1 files changed, 190 insertions, 22 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 85ff417bda7f..bf48cd73e967 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -438,6 +438,7 @@ struct tcp_out_options {
 	u8 ws;			/* window scale, 0 to disable */
 	u8 num_sack_blocks;	/* number of SACK blocks to include */
 	u8 hash_size;		/* bytes in hash_location */
+	u8 bpf_opt_len;		/* length of BPF hdr option */
 	__u8 *hash_location;	/* temporary pointer, overloaded */
 	__u32 tsval, tsecr;	/* need to include OPTION_TS */
 	struct tcp_fastopen_cookie *fastopen_cookie;	/* Fast open cookie */
@@ -452,6 +453,145 @@ static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts)
 #endif
 }
 
+#ifdef CONFIG_CGROUP_BPF
+static int bpf_skops_write_hdr_opt_arg0(struct sk_buff *skb,
+					enum tcp_synack_type synack_type)
+{
+	if (unlikely(!skb))
+		return BPF_WRITE_HDR_TCP_CURRENT_MSS;
+
+	if (unlikely(synack_type == TCP_SYNACK_COOKIE))
+		return BPF_WRITE_HDR_TCP_SYNACK_COOKIE;
+
+	return 0;
+}
+
+/* req, syn_skb and synack_type are used when writing synack */
+static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb,
+				  struct request_sock *req,
+				  struct sk_buff *syn_skb,
+				  enum tcp_synack_type synack_type,
+				  struct tcp_out_options *opts,
+				  unsigned int *remaining)
+{
+	struct bpf_sock_ops_kern sock_ops;
+	int err;
+
+	if (likely(!BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk),
+					   BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG)) ||
+	    !*remaining)
+		return;
+
+	/* *remaining has already been aligned to 4 bytes, so *remaining >= 4 */
+
+	/* init sock_ops */
+	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+
+	sock_ops.op = BPF_SOCK_OPS_HDR_OPT_LEN_CB;
+
+	if (req) {
+		/* The listen "sk" cannot be passed here because
+		 * it is not locked.  It would not make too much
+		 * sense to do bpf_setsockopt(listen_sk) based
+		 * on individual connection request also.
+		 *
+		 * Thus, "req" is passed here and the cgroup-bpf-progs
+		 * of the listen "sk" will be run.
+		 *
+		 * "req" is also used here for fastopen even the "sk" here is
+		 * a fullsock "child" sk.  It is to keep the behavior
+		 * consistent between fastopen and non-fastopen on
+		 * the bpf programming side.
+		 */
+		sock_ops.sk = (struct sock *)req;
+		sock_ops.syn_skb = syn_skb;
+	} else {
+		sock_owned_by_me(sk);
+
+		sock_ops.is_fullsock = 1;
+		sock_ops.sk = sk;
+	}
+
+	sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type);
+	sock_ops.remaining_opt_len = *remaining;
+	/* tcp_current_mss() does not pass a skb */
+	if (skb)
+		bpf_skops_init_skb(&sock_ops, skb, 0);
+
+	err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk);
+
+	if (err || sock_ops.remaining_opt_len == *remaining)
+		return;
+
+	opts->bpf_opt_len = *remaining - sock_ops.remaining_opt_len;
+	/* round up to 4 bytes */
+	opts->bpf_opt_len = (opts->bpf_opt_len + 3) & ~3;
+
+	*remaining -= opts->bpf_opt_len;
+}
+
+static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
+				    struct request_sock *req,
+				    struct sk_buff *syn_skb,
+				    enum tcp_synack_type synack_type,
+				    struct tcp_out_options *opts)
+{
+	u8 first_opt_off, nr_written, max_opt_len = opts->bpf_opt_len;
+	struct bpf_sock_ops_kern sock_ops;
+	int err;
+
+	if (likely(!max_opt_len))
+		return;
+
+	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+
+	sock_ops.op = BPF_SOCK_OPS_WRITE_HDR_OPT_CB;
+
+	if (req) {
+		sock_ops.sk = (struct sock *)req;
+		sock_ops.syn_skb = syn_skb;
+	} else {
+		sock_owned_by_me(sk);
+
+		sock_ops.is_fullsock = 1;
+		sock_ops.sk = sk;
+	}
+
+	sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type);
+	sock_ops.remaining_opt_len = max_opt_len;
+	first_opt_off = tcp_hdrlen(skb) - max_opt_len;
+	bpf_skops_init_skb(&sock_ops, skb, first_opt_off);
+
+	err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk);
+
+	if (err)
+		nr_written = 0;
+	else
+		nr_written = max_opt_len - sock_ops.remaining_opt_len;
+
+	if (nr_written < max_opt_len)
+		memset(skb->data + first_opt_off + nr_written, TCPOPT_NOP,
+		       max_opt_len - nr_written);
+}
+#else
+static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb,
+				  struct request_sock *req,
+				  struct sk_buff *syn_skb,
+				  enum tcp_synack_type synack_type,
+				  struct tcp_out_options *opts,
+				  unsigned int *remaining)
+{
+}
+
+static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
+				    struct request_sock *req,
+				    struct sk_buff *syn_skb,
+				    enum tcp_synack_type synack_type,
+				    struct tcp_out_options *opts)
+{
+}
+#endif
+
 /* Write previously computed TCP options to the packet.
  *
  * Beware: Something in the Internet is very sensitive to the ordering of
@@ -691,6 +831,8 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 		}
 	}
 
