Changes representative of linux-3.10.0-957.21.3.el7.tar.xz

Documentation/networking/ip-sysctl.txt

@@ -214,6 +214,14 @@ tcp_base_mss - INTEGER
 	Path MTU discovery (MTU probing).  If MTU probing is enabled,
 	this is the initial MSS used by the connection.
 
+tcp_min_snd_mss - INTEGER
+	TCP SYN and SYNACK messages usually advertise an ADVMSS option,
+	as described in RFC 1122 and RFC 6691.
+	If this ADVMSS option is smaller than tcp_min_snd_mss,
+	it is silently capped to tcp_min_snd_mss.
+
+	Default : 48 (at least 8 bytes of payload per segment)
+
 tcp_congestion_control - STRING
 	Set the congestion control algorithm to be used for new
 	connections. The algorithm "reno" is always available, but

Makefile

@@ -5,7 +5,7 @@ EXTRAVERSION =
 NAME = Unicycling Gorilla
 RHEL_MAJOR = 7
 RHEL_MINOR = 6
-RHEL_RELEASE = 957.21.2
+RHEL_RELEASE = 957.21.3
 
 #
 # DRM backport version

include/linux/tcp.h

@@ -413,4 +413,6 @@ static inline int fastopen_init_queue(struct sock *sk, int backlog)
 	return 0;
 }
 
+int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,
+		  int shiftlen);
 #endif	/* _LINUX_TCP_H */

include/net/net_namespace.h

@@ -193,6 +193,7 @@ struct net {
 	/* upstream has this as part of netns_ipv4 */
 	RH_KABI_EXTEND(struct fib_notifier_ops	*ipv4_ipmr_notifier_ops)
 	RH_KABI_EXTEND(unsigned int ipv4_ipmr_seq)	/* protected by rtnl_mutex */
+	RH_KABI_EXTEND(int ipv4_sysctl_tcp_min_snd_mss)
 };
 
 /*

include/net/tcp.h

@@ -54,6 +54,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 
 #define MAX_TCP_HEADER	(128 + MAX_HEADER)
 #define MAX_TCP_OPTION_SPACE 40
+#define TCP_MIN_SND_MSS		48
+#define TCP_MIN_GSO_SIZE	(TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE)
 
 /* 
  * Never offer a window over 32767 without using window scaling. Some

include/uapi/linux/snmp.h

@@ -281,6 +281,8 @@ enum
 	LINUX_MIB_TCPACKSKIPPEDFINWAIT2,	/* TCPACKSkippedFinWait2 */
 	LINUX_MIB_TCPACKSKIPPEDTIMEWAIT,	/* TCPACKSkippedTimeWait */
 	LINUX_MIB_TCPACKSKIPPEDCHALLENGE,	/* TCPACKSkippedChallenge */
+	LINUX_MIB_PFMEMALLOCDROP,
+	LINUX_MIB_TCPWQUEUETOOBIG,		/* TCPWqueueTooBig */
 #endif
 	__LINUX_MIB_MAX
 };

net/ipv4/proc.c

@@ -297,6 +297,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPACKSkippedFinWait2", LINUX_MIB_TCPACKSKIPPEDFINWAIT2),
 	SNMP_MIB_ITEM("TCPACKSkippedTimeWait", LINUX_MIB_TCPACKSKIPPEDTIMEWAIT),
 	SNMP_MIB_ITEM("TCPACKSkippedChallenge", LINUX_MIB_TCPACKSKIPPEDCHALLENGE),
+	SNMP_MIB_ITEM("TCPWqueueTooBig", LINUX_MIB_TCPWQUEUETOOBIG),
 	SNMP_MIB_SENTINEL
 };
 

net/ipv4/sysctl_net_ipv4.c

@@ -36,6 +36,8 @@ static int ip_local_port_range_min[] = { 1, 1 };
 static int ip_local_port_range_max[] = { 65535, 65535 };
 static int tcp_adv_win_scale_min = -31;
 static int tcp_adv_win_scale_max = 31;
+static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS;
+static int tcp_min_snd_mss_max = 65535;
 static int ip_ttl_min = 1;
 static int ip_ttl_max = 255;
 static int tcp_syn_retries_min = 1;
@@ -953,6 +955,15 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
+	{
+		.procname	= "tcp_min_snd_mss",
+		.data		= &init_net.ipv4_sysctl_tcp_min_snd_mss,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &tcp_min_snd_mss_min,
+		.extra2		= &tcp_min_snd_mss_max,
+	},
 	{ }
 };
 

net/ipv4/tcp.c

@@ -3102,6 +3102,7 @@ void __init tcp_init(void)
 	int max_rshare, max_wshare, cnt;
 	unsigned int i;
 
