Merge 4.9.182 into android-4.9
Changes in 4.9.182
tcp: reduce tcp_fastretrans_alert() verbosity
tcp: limit payload size of sacked skbs
tcp: tcp_fragment() should apply sane memory limits
tcp: add tcp_min_snd_mss sysctl
tcp: enforce tcp_min_snd_mss in tcp_mtu_probing()
Linux 4.9.182
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index fcdcee3..25e2cf0 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -230,6 +230,14 @@
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
diff --git a/Makefile b/Makefile
index 4df20ca..7a9a333 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
VERSION = 4
PATCHLEVEL = 9
-SUBLEVEL = 181
+SUBLEVEL = 182
EXTRAVERSION =
NAME = Roaring Lionus
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index b8ea15a..4fd7dd9 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -434,4 +434,7 @@
tp->saved_syn = NULL;
}
+int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,
+ int shiftlen);
+
#endif /* _LINUX_TCP_H */
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 7adf438..bf619a6 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -94,6 +94,7 @@
#endif
int sysctl_tcp_mtu_probing;
int sysctl_tcp_base_mss;
+ int sysctl_tcp_min_snd_mss;
int sysctl_tcp_probe_threshold;
u32 sysctl_tcp_probe_interval;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index d69edf1..a15d620 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -53,6 +53,8 @@
#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
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 3442a26..56e3460 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -282,6 +282,7 @@
LINUX_MIB_TCPKEEPALIVE, /* TCPKeepAlive */
LINUX_MIB_TCPMTUPFAIL, /* TCPMTUPFail */
LINUX_MIB_TCPMTUPSUCCESS, /* TCPMTUPSuccess */
+ LINUX_MIB_TCPWQUEUETOOBIG, /* TCPWqueueTooBig */
__LINUX_MIB_MAX
};
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index ec48d8ea..8b22139 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -306,6 +306,7 @@
SNMP_MIB_ITEM("TCPKeepAlive", LINUX_MIB_TCPKEEPALIVE),
SNMP_MIB_ITEM("TCPMTUPFail", LINUX_MIB_TCPMTUPFAIL),
SNMP_MIB_ITEM("TCPMTUPSuccess", LINUX_MIB_TCPMTUPSUCCESS),
+ SNMP_MIB_ITEM("TCPWqueueTooBig", LINUX_MIB_TCPWQUEUETOOBIG),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index c19c605..2243685 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -35,6 +35,8 @@
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;
@@ -861,6 +863,15 @@
.proc_handler = proc_dointvec,
},
{
+ .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,
+ },
+ {
.procname = "tcp_probe_threshold",
.data = &init_net.ipv4.sysctl_tcp_probe_threshold,
.maxlen = sizeof(int),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8e95797..d61190e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3350,6 +3350,7 @@
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));
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 44af880..1b95e22 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1321,7 +1321,7 @@
TCP_SKB_CB(skb)->seq += shifted;
tcp_skb_pcount_add(prev, pcount);
- BUG_ON(tcp_skb_pcount(skb) < pcount);
+ WARN_ON_ONCE(tcp_skb_pcount(skb) < pcount);
tcp_skb_pcount_add(skb, -pcount);
/* When we're adding to gso_segs == 1, gso_size will be zero,
@@ -1388,6 +1388,21 @@
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.
*/
@@ -1399,6 +1414,7 @@
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *prev;
int mss;
+ int next_pcount;
int pcount = 0;
int len;
int in_sack;
@@ -1496,7 +1512,7 @@
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))
goto out;
@@ -1515,11 +1531,11 @@
goto out;
len = skb->len;
- if (skb_shift(prev, skb, len)) {
- pcount += tcp_skb_pcount(skb);
- tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0);
+ next_pcount = tcp_skb_pcount(skb);
+ if (tcp_skb_shift(prev, skb, next_pcount, len)) {
+ pcount += next_pcount;
+ tcp_shifted_skb(sk, skb, state, next_pcount, len, mss, 0);
}
-
out:
state->fack_count += pcount;
return prev;
@@ -2838,9 +2854,9 @@
bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
(tcp_fackets_out(tp) > tp->reordering));
- if (WARN_ON(!tp->packets_out && tp->sacked_out))
+ if (!tp->packets_out && tp->sacked_out)
tp->sacked_out = 0;
- if (WARN_ON(!tp->sacked_out && tp->fackets_out))
+ if (!tp->sacked_out && tp->fackets_out)
tp->fackets_out = 0;
/* Now state machine starts.
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index e6a22c2..9e2e8ee 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2466,6 +2466,7 @@
net->ipv4.sysctl_tcp_ecn_fallback = 1;
net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
+ net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS;
net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD;
net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8d31f60..c1fd321 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1185,6 +1185,11 @@
if (nsize < 0)
nsize = 0;
+ if (unlikely((sk->sk_wmem_queued >> 1) > sk->sk_sndbuf)) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG);
+ return -ENOMEM;
+ }
+
if (skb_unclone(skb, gfp))
return -ENOMEM;
@@ -1355,8 +1360,7 @@
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;
}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 6952338..d9e364c 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -140,6 +140,7 @@
mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
mss = min(net->ipv4.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);
}