Merge branch 'bpf-Add-support-for-sock_ops'

Lawrence Brakmo says:

====================
bpf: Add support for sock_ops

Created a new BPF program type, BPF_PROG_TYPE_SOCK_OPS, and a corresponding
struct that allows BPF programs of this type to access some of the
socket's fields (such as IP addresses, ports, etc.) and setting
connection parameters such as buffer sizes, initial window, SYN/SYN-ACK
RTOs, etc.

Unlike current BPF program types that expect to be called at a particular
place in the network stack code, SOCK_OPS program can be called at
different places and use an "op" field to indicate the context. There
are currently two types of operations, those whose effect is through
their return value and those whose effect is through the new
bpf_setsocketop BPF helper function.

Example operands of the first type are:
  BPF_SOCK_OPS_TIMEOUT_INIT
  BPF_SOCK_OPS_RWND_INIT
  BPF_SOCK_OPS_NEEDS_ECN

Example operands of the secont type are:
  BPF_SOCK_OPS_TCP_CONNECT_CB
  BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB
  BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB

Current operands are only called during connection establishment so
there should not be any BPF overheads after connection establishment. The
main idea is to use connection information form both hosts, such as IP
addresses and ports to allow setting of per connection parameters to
optimize the connection's peformance.

Alghough there are already 3 mechanisms to set parameters (sysctls,
route metrics and setsockopts), this new mechanism provides some
disticnt advantages. Unlike sysctls, it can set parameters per
connection. In contrast to route metrics, it can also use port numbers
and information provided by a user level program. In addition, it could
set parameters probabilistically for evaluation purposes (i.e. do
something different on 10% of the flows and compare results with the
other 90% of the flows). Also, in cases where IPv6 addresses contain
geographic information, the rules to make changes based on the distance
(or RTT) between the hosts are much easier than route metric rules and
can be global. Finally, unlike setsockopt, it does not require
application changes and it can be updated easily at any time.

It uses the existing bpf cgroups infrastructure so the programs can be
attached per cgroup with full inheritance support. Although the bpf cgroup
framework already contains a sock related program type (BPF_PROG_TYPE_CGROUP_SOCK),
I created the new type (BPF_PROG_TYPE_SOCK_OPS) beccause the existing type
expects to be called only once during the connections's lifetime. In contrast,
the new program type will be called multiple times from different places in the
network stack code.  For example, before sending SYN and SYN-ACKs to set
an appropriate timeout, when the connection is established to set congestion
control, etc. As a result it has "op" field to specify the type of operation
requested.

This patch set also includes sample BPF programs to demostrate the differnet
features.

v2: Formatting changes, rebased to latest net-next

v3: Fixed build issues, changed socket_ops to sock_ops throught,
    fixed formatting issues, removed the syscall to load sock_ops
    program and added functionality to use existing bpf attach and
    bpf detach system calls, removed reader/writer locks in
    sock_bpfops.c (used when saving sock_ops global program)
    and fixed missing module refcount increment.

v4: Removed global sock_ops program and instead used existing cgroup bpf
    infrastructure to support a new BPF_CGROUP_ATTCH type.

v5: fixed kbuild warning happening in bpf-cgroup.h
    removed automatic converstion to host byte order from some sock_ops
      fields (ipv4 and ipv6 addresses, remote port)
    Added conversion to host byte order in some of the sample programs
    Added to sample BPF program comments about using load_sock_ops to load
    Removed is_req_sock field from bpf_sock_ops_kern and related places,
      using sk_fullsock() instead.

v6: fixes to BPF helper function setsockopt (possible NULL deferencing, etc.)
====================

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

include/linux/bpf-cgroup.h

@@ -7,6 +7,7 @@
 struct sock;
 struct cgroup;
 struct sk_buff;
+struct bpf_sock_ops_kern;
 
 #ifdef CONFIG_CGROUP_BPF
 
@@ -42,6 +43,10 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 int __cgroup_bpf_run_filter_sk(struct sock *sk,
 			       enum bpf_attach_type type);
 
+int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
+				     struct bpf_sock_ops_kern *sock_ops,
+				     enum bpf_attach_type type);
+
 /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb)			      \
 ({									      \
@@ -75,6 +80,18 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk,
 	__ret;								       \
 })
 
+#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops)				       \
+({									       \
+	int __ret = 0;							       \
+	if (cgroup_bpf_enabled && (sock_ops)->sk) {	       \
+		typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk);	       \
+		if (sk_fullsock(__sk))					       \
+			__ret = __cgroup_bpf_run_filter_sock_ops(__sk,	       \
+								 sock_ops,     \
+							 BPF_CGROUP_SOCK_OPS); \
+	}								       \
+	__ret;								       \
+})
 #else
 
 struct cgroup_bpf {};
@@ -85,6 +102,7 @@ static inline void cgroup_bpf_inherit(struct cgroup *cgrp,
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 
 #endif /* CONFIG_CGROUP_BPF */
 

include/linux/bpf_types.h

@@ -10,6 +10,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock_prog_ops)
 BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout_prog_ops)
 BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout_prog_ops)
 BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops_prog_ops)
 #endif
 #ifdef CONFIG_BPF_EVENTS
 BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops)

include/linux/filter.h

@@ -898,4 +898,13 @@ static inline int bpf_tell_extensions(void)
 	return SKF_AD_MAX;
 }
 
+struct bpf_sock_ops_kern {
+	struct	sock *sk;
+	u32	op;
+	union {
+		u32 reply;
+		u32 replylong[4];
+	};
+};
+
 #endif /* __LINUX_FILTER_H__ */

include/net/tcp.h

@@ -46,6 +46,10 @@
 #include <linux/seq_file.h>
 #include <linux/memcontrol.h>
 
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/bpf-cgroup.h>
+
 extern struct inet_hashinfo tcp_hashinfo;
 
 extern struct percpu_counter tcp_orphan_count;
@@ -1000,7 +1004,9 @@ void tcp_get_default_congestion_control(char *name);
 void tcp_get_available_congestion_control(char *buf, size_t len);
 void tcp_get_allowed_congestion_control(char *buf, size_t len);
 int tcp_set_allowed_congestion_control(char *allowed);
-int tcp_set_congestion_control(struct sock *sk, const char *name);
+int tcp_set_congestion_control(struct sock *sk, const char *name, bool load);
+void tcp_reinit_congestion_control(struct sock *sk,
+				   const struct tcp_congestion_ops *ca);
 u32 tcp_slow_start(struct tcp_sock *tp, u32 acked);
 void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked);
 
@@ -2021,4 +2027,62 @@ int tcp_set_ulp(struct sock *sk, const char *name);
 void tcp_get_available_ulp(char *buf, size_t len);
 void tcp_cleanup_ulp(struct sock *sk);
 
