mirror of
https://github.com/qemu/qemu.git
synced 2024-12-18 09:43:38 +08:00
aa38e19f05
Unlike ppoll(2) and epoll(7), Linux io_uring completions can be polled from userspace. Previously userspace polling was only allowed when all AioHandler's had an ->io_poll() callback. This prevented starvation of fds by userspace pollable handlers. Add the FDMonOps->need_wait() callback that enables userspace polling even when some AioHandlers lack ->io_poll(). For example, it's now possible to do userspace polling when a TCP/IP socket is monitored thanks to Linux io_uring. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Link: https://lore.kernel.org/r/20200305170806.1313245-7-stefanha@redhat.com Message-Id: <20200305170806.1313245-7-stefanha@redhat.com> |
||
---|---|---|
.. | ||
accounting.h | ||
aio_task.h | ||
aio-wait.h | ||
aio.h | ||
block_backup.h | ||
block_int.h | ||
block-copy.h | ||
block.h | ||
blockjob_int.h | ||
blockjob.h | ||
dirty-bitmap.h | ||
nbd.h | ||
nvme.h | ||
qapi.h | ||
qdict.h | ||
raw-aio.h | ||
snapshot.h | ||
thread-pool.h | ||
throttle-groups.h | ||
write-threshold.h |