Loading...
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 | /*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 Fabrice Bellard
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu-common.h"
#include "block/aio.h"
#include "block/thread-pool.h"
#include "qemu/main-loop.h"
#include "qemu/atomic.h"
/***********************************************************/
/* bottom halves (can be seen as timers which expire ASAP) */
struct QEMUBH {
AioContext *ctx;
QEMUBHFunc *cb;
void *opaque;
QEMUBH *next;
bool scheduled;
bool idle;
bool deleted;
};
QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
{
QEMUBH *bh;
bh = g_new(QEMUBH, 1);
*bh = (QEMUBH){
.ctx = ctx,
.cb = cb,
.opaque = opaque,
};
qemu_mutex_lock(&ctx->bh_lock);
bh->next = ctx->first_bh;
/* Make sure that the members are ready before putting bh into list */
smp_wmb();
ctx->first_bh = bh;
qemu_mutex_unlock(&ctx->bh_lock);
return bh;
}
void aio_bh_call(QEMUBH *bh)
{
bh->cb(bh->opaque);
}
/* Multiple occurrences of aio_bh_poll cannot be called concurrently */
int aio_bh_poll(AioContext *ctx)
{
QEMUBH *bh, **bhp, *next;
int ret;
ctx->walking_bh++;
ret = 0;
for (bh = ctx->first_bh; bh; bh = next) {
/* Make sure that fetching bh happens before accessing its members */
smp_read_barrier_depends();
next = bh->next;
/* The atomic_xchg is paired with the one in qemu_bh_schedule. The
* implicit memory barrier ensures that the callback sees all writes
* done by the scheduling thread. It also ensures that the scheduling
* thread sees the zero before bh->cb has run, and thus will call
* aio_notify again if necessary.
*/
if (!bh->deleted && atomic_xchg(&bh->scheduled, 0)) {
/* Idle BHs and the notify BH don't count as progress */
if (!bh->idle && bh != ctx->notify_dummy_bh) {
ret = 1;
}
bh->idle = 0;
aio_bh_call(bh);
}
}
ctx->walking_bh--;
/* remove deleted bhs */
if (!ctx->walking_bh) {
qemu_mutex_lock(&ctx->bh_lock);
bhp = &ctx->first_bh;
while (*bhp) {
bh = *bhp;
if (bh->deleted) {
*bhp = bh->next;
g_free(bh);
} else {
bhp = &bh->next;
}
}
qemu_mutex_unlock(&ctx->bh_lock);
}
return ret;
}
void qemu_bh_schedule_idle(QEMUBH *bh)
{
bh->idle = 1;
/* Make sure that idle & any writes needed by the callback are done
* before the locations are read in the aio_bh_poll.
*/
atomic_mb_set(&bh->scheduled, 1);
}
void qemu_bh_schedule(QEMUBH *bh)
{
AioContext *ctx;
ctx = bh->ctx;
bh->idle = 0;
/* The memory barrier implicit in atomic_xchg makes sure that:
* 1. idle & any writes needed by the callback are done before the
* locations are read in the aio_bh_poll.
* 2. ctx is loaded before scheduled is set and the callback has a chance
* to execute.
*/
if (atomic_xchg(&bh->scheduled, 1) == 0) {
aio_notify(ctx);
}
}
/* This func is async.
*/
void qemu_bh_cancel(QEMUBH *bh)
{
bh->scheduled = 0;
}
/* This func is async.The bottom half will do the delete action at the finial
* end.
