{
return skb->len < size_goal &&
sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
- skb != tcp_write_queue_head(sk) &&
+ !tcp_rtx_queue_empty(sk) &&
refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
}
return mss_now;
}
+/* In some cases, both sendpage() and sendmsg() could have added
+ * an skb to the write queue, but failed adding payload on it.
+ * We need to remove it to consume less memory, but more
+ * importantly be able to generate EPOLLOUT for Edge Trigger epoll()
+ * users.
+ */
+static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
+{
+ if (skb && !skb->len) {
+ tcp_unlink_write_queue(skb, sk);
+ if (tcp_write_queue_empty(sk))
+ tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
+ sk_wmem_free_skb(sk, skb);
+ }
+}
+
ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
size_t size, int flags)
{
return copied;
do_error:
+ tcp_remove_empty_skb(sk, tcp_write_queue_tail(sk));
if (copied)
goto out;
out_err:
flags = msg->msg_flags;
- if (flags & MSG_ZEROCOPY && size) {
- if (sk->sk_state != TCP_ESTABLISHED) {
+ if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) {
+ if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
err = -EINVAL;
goto out_err;
}
uarg->zerocopy = 0;
}
- if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) {
+ if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
+ !tp->repair) {
err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
if (err == -EINPROGRESS && copied_syn > 0)
goto out;
sock_zerocopy_put(uarg);
return copied + copied_syn;
+do_error:
+ skb = tcp_write_queue_tail(sk);
do_fault:
- if (!skb->len) {
- tcp_unlink_write_queue(skb, sk);
- /* It is the one place in all of TCP, except connection
- * reset, where we can be unlinking the send_head.
- */
- tcp_check_send_head(sk, skb);
- sk_wmem_free_skb(sk, skb);
- }
+ tcp_remove_empty_skb(sk, skb);
-do_error:
if (copied + copied_syn)
goto out;
out_err:
* shouldn't happen.
*/
if (WARN(before(*seq, TCP_SKB_CB(skb)->seq),
- "recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n",
+ "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n",
*seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
flags))
break;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
goto found_fin_ok;
WARN(!(flags & MSG_PEEK),
- "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n",
+ "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n",
*seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags);
}
sock_hold(sk);
sock_orphan(sk);
- /* It is the last release_sock in its life. It will remove backlog. */
- release_sock(sk);
-
-
- /* Now socket is owned by kernel and we acquire BH lock
- * to finish close. No need to check for user refs.
- */
local_bh_disable();
bh_lock_sock(sk);
- WARN_ON(sock_owned_by_user(sk));
+ /* remove backlog if any, without releasing ownership. */
+ __release_sock(sk);
percpu_counter_inc(sk->sk_prot->orphan_count);
tcp_send_active_reset(sk, GFP_ATOMIC);
__NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPABORTONMEMORY);
+ } else if (!check_net(sock_net(sk))) {
+ /* Not possible to send reset; just close */
+ tcp_set_state(sk, TCP_CLOSE);
}
}
out:
bh_unlock_sock(sk);
local_bh_enable();
+ release_sock(sk);
sock_put(sk);
}
EXPORT_SYMBOL(tcp_close);
INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue);
sk_mem_reclaim(sk);
tcp_clear_all_retrans_hints(tcp_sk(sk));
+ tcp_sk(sk)->packets_out = 0;
+ inet_csk(sk)->icsk_backoff = 0;
}
int tcp_disconnect(struct sock *sk, int flags)
tp->write_seq += tp->max_window + 2;
if (tp->write_seq == 0)
tp->write_seq = 1;
- icsk->icsk_backoff = 0;
tp->snd_cwnd = 2;
icsk->icsk_probes_out = 0;
- tp->packets_out = 0;
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_cnt = 0;
tp->window_clamp = 0;
dst_release(sk->sk_rx_dst);
sk->sk_rx_dst = NULL;
tcp_saved_syn_free(tp);
+ tp->bytes_acked = 0;
+ tp->bytes_received = 0;
/* Clean up fastopen related fields */
tcp_free_fastopen_req(tp);
WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
+ if (sk->sk_frag.page) {
+ put_page(sk->sk_frag.page);
+ sk->sk_frag.page = NULL;
+ sk->sk_frag.offset = 0;
+ }
+
sk->sk_error_report(sk);
return err;
}
name[val] = 0;
lock_sock(sk);
- err = tcp_set_congestion_control(sk, name, true, true);
+ err = tcp_set_congestion_control(sk, name, true, true,
+ ns_capable(sock_net(sk)->user_ns,
+ CAP_NET_ADMIN));
release_sock(sk);
return err;
}
case TCP_REPAIR_QUEUE:
if (!tp->repair)
err = -EPERM;
- else if (val < TCP_QUEUES_NR)
+ else if ((unsigned int)val < TCP_QUEUES_NR)
tp->repair_queue = val;
else
err = -EINVAL;
#ifdef CONFIG_TCP_MD5SIG
case TCP_MD5SIG:
case TCP_MD5SIG_EXT:
- /* Read the IP->Key mappings from userspace */
- err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
+ if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
+ err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
+ else
+ err = -EINVAL;
break;
#endif
case TCP_USER_TIMEOUT:
struct request_sock *req = inet_reqsk(sk);
local_bh_disable();
- inet_csk_reqsk_queue_drop_and_put(req->rsk_listener,
- req);
+ inet_csk_reqsk_queue_drop(req->rsk_listener, req);
local_bh_enable();
return 0;
}
bh_unlock_sock(sk);
local_bh_enable();
+ tcp_write_queue_purge(sk);
release_sock(sk);
return 0;
}
unsigned long limit;
unsigned int i;
+ BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE);
BUILD_BUG_ON(sizeof(struct tcp_skb_cb) >
FIELD_SIZEOF(struct sk_buff, cb));
projects / mirror_ubuntu-bionic-kernel.git / blobdiff