+/* Call BPF_SOCK_OPS program that returns an int. If the return value
+ * is < 0, then the BPF op failed (for example if the loaded BPF
+ * program does not support the chosen operation or there is no BPF
+ * program loaded).
+ */
+#ifdef CONFIG_BPF
+static inline int tcp_call_bpf(struct sock *sk, int op)
+{
+	struct bpf_sock_ops_kern sock_ops;
+	int ret;
+
+	if (sk_fullsock(sk))
+		sock_owned_by_me(sk);
+
+	memset(&sock_ops, 0, sizeof(sock_ops));
+	sock_ops.sk = sk;
+	sock_ops.op = op;
+
+	ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
+	if (ret == 0)
+		ret = sock_ops.reply;
+	else
+		ret = -1;
+	return ret;
+}
+#else
+static inline int tcp_call_bpf(struct sock *sk, int op)
+{
+	return -EPERM;
+}
+#endif
+
+static inline u32 tcp_timeout_init(struct sock *sk)
+{
+	int timeout;
+
+	timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT);
+
+	if (timeout <= 0)
+		timeout = TCP_TIMEOUT_INIT;
+	return timeout;
+}
+
+static inline u32 tcp_rwnd_init_bpf(struct sock *sk)
+{
+	int rwnd;
+
+	rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT);
+
+	if (rwnd < 0)
+		rwnd = 0;
+	return rwnd;
+}
+
+static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk)
+{
+	return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN) == 1);
+}
 #endif	/* _TCP_H */

include/uapi/linux/bpf.h

@@ -120,12 +120,14 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_LWT_IN,
 	BPF_PROG_TYPE_LWT_OUT,
 	BPF_PROG_TYPE_LWT_XMIT,
+	BPF_PROG_TYPE_SOCK_OPS,
 };
 
 enum bpf_attach_type {
 	BPF_CGROUP_INET_INGRESS,
 	BPF_CGROUP_INET_EGRESS,
 	BPF_CGROUP_INET_SOCK_CREATE,
+	BPF_CGROUP_SOCK_OPS,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -518,6 +520,17 @@ union bpf_attr {
  *     Set full skb->hash.
  *     @skb: pointer to skb
  *     @hash: hash to set
+ *
+ * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
+ *     Calls setsockopt. Not all opts are available, only those with
+ *     integer optvals plus TCP_CONGESTION.
+ *     Supported levels: SOL_SOCKET and IPROTO_TCP
+ *     @bpf_socket: pointer to bpf_socket
+ *     @level: SOL_SOCKET or IPROTO_TCP
+ *     @optname: option name
+ *     @optval: pointer to option value
+ *     @optlen: length of optval in byes
+ *     Return: 0 or negative error
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -568,7 +581,8 @@ union bpf_attr {
 	FN(probe_read_str),		\
 	FN(get_socket_cookie),		\
 	FN(get_socket_uid),		\
-	FN(set_hash),
+	FN(set_hash),			\
+	FN(setsockopt),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -720,4 +734,56 @@ struct bpf_map_info {
 	__u32 map_flags;
 } __attribute__((aligned(8)));
 
+/* User bpf_sock_ops struct to access socket values and specify request ops
+ * and their replies.
+ * Some of this fields are in network (bigendian) byte order and may need
+ * to be converted before use (bpf_ntohl() defined in samples/bpf/bpf_endian.h).
+ * New fields can only be added at the end of this structure
+ */
+struct bpf_sock_ops {
+	__u32 op;
+	union {
+		__u32 reply;
+		__u32 replylong[4];
+	};
+	__u32 family;
+	__u32 remote_ip4;	/* Stored in network byte order */
+	__u32 local_ip4;	/* Stored in network byte order */
+	__u32 remote_ip6[4];	/* Stored in network byte order */
+	__u32 local_ip6[4];	/* Stored in network byte order */
+	__u32 remote_port;	/* Stored in network byte order */
+	__u32 local_port;	/* stored in host byte order */
+};
+
+/* List of known BPF sock_ops operators.
+ * New entries can only be added at the end
+ */
+enum {
+	BPF_SOCK_OPS_VOID,
+	BPF_SOCK_OPS_TIMEOUT_INIT,	/* Should return SYN-RTO value to use or
+					 * -1 if default value should be used
+					 */
+	BPF_SOCK_OPS_RWND_INIT,		/* Should return initial advertized
+					 * window (in packets) or -1 if default
+					 * value should be used
+					 */
+	BPF_SOCK_OPS_TCP_CONNECT_CB,	/* Calls BPF program right before an
+					 * active connection is initialized
+					 */
+	BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB,	/* Calls BPF program when an
+						 * active connection is
+						 * established
+						 */
+	BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB,	/* Calls BPF program when a
+						 * passive connection is
+						 * established
+						 */
+	BPF_SOCK_OPS_NEEDS_ECN,		/* If connection's congestion control
+					 * needs ECN
+					 */
+};
+
+#define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
+#define TCP_BPF_SNDCWND_CLAMP	1002	/* Set sndcwnd_clamp */
+
 #endif /* _UAPI__LINUX_BPF_H__ */

kernel/bpf/cgroup.c

@@ -236,3 +236,40 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk,
 	return ret;
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
+
+/**
+ * __cgroup_bpf_run_filter_sock_ops() - Run a program on a sock
+ * @sk: socket to get cgroup from
+ * @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains
+ * sk with connection information (IP addresses, etc.) May not contain
+ * cgroup info if it is a req sock.
+ * @type: The type of program to be exectuted
+ *
+ * socket passed is expected to be of type INET or INET6.
+ *
+ * The program type passed in via @type must be suitable for sock_ops
+ * filtering. No further check is performed to assert that.
+ *
+ * This function will return %-EPERM if any if an attached program was found
+ * and if it returned != 1 during execution. In all other cases, 0 is returned.
+ */
+int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
+				     struct bpf_sock_ops_kern *sock_ops,
+				     enum bpf_attach_type type)
+{
+	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	struct bpf_prog *prog;
+	int ret = 0;
+
+
+	rcu_read_lock();
+
+	prog = rcu_dereference(cgrp->bpf.effective[type]);
+	if (prog)
+		ret = BPF_PROG_RUN(prog, sock_ops) == 1 ? 0 : -EPERM;
+
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops);

kernel/bpf/syscall.c

@@ -1079,6 +1079,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	case BPF_CGROUP_INET_SOCK_CREATE:
 		ptype = BPF_PROG_TYPE_CGROUP_SOCK;
 		break;
+	case BPF_CGROUP_SOCK_OPS:
+		ptype = BPF_PROG_TYPE_SOCK_OPS;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1119,6 +1122,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	case BPF_CGROUP_INET_INGRESS:
 	case BPF_CGROUP_INET_EGRESS:
 	case BPF_CGROUP_INET_SOCK_CREATE:
+	case BPF_CGROUP_SOCK_OPS:
 		cgrp = cgroup_get_from_fd(attr->target_fd);
 		if (IS_ERR(cgrp))
 			return PTR_ERR(cgrp);
@@ -1133,6 +1137,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 
 	return ret;
 }
+
 #endif /* CONFIG_CGROUP_BPF */
 
