summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--include/linux/bpf.h13
-rw-r--r--include/net/tcp.h1
-rw-r--r--include/uapi/linux/bpf.h88
-rw-r--r--kernel/bpf/verifier.c43
-rw-r--r--net/core/filter.c128
-rw-r--r--net/ipv4/tcp_input.c3
-rwxr-xr-xscripts/bpf_doc.py4
-rw-r--r--tools/include/uapi/linux/bpf.h88
-rw-r--r--tools/testing/selftests/bpf/.gitignore1
-rw-r--r--tools/testing/selftests/bpf/Makefile3
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_synproxy.c183
-rw-r--r--tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c833
-rw-r--r--tools/testing/selftests/bpf/xdp_synproxy.c466
13 files changed, 1833 insertions, 21 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f3e88afdaffe..a94531971a7a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -401,6 +401,9 @@ enum bpf_type_flag {
/* DYNPTR points to a ringbuf record. */
DYNPTR_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS),
+ /* Size is known at compile time. */
+ MEM_FIXED_SIZE = BIT(10 + BPF_BASE_TYPE_BITS),
+
__BPF_TYPE_FLAG_MAX,
__BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1,
};
@@ -464,6 +467,8 @@ enum bpf_arg_type {
* all bytes or clear them in error case.
*/
ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM,
+ /* Pointer to valid memory of size known at compile time. */
+ ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM,
/* This must be the last entry. Its purpose is to ensure the enum is
* wide enough to hold the higher bits reserved for bpf_type_flag.
@@ -529,6 +534,14 @@ struct bpf_func_proto {
u32 *arg5_btf_id;
};
u32 *arg_btf_id[5];
+ struct {
+ size_t arg1_size;
+ size_t arg2_size;
+ size_t arg3_size;
+ size_t arg4_size;
+ size_t arg5_size;
+ };
+ size_t arg_size[5];
};
int *ret_btf_id; /* return value btf_id */
bool (*allowed)(const struct bpf_prog *prog);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 1e99f5c61f84..9a1efe23fab7 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -432,6 +432,7 @@ u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph,
struct tcphdr *th, u32 *cookie);
u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph,
struct tcphdr *th, u32 *cookie);
+u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss);
u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops,
const struct tcp_request_sock_ops *af_ops,
struct sock *sk, struct tcphdr *th);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f4009dbdf62d..e81362891596 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3597,10 +3597,11 @@ union bpf_attr {
*
* *iph* points to the start of the IPv4 or IPv6 header, while
* *iph_len* contains **sizeof**\ (**struct iphdr**) or
- * **sizeof**\ (**struct ip6hdr**).
+ * **sizeof**\ (**struct ipv6hdr**).
*
* *th* points to the start of the TCP header, while *th_len*
- * contains **sizeof**\ (**struct tcphdr**).
+ * contains the length of the TCP header (at least
+ * **sizeof**\ (**struct tcphdr**)).
* Return
* 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative
* error otherwise.
@@ -3783,10 +3784,11 @@ union bpf_attr {
*
* *iph* points to the start of the IPv4 or IPv6 header, while
* *iph_len* contains **sizeof**\ (**struct iphdr**) or
- * **sizeof**\ (**struct ip6hdr**).
+ * **sizeof**\ (**struct ipv6hdr**).
*
* *th* points to the start of the TCP header, while *th_len*
- * contains the length of the TCP header.
+ * contains the length of the TCP header with options (at least
+ * **sizeof**\ (**struct tcphdr**)).
* Return
* On success, lower 32 bits hold the generated SYN cookie in
* followed by 16 bits which hold the MSS value for that cookie,
@@ -5249,6 +5251,80 @@ union bpf_attr {
* Pointer to the underlying dynptr data, NULL if the dynptr is
* read-only, if the dynptr is invalid, or if the offset and length
* is out of bounds.
+ *
+ * s64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th, u32 th_len)
+ * Description
+ * Try to issue a SYN cookie for the packet with corresponding
+ * IPv4/TCP headers, *iph* and *th*, without depending on a
+ * listening socket.
+ *
+ * *iph* points to the IPv4 header.
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains the length of the TCP header (at least
+ * **sizeof**\ (**struct tcphdr**)).
+ * Return
+ * On success, lower 32 bits hold the generated SYN cookie in
+ * followed by 16 bits which hold the MSS value for that cookie,
+ * and the top 16 bits are unused.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EINVAL** if *th_len* is invalid.
+ *
+ * s64 bpf_tcp_raw_gen_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th, u32 th_len)
+ * Description
+ * Try to issue a SYN cookie for the packet with corresponding
+ * IPv6/TCP headers, *iph* and *th*, without depending on a
+ * listening socket.
+ *
+ * *iph* points to the IPv6 header.
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains the length of the TCP header (at least
+ * **sizeof**\ (**struct tcphdr**)).
+ * Return
+ * On success, lower 32 bits hold the generated SYN cookie in
+ * followed by 16 bits which hold the MSS value for that cookie,
+ * and the top 16 bits are unused.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EINVAL** if *th_len* is invalid.
+ *
+ * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * long bpf_tcp_raw_check_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th)
+ * Description
+ * Check whether *iph* and *th* contain a valid SYN cookie ACK
+ * without depending on a listening socket.
+ *
+ * *iph* points to the IPv4 header.
+ *
+ * *th* points to the TCP header.
+ * Return
+ * 0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EACCES** if the SYN cookie is not valid.
+ *
+ * long bpf_tcp_raw_check_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th)
+ * Description
+ * Check whether *iph* and *th* contain a valid SYN cookie ACK
+ * without depending on a listening socket.
+ *
+ * *iph* points to the IPv6 header.
+ *
+ * *th* points to the TCP header.
+ * Return
+ * 0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EACCES** if the SYN cookie is not valid.
+ *
+ * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -5455,6 +5531,10 @@ union bpf_attr {
FN(dynptr_read), \
FN(dynptr_write), \
FN(dynptr_data), \
+ FN(tcp_raw_gen_syncookie_ipv4), \
+ FN(tcp_raw_gen_syncookie_ipv6), \
+ FN(tcp_raw_check_syncookie_ipv4), \
+ FN(tcp_raw_check_syncookie_ipv6), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index eadc23a8452c..2859901ffbe3 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5848,6 +5848,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
enum bpf_arg_type arg_type = fn->arg_type[arg];
enum bpf_reg_type type = reg->type;
+ u32 *arg_btf_id = NULL;
int err = 0;
if (arg_type == ARG_DONTCARE)
@@ -5884,7 +5885,11 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
*/
goto skip_type_check;
- err = check_reg_type(env, regno, arg_type, fn->arg_btf_id[arg], meta);
+ /* arg_btf_id and arg_size are in a union. */
+ if (base_type(arg_type) == ARG_PTR_TO_BTF_ID)
+ arg_btf_id = fn->arg_btf_id[arg];
+
+ err = check_reg_type(env, regno, arg_type, arg_btf_id, meta);
if (err)
return err;
@@ -6011,6 +6016,11 @@ skip_type_check:
* next is_mem_size argument below.
*/
meta->raw_mode = arg_type & MEM_UNINIT;
+ if (arg_type & MEM_FIXED_SIZE) {
+ err = check_helper_mem_access(env, regno,
+ fn->arg_size[arg], false,
+ meta);
+ }
} else if (arg_type_is_mem_size(arg_type)) {
bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
@@ -6400,11 +6410,19 @@ static bool check_raw_mode_ok(const struct bpf_func_proto *fn)
return count <= 1;
}
-static bool check_args_pair_invalid(enum bpf_arg_type arg_curr,
- enum bpf_arg_type arg_next)
+static bool check_args_pair_invalid(const struct bpf_func_proto *fn, int arg)
{
- return (base_type(arg_curr) == ARG_PTR_TO_MEM) !=
- arg_type_is_mem_size(arg_next);
+ bool is_fixed = fn->arg_type[arg] & MEM_FIXED_SIZE;
+ bool has_size = fn->arg_size[arg] != 0;
+ bool is_next_size = false;
+
+ if (arg + 1 < ARRAY_SIZE(fn->arg_type))
+ is_next_size = arg_type_is_mem_size(fn->arg_type[arg + 1]);
+
+ if (base_type(fn->arg_type[arg]) != ARG_PTR_TO_MEM)
+ return is_next_size;
+
+ return has_size == is_next_size || is_next_size == is_fixed;
}
static bool check_arg_pair_ok(const struct bpf_func_proto *fn)
@@ -6415,11 +6433,11 @@ static bool check_arg_pair_ok(const struct bpf_func_proto *fn)
* helper function specification.
