* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
+#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/aio.h"
#include "qemu/queue.h"
+#include "block/block.h"
#include "block/raw-aio.h"
#include "qemu/event_notifier.h"
+#include "qemu/coroutine.h"
#include <libaio.h>
struct qemu_laiocb {
BlockAIOCB common;
- struct qemu_laio_state *ctx;
+ Coroutine *co;
+ LinuxAioState *ctx;
struct iocb iocb;
ssize_t ret;
size_t nbytes;
typedef struct {
int plugged;
- unsigned int idx;
+ unsigned int n;
+ bool blocked;
QSIMPLEQ_HEAD(, qemu_laiocb) pending;
} LaioQueue;
-struct qemu_laio_state {
+struct LinuxAioState {
io_context_t ctx;
EventNotifier e;
int event_max;
};
-static int ioq_submit(struct qemu_laio_state *s);
+static void ioq_submit(LinuxAioState *s);
static inline ssize_t io_event_ret(struct io_event *ev)
{
/*
* Completes an AIO request (calls the callback and frees the ACB).
*/
-static void qemu_laio_process_completion(struct qemu_laio_state *s,
- struct qemu_laiocb *laiocb)
+static void qemu_laio_process_completion(struct qemu_laiocb *laiocb)
{
int ret;
}
}
}
- laiocb->common.cb(laiocb->common.opaque, ret);
- qemu_aio_unref(laiocb);
+ laiocb->ret = ret;
+ if (laiocb->co) {
+ qemu_coroutine_enter(laiocb->co, NULL);
+ } else {
+ laiocb->common.cb(laiocb->common.opaque, ret);
+ qemu_aio_unref(laiocb);
+ }
}
/* The completion BH fetches completed I/O requests and invokes their
*
* The function is somewhat tricky because it supports nested event loops, for
* example when a request callback invokes aio_poll(). In order to do this,
- * the completion events array and index are kept in qemu_laio_state. The BH
+ * the completion events array and index are kept in LinuxAioState. The BH
* reschedules itself as long as there are completions pending so it will
* either be called again in a nested event loop or will be called after all
* events have been completed. When there are no events left to complete, the
*/
static void qemu_laio_completion_bh(void *opaque)
{
- struct qemu_laio_state *s = opaque;
+ LinuxAioState *s = opaque;
/* Fetch more completion events when empty */
if (s->event_idx == s->event_max) {
laiocb->ret = io_event_ret(&s->events[s->event_idx]);
s->event_idx++;
- qemu_laio_process_completion(s, laiocb);
+ qemu_laio_process_completion(laiocb);
}
if (!s->io_q.plugged && !QSIMPLEQ_EMPTY(&s->io_q.pending)) {
ioq_submit(s);
}
+
+ qemu_bh_cancel(s->completion_bh);
}
static void qemu_laio_completion_cb(EventNotifier *e)
{
- struct qemu_laio_state *s = container_of(e, struct qemu_laio_state, e);
+ LinuxAioState *s = container_of(e, LinuxAioState, e);
if (event_notifier_test_and_clear(&s->e)) {
- qemu_bh_schedule(s->completion_bh);
+ qemu_laio_completion_bh(s);
}
}
{
QSIMPLEQ_INIT(&io_q->pending);
io_q->plugged = 0;
- io_q->idx = 0;
+ io_q->n = 0;
+ io_q->blocked = false;
}
-static int ioq_submit(struct qemu_laio_state *s)
+static void ioq_submit(LinuxAioState *s)
{
- int ret, i;
- int len = 0;
+ int ret, len;
struct qemu_laiocb *aiocb;
struct iocb *iocbs[MAX_QUEUED_IO];
+ QSIMPLEQ_HEAD(, qemu_laiocb) completed;
+
+ do {
+ len = 0;
+ QSIMPLEQ_FOREACH(aiocb, &s->io_q.pending, next) {
+ iocbs[len++] = &aiocb->iocb;
+ if (len == MAX_QUEUED_IO) {
+ break;
+ }
+ }
- QSIMPLEQ_FOREACH(aiocb, &s->io_q.pending, next) {
- iocbs[len++] = &aiocb->iocb;
- if (len == MAX_QUEUED_IO) {
+ ret = io_submit(s->ctx, len, iocbs);
+ if (ret == -EAGAIN) {
break;
}
- }
-
- ret = io_submit(s->ctx, len, iocbs);
- if (ret == -EAGAIN) {
- ret = 0;
- }
- if (ret < 0) {
- abort();
- }
+ if (ret < 0) {
+ abort();
+ }
- for (i = 0; i < ret; i++) {
- s->io_q.idx--;
- QSIMPLEQ_REMOVE_HEAD(&s->io_q.pending, next);
- }
- return ret;
+ s->io_q.n -= ret;
+ aiocb = container_of(iocbs[ret - 1], struct qemu_laiocb, iocb);
+ QSIMPLEQ_SPLIT_AFTER(&s->io_q.pending, aiocb, next, &completed);
+ } while (ret == len && !QSIMPLEQ_EMPTY(&s->io_q.pending));
+ s->io_q.blocked = (s->io_q.n > 0);
}
-void laio_io_plug(BlockDriverState *bs, void *aio_ctx)
+void laio_io_plug(BlockDriverState *bs, LinuxAioState *s)
{
- struct qemu_laio_state *s = aio_ctx;
-
