bpf: selftests: Tcp header options

This patch adds tests for the new bpf tcp header option feature.

test_tcp_hdr_options.c:
- It tests header option writing and parsing in 3WHS: regular
  connection establishment, fastopen, and syncookie.
- In syncookie, the passive side's bpf prog is asking the active side
  to resend its bpf header option by specifying a RESEND bit in the
  outgoing SYNACK. handle_active_estab() and write_nodata_opt() has
  some details.
- handle_passive_estab() has comments on fastopen.
- It also has test for header writing and parsing in FIN packet.
- Most of the tests is writing an experimental option 254 with magic 0xeB9F.
- The no_exprm_estab() also tests writing a regular TCP option
  without any magic.

test_misc_tcp_options.c:
- It is an one directional test.  Active side writes option and
  passive side parses option.  The focus is to exercise
  the new helpers and API.
- Testing the new helper: bpf_load_hdr_opt() and bpf_store_hdr_opt().
- Testing the bpf_getsockopt(TCP_BPF_SYN).
- Negative tests for the above helpers.
- Testing the sock_ops->skb_data.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200820190117.2886749-1-kafai@fb.com

tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <stddef.h>
+#include <errno.h>
+#include <stdbool.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/socket.h>
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#define BPF_PROG_TEST_TCP_HDR_OPTIONS
+#include "test_tcp_hdr_options.h"
+
+__u16 last_addr16_n = __bpf_htons(0xeB9F);
+__u16 active_lport_n = 0;
+__u16 active_lport_h = 0;
+__u16 passive_lport_n = 0;
+__u16 passive_lport_h = 0;
+
+/* options received at passive side */
+unsigned int nr_pure_ack = 0;
+unsigned int nr_data = 0;
+unsigned int nr_syn = 0;
+unsigned int nr_fin = 0;
+
+/* Check the header received from the active side */
+static int __check_active_hdr_in(struct bpf_sock_ops *skops, bool check_syn)
+{
+	union {
+		struct tcphdr th;
+		struct ipv6hdr ip6;
+		struct tcp_exprm_opt exprm_opt;
+		struct tcp_opt reg_opt;
+		__u8 data[100]; /* IPv6 (40) + Max TCP hdr (60) */
+	} hdr = {};
+	__u64 load_flags = check_syn ? BPF_LOAD_HDR_OPT_TCP_SYN : 0;
+	struct tcphdr *pth;
+	int ret;
+
+	hdr.reg_opt.kind = 0xB9;
+
+	/* The option is 4 bytes long instead of 2 bytes */
+	ret = bpf_load_hdr_opt(skops, &hdr.reg_opt, 2, load_flags);
+	if (ret != -ENOSPC)
+		RET_CG_ERR(ret);
+
+	/* Test searching magic with regular kind */
+	hdr.reg_opt.len = 4;
+	ret = bpf_load_hdr_opt(skops, &hdr.reg_opt, sizeof(hdr.reg_opt),
+			       load_flags);
+	if (ret != -EINVAL)
+		RET_CG_ERR(ret);
+
+	hdr.reg_opt.len = 0;
+	ret = bpf_load_hdr_opt(skops, &hdr.reg_opt, sizeof(hdr.reg_opt),
+			       load_flags);
+	if (ret != 4 || hdr.reg_opt.len != 4 || hdr.reg_opt.kind != 0xB9 ||
+	    hdr.reg_opt.data[0] != 0xfa || hdr.reg_opt.data[1] != 0xce)
+		RET_CG_ERR(ret);
+
+	/* Test searching experimental option with invalid kind length */
+	hdr.exprm_opt.kind = TCPOPT_EXP;
+	hdr.exprm_opt.len = 5;
+	hdr.exprm_opt.magic = 0;
+	ret = bpf_load_hdr_opt(skops, &hdr.exprm_opt, sizeof(hdr.exprm_opt),
+			       load_flags);
+	if (ret != -EINVAL)
+		RET_CG_ERR(ret);
+
+	/* Test searching experimental option with 0 magic value */
+	hdr.exprm_opt.len = 4;
+	ret = bpf_load_hdr_opt(skops, &hdr.exprm_opt, sizeof(hdr.exprm_opt),
+			       load_flags);
+	if (ret != -ENOMSG)
+		RET_CG_ERR(ret);
+
+	hdr.exprm_opt.magic = __bpf_htons(0xeB9F);
+	ret = bpf_load_hdr_opt(skops, &hdr.exprm_opt, sizeof(hdr.exprm_opt),
+			       load_flags);
+	if (ret != 4 || hdr.exprm_opt.len != 4 ||
+	    hdr.exprm_opt.kind != TCPOPT_EXP ||
+	    hdr.exprm_opt.magic != __bpf_htons(0xeB9F))
+		RET_CG_ERR(ret);
+
+	if (!check_syn)
+		return CG_OK;
+
+	/* Test loading from skops->syn_skb if sk_state == TCP_NEW_SYN_RECV
+	 *
+	 * Test loading from tp->saved_syn for other sk_state.
