return period;
}
+/* Address-family independent initialization for a tcp_sock.
+ *
+ * NOTE: A lot of things set to zero explicitly by call to
+ * sk_alloc() so need not be done here.
+ */
+void tcp_init_sock(struct sock *sk)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ skb_queue_head_init(&tp->out_of_order_queue);
+ tcp_init_xmit_timers(sk);
+ tcp_prequeue_init(tp);
+
+ icsk->icsk_rto = TCP_TIMEOUT_INIT;
+ tp->mdev = TCP_TIMEOUT_INIT;
+
+ /* So many TCP implementations out there (incorrectly) count the
+ * initial SYN frame in their delayed-ACK and congestion control
+ * algorithms that we must have the following bandaid to talk
+ * efficiently to them. -DaveM
+ */
+ tp->snd_cwnd = TCP_INIT_CWND;
+
+ /* See draft-stevens-tcpca-spec-01 for discussion of the
+ * initialization of these values.
+ */
+ tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
+ tp->snd_cwnd_clamp = ~0;
+ tp->mss_cache = TCP_MSS_DEFAULT;
+
+ tp->reordering = sysctl_tcp_reordering;
+ tcp_enable_early_retrans(tp);
+ icsk->icsk_ca_ops = &tcp_init_congestion_ops;
+
+ sk->sk_state = TCP_CLOSE;
+
+ sk->sk_write_space = sk_stream_write_space;
+ sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
+
+ icsk->icsk_sync_mss = tcp_sync_mss;
+
+ /* TCP Cookie Transactions */
+ if (sysctl_tcp_cookie_size > 0) {
+ /* Default, cookies without s_data_payload. */
+ tp->cookie_values =
+ kzalloc(sizeof(*tp->cookie_values),
+ sk->sk_allocation);
+ if (tp->cookie_values != NULL)
+ kref_init(&tp->cookie_values->kref);
+ }
+ /* Presumed zeroed, in order of appearance:
+ * cookie_in_always, cookie_out_never,
+ * s_data_constant, s_data_in, s_data_out
+ */
+ sk->sk_sndbuf = sysctl_tcp_wmem[1];
+ sk->sk_rcvbuf = sysctl_tcp_rmem[1];
+
+ local_bh_disable();
+ sock_update_memcg(sk);
+ sk_sockets_allocated_inc(sk);
+ local_bh_enable();
+}
+EXPORT_SYMBOL(tcp_init_sock);
+
/*
* Wait for a TCP event.
*
while (psize > 0) {
struct sk_buff *skb = tcp_write_queue_tail(sk);
struct page *page = pages[poffset / PAGE_SIZE];
- int copy, i, can_coalesce;
+ int copy, i;
int offset = poffset % PAGE_SIZE;
int size = min_t(size_t, psize, PAGE_SIZE - offset);
+ bool can_coalesce;
if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0) {
new_segment:
return tmp;
}
-static int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
-{
- struct sk_buff *skb;
- struct tcp_skb_cb *cb;
- struct tcphdr *th;
-
- skb = alloc_skb(size + sizeof(*th), sk->sk_allocation);
- if (!skb)
- goto err;
-
- th = (struct tcphdr *)skb_put(skb, sizeof(*th));
- skb_reset_transport_header(skb);
- memset(th, 0, sizeof(*th));
-
- if (memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size))
- goto err_free;
-
- cb = TCP_SKB_CB(skb);
-
- TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
- TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + size;
- TCP_SKB_CB(skb)->ack_seq = tcp_sk(sk)->snd_una - 1;
-
- tcp_queue_rcv(sk, skb, sizeof(*th));
-
- return size;
-
-err_free:
- kfree_skb(skb);
-err:
- return -ENOMEM;
-}
-
int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t size)
{
break;
}
if (tcp_hdr(skb)->fin) {
- sk_eat_skb(sk, skb, 0);
+ sk_eat_skb(sk, skb, false);
++seq;
break;
}
- sk_eat_skb(sk, skb, 0);
+ sk_eat_skb(sk, skb, false);
if (!desc->count)
break;
tp->copied_seq = seq;
int target; /* Read at least this many bytes */
long timeo;
struct task_struct *user_recv = NULL;
- int copied_early = 0;
+ bool copied_early = false;
struct sk_buff *skb;
u32 urg_hole = 0;
}
if ((flags & MSG_PEEK) &&
(peek_seq - copied - urg_hole != tp->copied_seq)) {
- if (net_ratelimit())
- printk(KERN_DEBUG "TCP(%s:%d): Application bug, race in MSG_PEEK.\n",
