On Wed, Dec 02, 2020 at 10:10:21AM +0800, Ming Lei wrote: > > Yes, this will need a careful audit, I'm not too sure offhand. For the > > io_uring case which is sortof the fast path the caller won't free them > > unless we allow the buffer unregistration to race with I/O. > > Loop's aio usage is fine, just found fd_execute_rw_aio() isn't good. Yes. But that one is trivial to fix.