 #define BPF_PROG_TEST_RUN_LAST_FIELD test.duration

net/core/filter.c

@@ -54,6 +54,7 @@
 #include <net/dst.h>
 #include <net/sock_reuseport.h>
 #include <net/busy_poll.h>
+#include <net/tcp.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -2672,6 +2673,110 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
+	   int, level, int, optname, char *, optval, int, optlen)
+{
+	struct sock *sk = bpf_sock->sk;
+	int ret = 0;
+	int val;
+
+	if (!sk_fullsock(sk))
+		return -EINVAL;
+
+	if (level == SOL_SOCKET) {
+		if (optlen != sizeof(int))
+			return -EINVAL;
+		val = *((int *)optval);
+
+		/* Only some socketops are supported */
+		switch (optname) {
+		case SO_RCVBUF:
+			sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
+			sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
+			break;
+		case SO_SNDBUF:
+			sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
+			sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
+			break;
+		case SO_MAX_PACING_RATE:
+			sk->sk_max_pacing_rate = val;
+			sk->sk_pacing_rate = min(sk->sk_pacing_rate,
+						 sk->sk_max_pacing_rate);
+			break;
+		case SO_PRIORITY:
+			sk->sk_priority = val;
+			break;
+		case SO_RCVLOWAT:
+			if (val < 0)
+				val = INT_MAX;
+			sk->sk_rcvlowat = val ? : 1;
+			break;
+		case SO_MARK:
+			sk->sk_mark = val;
+			break;
+		default:
+			ret = -EINVAL;
+		}
+	} else if (level == SOL_TCP &&
+		   sk->sk_prot->setsockopt == tcp_setsockopt) {
+#ifdef CONFIG_INET
+		if (optname == TCP_CONGESTION) {
+			char name[TCP_CA_NAME_MAX];
+
+			strncpy(name, optval, min_t(long, optlen,
+						    TCP_CA_NAME_MAX-1));
+			name[TCP_CA_NAME_MAX-1] = 0;
+			ret = tcp_set_congestion_control(sk, name, false);
+			if (!ret && bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN)
+				/* replacing an existing ca */
+				tcp_reinit_congestion_control(sk,
+					inet_csk(sk)->icsk_ca_ops);
+		} else {
+			struct tcp_sock *tp = tcp_sk(sk);
+
+			if (optlen != sizeof(int))
+				return -EINVAL;
+
+			val = *((int *)optval);
+			/* Only some options are supported */
+			switch (optname) {
+			case TCP_BPF_IW:
+				if (val <= 0 || tp->data_segs_out > 0)
+					ret = -EINVAL;
+				else
+					tp->snd_cwnd = val;
+				break;
+			case TCP_BPF_SNDCWND_CLAMP:
+				if (val <= 0) {
+					ret = -EINVAL;
+				} else {
+					tp->snd_cwnd_clamp = val;
+					tp->snd_ssthresh = val;
+				}
+			default:
+				ret = -EINVAL;
+			}
+		}
+#else
+		ret = -EINVAL;
+#endif
+	} else {
+		ret = -EINVAL;
+	}
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_setsockopt_proto = {
+	.func		= bpf_setsockopt,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
+};
+
 static const struct bpf_func_proto *
 bpf_base_func_proto(enum bpf_func_id func_id)
 {
@@ -2822,6 +2927,17 @@ lwt_inout_func_proto(enum bpf_func_id func_id)
 	}
 }
 
+static const struct bpf_func_proto *
+	sock_ops_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_setsockopt:
+		return &bpf_setsockopt_proto;
+	default:
+		return bpf_base_func_proto(func_id);
+	}
+}
+
 static const struct bpf_func_proto *
 lwt_xmit_func_proto(enum bpf_func_id func_id)
 {
@@ -3110,6 +3226,36 @@ void bpf_warn_invalid_xdp_action(u32 act)
 }
 EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
 
+static bool __is_valid_sock_ops_access(int off, int size)
+{
+	if (off < 0 || off >= sizeof(struct bpf_sock_ops))
+		return false;
+	/* The verifier guarantees that size > 0. */
+	if (off % size != 0)
+		return false;
+	if (size != sizeof(__u32))
+		return false;
+
+	return true;
+}
+
+static bool sock_ops_is_valid_access(int off, int size,
+				     enum bpf_access_type type,
+				     struct bpf_insn_access_aux *info)
+{
+	if (type == BPF_WRITE) {
+		switch (off) {
+		case offsetof(struct bpf_sock_ops, op) ...
+		     offsetof(struct bpf_sock_ops, replylong[3]):
+			break;
+		default:
+			return false;
+		}
+	}
+
+	return __is_valid_sock_ops_access(off, size);
+}
+
 static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 				  const struct bpf_insn *si,
 				  struct bpf_insn *insn_buf,
@@ -3379,6 +3525,138 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 	return insn - insn_buf;
 }
 
