diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e7ee089e8a31a..8f6e87f0f3a89 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -767,12 +767,15 @@ enum bpf_type_flag { */ MEM_WRITE = BIT(18 + BPF_BASE_TYPE_BITS), + /* DYNPTR points to skb_metadata_end()-skb_metadata_len() */ + DYNPTR_TYPE_SKB_META = BIT(19 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; #define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF | DYNPTR_TYPE_SKB \ - | DYNPTR_TYPE_XDP) + | DYNPTR_TYPE_XDP | DYNPTR_TYPE_SKB_META) /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) @@ -1358,6 +1361,8 @@ enum bpf_dynptr_type { BPF_DYNPTR_TYPE_SKB, /* Underlying data is a xdp_buff */ BPF_DYNPTR_TYPE_XDP, + /* Points to skb_metadata_end()-skb_metadata_len() */ + BPF_DYNPTR_TYPE_SKB_META, }; int bpf_dynptr_check_size(u32 size); diff --git a/include/linux/filter.h b/include/linux/filter.h index 1e7fd3ee759e0..9ed21b65e2e96 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1784,6 +1784,7 @@ int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len); void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush); +void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset); #else /* CONFIG_NET */ static inline int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) @@ -1818,6 +1819,11 @@ static inline void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, voi unsigned long len, bool flush) { } + +static inline void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset) +{ + return NULL; +} #endif /* CONFIG_NET */ #endif /* __LINUX_FILTER_H__ */ diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 6b4877e85a68c..cdffd74ddbe65 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1780,6 +1780,9 @@ static int __bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr_kern *s return __bpf_skb_load_bytes(src->data, src->offset + offset, dst, len); case BPF_DYNPTR_TYPE_XDP: return __bpf_xdp_load_bytes(src->data, src->offset + offset, dst, len); + case BPF_DYNPTR_TYPE_SKB_META: + memmove(dst, bpf_skb_meta_pointer(src->data, src->offset + offset), len); + return 0; default: WARN_ONCE(true, "bpf_dynptr_read: unknown dynptr type %d\n", type); return -EFAULT; @@ -1836,6 +1839,11 @@ int __bpf_dynptr_write(const struct bpf_dynptr_kern *dst, u32 offset, void *src, if (flags) return -EINVAL; return __bpf_xdp_store_bytes(dst->data, dst->offset + offset, src, len); + case BPF_DYNPTR_TYPE_SKB_META: + if (flags) + return -EINVAL; + memmove(bpf_skb_meta_pointer(dst->data, dst->offset + offset), src, len); + return 0; default: WARN_ONCE(true, "bpf_dynptr_write: unknown dynptr type %d\n", type); return -EFAULT; @@ -1882,6 +1890,7 @@ BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u3 return (unsigned long)(ptr->data + ptr->offset + offset); case BPF_DYNPTR_TYPE_SKB: case BPF_DYNPTR_TYPE_XDP: + case BPF_DYNPTR_TYPE_SKB_META: /* skb and xdp dynptrs should use bpf_dynptr_slice / bpf_dynptr_slice_rdwr */ return 0; default: @@ -2710,6 +2719,8 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr *p, u32 offset, bpf_xdp_copy_buf(ptr->data, ptr->offset + offset, buffer__opt, len, false); return buffer__opt; } + case BPF_DYNPTR_TYPE_SKB_META: + return bpf_skb_meta_pointer(ptr->data, ptr->offset + offset); default: WARN_ONCE(true, "unknown dynptr type %d\n", type); return NULL; diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c index 38050f4ee4003..e4983c1303e76 100644 --- a/kernel/bpf/log.c +++ b/kernel/bpf/log.c @@ -498,6 +498,8 @@ const char *dynptr_type_str(enum bpf_dynptr_type type) return "skb"; case BPF_DYNPTR_TYPE_XDP: return "xdp"; + case BPF_DYNPTR_TYPE_SKB_META: + return "skb_meta"; case BPF_DYNPTR_TYPE_INVALID: return ""; default: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a61d579966923..2006d06d08048 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -674,6 +674,8 @@ static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type) return BPF_DYNPTR_TYPE_SKB; case DYNPTR_TYPE_XDP: return BPF_DYNPTR_TYPE_XDP; + case DYNPTR_TYPE_SKB_META: + return BPF_DYNPTR_TYPE_SKB_META; default: return BPF_DYNPTR_TYPE_INVALID; } @@ -690,6 +692,8 @@ static enum bpf_type_flag get_dynptr_type_flag(enum bpf_dynptr_type type) return DYNPTR_TYPE_SKB; case BPF_DYNPTR_TYPE_XDP: