aboutsummaryrefslogtreecommitdiffstats
path: root/gcc-4.9/gcc/tree-ssa-threadupdate.c
blob: c2f02a6ab8ecc54325d6f31c27cdd9c35c5ae930 (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
/* Thread edges through blocks and update the control flow and SSA graphs.
   Copyright (C) 2004-2014 Free Software Foundation, Inc.

This file is part of GCC.

GCC 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 3, or (at your option)
any later version.

GCC is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with GCC; see the file COPYING3.  If not see
<http://www.gnu.org/licenses/>.  */

#include "config.h"
#include "system.h"
#include "coretypes.h"
#include "tree.h"
#include "flags.h"
#include "basic-block.h"
#include "function.h"
#include "hash-table.h"
#include "tree-ssa-alias.h"
#include "internal-fn.h"
#include "gimple-expr.h"
#include "is-a.h"
#include "gimple.h"
#include "gimple-iterator.h"
#include "gimple-ssa.h"
#include "tree-phinodes.h"
#include "tree-ssa.h"
#include "tree-ssa-threadupdate.h"
#include "ssa-iterators.h"
#include "dumpfile.h"
#include "cfgloop.h"
#include "dbgcnt.h"
#include "tree-cfg.h"
#include "tree-pass.h"

/* Given a block B, update the CFG and SSA graph to reflect redirecting
   one or more in-edges to B to instead reach the destination of an
   out-edge from B while preserving any side effects in B.

   i.e., given A->B and B->C, change A->B to be A->C yet still preserve the
   side effects of executing B.

     1. Make a copy of B (including its outgoing edges and statements).  Call
	the copy B'.  Note B' has no incoming edges or PHIs at this time.

     2. Remove the control statement at the end of B' and all outgoing edges
	except B'->C.

     3. Add a new argument to each PHI in C with the same value as the existing
	argument associated with edge B->C.  Associate the new PHI arguments
	with the edge B'->C.

     4. For each PHI in B, find or create a PHI in B' with an identical
	PHI_RESULT.  Add an argument to the PHI in B' which has the same
	value as the PHI in B associated with the edge A->B.  Associate
	the new argument in the PHI in B' with the edge A->B.

     5. Change the edge A->B to A->B'.

	5a. This automatically deletes any PHI arguments associated with the
	    edge A->B in B.

	5b. This automatically associates each new argument added in step 4
	    with the edge A->B'.

     6. Repeat for other incoming edges into B.

     7. Put the duplicated resources in B and all the B' blocks into SSA form.

   Note that block duplication can be minimized by first collecting the
   set of unique destination blocks that the incoming edges should
   be threaded to.

   We reduce the number of edges and statements we create by not copying all
   the outgoing edges and the control statement in step #1.  We instead create
   a template block without the outgoing edges and duplicate the template.

   Another case this code handles is threading through a "joiner" block.  In
   this case, we do not know the destination of the joiner block, but one
   of the outgoing edges from the joiner block leads to a threadable path.  This
   case largely works as outlined above, except the duplicate of the joiner
   block still contains a full set of outgoing edges and its control statement.
   We just redirect one of its outgoing edges to our jump threading path.  */


/* Steps #5 and #6 of the above algorithm are best implemented by walking
   all the incoming edges which thread to the same destination edge at
   the same time.  That avoids lots of table lookups to get information
   for the destination edge.

   To realize that implementation we create a list of incoming edges
   which thread to the same outgoing edge.  Thus to implement steps
   #5 and #6 we traverse our hash table of outgoing edge information.
   For each entry we walk the list of incoming edges which thread to
   the current outgoing edge.  */

struct el
{
  edge e;
  struct el *next;
};

/* Main data structure recording information regarding B's duplicate
   blocks.  */

/* We need to efficiently record the unique thread destinations of this
   block and specific information associated with those destinations.  We
   may have many incoming edges threaded to the same outgoing edge.  This
   can be naturally implemented with a hash table.  */

struct redirection_data : typed_free_remove<redirection_data>
{
  /* We support wiring up two block duplicates in a jump threading path.

     One is a normal block copy where we remove the control statement
     and wire up its single remaining outgoing edge to the thread path.

     The other is a joiner block where we leave the control statement
     in place, but wire one of the outgoing edges to a thread path.

     In theory we could have multiple block duplicates in a jump
     threading path, but I haven't tried that.

     The duplicate blocks appear in this array in the same order in
     which they appear in the jump thread path.  */
  basic_block dup_blocks[2];

  /* The jump threading path.  */
  vec<jump_thread_edge *> *path;

  /* A list of incoming edges which we want to thread to the
     same path.  */
  struct el *incoming_edges;

  /* hash_table support.  */
  typedef redirection_data value_type;
  typedef redirection_data compare_type;
  static inline hashval_t hash (const value_type *);
  static inline int equal (const value_type *, const compare_type *);
};

/* Dump a jump threading path, including annotations about each
   edge in the path.  */

static void
dump_jump_thread_path (FILE *dump_file, vec<jump_thread_edge *> path,
		       bool registering)
{
  fprintf (dump_file,
	   "  %s%s jump thread: (%d, %d) incoming edge; ",
	   (registering ? "Registering" : "Cancelling"),
	   (path[0]->type == EDGE_FSM_THREAD ? " FSM": ""),
	   path[0]->e->src->index, path[0]->e->dest->index);

  for (unsigned int i = 1; i < path.length (); i++)
    {
      /* We can get paths with a NULL edge when the final destination
	 of a jump thread turns out to be a constant address.  We dump
	 those paths when debugging, so we have to be prepared for that
	 possibility here.  */
      if (path[i]->e == NULL)
	continue;

      if (path[i]->type == EDGE_COPY_SRC_JOINER_BLOCK)
	fprintf (dump_file, " (%d, %d) joiner; ",
		 path[i]->e->src->index, path[i]->e->dest->index);
      if (path[i]->type == EDGE_COPY_SRC_BLOCK)
       fprintf (dump_file, " (%d, %d) normal;",
		 path[i]->e->src->index, path[i]->e->dest->index);
      if (path[i]->type == EDGE_NO_COPY_SRC_BLOCK)
       fprintf (dump_file, " (%d, %d) nocopy;",
		 path[i]->e->src->index, path[i]->e->dest->index);
    }
  fputc ('\n', dump_file);
}

/* Simple hashing function.  For any given incoming edge E, we're going
   to be most concerned with the final destination of its jump thread
   path.  So hash on the block index of the final edge in the path.  */

inline hashval_t
redirection_data::hash (const value_type *p)
{
  vec<jump_thread_edge *> *path = p->path;
  return path->last ()->e->dest->index;
}

/* Given two hash table entries, return true if they have the same
   jump threading path.  */
inline int
redirection_data::equal (const value_type *p1, const compare_type *p2)
{
  vec<jump_thread_edge *> *path1 = p1->path;
  vec<jump_thread_edge *> *path2 = p2->path;

  if (path1->length () != path2->length ())
    return false;

  for (unsigned int i = 1; i < path1->length (); i++)
    {
      if ((*path1)[i]->type != (*path2)[i]->type
	  || (*path1)[i]->e != (*path2)[i]->e)
	return false;
    }

  return true;
}

/* Data structure of information to pass to hash table traversal routines.  */
struct ssa_local_info_t
{
  /* The current block we are working on.  */
  basic_block bb;

  /* We only create a template block for the first duplicated block in a
     jump threading path as we may need many duplicates of that block.

     The second duplicate block in a path is specific to that path.  Creating
     and sharing a template for that block is considerably more difficult.  */
  basic_block template_block;

  /* TRUE if we thread one or more jumps, FALSE otherwise.  */
  bool jumps_threaded;
};

/* Passes which use the jump threading code register jump threading
   opportunities as they are discovered.  We keep the registered
   jump threading opportunities in this vector as edge pairs
   (original_edge, target_edge).  */
static vec<vec<jump_thread_edge *> *> paths;

/* When we start updating the CFG for threading, data necessary for jump
   threading is attached to the AUX field for the incoming edge.  Use these
   macros to access the underlying structure attached to the AUX field.  */
#define THREAD_PATH(E) ((vec<jump_thread_edge *> *)(E)->aux)

/* Jump threading statistics.  */

struct thread_stats_d
{
  unsigned long num_threaded_edges;
};

struct thread_stats_d thread_stats;


/* Remove the last statement in block BB if it is a control statement
   Also remove all outgoing edges except the edge which reaches DEST_BB.
   If DEST_BB is NULL, then remove all outgoing edges.  */

static void
remove_ctrl_stmt_and_useless_edges (basic_block bb, basic_block dest_bb)
{
  gimple_stmt_iterator gsi;
  edge e;
  edge_iterator ei;

  gsi = gsi_last_bb (bb);

  /* If the duplicate ends with a control statement, then remove it.