+	 */
+	ret = bpf_getsockopt(skops, SOL_TCP, TCP_BPF_SYN_IP, &hdr.ip6,
+			     sizeof(hdr.ip6));
+	if (ret != -ENOSPC)
+		RET_CG_ERR(ret);
+
+	if (hdr.ip6.saddr.s6_addr16[7] != last_addr16_n ||
+	    hdr.ip6.daddr.s6_addr16[7] != last_addr16_n)
+		RET_CG_ERR(0);
+
+	ret = bpf_getsockopt(skops, SOL_TCP, TCP_BPF_SYN_IP, &hdr, sizeof(hdr));
+	if (ret < 0)
+		RET_CG_ERR(ret);
+
+	pth = (struct tcphdr *)(&hdr.ip6 + 1);
+	if (pth->dest != passive_lport_n || pth->source != active_lport_n)
+		RET_CG_ERR(0);
+
+	ret = bpf_getsockopt(skops, SOL_TCP, TCP_BPF_SYN, &hdr, sizeof(hdr));
+	if (ret < 0)
+		RET_CG_ERR(ret);
+
+	if (hdr.th.dest != passive_lport_n || hdr.th.source != active_lport_n)
+		RET_CG_ERR(0);
+
+	return CG_OK;
+}
+
+static int check_active_syn_in(struct bpf_sock_ops *skops)
+{
+	return __check_active_hdr_in(skops, true);
+}
+
+static int check_active_hdr_in(struct bpf_sock_ops *skops)
+{
+	struct tcphdr *th;
+
+	if (__check_active_hdr_in(skops, false) == CG_ERR)
+		return CG_ERR;
+
+	th = skops->skb_data;
+	if (th + 1 > skops->skb_data_end)
+		RET_CG_ERR(0);
+
+	if (tcp_hdrlen(th) < skops->skb_len)
+		nr_data++;
+
+	if (th->fin)
+		nr_fin++;
+
+	if (th->ack && !th->fin && tcp_hdrlen(th) == skops->skb_len)
+		nr_pure_ack++;
+
+	return CG_OK;
+}
+
+static int active_opt_len(struct bpf_sock_ops *skops)
+{
+	int err;
+
+	/* Reserve more than enough to allow the -EEXIST test in
+	 * the write_active_opt().
+	 */
+	err = bpf_reserve_hdr_opt(skops, 12, 0);
+	if (err)
+		RET_CG_ERR(err);
+
+	return CG_OK;
+}
+
+static int write_active_opt(struct bpf_sock_ops *skops)
+{
+	struct tcp_exprm_opt exprm_opt = {};
+	struct tcp_opt win_scale_opt = {};
+	struct tcp_opt reg_opt = {};
+	struct tcphdr *th;
+	int err, ret;
+
+	exprm_opt.kind = TCPOPT_EXP;
+	exprm_opt.len = 4;
+	exprm_opt.magic = __bpf_htons(0xeB9F);
+
+	reg_opt.kind = 0xB9;
+	reg_opt.len = 4;
+	reg_opt.data[0] = 0xfa;
+	reg_opt.data[1] = 0xce;
+
+	win_scale_opt.kind = TCPOPT_WINDOW;
+
+	err = bpf_store_hdr_opt(skops, &exprm_opt, sizeof(exprm_opt), 0);
+	if (err)
+		RET_CG_ERR(err);
+
+	/* Store the same exprm option */
+	err = bpf_store_hdr_opt(skops, &exprm_opt, sizeof(exprm_opt), 0);
+	if (err != -EEXIST)
+		RET_CG_ERR(err);
+
+	err = bpf_store_hdr_opt(skops, &reg_opt, sizeof(reg_opt), 0);
+	if (err)
+		RET_CG_ERR(err);
+	err = bpf_store_hdr_opt(skops, &reg_opt, sizeof(reg_opt), 0);
+	if (err != -EEXIST)
+		RET_CG_ERR(err);
+
+	/* Check the option has been written and can be searched */
+	ret = bpf_load_hdr_opt(skops, &exprm_opt, sizeof(exprm_opt), 0);
+	if (ret != 4 || exprm_opt.len != 4 || exprm_opt.kind != TCPOPT_EXP ||
+	    exprm_opt.magic != __bpf_htons(0xeB9F))
+		RET_CG_ERR(ret);
+
+	reg_opt.len = 0;
+	ret = bpf_load_hdr_opt(skops, &reg_opt, sizeof(reg_opt), 0);
+	if (ret != 4 || reg_opt.len != 4 || reg_opt.kind != 0xB9 ||
+	    reg_opt.data[0] != 0xfa || reg_opt.data[1] != 0xce)
+		RET_CG_ERR(ret);
+
+	th = skops->skb_data;
+	if (th + 1 > skops->skb_data_end)
+		RET_CG_ERR(0);
+
+	if (th->syn) {
+		active_lport_h = skops->local_port;
+		active_lport_n = th->source;
+
+		/* Search the win scale option written by kernel
+		 * in the SYN packet.
