bpf: Add __bpf_kfunc tag to all kfuncs

Now that we have the __bpf_kfunc tag, we should use add it to all
existing kfuncs to ensure that they'll never be elided in LTO builds.

Signed-off-by: David Vernet <void@manifault.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/bpf/20230201173016.342758-4-void@manifault.com

9 files changed, 72 insertions, 71 deletions

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 7dbefa4fd2eb..af9827c4b351 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -484,7 +484,7 @@ out:
 __diag_push();
 __diag_ignore_all("-Wmissing-prototypes",
 		  "Global functions as their definitions will be in vmlinux BTF");
-int noinline bpf_fentry_test1(int a)
+__bpf_kfunc int bpf_fentry_test1(int a)
 {
 	return a + 1;
 }
@@ -529,23 +529,23 @@ int noinline bpf_fentry_test8(struct bpf_fentry_test_t *arg)
 	return (long)arg->a;
 }
 
-int noinline bpf_modify_return_test(int a, int *b)
+__bpf_kfunc int bpf_modify_return_test(int a, int *b)
 {
 	*b += 1;
 	return a + *b;
 }
 
-u64 noinline bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d)
+__bpf_kfunc u64 bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d)
 {
 	return a + b + c + d;
 }
 
-int noinline bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b)
+__bpf_kfunc int bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b)
 {
 	return a + b;
 }
 
-struct sock * noinline bpf_kfunc_call_test3(struct sock *sk)
+__bpf_kfunc struct sock *bpf_kfunc_call_test3(struct sock *sk)
 {
 	return sk;
 }
@@ -582,21 +582,21 @@ static struct prog_test_ref_kfunc prog_test_struct = {
 	.cnt = REFCOUNT_INIT(1),
 };
 
-noinline struct prog_test_ref_kfunc *
+__bpf_kfunc struct prog_test_ref_kfunc *
 bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr)
 {
 	refcount_inc(&prog_test_struct.cnt);
 	return &prog_test_struct;
 }
 
-noinline struct prog_test_member *
+__bpf_kfunc struct prog_test_member *
 bpf_kfunc_call_memb_acquire(void)
 {
 	WARN_ON_ONCE(1);
 	return NULL;
 }
 
-noinline void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p)
+__bpf_kfunc void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p)
 {
 	if (!p)
 		return;
@@ -604,11 +604,11 @@ noinline void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p)
 	refcount_dec(&p->cnt);
 }
 
-noinline void bpf_kfunc_call_memb_release(struct prog_test_member *p)
+__bpf_kfunc void bpf_kfunc_call_memb_release(struct prog_test_member *p)
 {
 }
 
-noinline void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p)
+__bpf_kfunc void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p)
 {
 	WARN_ON_ONCE(1);
 }
@@ -621,12 +621,14 @@ static int *__bpf_kfunc_call_test_get_mem(struct prog_test_ref_kfunc *p, const i
 	return (int *)p;
 }
 
-noinline int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size)
+__bpf_kfunc int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p,
+						  const int rdwr_buf_size)
 {
 	return __bpf_kfunc_call_test_get_mem(p, rdwr_buf_size);
 }
 
-noinline int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size)
+__bpf_kfunc int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p,
+						    const int rdonly_buf_size)
 {
 	return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size);
 }
@@ -636,16 +638,17 @@ noinline int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p,
  * Acquire functions must return struct pointers, so these ones are
  * failing.
  */
-noinline int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size)
+__bpf_kfunc int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p,
+						    const int rdonly_buf_size)
 {
 	return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size);
 }
 
-noinline void bpf_kfunc_call_int_mem_release(int *p)
+__bpf_kfunc void bpf_kfunc_call_int_mem_release(int *p)
 {
 }
 
-noinline struct prog_test_ref_kfunc *
+__bpf_kfunc struct prog_test_ref_kfunc *
 bpf_kfunc_call_test_kptr_get(struct prog_test_ref_kfunc **pp, int a, int b)
 {
 	struct prog_test_ref_kfunc *p = READ_ONCE(*pp);
@@ -694,47 +697,47 @@ struct prog_test_fail3 {
 	char arr2[];
 };
 
-noinline void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb)
+__bpf_kfunc void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb)
 {
 }
 
-noinline void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p)
+__bpf_kfunc void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p)
 {
 }
 
-noinline void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p)
+__bpf_kfunc void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p)
 {
 }
 
