diff options
author | Alexei Starovoitov <ast@kernel.org> | 2023-04-21 11:35:51 -0700 |
---|---|---|
committer | Alexei Starovoitov <ast@kernel.org> | 2023-04-21 11:37:41 -0700 |
commit | d7a799ec782b6ae9158f8d587c9f49cf34a6c5f4 (patch) | |
tree | a3b43374a8f86d3ae74143bf60a2d493f4ea01af /tools | |
parent | 45cea721ea36d83969473d2abd29bcc2321cacdd (diff) | |
parent | 006c0e44ed924140d44bc756e6ea36301fcea68d (diff) | |
download | linux-d7a799ec782b6ae9158f8d587c9f49cf34a6c5f4.tar.gz linux-d7a799ec782b6ae9158f8d587c9f49cf34a6c5f4.tar.bz2 linux-d7a799ec782b6ae9158f8d587c9f49cf34a6c5f4.zip |
Merge branch 'bpf: add netfilter program type'
Florian Westphal says:
====================
Changes since last version:
- rework test case in last patch wrt. ctx->skb dereference etc (Alexei)
- pacify bpf ci tests, netfilter program type missed string translation
in libbpf helper.
This still uses runtime btf walk rather than extending
the btf trace array as Alexei suggested, I would do this later (or someone else can).
v1 cover letter:
Add minimal support to hook bpf programs to netfilter hooks, e.g.
PREROUTING or FORWARD.
For this the most relevant parts for registering a netfilter
hook via the in-kernel api are exposed to userspace via bpf_link.
The new program type is 'tracing style', i.e. there is no context
access rewrite done by verifier, the function argument (struct bpf_nf_ctx)
isn't stable.
There is no support for direct packet access, dynptr api should be used
instead.
With this its possible to build a small test program such as:
#include "vmlinux.h"
extern int bpf_dynptr_from_skb(struct __sk_buff *skb, __u64 flags,
struct bpf_dynptr *ptr__uninit) __ksym;
extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, uint32_t offset,
void *buffer, uint32_t buffer__sz) __ksym;
SEC("netfilter")
int nf_test(struct bpf_nf_ctx *ctx)
{
struct nf_hook_state *state = ctx->state;
struct sk_buff *skb = ctx->skb;
const struct iphdr *iph, _iph;
const struct tcphdr *th, _th;
struct bpf_dynptr ptr;
if (bpf_dynptr_from_skb(skb, 0, &ptr))
return NF_DROP;
iph = bpf_dynptr_slice(&ptr, 0, &_iph, sizeof(_iph));
if (!iph)
return NF_DROP;
th = bpf_dynptr_slice(&ptr, iph->ihl << 2, &_th, sizeof(_th));
if (!th)
return NF_DROP;
bpf_printk("accept %x:%d->%x:%d, hook %d ifin %d\n",
iph->saddr, bpf_ntohs(th->source), iph->daddr,
bpf_ntohs(th->dest), state->hook, state->in->ifindex);
return NF_ACCEPT;
}
Then, tail /sys/kernel/tracing/trace_pipe.
Changes since v3:
- uapi: remove 'reserved' struct member, s/prio/priority (Alexei)
- add ctx access test cases (Alexei, see last patch)
- some arm32 can only handle cmpxchg on u32 (build bot)
- Fix kdoc annotations (Simon Horman)
- bpftool: prefer p_err, not fprintf (Quentin)
- add test cases in separate patch
Changes since v2:
1. don't WARN when user calls 'bpftool loink detach' twice
restrict attachment to ip+ip6 families, lets relax this
later in case arp/bridge/netdev are needed too.
2. show netfilter links in 'bpftool net' output as well.
Changes since v1:
1. Don't fail to link when CONFIG_NETFILTER=n (build bot)
2. Use test_progs instead of test_verifier (Alexei)
Changes since last RFC version:
1. extend 'bpftool link show' to print prio/hooknum etc
2. extend 'nft list hooks' so it can print the bpf program id
3. Add an extra patch to artificially restrict bpf progs with
same priority. Its fine from a technical pov but it will
cause ordering issues (most recent one comes first).
Can be removed later.
