Merge branch 'tcp-accecn'

Chia-Yu Chang says:

====================
AccECN protocol preparation patch series

Please find the v7

v7 (03-Mar-2025)
- Move 2 new patches added in v6 to the next AccECN patch series

v6 (27-Dec-2024)
- Avoid removing removing the potential CA_ACK_WIN_UPDATE in ack_ev_flags of patch #1 (Eric Dumazet <edumazet@google.com>)
- Add reviewed-by tag in patches #2, #3, #4, #5, #6, #7, #8, #12, #14
- Foloiwng 2 new pathces are added after patch #9 (Patch that adds SKB_GSO_TCP_ACCECN)
  * New patch #10 to replace exisiting SKB_GSO_TCP_ECN with SKB_GSO_TCP_ACCECN in the driver to avoid CWR flag corruption
  * New patch #11 adds AccECN for virtio by adding new negotiation flag (VIRTIO_NET_F_HOST/GUEST_ACCECN) in feature handshake and translating Accurate ECN GSO flag between virtio_net_hdr (VIRTIO_NET_HDR_GSO_ACCECN) and skb header (SKB_GSO_TCP_ACCECN)
- Add detailed changelog and comments in #13 (Eric Dumazet <edumazet@google.com>)
- Move patch #14 to the next AccECN patch series (Eric Dumazet <edumazet@google.com>)

v5 (5-Nov-2024)
- Add helper function "tcp_flags_ntohs" to preserve last 2 bytes of TCP flags of patch #4 (Paolo Abeni <pabeni@redhat.com>)
- Fix reverse X-max tree order of patches #4, #11 (Paolo Abeni <pabeni@redhat.com>)
- Rename variable "delta" as "timestamp_delta" of patch #2 fo clariety
- Remove patch #14 in this series (Paolo Abeni <pabeni@redhat.com>, Joel Granados <joel.granados@kernel.org>)

v4 (21-Oct-2024)
- Fix line length warning of patches #2, #4, #8, #10, #11, #14
- Fix spaces preferred around '|' (ctx:VxV) warning of patch #7
- Add missing CC'ed of patches #4, #12, #14

v3 (19-Oct-2024)
- Fix build error in v2

v2 (18-Oct-2024)
- Fix warning caused by NETIF_F_GSO_ACCECN_BIT in patch #9 (Jakub Kicinski <kuba@kernel.org>)

The full patch series can be found in
https://github.com/L4STeam/linux-net-next/commits/upstream_l4steam/

The Accurate ECN draft can be found in
https://datatracker.ietf.org/doc/html/draft-ietf-tcpm-accurate-ecn-28
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netdev_features.h

@@ -53,12 +53,12 @@ enum {
 	NETIF_F_GSO_UDP_BIT,		/* ... UFO, deprecated except tuntap */
 	NETIF_F_GSO_UDP_L4_BIT,		/* ... UDP payload GSO (not UFO) */
 	NETIF_F_GSO_FRAGLIST_BIT,		/* ... Fraglist GSO */
+	NETIF_F_GSO_ACCECN_BIT,		/* TCP AccECN w/ TSO (no clear CWR) */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
-		NETIF_F_GSO_FRAGLIST_BIT,
+		NETIF_F_GSO_ACCECN_BIT,
 
 	NETIF_F_FCOE_CRC_BIT,		/* FCoE CRC32 */
 	NETIF_F_SCTP_CRC_BIT,		/* SCTP checksum offload */
-	__UNUSED_NETIF_F_37,
 	NETIF_F_NTUPLE_BIT,		/* N-tuple filters supported */
 	NETIF_F_RXHASH_BIT,		/* Receive hashing offload */
 	NETIF_F_RXCSUM_BIT,		/* Receive checksumming offload */
@@ -128,6 +128,7 @@ enum {
 #define NETIF_F_SG		__NETIF_F(SG)
 #define NETIF_F_TSO6		__NETIF_F(TSO6)
 #define NETIF_F_TSO_ECN		__NETIF_F(TSO_ECN)
+#define NETIF_F_GSO_ACCECN	__NETIF_F(GSO_ACCECN)
 #define NETIF_F_TSO		__NETIF_F(TSO)
 #define NETIF_F_VLAN_CHALLENGED	__NETIF_F(VLAN_CHALLENGED)
 #define NETIF_F_RXFCS		__NETIF_F(RXFCS)
@@ -210,7 +211,8 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start)
 				 NETIF_F_TSO_ECN | NETIF_F_TSO_MANGLEID)
 
