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
|
/* Control flow optimization code for GNU compiler.
Copyright (C) 1987, 1988, 1992, 1993, 1994, 1995, 1996, 1997, 1998,
1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007
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/>. */
/* This file contains optimizer of the control flow. The main entry point is
cleanup_cfg. Following optimizations are performed:
- Unreachable blocks removal
- Edge forwarding (edge to the forwarder block is forwarded to its
successor. Simplification of the branch instruction is performed by
underlying infrastructure so branch can be converted to simplejump or
eliminated).
- Cross jumping (tail merging)
- Conditional jump-around-simplejump simplification
- Basic block merging. */
#include "config.h"
#include "system.h"
#include "coretypes.h"
#include "tm.h"
#include "rtl.h"
#include "hard-reg-set.h"
#include "regs.h"
#include "timevar.h"
#include "output.h"
#include "insn-config.h"
#include "flags.h"
#include "recog.h"
#include "toplev.h"
#include "cselib.h"
#include "params.h"
#include "tm_p.h"
#include "target.h"
#include "cfglayout.h"
#include "emit-rtl.h"
#include "tree-pass.h"
#include "cfgloop.h"
#include "expr.h"
#include "df.h"
#include "dce.h"
#include "dbgcnt.h"
#define FORWARDER_BLOCK_P(BB) ((BB)->flags & BB_FORWARDER_BLOCK)
/* Set to true when we are running first pass of try_optimize_cfg loop. */
static bool first_pass;
/* Set to true if crossjumps occured in the latest run of try_optimize_cfg. */
static bool crossjumps_occured;
static bool try_crossjump_to_edge (int, edge, edge);
static bool try_crossjump_bb (int, basic_block);
static bool outgoing_edges_match (int, basic_block, basic_block);
static int flow_find_cross_jump (int, basic_block, basic_block, rtx *, rtx *);
static bool old_insns_match_p (int, rtx, rtx);
static void merge_blocks_move_predecessor_nojumps (basic_block, basic_block);
static void merge_blocks_move_successor_nojumps (basic_block, basic_block);
static bool try_optimize_cfg (int);
static bool try_simplify_condjump (basic_block);
static bool try_forward_edges (int, basic_block);
static edge thread_jump (edge, basic_block);
static bool mark_effect (rtx, bitmap);
static void notice_new_block (basic_block);
static void update_forwarder_flag (basic_block);
static int mentions_nonequal_regs (rtx *, void *);
static void merge_memattrs (rtx, rtx);
/* Set flags for newly created block. */
static void
notice_new_block (basic_block bb)
{
if (!bb)
return;
if (forwarder_block_p (bb))
bb->flags |= BB_FORWARDER_BLOCK;
}
/* Recompute forwarder flag after block has been modified. */
static void
update_forwarder_flag (basic_block bb)
{
if (forwarder_block_p (bb))
bb->flags |= BB_FORWARDER_BLOCK;
else
bb->flags &= ~BB_FORWARDER_BLOCK;
}
/* Simplify a conditional jump around an unconditional jump.
Return true if something changed. */
static bool
try_simplify_condjump (basic_block cbranch_block)
{
basic_block jump_block, jump_dest_block, cbranch_dest_block;
edge cbranch_jump_edge, cbranch_fallthru_edge;
rtx cbranch_insn;
/* Verify that there are exactly two successors. */
if (EDGE_COUNT (cbranch_block->succs) != 2)
return false;
/* Verify that we've got a normal conditional branch at the end
of the block. */
cbranch_insn = BB_END (cbranch_block);
if (!any_condjump_p (cbranch_insn))
return false;
cbranch_fallthru_edge = FALLTHRU_EDGE (cbranch_block);
cbranch_jump_edge = BRANCH_EDGE (cbranch_block);
/* The next block must not have multiple predecessors, must not
be the last block in the function, and must contain just the
unconditional jump. */
jump_block = cbranch_fallthru_edge->dest;
if (!single_pred_p (jump_block)
|| jump_block->next_bb == EXIT_BLOCK_PTR
|| !FORWARDER_BLOCK_P (jump_block))
return false;
jump_dest_block = single_succ (jump_block);
/* If we are partitioning hot/cold basic blocks, we don't want to
mess up unconditional or indirect jumps that cross between hot
and cold sections.
Basic block partitioning may result in some jumps that appear to
be optimizable (or blocks that appear to be mergeable), but which really
must be left untouched (they are required to make it safely across
partition boundaries). See the comments at the top of
bb-reorder.c:partition_hot_cold_basic_blocks for complete details. */
if (BB_PARTITION (jump_block) != BB_PARTITION (jump_dest_block)
|| (cbranch_jump_edge->flags & EDGE_CROSSING))
return false;
/* The conditional branch must target the block after the
unconditional branch. */
cbranch_dest_block = cbranch_jump_edge->dest;
if (cbranch_dest_block == EXIT_BLOCK_PTR
|| !can_fallthru (jump_block, cbranch_dest_block))
return false;
/* Invert the conditional branch. */
if (!invert_jump (cbranch_insn, block_label (jump_dest_block), 0))
return false;
if (dump_file)
fprintf (dump_file, "Simplifying condjump %i around jump %i\n",
INSN_UID (cbranch_insn), INSN_UID (BB_END (jump_block)));
/* Success. Update the CFG to match. Note that after this point
the edge variable names appear backwards; the redirection is done
this way to preserve edge profile data. */
cbranch_jump_edge = redirect_edge_succ_nodup (cbranch_jump_edge,
cbranch_dest_block);
cbranch_fallthru_edge = redirect_edge_succ_nodup (cbranch_fallthru_edge,
jump_dest_block);
cbranch_jump_edge->flags |= EDGE_FALLTHRU;
cbranch_fallthru_edge->flags &= ~EDGE_FALLTHRU;
update_br_prob_note (cbranch_block);
/* Delete the block with the unconditional jump, and clean up the mess. */
delete_basic_block (jump_block);
tidy_fallthru_edge (cbranch_jump_edge);
update_forwarder_flag (cbranch_block);
return true;
}
/* Attempt to prove that operation is NOOP using CSElib or mark the effect
on register. Used by jump threading. */
static bool
mark_effect (rtx exp, regset nonequal)
{
int regno;
rtx dest;
switch (GET_CODE (exp))
{
/* In case we do clobber the register, mark it as equal, as we know the
value is dead so it don't have to match. */
case CLOBBER:
if (REG_P (XEXP (exp, 0)))
{
dest = XEXP (exp, 0);
regno = REGNO (dest);
CLEAR_REGNO_REG_SET (nonequal, regno);
if (regno < FIRST_PSEUDO_REGISTER)
{
int n = hard_regno_nregs[regno][GET_MODE (dest)];
while (--n > 0)
CLEAR_REGNO_REG_SET (nonequal, regno + n);
}
}
return false;
case SET:
if (rtx_equal_for_cselib_p (SET_DEST (exp), SET_SRC (exp)))
return false;
dest = SET_DEST (exp);
if (dest == pc_rtx)
return false;
if (!REG_P (dest))
return true;
regno = REGNO (dest);
SET_REGNO_REG_SET (nonequal, regno);
if (regno < FIRST_PSEUDO_REGISTER)
{
int n = hard_regno_nregs[regno][GET_MODE (dest)];
while (--n > 0)
SET_REGNO_REG_SET (nonequal, regno + n);
}
return false;
default:
return false;
}
}
/* Return nonzero if X is a register set in regset DATA.