4. Add test_run support for netfilter prog type and a small
extension to verifier tests to make sure we can't return
verdicts like NF_STOLEN.
5. Alter the netfilter part of the bpf_link uapi struct:
- add flags/reserved members.
Not used here except returning errors when they are nonzero.
Plan is to allow the bpf_link users to enable netfilter
defrag or conntrack engine by setting feature flags at
link create time in the future.
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'tools')
-rw-r--r-- | tools/bpf/bpftool/link.c | 83 | ||||
-rw-r--r-- | tools/bpf/bpftool/main.h | 3 | ||||
-rw-r--r-- | tools/bpf/bpftool/net.c | 106 | ||||
-rw-r--r-- | tools/include/uapi/linux/bpf.h | 14 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf.c | 3 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf_probes.c | 1 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/prog_tests/verifier.c | 4 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c | 121 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c | 49 |
9 files changed, 384 insertions, 0 deletions
diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index f985b79cca27..d98dbc50cf4c 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -3,6 +3,8 @@ #include <errno.h> #include <linux/err.h> +#include <linux/netfilter.h> +#include <linux/netfilter_arp.h> #include <net/if.h> #include <stdio.h> #include <unistd.h> @@ -135,6 +137,18 @@ static void show_iter_json(struct bpf_link_info *info, json_writer_t *wtr) } } +void netfilter_dump_json(const struct bpf_link_info *info, json_writer_t *wtr) +{ + jsonw_uint_field(json_wtr, "pf", + info->netfilter.pf); + jsonw_uint_field(json_wtr, "hook", + info->netfilter.hooknum); + jsonw_int_field(json_wtr, "prio", + info->netfilter.priority); + jsonw_uint_field(json_wtr, "flags", + info->netfilter.flags); +} + static int get_prog_info(int prog_id, struct bpf_prog_info *info) { __u32 len = sizeof(*info); @@ -195,6 +209,10 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) info->netns.netns_ino); show_link_attach_type_json(info->netns.attach_type, json_wtr); break; + case BPF_LINK_TYPE_NETFILTER: + netfilter_dump_json(info, json_wtr); + break; + default: break; } @@ -263,6 +281,68 @@ static void show_iter_plain(struct bpf_link_info *info) } } +static const char * const pf2name[] = { + [NFPROTO_INET] = "inet", + [NFPROTO_IPV4] = "ip", + [NFPROTO_ARP] = "arp", + [NFPROTO_NETDEV] = "netdev", + [NFPROTO_BRIDGE] = "bridge", + [NFPROTO_IPV6] = "ip6", +}; + +static const char * const inethook2name[] = { + [NF_INET_PRE_ROUTING] = "prerouting", + [NF_INET_LOCAL_IN] = "input", + [NF_INET_FORWARD] = "forward", + [NF_INET_LOCAL_OUT] = "output", + [NF_INET_POST_ROUTING] = "postrouting", +}; + +static const char * const arphook2name[] = { + [NF_ARP_IN] = "input", + [NF_ARP_OUT] = "output", +}; + +void netfilter_dump_plain(const struct bpf_link_info *info) +{ + const char *hookname = NULL, *pfname = NULL; + unsigned int hook = info->netfilter.hooknum; + unsigned int pf = info->netfilter.pf; + + if (pf < ARRAY_SIZE(pf2name)) + pfname = pf2name[pf]; + + switch (pf) { + case NFPROTO_BRIDGE: /* bridge shares numbers with enum nf_inet_hooks */ + case NFPROTO_IPV4: + case NFPROTO_IPV6: + case NFPROTO_INET: + if (hook < ARRAY_SIZE(inethook2name)) + hookname = inethook2name[hook]; + break; + case NFPROTO_ARP: + if (hook < ARRAY_SIZE(arphook2name)) + hookname = arphook2name[hook]; + default: + break; + } + + if (pfname) + printf("\n\t%s", pfname); + else + printf("\n\tpf: %d", pf); + + if (hookname) + printf(" %s", hookname); + else + printf(", hook %u,", hook); + + printf(" prio %d", info->netfilter.priority); + + if (info->netfilter.flags) + printf(" flags 0x%x", info->netfilter.flags); +} + static int show_link_close_plain(int