It is not safe to close an event channel from the QEMU main thread when
that channel's poller is running in IOThread context.
This patch adds a new xen_device_set_event_channel_context() function
to explicitly assign the channel AioContext, and modifies
xen_device_bind_event_channel() to initially assign the channel's poller
to the QEMU main thread context. The code in xen-block's dataplane is
then modified to assign the channel to IOThread context during
xen_block_dataplane_start() and de-assign it during in
xen_block_dataplane_stop(), such that the channel is always assigned
back to main thread context before it is closed. aio_set_fd_handler()
already deals with all the necessary synchronization when moving an fd
between AioContext-s so no extra code is needed to manage this.
Reported-by: Julien Grall <jgrall@amazon.com>
Signed-off-by: Paul Durrant <pdurrant@amazon.com>
Reviewed-by: Anthony PERARD <anthony.perard@citrix.com>
Message-Id: <
20191216143451.19024-1-pdurrant@amazon.com>
Signed-off-by: Anthony PERARD <anthony.perard@citrix.com>
(cherry picked from commit
32d0b7be68216f130dc962533c6fc2f9ad848a8b)
return;
}
+ xendev = dataplane->xendev;
+
aio_context_acquire(dataplane->ctx);
+ if (dataplane->event_channel) {
+ /* Only reason for failure is a NULL channel */
+ xen_device_set_event_channel_context(xendev, dataplane->event_channel,
+ qemu_get_aio_context(),
+ &error_abort);
+ }
/* Xen doesn't have multiple users for nodes, so this can't fail */
blk_set_aio_context(dataplane->blk, qemu_get_aio_context(), &error_abort);
aio_context_release(dataplane->ctx);
- xendev = dataplane->xendev;
+ /*
+ * Now that the context has been moved onto the main thread, cancel
+ * further processing.
+ */
+ qemu_bh_cancel(dataplane->bh);
if (dataplane->event_channel) {
Error *local_err = NULL;
}
dataplane->event_channel =
- xen_device_bind_event_channel(xendev, dataplane->ctx, event_channel,
+ xen_device_bind_event_channel(xendev, event_channel,
xen_block_dataplane_event, dataplane,
&local_err);
if (local_err) {
aio_context_acquire(dataplane->ctx);
/* If other users keep the BlockBackend in the iothread, that's ok */
blk_set_aio_context(dataplane->blk, dataplane->ctx, NULL);
+ /* Only reason for failure is a NULL channel */
+ xen_device_set_event_channel_context(xendev, dataplane->event_channel,
+ dataplane->ctx, &error_abort);
aio_context_release(dataplane->ctx);
+
return;
stop:
}
}
+void xen_device_set_event_channel_context(XenDevice *xendev,
+ XenEventChannel *channel,
+ AioContext *ctx,
+ Error **errp)
+{
+ if (!channel) {
+ error_setg(errp, "bad channel");
+ return;
+ }
+
+ if (channel->ctx)
+ aio_set_fd_handler(channel->ctx, xenevtchn_fd(channel->xeh), true,
+ NULL, NULL, NULL, NULL);
+
+ channel->ctx = ctx;
+ aio_set_fd_handler(channel->ctx, xenevtchn_fd(channel->xeh), true,
+ xen_device_event, NULL, xen_device_poll, channel);
+}
+
XenEventChannel *xen_device_bind_event_channel(XenDevice *xendev,
- AioContext *ctx,
unsigned int port,
XenEventHandler handler,
void *opaque, Error **errp)
channel->handler = handler;
channel->opaque = opaque;
- channel->ctx = ctx;
- aio_set_fd_handler(channel->ctx, xenevtchn_fd(channel->xeh), true,
- xen_device_event, NULL, xen_device_poll, channel);
+ /* Only reason for failure is a NULL channel */
+ xen_device_set_event_channel_context(xendev, channel,
+ qemu_get_aio_context(),
+ &error_abort);
QLIST_INSERT_HEAD(&xendev->event_channels, channel, list);
typedef bool (*XenEventHandler)(void *opaque);
XenEventChannel *xen_device_bind_event_channel(XenDevice *xendev,
- AioContext *ctx,
unsigned int port,
XenEventHandler handler,
void *opaque, Error **errp);
+void xen_device_set_event_channel_context(XenDevice *xendev,
+ XenEventChannel *channel,
+ AioContext *ctx,
+ Error **errp);
void xen_device_notify_event_channel(XenDevice *xendev,
XenEventChannel *channel,
Error **errp);