*/
if (arg_type_is_mem_size(fn->arg1_type) ||
- base_type(fn->arg5_type) == ARG_PTR_TO_MEM ||
- check_args_pair_invalid(fn->arg1_type, fn->arg2_type) ||
- check_args_pair_invalid(fn->arg2_type, fn->arg3_type) ||
- check_args_pair_invalid(fn->arg3_type, fn->arg4_type) ||
- check_args_pair_invalid(fn->arg4_type, fn->arg5_type))
+ check_args_pair_invalid(fn, 0) ||
+ check_args_pair_invalid(fn, 1) ||
+ check_args_pair_invalid(fn, 2) ||
+ check_args_pair_invalid(fn, 3) ||
+ check_args_pair_invalid(fn, 4))
return false;
return true;
@@ -6460,7 +6478,10 @@ static bool check_btf_id_ok(const struct bpf_func_proto *fn)
if (base_type(fn->arg_type[i]) == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i])
return false;
- if (base_type(fn->arg_type[i]) != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i])
+ if (base_type(fn->arg_type[i]) != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i] &&
+ /* arg_btf_id and arg_size are in a union. */
+ (base_type(fn->arg_type[i]) != ARG_PTR_TO_MEM ||
+ !(fn->arg_type[i] & MEM_FIXED_SIZE)))
return false;
}
diff --git a/net/core/filter.c b/net/core/filter.c
index 5af58eb48587..423f47db84c6 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7444,6 +7444,114 @@ static const struct bpf_func_proto bpf_skb_set_tstamp_proto = {
.arg3_type = ARG_ANYTHING,
};
+#ifdef CONFIG_SYN_COOKIES
+BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv4, struct iphdr *, iph,
+ struct tcphdr *, th, u32, th_len)
+{
+ u32 cookie;
+ u16 mss;
+
+ if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4))
+ return -EINVAL;
+
+ mss = tcp_parse_mss_option(th, 0) ?: TCP_MSS_DEFAULT;
+ cookie = __cookie_v4_init_sequence(iph, th, &mss);
+
+ return cookie | ((u64)mss << 32);
+}
+
+static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv4_proto = {
+ .func = bpf_tcp_raw_gen_syncookie_ipv4,
+ .gpl_only = true, /* __cookie_v4_init_sequence() is GPL */
+ .pkt_access = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM,
+ .arg1_size = sizeof(struct iphdr),
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+};
+
+BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv6, struct ipv6hdr *, iph,
+ struct tcphdr *, th, u32, th_len)
+{
+#if IS_BUILTIN(CONFIG_IPV6)
+ const u16 mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) -
+ sizeof(struct ipv6hdr);
+ u32 cookie;
+ u16 mss;
+
+ if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4))
+ return -EINVAL;
+
+ mss = tcp_parse_mss_option(th, 0) ?: mss_clamp;
+ cookie = __cookie_v6_init_sequence(iph, th, &mss);
+
+ return cookie | ((u64)mss << 32);
+#else
+ return -EPROTONOSUPPORT;
+#endif
+}
+
+static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = {
+ .func = bpf_tcp_raw_gen_syncookie_ipv6,
+ .gpl_only = true, /* __cookie_v6_init_sequence() is GPL */
+ .pkt_access = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM,
+ .arg1_size = sizeof(struct ipv6hdr),
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+};
+
+BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv4, struct iphdr *, iph,
+ struct tcphdr *, th)
+{
+ u32 cookie = ntohl(th->ack_seq) - 1;
+
+ if (__cookie_v4_check(iph, th, cookie) > 0)
+ return 0;
+
+ return -EACCES;
+}
+
+static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv4_proto = {
+ .func = bpf_tcp_raw_check_syncookie_ipv4,
+ .gpl_only = true, /* __cookie_v4_check is GPL */
+ .pkt_access = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM,
+ .arg1_size = sizeof(struct iphdr),
+ .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM,
+ .arg2_size = sizeof(struct tcphdr),
+};
+
+BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv6, struct ipv6hdr *, iph,
+ struct tcphdr *, th)
+{
+#if IS_BUILTIN(CONFIG_IPV6)
+ u32 cookie = ntohl(th->ack_seq) - 1;
+
+ if (__cookie_v6_check(iph, th, cookie) > 0)
+ return 0;
+
+ return -EACCES;
+#else
+ return -EPROTONOSUPPORT;
+#endif
+}
+
+static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv6_proto = {
+ .func = bpf_tcp_raw_check_syncookie_ipv6,
+ .gpl_only = true, /* __cookie_v6_check is GPL */
+ .pkt_access = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM,
+ .arg1_size = sizeof(struct ipv6hdr),
+ .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM,
+ .arg2_size = sizeof(struct tcphdr),
+};
+#endif /* CONFIG_SYN_COOKIES */
+
#endif /* CONFIG_INET */
bool bpf_helper_changes_pkt_data(void *func)
@@ -7807,6 +7915,16 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_sk_assign_proto;
case BPF_FUNC_skb_set_tstamp:
return &bpf_skb_set_tstamp_proto;
+#ifdef CONFIG_SYN_COOKIES
+ case BPF_FUNC_tcp_raw_gen_syncookie_ipv4:
+ return &bpf_tcp_raw_gen_syncookie_ipv4_proto;
+ case BPF_FUNC_tcp_raw_gen_syncookie_ipv6:
+ return &bpf_tcp_raw_gen_syncookie_ipv6_proto;
+ case BPF_FUNC_tcp_raw_check_syncookie_ipv4:
+ return &bpf_tcp_raw_check_syncookie_ipv4_proto;
+ case BPF_FUNC_tcp_raw_check_syncookie_ipv6:
+ return &bpf_tcp_raw_check_syncookie_ipv6_proto;
+#endif
#endif
default:
return bpf_sk_base_func_proto(func_id);
@@ -7856,6 +7974,16 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_tcp_check_syncookie_proto;
case BPF_FUNC_tcp_gen_syncookie:
return &bpf_tcp_gen_syncookie_proto;
+#ifdef CONFIG_SYN_COOKIES
+ case BPF_FUNC_tcp_raw_gen_syncookie_ipv4:
+ return &bpf_tcp_raw_gen_syncookie_ipv4_proto;
+ case BPF_FUNC_tcp_raw_gen_syncookie_ipv6:
+ return &bpf_tcp_raw_gen_syncookie_ipv6_proto;
+ case BPF_FUNC_tcp_raw_check_syncookie_ipv4:
+ return &bpf_tcp_raw_check_syncookie_ipv4_proto;
+ case BPF_FUNC_tcp_raw_check_syncookie_ipv6:
+ return &bpf_tcp_raw_check_syncookie_ipv6_proto;
+#endif
#endif
default:
return bpf_sk_base_func_proto(func_id);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2e2a9ece9af2..6426f6a2e744 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3967,7 +3967,7 @@ static bool smc_parse_options(const struct tcphdr *th,
/* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped
* value on success.
*/
-static u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss)
+u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss)
{
const unsigned char *ptr = (const unsigned char *)(th + 1);
int length = (th->doff * 4) - sizeof(struct tcphdr);
@@ -4006,6 +4006,7 @@ static u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss)
}
return mss;
}
+EXPORT_SYMBOL_GPL(tcp_parse_mss_option);
/* Look for tcp options. Normally only called on SYN and SYNACK packets.
* But, this can also be called on packets in the established flow when
diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py
index 855b937e7585..a0ec321469bd 100755
--- a/scripts/bpf_doc.py
+++ b/scripts/bpf_doc.py
@@ -635,6 +635,8 @@ class PrinterHelpers(Printer):
'struct bpf_timer',
'struct mptcp_sock',
'struct bpf_dynptr',
+ 'struct iphdr',
+ 'struct ipv6hdr',
]
known_types = {
'...',
@@ -686,6 +688,8 @@ class PrinterHelpers(Printer):
'struct bpf_timer',
'struct mptcp_sock',
'struct bpf_dynptr',
+ 'struct iphdr',
+ 'struct ipv6hdr',
}
mapped_types = {
'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f4009dbdf62d..e81362891596 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3597,10 +3597,11 @@ union bpf_attr {
*
* *iph* points to the start of the IPv4 or IPv6 header, while
* *iph_len* contains **sizeof**\ (**struct iphdr**) or
- * **sizeof**\ (**struct ip6hdr**).
+ * **sizeof**\ (**struct ipv6hdr**).
*
* *th* points to the start of the TCP header, while *th_len*
- * contains **sizeof**\ (**struct tcphdr**).
+ * contains the length of the TCP header (at least
+ * **sizeof**\ (**struct tcphdr**)).
* Return
* 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative
* error otherwise.
@@ -3783,10 +3784,11 @@ union bpf_attr {
*
* *iph* points to the start of the IPv4 or IPv6 header, while
* *iph_len* contains **sizeof**\ (**struct iphdr**) or
- * **sizeof**\ (**struct ip6hdr**).
+ * **sizeof**\ (**struct ipv6hdr**).
*
* *th* points to the start of the TCP header, while *th_len*
- * contains the length of the TCP header.
+ * contains the length of the TCP header with options (at least
+ * **sizeof**\ (**struct tcphdr**)).
* Return
* On success, lower 32 bits hold the generated SYN cookie in
* followed by 16 bits which hold the MSS value for that cookie,
@@ -5249,6 +5251,80 @@ union bpf_attr {
* Pointer to the underlying dynptr data, NULL if the dynptr is
* read-only, if the dynptr is invalid, or if the offset and length
* is out of bounds.
+ *
+ * s64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th, u32 th_len)
+ * Description
+ * Try to issue a SYN cookie for the packet with corresponding
+ * IPv4/TCP headers, *iph* and *th*, without depending on a
+ * listening socket.
+ *
+ * *iph* points to the IPv4 header.
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains the length of the TCP header (at least
+ * **sizeof**\ (**struct tcphdr**)).