     Note that if we are duplicating the template block rather than the
     original basic block, then the duplicate might not have any real
     statements in it.  */
  if (!gsi_end_p (gsi)
      && gsi_stmt (gsi)
      && (gimple_code (gsi_stmt (gsi)) == GIMPLE_COND
	  || gimple_code (gsi_stmt (gsi)) == GIMPLE_GOTO
	  || gimple_code (gsi_stmt (gsi)) == GIMPLE_SWITCH))
    gsi_remove (&gsi, true);

  for (ei = ei_start (bb->succs); (e = ei_safe_edge (ei)); )
    {
      if (e->dest != dest_bb)
	remove_edge (e);
      else
	ei_next (&ei);
    }
}

/* Create a duplicate of BB.  Record the duplicate block in an array
   indexed by COUNT stored in RD.  */

static void
create_block_for_threading (basic_block bb,
			    struct redirection_data *rd,
			    unsigned int count)
{
  edge_iterator ei;
  edge e;

  /* We can use the generic block duplication code and simply remove
     the stuff we do not need.  */
  rd->dup_blocks[count] = duplicate_block (bb, NULL, NULL);

  FOR_EACH_EDGE (e, ei, rd->dup_blocks[count]->succs)
    e->aux = NULL;

  /* Zero out the profile, since the block is unreachable for now.  */
  rd->dup_blocks[count]->frequency = 0;
  rd->dup_blocks[count]->count = 0;
}

/* Main data structure to hold information for duplicates of BB.  */

static hash_table <redirection_data> redirection_data;

/* Given an outgoing edge E lookup and return its entry in our hash table.

   If INSERT is true, then we insert the entry into the hash table if
   it is not already present.  INCOMING_EDGE is added to the list of incoming
   edges associated with E in the hash table.  */

static struct redirection_data *
lookup_redirection_data (edge e, enum insert_option insert)
{
  struct redirection_data **slot;
  struct redirection_data *elt;
  vec<jump_thread_edge *> *path = THREAD_PATH (e);

 /* Build a hash table element so we can see if E is already
     in the table.  */
  elt = XNEW (struct redirection_data);
  elt->path = path;
  elt->dup_blocks[0] = NULL;
  elt->dup_blocks[1] = NULL;
  elt->incoming_edges = NULL;

  slot = redirection_data.find_slot (elt, insert);

  /* This will only happen if INSERT is false and the entry is not
     in the hash table.  */
  if (slot == NULL)
    {
      free (elt);
      return NULL;
    }

  /* This will only happen if E was not in the hash table and
     INSERT is true.  */
  if (*slot == NULL)
    {
      *slot = elt;
      elt->incoming_edges = XNEW (struct el);
      elt->incoming_edges->e = e;
      elt->incoming_edges->next = NULL;
      return elt;
    }
  /* E was in the hash table.  */
  else
    {
      /* Free ELT as we do not need it anymore, we will extract the
	 relevant entry from the hash table itself.  */
      free (elt);

      /* Get the entry stored in the hash table.  */
      elt = *slot;

      /* If insertion was requested, then we need to add INCOMING_EDGE
	 to the list of incoming edges associated with E.  */
      if (insert)
	{
	  struct el *el = XNEW (struct el);
	  el->next = elt->incoming_edges;
	  el->e = e;
	  elt->incoming_edges = el;
	}

      return elt;
    }
}

/* Similar to copy_phi_args, except that the PHI arg exists, it just
   does not have a value associated with it.  */

static void
copy_phi_arg_into_existing_phi (edge src_e, edge tgt_e)
{
  int src_idx = src_e->dest_idx;
  int tgt_idx = tgt_e->dest_idx;

  /* Iterate over each PHI in e->dest.  */
  for (gimple_stmt_iterator gsi = gsi_start_phis (src_e->dest),
			    gsi2 = gsi_start_phis (tgt_e->dest);
       !gsi_end_p (gsi);
       gsi_next (&gsi), gsi_next (&gsi2))
    {
      gimple src_phi = gsi_stmt (gsi);
      gimple dest_phi = gsi_stmt (gsi2);
      tree val = gimple_phi_arg_def (src_phi, src_idx);
      source_location locus = gimple_phi_arg_location (src_phi, src_idx);

      SET_PHI_ARG_DEF (dest_phi, tgt_idx, val);
      gimple_phi_arg_set_location (dest_phi, tgt_idx, locus);
    }
}

/* For each PHI in BB, copy the argument associated with SRC_E to TGT_E.  */

static void
copy_phi_args (basic_block bb, edge src_e, edge tgt_e)
{
  gimple_stmt_iterator gsi;
  int src_indx = src_e->dest_idx;

  for (gsi = gsi_start_phis (bb); !gsi_end_p (gsi); gsi_next (&gsi))
    {
      gimple phi = gsi_stmt (gsi);
      source_location locus = gimple_phi_arg_location (phi, src_indx);
      add_phi_arg (phi, gimple_phi_arg_def (phi, src_indx), tgt_e, locus);
    }
}

/* We have recently made a copy of ORIG_BB, including its outgoing
   edges.  The copy is NEW_BB.  Every PHI node in every direct successor of
   ORIG_BB has a new argument associated with edge from NEW_BB to the
   successor.  Initialize the PHI argument so that it is equal to the PHI
   argument associated with the edge from ORIG_BB to the successor.  */

static void
update_destination_phis (basic_block orig_bb, basic_block new_bb)
{
  edge_iterator ei;
  edge e;

  FOR_EACH_EDGE (e, ei, orig_bb->succs)
    {
      edge e2 = find_edge (new_bb, e->dest);
      copy_phi_args (e->dest, e, e2);
    }
}

/* Given a duplicate block and its single destination (both stored
   in RD).  Create an edge between the duplicate and its single
   destination.

   Add an additional argument to any PHI nodes at the single
   destination.  */

static void
create_edge_and_update_destination_phis (struct redirection_data *rd,
					 basic_block bb)
{
  edge e = make_edge (bb, rd->path->last ()->e->dest, EDGE_FALLTHRU);

  rescan_loop_exit (e, true, false);
  e->probability = REG_BR_PROB_BASE;
  e->count = bb->count;

  /* We used to copy the thread path here.  That was added in 2007
     and dutifully updated through the representation changes in 2013.

     In 2013 we added code to thread from an interior node through
     the backedge to another interior node.  That runs after the code
     to thread through loop headers from outside the loop.

     The latter may delete edges in the CFG, including those
     which appeared in the jump threading path we copied here.  Thus
     we'd end up using a dangling pointer.

     After reviewing the 2007/2011 code, I can't see how anything
     depended on copying the AUX field and clearly copying the jump
     threading path is problematical due to embedded edge pointers.
     It has been removed.  */
  e->aux = NULL;

  /* If there are any PHI nodes at the destination of the outgoing edge
     from the duplicate block, then we will need to add a new argument
     to them.  The argument should have the same value as the argument
     associated with the outgoing edge stored in RD.  */
  copy_phi_args (e->dest, rd->path->last ()->e, e);
}

/* Look through PATH beginning at START and return TRUE if there are
   any additional blocks that need to be duplicated.  Otherwise,
   return FALSE.  */
static bool
any_remaining_duplicated_blocks (vec<jump_thread_edge *> *path,
				 unsigned int start)
{
  for (unsigned int i = start + 1; i < path->length (); i++)
    {
      if ((*path)[i]->type == EDGE_COPY_SRC_JOINER_BLOCK
	  || (*path)[i]->type == EDGE_COPY_SRC_BLOCK)
	return true;
    }
  return false;
}

/* Wire up the outgoing edges from the duplicate blocks and
   update any PHIs as needed.  */
void
ssa_fix_duplicate_block_edges (struct redirection_data *rd,
			       ssa_local_info_t *local_info)
{
  edge e = rd->incoming_edges->e;
  vec<jump_thread_edge *> *path = THREAD_PATH (e);

  for (unsigned int count = 0, i = 1; i < path->length (); i++)
    {
      /* If we were threading through an joiner block, then we want
	 to keep its control statement and redirect an outgoing edge.
	 Else we want to remove the control statement & edges, then create
	 a new outgoing edge.  In both cases we may need to update PHIs.  */
      if ((*path)[i]->type == EDGE_COPY_SRC_JOINER_BLOCK)
	{
	  edge victim;
	  edge e2;