Called via for_each_rtx. */
static int
mentions_nonequal_regs (rtx *x, void *data)
{
regset nonequal = (regset) data;
if (REG_P (*x))
{
int regno;
regno = REGNO (*x);
if (REGNO_REG_SET_P (nonequal, regno))
return 1;
if (regno < FIRST_PSEUDO_REGISTER)
{
int n = hard_regno_nregs[regno][GET_MODE (*x)];
while (--n > 0)
if (REGNO_REG_SET_P (nonequal, regno + n))
return 1;
}
}
return 0;
}
/* Attempt to prove that the basic block B will have no side effects and
always continues in the same edge if reached via E. Return the edge
if exist, NULL otherwise. */
static edge
thread_jump (edge e, basic_block b)
{
rtx set1, set2, cond1, cond2, insn;
enum rtx_code code1, code2, reversed_code2;
bool reverse1 = false;
unsigned i;
regset nonequal;
bool failed = false;
reg_set_iterator rsi;
if (b->flags & BB_NONTHREADABLE_BLOCK)
return NULL;
/* At the moment, we do handle only conditional jumps, but later we may
want to extend this code to tablejumps and others. */
if (EDGE_COUNT (e->src->succs) != 2)
return NULL;
if (EDGE_COUNT (b->succs) != 2)
{
b->flags |= BB_NONTHREADABLE_BLOCK;
return NULL;
}
/* Second branch must end with onlyjump, as we will eliminate the jump. */
if (!any_condjump_p (BB_END (e->src)))
return NULL;
if (!any_condjump_p (BB_END (b)) || !onlyjump_p (BB_END (b)))
{
b->flags |= BB_NONTHREADABLE_BLOCK;
return NULL;
}
set1 = pc_set (BB_END (e->src));
set2 = pc_set (BB_END (b));
if (((e->flags & EDGE_FALLTHRU) != 0)
!= (XEXP (SET_SRC (set1), 1) == pc_rtx))
reverse1 = true;
cond1 = XEXP (SET_SRC (set1), 0);
cond2 = XEXP (SET_SRC (set2), 0);
if (reverse1)
code1 = reversed_comparison_code (cond1, BB_END (e->src));
else
code1 = GET_CODE (cond1);
code2 = GET_CODE (cond2);
reversed_code2 = reversed_comparison_code (cond2, BB_END (b));
if (!comparison_dominates_p (code1, code2)
&& !comparison_dominates_p (code1, reversed_code2))
return NULL;
/* Ensure that the comparison operators are equivalent.
??? This is far too pessimistic. We should allow swapped operands,
different CCmodes, or for example comparisons for interval, that
dominate even when operands are not equivalent. */
if (!rtx_equal_p (XEXP (cond1, 0), XEXP (cond2, 0))
|| !rtx_equal_p (XEXP (cond1, 1), XEXP (cond2, 1)))
return NULL;
/* Short circuit cases where block B contains some side effects, as we can't
safely bypass it. */
for (insn = NEXT_INSN (BB_HEAD (b)); insn != NEXT_INSN (BB_END (b));
insn = NEXT_INSN (insn))
if (INSN_P (insn) && side_effects_p (PATTERN (insn)))
{
b->flags |= BB_NONTHREADABLE_BLOCK;
return NULL;
}
cselib_init (false);
/* First process all values computed in the source basic block. */
for (insn = NEXT_INSN (BB_HEAD (e->src));
insn != NEXT_INSN (BB_END (e->src));
insn = NEXT_INSN (insn))
if (INSN_P (insn))
cselib_process_insn (insn);
nonequal = BITMAP_ALLOC (NULL);
CLEAR_REG_SET (nonequal);
/* Now assume that we've continued by the edge E to B and continue
processing as if it were same basic block.
Our goal is to prove that whole block is an NOOP. */
for (insn = NEXT_INSN (BB_HEAD (b));
insn != NEXT_INSN (BB_END (b)) && !failed;
insn = NEXT_INSN (insn))
{
if (INSN_P (insn))
{
rtx pat = PATTERN (insn);
if (GET_CODE (pat) == PARALLEL)
{
for (i = 0; i < (unsigned)XVECLEN (pat, 0); i++)
failed |= mark_effect (XVECEXP (pat, 0, i), nonequal);
}
else
failed |= mark_effect (pat, nonequal);
}
cselib_process_insn (insn);
}
/* Later we should clear nonequal of dead registers. So far we don't
have life information in cfg_cleanup. */
if (failed)
{
b->flags |= BB_NONTHREADABLE_BLOCK;
goto failed_exit;
}
/* cond2 must not mention any register that is not equal to the
former block. */
if (for_each_rtx (&cond2, mentions_nonequal_regs, nonequal))
goto failed_exit;
EXECUTE_IF_SET_IN_REG_SET (nonequal, 0, i, rsi)
goto failed_exit;
BITMAP_FREE (nonequal);
cselib_finish ();
if ((comparison_dominates_p (code1, code2) != 0)
!= (XEXP (SET_SRC (set2), 1) == pc_rtx))
return BRANCH_EDGE (b);
else
return FALLTHRU_EDGE (b);
failed_exit:
BITMAP_FREE (nonequal);
cselib_finish ();
return NULL;
}
/* Attempt to forward edges leaving basic block B.
Return true if successful. */
static bool
try_forward_edges (int mode, basic_block b)
{
bool changed = false;
edge_iterator ei;
edge e, *threaded_edges = NULL;
/* If we are partitioning hot/cold basic blocks, we don't want to
mess up unconditional or indirect jumps that cross between hot
and cold sections.
Basic block partitioning may result in some jumps that appear to
be optimizable (or blocks that appear to be mergeable), but which really m
ust be left untouched (they are required to make it safely across
partition boundaries). See the comments at the top of
bb-reorder.c:partition_hot_cold_basic_blocks for complete details. */
if (find_reg_note (BB_END (b), REG_CROSSING_JUMP, NULL_RTX))
return false;
for (ei = ei_start (b->succs); (e = ei_safe_edge (ei)); )
{
basic_block target, first;
int counter;
bool threaded = false;
int nthreaded_edges = 0;
bool may_thread = first_pass | df_get_bb_dirty (b);
/* Skip complex edges because we don't know how to update them.
Still handle fallthru edges, as we can succeed to forward fallthru
edge to the same place as the branch edge of conditional branch
and turn conditional branch to an unconditional branch. */
if (e->flags & EDGE_COMPLEX)
{
ei_next (&ei);
continue;
}
target = first = e->dest;
counter = NUM_FIXED_BLOCKS;
/* If we are partitioning hot/cold basic_blocks, we don't want to mess
up jumps that cross between hot/cold sections.
Basic block partitioning may result in some jumps that appear
to be optimizable (or blocks that appear to be mergeable), but which
really must be left untouched (they are required to make it safely
across partition boundaries). See the comments at the top of
bb-reorder.c:partition_hot_cold_basic_blocks for complete
details. */
if (first != EXIT_BLOCK_PTR
&& find_reg_note (BB_END (first), REG_CROSSING_JUMP, NULL_RTX))
return false;
while (counter < n_basic_blocks)
{
basic_block new_target = NULL;
bool new_target_threaded = false;
may_thread |= df_get_bb_dirty (target);
if (FORWARDER_BLOCK_P (target)
&& !(single_succ_edge (target)->flags & EDGE_CROSSING)
&& single_succ (target) != EXIT_BLOCK_PTR)
{
/* Bypass trivial infinite loops. */
new_target = single_succ (target);
if (target == new_target)
counter = n_basic_blocks;
}
/* Allow to thread only over one edge at time to simplify updating
of probabilities. */
else if ((mode & CLEANUP_THREADING) && may_thread)
{
edge t = thread_jump (e, target);
if (t)
{
if (!threaded_edges)
threaded_edges = XNEWVEC (edge, n_basic_blocks);
else
{
int i;
/* Detect an infinite loop across blocks not
including the start block. */
for (i = 0; i < nthreaded_edges; ++i)
if (threaded_edges[i] == t)
break;
if (i < nthreaded_edges)
{
counter = n_basic_blocks;
break;
}
}
/* Detect an infinite loop across the start block. */
if (t->dest == b)
break;
gcc_assert (nthreaded_edges < n_basic_blocks - NUM_FIXED_BLOCKS);
threaded_edges[nthreaded_edges++] = t;
new_target = t->dest;
new_target_threaded = true;
}
}
if (!new_target)
break;
counter++;
target = new_target;
threaded |= new_target_threaded;
}
if (counter >= n_basic_blocks)
{
if (dump_file)
fprintf (dump_file, "Infinite loop in BB %i.\n",
target->index);
}
else if (target == first)
; /* We didn't do anything. */
else
{
/* Save the values now, as the edge may get removed. */
gcov_type edge_count = e->count;
int edge_probability = e->probability;
int edge_frequency;
int n = 0;
/* Don't force if target is exit block. */
if (threaded && target != EXIT_BLOCK_PTR)
{
notice_new_block (redirect_edge_and_branch_force (e, target));
if (dump_file)
fprintf (dump_file, "Conditionals threaded.\n");
}
else if (!redirect_edge_and_branch (e, target))
{
if (dump_file)
fprintf (dump_file,
"Forwarding edge %i->%i to %i failed.\n",
b->index, e->dest->index, target->index);
ei_next (&ei);
continue;
}
/* We successfully forwarded the edge. Now update profile
data: for each edge we traversed in the chain, remove
the original edge's execution count. */
edge_frequency = ((edge_probability * b->frequency
+ REG_BR_PROB_BASE / 2)
/ REG_BR_PROB_BASE);
if (!FORWARDER_BLOCK_P (b) && forwarder_block_p (b))
b->flags |= BB_FORWARDER_BLOCK;
do
{
edge t;
if (!single_succ_p (first))
{
gcc_assert (n < nthreaded_edges);
t = threaded_edges [n++];
gcc_assert (t->src == first);
update_bb_profile_for_threading (first, edge_frequency,
edge_count, t);
update_br_prob_note (first);
}
else
{
first->count -= edge_count;
if (first->count < 0)
first->count = 0;
first->frequency -= edge_frequency;
if (first->frequency < 0)
first->frequency = 0;
/* It is possible that as the result of
threading we've removed edge as it is
threaded to the fallthru edge. Avoid
getting out of sync. */
if (n < nthreaded_edges
&& first == threaded_edges [n]->src)
n++;
t = single_succ_edge (first);
}
t->count -= edge_count;
if (t->count < 0)
t->count = 0;
first = t->dest;
}
while (first != target);
changed = true;
continue;
}
ei_next (&ei);
}
if (threaded_edges)
free (threaded_edges);
return changed;
}
/* Blocks A and B are to be merged into a single block. A has no incoming
fallthru edge, so it can be moved before B without adding or modifying
any jumps (aside from the jump from A to B). */
static void
merge_blocks_move_predecessor_nojumps (basic_block a, basic_block b)
{
rtx barrier;
/* If we are partitioning hot/cold basic blocks, we don't want to
mess up unconditional or indirect jumps that cross between hot
and cold sections.