fd, struct bpf_link_info *info) { struct bpf_prog_info prog_info; @@ -301,6 +381,9 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) printf("\n\tnetns_ino %u ", info->netns.netns_ino); show_link_attach_type_plain(info->netns.attach_type); break; + case BPF_LINK_TYPE_NETFILTER: + netfilter_dump_plain(info); + break; default: break; } diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 9a95788e654d..a49534d7eafa 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -267,4 +267,7 @@ static inline bool hashmap__empty(struct hashmap *map) int pathname_concat(char *buf, int buf_sz, const char *path, const char *name); +/* print netfilter bpf_link info */ +void netfilter_dump_plain(const struct bpf_link_info *info); +void netfilter_dump_json(const struct bpf_link_info *info, json_writer_t *wtr); #endif diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index c40e44c938ae..26a49965bf71 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -647,6 +647,108 @@ static int do_detach(int argc, char **argv) return 0; } +static int netfilter_link_compar(const void *a, const void *b) +{ + const struct bpf_link_info *nfa = a; + const struct bpf_link_info *nfb = b; + int delta; + + delta = nfa->netfilter.pf - nfb->netfilter.pf; + if (delta) + return delta; + + delta = nfa->netfilter.hooknum - nfb->netfilter.hooknum; + if (delta) + return delta; + + if (nfa->netfilter.priority < nfb->netfilter.priority) + return -1; + if (nfa->netfilter.priority > nfb->netfilter.priority) + return 1; + + return nfa->netfilter.flags - nfb->netfilter.flags; +} + +static void show_link_netfilter(void) +{ + unsigned int nf_link_len = 0, nf_link_count = 0; + struct bpf_link_info *nf_link_info = NULL; + __u32 id = 0; + + while (true) { + struct bpf_link_info info; + int fd, err; + __u32 len; + + err = bpf_link_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + break; + p_err("can't get next link: %s (id %d)", strerror(errno), id); + break; + } + + fd = bpf_link_get_fd_by_id(id); + if (fd < 0) { + p_err("can't get link by id (%u): %s", id, strerror(errno)); + continue; + } + + memset(&info, 0, sizeof(info)); + len = sizeof(info); + + err = bpf_link_get_info_by_fd(fd, &info, &len); + + close(fd); + + if (err) { + p_err("can't get link info for fd %d: %s", fd, strerror(errno)); + continue; + } + + if (info.type != BPF_LINK_TYPE_NETFILTER) + continue; + + if (nf_link_count >= nf_link_len) { + static const unsigned int max_link_count = INT_MAX / sizeof(info); + struct bpf_link_info *expand; + + if (nf_link_count > max_link_count) { + p_err("cannot handle more than %u links\n", max_link_count); + break; + } + + nf_link_len += 16; + + expand = realloc(nf_link_info, nf_link_len * sizeof(info)); + if (!expand) { + p_err("realloc: %s", strerror(errno)); + break; + } + + nf_link_info = expand; + } + + nf_link_info[nf_link_count] = info; + nf_link_count++; + } + + qsort(nf_link_info, nf_link_count, sizeof(*nf_link_info), netfilter_link_compar); + + for (id = 0; id < nf_link_count; id++) { + NET_START_OBJECT; + if (json_output) + netfilter_dump_json(&nf_link_info[id], json_wtr); + else + netfilter_dump_plain(&nf_link_info[id]); + + NET_DUMP_UINT("id", " prog_id %u", nf_link_info[id].prog_id); + NET_END_OBJECT; + } + + free(nf_link_info); +} + static int do_show(int argc, char **argv) { struct bpf_attach_info attach_info = {}; @@ -701,6 +803,10 @@ static int do_show(int argc, char **argv) NET_DUMP_UINT("id", "id %u", attach_info.flow_dissector_id); NET_END_ARRAY("\n"); + NET_START_ARRAY("netfilter", "%s:\n"); + show_link_netfilter(); + NET_END_ARRAY("\n"); + NET_END_OBJECT; if (json_output) jsonw_end_array(json_wtr); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 4b20a7269bee..1bb11a6ee667 