- current->comm, task_pid_nr(current));
+ net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n",
+ current->comm,
+ task_pid_nr(current));
peek_seq = tp->copied_seq;
}
continue;
dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
if ((offset + used) == skb->len)
- copied_early = 1;
+ copied_early = true;
} else
#endif
goto found_fin_ok;
if (!(flags & MSG_PEEK)) {
sk_eat_skb(sk, skb, copied_early);
- copied_early = 0;
+ copied_early = false;
}
continue;
++*seq;
if (!(flags & MSG_PEEK)) {
sk_eat_skb(sk, skb, copied_early);
- copied_early = 0;
+ copied_early = false;
}
break;
} while (len > 0);
too_many_orphans = tcp_too_many_orphans(sk, shift);
out_of_socket_memory = tcp_out_of_memory(sk);
- if (too_many_orphans && net_ratelimit())
- pr_info("too many orphaned sockets\n");
- if (out_of_socket_memory && net_ratelimit())
- pr_info("out of memory -- consider tuning tcp_mem\n");
+ if (too_many_orphans)
+ net_info_ratelimited("too many orphaned sockets\n");
+ if (out_of_socket_memory)
+ net_info_ratelimited("out of memory -- consider tuning tcp_mem\n");
return too_many_orphans || out_of_socket_memory;
}
((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_ESTABLISHED));
}
+static int tcp_repair_options_est(struct tcp_sock *tp,
+ struct tcp_repair_opt __user *optbuf, unsigned int len)
+{
+ struct tcp_repair_opt opt;
+
+ while (len >= sizeof(opt)) {
+ if (copy_from_user(&opt, optbuf, sizeof(opt)))
+ return -EFAULT;
+
+ optbuf++;
+ len -= sizeof(opt);
+
+ switch (opt.opt_code) {
+ case TCPOPT_MSS:
+ tp->rx_opt.mss_clamp = opt.opt_val;
+ break;
+ case TCPOPT_WINDOW:
+ if (opt.opt_val > 14)
+ return -EFBIG;
+
+ tp->rx_opt.snd_wscale = opt.opt_val;
+ break;
+ case TCPOPT_SACK_PERM:
+ if (opt.opt_val != 0)
+ return -EINVAL;
+
+ tp->rx_opt.sack_ok |= TCP_SACK_SEEN;
+ if (sysctl_tcp_fack)
+ tcp_enable_fack(tp);
+ break;
+ case TCPOPT_TIMESTAMP:
+ if (opt.opt_val != 0)
+ return -EINVAL;
+
+ tp->rx_opt.tstamp_ok = 1;
+ break;
+ }
+ }
+
+ return 0;
+}
+
/*
* Socket option code for TCP.
*/
err = -EINVAL;
else
tp->thin_dupack = val;
+ if (tp->thin_dupack)
+ tcp_disable_early_retrans(tp);
break;
case TCP_REPAIR:
err = -EINVAL;
break;
+ case TCP_REPAIR_OPTIONS:
+ if (!tp->repair)
+ err = -EINVAL;
+ else if (sk->sk_state == TCP_ESTABLISHED)
+ err = tcp_repair_options_est(tp,
+ (struct tcp_repair_opt __user *)optval,
+ optlen);
+ else
+ err = -EPERM;
+ break;
+
case TCP_CORK:
/* When set indicates to always queue non-full frames.
* Later the user clears this option and we transmit
val = tp->mss_cache;
if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
val = tp->rx_opt.user_mss;
+ if (tp->repair)
+ val = tp->rx_opt.mss_clamp;
break;
case TCP_NODELAY:
val = !!(tp->nonagle&TCP_NAGLE_OFF);
{
struct sk_buff *skb = NULL;
unsigned long limit;
- int max_share, cnt;
+ int max_rshare, max_wshare, cnt;
unsigned int i;
unsigned long jiffy = jiffies;
tcp_init_mem(&init_net);
/* Set per-socket limits to no more than 1/128 the pressure threshold */
limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7);
- max_share = min(4UL*1024*1024, limit);
+ max_wshare = min(4UL*1024*1024, limit);
+ max_rshare = min(6UL*1024*1024, limit);
sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;
sysctl_tcp_wmem[1] = 16*1024;
- sysctl_tcp_wmem[2] = max(64*1024, max_share);
+ sysctl_tcp_wmem[2] = max(64*1024, max_wshare);
sysctl_tcp_rmem[0] = SK_MEM_QUANTUM;
sysctl_tcp_rmem[1] = 87380;
- sysctl_tcp_rmem[2] = max(87380, max_share);
+ sysctl_tcp_rmem[2] = max(87380, max_rshare);
pr_info("Hash tables configured (established %u bind %u)\n",
tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
projects / deliverable / linux.git / blobdiff