+ * Return
+ * On success, lower 32 bits hold the generated SYN cookie in
+ * followed by 16 bits which hold the MSS value for that cookie,
+ * and the top 16 bits are unused.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EINVAL** if *th_len* is invalid.
+ *
+ * s64 bpf_tcp_raw_gen_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th, u32 th_len)
+ * Description
+ * Try to issue a SYN cookie for the packet with corresponding
+ * IPv6/TCP headers, *iph* and *th*, without depending on a
+ * listening socket.
+ *
+ * *iph* points to the IPv6 header.
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains the length of the TCP header (at least
+ * **sizeof**\ (**struct tcphdr**)).
+ * Return
+ * On success, lower 32 bits hold the generated SYN cookie in
+ * followed by 16 bits which hold the MSS value for that cookie,
+ * and the top 16 bits are unused.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EINVAL** if *th_len* is invalid.
+ *
+ * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * long bpf_tcp_raw_check_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th)
+ * Description
+ * Check whether *iph* and *th* contain a valid SYN cookie ACK
+ * without depending on a listening socket.
+ *
+ * *iph* points to the IPv4 header.
+ *
+ * *th* points to the TCP header.
+ * Return
+ * 0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EACCES** if the SYN cookie is not valid.
+ *
+ * long bpf_tcp_raw_check_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th)
+ * Description
+ * Check whether *iph* and *th* contain a valid SYN cookie ACK
+ * without depending on a listening socket.
+ *
+ * *iph* points to the IPv6 header.
+ *
+ * *th* points to the TCP header.
+ * Return
+ * 0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EACCES** if the SYN cookie is not valid.
+ *
+ * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -5455,6 +5531,10 @@ union bpf_attr {
FN(dynptr_read), \
FN(dynptr_write), \
FN(dynptr_data), \
+ FN(tcp_raw_gen_syncookie_ipv4), \
+ FN(tcp_raw_gen_syncookie_ipv6), \
+ FN(tcp_raw_check_syncookie_ipv4), \
+ FN(tcp_raw_check_syncookie_ipv6), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 595565eb68c0..ca2f47f45670 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -43,3 +43,4 @@ test_cpp
*.tmp
xdpxceiver
xdp_redirect_multi
+xdp_synproxy
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e08e8e34e793..8b30bb743e24 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -82,7 +82,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \
TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
- xdpxceiver xdp_redirect_multi
+ xdpxceiver xdp_redirect_multi xdp_synproxy
TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read
@@ -504,6 +504,7 @@ TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \
cap_helpers.c
TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \
$(OUTPUT)/liburandom_read.so \
+ $(OUTPUT)/xdp_synproxy \
ima_setup.sh \
$(wildcard progs/btf_dump_test_case_*.c)
TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_synproxy.c b/tools/testing/selftests/bpf/prog_tests/xdp_synproxy.c
new file mode 100644
index 000000000000..fb77a123fe89
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_synproxy.c
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: LGPL-2.1 OR BSD-2-Clause
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#define _GNU_SOURCE
+#include <test_progs.h>
+#include <network_helpers.h>
+#include <ctype.h>
+
+#define CMD_OUT_BUF_SIZE 1023
+
+#define SYS(cmd) ({ \
+ if (!ASSERT_OK(system(cmd), (cmd))) \
+ goto out; \
+})
+
+#define SYS_OUT(cmd, ...) ({ \
+ char buf[1024]; \
+ snprintf(buf, sizeof(buf), (cmd), ##__VA_ARGS__); \
+ FILE *f = popen(buf, "r"); \
+ if (!ASSERT_OK_PTR(f, buf)) \
+ goto out; \
+ f; \
+})
+
+/* out must be at least `size * 4 + 1` bytes long */
+static void escape_str(char *out, const char *in, size_t size)
+{
+ static const char *hex = "0123456789ABCDEF";
+ size_t i;
+
+ for (i = 0; i < size; i++) {
+ if (isprint(in[i]) && in[i] != '\\' && in[i] != '\'') {
+ *out++ = in[i];
+ } else {
+ *out++ = '\\';
+ *out++ = 'x';
+ *out++ = hex[(in[i] >> 4) & 0xf];
+ *out++ = hex[in[i] & 0xf];
+ }
+ }
+ *out++ = '\0';
+}
+
+static bool expect_str(char *buf, size_t size, const char *str, const char *name)
+{
+ static char escbuf_expected[CMD_OUT_BUF_SIZE * 4];
+ static char escbuf_actual[CMD_OUT_BUF_SIZE * 4];
+ static int duration = 0;
+ bool ok;
+
+ ok = size == strlen(str) && !memcmp(buf, str, size);
+
+ if (!ok) {
+ escape_str(escbuf_expected, str, strlen(str));
+ escape_str(escbuf_actual, buf, size);
+ }
+ CHECK(!ok, name, "unexpected %s: actual '%s' != expected '%s'\n",
+ name, escbuf_actual, escbuf_expected);
+
+ return ok;
+}
+
+static void test_synproxy(bool xdp)
+{
+ int server_fd = -1, client_fd = -1, accept_fd = -1;
+ char *prog_id, *prog_id_end;
+ struct nstoken *ns = NULL;
+ FILE *ctrl_file = NULL;
+ char buf[CMD_OUT_BUF_SIZE];
+ size_t size;
+
+ SYS("ip netns add synproxy");
+
+ SYS("ip link add tmp0 type veth peer name tmp1");
+ SYS("ip link set tmp1 netns synproxy");
+ SYS("ip link set tmp0 up");
+ SYS("ip addr replace 198.18.0.1/24 dev tmp0");
+
+ /* When checksum offload is enabled, the XDP program sees wrong
+ * checksums and drops packets.
+ */
+ SYS("ethtool -K tmp0 tx off");
+ if (xdp)
+ /* Workaround required for veth. */
+ SYS("ip link set tmp0 xdp object xdp_dummy.o section xdp 2> /dev/null");
+
+ ns = open_netns("synproxy");
+ if (!ASSERT_OK_PTR(ns, "setns"))
+ goto out;
+
+ SYS("ip link set lo up");
+ SYS("ip link set tmp1 up");
+ SYS("ip addr replace 198.18.0.2/24 dev tmp1");
+ SYS("sysctl -w net.ipv4.tcp_syncookies=2");
+ SYS("sysctl -w net.ipv4.tcp_timestamps=1");
+ SYS("sysctl -w net.netfilter.nf_conntrack_tcp_loose=0");
+ SYS("iptables -t raw -I PREROUTING \
+ -i tmp1 -p tcp -m tcp --syn --dport 8080 -j CT --notrack");
+ SYS("iptables -t filter -A INPUT \
+ -i tmp1 -p tcp -m tcp --dport 8080 -m state --state INVALID,UNTRACKED \
+ -j SYNPROXY --sack-perm --timestamp --wscale 7 --mss 1460");
+ SYS("iptables -t filter -A INPUT \
+ -i tmp1 -m state --state INVALID -j DROP");
+
+ ctrl_file = SYS_OUT("./xdp_synproxy --iface tmp1 --ports 8080 \
+ --single --mss4 1460 --mss6 1440 \
+ --wscale 7 --ttl 64%s", xdp ? "" : " --tc");
+ size = fread(buf, 1, sizeof(buf), ctrl_file);
+ pclose(ctrl_file);
+ if (!expect_str(buf, size, "Total SYNACKs generated: 0\n",
+ "initial SYNACKs"))
+ goto out;
+
+ if (!xdp) {
+ ctrl_file = SYS_OUT("tc filter show dev tmp1 ingress");
+ size = fread(buf, 1, sizeof(buf), ctrl_file);
+ pclose(ctrl_file);
+ prog_id = memmem(buf, size, " id ", 4);
+ if (!ASSERT_OK_PTR(prog_id, "find prog id"))
+ goto out;
+ prog_id += 4;
+ if (!ASSERT_LT(prog_id, buf + size, "find prog id begin"))
+ goto out;
+ prog_id_end = prog_id;
+ while (prog_id_end < buf + size && *prog_id_end >= '0' &&
+ *prog_id_end <= '9')
+ prog_id_end++;
+ if (!ASSERT_LT(prog_id_end, buf + size, "find prog id end"))
+ goto out;
+ *prog_id_end = '\0';
+ }
+
+ server_fd = start_server(AF_INET, SOCK_STREAM, "198.18.0.2", 8080, 0);
+ if (!ASSERT_GE(server_fd, 0, "start_server"))
+ goto out;
+
+ close_netns(ns);
+ ns = NULL;
+
+ client_fd = connect_to_fd(server_fd, 10000);
+ if (!ASSERT_GE(client_fd, 0, "connect_to_fd"))
+ goto out;
+
+ accept_fd = accept(server_fd, NULL, NULL);
+ if (!ASSERT_GE(accept_fd, 0, "accept"))
+ goto out;
+
+ ns = open_netns("synproxy");
+ if (!ASSERT_OK_PTR(ns, "setns"))
+ goto out;
+
+ if (xdp)
+ ctrl_file = SYS_OUT("./xdp_synproxy --iface tmp1 --single");
+ else
+ ctrl_file = SYS_OUT("./xdp_synproxy --prog %s --single",
+ prog_id);
+ size = fread(buf, 1, sizeof(buf), ctrl_file);
+ pclose(ctrl_file);
+ if (!expect_str(buf, size, "Total SYNACKs generated: 1\n",
