[PATCH v3 bpf-next 00/11] bpf: More sock_ops callbacks

[PATCH v3 bpf-next 00/11] bpf: More sock_ops callbacks

[Lawrence Brakmo]

This patchset adds support for:

- direct R or R/W access to many tcp_sock fields
- passing up to 4 arguments to sock_ops BPF functions
- tcp_sock field bpf_sock_ops_flags for controlling callbacks
- optionally calling sock_ops BPF program when RTO fires
- optionally calling sock_ops BPF program when packet is retransmitted
- optionally calling sock_ops BPF program when TCP state changes
- access to tclass and sk_txhash
- new selftest

v2: Fixed commit message 0/11. The commit is to "bpf-next" but the patch
    below used "bpf" and Patchwork didn't work correctly.
v3: Cleaned RTO callback as per  Yuchung's comment
    Added BPF enum for TCP states as per  Alexei's comment

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>

Consists of the following patches:
[PATCH v3 bpf-next 01/11] bpf: Make SOCK_OPS_GET_TCP size independent
[PATCH v3 bpf-next 02/11] bpf: Make SOCK_OPS_GET_TCP struct
[PATCH v3 bpf-next 03/11] bpf: Add write access to tcp_sock and sock
[PATCH v3 bpf-next 04/11] bpf: Support passing args to sock_ops bpf
[PATCH v3 bpf-next 05/11] bpf: Adds field bpf_sock_ops_flags to
[PATCH v3 bpf-next 06/11] bpf: Add sock_ops RTO callback
[PATCH v3 bpf-next 07/11] bpf: Add support for reading sk_state and
[PATCH v3 bpf-next 08/11] bpf: Add sock_ops R/W access to tclass &
[PATCH v3 bpf-next 09/11] bpf: Add BPF_SOCK_OPS_RETRANS_CB
[PATCH v3 bpf-next 10/11] bpf: Add BPF_SOCK_OPS_STATE_CB
[PATCH v3 bpf-next 11/11] bpf: add selftest for tcpbpf

include/linux/filter.h                         |   4 +
include/linux/tcp.h                            |   8 ++
include/net/tcp.h                              |  66 +++++++++-
include/uapi/linux/bpf.h                       |  61 ++++++++-
include/uapi/linux/tcp.h                       |   5 +
net/core/filter.c                              | 221 ++++++++++++++++++++++++++++++--
net/ipv4/tcp.c                                 |   6 +-
net/ipv4/tcp_nv.c                              |   2 +-
net/ipv4/tcp_output.c                          |   5 +-
net/ipv4/tcp_timer.c                           |   7 +
tools/include/uapi/linux/bpf.h                 |  70 +++++++++-
tools/testing/selftests/bpf/Makefile           |   4 +-
tools/testing/selftests/bpf/tcp_client.py      |  52 ++++++++
tools/testing/selftests/bpf/tcp_server.py      |  79 ++++++++++++
tools/testing/selftests/bpf/test_tcpbpf_kern.c | 125 ++++++++++++++++++
tools/testing/selftests/bpf/test_tcpbpf_user.c | 113 ++++++++++++++++
16 files changed, 803 insertions(+), 25 deletions(-)

[PATCH v3 bpf-next 01/11] bpf: Make SOCK_OPS_GET_TCP size independent

[Lawrence Brakmo]

Make SOCK_OPS_GET_TCP helper macro size independent (before only worked
with 4-byte fields.

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
 net/core/filter.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 130b842..099ff9fd 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4449,9 +4449,10 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 		break;
 
 /* Helper macro for adding read access to tcp_sock fields. */
-#define SOCK_OPS_GET_TCP32(FIELD_NAME)					      \
+#define SOCK_OPS_GET_TCP(FIELD_NAME)					      \
 	do {								      \
-		BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, FIELD_NAME) != 4); \
+		BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, FIELD_NAME) >      \
+			     FIELD_SIZEOF(struct bpf_sock_ops, FIELD_NAME));  \
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
 						struct bpf_sock_ops_kern,     \
 						is_fullsock),		      \
@@ -4463,16 +4464,18 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 						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,        \
+		*insn++ = BPF_LDX_MEM(FIELD_SIZEOF(struct tcp_sock,	      \
+						   FIELD_NAME), si->dst_reg,  \
+				      si->dst_reg,			      \
 				      offsetof(struct tcp_sock, FIELD_NAME)); \
 	} while (0)
 
 	case offsetof(struct bpf_sock_ops, snd_cwnd):
-		SOCK_OPS_GET_TCP32(snd_cwnd);
+		SOCK_OPS_GET_TCP(snd_cwnd);
 		break;
 
 	case offsetof(struct bpf_sock_ops, srtt_us):
-		SOCK_OPS_GET_TCP32(srtt_us);
+		SOCK_OPS_GET_TCP(srtt_us);
 		break;
 	}
 	return insn - insn_buf;
-- 
2.9.5

[PATCH v3 bpf-next 02/11] bpf: Make SOCK_OPS_GET_TCP struct independent

[Lawrence Brakmo]

Changed SOCK_OPS_GET_TCP to SOCK_OPS_GET_FIELD and added 2
arguments so now it can also work with struct sock fields.
The first argument is the name of the field in the bpf_sock_ops
struct, the 2nd argument is the name of the field in the OBJ struct.

Previous: SOCK_OPS_GET_TCP(FIELD_NAME)
New:      SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ)

Where OBJ is either "struct tcp_sock" or "struct sock" (without
quotation). BPF_FIELD is the name of the field in the bpf_sock_ops
struct and OBJ_FIELD is the name of the field in the OBJ struct.

Although the field names are currently the same, the kernel struct names
could change in the future and this change makes it easier to support
that.

Note that adding access to tcp_sock fields in sock_ops programs does
not preclude the tcp_sock fields from being removed as long as we are
willing to do one of the following:

  1) Return a fixed value (e.x. 0 or 0xffffffff), or
  2) Make the verifier fail if that field is accessed (i.e. program
    fails to load) so the user will know that field is no longer
    supported.

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
 net/core/filter.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 099ff9fd..7064862 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4448,11 +4448,11 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 					       is_fullsock));
 		break;
 
-/* Helper macro for adding read access to tcp_sock fields. */
-#define SOCK_OPS_GET_TCP(FIELD_NAME)					      \
+/* Helper macro for adding read access to tcp_sock or sock fields. */
+#define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ)			      \
 	do {								      \
-		BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, FIELD_NAME) >      \
-			     FIELD_SIZEOF(struct bpf_sock_ops, FIELD_NAME));  \
+		BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) >		      \
+			     FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD));   \
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
 						struct bpf_sock_ops_kern,     \
 						is_fullsock),		      \
@@ -4464,18 +4464,18 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 						struct bpf_sock_ops_kern, sk),\
 				      si->dst_reg, si->src_reg,		      \
 				      offsetof(struct bpf_sock_ops_kern, sk));\
-		*insn++ = BPF_LDX_MEM(FIELD_SIZEOF(struct tcp_sock,	      \
-						   FIELD_NAME), si->dst_reg,  \
-				      si->dst_reg,			      \
-				      offsetof(struct tcp_sock, FIELD_NAME)); \
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(OBJ,		      \
+						       OBJ_FIELD),	      \
+				      si->dst_reg, si->dst_reg,		      \
+				      offsetof(OBJ, OBJ_FIELD));	      \
 	} while (0)
 
 	case offsetof(struct bpf_sock_ops, snd_cwnd):
-		SOCK_OPS_GET_TCP(snd_cwnd);
+		SOCK_OPS_GET_FIELD(snd_cwnd, snd_cwnd, struct tcp_sock);
 		break;
 
 	case offsetof(struct bpf_sock_ops, srtt_us):
-		SOCK_OPS_GET_TCP(srtt_us);
+		SOCK_OPS_GET_FIELD(srtt_us, srtt_us, struct tcp_sock);
 		break;
 	}
 	return insn - insn_buf;
-- 
2.9.5

[PATCH v3 bpf-next 03/11] bpf: Add write access to tcp_sock and sock fields

[Lawrence Brakmo]

This patch adds a macro, SOCK_OPS_SET_FIELD, for writing to
struct tcp_sock or struct sock fields. This required adding a new
field "temp" to struct bpf_sock_ops_kern for temporary storage that
is used by sock_ops_convert_ctx_access. It is used to store and recover
the contents of a register, so the register can be used to store the
address of the sk. Since we cannot overwrite the dst_reg because it
contains the pointer to ctx, nor the src_reg since it contains the value
we want to store, we need an extra register to contain the address
of the sk.

