Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2023-12-18

This PR is larger than usual and contains changes in various parts
of the kernel.

The main changes are:

1) Fix kCFI bugs in BPF, from Peter Zijlstra.

End result: all forms of indirect calls from BPF into kernel
and from kernel into BPF work with CFI enabled. This allows BPF
to work with CONFIG_FINEIBT=y.

2) Introduce BPF token object, from Andrii Nakryiko.

It adds an ability to delegate a subset of BPF features from privileged
daemon (e.g., systemd) through special mount options for userns-bound
BPF FS to a trusted unprivileged application. The design accommodates
suggestions from Christian Brauner and Paul Moore.

Example:
$ sudo mkdir -p /sys/fs/bpf/token
$ sudo mount -t bpf bpffs /sys/fs/bpf/token \
             -o delegate_cmds=prog_load:MAP_CREATE \
             -o delegate_progs=kprobe \
             -o delegate_attachs=xdp

3) Various verifier improvements and fixes, from Andrii Nakryiko, Andrei Matei.

 - Complete precision tracking support for register spills
 - Fix verification of possibly-zero-sized stack accesses
 - Fix access to uninit stack slots
 - Track aligned STACK_ZERO cases as imprecise spilled registers.
   It improves the verifier "instructions processed" metric from single
   digit to 50-60% for some programs.
 - Fix verifier retval logic

4) Support for VLAN tag in XDP hints, from Larysa Zaremba.

5) Allocate BPF trampoline via bpf_prog_pack mechanism, from Song Liu.

End result: better memory utilization and lower I$ miss for calls to BPF
via BPF trampoline.

6) Fix race between BPF prog accessing inner map and parallel delete,
from Hou Tao.

7) Add bpf_xdp_get_xfrm_state() kfunc, from Daniel Xu.

It allows BPF interact with IPSEC infra. The intent is to support
software RSS (via XDP) for the upcoming ipsec pcpu work.
Experiments on AWS demonstrate single tunnel pcpu ipsec reaching
line rate on 100G ENA nics.

8) Expand bpf_cgrp_storage to support cgroup1 non-attach, from Yafang Shao.

9) BPF file verification via fsverity, from Song Liu.

It allows BPF progs get fsverity digest.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (164 commits)
  bpf: Ensure precise is reset to false in __mark_reg_const_zero()
  selftests/bpf: Add more uprobe multi fail tests
  bpf: Fail uprobe multi link with negative offset
  selftests/bpf: Test the release of map btf
  s390/bpf: Fix indirect trampoline generation
  selftests/bpf: Temporarily disable dummy_struct_ops test on s390
  x86/cfi,bpf: Fix bpf_exception_cb() signature
  bpf: Fix dtor CFI
  cfi: Add CFI_NOSEAL()
  x86/cfi,bpf: Fix bpf_struct_ops CFI
  x86/cfi,bpf: Fix bpf_callback_t CFI
  x86/cfi,bpf: Fix BPF JIT call
  cfi: Flip headers
  selftests/bpf: Add test for abnormal cnt during multi-kprobe attachment
  selftests/bpf: Don't use libbpf_get_error() in kprobe_multi_test
  selftests/bpf: Add test for abnormal cnt during multi-uprobe attachment
  bpf: Limit the number of kprobes when attaching program to multiple kprobes
  bpf: Limit the number of uprobes when attaching program to multiple uprobes
  bpf: xdp: Register generic_kfunc_set with XDP programs
  selftests/bpf: utilize string values for delegate_xxx mount options
  ...
====================

Link: https://lore.kernel.org/r/20231219000520.34178-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

10 files changed, 317 insertions, 27 deletions

diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c
index 5918d1b32e19..8906f7bdf4a9 100644
--- a/net/bpf/bpf_dummy_struct_ops.c
+++ b/net/bpf/bpf_dummy_struct_ops.c
@@ -12,6 +12,11 @@ extern struct bpf_struct_ops bpf_bpf_dummy_ops;
 /* A common type for test_N with return value in bpf_dummy_ops */
 typedef int (*dummy_ops_test_ret_fn)(struct bpf_dummy_ops_state *state, ...);
 
