diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-11 08:27:49 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-11 08:27:49 +0000 |
commit | ace9429bb58fd418f0c81d4c2835699bddf6bde6 (patch) | |
tree | b2d64bc10158fdd5497876388cd68142ca374ed3 /tools/testing/selftests/bpf/progs | |
parent | Initial commit. (diff) | |
download | linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.tar.xz linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.zip |
Adding upstream version 6.6.15.upstream/6.6.15
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'tools/testing/selftests/bpf/progs')
690 files changed, 85733 insertions, 0 deletions
diff --git a/tools/testing/selftests/bpf/progs/async_stack_depth.c b/tools/testing/selftests/bpf/progs/async_stack_depth.c new file mode 100644 index 0000000000..3517c0e012 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/async_stack_depth.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +struct hmap_elem { + struct bpf_timer timer; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 64); + __type(key, int); + __type(value, struct hmap_elem); +} hmap SEC(".maps"); + +__attribute__((noinline)) +static int timer_cb(void *map, int *key, struct bpf_timer *timer) +{ + volatile char buf[256] = {}; + return buf[69]; +} + +__attribute__((noinline)) +static int bad_timer_cb(void *map, int *key, struct bpf_timer *timer) +{ + volatile char buf[300] = {}; + return buf[255] + timer_cb(NULL, NULL, NULL); +} + +SEC("tc") +__failure __msg("combined stack size of 2 calls is 576. Too large") +int pseudo_call_check(struct __sk_buff *ctx) +{ + struct hmap_elem *elem; + volatile char buf[256] = {}; + + elem = bpf_map_lookup_elem(&hmap, &(int){0}); + if (!elem) + return 0; + + timer_cb(NULL, NULL, NULL); + return bpf_timer_set_callback(&elem->timer, timer_cb) + buf[0]; +} + +SEC("tc") +__failure __msg("combined stack size of 2 calls is 608. Too large") +int async_call_root_check(struct __sk_buff *ctx) +{ + struct hmap_elem *elem; + volatile char buf[256] = {}; + + elem = bpf_map_lookup_elem(&hmap, &(int){0}); + if (!elem) + return 0; + + return bpf_timer_set_callback(&elem->timer, bad_timer_cb) + buf[0]; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/atomic_bounds.c b/tools/testing/selftests/bpf/progs/atomic_bounds.c new file mode 100644 index 0000000000..e5fff7fc7f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/atomic_bounds.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <stdbool.h> + +#ifdef ENABLE_ATOMICS_TESTS +bool skip_tests __attribute((__section__(".data"))) = false; +#else +bool skip_tests = true; +#endif + +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(sub, int x) +{ +#ifdef ENABLE_ATOMICS_TESTS + int a = 0; + int b = __sync_fetch_and_add(&a, 1); + /* b is certainly 0 here. Can the verifier tell? */ + while (b) + continue; +#endif + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/atomics.c b/tools/testing/selftests/bpf/progs/atomics.c new file mode 100644 index 0000000000..f89c7f0cc5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/atomics.c @@ -0,0 +1,170 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <stdbool.h> + +#ifdef ENABLE_ATOMICS_TESTS +bool skip_tests __attribute((__section__(".data"))) = false; +#else +bool skip_tests = true; +#endif + +__u32 pid = 0; + +__u64 add64_value = 1; +__u64 add64_result = 0; +__u32 add32_value = 1; +__u32 add32_result = 0; +__u64 add_stack_value_copy = 0; +__u64 add_stack_result = 0; +__u64 add_noreturn_value = 1; + +SEC("raw_tp/sys_enter") +int add(const void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; +#ifdef ENABLE_ATOMICS_TESTS + __u64 add_stack_value = 1; + + add64_result = __sync_fetch_and_add(&add64_value, 2); + add32_result = __sync_fetch_and_add(&add32_value, 2); + add_stack_result = __sync_fetch_and_add(&add_stack_value, 2); + add_stack_value_copy = add_stack_value; + __sync_fetch_and_add(&add_noreturn_value, 2); +#endif + + return 0; +} + +__s64 sub64_value = 1; +__s64 sub64_result = 0; +__s32 sub32_value = 1; +__s32 sub32_result = 0; +__s64 sub_stack_value_copy = 0; +__s64 sub_stack_result = 0; +__s64 sub_noreturn_value = 1; + +SEC("raw_tp/sys_enter") +int sub(const void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; +#ifdef ENABLE_ATOMICS_TESTS + __u64 sub_stack_value = 1; + + sub64_result = __sync_fetch_and_sub(&sub64_value, 2); + sub32_result = __sync_fetch_and_sub(&sub32_value, 2); + sub_stack_result = __sync_fetch_and_sub(&sub_stack_value, 2); + sub_stack_value_copy = sub_stack_value; + __sync_fetch_and_sub(&sub_noreturn_value, 2); +#endif + + return 0; +} + +__u64 and64_value = (0x110ull << 32); +__u64 and64_result = 0; +__u32 and32_value = 0x110; +__u32 and32_result = 0; +__u64 and_noreturn_value = (0x110ull << 32); + +SEC("raw_tp/sys_enter") +int and(const void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; +#ifdef ENABLE_ATOMICS_TESTS + + and64_result = __sync_fetch_and_and(&and64_value, 0x011ull << 32); + and32_result = __sync_fetch_and_and(&and32_value, 0x011); + __sync_fetch_and_and(&and_noreturn_value, 0x011ull << 32); +#endif + + return 0; +} + +__u64 or64_value = (0x110ull << 32); +__u64 or64_result = 0; +__u32 or32_value = 0x110; +__u32 or32_result = 0; +__u64 or_noreturn_value = (0x110ull << 32); + +SEC("raw_tp/sys_enter") +int or(const void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; +#ifdef ENABLE_ATOMICS_TESTS + or64_result = __sync_fetch_and_or(&or64_value, 0x011ull << 32); + or32_result = __sync_fetch_and_or(&or32_value, 0x011); + __sync_fetch_and_or(&or_noreturn_value, 0x011ull << 32); +#endif + + return 0; +} + +__u64 xor64_value = (0x110ull << 32); +__u64 xor64_result = 0; +__u32 xor32_value = 0x110; +__u32 xor32_result = 0; +__u64 xor_noreturn_value = (0x110ull << 32); + +SEC("raw_tp/sys_enter") +int xor(const void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; +#ifdef ENABLE_ATOMICS_TESTS + xor64_result = __sync_fetch_and_xor(&xor64_value, 0x011ull << 32); + xor32_result = __sync_fetch_and_xor(&xor32_value, 0x011); + __sync_fetch_and_xor(&xor_noreturn_value, 0x011ull << 32); +#endif + + return 0; +} + +__u64 cmpxchg64_value = 1; +__u64 cmpxchg64_result_fail = 0; +__u64 cmpxchg64_result_succeed = 0; +__u32 cmpxchg32_value = 1; +__u32 cmpxchg32_result_fail = 0; +__u32 cmpxchg32_result_succeed = 0; + +SEC("raw_tp/sys_enter") +int cmpxchg(const void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; +#ifdef ENABLE_ATOMICS_TESTS + cmpxchg64_result_fail = __sync_val_compare_and_swap(&cmpxchg64_value, 0, 3); + cmpxchg64_result_succeed = __sync_val_compare_and_swap(&cmpxchg64_value, 1, 2); + + cmpxchg32_result_fail = __sync_val_compare_and_swap(&cmpxchg32_value, 0, 3); + cmpxchg32_result_succeed = __sync_val_compare_and_swap(&cmpxchg32_value, 1, 2); +#endif + + return 0; +} + +__u64 xchg64_value = 1; +__u64 xchg64_result = 0; +__u32 xchg32_value = 1; +__u32 xchg32_result = 0; + +SEC("raw_tp/sys_enter") +int xchg(const void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; +#ifdef ENABLE_ATOMICS_TESTS + __u64 val64 = 2; + __u32 val32 = 2; + + xchg64_result = __sync_lock_test_and_set(&xchg64_value, val64); + xchg32_result = __sync_lock_test_and_set(&xchg32_value, val32); +#endif + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bench_local_storage_create.c b/tools/testing/selftests/bpf/progs/bench_local_storage_create.c new file mode 100644 index 0000000000..e4bfbba6c1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bench_local_storage_create.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +long create_errs = 0; +long create_cnts = 0; +long kmalloc_cnts = 0; +__u32 bench_pid = 0; + +struct storage { + __u8 data[64]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct storage); +} sk_storage_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct storage); +} task_storage_map SEC(".maps"); + +SEC("raw_tp/kmalloc") +int BPF_PROG(kmalloc, unsigned long call_site, const void *ptr, + size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, + int node) +{ + __sync_fetch_and_add(&kmalloc_cnts, 1); + + return 0; +} + +SEC("tp_btf/sched_process_fork") +int BPF_PROG(sched_process_fork, struct task_struct *parent, struct task_struct *child) +{ + struct storage *stg; + + if (parent->tgid != bench_pid) + return 0; + + stg = bpf_task_storage_get(&task_storage_map, child, NULL, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (stg) + __sync_fetch_and_add(&create_cnts, 1); + else + __sync_fetch_and_add(&create_errs, 1); + + return 0; +} + +SEC("lsm.s/socket_post_create") +int BPF_PROG(socket_post_create, struct socket *sock, int family, int type, + int protocol, int kern) +{ + struct storage *stg; + __u32 pid; + + pid = bpf_get_current_pid_tgid() >> 32; + if (pid != bench_pid) + return 0; + + stg = bpf_sk_storage_get(&sk_storage_map, sock->sk, NULL, + BPF_LOCAL_STORAGE_GET_F_CREATE); + + if (stg) + __sync_fetch_and_add(&create_cnts, 1); + else + __sync_fetch_and_add(&create_errs, 1); + + return 0; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bind4_prog.c b/tools/testing/selftests/bpf/progs/bind4_prog.c new file mode 100644 index 0000000000..a487f60b73 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bind4_prog.c @@ -0,0 +1,159 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/if.h> +#include <errno.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define SERV4_IP 0xc0a801feU /* 192.168.1.254 */ +#define SERV4_PORT 4040 +#define SERV4_REWRITE_IP 0x7f000001U /* 127.0.0.1 */ +#define SERV4_REWRITE_PORT 4444 + +#ifndef IFNAMSIZ +#define IFNAMSIZ 16 +#endif + +static __inline int bind_to_device(struct bpf_sock_addr *ctx) +{ + char veth1[IFNAMSIZ] = "test_sock_addr1"; + char veth2[IFNAMSIZ] = "test_sock_addr2"; + char missing[IFNAMSIZ] = "nonexistent_dev"; + char del_bind[IFNAMSIZ] = ""; + int veth1_idx, veth2_idx; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &veth1, sizeof(veth1))) + return 1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &veth1_idx, sizeof(veth1_idx)) || !veth1_idx) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &veth2, sizeof(veth2))) + return 1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &veth2_idx, sizeof(veth2_idx)) || !veth2_idx || + veth1_idx == veth2_idx) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &missing, sizeof(missing)) != -ENODEV) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &veth1_idx, sizeof(veth1_idx))) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &del_bind, sizeof(del_bind))) + return 1; + + return 0; +} + +static __inline int bind_reuseport(struct bpf_sock_addr *ctx) +{ + int val = 1; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_REUSEPORT, + &val, sizeof(val))) + return 1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_REUSEPORT, + &val, sizeof(val)) || !val) + return 1; + val = 0; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_REUSEPORT, + &val, sizeof(val))) + return 1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_REUSEPORT, + &val, sizeof(val)) || val) + return 1; + + return 0; +} + +static __inline int misc_opts(struct bpf_sock_addr *ctx, int opt) +{ + int old, tmp, new = 0xeb9f; + + /* Socket in test case has guarantee that old never equals to new. */ + if (bpf_getsockopt(ctx, SOL_SOCKET, opt, &old, sizeof(old)) || + old == new) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, opt, &new, sizeof(new))) + return 1; + if (bpf_getsockopt(ctx, SOL_SOCKET, opt, &tmp, sizeof(tmp)) || + tmp != new) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, opt, &old, sizeof(old))) + return 1; + + return 0; +} + +SEC("cgroup/bind4") +int bind_v4_prog(struct bpf_sock_addr *ctx) +{ + struct bpf_sock *sk; + __u32 user_ip4; + __u16 user_port; + + sk = ctx->sk; + if (!sk) + return 0; + + if (sk->family != AF_INET) + return 0; + + if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM) + return 0; + + if (ctx->user_ip4 != bpf_htonl(SERV4_IP) || + ctx->user_port != bpf_htons(SERV4_PORT)) + return 0; + + // u8 narrow loads: + user_ip4 = 0; + user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[0] << 0; + user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[1] << 8; + user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[2] << 16; + user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[3] << 24; + if (ctx->user_ip4 != user_ip4) + return 0; + + user_port = 0; + user_port |= ((volatile __u8 *)&ctx->user_port)[0] << 0; + user_port |= ((volatile __u8 *)&ctx->user_port)[1] << 8; + if (ctx->user_port != user_port) + return 0; + + // u16 narrow loads: + user_ip4 = 0; + user_ip4 |= ((volatile __u16 *)&ctx->user_ip4)[0] << 0; + user_ip4 |= ((volatile __u16 *)&ctx->user_ip4)[1] << 16; + if (ctx->user_ip4 != user_ip4) + return 0; + + /* Bind to device and unbind it. */ + if (bind_to_device(ctx)) + return 0; + + /* Test for misc socket options. */ + if (misc_opts(ctx, SO_MARK) || misc_opts(ctx, SO_PRIORITY)) + return 0; + + /* Set reuseport and unset */ + if (bind_reuseport(ctx)) + return 0; + + ctx->user_ip4 = bpf_htonl(SERV4_REWRITE_IP); + ctx->user_port = bpf_htons(SERV4_REWRITE_PORT); + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bind6_prog.c b/tools/testing/selftests/bpf/progs/bind6_prog.c new file mode 100644 index 0000000000..d62cd9e9cf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bind6_prog.c @@ -0,0 +1,176 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/if.h> +#include <errno.