-noinline void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p)
+__bpf_kfunc void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p)
 {
 }
 
-noinline void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p)
+__bpf_kfunc void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p)
 {
 }
 
-noinline void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p)
+__bpf_kfunc void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p)
 {
 }
 
-noinline void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz)
+__bpf_kfunc void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz)
 {
 }
 
-noinline void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len)
+__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len)
 {
 }
 
-noinline void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len)
+__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len)
 {
 }
 
-noinline void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p)
+__bpf_kfunc void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p)
 {
 }
 
-noinline void bpf_kfunc_call_test_destructive(void)
+__bpf_kfunc void bpf_kfunc_call_test_destructive(void)
 {
 }
 
diff --git a/net/core/xdp.c b/net/core/xdp.c
index a5a7ecf6391c..787fb9f92b36 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -4,6 +4,7 @@
  * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
  */
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <linux/btf_ids.h>
 #include <linux/filter.h>
 #include <linux/types.h>
@@ -722,7 +723,7 @@ __diag_ignore_all("-Wmissing-prototypes",
  *
  * Returns 0 on success or ``-errno`` on error.
  */
-int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp)
+__bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp)
 {
 	return -EOPNOTSUPP;
 }
@@ -734,7 +735,7 @@ int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp)
  *
  * Returns 0 on success or ``-errno`` on error.
  */
-int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash)
+__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index d2c470524e58..146792cd26fe 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -295,7 +295,7 @@ static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain)
 }
 
 /* override sysctl_tcp_min_tso_segs */
-static u32 bbr_min_tso_segs(struct sock *sk)
+__bpf_kfunc static u32 bbr_min_tso_segs(struct sock *sk)
 {
 	return sk->sk_pacing_rate < (bbr_min_tso_rate >> 3) ? 1 : 2;
 }
@@ -328,7 +328,7 @@ static void bbr_save_cwnd(struct sock *sk)
 		bbr->prior_cwnd = max(bbr->prior_cwnd, tcp_snd_cwnd(tp));
 }
 
-static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event)
+__bpf_kfunc static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bbr *bbr = inet_csk_ca(sk);
@@ -1023,7 +1023,7 @@ static void bbr_update_model(struct sock *sk, const struct rate_sample *rs)
 	bbr_update_gains(sk);
 }
 
-static void bbr_main(struct sock *sk, const struct rate_sample *rs)
+__bpf_kfunc static void bbr_main(struct sock *sk, const struct rate_sample *rs)
 {
 	struct bbr *bbr = inet_csk_ca(sk);
 	u32 bw;
@@ -1035,7 +1035,7 @@ static void bbr_main(struct sock *sk, const struct rate_sample *rs)
 	bbr_set_cwnd(sk, rs, rs->acked_sacked, bw, bbr->cwnd_gain);
 }
 
-static void bbr_init(struct sock *sk)
+__bpf_kfunc static void bbr_init(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bbr *bbr = inet_csk_ca(sk);
@@ -1077,7 +1077,7 @@ static void bbr_init(struct sock *sk)
 	cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED);
 }
 
-static u32 bbr_sndbuf_expand(struct sock *sk)
+__bpf_kfunc static u32 bbr_sndbuf_expand(struct sock *sk)
 {
 	/* Provision 3 * cwnd since BBR may slow-start even during recovery. */
 	return 3;
@@ -1086,7 +1086,7 @@ static u32 bbr_sndbuf_expand(struct sock *sk)
 /* In theory BBR does not need to undo the cwnd since it does not
  * always reduce cwnd on losses (see bbr_main()). Keep it for now.
  */
-static u32 bbr_undo_cwnd(struct sock *sk)
+__bpf_kfunc static u32 bbr_undo_cwnd(struct sock *sk)
 {
 	struct bbr *bbr = inet_csk_ca(sk);
 
@@ -1097,7 +1097,7 @@ static u32 bbr_undo_cwnd(struct sock *sk)
 }
 
 /* Entering loss recovery, so save cwnd for when we exit or undo recovery. */
-static u32 bbr_ssthresh(struct sock *sk)
+__bpf_kfunc static u32 bbr_ssthresh(struct sock *sk)
 {
 	bbr_save_cwnd(sk);
 	return tcp_sk(sk)->snd_ssthresh;
@@ -1125,7 +1125,7 @@ static size_t bbr_get_info(struct sock *sk, u32 ext, int *attr,
 	return 0;
 }
 
