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
|
/*
* QEMU coroutines
*
* Copyright IBM, Corp. 2011
*
* Authors:
* Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
* Kevin Wolf <kwolf@redhat.com>
*
* This work is licensed under the terms of the GNU LGPL, version 2 or later.
* See the COPYING.LIB file in the top-level directory.
*
*/
#include "qemu/osdep.h"
#include "trace.h"
#include "qemu/thread.h"
#include "qemu/atomic.h"
#include "qemu/coroutine_int.h"
#include "qemu/coroutine-tls.h"
#include "block/aio.h"
/**
* The minimal batch size is always 64, coroutines from the release_pool are
* reused as soon as there are 64 coroutines in it. The maximum pool size starts
* with 64 and is increased on demand so that coroutines are not deleted even if
* they are not immediately reused.
*/
enum {
POOL_MIN_BATCH_SIZE = 64,
POOL_INITIAL_MAX_SIZE = 64,
};
/** Free list to speed up creation */
static QSLIST_HEAD(, Coroutine) release_pool = QSLIST_HEAD_INITIALIZER(pool);
static unsigned int pool_max_size = POOL_INITIAL_MAX_SIZE;
static unsigned int release_pool_size;
typedef QSLIST_HEAD(, Coroutine) CoroutineQSList;
QEMU_DEFINE_STATIC_CO_TLS(CoroutineQSList, alloc_pool);
QEMU_DEFINE_STATIC_CO_TLS(unsigned int, alloc_pool_size);
QEMU_DEFINE_STATIC_CO_TLS(Notifier, coroutine_pool_cleanup_notifier);
static void coroutine_pool_cleanup(Notifier *n, void *value)
{
Coroutine *co;
Coroutine *tmp;
CoroutineQSList *alloc_pool = get_ptr_alloc_pool();
QSLIST_FOREACH_SAFE(co, alloc_pool, pool_next, tmp) {
QSLIST_REMOVE_HEAD(alloc_pool, pool_next);
qemu_coroutine_delete(co);
}
}
Coroutine *qemu_coroutine_create(CoroutineEntry *entry, void *opaque)
{
Coroutine *co = NULL;
if (CONFIG_COROUTINE_POOL) {
CoroutineQSList *alloc_pool = get_ptr_alloc_pool();
co = QSLIST_FIRST(alloc_pool);
if (!co) {
if (release_pool_size > POOL_MIN_BATCH_SIZE) {
/* Slow path; a good place to register the destructor, too. */
Notifier *notifier = get_ptr_coroutine_pool_cleanup_notifier();
if (!notifier->notify) {
notifier->notify = coroutine_pool_cleanup;
qemu_thread_atexit_add(notifier);
}
/* This is not exact; there could be a little skew between
* release_pool_size and the actual size of release_pool. But
* it is just a heuristic, it does not need to be perfect.
*/
set_alloc_pool_size(qatomic_xchg(&release_pool_size, 0));
QSLIST_MOVE_ATOMIC(alloc_pool, &release_pool);
co = QSLIST_FIRST(alloc_pool);
}
}
if (co) {
QSLIST_REMOVE_HEAD(alloc_pool, pool_next);
set_alloc_pool_size(get_alloc_pool_size() - 1);
}
}
if (!co) {
co = qemu_coroutine_new();
}
co->entry = entry;
co->entry_arg = opaque;
QSIMPLEQ_INIT(&co->co_queue_wakeup);
return co;
}
static void coroutine_delete(Coroutine *co)
{
co->caller = NULL;
if (CONFIG_COROUTINE_POOL) {
if (release_pool_size < qatomic_read(&pool_max_size) * 2) {
QSLIST_INSERT_HEAD_ATOMIC(&release_pool, co, pool_next);
qatomic_inc(&release_pool_size);
return;
}
if (get_alloc_pool_size() < qatomic_read(&pool_max_size)) {
QSLIST_INSERT_HEAD(get_ptr_alloc_pool(), co, pool_next);
set_alloc_pool_size(get_alloc_pool_size() + 1);
return;
}
}
qemu_coroutine_delete(co);
}
void qemu_aio_coroutine_enter(AioContext *ctx, Coroutine *co)
{
QSIMPLEQ_HEAD(, Coroutine) pending = QSIMPLEQ_HEAD_INITIALIZER(pending);
Coroutine *from = qemu_coroutine_self();
QSIMPLEQ_INSERT_TAIL(&pending, co, co_queue_next);
/* Run co and any queued coroutines */
while (!QSIMPLEQ_EMPTY(&pending)) {
Coroutine *to = QSIMPLEQ_FIRST(&pending);
CoroutineAction ret;
/* Cannot rely on the read barrier for to in aio_co_wake(), as there are
* callers outside of aio_co_wake() */
const char *scheduled = qatomic_mb_read(&to->scheduled);
QSIMPLEQ_REMOVE_HEAD(&pending, co_queue_next);
trace_qemu_aio_coroutine_enter(ctx, from, to, to->entry_arg);
/* if the Coroutine has already been scheduled, entering it again will
* cause us to enter it twice, potentially even after the coroutine has
* been deleted */
if (scheduled) {
fprintf(stderr,
"%s: Co-routine was already scheduled in '%s'\n",
__func__, scheduled);
abort();
}
if (to->caller) {
fprintf(stderr, "Co-routine re-entered recursively\n");
abort();
}
to->caller = from;
to->ctx = ctx;
/* Store to->ctx before anything that stores to. Matches
* barrier in aio_co_wake and qemu_co_mutex_wake.
*/
smp_wmb();
ret = qemu_coroutine_switch(from, to, COROUTINE_ENTER);
/* Queued coroutines are run depth-first; previously pending coroutines
* run after those queued more recently.
*/
QSIMPLEQ_PREPEND(&pending, &to->co_queue_wakeup);
switch (ret) {
case COROUTINE_YIELD:
break;
case COROUTINE_TERMINATE:
assert(!to->locks_held);
trace_qemu_coroutine_terminate(to);
coroutine_delete(to);
break;
default:
abort();
}
}
}
void qemu_coroutine_enter(Coroutine *co)
{
qemu_aio_coroutine_enter(qemu_get_current_aio_context(), co);
}
void qemu_coroutine_enter_if_inactive(Coroutine *co)
{
if (!qemu_coroutine_entered(co)) {
qemu_coroutine_enter(co);
}
}
void coroutine_fn qemu_coroutine_yield(void)
{
Coroutine *self = qemu_coroutine_self();
Coroutine *to = self->caller;
trace_qemu_coroutine_yield(self, to);
if (!to) {
fprintf(stderr, "Co-routine is yielding to no one\n");
abort();
}
self->caller = NULL;
qemu_coroutine_switch(self, to, COROUTINE_YIELD);
}
bool qemu_coroutine_entered(Coroutine *co)
{
return co->caller;
}
AioContext *qemu_coroutine_get_aio_context(Coroutine *co)
{
return co->ctx;
}
void qemu_coroutine_inc_pool_size(unsigned int additional_pool_size)
{
qatomic_add(&pool_max_size, additional_pool_size);
}
void qemu_coroutine_dec_pool_size(unsigned int removing_pool_size)
{
qatomic_sub(&pool_max_size, removing_pool_size);
}
|