Basic block partitioning may result in some jumps that appear to
be optimizable (or blocks that appear to be mergeable), but which really
must be left untouched (they are required to make it safely across
partition boundaries). See the comments at the top of
bb-reorder.c:partition_hot_cold_basic_blocks for complete details. */
if (BB_PARTITION (a) != BB_PARTITION (b))
return;
barrier = next_nonnote_insn (BB_END (a));
gcc_assert (BARRIER_P (barrier));
delete_insn (barrier);
/* Scramble the insn chain. */
if (BB_END (a) != PREV_INSN (BB_HEAD (b)))
reorder_insns_nobb (BB_HEAD (a), BB_END (a), PREV_INSN (BB_HEAD (b)));
df_set_bb_dirty (a);
if (dump_file)
fprintf (dump_file, "Moved block %d before %d and merged.\n",
a->index, b->index);
/* Swap the records for the two blocks around. */
unlink_block (a);
link_block (a, b->prev_bb);
/* Now blocks A and B are contiguous. Merge them. */
merge_blocks (a, b);
}
/* Blocks A and B are to be merged into a single block. B has no outgoing
fallthru edge, so it can be moved after A without adding or modifying
any jumps (aside from the jump from A to B). */
static void
merge_blocks_move_successor_nojumps (basic_block a, basic_block b)
{
rtx barrier, real_b_end;
rtx label, table;
/* If we are partitioning hot/cold basic blocks, we don't want to
mess up unconditional or indirect jumps that cross between hot
and cold sections.
Basic block partitioning may result in some jumps that appear to
be optimizable (or blocks that appear to be mergeable), but which really
must be left untouched (they are required to make it safely across
partition boundaries). See the comments at the top of
bb-reorder.c:partition_hot_cold_basic_blocks for complete details. */
if (BB_PARTITION (a) != BB_PARTITION (b))
return;
real_b_end = BB_END (b);
/* If there is a jump table following block B temporarily add the jump table
to block B so that it will also be moved to the correct location. */
if (tablejump_p (BB_END (b), &label, &table)
&& prev_active_insn (label) == BB_END (b))
{
BB_END (b) = table;
}
/* There had better have been a barrier there. Delete it. */
barrier = NEXT_INSN (BB_END (b));
if (barrier && BARRIER_P (barrier))
delete_insn (barrier);
/* Scramble the insn chain. */
reorder_insns_nobb (BB_HEAD (b), BB_END (b), BB_END (a));
/* Restore the real end of b. */
BB_END (b) = real_b_end;
if (dump_file)
fprintf (dump_file, "Moved block %d after %d and merged.\n",
b->index, a->index);
/* Now blocks A and B are contiguous. Merge them. */
merge_blocks (a, b);
}
/* Attempt to merge basic blocks that are potentially non-adjacent.
Return NULL iff the attempt failed, otherwise return basic block
where cleanup_cfg should continue. Because the merging commonly
moves basic block away or introduces another optimization
possibility, return basic block just before B so cleanup_cfg don't
need to iterate.
It may be good idea to return basic block before C in the case
C has been moved after B and originally appeared earlier in the
insn sequence, but we have no information available about the
relative ordering of these two. Hopefully it is not too common. */
static basic_block
merge_blocks_move (edge e, basic_block b, basic_block c, int mode)
{
basic_block next;
/* If we are partitioning hot/cold basic blocks, we don't want to
mess up unconditional or indirect jumps that cross between hot
and cold sections.
Basic block partitioning may result in some jumps that appear to
be optimizable (or blocks that appear to be mergeable), but which really
must be left untouched (they are required to make it safely across
partition boundaries). See the comments at the top of
bb-reorder.c:partition_hot_cold_basic_blocks for complete details. */
if (BB_PARTITION (b) != BB_PARTITION (c))
return NULL;
/* If B has a fallthru edge to C, no need to move anything. */
if (e->flags & EDGE_FALLTHRU)
{
int b_index = b->index, c_index = c->index;
merge_blocks (b, c);
update_forwarder_flag (b);
if (dump_file)
fprintf (dump_file, "Merged %d and %d without moving.\n",
b_index, c_index);
return b->prev_bb == ENTRY_BLOCK_PTR ? b : b->prev_bb;
}
/* Otherwise we will need to move code around. Do that only if expensive
transformations are allowed. */
else if (mode & CLEANUP_EXPENSIVE)
{
edge tmp_edge, b_fallthru_edge;
bool c_has_outgoing_fallthru;
bool b_has_incoming_fallthru;
edge_iterator ei;
/* Avoid overactive code motion, as the forwarder blocks should be
eliminated by edge redirection instead. One exception might have
been if B is a forwarder block and C has no fallthru edge, but
that should be cleaned up by bb-reorder instead. */
if (FORWARDER_BLOCK_P (b) || FORWARDER_BLOCK_P (c))
return NULL;
/* We must make sure to not munge nesting of lexical blocks,
and loop notes. This is done by squeezing out all the notes
and leaving them there to lie. Not ideal, but functional. */
FOR_EACH_EDGE (tmp_edge, ei, c->succs)
if (tmp_edge->flags & EDGE_FALLTHRU)
break;
c_has_outgoing_fallthru = (tmp_edge != NULL);
FOR_EACH_EDGE (tmp_edge, ei, b->preds)
if (tmp_edge->flags & EDGE_FALLTHRU)
break;
b_has_incoming_fallthru = (tmp_edge != NULL);
b_fallthru_edge = tmp_edge;
next = b->prev_bb;
if (next == c)
next = next->prev_bb;
/* Otherwise, we're going to try to move C after B. If C does
not have an outgoing fallthru, then it can be moved
immediately after B without introducing or modifying jumps. */
if (! c_has_outgoing_fallthru)
{
merge_blocks_move_successor_nojumps (b, c);
return next == ENTRY_BLOCK_PTR ? next->next_bb : next;
}
/* If B does not have an incoming fallthru, then it can be moved
immediately before C without introducing or modifying jumps.