+	BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE);
 	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
 
 	percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL);

net/ipv4/tcp_input.c

@@ -1300,13 +1300,13 @@ static u8 tcp_sacktag_one(struct sock *sk,
 /* Shift newly-SACKed bytes from this skb to the immediately previous
  * already-SACKed sk_buff. Mark the newly-SACKed bytes as such.
  */
-static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
+static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
+			    struct sk_buff *skb,
 			    struct tcp_sacktag_state *state,
 			    unsigned int pcount, int shifted, int mss,
 			    bool dup_sack)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *prev = tcp_write_queue_prev(sk, skb);
 	u32 start_seq = TCP_SKB_CB(skb)->seq;	/* start of newly-SACKed */
 	u32 end_seq = start_seq + shifted;	/* end of newly-SACKed */
 
@@ -1329,7 +1329,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 	TCP_SKB_CB(skb)->seq += shifted;
 
 	skb_shinfo(prev)->gso_segs += pcount;
-	BUG_ON(skb_shinfo(skb)->gso_segs < pcount);
+	WARN_ON_ONCE(tcp_skb_pcount(skb) < pcount);
 	skb_shinfo(skb)->gso_segs -= pcount;
 
 	/* When we're adding to gso_segs == 1, gso_size will be zero,
@@ -1395,6 +1395,21 @@ static int skb_can_shift(const struct sk_buff *skb)
 	return !skb_headlen(skb) && skb_is_nonlinear(skb);
 }
 
+int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from,
+		  int pcount, int shiftlen)
+{
+	/* TCP min gso_size is 8 bytes (TCP_MIN_GSO_SIZE)
+	 * Since TCP_SKB_CB(skb)->tcp_gso_segs is 16 bits, we need
+	 * to make sure not storing more than 65535 * 8 bytes per skb,
+	 * even if current MSS is bigger.
+	 */
+	if (unlikely(to->len + shiftlen >= 65535 * TCP_MIN_GSO_SIZE))
+		return 0;
+	if (unlikely(tcp_skb_pcount(to) + pcount > 65535))
+		return 0;
+	return skb_shift(to, from, shiftlen);
+}
+
 /* Try collapsing SACK blocks spanning across multiple skbs to a single
  * skb.
  */
@@ -1500,9 +1515,9 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 	if (!after(TCP_SKB_CB(skb)->seq + len, tp->snd_una))
 		goto fallback;
 
-	if (!skb_shift(prev, skb, len))
+	if (!tcp_skb_shift(prev, skb, pcount, len))
 		goto fallback;
-	if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack))
+	if (!tcp_shifted_skb(sk, prev, skb, state, pcount, len, mss, dup_sack))
 		goto out;
 
 	/* Hole filled allows collapsing with the next as well, this is very
@@ -1519,11 +1534,11 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 		goto out;
 
 	len = skb->len;
-	if (skb_shift(prev, skb, len)) {
+	if (tcp_skb_shift(prev, skb, tcp_skb_pcount(skb), len)) {
 		pcount += tcp_skb_pcount(skb);
-		tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0);
+		tcp_shifted_skb(sk, prev, skb, state, tcp_skb_pcount(skb),
+				len, mss, 0);
 	}
-
 out:
 	state->fack_count += pcount;
 	return prev;

net/ipv4/tcp_ipv4.c

@@ -2519,6 +2519,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_ecn = 2;
 
 	net->ipv4_sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME;
+	net->ipv4_sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS;
 	net->ipv4_sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES;
 	net->ipv4_sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL;
 

net/ipv4/tcp_output.c

@@ -1128,6 +1128,12 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 	if (nsize < 0)
 		nsize = 0;
 
+	if (unlikely((sk->sk_wmem_queued >> 1) > sk->sk_sndbuf) ||
+	    skb_queue_len(&sk->sk_write_queue) > 2048) {
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG);
+		return -ENOMEM;
+	}
+
 	if (skb_unclone(skb, GFP_ATOMIC))
 		return -ENOMEM;
 
@@ -1293,8 +1299,7 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu)
 	mss_now -= icsk->icsk_ext_hdr_len;
 
 	/* Then reserve room for full set of TCP options and 8 bytes of data */
-	if (mss_now < 48)
-		mss_now = 48;
+	mss_now = max(mss_now, sock_net(sk)->ipv4_sysctl_tcp_min_snd_mss);
 	return mss_now;
 }
 

net/ipv4/tcp_timer.c

@@ -104,12 +104,14 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 			icsk->icsk_mtup.enabled = 1;
 			tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		} else {
+			const struct net *net = sock_net(sk);
 			struct tcp_sock *tp = tcp_sk(sk);
 			int mss;
 
 			mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
 			mss = min(sysctl_tcp_base_mss, mss);
 			mss = max(mss, 68 - tp->tcp_header_len);
+			mss = max(mss, net->ipv4_sysctl_tcp_min_snd_mss);
 			icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
 			tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		}