	  /* This updates the PHIs at the destination of the duplicate
	     block.  */
	  update_destination_phis (local_info->bb, rd->dup_blocks[count]);

	  /* Find the edge from the duplicate block to the block we're
	     threading through.  That's the edge we want to redirect.  */
	  victim = find_edge (rd->dup_blocks[count], (*path)[i]->e->dest);

	  /* If there are no remaining blocks on the path to duplicate,
	     then redirect VICTIM to the final destination of the jump
	     threading path.  */
	  if (!any_remaining_duplicated_blocks (path, i))
	    {
	      e2 = redirect_edge_and_branch (victim, path->last ()->e->dest);
	      e2->count = path->last ()->e->count;
	      /* If we redirected the edge, then we need to copy PHI arguments
		 at the target.  If the edge already existed (e2 != victim
		 case), then the PHIs in the target already have the correct
		 arguments.  */
	      if (e2 == victim)
		copy_phi_args (e2->dest, path->last ()->e, e2);
	    }
	  else
	    {
	      /* Redirect VICTIM to the next duplicated block in the path.  */
	      e2 = redirect_edge_and_branch (victim, rd->dup_blocks[count + 1]);

	      /* We need to update the PHIs in the next duplicated block.  We
		 want the new PHI args to have the same value as they had
		 in the source of the next duplicate block.

		 Thus, we need to know which edge we traversed into the
		 source of the duplicate.  Furthermore, we may have
		 traversed many edges to reach the source of the duplicate.

		 Walk through the path starting at element I until we
		 hit an edge marked with EDGE_COPY_SRC_BLOCK.  We want
		 the edge from the prior element.  */
	      for (unsigned int j = i + 1; j < path->length (); j++)
		{
		  if ((*path)[j]->type == EDGE_COPY_SRC_BLOCK)
		    {
		      copy_phi_arg_into_existing_phi ((*path)[j - 1]->e, e2);
		      break;
		    }
		}
	    }
	  count++;
	}
      else if ((*path)[i]->type == EDGE_COPY_SRC_BLOCK)
	{
	  remove_ctrl_stmt_and_useless_edges (rd->dup_blocks[count], NULL);
	  create_edge_and_update_destination_phis (rd, rd->dup_blocks[count]);
	  if (count == 1)
	    single_succ_edge (rd->dup_blocks[1])->aux = NULL;
	  count++;
	}
    }
}

/* Hash table traversal callback routine to create duplicate blocks.  */

int
ssa_create_duplicates (struct redirection_data **slot,
		       ssa_local_info_t *local_info)
{
  struct redirection_data *rd = *slot;

  /* The second duplicated block in a jump threading path is specific
     to the path.  So it gets stored in RD rather than in LOCAL_DATA.

     Each time we're called, we have to look through the path and see
     if a second block needs to be duplicated.

     Note the search starts with the third edge on the path.  The first
     edge is the incoming edge, the second edge always has its source
     duplicated.  Thus we start our search with the third edge.  */
  vec<jump_thread_edge *> *path = rd->path;
  for (unsigned int i = 2; i < path->length (); i++)
    {
      if ((*path)[i]->type == EDGE_COPY_SRC_BLOCK
	  || (*path)[i]->type == EDGE_COPY_SRC_JOINER_BLOCK)
	{
	  create_block_for_threading ((*path)[i]->e->src, rd, 1);
	  break;
	}
    }

  /* Create a template block if we have not done so already.  Otherwise
     use the template to create a new block.  */
  if (local_info->template_block == NULL)
    {
      create_block_for_threading ((*path)[1]->e->src, rd, 0);
      local_info->template_block = rd->dup_blocks[0];

      /* We do not create any outgoing edges for the template.  We will
	 take care of that in a later traversal.  That way we do not
	 create edges that are going to just be deleted.  */
    }
  else
    {
      create_block_for_threading (local_info->template_block, rd, 0);

      /* Go ahead and wire up outgoing edges and update PHIs for the duplicate
	 block.   */
      ssa_fix_duplicate_block_edges (rd, local_info);
    }

  /* Keep walking the hash table.  */
  return 1;
}

/* We did not create any outgoing edges for the template block during
   block creation.  This hash table traversal callback creates the
   outgoing edge for the template block.  */

inline int
ssa_fixup_template_block (struct redirection_data **slot,
			  ssa_local_info_t *local_info)
{
  struct redirection_data *rd = *slot;

  /* If this is the template block halt the traversal after updating
     it appropriately.

     If we were threading through an joiner block, then we want
     to keep its control statement and redirect an outgoing edge.
     Else we want to remove the control statement & edges, then create
     a new outgoing edge.  In both cases we may need to update PHIs.  */
  if (rd->dup_blocks[0] && rd->dup_blocks[0] == local_info->template_block)
    {
      ssa_fix_duplicate_block_edges (rd, local_info);
      return 0;
    }

  return 1;
}

/* Hash table traversal callback to redirect each incoming edge
   associated with this hash table element to its new destination.  */

int
ssa_redirect_edges (struct redirection_data **slot,
		    ssa_local_info_t *local_info)
{
  struct redirection_data *rd = *slot;
  struct el *next, *el;

  /* Walk over all the incoming edges associated associated with this
     hash table entry.  */
  for (el = rd->incoming_edges; el; el = next)
    {
      edge e = el->e;
      vec<jump_thread_edge *> *path = THREAD_PATH (e);

      /* Go ahead and free this element from the list.  Doing this now
	 avoids the need for another list walk when we destroy the hash
	 table.  */
      next = el->next;
      free (el);

      thread_stats.num_threaded_edges++;

      if (rd->dup_blocks[0])
	{
	  edge e2;

	  if (dump_file && (dump_flags & TDF_DETAILS))
	    fprintf (dump_file, "  Threaded jump %d --> %d to %d\n",
		     e->src->index, e->dest->index, rd->dup_blocks[0]->index);

	  rd->dup_blocks[0]->count += e->count;

	  /* Excessive jump threading may make frequencies large enough so
	     the computation overflows.  */
	  if (rd->dup_blocks[0]->frequency < BB_FREQ_MAX * 2)
	    rd->dup_blocks[0]->frequency += EDGE_FREQUENCY (e);

	  /* In the case of threading through a joiner block, the outgoing
	     edges from the duplicate block were updated when they were
	     redirected during ssa_fix_duplicate_block_edges.  */
	  if ((*path)[1]->type != EDGE_COPY_SRC_JOINER_BLOCK)
	    EDGE_SUCC (rd->dup_blocks[0], 0)->count += e->count;

	  /* Redirect the incoming edge (possibly to the joiner block) to the
	     appropriate duplicate block.  */
	  e2 = redirect_edge_and_branch (e, rd->dup_blocks[0]);
	  gcc_assert (e == e2);
	  flush_pending_stmts (e2);
	}

      /* Go ahead and clear E->aux.  It's not needed anymore and failure
	 to clear it will cause all kinds of unpleasant problems later.  */
      delete_jump_thread_path (path);
      e->aux = NULL;

    }

  /* Indicate that we actually threaded one or more jumps.  */
  if (rd->incoming_edges)
    local_info->jumps_threaded = true;

  return 1;
}

/* Return true if this block has no executable statements other than
   a simple ctrl flow instruction.  When the number of outgoing edges
   is one, this is equivalent to a "forwarder" block.  */

static bool
redirection_block_p (basic_block bb)
{
  gimple_stmt_iterator gsi;

  /* Advance to the first executable statement.  */
  gsi = gsi_start_bb (bb);
  while (!gsi_end_p (gsi)
	 && (gimple_code (gsi_stmt (gsi)) == GIMPLE_LABEL
	     || is_gimple_debug (gsi_stmt (gsi))
	     || gimple_nop_p (gsi_stmt (gsi))))
    gsi_next (&gsi);

  /* Check if this is an empty block.  */
  if (gsi_end_p (gsi))
    return true;

  /* Test that we've reached the terminating control statement.  */
  return gsi_stmt (gsi)
	 && (gimple_code (gsi_stmt (gsi)) == GIMPLE_COND
	     || gimple_code (gsi_stmt (gsi)) == GIMPLE_GOTO
	     || gimple_code (gsi_stmt (gsi)) == GIMPLE_SWITCH);
}

/* BB is a block which ends with a COND_EXPR or SWITCH_EXPR and when BB
   is reached via one or more specific incoming edges, we know which
   outgoing edge from BB will be traversed.

   We want to redirect those incoming edges to the target of the
   appropriate outgoing edge.  Doing so avoids a conditional branch
   and may expose new optimization opportunities.  Note that we have
   to update dominator tree and SSA graph after such changes.

