tcp: flush DMA queue before sk_wait_data if rcv_wnd is zero

If recv() syscall is called for a TCP socket so that
  - IOAT DMA is used
  - MSG_WAITALL flag is used
  - requested length is bigger than sk_rcvbuf
  - enough data has already arrived to bring rcv_wnd to zero
then when tcp_recvmsg() gets to calling sk_wait_data(), receive
window can be still zero while sk_async_wait_queue exhausts
enough space to keep it zero. As this queue isn't cleaned until
the tcp_service_net_dma() call, sk_wait_data() cannot receive
any data and blocks forever.

If zero receive window and non-empty sk_async_wait_queue is
detected before calling sk_wait_data(), process the queue first.

Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2109ff4a1dafd489fbe0e2240075432df4517374..bf9a8ab294590029a12e9c8a737af2e5a8a4940e 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1762,8 +1762,14 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                }
 
 #ifdef CONFIG_NET_DMA
-               if (tp->ucopy.dma_chan)
-                       dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+               if (tp->ucopy.dma_chan) {
+                       if (tp->rcv_wnd == 0 &&
+                           !skb_queue_empty(&sk->sk_async_wait_queue)) {
+                               tcp_service_net_dma(sk, true);
+                               tcp_cleanup_rbuf(sk, copied);
+                       } else
+                               dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+               }
 #endif
                if (copied >= target) {
                        /* Do not sleep, just process backlog. */