Merge branch 'tcp-receiver-changes'

Eric Dumazet says:

====================
tcp: receiver changes

Before accepting an incoming packet:

- Make sure to not accept a packet beyond advertized RWIN.
  If not, increment a new SNMP counter (LINUX_MIB_BEYOND_WINDOW)

- ooo packets should update rcv_mss and tp->scaling_ratio.

- Make sure to not accept packet beyond sk_rcvbuf limit.

This series includes three associated packetdrill tests.
====================

Link: https://patch.msgid.link/20250711114006.480026-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/networking/net_cachelines/snmp.rst

@@ -36,6 +36,7 @@ unsigned_long  LINUX_MIB_TIMEWAITRECYCLED
 unsigned_long  LINUX_MIB_TIMEWAITKILLED
 unsigned_long  LINUX_MIB_PAWSACTIVEREJECTED
 unsigned_long  LINUX_MIB_PAWSESTABREJECTED
+unsigned_long  LINUX_MIB_BEYOND_WINDOW
 unsigned_long  LINUX_MIB_TSECR_REJECTED
 unsigned_long  LINUX_MIB_PAWS_OLD_ACK
 unsigned_long  LINUX_MIB_PAWS_TW_REJECTED

include/net/dropreason-core.h

@@ -45,6 +45,7 @@
 	FN(TCP_LISTEN_OVERFLOW)		\
 	FN(TCP_OLD_SEQUENCE)		\
 	FN(TCP_INVALID_SEQUENCE)	\
+	FN(TCP_INVALID_END_SEQUENCE)	\
 	FN(TCP_INVALID_ACK_SEQUENCE)	\
 	FN(TCP_RESET)			\
 	FN(TCP_INVALID_SYN)		\
@@ -303,8 +304,14 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_TCP_LISTEN_OVERFLOW,
 	/** @SKB_DROP_REASON_TCP_OLD_SEQUENCE: Old SEQ field (duplicate packet) */
 	SKB_DROP_REASON_TCP_OLD_SEQUENCE,
-	/** @SKB_DROP_REASON_TCP_INVALID_SEQUENCE: Not acceptable SEQ field */
+	/** @SKB_DROP_REASON_TCP_INVALID_SEQUENCE: Not acceptable SEQ field. */
 	SKB_DROP_REASON_TCP_INVALID_SEQUENCE,
+	/**
+	 * @SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE:
+	 * Not acceptable END_SEQ field.
+	 * Corresponds to LINUX_MIB_BEYOND_WINDOW.
+	 */
+	SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE,
 	/**
 	 * @SKB_DROP_REASON_TCP_INVALID_ACK_SEQUENCE: Not acceptable ACK SEQ
 	 * field because ack sequence is not in the window between snd_una

include/net/sock.h

@@ -1553,7 +1553,7 @@ __sk_rmem_schedule(struct sock *sk, int size, bool pfmemalloc)
 }
 
 static inline bool
-sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size)
+sk_rmem_schedule(struct sock *sk, const struct sk_buff *skb, int size)
 {
 	return __sk_rmem_schedule(sk, size, skb_pfmemalloc(skb));
 }

include/uapi/linux/snmp.h

@@ -186,6 +186,7 @@ enum
 	LINUX_MIB_TIMEWAITKILLED,		/* TimeWaitKilled */
 	LINUX_MIB_PAWSACTIVEREJECTED,		/* PAWSActiveRejected */
 	LINUX_MIB_PAWSESTABREJECTED,		/* PAWSEstabRejected */
+	LINUX_MIB_BEYOND_WINDOW,		/* BeyondWindow */
 	LINUX_MIB_TSECRREJECTED,		/* TSEcrRejected */
 	LINUX_MIB_PAWS_OLD_ACK,			/* PAWSOldAck */
 	LINUX_MIB_PAWS_TW_REJECTED,		/* PAWSTimewait */

net/ipv4/proc.c

@@ -189,6 +189,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TWKilled", LINUX_MIB_TIMEWAITKILLED),
 	SNMP_MIB_ITEM("PAWSActive", LINUX_MIB_PAWSACTIVEREJECTED),
 	SNMP_MIB_ITEM("PAWSEstab", LINUX_MIB_PAWSESTABREJECTED),
+	SNMP_MIB_ITEM("BeyondWindow", LINUX_MIB_BEYOND_WINDOW),
 	SNMP_MIB_ITEM("TSEcrRejected", LINUX_MIB_TSECRREJECTED),
 	SNMP_MIB_ITEM("PAWSOldAck", LINUX_MIB_PAWS_OLD_ACK),
 	SNMP_MIB_ITEM("PAWSTimewait", LINUX_MIB_PAWS_TW_REJECTED),

net/ipv4/tcp_input.c

@@ -4391,14 +4391,22 @@ static enum skb_drop_reason tcp_disordered_ack_check(const struct sock *sk,
  * (borrowed from freebsd)
  */
 