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -986,6 +986,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_LSM, BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ + BPF_PROG_TYPE_NETFILTER, }; enum bpf_attach_type { @@ -1050,6 +1051,7 @@ enum bpf_link_type { BPF_LINK_TYPE_PERF_EVENT = 7, BPF_LINK_TYPE_KPROBE_MULTI = 8, BPF_LINK_TYPE_STRUCT_OPS = 9, + BPF_LINK_TYPE_NETFILTER = 10, MAX_BPF_LINK_TYPE, }; @@ -1560,6 +1562,12 @@ union bpf_attr { */ __u64 cookie; } tracing; + struct { + __u32 pf; + __u32 hooknum; + __s32 priority; + __u32 flags; + } netfilter; }; } link_create; @@ -6410,6 +6418,12 @@ struct bpf_link_info { struct { __u32 map_id; } struct_ops; + struct { + __u32 pf; + __u32 hooknum; + __s32 priority; + __u32 flags; + } netfilter; }; } __attribute__((aligned(8))); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 2600d8384252..1cbacf9e71f3 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -130,6 +130,7 @@ static const char * const link_type_name[] = { [BPF_LINK_TYPE_PERF_EVENT] = "perf_event", [BPF_LINK_TYPE_KPROBE_MULTI] = "kprobe_multi", [BPF_LINK_TYPE_STRUCT_OPS] = "struct_ops", + [BPF_LINK_TYPE_NETFILTER] = "netfilter", }; static const char * const map_type_name[] = { @@ -201,6 +202,7 @@ static const char * const prog_type_name[] = { [BPF_PROG_TYPE_LSM] = "lsm", [BPF_PROG_TYPE_SK_LOOKUP] = "sk_lookup", [BPF_PROG_TYPE_SYSCALL] = "syscall", + [BPF_PROG_TYPE_NETFILTER] = "netfilter", }; static int __base_pr(enum libbpf_print_level level, const char *format, @@ -8710,6 +8712,7 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE), SEC_DEF("struct_ops.s+", STRUCT_OPS, 0, SEC_SLEEPABLE), SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE), + SEC_DEF("netfilter", NETFILTER, 0, SEC_NONE), }; static size_t custom_sec_def_cnt; diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 4f3bc968ff8e..6065f408a59c 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -180,6 +180,7 @@ static int probe_prog_load(enum bpf_prog_type prog_type, case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_NETFILTER: break; default: return -EOPNOTSUPP; diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 7c68d78da9ea..7534f5499d11 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -29,6 +29,8 @@ #include "verifier_map_ret_val.skel.h" #include "verifier_masking.skel.h" #include "verifier_meta_access.skel.h" +#include "verifier_netfilter_ctx.skel.h" +#include "verifier_netfilter_retcode.skel.h" #include "verifier_raw_stack.skel.h" #include "verifier_raw_tp_writable.skel.h" #include "verifier_reg_equal.skel.h" @@ -103,6 +105,8 @@ void test_verifier_map_ptr(void) { RUN(verifier_map_ptr); } void test_verifier_map_ret_val(void) { RUN(verifier_map_ret_val); } void test_verifier_masking(void) { RUN(verifier_masking); } void test_verifier_meta_access(void) { RUN(verifier_meta_access); } +void test_verifier_netfilter_ctx(void) { RUN(verifier_netfilter_ctx); } +void test_verifier_netfilter_retcode(void) { RUN(verifier_netfilter_retcode); } void test_verifier_raw_stack(void) { RUN(verifier_raw_stack); } void test_verifier_raw_tp_writable(void) { RUN(verifier_raw_tp_writable); } void test_verifier_reg_equal(void) { RUN(verifier_reg_equal); } diff --git a/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c b/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c new file mode 100644 index 000000000000..65bba330e7e5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" + +#include "bpf_misc.h" + +#include <bpf/bpf_endian.