Also adds the macro SOCK_OPS_GET_OR_SET_FIELD that calls one of the
GET or SET macros depending on the value of the TYPE field.

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
 include/linux/filter.h |  3 +++
 include/net/tcp.h      |  2 +-
 net/core/filter.c      | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 52 insertions(+), 1 deletion(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 2b0df27..2e6e889 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1005,6 +1005,9 @@ struct bpf_sock_ops_kern {
 		u32 replylong[4];
 	};
 	u32	is_fullsock;
+	u64	temp;			/* Used by sock_ops_convert_ctx_access
+					 * as temporary storaage of a register
+					 */
 };
 
 #endif /* __LINUX_FILTER_H__ */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6939e69..108d16a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2010,7 +2010,7 @@ static inline int tcp_call_bpf(struct sock *sk, int op)
 	struct bpf_sock_ops_kern sock_ops;
 	int ret;
 
-	memset(&sock_ops, 0, sizeof(sock_ops));
+	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
 	if (sk_fullsock(sk)) {
 		sock_ops.is_fullsock = 1;
 		sock_owned_by_me(sk);
diff --git a/net/core/filter.c b/net/core/filter.c
index 7064862..978ac78 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4470,6 +4470,54 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 				      offsetof(OBJ, OBJ_FIELD));	      \
 	} while (0)
 
+/* Helper macro for adding write access to tcp_sock or sock fields.
+ * The macro is called with two registers, dst_reg which contains a pointer
+ * to ctx (context) and src_reg which contains the value that should be
+ * stored. However, we need an additional register since we cannot overwrite
+ * dst_reg because it may be used later in the program.
+ * Instead we "borrow" one of the other register. We first save its value
+ * into a new (temp) field in bpf_sock_ops_kern, use it, and then restore
+ * it at the end of the macro.
+ */
+#define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ)			      \
+	do {								      \
+		int reg = BPF_REG_9;					      \
+		BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) >		      \
+			     FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD));   \
+		if (si->dst_reg == reg || si->src_reg == reg)		      \
+			reg--;						      \
+		if (si->dst_reg == reg || si->src_reg == reg)		      \
+			reg--;						      \
+		*insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, reg,		      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+					       temp));			      \
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
+						struct bpf_sock_ops_kern,     \
+						is_fullsock),		      \
+				      reg, si->dst_reg,			      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+					       is_fullsock));		      \
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2);		      \
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
+						struct bpf_sock_ops_kern, sk),\
+				      reg, si->dst_reg,			      \
+				      offsetof(struct bpf_sock_ops_kern, sk));\
+		*insn++ = BPF_STX_MEM(BPF_FIELD_SIZEOF(OBJ, OBJ_FIELD),	      \
+				      reg, si->src_reg,			      \
+				      offsetof(OBJ, OBJ_FIELD));	      \
+		*insn++ = BPF_LDX_MEM(BPF_DW, reg, si->dst_reg,		      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+					       temp));			      \
+	} while (0)
+
+#define SOCK_OPS_GET_OR_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ, TYPE)	      \
+	do {								      \
+		if (TYPE == BPF_WRITE)					      \
+			SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ);	      \
+		else							      \
+			SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ);	      \
+	} while (0)
+
 	case offsetof(struct bpf_sock_ops, snd_cwnd):
 		SOCK_OPS_GET_FIELD(snd_cwnd, snd_cwnd, struct tcp_sock);
 		break;
-- 
2.9.5

[PATCH v3 bpf-next 04/11] bpf: Support passing args to sock_ops bpf function

[Lawrence Brakmo]

Adds support for passing up to 4 arguments to sock_ops bpf functions. It
reusues the reply union, so the bpf_sock_ops structures are not
increased in size.

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
 include/linux/filter.h   |  1 +
 include/net/tcp.h        | 64 ++++++++++++++++++++++++++++++++++++++++++++----
 include/uapi/linux/bpf.h |  5 ++--
 net/ipv4/tcp.c           |  2 +-
 net/ipv4/tcp_nv.c        |  2 +-
 net/ipv4/tcp_output.c    |  2 +-
 6 files changed, 66 insertions(+), 10 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 2e6e889..97f9a02 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1001,6 +1001,7 @@ struct bpf_sock_ops_kern {
 	struct	sock *sk;
 	u32	op;
 	union {
+		u32 args[4];
 		u32 reply;
 		u32 replylong[4];
 	};
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 108d16a..8e9111f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2005,7 +2005,7 @@ void tcp_cleanup_ulp(struct sock *sk);
  * program loaded).
  */
 #ifdef CONFIG_BPF
-static inline int tcp_call_bpf(struct sock *sk, int op)
+static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
 {
 	struct bpf_sock_ops_kern sock_ops;
 	int ret;
@@ -2018,6 +2018,8 @@ static inline int tcp_call_bpf(struct sock *sk, int op)
 
 	sock_ops.sk = sk;
 	sock_ops.op = op;
+	if (nargs > 0)
+		memcpy(sock_ops.args, args, nargs*sizeof(u32));
 
 	ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
 	if (ret == 0)
@@ -2026,18 +2028,70 @@ static inline int tcp_call_bpf(struct sock *sk, int op)
 		ret = -1;
 	return ret;
 }
+
+static inline int tcp_call_bpf_1arg(struct sock *sk, int op, u32 arg)
+{
+	return tcp_call_bpf(sk, op, 1, &arg);
+}
+
+static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2)
+{
+	u32 args[2] = {arg1, arg2};
+
+	return tcp_call_bpf(sk, op, 2, args);
+}
+
+static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+				    u32 arg3)
+{
+	u32 args[3] = {arg1, arg2, arg3};
+
+	return tcp_call_bpf(sk, op, 3, args);
+}
+
+static inline int tcp_call_bpf_4arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+				    u32 arg3, u32 arg4)
+{
+	u32 args[4] = {arg1, arg2, arg3, arg4};
+
+	return tcp_call_bpf(sk, op, 4, args);
+}
+
 #else
-static inline int tcp_call_bpf(struct sock *sk, int op)
+static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
 {
 	return -EPERM;
 }
+
+static inline int tcp_call_bpf_1arg(struct sock *sk, int op, u32 arg)
+{
+	return -EPERM;
+}
+
+static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2)
+{
+	return -EPERM;
+}
+
+static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+	u32 arg3)
+{
+	return -EPERM;
+}
+
+static inline int tcp_call_bpf_4arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+				    u32 arg3, u32 arg4)
+{
+	return -EPERM;
+}
+
 #endif
 
 static inline u32 tcp_timeout_init(struct sock *sk)
 {
 	int timeout;
 