-static enum skb_drop_reason tcp_sequence(const struct tcp_sock *tp,
+static enum skb_drop_reason tcp_sequence(const struct sock *sk,
 					 u32 seq, u32 end_seq)
 {
+	const struct tcp_sock *tp = tcp_sk(sk);
+
 	if (before(end_seq, tp->rcv_wup))
 		return SKB_DROP_REASON_TCP_OLD_SEQUENCE;
 
-	if (after(seq, tp->rcv_nxt + tcp_receive_window(tp)))
+	if (after(end_seq, tp->rcv_nxt + tcp_receive_window(tp))) {
-		return SKB_DROP_REASON_TCP_INVALID_SEQUENCE;
+		if (after(seq, tp->rcv_nxt + tcp_receive_window(tp)))
+			return SKB_DROP_REASON_TCP_INVALID_SEQUENCE;
+
+		/* Only accept this packet if receive queue is empty. */
+		if (skb_queue_len(&sk->sk_receive_queue))
+			return SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE;
+	}
 
 	return SKB_NOT_DROPPED_YET;
 }
@@ -4880,10 +4888,20 @@ static void tcp_ofo_queue(struct sock *sk)
 static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb);
 static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb);
 
-static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb,
+/* Check if this incoming skb can be added to socket receive queues
+ * while satisfying sk->sk_rcvbuf limit.
+ */
+static bool tcp_can_ingest(const struct sock *sk, const struct sk_buff *skb)
+{
+	unsigned int new_mem = atomic_read(&sk->sk_rmem_alloc) + skb->truesize;
+
+	return new_mem <= sk->sk_rcvbuf;
+}
+
+static int tcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb,
 				 unsigned int size)
 {
-	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
+	if (!tcp_can_ingest(sk, skb) ||
 	    !sk_rmem_schedule(sk, skb, size)) {
 
 		if (tcp_prune_queue(sk, skb) < 0)
@@ -4915,6 +4933,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 		return;
 	}
 
+	tcp_measure_rcv_mss(sk, skb);
 	/* Disable header prediction. */
 	tp->pred_flags = 0;
 	inet_csk_schedule_ack(sk);
@@ -5498,7 +5517,7 @@ static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb)
 		tcp_drop_reason(sk, skb, SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE);
 		tp->ooo_last_skb = rb_to_skb(prev);
 		if (!prev || goal <= 0) {
-			if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+			if (tcp_can_ingest(sk, skb) &&
 			    !tcp_under_memory_pressure(sk))
 				break;
 			goal = sk->sk_rcvbuf >> 3;
@@ -5532,12 +5551,12 @@ static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb)
 
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_PRUNECALLED);
 
-	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
+	if (!tcp_can_ingest(sk, in_skb))
 		tcp_clamp_window(sk);
 	else if (tcp_under_memory_pressure(sk))
 		tcp_adjust_rcv_ssthresh(sk);
 
-	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+	if (tcp_can_ingest(sk, in_skb))
 		return 0;
 
 	tcp_collapse_ofo_queue(sk);
@@ -5547,7 +5566,7 @@ static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb)
 			     NULL,
 			     tp->copied_seq, tp->rcv_nxt);
 
-	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+	if (tcp_can_ingest(sk, in_skb))
 		return 0;
 
 	/* Collapsing did not help, destructive actions follow.
@@ -5555,7 +5574,7 @@ static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb)
 
 	tcp_prune_ofo_queue(sk, in_skb);
 
-	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+	if (tcp_can_ingest(sk, in_skb))
 		return 0;
 