 /* List of features with software fallbacks. */
-#define NETIF_F_GSO_SOFTWARE	(NETIF_F_ALL_TSO | NETIF_F_GSO_SCTP |	     \
+#define NETIF_F_GSO_SOFTWARE	(NETIF_F_ALL_TSO | \
+				 NETIF_F_GSO_ACCECN | NETIF_F_GSO_SCTP | \
 				 NETIF_F_GSO_UDP_L4 | NETIF_F_GSO_FRAGLIST)
 
 /*

include/linux/netdevice.h

@@ -5269,6 +5269,8 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_FRAGLIST != (NETIF_F_GSO_FRAGLIST >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_TCP_ACCECN !=
+		     (NETIF_F_GSO_ACCECN >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
 }

include/linux/skbuff.h

@@ -708,6 +708,8 @@ enum {
 	SKB_GSO_UDP_L4 = 1 << 17,
 
 	SKB_GSO_FRAGLIST = 1 << 18,
+
+	SKB_GSO_TCP_ACCECN = 1 << 19,
 };
 
 #if BITS_PER_LONG > 32

include/net/tcp.h

@@ -26,6 +26,7 @@
 #include <linux/kref.h>
 #include <linux/ktime.h>
 #include <linux/indirect_call_wrapper.h>
+#include <linux/bits.h>
 
 #include <net/inet_connection_sock.h>
 #include <net/inet_timewait_sock.h>
@@ -373,16 +374,53 @@ static inline void tcp_dec_quickack_mode(struct sock *sk)
 	}
 }
 
-#define	TCP_ECN_OK		1
-#define	TCP_ECN_QUEUE_CWR	2
-#define	TCP_ECN_DEMAND_CWR	4
-#define	TCP_ECN_SEEN		8
+#define	TCP_ECN_MODE_RFC3168	BIT(0)
+#define	TCP_ECN_QUEUE_CWR	BIT(1)
+#define	TCP_ECN_DEMAND_CWR	BIT(2)
+#define	TCP_ECN_SEEN		BIT(3)
+#define	TCP_ECN_MODE_ACCECN	BIT(4)
+
+#define	TCP_ECN_DISABLED	0
+#define	TCP_ECN_MODE_PENDING	(TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN)
+#define	TCP_ECN_MODE_ANY	(TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN)
+
+static inline bool tcp_ecn_mode_any(const struct tcp_sock *tp)
+{
+	return tp->ecn_flags & TCP_ECN_MODE_ANY;
+}
+
+static inline bool tcp_ecn_mode_rfc3168(const struct tcp_sock *tp)
+{
+	return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_RFC3168;
+}
+
+static inline bool tcp_ecn_mode_accecn(const struct tcp_sock *tp)
+{
+	return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_ACCECN;
+}
+
+static inline bool tcp_ecn_disabled(const struct tcp_sock *tp)
+{
+	return !tcp_ecn_mode_any(tp);
+}
+
+static inline bool tcp_ecn_mode_pending(const struct tcp_sock *tp)
+{
+	return (tp->ecn_flags & TCP_ECN_MODE_PENDING) == TCP_ECN_MODE_PENDING;
+}
+
+static inline void tcp_ecn_mode_set(struct tcp_sock *tp, u8 mode)
+{
+	tp->ecn_flags &= ~TCP_ECN_MODE_ANY;
+	tp->ecn_flags |= mode;
+}
 
 enum tcp_tw_status {
 	TCP_TW_SUCCESS = 0,
 	TCP_TW_RST = 1,
 	TCP_TW_ACK = 2,
-	TCP_TW_SYN = 3
+	TCP_TW_SYN = 3,
+	TCP_TW_ACK_OOW = 4
 };
 