-	timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT);
+	timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT, 0, NULL);
 
 	if (timeout <= 0)
 		timeout = TCP_TIMEOUT_INIT;
@@ -2048,7 +2102,7 @@ static inline u32 tcp_rwnd_init_bpf(struct sock *sk)
 {
 	int rwnd;
 
-	rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT);
+	rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT, 0, NULL);
 
 	if (rwnd < 0)
 		rwnd = 0;
@@ -2057,7 +2111,7 @@ static inline u32 tcp_rwnd_init_bpf(struct sock *sk)
 
 static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk)
 {
-	return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN) == 1);
+	return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1);
 }
 
 #if IS_ENABLED(CONFIG_SMC)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 69eabfc..1fea987 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -942,8 +942,9 @@ struct bpf_map_info {
 struct bpf_sock_ops {
 	__u32 op;
 	union {
-		__u32 reply;
-		__u32 replylong[4];
+		__u32 args[4];		/* Optionally passed to bpf program */
+		__u32 reply;		/* Returned by bpf program	    */
+		__u32 replylong[4];	/* Optionally returned by bpf prog  */
 	};
 	__u32 family;
 	__u32 remote_ip4;	/* Stored in network byte order */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7ac583a..a1fe7a7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -463,7 +463,7 @@ void tcp_init_transfer(struct sock *sk, int bpf_op)
 	tcp_mtup_init(sk);
 	icsk->icsk_af_ops->rebuild_header(sk);
 	tcp_init_metrics(sk);
-	tcp_call_bpf(sk, bpf_op);
+	tcp_call_bpf(sk, bpf_op, 0, NULL);
 	tcp_init_congestion_control(sk);
 	tcp_init_buffer_space(sk);
 }
diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c
index 0b5a05b..ddbce73 100644
--- a/net/ipv4/tcp_nv.c
+++ b/net/ipv4/tcp_nv.c
@@ -146,7 +146,7 @@ static void tcpnv_init(struct sock *sk)
 	 * within a datacenter, where we have reasonable estimates of
 	 * RTTs
 	 */
-	base_rtt = tcp_call_bpf(sk, BPF_SOCK_OPS_BASE_RTT);
+	base_rtt = tcp_call_bpf(sk, BPF_SOCK_OPS_BASE_RTT, 0, NULL);
 	if (base_rtt > 0) {
 		ca->nv_base_rtt = base_rtt;
 		ca->nv_lower_bound_rtt = (base_rtt * 205) >> 8; /* 80% */
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 04be9f83..b093985 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3468,7 +3468,7 @@ int tcp_connect(struct sock *sk)
 	struct sk_buff *buff;
 	int err;
 
-	tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB);
+	tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB, 0, NULL);
 
 	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
 		return -EHOSTUNREACH; /* Routing failure or similar. */
-- 
2.9.5

[PATCH v3 bpf-next 05/11] bpf: Adds field bpf_sock_ops_flags to tcp_sock

[Lawrence Brakmo]

Adds field bpf_sock_ops_flags to tcp_sock and bpf_sock_ops. Its primary
use is to determine if there should be calls to sock_ops bpf program at
various points in the TCP code. The field is initialized to zero,
disabling the calls. A sock_ops BPF program can set, per connection and
as necessary, when the connection is established.

It also adds support for reading and writting the field within a
sock_ops BPF program.

Examples of where to call the bpf program:

1) When RTO fires
2) When a packet is retransmitted
3) When the connection terminates
4) When a packet is sent
5) When a packet is received

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
 include/linux/tcp.h      | 8 ++++++++
 include/uapi/linux/bpf.h | 1 +
 net/core/filter.c        | 7 +++++++
 3 files changed, 16 insertions(+)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 4f93f095..62f4388 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -373,6 +373,14 @@ struct tcp_sock {
 	 */
 	struct request_sock *fastopen_rsk;
 	u32	*saved_syn;
+
+/* Sock_ops bpf program related variables */
+#ifdef CONFIG_BPF
+	u32     bpf_sock_ops_flags;     /* values defined in uapi/linux/tcp.h */
+#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) (TP->bpf_sock_ops_flags & ARG)
+#else
+#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0
+#endif
 };
 
 enum tsq_enum {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 1fea987..62b2c89 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -959,6 +959,7 @@ struct bpf_sock_ops {
 				 */
 	__u32 snd_cwnd;
 	__u32 srtt_us;		/* Averaged RTT << 3 in usecs */
+	__u32 bpf_sock_ops_flags; /* flags defined in uapi/linux/tcp.h */
 };
 
 /* List of known BPF sock_ops operators.
diff --git a/net/core/filter.c b/net/core/filter.c
index 978ac78..76fd6e9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3843,6 +3843,7 @@ static bool sock_ops_is_valid_access(int off, int size,
 		switch (off) {
 		case offsetof(struct bpf_sock_ops, op) ...
 		     offsetof(struct bpf_sock_ops, replylong[3]):
+		case offsetof(struct bpf_sock_ops, bpf_sock_ops_flags):
 			break;
 		default:
 			return false;
@@ -4525,6 +4526,12 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 	case offsetof(struct bpf_sock_ops, srtt_us):
 		SOCK_OPS_GET_FIELD(srtt_us, srtt_us, struct tcp_sock);
 		break;
+
+	case offsetof(struct bpf_sock_ops, bpf_sock_ops_flags):
+		SOCK_OPS_GET_OR_SET_FIELD(bpf_sock_ops_flags,
+					  bpf_sock_ops_flags,
+					  struct tcp_sock, type);
+		break;
 	}
 	return insn - insn_buf;
 }
-- 
2.9.5

[PATCH v3 bpf-next 06/11] bpf: Add sock_ops RTO callback

[Lawrence Brakmo]

Adds an optional call to sock_ops BPF program based on whether the
BPF_SOCK_OPS_RTO_CB_FLAG is set in bpf_sock_ops_flags.
The BPF program is passed 2 arguments: icsk_retransmits and whether the
RTO has expired.

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
 include/uapi/linux/bpf.h | 5 +++++
 include/uapi/linux/tcp.h | 3 +++
 net/ipv4/tcp_timer.c     | 7 +++++++
 3 files changed, 15 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 62b2c89..3cf9014 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -995,6 +995,11 @@ enum {
 					 * a congestion threshold. RTTs above
 					 * this indicate congestion
 					 */
+	BPF_SOCK_OPS_RTO_CB,		/* Called when an RTO has triggered.
+					 * Arg1: value of icsk_retransmits
+					 * Arg2: value of icsk_rto
+					 * Arg3: whether RTO has expired
+					 */
 };
 
 #define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index b4a4f64..089c19e 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -259,6 +259,9 @@ struct tcp_md5sig {
 	__u8	tcpm_key[TCP_MD5SIG_MAXKEYLEN];		/* key (binary) */
 };
 
+/* Definitions for bpf_sock_ops_flags */
+#define BPF_SOCK_OPS_RTO_CB_FLAG	(1<<0)
+
 /* INET_DIAG_MD5SIG */
 struct tcp_diag_md5sig {
 	__u8	tcpm_family;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 6db3124..257abdd 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -213,11 +213,18 @@ static int tcp_write_timeout(struct sock *sk)
 						icsk->icsk_user_timeout);
 	}
 	tcp_fastopen_active_detect_blackhole(sk, expired);
+
+	if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG))
+		tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RTO_CB,
+				  icsk->icsk_retransmits,
+				  icsk->icsk_rto, (int)expired);
+
 	if (expired) {
 		/* Has it gone just too far? */
 		tcp_write_err(sk);
 		return 1;
 	}
+
 	return 0;
 }
 