   The key to keeping the SSA graph update manageable is to duplicate
   the side effects occurring in BB so that those side effects still
   occur on the paths which bypass BB after redirecting edges.

   We accomplish this by creating duplicates of BB and arranging for
   the duplicates to unconditionally pass control to one specific
   successor of BB.  We then revector the incoming edges into BB to
   the appropriate duplicate of BB.

   If NOLOOP_ONLY is true, we only perform the threading as long as it
   does not affect the structure of the loops in a nontrivial way.

   If JOINERS is true, then thread through joiner blocks as well.  */

static bool
thread_block_1 (basic_block bb, bool noloop_only, bool joiners)
{
  /* E is an incoming edge into BB that we may or may not want to
     redirect to a duplicate of BB.  */
  edge e, e2;
  edge_iterator ei;
  ssa_local_info_t local_info;
  struct loop *loop = bb->loop_father;

  /* To avoid scanning a linear array for the element we need we instead
     use a hash table.  For normal code there should be no noticeable
     difference.  However, if we have a block with a large number of
     incoming and outgoing edges such linear searches can get expensive.  */
  redirection_data.create (EDGE_COUNT (bb->succs));

  /* If we thread the latch of the loop to its exit, the loop ceases to
     exist.  Make sure we do not restrict ourselves in order to preserve
     this loop.  */
  if (loop->header == bb)
    {
      e = loop_latch_edge (loop);
      vec<jump_thread_edge *> *path = THREAD_PATH (e);

      if (path
	  && (((*path)[1]->type == EDGE_COPY_SRC_JOINER_BLOCK && joiners)
	      || ((*path)[1]->type == EDGE_COPY_SRC_BLOCK && !joiners)))
	{
	  for (unsigned int i = 1; i < path->length (); i++)
	    {
	      edge e2 = (*path)[i]->e;

	      if (loop_exit_edge_p (loop, e2))
		{
		  loop->header = NULL;
		  loop->latch = NULL;
		  loops_state_set (LOOPS_NEED_FIXUP);
		}
	    }
	}
    }

  /* Record each unique threaded destination into a hash table for
     efficient lookups.  */
  FOR_EACH_EDGE (e, ei, bb->preds)
    {
      if (e->aux == NULL)
	continue;

      vec<jump_thread_edge *> *path = THREAD_PATH (e);

      if (((*path)[1]->type == EDGE_COPY_SRC_JOINER_BLOCK && !joiners)
	  || ((*path)[1]->type == EDGE_COPY_SRC_BLOCK && joiners))
	continue;

      e2 = path->last ()->e;
      if (!e2 || noloop_only)
	{
	  /* If NOLOOP_ONLY is true, we only allow threading through the
	     header of a loop to exit edges.  */

	  /* One case occurs when there was loop header buried in a jump
	     threading path that crosses loop boundaries.  We do not try
	     and thread this elsewhere, so just cancel the jump threading
	     request by clearing the AUX field now.  */
	  if ((bb->loop_father != e2->src->loop_father
	       && !loop_exit_edge_p (e2->src->loop_father, e2))
	      || (e2->src->loop_father != e2->dest->loop_father
		  && !loop_exit_edge_p (e2->src->loop_father, e2)))
	    {
	      /* Since this case is not handled by our special code
		 to thread through a loop header, we must explicitly
		 cancel the threading request here.  */
	      delete_jump_thread_path (path);
	      e->aux = NULL;
	      continue;
	    }

	  /* Another case occurs when trying to thread through our
	     own loop header, possibly from inside the loop.  We will
	     thread these later.  */
	  unsigned int i;
	  for (i = 1; i < path->length (); i++)
	    {
	      if ((*path)[i]->e->src == bb->loop_father->header
		  && (!loop_exit_edge_p (bb->loop_father, e2)
		      || (*path)[1]->type == EDGE_COPY_SRC_JOINER_BLOCK))
		break;
	    }

	  if (i != path->length ())
	    continue;
	}

      if (e->dest == e2->src)
	update_bb_profile_for_threading (e->dest, EDGE_FREQUENCY (e),
					 e->count, (*THREAD_PATH (e))[1]->e);

      /* Insert the outgoing edge into the hash table if it is not
	 already in the hash table.  */
      lookup_redirection_data (e, INSERT);
    }

  /* We do not update dominance info.  */
  free_dominance_info (CDI_DOMINATORS);

  /* We know we only thread through the loop header to loop exits.
     Let the basic block duplication hook know we are not creating
     a multiple entry loop.  */
  if (noloop_only
      && bb == bb->loop_father->header)
    set_loop_copy (bb->loop_father, loop_outer (bb->loop_father));

  /* Now create duplicates of BB.

     Note that for a block with a high outgoing degree we can waste
     a lot of time and memory creating and destroying useless edges.

     So we first duplicate BB and remove the control structure at the
     tail of the duplicate as well as all outgoing edges from the
     duplicate.  We then use that duplicate block as a template for
     the rest of the duplicates.  */
  local_info.template_block = NULL;
  local_info.bb = bb;
  local_info.jumps_threaded = false;
  redirection_data.traverse <ssa_local_info_t *, ssa_create_duplicates>
			    (&local_info);

  /* The template does not have an outgoing edge.  Create that outgoing
     edge and update PHI nodes as the edge's target as necessary.

     We do this after creating all the duplicates to avoid creating
     unnecessary edges.  */
  redirection_data.traverse <ssa_local_info_t *, ssa_fixup_template_block>
			    (&local_info);

  /* The hash table traversals above created the duplicate blocks (and the
     statements within the duplicate blocks).  This loop creates PHI nodes for
     the duplicated blocks and redirects the incoming edges into BB to reach
     the duplicates of BB.  */
  redirection_data.traverse <ssa_local_info_t *, ssa_redirect_edges>
			    (&local_info);

  /* Done with this block.  Clear REDIRECTION_DATA.  */
  redirection_data.dispose ();

  if (noloop_only
      && bb == bb->loop_father->header)
    set_loop_copy (bb->loop_father, NULL);

  /* Indicate to our caller whether or not any jumps were threaded.  */
  return local_info.jumps_threaded;
}

/* Wrapper for thread_block_1 so that we can first handle jump
   thread paths which do not involve copying joiner blocks, then
   handle jump thread paths which have joiner blocks.

   By doing things this way we can be as aggressive as possible and
   not worry that copying a joiner block will create a jump threading
   opportunity.  */

static bool
thread_block (basic_block bb, bool noloop_only)
{
  bool retval;
  retval = thread_block_1 (bb, noloop_only, false);
  retval |= thread_block_1 (bb, noloop_only, true);
  return retval;
}


/* Threads edge E through E->dest to the edge THREAD_TARGET (E).  Returns the
   copy of E->dest created during threading, or E->dest if it was not necessary
   to copy it (E is its single predecessor).  */

static basic_block
thread_single_edge (edge e)
{
  basic_block bb = e->dest;
  struct redirection_data rd;
  vec<jump_thread_edge *> *path = THREAD_PATH (e);
  edge eto = (*path)[1]->e;

  for (unsigned int i = 0; i < path->length (); i++)
    delete (*path)[i];
  delete path;
  e->aux = NULL;

  thread_stats.num_threaded_edges++;

  if (single_pred_p (bb))
    {
      /* If BB has just a single predecessor, we should only remove the
	 control statements at its end, and successors except for ETO.  */
      remove_ctrl_stmt_and_useless_edges (bb, eto->dest);

      /* And fixup the flags on the single remaining edge.  */
      eto->flags &= ~(EDGE_TRUE_VALUE | EDGE_FALSE_VALUE | EDGE_ABNORMAL);
      eto->flags |= EDGE_FALLTHRU;

      return bb;
    }

  /* Otherwise, we need to create a copy.  */
  if (e->dest == eto->src)
    update_bb_profile_for_threading (bb, EDGE_FREQUENCY (e), e->count, eto);

  vec<jump_thread_edge *> *npath = new vec<jump_thread_edge *> ();
  jump_thread_edge *x = new jump_thread_edge (e, EDGE_START_JUMP_THREAD);
  npath->safe_push (x);

  x = new jump_thread_edge (eto, EDGE_COPY_SRC_BLOCK);
  npath->safe_push (x);
  rd.path = npath;

  create_block_for_threading (bb, &rd, 0);
  remove_ctrl_stmt_and_useless_edges (rd.dup_blocks[0], NULL);
  create_edge_and_update_destination_phis (&rd, rd.dup_blocks[0]);

  if (dump_file && (dump_flags & TDF_DETAILS))
    fprintf (dump_file, "  Threaded jump %d --> %d to %d\n",
	     e->src->index, e->dest->index, rd.dup_blocks[0]->index);

  rd.dup_blocks[0]->count = e->count;
  rd.dup_blocks[0]->frequency = EDGE_FREQUENCY (e);
  single_succ_edge (rd.dup_blocks[0])->count = e->count;
  redirect_edge_and_branch (e, rd.dup_blocks[0]);
  flush_pending_stmts (e);

  return rd.dup_blocks[0];
}

/* Callback for dfs_enumerate_from.  Returns true if BB is different
   from STOP and DBDS_CE_STOP.  */

static basic_block dbds_ce_stop;
static bool
dbds_continue_enumeration_p (const_basic_block bb, const void *stop)
{
  return (bb != (const_basic_block) stop
	  && bb != dbds_ce_stop);
}