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define SERV6_IP_0 0xfaceb00c /* face:b00c:1234:5678::abcd */ +#define SERV6_IP_1 0x12345678 +#define SERV6_IP_2 0x00000000 +#define SERV6_IP_3 0x0000abcd +#define SERV6_PORT 6060 +#define SERV6_REWRITE_IP_0 0x00000000 +#define SERV6_REWRITE_IP_1 0x00000000 +#define SERV6_REWRITE_IP_2 0x00000000 +#define SERV6_REWRITE_IP_3 0x00000001 +#define SERV6_REWRITE_PORT 6666 + +#ifndef IFNAMSIZ +#define IFNAMSIZ 16 +#endif + +static __inline int bind_to_device(struct bpf_sock_addr *ctx) +{ + char veth1[IFNAMSIZ] = "test_sock_addr1"; + char veth2[IFNAMSIZ] = "test_sock_addr2"; + char missing[IFNAMSIZ] = "nonexistent_dev"; + char del_bind[IFNAMSIZ] = ""; + int veth1_idx, veth2_idx; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &veth1, sizeof(veth1))) + return 1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &veth1_idx, sizeof(veth1_idx)) || !veth1_idx) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &veth2, sizeof(veth2))) + return 1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &veth2_idx, sizeof(veth2_idx)) || !veth2_idx || + veth1_idx == veth2_idx) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &missing, sizeof(missing)) != -ENODEV) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &veth1_idx, sizeof(veth1_idx))) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &del_bind, sizeof(del_bind))) + return 1; + + return 0; +} + +static __inline int bind_reuseport(struct bpf_sock_addr *ctx) +{ + int val = 1; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_REUSEPORT, + &val, sizeof(val))) + return 1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_REUSEPORT, + &val, sizeof(val)) || !val) + return 1; + val = 0; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_REUSEPORT, + &val, sizeof(val))) + return 1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_REUSEPORT, + &val, sizeof(val)) || val) + return 1; + + return 0; +} + +static __inline int misc_opts(struct bpf_sock_addr *ctx, int opt) +{ + int old, tmp, new = 0xeb9f; + + /* Socket in test case has guarantee that old never equals to new. */ + if (bpf_getsockopt(ctx, SOL_SOCKET, opt, &old, sizeof(old)) || + old == new) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, opt, &new, sizeof(new))) + return 1; + if (bpf_getsockopt(ctx, SOL_SOCKET, opt, &tmp, sizeof(tmp)) || + tmp != new) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, opt, &old, sizeof(old))) + return 1; + + return 0; +} + +SEC("cgroup/bind6") +int bind_v6_prog(struct bpf_sock_addr *ctx) +{ + struct bpf_sock *sk; + __u32 user_ip6; + __u16 user_port; + int i; + + sk = ctx->sk; + if (!sk) + return 0; + + if (sk->family != AF_INET6) + return 0; + + if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM) + return 0; + + if (ctx->user_ip6[0] != bpf_htonl(SERV6_IP_0) || + ctx->user_ip6[1] != bpf_htonl(SERV6_IP_1) || + ctx->user_ip6[2] != bpf_htonl(SERV6_IP_2) || + ctx->user_ip6[3] != bpf_htonl(SERV6_IP_3) || + ctx->user_port != bpf_htons(SERV6_PORT)) + return 0; + + // u8 narrow loads: + for (i = 0; i < 4; i++) { + user_ip6 = 0; + user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[0] << 0; + user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[1] << 8; + user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[2] << 16; + user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[3] << 24; + if (ctx->user_ip6[i] != user_ip6) + return 0; + } + + user_port = 0; + user_port |= ((volatile __u8 *)&ctx->user_port)[0] << 0; + user_port |= ((volatile __u8 *)&ctx->user_port)[1] << 8; + if (ctx->user_port != user_port) + return 0; + + // u16 narrow loads: + for (i = 0; i < 4; i++) { + user_ip6 = 0; + user_ip6 |= ((volatile __u16 *)&ctx->user_ip6[i])[0] << 0; + user_ip6 |= ((volatile __u16 *)&ctx->user_ip6[i])[1] << 16; + if (ctx->user_ip6[i] != user_ip6) + return 0; + } + + /* Bind to device and unbind it. */ + if (bind_to_device(ctx)) + return 0; + + /* Test for misc socket options. */ + if (misc_opts(ctx, SO_MARK) || misc_opts(ctx, SO_PRIORITY)) + return 0; + + /* Set reuseport and unset */ + if (bind_reuseport(ctx)) + return 0; + + ctx->user_ip6[0] = bpf_htonl(SERV6_REWRITE_IP_0); + ctx->user_ip6[1] = bpf_htonl(SERV6_REWRITE_IP_1); + ctx->user_ip6[2] = bpf_htonl(SERV6_REWRITE_IP_2); + ctx->user_ip6[3] = bpf_htonl(SERV6_REWRITE_IP_3); + ctx->user_port = bpf_htons(SERV6_REWRITE_PORT); + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bind_perm.c b/tools/testing/selftests/bpf/progs/bind_perm.c new file mode 100644 index 0000000000..7bd2a02702 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bind_perm.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +static __always_inline int bind_prog(struct bpf_sock_addr *ctx, int family) +{ + struct bpf_sock *sk; + + sk = ctx->sk; + if (!sk) + return 0; + + if (sk->family != family) + return 0; + + if (ctx->type != SOCK_STREAM) + return 0; + + /* Return 1 OR'ed with the first bit set to indicate + * that CAP_NET_BIND_SERVICE should be bypassed. + */ + if (ctx->user_port == bpf_htons(111)) + return (1 | 2); + + return 1; +} + +SEC("cgroup/bind4") +int bind_v4_prog(struct bpf_sock_addr *ctx) +{ + return bind_prog(ctx, AF_INET); +} + +SEC("cgroup/bind6") +int bind_v6_prog(struct bpf_sock_addr *ctx) +{ + return bind_prog(ctx, AF_INET6); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bloom_filter_bench.c b/tools/testing/selftests/bpf/progs/bloom_filter_bench.c new file mode 100644 index 0000000000..7efcbdbe77 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bloom_filter_bench.c @@ -0,0 +1,154 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <errno.h> +#include <linux/bpf.h> +#include <stdbool.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct bpf_map; + +__u8 rand_vals[2500000]; +const __u32 nr_rand_bytes = 2500000; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(key_size, sizeof(__u32)); + /* max entries and value_size will be set programmatically. + * They are configurable from the userspace bench program. + */ +} array_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_BLOOM_FILTER); + /* max entries, value_size, and # of hash functions will be set + * programmatically. They are configurable from the userspace + * bench program. + */ + __uint(map_extra, 3); +} bloom_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + /* max entries, key_size, and value_size, will be set + * programmatically. They are configurable from the userspace + * bench program. + */ +} hashmap SEC(".maps"); + +struct callback_ctx { + struct bpf_map *map; + bool update; +}; + +/* Tracks the number of hits, drops, and false hits */ +struct { + __u32 stats[3]; +} __attribute__((__aligned__(256))) percpu_stats[256]; + +const __u32 hit_key = 0; +const __u32 drop_key = 1; +const __u32 false_hit_key = 2; + +__u8 value_size; + +const volatile bool hashmap_use_bloom; +const volatile bool count_false_hits; + +int error = 0; + +static __always_inline void log_result(__u32 key) +{ + __u32 cpu = bpf_get_smp_processor_id(); + + percpu_stats[cpu & 255].stats[key]++; +} + +static __u64 +bloom_callback(struct bpf_map *map, __u32 *key, void *val, + struct callback_ctx *data) +{ + int err; + + if (data->update) + err = bpf_map_push_elem(data->map, val, 0); + else + err = bpf_map_peek_elem(data->map, val); + + if (err) { + error |= 1; + return 1; /* stop the iteration */ + } + + log_result(hit_key); + + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int bloom_lookup(void *ctx) +{ + struct callback_ctx data; + + data.map = (struct bpf_map *)&bloom_map; + data.update = false; + + bpf_for_each_map_elem(&array_map, bloom_callback, &data, 0); + + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int bloom_update(void *ctx) +{ + struct callback_ctx data; + + data.map = (struct bpf_map *)&bloom_map; + data.update = true; + + bpf_for_each_map_elem(&array_map, bloom_callback, &data, 0); + + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int bloom_hashmap_lookup(void *ctx) +{ + __u64 *result; + int i, err; + + __u32 index = bpf_get_prandom_u32(); + __u32 bitmask = (1ULL << 21) - 1; + + for (i = 0; i < 1024; i++, index += value_size) { + index = index & bitmask; + + if (hashmap_use_bloom) { + err = bpf_map_peek_elem(&bloom_map, + rand_vals + index); + if (err) { + if (err != -ENOENT) { + error |= 2; + return 0; + } + log_result(hit_key); + continue; + } + } + + result = bpf_map_lookup_elem(&hashmap, + rand_vals + index); + if (result) { + log_result(hit_key); + } else { + if (hashmap_use_bloom && count_false_hits) + log_result(false_hit_key); + log_result(drop_key); + } + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bloom_filter_map.c b/tools/testing/selftests/bpf/progs/bloom_filter_map.c new file mode 100644 index 0000000000..f245fcfe0c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bloom_filter_map.c @@ -0,0 +1,83 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct bpf_map; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 1000); +} map_random_data SEC(".maps"); + +struct map_bloom_type { + __uint(type, BPF_MAP_TYPE_BLOOM_FILTER); + __type(value, __u32); + __uint(max_entries, 10000); + __uint(map_extra, 5); +} map_bloom SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __type(key, int); + __type(value, int); + __uint(max_entries, 1); + __array(values, struct map_bloom_type); +} outer_map SEC(".maps"); + +struct callback_ctx { + struct bpf_map *map; +}; + +int error = 0; + +static __u64 +check_elem(struct bpf_map *map, __u32 *key, __u32 *val, + struct callback_ctx *data) +{ + int err; + + err = bpf_map_peek_elem(data->map, val); + if (err) { + error |= 1; + return 1; /* stop the iteration */ + } + + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int inner_map(void *ctx) +{ + struct bpf_map *inner_map; + struct callback_ctx data; + int key = 0; + + inner_map = bpf_map_lookup_elem(&outer_map, &key); + if (!inner_map) { + error |= 2; + return 0; + } + + data.map = inner_map; + bpf_for_each_map_elem(&map_random_data, check_elem, &data, 0); + + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int check_bloom(void *ctx) +{ + struct callback_ctx data; + + data.map = (struct bpf_map *)&map_bloom; + bpf_for_each_map_elem(&map_random_data, check_elem, &data, 0); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c new file mode 100644 index 0000000000..c997e3e3d3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c @@ -0,0 +1,542 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* WARNING: This implemenation is not necessarily the same + * as the tcp_cubic.c. The purpose is mainly for testing + * the kernel BPF logic. + * + * Highlights: + * 1. CONFIG_HZ .kconfig map is used. + * 2. In bictcp_update(), calculation is changed to use usec + * resolution (i.e. USEC_PER_JIFFY) instead of using jiffies. + * Thus, usecs_to_jiffies() is not used in the bpf_cubic.c. + * 3. In bitctcp_update() [under tcp_friendliness], the original + * "while (ca->ack_cnt > delta)" loop is changed to the equivalent + * "ca->ack_cnt / delta" operation. + */ + +#include <linux/bpf.h> +#include <linux/stddef.h> +#include <linux/tcp.