qemu/io/channel-file.c
Stefan Hajnoczi 06e0f098d6 io: follow coroutine AioContext in qio_channel_yield()
The ongoing QEMU multi-queue block layer effort makes it possible for multiple
threads to process I/O in parallel. The nbd block driver is not compatible with
the multi-queue block layer yet because QIOChannel cannot be used easily from
coroutines running in multiple threads. This series changes the QIOChannel API
to make that possible.

In the current API, calling qio_channel_attach_aio_context() sets the
AioContext where qio_channel_yield() installs an fd handler prior to yielding:

  qio_channel_attach_aio_context(ioc, my_ctx);
  ...
  qio_channel_yield(ioc); // my_ctx is used here
  ...
  qio_channel_detach_aio_context(ioc);

This API design has limitations: reading and writing must be done in the same
AioContext and moving between AioContexts involves a cumbersome sequence of API
calls that is not suitable for doing on a per-request basis.

There is no fundamental reason why a QIOChannel needs to run within the
same AioContext every time qio_channel_yield() is called. QIOChannel
only uses the AioContext while inside qio_channel_yield(). The rest of
the time, QIOChannel is independent of any AioContext.

In the new API, qio_channel_yield() queries the AioContext from the current
coroutine using qemu_coroutine_get_aio_context(). There is no need to
explicitly attach/detach AioContexts anymore and
qio_channel_attach_aio_context() and qio_channel_detach_aio_context() are gone.
One coroutine can read from the QIOChannel while another coroutine writes from
a different AioContext.

This API change allows the nbd block driver to use QIOChannel from any thread.
It's important to keep in mind that the block driver already synchronizes
QIOChannel access and ensures that two coroutines never read simultaneously or
write simultaneously.

This patch updates all users of qio_channel_attach_aio_context() to the
new API. Most conversions are simple, but vhost-user-server requires a
new qemu_coroutine_yield() call to quiesce the vu_client_trip()
coroutine when not attached to any AioContext.

While the API is has become simpler, there is one wart: QIOChannel has a
special case for the iohandler AioContext (used for handlers that must not run
in nested event loops). I didn't find an elegant way preserve that behavior, so
I added a new API called qio_channel_set_follow_coroutine_ctx(ioc, true|false)
for opting in to the new AioContext model. By default QIOChannel uses the
iohandler AioHandler. Code that formerly called
qio_channel_attach_aio_context() now calls
qio_channel_set_follow_coroutine_ctx(ioc, true) once after the QIOChannel is
created.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Acked-by: Daniel P. Berrangé <berrange@redhat.com>
Message-ID: <20230830224802.493686-5-stefanha@redhat.com>
[eblake: also fix migration/rdma.c]
Signed-off-by: Eric Blake <eblake@redhat.com>
2023-09-07 20:32:11 -05:00