-- 
2.9.5

[PATCH v3 bpf-next 07/11] bpf: Add support for reading sk_state and more

[Lawrence Brakmo]

Add support for reading many more tcp_sock fields

  state,	same as sk->sk_state
  rtt_min	same as sk->rtt_min.s[0].v (current rtt_min)
  snd_ssthresh
  rcv_nxt
  snd_nxt
  snd_una
  mss_cache
  ecn_flags
  rate_delivered
  rate_interval_us
  packets_out
  retrans_out
  total_retrans
  segs_in
  data_segs_in
  segs_out
  data_segs_out
  bytes_received (__u64)
  bytes_acked    (__u64)

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
 include/uapi/linux/bpf.h |  19 +++++++++
 net/core/filter.c        | 101 ++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 119 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3cf9014..c81fdec 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -960,6 +960,25 @@ struct bpf_sock_ops {
 	__u32 snd_cwnd;
 	__u32 srtt_us;		/* Averaged RTT << 3 in usecs */
 	__u32 bpf_sock_ops_flags; /* flags defined in uapi/linux/tcp.h */
+	__u32 state;
+	__u32 rtt_min;
+	__u32 snd_ssthresh;
+	__u32 rcv_nxt;
+	__u32 snd_nxt;
+	__u32 snd_una;
+	__u32 mss_cache;
+	__u32 ecn_flags;
+	__u32 rate_delivered;
+	__u32 rate_interval_us;
+	__u32 packets_out;
+	__u32 retrans_out;
+	__u32 total_retrans;
+	__u32 segs_in;
+	__u32 data_segs_in;
+	__u32 segs_out;
+	__u32 data_segs_out;
+	__u64 bytes_received;
+	__u64 bytes_acked;
 };
 
 /* List of known BPF sock_ops operators.
diff --git a/net/core/filter.c b/net/core/filter.c
index 76fd6e9..d4c5c1a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3829,7 +3829,7 @@ static bool __is_valid_sock_ops_access(int off, int size)
 	/* The verifier guarantees that size > 0. */
 	if (off % size != 0)
 		return false;
-	if (size != sizeof(__u32))
+	if (size != sizeof(__u32) && size != sizeof(__u64))
 		return false;
 
 	return true;
@@ -4449,6 +4449,32 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 					       is_fullsock));
 		break;
 
+	case offsetof(struct bpf_sock_ops, state):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_state) != 1);
+
+		*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_B, si->dst_reg, si->dst_reg,
+				      offsetof(struct sock_common, skc_state));
+		break;
+
+	case offsetof(struct bpf_sock_ops, rtt_min):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, rtt_min) !=
+			     sizeof(struct minmax));
+		BUILD_BUG_ON(sizeof(struct minmax) <
+			     sizeof(struct minmax_sample));
+
+		*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 tcp_sock, rtt_min) +
+				      FIELD_SIZEOF(struct minmax_sample, t));
+		break;
+
 /* Helper macro for adding read access to tcp_sock or sock fields. */
 #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ)			      \
 	do {								      \
@@ -4532,6 +4558,79 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 					  bpf_sock_ops_flags,
 					  struct tcp_sock, type);
 		break;
+
+	case offsetof(struct bpf_sock_ops, snd_ssthresh):
+		SOCK_OPS_GET_FIELD(snd_ssthresh, snd_ssthresh, struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, rcv_nxt):
+		SOCK_OPS_GET_FIELD(rcv_nxt, rcv_nxt, struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, snd_nxt):
+		SOCK_OPS_GET_FIELD(snd_nxt, snd_nxt, struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, snd_una):
+		SOCK_OPS_GET_FIELD(snd_una, snd_una, struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, mss_cache):
+		SOCK_OPS_GET_FIELD(mss_cache, mss_cache, struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, ecn_flags):
+		SOCK_OPS_GET_FIELD(ecn_flags, ecn_flags, struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, rate_delivered):
+		SOCK_OPS_GET_FIELD(rate_delivered, rate_delivered,
+				   struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, rate_interval_us):
+		SOCK_OPS_GET_FIELD(rate_interval_us, rate_interval_us,
+				   struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, packets_out):
+		SOCK_OPS_GET_FIELD(packets_out, packets_out, struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, retrans_out):
+		SOCK_OPS_GET_FIELD(retrans_out, retrans_out, struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, total_retrans):
+		SOCK_OPS_GET_FIELD(total_retrans, total_retrans,
+				   struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, segs_in):
+		SOCK_OPS_GET_FIELD(segs_in, segs_in, struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, data_segs_in):
+		SOCK_OPS_GET_FIELD(data_segs_in, data_segs_in, struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, segs_out):
+		SOCK_OPS_GET_FIELD(segs_out, segs_out, struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, data_segs_out):
+		SOCK_OPS_GET_FIELD(data_segs_out, data_segs_out,
+				   struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, bytes_received):
+		SOCK_OPS_GET_FIELD(bytes_received, bytes_received,
+				   struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, bytes_acked):
+		SOCK_OPS_GET_FIELD(bytes_acked, bytes_acked, struct tcp_sock);
+		break;
 	}
 	return insn - insn_buf;
 }
-- 
2.9.5

[PATCH v3 bpf-next 08/11] bpf: Add sock_ops R/W access to tclass & sk_txhash

[Lawrence Brakmo]

Adds direct R/W access to sk_txhash and access to tclass for ipv6 flows
through getsockopt and setsockopt. Sample usage for tclass:

  bpf_getsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v, sizeof(v))

where skops is a pointer to the ctx (struct bpf_sock_ops).

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
 include/uapi/linux/bpf.h |  1 +
 net/core/filter.c        | 48 +++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 48 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c81fdec..5bead0e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -979,6 +979,7 @@ struct bpf_sock_ops {
 	__u32 data_segs_out;
 	__u64 bytes_received;
 	__u64 bytes_acked;
+	__u32 sk_txhash;
 };
 
 /* List of known BPF sock_ops operators.
diff --git a/net/core/filter.c b/net/core/filter.c
index d4c5c1a..4d2ff88 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3230,6 +3230,29 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 			ret = -EINVAL;
 		}
 #ifdef CONFIG_INET
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (level == SOL_IPV6) {
+		if (optlen != sizeof(int) || sk->sk_family != AF_INET6)
+			return -EINVAL;
+
+		val = *((int *)optval);
+		/* Only some options are supported */
+		switch (optname) {
+		case IPV6_TCLASS:
+			if (val < -1 || val > 0xff) {
+				ret = -EINVAL;
+			} else {
+				struct ipv6_pinfo *np = inet6_sk(sk);
+
+				if (val == -1)
+					val = 0;
+				np->tclass = val;
+			}
+			break;
+		default:
+			ret = -EINVAL;
+		}
+#endif
 	} else if (level == SOL_TCP &&
 		   sk->sk_prot->setsockopt == tcp_setsockopt) {
 		if (optname == TCP_CONGESTION) {
@@ -3239,7 +3262,8 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 			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, reinit);
+			ret = tcp_set_congestion_control(sk, name, false,
+							 reinit);
 		} else {
 			struct tcp_sock *tp = tcp_sk(sk);
 