/* Evaluates the dominance relationship of latch of the LOOP and BB, and
   returns the state.  */

enum bb_dom_status
{
  /* BB does not dominate latch of the LOOP.  */
  DOMST_NONDOMINATING,
  /* The LOOP is broken (there is no path from the header to its latch.  */
  DOMST_LOOP_BROKEN,
  /* BB dominates the latch of the LOOP.  */
  DOMST_DOMINATING
};

static enum bb_dom_status
determine_bb_domination_status (struct loop *loop, basic_block bb)
{
  basic_block *bblocks;
  unsigned nblocks, i;
  bool bb_reachable = false;
  edge_iterator ei;
  edge e;

  /* This function assumes BB is a successor of LOOP->header.
     If that is not the case return DOMST_NONDOMINATING which
     is always safe.  */
    {
      bool ok = false;

      FOR_EACH_EDGE (e, ei, bb->preds)
	{
     	  if (e->src == loop->header)
	    {
	      ok = true;
	      break;
	    }
	}

      if (!ok)
	return DOMST_NONDOMINATING;
    }

  if (bb == loop->latch)
    return DOMST_DOMINATING;

  /* Check that BB dominates LOOP->latch, and that it is back-reachable
     from it.  */

  bblocks = XCNEWVEC (basic_block, loop->num_nodes);
  dbds_ce_stop = loop->header;
  nblocks = dfs_enumerate_from (loop->latch, 1, dbds_continue_enumeration_p,
				bblocks, loop->num_nodes, bb);
  for (i = 0; i < nblocks; i++)
    FOR_EACH_EDGE (e, ei, bblocks[i]->preds)
      {
	if (e->src == loop->header)
	  {
	    free (bblocks);
	    return DOMST_NONDOMINATING;
	  }
	if (e->src == bb)
	  bb_reachable = true;
      }

  free (bblocks);
  return (bb_reachable ? DOMST_DOMINATING : DOMST_LOOP_BROKEN);
}

/* Return true if BB is part of the new pre-header that is created
   when threading the latch to DATA.  */

static bool
def_split_header_continue_p (const_basic_block bb, const void *data)
{
  const_basic_block new_header = (const_basic_block) data;
  const struct loop *l;

  if (bb == new_header
      || loop_depth (bb->loop_father) < loop_depth (new_header->loop_father))
    return false;
  for (l = bb->loop_father; l; l = loop_outer (l))
    if (l == new_header->loop_father)
      return true;
  return false;
}

/* Thread jumps through the header of LOOP.  Returns true if cfg changes.
   If MAY_PEEL_LOOP_HEADERS is false, we avoid threading from entry edges
   to the inside of the loop.  */

static bool
thread_through_loop_header (struct loop *loop, bool may_peel_loop_headers)
{
  basic_block header = loop->header;
  edge e, tgt_edge, latch = loop_latch_edge (loop);
  edge_iterator ei;
  basic_block tgt_bb, atgt_bb;
  enum bb_dom_status domst;

  /* We have already threaded through headers to exits, so all the threading
     requests now are to the inside of the loop.  We need to avoid creating
     irreducible regions (i.e., loops with more than one entry block), and
     also loop with several latch edges, or new subloops of the loop (although
     there are cases where it might be appropriate, it is difficult to decide,
     and doing it wrongly may confuse other optimizers).

     We could handle more general cases here.  However, the intention is to
     preserve some information about the loop, which is impossible if its
     structure changes significantly, in a way that is not well understood.
     Thus we only handle few important special cases, in which also updating
     of the loop-carried information should be feasible:

     1) Propagation of latch edge to a block that dominates the latch block
	of a loop.  This aims to handle the following idiom:

	first = 1;
	while (1)
	  {
	    if (first)
	      initialize;
	    first = 0;
	    body;
	  }

	After threading the latch edge, this becomes

	first = 1;
	if (first)
	  initialize;
	while (1)
	  {
	    first = 0;
	    body;
	  }

	The original header of the loop is moved out of it, and we may thread
	the remaining edges through it without further constraints.

     2) All entry edges are propagated to a single basic block that dominates
	the latch block of the loop.  This aims to handle the following idiom
	(normally created for "for" loops):

	i = 0;
	while (1)
	  {
	    if (i >= 100)
	      break;
	    body;
	    i++;
	  }

	This becomes

	i = 0;
	while (1)
	  {
	    body;
	    i++;
	    if (i >= 100)
	      break;
	  }
     */

  /* Threading through the header won't improve the code if the header has just
     one successor.  */
  if (single_succ_p (header))
    goto fail;

  /* If we threaded the latch using a joiner block, we cancel the
     threading opportunity out of an abundance of caution.  However,
     still allow threading from outside to inside the loop.  */
  if (latch->aux)
    {
      vec<jump_thread_edge *> *path = THREAD_PATH (latch);
      if ((*path)[1]->type == EDGE_COPY_SRC_JOINER_BLOCK)
	{
	  delete_jump_thread_path (path);
	  latch->aux = NULL;
	}
    }

  if (latch->aux)
    {
      vec<jump_thread_edge *> *path = THREAD_PATH (latch);
      tgt_edge = (*path)[1]->e;
      tgt_bb = tgt_edge->dest;
    }
  else if (!may_peel_loop_headers
	   && !redirection_block_p (loop->header))
    goto fail;
  else
    {
      tgt_bb = NULL;
      tgt_edge = NULL;
      FOR_EACH_EDGE (e, ei, header->preds)
	{
	  if (!e->aux)
	    {
	      if (e == latch)
		continue;

	      /* If latch is not threaded, and there is a header
		 edge that is not threaded, we would create loop
		 with multiple entries.  */
	      goto fail;
	    }

	  vec<jump_thread_edge *> *path = THREAD_PATH (e);

	  if ((*path)[1]->type == EDGE_COPY_SRC_JOINER_BLOCK)
	    goto fail;
	  tgt_edge = (*path)[1]->e;
	  atgt_bb = tgt_edge->dest;
	  if (!tgt_bb)
	    tgt_bb = atgt_bb;
	  /* Two targets of threading would make us create loop
	     with multiple entries.  */
	  else if (tgt_bb != atgt_bb)
	    goto fail;
	}

      if (!tgt_bb)
	{
	  /* There are no threading requests.  */
	  return false;
	}

      /* Redirecting to empty loop latch is useless.  */
      if (tgt_bb == loop->latch
	  && empty_block_p (loop->latch))
	goto fail;
    }

  /* The target block must dominate the loop latch, otherwise we would be
     creating a subloop.  */
  domst = determine_bb_domination_status (loop, tgt_bb);
  if (domst == DOMST_NONDOMINATING)
    goto fail;
  if (domst == DOMST_LOOP_BROKEN)
    {
      /* If the loop ceased to exist, mark it as such, and thread through its
	 original header.  */
      loop->header = NULL;
      loop->latch = NULL;
      loops_state_set (LOOPS_NEED_FIXUP);
      return thread_block (header, false);
    }

  if (tgt_bb->loop_father->header == tgt_bb)
    {
      /* If the target of the threading is a header of a subloop, we need
	 to create a preheader for it, so that the headers of the two loops
	 do not merge.  */
      if (EDGE_COUNT (tgt_bb->preds) > 2)
	{
	  tgt_bb = create_preheader (tgt_bb->loop_father, 0);
	  gcc_assert (tgt_bb != NULL);
	}
      else
	tgt_bb = split_edge (tgt_edge);
    }

  if (latch->aux)
    {
      basic_block *bblocks;
      unsigned nblocks, i;