*/
void qemu_bh_delete(QEMUBH *bh)
{
bh->scheduled = 0;
bh->deleted = 1;
}
int64_t
aio_compute_timeout(AioContext *ctx)
{
int64_t deadline;
int timeout = -1;
QEMUBH *bh;
for (bh = ctx->first_bh; bh; bh = bh->next) {
if (!bh->deleted && bh->scheduled) {
if (bh->idle) {
/* idle bottom halves will be polled at least
* every 10ms */
timeout = 10000000;
} else {
/* non-idle bottom halves will be executed
* immediately */
return 0;
}
}
}
deadline = timerlistgroup_deadline_ns(&ctx->tlg);
if (deadline == 0) {
return 0;
} else {
return qemu_soonest_timeout(timeout, deadline);
}
}
static gboolean
aio_ctx_prepare(GSource *source, gint *timeout)
{
AioContext *ctx = (AioContext *) source;
atomic_or(&ctx->notify_me, 1);
/* We assume there is no timeout already supplied */
*timeout = qemu_timeout_ns_to_ms(aio_compute_timeout(ctx));
if (aio_prepare(ctx)) {
*timeout = 0;
}
return *timeout == 0;
}
static gboolean
aio_ctx_check(GSource *source)
{
AioContext *ctx = (AioContext *) source;
QEMUBH *bh;
atomic_and(&ctx->notify_me, ~1);
aio_notify_accept(ctx);
for (bh = ctx->first_bh; bh; bh = bh->next) {
if (!bh->deleted && bh->scheduled) {
return true;
}
}
return aio_pending(ctx) || (timerlistgroup_deadline_ns(&ctx->tlg) == 0);
}
static gboolean
aio_ctx_dispatch(GSource *source,
GSourceFunc callback,
gpointer user_data)
{
AioContext *ctx = (AioContext *) source;
assert(callback == NULL);
aio_dispatch(ctx);
return true;
}
static void
aio_ctx_finalize(GSource *source)
{
AioContext *ctx = (AioContext *) source;
qemu_bh_delete(ctx->notify_dummy_bh);
thread_pool_free(ctx->thread_pool);
qemu_mutex_lock(&ctx->bh_lock);
while (ctx->first_bh) {
QEMUBH *next = ctx->first_bh->next;
/* qemu_bh_delete() must have been called on BHs in this AioContext */
assert(ctx->first_bh->deleted);
g_free(ctx->first_bh);
ctx->first_bh = next;
}
qemu_mutex_unlock(&ctx->bh_lock);
aio_set_event_notifier(ctx, &ctx->notifier, false, NULL);
event_notifier_cleanup(&ctx->notifier);
rfifolock_destroy(&ctx->lock);
qemu_mutex_destroy(&ctx->bh_lock);
timerlistgroup_deinit(&ctx->tlg);
}
static GSourceFuncs aio_source_funcs = {
aio_ctx_prepare,
aio_ctx_check,
aio_ctx_dispatch,
aio_ctx_finalize
};
GSource *aio_get_g_source(AioContext *ctx)
{
g_source_ref(&ctx->source);
return &ctx->source;
}
ThreadPool *aio_get_thread_pool(AioContext *ctx)
{
if (!ctx->thread_pool) {
ctx->thread_pool = thread_pool_new(ctx);
}
return ctx->thread_pool;
}
void aio_notify(AioContext *ctx)
{
/* Write e.g. bh->scheduled before reading ctx->notify_me. Pairs
* with atomic_or in aio_ctx_prepare or atomic_add in aio_poll.
*/
smp_mb();
if (ctx->notify_me) {
event_notifier_set(&ctx->notifier);
atomic_mb_set(&ctx->notified, true);
}
}
void aio_notify_accept(AioContext *ctx)
{
if (atomic_xchg(&ctx->notified, false)) {
event_notifier_test_and_clear(&ctx->notifier);
}
}
static void aio_timerlist_notify(void *opaque)
{
aio_notify(opaque);
}
static void aio_rfifolock_cb(void *opaque)
{
AioContext *ctx = opaque;
/* Kick owner thread in case they are blocked in aio_poll() */
qemu_bh_schedule(ctx->notify_dummy_bh);
}
static void notify_dummy_bh(void *opaque)
{
/* Do nothing, we were invoked just to force the event loop to iterate */
}
static void event_notifier_dummy_cb(EventNotifier *e)
{
}
AioContext *aio_context_new(Error **errp)
{
int ret;
AioContext *ctx;
Error *local_err = NULL;
ctx = (AioContext *) g_source_new(&aio_source_funcs, sizeof(AioContext));
aio_context_setup(ctx, &local_err);
if (local_err) {
error_propagate(errp, local_err);
goto fail;
}
ret = event_notifier_init(&ctx->notifier, false);
if (ret < 0) {
error_setg_errno(errp, -ret, "Failed to initialize event notifier");
goto fail;
}
g_source_set_can_recurse(&ctx->source, true);
aio_set_event_notifier(ctx, &ctx->notifier,
false,
(EventNotifierHandler *)
event_notifier_dummy_cb);
ctx->thread_pool = NULL;
qemu_mutex_init(&ctx->bh_lock);
rfifolock_init(&ctx->lock, aio_rfifolock_cb, ctx);
timerlistgroup_init(&ctx->tlg, aio_timerlist_notify, ctx);
ctx->notify_dummy_bh = aio_bh_new(ctx, notify_dummy_bh, NULL);
return ctx;
fail:
g_source_destroy(&ctx->source);
return NULL;
}
void aio_context_ref(AioContext *ctx)
{
g_source_ref(&ctx->source);
}
void aio_context_unref(AioContext *ctx)
{
g_source_unref(&ctx->source);
}
void aio_context_acquire(AioContext *ctx)
{
rfifolock_lock(&ctx->lock);
}
void aio_context_release(AioContext *ctx)
{
rfifolock_unlock(&ctx->lock);
}
|