+static int dummy_ops_test_ret_function(struct bpf_dummy_ops_state *state, ...)
+{
+	return 0;
+}
+
 struct bpf_dummy_ops_test_args {
 	u64 args[MAX_BPF_FUNC_ARGS];
 	struct bpf_dummy_ops_state state;
@@ -62,7 +67,7 @@ static int dummy_ops_copy_args(struct bpf_dummy_ops_test_args *args)
 
 static int dummy_ops_call_op(void *image, struct bpf_dummy_ops_test_args *args)
 {
-	dummy_ops_test_ret_fn test = (void *)image;
+	dummy_ops_test_ret_fn test = (void *)image + cfi_get_offset();
 	struct bpf_dummy_ops_state *state = NULL;
 
 	/* state needs to be NULL if args[0] is 0 */
@@ -101,12 +106,11 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 		goto out;
 	}
 
-	image = bpf_jit_alloc_exec(PAGE_SIZE);
+	image = arch_alloc_bpf_trampoline(PAGE_SIZE);
 	if (!image) {
 		err = -ENOMEM;
 		goto out;
 	}
-	set_vm_flush_reset_perms(image);
 
 	link = kzalloc(sizeof(*link), GFP_USER);
 	if (!link) {
@@ -120,11 +124,12 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 	op_idx = prog->expected_attach_type;
 	err = bpf_struct_ops_prepare_trampoline(tlinks, link,
 						&st_ops->func_models[op_idx],
+						&dummy_ops_test_ret_function,
 						image, image + PAGE_SIZE);
 	if (err < 0)
 		goto out;
 
-	set_memory_rox((long)image, 1);
+	arch_protect_bpf_trampoline(image, PAGE_SIZE);
 	prog_ret = dummy_ops_call_op(image, args);
 
 	err = dummy_ops_copy_args(args);
@@ -134,7 +139,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 		err = -EFAULT;
 out:
 	kfree(args);
-	bpf_jit_free_exec(image);
+	arch_free_bpf_trampoline(image, PAGE_SIZE);
 	if (link)
 		bpf_link_put(&link->link);
 	kfree(tlinks);
@@ -220,6 +225,28 @@ static void bpf_dummy_unreg(void *kdata)
 {
 }
 
+static int bpf_dummy_test_1(struct bpf_dummy_ops_state *cb)
+{
+	return 0;
+}
+
+static int bpf_dummy_test_2(struct bpf_dummy_ops_state *cb, int a1, unsigned short a2,
+			    char a3, unsigned long a4)
+{
+	return 0;
+}
+
+static int bpf_dummy_test_sleepable(struct bpf_dummy_ops_state *cb)
+{
+	return 0;
+}
+
+static struct bpf_dummy_ops __bpf_bpf_dummy_ops = {
+	.test_1 = bpf_dummy_test_1,
+	.test_2 = bpf_dummy_test_2,
+	.test_sleepable = bpf_dummy_test_sleepable,
+};
+
 struct bpf_struct_ops bpf_bpf_dummy_ops = {
 	.verifier_ops = &bpf_dummy_verifier_ops,
 	.init = bpf_dummy_init,
@@ -228,4 +255,5 @@ struct bpf_struct_ops bpf_bpf_dummy_ops = {
 	.reg = bpf_dummy_reg,
 	.unreg = bpf_dummy_unreg,
 	.name = "bpf_dummy_ops",
+	.cfi_stubs = &__bpf_bpf_dummy_ops,
 };
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 711cf5d59816..dfd919374017 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -600,10 +600,21 @@ __bpf_kfunc void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p)
 	refcount_dec(&p->cnt);
 }
 
