tcp: make connect() mem charging friendly

While working on sk_forward_alloc problems reported by Denys
Fedoryshchenko, we found that tcp connect() (and fastopen) do not call
sk_wmem_schedule() for SYN packet (and/or SYN/DATA packet), so
sk_forward_alloc is negative while connect is in progress.

We can fix this by calling regular sk_stream_alloc_skb() both for the
SYN packet (in tcp_connect()) and the syn_data packet in
tcp_send_syn_data()

Then, tcp_send_syn_data() can avoid copying syn_data as we simply
can manipulate syn_data->cb[] to remove SYN flag (and increment seq)

Instead of open coding memcpy_fromiovecend(), simply use this helper.

This leaves in socket write queue clean fast clone skbs.

This was tested against our fastopen packetdrill tests.

Reported-by: Denys Fedoryshchenko <nuclearcat@nuclearcat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index eb73a1d..f5bd4bd 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3011,9 +3011,9 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 {
        struct tcp_sock *tp = tcp_sk(sk);
        struct tcp_fastopen_request *fo = tp->fastopen_req;
-       int syn_loss = 0, space, i, err = 0, iovlen = fo->data->msg_iovlen;
-       struct sk_buff *syn_data = NULL, *data;
+       int syn_loss = 0, space, err = 0;
        unsigned long last_syn_loss = 0;
+       struct sk_buff *syn_data;
 
        tp->rx_opt.mss_clamp = tp->advmss;  /* If MSS is not cached */
        tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie,
@@ -3044,48 +3044,40 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
        /* limit to order-0 allocations */
        space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
 
-       syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space,
-                                  sk->sk_allocation);
-       if (syn_data == NULL)
+       syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation);
+       if (!syn_data)
                goto fallback;
+       syn_data->ip_summed = CHECKSUM_PARTIAL;
+       memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
+       if (unlikely(memcpy_fromiovecend(skb_put(syn_data, space),
+                                        fo->data->msg_iov, 0, space))) {
+               kfree_skb(syn_data);
+               goto fallback;
+       }
 
-       for (i = 0; i < iovlen && syn_data->len < space; ++i) {
-               struct iovec *iov = &fo->data->msg_iov[i];
-               unsigned char __user *from = iov->iov_base;
-               int len = iov->iov_len;
+       /* No more data pending in inet_wait_for_connect() */
+       if (space == fo->size)
+               fo->data = NULL;
+       fo->copied = space;
 
-               if (syn_data->len + len > space)
-                       len = space - syn_data->len;
-               else if (i + 1 == iovlen)
-                       /* No more data pending in inet_wait_for_connect() */
-                       fo->data = NULL;
+       tcp_connect_queue_skb(sk, syn_data);
 
-               if (skb_add_data(syn_data, from, len))
-                       goto fallback;
-       }
+       err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation);
 
-       /* Queue a data-only packet after the regular SYN for retransmission */
-       data = pskb_copy(syn_data, sk->sk_allocation);
-       if (data == NULL)
-               goto fallback;
-       TCP_SKB_CB(data)->seq++;
-       TCP_SKB_CB(data)->tcp_flags &= ~TCPHDR_SYN;
-       TCP_SKB_CB(data)->tcp_flags = (TCPHDR_ACK|TCPHDR_PSH);
-       tcp_connect_queue_skb(sk, data);
-       fo->copied = data->len;
-
-       /* syn_data is about to be sent, we need to take current time stamps
-        * for the packets that are in write queue : SYN packet and DATA
-        */
-       skb_mstamp_get(&syn->skb_mstamp);
-       data->skb_mstamp = syn->skb_mstamp;
+       syn->skb_mstamp = syn_data->skb_mstamp;
 
-       if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) {
+       /* Now full SYN+DATA was cloned and sent (or not),
+        * remove the SYN from the original skb (syn_data)
+        * we keep in write queue in case of a retransmit, as we
+        * also have the SYN packet (with no data) in the same queue.
+        */
+       TCP_SKB_CB(syn_data)->seq++;
+       TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH;
+       if (!err) {
                tp->syn_data = (fo->copied > 0);
                NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT);
                goto done;
        }
-       syn_data = NULL;
 
 fallback:
        /* Send a regular SYN with Fast Open cookie request option */
@@ -3094,7 +3086,6 @@ fallback:
        err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation);
        if (err)
                tp->syn_fastopen = 0;
-       kfree_skb(syn_data);
 done:
        fo->cookie.len = -1;  /* Exclude Fast Open option for SYN retries */
        return err;
@@ -3114,13 +3105,10 @@ int tcp_connect(struct sock *sk)
                return 0;
        }
 
-       buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation);
-       if (unlikely(buff == NULL))
+       buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
+       if (unlikely(!buff))
                return -ENOBUFS;
 
-       /* Reserve space for headers. */
-       skb_reserve(buff, MAX_TCP_HEADER);
-
        tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
        tp->retrans_stamp = tcp_time_stamp;
        tcp_connect_queue_skb(sk, buff);