@@ -3305,6 +3329,22 @@ BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 		} else {
 			goto err_clear;
 		}
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (level == SOL_IPV6) {
+		struct ipv6_pinfo *np = inet6_sk(sk);
+
+		if (optlen != sizeof(int) || sk->sk_family != AF_INET6)
+			goto err_clear;
+
+		/* Only some options are supported */
+		switch (optname) {
+		case IPV6_TCLASS:
+			*((int *)optval) = (int)np->tclass;
+			break;
+		default:
+			goto err_clear;
+		}
+#endif
 	} else {
 		goto err_clear;
 	}
@@ -3844,6 +3884,7 @@ static bool sock_ops_is_valid_access(int off, int size,
 		case offsetof(struct bpf_sock_ops, op) ...
 		     offsetof(struct bpf_sock_ops, replylong[3]):
 		case offsetof(struct bpf_sock_ops, bpf_sock_ops_flags):
+		case offsetof(struct bpf_sock_ops, sk_txhash):
 			break;
 		default:
 			return false;
@@ -4631,6 +4672,11 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 	case offsetof(struct bpf_sock_ops, bytes_acked):
 		SOCK_OPS_GET_FIELD(bytes_acked, bytes_acked, struct tcp_sock);
 		break;
+
+	case offsetof(struct bpf_sock_ops, sk_txhash):
+		SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash,
+					  struct sock, type);
+		break;
 	}
 	return insn - insn_buf;
 }
-- 
2.9.5

[PATCH v3 bpf-next 09/11] bpf: Add BPF_SOCK_OPS_RETRANS_CB

[Lawrence Brakmo]

Adds support for calling sock_ops BPF program when there is a
retransmission. Two arguments are used; one for the sequence number and
other for the number of segments retransmitted. Does not include syn-ack
retransmissions.

New op: BPF_SOCK_OPS_RETRANS_CB.

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
 include/uapi/linux/bpf.h | 4 ++++
 include/uapi/linux/tcp.h | 1 +
 net/ipv4/tcp_output.c    | 3 +++
 3 files changed, 8 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 5bead0e..415b951 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1020,6 +1020,10 @@ enum {
 					 * Arg2: value of icsk_rto
 					 * Arg3: whether RTO has expired
 					 */
+	BPF_SOCK_OPS_RETRANS_CB,	/* Called when skb is retransmitted.
+					 * Arg1: sequence number of 1st byte
+					 * Arg2: # segments
+					 */
 };
 
 #define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 089c19e..dc36d3c 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -261,6 +261,7 @@ struct tcp_md5sig {
 
 /* Definitions for bpf_sock_ops_flags */
 #define BPF_SOCK_OPS_RTO_CB_FLAG	(1<<0)
+#define BPF_SOCK_OPS_RETRANS_CB_FLAG	(1<<1)
 
 /* INET_DIAG_MD5SIG */
 struct tcp_diag_md5sig {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b093985..8109675 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2907,6 +2907,9 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 	if (likely(!err)) {
 		TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
 		trace_tcp_retransmit_skb(sk, skb);
+		if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG))
+			tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_RETRANS_CB,
+					  TCP_SKB_CB(skb)->seq, segs);
 	} else if (err != -EBUSY) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
 	}
-- 
2.9.5

[PATCH v3 bpf-next 10/11] bpf: Add BPF_SOCK_OPS_STATE_CB

[Lawrence Brakmo]

Adds support for calling sock_ops BPF program when there is a TCP state
change. Two arguments are used; one for the old state and another for
the new state.

There is a new enum in include/uapi/linux/bpf.h that exports the TCP
states that prepends BPF_ to the current TCP state names. If it is ever
necessary to change the internal TCP state values (other than adding
more to the end), then it will become necessary to convert from the
internal TCP state value to the BPF value before calling the BPF
sock_ops function.

New op: BPF_SOCK_OPS_STATE_CB.

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
 include/uapi/linux/bpf.h | 26 ++++++++++++++++++++++++++
 include/uapi/linux/tcp.h |  1 +
 net/ipv4/tcp.c           |  4 ++++
 3 files changed, 31 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 415b951..b653273 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1024,6 +1024,32 @@ enum {
 					 * Arg1: sequence number of 1st byte
 					 * Arg2: # segments
 					 */
+	BPF_SOCK_OPS_STATE_CB,		/* Called when TCP changes state.
+					 * Arg1: old_state
+					 * Arg2: new_state
+					 */
+};
+
+/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
+ * changes between the TCP and BPF versions. Ideally this should never happen.
+ * If it does, we need to add code to convert them before calling
+ * the BPF sock_ops function.
+ */
+enum {
+	BPF_TCP_ESTABLISHED = 1,
+	BPF_TCP_SYN_SENT,
+	BPF_TCP_SYN_RECV,
+	BPF_TCP_FIN_WAIT1,
+	BPF_TCP_FIN_WAIT2,
+	BPF_TCP_TIME_WAIT,
+	BPF_TCP_CLOSE,
+	BPF_TCP_CLOSE_WAIT,
+	BPF_TCP_LAST_ACK,
+	BPF_TCP_LISTEN,
+	BPF_TCP_CLOSING,	/* Now a valid state */
+	BPF_TCP_NEW_SYN_RECV,
+
+	BPF_TCP_MAX_STATES	/* Leave at the end! */
 };
 
 #define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index dc36d3c..211322c 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -262,6 +262,7 @@ struct tcp_md5sig {
 /* Definitions for bpf_sock_ops_flags */
 #define BPF_SOCK_OPS_RTO_CB_FLAG	(1<<0)
 #define BPF_SOCK_OPS_RETRANS_CB_FLAG	(1<<1)
+#define BPF_SOCK_OPS_STATE_CB_FLAG	(1<<2)
 
 /* INET_DIAG_MD5SIG */
 struct tcp_diag_md5sig {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a1fe7a7..b321dfd 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2044,6 +2044,10 @@ void tcp_set_state(struct sock *sk, int state)
 {
 	int oldstate = sk->sk_state;
 
+	BUILD_BUG_ON(BPF_TCP_MAX_STATES != TCP_MAX_STATES);
+	if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_STATE_CB_FLAG))
+		tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_STATE_CB, oldstate, state);
+
 	switch (state) {
 	case TCP_ESTABLISHED:
 		if (oldstate != TCP_ESTABLISHED)
-- 
2.9.5

Re: [PATCH v3 bpf-next 10/11] bpf: Add BPF_SOCK_OPS_STATE_CB

[kbuild test robot]

[-- Attachment #1: Type: text/plain, Size: 3449 bytes --]

Hi Lawrence,

Thank you for the patch! Perhaps something to improve:

[auto build test WARNING on net-next/master]
[also build test WARNING on next-20171222]
[cannot apply to bpf-next/master linus/master net/master v4.15-rc6]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/Lawrence-Brakmo/bpf-More-sock_ops-callbacks/20180102-111550
config: x86_64-randconfig-x007-201800 (attached as .config)
compiler: gcc-7 (Debian 7.2.0-12) 7.2.1 20171025
reproduce:
        # save the attached .config to linux build tree
        make ARCH=x86_64 

All warnings (new ones prefixed by >>):