-static void bbr_set_state(struct sock *sk, u8 new_state)
+__bpf_kfunc static void bbr_set_state(struct sock *sk, u8 new_state)
 {
 	struct bbr *bbr = inet_csk_ca(sk);
 
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index d3cae40749e8..db8b4b488c31 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -403,7 +403,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
  * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and
  * returns the leftover acks to adjust cwnd in congestion avoidance mode.
  */
-u32 tcp_slow_start(struct tcp_sock *tp, u32 acked)
+__bpf_kfunc u32 tcp_slow_start(struct tcp_sock *tp, u32 acked)
 {
 	u32 cwnd = min(tcp_snd_cwnd(tp) + acked, tp->snd_ssthresh);
 
@@ -417,7 +417,7 @@ EXPORT_SYMBOL_GPL(tcp_slow_start);
 /* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w),
  * for every packet that was ACKed.
  */
-void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked)
+__bpf_kfunc void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked)
 {
 	/* If credits accumulated at a higher w, apply them gently now. */
 	if (tp->snd_cwnd_cnt >= w) {
@@ -443,7 +443,7 @@ EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai);
 /* This is Jacobson's slow start and congestion avoidance.
  * SIGCOMM '88, p. 328.
  */
-void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
+__bpf_kfunc void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -462,7 +462,7 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid);
 
 /* Slow start threshold is half the congestion window (min 2) */
-u32 tcp_reno_ssthresh(struct sock *sk)
+__bpf_kfunc u32 tcp_reno_ssthresh(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 
@@ -470,7 +470,7 @@ u32 tcp_reno_ssthresh(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(tcp_reno_ssthresh);
 
-u32 tcp_reno_undo_cwnd(struct sock *sk)
+__bpf_kfunc u32 tcp_reno_undo_cwnd(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 768c10c1f649..0fd78ecb67e7 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -126,7 +126,7 @@ static inline void bictcp_hystart_reset(struct sock *sk)
 	ca->sample_cnt = 0;
 }
 
-static void cubictcp_init(struct sock *sk)
+__bpf_kfunc static void cubictcp_init(struct sock *sk)
 {
 	struct bictcp *ca = inet_csk_ca(sk);
 
@@ -139,7 +139,7 @@ static void cubictcp_init(struct sock *sk)
 		tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
 }
 
-static void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event)
+__bpf_kfunc static void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event)
 {
 	if (event == CA_EVENT_TX_START) {
 		struct bictcp *ca = inet_csk_ca(sk);
@@ -321,7 +321,7 @@ tcp_friendliness:
 	ca->cnt = max(ca->cnt, 2U);
 }
 
-static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
+__bpf_kfunc static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
@@ -338,7 +338,7 @@ static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 	tcp_cong_avoid_ai(tp, ca->cnt, acked);
 }
 
-static u32 cubictcp_recalc_ssthresh(struct sock *sk)
+__bpf_kfunc static u32 cubictcp_recalc_ssthresh(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
@@ -355,7 +355,7 @@ static u32 cubictcp_recalc_ssthresh(struct sock *sk)
 	return max((tcp_snd_cwnd(tp) * beta) / BICTCP_BETA_SCALE, 2U);
 }
 
-static void cubictcp_state(struct sock *sk, u8 new_state)
+__bpf_kfunc static void cubictcp_state(struct sock *sk, u8 new_state)
 {
 	if (new_state == TCP_CA_Loss) {
 		bictcp_reset(inet_csk_ca(sk));
@@ -445,7 +445,7 @@ static void hystart_update(struct sock *sk, u32 delay)
 	}
 }
 
-static void cubictcp_acked(struct sock *sk, const struct ack_sample *sample)
+__bpf_kfunc static void cubictcp_acked(struct sock *sk, const struct ack_sample *sample)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index e0a2ca7456ff..bb23bb5b387a 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -75,7 +75,7 @@ static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
 	ca->old_delivered_ce = tp->delivered_ce;
 }
 
-static void dctcp_init(struct sock *sk)
+__bpf_kfunc static void dctcp_init(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 
@@ -104,7 +104,7 @@ static void dctcp_init(struct sock *sk)
 	INET_ECN_dontxmit(sk);
 }
 