 
@@ -669,7 +707,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority,
 			   enum sk_rst_reason reason);
 int tcp_send_synack(struct sock *);
 void tcp_push_one(struct sock *, unsigned int mss_now);
-void __tcp_send_ack(struct sock *sk, u32 rcv_nxt);
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt, u16 flags);
 void tcp_send_ack(struct sock *sk);
 void tcp_send_delayed_ack(struct sock *sk);
 void tcp_send_loss_probe(struct sock *sk);
@@ -934,15 +972,22 @@ static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq)
 
 #define tcp_flag_byte(th) (((u_int8_t *)th)[13])
 
-#define TCPHDR_FIN 0x01
-#define TCPHDR_SYN 0x02
-#define TCPHDR_RST 0x04
-#define TCPHDR_PSH 0x08
-#define TCPHDR_ACK 0x10
-#define TCPHDR_URG 0x20
-#define TCPHDR_ECE 0x40
-#define TCPHDR_CWR 0x80
-
+#define TCPHDR_FIN	BIT(0)
+#define TCPHDR_SYN	BIT(1)
+#define TCPHDR_RST	BIT(2)
+#define TCPHDR_PSH	BIT(3)
+#define TCPHDR_ACK	BIT(4)
+#define TCPHDR_URG	BIT(5)
+#define TCPHDR_ECE	BIT(6)
+#define TCPHDR_CWR	BIT(7)
+#define TCPHDR_AE	BIT(8)
+#define TCPHDR_FLAGS_MASK (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST | \
+			   TCPHDR_PSH | TCPHDR_ACK | TCPHDR_URG | \
+			   TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE)
+#define tcp_flags_ntohs(th) (ntohs(*(__be16 *)&tcp_flag_word(th)) & \
+			    TCPHDR_FLAGS_MASK)
+
+#define TCPHDR_ACE (TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE)
 #define TCPHDR_SYN_ECN	(TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR)
 
 /* State flags for sacked in struct tcp_skb_cb */
@@ -977,7 +1022,7 @@ struct tcp_skb_cb {
 			u16	tcp_gso_size;
 		};
 	};
-	__u8		tcp_flags;	/* TCP header flags. (tcp[13])	*/
+	__u16		tcp_flags;	/* TCP header flags (tcp[12-13])*/
 
 	__u8		sacked;		/* State flags for SACK.	*/
 	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
@@ -1132,9 +1177,9 @@ enum tcp_ca_ack_event_flags {
 #define TCP_CA_UNSPEC	0
 
 /* Algorithm can be set on socket without CAP_NET_ADMIN privileges */
-#define TCP_CONG_NON_RESTRICTED 0x1
+#define TCP_CONG_NON_RESTRICTED		BIT(0)
 /* Requires ECN/ECT set on all packets */
-#define TCP_CONG_NEEDS_ECN	0x2
+#define TCP_CONG_NEEDS_ECN		BIT(1)
 #define TCP_CONG_MASK	(TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN)
 
 union tcp_cc_info;

include/uapi/linux/tcp.h

@@ -28,7 +28,8 @@ struct tcphdr {
 	__be32	seq;
 	__be32	ack_seq;
 #if defined(__LITTLE_ENDIAN_BITFIELD)
-	__u16	res1:4,
+	__u16	ae:1,
+		res1:3,
 		doff:4,
 		fin:1,
 		syn:1,
@@ -40,7 +41,8 @@ struct tcphdr {
 		cwr:1;
 #elif defined(__BIG_ENDIAN_BITFIELD)
 	__u16	doff:4,
-		res1:4,
+		res1:3,
+		ae:1,
 		cwr:1,
 		ece:1,
 		urg:1,
@@ -70,6 +72,7 @@ union tcp_word_hdr {
 #define tcp_flag_word(tp) (((union tcp_word_hdr *)(tp))->words[3])
 