247 lines
7.0 KiB
C

/*
* QEMU I/O channels files driver
*
* Copyright (c) 2015 Red Hat, Inc.
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library 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
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, see <http://www.gnu.org/licenses/>.
*
*/
#include "qemu/osdep.h"
#include "io/channel-file.h"
#include "io/channel-util.h"
#include "io/channel-watch.h"
#include "qapi/error.h"
#include "qemu/module.h"
#include "qemu/sockets.h"
#include "trace.h"
QIOChannelFile *
qio_channel_file_new_fd(int fd)
{
QIOChannelFile *ioc;
ioc = QIO_CHANNEL_FILE(object_new(TYPE_QIO_CHANNEL_FILE));
ioc->fd = fd;
trace_qio_channel_file_new_fd(ioc, fd);
return ioc;
}
QIOChannelFile *
qio_channel_file_new_path(const char *path,
int flags,
mode_t mode,
Error **errp)
{
QIOChannelFile *ioc;
ioc = QIO_CHANNEL_FILE(object_new(TYPE_QIO_CHANNEL_FILE));
ioc->fd = qemu_open_old(path, flags, mode);
if (ioc->fd < 0) {
object_unref(OBJECT(ioc));
error_setg_errno(errp, errno,
"Unable to open %s", path);
return NULL;
}
trace_qio_channel_file_new_path(ioc, path, flags, mode, ioc->fd);
return ioc;
}
static void qio_channel_file_init(Object *obj)
{
QIOChannelFile *ioc = QIO_CHANNEL_FILE(obj);
ioc->fd = -1;
}
static void qio_channel_file_finalize(Object *obj)
{
QIOChannelFile *ioc = QIO_CHANNEL_FILE(obj);
if (ioc->fd != -1) {
qemu_close(ioc->fd);
ioc->fd = -1;
}
}
static ssize_t qio_channel_file_readv(QIOChannel *ioc,
const struct iovec *iov,
size_t niov,
int **fds,
size_t *nfds,
int flags,
Error **errp)
{
QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
ssize_t ret;
retry:
ret = readv(fioc->fd, iov, niov);
if (ret < 0) {
if (errno == EAGAIN) {
return QIO_CHANNEL_ERR_BLOCK;
}
if (errno == EINTR) {
goto retry;
}
error_setg_errno(errp, errno,
"Unable to read from file");
return -1;
}
return ret;
}
static ssize_t qio_channel_file_writev(QIOChannel *ioc,
const struct iovec *iov,
size_t niov,
int *fds,
size_t nfds,
int flags,
Error **errp)
{
QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
ssize_t ret;
retry:
ret = writev(fioc->fd, iov, niov);
if (ret <= 0) {
if (errno == EAGAIN) {
return QIO_CHANNEL_ERR_BLOCK;
}
if (errno == EINTR) {
goto retry;
}
error_setg_errno(errp, errno,
"Unable to write to file");
return -1;
}
return ret;
}
static int qio_channel_file_set_blocking(QIOChannel *ioc,
bool enabled,
Error **errp)
{
#ifdef WIN32
/* not implemented */
error_setg_errno(errp, errno, "Failed to set FD nonblocking");
return -1;
#else
QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
if (!g_unix_set_fd_nonblocking(fioc->fd, !enabled, NULL)) {
error_setg_errno(errp, errno, "Failed to set FD nonblocking");
return -1;
}
return 0;
#endif
}
static off_t qio_channel_file_seek(QIOChannel *ioc,
off_t offset,
int whence,
Error **errp)
{
QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
off_t ret;
ret = lseek(fioc->fd, offset, whence);
if (ret == (off_t)-1) {
error_setg_errno(errp, errno,
"Unable to seek to offset %lld whence %d in file",
(long long int)offset, whence);
return -1;
}
return ret;
}
static int qio_channel_file_close(QIOChannel *ioc,
Error **errp)
{
QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
if (qemu_close(fioc->fd) < 0) {
error_setg_errno(errp, errno,
"Unable to close file");
return -1;
}
fioc->fd = -1;
return 0;
}
static void qio_channel_file_set_aio_fd_handler(QIOChannel *ioc,
AioContext *read_ctx,
IOHandler *io_read,
AioContext *write_ctx,
IOHandler *io_write,
void *opaque)
{
QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
qio_channel_util_set_aio_fd_handler(fioc->fd, read_ctx, io_read,
fioc->fd, write_ctx, io_write,
opaque);
}
static GSource *qio_channel_file_create_watch(QIOChannel *ioc,
GIOCondition condition)
{
QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
return qio_channel_create_fd_watch(ioc,
fioc->fd,
condition);
}
static void qio_channel_file_class_init(ObjectClass *klass,
void *class_data G_GNUC_UNUSED)
{
QIOChannelClass *ioc_klass = QIO_CHANNEL_CLASS(klass);
ioc_klass->io_writev = qio_channel_file_writev;
ioc_klass->io_readv = qio_channel_file_readv;
ioc_klass->io_set_blocking = qio_channel_file_set_blocking;
ioc_klass->io_seek = qio_channel_file_seek;
ioc_klass->io_close = qio_channel_file_close;
ioc_klass->io_create_watch = qio_channel_file_create_watch;
ioc_klass->io_set_aio_fd_handler = qio_channel_file_set_aio_fd_handler;
}
static const TypeInfo qio_channel_file_info = {
.parent = TYPE_QIO_CHANNEL,
.name = TYPE_QIO_CHANNEL_FILE,
.instance_size = sizeof(QIOChannelFile),
.instance_init = qio_channel_file_init,
.instance_finalize = qio_channel_file_finalize,
.class_init = qio_channel_file_class_init,
};
static void qio_channel_file_register_types(void)
{
type_register_static(&qio_channel_file_info);
}
type_init(qio_channel_file_register_types);