+ "SYNACKs after connection"))
+ goto out;
+
+out:
+ if (accept_fd >= 0)
+ close(accept_fd);
+ if (client_fd >= 0)
+ close(client_fd);
+ if (server_fd >= 0)
+ close(server_fd);
+ if (ns)
+ close_netns(ns);
+
+ system("ip link del tmp0");
+ system("ip netns del synproxy");
+}
+
+void test_xdp_synproxy(void)
+{
+ if (test__start_subtest("xdp"))
+ test_synproxy(true);
+ if (test__start_subtest("tc"))
+ test_synproxy(false);
+}
diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
new file mode 100644
index 000000000000..9fd62e94b5e6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
@@ -0,0 +1,833 @@
+// SPDX-License-Identifier: LGPL-2.1 OR BSD-2-Clause
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include "vmlinux.h"
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include <asm/errno.h>
+
+#define TC_ACT_OK 0
+#define TC_ACT_SHOT 2
+
+#define NSEC_PER_SEC 1000000000L
+
+#define ETH_ALEN 6
+#define ETH_P_IP 0x0800
+#define ETH_P_IPV6 0x86DD
+
+#define tcp_flag_word(tp) (((union tcp_word_hdr *)(tp))->words[3])
+
+#define IP_DF 0x4000
+#define IP_MF 0x2000
+#define IP_OFFSET 0x1fff
+
+#define NEXTHDR_TCP 6
+
+#define TCPOPT_NOP 1
+#define TCPOPT_EOL 0
+#define TCPOPT_MSS 2
+#define TCPOPT_WINDOW 3
+#define TCPOPT_SACK_PERM 4
+#define TCPOPT_TIMESTAMP 8
+
+#define TCPOLEN_MSS 4
+#define TCPOLEN_WINDOW 3
+#define TCPOLEN_SACK_PERM 2
+#define TCPOLEN_TIMESTAMP 10
+
+#define TCP_TS_HZ 1000
+#define TS_OPT_WSCALE_MASK 0xf
+#define TS_OPT_SACK (1 << 4)
+#define TS_OPT_ECN (1 << 5)
+#define TSBITS 6
+#define TSMASK (((__u32)1 << TSBITS) - 1)
+#define TCP_MAX_WSCALE 14U
+
+#define IPV4_MAXLEN 60
+#define TCP_MAXLEN 60
+
+#define DEFAULT_MSS4 1460
+#define DEFAULT_MSS6 1440
+#define DEFAULT_WSCALE 7
+#define DEFAULT_TTL 64
+#define MAX_ALLOWED_PORTS 8
+
+#define swap(a, b) \
+ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
+
+#define __get_unaligned_t(type, ptr) ({ \
+ const struct { type x; } __attribute__((__packed__)) *__pptr = (typeof(__pptr))(ptr); \
+ __pptr->x; \
+})
+
+#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr))
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, __u32);
+ __type(value, __u64);
+ __uint(max_entries, 2);
+} values SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, __u32);
+ __type(value, __u16);
+ __uint(max_entries, MAX_ALLOWED_PORTS);
+} allowed_ports SEC(".maps");
+
+extern struct nf_conn *bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx,
+ struct bpf_sock_tuple *bpf_tuple,
+ __u32 len_tuple,
+ struct bpf_ct_opts *opts,
+ __u32 len_opts) __ksym;
+
+extern struct nf_conn *bpf_skb_ct_lookup(struct __sk_buff *skb_ctx,
+ struct bpf_sock_tuple *bpf_tuple,
+ u32 len_tuple,
+ struct bpf_ct_opts *opts,
+ u32 len_opts) __ksym;
+
+extern void bpf_ct_release(struct nf_conn *ct) __ksym;
+
+static __always_inline void swap_eth_addr(__u8 *a, __u8 *b)
+{
+ __u8 tmp[ETH_ALEN];
+
+ __builtin_memcpy(tmp, a, ETH_ALEN);
+ __builtin_memcpy(a, b, ETH_ALEN);
+ __builtin_memcpy(b, tmp, ETH_ALEN);
+}
+
+static __always_inline __u16 csum_fold(__u32 csum)
+{
+ csum = (csum & 0xffff) + (csum >> 16);
+ csum = (csum & 0xffff) + (csum >> 16);
+ return (__u16)~csum;
+}
+
+static __always_inline __u16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+ __u32 len, __u8 proto,
+ __u32 csum)
+{
+ __u64 s = csum;
+
+ s += (__u32)saddr;
+ s += (__u32)daddr;
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+ s += proto + len;
+#elif __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+ s += (proto + len) << 8;
+#else
+#error Unknown endian
+#endif
+ s = (s & 0xffffffff) + (s >> 32);
+ s = (s & 0xffffffff) + (s >> 32);
+
+ return csum_fold((__u32)s);
+}
+
+static __always_inline __u16 csum_ipv6_magic(const struct in6_addr *saddr,
+ const struct in6_addr *daddr,
+ __u32 len, __u8 proto, __u32 csum)
+{
+ __u64 sum = csum;
+ int i;
+
+#pragma unroll
+ for (i = 0; i < 4; i++)
+ sum += (__u32)saddr->in6_u.u6_addr32[i];
+
+#pragma unroll
+ for (i = 0; i < 4; i++)
+ sum += (__u32)daddr->in6_u.u6_addr32[i];
+
+ /* Don't combine additions to avoid 32-bit overflow. */
+ sum += bpf_htonl(len);
+ sum += bpf_htonl(proto);
+
+ sum = (sum & 0xffffffff) + (sum >> 32);
+ sum = (sum & 0xffffffff) + (sum >> 32);
+
+ return csum_fold((__u32)sum);
+}
+
+static __always_inline __u64 tcp_clock_ns(void)
+{
+ return bpf_ktime_get_ns();
+}
+
+static __always_inline __u32 tcp_ns_to_ts(__u64 ns)
+{
+ return ns / (NSEC_PER_SEC / TCP_TS_HZ);
+}
+
+static __always_inline __u32 tcp_time_stamp_raw(void)
+{
+ return tcp_ns_to_ts(tcp_clock_ns());
+}
+
+struct tcpopt_context {
+ __u8 *ptr;
+ __u8 *end;
+ void *data_end;
+ __be32 *tsecr;
+ __u8 wscale;
+ bool option_timestamp;
+ bool option_sack;
+};
+
+static int tscookie_tcpopt_parse(struct tcpopt_context *ctx)
+{
+ __u8 opcode, opsize;
+
+ if (ctx->ptr >= ctx->end)
+ return 1;
+ if (ctx->ptr >= ctx->data_end)
+ return 1;
+
+ opcode = ctx->ptr[0];
+
+ if (opcode == TCPOPT_EOL)
+ return 1;
+ if (opcode == TCPOPT_NOP) {
+ ++ctx->ptr;
+ return 0;
+ }
+
+ if (ctx->ptr + 1 >= ctx->end)
+ return 1;
+ if (ctx->ptr + 1 >= ctx->data_end)
+ return 1;
+ opsize = ctx->ptr[1];
+ if (opsize < 2)
+ return 1;
+
+ if (ctx->ptr + opsize > ctx->end)
+ return 1;
+
+ switch (opcode) {
+ case TCPOPT_WINDOW:
+ if (opsize == TCPOLEN_WINDOW && ctx->ptr + TCPOLEN_WINDOW <= ctx->data_end)
+ ctx->wscale = ctx->ptr[2] < TCP_MAX_WSCALE ? ctx->ptr[2] : TCP_MAX_WSCALE;
+ break;
+ case TCPOPT_TIMESTAMP:
+ if (opsize == TCPOLEN_TIMESTAMP && ctx->ptr + TCPOLEN_TIMESTAMP <= ctx->data_end) {
+ ctx->option_timestamp = true;
+ /* Client's tsval becomes our tsecr. */
+ *ctx->tsecr = get_unaligned((__be32 *)(ctx->ptr + 2));
+ }
+ break;
+ case TCPOPT_SACK_PERM:
+ if (opsize == TCPOLEN_SACK_PERM)
+ ctx->option_sack = true;
+ break;
+ }
+
+ ctx->ptr += opsize;
+
+ return 0;
+}
+
+static int tscookie_tcpopt_parse_batch(__u32 index, void *context)
+{
+ int i;
+
+ for (i = 0; i < 7; i++)
+ if (tscookie_tcpopt_parse(context))
+ return 1;
+ return 0;
+}
+
+static __always_inline bool tscookie_init(struct tcphdr *tcp_header,
+ __u16 tcp_len, __be32 *tsval,
+ __be32 *tsecr, void *data_end)
+{
+ struct tcpopt_context loop_ctx = {
+ .ptr = (__u8 *)(tcp_header + 1),
+ .end = (__u8 *)tcp_header + tcp_len,
+ .data_end = data_end,
+ .tsecr = tsecr,
+ .wscale = TS_OPT_WSCALE_MASK,
+ .option_timestamp = false,
+ .option_sack = false,
+ };
+ u32 cookie;
+
+ bpf_loop(6, tscookie_tcpopt_parse_batch, &loop_ctx, 0);
+
+ if (!loop_ctx.option_timestamp)
+ return false;
+
+ cookie = tcp_time_stamp_raw() & ~TSMASK;
+ cookie |= loop_ctx.wscale & TS_OPT_WSCALE_MASK;
+ if (loop_ctx.option_sack)
+ cookie |= TS_OPT_SACK;
+ if (tcp_header->ece && tcp_header->cwr)
+ cookie |= TS_OPT_ECN;
+ *tsval = bpf_htonl(cookie);
+
+ return true;
+}
+
+static __always_inline void values_get_tcpipopts(__u16 *mss, __u8 *wscale,
+ __u8 *ttl, bool ipv6)
+{
+ __u32 key = 0;
+ __u64 *value;
+
+ value = bpf_map_lookup_elem(&values, &key);
+ if (value && *value != 0) {
+ if (ipv6)
+ *mss = (*value >> 32) & 0xffff;
+ else
+ *mss = *value & 0xffff;
+ *wscale = (*value >> 16) & 0xf;
+ *ttl = (*value >> 24) & 0xff;
+ return;
+ }
+
+ *mss = ipv6 ? DEFAULT_MSS6 : DEFAULT_MSS4;
+ *wscale = DEFAULT_WSCALE;
+ *ttl = DEFAULT_TTL;
+}
+
+static __always_inline void values_inc_synacks(void)
+{
+ __u32 key = 1;
+ __u32 *value;
+
+ value = bpf_map_lookup_elem(&values, &key);
+ if (value)
+ __sync_fetch_and_add(value, 1);
+}
+
+static __always_inline bool check_port_allowed(__u16 port)
+{
+ __u32 i;
+
+ for (i = 0; i < MAX_ALLOWED_PORTS; i++) {
+ __u32 key = i;
+ __u16 *value;
+
+ value = bpf_map_lookup_elem(&allowed_ports, &key);
+
+ if (!value)
+ break;
+ /* 0 is a terminator value. Check it first to avoid matching on
+ * a forbidden port == 0 and returning true.