C cannot be the first block, so we do not have to worry about
accessing a non-existent block. */
if (b_has_incoming_fallthru)
{
basic_block bb;
if (b_fallthru_edge->src == ENTRY_BLOCK_PTR)
return NULL;
bb = force_nonfallthru (b_fallthru_edge);
if (bb)
notice_new_block (bb);
}
merge_blocks_move_predecessor_nojumps (b, c);
return next == ENTRY_BLOCK_PTR ? next->next_bb : next;
}
return NULL;
}
/* Removes the memory attributes of MEM expression
if they are not equal. */
void
merge_memattrs (rtx x, rtx y)
{
int i;
int j;
enum rtx_code code;
const char *fmt;
if (x == y)
return;
if (x == 0 || y == 0)
return;
code = GET_CODE (x);
if (code != GET_CODE (y))
return;
if (GET_MODE (x) != GET_MODE (y))
return;
if (code == MEM && MEM_ATTRS (x) != MEM_ATTRS (y))
{
if (! MEM_ATTRS (x))
MEM_ATTRS (y) = 0;
else if (! MEM_ATTRS (y))
MEM_ATTRS (x) = 0;
else
{
rtx mem_size;
if (MEM_ALIAS_SET (x) != MEM_ALIAS_SET (y))
{
set_mem_alias_set (x, 0);
set_mem_alias_set (y, 0);
}
if (! mem_expr_equal_p (MEM_EXPR (x), MEM_EXPR (y)))
{
set_mem_expr (x, 0);
set_mem_expr (y, 0);
set_mem_offset (x, 0);
set_mem_offset (y, 0);
}
else if (MEM_OFFSET (x) != MEM_OFFSET (y))
{
set_mem_offset (x, 0);
set_mem_offset (y, 0);
}
if (!MEM_SIZE (x))
mem_size = NULL_RTX;
else if (!MEM_SIZE (y))
mem_size = NULL_RTX;
else
mem_size = GEN_INT (MAX (INTVAL (MEM_SIZE (x)),
INTVAL (MEM_SIZE (y))));
set_mem_size (x, mem_size);
set_mem_size (y, mem_size);
set_mem_align (x, MIN (MEM_ALIGN (x), MEM_ALIGN (y)));
set_mem_align (y, MEM_ALIGN (x));
}
}
fmt = GET_RTX_FORMAT (code);
for (i = GET_RTX_LENGTH (code) - 1; i >= 0; i--)
{
switch (fmt[i])
{
case 'E':
/* Two vectors must have the same length. */
if (XVECLEN (x, i) != XVECLEN (y, i))
return;
for (j = 0; j < XVECLEN (x, i); j++)
merge_memattrs (XVECEXP (x, i, j), XVECEXP (y, i, j));
break;
case 'e':
merge_memattrs (XEXP (x, i), XEXP (y, i));
}
}
return;
}
/* Return true if I1 and I2 are equivalent and thus can be crossjumped. */
static bool
old_insns_match_p (int mode ATTRIBUTE_UNUSED, rtx i1, rtx i2)
{
rtx p1, p2;
/* Verify that I1 and I2 are equivalent. */
if (GET_CODE (i1) != GET_CODE (i2))
return false;
p1 = PATTERN (i1);
p2 = PATTERN (i2);
if (GET_CODE (p1) != GET_CODE (p2))
return false;
/* If this is a CALL_INSN, compare register usage information.
If we don't check this on stack register machines, the two
CALL_INSNs might be merged leaving reg-stack.c with mismatching
numbers of stack registers in the same basic block.
If we don't check this on machines with delay slots, a delay slot may
be filled that clobbers a parameter expected by the subroutine.
??? We take the simple route for now and assume that if they're
equal, they were constructed identically. */
if (CALL_P (i1)
&& (!rtx_equal_p (CALL_INSN_FUNCTION_USAGE (i1),
CALL_INSN_FUNCTION_USAGE (i2))
|| SIBLING_CALL_P (i1) != SIBLING_CALL_P (i2)))
return false;
#ifdef STACK_REGS
/* If cross_jump_death_matters is not 0, the insn's mode
indicates whether or not the insn contains any stack-like
regs. */
if ((mode & CLEANUP_POST_REGSTACK) && stack_regs_mentioned (i1))
{
/* If register stack conversion has already been done, then
death notes must also be compared before it is certain that
the two instruction streams match. */
rtx note;
HARD_REG_SET i1_regset, i2_regset;
CLEAR_HARD_REG_SET (i1_regset);
CLEAR_HARD_REG_SET (i2_regset);
for (note = REG_NOTES (i1); note; note = XEXP (note, 1))
if (REG_NOTE_KIND (note) == REG_DEAD && STACK_REG_P (XEXP (note, 0)))
SET_HARD_REG_BIT (i1_regset, REGNO (XEXP (note, 0)));
for (note = REG_NOTES (i2); note; note = XEXP (note, 1))
if (REG_NOTE_KIND (note) == REG_DEAD && STACK_REG_P (XEXP (note, 0)))
SET_HARD_REG_BIT (i2_regset, REGNO (XEXP (note, 0)));
if (!hard_reg_set_equal_p (i1_regset, i2_regset))
return false;
}
#endif
if (reload_completed
? rtx_renumbered_equal_p (p1, p2) : rtx_equal_p (p1, p2))
return true;
/* Do not do EQUIV substitution after reload. First, we're undoing the
work of reload_cse. Second, we may be undoing the work of the post-
reload splitting pass. */
/* ??? Possibly add a new phase switch variable that can be used by
targets to disallow the troublesome insns after splitting. */
if (!reload_completed)
{
/* The following code helps take care of G++ cleanups. */
rtx equiv1 = find_reg_equal_equiv_note (i1);
rtx equiv2 = find_reg_equal_equiv_note (i2);
if (equiv1 && equiv2
/* If the equivalences are not to a constant, they may
reference pseudos that no longer exist, so we can't
use them. */
&& (! reload_completed
|| (CONSTANT_P (XEXP (equiv1, 0))
&& rtx_equal_p (XEXP (equiv1, 0), XEXP (equiv2, 0)))))
{
rtx s1 = single_set (i1);
rtx s2 = single_set (i2);
if (s1 != 0 && s2 != 0
&& rtx_renumbered_equal_p (SET_DEST (s1), SET_DEST (s2)))
{
validate_change (i1, &SET_SRC (s1), XEXP (equiv1, 0), 1);
validate_change (i2, &SET_SRC (s2), XEXP (equiv2, 0), 1);
if (! rtx_renumbered_equal_p (p1, p2))
cancel_changes (0);
else if (apply_change_group ())
return true;
}
}
}
return false;
}
/* Look through the insns at the end of BB1 and BB2 and find the longest
sequence that are equivalent. Store the first insns for that sequence
in *F1 and *F2 and return the sequence length.
To simplify callers of this function, if the blocks match exactly,
store the head of the blocks in *F1 and *F2. */
static int
flow_find_cross_jump (int mode ATTRIBUTE_UNUSED, basic_block bb1,
basic_block bb2, rtx *f1, rtx *f2)
{
rtx i1, i2, last1, last2, afterlast1, afterlast2;
int ninsns = 0;
/* Skip simple jumps at the end of the blocks. Complex jumps still
need to be compared for equivalence, which we'll do below. */
i1 = BB_END (bb1);
last1 = afterlast1 = last2 = afterlast2 = NULL_RTX;
if (onlyjump_p (i1)
|| (returnjump_p (i1) && !side_effects_p (PATTERN (i1))))
{
last1 = i1;
i1 = PREV_INSN (i1);
}
i2 = BB_END (bb2);
if (onlyjump_p (i2)
|| (returnjump_p (i2) && !side_effects_p (PATTERN (i2))))
{
last2 = i2;
/* Count everything except for unconditional jump as insn. */
if (!simplejump_p (i2) && !returnjump_p (i2) && last1)
ninsns++;
i2 = PREV_INSN (i2);
}
while (true)
{
/* Ignore notes. */
while (!INSN_P (i1) && i1 != BB_HEAD (bb1))
i1 = PREV_INSN (i1);
while (!INSN_P (i2) && i2 != BB_HEAD (bb2))
i2 = PREV_INSN (i2);
if (i1 == BB_HEAD (bb1) || i2 == BB_HEAD (bb2))
break;
if (!old_insns_match_p (mode, i1, i2))
break;
merge_memattrs (i1, i2);
/* Don't begin a cross-jump with a NOTE insn. */
if (INSN_P (i1))
{
/* If the merged insns have different REG_EQUAL notes, then
remove them. */
rtx equiv1 = find_reg_equal_equiv_note (i1);
rtx equiv2 = find_reg_equal_equiv_note (i2);
if (equiv1 && !equiv2)
remove_note (i1, equiv1);
else if (!equiv1 && equiv2)
remove_note (i2, equiv2);
else if (equiv1 && equiv2
&& !rtx_equal_p (XEXP (equiv1, 0), XEXP (equiv2, 0)))
{
remove_note (i1, equiv1);
remove_note (i2, equiv2);
}
afterlast1 = last1, afterlast2 = last2;
last1 = i1, last2 = i2;
ninsns++;
}
i1 = PREV_INSN (i1);
i2 = PREV_INSN (i2);
}
#ifdef HAVE_cc0
/* Don't allow the insn after a compare to be shared by
cross-jumping unless the compare is also shared. */
if (ninsns && reg_mentioned_p (cc0_rtx, last1) && ! sets_cc0_p (last1))
last1 = afterlast1, last2 = afterlast2, ninsns--;
#endif
/* Include preceding notes and labels in the cross-jump. One,
this may bring us to the head of the blocks as requested above.
Two, it keeps line number notes as matched as may be. */
if (ninsns)
{
while (last1 != BB_HEAD (bb1) && !INSN_P (PREV_INSN (last1)))
last1 = PREV_INSN (last1);
if (last1 != BB_HEAD (bb1) && LABEL_P (PREV_INSN (last1)))
last1 = PREV_INSN (last1);
while (last2 != BB_HEAD (bb2) && !INSN_P (PREV_INSN (last2)))
last2 = PREV_INSN (last2);
if (last2 != BB_HEAD (bb2) && LABEL_P (PREV_INSN (last2)))
last2 = PREV_INSN (last2);
*f1 = last1;
*f2 = last2;
}
return ninsns;
}
/* Return true iff outgoing edges of BB1 and BB2 match, together with
the branch instruction. This means that if we commonize the control
flow before end of the basic block, the semantic remains unchanged.
