struct sockaddr __user *addr;
int addr_len;
bool in_progress;
+ bool seen_econnaborted;
};
struct io_sr_msg {
u16 flags;
/* initialised and used only by !msg send variants */
u16 addr_len;
+ u16 buf_group;
void __user *addr;
+ void __user *msg_control;
/* used only for send zerocopy */
struct io_kiocb *notif;
};
struct io_cache_entry *entry;
struct io_async_msghdr *hdr;
- if (!(issue_flags & IO_URING_F_UNLOCKED) &&
- (entry = io_alloc_cache_get(&ctx->netmsg_cache)) != NULL) {
- hdr = container_of(entry, struct io_async_msghdr, cache);
- hdr->free_iov = NULL;
- req->flags |= REQ_F_ASYNC_DATA;
- req->async_data = hdr;
- return hdr;
+ if (!(issue_flags & IO_URING_F_UNLOCKED)) {
+ entry = io_alloc_cache_get(&ctx->netmsg_cache);
+ if (entry) {
+ hdr = container_of(entry, struct io_async_msghdr, cache);
+ hdr->free_iov = NULL;
+ req->flags |= REQ_F_ASYNC_DATA;
+ req->async_data = hdr;
+ return hdr;
+ }
}
if (!io_alloc_async_data(req)) {
struct io_async_msghdr *iomsg)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+ int ret;
iomsg->msg.msg_name = &iomsg->addr;
iomsg->free_iov = iomsg->fast_iov;
- return sendmsg_copy_msghdr(&iomsg->msg, sr->umsg, sr->msg_flags,
+ ret = sendmsg_copy_msghdr(&iomsg->msg, sr->umsg, sr->msg_flags,
&iomsg->free_iov);
+ /* save msg_control as sys_sendmsg() overwrites it */
+ sr->msg_control = iomsg->msg.msg_control_user;
+ return ret;
}
int io_send_prep_async(struct io_kiocb *req)
if (req_has_async_data(req)) {
kmsg = req->async_data;
+ kmsg->msg.msg_control_user = sr->msg_control;
} else {
ret = io_sendmsg_copy_hdr(req, &iomsg);
if (ret)
if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
return io_setup_async_msg(req, kmsg, issue_flags);
if (ret > 0 && io_net_retry(sock, flags)) {
+ kmsg->msg.msg_controllen = 0;
+ kmsg->msg.msg_control = NULL;
sr->done_io += ret;
req->flags |= REQ_F_PARTIAL_IO;
return io_setup_async_msg(req, kmsg, issue_flags);
if (unlikely(!sock))
return -ENOTSOCK;
- ret = import_single_range(WRITE, sr->buf, sr->len, &iov, &msg.msg_iter);
+ ret = import_single_range(ITER_SOURCE, sr->buf, sr->len, &iov, &msg.msg_iter);
if (unlikely(ret))
return ret;
}
} else {
iomsg->free_iov = iomsg->fast_iov;
- ret = __import_iovec(READ, msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV,
+ ret = __import_iovec(ITER_DEST, msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV,
&iomsg->free_iov, &iomsg->msg.msg_iter,
false);
if (ret > 0)
if (req->flags & REQ_F_BUFFER_SELECT) {
compat_ssize_t clen;
+ iomsg->free_iov = NULL;
if (msg.msg_iovlen == 0) {
sr->len = 0;
} else if (msg.msg_iovlen > 1) {
}
} else {
iomsg->free_iov = iomsg->fast_iov;
- ret = __import_iovec(READ, (struct iovec __user *)uiov, msg.msg_iovlen,
+ ret = __import_iovec(ITER_DEST, (struct iovec __user *)uiov, msg.msg_iovlen,
UIO_FASTIOV, &iomsg->free_iov,
&iomsg->msg.msg_iter, true);
if (ret < 0)
sr->flags = READ_ONCE(sqe->ioprio);
if (sr->flags & ~(RECVMSG_FLAGS))
return -EINVAL;
- sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
+ sr->msg_flags = READ_ONCE(sqe->msg_flags);
if (sr->msg_flags & MSG_DONTWAIT)
req->flags |= REQ_F_NOWAIT;
if (sr->msg_flags & MSG_ERRQUEUE)
if (req->opcode == IORING_OP_RECV && sr->len)
return -EINVAL;
req->flags |= REQ_F_APOLL_MULTISHOT;
+ /*
+ * Store the buffer group for this multishot receive separately,
+ * as if we end up doing an io-wq based issue that selects a
+ * buffer, it has to be committed immediately and that will
+ * clear ->buf_list. This means we lose the link to the buffer
+ * list, and the eventual buffer put on completion then cannot
+ * restore it.