+ */
+ if (*value == 0)
+ break;
+
+ if (*value == port)
+ return true;
+ }
+
+ return false;
+}
+
+struct header_pointers {
+ struct ethhdr *eth;
+ struct iphdr *ipv4;
+ struct ipv6hdr *ipv6;
+ struct tcphdr *tcp;
+ __u16 tcp_len;
+};
+
+static __always_inline int tcp_dissect(void *data, void *data_end,
+ struct header_pointers *hdr)
+{
+ hdr->eth = data;
+ if (hdr->eth + 1 > data_end)
+ return XDP_DROP;
+
+ switch (bpf_ntohs(hdr->eth->h_proto)) {
+ case ETH_P_IP:
+ hdr->ipv6 = NULL;
+
+ hdr->ipv4 = (void *)hdr->eth + sizeof(*hdr->eth);
+ if (hdr->ipv4 + 1 > data_end)
+ return XDP_DROP;
+ if (hdr->ipv4->ihl * 4 < sizeof(*hdr->ipv4))
+ return XDP_DROP;
+ if (hdr->ipv4->version != 4)
+ return XDP_DROP;
+
+ if (hdr->ipv4->protocol != IPPROTO_TCP)
+ return XDP_PASS;
+
+ hdr->tcp = (void *)hdr->ipv4 + hdr->ipv4->ihl * 4;
+ break;
+ case ETH_P_IPV6:
+ hdr->ipv4 = NULL;
+
+ hdr->ipv6 = (void *)hdr->eth + sizeof(*hdr->eth);
+ if (hdr->ipv6 + 1 > data_end)
+ return XDP_DROP;
+ if (hdr->ipv6->version != 6)
+ return XDP_DROP;
+
+ /* XXX: Extension headers are not supported and could circumvent
+ * XDP SYN flood protection.
+ */
+ if (hdr->ipv6->nexthdr != NEXTHDR_TCP)
+ return XDP_PASS;
+
+ hdr->tcp = (void *)hdr->ipv6 + sizeof(*hdr->ipv6);
+ break;
+ default:
+ /* XXX: VLANs will circumvent XDP SYN flood protection. */
+ return XDP_PASS;
+ }
+
+ if (hdr->tcp + 1 > data_end)
+ return XDP_DROP;
+ hdr->tcp_len = hdr->tcp->doff * 4;
+ if (hdr->tcp_len < sizeof(*hdr->tcp))
+ return XDP_DROP;
+
+ return XDP_TX;
+}
+
+static __always_inline int tcp_lookup(void *ctx, struct header_pointers *hdr, bool xdp)
+{
+ struct bpf_ct_opts ct_lookup_opts = {
+ .netns_id = BPF_F_CURRENT_NETNS,
+ .l4proto = IPPROTO_TCP,
+ };
+ struct bpf_sock_tuple tup = {};
+ struct nf_conn *ct;
+ __u32 tup_size;
+
+ if (hdr->ipv4) {
+ /* TCP doesn't normally use fragments, and XDP can't reassemble
+ * them.
+ */
+ if ((hdr->ipv4->frag_off & bpf_htons(IP_DF | IP_MF | IP_OFFSET)) != bpf_htons(IP_DF))
+ return XDP_DROP;
+
+ tup.ipv4.saddr = hdr->ipv4->saddr;
+ tup.ipv4.daddr = hdr->ipv4->daddr;
+ tup.ipv4.sport = hdr->tcp->source;
+ tup.ipv4.dport = hdr->tcp->dest;
+ tup_size = sizeof(tup.ipv4);
+ } else if (hdr->ipv6) {
+ __builtin_memcpy(tup.ipv6.saddr, &hdr->ipv6->saddr, sizeof(tup.ipv6.saddr));
+ __builtin_memcpy(tup.ipv6.daddr, &hdr->ipv6->daddr, sizeof(tup.ipv6.daddr));
+ tup.ipv6.sport = hdr->tcp->source;
+ tup.ipv6.dport = hdr->tcp->dest;
+ tup_size = sizeof(tup.ipv6);
+ } else {
+ /* The verifier can't track that either ipv4 or ipv6 is not
+ * NULL.
+ */
+ return XDP_ABORTED;
+ }
+ if (xdp)
+ ct = bpf_xdp_ct_lookup(ctx, &tup, tup_size, &ct_lookup_opts, sizeof(ct_lookup_opts));
+ else
+ ct = bpf_skb_ct_lookup(ctx, &tup, tup_size, &ct_lookup_opts, sizeof(ct_lookup_opts));
+ if (ct) {
+ unsigned long status = ct->status;
+
+ bpf_ct_release(ct);
+ if (status & IPS_CONFIRMED_BIT)
+ return XDP_PASS;
+ } else if (ct_lookup_opts.error != -ENOENT) {
+ return XDP_ABORTED;
+ }
+
+ /* error == -ENOENT || !(status & IPS_CONFIRMED_BIT) */
+ return XDP_TX;
+}
+
+static __always_inline __u8 tcp_mkoptions(__be32 *buf, __be32 *tsopt, __u16 mss,
+ __u8 wscale)
+{
+ __be32 *start = buf;
+
+ *buf++ = bpf_htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | mss);
+
+ if (!tsopt)
+ return buf - start;
+
+ if (tsopt[0] & bpf_htonl(1 << 4))
+ *buf++ = bpf_htonl((TCPOPT_SACK_PERM << 24) |
+ (TCPOLEN_SACK_PERM << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP);
+ else
+ *buf++ = bpf_htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP);
+ *buf++ = tsopt[0];
+ *buf++ = tsopt[1];
+
+ if ((tsopt[0] & bpf_htonl(0xf)) != bpf_htonl(0xf))
+ *buf++ = bpf_htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_WINDOW << 16) |
+ (TCPOLEN_WINDOW << 8) |
+ wscale);
+
+ return buf - start;
+}
+
+static __always_inline void tcp_gen_synack(struct tcphdr *tcp_header,
+ __u32 cookie, __be32 *tsopt,
+ __u16 mss, __u8 wscale)
+{
+ void *tcp_options;
+
+ tcp_flag_word(tcp_header) = TCP_FLAG_SYN | TCP_FLAG_ACK;
+ if (tsopt && (tsopt[0] & bpf_htonl(1 << 5)))
+ tcp_flag_word(tcp_header) |= TCP_FLAG_ECE;
+ tcp_header->doff = 5; /* doff is part of tcp_flag_word. */
+ swap(tcp_header->source, tcp_header->dest);
+ tcp_header->ack_seq = bpf_htonl(bpf_ntohl(tcp_header->seq) + 1);
+ tcp_header->seq = bpf_htonl(cookie);
+ tcp_header->window = 0;
+ tcp_header->urg_ptr = 0;
+ tcp_header->check = 0; /* Calculate checksum later. */
+
+ tcp_options = (void *)(tcp_header + 1);
+ tcp_header->doff += tcp_mkoptions(tcp_options, tsopt, mss, wscale);
+}
+
+static __always_inline void tcpv4_gen_synack(struct header_pointers *hdr,
+ __u32 cookie, __be32 *tsopt)
+{
+ __u8 wscale;
+ __u16 mss;
+ __u8 ttl;
+
+ values_get_tcpipopts(&mss, &wscale, &ttl, false);
+
+ swap_eth_addr(hdr->eth->h_source, hdr->eth->h_dest);
+
+ swap(hdr->ipv4->saddr, hdr->ipv4->daddr);
+ hdr->ipv4->check = 0; /* Calculate checksum later. */
+ hdr->ipv4->tos = 0;
+ hdr->ipv4->id = 0;
+ hdr->ipv4->ttl = ttl;
+
+ tcp_gen_synack(hdr->tcp, cookie, tsopt, mss, wscale);
+
+ hdr->tcp_len = hdr->tcp->doff * 4;
+ hdr->ipv4->tot_len = bpf_htons(sizeof(*hdr->ipv4) + hdr->tcp_len);
+}
+
+static __always_inline void tcpv6_gen_synack(struct header_pointers *hdr,
+ __u32 cookie, __be32 *tsopt)
+{
+ __u8 wscale;
+ __u16 mss;
+ __u8 ttl;
+
+ values_get_tcpipopts(&mss, &wscale, &ttl, true);
+
+ swap_eth_addr(hdr->eth->h_source, hdr->eth->h_dest);
+
+ swap(hdr->ipv6->saddr, hdr->ipv6->daddr);
+ *(__be32 *)hdr->ipv6 = bpf_htonl(0x60000000);
+ hdr->ipv6->hop_limit = ttl;
+
+ tcp_gen_synack(hdr->tcp, cookie, tsopt, mss, wscale);
+
+ hdr->tcp_len = hdr->tcp->doff * 4;
+ hdr->ipv6->payload_len = bpf_htons(hdr->tcp_len);
+}
+
+static __always_inline int syncookie_handle_syn(struct header_pointers *hdr,
+ void *ctx,
+ void *data, void *data_end,
+ bool xdp)
+{
+ __u32 old_pkt_size, new_pkt_size;
+ /* Unlike clang 10, clang 11 and 12 generate code that doesn't pass the
+ * BPF verifier if tsopt is not volatile. Volatile forces it to store
+ * the pointer value and use it directly, otherwise tcp_mkoptions is
+ * (mis)compiled like this:
+ * if (!tsopt)
+ * return buf - start;
+ * reg = stored_return_value_of_tscookie_init;
+ * if (reg)
+ * tsopt = tsopt_buf;
+ * else
+ * tsopt = NULL;
+ * ...
