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
|
/* -----------------------------------------------------------------------------
*
* (c) The GHC Team, 1998-2004
*
* Performing updates.
*
* ---------------------------------------------------------------------------*/
#ifndef UPDATES_H
#define UPDATES_H
#ifndef CMINUSMINUS
BEGIN_RTS_PRIVATE
#endif
/* -----------------------------------------------------------------------------
Updates
-------------------------------------------------------------------------- */
/* LDV profiling:
* We call LDV_recordDead_FILL_SLOP_DYNAMIC(p1) regardless of the generation in
* which p1 resides.
*
* Note:
* After all, we do *NOT* need to call LDV_RECORD_CREATE() for both IND and
* IND_OLDGEN closures because they are inherently used. But, it corrupts
* the invariants that every closure keeps its creation time in the profiling
* field. So, we call LDV_RECORD_CREATE().
*/
/* In the DEBUG case, we also zero out the slop of the old closure,
* so that the sanity checker can tell where the next closure is.
*
* Two important invariants: we should never try to update a closure
* to point to itself, and the closure being updated should not
* already have been updated (the mutable list will get messed up
* otherwise).
*
* NB. We do *not* do this in THREADED_RTS mode, because when we have the
* possibility of multiple threads entering the same closure, zeroing
* the slop in one of the threads would have a disastrous effect on
* the other (seen in the wild!).
*/
#ifdef CMINUSMINUS
#define FILL_SLOP(p) \
W_ inf; \
W_ sz; \
W_ i; \
inf = %GET_STD_INFO(p); \
if (%INFO_TYPE(inf) != HALF_W_(BLACKHOLE) \
&& %INFO_TYPE(inf) != HALF_W_(CAF_BLACKHOLE)) { \
if (%INFO_TYPE(inf) == HALF_W_(THUNK_SELECTOR)) { \
sz = BYTES_TO_WDS(SIZEOF_StgSelector_NoThunkHdr); \
} else { \
if (%INFO_TYPE(inf) == HALF_W_(AP_STACK)) { \
sz = StgAP_STACK_size(p) + BYTES_TO_WDS(SIZEOF_StgAP_STACK_NoThunkHdr); \
} else { \
if (%INFO_TYPE(inf) == HALF_W_(AP)) { \
sz = TO_W_(StgAP_n_args(p)) + BYTES_TO_WDS(SIZEOF_StgAP_NoThunkHdr); \
} else { \
sz = TO_W_(%INFO_PTRS(inf)) + TO_W_(%INFO_NPTRS(inf)); \
} \
} \
} \
i = 0; \
for: \
if (i < sz) { \
StgThunk_payload(p,i) = 0; \
i = i + 1; \
goto for; \
} \
}
#else /* !CMINUSMINUS */
INLINE_HEADER void
FILL_SLOP(StgClosure *p)
{
StgInfoTable *inf = get_itbl(p);
nat i, sz;
switch (inf->type) {
case BLACKHOLE:
case CAF_BLACKHOLE:
goto no_slop;
// we already filled in the slop when we overwrote the thunk
// with BLACKHOLE, and also an evacuated BLACKHOLE is only the
// size of an IND.
case THUNK_SELECTOR:
sz = sizeofW(StgSelector) - sizeofW(StgThunkHeader);
break;
case AP:
sz = ((StgAP *)p)->n_args + sizeofW(StgAP) - sizeofW(StgThunkHeader);
break;
case AP_STACK:
sz = ((StgAP_STACK *)p)->size + sizeofW(StgAP_STACK) - sizeofW(StgThunkHeader);
break;
default:
sz = inf->layout.payload.ptrs + inf->layout.payload.nptrs;
break;
}
for (i = 0; i < sz; i++) {
((StgThunk *)p)->payload[i] = 0;
}
no_slop:
;
}
#endif /* CMINUSMINUS */
#if !defined(DEBUG) || defined(THREADED_RTS)
#define DEBUG_FILL_SLOP(p) /* do nothing */
#else
#define DEBUG_FILL_SLOP(p) FILL_SLOP(p)
#endif
/* We have two versions of this macro (sadly), one for use in C-- code,
* and the other for C.
*
* The and_then argument is a performance hack so that we can paste in
* the continuation code directly. It helps shave a couple of
* instructions off the common case in the update code, which is
* worthwhile (the update code is often part of the inner loop).
* (except that gcc now appears to common up this code again and
* invert the optimisation. Grrrr --SDM).
*/
#ifdef CMINUSMINUS
#define updateWithIndirection(ind_info, p1, p2, and_then) \
W_ bd; \
\
DEBUG_FILL_SLOP(p1); \
LDV_RECORD_DEAD_FILL_SLOP_DYNAMIC(p1); \
StgInd_indirectee(p1) = p2; \
prim %write_barrier() []; \
bd = Bdescr(p1); \
if (bdescr_gen_no(bd) != 0 :: bits16) { \
recordMutableCap(p1, TO_W_(bdescr_gen_no(bd)), R1); \
SET_INFO(p1, stg_IND_OLDGEN_info); \
LDV_RECORD_CREATE(p1); \
TICK_UPD_OLD_IND(); \
and_then; \
} else { \
SET_INFO(p1, ind_info); \
LDV_RECORD_CREATE(p1); \
TICK_UPD_NEW_IND(); \
and_then; \
}
#else /* !CMINUSMINUS */
INLINE_HEADER void updateWithIndirection (Capability *cap,
const StgInfoTable *ind_info,
StgClosure *p1,
StgClosure *p2)
{
bdescr *bd;
ASSERT( (P_)p1 != (P_)p2 );
/* not necessarily true: ASSERT( !closure_IND(p1) ); */
/* occurs in RaiseAsync.c:raiseAsync() */
DEBUG_FILL_SLOP(p1);
LDV_RECORD_DEAD_FILL_SLOP_DYNAMIC(p1);
((StgInd *)p1)->indirectee = p2;
write_barrier();
bd = Bdescr((StgPtr)p1);
if (bd->gen_no != 0) {
recordMutableCap(p1, cap, bd->gen_no);
SET_INFO(p1, &stg_IND_OLDGEN_info);
TICK_UPD_OLD_IND();
} else {
SET_INFO(p1, ind_info);
LDV_RECORD_CREATE(p1);
TICK_UPD_NEW_IND();
}
}
#endif /* CMINUSMINUS */
#define UPD_IND(cap, updclosure, heapptr) \
updateWithIndirection(cap, &stg_IND_info, \
updclosure, \
heapptr)
#ifndef CMINUSMINUS
END_RTS_PRIVATE
#endif
#endif /* UPDATES_H */
|