+__bpf_kfunc void bpf_kfunc_call_test_release_dtor(void *p)
+{
+	bpf_kfunc_call_test_release(p);
+}
+CFI_NOSEAL(bpf_kfunc_call_test_release_dtor);
+
 __bpf_kfunc void bpf_kfunc_call_memb_release(struct prog_test_member *p)
 {
 }
 
+__bpf_kfunc void bpf_kfunc_call_memb_release_dtor(void *p)
+{
+}
+CFI_NOSEAL(bpf_kfunc_call_memb_release_dtor);
+
 __bpf_kfunc_end_defs();
 
 BTF_SET8_START(bpf_test_modify_return_ids)
@@ -1671,9 +1682,9 @@ static const struct btf_kfunc_id_set bpf_prog_test_kfunc_set = {
 
 BTF_ID_LIST(bpf_prog_test_dtor_kfunc_ids)
 BTF_ID(struct, prog_test_ref_kfunc)
-BTF_ID(func, bpf_kfunc_call_test_release)
+BTF_ID(func, bpf_kfunc_call_test_release_dtor)
 BTF_ID(struct, prog_test_member)
-BTF_ID(func, bpf_kfunc_call_memb_release)
+BTF_ID(func, bpf_kfunc_call_memb_release_dtor)
 
 static int __init bpf_prog_test_run_init(void)
 {
diff --git a/net/core/filter.c b/net/core/filter.c
index 6d89a9cf33c9..4ff6100c6a27 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -87,7 +87,7 @@
 #include "dev.h"
 
 static const struct bpf_func_proto *
-bpf_sk_base_func_proto(enum bpf_func_id func_id);
+bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog);
 
 int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len)
 {
@@ -7862,7 +7862,7 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
@@ -7955,7 +7955,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 			return NULL;
 		}
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -7974,7 +7974,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_skb_event_output_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8161,7 +8161,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #endif
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8220,7 +8220,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #endif
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 
 #if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)
@@ -8281,7 +8281,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_sock_proto;
 #endif /* CONFIG_INET */
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8323,7 +8323,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_cgroup_classid_curr_proto;
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8367,7 +8367,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skc_lookup_tcp_proto;
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8378,7 +8378,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_flow_dissector_load_bytes_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8405,7 +8405,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_under_cgroup:
 		return &bpf_skb_under_cgroup_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8580,7 +8580,7 @@ static bool cg_skb_is_valid_access(int off, int size,
 		return false;
 	case bpf_ctx_range(struct __sk_buff, data):
 	case bpf_ctx_range(struct __sk_buff, data_end):
-		if (!bpf_capable())
+		if (!bpf_token_capable(prog->aux->token, CAP_BPF))
 			return false;
 		break;
 	}
@@ -8592,7 +8592,7 @@ static bool cg_skb_is_valid_access(int off, int size,
 		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
 			break;
 		case bpf_ctx_range(struct __sk_buff, tstamp):
-			if (!bpf_capable())
+			if (!bpf_token_capable(prog->aux->token, CAP_BPF))
 				return false;
 			break;
 		default:
@@ -11236,7 +11236,7 @@ sk_reuseport_func_proto(enum bpf_func_id func_id,
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
@@ -11418,7 +11418,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -11752,7 +11752,7 @@ const struct bpf_func_proto bpf_sock_from_file_proto = {
 };
 
 static const struct bpf_func_proto *
-bpf_sk_base_func_proto(enum bpf_func_id func_id)
+bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	const struct bpf_func_proto *func;
 
@@ -11781,10 +11781,10 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 
-	if (!perfmon_capable())
+	if (!bpf_token_capable(prog->aux->token, CAP_PERFMON))
 		return NULL;
 
 	return func;
diff --git a/net/core/xdp.c b/net/core/xdp.c
index b6f1d6dab3f2..4869c1c2d8f3 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -736,6 +736,39 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash,
 	return -EOPNOTSUPP;
 }
 