return DYNPTR_TYPE_XDP; + case BPF_DYNPTR_TYPE_SKB_META: + return DYNPTR_TYPE_SKB_META; default: return 0; } @@ -2274,7 +2278,8 @@ static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg) static bool reg_is_dynptr_slice_pkt(const struct bpf_reg_state *reg) { return base_type(reg->type) == PTR_TO_MEM && - (reg->type & DYNPTR_TYPE_SKB || reg->type & DYNPTR_TYPE_XDP); + (reg->type & + (DYNPTR_TYPE_SKB | DYNPTR_TYPE_XDP | DYNPTR_TYPE_SKB_META)); } /* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */ @@ -11641,7 +11646,8 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn if (dynptr_type == BPF_DYNPTR_TYPE_INVALID) return -EFAULT; - if (dynptr_type == BPF_DYNPTR_TYPE_SKB) + if (dynptr_type == BPF_DYNPTR_TYPE_SKB || + dynptr_type == BPF_DYNPTR_TYPE_SKB_META) /* this will trigger clear_all_pkt_pointers(), which will * invalidate all dynptr slices associated with the skb */ @@ -12228,6 +12234,7 @@ enum special_kfunc_type { KF_bpf_rbtree_right, KF_bpf_dynptr_from_skb, KF_bpf_dynptr_from_xdp, + KF_bpf_dynptr_from_skb_meta, KF_bpf_dynptr_slice, KF_bpf_dynptr_slice_rdwr, KF_bpf_dynptr_clone, @@ -12277,9 +12284,11 @@ BTF_ID(func, bpf_rbtree_right) #ifdef CONFIG_NET BTF_ID(func, bpf_dynptr_from_skb) BTF_ID(func, bpf_dynptr_from_xdp) +BTF_ID(func, bpf_dynptr_from_skb_meta) #else BTF_ID_UNUSED BTF_ID_UNUSED +BTF_ID_UNUSED #endif BTF_ID(func, bpf_dynptr_slice) BTF_ID(func, bpf_dynptr_slice_rdwr) @@ -13253,6 +13262,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ dynptr_arg_type |= DYNPTR_TYPE_SKB; } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_xdp]) { dynptr_arg_type |= DYNPTR_TYPE_XDP; + } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb_meta]) { + dynptr_arg_type |= DYNPTR_TYPE_SKB_META; } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_clone] && (dynptr_arg_type & MEM_UNINIT)) { enum bpf_dynptr_type parent_type = meta->initialized_dynptr.type; diff --git a/net/core/filter.c b/net/core/filter.c index da391e2b0788d..5aa228c720afe 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -11990,6 +11990,16 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return func; } +/** + * bpf_skb_meta_pointer() - Gets a mutable pointer within the skb metadata area. + * @skb: socket buffer carrying the metadata + * @offset: offset into the metadata area, must be <= skb_metadata_len() + */ +void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset) +{ + return skb_metadata_end(skb) - skb_metadata_len(skb) + offset; +} + __bpf_kfunc_start_defs(); __bpf_kfunc int bpf_dynptr_from_skb(struct __sk_buff *s, u64 flags, struct bpf_dynptr *ptr__uninit) @@ -12007,6 +12017,36 @@ __bpf_kfunc int bpf_dynptr_from_skb(struct __sk_buff *s, u64 flags, return 0; } +/** + * bpf_dynptr_from_skb_meta() - Initialize a dynptr to the skb metadata area. + * @skb_: socket buffer carrying the metadata + * @flags: future use, must be zero + * @ptr__uninit: dynptr to initialize + * + * Set up a dynptr for access to the metadata area earlier allocated from the + * XDP context with bpf_xdp_adjust_meta(). Serves as an alternative to + * &__sk_buff->data_meta. + * + * Return: + * * %0 - dynptr ready to use + * * %-EINVAL - invalid flags, dynptr set to null + */ +__bpf_kfunc int bpf_dynptr_from_skb_meta(struct __sk_buff *skb_, u64 flags, + struct bpf_dynptr *ptr__uninit) +{ + struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; + struct sk_buff *skb = (struct sk_buff *)skb_; + + if (flags) { + bpf_dynptr_set_null(ptr); + return -EINVAL; + } + + bpf_dynptr_init(ptr, skb, BPF_DYNPTR_TYPE_SKB_META, 0, skb_metadata_len(skb)); + + return 0; +} + __bpf_kfunc int bpf_dynptr_from_xdp(struct xdp_md *x, u64 flags, struct bpf_dynptr *ptr__uninit) { @@ -12181,6 +12221,10 @@ BTF_KFUNCS_START(bpf_kfunc_check_set_skb) BTF_ID_FLAGS(func, bpf_dynptr_from_skb, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_kfunc_check_set_skb) +BTF_KFUNCS_START(bpf_kfunc_check_set_skb_meta) +BTF_ID_FLAGS(func, bpf_dynptr_from_skb_meta, KF_TRUSTED_ARGS) +BTF_KFUNCS_END(bpf_kfunc_check_set_skb_meta) + BTF_KFUNCS_START(bpf_kfunc_check_set_xdp) BTF_ID_FLAGS(func, bpf_dynptr_from_xdp) BTF_KFUNCS_END(bpf_kfunc_check_set_xdp) @@ -12202,6 +12246,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_skb = { .set = &bpf_kfunc_check_set_skb, }; +static const struct btf_kfunc_id_set bpf_kfunc_set_skb_meta = { + .owner = THIS_MODULE, + .set = &bpf_kfunc_check_set_skb_meta, +}; + static const struct btf_kfunc_id_set bpf_kfunc_set_xdp = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_xdp, @@ -12237,6 +12286,8 @@ static int __init bpf_kfunc_init(void) ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_NETFILTER, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_kfunc_set_skb); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_skb_meta); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_ACT, &bpf_kfunc_set_skb_meta); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, &bpf_kfunc_set_sock_addr); diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h index 9386dfe8b8849..794d44d19c886 100644 --- a/tools/testing/selftests/bpf/bpf_kfuncs.h +++ b/tools/testing/selftests/bpf/bpf_kfuncs.h @@ -19,6 +19,9 @@ extern int bpf_dynptr_from_skb(struct __sk_buff *skb, __u64 flags, extern int bpf_dynptr_from_xdp(struct xdp_md *xdp, __u64 flags, struct bpf_dynptr *ptr__uninit) __ksym __weak; +extern int bpf_dynptr_from_skb_meta(struct __sk_buff *skb, __u64 flags, + struct bpf_dynptr *ptr__uninit) __ksym __weak; + /* Description * Obtain a read-only pointer to the dynptr's data * Returns diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 8916ab814a3ea..70b28c1e653ea 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -61,6 +61,7 @@ CONFIG_MPLS_IPTUNNEL=y CONFIG_MPLS_ROUTING=y CONFIG_MPTCP=y CONFIG_NET_ACT_GACT=y +CONFIG_NET_ACT_MIRRED=y CONFIG_NET_ACT_SKBMOD=y CONFIG_NET_CLS=y CONFIG_NET_CLS_ACT=y diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c index 9b2d9ceda2102..b9f86cb91e81b 100644 --- a/tools/testing/selftests/bpf/prog_tests/dynptr.c +++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c @@ -32,6 +32,8 @@ static struct { {"test_ringbuf", SETUP_SYSCALL_SLEEP}, {"test_skb_readonly", SETUP_SKB_PROG}, {"test_dynptr_skb_data", SETUP_SKB_PROG}, + {"test_dynptr_skb_meta_data", SETUP_SKB_PROG}, + {"test_dynptr_skb_meta_flags", SETUP_SKB_PROG}, {"test_adjust", SETUP_SYSCALL_SLEEP}, {"test_adjust_err", SETUP_SYSCALL_SLEEP}, {"test_zero_size_dynptr", SETUP_SYSCALL_SLEEP}, diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c index b9d9f0a502cea..6a59297f3f8df 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c @@ -9,6 +9,7 @@ #define TX_NETNS "xdp_context_tx" #define RX_NETNS "xdp_context_rx" #define TAP_NAME "tap0" +#define DUMMY_NAME "dum0" #define TAP_NETNS "xdp_context_tuntap" #define TEST_PAYLOAD_LEN 32 @@ -156,15 +157,30 @@ static int send_test_packet(int ifindex) return -1; } -static void assert_test_result(struct test_xdp_meta *skel) +static int write_test_packet(int tap_fd) +{ + __u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN]; + int n; + + /* The ethernet header doesn't need to be valid for this test */ + memset(packet, 0, sizeof(struct ethhdr)); + memcpy(packet + sizeof(struct ethhdr), test_payload, TEST_PAYLOAD_LEN); + + n = write(tap_fd, packet, sizeof(packet)); + if (!ASSERT_EQ(n, sizeof(packet), "write packet")) + return -1; + + return 0; +} + +static void assert_test_result(const struct bpf_map *result_map) { int err; __u32 map_key = 0; __u8 map_value[TEST_PAYLOAD_LEN]; - err = bpf_map__lookup_elem(skel->maps.test_result, &map_key, - sizeof(map_key), &map_value, - TEST_PAYLOAD_LEN, BPF_ANY); + err = bpf_map__lookup_elem(result_map, &map_key, sizeof(map_key), + &map_value, TEST_PAYLOAD_LEN, BPF_ANY); if (!ASSERT_OK(err, "lookup test_result")) return; @@ -172,6 +188,18 @@ static void assert_test_result(struct test_xdp_meta *skel) "test_result map contains test payload"); } +static bool clear_test_result(struct bpf_map *result_map) +{ + const __u8 v[sizeof(test_payload)] = {}; + const __u32 k = 0; + int err; + + err = bpf_map__update_elem(result_map, &k, sizeof(k), v, sizeof(v), BPF_ANY); + ASSERT_OK(err, "update test_result"); + + return err == 0; +} + void test_xdp_context_veth(void) { LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS); @@ -248,7 +276,7 @@ void test_xdp_context_veth(void) if (!ASSERT_OK(ret, "send_test_packet")) goto close; - assert_test_result(skel); + assert_test_result(skel->maps.test_result); close: close_netns(nstoken); @@ -257,17 +285,21 @@ void test_xdp_context_veth(void) netns_free(tx_ns); } -void test_xdp_context_tuntap(void) +static void test_tuntap(struct bpf_program *xdp_prog, + struct bpf_program *tc_prio_1_prog, + struct bpf_program *tc_prio_2_prog, + struct bpf_map *result_map) { LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS); LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); struct netns_obj *ns = NULL; - struct test_xdp_meta *skel = NULL; - __u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN]; int tap_fd = -1; int tap_ifindex; int ret; + if (!clear_test_result(result_map)) + return; + ns = netns_new(TAP_NETNS, true); if (!ASSERT_OK_PTR(ns, "create and open ns")) return; @@ -278,10 +310,6 @@ void test_xdp_context_tuntap(void) SYS(close, "ip link set dev " TAP_NAME " up"); - skel = test_xdp_meta__open_and_load(); - if (!ASSERT_OK_PTR(skel, "open and load skeleton")) - goto close; - tap_ifindex = if_nametoindex(TAP_NAME); if (!ASSERT_GE(tap_ifindex, 0, "if_nametoindex")) goto close; @@ -291,33 +319,159 @@ void test_xdp_context_tuntap(void) if (!ASSERT_OK(ret, "bpf_tc_hook_create")) goto close; - tc_opts.prog_fd = bpf_program__fd(skel->progs.ing_cls); + tc_opts.prog_fd = bpf_program__fd(tc_prio_1_prog); ret = bpf_tc_attach(&tc_hook, &tc_opts); if (!ASSERT_OK(ret, "bpf_tc_attach")) goto close; - ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(skel->progs.ing_xdp), + if (tc_prio_2_prog) { + LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 2, + .prog_fd = bpf_program__fd(tc_prio_2_prog)); + + ret = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) + goto close; + } + + ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(xdp_prog), 0, NULL); if (!ASSERT_GE(ret, 0, "bpf_xdp_attach")) goto close; - /* The ethernet header is not relevant for this test and doesn't need to - * be meaningful. - */ - struct ethhdr eth = { 0 }; + ret = write_test_packet(tap_fd); + if (!ASSERT_OK(ret, "write_test_packet")) + goto close; - memcpy(packet, ð, sizeof(eth)); - memcpy(packet + sizeof(eth), test_payload, TEST_PAYLOAD_LEN); + assert_test_result(result_map); + +close: + if (tap_fd >= 0) + close(tap_fd); + netns_free(ns); +} - ret = write(tap_fd, packet, sizeof(packet)); - if (!ASSERT_EQ(ret, sizeof(packet), "write packet")) +/* Write a packet to a tap dev and copy it to ingress of a dummy dev */ +static void test_tuntap_mirred(struct bpf_program *xdp_prog, + struct bpf_program *tc_prog, + bool *test_pass) +{ + LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS); + LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); + struct netns_obj *ns = NULL; + int dummy_ifindex; + int tap_fd = -1; + int tap_ifindex; + int ret; + + *test_pass = false; + + ns = netns_new(TAP_NETNS, true); + if (!ASSERT_OK_PTR(ns, "netns_new")) + return; + + /* Setup dummy interface */ + SYS(close, "ip link add name " DUMMY_NAME " type dummy"); + SYS(close, "ip link set dev " DUMMY_NAME " up"); + + dummy_ifindex = if_nametoindex(DUMMY_NAME); + if (!ASSERT_GE(dummy_ifindex, 0, "if_nametoindex")) + goto close; + + tc_hook.ifindex = dummy_ifindex; + ret = bpf_tc_hook_create(&tc_hook); + if (!ASSERT_OK(ret, "bpf_tc_hook_create")) + goto close; + + tc_opts.prog_fd = bpf_program__fd(tc_prog); + ret = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) + goto close; + + /* Setup TAP interface */ + tap_fd = open_tuntap(TAP_NAME, true); + if (!ASSERT_GE(tap_fd, 0, "open_tuntap")) + goto close; + + SYS(close, "ip link set dev " TAP_NAME " up"); + + tap_ifindex = if_nametoindex(TAP_NAME); + if (!ASSERT_GE(tap_ifindex, 0, "if_nametoindex")) + goto close; + + ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(xdp_prog), 0, NULL); + if (!ASSERT_GE(ret, 0, "bpf_xdp_attach")) goto close; - assert_test_result(skel); + /* Copy all packets received from TAP to dummy ingress */ + SYS(close, "tc qdisc add dev " TAP_NAME " clsact"); + SYS(close, "tc filter add dev " TAP_NAME " ingress " + "protocol all matchall " + "action mirred ingress mirror dev " DUMMY_NAME); + + /* Receive a packet on TAP */ + ret = write_test_packet(tap_fd); + if (!ASSERT_OK(ret, "write_test_packet")) + goto close; + + ASSERT_TRUE(*test_pass, "test_pass"); close: if (tap_fd >= 0) close(tap_fd); - test_xdp_meta__destroy(skel); netns_free(ns); } + +void test_xdp_context_tuntap(void) +{ + struct test_xdp_meta *skel = NULL; + + skel = test_xdp_meta__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open and load skeleton")) + return; + + if (test__start_subtest("data_meta")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.ing_cls, + NULL, /* tc prio 2 */ + skel->maps.test_result); + if (test__start_subtest("dynptr_read")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.ing_cls_dynptr_read, + NULL, /* tc prio 2 */ + skel->maps.test_result); + if (test__start_subtest("dynptr_slice")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.ing_cls_dynptr_slice, + NULL, /* tc prio 2 */ + skel->maps.test_result); + if (test__start_subtest("dynptr_write")) + test_tuntap(skel->progs.ing_xdp_zalloc_meta, + skel->progs.ing_cls_dynptr_write, + skel->progs.ing_cls_dynptr_read, + skel->maps.test_result); + if (test__start_subtest("dynptr_slice_rdwr")) + test_tuntap(skel->progs.ing_xdp_zalloc_meta, + skel->progs.ing_cls_dynptr_slice_rdwr, + skel->progs.ing_cls_dynptr_slice, + skel->maps.test_result); + if (test__start_subtest("dynptr_offset")) + test_tuntap(skel->progs.ing_xdp_zalloc_meta, + skel->progs.ing_cls_dynptr_offset_wr, + skel->progs.ing_cls_dynptr_offset_rd, + skel->maps.test_result); + if (test__start_subtest("dynptr_offset_oob")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.ing_cls_dynptr_offset_oob, + skel->progs.ing_cls, + skel->maps.test_result); + if (test__start_subtest("skb_clone_data_meta_empty")) + test_tuntap_mirred(skel->progs.ing_xdp, + skel->progs.ing_cls_data_meta_empty, + &skel->bss->test_pass); + if (test__start_subtest("skb_clone_dynptr_empty")) + test_tuntap_mirred(skel->progs.ing_xdp, + skel->progs.ing_cls_dynptr_empty, + &skel->bss->test_pass); + + test_xdp_meta__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index bd8f15229f5c7..dda6a8dada826 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -269,6 +269,26 @@ int data_slice_out_of_bounds_skb(struct __sk_buff *skb) return SK_PASS; } +/* A metadata slice can't be accessed out of bounds */ +SEC("?tc") +__failure __msg("value is outside of the allowed memory range") +int data_slice_out_of_bounds_skb_meta(struct __sk_buff *skb) +{ + struct bpf_dynptr meta; + __u8 *md; + + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + /* this should fail */ + *(md + 1) = 42; + + return SK_PASS; +} + SEC("?raw_tp") __failure __msg("value is outside of the allowed memory range") int data_slice_out_of_bounds_map_value(void *ctx) @@ -1089,6 +1109,26 @@ int skb_invalid_slice_write(struct __sk_buff *skb) return SK_PASS; } +/* bpf_dynptr_slice()s are read-only and cannot be written to */ +SEC("?tc") +__failure __msg("R{{[0-9]+}} cannot write into rdonly_mem") +int skb_meta_invalid_slice_write(struct __sk_buff *skb) +{ + struct bpf_dynptr meta; + __u8 *md; + + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + /* this should fail */ + *md = 42; + + return SK_PASS; +} + /* The read-only data slice is invalidated whenever a helper changes packet data */ SEC("?tc") __failure __msg("invalid mem access 'scalar'") @@ -1192,6 +1232,188 @@ int skb_invalid_data_slice4(struct __sk_buff *skb) return SK_PASS; } +/* Read-only skb data slice is invalidated on write to skb metadata */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int ro_skb_slice_invalid_after_metadata_write(struct __sk_buff *skb) +{ + struct bpf_dynptr data, meta; + __u8 *d; + + bpf_dynptr_from_skb(skb, 0, &data); + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + d = bpf_dynptr_slice(&data, 0, NULL, sizeof(*d)); + if (!d) + return SK_DROP; + + bpf_dynptr_write(&meta, 0, "x", 1, 0); + + /* this should fail */ + val = *d; + + return SK_PASS; +} + +/* Read-write skb data slice is invalidated on write to skb metadata */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int rw_skb_slice_invalid_after_metadata_write(struct __sk_buff *skb) +{ + struct bpf_dynptr data, meta; + __u8 *d; + + bpf_dynptr_from_skb(skb, 0, &data); + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + d = bpf_dynptr_slice_rdwr(&data, 0, NULL, sizeof(*d)); + if (!d) + return