+static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
+				       const struct bpf_insn *si,
+				       struct bpf_insn *insn_buf,
+				       struct bpf_prog *prog)
+{
+	struct bpf_insn *insn = insn_buf;
+	int off;
+
+	switch (si->off) {
+	case offsetof(struct bpf_sock_ops, op) ...
+	     offsetof(struct bpf_sock_ops, replylong[3]):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, op) !=
+			     FIELD_SIZEOF(struct bpf_sock_ops_kern, op));
+		BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, reply) !=
+			     FIELD_SIZEOF(struct bpf_sock_ops_kern, reply));
+		BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, replylong) !=
+			     FIELD_SIZEOF(struct bpf_sock_ops_kern, replylong));
+		off = si->off;
+		off -= offsetof(struct bpf_sock_ops, op);
+		off += offsetof(struct bpf_sock_ops_kern, op);
+		if (type == BPF_WRITE)
+			*insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg,
+					      off);
+		else
+			*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg,
+					      off);
+		break;
+
+	case offsetof(struct bpf_sock_ops, family):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2);
+
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
+					      struct bpf_sock_ops_kern, sk),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern, sk));
+		*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg,
+				      offsetof(struct sock_common, skc_family));
+		break;
+
+	case offsetof(struct bpf_sock_ops, remote_ip4):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4);
+
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
+						struct bpf_sock_ops_kern, sk),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern, sk));
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+				      offsetof(struct sock_common, skc_daddr));
+		break;
+
+	case offsetof(struct bpf_sock_ops, local_ip4):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_rcv_saddr) != 4);
+
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
+					      struct bpf_sock_ops_kern, sk),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern, sk));
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+				      offsetof(struct sock_common,
+					       skc_rcv_saddr));
+		break;
+
+	case offsetof(struct bpf_sock_ops, remote_ip6[0]) ...
+	     offsetof(struct bpf_sock_ops, remote_ip6[3]):
+#if IS_ENABLED(CONFIG_IPV6)
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common,
+					  skc_v6_daddr.s6_addr32[0]) != 4);
+
+		off = si->off;
+		off -= offsetof(struct bpf_sock_ops, remote_ip6[0]);
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
+						struct bpf_sock_ops_kern, sk),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern, sk));
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+				      offsetof(struct sock_common,
+					       skc_v6_daddr.s6_addr32[0]) +
+				      off);
+#else
+		*insn++ = BPF_MOV32_IMM(si->dst_reg, 0);
+#endif
+		break;
+
+	case offsetof(struct bpf_sock_ops, local_ip6[0]) ...
+	     offsetof(struct bpf_sock_ops, local_ip6[3]):
+#if IS_ENABLED(CONFIG_IPV6)
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common,
+					  skc_v6_rcv_saddr.s6_addr32[0]) != 4);
+
+		off = si->off;
+		off -= offsetof(struct bpf_sock_ops, local_ip6[0]);
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
+						struct bpf_sock_ops_kern, sk),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern, sk));
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+				      offsetof(struct sock_common,
+					       skc_v6_rcv_saddr.s6_addr32[0]) +
+				      off);
+#else
+		*insn++ = BPF_MOV32_IMM(si->dst_reg, 0);
+#endif
+		break;
+
+	case offsetof(struct bpf_sock_ops, remote_port):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2);
+
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
+						struct bpf_sock_ops_kern, sk),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern, sk));
+		*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg,
+				      offsetof(struct sock_common, skc_dport));
+#ifndef __BIG_ENDIAN_BITFIELD
+		*insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16);
+#endif
+		break;
+
+	case offsetof(struct bpf_sock_ops, local_port):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2);
+
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
+						struct bpf_sock_ops_kern, sk),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern, sk));
+		*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg,
+				      offsetof(struct sock_common, skc_num));
+		break;
+	}
+	return insn - insn_buf;
+}
+
 const struct bpf_verifier_ops sk_filter_prog_ops = {
 	.get_func_proto		= sk_filter_func_proto,
 	.is_valid_access	= sk_filter_is_valid_access,
@@ -3428,6 +3706,12 @@ const struct bpf_verifier_ops cg_sock_prog_ops = {
 	.convert_ctx_access	= sock_filter_convert_ctx_access,
 };
 
+const struct bpf_verifier_ops sock_ops_prog_ops = {
+	.get_func_proto		= sock_ops_func_proto,
+	.is_valid_access	= sock_ops_is_valid_access,
+	.convert_ctx_access	= sock_ops_convert_ctx_access,
+};
+
 int sk_detach_filter(struct sock *sk)
 {
 	int ret = -ENOENT;

net/ipv4/tcp.c

@@ -2481,7 +2481,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		name[val] = 0;
 
 		lock_sock(sk);
-		err = tcp_set_congestion_control(sk, name);
+		err = tcp_set_congestion_control(sk, name, true);
 		release_sock(sk);
 		return err;
 	}

net/ipv4/tcp_cong.c

@@ -189,8 +189,8 @@ void tcp_init_congestion_control(struct sock *sk)
 		INET_ECN_dontxmit(sk);
 }
 
-static void tcp_reinit_congestion_control(struct sock *sk,
-					  const struct tcp_congestion_ops *ca)
+void tcp_reinit_congestion_control(struct sock *sk,
+				   const struct tcp_congestion_ops *ca)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -333,8 +333,12 @@ out:
 	return ret;
 }
 
-/* Change congestion control for socket */
-int tcp_set_congestion_control(struct sock *sk, const char *name)
+/* Change congestion control for socket. If load is false, then it is the
+ * responsibility of the caller to call tcp_init_congestion_control or
+ * tcp_reinit_congestion_control (if the current congestion control was
+ * already initialized.
+ */
+int tcp_set_congestion_control(struct sock *sk, const char *name, bool load)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_congestion_ops *ca;
@@ -344,21 +348,29 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
 		return -EPERM;
 
 	rcu_read_lock();
-	ca = __tcp_ca_find_autoload(name);
+	if (!load)
+		ca = tcp_ca_find(name);
+	else
+		ca = __tcp_ca_find_autoload(name);
 	/* No change asking for existing value */
 	if (ca == icsk->icsk_ca_ops) {
 		icsk->icsk_ca_setsockopt = 1;
 		goto out;
 	}
-	if (!ca)
+	if (!ca) {
 		err = -ENOENT;
-	else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
-		   ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)))
+	} else if (!load) {
+		icsk->icsk_ca_ops = ca;
+		if (!try_module_get(ca->owner))
+			err = -EBUSY;
+	} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
+		     ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) {
 		err = -EPERM;
-	else if (!try_module_get(ca->owner))
+	} else if (!try_module_get(ca->owner)) {
 		err = -EBUSY;
-	else
+	} else {
 		tcp_reinit_congestion_control(sk, ca);
+	}
  out:
 	rcu_read_unlock();
 	return err;

net/ipv4/tcp_fastopen.c

@@ -221,6 +221,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	tcp_init_congestion_control(child);
 	tcp_mtup_init(child);
 	tcp_init_metrics(child);
+	tcp_call_bpf(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
 	tcp_init_buffer_space(child);
 
 	tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;

net/ipv4/tcp_input.c

@@ -5571,7 +5571,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 	icsk->icsk_af_ops->rebuild_header(sk);
 
 	tcp_init_metrics(sk);
-
+	tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
 	tcp_init_congestion_control(sk);
 
 	/* Prevent spurious tcp_cwnd_restart() on first data
@@ -5977,6 +5977,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		} else {
 			/* Make sure socket is routed, for correct metrics. */
 			icsk->icsk_af_ops->rebuild_header(sk);
+			tcp_call_bpf(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
 			tcp_init_congestion_control(sk);
 
 			tcp_mtup_init(sk);
@@ -6190,7 +6191,8 @@ static void tcp_ecn_create_request(struct request_sock *req,
 	ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst;
 
 	if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk) ||
-	    (ecn_ok_dst & DST_FEATURE_ECN_CA))
+	    (ecn_ok_dst & DST_FEATURE_ECN_CA) ||
+	    tcp_bpf_ca_needs_ecn((struct sock *)req))
 		inet_rsk(req)->ecn_ok = 1;
 }
 