We may assume that there exists one edge with a common destination. */
static bool
outgoing_edges_match (int mode, basic_block bb1, basic_block bb2)
{
int nehedges1 = 0, nehedges2 = 0;
edge fallthru1 = 0, fallthru2 = 0;
edge e1, e2;
edge_iterator ei;
/* If BB1 has only one successor, we may be looking at either an
unconditional jump, or a fake edge to exit. */
if (single_succ_p (bb1)
&& (single_succ_edge (bb1)->flags & (EDGE_COMPLEX | EDGE_FAKE)) == 0
&& (!JUMP_P (BB_END (bb1)) || simplejump_p (BB_END (bb1))))
return (single_succ_p (bb2)
&& (single_succ_edge (bb2)->flags
& (EDGE_COMPLEX | EDGE_FAKE)) == 0
&& (!JUMP_P (BB_END (bb2)) || simplejump_p (BB_END (bb2))));
/* Match conditional jumps - this may get tricky when fallthru and branch
edges are crossed. */
if (EDGE_COUNT (bb1->succs) == 2
&& any_condjump_p (BB_END (bb1))
&& onlyjump_p (BB_END (bb1)))
{
edge b1, f1, b2, f2;
bool reverse, match;
rtx set1, set2, cond1, cond2;
enum rtx_code code1, code2;
if (EDGE_COUNT (bb2->succs) != 2
|| !any_condjump_p (BB_END (bb2))
|| !onlyjump_p (BB_END (bb2)))
return false;
b1 = BRANCH_EDGE (bb1);
b2 = BRANCH_EDGE (bb2);
f1 = FALLTHRU_EDGE (bb1);
f2 = FALLTHRU_EDGE (bb2);
/* Get around possible forwarders on fallthru edges. Other cases
should be optimized out already. */
if (FORWARDER_BLOCK_P (f1->dest))
f1 = single_succ_edge (f1->dest);
if (FORWARDER_BLOCK_P (f2->dest))
f2 = single_succ_edge (f2->dest);
/* To simplify use of this function, return false if there are
unneeded forwarder blocks. These will get eliminated later
during cleanup_cfg. */
if (FORWARDER_BLOCK_P (f1->dest)
|| FORWARDER_BLOCK_P (f2->dest)
|| FORWARDER_BLOCK_P (b1->dest)
|| FORWARDER_BLOCK_P (b2->dest))
return false;
if (f1->dest == f2->dest && b1->dest == b2->dest)
reverse = false;
else if (f1->dest == b2->dest && b1->dest == f2->dest)
reverse = true;
else
return false;
set1 = pc_set (BB_END (bb1));
set2 = pc_set (BB_END (bb2));
if ((XEXP (SET_SRC (set1), 1) == pc_rtx)
!= (XEXP (SET_SRC (set2), 1) == pc_rtx))
reverse = !reverse;
cond1 = XEXP (SET_SRC (set1), 0);
cond2 = XEXP (SET_SRC (set2), 0);
code1 = GET_CODE (cond1);
if (reverse)
code2 = reversed_comparison_code (cond2, BB_END (bb2));
else
code2 = GET_CODE (cond2);
if (code2 == UNKNOWN)
return false;
/* Verify codes and operands match. */
match = ((code1 == code2
&& rtx_renumbered_equal_p (XEXP (cond1, 0), XEXP (cond2, 0))
&& rtx_renumbered_equal_p (XEXP (cond1, 1), XEXP (cond2, 1)))
|| (code1 == swap_condition (code2)
&& rtx_renumbered_equal_p (XEXP (cond1, 1),
XEXP (cond2, 0))
&& rtx_renumbered_equal_p (XEXP (cond1, 0),
XEXP (cond2, 1))));
/* If we return true, we will join the blocks. Which means that
we will only have one branch prediction bit to work with. Thus
we require the existing branches to have probabilities that are
roughly similar. */
if (match
&& !optimize_size
&& maybe_hot_bb_p (bb1)
&& maybe_hot_bb_p (bb2))
{
int prob2;
if (b1->dest == b2->dest)
prob2 = b2->probability;
else
/* Do not use f2 probability as f2 may be forwarded. */
prob2 = REG_BR_PROB_BASE - b2->probability;
/* Fail if the difference in probabilities is greater than 50%.
This rules out two well-predicted branches with opposite
outcomes. */
if (abs (b1->probability - prob2) > REG_BR_PROB_BASE / 2)
{
if (dump_file)
fprintf (dump_file,
"Outcomes of branch in bb %i and %i differ too much (%i %i)\n",
bb1->index, bb2->index, b1->probability, prob2);
return false;
}
}
if (dump_file && match)
fprintf (dump_file, "Conditionals in bb %i and %i match.\n",
bb1->index, bb2->index);
return match;
}
/* Generic case - we are seeing a computed jump, table jump or trapping
instruction. */
/* Check whether there are tablejumps in the end of BB1 and BB2.
Return true if they are identical. */
{
rtx label1, label2;
rtx table1, table2;
if (tablejump_p (BB_END (bb1), &label1, &table1)
&& tablejump_p (BB_END (bb2), &label2, &table2)
&& GET_CODE (PATTERN (table1)) == GET_CODE (PATTERN (table2)))
{
/* The labels should never be the same rtx. If they really are same
the jump tables are same too. So disable crossjumping of blocks BB1
and BB2 because when deleting the common insns in the end of BB1
by delete_basic_block () the jump table would be deleted too. */
/* If LABEL2 is referenced in BB1->END do not do anything
because we would loose information when replacing
LABEL1 by LABEL2 and then LABEL2 by LABEL1 in BB1->END. */
if (label1 != label2 && !rtx_referenced_p (label2, BB_END (bb1)))
{
/* Set IDENTICAL to true when the tables are identical. */
bool identical = false;
rtx p1, p2;
p1 = PATTERN (table1);
p2 = PATTERN (table2);
if (GET_CODE (p1) == ADDR_VEC && rtx_equal_p (p1, p2))
{
identical = true;
}
else if (GET_CODE (p1) == ADDR_DIFF_VEC
&& (XVECLEN (p1, 1) == XVECLEN (p2, 1))
&& rtx_equal_p (XEXP (p1, 2), XEXP (p2, 2))
&& rtx_equal_p (XEXP (p1, 3), XEXP (p2, 3)))
{
int i;
identical = true;
for (i = XVECLEN (p1, 1) - 1; i >= 0 && identical; i--)
if (!rtx_equal_p (XVECEXP (p1, 1, i), XVECEXP (p2, 1, i)))
identical = false;
}
if (identical)
{
replace_label_data rr;
bool match;
/* Temporarily replace references to LABEL1 with LABEL2
in BB1->END so that we could compare the instructions. */
rr.r1 = label1;
rr.r2 = label2;
rr.update_label_nuses = false;
for_each_rtx (&BB_END (bb1), replace_label, &rr);
match = old_insns_match_p (mode, BB_END (bb1), BB_END (bb2));
if (dump_file && match)
fprintf (dump_file,
"Tablejumps in bb %i and %i match.\n",
bb1->index, bb2->index);
/* Set the original label in BB1->END because when deleting
a block whose end is a tablejump, the tablejump referenced
from the instruction is deleted too. */
rr.r1 = label2;
rr.r2 = label1;
for_each_rtx (&BB_END (bb1), replace_label, &rr);
return match;
}
}
return false;
}
}
/* First ensure that the instructions match. There may be many outgoing
edges so this test is generally cheaper. */
if (!old_insns_match_p (mode, BB_END (bb1), BB_END (bb2)))
return false;
/* Search the outgoing edges, ensure that the counts do match, find possible
fallthru and exception handling edges since these needs more
validation. */
if (EDGE_COUNT (bb1->succs) != EDGE_COUNT (bb2->succs))
return false;
FOR_EACH_EDGE (e1, ei, bb1->succs)
{
e2 = EDGE_SUCC (bb2, ei.index);
if (e1->flags & EDGE_EH)
nehedges1++;
if (e2->flags & EDGE_EH)
nehedges2++;
if (e1->flags & EDGE_FALLTHRU)
fallthru1 = e1;
if (e2->flags & EDGE_FALLTHRU)
fallthru2 = e2;
}
/* If number of edges of various types does not match, fail. */
if (nehedges1 != nehedges2
|| (fallthru1 != 0) != (fallthru2 != 0))
return false;
/* fallthru edges must be forwarded to the same destination. */
if (fallthru1)
{
basic_block d1 = (forwarder_block_p (fallthru1->dest)
? single_succ (fallthru1->dest): fallthru1->dest);
basic_block d2 = (forwarder_block_p (fallthru2->dest)
? single_succ (fallthru2->dest): fallthru2->dest);
if (d1 != d2)
return false;
}
/* Ensure the same EH region. */
{
rtx n1 = find_reg_note (BB_END (bb1), REG_EH_REGION, 0);
rtx n2 = find_reg_note (BB_END (bb2), REG_EH_REGION, 0);
if (!n1 && n2)
return false;
if (n1 && (!n2 || XEXP (n1, 0) != XEXP (n2, 0)))
return false;
}
/* The same checks as in try_crossjump_to_edge. It is required for RTL
version of sequence abstraction. */
FOR_EACH_EDGE (e1, ei, bb2->succs)
{
edge e2;
edge_iterator ei;
basic_block d1 = e1->dest;
if (FORWARDER_BLOCK_P (d1))
d1 = EDGE_SUCC (d1, 0)->dest;
FOR_EACH_EDGE (e2, ei, bb1->succs)
{
basic_block d2 = e2->dest;
if (FORWARDER_BLOCK_P (d2))
d2 = EDGE_SUCC (d2, 0)->dest;
if (d1 == d2)
break;
}
if (!e2)
return false;
}
return true;
}
/* Returns true if BB basic block has a preserve label. */
static bool
block_has_preserve_label (basic_block bb)
{
return (bb
&& block_label (bb)
&& LABEL_PRESERVE_P (block_label (bb)));
}
/* E1 and E2 are edges with the same destination block. Search their
predecessors for common code. If found, redirect control flow from
(maybe the middle of) E1->SRC to (maybe the middle of) E2->SRC. */
static bool
try_crossjump_to_edge (int mode, edge e1, edge e2)
{
int nmatch;
basic_block src1 = e1->src, src2 = e2->src;
basic_block redirect_to, redirect_from, to_remove;
rtx newpos1, newpos2;
edge s;
edge_iterator ei;
newpos1 = newpos2 = NULL_RTX;
/* If we have partitioned hot/cold basic blocks, it is a bad idea
to try this optimization.
