From 6f6183a39533d727deaa5061cadae6dd9e6744d0 Mon Sep 17 00:00:00 2001 From: Yiyang Chen Date: Thu, 18 Jun 2026 10:18:43 +0000 Subject: [PATCH 1/2] bpf: Guard conntrack opts error writes The conntrack lookup and allocation kfuncs take an opts pointer together with an opts__sz argument. The verifier checks only the memory range described by opts__sz, but the wrappers unconditionally write opts->error whenever the internal lookup or allocation helper returns an error. For an invalid size smaller than the end of opts->error, that write can land outside the verifier-checked range. Keep returning NULL for invalid arguments, but only report the error through opts->error when the supplied size includes the field. This preserves error reporting for the supported 12-byte and 16-byte layouts, and for other invalid sizes that still include opts->error. Fixes: b4c2b9593a1c ("net/netfilter: Add unstable CT lookup helpers for XDP and TC-BPF") Fixes: d7e79c97c00c ("net: netfilter: Add kfuncs to allocate and insert CT") Signed-off-by: Yiyang Chen Link: https://lore.kernel.org/r/9535e781fe14449b1d4e9bbc3baa7566a93bf512.1781765747.git.chenyy23@mails.tsinghua.edu.cn Signed-off-by: Alexei Starovoitov --- net/netfilter/nf_conntrack_bpf.c | 35 ++++++++++++-------------------- 1 file changed, 13 insertions(+), 22 deletions(-) diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index 40c261cd0af3..f98d1d4b42c3 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -65,6 +65,15 @@ enum { NF_BPF_CT_OPTS_SZ = 16, }; +static void *bpf_ct_opts_result(struct bpf_ct_opts *opts, u32 opts__sz, void *ret) +{ + if (!IS_ERR(ret)) + return ret; + if (opts__sz >= offsetofend(struct bpf_ct_opts, error)) + opts->error = PTR_ERR(ret); + return NULL; +} + static int bpf_nf_ct_tuple_parse(struct bpf_sock_tuple *bpf_tuple, u32 tuple_len, u8 protonum, u8 dir, struct nf_conntrack_tuple *tuple) @@ -297,12 +306,7 @@ bpf_xdp_ct_alloc(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, nfct = __bpf_nf_ct_alloc_entry(dev_net(ctx->rxq->dev), bpf_tuple, tuple__sz, opts, opts__sz, 10); - if (IS_ERR(nfct)) { - opts->error = PTR_ERR(nfct); - return NULL; - } - - return (struct nf_conn___init *)nfct; + return (struct nf_conn___init *)bpf_ct_opts_result(opts, opts__sz, nfct); } /* bpf_xdp_ct_lookup - Lookup CT entry for the given tuple, and acquire a @@ -331,11 +335,7 @@ bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, caller_net = dev_net(ctx->rxq->dev); nfct = __bpf_nf_ct_lookup(caller_net, bpf_tuple, tuple__sz, opts, opts__sz); - if (IS_ERR(nfct)) { - opts->error = PTR_ERR(nfct); - return NULL; - } - return nfct; + return bpf_ct_opts_result(opts, opts__sz, nfct); } /* bpf_skb_ct_alloc - Allocate a new CT entry @@ -363,12 +363,7 @@ bpf_skb_ct_alloc(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, net = skb->dev ? dev_net(skb->dev) : sock_net(skb->sk); nfct = __bpf_nf_ct_alloc_entry(net, bpf_tuple, tuple__sz, opts, opts__sz, 10); - if (IS_ERR(nfct)) { - opts->error = PTR_ERR(nfct); - return NULL; - } - - return (struct nf_conn___init *)nfct; + return (struct nf_conn___init *)bpf_ct_opts_result(opts, opts__sz, nfct); } /* bpf_skb_ct_lookup - Lookup CT entry for the given tuple, and acquire a @@ -397,11 +392,7 @@ bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, caller_net = skb->dev ? dev_net(skb->dev) : sock_net(skb->sk); nfct = __bpf_nf_ct_lookup(caller_net, bpf_tuple, tuple__sz, opts, opts__sz); - if (IS_ERR(nfct)) { - opts->error = PTR_ERR(nfct); - return NULL; - } - return nfct; + return bpf_ct_opts_result(opts, opts__sz, nfct); } /* bpf_ct_insert_entry - Add the provided entry into a CT map From 38ba6d43af3844ae502092ee9dcc47214e82acb8 Mon Sep 17 00:00:00 2001 From: Yiyang Chen Date: Thu, 18 Jun 2026 10:18:44 +0000 Subject: [PATCH 2/2] selftests/bpf: Cover small conntrack opts error writes Add a conntrack kfunc regression check for opts__sz values that do not cover opts->error. The BPF program initializes opts->error with a guard value, calls the lookup and allocation kfuncs with opts__sz set to sizeof(opts->netns_id), and verifies that the guard is still intact after the kfunc returns NULL. Without the conntrack wrapper guard, the kfunc error path overwrites that guard with -EINVAL even though the verifier checked only the first four bytes of the options object. Fixes: b4c2b9593a1c ("net/netfilter: Add unstable CT lookup helpers for XDP and TC-BPF") Fixes: d7e79c97c00c ("net: netfilter: Add kfuncs to allocate and insert CT") Signed-off-by: Yiyang Chen Link: https://lore.kernel.org/r/007dfd0341cd84560e4795a2a951cc56d4adff1d.1781765747.git.chenyy23@mails.tsinghua.edu.cn Signed-off-by: Alexei Starovoitov --- .../testing/selftests/bpf/prog_tests/bpf_nf.c | 6 +++++ .../testing/selftests/bpf/progs/test_bpf_nf.c | 26 +++++++++++++++++++ 2 files changed, 32 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c index b33dba4b126e..14d4c1793aed 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c @@ -5,6 +5,8 @@ #include "test_bpf_nf.skel.h" #include "test_bpf_nf_fail.skel.h" +#define CT_OPTS_ERROR_GUARD 0x12345678 + static char log_buf[1024 * 1024]; struct { @@ -119,6 +121,10 @@ static void test_bpf_nf_ct(int mode) ASSERT_EQ(skel->bss->test_einval_reserved_new, -EINVAL, "Test EINVAL for reserved in new struct not set to 0"); ASSERT_EQ(skel->bss->test_einval_netns_id, -EINVAL, "Test EINVAL for netns_id < -1"); ASSERT_EQ(skel->bss->test_einval_len_opts, -EINVAL, "Test EINVAL for len__opts != NF_BPF_CT_OPTS_SZ"); + ASSERT_EQ(skel->bss->test_einval_len_opts_small_lookup, CT_OPTS_ERROR_GUARD, + "Test no error write for lookup opts__sz before error field"); + ASSERT_EQ(skel->bss->test_einval_len_opts_small_alloc, CT_OPTS_ERROR_GUARD, + "Test no error write for alloc opts__sz before error field"); ASSERT_EQ(skel->bss->test_eproto_l4proto, -EPROTO, "Test EPROTO for l4proto != TCP or UDP"); ASSERT_EQ(skel->bss->test_enonet_netns_id, -ENONET, "Test ENONET for bad but valid netns_id"); ASSERT_EQ(skel->bss->test_enoent_lookup, -ENOENT, "Test ENOENT for failed lookup"); diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c index 076fbf03a126..df43649ecb78 100644 --- a/tools/testing/selftests/bpf/progs/test_bpf_nf.c +++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c @@ -10,6 +10,8 @@ #define EINVAL 22 #define ENOENT 2 +#define CT_OPTS_ERROR_GUARD 0x12345678 + #define NF_CT_ZONE_DIR_ORIG (1 << IP_CT_DIR_ORIGINAL) #define NF_CT_ZONE_DIR_REPL (1 << IP_CT_DIR_REPLY) @@ -19,6 +21,8 @@ int test_einval_reserved = 0; int test_einval_reserved_new = 0; int test_einval_netns_id = 0; int test_einval_len_opts = 0; +int test_einval_len_opts_small_lookup = 0; +int test_einval_len_opts_small_alloc = 0; int test_eproto_l4proto = 0; int test_enonet_netns_id = 0; int test_enoent_lookup = 0; @@ -124,6 +128,28 @@ nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32, else test_einval_len_opts = opts_def.error; + opts_def.error = CT_OPTS_ERROR_GUARD; + ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, + sizeof(opts_def.netns_id)); + if (ct) { + bpf_ct_release(ct); + test_einval_len_opts_small_lookup = -EINVAL; + } else { + test_einval_len_opts_small_lookup = opts_def.error; + } + + opts_def.error = CT_OPTS_ERROR_GUARD; + ct = alloc_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, + sizeof(opts_def.netns_id)); + if (ct) { + ct = bpf_ct_insert_entry(ct); + if (ct) + bpf_ct_release(ct); + test_einval_len_opts_small_alloc = -EINVAL; + } else { + test_einval_len_opts_small_alloc = opts_def.error; + } + opts_def.l4proto = IPPROTO_ICMP; ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def));