SK_DROP; + + bpf_dynptr_write(&meta, 0, "x", 1, 0); + + /* this should fail */ + *d = 42; + + return SK_PASS; +} + +/* Read-only skb metadata slice is invalidated on write to skb data */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int ro_skb_meta_slice_invalid_after_payload_write(struct __sk_buff *skb) +{ + struct bpf_dynptr data, meta; + __u8 *md; + + bpf_dynptr_from_skb(skb, 0, &data); + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + bpf_dynptr_write(&data, 0, "x", 1, 0); + + /* this should fail */ + val = *md; + + return SK_PASS; +} + +/* Read-write skb metadata slice is invalidated on write to skb data slice */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int rw_skb_meta_slice_invalid_after_payload_write(struct __sk_buff *skb) +{ + struct bpf_dynptr data, meta; + __u8 *md; + + bpf_dynptr_from_skb(skb, 0, &data); + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + bpf_dynptr_write(&data, 0, "x", 1, 0); + + /* this should fail */ + *md = 42; + + return SK_PASS; +} + +/* Read-only skb metadata slice is invalidated whenever a helper changes packet data */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int ro_skb_meta_slice_invalid_after_payload_helper(struct __sk_buff *skb) +{ + struct bpf_dynptr meta; + __u8 *md; + + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + if (bpf_skb_pull_data(skb, skb->len)) + return SK_DROP; + + /* this should fail */ + val = *md; + + return SK_PASS; +} + +/* Read-write skb metadata slice is invalidated whenever a helper changes packet data */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int rw_skb_meta_slice_invalid_after_payload_helper(struct __sk_buff *skb) +{ + struct bpf_dynptr meta; + __u8 *md; + + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + if (bpf_skb_pull_data(skb, skb->len)) + return SK_DROP; + + /* this should fail */ + *md = 42; + + return SK_PASS; +} + +/* Read-only skb metadata slice is invalidated on write to skb metadata */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int ro_skb_meta_slice_invalid_after_metadata_write(struct __sk_buff *skb) +{ + struct bpf_dynptr meta; + __u8 *md; + + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + bpf_dynptr_write(&meta, 0, "x", 1, 0); + + /* this should fail */ + val = *md; + + return SK_PASS; +} + +/* Read-write skb metadata slice is invalidated on write to skb metadata */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int rw_skb_meta_slice_invalid_after_metadata_write(struct __sk_buff *skb) +{ + struct bpf_dynptr meta; + __u8 *md; + + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + bpf_dynptr_write(&meta, 0, "x", 1, 0); + + /* this should fail */ + *md = 42; + + return SK_PASS; +} + /* The read-only data slice is invalidated whenever a helper changes packet data */ SEC("?xdp") __failure __msg("invalid mem access 'scalar'") @@ -1255,6 +1477,19 @@ int skb_invalid_ctx(void *ctx) return 0; } +/* Only supported prog type can create skb_meta-type dynptrs */ +SEC("?raw_tp") +__failure __msg("calling kernel function bpf_dynptr_from_skb_meta is not allowed") +int skb_meta_invalid_ctx(void *ctx) +{ + struct bpf_dynptr meta; + + /* this should fail */ + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + + return 0; +} + SEC("fentry/skb_tx_error") __failure __msg("must be referenced or trusted") int BPF_PROG(skb_invalid_ctx_fentry, void *skb) @@ -1665,6 +1900,29 @@ int clone_skb_packet_data(struct __sk_buff *skb) return 0; } +/* A skb clone's metadata slice becomes invalid anytime packet data changes */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int clone_skb_packet_meta(struct __sk_buff *skb) +{ + struct bpf_dynptr clone, meta; + __u8 *md; + + bpf_dynptr_from_skb_meta(skb, 0, &meta); + bpf_dynptr_clone(&meta, &clone); + md = bpf_dynptr_slice_rdwr(&clone, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + if (bpf_skb_pull_data(skb, skb->len)) + return SK_DROP; + + /* this should fail */ + *md = 42; + + return 0; +} + /* A xdp clone's data slices should be invalid anytime packet data changes */ SEC("?xdp") __failure __msg("invalid mem access 'scalar'") diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c index 8315273cb900c..127dea342e5a6 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_success.c +++ b/tools/testing/selftests/bpf/progs/dynptr_success.c @@ -211,6 +211,61 @@ int test_dynptr_skb_data(struct __sk_buff *skb) return 1; } +SEC("?tc") +int test_dynptr_skb_meta_data(struct __sk_buff *skb) +{ + struct bpf_dynptr meta; + __u8 *md; + int ret; + + err = 1; + ret = bpf_dynptr_from_skb_meta(skb, 0, &meta); + if (ret) + return 1; + + /* This should return NULL. Must use bpf_dynptr_slice API */ + err = 2; + md = bpf_dynptr_data(&meta, 0, sizeof(*md)); + if (md) + return 1; + + err = 0; + return 1; +} + +/* Check that skb metadata dynptr ops don't accept any flags. */ +SEC("?tc") +int test_dynptr_skb_meta_flags(struct __sk_buff *skb) +{ + const __u64 INVALID_FLAGS = ~0ULL; + struct bpf_dynptr meta; + __u8 buf; + int ret; + + err = 1; + ret = bpf_dynptr_from_skb_meta(skb, INVALID_FLAGS, &meta); + if (ret != -EINVAL) + return 1; + + err = 2; + ret = bpf_dynptr_from_skb_meta(skb, 0, &meta); + if (ret) + return 1; + + err = 3; + ret = bpf_dynptr_read(&buf, 0, &meta, 0, INVALID_FLAGS); + if (ret != -EINVAL) + return 1; + + err = 4; + ret = bpf_dynptr_write(&meta, 0, &buf, 0, INVALID_FLAGS); + if (ret != -EINVAL) + return 1; + + err = 0; + return 1; +} + SEC("tp/syscalls/sys_enter_nanosleep") int test_adjust(void *ctx) { diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c index fcf6ca14f2ea2..b2363852479c6 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c @@ -1,8 +1,11 @@ +#include #include +#include #include #include #include +#include "bpf_kfuncs.h" #define META_SIZE 32 @@ -23,6 +26,8 @@ struct { __uint(value_size, META_SIZE); } test_result SEC(".maps"); +bool test_pass; + SEC("tc") int ing_cls(struct __sk_buff *ctx) { @@ -40,6 +45,281 @@ int ing_cls(struct __sk_buff *ctx) return TC_ACT_SHOT; } +/* Check that skb->data_meta..skb->data is empty */ +SEC("tc") +int ing_cls_data_meta_empty(struct __sk_buff *ctx) +{ + struct ethhdr *eth = ctx_ptr(ctx, data); + + if (eth + 1 > ctx_ptr(ctx, data_end)) + goto out; + /* Ignore non-test packets */ + if (eth->h_proto != 0) + goto out; + /* Packet write to trigger unclone in prologue */ + eth->h_proto = 42; + + /* Expect no metadata */ + if (ctx->data_meta < ctx->data) + goto out; + + test_pass = true; +out: + return TC_ACT_SHOT; +} + +/* Check that skb_meta dynptr is empty */ +SEC("tc") +int ing_cls_dynptr_empty(struct __sk_buff *ctx) +{ + struct bpf_dynptr data, meta; + struct ethhdr *eth; + + bpf_dynptr_from_skb(ctx, 0, &data); + eth = bpf_dynptr_slice_rdwr(&data, 0, NULL, sizeof(*eth)); + if (!eth) + goto out; + /* Ignore non-test packets */ + if (eth->h_proto != 0) + goto out; + /* Packet write to trigger unclone in prologue */ + eth->h_proto = 42; + + /* Expect no metadata */ + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + if (bpf_dynptr_size(&meta) > 0) + goto out; + + test_pass = true; +out: + return TC_ACT_SHOT; +} + +/* Read from metadata using bpf_dynptr_read helper */ +SEC("tc") +int ing_cls_dynptr_read(struct __sk_buff *ctx) +{ + struct bpf_dynptr meta; + const __u32 zero = 0; + __u8 *dst; + + dst = bpf_map_lookup_elem(&test_result, &zero); + if (!dst) + return TC_ACT_SHOT; + + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + bpf_dynptr_read(dst, META_SIZE, &meta, 0, 0); + + return TC_ACT_SHOT; +} + +/* Write to metadata using bpf_dynptr_write helper */ +SEC("tc") +int ing_cls_dynptr_write(struct __sk_buff *ctx) +{ + struct bpf_dynptr data, meta; + __u8 *src; + + bpf_dynptr_from_skb(ctx, 0, &data); + src = bpf_dynptr_slice(&data, sizeof(struct ethhdr), NULL, META_SIZE); + if (!src) + return TC_ACT_SHOT; + + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + bpf_dynptr_write(&meta, 0, src, META_SIZE, 0); + + return TC_ACT_UNSPEC; /* pass */ +} + +/* Read from metadata using read-only dynptr slice */ +SEC("tc") +int ing_cls_dynptr_slice(struct __sk_buff *ctx) +{ + struct bpf_dynptr meta; + const __u32 zero = 0; + __u8 *dst, *src; + + dst = bpf_map_lookup_elem(&test_result, &zero); + if (!dst) + return TC_ACT_SHOT; + + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + src = bpf_dynptr_slice(&meta, 0, NULL, META_SIZE); + if (!src) + return TC_ACT_SHOT; + + __builtin_memcpy(dst, src, META_SIZE); + + return TC_ACT_SHOT; +} + +/* Write to metadata using