@@ -6406,7 +6408,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	} else {
 		tcp_rsk(req)->tfo_listener = false;
 		if (!want_cookie)
-			inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+			inet_csk_reqsk_queue_hash_add(sk, req,
+				tcp_timeout_init((struct sock *)req));
 		af_ops->send_synack(sk, dst, &fl, req, &foc,
 				    !want_cookie ? TCP_SYNACK_NORMAL :
 						   TCP_SYNACK_COOKIE);

net/ipv4/tcp_minisocks.c

@@ -351,6 +351,7 @@ void tcp_openreq_init_rwin(struct request_sock *req,
 	int full_space = tcp_full_space(sk_listener);
 	u32 window_clamp;
 	__u8 rcv_wscale;
+	u32 rcv_wnd;
 	int mss;
 
 	mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
@@ -363,6 +364,12 @@ void tcp_openreq_init_rwin(struct request_sock *req,
 	    (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
 		req->rsk_window_clamp = full_space;
 
+	rcv_wnd = tcp_rwnd_init_bpf((struct sock *)req);
+	if (rcv_wnd == 0)
+		rcv_wnd = dst_metric(dst, RTAX_INITRWND);
+	else if (full_space < rcv_wnd * mss)
+		full_space = rcv_wnd * mss;
+
 	/* tcp_full_space because it is guaranteed to be the first packet */
 	tcp_select_initial_window(full_space,
 		mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
@@ -370,7 +377,7 @@ void tcp_openreq_init_rwin(struct request_sock *req,
 		&req->rsk_window_clamp,
 		ireq->wscale_ok,
 		&rcv_wscale,
-		dst_metric(dst, RTAX_INITRWND));
+		rcv_wnd);
 	ireq->rcv_wscale = rcv_wscale;
 }
 EXPORT_SYMBOL(tcp_openreq_init_rwin);

net/ipv4/tcp_output.c

@@ -316,7 +316,8 @@ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb)
 	TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR;
 	if (!(tp->ecn_flags & TCP_ECN_OK))
 		TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE;
-	else if (tcp_ca_needs_ecn(sk))
+	else if (tcp_ca_needs_ecn(sk) ||
+		 tcp_bpf_ca_needs_ecn(sk))
 		INET_ECN_xmit(sk);
 }
 
@@ -324,8 +325,9 @@ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb)
 static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk);
 	bool use_ecn = sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
-		       tcp_ca_needs_ecn(sk);
+		tcp_ca_needs_ecn(sk) || bpf_needs_ecn;
 
 	if (!use_ecn) {
 		const struct dst_entry *dst = __sk_dst_get(sk);
@@ -339,7 +341,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 	if (use_ecn) {
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
 		tp->ecn_flags = TCP_ECN_OK;
-		if (tcp_ca_needs_ecn(sk))
+		if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn)
 			INET_ECN_xmit(sk);
 	}
 }
@@ -3266,6 +3268,7 @@ static void tcp_connect_init(struct sock *sk)
 	const struct dst_entry *dst = __sk_dst_get(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	__u8 rcv_wscale;
+	u32 rcv_wnd;
 
 	/* We'll fix this up when we get a response from the other end.
 	 * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT.
@@ -3299,13 +3302,17 @@ static void tcp_connect_init(struct sock *sk)
 	    (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0))
 		tp->window_clamp = tcp_full_space(sk);
 
+	rcv_wnd = tcp_rwnd_init_bpf(sk);
+	if (rcv_wnd == 0)
+		rcv_wnd = dst_metric(dst, RTAX_INITRWND);
+
 	tcp_select_initial_window(tcp_full_space(sk),
 				  tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
 				  &tp->rcv_wnd,
 				  &tp->window_clamp,
 				  sock_net(sk)->ipv4.sysctl_tcp_window_scaling,
 				  &rcv_wscale,
-				  dst_metric(dst, RTAX_INITRWND));
+				  rcv_wnd);
 
 	tp->rx_opt.rcv_wscale = rcv_wscale;
 	tp->rcv_ssthresh = tp->rcv_wnd;
@@ -3326,7 +3333,7 @@ static void tcp_connect_init(struct sock *sk)
 	tp->rcv_wup = tp->rcv_nxt;
 	tp->copied_seq = tp->rcv_nxt;
 
-	inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
+	inet_csk(sk)->icsk_rto = tcp_timeout_init(sk);
 	inet_csk(sk)->icsk_retransmits = 0;
 	tcp_clear_retrans(tp);
 }
@@ -3439,6 +3446,7 @@ int tcp_connect(struct sock *sk)
 	struct sk_buff *buff;
 	int err;
 
+	tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB);
 	tcp_connect_init(sk);
 
 	if (unlikely(tp->repair)) {

samples/bpf/Makefile

@@ -36,6 +36,7 @@ hostprogs-y += lwt_len_hist
 hostprogs-y += xdp_tx_iptunnel
 hostprogs-y += test_map_in_map
 hostprogs-y += per_socket_stats_example
+hostprogs-y += load_sock_ops
 
 # Libbpf dependencies
 LIBBPF := ../../tools/lib/bpf/bpf.o
@@ -52,6 +53,7 @@ tracex3-objs := bpf_load.o $(LIBBPF) tracex3_user.o
 tracex4-objs := bpf_load.o $(LIBBPF) tracex4_user.o
 tracex5-objs := bpf_load.o $(LIBBPF) tracex5_user.o
 tracex6-objs := bpf_load.o $(LIBBPF) tracex6_user.o
+load_sock_ops-objs := bpf_load.o $(LIBBPF) load_sock_ops.o
 test_probe_write_user-objs := bpf_load.o $(LIBBPF) test_probe_write_user_user.o
 trace_output-objs := bpf_load.o $(LIBBPF) trace_output_user.o
 lathist-objs := bpf_load.o $(LIBBPF) lathist_user.o
@@ -111,6 +113,12 @@ always += lwt_len_hist_kern.o
 always += xdp_tx_iptunnel_kern.o
 always += test_map_in_map_kern.o
 always += cookie_uid_helper_example.o
+always += tcp_synrto_kern.o
+always += tcp_rwnd_kern.o
+always += tcp_bufs_kern.o
+always += tcp_cong_kern.o
+always += tcp_iw_kern.o
+always += tcp_clamp_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/lib/
@@ -130,6 +138,7 @@ HOSTLOADLIBES_tracex4 += -lelf -lrt
 HOSTLOADLIBES_tracex5 += -lelf
 HOSTLOADLIBES_tracex6 += -lelf
 HOSTLOADLIBES_test_cgrp2_sock2 += -lelf
+HOSTLOADLIBES_load_sock_ops += -lelf
 HOSTLOADLIBES_test_probe_write_user += -lelf
 HOSTLOADLIBES_trace_output += -lelf -lrt
 HOSTLOADLIBES_lathist += -lelf