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; + +#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi) + +#define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation + * max_cwnd = snd_cwnd * beta + */ +#define BICTCP_HZ 10 /* BIC HZ 2^10 = 1024 */ + +/* Two methods of hybrid slow start */ +#define HYSTART_ACK_TRAIN 0x1 +#define HYSTART_DELAY 0x2 + +/* Number of delay samples for detecting the increase of delay */ +#define HYSTART_MIN_SAMPLES 8 +#define HYSTART_DELAY_MIN (4000U) /* 4ms */ +#define HYSTART_DELAY_MAX (16000U) /* 16 ms */ +#define HYSTART_DELAY_THRESH(x) clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX) + +static int fast_convergence = 1; +static const int beta = 717; /* = 717/1024 (BICTCP_BETA_SCALE) */ +static int initial_ssthresh; +static const int bic_scale = 41; +static int tcp_friendliness = 1; + +static int hystart = 1; +static int hystart_detect = HYSTART_ACK_TRAIN | HYSTART_DELAY; +static int hystart_low_window = 16; +static int hystart_ack_delta_us = 2000; + +static const __u32 cube_rtt_scale = (bic_scale * 10); /* 1024*c/rtt */ +static const __u32 beta_scale = 8*(BICTCP_BETA_SCALE+beta) / 3 + / (BICTCP_BETA_SCALE - beta); +/* calculate the "K" for (wmax-cwnd) = c/rtt * K^3 + * so K = cubic_root( (wmax-cwnd)*rtt/c ) + * the unit of K is bictcp_HZ=2^10, not HZ + * + * c = bic_scale >> 10 + * rtt = 100ms + * + * the following code has been designed and tested for + * cwnd < 1 million packets + * RTT < 100 seconds + * HZ < 1,000,00 (corresponding to 10 nano-second) + */ + +/* 1/c * 2^2*bictcp_HZ * srtt, 2^40 */ +static const __u64 cube_factor = (__u64)(1ull << (10+3*BICTCP_HZ)) + / (bic_scale * 10); + +/* BIC TCP Parameters */ +struct bictcp { + __u32 cnt; /* increase cwnd by 1 after ACKs */ + __u32 last_max_cwnd; /* last maximum snd_cwnd */ + __u32 last_cwnd; /* the last snd_cwnd */ + __u32 last_time; /* time when updated last_cwnd */ + __u32 bic_origin_point;/* origin point of bic function */ + __u32 bic_K; /* time to origin point + from the beginning of the current epoch */ + __u32 delay_min; /* min delay (usec) */ + __u32 epoch_start; /* beginning of an epoch */ + __u32 ack_cnt; /* number of acks */ + __u32 tcp_cwnd; /* estimated tcp cwnd */ + __u16 unused; + __u8 sample_cnt; /* number of samples to decide curr_rtt */ + __u8 found; /* the exit point is found? */ + __u32 round_start; /* beginning of each round */ + __u32 end_seq; /* end_seq of the round */ + __u32 last_ack; /* last time when the ACK spacing is close */ + __u32 curr_rtt; /* the minimum rtt of current round */ +}; + +static inline void bictcp_reset(struct bictcp *ca) +{ + ca->cnt = 0; + ca->last_max_cwnd = 0; + ca->last_cwnd = 0; + ca->last_time = 0; + ca->bic_origin_point = 0; + ca->bic_K = 0; + ca->delay_min = 0; + ca->epoch_start = 0; + ca->ack_cnt = 0; + ca->tcp_cwnd = 0; + ca->found = 0; +} + +extern unsigned long CONFIG_HZ __kconfig; +#define HZ CONFIG_HZ +#define USEC_PER_MSEC 1000UL +#define USEC_PER_SEC 1000000UL +#define USEC_PER_JIFFY (USEC_PER_SEC / HZ) + +static __always_inline __u64 div64_u64(__u64 dividend, __u64 divisor) +{ + return dividend / divisor; +} + +#define div64_ul div64_u64 + +#define BITS_PER_U64 (sizeof(__u64) * 8) +static __always_inline int fls64(__u64 x) +{ + int num = BITS_PER_U64 - 1; + + if (x == 0) + return 0; + + if (!(x & (~0ull << (BITS_PER_U64-32)))) { + num -= 32; + x <<= 32; + } + if (!(x & (~0ull << (BITS_PER_U64-16)))) { + num -= 16; + x <<= 16; + } + if (!(x & (~0ull << (BITS_PER_U64-8)))) { + num -= 8; + x <<= 8; + } + if (!(x & (~0ull << (BITS_PER_U64-4)))) { + num -= 4; + x <<= 4; + } + if (!(x & (~0ull << (BITS_PER_U64-2)))) { + num -= 2; + x <<= 2; + } + if (!(x & (~0ull << (BITS_PER_U64-1)))) + num -= 1; + + return num + 1; +} + +static __always_inline __u32 bictcp_clock_us(const struct sock *sk) +{ + return tcp_sk(sk)->tcp_mstamp; +} + +static __always_inline void bictcp_hystart_reset(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + + ca->round_start = ca->last_ack = bictcp_clock_us(sk); + ca->end_seq = tp->snd_nxt; + ca->curr_rtt = ~0U; + ca->sample_cnt = 0; +} + +/* "struct_ops/" prefix is a requirement */ +SEC("struct_ops/bpf_cubic_init") +void BPF_PROG(bpf_cubic_init, struct sock *sk) +{ + struct bictcp *ca = inet_csk_ca(sk); + + bictcp_reset(ca); + + if (hystart) + bictcp_hystart_reset(sk); + + if (!hystart && initial_ssthresh) + tcp_sk(sk)->snd_ssthresh = initial_ssthresh; +} + +/* "struct_ops" prefix is a requirement */ +SEC("struct_ops/bpf_cubic_cwnd_event") +void BPF_PROG(bpf_cubic_cwnd_event, struct sock *sk, enum tcp_ca_event event) +{ + if (event == CA_EVENT_TX_START) { + struct bictcp *ca = inet_csk_ca(sk); + __u32 now = tcp_jiffies32; + __s32 delta; + + delta = now - tcp_sk(sk)->lsndtime; + + /* We were application limited (idle) for a while. + * Shift epoch_start to keep cwnd growth to cubic curve. + */ + if (ca->epoch_start && delta > 0) { + ca->epoch_start += delta; + if (after(ca->epoch_start, now)) + ca->epoch_start = now; + } + return; + } +} + +/* + * cbrt(x) MSB values for x MSB values in [0..63]. + * Precomputed then refined by hand - Willy Tarreau + * + * For x in [0..63], + * v = cbrt(x << 18) - 1 + * cbrt(x) = (v[x] + 10) >> 6 + */ +static const __u8 v[] = { + /* 0x00 */ 0, 54, 54, 54, 118, 118, 118, 118, + /* 0x08 */ 123, 129, 134, 138, 143, 147, 151, 156, + /* 0x10 */ 157, 161, 164, 168, 170, 173, 176, 179, + /* 0x18 */ 181, 185, 187, 190, 192, 194, 197, 199, + /* 0x20 */ 200, 202, 204, 206, 209, 211, 213, 215, + /* 0x28 */ 217, 219, 221, 222, 224, 225, 227, 229, + /* 0x30 */ 231, 232, 234, 236, 237, 239, 240, 242, + /* 0x38 */ 244, 245, 246, 248, 250, 251, 252, 254, +}; + +/* calculate the cubic root of x using a table lookup followed by one + * Newton-Raphson iteration. + * Avg err ~= 0.195% + */ +static __always_inline __u32 cubic_root(__u64 a) +{ + __u32 x, b, shift; + + if (a < 64) { + /* a in [0..63] */ + return ((__u32)v[(__u32)a] + 35) >> 6; + } + + b = fls64(a); + b = ((b * 84) >> 8) - 1; + shift = (a >> (b * 3)); + + /* it is needed for verifier's bound check on v */ + if (shift >= 64) + return 0; + + x = ((__u32)(((__u32)v[shift] + 10) << b)) >> 6; + + /* + * Newton-Raphson iteration + * 2 + * x = ( 2 * x + a / x ) / 3 + * k+1 k k + */ + x = (2 * x + (__u32)div64_u64(a, (__u64)x * (__u64)(x - 1))); + x = ((x * 341) >> 10); + return x; +} + +/* + * Compute congestion window to use. + */ +static __always_inline void bictcp_update(struct bictcp *ca, __u32 cwnd, + __u32 acked) +{ + __u32 delta, bic_target, max_cnt; + __u64 offs, t; + + ca->ack_cnt += acked; /* count the number of ACKed packets */ + + if (ca->last_cwnd == cwnd && + (__s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32) + return; + + /* The CUBIC function can update ca->cnt at most once per jiffy. + * On all cwnd reduction events, ca->epoch_start is set to 0, + * which will force a recalculation of ca->cnt. + */ + if (ca->epoch_start && tcp_jiffies32 == ca->last_time) + goto tcp_friendliness; + + ca->last_cwnd = cwnd; + ca->last_time = tcp_jiffies32; + + if (ca->epoch_start == 0) { + ca->epoch_start = tcp_jiffies32; /* record beginning */ + ca->ack_cnt = acked; /* start counting */ + ca->tcp_cwnd = cwnd; /* syn with cubic */ + + if (ca->last_max_cwnd <= cwnd) { + ca->bic_K = 0; + ca->bic_origin_point = cwnd; + } else { + /* Compute new K based on + * (wmax-cwnd) * (srtt>>3 / HZ) / c * 2^(3*bictcp_HZ) + */ + ca->bic_K = cubic_root(cube_factor + * (ca->last_max_cwnd - cwnd)); + ca->bic_origin_point = ca->last_max_cwnd; + } + } + + /* cubic function - calc*/ + /* calculate c * time^3 / rtt, + * while considering overflow in calculation of time^3 + * (so time^3 is done by using 64 bit) + * and without the support of division of 64bit numbers + * (so all divisions are done by using 32 bit) + * also NOTE the unit of those veriables + * time = (t - K) / 2^bictcp_HZ + * c = bic_scale >> 10 + * rtt = (srtt >> 3) / HZ + * !!! The following code does not have overflow problems, + * if the cwnd < 1 million packets !!! + */ + + t = (__s32)(tcp_jiffies32 - ca->epoch_start) * USEC_PER_JIFFY; + t += ca->delay_min; + /* change the unit from usec to bictcp_HZ */ + t <<= BICTCP_HZ; + t /= USEC_PER_SEC; + + if (t < ca->bic_K) /* t - K */ + offs = ca->bic_K - t; + else + offs = t - ca->bic_K; + + /* c/rtt * (t-K)^3 */ + delta = (cube_rtt_scale * offs * offs * offs) >> (10+3*BICTCP_HZ); + if (t < ca->bic_K) /* below origin*/ + bic_target = ca->bic_origin_point - delta; + else /* above origin*/ + bic_target = ca->bic_origin_point + delta; + + /* cubic function - calc bictcp_cnt*/ + if (bic_target > cwnd) { + ca->cnt = cwnd / (bic_target - cwnd); + } else { + ca->cnt = 100 * cwnd; /* very small increment*/ + } + + /* + * The initial growth of cubic function may be too conservative + * when the available bandwidth is still unknown. + */ + if (ca->last_max_cwnd == 0 && ca->cnt > 20) + ca->cnt = 20; /* increase cwnd 5% per RTT */ + +tcp_friendliness: + /* TCP Friendly */ + if (tcp_friendliness) { + __u32 scale = beta_scale; + __u32 n; + + /* update tcp cwnd */ + delta = (cwnd * scale) >> 3; + if (ca->ack_cnt > delta && delta) { + n = ca->ack_cnt / delta; + ca->ack_cnt -= n * delta; + ca->tcp_cwnd += n; + } + + if (ca->tcp_cwnd > cwnd) { /* if bic is slower than tcp */ + delta = ca->tcp_cwnd - cwnd; + max_cnt = cwnd / delta; + if (ca->cnt > max_cnt) + ca->cnt = max_cnt; + } + } + + /* The maximum rate of cwnd increase CUBIC allows is 1 packet per + * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT. + */ + ca->cnt = max(ca->cnt, 2U); +} + +/* Or simply use the BPF_STRUCT_OPS to avoid the SEC boiler plate. */ +void BPF_STRUCT_OPS(bpf_cubic_cong_avoid, struct sock *sk, __u32 ack, __u32 acked) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + + if (!tcp_is_cwnd_limited(sk)) + return; + + if (tcp_in_slow_start(tp)) { + if (hystart && after(ack, ca->end_seq)) + bictcp_hystart_reset(sk); + acked = tcp_slow_start(tp, acked); + if (!acked) + return; + } + bictcp_update(ca, tp->snd_cwnd, acked); + tcp_cong_avoid_ai(tp, ca->cnt, acked); +} + +__u32 BPF_STRUCT_OPS(bpf_cubic_recalc_ssthresh, struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + + ca->epoch_start = 0; /* end of epoch */ + + /* Wmax and fast convergence */ + if (tp->snd_cwnd < ca->last_max_cwnd && fast_convergence) + ca->last_max_cwnd = (tp->snd_cwnd * (BICTCP_BETA_SCALE + beta)) + / (2 * BICTCP_BETA_SCALE); + else + ca->last_max_cwnd = tp->snd_cwnd; + + return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U); +} + +void BPF_STRUCT_OPS(bpf_cubic_state, struct sock *sk, __u8 new_state) +{ + if (new_state == TCP_CA_Loss) { + bictcp_reset(inet_csk_ca(sk)); + bictcp_hystart_reset(sk); + } +} + +#define GSO_MAX_SIZE 65536 + +/* Account for TSO/GRO delays. + * Otherwise short RTT flows could get too small ssthresh, since during + * slow start we begin with small TSO packets and ca->delay_min would + * not account for long aggregation delay when TSO packets get bigger. + * Ideally even with a very small RTT we would like to have at least one + * TSO packet being sent and received by GRO, and another one in qdisc layer. + * We apply another 100% factor because @rate is doubled at this point. + * We cap the cushion to 1ms. + */ +static __always_inline __u32 hystart_ack_delay(struct sock *sk) +{ + unsigned long rate; + + rate = sk->sk_pacing_rate; + if (!rate) + return 0; + return min((__u64)USEC_PER_MSEC, + div64_ul((__u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate)); +} + +static __always_inline void hystart_update(struct sock *sk, __u32 delay) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + __u32 threshold; + + if (hystart_detect & HYSTART_ACK_TRAIN) { + __u32 now = bictcp_clock_us(sk); + + /* first detection parameter - ack-train detection */ + if ((__s32)(now - ca->last_ack) <= hystart_ack_delta_us) { + ca->last_ack = now; + + threshold = ca->delay_min + hystart_ack_delay(sk); + + /* Hystart ack train triggers if we get ack past + * ca->delay_min/2. + * Pacing might have delayed packets up to RTT/2 + * during slow start. + */ + if (sk->sk_pacing_status == SK_PACING_NONE) + threshold >>= 1; + + if ((__s32)(now - ca->round_start) > threshold) { + ca->found = 1; + tp->snd_ssthresh = tp->snd_cwnd; + } + } + } + + if (hystart_detect & HYSTART_DELAY) { + /* obtain the minimum delay of more than sampling packets */ + if (ca->curr_rtt > delay) + ca->curr_rtt = delay; + if (ca->sample_cnt < HYSTART_MIN_SAMPLES) { + ca->sample_cnt++; + } else { + if (ca->curr_rtt > ca->delay_min + + HYSTART_DELAY_THRESH(ca->delay_min >> 3)) { + ca->found = 1; + tp->snd_ssthresh = tp->snd_cwnd; + } + } + } +} + +int bpf_cubic_acked_called = 0; + +void BPF_STRUCT_OPS(bpf_cubic_acked, struct sock *sk, + const struct ack_sample *sample) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + __u32 delay; + + bpf_cubic_acked_called = 1; + /* Some calls are for duplicates without timetamps */ + if (sample->rtt_us < 0) + return; + + /* Discard delay samples right after fast recovery */ + if (ca->epoch_start && (__s32)(tcp_jiffies32 - ca->epoch_start) < HZ) + return; + + delay = sample->rtt_us; + if (delay == 0) + delay = 1; + + /* first time call or link delay decreases */ + if (ca->delay_min == 0 || ca->delay_min > delay) + ca->delay_min = delay; + + /* hystart triggers when cwnd is larger than some threshold */ + if (!ca->found && tcp_in_slow_start(tp) && hystart && + tp->snd_cwnd >= hystart_low_window) + hystart_update(sk, delay); +} + +extern __u32 tcp_reno_undo_cwnd(struct sock *sk) __ksym; + +__u32 BPF_STRUCT_OPS(bpf_cubic_undo_cwnd, struct sock *sk) +{ + return tcp_reno_undo_cwnd(sk); +} + +SEC(".struct_ops") +struct tcp_congestion_ops cubic = { + .init = (void *)bpf_cubic_init, + .ssthresh = (void *)bpf_cubic_recalc_ssthresh, + .cong_avoid = (void *)bpf_cubic_cong_avoid, + .set_state = (void *)bpf_cubic_state, + .undo_cwnd = (void *)bpf_cubic_undo_cwnd, + .cwnd_event = (void *)bpf_cubic_cwnd_event, + .pkts_acked = (void *)bpf_cubic_acked, + .name = "bpf_cubic", +}; diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c new file mode 100644 index 0000000000..460682759a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c @@ -0,0 +1,258 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +/* WARNING: This implemenation is not necessarily the same + * as the tcp_dctcp.c. The purpose is mainly for testing + * the kernel BPF logic. + */ + +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/types.h> +#include <linux/stddef.h> +#include <linux/tcp.h> +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; + +volatile const char fallback[TCP_CA_NAME_MAX]; +const char bpf_dctcp[] = "bpf_dctcp"; +const char tcp_cdg[] = "cdg"; +char cc_res[TCP_CA_NAME_MAX]; +int tcp_cdg_res = 0; +int stg_result = 0; +int ebusy_cnt = 0; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} sk_stg_map SEC(".maps"); + +#define DCTCP_MAX_ALPHA 1024U + +struct dctcp { + __u32 old_delivered; + __u32 old_delivered_ce; + __u32 prior_rcv_nxt; + __u32 dctcp_alpha; + __u32 next_seq; + __u32 ce_state; + __u32 loss_cwnd; +}; + +static unsigned int dctcp_shift_g = 4; /* g = 1/2^4 */ +static unsigned int dctcp_alpha_on_init = DCTCP_MAX_ALPHA; + +static __always_inline void dctcp_reset(const struct tcp_sock *tp, + struct dctcp *ca) +{ + ca->next_seq = tp->snd_nxt; + + ca->old_delivered = tp->delivered; + ca->old_delivered_ce = tp->delivered_ce; +} + +SEC("struct_ops/dctcp_init") +void BPF_PROG(dctcp_init, struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct dctcp *ca = inet_csk_ca(sk); + int *stg; + + if (!(tp->ecn_flags & TCP_ECN_OK) && fallback[0]) { + /* Switch to fallback */ + if (bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION, + (void *)fallback, sizeof(fallback)) == -EBUSY) + ebusy_cnt++; + + /* Switch back to myself and the recurred dctcp_init() + * will get -EBUSY for all bpf_setsockopt(TCP_CONGESTION), + * except the last "cdg" one. + */ + if (bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION, + (void *)bpf_dctcp, sizeof(bpf_dctcp)) == -EBUSY) + ebusy_cnt++; + + /* Switch back to fallback */ + if (bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION, + (void *)fallback, sizeof(fallback)) == -EBUSY) + ebusy_cnt++; + + /* Expecting -ENOTSUPP for tcp_cdg_res */ + tcp_cdg_res = bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION, + (void *)tcp_cdg, sizeof(tcp_cdg)); + bpf_getsockopt(sk, SOL_TCP, TCP_CONGESTION, + (void *)cc_res, sizeof(cc_res)); + return; + } + + ca->prior_rcv_nxt = tp->rcv_nxt; + ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA); + ca->loss_cwnd = 0; + ca->ce_state = 0; + + stg = bpf_sk_storage_get(&sk_stg_map, (void *)tp, NULL, 0); + if (stg) { + stg_result = *stg; + bpf_sk_storage_delete(&sk_stg_map, (void *)tp); + } + dctcp_reset(tp, ca); +} + +SEC("struct_ops/dctcp_ssthresh") +__u32 BPF_PROG(dctcp_ssthresh, struct sock *sk) +{ + struct dctcp *ca = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); + + ca->loss_cwnd = tp->snd_cwnd; + return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U); +} + +SEC("struct_ops/dctcp_update_alpha") +void BPF_PROG(dctcp_update_alpha, struct sock *sk, __u32 flags) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct dctcp *ca = inet_csk_ca(sk); + + /* Expired RTT */ + if (!before(tp->snd_una, ca->next_seq)) { + __u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce; + __u32 alpha = ca->dctcp_alpha; + + /* alpha = (1 - g) * alpha + g * F */ + + alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g); + if (delivered_ce) { + __u32 delivered = tp->delivered - ca->old_delivered; + + /* If dctcp_shift_g == 1, a 32bit value would overflow + * after 8 M packets. + */ + delivered_ce <<= (10 - dctcp_shift_g); + delivered_ce /= max(1U, delivered); + + alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA); + } + ca->dctcp_alpha = alpha; + dctcp_reset(tp, ca); + } +} + +static __always_inline void dctcp_react_to_loss(struct sock *sk) +{ + struct dctcp *ca = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); + + ca->loss_cwnd = tp->snd_cwnd; + tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U); +} + +SEC("struct_ops/dctcp_state") +void BPF_PROG(dctcp_state, struct sock *sk, __u8 new_state) +{ + if (new_state == TCP_CA_Recovery && + new_state != BPF_CORE_READ_BITFIELD(inet_csk(sk), icsk_ca_state)) + dctcp_react_to_loss(sk); + /* We handle RTO in dctcp_cwnd_event to ensure that we perform only + * one loss-adjustment per RTT. + */ +} + +static __always_inline void dctcp_ece_ack_cwr(struct sock *sk, __u32 ce_state) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (ce_state == 1) + tp->ecn_flags |= TCP_ECN_DEMAND_CWR; + else + tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; +} + +/* Minimal DCTP CE state machine: + * + * S: 0 <- last pkt was non-CE + * 1 <- last pkt was CE + */ +static __always_inline +void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt, + __u32 *prior_rcv_nxt, __u32 *ce_state) +{ + __u32 new_ce_state = (evt == CA_EVENT_ECN_IS_CE) ? 1 : 0; + + if (*ce_state != new_ce_state) { + /* CE state has changed, force an immediate ACK to + * reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { + dctcp_ece_ack_cwr(sk, *ce_state); + bpf_tcp_send_ack(sk, *prior_rcv_nxt); + } + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; + } + *prior_rcv_nxt = tcp_sk(sk)->rcv_nxt; + *ce_state = new_ce_state; + dctcp_ece_ack_cwr(sk, new_ce_state); +} + +SEC("struct_ops/dctcp_cwnd_event") +void BPF_PROG(dctcp_cwnd_event, struct sock *sk, enum tcp_ca_event ev) +{ + struct dctcp *ca = inet_csk_ca(sk); + + switch (ev) { + case CA_EVENT_ECN_IS_CE: + case CA_EVENT_ECN_NO_CE: + dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state); + break; + case CA_EVENT_LOSS: + dctcp_react_to_loss(sk); + break; + default: + /* Don't care for the rest. */ + break; + } +} + +SEC("struct_ops/dctcp_cwnd_undo") +__u32 BPF_PROG(dctcp_cwnd_undo, struct sock *sk) +{ + const struct dctcp *ca = inet_csk_ca(sk); + + return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd); +} + +extern void tcp_reno_cong_avoid(struct sock *sk, __u32 ack, __u32 acked) __ksym; + +SEC("struct_ops/dctcp_reno_cong_avoid") +void BPF_PROG(dctcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked) +{ + tcp_reno_cong_avoid(sk, ack, acked); +} + +SEC(".struct_ops") +struct tcp_congestion_ops dctcp_nouse = { + .init = (void *)dctcp_init, + .set_state = (void *)dctcp_state, + .flags = TCP_CONG_NEEDS_ECN, + .name = "bpf_dctcp_nouse", +}; + +SEC(".struct_ops") +struct tcp_congestion_ops dctcp = { + .init = (void *)dctcp_init, + .in_ack_event = (void *)dctcp_update_alpha, + .cwnd_event = (void *)dctcp_cwnd_event, + .ssthresh = (void *)dctcp_ssthresh, + .cong_avoid = (void *)dctcp_cong_avoid, + .undo_cwnd = (void *)dctcp_cwnd_undo, + .set_state = (void *)dctcp_state, + .flags = TCP_CONG_NEEDS_ECN, + .name = "bpf_dctcp", +}; diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp_release.c b/tools/testing/selftests/bpf/progs/bpf_dctcp_release.c new file mode 100644 index 0000000000..d836f7c372 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_dctcp_release.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/types.h> +#include <linux/stddef.h> +#include <linux/tcp.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; +const char cubic[] = "cubic"; + +void BPF_STRUCT_OPS(dctcp_nouse_release, struct sock *sk) +{ + bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION, + (void *)cubic, sizeof(cubic)); +} + +SEC(".struct_ops") +struct tcp_congestion_ops dctcp_rel = { + .release = (void *)dctcp_nouse_release, + .name = "bpf_dctcp_rel", +}; diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c new file mode 100644 index 0000000000..b04e092fac --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -0,0 +1,437 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <limits.h> +#include <stddef.h> +#include <stdbool.h> +#include <string.h> +#include <linux/pkt_cls.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/icmp.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/if_packet.h> +#include <sys/socket.h> +#include <linux/if_tunnel.h> +#include <linux/mpls.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define PROG(F) PROG_(F, _##F) +#define PROG_(NUM, NAME) SEC("flow_dissector") int flow_dissector_##NUM + +#define FLOW_CONTINUE_SADDR 0x7f00007f /* 127.0.0.127 */ + +/* These are the identifiers of the BPF programs that will be used in tail + * calls. Name is limited to 16 characters, with the terminating character and + * bpf_func_ above, we have only 6 to work with, anything after will be cropped. + */ +#define IP 0 +#define IPV6 1 +#define IPV6OP 2 /* Destination/Hop-by-Hop Options IPv6 Ext. Header */ +#define IPV6FR 3 /* Fragmentation IPv6 Extension Header */ +#define MPLS 4 +#define VLAN 5 +#define MAX_PROG 6 + +#define IP_MF 0x2000 +#define IP_OFFSET 0x1FFF +#define IP6_MF 0x0001 +#define IP6_OFFSET 0xFFF8 + +struct vlan_hdr { + __be16 h_vlan_TCI; + __be16 h_vlan_encapsulated_proto; +}; + +struct gre_hdr { + __be16 flags; + __be16 proto; +}; + +struct frag_hdr { + __u8 nexthdr; + __u8 reserved; + __be16 frag_off; + __be32 identification; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, MAX_PROG); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1024); + __type(key, __u32); + __type(value, struct bpf_flow_keys); +} last_dissection SEC(".maps"); + +static __always_inline int export_flow_keys(struct bpf_flow_keys *keys, + int ret) +{ + __u32 key = (__u32)(keys->sport) << 16 | keys->dport; + struct bpf_flow_keys val; + + memcpy(&val, keys, sizeof(val)); + bpf_map_update_elem(&last_dissection, &key, &val, BPF_ANY); + return ret; +} + +#define IPV6_FLOWLABEL_MASK __bpf_constant_htonl(0x000FFFFF) +static inline __be32 ip6_flowlabel(const struct ipv6hdr *hdr) +{ + return *(__be32 *)hdr & IPV6_FLOWLABEL_MASK; +} + +static __always_inline void *bpf_flow_dissect_get_header(struct __sk_buff *skb, + __u16 hdr_size, + void *buffer) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + __u16 thoff = skb->flow_keys->thoff; + __u8 *hdr; + + /* Verifies this variable offset does not overflow */ + if (thoff > (USHRT_MAX - hdr_size)) + return NULL; + + hdr = data + thoff; + if (hdr + hdr_size <= data_end) + return hdr; + + if (bpf_skb_load_bytes(skb, thoff, buffer, hdr_size)) + return NULL; + + return buffer; +} + +/* Dispatches on ETHERTYPE */ +static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto) +{ + struct bpf_flow_keys *keys = skb->flow_keys; + + switch (proto) { + case bpf_htons(ETH_P_IP): + bpf_tail_call_static(skb, &jmp_table, IP); + break; + case bpf_htons(ETH_P_IPV6): + bpf_tail_call_static(skb, &jmp_table, IPV6); + break; + case bpf_htons(ETH_P_MPLS_MC): + case bpf_htons(ETH_P_MPLS_UC): + bpf_tail_call_static(skb, &jmp_table, MPLS); + break; + case bpf_htons(ETH_P_8021Q): + case bpf_htons(ETH_P_8021AD): + bpf_tail_call_static(skb, &jmp_table, VLAN); + break; + default: + /* Protocol not supported */ + return export_flow_keys(keys, BPF_DROP); + } + + return export_flow_keys(keys, BPF_DROP); +} + +SEC("flow_dissector") +int _dissect(struct __sk_buff *skb) +{ + struct bpf_flow_keys *keys = skb->flow_keys; + + if (keys->n_proto == bpf_htons(ETH_P_IP)) { + /* IP traffic from FLOW_CONTINUE_SADDR falls-back to + * standard dissector + */ + struct iphdr *iph, _iph; + + iph = bpf_flow_dissect_get_header(skb, sizeof(*iph), &_iph); + if (iph && iph->ihl == 5 && + iph->saddr == bpf_htonl(FLOW_CONTINUE_SADDR)) { + return BPF_FLOW_DISSECTOR_CONTINUE; + } + } + + return parse_eth_proto(skb, keys->n_proto); +} + +/* Parses on IPPROTO_* */ +static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) +{ + struct bpf_flow_keys *keys = skb->flow_keys; + void *data_end = (void *)(long)skb->data_end; + struct icmphdr *icmp, _icmp; + struct gre_hdr *gre, _gre; + struct ethhdr *eth, _eth; + struct tcphdr *tcp, _tcp; + struct udphdr *udp, _udp; + + switch (proto) { + case IPPROTO_ICMP: + icmp = bpf_flow_dissect_get_header(skb, sizeof(*icmp), &_icmp); + if (!icmp) + return export_flow_keys(keys, BPF_DROP); + return export_flow_keys(keys, BPF_OK); + case IPPROTO_IPIP: + keys->is_encap = true; + if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP) + return export_flow_keys(keys, BPF_OK); + + return parse_eth_proto(skb, bpf_htons(ETH_P_IP)); + case IPPROTO_IPV6: + keys->is_encap = true; + if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP) + return export_flow_keys(keys, BPF_OK); + + return parse_eth_proto(skb, bpf_htons(ETH_P_IPV6)); + case IPPROTO_GRE: + gre = bpf_flow_dissect_get_header(skb, sizeof(*gre), &_gre); + if (!gre) + return export_flow_keys(keys, BPF_DROP); + + if (bpf_htons(gre->flags & GRE_VERSION)) + /* Only inspect standard GRE packets with version 0 */ + return export_flow_keys(keys, BPF_OK); + + keys->thoff += sizeof(*gre); /* Step over GRE Flags and Proto */ + if (GRE_IS_CSUM(gre->flags)) + keys->thoff += 4; /* Step over chksum and Padding */ + if (GRE_IS_KEY(gre->flags)) + keys->thoff += 4; /* Step over key */ + if (GRE_IS_SEQ(gre->flags)) + keys->thoff += 4; /* Step over sequence number */ + + keys->is_encap = true; + if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP) + return export_flow_keys(keys, BPF_OK); + + if (gre->proto == bpf_htons(ETH_P_TEB)) { + eth = bpf_flow_dissect_get_header(skb, sizeof(*eth), + &_eth); + if (!eth) + return export_flow_keys(keys, BPF_DROP); + + keys->thoff += sizeof(*eth); + + return parse_eth_proto(skb, eth->h_proto); + } else { + return parse_eth_proto(skb, gre->proto); + } + case IPPROTO_TCP: + tcp = bpf_flow_dissect_get_header(skb, sizeof(*tcp), &_tcp); + if (!tcp) + return export_flow_keys(keys, BPF_DROP); + + if (tcp->doff < 5) + return export_flow_keys(keys, BPF_DROP); + + if ((__u8 *)tcp + (tcp->doff << 2) > data_end) + return export_flow_keys(keys, BPF_DROP); + + keys->sport = tcp->source; + keys->dport = tcp->dest; + return export_flow_keys(keys, BPF_OK); + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + udp = bpf_flow_dissect_get_header(skb, sizeof(*udp), &_udp); + if (!udp) + return export_flow_keys(keys, BPF_DROP); + + keys->sport = udp->source; + keys->dport = udp->dest; + return export_flow_keys(keys, BPF_OK); + default: + return export_flow_keys(keys, BPF_DROP); + } + + return export_flow_keys(keys, BPF_DROP); +} + +static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr) +{ + struct bpf_flow_keys *keys = skb->flow_keys; + + switch (nexthdr) { + case IPPROTO_HOPOPTS: + case IPPROTO_DSTOPTS: + bpf_tail_call_static(skb, &jmp_table, IPV6OP); + break; + case IPPROTO_FRAGMENT: + bpf_tail_call_static(skb, &jmp_table, IPV6FR); + break; + default: + return parse_ip_proto(skb, nexthdr); + } + + return export_flow_keys(keys, BPF_DROP); +} + +PROG(IP)(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + struct bpf_flow_keys *keys = skb->flow_keys; + void *data = (void *)(long)skb->data; + struct iphdr *iph, _iph; + bool done = false; + + iph = bpf_flow_dissect_get_header(skb, sizeof(*iph), &_iph); + if (!iph) + return export_flow_keys(keys, BPF_DROP); + + /* IP header cannot be smaller than 20 bytes */ + if (iph->ihl < 5) + return export_flow_keys(keys, BPF_DROP); + + keys->addr_proto = ETH_P_IP; + keys->ipv4_src = iph->saddr; + keys->ipv4_dst = iph->daddr; + keys->ip_proto = iph->protocol; + + keys->thoff += iph->ihl << 2; + if (data + keys->thoff > data_end) + return export_flow_keys(keys, BPF_DROP); + + if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET)) { + keys->is_frag = true; + if (iph->frag_off & bpf_htons(IP_OFFSET)) { + /* From second fragment on, packets do not have headers + * we can parse. + */ + done = true; + } else { + keys->is_first_frag = true; + /* No need to parse fragmented packet unless + * explicitly asked for. + */ + if (!(keys->flags & + BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) + done = true; + } + } + + if (done) + return export_flow_keys(keys, BPF_OK); + + return parse_ip_proto(skb, iph->protocol); +} + +PROG(IPV6)(struct __sk_buff *skb) +{ + struct bpf_flow_keys *keys = skb->flow_keys; + struct ipv6hdr *ip6h, _ip6h; + + ip6h = bpf_flow_dissect_get_header(skb, sizeof(*ip6h), &_ip6h); + if (!ip6h) + return export_flow_keys(keys, BPF_DROP); + + keys->addr_proto = ETH_P_IPV6; + memcpy(&keys->ipv6_src, &ip6h->saddr, 2*sizeof(ip6h->saddr)); + + keys->thoff += sizeof(struct ipv6hdr); + keys->ip_proto = ip6h->nexthdr; + keys->flow_label = ip6_flowlabel(ip6h); + + if (keys->flow_label && keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL) + return export_flow_keys(keys, BPF_OK); + + return parse_ipv6_proto(skb, ip6h->nexthdr); +} + +PROG(IPV6OP)(struct __sk_buff *skb) +{ + struct bpf_flow_keys *keys = skb->flow_keys; + struct ipv6_opt_hdr *ip6h, _ip6h; + + ip6h = bpf_flow_dissect_get_header(skb, sizeof(*ip6h), &_ip6h); + if (!ip6h) + return export_flow_keys(keys, BPF_DROP); + + /* hlen is in 8-octets and does not include the first 8 bytes + * of the header + */ + keys->thoff += (1 + ip6h->hdrlen) << 3; + keys->ip_proto = ip6h->nexthdr; + + return parse_ipv6_proto(skb, ip6h->nexthdr); +} + +PROG(IPV6FR)(struct __sk_buff *skb) +{ + struct bpf_flow_keys *keys = skb->flow_keys; + struct frag_hdr *fragh, _fragh; + + fragh = bpf_flow_dissect_get_header(skb, sizeof(*fragh), &_fragh); + if (!fragh) + return export_flow_keys(keys, BPF_DROP); + + keys->thoff += sizeof(*fragh); + keys->is_frag = true; + keys->ip_proto = fragh->nexthdr; + + if (!(fragh->frag_off & bpf_htons(IP6_OFFSET))) { + keys->is_first_frag = true; + + /* No need to parse fragmented packet unless + * explicitly asked for. + */ + if (!(keys->flags & BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) + return export_flow_keys(keys, BPF_OK); + } else { + return export_flow_keys(keys, BPF_OK); + } + + return parse_ipv6_proto(skb, fragh->nexthdr); +} + +PROG(MPLS)(struct __sk_buff *skb) +{ + struct bpf_flow_keys *keys = skb->flow_keys; + struct mpls_label *mpls, _mpls; + + mpls = bpf_flow_dissect_get_header(skb, sizeof(*mpls), &_mpls); + if (!mpls) + return export_flow_keys(keys, BPF_DROP); + + return export_flow_keys(keys, BPF_OK); +} + +PROG(VLAN)(struct __sk_buff *skb) +{ + struct bpf_flow_keys *keys = skb->flow_keys; + struct vlan_hdr *vlan, _vlan; + + /* Account for double-tagging */ + if (keys->n_proto == bpf_htons(ETH_P_8021AD)) { + vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan); + if (!vlan) + return export_flow_keys(keys, BPF_DROP); + + if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q)) + return export_flow_keys(keys, BPF_DROP); + + keys->nhoff += sizeof(*vlan); + keys->thoff += sizeof(*vlan); + } + + vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan); + if (!vlan) + return export_flow_keys(keys, BPF_DROP); + + keys->nhoff += sizeof(*vlan); + keys->thoff += sizeof(*vlan); + /* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/ + if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) || + vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q)) + return export_flow_keys(keys, BPF_DROP); + + keys->n_proto = vlan->h_vlan_encapsulated_proto; + return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto); +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_hashmap_full_update_bench.c b/tools/testing/selftests/bpf/progs/bpf_hashmap_full_update_bench.c new file mode 100644 index 0000000000..56957557e3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_hashmap_full_update_bench.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Bytedance */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +#define MAX_ENTRIES 1000 + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, u64); + __uint(max_entries, MAX_ENTRIES); +} hash_map_bench SEC(".maps"); + +u64 __attribute__((__aligned__(256))) percpu_time[256]; +u64 nr_loops; + +static int loop_update_callback(__u32 index, u32 *key) +{ + u64 init_val = 1; + + bpf_map_update_elem(&hash_map_bench, key, &init_val, BPF_ANY); + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int benchmark(void *ctx) +{ + u32 cpu = bpf_get_smp_processor_id(); + u32 key = cpu + MAX_ENTRIES; + u64 start_time = bpf_ktime_get_ns(); + + bpf_loop(nr_loops, loop_update_callback, &key, 0); + percpu_time[cpu & 255] = bpf_ktime_get_ns() - start_time; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_hashmap_lookup.c b/tools/testing/selftests/bpf/progs/bpf_hashmap_lookup.c new file mode 100644 index 0000000000..1eb74ddca4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_hashmap_lookup.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); +} hash_map_bench SEC(".maps"); + +/* The number of slots to store times */ +#define NR_SLOTS 32 +#define NR_CPUS 256 +#define CPU_MASK (NR_CPUS-1) + +/* Configured by userspace */ +u64 nr_entries; +u64 nr_loops; +u32 __attribute__((__aligned__(8))) key[NR_CPUS]; + +/* Filled by us */ +u64 __attribute__((__aligned__(256))) percpu_times_index[NR_CPUS]; +u64 __attribute__((__aligned__(256))) percpu_times[NR_CPUS][NR_SLOTS]; + +static inline void patch_key(u32 i) +{ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + key[0] = i + 1; +#else + key[0] = __builtin_bswap32(i + 1); +#endif + /* the rest of key is random and is configured by userspace */ +} + +static int lookup_callback(__u32 index, u32 *unused) +{ + patch_key(index); + return bpf_map_lookup_elem(&hash_map_bench, key) ? 0 : 1; +} + +static int loop_lookup_callback(__u32 index, u32 *unused) +{ + return bpf_loop(nr_entries, lookup_callback, NULL, 0) ? 