+	bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining);
+
 	return MAX_TCP_OPTION_SPACE - remaining;
 }
 
@@ -701,7 +843,8 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 				       struct tcp_out_options *opts,
 				       const struct tcp_md5sig_key *md5,
 				       struct tcp_fastopen_cookie *foc,
-				       enum tcp_synack_type synack_type)
+				       enum tcp_synack_type synack_type,
+				       struct sk_buff *syn_skb)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
@@ -758,6 +901,9 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 
 	smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining);
 
+	bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb,
+			      synack_type, opts, &remaining);
+
 	return MAX_TCP_OPTION_SPACE - remaining;
 }
 
@@ -826,6 +972,15 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 			opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
 	}
 
+	if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp,
+					    BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG))) {
+		unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
+
+		bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining);
+
+		size = MAX_TCP_OPTION_SPACE - remaining;
+	}
+
 	return size;
 }
 
@@ -1213,6 +1368,9 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	}
 #endif
 
+	/* BPF prog is the last one writing header option */
+	bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts);
+
 	INDIRECT_CALL_INET(icsk->icsk_af_ops->send_check,
 			   tcp_v6_send_check, tcp_v4_send_check,
 			   sk, skb);
@@ -1524,7 +1682,6 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 		skb->truesize	   -= delta_truesize;
 		sk_wmem_queued_add(sk, -delta_truesize);
 		sk_mem_uncharge(sk, delta_truesize);
-		sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
 	}
 
 	/* Any change of skb->len requires recalculation of tso factor. */
@@ -3336,20 +3493,20 @@ int tcp_send_synack(struct sock *sk)
 }
 
 /**
- * tcp_make_synack - Prepare a SYN-ACK.
- * sk: listener socket
- * dst: dst entry attached to the SYNACK
- * req: request_sock pointer
- * foc: cookie for tcp fast open
- * synack_type: Type of synback to prepare
- *
- * Allocate one skb and build a SYNACK packet.
- * @dst is consumed : Caller should not use it again.
+ * tcp_make_synack - Allocate one skb and build a SYNACK packet.
+ * @sk: listener socket
+ * @dst: dst entry attached to the SYNACK. It is consumed and caller
+ *       should not use it again.
+ * @req: request_sock pointer
+ * @foc: cookie for tcp fast open
+ * @synack_type: Type of synack to prepare
+ * @syn_skb: SYN packet just received.  It could be NULL for rtx case.
  */
 struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 				struct request_sock *req,
 				struct tcp_fastopen_cookie *foc,
-				enum tcp_synack_type synack_type)
+				enum tcp_synack_type synack_type,
+				struct sk_buff *syn_skb)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -3408,8 +3565,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
 #endif
 	skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
+	/* bpf program will be interested in the tcp_flags */
+	TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK;
 	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
-					     foc, synack_type) + sizeof(*th);
+					     foc, synack_type,
+					     syn_skb) + sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
@@ -3441,6 +3601,9 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	rcu_read_unlock();
 #endif
 
+	bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb,
+				synack_type, &opts);
+
 	skb->skb_mstamp_ns = now;
 	tcp_add_tx_delay(skb, tp);
 
@@ -3741,16 +3904,15 @@ void tcp_send_delayed_ack(struct sock *sk)
 		ato = min(ato, max_ato);
 	}
 
+	ato = min_t(u32, ato, inet_csk(sk)->icsk_delack_max);
+
 	/* Stay within the limit we were given */
 	timeout = jiffies + ato;
 
 	/* Use new timeout only if there wasn't a older one earlier. */
 	if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) {
-		/* If delack timer was blocked or is about to expire,
-		 * send ACK now.
-		 */
-		if (icsk->icsk_ack.blocked ||
-		    time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) {
+		/* If delack timer is about to expire, send ACK now. */
+		if (time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) {
 			tcp_send_ack(sk);
 			return;
 		}
@@ -3779,10 +3941,15 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 	buff = alloc_skb(MAX_TCP_HEADER,
 			 sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN));
 	if (unlikely(!buff)) {
+		struct inet_connection_sock *icsk = inet_csk(sk);
+		unsigned long delay;
+
+		delay = TCP_DELACK_MAX << icsk->icsk_ack.retry;
+		if (delay < TCP_RTO_MAX)
+			icsk->icsk_ack.retry++;
 		inet_csk_schedule_ack(sk);
-		inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
-					  TCP_DELACK_MAX, TCP_RTO_MAX);
+		icsk->icsk_ack.ato = TCP_ATO_MIN;
+		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, TCP_RTO_MAX);
 		return;
 	}
 
@@ -3934,7 +4101,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
 	int res;
 
 	tcp_rsk(req)->txhash = net_tx_rndhash();
-	res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL);
+	res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL,
+				  NULL);
 	if (!res) {
 		__TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);