-static u32 dctcp_ssthresh(struct sock *sk)
+__bpf_kfunc static u32 dctcp_ssthresh(struct sock *sk)
 {
 	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -113,7 +113,7 @@ static u32 dctcp_ssthresh(struct sock *sk)
 	return max(tcp_snd_cwnd(tp) - ((tcp_snd_cwnd(tp) * ca->dctcp_alpha) >> 11U), 2U);
 }
 
-static void dctcp_update_alpha(struct sock *sk, u32 flags)
+__bpf_kfunc static void dctcp_update_alpha(struct sock *sk, u32 flags)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct dctcp *ca = inet_csk_ca(sk);
@@ -169,7 +169,7 @@ static void dctcp_react_to_loss(struct sock *sk)
 	tp->snd_ssthresh = max(tcp_snd_cwnd(tp) >> 1U, 2U);
 }
 
-static void dctcp_state(struct sock *sk, u8 new_state)
+__bpf_kfunc static void dctcp_state(struct sock *sk, u8 new_state)
 {
 	if (new_state == TCP_CA_Recovery &&
 	    new_state != inet_csk(sk)->icsk_ca_state)
@@ -179,7 +179,7 @@ static void dctcp_state(struct sock *sk, u8 new_state)
 	 */
 }
 
-static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
+__bpf_kfunc static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 {
 	struct dctcp *ca = inet_csk_ca(sk);
 
@@ -229,7 +229,7 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
 	return 0;
 }
 
