->middle = NULL;

	/* data */
	m->nr_pages = 0;
	m->pages = NULL;
	m->pagelist = NULL;
	m->bio = NULL;
	m->bio_iter = NULL;
	m->bio_seg = 0;
	m->trail = NULL;

	dout("ceph_msg_new %p front %d\n", m, front_len);
	return m;

out2:
	ceph_msg_put(m);
out:
	pr_err("msg_new can't create type %d front %d\n", type, front_len);
	return NULL;
}
EXPORT_SYMBOL(ceph_msg_new);

/*
 * Allocate "middle" portion of a message, if it is needed and wasn't
 * allocated by alloc_msg.  This allows us to read a small fixed-size
 * per-type header in the front and then gracefully fail (i.e.,
 * propagate the error to the caller based on info in the front) when
 * the middle is too large.
 */
static int ceph_alloc_middle(struct ceph_connection *con, struct ceph_msg *msg)
{
	int type = le16_to_cpu(msg->hdr.type);
	int middle_len = le32_to_cpu(msg->hdr.middle_len);

	dout("alloc_middle %p type %d %s middle_len %d\n", msg, type,
	     ceph_msg_type_name(type), middle_len);
	BUG_ON(!middle_len);
	BUG_ON(msg->middle);

	msg->middle = ceph_buffer_new(middle_len, GFP_NOFS);
	if (!msg->middle)
		return -ENOMEM;
	return 0;
}

/*
 * Generic message allocator, for incoming messages.
 */
static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
				struct ceph_msg_header *hdr,
				int *skip)
{
	int type = le16_to_cpu(hdr->type);
	int front_len = le32_to_cpu(hdr->front_len);
	int middle_len = le32_to_cpu(hdr->middle_len);
	struct ceph_msg *msg = NULL;
	int ret;

	if (con->ops->alloc_msg) {
		mutex_unlock(&con->mutex);
		msg = con->ops->alloc_msg(con, hdr, skip);
		mutex_lock(&con->mutex);
		if (!msg || *skip)
			return NULL;
	}
	if (!msg) {
		*skip = 0;
		msg = ceph_msg_new(type, front_len, GFP_NOFS);
		if (!msg) {
			pr_err("unable to allocate msg type %d len %d\n",
			       type, front_len);
			return NULL;
		}
	}
	memcpy(&msg->hdr, &con->in_hdr, sizeof(con->in_hdr));

	if (middle_len && !msg->middle) {
		ret = ceph_alloc_middle(con, msg);
		if (ret < 0) {
			ceph_msg_put(msg);
			return NULL;
		}
	}

	return msg;
}


/*
 * Free a generically kmalloc'd message.
 */
void ceph_msg_kfree(struct ceph_msg *m)
{
	dout("msg_kfree %p\n", m);
	if (m->front_is_vmalloc)
		vfree(m->front.iov_base);
	else
		kfree(m->front.iov_base);
	kfree(m);
}

/*
 * Drop a msg ref.  Destroy as needed.
 */
void ceph_msg_last_put(struct kref *kref)
{
	struct ceph_msg *m = container_of(kref, struct ceph_msg, kref);

	dout("ceph_msg_put last one on %p\n", m);
	WARN_ON(!list_empty(&m->list_head));

	/* drop middle, data, if any */
	if (m->middle) {
		ceph_buffer_put(m->middle);
		m->middle = NULL;
	}
	m->nr_pages = 0;
	m->pages = NULL;

	if (m->pagelist) {
		ceph_pagelist_release(m->pagelist);
		kfree(m->pagelist);
		m->pagelist = NULL;
	}

	m->trail = NULL;

	if (m->pool)
		ceph_msgpool_put(m->pool, m);
	else
		ceph_msg_kfree(m);
}
EXPORT_SYMBOL(ceph_msg_last_put);

void ceph_msg_dump(struct ceph_msg *msg)
{
	pr_debug("msg_dump %p (front_max %d nr_pages %d)\n", msg,
		 msg->front_max, msg->nr_pages);
	print_hex_dump(KERN_DEBUG, "header: ",
		       DUMP_PREFIX_OFFSET, 16, 1,
		       &msg->hdr, sizeof(msg->hdr), true);
	print_hex_dump(KERN_DEBUG, " front: ",
		       DUMP_PREFIX_OFFSET, 16, 1,
		       msg->front.iov_base, msg->front.iov_len, true);
	if (msg->middle)
		print_hex_dump(KERN_DEBUG, "middle: ",
			       DUMP_PREFIX_OFFSET, 16, 1,
			       msg->middle->vec.iov_base,
			       msg->middle->vec.iov_len, true);
	print_hex_dump(KERN_DEBUG, "footer: ",
		       DUMP_PREFIX_OFFSET, 16, 1,
		       &msg->footer, sizeof(msg->footer), true);
}
EXPORT_SYMBOL(ceph_msg_dump);