samples/bpf/bpf_helpers.h

@@ -60,6 +60,9 @@ static unsigned long long (*bpf_get_prandom_u32)(void) =
 	(void *) BPF_FUNC_get_prandom_u32;
 static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
 	(void *) BPF_FUNC_xdp_adjust_head;
+static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval,
+			     int optlen) =
+	(void *) BPF_FUNC_setsockopt;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions

samples/bpf/bpf_load.c

@@ -64,6 +64,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 	bool is_perf_event = strncmp(event, "perf_event", 10) == 0;
 	bool is_cgroup_skb = strncmp(event, "cgroup/skb", 10) == 0;
 	bool is_cgroup_sk = strncmp(event, "cgroup/sock", 11) == 0;
+	bool is_sockops = strncmp(event, "sockops", 7) == 0;
 	size_t insns_cnt = size / sizeof(struct bpf_insn);
 	enum bpf_prog_type prog_type;
 	char buf[256];
@@ -89,6 +90,8 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 		prog_type = BPF_PROG_TYPE_CGROUP_SKB;
 	} else if (is_cgroup_sk) {
 		prog_type = BPF_PROG_TYPE_CGROUP_SOCK;
+	} else if (is_sockops) {
+		prog_type = BPF_PROG_TYPE_SOCK_OPS;
 	} else {
 		printf("Unknown event '%s'\n", event);
 		return -1;
@@ -106,8 +109,11 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 	if (is_xdp || is_perf_event || is_cgroup_skb || is_cgroup_sk)
 		return 0;
 
-	if (is_socket) {
-		event += 6;
+	if (is_socket || is_sockops) {
+		if (is_socket)
+			event += 6;
+		else
+			event += 7;
 		if (*event != '/')
 			return 0;
 		event++;
@@ -560,7 +566,8 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map)
 		    memcmp(shname, "xdp", 3) == 0 ||
 		    memcmp(shname, "perf_event", 10) == 0 ||
 		    memcmp(shname, "socket", 6) == 0 ||
-		    memcmp(shname, "cgroup/", 7) == 0)
+		    memcmp(shname, "cgroup/", 7) == 0 ||
+		    memcmp(shname, "sockops", 7) == 0)
 			load_and_attach(shname, data->d_buf, data->d_size);
 	}
 

samples/bpf/load_sock_ops.c

@@ -0,0 +1,97 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+#include <unistd.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/unistd.h>
+
+static void usage(char *pname)
+{
+	printf("USAGE:\n  %s [-l] <cg-path> <prog filename>\n", pname);
+	printf("\tLoad and attach a sock_ops program to the specified "
+	       "cgroup\n");
+	printf("\tIf \"-l\" is used, the program will continue to run\n");
+	printf("\tprinting the BPF log buffer\n");
+	printf("\tIf the specified filename does not end in \".o\", it\n");
+	printf("\tappends \"_kern.o\" to the name\n");
+	printf("\n");
+	printf("  %s -r <cg-path>\n", pname);
+	printf("\tDetaches the currently attached sock_ops program\n");
+	printf("\tfrom the specified cgroup\n");
+	printf("\n");
+	exit(1);
+}
+
+int main(int argc, char **argv)
+{
+	int logFlag = 0;
+	int error = 0;
+	char *cg_path;
+	char fn[500];
+	char *prog;
+	int cg_fd;
+
+	if (argc < 3)
+		usage(argv[0]);
+
+	if (!strcmp(argv[1], "-r")) {
+		cg_path = argv[2];
+		cg_fd = open(cg_path, O_DIRECTORY, O_RDONLY);
+		error = bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+		if (error) {
+			printf("ERROR: bpf_prog_detach: %d (%s)\n",
+			       error, strerror(errno));
+			return 2;
+		}
+		return 0;
+	} else if (!strcmp(argv[1], "-h")) {
+		usage(argv[0]);
+	} else if (!strcmp(argv[1], "-l")) {
+		logFlag = 1;
+		if (argc < 4)
+			usage(argv[0]);
+	}
+
+	prog = argv[argc - 1];
+	cg_path = argv[argc - 2];
+	if (strlen(prog) > 480) {
+		fprintf(stderr, "ERROR: program name too long (> 480 chars)\n");
+		return 3;
+	}
+	cg_fd = open(cg_path, O_DIRECTORY, O_RDONLY);
+
+	if (!strcmp(prog + strlen(prog)-2, ".o"))
+		strcpy(fn, prog);
+	else
+		sprintf(fn, "%s_kern.o", prog);
+	if (logFlag)
+		printf("loading bpf file:%s\n", fn);
+	if (load_bpf_file(fn)) {
+		printf("ERROR: load_bpf_file failed for: %s\n", fn);
+		printf("%s", bpf_log_buf);
+		return 4;
+	}
+	if (logFlag)
+		printf("TCP BPF Loaded %s\n", fn);
+
+	error = bpf_prog_attach(prog_fd[0], cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+	if (error) {
+		printf("ERROR: bpf_prog_attach: %d (%s)\n",
+		       error, strerror(errno));
+		return 5;
+	} else if (logFlag) {
+		read_trace_pipe();
+	}
+
+	return error;
+}

samples/bpf/tcp_bufs_kern.c

@@ -0,0 +1,86 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * BPF program to set initial receive window to 40 packets and send
+ * and receive buffers to 1.5MB. This would usually be done after
+ * doing appropriate checks that indicate the hosts are far enough
+ * away (i.e. large RTT).
+ *
+ * Use load_sock_ops to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define DEBUG 1
+
+#define bpf_printk(fmt, ...)					\
+({								\
+	       char ____fmt[] = fmt;				\
+	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				##__VA_ARGS__);			\
+})
+
+SEC("sockops")
+int bpf_bufs(struct bpf_sock_ops *skops)
+{
+	int bufsize = 1500000;
+	int rwnd_init = 40;
+	int rv = 0;
+	int op;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if neither port numberis 55601
+	 */
+	if (bpf_ntohl(skops->remote_port) != 55601 &&
+	    skops->local_port != 55601)
+		return -1;
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+
+	/* Usually there would be a check to insure the hosts are far
+	 * from each other so it makes sense to increase buffer sizes
+	 */
+	switch (op) {
+	case BPF_SOCK_OPS_RWND_INIT:
+		rv = rwnd_init;
+		break;
+	case BPF_SOCK_OPS_TCP_CONNECT_CB:
+		/* Set sndbuf and rcvbuf of active connections */
+		rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize,
+				    sizeof(bufsize));
+		rv = rv*100 + bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF,
+					     &bufsize, sizeof(bufsize));
+		break;
+	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+		/* Nothing to do */
+		break;
+	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+		/* Set sndbuf and rcvbuf of passive connections */
+		rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize,
+				    sizeof(bufsize));
+		rv = rv*100 + bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF,
+					     &bufsize, sizeof(bufsize));
+		break;
+	default:
+		rv = -1;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

