fixes for 4.9

Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/queue-4.9/series b/queue-4.9/series
index e09a14ca37f4a7993a69a0dd5670f12548bb71e3..eeffc5ebd41f537f156e79f8d2546d019598dfa3 100644 (file)
--- a/queue-4.9/series
+++ b/queue-4.9/series
@@ -4,3 +4,4 @@ arm-dts-add-pinmuxing-for-i2c2-and-i2c3-for-logicpd-.patch-5864
 arm-dts-logicpd-som-lv-fix-audio-mute.patch
 arm64-cpufeature-fix-ctr_el0-field-definitions.patch
 arm64-cpufeature-fix-feature-comparison-for-ctr_el0..patch
+tcp-be-more-careful-in-tcp_fragment.patch

diff --git a/queue-4.9/tcp-be-more-careful-in-tcp_fragment.patch b/queue-4.9/tcp-be-more-careful-in-tcp_fragment.patch
new file mode 100644 (file)
index 0000000..2d2fe0d
--- /dev/null
+++ b/queue-4.9/tcp-be-more-careful-in-tcp_fragment.patch
@@ -0,0 +1,109 @@
+From b826c9f6580257900da2071c5e16980b66b21b4d Mon Sep 17 00:00:00 2001
+From: Eric Dumazet <edumazet@google.com>
+Date: Tue, 6 Aug 2019 17:09:14 +0200
+Subject: tcp: be more careful in tcp_fragment()
+
+[ Upstream commit b617158dc096709d8600c53b6052144d12b89fab ]
+
+Some applications set tiny SO_SNDBUF values and expect
+TCP to just work. Recent patches to address CVE-2019-11478
+broke them in case of losses, since retransmits might
+be prevented.
+
+We should allow these flows to make progress.
+
+This patch allows the first and last skb in retransmit queue
+to be split even if memory limits are hit.
+
+It also adds the some room due to the fact that tcp_sendmsg()
+and tcp_sendpage() might overshoot sk_wmem_queued by about one full
+TSO skb (64KB size). Note this allowance was already present
+in stable backports for kernels < 4.15
+
+Note for < 4.15 backports :
+ tcp_rtx_queue_tail() will probably look like :
+
+static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk)
+{
+       struct sk_buff *skb = tcp_send_head(sk);
+
+       return skb ? tcp_write_queue_prev(sk, skb) : tcp_write_queue_tail(sk);
+}
+
+Fixes: f070ef2ac667 ("tcp: tcp_fragment() should apply sane memory limits")
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Reported-by: Andrew Prout <aprout@ll.mit.edu>
+Tested-by: Andrew Prout <aprout@ll.mit.edu>
+Tested-by: Jonathan Lemon <jonathan.lemon@gmail.com>
+Tested-by: Michal Kubecek <mkubecek@suse.cz>
+Acked-by: Neal Cardwell <ncardwell@google.com>
+Acked-by: Yuchung Cheng <ycheng@google.com>
+Acked-by: Christoph Paasch <cpaasch@apple.com>
+Cc: Jonathan Looney <jtl@netflix.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ include/net/tcp.h     | 17 +++++++++++++++++
+ net/ipv4/tcp_output.c | 11 ++++++++++-
+ 2 files changed, 27 insertions(+), 1 deletion(-)
+
+diff --git a/include/net/tcp.h b/include/net/tcp.h
+index 1eda31f7f013b..a474213ca015b 100644
+--- a/include/net/tcp.h
++++ b/include/net/tcp.h
+@@ -1595,6 +1595,23 @@ static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unli
+               tcp_sk(sk)->highest_sack = NULL;
+ }
+ 
++static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk)
++{
++      struct sk_buff *skb = tcp_write_queue_head(sk);
++
++      if (skb == tcp_send_head(sk))
++              skb = NULL;
++
++      return skb;
++}
++
++static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk)
++{
++      struct sk_buff *skb = tcp_send_head(sk);
++
++      return skb ? tcp_write_queue_prev(sk, skb) : tcp_write_queue_tail(sk);
++}
++
+ static inline void __tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
+ {
+       __skb_queue_tail(&sk->sk_write_queue, skb);
+diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
+index 0c195b0f42169..9ddb05b98312c 100644
+--- a/net/ipv4/tcp_output.c
++++ b/net/ipv4/tcp_output.c
+@@ -1175,6 +1175,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
+       struct tcp_sock *tp = tcp_sk(sk);
+       struct sk_buff *buff;
+       int nsize, old_factor;
++      long limit;
+       int nlen;
+       u8 flags;
+ 
+@@ -1185,7 +1186,15 @@ 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 + 0x20000)) {
++      /* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb.
++       * We need some allowance to not penalize applications setting small
++       * SO_SNDBUF values.
++       * Also allow first and last skb in retransmit queue to be split.
++       */
++      limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE);
++      if (unlikely((sk->sk_wmem_queued >> 1) > limit &&
++                   skb != tcp_rtx_queue_head(sk) &&
++                   skb != tcp_rtx_queue_tail(sk))) {
+               NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG);
+               return -ENOMEM;
+       }
+-- 
+2.20.1
+