+ * *buf++ = tsopt[1];
+ * It creates a dead branch where tsopt is assigned NULL, but the
+ * verifier can't prove it's dead and blocks the program.
+ */
+ __be32 * volatile tsopt = NULL;
+ __be32 tsopt_buf[2] = {};
+ __u16 ip_len;
+ __u32 cookie;
+ __s64 value;
+
+ /* Checksum is not yet verified, but both checksum failure and TCP
+ * header checks return XDP_DROP, so the order doesn't matter.
+ */
+ if (hdr->tcp->fin || hdr->tcp->rst)
+ return XDP_DROP;
+
+ /* Issue SYN cookies on allowed ports, drop SYN packets on blocked
+ * ports.
+ */
+ if (!check_port_allowed(bpf_ntohs(hdr->tcp->dest)))
+ return XDP_DROP;
+
+ if (hdr->ipv4) {
+ /* Check the IPv4 and TCP checksums before creating a SYNACK. */
+ value = bpf_csum_diff(0, 0, (void *)hdr->ipv4, hdr->ipv4->ihl * 4, 0);
+ if (value < 0)
+ return XDP_ABORTED;
+ if (csum_fold(value) != 0)
+ return XDP_DROP; /* Bad IPv4 checksum. */
+
+ value = bpf_csum_diff(0, 0, (void *)hdr->tcp, hdr->tcp_len, 0);
+ if (value < 0)
+ return XDP_ABORTED;
+ if (csum_tcpudp_magic(hdr->ipv4->saddr, hdr->ipv4->daddr,
+ hdr->tcp_len, IPPROTO_TCP, value) != 0)
+ return XDP_DROP; /* Bad TCP checksum. */
+
+ ip_len = sizeof(*hdr->ipv4);
+
+ value = bpf_tcp_raw_gen_syncookie_ipv4(hdr->ipv4, hdr->tcp,
+ hdr->tcp_len);
+ } else if (hdr->ipv6) {
+ /* Check the TCP checksum before creating a SYNACK. */
+ value = bpf_csum_diff(0, 0, (void *)hdr->tcp, hdr->tcp_len, 0);
+ if (value < 0)
+ return XDP_ABORTED;
+ if (csum_ipv6_magic(&hdr->ipv6->saddr, &hdr->ipv6->daddr,
+ hdr->tcp_len, IPPROTO_TCP, value) != 0)
+ return XDP_DROP; /* Bad TCP checksum. */
+
+ ip_len = sizeof(*hdr->ipv6);
+
+ value = bpf_tcp_raw_gen_syncookie_ipv6(hdr->ipv6, hdr->tcp,
+ hdr->tcp_len);
+ } else {
+ return XDP_ABORTED;
+ }
+
+ if (value < 0)
+ return XDP_ABORTED;
+ cookie = (__u32)value;
+
+ if (tscookie_init((void *)hdr->tcp, hdr->tcp_len,
+ &tsopt_buf[0], &tsopt_buf[1], data_end))
+ tsopt = tsopt_buf;
+
+ /* Check that there is enough space for a SYNACK. It also covers
+ * the check that the destination of the __builtin_memmove below
+ * doesn't overflow.
+ */
+ if (data + sizeof(*hdr->eth) + ip_len + TCP_MAXLEN > data_end)
+ return XDP_ABORTED;
+
+ if (hdr->ipv4) {
+ if (hdr->ipv4->ihl * 4 > sizeof(*hdr->ipv4)) {
+ struct tcphdr *new_tcp_header;
+
+ new_tcp_header = data + sizeof(*hdr->eth) + sizeof(*hdr->ipv4);
+ __builtin_memmove(new_tcp_header, hdr->tcp, sizeof(*hdr->tcp));
+ hdr->tcp = new_tcp_header;
+
+ hdr->ipv4->ihl = sizeof(*hdr->ipv4) / 4;
+ }
+
+ tcpv4_gen_synack(hdr, cookie, tsopt);
+ } else if (hdr->ipv6) {
+ tcpv6_gen_synack(hdr, cookie, tsopt);
+ } else {
+ return XDP_ABORTED;
+ }
+
+ /* Recalculate checksums. */
+ hdr->tcp->check = 0;
+ value = bpf_csum_diff(0, 0, (void *)hdr->tcp, hdr->tcp_len, 0);
+ if (value < 0)
+ return XDP_ABORTED;
+ if (hdr->ipv4) {
+ hdr->tcp->check = csum_tcpudp_magic(hdr->ipv4->saddr,
+ hdr->ipv4->daddr,
+ hdr->tcp_len,
+ IPPROTO_TCP,
+ value);
+
+ hdr->ipv4->check = 0;
+ value = bpf_csum_diff(0, 0, (void *)hdr->ipv4, sizeof(*hdr->ipv4), 0);
+ if (value < 0)
+ return XDP_ABORTED;
+ hdr->ipv4->check = csum_fold(value);
+ } else if (hdr->ipv6) {
+ hdr->tcp->check = csum_ipv6_magic(&hdr->ipv6->saddr,
+ &hdr->ipv6->daddr,
+ hdr->tcp_len,
+ IPPROTO_TCP,
+ value);
+ } else {
+ return XDP_ABORTED;
+ }
+
+ /* Set the new packet size. */
+ old_pkt_size = data_end - data;
+ new_pkt_size = sizeof(*hdr->eth) + ip_len + hdr->tcp->doff * 4;
+ if (xdp) {
+ if (bpf_xdp_adjust_tail(ctx, new_pkt_size - old_pkt_size))
+ return XDP_ABORTED;
+ } else {
+ if (bpf_skb_change_tail(ctx, new_pkt_size, 0))
+ return XDP_ABORTED;
+ }
+
+ values_inc_synacks();
+
+ return XDP_TX;
+}
+
+static __always_inline int syncookie_handle_ack(struct header_pointers *hdr)
+{
+ int err;
+
+ if (hdr->tcp->rst)
+ return XDP_DROP;
+
+ if (hdr->ipv4)
+ err = bpf_tcp_raw_check_syncookie_ipv4(hdr->ipv4, hdr->tcp);
+ else if (hdr->ipv6)
+ err = bpf_tcp_raw_check_syncookie_ipv6(hdr->ipv6, hdr->tcp);
+ else
+ return XDP_ABORTED;
+ if (err)
+ return XDP_DROP;
+
+ return XDP_PASS;
+}
+
+static __always_inline int syncookie_part1(void *ctx, void *data, void *data_end,
+ struct header_pointers *hdr, bool xdp)
+{
+ struct bpf_ct_opts ct_lookup_opts = {
+ .netns_id = BPF_F_CURRENT_NETNS,
+ .l4proto = IPPROTO_TCP,
+ };
+ int ret;
+
+ ret = tcp_dissect(data, data_end, hdr);
+ if (ret != XDP_TX)
+ return ret;
+
+ ret = tcp_lookup(ctx, hdr, xdp);
+ if (ret != XDP_TX)
+ return ret;
+
+ /* Packet is TCP and doesn't belong to an established connection. */
+
+ if ((hdr->tcp->syn ^ hdr->tcp->ack) != 1)
+ return XDP_DROP;
+
+ /* Grow the TCP header to TCP_MAXLEN to be able to pass any hdr->tcp_len
+ * to bpf_tcp_raw_gen_syncookie_ipv{4,6} and pass the verifier.
