1 files changed, 284 insertions, 39 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8bb6adeb62c0..bb485fcb077e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -363,6 +363,71 @@ static int retrans_to_secs(u8 retrans, int timeout, int rto_max)
 	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.
  *
@@ -528,7 +593,7 @@ static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb)
 	tp->pushed_seq = tp->write_seq;
 }
 
-static inline int forced_push(const struct tcp_sock *tp)
+static inline bool forced_push(const struct tcp_sock *tp)
 {
 	return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1));
 }
@@ -784,9 +849,10 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse
 	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:
@@ -851,8 +917,7 @@ new_segment:
 wait_for_sndbuf:
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
-		if (copied)
-			tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
+		tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
 
 		if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
 			goto do_error;
@@ -919,7 +984,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 	int iovlen, flags, err, copied;
-	int mss_now, size_goal;
+	int mss_now = 0, size_goal;
 	bool sg;
 	long timeo;
 
@@ -933,6 +998,19 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
 			goto out_err;
 
+	if (unlikely(tp->repair)) {
+		if (tp->repair_queue == TCP_RECV_QUEUE) {
+			copied = tcp_send_rcvq(sk, msg, size);
+			goto out;
+		}
+
+		err = -EINVAL;
+		if (tp->repair_queue == TCP_NO_QUEUE)
+			goto out_err;
+
+		/* 'common' sending to sendq */
+	}
+
 	/* This should be in poll */
 	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
 
@@ -1003,7 +1081,7 @@ new_segment:
 				if (err)
 					goto do_fault;
 			} else {
-				int merge = 0;
+				bool merge = false;
 				int i = skb_shinfo(skb)->nr_frags;
 				struct page *page = sk->sk_sndmsg_page;
 				int off;
@@ -1017,7 +1095,7 @@ new_segment:
 				    off != PAGE_SIZE) {
 					/* We can extend the last page
 					 * fragment. */
-					merge = 1;
+					merge = true;
 				} else if (i == MAX_SKB_FRAGS || !sg) {
 					/* Need to add new fragment and cannot
 					 * do this because interface is non-SG,
@@ -1089,7 +1167,7 @@ new_segment:
 			if ((seglen -= copy) == 0 && iovlen == 0)
 				goto out;
 
-			if (skb->len < max || (flags & MSG_OOB))
+			if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair))
 				continue;
 
 			if (forced_push(tp)) {
@@ -1102,7 +1180,7 @@ new_segment:
 wait_for_sndbuf:
 			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
-			if (copied)
+			if (copied && likely(!tp->repair))
 				tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
 
 			if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
@@ -1113,7 +1191,7 @@ wait_for_memory:
 	}
 
 out:
-	if (copied)
+	if (copied && likely(!tp->repair))
 		tcp_push(sk, flags, mss_now, tp->nonagle);
 	release_sock(sk);
 	return copied;
@@ -1187,6 +1265,24 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags)
 	return -EAGAIN;
 }
 
+static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
+{
+	struct sk_buff *skb;
+	int copied = 0, err = 0;
+
+	/* XXX -- need to support SO_PEEK_OFF */
+
+	skb_queue_walk(&sk->sk_write_queue, skb) {
+		err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, skb->len);
+		if (err)
+			break;
+
+		copied += skb->len;
+	}
+
+	return err ?: copied;
+}
+
 /* Clean up the receive buffer for full frames taken by the user,
  * then send an ACK if necessary.  COPIED is the number of bytes
  * tcp_recvmsg has given to the user so far, it speeds up the
@@ -1196,7 +1292,7 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags)
 void tcp_cleanup_rbuf(struct sock *sk, int copied)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	int time_to_ack = 0;
+	bool time_to_ack = false;
 
 	struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
 
@@ -1222,7 +1318,7 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied)
 		      ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) &&
 		       !icsk->icsk_ack.pingpong)) &&
 		      !atomic_read(&sk->sk_rmem_alloc)))
-			time_to_ack = 1;
+			time_to_ack = true;
 	}
 