Basic block partitioning may result in some jumps that appear to
be optimizable (or blocks that appear to be mergeable), but which really
must be left untouched (they are required to make it safely across
partition boundaries). See the comments at the top of
bb-reorder.c:partition_hot_cold_basic_blocks for complete details. */
if (flag_reorder_blocks_and_partition && reload_completed)
return false;
/* Search backward through forwarder blocks. We don't need to worry
about multiple entry or chained forwarders, as they will be optimized
away. We do this to look past the unconditional jump following a
conditional jump that is required due to the current CFG shape. */
if (single_pred_p (src1)
&& FORWARDER_BLOCK_P (src1))
e1 = single_pred_edge (src1), src1 = e1->src;
if (single_pred_p (src2)
&& FORWARDER_BLOCK_P (src2))
e2 = single_pred_edge (src2), src2 = e2->src;
/* Nothing to do if we reach ENTRY, or a common source block. */
if (src1 == ENTRY_BLOCK_PTR || src2 == ENTRY_BLOCK_PTR)
return false;
if (src1 == src2)
return false;
/* Seeing more than 1 forwarder blocks would confuse us later... */
if (FORWARDER_BLOCK_P (e1->dest)
&& FORWARDER_BLOCK_P (single_succ (e1->dest)))
return false;
if (FORWARDER_BLOCK_P (e2->dest)
&& FORWARDER_BLOCK_P (single_succ (e2->dest)))
return false;
/* Likewise with dead code (possibly newly created by the other optimizations
of cfg_cleanup). */
if (EDGE_COUNT (src1->preds) == 0 || EDGE_COUNT (src2->preds) == 0)
return false;
/* Look for the common insn sequence, part the first ... */
if (!outgoing_edges_match (mode, src1, src2))
return false;
/* ... and part the second. */
nmatch = flow_find_cross_jump (mode, src1, src2, &newpos1, &newpos2);
/* Don't proceed with the crossjump unless we found a sufficient number
of matching instructions or the 'from' block was totally matched
(such that its predecessors will hopefully be redirected and the
block removed). */
if ((nmatch < PARAM_VALUE (PARAM_MIN_CROSSJUMP_INSNS))
&& (newpos1 != BB_HEAD (src1)))
return false;
/* Avoid deleting preserve label when redirecting ABNORMAL edges. */
if (block_has_preserve_label (e1->dest)
&& (e1->flags & EDGE_ABNORMAL))
return false;
/* Here we know that the insns in the end of SRC1 which are common with SRC2
will be deleted.
If we have tablejumps in the end of SRC1 and SRC2
they have been already compared for equivalence in outgoing_edges_match ()
so replace the references to TABLE1 by references to TABLE2. */
{
rtx label1, label2;
rtx table1, table2;
if (tablejump_p (BB_END (src1), &label1, &table1)
&& tablejump_p (BB_END (src2), &label2, &table2)
&& label1 != label2)
{
replace_label_data rr;
rtx insn;
/* Replace references to LABEL1 with LABEL2. */
rr.r1 = label1;
rr.r2 = label2;
rr.update_label_nuses = true;
for (insn = get_insns (); insn; insn = NEXT_INSN (insn))
{
/* Do not replace the label in SRC1->END because when deleting
a block whose end is a tablejump, the tablejump referenced
from the instruction is deleted too. */
if (insn != BB_END (src1))
for_each_rtx (&insn, replace_label, &rr);
}
}
}
/* Avoid splitting if possible. We must always split when SRC2 has
EH predecessor edges, or we may end up with basic blocks with both
normal and EH predecessor edges. */
if (newpos2 == BB_HEAD (src2)
&& !(EDGE_PRED (src2, 0)->flags & EDGE_EH))
redirect_to = src2;
else
{
if (newpos2 == BB_HEAD (src2))
{
/* Skip possible basic block header. */
if (LABEL_P (newpos2))
newpos2 = NEXT_INSN (newpos2);
if (NOTE_P (newpos2))
newpos2 = NEXT_INSN (newpos2);
}
if (dump_file)
fprintf (dump_file, "Splitting bb %i before %i insns\n",
src2->index, nmatch);
redirect_to = split_block (src2, PREV_INSN (newpos2))->dest;
}
if (dump_file)
fprintf (dump_file,
"Cross jumping from bb %i to bb %i; %i common insns\n",
src1->index, src2->index, nmatch);
/* We may have some registers visible through the block. */
df_set_bb_dirty (redirect_to);
/* Recompute the frequencies and counts of outgoing edges. */
FOR_EACH_EDGE (s, ei, redirect_to->succs)
{
edge s2;
edge_iterator ei;
basic_block d = s->dest;
if (FORWARDER_BLOCK_P (d))
d = single_succ (d);
FOR_EACH_EDGE (s2, ei, src1->succs)
{
basic_block d2 = s2->dest;
if (FORWARDER_BLOCK_P (d2))
d2 = single_succ (d2);
if (d == d2)
break;
}
s->count += s2->count;
/* Take care to update possible forwarder blocks. We verified
that there is no more than one in the chain, so we can't run
into infinite loop. */
if (FORWARDER_BLOCK_P (s->dest))
{
single_succ_edge (s->dest)->count += s2->count;
s->dest->count += s2->count;
s->dest->frequency += EDGE_FREQUENCY (s);
}
if (FORWARDER_BLOCK_P (s2->dest))
{
single_succ_edge (s2->dest)->count -= s2->count;
if (single_succ_edge (s2->dest)->count < 0)
single_succ_edge (s2->dest)->count = 0;
s2->dest->count -= s2->count;
s2->dest->frequency -= EDGE_FREQUENCY (s);
if (s2->dest->frequency < 0)
s2->dest->frequency = 0;
if (s2->dest->count < 0)
s2->dest->count = 0;
}
if (!redirect_to->frequency && !src1->frequency)
s->probability = (s->probability + s2->probability) / 2;
else
s->probability
= ((s->probability * redirect_to->frequency +
s2->probability * src1->frequency)
/ (redirect_to->frequency + src1->frequency));
}
/* Adjust count and frequency for the block. An earlier jump
threading pass may have left the profile in an inconsistent
state (see update_bb_profile_for_threading) so we must be
prepared for overflows. */
redirect_to->count += src1->count;
redirect_to->frequency += src1->frequency;
if (redirect_to->frequency > BB_FREQ_MAX)
redirect_to->frequency = BB_FREQ_MAX;
update_br_prob_note (redirect_to);
/* Edit SRC1 to go to REDIRECT_TO at NEWPOS1. */
/* Skip possible basic block header. */
if (LABEL_P (newpos1))
newpos1 = NEXT_INSN (newpos1);
if (NOTE_P (newpos1))
newpos1 = NEXT_INSN (newpos1);
redirect_from = split_block (src1, PREV_INSN (newpos1))->src;
to_remove = single_succ (redirect_from);
redirect_edge_and_branch_force (single_succ_edge (redirect_from), redirect_to);
delete_basic_block (to_remove);
update_forwarder_flag (redirect_from);
if (redirect_to != src2)
update_forwarder_flag (src2);
return true;
}
/* Search the predecessors of BB for common insn sequences. When found,
share code between them by redirecting control flow. Return true if
any changes made. */
static bool
try_crossjump_bb (int mode, basic_block bb)
{
edge e, e2, fallthru;
bool changed;
unsigned max, ix, ix2;
basic_block ev, ev2;
edge_iterator ei;
/* Nothing to do if there is not at least two incoming edges. */
if (EDGE_COUNT (bb->preds) < 2)
return false;
/* Don't crossjump if this block ends in a computed jump,
unless we are optimizing for size. */
if (!optimize_size
&& bb != EXIT_BLOCK_PTR
&& computed_jump_p (BB_END (bb)))
return false;
/* If we are partitioning hot/cold basic blocks, we don't want to
mess up unconditional or indirect jumps that cross between hot
and cold sections.