   In file included from arch/x86/include/asm/atomic.h:5:0,
                    from include/linux/atomic.h:5,
                    from include/linux/crypto.h:20,
                    from include/crypto/hash.h:16,
                    from net//ipv4/tcp.c:250:
   net//ipv4/tcp.c: In function 'tcp_set_state':
>> net//ipv4/tcp.c:2041:34: warning: comparison between 'enum <anonymous>' and 'enum <anonymous>' [-Wenum-compare]
     BUILD_BUG_ON(BPF_TCP_MAX_STATES != TCP_MAX_STATES);
                                     ^
   include/linux/compiler.h:301:19: note: in definition of macro '__compiletime_assert'
      bool __cond = !(condition);    \
                      ^~~~~~~~~
   include/linux/compiler.h:324:2: note: in expansion of macro '_compiletime_assert'
     _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
     ^~~~~~~~~~~~~~~~~~~
   include/linux/build_bug.h:47:37: note: in expansion of macro 'compiletime_assert'
    #define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
                                        ^~~~~~~~~~~~~~~~~~
   include/linux/build_bug.h:71:2: note: in expansion of macro 'BUILD_BUG_ON_MSG'
     BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition)
     ^~~~~~~~~~~~~~~~
>> net//ipv4/tcp.c:2041:2: note: in expansion of macro 'BUILD_BUG_ON'
     BUILD_BUG_ON(BPF_TCP_MAX_STATES != TCP_MAX_STATES);
     ^~~~~~~~~~~~

vim +/BUILD_BUG_ON +2041 net//ipv4/tcp.c

  2036	
  2037	void tcp_set_state(struct sock *sk, int state)
  2038	{
  2039		int oldstate = sk->sk_state;
  2040	
> 2041		BUILD_BUG_ON(BPF_TCP_MAX_STATES != TCP_MAX_STATES);
  2042		if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_STATE_CB_FLAG))
  2043			tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_STATE_CB, oldstate, state);
  2044	
  2045		switch (state) {
  2046		case TCP_ESTABLISHED:
  2047			if (oldstate != TCP_ESTABLISHED)
  2048				TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
  2049			break;
  2050	
  2051		case TCP_CLOSE:
  2052			if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED)
  2053				TCP_INC_STATS(sock_net(sk), TCP_MIB_ESTABRESETS);
  2054	
  2055			sk->sk_prot->unhash(sk);
  2056			if (inet_csk(sk)->icsk_bind_hash &&
  2057			    !(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
  2058				inet_put_port(sk);
  2059			/* fall through */
  2060		default:
  2061			if (oldstate == TCP_ESTABLISHED)
  2062				TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
  2063		}
  2064	
  2065		/* Change state AFTER socket is unhashed to avoid closed
  2066		 * socket sitting in hash tables.
  2067		 */
  2068		inet_sk_state_store(sk, state);
  2069	

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation

[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 31602 bytes --]

Re: [PATCH v3 bpf-next 10/11] bpf: Add BPF_SOCK_OPS_STATE_CB

[Lawrence Brakmo]

We created a new enum to allow different TCP state names between the kernel and BPF sock_ops programs. Since we want to catch changes in the original enum, we are comparing the values of the last entries of the enum types (which is triggering the warning). 

On 1/1/18, 8:02 PM, "kbuild test robot" <lkp@intel.com> wrote:

    Hi Lawrence,
    
    Thank you for the patch! Perhaps something to improve:
    
    [auto build test WARNING on net-next/master]
    [also build test WARNING on next-20171222]
    [cannot apply to bpf-next/master linus/master net/master v4.15-rc6]
    [if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
    
    url:    https://github.com/0day-ci/linux/commits/Lawrence-Brakmo/bpf-More-sock_ops-callbacks/20180102-111550
    config: x86_64-randconfig-x007-201800 (attached as .config)
    compiler: gcc-7 (Debian 7.2.0-12) 7.2.1 20171025
    reproduce:
            # save the attached .config to linux build tree
            make ARCH=x86_64 
    
    All warnings (new ones prefixed by >>):
    
       In file included from arch/x86/include/asm/atomic.h:5:0,
                        from include/linux/atomic.h:5,
                        from include/linux/crypto.h:20,
                        from include/crypto/hash.h:16,
                        from net//ipv4/tcp.c:250:
       net//ipv4/tcp.c: In function 'tcp_set_state':
    >> net//ipv4/tcp.c:2041:34: warning: comparison between 'enum <anonymous>' and 'enum <anonymous>' [-Wenum-compare]
         BUILD_BUG_ON(BPF_TCP_MAX_STATES != TCP_MAX_STATES);
                                         ^
       include/linux/compiler.h:301:19: note: in definition of macro '__compiletime_assert'
          bool __cond = !(condition);    \
                          ^~~~~~~~~
       include/linux/compiler.h:324:2: note: in expansion of macro '_compiletime_assert'
         _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
         ^~~~~~~~~~~~~~~~~~~
       include/linux/build_bug.h:47:37: note: in expansion of macro 'compiletime_assert'
        #define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
                                            ^~~~~~~~~~~~~~~~~~
       include/linux/build_bug.h:71:2: note: in expansion of macro 'BUILD_BUG_ON_MSG'
         BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition)
         ^~~~~~~~~~~~~~~~
    >> net//ipv4/tcp.c:2041:2: note: in expansion of macro 'BUILD_BUG_ON'
         BUILD_BUG_ON(BPF_TCP_MAX_STATES != TCP_MAX_STATES);
         ^~~~~~~~~~~~
    
    vim +/BUILD_BUG_ON +2041 net//ipv4/tcp.c
    
      2036	
      2037	void tcp_set_state(struct sock *sk, int state)
      2038	{
      2039		int oldstate = sk->sk_state;
      2040	
    > 2041		BUILD_BUG_ON(BPF_TCP_MAX_STATES != TCP_MAX_STATES);
      2042		if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_STATE_CB_FLAG))
      2043			tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_STATE_CB, oldstate, state);
      2044	
      2045		switch (state) {
      2046		case TCP_ESTABLISHED:
      2047			if (oldstate != TCP_ESTABLISHED)
      2048				TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
      2049			break;
      2050	
      2051		case TCP_CLOSE:
      2052			if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED)
      2053				TCP_INC_STATS(sock_net(sk), TCP_MIB_ESTABRESETS);
      2054	
      2055			sk->sk_prot->unhash(sk);
      2056			if (inet_csk(sk)->icsk_bind_hash &&
      2057			    !(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
      2058				inet_put_port(sk);
      2059			/* fall through */
      2060		default:
      2061			if (oldstate == TCP_ESTABLISHED)
      2062				TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
      2063		}
      2064	
      2065		/* Change state AFTER socket is unhashed to avoid closed
      2066		 * socket sitting in hash tables.
      2067		 */
      2068		inet_sk_state_store(sk, state);
      2069	
    
    ---
    0-DAY kernel test infrastructure                Open Source Technology Center
    https://urldefense.proofpoint.com/v2/url?u=https-3A__lists.01.org_pipermail_kbuild-2Dall&d=DwIBAg&c=5VD0RTtNlTh3ycd41b3MUw&r=pq_Mqvzfy-C8ltkgyx1u_g&m=Q7DgPe3X_jy4GHXyZsGUWwNoAYwdvyKbdsSNwopo4LA&s=hDQMCMBEVY9MOxG2fIWSCTeKMAmXhkbFc6batWKJgBg&e=                   Intel Corporation
    

[PATCH v3 bpf-next 11/11] bpf: add selftest for tcpbpf

[Lawrence Brakmo]

Added a selftest for tcpbpf (sock_ops) that checks that the appropriate
callbacks occured and that it can access tcp_sock fields and that their
values are correct.