 	/* We send an ACK if we can now advertise a non-zero window
@@ -1244,7 +1340,7 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied)
 			 * "Lots" means "at least twice" here.
 			 */
 			if (new_window && new_window >= 2 * rcv_window_now)
-				time_to_ack = 1;
+				time_to_ack = true;
 		}
 	}
 	if (time_to_ack)
@@ -1376,11 +1472,11 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 				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;
@@ -1416,7 +1512,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	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;
 
@@ -1432,6 +1528,21 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (flags & MSG_OOB)
 		goto recv_urg;
 
+	if (unlikely(tp->repair)) {
+		err = -EPERM;
+		if (!(flags & MSG_PEEK))
+			goto out;
+
+		if (tp->repair_queue == TCP_SEND_QUEUE)
+			goto recv_sndq;
+
+		err = -EINVAL;
+		if (tp->repair_queue == TCP_NO_QUEUE)
+			goto out;
+
+		/* 'common' recv queue MSG_PEEK-ing */
+	}
+
 	seq = &tp->copied_seq;
 	if (flags & MSG_PEEK) {
 		peek_seq = tp->copied_seq;
@@ -1633,9 +1744,9 @@ do_prequeue:
 		}
 		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;
@@ -1689,7 +1800,7 @@ do_prequeue:
 				dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
 
 				if ((offset + used) == skb->len)
-					copied_early = 1;
+					copied_early = true;
 
 			} else
 #endif
@@ -1723,7 +1834,7 @@ skip_copy:
 			goto found_fin_ok;
 		if (!(flags & MSG_PEEK)) {
 			sk_eat_skb(sk, skb, copied_early);
-			copied_early = 0;
+			copied_early = false;
 		}
 		continue;
 
@@ -1732,7 +1843,7 @@ skip_copy:
 		++*seq;
 		if (!(flags & MSG_PEEK)) {
 			sk_eat_skb(sk, skb, copied_early);
-			copied_early = 0;
+			copied_early = false;
 		}
 		break;
 	} while (len > 0);
@@ -1783,6 +1894,10 @@ out:
 recv_urg:
 	err = tcp_recv_urg(sk, msg, len, flags);
 	goto out;
+
+recv_sndq:
+	err = tcp_peek_sndq(sk, msg, len);
+	goto out;
 }
 EXPORT_SYMBOL(tcp_recvmsg);
 
@@ -1886,10 +2001,10 @@ bool tcp_check_oom(struct sock *sk, int shift)
 	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;
 }
 
@@ -1935,7 +2050,9 @@ void tcp_close(struct sock *sk, long timeout)
 	 * advertise a zero window, then kill -9 the FTP client, wheee...
 	 * Note: timeout is always zero in such a case.
 	 */
-	if (data_was_unread) {
+	if (unlikely(tcp_sk(sk)->repair)) {
+		sk->sk_prot->disconnect(sk, 0);
+	} else if (data_was_unread) {
 		/* Unread data was tossed, zap the connection. */
 		NET_INC_STATS_USER(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE);
 		tcp_set_state(sk, TCP_CLOSE);
@@ -2053,7 +2170,7 @@ EXPORT_SYMBOL(tcp_close);
 
 /* These states need RST on ABORT according to RFC793 */
 
-static inline int tcp_need_reset(int state)
+static inline bool tcp_need_reset(int state)
 {
 	return (1 << state) &
 	       (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_FIN_WAIT1 |
@@ -2074,6 +2191,8 @@ int tcp_disconnect(struct sock *sk, int flags)
 	/* ABORT function of RFC793 */
 	if (old_state == TCP_LISTEN) {
 		inet_csk_listen_stop(sk);
+	} else if (unlikely(tp->repair)) {
+		sk->sk_err = ECONNABORTED;
 	} else if (tcp_need_reset(old_state) ||
 		   (tp->snd_nxt != tp->write_seq &&
 		    (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) {
@@ -2125,6 +2244,54 @@ int tcp_disconnect(struct sock *sk, int flags)
 }
 EXPORT_SYMBOL(tcp_disconnect);
 