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +SEC("netfilter") +__description("netfilter invalid context access, size too short") +__failure __msg("invalid bpf_context access") +__naked void with_invalid_ctx_access_test1(void) +{ + asm volatile (" \ + r2 = *(u8*)(r1 + %[__bpf_nf_ctx_state]); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__bpf_nf_ctx_state, offsetof(struct bpf_nf_ctx, state)) + : __clobber_all); +} + +SEC("netfilter") +__description("netfilter invalid context access, size too short") +__failure __msg("invalid bpf_context access") +__naked void with_invalid_ctx_access_test2(void) +{ + asm volatile (" \ + r2 = *(u16*)(r1 + %[__bpf_nf_ctx_skb]); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__bpf_nf_ctx_skb, offsetof(struct bpf_nf_ctx, skb)) + : __clobber_all); +} + +SEC("netfilter") +__description("netfilter invalid context access, past end of ctx") +__failure __msg("invalid bpf_context access") +__naked void with_invalid_ctx_access_test3(void) +{ + asm volatile (" \ + r2 = *(u64*)(r1 + %[__bpf_nf_ctx_size]); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__bpf_nf_ctx_size, sizeof(struct bpf_nf_ctx)) + : __clobber_all); +} + +SEC("netfilter") +__description("netfilter invalid context, write") +__failure __msg("invalid bpf_context access") +__naked void with_invalid_ctx_access_test4(void) +{ + asm volatile (" \ + r2 = r1; \ + *(u64*)(r2 + 0) = r1; \ + r0 = 1; \ + exit; \ +" : + : __imm_const(__bpf_nf_ctx_skb, offsetof(struct bpf_nf_ctx, skb)) + : __clobber_all); +} + +#define NF_DROP 0 +#define NF_ACCEPT 1 + +SEC("netfilter") +__description("netfilter valid context read and invalid write") +__failure __msg("only read is supported") +int with_invalid_ctx_access_test5(struct bpf_nf_ctx *ctx) +{ + struct nf_hook_state *state = (void *)ctx->state; + + state->sk = NULL; + return NF_ACCEPT; +} + +extern int bpf_dynptr_from_skb(struct sk_buff *skb, __u64 flags, + struct bpf_dynptr *ptr__uninit) __ksym; +extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, uint32_t offset, + void *buffer, uint32_t buffer__sz) __ksym; + +SEC("netfilter") +__description("netfilter test prog with skb and state read access") +__success __failure_unpriv +__retval(0) +int with_valid_ctx_access_test6(struct bpf_nf_ctx *ctx) +{ + const struct nf_hook_state *state = ctx->state; + struct sk_buff *skb = ctx->skb; + const struct iphdr *iph; + const struct tcphdr *th; + u8 buffer_iph[20] = {}; + u8 buffer_th[40] = {}; + struct bpf_dynptr ptr; + uint8_t ihl; + + if (skb->len <= 20 || bpf_dynptr_from_skb(skb, 0, &ptr)) + return NF_ACCEPT; + + iph = bpf_dynptr_slice(&ptr, 0, buffer_iph, sizeof(buffer_iph)); + if (!iph) + return NF_ACCEPT; + + if (state->pf != 2) + return NF_ACCEPT; + + ihl = iph->ihl << 2; + + th = bpf_dynptr_slice(&ptr, ihl, buffer_th, sizeof(buffer_th)); + if (!th) + return NF_ACCEPT; + + return th->dest == bpf_htons(22) ? NF_ACCEPT : NF_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c b/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c new file mode 100644 index 000000000000..353ae6da00e1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("netfilter") +__description("bpf_exit with invalid return code. test1") +__failure __msg("R0 is not a known value") +__naked void with_invalid_return_code_test1(void) +{ + asm volatile (" \ + r0 = *(u64*)(r1 + 0); \ + exit; \ +" ::: __clobber_all); +} + +SEC("netfilter") +__description("bpf_exit with valid return code. test2") +__success +__naked void with_valid_return_code_test2(void) +{ + asm volatile (" \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("netfilter") +__description("bpf_exit with valid return code. test3") +__success +__naked void with_valid_return_code_test3(void) +{ + asm volatile (" \ + r0 = 1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("netfilter") +__description("bpf_exit with invalid return code. test4") +__failure __msg("R0 has value (0x2; 0x0)") +__naked void with_invalid_return_code_test4(void) +{ + asm volatile (" \ + r0 = 2; \ + exit; \ +" ::: __clobber_all); +} |