-static u32 dctcp_cwnd_undo(struct sock *sk)
+__bpf_kfunc static u32 dctcp_cwnd_undo(struct sock *sk)
 {
 	const struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c
index 24002bc61e07..34913521c385 100644
--- a/net/netfilter/nf_conntrack_bpf.c
+++ b/net/netfilter/nf_conntrack_bpf.c
@@ -249,7 +249,7 @@ __diag_ignore_all("-Wmissing-prototypes",
  * @opts__sz	- Length of the bpf_ct_opts structure
  *		    Must be NF_BPF_CT_OPTS_SZ (12)
  */
-struct nf_conn___init *
+__bpf_kfunc struct nf_conn___init *
 bpf_xdp_ct_alloc(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple,
 		 u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz)
 {
@@ -283,7 +283,7 @@ bpf_xdp_ct_alloc(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple,
  * @opts__sz	- Length of the bpf_ct_opts structure
  *		    Must be NF_BPF_CT_OPTS_SZ (12)
  */
-struct nf_conn *
+__bpf_kfunc struct nf_conn *
 bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple,
 		  u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz)
 {
@@ -316,7 +316,7 @@ bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple,
  * @opts__sz	- Length of the bpf_ct_opts structure
  *		    Must be NF_BPF_CT_OPTS_SZ (12)
  */
-struct nf_conn___init *
+__bpf_kfunc struct nf_conn___init *
 bpf_skb_ct_alloc(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple,
 		 u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz)
 {
@@ -351,7 +351,7 @@ bpf_skb_ct_alloc(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple,
  * @opts__sz	- Length of the bpf_ct_opts structure
  *		    Must be NF_BPF_CT_OPTS_SZ (12)
  */
-struct nf_conn *
+__bpf_kfunc struct nf_conn *
 bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple,
 		  u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz)
 {
@@ -376,7 +376,7 @@ bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple,
  * @nfct	 - Pointer to referenced nf_conn___init object, obtained
  *		   using bpf_xdp_ct_alloc or bpf_skb_ct_alloc.
  */
-struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i)
+__bpf_kfunc struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i)
 {
 	struct nf_conn *nfct = (struct nf_conn *)nfct_i;
 	int err;
@@ -400,7 +400,7 @@ struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i)
  * @nf_conn	 - Pointer to referenced nf_conn object, obtained using
  *		   bpf_xdp_ct_lookup or bpf_skb_ct_lookup.
  */
-void bpf_ct_release(struct nf_conn *nfct)
+__bpf_kfunc void bpf_ct_release(struct nf_conn *nfct)
 {
 	if (!nfct)
 		return;
@@ -417,7 +417,7 @@ void bpf_ct_release(struct nf_conn *nfct)
  *                 bpf_xdp_ct_alloc or bpf_skb_ct_alloc.
  * @timeout      - Timeout in msecs.
  */
-void bpf_ct_set_timeout(struct nf_conn___init *nfct, u32 timeout)
+__bpf_kfunc void bpf_ct_set_timeout(struct nf_conn___init *nfct, u32 timeout)
 {
 	__nf_ct_set_timeout((struct nf_conn *)nfct, msecs_to_jiffies(timeout));
 }
@@ -432,7 +432,7 @@ void bpf_ct_set_timeout(struct nf_conn___init *nfct, u32 timeout)
  *		   bpf_ct_insert_entry, bpf_xdp_ct_lookup, or bpf_skb_ct_lookup.
  * @timeout      - New timeout in msecs.
  */
-int bpf_ct_change_timeout(struct nf_conn *nfct, u32 timeout)
+__bpf_kfunc int bpf_ct_change_timeout(struct nf_conn *nfct, u32 timeout)
 {
 	return __nf_ct_change_timeout(nfct, msecs_to_jiffies(timeout));
 }
@@ -447,7 +447,7 @@ int bpf_ct_change_timeout(struct nf_conn *nfct, u32 timeout)
  *		   bpf_xdp_ct_alloc or bpf_skb_ct_alloc.
  * @status       - New status value.
  */
-int bpf_ct_set_status(const struct nf_conn___init *nfct, u32 status)
+__bpf_kfunc int bpf_ct_set_status(const struct nf_conn___init *nfct, u32 status)
 {
 	return nf_ct_change_status_common((struct nf_conn *)nfct, status);
 }
@@ -462,7 +462,7 @@ int bpf_ct_set_status(const struct nf_conn___init *nfct, u32 status)
  *		   bpf_ct_insert_entry, bpf_xdp_ct_lookup or bpf_skb_ct_lookup.
  * @status       - New status value.
  */
-int bpf_ct_change_status(struct nf_conn *nfct, u32 status)
+__bpf_kfunc int bpf_ct_change_status(struct nf_conn *nfct, u32 status)
 {
 	return nf_ct_change_status_common(nfct, status);
 }
diff --git a/net/netfilter/nf_nat_bpf.c b/net/netfilter/nf_nat_bpf.c
index 0fa5a0bbb0ff..141ee7783223 100644
--- a/net/netfilter/nf_nat_bpf.c
+++ b/net/netfilter/nf_nat_bpf.c
@@ -30,9 +30,9 @@ __diag_ignore_all("-Wmissing-prototypes",
  *		  interpreted as select a random port.
  * @manip	- NF_NAT_MANIP_SRC or NF_NAT_MANIP_DST
  */
-int bpf_ct_set_nat_info(struct nf_conn___init *nfct,
-			union nf_inet_addr *addr, int port,
-			enum nf_nat_manip_type manip)
+__bpf_kfunc int bpf_ct_set_nat_info(struct nf_conn___init *nfct,
+				    union nf_inet_addr *addr, int port,
+				    enum nf_nat_manip_type manip)
 {
 	struct nf_conn *ct = (struct nf_conn *)nfct;
 	u16 proto = nf_ct_l3num(ct);
diff --git a/net/xfrm/xfrm_interface_bpf.c b/net/xfrm/xfrm_interface_bpf.c
index 1ef2162cebcf..d74f3fd20f2b 100644
--- a/net/xfrm/xfrm_interface_bpf.c
+++ b/net/xfrm/xfrm_interface_bpf.c
@@ -39,8 +39,7 @@ __diag_ignore_all("-Wmissing-prototypes",
  * @to		- Pointer to memory to which the metadata will be copied
  *		    Cannot be NULL
  */
-__used noinline
-int bpf_skb_get_xfrm_info(struct __sk_buff *skb_ctx, struct bpf_xfrm_info *to)
+__bpf_kfunc int bpf_skb_get_xfrm_info(struct __sk_buff *skb_ctx, struct bpf_xfrm_info *to)
 {
 	struct sk_buff *skb = (struct sk_buff *)skb_ctx;
 	struct xfrm_md_info *info;
@@ -62,9 +61,7 @@ int bpf_skb_get_xfrm_info(struct __sk_buff *skb_ctx, struct bpf_xfrm_info *to)
  * @from	- Pointer to memory from which the metadata will be copied
  *		    Cannot be NULL
  */
-__used noinline
-int bpf_skb_set_xfrm_info(struct __sk_buff *skb_ctx,
-			  const struct bpf_xfrm_info *from)
+__bpf_kfunc int bpf_skb_set_xfrm_info(struct __sk_buff *skb_ctx, const struct bpf_xfrm_info *from)
 {
 	struct sk_buff *skb = (struct sk_buff *)skb_ctx;
 	struct metadata_dst *md_dst;