+ */
+ sr->buf_group = req->buf_index;
}
#ifdef CONFIG_COMPAT
sr->done_io = 0;
sr->len = 0; /* get from the provided buffer */
+ req->buf_index = sr->buf_group;
}
/*
kmsg->fast_iov[0].iov_base = buf;
kmsg->fast_iov[0].iov_len = len;
- iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1,
+ iov_iter_init(&kmsg->msg.msg_iter, ITER_DEST, kmsg->fast_iov, 1,
len);
}
flags = sr->msg_flags;
if (force_nonblock)
flags |= MSG_DONTWAIT;
- if (flags & MSG_WAITALL)
- min_ret = iov_iter_count(&kmsg->msg.msg_iter);
kmsg->msg.msg_get_inq = 1;
- if (req->flags & REQ_F_APOLL_MULTISHOT)
+ if (req->flags & REQ_F_APOLL_MULTISHOT) {
ret = io_recvmsg_multishot(sock, sr, kmsg, flags,
&mshot_finished);
- else
+ } else {
+ /* disable partial retry for recvmsg with cmsg attached */
+ if (flags & MSG_WAITALL && !kmsg->msg.msg_controllen)
+ min_ret = iov_iter_count(&kmsg->msg.msg_iter);
+
ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg,
kmsg->uaddr, flags);
+ }
if (ret < min_ret) {
if (ret == -EAGAIN && force_nonblock) {
goto retry_multishot;
if (mshot_finished) {
- io_netmsg_recycle(req, issue_flags);
/* fast path, check for non-NULL to avoid function call */
if (kmsg->free_iov)
kfree(kmsg->free_iov);
+ io_netmsg_recycle(req, issue_flags);
req->flags &= ~REQ_F_NEED_CLEANUP;
}
sr->buf = buf;
}
- ret = import_single_range(READ, sr->buf, len, &iov, &msg.msg_iter);
+ ret = import_single_range(ITER_DEST, sr->buf, len, &iov, &msg.msg_iter);
if (unlikely(ret))
goto out_free;
zc->flags = READ_ONCE(sqe->ioprio);
if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST |
- IORING_RECVSEND_FIXED_BUF))
+ IORING_RECVSEND_FIXED_BUF |
+ IORING_SEND_ZC_REPORT_USAGE))
return -EINVAL;
notif = zc->notif = io_alloc_notif(ctx);
if (!notif)
req->imu = READ_ONCE(ctx->user_bufs[idx]);
io_req_set_rsrc_node(notif, ctx, 0);
}
+ if (zc->flags & IORING_SEND_ZC_REPORT_USAGE) {
+ io_notif_to_data(notif)->zc_report = true;
+ }
if (req->opcode == IORING_OP_SEND_ZC) {
if (READ_ONCE(sqe->__pad3[0]))
return io_setup_async_addr(req, &__address, issue_flags);
if (zc->flags & IORING_RECVSEND_FIXED_BUF) {
- ret = io_import_fixed(WRITE, &msg.msg_iter, req->imu,
+ ret = io_import_fixed(ITER_SOURCE, &msg.msg_iter, req->imu,
(u64)(uintptr_t)zc->buf, zc->len);
if (unlikely(ret))
return ret;
msg.sg_from_iter = io_sg_from_iter;
} else {
- ret = import_single_range(WRITE, zc->buf, zc->len, &iov,
+ ret = import_single_range(ITER_SOURCE, zc->buf, zc->len, &iov,
&msg.msg_iter);
if (unlikely(ret))
return ret;
conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr));
conn->addr_len = READ_ONCE(sqe->addr2);
- conn->in_progress = false;
+ conn->in_progress = conn->seen_econnaborted = false;
return 0;
}
ret = __sys_connect_file(req->file, &io->address,
connect->addr_len, file_flags);
- if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) {
+ if ((ret == -EAGAIN || ret == -EINPROGRESS || ret == -ECONNABORTED)
+ && force_nonblock) {
if (ret == -EINPROGRESS) {
connect->in_progress = true;
- } else {
- if (req_has_async_data(req))
- return -EAGAIN;
- if (io_alloc_async_data(req)) {
- ret = -ENOMEM;
+ return -EAGAIN;
+ }
+ if (ret == -ECONNABORTED) {
+ if (connect->seen_econnaborted)
goto out;
- }
- memcpy(req->async_data, &__io, sizeof(__io));
+ connect->seen_econnaborted = true;
+ }
+ if (req_has_async_data(req))
+ return -EAGAIN;
+ if (io_alloc_async_data(req)) {
+ ret = -ENOMEM;
+ goto out;
}
+ memcpy(req->async_data, &__io, sizeof(__io));
return -EAGAIN;
}
if (ret == -ERESTARTSYS)