      /* First handle the case latch edge is redirected.  We are copying
	 the loop header but not creating a multiple entry loop.  Make the
	 cfg manipulation code aware of that fact.  */
      set_loop_copy (loop, loop);
      loop->latch = thread_single_edge (latch);
      set_loop_copy (loop, NULL);
      gcc_assert (single_succ (loop->latch) == tgt_bb);
      loop->header = tgt_bb;

      /* Remove the new pre-header blocks from our loop.  */
      bblocks = XCNEWVEC (basic_block, loop->num_nodes);
      nblocks = dfs_enumerate_from (header, 0, def_split_header_continue_p,
				    bblocks, loop->num_nodes, tgt_bb);
      for (i = 0; i < nblocks; i++)
	if (bblocks[i]->loop_father == loop)
	  {
	    remove_bb_from_loops (bblocks[i]);
	    add_bb_to_loop (bblocks[i], loop_outer (loop));
	  }
      free (bblocks);

      /* If the new header has multiple latches mark it so.  */
      FOR_EACH_EDGE (e, ei, loop->header->preds)
	if (e->src->loop_father == loop
	    && e->src != loop->latch)
	  {
	    loop->latch = NULL;
	    loops_state_set (LOOPS_MAY_HAVE_MULTIPLE_LATCHES);
	  }

      /* Cancel remaining threading requests that would make the
	 loop a multiple entry loop.  */
      FOR_EACH_EDGE (e, ei, header->preds)
	{
	  edge e2;

	  if (e->aux == NULL)
	    continue;

	  vec<jump_thread_edge *> *path = THREAD_PATH (e);
	  e2 = path->last ()->e;

	  if (e->src->loop_father != e2->dest->loop_father
	      && e2->dest != loop->header)
	    {
	      delete_jump_thread_path (path);
	      e->aux = NULL;
	    }
	}

      /* Thread the remaining edges through the former header.  */
      thread_block (header, false);
    }
  else
    {
      basic_block new_preheader;

      /* Now consider the case entry edges are redirected to the new entry
	 block.  Remember one entry edge, so that we can find the new
	 preheader (its destination after threading).  */
      FOR_EACH_EDGE (e, ei, header->preds)
	{
	  if (e->aux)
	    break;
	}

      /* The duplicate of the header is the new preheader of the loop.  Ensure
	 that it is placed correctly in the loop hierarchy.  */
      set_loop_copy (loop, loop_outer (loop));

      thread_block (header, false);
      set_loop_copy (loop, NULL);
      new_preheader = e->dest;

      /* Create the new latch block.  This is always necessary, as the latch
	 must have only a single successor, but the original header had at
	 least two successors.  */
      loop->latch = NULL;
      mfb_kj_edge = single_succ_edge (new_preheader);
      loop->header = mfb_kj_edge->dest;
      latch = make_forwarder_block (tgt_bb, mfb_keep_just, NULL);
      loop->header = latch->dest;
      loop->latch = latch->src;
    }

  return true;

fail:
  /* We failed to thread anything.  Cancel the requests.  */
  FOR_EACH_EDGE (e, ei, header->preds)
    {
      vec<jump_thread_edge *> *path = THREAD_PATH (e);

      if (path)
	{
	  delete_jump_thread_path (path);
	  e->aux = NULL;
	}
    }
  return false;
}

/* E1 and E2 are edges into the same basic block.  Return TRUE if the
   PHI arguments associated with those edges are equal or there are no
   PHI arguments, otherwise return FALSE.  */

static bool
phi_args_equal_on_edges (edge e1, edge e2)
{
  gimple_stmt_iterator gsi;
  int indx1 = e1->dest_idx;
  int indx2 = e2->dest_idx;

  for (gsi = gsi_start_phis (e1->dest); !gsi_end_p (gsi); gsi_next (&gsi))
    {
      gimple phi = gsi_stmt (gsi);

      if (!operand_equal_p (gimple_phi_arg_def (phi, indx1),
			    gimple_phi_arg_def (phi, indx2), 0))
	return false;
    }
  return true;
}

/* Walk through the registered jump threads and convert them into a
   form convenient for this pass.

   Any block which has incoming edges threaded to outgoing edges
   will have its entry in THREADED_BLOCK set.

   Any threaded edge will have its new outgoing edge stored in the
   original edge's AUX field.

   This form avoids the need to walk all the edges in the CFG to
   discover blocks which need processing and avoids unnecessary
   hash table lookups to map from threaded edge to new target.  */

static void
mark_threaded_blocks (bitmap threaded_blocks)
{
  unsigned int i;
  bitmap_iterator bi;
  bitmap tmp = BITMAP_ALLOC (NULL);
  basic_block bb;
  edge e;
  edge_iterator ei;

  /* It is possible to have jump threads in which one is a subpath
     of the other.  ie, (A, B), (B, C), (C, D) where B is a joiner
     block and (B, C), (C, D) where no joiner block exists.

     When this occurs ignore the jump thread request with the joiner
     block.  It's totally subsumed by the simpler jump thread request.

     This results in less block copying, simpler CFGs.  More importantly,
     when we duplicate the joiner block, B, in this case we will create
     a new threading opportunity that we wouldn't be able to optimize
     until the next jump threading iteration.

     So first convert the jump thread requests which do not require a
     joiner block.  */
  for (i = 0; i < paths.length (); i++)
    {
      vec<jump_thread_edge *> *path = paths[i];

      if ((*path)[1]->type != EDGE_COPY_SRC_JOINER_BLOCK)
	{
	  edge e = (*path)[0]->e;
	  e->aux = (void *)path;
	  bitmap_set_bit (tmp, e->dest->index);
	}
    }

  /* Now iterate again, converting cases where we want to thread
     through a joiner block, but only if no other edge on the path
     already has a jump thread attached to it.  */
  for (i = 0; i < paths.length (); i++)
    {
      vec<jump_thread_edge *> *path = paths[i];

      if ((*path)[1]->type == EDGE_COPY_SRC_JOINER_BLOCK)
	{
	  unsigned int j;

	  for (j = 0; j < path->length (); j++)
	    if ((*path)[j]->e->aux != NULL)
	      break;

	  /* If we iterated through the entire path without exiting the loop,
	     then we are good to go, attach the path to the starting edge.  */
	  if (j == path->length ())
	    {
	      edge e = (*path)[0]->e;
	      e->aux = path;
	      bitmap_set_bit (tmp, e->dest->index);
	    }
	  else if (dump_file && (dump_flags & TDF_DETAILS))
	    {
	      dump_jump_thread_path (dump_file, *path, false);
	    }
	}
    }


  /* If optimizing for size, only thread through block if we don't have
     to duplicate it or it's an otherwise empty redirection block.  */
  if (optimize_function_for_size_p (cfun))
    {
      EXECUTE_IF_SET_IN_BITMAP (tmp, 0, i, bi)
	{
	  bb = BASIC_BLOCK_FOR_FN (cfun, i);
	  if (EDGE_COUNT (bb->preds) > 1
	      && !redirection_block_p (bb))
	    {
	      FOR_EACH_EDGE (e, ei, bb->preds)
		{
		  if (e->aux)
		    {
		      vec<jump_thread_edge *> *path = THREAD_PATH (e);
		      delete_jump_thread_path (path);
		      e->aux = NULL;
		    }
		}
	    }
	  else
	    bitmap_set_bit (threaded_blocks, i);
	}
    }
  else
    bitmap_copy (threaded_blocks, tmp);

  /* Look for jump threading paths which cross multiple loop headers.

     The code to thread through loop headers will change the CFG in ways
     that break assumptions made by the loop optimization code.

     We don't want to blindly cancel the requests.  We can instead do better
     by trimming off the end of the jump thread path.  */
  EXECUTE_IF_SET_IN_BITMAP (tmp, 0, i, bi)
    {
      basic_block bb = BASIC_BLOCK_FOR_FN (cfun, i);
      FOR_EACH_EDGE (e, ei, bb->preds)
	{
	  if (e->aux)
	    {
	      vec<jump_thread_edge *> *path = THREAD_PATH (e);

	      for (unsigned int i = 0, crossed_headers = 0;
		   i < path->length ();
		   i++)
		{
		  basic_block dest = (*path)[i]->e->dest;
		  crossed_headers += (dest == dest->loop_father->header);
		  if (crossed_headers > 1)
		    {
		      /* Trim from entry I onwards.  */
		      for (unsigned int j = i; j < path->length (); j++)
			delete (*path)[j];
		      path->truncate (i);

		      /* Now that we've truncated the path, make sure
			 what's left is still valid.   We need at least
			 two edges on the path and the last edge can not
			 be a joiner.  This should never happen, but let's
			 be safe.  */
		      if (path->length () < 2
			  || (path->last ()->type
			      == EDGE_COPY_SRC_JOINER_BLOCK))
			{
			  delete_jump_thread_path (path);
			  e->aux = NULL;
			}
		      break;
		    }
		}
	    }
	}
    }

  /* If we have a joiner block (J) which has two successors S1 and S2 and
     we are threading though S1 and the final destination of the thread
     is S2, then we must verify that any PHI nodes in S2 have the same
     PHI arguments for the edge J->S2 and J->S1->...->S2.