+/**
+ * bpf_xdp_metadata_rx_vlan_tag - Get XDP packet outermost VLAN tag
+ * @ctx: XDP context pointer.
+ * @vlan_proto: Destination pointer for VLAN Tag protocol identifier (TPID).
+ * @vlan_tci: Destination pointer for VLAN TCI (VID + DEI + PCP)
+ *
+ * In case of success, ``vlan_proto`` contains *Tag protocol identifier (TPID)*,
+ * usually ``ETH_P_8021Q`` or ``ETH_P_8021AD``, but some networks can use
+ * custom TPIDs. ``vlan_proto`` is stored in **network byte order (BE)**
+ * and should be used as follows:
+ * ``if (vlan_proto == bpf_htons(ETH_P_8021Q)) do_something();``
+ *
+ * ``vlan_tci`` contains the remaining 16 bits of a VLAN tag.
+ * Driver is expected to provide those in **host byte order (usually LE)**,
+ * so the bpf program should not perform byte conversion.
+ * According to 802.1Q standard, *VLAN TCI (Tag control information)*
+ * is a bit field that contains:
+ * *VLAN identifier (VID)* that can be read with ``vlan_tci & 0xfff``,
+ * *Drop eligible indicator (DEI)* - 1 bit,
+ * *Priority code point (PCP)* - 3 bits.
+ * For detailed meaning of DEI and PCP, please refer to other sources.
+ *
+ * Return:
+ * * Returns 0 on success or ``-errno`` on error.
+ * * ``-EOPNOTSUPP`` : device driver doesn't implement kfunc
+ * * ``-ENODATA``    : VLAN tag was not stripped or is not available
+ */
+__bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
+					     __be16 *vlan_proto, u16 *vlan_tci)
+{
+	return -EOPNOTSUPP;
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_SET8_START(xdp_metadata_kfunc_ids)
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 39dcccf0f174..634cfafa583d 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -191,7 +191,7 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
@@ -271,6 +271,74 @@ static int bpf_tcp_ca_validate(void *kdata)
 	return tcp_validate_congestion_control(kdata);
 }
 
+static u32 bpf_tcp_ca_ssthresh(struct sock *sk)
+{
+	return 0;
+}
+
+static void bpf_tcp_ca_cong_avoid(struct sock *sk, u32 ack, u32 acked)
+{
+}
+
+static void bpf_tcp_ca_set_state(struct sock *sk, u8 new_state)
+{
+}
+
+static void bpf_tcp_ca_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
+{
+}
+
+static void bpf_tcp_ca_in_ack_event(struct sock *sk, u32 flags)
+{
+}
+
+static void bpf_tcp_ca_pkts_acked(struct sock *sk, const struct ack_sample *sample)
+{
+}
+
+static u32 bpf_tcp_ca_min_tso_segs(struct sock *sk)
+{
+	return 0;
+}
+
+static void bpf_tcp_ca_cong_control(struct sock *sk, const struct rate_sample *rs)
+{
+}
+
+static u32 bpf_tcp_ca_undo_cwnd(struct sock *sk)
+{
+	return 0;
+}
+
+static u32 bpf_tcp_ca_sndbuf_expand(struct sock *sk)
+{
+	return 0;
+}
+
+static void __bpf_tcp_ca_init(struct sock *sk)
+{
+}
+
+static void __bpf_tcp_ca_release(struct sock *sk)
+{
+}
+
+static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = {
+	.ssthresh = bpf_tcp_ca_ssthresh,
+	.cong_avoid = bpf_tcp_ca_cong_avoid,
+	.set_state = bpf_tcp_ca_set_state,
+	.cwnd_event = bpf_tcp_ca_cwnd_event,
+	.in_ack_event = bpf_tcp_ca_in_ack_event,
+	.pkts_acked = bpf_tcp_ca_pkts_acked,
+	.min_tso_segs = bpf_tcp_ca_min_tso_segs,
+	.cong_control = bpf_tcp_ca_cong_control,
+	.undo_cwnd = bpf_tcp_ca_undo_cwnd,
+	.sndbuf_expand = bpf_tcp_ca_sndbuf_expand,
+
+	.init = __bpf_tcp_ca_init,
+	.release = __bpf_tcp_ca_release,
+};
+
 struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.verifier_ops = &bpf_tcp_ca_verifier_ops,
 	.reg = bpf_tcp_ca_reg,
@@ -281,6 +349,7 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.init = bpf_tcp_ca_init,
 	.validate = bpf_tcp_ca_validate,
 	.name = "tcp_congestion_ops",
+	.cfi_stubs = &__bpf_ops_tcp_congestion_ops,
 };
 