 enum {
+	TCP_FLAG_AE  = __constant_cpu_to_be32(0x01000000),
 	TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000),
 	TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000),
 	TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000),
@@ -78,7 +81,7 @@ enum {
 	TCP_FLAG_RST = __constant_cpu_to_be32(0x00040000),
 	TCP_FLAG_SYN = __constant_cpu_to_be32(0x00020000),
 	TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000),
-	TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000),
+	TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0E000000),
 	TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000)
 };
 

net/ethtool/common.c

@@ -36,6 +36,7 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = {
 	[NETIF_F_TSO_BIT] =              "tx-tcp-segmentation",
 	[NETIF_F_GSO_ROBUST_BIT] =       "tx-gso-robust",
 	[NETIF_F_TSO_ECN_BIT] =          "tx-tcp-ecn-segmentation",
+	[NETIF_F_GSO_ACCECN_BIT] =	 "tx-tcp-accecn-segmentation",
 	[NETIF_F_TSO_MANGLEID_BIT] =	 "tx-tcp-mangleid-segmentation",
 	[NETIF_F_TSO6_BIT] =             "tx-tcp6-segmentation",
 	[NETIF_F_FSO_BIT] =              "tx-fcoe-segmentation",

net/ipv4/bpf_tcp_ca.c

@@ -121,7 +121,7 @@ static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
 BPF_CALL_2(bpf_tcp_send_ack, struct tcp_sock *, tp, u32, rcv_nxt)
 {
 	/* bpf_tcp_ca prog cannot have NULL tp */
-	__tcp_send_ack((struct sock *)tp, rcv_nxt);
+	__tcp_send_ack((struct sock *)tp, rcv_nxt, 0);
 	return 0;
 }
 

net/ipv4/ip_output.c

@@ -75,7 +75,6 @@
 #include <net/checksum.h>
 #include <net/gso.h>
 #include <net/inetpeer.h>
-#include <net/inet_ecn.h>
 #include <net/lwtunnel.h>
 #include <net/inet_dscp.h>
 #include <linux/bpf-cgroup.h>
@@ -1640,7 +1639,7 @@ void ip_send_unicast_reply(struct sock *sk, const struct sock *orig_sk,
 	if (IS_ERR(rt))
 		return;
 
-	inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK;
+	inet_sk(sk)->tos = arg->tos;
 
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;

net/ipv4/tcp.c

@@ -4138,7 +4138,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 		info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale;
 	}
 
-	if (tp->ecn_flags & TCP_ECN_OK)
+	if (tcp_ecn_mode_any(tp))
 		info->tcpi_options |= TCPI_OPT_ECN;
 	if (tp->ecn_flags & TCP_ECN_SEEN)
 		info->tcpi_options |= TCPI_OPT_ECN_SEEN;

net/ipv4/tcp_dctcp.c

@@ -90,7 +90,7 @@ __bpf_kfunc static void dctcp_init(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 
-	if ((tp->ecn_flags & TCP_ECN_OK) ||
+	if (tcp_ecn_mode_any(tp) ||
 	    (sk->sk_state == TCP_LISTEN ||
 	     sk->sk_state == TCP_CLOSE)) {
 		struct dctcp *ca = inet_csk_ca(sk);

net/ipv4/tcp_dctcp.h

@@ -28,7 +28,7 @@ static inline void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt,
 		 */
 		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
 			dctcp_ece_ack_cwr(sk, *ce_state);
-			__tcp_send_ack(sk, *prior_rcv_nxt);
+			__tcp_send_ack(sk, *prior_rcv_nxt, 0);
 		}
 		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 	}