 	/* If we are really being abused, tell the caller to silently
@@ -5881,7 +5900,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 
 step1:
 	/* Step 1: check sequence number */
-	reason = tcp_sequence(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
+	reason = tcp_sequence(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
 	if (reason) {
 		/* RFC793, page 37: "In all states except SYN-SENT, all reset
 		 * (RST) segments are validated by checking their SEQ-fields."
@@ -5892,6 +5911,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 		if (!th->rst) {
 			if (th->syn)
 				goto syn_challenge;
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_BEYOND_WINDOW);
 			if (!tcp_oow_rate_limited(sock_net(sk), skb,
 						  LINUX_MIB_TCPACKSKIPPEDSEQ,
 						  &tp->last_oow_ack_time))
@@ -6110,6 +6130,10 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 			if (tcp_checksum_complete(skb))
 				goto csum_error;
 
+			if (after(TCP_SKB_CB(skb)->end_seq,
+				  tp->rcv_nxt + tcp_receive_window(tp)))
+				goto validate;
+
 			if ((int)skb->truesize > sk->sk_forward_alloc)
 				goto step5;
 
@@ -6165,7 +6189,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 	/*
 	 *	Standard slow path.
 	 */
-
+validate:
 	if (!tcp_validate_incoming(sk, skb, th, 1))
 		return;
 

tools/testing/selftests/net/packetdrill/tcp_ooo_rcv_mss.pkt

@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+
+--mss=1000
+
+`./defaults.sh
+sysctl -q net.ipv4.tcp_rmem="4096 131072 $((32*1024*1024))"`
+
+   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 65535 <mss 1000,nop,nop,sackOK,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 10>
+  +.1 < . 1:1(0) ack 1 win 257
+
+   +0 accept(3, ..., ...) = 4
+
+   +0 < . 2001:11001(9000) ack 1 win 257
+   +0 > . 1:1(0) ack 1 win 81 <nop,nop,sack 2001:11001>
+
+// check that ooo packet properly updates tcpi_rcv_mss
+   +0 %{ assert tcpi_rcv_mss == 1000, tcpi_rcv_mss }%
+
+   +0 < . 11001:21001(10000) ack 1 win 257
+   +0 > . 1:1(0) ack 1 win 81 <nop,nop,sack 2001:21001>
+

tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt

@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+
+--mss=1000
+
+`./defaults.sh`
+
+    0 `nstat -n`
+
+// Establish a connection.
+   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [10000], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 0>
+  +.1 < . 1:1(0) ack 1 win 257
+
+  +0 accept(3, ..., ...) = 4
+
+  +0 < P. 1:4001(4000) ack 1 win 257
+  +0 > .  1:1(0) ack 4001 win 5000
+
+// packet in sequence : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
+  +0 < P. 4001:54001(50000) ack 1 win 257
+  +0 > .  1:1(0) ack 4001 win 5000
+
+// ooo packet. : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
+  +1 < P. 5001:55001(50000) ack 1 win 257
+  +0 > .  1:1(0) ack 4001 win 5000
+
+// SKB_DROP_REASON_TCP_INVALID_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
+  +0 < P. 70001:80001(10000) ack 1 win 257
+  +0 > .  1:1(0) ack 4001 win 5000
+
+  +0 read(4, ..., 100000) = 4000
+
+// If queue is empty, accept a packet even if its end_seq is above wup + rcv_wnd
+  +0 < P. 4001:54001(50000) ack 1 win 257
+  +.040 > .  1:1(0) ack 54001 win 0
+
+// Check LINUX_MIB_BEYOND_WINDOW has been incremented 3 times.
++0 `nstat | grep TcpExtBeyondWindow | grep -q " 3 "`

tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt

@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+
+--mss=1000
+
+`./defaults.sh`
+
+    0 `nstat -n`
+
+// Establish a connection.
+   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 win 18980 <mss 1460,nop,wscale 0>
+  +.1 < . 1:1(0) ack 1 win 257
+
+   +0 accept(3, ..., ...) = 4
+
+   +0 < P. 1:20001(20000) ack 1 win 257
+ +.04 > .  1:1(0) ack 20001 win 18000
+
+   +0 setsockopt(4, SOL_SOCKET, SO_RCVBUF, [12000], 4) = 0
+   +0 < P. 20001:80001(60000) ack 1 win 257
+   +0 > .  1:1(0) ack 20001 win 18000
+
+   +0 read(4, ..., 20000) = 20000
+// A too big packet is accepted if the receive queue is empty
+   +0 < P. 20001:80001(60000) ack 1 win 257
+   +0 > .  1:1(0) ack 80001 win 0
+