+ */
+ if (xdp) {
+ if (bpf_xdp_adjust_tail(ctx, TCP_MAXLEN - hdr->tcp_len))
+ return XDP_ABORTED;
+ } else {
+ /* Without volatile the verifier throws this error:
+ * R9 32-bit pointer arithmetic prohibited
+ */
+ volatile u64 old_len = data_end - data;
+
+ if (bpf_skb_change_tail(ctx, old_len + TCP_MAXLEN - hdr->tcp_len, 0))
+ return XDP_ABORTED;
+ }
+
+ return XDP_TX;
+}
+
+static __always_inline int syncookie_part2(void *ctx, void *data, void *data_end,
+ struct header_pointers *hdr, bool xdp)
+{
+ if (hdr->ipv4) {
+ hdr->eth = data;
+ hdr->ipv4 = (void *)hdr->eth + sizeof(*hdr->eth);
+ /* IPV4_MAXLEN is needed when calculating checksum.
+ * At least sizeof(struct iphdr) is needed here to access ihl.
+ */
+ if ((void *)hdr->ipv4 + IPV4_MAXLEN > data_end)
+ return XDP_ABORTED;
+ hdr->tcp = (void *)hdr->ipv4 + hdr->ipv4->ihl * 4;
+ } else if (hdr->ipv6) {
+ hdr->eth = data;
+ hdr->ipv6 = (void *)hdr->eth + sizeof(*hdr->eth);
+ hdr->tcp = (void *)hdr->ipv6 + sizeof(*hdr->ipv6);
+ } else {
+ return XDP_ABORTED;
+ }
+
+ if ((void *)hdr->tcp + TCP_MAXLEN > data_end)
+ return XDP_ABORTED;
+
+ /* We run out of registers, tcp_len gets spilled to the stack, and the
+ * verifier forgets its min and max values checked above in tcp_dissect.
+ */
+ hdr->tcp_len = hdr->tcp->doff * 4;
+ if (hdr->tcp_len < sizeof(*hdr->tcp))
+ return XDP_ABORTED;
+
+ return hdr->tcp->syn ? syncookie_handle_syn(hdr, ctx, data, data_end, xdp) :
+ syncookie_handle_ack(hdr);
+}
+
+SEC("xdp")
+int syncookie_xdp(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct header_pointers hdr;
+ int ret;
+
+ ret = syncookie_part1(ctx, data, data_end, &hdr, true);
+ if (ret != XDP_TX)
+ return ret;
+
+ data_end = (void *)(long)ctx->data_end;
+ data = (void *)(long)ctx->data;
+
+ return syncookie_part2(ctx, data, data_end, &hdr, true);
+}
+
+SEC("tc")
+int syncookie_tc(struct __sk_buff *skb)
+{
+ void *data_end = (void *)(long)skb->data_end;
+ void *data = (void *)(long)skb->data;
+ struct header_pointers hdr;
+ int ret;
+
+ ret = syncookie_part1(skb, data, data_end, &hdr, false);
+ if (ret != XDP_TX)
+ return ret == XDP_PASS ? TC_ACT_OK : TC_ACT_SHOT;
+
+ data_end = (void *)(long)skb->data_end;
+ data = (void *)(long)skb->data;
+
+ ret = syncookie_part2(skb, data, data_end, &hdr, false);
+ switch (ret) {
+ case XDP_PASS:
+ return TC_ACT_OK;
+ case XDP_TX:
+ return bpf_redirect(skb->ifindex, 0);
+ default:
+ return TC_ACT_SHOT;
+ }
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/xdp_synproxy.c b/tools/testing/selftests/bpf/xdp_synproxy.c
new file mode 100644
index 000000000000..d874ddfb39c4
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_synproxy.c
@@ -0,0 +1,466 @@
+// SPDX-License-Identifier: LGPL-2.1 OR BSD-2-Clause
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include <stdnoreturn.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <getopt.h>
+#include <signal.h>
+#include <sys/types.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <net/if.h>
+#include <linux/if_link.h>
+#include <linux/limits.h>
+
+static unsigned int ifindex;
+static __u32 attached_prog_id;
+static bool attached_tc;
+
+static void noreturn cleanup(int sig)
+{
+ LIBBPF_OPTS(bpf_xdp_attach_opts, opts);
+ int prog_fd;
+ int err;
+
+ if (attached_prog_id == 0)
+ exit(0);
+
+ if (attached_tc) {
+ LIBBPF_OPTS(bpf_tc_hook, hook,
+ .ifindex = ifindex,
+ .attach_point = BPF_TC_INGRESS);
+
+ err = bpf_tc_hook_destroy(&hook);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_tc_hook_destroy: %s\n", strerror(-err));
+ fprintf(stderr, "Failed to destroy the TC hook\n");
+ exit(1);
+ }
+ exit(0);
+ }
+
+ prog_fd = bpf_prog_get_fd_by_id(attached_prog_id);
+ if (prog_fd < 0) {
+ fprintf(stderr, "Error: bpf_prog_get_fd_by_id: %s\n", strerror(-prog_fd));
+ err = bpf_xdp_attach(ifindex, -1, 0, NULL);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_set_link_xdp_fd: %s\n", strerror(-err));
+ fprintf(stderr, "Failed to detach XDP program\n");
+ exit(1);
+ }
+ } else {
+ opts.old_prog_fd = prog_fd;
+ err = bpf_xdp_attach(ifindex, -1, XDP_FLAGS_REPLACE, &opts);
+ close(prog_fd);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_set_link_xdp_fd_opts: %s\n", strerror(-err));
+ /* Not an error if already replaced by someone else. */
+ if (err != -EEXIST) {
+ fprintf(stderr, "Failed to detach XDP program\n");
+ exit(1);
+ }
+ }
+ }
+ exit(0);
+}
+
+static noreturn void usage(const char *progname)
+{
+ fprintf(stderr, "Usage: %s [--iface <iface>|--prog <prog_id>] [--mss4 <mss ipv4> --mss6 <mss ipv6> --wscale <wscale> --ttl <ttl>] [--ports <port1>,<port2>,...] [--single] [--tc]\n",
+ progname);
+ exit(1);
+}
+
+static unsigned long parse_arg_ul(const char *progname, const char *arg, unsigned long limit)
+{
+ unsigned long res;
+ char *endptr;
+
+ errno = 0;
+ res = strtoul(arg, &endptr, 10);
+ if (errno != 0 || *endptr != '\0' || arg[0] == '\0' || res > limit)
+ usage(progname);
+
+ return res;
+}
+
+static void parse_options(int argc, char *argv[], unsigned int *ifindex, __u32 *prog_id,
+ __u64 *tcpipopts, char **ports, bool *single, bool *tc)
+{
+ static struct option long_options[] = {
+ { "help", no_argument, NULL, 'h' },
+ { "iface", required_argument, NULL, 'i' },
+ { "prog", required_argument, NULL, 'x' },
+ { "mss4", required_argument, NULL, 4 },
+ { "mss6", required_argument, NULL, 6 },
+ { "wscale", required_argument, NULL, 'w' },
+ { "ttl", required_argument, NULL, 't' },
+ { "ports", required_argument, NULL, 'p' },
+ { "single", no_argument, NULL, 's' },
+ { "tc", no_argument, NULL, 'c' },
+ { NULL, 0, NULL, 0 },
+ };
+ unsigned long mss4, mss6, wscale, ttl;
+ unsigned int tcpipopts_mask = 0;
+
+ if (argc < 2)
+ usage(argv[0]);
+
+ *ifindex = 0;
+ *prog_id = 0;
+ *tcpipopts = 0;
+ *ports = NULL;
+ *single = false;
+
+ while (true) {
+ int opt;
+
+ opt = getopt_long(argc, argv, "", long_options, NULL);
+ if (opt == -1)
+ break;
+
+ switch (opt) {
+ case 'h':
+ usage(argv[0]);
+ break;
+ case 'i':
+ *ifindex = if_nametoindex(optarg);
+ if (*ifindex == 0)
+ usage(argv[0]);
+ break;
+ case 'x':
+ *prog_id = parse_arg_ul(argv[0], optarg, UINT32_MAX);
+ if (*prog_id == 0)
+ usage(argv[0]);
+ break;
+ case 4:
+ mss4 = parse_arg_ul(argv[0], optarg, UINT16_MAX);
+ tcpipopts_mask |= 1 << 0;
+ break;
+ case 6:
+ mss6 = parse_arg_ul(argv[0], optarg, UINT16_MAX);
+ tcpipopts_mask |= 1 << 1;
+ break;
+ case 'w':
+ wscale = parse_arg_ul(argv[0], optarg, 14);
+ tcpipopts_mask |= 1 << 2;
+ break;
+ case 't':
+ ttl = parse_arg_ul(argv[0], optarg, UINT8_MAX);
+ tcpipopts_mask |= 1 << 3;
+ break;
+ case 'p':
+ *ports = optarg;
+ break;
+ case 's':
+ *single = true;
+ break;
+ case 'c':
+ *tc = true;
+ break;
+ default:
+ usage(argv[0]);
+ }
+ }
+ if (optind < argc)
+ usage(argv[0]);
+
+ if (tcpipopts_mask == 0xf) {
+ if (mss4 == 0 || mss6 == 0 || wscale == 0 || ttl == 0)