samples/bpf/tcp_clamp_kern.c

@@ -0,0 +1,102 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * Sample BPF program to set send and receive buffers to 150KB, sndcwnd clamp
+ * to 100 packets and SYN and SYN_ACK RTOs to 10ms when both hosts are within
+ * the same datacenter. For his example, we assume they are within the same
+ * datacenter when the first 5.5 bytes of their IPv6 addresses are the same.
+ *
+ * Use load_sock_ops to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define DEBUG 1
+
+#define bpf_printk(fmt, ...)					\
+({								\
+	       char ____fmt[] = fmt;				\
+	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				##__VA_ARGS__);			\
+})
+
+SEC("sockops")
+int bpf_clamp(struct bpf_sock_ops *skops)
+{
+	int bufsize = 150000;
+	int to_init = 10;
+	int clamp = 100;
+	int rv = 0;
+	int op;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if neither port numberis 55601
+	 */
+	if (bpf_ntohl(skops->remote_port) != 55601 && skops->local_port != 55601)
+		return -1;
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("BPF command: %d\n", op);
+#endif
+
+	/* Check that both hosts are within same datacenter. For this example
+	 * it is the case when the first 5.5 bytes of their IPv6 addresses are
+	 * the same.
+	 */
+	if (skops->family == AF_INET6 &&
+	    skops->local_ip6[0] == skops->remote_ip6[0] &&
+	    (bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) ==
+	    (bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000)) {
+		switch (op) {
+		case BPF_SOCK_OPS_TIMEOUT_INIT:
+			rv = to_init;
+			break;
+		case BPF_SOCK_OPS_TCP_CONNECT_CB:
+			/* Set sndbuf and rcvbuf of active connections */
+			rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF,
+					    &bufsize, sizeof(bufsize));
+			rv = rv*100 + bpf_setsockopt(skops, SOL_SOCKET,
+						      SO_RCVBUF, &bufsize,
+						      sizeof(bufsize));
+			break;
+		case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+			rv = bpf_setsockopt(skops, SOL_TCP,
+					    TCP_BPF_SNDCWND_CLAMP,
+					    &clamp, sizeof(clamp));
+			break;
+		case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+			/* Set sndbuf and rcvbuf of passive connections */
+			rv = bpf_setsockopt(skops, SOL_TCP,
+					    TCP_BPF_SNDCWND_CLAMP,
+					    &clamp, sizeof(clamp));
+			rv = rv*100 + bpf_setsockopt(skops, SOL_SOCKET,
+						      SO_SNDBUF, &bufsize,
+						      sizeof(bufsize));
+			rv = rv*100 + bpf_setsockopt(skops, SOL_SOCKET,
+						      SO_RCVBUF, &bufsize,
+						      sizeof(bufsize));
+			break;
+		default:
+			rv = -1;
+		}
+	} else {
+		rv = -1;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

samples/bpf/tcp_cong_kern.c

@@ -0,0 +1,83 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * BPF program to set congestion control to dctcp when both hosts are
+ * in the same datacenter (as deteremined by IPv6 prefix).
+ *
+ * Use load_sock_ops to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define DEBUG 1
+
+#define bpf_printk(fmt, ...)					\
+({								\
+	       char ____fmt[] = fmt;				\
+	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				##__VA_ARGS__);			\
+})
+
+SEC("sockops")
+int bpf_cong(struct bpf_sock_ops *skops)
+{
+	char cong[] = "dctcp";
+	int rv = 0;
+	int op;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if neither port numberis 55601
+	 */
+	if (bpf_ntohl(skops->remote_port) != 55601 &&
+	    skops->local_port != 55601)
+		return -1;
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("BPF command: %d\n", op);
+#endif
+
+	/* Check if both hosts are in the same datacenter. For this
+	 * example they are if the 1st 5.5 bytes in the IPv6 address
+	 * are the same.
+	 */
+	if (skops->family == AF_INET6 &&
+	    skops->local_ip6[0] == skops->remote_ip6[0] &&
+	    (bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) ==
+	    (bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000)) {
+		switch (op) {
+		case BPF_SOCK_OPS_NEEDS_ECN:
+			rv = 1;
+			break;
+		case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+			rv = bpf_setsockopt(skops, SOL_TCP, TCP_CONGESTION,
+					    cong, sizeof(cong));
+			break;
+		case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+			rv = bpf_setsockopt(skops, SOL_TCP, TCP_CONGESTION,
+					    cong, sizeof(cong));
+			break;
+		default:
+			rv = -1;
+		}
+	} else {
+		rv = -1;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

samples/bpf/tcp_iw_kern.c

@@ -0,0 +1,88 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * BPF program to set initial congestion window and initial receive
+ * window to 40 packets and send and receive buffers to 1.5MB. This
+ * would usually be done after doing appropriate checks that indicate
+ * the hosts are far enough away (i.e. large RTT).
+ *
+ * Use load_sock_ops to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define DEBUG 1
+
+#define bpf_printk(fmt, ...)					\
+({								\
+	       char ____fmt[] = fmt;				\
+	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				##__VA_ARGS__);			\
+})
+
+SEC("sockops")
+int bpf_iw(struct bpf_sock_ops *skops)
+{
+	int bufsize = 1500000;
+	int rwnd_init = 40;
+	int iw = 40;
+	int rv = 0;
+	int op;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if neither port numberis 55601
+	 */
+	if (bpf_ntohl(skops->remote_port) != 55601 &&
+	    skops->local_port != 55601)
+		return -1;
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("BPF command: %d\n", op);
+#endif
+
+	/* Usually there would be a check to insure the hosts are far
+	 * from each other so it makes sense to increase buffer sizes
+	 */
+	switch (op) {
+	case BPF_SOCK_OPS_RWND_INIT:
+		rv = rwnd_init;
+		break;
+	case BPF_SOCK_OPS_TCP_CONNECT_CB:
+		/* Set sndbuf and rcvbuf of active connections */
+		rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize,
+				    sizeof(bufsize));
+		rv = rv*100 + bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF,
+					     &bufsize, sizeof(bufsize));
+		break;
+	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+		rv = bpf_setsockopt(skops, SOL_TCP, TCP_BPF_IW, &iw,
+				    sizeof(iw));
+		break;
+	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+		/* Set sndbuf and rcvbuf of passive connections */
+		rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize,
+				    sizeof(bufsize));
+		rv = rv*100 + bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF,
+					     &bufsize, sizeof(bufsize));
+		break;
+	default:
+		rv = -1;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