writeable dynptr slice */ +SEC("tc") +int ing_cls_dynptr_slice_rdwr(struct __sk_buff *ctx) +{ + struct bpf_dynptr data, meta; + __u8 *src, *dst; + + bpf_dynptr_from_skb(ctx, 0, &data); + src = bpf_dynptr_slice(&data, sizeof(struct ethhdr), NULL, META_SIZE); + if (!src) + return TC_ACT_SHOT; + + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + dst = bpf_dynptr_slice_rdwr(&meta, 0, NULL, META_SIZE); + if (!dst) + return TC_ACT_SHOT; + + __builtin_memcpy(dst, src, META_SIZE); + + return TC_ACT_UNSPEC; /* pass */ +} + +/* Read skb metadata in chunks from various offsets in different ways. */ +SEC("tc") +int ing_cls_dynptr_offset_rd(struct __sk_buff *ctx) +{ + struct bpf_dynptr meta; + const __u32 chunk_len = META_SIZE / 4; + const __u32 zero = 0; + __u8 *dst, *src; + + dst = bpf_map_lookup_elem(&test_result, &zero); + if (!dst) + return TC_ACT_SHOT; + + /* 1. Regular read */ + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + bpf_dynptr_read(dst, chunk_len, &meta, 0, 0); + dst += chunk_len; + + /* 2. Read from an offset-adjusted dynptr */ + bpf_dynptr_adjust(&meta, chunk_len, bpf_dynptr_size(&meta)); + bpf_dynptr_read(dst, chunk_len, &meta, 0, 0); + dst += chunk_len; + + /* 3. Read at an offset */ + bpf_dynptr_read(dst, chunk_len, &meta, chunk_len, 0); + dst += chunk_len; + + /* 4. Read from a slice starting at an offset */ + src = bpf_dynptr_slice(&meta, 2 * chunk_len, NULL, chunk_len); + if (!src) + return TC_ACT_SHOT; + __builtin_memcpy(dst, src, chunk_len); + + return TC_ACT_SHOT; +} + +/* Write skb metadata in chunks at various offsets in different ways. */ +SEC("tc") +int ing_cls_dynptr_offset_wr(struct __sk_buff *ctx) +{ + const __u32 chunk_len = META_SIZE / 4; + __u8 payload[META_SIZE]; + struct bpf_dynptr meta; + __u8 *dst, *src; + + bpf_skb_load_bytes(ctx, sizeof(struct ethhdr), payload, sizeof(payload)); + src = payload; + + /* 1. Regular write */ + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + bpf_dynptr_write(&meta, 0, src, chunk_len, 0); + src += chunk_len; + + /* 2. Write to an offset-adjusted dynptr */ + bpf_dynptr_adjust(&meta, chunk_len, bpf_dynptr_size(&meta)); + bpf_dynptr_write(&meta, 0, src, chunk_len, 0); + src += chunk_len; + + /* 3. Write at an offset */ + bpf_dynptr_write(&meta, chunk_len, src, chunk_len, 0); + src += chunk_len; + + /* 4. Write to a slice starting at an offset */ + dst = bpf_dynptr_slice_rdwr(&meta, 2 * chunk_len, NULL, chunk_len); + if (!dst) + return TC_ACT_SHOT; + __builtin_memcpy(dst, src, chunk_len); + + return TC_ACT_UNSPEC; /* pass */ +} + +/* Pass an OOB offset to dynptr read, write, adjust, slice. */ +SEC("tc") +int ing_cls_dynptr_offset_oob(struct __sk_buff *ctx) +{ + struct bpf_dynptr meta; + __u8 md, *p; + int err; + + err = bpf_dynptr_from_skb_meta(ctx, 0, &meta); + if (err) + goto fail; + + /* read offset OOB */ + err = bpf_dynptr_read(&md, sizeof(md), &meta, META_SIZE, 0); + if (err != -E2BIG) + goto fail; + + /* write offset OOB */ + err = bpf_dynptr_write(&meta, META_SIZE, &md, sizeof(md), 0); + if (err != -E2BIG) + goto fail; + + /* adjust end offset OOB */ + err = bpf_dynptr_adjust(&meta, 0, META_SIZE + 1); + if (err != -ERANGE) + goto fail; + + /* adjust start offset OOB */ + err = bpf_dynptr_adjust(&meta, META_SIZE + 1, META_SIZE + 1); + if (err != -ERANGE) + goto fail; + + /* slice offset OOB */ + p = bpf_dynptr_slice(&meta, META_SIZE, NULL, sizeof(*p)); + if (p) + goto fail; + + /* slice rdwr offset OOB */ + p = bpf_dynptr_slice_rdwr(&meta, META_SIZE, NULL, sizeof(*p)); + if (p) + goto fail; + + return TC_ACT_UNSPEC; +fail: + return TC_ACT_SHOT; +} + +/* Reserve and clear space for metadata but don't populate it */ +SEC("xdp") +int ing_xdp_zalloc_meta(struct xdp_md *ctx) +{ + struct ethhdr *eth = ctx_ptr(ctx, data); + __u8 *meta; + int ret; + + /* Drop any non-test packets */ + if (eth + 1 > ctx_ptr(ctx, data_end)) + return XDP_DROP; + if (eth->h_proto != 0) + return XDP_DROP; + + ret = bpf_xdp_adjust_meta(ctx, -META_SIZE); + if (ret < 0) + return XDP_DROP; + + meta = ctx_ptr(ctx, data_meta); + if (meta + META_SIZE > ctx_ptr(ctx, data)) + return XDP_DROP; + + __builtin_memset(meta, 0, META_SIZE); + + return XDP_PASS; +} + SEC("xdp") int ing_xdp(struct xdp_md *ctx) {