Run with command: ./test_tcpbpf_user

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
 tools/include/uapi/linux/bpf.h                 |  70 +++++++++++++-
 tools/testing/selftests/bpf/Makefile           |   4 +-
 tools/testing/selftests/bpf/tcp_client.py      |  52 ++++++++++
 tools/testing/selftests/bpf/tcp_server.py      |  79 ++++++++++++++++
 tools/testing/selftests/bpf/test_tcpbpf_kern.c | 125 +++++++++++++++++++++++++
 tools/testing/selftests/bpf/test_tcpbpf_user.c | 113 ++++++++++++++++++++++
 6 files changed, 438 insertions(+), 5 deletions(-)
 create mode 100755 tools/testing/selftests/bpf/tcp_client.py
 create mode 100755 tools/testing/selftests/bpf/tcp_server.py
 create mode 100644 tools/testing/selftests/bpf/test_tcpbpf_kern.c
 create mode 100644 tools/testing/selftests/bpf/test_tcpbpf_user.c

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index db1b092..b653273 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -942,8 +942,9 @@ struct bpf_map_info {
 struct bpf_sock_ops {
 	__u32 op;
 	union {
-		__u32 reply;
-		__u32 replylong[4];
+		__u32 args[4];		/* Optionally passed to bpf program */
+		__u32 reply;		/* Returned by bpf program	    */
+		__u32 replylong[4];	/* Optionally returned by bpf prog  */
 	};
 	__u32 family;
 	__u32 remote_ip4;	/* Stored in network byte order */
@@ -952,6 +953,33 @@ struct bpf_sock_ops {
 	__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 */
+	__u32 is_fullsock;	/* Some TCP fields are only valid if
+				 * there is a full socket. If not, the
+				 * fields read as zero.
+				 */
+	__u32 snd_cwnd;
+	__u32 srtt_us;		/* Averaged RTT << 3 in usecs */
+	__u32 bpf_sock_ops_flags; /* flags defined in uapi/linux/tcp.h */
+	__u32 state;
+	__u32 rtt_min;
+	__u32 snd_ssthresh;
+	__u32 rcv_nxt;
+	__u32 snd_nxt;
+	__u32 snd_una;
+	__u32 mss_cache;
+	__u32 ecn_flags;
+	__u32 rate_delivered;
+	__u32 rate_interval_us;
+	__u32 packets_out;
+	__u32 retrans_out;
+	__u32 total_retrans;
+	__u32 segs_in;
+	__u32 data_segs_in;
+	__u32 segs_out;
+	__u32 data_segs_out;
+	__u64 bytes_received;
+	__u64 bytes_acked;
+	__u32 sk_txhash;
 };
 
 /* List of known BPF sock_ops operators.
@@ -987,6 +1015,41 @@ enum {
 					 * a congestion threshold. RTTs above
 					 * this indicate congestion
 					 */
+	BPF_SOCK_OPS_RTO_CB,		/* Called when an RTO has triggered.
+					 * Arg1: value of icsk_retransmits
+					 * Arg2: value of icsk_rto
+					 * Arg3: whether RTO has expired
+					 */
+	BPF_SOCK_OPS_RETRANS_CB,	/* Called when skb is retransmitted.
+					 * Arg1: sequence number of 1st byte
+					 * Arg2: # segments
+					 */
+	BPF_SOCK_OPS_STATE_CB,		/* Called when TCP changes state.
+					 * Arg1: old_state
+					 * Arg2: new_state
+					 */
+};
+
+/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
+ * changes between the TCP and BPF versions. Ideally this should never happen.
+ * If it does, we need to add code to convert them before calling
+ * the BPF sock_ops function.
+ */
+enum {
+	BPF_TCP_ESTABLISHED = 1,
+	BPF_TCP_SYN_SENT,
+	BPF_TCP_SYN_RECV,
+	BPF_TCP_FIN_WAIT1,
+	BPF_TCP_FIN_WAIT2,
+	BPF_TCP_TIME_WAIT,
+	BPF_TCP_CLOSE,
+	BPF_TCP_CLOSE_WAIT,
+	BPF_TCP_LAST_ACK,
+	BPF_TCP_LISTEN,
+	BPF_TCP_CLOSING,	/* Now a valid state */
+	BPF_TCP_NEW_SYN_RECV,
+
+	BPF_TCP_MAX_STATES	/* Leave at the end! */
 };
 
 #define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
@@ -1006,7 +1069,8 @@ struct bpf_perf_event_value {
 #define BPF_DEVCG_DEV_CHAR	(1ULL << 1)
 
 struct bpf_cgroup_dev_ctx {
-	__u32 access_type; /* (access << 16) | type */
+	/* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */
+	__u32 access_type;
 	__u32 major;
 	__u32 minor;
 };
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 1304753..8e032a2 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -14,12 +14,12 @@ CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../i
 LDLIBS += -lcap -lelf -lrt
 
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
-	test_align test_verifier_log test_dev_cgroup
+	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
 	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
 	sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \
-	test_l4lb_noinline.o test_xdp_noinline.o
+	test_l4lb_noinline.o test_xdp_noinline.o test_tcpbpf_kern.o
 
 TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \
 	test_offload.py
diff --git a/tools/testing/selftests/bpf/tcp_client.py b/tools/testing/selftests/bpf/tcp_client.py
new file mode 100755
index 0000000..ac2ce32
--- /dev/null
+++ b/tools/testing/selftests/bpf/tcp_client.py
@@ -0,0 +1,52 @@
+#!/usr/local/bin/python
+#
+# SPDX-License-Identifier: GPL-2.0
+#
+
+import sys, os, os.path, getopt
+import socket, time
+import subprocess
+import select
+
+def read(sock, n):
+    buf = ''
+    while len(buf) < n:
+        rem = n - len(buf)
+        try: s = sock.recv(rem)
+        except (socket.error), e: return ''
+        buf += s
+    return buf
+
+def send(sock, s):
+    total = len(s)
+    count = 0
+    while count < total:
+        try: n = sock.send(s)
+        except (socket.error), e: n = 0
+        if n == 0:
+            return count;
+        count += n
+    return count
+
+
+serverPort = int(sys.argv[1])
+HostName = socket.gethostname()
+
+time.sleep(1)
+
+# create active socket
+sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
+try:
+    sock.connect((HostName, serverPort))
+except socket.error as e:
+    sys.exit(1)
+
+buf = ''
+n = 0
+while n < 1000:
+    buf += '+'
+    n += 1
+
+n = send(sock, buf)
+n = read(sock, 500)
+sys.exit(0)
diff --git a/tools/testing/selftests/bpf/tcp_server.py b/tools/testing/selftests/bpf/tcp_server.py
new file mode 100755
index 0000000..9e5db0d
--- /dev/null
+++ b/tools/testing/selftests/bpf/tcp_server.py
@@ -0,0 +1,79 @@
+#!/usr/local/bin/python
+#
+# SPDX-License-Identifier: GPL-2.0
+#
+
+import sys, os, os.path, getopt
+import socket, time
+import subprocess
+import select
+
+def read(sock, n):
+    buf = ''
+    while len(buf) < n:
+        rem = n - len(buf)
+        try: s = sock.recv(rem)
+        except (socket.error), e: return ''
+        buf += s
+    return buf
+
+def send(sock, s):
+    total = len(s)
+    count = 0
+    while count < total:
+        try: n = sock.send(s)
+        except (socket.error), e: n = 0
+        if n == 0:
+            return count;
+        count += n
+    return count
+
+
+SERVER_PORT = 12877
+MAX_PORTS = 2
+
+serverPort = SERVER_PORT
+serverSocket = None
+
+HostName = socket.gethostname()
+
+# create passive socket
+serverSocket = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
+host = socket.gethostname()
+
+while serverPort < SERVER_PORT + 5:
+	try: serverSocket.bind((host, serverPort))
+	except socket.error as msg:
+            serverPort += 1
+            continue
+	break
+
+cmdStr = ("./tcp_client.py %d &") % (serverPort)
+os.system(cmdStr)
+
+buf = ''
+n = 0
+while n < 500:
+    buf += '.'
+    n += 1
+
+serverSocket.listen(MAX_PORTS)
+readList = [serverSocket]
+
+while True:
+    readyRead, readyWrite, inError = \
+        select.select(readList, [], [], 10)
+
+    if len(readyRead) > 0:
+        waitCount = 0
+        for sock in readyRead:
+            if sock == serverSocket:
+                (clientSocket, address) = serverSocket.accept()
+                address = str(address[0])
+                readList.append(clientSocket)
+            else:
+                s = read(sock, 1000)
+                n = send(sock, buf)
+                sock.close()
+                time.sleep(1)
+                sys.exit(0)
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
new file mode 100644
index 0000000..0fa7429
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/in6.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <netinet/in.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+struct globals {
+	__u32 event_map;
+	__u32 total_retrans;
+	__u32 data_segs_in;
+	__u32 data_segs_out;
+	__u64 bytes_received;
+	__u64 bytes_acked;
+};
+
+struct bpf_map_def SEC("maps") global_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct globals),
+	.max_entries = 2,
+};
+
+static inline void update_event_map(int event)
+{
+	__u32 key = 0;
+	struct globals g, *gp;
+
+	gp = bpf_map_lookup_elem(&global_map, &key);
+	if (gp == NULL) {
+		struct globals g = {0, 0, 0, 0, 0, 0};
+
+		g.event_map |= (1 << event);
+		bpf_map_update_elem(&global_map, &key, &g,
+			    BPF_ANY);
+	} else {
+		g = *gp;
+		g.event_map |= (1 << event);
+		bpf_map_update_elem(&global_map, &key, &g,
+			    BPF_ANY);
+	}
+}
+
+int _version SEC("version") = 1;
+
+SEC("sockops")
+int bpf_testcb(struct bpf_sock_ops *skops)
+{
+	int rv = -1;
+	int op;
+	int init_seq = 0;
+	int ret = 0;
+	int v = 0;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if remote port number is in the range 12877..12887
+	 * I.e. the active side of the connection
+	 */
+	if ((bpf_ntohl(skops->remote_port) < 12877 ||
+	     bpf_ntohl(skops->remote_port) >= 12887)) {
+		skops->reply = -1;
+		return 1;
+	}
+
+	op = (int) skops->op;
+
+	/* 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 (1) {
+		update_event_map(op);
+
+		switch (op) {
+		case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+			skops->bpf_sock_ops_flags = 0xfff;
+			init_seq = skops->snd_nxt;
+			break;
+		case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+			init_seq = skops->snd_nxt;
+			skops->bpf_sock_ops_flags = 0xfff;
+			skops->sk_txhash = 0x12345f;
+			v = 0xff;
+			ret = bpf_setsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v,
+					     sizeof(v));
+			break;
+		case BPF_SOCK_OPS_RTO_CB:
+			break;
+		case BPF_SOCK_OPS_RETRANS_CB:
+			break;
+		case BPF_SOCK_OPS_STATE_CB:
+			if (skops->args[1] == BPF_TCP_CLOSE) {
+				__u32 key = 0;
+				struct globals g, *gp;
+
+				gp = bpf_map_lookup_elem(&global_map, &key);
+				if (!gp)
+					break;
+				g = *gp;
+				g.total_retrans = skops->total_retrans;
+				g.data_segs_in = skops->data_segs_in;
+				g.data_segs_out = skops->data_segs_out;
+				g.bytes_received = skops->bytes_received;
+				g.bytes_acked = skops->bytes_acked;
+				bpf_map_update_elem(&global_map, &key, &g,
+						    BPF_ANY);
+			}
+			break;
+		default:
+			rv = -1;
+		}
+	} else {
+		rv = -1;
+	}
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
new file mode 100644
index 0000000..38665ea
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <errno.h>
+#include <signal.h>
+#include <string.h>
+#include <assert.h>
+#include <linux/perf_event.h>
+#include <linux/ptrace.h>
+#include <linux/bpf.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "bpf_util.h"
+#include <linux/perf_event.h>
+
+struct globals {
+	__u32 event_map;
+	__u32 total_retrans;
+	__u32 data_segs_in;
+	__u32 data_segs_out;
+	__u64 bytes_received;
+	__u64 bytes_acked;
+};
+
+static int bpf_find_map(const char *test, struct bpf_object *obj,
+			const char *name)
+{
+	struct bpf_map *map;
+
+	map = bpf_object__find_map_by_name(obj, name);
+	if (!map) {
+		printf("%s:FAIL:map '%s' not found\n", test, name);
+		return -1;
+	}
+	return bpf_map__fd(map);
+}
+
+#define SYSTEM(CMD)						\
+	do {							\
+		if (system(CMD)) {				\
+			printf("system(%s) FAILS!\n", CMD);	\
+		}						\
+	} while (0)
+
+int main(int argc, char **argv)
+{
+	struct globals g = {0, 0, 0, 0, 0, 0};
+	__u32 key = 0;
+	int rv;
+	int pid;
+	int error = EXIT_FAILURE;
+	int cg_fd, prog_fd, map_fd;
+	char cmd[100], *dir;
+	const char *file = "test_tcpbpf_kern.o";
+	struct bpf_object *obj;
+	struct stat buffer;
+
+	dir = "/tmp/cgroupv2/foo";
+
+	if (stat(dir, &buffer) != 0) {
+		SYSTEM("mkdir -p /tmp/cgroupv2");
+		SYSTEM("mount -t cgroup2 none /tmp/cgroupv2");
+		SYSTEM("mkdir -p /tmp/cgroupv2/foo");
+	}
+	pid = (int) getpid();
+	sprintf(cmd, "echo %d >> /tmp/cgroupv2/foo/cgroup.procs", pid);
+	SYSTEM(cmd);
+
+	cg_fd = open(dir, O_DIRECTORY, O_RDONLY);
+	if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
+//	if (load_bpf_file(prog)) {
+		printf("FAILED: load_bpf_file failed for: %s\n", file);
+//		printf("%s", bpf_log_buf);
+		goto err;
+	}
+
+	rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+	if (rv) {
+		printf("FAILED: bpf_prog_attach: %d (%s)\n",
+		       error, strerror(errno));
+		goto err;
+	}
+
+	SYSTEM("./tcp_server.py");
+
+	map_fd = bpf_find_map(__func__, obj, "global_map");
+	if (map_fd < 0)
+		goto err;
+
+	rv = bpf_map_lookup_elem(map_fd, &key, &g);
+	if (rv != 0) {
+		printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
+		goto err;
+	}
+
+	if (g.bytes_received != 501 || g.bytes_acked != 1002 ||
+	    g.data_segs_in != 1 || g.data_segs_out != 1 ||
+		g.event_map != 0x45e) {
+		printf("FAILED: Wrong stats\n");
+		goto err;
+	}
+	printf("PASSED!\n");
+	error = 0;
+err:
+	bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+	return error;
+}
-- 
2.9.5