 static int __init bpf_tcp_ca_kfunc_init(void)
diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c
index 0e4beae421f8..5257d5e7eb09 100644
--- a/net/netfilter/nf_bpf_link.c
+++ b/net/netfilter/nf_bpf_link.c
@@ -314,7 +314,7 @@ static bool nf_is_valid_access(int off, int size, enum bpf_access_type type,
 static const struct bpf_func_proto *
 bpf_nf_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
-	return bpf_base_func_proto(func_id);
+	return bpf_base_func_proto(func_id, prog);
 }
 
 const struct bpf_verifier_ops netfilter_verifier_ops = {
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 4f6f538a5462..28711cc44ced 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -125,6 +125,18 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
 }
 EXPORT_SYMBOL(xp_set_rxq_info);
 
+void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc)
+{
+	u32 i;
+
+	for (i = 0; i < pool->heads_cnt; i++) {
+		struct xdp_buff_xsk *xskb = &pool->heads[i];
+
+		memcpy(xskb->cb + desc->off, desc->src, desc->bytes);
+	}
+}
+EXPORT_SYMBOL(xp_fill_cb);
+
 static void xp_disable_drv_zc(struct xsk_buff_pool *pool)
 {
 	struct netdev_bpf bpf;
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
index cd47f88921f5..547cec77ba03 100644
--- a/net/xfrm/Makefile
+++ b/net/xfrm/Makefile
@@ -21,3 +21,4 @@ obj-$(CONFIG_XFRM_USER_COMPAT) += xfrm_compat.o
 obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o
 obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o
 obj-$(CONFIG_XFRM_ESPINTCP) += espintcp.o
+obj-$(CONFIG_DEBUG_INFO_BTF) += xfrm_state_bpf.o
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index c13dc3ef7910..1b7e75159727 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4218,6 +4218,8 @@ void __init xfrm_init(void)
 #ifdef CONFIG_XFRM_ESPINTCP
 	espintcp_init();
 #endif
+
+	register_xfrm_state_bpf();
 }
 