samples/bpf/tcp_rwnd_kern.c

@@ -0,0 +1,69 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * BPF program to set initial receive window to 40 packets when using IPv6
+ * and the first 5.5 bytes of the IPv6 addresses are not the same (in this
+ * example that means both hosts are not the same datacenter).
+ *
+ * Use load_sock_ops to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define DEBUG 1
+
+#define bpf_printk(fmt, ...)					\
+({								\
+	       char ____fmt[] = fmt;				\
+	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				##__VA_ARGS__);			\
+})
+
+SEC("sockops")
+int bpf_rwnd(struct bpf_sock_ops *skops)
+{
+	int rv = -1;
+	int op;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if neither port numberis 55601
+	 */
+	if (bpf_ntohl(skops->remote_port) !=
+	    55601 && skops->local_port != 55601)
+		return -1;
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("BPF command: %d\n", op);
+#endif
+
+	/* Check for RWND_INIT operation and IPv6 addresses */
+	if (op == BPF_SOCK_OPS_RWND_INIT &&
+		skops->family == AF_INET6) {
+
+		/* If the first 5.5 bytes of the IPv6 address are not the same
+		 * then both hosts are not in the same datacenter
+		 * so use a larger initial advertized window (40 packets)
+		 */
+		if (skops->local_ip6[0] != skops->remote_ip6[0] ||
+		    (bpf_ntohl(skops->local_ip6[1]) & 0xfffff000) !=
+		    (bpf_ntohl(skops->remote_ip6[1]) & 0xfffff000))
+			rv = 40;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

samples/bpf/tcp_synrto_kern.c

@@ -0,0 +1,69 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * BPF program to set SYN and SYN-ACK RTOs to 10ms when using IPv6 addresses
+ * and the first 5.5 bytes of the IPv6 addresses are the same (in this example
+ * that means both hosts are in the same datacenter).
+ *
+ * Use load_sock_ops to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define DEBUG 1
+
+#define bpf_printk(fmt, ...)					\
+({								\
+	       char ____fmt[] = fmt;				\
+	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				##__VA_ARGS__);			\
+})
+
+SEC("sockops")
+int bpf_synrto(struct bpf_sock_ops *skops)
+{
+	int rv = -1;
+	int op;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if neither port numberis 55601
+	 */
+	if (bpf_ntohl(skops->remote_port) != 55601 &&
+	    skops->local_port != 55601)
+		return -1;
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("BPF command: %d\n", op);
+#endif
+
+	/* Check for TIMEOUT_INIT operation and IPv6 addresses */
+	if (op == BPF_SOCK_OPS_TIMEOUT_INIT &&
+		skops->family == AF_INET6) {
+
+		/* If the first 5.5 bytes of the IPv6 address are the same
+		 * then both hosts are in the same datacenter
+		 * so use an RTO of 10ms
+		 */
+		if (skops->local_ip6[0] == skops->remote_ip6[0] &&
+		    (bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) ==
+		    (bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000))
+			rv = 10;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

tools/include/uapi/linux/bpf.h

@@ -120,12 +120,14 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_LWT_IN,
 	BPF_PROG_TYPE_LWT_OUT,
 	BPF_PROG_TYPE_LWT_XMIT,
+	BPF_PROG_TYPE_SOCK_OPS,
 };
 
 enum bpf_attach_type {
 	BPF_CGROUP_INET_INGRESS,
 	BPF_CGROUP_INET_EGRESS,
 	BPF_CGROUP_INET_SOCK_CREATE,
+	BPF_CGROUP_SOCK_OPS,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -518,6 +520,17 @@ union bpf_attr {
  *     Set full skb->hash.
  *     @skb: pointer to skb
  *     @hash: hash to set
+ *
+ * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
+ *     Calls setsockopt. Not all opts are available, only those with
+ *     integer optvals plus TCP_CONGESTION.
+ *     Supported levels: SOL_SOCKET and IPROTO_TCP
+ *     @bpf_socket: pointer to bpf_socket
+ *     @level: SOL_SOCKET or IPROTO_TCP
+ *     @optname: option name
+ *     @optval: pointer to option value
+ *     @optlen: length of optval in byes
+ *     Return: 0 or negative error
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -568,7 +581,8 @@ union bpf_attr {
 	FN(probe_read_str),		\
 	FN(get_socket_cookie),		\
 	FN(get_socket_uid),		\
-	FN(set_hash),
+	FN(set_hash),			\
+	FN(setsockopt),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -720,4 +734,54 @@ struct bpf_map_info {
 	__u32 map_flags;
 } __attribute__((aligned(8)));
 
+/* User bpf_sock_ops struct to access socket values and specify request ops
+ * and their replies.
+ * New fields can only be added at the end of this structure
+ */
+struct bpf_sock_ops {
+	__u32 op;
+	union {
+		__u32 reply;
+		__u32 replylong[4];
+	};
+	__u32 family;
+	__u32 remote_ip4;
+	__u32 local_ip4;
+	__u32 remote_ip6[4];
+	__u32 local_ip6[4];
+	__u32 remote_port;
+	__u32 local_port;
+};
+
+/* List of known BPF sock_ops operators.
+ * New entries can only be added at the end
+ */
+enum {
+	BPF_SOCK_OPS_VOID,
+	BPF_SOCK_OPS_TIMEOUT_INIT,	/* Should return SYN-RTO value to use or
+					 * -1 if default value should be used
+					 */
+	BPF_SOCK_OPS_RWND_INIT,		/* Should return initial advertized
+					 * window (in packets) or -1 if default
+					 * value should be used
+					 */
+	BPF_SOCK_OPS_TCP_CONNECT_CB,	/* Calls BPF program right before an
+					 * active connection is initialized
+					 */
+	BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB,	/* Calls BPF program when an
+						 * active connection is
+						 * established
+						 */
+	BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB,	/* Calls BPF program when a
+						 * passive connection is
+						 * established
+						 */
+	BPF_SOCK_OPS_NEEDS_ECN,		/* If connection's congestion control
+					 * needs ECN
+					 */
+};
+
+#define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
+#define TCP_BPF_SNDCWND_CLAMP	1002	/* Set sndcwnd_clamp */
+
 #endif /* _UAPI__LINUX_BPF_H__ */