tcp: add datapath logic for PSP with inline key exchange

Add validation points and state propagation to support PSP key
exchange inline, on TCP connections. The expectation is that
application will use some well established mechanism like TLS
handshake to establish a secure channel over the connection and
if both endpoints are PSP-capable - exchange and install PSP keys.
Because the connection can existing in PSP-unsecured and PSP-secured
state we need to make sure that there are no race conditions or
retransmission leaks.

On Tx - mark packets with the skb->decrypted bit when PSP key
is at the enqueue time. Drivers should only encrypt packets with
this bit set. This prevents retransmissions getting encrypted when
original transmission was not. Similarly to TLS, we'll use
sk->sk_validate_xmit_skb to make sure PSP skbs can't "escape"
via a PSP-unaware device without being encrypted.

On Rx - validation is done under socket lock. This moves the validation
point later than xfrm, for example. Please see the documentation patch
for more details on the flow of securing a connection, but for
the purpose of this patch what's important is that we want to
enforce the invariant that once connection is secured any skb
in the receive queue has been encrypted with PSP.

Add GRO and coalescing checks to prevent PSP authenticated data from
being combined with cleartext data, or data with non-matching PSP
state. On Rx, check skb's with psp_skb_coalesce_diff() at points
before psp_sk_rx_policy_check(). After skb's are policy checked and on
the socket receive queue, skb_cmp_decrypted() is sufficient for
checking for coalescable PSP state. On Tx, tcp_write_collapse_fence()
should be called when transitioning a socket into PSP Tx state to
prevent data sent as cleartext from being coalesced with PSP
encapsulated data.

This change only adds the validation points, for ease of review.
Subsequent change will add the ability to install keys, and flesh
the enforcement logic out

Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Co-developed-by: Daniel Zahka <daniel.zahka@gmail.com>
Signed-off-by: Daniel Zahka <daniel.zahka@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250917000954.859376-5-daniel.zahka@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

1 files changed, 11 insertions, 6 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 388c45859469..223d7feeb19d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -41,6 +41,7 @@
 #include <net/tcp_ecn.h>
 #include <net/mptcp.h>
 #include <net/proto_memory.h>
+#include <net/psp.h>
 
 #include <linux/compiler.h>
 #include <linux/gfp.h>
@@ -358,13 +359,15 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb,
 /* Constructs common control bits of non-data skb. If SYN/FIN is present,
  * auto increment end seqno.
  */
-static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u16 flags)
+static void tcp_init_nondata_skb(struct sk_buff *skb, struct sock *sk,
+				 u32 seq, u16 flags)
 {
 	skb->ip_summed = CHECKSUM_PARTIAL;
 
 	TCP_SKB_CB(skb)->tcp_flags = flags;
 
 	tcp_skb_pcount_set(skb, 1);
+	psp_enqueue_set_decrypted(sk, skb);
 
 	TCP_SKB_CB(skb)->seq = seq;
 	if (flags & (TCPHDR_SYN | TCPHDR_FIN))
@@ -1656,6 +1659,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 	/* Advance write_seq and place onto the write_queue. */
 	WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq);
 	__skb_header_release(skb);
+	psp_enqueue_set_decrypted(sk, skb);
 	tcp_add_write_queue_tail(sk, skb);
 	sk_wmem_queued_add(sk, skb->truesize);
 	sk_mem_charge(sk, skb->truesize);
@@ -3778,7 +3782,7 @@ void tcp_send_fin(struct sock *sk)
 		skb_reserve(skb, MAX_TCP_HEADER);
 		sk_forced_mem_schedule(sk, skb->truesize);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
-		tcp_init_nondata_skb(skb, tp->write_seq,
+		tcp_init_nondata_skb(skb, sk, tp->write_seq,
 				     TCPHDR_ACK | TCPHDR_FIN);
 		tcp_queue_skb(sk, skb);
 	}
@@ -3806,7 +3810,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority,
 
 	/* Reserve space for headers and prepare control bits. */
 	skb_reserve(skb, MAX_TCP_HEADER);
-	tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk),
+	tcp_init_nondata_skb(skb, sk, tcp_acceptable_seq(sk),
 			     TCPHDR_ACK | TCPHDR_RST);
 	tcp_mstamp_refresh(tcp_sk(sk));
 	/* Send it off. */
@@ -4303,7 +4307,7 @@ int tcp_connect(struct sock *sk)
 	/* SYN eats a sequence byte, write_seq updated by
 	 * tcp_connect_queue_skb().
 	 */
-	tcp_init_nondata_skb(buff, tp->write_seq, TCPHDR_SYN);
+	tcp_init_nondata_skb(buff, sk, tp->write_seq, TCPHDR_SYN);
 	tcp_mstamp_refresh(tp);
 	tp->retrans_stamp = tcp_time_stamp_ts(tp);
 	tcp_connect_queue_skb(sk, buff);
@@ -4428,7 +4432,8 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt, u16 flags)
 
 	/* Reserve space for headers and prepare control bits. */
 	skb_reserve(buff, MAX_TCP_HEADER);
-	tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK | flags);
+	tcp_init_nondata_skb(buff, sk,
+			     tcp_acceptable_seq(sk), TCPHDR_ACK | flags);
 
 	/* We do not want pure acks influencing TCP Small Queues or fq/pacing
 	 * too much.
@@ -4474,7 +4479,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib)
 	 * end to send an ack.  Don't queue or clone SKB, just
 	 * send it.
 	 */
-	tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK);
+	tcp_init_nondata_skb(skb, sk, tp->snd_una - !urgent, TCPHDR_ACK);
 	NET_INC_STATS(sock_net(sk), mib);
 	return tcp_transmit_skb(sk, skb, 0, (__force gfp_t)0);
 }