     We used to detect this prior to registering the jump thread, but
     that prohibits propagation of edge equivalences into non-dominated
     PHI nodes as the equivalency test might occur before propagation.

     This must also occur after we truncate any jump threading paths
     as this scenario may only show up after truncation.

     This works for now, but will need improvement as part of the FSA
     optimization.

     Note since we've moved the thread request data to the edges,
     we have to iterate on those rather than the threaded_edges vector.  */
  EXECUTE_IF_SET_IN_BITMAP (tmp, 0, i, bi)
    {
      bb = BASIC_BLOCK_FOR_FN (cfun, i);
      FOR_EACH_EDGE (e, ei, bb->preds)
	{
	  if (e->aux)
	    {
	      vec<jump_thread_edge *> *path = THREAD_PATH (e);
	      bool have_joiner = ((*path)[1]->type == EDGE_COPY_SRC_JOINER_BLOCK);

	      if (have_joiner)
		{
		  basic_block joiner = e->dest;
		  edge final_edge = path->last ()->e;
		  basic_block final_dest = final_edge->dest;
		  edge e2 = find_edge (joiner, final_dest);

		  if (e2 && !phi_args_equal_on_edges (e2, final_edge))
		    {
		      delete_jump_thread_path (path);
		      e->aux = NULL;
		    }
		}
	    }
	}
    }

  BITMAP_FREE (tmp);
}


/* Return TRUE if BB ends with a switch statement or a computed goto.
   Otherwise return false.  */
static bool
bb_ends_with_multiway_branch (basic_block bb ATTRIBUTE_UNUSED)
{
  gimple stmt = last_stmt (bb);
  if (stmt && gimple_code (stmt) == GIMPLE_SWITCH)
    return true;
  if (stmt && gimple_code (stmt) == GIMPLE_GOTO
      && TREE_CODE (gimple_goto_dest (stmt)) == SSA_NAME)
    return true;
  return false;
}

/* Verify that the REGION is a valid jump thread.  A jump thread is a special
   case of SEME Single Entry Multiple Exits region in which all nodes in the
   REGION have exactly one incoming edge.  The only exception is the first block
   that may not have been connected to the rest of the cfg yet.  */

DEBUG_FUNCTION void
verify_jump_thread (basic_block *region, unsigned n_region)
{
  for (unsigned i = 0; i < n_region; i++)
    gcc_assert (EDGE_COUNT (region[i]->preds) <= 1);
}

/* Return true when BB is one of the first N items in BBS.  */

static inline bool
bb_in_bbs (basic_block bb, basic_block *bbs, int n)
{
  for (int i = 0; i < n; i++)
    if (bb == bbs[i])
      return true;

  return false;
}

/* Duplicates a jump-thread path of N_REGION basic blocks.
   The ENTRY edge is redirected to the duplicate of the region.

   Remove the last conditional statement in the last basic block in the REGION,
   and create a single fallthru edge pointing to the same destination as the
   EXIT edge.

   The new basic blocks are stored to REGION_COPY in the same order as they had
   in REGION, provided that REGION_COPY is not NULL.

   Returns false if it is unable to copy the region, true otherwise.  */

static bool
duplicate_thread_path (edge entry, edge exit,
		       basic_block *region, unsigned n_region,
		       basic_block *region_copy)
{
  unsigned i;
  bool free_region_copy = false, copying_header = false;
  struct loop *loop = entry->dest->loop_father;
  edge exit_copy;
  edge redirected;
  int total_freq = 0, entry_freq = 0;
  gcov_type total_count = 0, entry_count = 0;

  if (!can_copy_bbs_p (region, n_region))
    return false;

  /* Some sanity checking.  Note that we do not check for all possible
     missuses of the functions.  I.e. if you ask to copy something weird,
     it will work, but the state of structures probably will not be
     correct.  */
  for (i = 0; i < n_region; i++)
    {
      /* We do not handle subloops, i.e. all the blocks must belong to the
	 same loop.  */
      if (region[i]->loop_father != loop)
	return false;
    }

  initialize_original_copy_tables ();

  if (copying_header)
    set_loop_copy (loop, loop_outer (loop));
  else
    set_loop_copy (loop, loop);

  if (!region_copy)
    {
      region_copy = XNEWVEC (basic_block, n_region);
      free_region_copy = true;
    }

  if (entry->dest->count)
    {
      total_count = entry->dest->count;
      entry_count = entry->count;
      /* Fix up corner cases, to avoid division by zero or creation of negative
	 frequencies.  */
      if (entry_count > total_count)
	entry_count = total_count;
    }
  else
    {
      total_freq = entry->dest->frequency;
      entry_freq = EDGE_FREQUENCY (entry);
      /* Fix up corner cases, to avoid division by zero or creation of negative
	 frequencies.  */
      if (total_freq == 0)
	total_freq = 1;
      else if (entry_freq > total_freq)
	entry_freq = total_freq;
    }

  copy_bbs (region, n_region, region_copy, &exit, 1, &exit_copy, loop,
	    split_edge_bb_loc (entry), false);

  /* Fix up: copy_bbs redirects all edges pointing to copied blocks.  The
     following code ensures that all the edges exiting the jump-thread path are
     redirected back to the original code: these edges are exceptions
     invalidating the property that is propagated by executing all the blocks of
     the jump-thread path in order.  */

  for (i = 0; i < n_region; i++)
    {
      edge e;
      edge_iterator ei;
      basic_block bb = region_copy[i];

      if (single_succ_p (bb))
	{
	  /* Make sure the successor is the next node in the path.  */
	  gcc_assert (i + 1 == n_region
		      || region_copy[i + 1] == single_succ_edge (bb)->dest);
	  continue;
	}

      /* Special case the last block on the path: make sure that it does not
	 jump back on the copied path.  */
      if (i + 1 == n_region)
	{
	  FOR_EACH_EDGE (e, ei, bb->succs)
	    if (bb_in_bbs (e->dest, region_copy, n_region - 1))
	      {
		basic_block orig = get_bb_original (e->dest);
		if (orig)
		  redirect_edge_and_branch_force (e, orig);
	      }
	  continue;
	}

      /* Redirect all other edges jumping to non-adjacent blocks back to the
	 original code.  */
      FOR_EACH_EDGE (e, ei, bb->succs)
	if (region_copy[i + 1] != e->dest)
	  {
	    basic_block orig = get_bb_original (e->dest);
	    if (orig)
	      redirect_edge_and_branch_force (e, orig);
	  }
    }

  if (total_count)
    {
      scale_bbs_frequencies_gcov_type (region, n_region,
				       total_count - entry_count,
				       total_count);
      scale_bbs_frequencies_gcov_type (region_copy, n_region, entry_count,
				       total_count);
    }
  else
    {
      scale_bbs_frequencies_int (region, n_region, total_freq - entry_freq,
				 total_freq);
      scale_bbs_frequencies_int (region_copy, n_region, entry_freq, total_freq);
    }

#ifdef ENABLE_CHECKING
  verify_jump_thread (region_copy, n_region);
#endif

  /* Remove the last branch in the jump thread path.  */
  remove_ctrl_stmt_and_useless_edges (region_copy[n_region - 1], exit->dest);
  edge e = make_edge (region_copy[n_region - 1], exit->dest, EDGE_FALLTHRU);

  if (e) {
    rescan_loop_exit (e, true, false);
    e->probability = REG_BR_PROB_BASE;
    e->count = region_copy[n_region - 1]->count;
  }

  /* Redirect the entry and add the phi node arguments.  */
  redirected = redirect_edge_and_branch (entry, get_bb_copy (entry->dest));
  gcc_assert (redirected != NULL);
  flush_pending_stmts (entry);

  /* Add the other PHI node arguments.  */
  add_phi_args_after_copy (region_copy, n_region, NULL);

  if (free_region_copy)
    free (region_copy);

  free_original_copy_tables ();
  return true;
}

/* Return true when PATH is a valid jump-thread path.  */

static bool
valid_jump_thread_path (vec<jump_thread_edge *> *path)
{
  unsigned len = path->length ();

  /* Check that the path is connected.  */
  for (unsigned int j = 0; j < len - 1; j++)
    if ((*path)[j]->e->dest != (*path)[j+1]->e->src)
      return false;

  return true;
}

/* Walk through all blocks and thread incoming edges to the appropriate
   outgoing edge for each edge pair recorded in THREADED_EDGES.