+		 */
+		ret = bpf_load_hdr_opt(skops, &win_scale_opt,
+				       sizeof(win_scale_opt), 0);
+		if (ret != 3 || win_scale_opt.len != 3 ||
+		    win_scale_opt.kind != TCPOPT_WINDOW)
+			RET_CG_ERR(ret);
+
+		/* Write the win scale option that kernel
+		 * has already written.
+		 */
+		err = bpf_store_hdr_opt(skops, &win_scale_opt,
+					sizeof(win_scale_opt), 0);
+		if (err != -EEXIST)
+			RET_CG_ERR(err);
+	}
+
+	return CG_OK;
+}
+
+static int handle_hdr_opt_len(struct bpf_sock_ops *skops)
+{
+	__u8 tcp_flags = skops_tcp_flags(skops);
+
+	if ((tcp_flags & TCPHDR_SYNACK) == TCPHDR_SYNACK)
+		/* Check the SYN from bpf_sock_ops_kern->syn_skb */
+		return check_active_syn_in(skops);
+
+	/* Passive side should have cleared the write hdr cb by now */
+	if (skops->local_port == passive_lport_h)
+		RET_CG_ERR(0);
+
+	return active_opt_len(skops);
+}
+
+static int handle_write_hdr_opt(struct bpf_sock_ops *skops)
+{
+	if (skops->local_port == passive_lport_h)
+		RET_CG_ERR(0);
+
+	return write_active_opt(skops);
+}
+
+static int handle_parse_hdr(struct bpf_sock_ops *skops)
+{
+	/* Passive side is not writing any non-standard/unknown
+	 * option, so the active side should never be called.
+	 */
+	if (skops->local_port == active_lport_h)
+		RET_CG_ERR(0);
+
+	return check_active_hdr_in(skops);
+}
+
+static int handle_passive_estab(struct bpf_sock_ops *skops)
+{
+	int err;
+
+	/* No more write hdr cb */
+	bpf_sock_ops_cb_flags_set(skops,
+				  skops->bpf_sock_ops_cb_flags &
+				  ~BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG);
+
+	/* Recheck the SYN but check the tp->saved_syn this time */
+	err = check_active_syn_in(skops);
+	if (err == CG_ERR)
+		return err;
+
+	nr_syn++;
+
+	/* The ack has header option written by the active side also */
+	return check_active_hdr_in(skops);
+}
+
+SEC("sockops/misc_estab")
+int misc_estab(struct bpf_sock_ops *skops)
+{
+	int true_val = 1;
+
+	switch (skops->op) {
+	case BPF_SOCK_OPS_TCP_LISTEN_CB:
+		passive_lport_h = skops->local_port;
+		passive_lport_n = __bpf_htons(passive_lport_h);
+		bpf_setsockopt(skops, SOL_TCP, TCP_SAVE_SYN,
+			       &true_val, sizeof(true_val));
+		set_hdr_cb_flags(skops);
+		break;
+	case BPF_SOCK_OPS_TCP_CONNECT_CB:
+		set_hdr_cb_flags(skops);
+		break;
+	case BPF_SOCK_OPS_PARSE_HDR_OPT_CB:
+		return handle_parse_hdr(skops);
+	case BPF_SOCK_OPS_HDR_OPT_LEN_CB:
+		return handle_hdr_opt_len(skops);
+	case BPF_SOCK_OPS_WRITE_HDR_OPT_CB:
+		return handle_write_hdr_opt(skops);
+	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+		return handle_passive_estab(skops);
+	}
+
+	return CG_OK;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/test_tcp_hdr_options.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+
+#ifndef _TEST_TCP_HDR_OPTIONS_H
+#define _TEST_TCP_HDR_OPTIONS_H
+
+struct bpf_test_option {
+	__u8 flags;
+	__u8 max_delack_ms;
+	__u8 rand;
+} __attribute__((packed));
+
+enum {
+	OPTION_RESEND,
+	OPTION_MAX_DELACK_MS,
+	OPTION_RAND,
+	__NR_OPTION_FLAGS,
+};
+
+#define OPTION_F_RESEND		(1 << OPTION_RESEND)
+#define OPTION_F_MAX_DELACK_MS	(1 << OPTION_MAX_DELACK_MS)
+#define OPTION_F_RAND		(1 << OPTION_RAND)