- s->io_q.plugged++;
+ assert(!s->io_q.plugged);
+ s->io_q.plugged = 1;
}
-int laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug)
+void laio_io_unplug(BlockDriverState *bs, LinuxAioState *s)
{
- struct qemu_laio_state *s = aio_ctx;
- int ret = 0;
-
- assert(s->io_q.plugged > 0 || !unplug);
-
- if (unplug && --s->io_q.plugged > 0) {
- return 0;
- }
-
- if (!QSIMPLEQ_EMPTY(&s->io_q.pending)) {
- ret = ioq_submit(s);
+ assert(s->io_q.plugged);
+ s->io_q.plugged = 0;
+ if (!s->io_q.blocked && !QSIMPLEQ_EMPTY(&s->io_q.pending)) {
+ ioq_submit(s);
}
-
- return ret;
}
-BlockAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
- int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockCompletionFunc *cb, void *opaque, int type)
+static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset,
+ int type)
{
- struct qemu_laio_state *s = aio_ctx;
- struct qemu_laiocb *laiocb;
- struct iocb *iocbs;
- off_t offset = sector_num * 512;
-
- laiocb = qemu_aio_get(&laio_aiocb_info, bs, cb, opaque);
- laiocb->nbytes = nb_sectors * 512;
- laiocb->ctx = s;
- laiocb->ret = -EINPROGRESS;
- laiocb->is_read = (type == QEMU_AIO_READ);
- laiocb->qiov = qiov;
-
- iocbs = &laiocb->iocb;
+ LinuxAioState *s = laiocb->ctx;
+ struct iocb *iocbs = &laiocb->iocb;
+ QEMUIOVector *qiov = laiocb->qiov;
switch (type) {
case QEMU_AIO_WRITE:
default:
fprintf(stderr, "%s: invalid AIO request type 0x%x.\n",
__func__, type);
- goto out_free_aiocb;
+ return -EIO;
}
io_set_eventfd(&laiocb->iocb, event_notifier_get_fd(&s->e));
QSIMPLEQ_INSERT_TAIL(&s->io_q.pending, laiocb, next);
- s->io_q.idx++;
- if (s->io_q.idx == (s->io_q.plugged ? MAX_QUEUED_IO : 1)) {
+ s->io_q.n++;
+ if (!s->io_q.blocked &&
+ (!s->io_q.plugged || s->io_q.n >= MAX_QUEUED_IO)) {
ioq_submit(s);
}
- return &laiocb->common;
-out_free_aiocb:
- qemu_aio_unref(laiocb);
- return NULL;
+ return 0;
}
-void laio_detach_aio_context(void *s_, AioContext *old_context)
+int coroutine_fn laio_co_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
+ uint64_t offset, QEMUIOVector *qiov, int type)
{
- struct qemu_laio_state *s = s_;
+ int ret;
+ struct qemu_laiocb laiocb = {
+ .co = qemu_coroutine_self(),
+ .nbytes = qiov->size,
+ .ctx = s,
+ .is_read = (type == QEMU_AIO_READ),
+ .qiov = qiov,
+ };
+
+ ret = laio_do_submit(fd, &laiocb, offset, type);
+ if (ret < 0) {
+ return ret;
+ }
- aio_set_event_notifier(old_context, &s->e, NULL);
- qemu_bh_delete(s->completion_bh);
+ qemu_coroutine_yield();
+ return laiocb.ret;
+}
+
+BlockAIOCB *laio_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
+ int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+ BlockCompletionFunc *cb, void *opaque, int type)
+{
+ struct qemu_laiocb *laiocb;
+ off_t offset = sector_num * BDRV_SECTOR_SIZE;
+ int ret;
+
+ laiocb = qemu_aio_get(&laio_aiocb_info, bs, cb, opaque);
+ laiocb->nbytes = nb_sectors * BDRV_SECTOR_SIZE;
+ laiocb->ctx = s;
+ laiocb->ret = -EINPROGRESS;
+ laiocb->is_read = (type == QEMU_AIO_READ);
+ laiocb->qiov = qiov;
+
+ ret = laio_do_submit(fd, laiocb, offset, type);
+ if (ret < 0) {
+ qemu_aio_unref(laiocb);
+ return NULL;
+ }
+
+ return &laiocb->common;
}
-void laio_attach_aio_context(void *s_, AioContext *new_context)
+void laio_detach_aio_context(LinuxAioState *s, AioContext *old_context)
{
- struct qemu_laio_state *s = s_;
+ aio_set_event_notifier(old_context, &s->e, false, NULL);
+ qemu_bh_delete(s->completion_bh);
+}
+void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context)
+{
s->completion_bh = aio_bh_new(new_context, qemu_laio_completion_bh, s);
- aio_set_event_notifier(new_context, &s->e, qemu_laio_completion_cb);
+ aio_set_event_notifier(new_context, &s->e, false,
+ qemu_laio_completion_cb);
}
-void *laio_init(void)
+LinuxAioState *laio_init(void)
{
- struct qemu_laio_state *s;
+ LinuxAioState *s;
s = g_malloc0(sizeof(*s));
if (event_notifier_init(&s->e, false) < 0) {
return NULL;
}
-void laio_cleanup(void *s_)
+void laio_cleanup(LinuxAioState *s)
{
- struct qemu_laio_state *s = s_;
-
event_notifier_cleanup(&s->e);
if (io_destroy(s->ctx) != 0) {
projects / qemu.git / blobdiff