   It is the caller's responsibility to fix the dominance information
   and rewrite duplicated SSA_NAMEs back into SSA form.

   If MAY_PEEL_LOOP_HEADERS is false, we avoid threading edges through
   loop headers if it does not simplify the loop.

   Returns true if one or more edges were threaded, false otherwise.  */

bool
thread_through_all_blocks (bool may_peel_loop_headers)
{
  bool retval = false;
  unsigned int i;
  bitmap_iterator bi;
  bitmap threaded_blocks;
  struct loop *loop;

  /* We must know about loops in order to preserve them.  */
  gcc_assert (current_loops != NULL);

  if (!paths.exists ())
    return false;

  threaded_blocks = BITMAP_ALLOC (NULL);
  memset (&thread_stats, 0, sizeof (thread_stats));

  /* Jump-thread all FSM threads before other jump-threads.  */
  for (i = 0; i < paths.length ();)
    {
      vec<jump_thread_edge *> *path = paths[i];
      edge entry = (*path)[0]->e;

      /* Only code-generate FSM jump-threads in this loop.  */
      if ((*path)[0]->type != EDGE_FSM_THREAD)
	{
	  i++;
	  continue;
	}

      /* Do not jump-thread twice from the same block.  */
      if (bitmap_bit_p (threaded_blocks, entry->src->index)
	  /* Verify that the jump thread path is still valid: a
	     previous jump-thread may have changed the CFG, and
	     invalidated the current path.  */
	  || !valid_jump_thread_path (path))
	{
	  /* Remove invalid FSM jump-thread paths.  */
	  delete_jump_thread_path (path);
	  paths.unordered_remove (i);
	  continue;
	}

      unsigned len = path->length ();
      edge exit = (*path)[len - 1]->e;
      basic_block *region = XNEWVEC (basic_block, len - 1);

      for (unsigned int j = 0; j < len - 1; j++)
	region[j] = (*path)[j]->e->dest;

      if (duplicate_thread_path (entry, exit, region, len - 1, NULL))
	{
	  /* We do not update dominance info.  */
	  free_dominance_info (CDI_DOMINATORS);
	  bitmap_set_bit (threaded_blocks, entry->src->index);
	  retval = true;
	}

      delete_jump_thread_path (path);
      paths.unordered_remove (i);
    }

  /* Remove from PATHS all the jump-threads starting with an edge already
     jump-threaded.  */
  for (i = 0; i < paths.length ();)
    {
      vec<jump_thread_edge *> *path = paths[i];
      edge entry = (*path)[0]->e;

      /* Do not jump-thread twice from the same block.  */
      if (bitmap_bit_p (threaded_blocks, entry->src->index))
	{
	  delete_jump_thread_path (path);
	  paths.unordered_remove (i);
	}
      else
	i++;
    }

  bitmap_clear (threaded_blocks);

  mark_threaded_blocks (threaded_blocks);

  initialize_original_copy_tables ();

  /* First perform the threading requests that do not affect
     loop structure.  */
  EXECUTE_IF_SET_IN_BITMAP (threaded_blocks, 0, i, bi)
    {
      basic_block bb = BASIC_BLOCK_FOR_FN (cfun, i);

      if (EDGE_COUNT (bb->preds) > 0)
	retval |= thread_block (bb, true);
    }

  /* Then perform the threading through loop headers.  We start with the
     innermost loop, so that the changes in cfg we perform won't affect
     further threading.  */
  FOR_EACH_LOOP (loop, LI_FROM_INNERMOST)
    {
      if (!loop->header
	  || !bitmap_bit_p (threaded_blocks, loop->header->index))
	continue;

      retval |= thread_through_loop_header (loop, may_peel_loop_headers);
    }

  /* Any jump threading paths that are still attached to edges at this
     point must be one of two cases.

     First, we could have a jump threading path which went from outside
     a loop to inside a loop that was ignored because a prior jump thread
     across a backedge was realized (which indirectly causes the loop
     above to ignore the latter thread).  We can detect these because the
     loop structures will be different and we do not currently try to
     optimize this case.

     Second, we could be threading across a backedge to a point within the
     same loop.  This occurrs for the FSA/FSM optimization and we would
     like to optimize it.  However, we have to be very careful as this
     may completely scramble the loop structures, with the result being
     irreducible loops causing us to throw away our loop structure.

     As a compromise for the latter case, if the thread path ends in
     a block where the last statement is a multiway branch, then go
     ahead and thread it, else ignore it.  */
  basic_block bb;
  edge e;
  FOR_EACH_BB_FN (bb, cfun)
    {
      /* If we do end up threading here, we can remove elements from
	 BB->preds.  Thus we can not use the FOR_EACH_EDGE iterator.  */
      for (edge_iterator ei = ei_start (bb->preds);
	   (e = ei_safe_edge (ei));)
	if (e->aux)
	  {
	    vec<jump_thread_edge *> *path = THREAD_PATH (e);

	    /* Case 1, threading from outside to inside the loop
	       after we'd already threaded through the header.  */
	    if ((*path)[0]->e->dest->loop_father
		!= path->last ()->e->src->loop_father)
	      {
		delete_jump_thread_path (path);
		e->aux = NULL;
		ei_next (&ei);
	      }
	   else if (bb_ends_with_multiway_branch (path->last ()->e->src))
	      {
		/* The code to thread through loop headers may have
		   split a block with jump threads attached to it.

		   We can identify this with a disjoint jump threading
		   path.  If found, just remove it.  */
		for (unsigned int i = 0; i < path->length () - 1; i++)
		  if ((*path)[i]->e->dest != (*path)[i + 1]->e->src)
		    {
		      delete_jump_thread_path (path);
		      e->aux = NULL;
		      ei_next (&ei);
		      break;
		    }

		/* Our path is still valid, thread it.  */
	        if (e->aux)
		  {
		    struct loop *loop = (*path)[0]->e->dest->loop_father;

		    if (thread_block ((*path)[0]->e->dest, false))
		      {
			/* This jump thread likely totally scrambled this loop.
			   So arrange for it to be fixed up.  */
			loop->header = NULL;
			loop->latch = NULL;
			e->aux = NULL;
		      }
		    else
		      {
		        delete_jump_thread_path (path);
			e->aux = NULL;
			ei_next (&ei);
		      }
		  }
	      }
	   else
	      {
		delete_jump_thread_path (path);
		e->aux = NULL;
		ei_next (&ei);
	      }
 	  }
	else
	  ei_next (&ei);
    }

  statistics_counter_event (cfun, "Jumps threaded",
			    thread_stats.num_threaded_edges);

  free_original_copy_tables ();

  BITMAP_FREE (threaded_blocks);
  threaded_blocks = NULL;
  paths.release ();

  if (retval)
    loops_state_set (LOOPS_NEED_FIXUP);

  return retval;
}

/* Delete the jump threading path PATH.  We have to explcitly delete
   each entry in the vector, then the container.  */

void
delete_jump_thread_path (vec<jump_thread_edge *> *path)
{
  for (unsigned int i = 0; i < path->length (); i++)
    delete (*path)[i];
  path->release();
}

/* Register a jump threading opportunity.  We queue up all the jump
   threading opportunities discovered by a pass and update the CFG
   and SSA form all at once.

   E is the edge we can thread, E2 is the new target edge, i.e., we
   are effectively recording that E->dest can be changed to E2->dest
   after fixing the SSA graph.  */

void
register_jump_thread (vec<jump_thread_edge *> *path)
{
  if (!dbg_cnt (registered_jump_thread))
    {
      delete_jump_thread_path (path);
      return;
    }

  /* First make sure there are no NULL outgoing edges on the jump threading
     path.  That can happen for jumping to a constant address.  */
  for (unsigned int i = 0; i < path->length (); i++)
    if ((*path)[i]->e == NULL)
      {
	if (dump_file && (dump_flags & TDF_DETAILS))
	  {
	    fprintf (dump_file,
		     "Found NULL edge in jump threading path.  Cancelling jump thread:\n");
	    dump_jump_thread_path (dump_file, *path, false);
	  }

	delete_jump_thread_path (path);
	return;
      }

  if (dump_file && (dump_flags & TDF_DETAILS))
    dump_jump_thread_path (dump_file, *path, true);

  if (!paths.exists ())
    paths.create (5);

  paths.safe_push (path);
}