+#define OPTION_MASK		((1 << __NR_OPTION_FLAGS) - 1)
+
+#define TEST_OPTION_FLAGS(flags, option) (1 & ((flags) >> (option)))
+#define SET_OPTION_FLAGS(flags, option)	((flags) |= (1 << (option)))
+
+/* Store in bpf_sk_storage */
+struct hdr_stg {
+	bool active;
+	bool resend_syn; /* active side only */
+	bool syncookie;  /* passive side only */
+	bool fastopen;	/* passive side only */
+};
+
+struct linum_err {
+	unsigned int linum;
+	int err;
+};
+
+#define TCPHDR_FIN 0x01
+#define TCPHDR_SYN 0x02
+#define TCPHDR_RST 0x04
+#define TCPHDR_PSH 0x08
+#define TCPHDR_ACK 0x10
+#define TCPHDR_URG 0x20
+#define TCPHDR_ECE 0x40
+#define TCPHDR_CWR 0x80
+#define TCPHDR_SYNACK (TCPHDR_SYN | TCPHDR_ACK)
+
+#define TCPOPT_EOL		0
+#define TCPOPT_NOP		1
+#define TCPOPT_WINDOW		3
+#define TCPOPT_EXP		254
+
+#define TCP_BPF_EXPOPT_BASE_LEN 4
+#define MAX_TCP_HDR_LEN		60
+#define MAX_TCP_OPTION_SPACE	40
+
+#ifdef BPF_PROG_TEST_TCP_HDR_OPTIONS
+
+#define CG_OK	1
+#define CG_ERR	0
+
+#ifndef SOL_TCP
+#define SOL_TCP 6
+#endif
+
+struct tcp_exprm_opt {
+	__u8 kind;
+	__u8 len;
+	__u16 magic;
+	union {
+		__u8 data[4];
+		__u32 data32;
+	};
+} __attribute__((packed));
+
+struct tcp_opt {
+	__u8 kind;
+	__u8 len;
+	union {
+		__u8 data[4];
+		__u32 data32;
+	};
+} __attribute__((packed));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 2);
+	__type(key, int);
+	__type(value, struct linum_err);
+} lport_linum_map SEC(".maps");
+
+static inline unsigned int tcp_hdrlen(const struct tcphdr *th)
+{
+	return th->doff << 2;
+}
+
+static inline __u8 skops_tcp_flags(const struct bpf_sock_ops *skops)
+{
+	return skops->skb_tcp_flags;
+}
+
+static inline void clear_hdr_cb_flags(struct bpf_sock_ops *skops)
+{
+	bpf_sock_ops_cb_flags_set(skops,
+				  skops->bpf_sock_ops_cb_flags &
+				  ~(BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG |
+				    BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG));
+}
+
+static inline void set_hdr_cb_flags(struct bpf_sock_ops *skops)
+{
+	bpf_sock_ops_cb_flags_set(skops,
+				  skops->bpf_sock_ops_cb_flags |
+				  BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG |
+				  BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG);
+}
+static inline void
+clear_parse_all_hdr_cb_flags(struct bpf_sock_ops *skops)
+{
+	bpf_sock_ops_cb_flags_set(skops,
+				  skops->bpf_sock_ops_cb_flags &
+				  ~BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG);
+}
+
+static inline void
+set_parse_all_hdr_cb_flags(struct bpf_sock_ops *skops)
+{
+	bpf_sock_ops_cb_flags_set(skops,
+				  skops->bpf_sock_ops_cb_flags |
+				  BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG);
+}
+
+#define RET_CG_ERR(__err) ({			\
+	struct linum_err __linum_err;		\
+	int __lport;				\
+						\
+	__linum_err.linum = __LINE__;		\
+	__linum_err.err = __err;		\
+	__lport = skops->local_port;		\
+	bpf_map_update_elem(&lport_linum_map, &__lport, &__linum_err, BPF_NOEXIST); \
+	clear_hdr_cb_flags(skops);					\
+	clear_parse_all_hdr_cb_flags(skops);				\
+	return CG_ERR;							\
+})
+
+#endif /* BPF_PROG_TEST_TCP_HDR_OPTIONS */
+
+#endif /* _TEST_TCP_HDR_OPTIONS_H */