+ usage(argv[0]);
+ *tcpipopts = (mss6 << 32) | (ttl << 24) | (wscale << 16) | mss4;
+ } else if (tcpipopts_mask != 0) {
+ usage(argv[0]);
+ }
+
+ if (*ifindex != 0 && *prog_id != 0)
+ usage(argv[0]);
+ if (*ifindex == 0 && *prog_id == 0)
+ usage(argv[0]);
+}
+
+static int syncookie_attach(const char *argv0, unsigned int ifindex, bool tc)
+{
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
+ char xdp_filename[PATH_MAX];
+ struct bpf_program *prog;
+ struct bpf_object *obj;
+ int prog_fd;
+ int err;
+
+ snprintf(xdp_filename, sizeof(xdp_filename), "%s_kern.o", argv0);
+ obj = bpf_object__open_file(xdp_filename, NULL);
+ err = libbpf_get_error(obj);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_object__open_file: %s\n", strerror(-err));
+ return err;
+ }
+
+ err = bpf_object__load(obj);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_object__open_file: %s\n", strerror(-err));
+ return err;
+ }
+
+ prog = bpf_object__find_program_by_name(obj, tc ? "syncookie_tc" : "syncookie_xdp");
+ if (!prog) {
+ fprintf(stderr, "Error: bpf_object__find_program_by_name: program was not found\n");
+ return -ENOENT;
+ }
+
+ prog_fd = bpf_program__fd(prog);
+
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_obj_get_info_by_fd: %s\n", strerror(-err));
+ goto out;
+ }
+ attached_tc = tc;
+ attached_prog_id = info.id;
+ signal(SIGINT, cleanup);
+ signal(SIGTERM, cleanup);
+ if (tc) {
+ LIBBPF_OPTS(bpf_tc_hook, hook,
+ .ifindex = ifindex,
+ .attach_point = BPF_TC_INGRESS);
+ LIBBPF_OPTS(bpf_tc_opts, opts,
+ .handle = 1,
+ .priority = 1,
+ .prog_fd = prog_fd);
+
+ err = bpf_tc_hook_create(&hook);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_tc_hook_create: %s\n",
+ strerror(-err));
+ goto fail;
+ }
+ err = bpf_tc_attach(&hook, &opts);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_tc_attach: %s\n",
+ strerror(-err));
+ goto fail;
+ }
+
+ } else {
+ err = bpf_xdp_attach(ifindex, prog_fd,
+ XDP_FLAGS_UPDATE_IF_NOEXIST, NULL);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_set_link_xdp_fd: %s\n",
+ strerror(-err));
+ goto fail;
+ }
+ }
+ err = 0;
+out:
+ bpf_object__close(obj);
+ return err;
+fail:
+ signal(SIGINT, SIG_DFL);
+ signal(SIGTERM, SIG_DFL);
+ attached_prog_id = 0;
+ goto out;
+}
+
+static int syncookie_open_bpf_maps(__u32 prog_id, int *values_map_fd, int *ports_map_fd)
+{
+ struct bpf_prog_info prog_info;
+ __u32 map_ids[8];
+ __u32 info_len;
+ int prog_fd;
+ int err;
+ int i;
+
+ *values_map_fd = -1;
+ *ports_map_fd = -1;
+
+ prog_fd = bpf_prog_get_fd_by_id(prog_id);
+ if (prog_fd < 0) {
+ fprintf(stderr, "Error: bpf_prog_get_fd_by_id: %s\n", strerror(-prog_fd));
+ return prog_fd;
+ }
+
+ prog_info = (struct bpf_prog_info) {
+ .nr_map_ids = 8,
+ .map_ids = (__u64)map_ids,
+ };
+ info_len = sizeof(prog_info);
+
+ err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
+ if (err != 0) {
+ fprintf(stderr, "Error: bpf_obj_get_info_by_fd: %s\n", strerror(-err));
+ goto out;
+ }
+
+ if (prog_info.nr_map_ids < 2) {
+ fprintf(stderr, "Error: Found %u BPF maps, expected at least 2\n",
+ prog_info.nr_map_ids);
+ err = -ENOENT;
+ goto out;
+ }
+
+ for (i = 0; i < prog_info.nr_map_ids; i++) {
+ struct bpf_map_info map_info = {};
+ int map_fd;
+
+ err = bpf_map_get_fd_by_id(map_ids[i]);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_map_get_fd_by_id: %s\n", strerror(-err));
+ goto err_close_map_fds;
+ }
+ map_fd = err;
+
+ info_len = sizeof(map_info);
+ err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len);
+ if (err != 0) {
+ fprintf(stderr, "Error: bpf_obj_get_info_by_fd: %s\n", strerror(-err));
+ close(map_fd);
+ goto err_close_map_fds;
+ }
+ if (strcmp(map_info.name, "values") == 0) {
+ *values_map_fd = map_fd;
+ continue;
+ }
+ if (strcmp(map_info.name, "allowed_ports") == 0) {
+ *ports_map_fd = map_fd;
+ continue;
+ }
+ close(map_fd);
+ }
+
+ if (*values_map_fd != -1 && *ports_map_fd != -1) {
+ err = 0;
+ goto out;
+ }
+
+ err = -ENOENT;
+
+err_close_map_fds:
+ if (*values_map_fd != -1)
+ close(*values_map_fd);
+ if (*ports_map_fd != -1)
+ close(*ports_map_fd);
+ *values_map_fd = -1;
+ *ports_map_fd = -1;
+
+out:
+ close(prog_fd);
+ return err;
+}
+
+int main(int argc, char *argv[])
+{
+ int values_map_fd, ports_map_fd;
+ __u64 tcpipopts;
+ bool firstiter;
+ __u64 prevcnt;
+ __u32 prog_id;
+ char *ports;
+ bool single;
+ int err = 0;
+ bool tc;
+
+ parse_options(argc, argv, &ifindex, &prog_id, &tcpipopts, &ports,
+ &single, &tc);
+
+ if (prog_id == 0) {
+ if (!tc) {
+ err = bpf_xdp_query_id(ifindex, 0, &prog_id);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_get_link_xdp_id: %s\n",
+ strerror(-err));
+ goto out;
+ }
+ }
+ if (prog_id == 0) {
+ err = syncookie_attach(argv[0], ifindex, tc);
+ if (err < 0)
+ goto out;
+ prog_id = attached_prog_id;
+ }
+ }
+
+ err = syncookie_open_bpf_maps(prog_id, &values_map_fd, &ports_map_fd);
+ if (err < 0)
+ goto out;
+
+ if (ports) {
+ __u16 port_last = 0;
+ __u32 port_idx = 0;
+ char *p = ports;
+
+ fprintf(stderr, "Replacing allowed ports\n");
+
+ while (p && *p != '\0') {
+ char *token = strsep(&p, ",");
+ __u16 port;
+
+ port = parse_arg_ul(argv[0], token, UINT16_MAX);
+ err = bpf_map_update_elem(ports_map_fd, &port_idx, &port, BPF_ANY);
+ if (err != 0) {
+ fprintf(stderr, "Error: bpf_map_update_elem: %s\n", strerror(-err));
+ fprintf(stderr, "Failed to add port %u (index %u)\n",
+ port, port_idx);
+ goto out_close_maps;
+ }
+ fprintf(stderr, "Added port %u\n", port);
+ port_idx++;
+ }
+ err = bpf_map_update_elem(ports_map_fd, &port_idx, &port_last, BPF_ANY);
+ if (err != 0) {
+ fprintf(stderr, "Error: bpf_map_update_elem: %s\n", strerror(-err));
+ fprintf(stderr, "Failed to add the terminator value 0 (index %u)\n",
+ port_idx);
+ goto out_close_maps;
+ }
+ }
+
+ if (tcpipopts) {
+ __u32 key = 0;
+
+ fprintf(stderr, "Replacing TCP/IP options\n");
+
+ err = bpf_map_update_elem(values_map_fd, &key, &tcpipopts, BPF_ANY);
+ if (err != 0) {
+ fprintf(stderr, "Error: bpf_map_update_elem: %s\n", strerror(-err));
+ goto out_close_maps;
+ }
+ }
+
+ if ((ports || tcpipopts) && attached_prog_id == 0 && !single)
+ goto out_close_maps;
+
+ prevcnt = 0;
+ firstiter = true;
+ while (true) {
+ __u32 key = 1;
+ __u64 value;
+
+ err = bpf_map_lookup_elem(values_map_fd, &key, &value);
+ if (err != 0) {
+ fprintf(stderr, "Error: bpf_map_lookup_elem: %s\n", strerror(-err));
+ goto out_close_maps;
+ }
+ if (firstiter) {
+ prevcnt = value;
+ firstiter = false;
+ }
+ if (single) {
+ printf("Total SYNACKs generated: %llu\n", value);
+ break;
+ }
+ printf("SYNACKs generated: %llu (total %llu)\n", value - prevcnt, value);
+ prevcnt = value;
+ sleep(1);
+ }
+
+out_close_maps:
+ close(values_map_fd);
+ close(ports_map_fd);
+out:
+ return err == 0 ? 0 : 1;
+}
generated by cgit v1.2.3 (git 2.0.4) at 2026-02-03 02:39:36 +0000