Basic block partitioning may result in some jumps that appear to
be optimizable (or blocks that appear to be mergeable), but which really
must be left untouched (they are required to make it safely across
partition boundaries). See the comments at the top of
bb-reorder.c:partition_hot_cold_basic_blocks for complete details. */
if (BB_PARTITION (EDGE_PRED (bb, 0)->src) !=
BB_PARTITION (EDGE_PRED (bb, 1)->src)
|| (EDGE_PRED (bb, 0)->flags & EDGE_CROSSING))
return false;
/* It is always cheapest to redirect a block that ends in a branch to
a block that falls through into BB, as that adds no branches to the
program. We'll try that combination first. */
fallthru = NULL;
max = PARAM_VALUE (PARAM_MAX_CROSSJUMP_EDGES);
if (EDGE_COUNT (bb->preds) > max)
return false;
FOR_EACH_EDGE (e, ei, bb->preds)
{
if (e->flags & EDGE_FALLTHRU)
{
fallthru = e;
break;
}
}
changed = false;
for (ix = 0, ev = bb; ix < EDGE_COUNT (ev->preds); )
{
e = EDGE_PRED (ev, ix);
ix++;
/* As noted above, first try with the fallthru predecessor (or, a
fallthru predecessor if we are in cfglayout mode). */
if (fallthru)
{
/* Don't combine the fallthru edge into anything else.
If there is a match, we'll do it the other way around. */
if (e == fallthru)
continue;
/* If nothing changed since the last attempt, there is nothing
we can do. */
if (!first_pass
&& (!(df_get_bb_dirty (e->src))
&& !(df_get_bb_dirty (fallthru->src))))
continue;
if (try_crossjump_to_edge (mode, e, fallthru))
{
changed = true;
ix = 0;
ev = bb;
continue;
}
}
/* Non-obvious work limiting check: Recognize that we're going
to call try_crossjump_bb on every basic block. So if we have
two blocks with lots of outgoing edges (a switch) and they
share lots of common destinations, then we would do the
cross-jump check once for each common destination.
Now, if the blocks actually are cross-jump candidates, then
all of their destinations will be shared. Which means that
we only need check them for cross-jump candidacy once. We
can eliminate redundant checks of crossjump(A,B) by arbitrarily
choosing to do the check from the block for which the edge
in question is the first successor of A. */
if (EDGE_SUCC (e->src, 0) != e)
continue;
for (ix2 = 0, ev2 = bb; ix2 < EDGE_COUNT (ev2->preds); )
{
e2 = EDGE_PRED (ev2, ix2);
ix2++;
if (e2 == e)
continue;
/* We've already checked the fallthru edge above. */
if (e2 == fallthru)
continue;
/* The "first successor" check above only prevents multiple
checks of crossjump(A,B). In order to prevent redundant
checks of crossjump(B,A), require that A be the block
with the lowest index. */
if (e->src->index > e2->src->index)
continue;
/* If nothing changed since the last attempt, there is nothing
we can do. */
if (!first_pass
&& (!(df_get_bb_dirty (e->src))
&& !(df_get_bb_dirty (e2->src))))
continue;
if (try_crossjump_to_edge (mode, e, e2))
{
changed = true;
ev2 = bb;
ix = 0;
break;
}
}
}
if (changed)
crossjumps_occured = true;
return changed;
}
/* Do simple CFG optimizations - basic block merging, simplifying of jump
instructions etc. Return nonzero if changes were made. */
static bool
try_optimize_cfg (int mode)
{
bool changed_overall = false;
bool changed;
int iterations = 0;
basic_block bb, b, next;
if (mode & (CLEANUP_CROSSJUMP | CLEANUP_THREADING))
clear_bb_flags ();
crossjumps_occured = false;
FOR_EACH_BB (bb)
update_forwarder_flag (bb);
if (! targetm.cannot_modify_jumps_p ())
{
first_pass = true;
/* Attempt to merge blocks as made possible by edge removal. If
a block has only one successor, and the successor has only
one predecessor, they may be combined. */
do
{
changed = false;
iterations++;
if (dump_file)
fprintf (dump_file,
"\n\ntry_optimize_cfg iteration %i\n\n",
iterations);
for (b = ENTRY_BLOCK_PTR->next_bb; b != EXIT_BLOCK_PTR;)
{
basic_block c;
edge s;
bool changed_here = false;
/* Delete trivially dead basic blocks. */
if (EDGE_COUNT (b->preds) == 0)
{
c = b->prev_bb;
if (dump_file)
fprintf (dump_file, "Deleting block %i.\n",
b->index);
delete_basic_block (b);
if (!(mode & CLEANUP_CFGLAYOUT))
changed = true;
/* Avoid trying to remove ENTRY_BLOCK_PTR. */
b = (c == ENTRY_BLOCK_PTR ? c->next_bb : c);
continue;
}
/* Remove code labels no longer used. */
if (single_pred_p (b)
&& (single_pred_edge (b)->flags & EDGE_FALLTHRU)
&& !(single_pred_edge (b)->flags & EDGE_COMPLEX)
&& LABEL_P (BB_HEAD (b))
/* If the previous block ends with a branch to this
block, we can't delete the label. Normally this
is a condjump that is yet to be simplified, but
if CASE_DROPS_THRU, this can be a tablejump with
some element going to the same place as the
default (fallthru). */
&& (single_pred (b) == ENTRY_BLOCK_PTR
|| !JUMP_P (BB_END (single_pred (b)))
|| ! label_is_jump_target_p (BB_HEAD (b),
BB_END (single_pred (b)))))
{
rtx label = BB_HEAD (b);
delete_insn_chain (label, label, false);
/* If the case label is undeletable, move it after the
BASIC_BLOCK note. */
if (NOTE_KIND (BB_HEAD (b)) == NOTE_INSN_DELETED_LABEL)
{
rtx bb_note = NEXT_INSN (BB_HEAD (b));
reorder_insns_nobb (label, label, bb_note);
BB_HEAD (b) = bb_note;
if (BB_END (b) == bb_note)
BB_END (b) = label;
}
if (dump_file)
fprintf (dump_file, "Deleted label in block %i.\n",
b->index);
}
/* If we fall through an empty block, we can remove it. */
if (!(mode & CLEANUP_CFGLAYOUT)
&& single_pred_p (b)
&& (single_pred_edge (b)->flags & EDGE_FALLTHRU)
&& !LABEL_P (BB_HEAD (b))
&& FORWARDER_BLOCK_P (b)
/* Note that forwarder_block_p true ensures that
there is a successor for this block. */
&& (single_succ_edge (b)->flags & EDGE_FALLTHRU)
&& n_basic_blocks > NUM_FIXED_BLOCKS + 1)
{
if (dump_file)
fprintf (dump_file,
"Deleting fallthru block %i.\n",
b->index);
c = b->prev_bb == ENTRY_BLOCK_PTR ? b->next_bb : b->prev_bb;
redirect_edge_succ_nodup (single_pred_edge (b),
single_succ (b));
delete_basic_block (b);
changed = true;
b = c;
}
if (single_succ_p (b)
&& (s = single_succ_edge (b))
&& !(s->flags & EDGE_COMPLEX)
&& (c = s->dest) != EXIT_BLOCK_PTR
&& single_pred_p (c)
&& b != c)
{
/* When not in cfg_layout mode use code aware of reordering
INSN. This code possibly creates new basic blocks so it
does not fit merge_blocks interface and is kept here in
hope that it will become useless once more of compiler
is transformed to use cfg_layout mode. */
if ((mode & CLEANUP_CFGLAYOUT)
&& can_merge_blocks_p (b, c))
{
merge_blocks (b, c);
update_forwarder_flag (b);
changed_here = true;
}
else if (!(mode & CLEANUP_CFGLAYOUT)
/* If the jump insn has side effects,
we can't kill the edge. */
