static int
soo_aio_queue(struct file *fp, struct kaiocb *job)
{
struct socket *so;
struct sockbuf *sb;
int error;
so = fp->f_data;
error = (*so->so_proto->pr_usrreqs->pru_aio_queue)(so, job);
if (error == 0)
return (0);
switch (job->uaiocb.aio_lio_opcode) {
case LIO_READ:
sb = &so->so_rcv;
break;
case LIO_WRITE:
sb = &so->so_snd;
break;
default:
return (EINVAL);
}
SOCKBUF_LOCK(sb);
if (!aio_set_cancel_function(job, soo_aio_cancel))
panic("new job was cancelled");
TAILQ_INSERT_TAIL(&sb->sb_aiojobq, job, list);
if (!(sb->sb_flags & SB_AIO_RUNNING)) {
if (soaio_ready(so, sb))
sowakeup_aio(so, sb);
else
sb->sb_flags |= SB_AIO;
}
SOCKBUF_UNLOCK(sb);
return (0);
}
static void
soaio_process_job(struct socket *so, struct sockbuf *sb, struct kaiocb *job)
{
struct ucred *td_savedcred;
struct thread *td;
struct file *fp;
struct uio uio;
struct iovec iov;
size_t cnt;
int error, flags;
SOCKBUF_UNLOCK(sb);
aio_switch_vmspace(job);
td = curthread;
fp = job->fd_file;
retry:
td_savedcred = td->td_ucred;
td->td_ucred = job->cred;
cnt = job->uaiocb.aio_nbytes;
iov.iov_base = (void *)(uintptr_t)job->uaiocb.aio_buf;
iov.iov_len = cnt;
uio.uio_iov = &iov;
uio.uio_iovcnt = 1;
uio.uio_offset = 0;
uio.uio_resid = cnt;
uio.uio_segflg = UIO_USERSPACE;
uio.uio_td = td;
flags = MSG_NBIO;
/* TODO: Charge ru_msg* to job. */
if (sb == &so->so_rcv) {
uio.uio_rw = UIO_READ;
#ifdef MAC
error = mac_socket_check_receive(fp->f_cred, so);
if (error == 0)
#endif
error = soreceive(so, NULL, &uio, NULL, NULL, &flags);
} else {
uio.uio_rw = UIO_WRITE;
#ifdef MAC
error = mac_socket_check_send(fp->f_cred, so);
if (error == 0)
#endif
error = sosend(so, NULL, &uio, NULL, NULL, flags, td);
if (error == EPIPE && (so->so_options & SO_NOSIGPIPE) == 0) {
PROC_LOCK(job->userproc);
kern_psignal(job->userproc, SIGPIPE);
PROC_UNLOCK(job->userproc);
}
}
cnt -= uio.uio_resid;
td->td_ucred = td_savedcred;
/* XXX: Not sure if this is needed? */
if (cnt != 0 && (error == ERESTART || error == EINTR ||
error == EWOULDBLOCK))
error = 0;
if (error == EWOULDBLOCK) {
/*
* A read() or write() on the socket raced with this
* request. If the socket is now ready, try again.
* If it is not, place this request at the head of the
* queue to try again when the socket is ready.
*/
SOCKBUF_LOCK(sb);
empty_results++;
if (soaio_ready(so, sb)) {
empty_retries++;
SOCKBUF_UNLOCK(sb);
goto retry;
}
if (!aio_set_cancel_function(job, soo_aio_cancel)) {
MPASS(cnt == 0);
SOCKBUF_UNLOCK(sb);
aio_cancel(job);
SOCKBUF_LOCK(sb);
} else {
TAILQ_INSERT_HEAD(&sb->sb_aiojobq, job, list);
}
} else {
aio_complete(job, cnt, error);
SOCKBUF_LOCK(sb);
}
}
static void
soaio_process_job(struct socket *so, struct sockbuf *sb, struct kaiocb *job)
{
struct ucred *td_savedcred;
struct thread *td;
struct file *fp;
struct uio uio;
struct iovec iov;
size_t cnt, done;
long ru_before;
int error, flags;
SOCKBUF_UNLOCK(sb);
aio_switch_vmspace(job);
td = curthread;
fp = job->fd_file;
retry:
td_savedcred = td->td_ucred;
td->td_ucred = job->cred;
done = job->aio_done;
cnt = job->uaiocb.aio_nbytes - done;
iov.iov_base = (void *)((uintptr_t)job->uaiocb.aio_buf + done);
iov.iov_len = cnt;
uio.uio_iov = &iov;
uio.uio_iovcnt = 1;
uio.uio_offset = 0;
uio.uio_resid = cnt;
uio.uio_segflg = UIO_USERSPACE;
uio.uio_td = td;
flags = MSG_NBIO;
/*
* For resource usage accounting, only count a completed request
* as a single message to avoid counting multiple calls to
* sosend/soreceive on a blocking socket.
*/
if (sb == &so->so_rcv) {
uio.uio_rw = UIO_READ;
ru_before = td->td_ru.ru_msgrcv;
#ifdef MAC
error = mac_socket_check_receive(fp->f_cred, so);
if (error == 0)
#endif
error = soreceive(so, NULL, &uio, NULL, NULL, &flags);
if (td->td_ru.ru_msgrcv != ru_before)
job->msgrcv = 1;
} else {
uio.uio_rw = UIO_WRITE;
ru_before = td->td_ru.ru_msgsnd;
#ifdef MAC
error = mac_socket_check_send(fp->f_cred, so);
if (error == 0)
#endif
error = sosend(so, NULL, &uio, NULL, NULL, flags, td);
if (td->td_ru.ru_msgsnd != ru_before)
job->msgsnd = 1;
if (error == EPIPE && (so->so_options & SO_NOSIGPIPE) == 0) {
PROC_LOCK(job->userproc);
kern_psignal(job->userproc, SIGPIPE);
PROC_UNLOCK(job->userproc);
}
}
done += cnt - uio.uio_resid;
job->aio_done = done;
td->td_ucred = td_savedcred;
if (error == EWOULDBLOCK) {
/*
* The request was either partially completed or not
* completed at all due to racing with a read() or
* write() on the socket. If the socket is
* non-blocking, return with any partial completion.
* If the socket is blocking or if no progress has
* been made, requeue this request at the head of the
* queue to try again when the socket is ready.
*/
MPASS(done != job->uaiocb.aio_nbytes);
SOCKBUF_LOCK(sb);
if (done == 0 || !(so->so_state & SS_NBIO)) {
empty_results++;
if (soaio_ready(so, sb)) {
empty_retries++;
SOCKBUF_UNLOCK(sb);
goto retry;
}
if (!aio_set_cancel_function(job, soo_aio_cancel)) {
SOCKBUF_UNLOCK(sb);
if (done != 0)
aio_complete(job, done, 0);
else
aio_cancel(job);
SOCKBUF_LOCK(sb);
} else {
TAILQ_INSERT_HEAD(&sb->sb_aiojobq, job, list);
}
return;
}
SOCKBUF_UNLOCK(sb);
}
if (done != 0 && (error == ERESTART || error == EINTR ||
error == EWOULDBLOCK))
error = 0;
if (error)
aio_complete(job, -1, error);
else
aio_complete(job, done, 0);
SOCKBUF_LOCK(sb);
}