0 : 1; +} + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int benchmark(void *ctx) +{ + u32 cpu = bpf_get_smp_processor_id(); + u32 times_index; + u64 start_time; + + times_index = percpu_times_index[cpu & CPU_MASK] % NR_SLOTS; + start_time = bpf_ktime_get_ns(); + bpf_loop(nr_loops, loop_lookup_callback, NULL, 0); + percpu_times[cpu & CPU_MASK][times_index] = bpf_ktime_get_ns() - start_time; + percpu_times_index[cpu & CPU_MASK] += 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h new file mode 100644 index 0000000000..c41ee80533 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter.h @@ -0,0 +1,167 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2020 Facebook */ +/* "undefine" structs in vmlinux.h, because we "override" them below */ +#define bpf_iter_meta bpf_iter_meta___not_used +#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used +#define bpf_iter__ipv6_route bpf_iter__ipv6_route___not_used +#define bpf_iter__netlink bpf_iter__netlink___not_used +#define bpf_iter__task bpf_iter__task___not_used +#define bpf_iter__task_file bpf_iter__task_file___not_used +#define bpf_iter__task_vma bpf_iter__task_vma___not_used +#define bpf_iter__tcp bpf_iter__tcp___not_used +#define tcp6_sock tcp6_sock___not_used +#define bpf_iter__udp bpf_iter__udp___not_used +#define udp6_sock udp6_sock___not_used +#define bpf_iter__unix bpf_iter__unix___not_used +#define bpf_iter__bpf_map_elem bpf_iter__bpf_map_elem___not_used +#define bpf_iter__bpf_sk_storage_map bpf_iter__bpf_sk_storage_map___not_used +#define bpf_iter__sockmap bpf_iter__sockmap___not_used +#define bpf_iter__bpf_link bpf_iter__bpf_link___not_used +#define bpf_iter__cgroup bpf_iter__cgroup___not_used +#define btf_ptr btf_ptr___not_used +#define BTF_F_COMPACT BTF_F_COMPACT___not_used +#define BTF_F_NONAME BTF_F_NONAME___not_used +#define BTF_F_PTR_RAW BTF_F_PTR_RAW___not_used +#define BTF_F_ZERO BTF_F_ZERO___not_used +#define bpf_iter__ksym bpf_iter__ksym___not_used +#include "vmlinux.h" +#undef bpf_iter_meta +#undef bpf_iter__bpf_map +#undef bpf_iter__ipv6_route +#undef bpf_iter__netlink +#undef bpf_iter__task +#undef bpf_iter__task_file +#undef bpf_iter__task_vma +#undef bpf_iter__tcp +#undef tcp6_sock +#undef bpf_iter__udp +#undef udp6_sock +#undef bpf_iter__unix +#undef bpf_iter__bpf_map_elem +#undef bpf_iter__bpf_sk_storage_map +#undef bpf_iter__sockmap +#undef bpf_iter__bpf_link +#undef bpf_iter__cgroup +#undef btf_ptr +#undef BTF_F_COMPACT +#undef BTF_F_NONAME +#undef BTF_F_PTR_RAW +#undef BTF_F_ZERO +#undef bpf_iter__ksym + +struct bpf_iter_meta { + struct seq_file *seq; + __u64 session_id; + __u64 seq_num; +} __attribute__((preserve_access_index)); + +struct bpf_iter__ipv6_route { + struct bpf_iter_meta *meta; + struct fib6_info *rt; +} __attribute__((preserve_access_index)); + +struct bpf_iter__netlink { + struct bpf_iter_meta *meta; + struct netlink_sock *sk; +} __attribute__((preserve_access_index)); + +struct bpf_iter__task { + struct bpf_iter_meta *meta; + struct task_struct *task; +} __attribute__((preserve_access_index)); + +struct bpf_iter__task_file { + struct bpf_iter_meta *meta; + struct task_struct *task; + __u32 fd; + struct file *file; +} __attribute__((preserve_access_index)); + +struct bpf_iter__task_vma { + struct bpf_iter_meta *meta; + struct task_struct *task; + struct vm_area_struct *vma; +} __attribute__((preserve_access_index)); + +struct bpf_iter__bpf_map { + struct bpf_iter_meta *meta; + struct bpf_map *map; +} __attribute__((preserve_access_index)); + +struct bpf_iter__tcp { + struct bpf_iter_meta *meta; + struct sock_common *sk_common; + uid_t uid; +} __attribute__((preserve_access_index)); + +struct tcp6_sock { + struct tcp_sock tcp; + struct ipv6_pinfo inet6; +} __attribute__((preserve_access_index)); + +struct bpf_iter__udp { + struct bpf_iter_meta *meta; + struct udp_sock *udp_sk; + uid_t uid __attribute__((aligned(8))); + int bucket __attribute__((aligned(8))); +} __attribute__((preserve_access_index)); + +struct udp6_sock { + struct udp_sock udp; + struct ipv6_pinfo inet6; +} __attribute__((preserve_access_index)); + +struct bpf_iter__unix { + struct bpf_iter_meta *meta; + struct unix_sock *unix_sk; + uid_t uid; +} __attribute__((preserve_access_index)); + +struct bpf_iter__bpf_map_elem { + struct bpf_iter_meta *meta; + struct bpf_map *map; + void *key; + void *value; +}; + +struct bpf_iter__bpf_sk_storage_map { + struct bpf_iter_meta *meta; + struct bpf_map *map; + struct sock *sk; + void *value; +}; + +struct bpf_iter__sockmap { + struct bpf_iter_meta *meta; + struct bpf_map *map; + void *key; + struct sock *sk; +}; + +struct bpf_iter__bpf_link { + struct bpf_iter_meta *meta; + struct bpf_link *link; +}; + +struct bpf_iter__cgroup { + struct bpf_iter_meta *meta; + struct cgroup *cgroup; +} __attribute__((preserve_access_index)); + +struct btf_ptr { + void *ptr; + __u32 type_id; + __u32 flags; +}; + +enum { + BTF_F_COMPACT = (1ULL << 0), + BTF_F_NONAME = (1ULL << 1), + BTF_F_PTR_RAW = (1ULL << 2), + BTF_F_ZERO = (1ULL << 3), +}; + +struct bpf_iter__ksym { + struct bpf_iter_meta *meta; + struct kallsym_iter *ksym; +}; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c new file mode 100644 index 0000000000..c5969ca6f2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct key_t { + int a; + int b; + int c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 3); + __type(key, __u32); + __type(value, __u64); +} arraymap1 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 10); + __type(key, __u64); + __type(value, __u32); +} hashmap1 SEC(".maps"); + +__u32 key_sum = 0; +__u64 val_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_array_map(struct bpf_iter__bpf_map_elem *ctx) +{ + __u32 *hmap_val, *key = ctx->key; + __u64 *val = ctx->value; + + if (key == (void *)0 || val == (void *)0) + return 0; + + bpf_seq_write(ctx->meta->seq, key, sizeof(__u32)); + bpf_seq_write(ctx->meta->seq, val, sizeof(__u64)); + key_sum += *key; + val_sum += *val; + + /* workaround - It's necessary to do this convoluted (val, key) + * write into hashmap1, instead of simply doing + * bpf_map_update_elem(&hashmap1, val, key, BPF_ANY); + * because key has MEM_RDONLY flag and bpf_map_update elem expects + * types without this flag + */ + bpf_map_update_elem(&hashmap1, val, val, BPF_ANY); + hmap_val = bpf_map_lookup_elem(&hashmap1, val); + if (hmap_val) + *hmap_val = *key; + + *val = *key; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c new file mode 100644 index 0000000000..d7a69217fb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct key_t { + int a; + int b; + int c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, struct key_t); + __type(value, __u64); +} hashmap1 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, __u64); + __type(value, __u64); +} hashmap2 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, struct key_t); + __type(value, __u32); +} hashmap3 SEC(".maps"); + +/* will set before prog run */ +bool in_test_mode = 0; + +/* will collect results during prog run */ +__u32 key_sum_a = 0, key_sum_b = 0, key_sum_c = 0; +__u64 val_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + __u32 seq_num = ctx->meta->seq_num; + struct bpf_map *map = ctx->map; + struct key_t *key = ctx->key; + struct key_t tmp_key; + __u64 *val = ctx->value; + __u64 tmp_val = 0; + int ret; + + if (in_test_mode) { + /* test mode is used by selftests to + * test functionality of bpf_hash_map iter. + * + * the above hashmap1 will have correct size + * and will be accepted, hashmap2 and hashmap3 + * should be rejected due to smaller key/value + * size. + */ + if (key == (void *)0 || val == (void *)0) + return 0; + + /* update the value and then delete the <key, value> pair. + * it should not impact the existing 'val' which is still + * accessible under rcu. + */ + __builtin_memcpy(&tmp_key, key, sizeof(struct key_t)); + ret = bpf_map_update_elem(&hashmap1, &tmp_key, &tmp_val, 0); + if (ret) + return 0; + ret = bpf_map_delete_elem(&hashmap1, &tmp_key); + if (ret) + return 0; + + key_sum_a += key->a; + key_sum_b += key->b; + key_sum_c += key->c; + val_sum += *val; + return 0; + } + + /* non-test mode, the map is prepared with the + * below bpftool command sequence: + * bpftool map create /sys/fs/bpf/m1 type hash \ + * key 12 value 8 entries 3 name map1 + * bpftool map update id 77 key 0 0 0 1 0 0 0 0 0 0 0 1 \ + * value 0 0 0 1 0 0 0 1 + * bpftool map update id 77 key 0 0 0 1 0 0 0 0 0 0 0 2 \ + * value 0 0 0 1 0 0 0 2 + * The bpftool iter command line: + * bpftool iter pin ./bpf_iter_bpf_hash_map.o /sys/fs/bpf/p1 \ + * map id 77 + * The below output will be: + * map dump starts + * 77: (1000000 0 2000000) (200000001000000) + * 77: (1000000 0 1000000) (100000001000000) + * map dump ends + */ + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, "map dump starts\n"); + + if (key == (void *)0 || val == (void *)0) { + BPF_SEQ_PRINTF(seq, "map dump ends\n"); + return 0; + } + + BPF_SEQ_PRINTF(seq, "%d: (%x %d %x) (%llx)\n", map->id, + key->a, key->b, key->c, *val); + + return 0; +} + +SEC("iter.s/bpf_map_elem") +int sleepable_dummy_dump(struct bpf_iter__bpf_map_elem *ctx) +{ + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(ctx->meta->seq, "map dump starts\n"); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_link.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_link.c new file mode 100644 index 0000000000..e1af2f8f75 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_link.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Red Hat, Inc. */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +SEC("iter/bpf_link") +int dump_bpf_link(struct bpf_iter__bpf_link *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct bpf_link *link = ctx->link; + int link_id; + + if (!link) + return 0; + + link_id = link->id; + bpf_seq_write(seq, &link_id, sizeof(link_id)); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c new file mode 100644 index 0000000000..6c39e86b66 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +SEC("iter/bpf_map") +int dump_bpf_map(struct bpf_iter__bpf_map *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + __u64 seq_num = ctx->meta->seq_num; + struct bpf_map *map = ctx->map; + + if (map == (void *)0) { + BPF_SEQ_PRINTF(seq, " %%%%%% END %%%%%%\n"); + return 0; + } + + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, " id refcnt usercnt locked_vm\n"); + + BPF_SEQ_PRINTF(seq, "%8u %8ld %8ld %10lu\n", map->id, map->refcnt.counter, + map->usercnt.counter, + 0LLU); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c new file mode 100644 index 0000000000..85fa710fad --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct key_t { + int a; + int b; + int c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 3); + __type(key, __u32); + __type(value, __u32); +} arraymap1 SEC(".maps"); + +/* will set before prog run */ +volatile const __u32 num_cpus = 0; + +__u32 key_sum = 0, val_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_percpu_array_map(struct bpf_iter__bpf_map_elem *ctx) +{ + __u32 *key = ctx->key; + void *pptr = ctx->value; + __u32 step; + int i; + + if (key == (void *)0 || pptr == (void *)0) + return 0; + + key_sum += *key; + + step = 8; + for (i = 0; i < num_cpus; i++) { + val_sum += *(__u32 *)pptr; + pptr += step; + } + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c new file mode 100644 index 0000000000..feaaa2b89c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct key_t { + int a; + int b; + int c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 3); + __type(key, struct key_t); + __type(value, __u32); +} hashmap1 SEC(".maps"); + +/* will set before prog run */ +volatile const __u32 num_cpus = 0; + +/* will collect results during prog run */ +__u32 key_sum_a = 0, key_sum_b = 0, key_sum_c = 0; +__u32 val_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_percpu_hash_map(struct bpf_iter__bpf_map_elem *ctx) +{ + struct key_t *key = ctx->key; + void *pptr = ctx->value; + __u32 step; + int i; + + if (key == (void *)0 || pptr == (void *)0) + return 0; + + key_sum_a += key->a; + key_sum_b += key->b; + key_sum_c += key->c; + + step = 8; + for (i = 0; i < num_cpus; i++) { + val_sum += *(__u32 *)pptr; + pptr += step; + } + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_helpers.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_helpers.c new file mode 100644 index 0000000000..6cecab2b32 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_helpers.