&& (!JUMP_P (BB_END (b))
|| (reload_completed
? simplejump_p (BB_END (b))
: (onlyjump_p (BB_END (b))
&& !tablejump_p (BB_END (b),
NULL, NULL))))
&& (next = merge_blocks_move (s, b, c, mode)))
{
b = next;
changed_here = true;
}
}
/* Simplify branch over branch. */
if ((mode & CLEANUP_EXPENSIVE)
&& !(mode & CLEANUP_CFGLAYOUT)
&& try_simplify_condjump (b))
changed_here = true;
/* If B has a single outgoing edge, but uses a
non-trivial jump instruction without side-effects, we
can either delete the jump entirely, or replace it
with a simple unconditional jump. */
if (single_succ_p (b)
&& single_succ (b) != EXIT_BLOCK_PTR
&& onlyjump_p (BB_END (b))
&& !find_reg_note (BB_END (b), REG_CROSSING_JUMP, NULL_RTX)
&& try_redirect_by_replacing_jump (single_succ_edge (b),
single_succ (b),
(mode & CLEANUP_CFGLAYOUT) != 0))
{
update_forwarder_flag (b);
changed_here = true;
}
/* Simplify branch to branch. */
if (try_forward_edges (mode, b))
changed_here = true;
/* Look for shared code between blocks. */
if ((mode & CLEANUP_CROSSJUMP)
&& try_crossjump_bb (mode, b))
changed_here = true;
/* Don't get confused by the index shift caused by
deleting blocks. */
if (!changed_here)
b = b->next_bb;
else
changed = true;
}
if ((mode & CLEANUP_CROSSJUMP)
&& try_crossjump_bb (mode, EXIT_BLOCK_PTR))
changed = true;
#ifdef ENABLE_CHECKING
if (changed)
verify_flow_info ();
#endif
changed_overall |= changed;
first_pass = false;
}
while (changed);
}
FOR_ALL_BB (b)
b->flags &= ~(BB_FORWARDER_BLOCK | BB_NONTHREADABLE_BLOCK);
return changed_overall;
}
/* Delete all unreachable basic blocks. */
bool
delete_unreachable_blocks (void)
{
bool changed = false;
basic_block b, next_bb;
find_unreachable_blocks ();
/* Delete all unreachable basic blocks. */
for (b = ENTRY_BLOCK_PTR->next_bb; b != EXIT_BLOCK_PTR; b = next_bb)
{
next_bb = b->next_bb;
if (!(b->flags & BB_REACHABLE))
{
delete_basic_block (b);
changed = true;
}
}
if (changed)
tidy_fallthru_edges ();
return changed;
}
/* Delete any jump tables never referenced. We can't delete them at the
time of removing tablejump insn as they are referenced by the preceding
insns computing the destination, so we delay deleting and garbagecollect
them once life information is computed. */
void
delete_dead_jumptables (void)
{
basic_block bb;
/* A dead jump table does not belong to any basic block. Scan insns
between two adjacent basic blocks. */
FOR_EACH_BB (bb)
{
rtx insn, next;
for (insn = NEXT_INSN (BB_END (bb));
insn && !NOTE_INSN_BASIC_BLOCK_P (insn);
insn = next)
{
next = NEXT_INSN (insn);
if (LABEL_P (insn)
&& LABEL_NUSES (insn) == LABEL_PRESERVE_P (insn)
&& JUMP_P (next)
&& (GET_CODE (PATTERN (next)) == ADDR_VEC
|| GET_CODE (PATTERN (next)) == ADDR_DIFF_VEC))
{
rtx label = insn, jump = next;
if (dump_file)
fprintf (dump_file, "Dead jumptable %i removed\n",
INSN_UID (insn));
next = NEXT_INSN (next);
delete_insn (jump);
delete_insn (label);
}
}
}
}
/* Tidy the CFG by deleting unreachable code and whatnot. */
bool
cleanup_cfg (int mode)
{
bool changed = false;
/* Set the cfglayout mode flag here. We could update all the callers
but that is just inconvenient, especially given that we eventually
want to have cfglayout mode as the default. */
if (current_ir_type () == IR_RTL_CFGLAYOUT)
mode |= CLEANUP_CFGLAYOUT;
timevar_push (TV_CLEANUP_CFG);
if (delete_unreachable_blocks ())
{
changed = true;
/* We've possibly created trivially dead code. Cleanup it right
now to introduce more opportunities for try_optimize_cfg. */
if (!(mode & (CLEANUP_NO_INSN_DEL))
&& !reload_completed)
delete_trivially_dead_insns (get_insns (), max_reg_num ());
}
compact_blocks ();
/* To tail-merge blocks ending in the same noreturn function (e.g.
a call to abort) we have to insert fake edges to exit. Do this
here once. The fake edges do not interfere with any other CFG
cleanups. */
if (mode & CLEANUP_CROSSJUMP)
add_noreturn_fake_exit_edges ();
if (!dbg_cnt (cfg_cleanup))
return changed;
while (try_optimize_cfg (mode))
{
delete_unreachable_blocks (), changed = true;
if (!(mode & CLEANUP_NO_INSN_DEL))
{
/* Try to remove some trivially dead insns when doing an expensive
cleanup. But delete_trivially_dead_insns doesn't work after
reload (it only handles pseudos) and run_fast_dce is too costly
to run in every iteration.
For effective cross jumping, we really want to run a fast DCE to
clean up any dead conditions, or they get in the way of performing
useful tail merges.
Other transformations in cleanup_cfg are not so sensitive to dead
code, so delete_trivially_dead_insns or even doing nothing at all
is good enough. */
if ((mode & CLEANUP_EXPENSIVE) && !reload_completed
&& !delete_trivially_dead_insns (get_insns (), max_reg_num ()))
break;
else if ((mode & CLEANUP_CROSSJUMP)
&& crossjumps_occured)
run_fast_dce ();
}
else
break;
}
if (mode & CLEANUP_CROSSJUMP)
remove_fake_exit_edges ();
/* Don't call delete_dead_jumptables in cfglayout mode, because
that function assumes that jump tables are in the insns stream.
But we also don't _have_ to delete dead jumptables in cfglayout
mode because we shouldn't even be looking at things that are
not in a basic block. Dead jumptables are cleaned up when
going out of cfglayout mode. */
if (!(mode & CLEANUP_CFGLAYOUT))
delete_dead_jumptables ();
timevar_pop (TV_CLEANUP_CFG);
return changed;
}
static unsigned int
rest_of_handle_jump (void)
{
delete_unreachable_blocks ();
if (cfun->tail_call_emit)
fixup_tail_calls ();
return 0;
}
struct rtl_opt_pass pass_jump =
{
{
RTL_PASS,
"sibling", /* name */
NULL, /* gate */
rest_of_handle_jump, /* execute */
NULL, /* sub */
NULL, /* next */
0, /* static_pass_number */
TV_JUMP, /* tv_id */
0, /* properties_required */
0, /* properties_provided */
0, /* properties_destroyed */
TODO_ggc_collect, /* todo_flags_start */
TODO_verify_flow, /* todo_flags_finish */
}
};
static unsigned int
rest_of_handle_jump2 (void)
{
delete_trivially_dead_insns (get_insns (), max_reg_num ());
if (dump_file)
dump_flow_info (dump_file, dump_flags);
cleanup_cfg ((optimize ? CLEANUP_EXPENSIVE : 0)
| (flag_thread_jumps ? CLEANUP_THREADING : 0));
return 0;
}
struct rtl_opt_pass pass_jump2 =
{
{
RTL_PASS,
"jump", /* name */
NULL, /* gate */
rest_of_handle_jump2, /* execute */
NULL, /* sub */
NULL, /* next */
0, /* static_pass_number */
TV_JUMP, /* tv_id */
0, /* properties_required */
0, /* properties_provided */
0, /* properties_destroyed */
TODO_ggc_collect, /* todo_flags_start */
TODO_dump_func | TODO_verify_rtl_sharing,/* todo_flags_finish */
}
};
|