netdev - [RFC PATCH v2 18/45] tcp: Prevent coalesce/collapse when skb has MPTCP extensions

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20191002233655.24323-19-mathew.j.martineau@linux.intel.com>
Date:   Wed,  2 Oct 2019 16:36:28 -0700
From:   Mat Martineau <mathew.j.martineau@...ux.intel.com>
To:     netdev@...r.kernel.org, edumazet@...gle.com
Cc:     Mat Martineau <mathew.j.martineau@...ux.intel.com>,
        cpaasch@...le.com, fw@...len.de, pabeni@...hat.com,
        peter.krystad@...ux.intel.com, dcaratti@...hat.com,
        matthieu.baerts@...sares.net
Subject: [RFC PATCH v2 18/45] tcp: Prevent coalesce/collapse when skb has MPTCP extensions

The MPTCP extension data needs to be preserved as it passes through the
TCP stack. Make sure that these skbs are not appended to others during
coalesce or collapse, so the data remains associated with the payload of
the given skb.

Signed-off-by: Mat Martineau <mathew.j.martineau@...ux.intel.com>
---
 include/net/mptcp.h   | 10 ++++++++++
 include/net/tcp.h     |  8 ++++++++
 net/ipv4/tcp_input.c  | 10 ++++++++--
 net/ipv4/tcp_output.c |  2 +-
 4 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 6921b7fb6f0d..5ec275708036 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -56,6 +56,11 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
 bool mptcp_established_options(struct sock *sk, unsigned int *size,
 			       struct mptcp_out_options *opts);
 
+static inline bool mptcp_skb_ext_exist(const struct sk_buff *skb)
+{
+	return skb_ext_exist(skb, SKB_EXT_MPTCP);
+}
+
 void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts);
 
 #else
@@ -103,5 +108,10 @@ static inline bool mptcp_established_options(struct sock *sk,
 	return false;
 }
 
+static inline bool mptcp_skb_ext_exist(const struct sk_buff *skb)
+{
+	return false;
+}
+
 #endif /* CONFIG_MPTCP */
 #endif /* __NET_MPTCP_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 907fd214ff1e..ddc098b33999 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -39,6 +39,7 @@
 #include <net/tcp_states.h>
 #include <net/inet_ecn.h>
 #include <net/dst.h>
+#include <net/mptcp.h>
 
 #include <linux/seq_file.h>
 #include <linux/memcontrol.h>
@@ -962,6 +963,13 @@ static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb)
 	return likely(!TCP_SKB_CB(skb)->eor);
 }
 
+static inline bool tcp_skb_can_collapse(const struct sk_buff *to,
+					const struct sk_buff *from)
+{
+	return likely(tcp_skb_can_collapse_to(to) &&
+		      !mptcp_skb_ext_exist(from));
+}
+
 /* Events passed to congestion control interface */
 enum tcp_ca_event {
 	CA_EVENT_TX_START,	/* first transmit when no packets in flight */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 218df735c822..04267684babf 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1421,7 +1421,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 	if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED)
 		goto fallback;
 
-	if (!tcp_skb_can_collapse_to(prev))
+	if (!tcp_skb_can_collapse(prev, skb))
 		goto fallback;
 
 	in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
@@ -4423,6 +4423,9 @@ static bool tcp_try_coalesce(struct sock *sk,
 	if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
 		return false;
 
+	if (mptcp_skb_ext_exist(from))
+		return false;
+
 #ifdef CONFIG_TLS_DEVICE
 	if (from->decrypted != to->decrypted)
 		return false;
@@ -4931,10 +4934,12 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
 
 		/* The first skb to collapse is:
 		 * - not SYN/FIN and
+		 * - does not include a MPTCP skb extension
 		 * - bloated or contains data before "start" or
 		 *   overlaps to the next one.
 		 */
 		if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) &&
+		    !mptcp_skb_ext_exist(skb) &&
 		    (tcp_win_from_space(sk, skb->truesize) > skb->len ||
 		     before(TCP_SKB_CB(skb)->seq, start))) {
 			end_of_skbs = false;
@@ -4950,7 +4955,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
 		/* Decided to skip this, advance start seq. */
 		start = TCP_SKB_CB(skb)->end_seq;
 	}
-	if (end_of_skbs ||
+	if (end_of_skbs || mptcp_skb_ext_exist(skb) ||
 	    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
 		return;
 
@@ -4993,6 +4998,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
 				skb = tcp_collapse_one(sk, skb, list, root);
 				if (!skb ||
 				    skb == tail ||
+				    mptcp_skb_ext_exist(skb) ||
 				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
 					goto end;
 #ifdef CONFIG_TLS_DEVICE
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e21e8134559a..415b0414d738 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2911,7 +2911,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
 		if (!tcp_can_collapse(sk, skb))
 			break;
 
-		if (!tcp_skb_can_collapse_to(to))
+		if (!tcp_skb_can_collapse(to, skb))
 			break;
 
 		space -= skb->len;
-- 
2.23.0