 #ifdef CONFIG_AUDITSYSCALL
diff --git a/net/xfrm/xfrm_state_bpf.c b/net/xfrm/xfrm_state_bpf.c
new file mode 100644
index 000000000000..9e20d4a377f7
--- /dev/null
+++ b/net/xfrm/xfrm_state_bpf.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Unstable XFRM state BPF helpers.
+ *
+ * Note that it is allowed to break compatibility for these functions since the
+ * interface they are exposed through to BPF programs is explicitly unstable.
+ */
+
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
+#include <net/xdp.h>
+#include <net/xfrm.h>
+
+/* bpf_xfrm_state_opts - Options for XFRM state lookup helpers
+ *
+ * Members:
+ * @error      - Out parameter, set for any errors encountered
+ *		 Values:
+ *		   -EINVAL - netns_id is less than -1
+ *		   -EINVAL - opts__sz isn't BPF_XFRM_STATE_OPTS_SZ
+ *		   -ENONET - No network namespace found for netns_id
+ *		   -ENOENT - No xfrm_state found
+ * @netns_id	- Specify the network namespace for lookup
+ *		 Values:
+ *		   BPF_F_CURRENT_NETNS (-1)
+ *		     Use namespace associated with ctx
+ *		   [0, S32_MAX]
+ *		     Network Namespace ID
+ * @mark	- XFRM mark to match on
+ * @daddr	- Destination address to match on
+ * @spi		- Security parameter index to match on
+ * @proto	- IP protocol to match on (eg. IPPROTO_ESP)
+ * @family	- Protocol family to match on (AF_INET/AF_INET6)
+ */
+struct bpf_xfrm_state_opts {
+	s32 error;
+	s32 netns_id;
+	u32 mark;
+	xfrm_address_t daddr;
+	__be32 spi;
+	u8 proto;
+	u16 family;
+};
+
+enum {
+	BPF_XFRM_STATE_OPTS_SZ = sizeof(struct bpf_xfrm_state_opts),
+};
+
+__bpf_kfunc_start_defs();
+
+/* bpf_xdp_get_xfrm_state - Get XFRM state
+ *
+ * A `struct xfrm_state *`, if found, must be released with a corresponding
+ * bpf_xdp_xfrm_state_release.
+ *
+ * Parameters:
+ * @ctx	- Pointer to ctx (xdp_md) in XDP program
+ *		    Cannot be NULL
+ * @opts	- Options for lookup (documented above)
+ *		    Cannot be NULL
+ * @opts__sz	- Length of the bpf_xfrm_state_opts structure
+ *		    Must be BPF_XFRM_STATE_OPTS_SZ
+ */
+__bpf_kfunc struct xfrm_state *
+bpf_xdp_get_xfrm_state(struct xdp_md *ctx, struct bpf_xfrm_state_opts *opts, u32 opts__sz)
+{
+	struct xdp_buff *xdp = (struct xdp_buff *)ctx;
+	struct net *net = dev_net(xdp->rxq->dev);
+	struct xfrm_state *x;
+
+	if (!opts || opts__sz < sizeof(opts->error))
+		return NULL;
+
+	if (opts__sz != BPF_XFRM_STATE_OPTS_SZ) {
+		opts->error = -EINVAL;
+		return NULL;
+	}
+
+	if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS)) {
+		opts->error = -EINVAL;
+		return NULL;
+	}
+
+	if (opts->netns_id >= 0) {
+		net = get_net_ns_by_id(net, opts->netns_id);
+		if (unlikely(!net)) {
+			opts->error = -ENONET;
+			return NULL;
+		}
+	}
+
+	x = xfrm_state_lookup(net, opts->mark, &opts->daddr, opts->spi,
+			      opts->proto, opts->family);
+
+	if (opts->netns_id >= 0)
+		put_net(net);
+	if (!x)
+		opts->error = -ENOENT;
+
+	return x;
+}
+
+/* bpf_xdp_xfrm_state_release - Release acquired xfrm_state object
+ *
+ * This must be invoked for referenced PTR_TO_BTF_ID, and the verifier rejects
+ * the program if any references remain in the program in all of the explored
+ * states.
+ *
+ * Parameters:
+ * @x		- Pointer to referenced xfrm_state object, obtained using
+ *		  bpf_xdp_get_xfrm_state.
+ */
+__bpf_kfunc void bpf_xdp_xfrm_state_release(struct xfrm_state *x)
+{
+	xfrm_state_put(x);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_SET8_START(xfrm_state_kfunc_set)
+BTF_ID_FLAGS(func, bpf_xdp_get_xfrm_state, KF_RET_NULL | KF_ACQUIRE)
+BTF_ID_FLAGS(func, bpf_xdp_xfrm_state_release, KF_RELEASE)
+BTF_SET8_END(xfrm_state_kfunc_set)
+
+static const struct btf_kfunc_id_set xfrm_state_xdp_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &xfrm_state_kfunc_set,
+};
+
+int __init register_xfrm_state_bpf(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP,
+					 &xfrm_state_xdp_kfunc_set);
+}