+static inline bool tcp_can_repair_sock(const struct sock *sk)
+{
+	return capable(CAP_NET_ADMIN) &&
+		((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.
  */
@@ -2295,6 +2462,55 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 			err = -EINVAL;
 		else
 			tp->thin_dupack = val;
+			if (tp->thin_dupack)
+				tcp_disable_early_retrans(tp);
+		break;
+
+	case TCP_REPAIR:
+		if (!tcp_can_repair_sock(sk))
+			err = -EPERM;
+		else if (val == 1) {
+			tp->repair = 1;
+			sk->sk_reuse = SK_FORCE_REUSE;
+			tp->repair_queue = TCP_NO_QUEUE;
+		} else if (val == 0) {
+			tp->repair = 0;
+			sk->sk_reuse = SK_NO_REUSE;
+			tcp_send_window_probe(sk);
+		} else
+			err = -EINVAL;
+
+		break;
+
+	case TCP_REPAIR_QUEUE:
+		if (!tp->repair)
+			err = -EPERM;
+		else if (val < TCP_QUEUES_NR)
+			tp->repair_queue = val;
+		else
+			err = -EINVAL;
+		break;
+
+	case TCP_QUEUE_SEQ:
+		if (sk->sk_state != TCP_CLOSE)
+			err = -EPERM;
+		else if (tp->repair_queue == TCP_SEND_QUEUE)
+			tp->write_seq = val;
+		else if (tp->repair_queue == TCP_RECV_QUEUE)
+			tp->rcv_nxt = val;
+		else
+			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:
@@ -2530,6 +2746,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		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);
@@ -2632,6 +2850,26 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		val = tp->thin_dupack;
 		break;
 
+	case TCP_REPAIR:
+		val = tp->repair;
+		break;
+
+	case TCP_REPAIR_QUEUE:
+		if (tp->repair)
+			val = tp->repair_queue;
+		else
+			return -EINVAL;
+		break;
+
+	case TCP_QUEUE_SEQ:
+		if (tp->repair_queue == TCP_SEND_QUEUE)
+			val = tp->write_seq;
+		else if (tp->repair_queue == TCP_RECV_QUEUE)
+			val = tp->rcv_nxt;
+		else
+			return -EINVAL;
+		break;
+
 	case TCP_USER_TIMEOUT:
 		val = jiffies_to_msecs(icsk->icsk_user_timeout);
 		break;
@@ -2675,7 +2913,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct tcphdr *th;
-	unsigned thlen;
+	unsigned int thlen;
 	unsigned int seq;
 	__be32 delta;
 	unsigned int oldlen;
@@ -2933,13 +3171,13 @@ out_free:
 struct tcp_md5sig_pool __percpu *tcp_alloc_md5sig_pool(struct sock *sk)
 {
 	struct tcp_md5sig_pool __percpu *pool;
-	int alloc = 0;
+	bool alloc = false;
 
 retry:
 	spin_lock_bh(&tcp_md5sig_pool_lock);
 	pool = tcp_md5sig_pool;
 	if (tcp_md5sig_users++ == 0) {
-		alloc = 1;
+		alloc = true;
 		spin_unlock_bh(&tcp_md5sig_pool_lock);
 	} else if (!pool) {
 		tcp_md5sig_users--;
@@ -3033,9 +3271,9 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
 	struct scatterlist sg;
 	const struct tcphdr *tp = tcp_hdr(skb);
 	struct hash_desc *desc = &hp->md5_desc;
-	unsigned i;
-	const unsigned head_data_len = skb_headlen(skb) > header_len ?
-				       skb_headlen(skb) - header_len : 0;
+	unsigned int i;
+	const unsigned int head_data_len = skb_headlen(skb) > header_len ?
+					   skb_headlen(skb) - header_len : 0;
 	const struct skb_shared_info *shi = skb_shinfo(skb);
 	struct sk_buff *frag_iter;
 
@@ -3223,9 +3461,15 @@ extern struct tcp_congestion_ops tcp_reno;
 static __initdata unsigned long thash_entries;
 static int __init set_thash_entries(char *str)
 {
+	ssize_t ret;
+
 	if (!str)
 		return 0;
-	thash_entries = simple_strtoul(str, &str, 0);
+
+	ret = kstrtoul(str, 0, &thash_entries);
+	if (ret)
+		return 0;
+
 	return 1;
 }
 __setup("thash_entries=", set_thash_entries);
@@ -3243,7 +3487,7 @@ void __init tcp_init(void)
 {
 	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;
 
@@ -3303,15 +3547,16 @@ void __init tcp_init(void)
 	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);