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Google LLC. */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} sk_stg_map SEC(".maps"); + +SEC("iter/bpf_sk_storage_map") +int delete_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx) +{ + if (ctx->sk) + bpf_sk_storage_delete(&sk_stg_map, ctx->sk); + + return 0; +} + +SEC("iter/task_file") +int fill_socket_owner(struct bpf_iter__task_file *ctx) +{ + struct task_struct *task = ctx->task; + struct file *file = ctx->file; + struct socket *sock; + int *sock_tgid; + + if (!task || !file) + return 0; + + sock = bpf_sock_from_file(file); + if (!sock) + return 0; + + sock_tgid = bpf_sk_storage_get(&sk_stg_map, sock->sk, 0, 0); + if (!sock_tgid) + return 0; + + *sock_tgid = task->tgid; + + return 0; +} + +SEC("iter/tcp") +int negate_socket_local_storage(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + int *sock_tgid; + + if (!sk_common) + return 0; + + sock_tgid = bpf_sk_storage_get(&sk_stg_map, sk_common, 0, 0); + if (!sock_tgid) + return 0; + + *sock_tgid = -*sock_tgid; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c new file mode 100644 index 0000000000..c7b8e006b1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} sk_stg_map SEC(".maps"); + +__u32 val_sum = 0; +__u32 ipv6_sk_count = 0; +__u32 to_add_val = 0; + +SEC("iter/bpf_sk_storage_map") +int rw_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx) +{ + struct sock *sk = ctx->sk; + __u32 *val = ctx->value; + + if (sk == NULL || val == NULL) + return 0; + + if (sk->sk_family == AF_INET6) + ipv6_sk_count++; + + val_sum += *val; + + *val += to_add_val; + + return 0; +} + +SEC("iter/bpf_sk_storage_map") +int oob_write_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx) +{ + struct sock *sk = ctx->sk; + __u32 *val = ctx->value; + + if (sk == NULL || val == NULL) + return 0; + + *(val + 1) = 0xdeadbeef; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c new file mode 100644 index 0000000000..784a610ce0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +extern bool CONFIG_IPV6_SUBTREES __kconfig __weak; + +SEC("iter/ipv6_route") +int dump_ipv6_route(struct bpf_iter__ipv6_route *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct fib6_info *rt = ctx->rt; + const struct net_device *dev; + struct fib6_nh *fib6_nh; + unsigned int flags; + struct nexthop *nh; + + if (rt == (void *)0) + return 0; + + fib6_nh = &rt->fib6_nh[0]; + flags = rt->fib6_flags; + + /* FIXME: nexthop_is_multipath is not handled here. */ + nh = rt->nh; + if (rt->nh) + fib6_nh = &nh->nh_info->fib6_nh; + + BPF_SEQ_PRINTF(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); + + if (CONFIG_IPV6_SUBTREES) + BPF_SEQ_PRINTF(seq, "%pi6 %02x ", &rt->fib6_src.addr, + rt->fib6_src.plen); + else + BPF_SEQ_PRINTF(seq, "00000000000000000000000000000000 00 "); + + if (fib6_nh->fib_nh_gw_family) { + flags |= RTF_GATEWAY; + BPF_SEQ_PRINTF(seq, "%pi6 ", &fib6_nh->fib_nh_gw6); + } else { + BPF_SEQ_PRINTF(seq, "00000000000000000000000000000000 "); + } + + dev = fib6_nh->fib_nh_dev; + if (dev) + BPF_SEQ_PRINTF(seq, "%08x %08x %08x %08x %8s\n", rt->fib6_metric, + rt->fib6_ref.refs.counter, 0, flags, dev->name); + else + BPF_SEQ_PRINTF(seq, "%08x %08x %08x %08x\n", rt->fib6_metric, + rt->fib6_ref.refs.counter, 0, flags); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c b/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c new file mode 100644 index 0000000000..521267818f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022, Oracle and/or its affiliates. */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +unsigned long last_sym_value = 0; + +static inline char to_lower(char c) +{ + if (c >= 'A' && c <= 'Z') + c += ('a' - 'A'); + return c; +} + +static inline char to_upper(char c) +{ + if (c >= 'a' && c <= 'z') + c -= ('a' - 'A'); + return c; +} + +/* Dump symbols with max size; the latter is calculated by caching symbol N value + * and when iterating on symbol N+1, we can print max size of symbol N via + * address of N+1 - address of N. + */ +SEC("iter/ksym") +int dump_ksym(struct bpf_iter__ksym *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct kallsym_iter *iter = ctx->ksym; + __u32 seq_num = ctx->meta->seq_num; + unsigned long value; + char type; + + if (!iter) + return 0; + + if (seq_num == 0) { + BPF_SEQ_PRINTF(seq, "ADDR TYPE NAME MODULE_NAME KIND MAX_SIZE\n"); + return 0; + } + if (last_sym_value) + BPF_SEQ_PRINTF(seq, "0x%x\n", iter->value - last_sym_value); + else + BPF_SEQ_PRINTF(seq, "\n"); + + value = iter->show_value ? iter->value : 0; + + last_sym_value = value; + + type = iter->type; + + if (iter->module_name[0]) { + type = iter->exported ? to_upper(type) : to_lower(type); + BPF_SEQ_PRINTF(seq, "0x%llx %c %s [ %s ] ", + value, type, iter->name, iter->module_name); + } else { + BPF_SEQ_PRINTF(seq, "0x%llx %c %s ", value, type, iter->name); + } + if (!iter->pos_mod_end || iter->pos_mod_end > iter->pos) + BPF_SEQ_PRINTF(seq, "MOD "); + else if (!iter->pos_ftrace_mod_end || iter->pos_ftrace_mod_end > iter->pos) + BPF_SEQ_PRINTF(seq, "FTRACE_MOD "); + else if (!iter->pos_bpf_end || iter->pos_bpf_end > iter->pos) + BPF_SEQ_PRINTF(seq, "BPF "); + else + BPF_SEQ_PRINTF(seq, "KPROBE "); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c new file mode 100644 index 0000000000..a28e51e2dc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +static __attribute__((noinline)) struct inode *SOCK_INODE(struct socket *socket) +{ + return &container_of(socket, struct socket_alloc, socket)->vfs_inode; +} + +SEC("iter/netlink") +int dump_netlink(struct bpf_iter__netlink *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct netlink_sock *nlk = ctx->sk; + unsigned long group, ino; + struct inode *inode; + struct socket *sk; + struct sock *s; + + if (nlk == (void *)0) + return 0; + + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(seq, "sk Eth Pid Groups " + "Rmem Wmem Dump Locks Drops " + "Inode\n"); + + s = &nlk->sk; + BPF_SEQ_PRINTF(seq, "%pK %-3d ", s, s->sk_protocol); + + if (!nlk->groups) { + group = 0; + } else { + /* FIXME: temporary use bpf_probe_read_kernel here, needs + * verifier support to do direct access. + */ + bpf_probe_read_kernel(&group, sizeof(group), &nlk->groups[0]); + } + BPF_SEQ_PRINTF(seq, "%-10u %08x %-8d %-8d %-5d %-8d ", + nlk->portid, (u32)group, + s->sk_rmem_alloc.counter, + s->sk_wmem_alloc.refs.counter - 1, + nlk->cb_running, s->sk_refcnt.refs.counter); + + sk = s->sk_socket; + if (!sk) { + ino = 0; + } else { + /* FIXME: container_of inside SOCK_INODE has a forced + * type conversion, and direct access cannot be used + * with current verifier. + */ + inode = SOCK_INODE(sk); + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); + } + BPF_SEQ_PRINTF(seq, "%-8u %-8lu\n", s->sk_drops.counter, ino); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt.c b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt.c new file mode 100644 index 0000000000..ec7f91850d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define bpf_tcp_sk(skc) ({ \ + struct sock_common *_skc = skc; \ + sk = NULL; \ + tp = NULL; \ + if (_skc) { \ + tp = bpf_skc_to_tcp_sock(_skc); \ + sk = (struct sock *)tp; \ + } \ + tp; \ +}) + +unsigned short reuse_listen_hport = 0; +unsigned short listen_hport = 0; +char cubic_cc[TCP_CA_NAME_MAX] = "bpf_cubic"; +char dctcp_cc[TCP_CA_NAME_MAX] = "bpf_dctcp"; +bool random_retry = false; + +static bool tcp_cc_eq(const char *a, const char *b) +{ + int i; + + for (i = 0; i < TCP_CA_NAME_MAX; i++) { + if (a[i] != b[i]) + return false; + if (!a[i]) + break; + } + + return true; +} + +SEC("iter/tcp") +int change_tcp_cc(struct bpf_iter__tcp *ctx) +{ + char cur_cc[TCP_CA_NAME_MAX]; + struct tcp_sock *tp; + struct sock *sk; + + if (!bpf_tcp_sk(ctx->sk_common)) + return 0; + + if (sk->sk_family != AF_INET6 || + (sk->sk_state != TCP_LISTEN && + sk->sk_state != TCP_ESTABLISHED) || + (sk->sk_num != reuse_listen_hport && + sk->sk_num != listen_hport && + bpf_ntohs(sk->sk_dport) != listen_hport)) + return 0; + + if (bpf_getsockopt(tp, SOL_TCP, TCP_CONGESTION, + cur_cc, sizeof(cur_cc))) + return 0; + + if (!tcp_cc_eq(cur_cc, cubic_cc)) + return 0; + + if (random_retry && bpf_get_prandom_u32() % 4 == 1) + return 1; + + bpf_setsockopt(tp, SOL_TCP, TCP_CONGESTION, dctcp_cc, sizeof(dctcp_cc)); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c new file mode 100644 index 0000000000..eafc877ea4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <limits.h> + +#define AUTOBIND_LEN 6 +char sun_path[AUTOBIND_LEN]; + +#define NR_CASES 5 +int sndbuf_setsockopt[NR_CASES] = {-1, 0, 8192, INT_MAX / 2, INT_MAX}; +int sndbuf_getsockopt[NR_CASES] = {-1, -1, -1, -1, -1}; +int sndbuf_getsockopt_expected[NR_CASES]; + +static inline int cmpname(struct unix_sock *unix_sk) +{ + int i; + + for (i = 0; i < AUTOBIND_LEN; i++) { + if (unix_sk->addr->name->sun_path[i] != sun_path[i]) + return -1; + } + + return 0; +} + +SEC("iter/unix") +int change_sndbuf(struct bpf_iter__unix *ctx) +{ + struct unix_sock *unix_sk = ctx->unix_sk; + int i, err; + + if (!unix_sk || !unix_sk->addr) + return 0; + + if (unix_sk->addr->name->sun_path[0]) + return 0; + + if (cmpname(unix_sk)) + return 0; + + for (i = 0; i < NR_CASES; i++) { + err = bpf_setsockopt(unix_sk, SOL_SOCKET, SO_SNDBUF, + &sndbuf_setsockopt[i], + sizeof(sndbuf_setsockopt[i])); + if (err) + break; + + err = bpf_getsockopt(unix_sk, SOL_SOCKET, SO_SNDBUF, + &sndbuf_getsockopt[i], + sizeof(sndbuf_getsockopt[i])); + if (err) + break; + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c b/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c new file mode 100644 index 0000000000..f3af0e30ce --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Cloudflare */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <errno.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 64); + __type(key, __u32); + __type(value, __u64); +} sockmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, 64); + __type(key, __u32); + __type(value, __u64); +} sockhash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, 64); + __type(key, __u32); + __type(value, __u64); +} dst SEC(".maps"); + +__u32 elems = 0; +__u32 socks = 0; + +SEC("iter/sockmap") +int copy(struct bpf_iter__sockmap *ctx) +{ + struct sock *sk = ctx->sk; + __u32 tmp, *key = ctx->key; + int ret; + + if (!key) + return 0; + + elems++; + + /* We need a temporary buffer on the stack, since the verifier doesn't + * let us use the pointer from the context as an argument to the helper. + */ + tmp = *key; + + if (sk) { + socks++; + return bpf_map_update_elem(&dst, &tmp, sk, 0) != 0; + } + + ret = bpf_map_delete_elem(&dst, &tmp); + return ret && ret != -ENOENT; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c new file mode 100644 index 0000000000..96131b9a1c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +uint32_t tid = 0; +int num_unknown_tid = 0; +int num_known_tid = 0; + +SEC("iter/task") +int dump_task(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + static char info[] = " === END ==="; + + if (task == (void *)0) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + if (task->pid != tid) + num_unknown_tid++; + else + num_known_tid++; + + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(seq, " tgid gid\n"); + + BPF_SEQ_PRINTF(seq, "%8d %8d\n", task->tgid, task->pid); + return 0; +} + +int num_expected_failure_copy_from_user_task = 0; +int num_success_copy_from_user_task = 0; + +SEC("iter.s/task") +int dump_task_sleepable(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + static const char info[] = " === END ==="; + struct pt_regs *regs; + void *ptr; + uint32_t user_data = 0; + int ret; + + if (task == (void *)0) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Read an invalid pointer and ensure we get an error */ + ptr = NULL; + ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0); + if (ret) { + ++num_expected_failure_copy_from_user_task; + } else { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Try to read the contents of the task's instruction pointer from the + * remote task's address space. + */ + regs = (struct pt_regs *)bpf_task_pt_regs(task); + if (regs == (void *)0) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + ptr = (void *)PT_REGS_IP(regs); + + ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0); + if (ret) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + ++num_success_copy_from_user_task; + + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(seq, " tgid gid data\n"); + + BPF_SEQ_PRINTF(seq, "%8d %8d %8d\n", task->tgid, task->pid, user_data); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c new file mode 100644 index 0000000000..bca8b889cb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020, Oracle and/or its affiliates. */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +#include <errno.h> + +char _license[] SEC("license") = "GPL"; + +long tasks = 0; +long seq_err = 0; +bool skip = false; + +SEC("iter/task") +int dump_task_struct(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + static struct btf_ptr ptr = { }; + long ret; + +#if __has_builtin(__builtin_btf_type_id) + ptr.type_id = bpf_core_type_id_kernel(struct task_struct); + ptr.ptr = task; + + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(seq, "Raw BTF task\n"); + + ret = bpf_seq_printf_btf(seq, &ptr, sizeof(ptr), 0); + switch (ret) { + case 0: + tasks++; + break; + case -ERANGE: + /* NULL task or task->fs, don't count it as an error. */ + break; + case -E2BIG: + return 1; + default: + seq_err = ret; + break; + } +#else + skip = true; +#endif + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c new file mode 100644 index 0000000000..b025508066 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +int count = 0; +int tgid = 0; +int last_tgid = 0; +int unique_tgid_count = 0; + +SEC("iter/task_file") +int dump_task_file(struct bpf_iter__task_file *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + struct file *file = ctx->file; + __u32 fd = ctx->fd; + + if (task == (void *)0 || file == (void *)0) + return 0; + + if (ctx->meta->seq_num == 0) { + count = 0; + BPF_SEQ_PRINTF(seq, " tgid gid fd file\n"); + } + + if (tgid == task->tgid && task->tgid != task->pid) + count++; + + if (last_tgid != task->tgid) { + last_tgid = task->tgid; + unique_tgid_count++; + } + + BPF_SEQ_PRINTF(seq, "%8d %8d %8d %lx\n", task->tgid, task->pid, fd, + (long)file->f_op); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c new file mode 100644 index 0000000000..442f4ca39f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +#define MAX_STACK_TRACE_DEPTH 64 +unsigned long entries[MAX_STACK_TRACE_DEPTH] = {}; +#define SIZE_OF_ULONG (sizeof(unsigned long)) + +SEC("iter/task") +int dump_task_stack(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + long i, retlen; + + if (task == (void *)0) + return 0; + + retlen = bpf_get_task_stack(task, entries, + MAX_STACK_TRACE_DEPTH * SIZE_OF_ULONG, 0); + if (retlen < 0) + return 0; + + BPF_SEQ_PRINTF(seq, "pid: %8u num_entries: %8u\n", task->pid, + retlen / SIZE_OF_ULONG); + for (i = 0; i < MAX_STACK_TRACE_DEPTH; i++) { + if (retlen > i * SIZE_OF_ULONG) + BPF_SEQ_PRINTF(seq, "[<0>] %pB\n", (void *)entries[i]); + } + BPF_SEQ_PRINTF(seq, "\n"); + + return 0; +} + +int num_user_stacks = 0; + +SEC("iter/task") +int get_task_user_stacks(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + uint64_t buf_sz = 0; + int64_t res; + + if (task == (void *)0) + return 0; + + res = bpf_get_task_stack(task, entries, + MAX_STACK_TRACE_DEPTH * SIZE_OF_ULONG, BPF_F_USER_STACK); + if (res <= 0) + return 0; + + /* Only one task, the current one, should succeed */ + ++num_user_stacks; + + buf_sz += res; + + /* If the verifier doesn't refine bpf_get_task_stack res, and instead + * assumes res is entirely unknown, this program will fail to load as + * the verifier will believe that max buf_sz value allows reading + * past the end of entries in bpf_seq_write call + */ + bpf_seq_write(seq, &entries, buf_sz); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c new file mode 100644 index 0000000000..dd923dc637 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +/* Copied from mm.h */ +#define VM_READ 0x00000001 +#define VM_WRITE 0x00000002 +#define VM_EXEC 0x00000004 +#define VM_MAYSHARE 0x00000080 + +/* Copied from kdev_t.h */ +#define MINORBITS 20 +#define MINORMASK ((1U << MINORBITS) - 1) +#define MAJOR(dev) ((unsigned int) ((dev) >> MINORBITS)) +#define MINOR(dev) ((unsigned int) ((dev) & MINORMASK)) + +#define D_PATH_BUF_SIZE 1024 +char d_path_buf[D_PATH_BUF_SIZE] = {}; +__u32 pid = 0; +__u32 one_task = 0; +__u32 one_task_error = 0; + +SEC("iter/task_vma") int proc_maps(struct bpf_iter__task_vma *ctx) +{ + struct vm_area_struct *vma = ctx->vma; + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + struct file *file; + char perm_str[] = "----"; + + if (task == (void *)0 || vma == (void *)0) + return 0; + + file = vma->vm_file; + if (task->tgid != pid) { + if (one_task) + one_task_error = 1; + return 0; + } + perm_str[0] = (vma->vm_flags & VM_READ) ? 'r' : '-'; + perm_str[1] = (vma->vm_flags & VM_WRITE) ? 'w' : '-'; + perm_str[2] = (vma->vm_flags & VM_EXEC) ? 'x' : '-'; + perm_str[3] = (vma->vm_flags & VM_MAYSHARE) ? 's' : 'p'; + BPF_SEQ_PRINTF(seq, "%08llx-%08llx %s ", vma->vm_start, vma->vm_end, perm_str); + + if (file) { + __u32 dev = file->f_inode->i_sb->s_dev; + + bpf_d_path(&file->f_path, d_path_buf, D_PATH_BUF_SIZE); + + BPF_SEQ_PRINTF(seq, "%08llx ", vma->vm_pgoff << 12); + BPF_SEQ_PRINTF(seq, "%02x:%02x %u", MAJOR(dev), MINOR(dev), + file->f_inode->i_ino); + BPF_SEQ_PRINTF(seq, "\t%s\n", d_path_buf); + } else { + BPF_SEQ_PRINTF(seq, "%08llx 00:00 0\n", 0ULL); + } + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c new file mode 100644 index 0000000000..92267abb46 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c @@ -0,0 +1,233 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +char _license[] SEC("license") = "GPL"; + +static int hlist_unhashed_lockless(const struct hlist_node *h) +{ + return !(h->pprev); +} + +static int timer_pending(const struct timer_list * timer) +{ + return !hlist_unhashed_lockless(&timer->entry); +} + +extern unsigned CONFIG_HZ __kconfig; + +#define USER_HZ 100 +#define NSEC_PER_SEC 1000000000ULL +static clock_t jiffies_to_clock_t(unsigned long x) +{ + /* The implementation here tailored to a particular + * setting of USER_HZ. + */ + u64 tick_nsec = (NSEC_PER_SEC + CONFIG_HZ/2) / CONFIG_HZ; + u64 user_hz_nsec = NSEC_PER_SEC / USER_HZ; + + if ((tick_nsec % user_hz_nsec) == 0) { + if (CONFIG_HZ < USER_HZ) + return x * (USER_HZ / CONFIG_HZ); + else + return x / (CONFIG_HZ / USER_HZ); + } + return x * tick_nsec/user_hz_nsec; +} + +static clock_t jiffies_delta_to_clock_t(long delta) +{ + if (delta <= 0) + return 0; + + return jiffies_to_clock_t(delta); +} + +static long sock_i_ino(const struct sock *sk) +{ + const struct socket *sk_socket = sk->sk_socket; + const struct inode *inode; + unsigned long ino; + + if (!sk_socket) + return 0; + + inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); + return ino; +} + +static bool +inet_csk_in_pingpong_mode(const struct inet_connection_sock *icsk) +{ + return icsk->icsk_ack.pingpong >= TCP_PINGPONG_THRESH; +} + +static bool tcp_in_initial_slowstart(const struct tcp_sock *tcp) +{ + return tcp->snd_ssthresh >= TCP_INFINITE_SSTHRESH; +} + +static int dump_tcp_sock(struct seq_file *seq, struct tcp_sock *tp, + uid_t uid, __u32 seq_num) +{ + const struct inet_connection_sock *icsk; + const struct fastopen_queue *fastopenq; + const struct inet_sock *inet; + unsigned long timer_expires; + const struct sock *sp; + __u16 destp, srcp; + __be32 dest, src; + int timer_active; + int rx_queue; + int state; + + icsk = &tp->inet_conn; + inet = &icsk->icsk_inet; + sp = &inet->sk; + fastopenq = &icsk->icsk_accept_queue.fastopenq; + + dest = inet->inet_daddr; + src = inet->inet_rcv_saddr; + destp = bpf_ntohs(inet->inet_dport); + srcp = bpf_ntohs(inet->inet_sport); + + if (icsk->icsk_pending == ICSK_TIME_RETRANS || + icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || + icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { + timer_active = 1; + timer_expires = icsk->icsk_timeout; + } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { + timer_active = 4; + timer_expires = icsk->icsk_timeout; + } else if (timer_pending(&sp->sk_timer)) { + timer_active = 2; + timer_expires = sp->sk_timer.expires; + } else { + timer_active = 0; + timer_expires = bpf_jiffies64(); + } + + state = sp->sk_state; + if (state == TCP_LISTEN) { + rx_queue = sp->sk_ack_backlog; + } else { + rx_queue = tp->rcv_nxt - tp->copied_seq; + if (rx_queue < 0) + rx_queue = 0; + } + + BPF_SEQ_PRINTF(seq, "%4d: %08X:%04X %08X:%04X ", + seq_num, src, srcp, dest, destp); + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d ", + state, + tp->write_seq - tp->snd_una, rx_queue, + timer_active, + jiffies_delta_to_clock_t(timer_expires - bpf_jiffies64()), + icsk->icsk_retransmits, uid, + icsk->icsk_probes_out, + sock_i_ino(sp), + sp->sk_refcnt.refs.counter); + BPF_SEQ_PRINTF(seq, "%pK %lu %lu %u %u %d\n", + tp, + jiffies_to_clock_t(icsk->icsk_rto), + jiffies_to_clock_t(icsk->icsk_ack.ato), + (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(icsk), + tp->snd_cwnd, + state == TCP_LISTEN ? fastopenq->max_qlen + : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh) + ); + + return 0; +} + +static int dump_tw_sock(struct seq_file *seq, struct tcp_timewait_sock *ttw, + uid_t uid, __u32 seq_num) +{ + struct inet_timewait_sock *tw = &ttw->tw_sk; + __u16 destp, srcp; + __be32 dest, src; + long delta; + + delta = tw->tw_timer.expires - bpf_jiffies64(); + dest = tw->tw_daddr; + src = tw->tw_rcv_saddr; + destp = bpf_ntohs(tw->tw_dport); + srcp = bpf_ntohs(tw->tw_sport); + + BPF_SEQ_PRINTF(seq, "%4d: %08X:%04X %08X:%04X ", + seq_num, src, srcp, dest, destp); + + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", + tw->tw_substate, 0, 0, + 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, + tw->tw_refcnt.refs.counter, tw); + + return 0; +} + +static int dump_req_sock(struct seq_file *seq, struct tcp_request_sock *treq, + uid_t uid, __u32 seq_num) +{ + struct inet_request_sock *irsk = &treq->req; + struct request_sock *req = &irsk->req; + long ttd; + + ttd = req->rsk_timer.expires - bpf_jiffies64(); + + if (ttd < 0) + ttd = 0; + + BPF_SEQ_PRINTF(seq, "%4d: %08X:%04X %08X:%04X ", + seq_num, irsk->ir_loc_addr, + irsk->ir_num, irsk->ir_rmt_addr, + bpf_ntohs(irsk->ir_rmt_port)); + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", + TCP_SYN_RECV, 0, 0, 1, jiffies_to_clock_t(ttd), + req->num_timeout, uid, 0, 0, 0, req); + + return 0; +} + +SEC("iter/tcp") +int dump_tcp4(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + struct seq_file *seq = ctx->meta->seq; + struct tcp_timewait_sock *tw; + struct tcp_request_sock *req; + struct tcp_sock *tp; + uid_t uid = ctx->uid; + __u32 seq_num; + + if (sk_common == (void *)0) + return 0; + + seq_num = ctx->meta->seq_num; + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, " sl " + "local_address " + "rem_address " + "st tx_queue rx_queue tr tm->when retrnsmt" + " uid timeout inode\n"); + + if (sk_common->skc_family != AF_INET) + return 0; + + tp = bpf_skc_to_tcp_sock(sk_common); + if (tp) + return dump_tcp_sock(seq, tp, uid, seq_num); + + tw = bpf_skc_to_tcp_timewait_sock(sk_common); + if (tw) + return dump_tw_sock(seq, tw, uid, seq_num); + + req = bpf_skc_to_tcp_request_sock(sk_common); + if (req) + return dump_req_sock(seq, req, uid, seq_num); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c new file mode 100644 index 0000000000..943f7bba18 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c @@ -0,0 +1,249 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +char _license[] SEC("license") = "GPL"; + +static int hlist_unhashed_lockless(const struct hlist_node *h) +{ + return !(h->pprev); +} + +static int timer_pending(const struct timer_list * timer) +{ + return !hlist_unhashed_lockless(&timer->entry); +} + +extern unsigned CONFIG_HZ __kconfig; + +#define USER_HZ 100 +#define NSEC_PER_SEC 1000000000ULL +static clock_t jiffies_to_clock_t(unsigned long x) +{ + /* The implementation here tailored to a particular + * setting of USER_HZ. + */ + u64 tick_nsec = (NSEC_PER_SEC + CONFIG_HZ/2) / CONFIG_HZ; + u64 user_hz_nsec = NSEC_PER_SEC / USER_HZ; + + if ((tick_nsec % user_hz_nsec) == 0) { + if (CONFIG_HZ < USER_HZ) + return x * (USER_HZ / CONFIG_HZ); + else + return x / (CONFIG_HZ / USER_HZ); + } + return x * tick_nsec/user_hz_nsec; +} + +static clock_t jiffies_delta_to_clock_t(long delta) +{ + if (delta <= 0) + return 0; + + return jiffies_to_clock_t(delta); +} + +static long sock_i_ino(const struct sock *sk) +{ + const struct socket *sk_socket = sk->sk_socket; + const struct inode *inode; + unsigned long ino; + + if (!sk_socket) + return 0; + + inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); + return ino; +} + +static bool +inet_csk_in_pingpong_mode(const struct inet_connection_sock *icsk) +{ + return icsk->icsk_ack.pingpong >= TCP_PINGPONG_THRESH; +} + +static bool tcp_in_initial_slowstart(const struct tcp_sock *tcp) +{ + return tcp->snd_ssthresh >= TCP_INFINITE_SSTHRESH; +} + +static int dump_tcp6_sock(struct seq_file *seq, struct tcp6_sock *tp, + uid_t uid, __u32 seq_num) +{ + const struct inet_connection_sock *icsk; + const struct fastopen_queue *fastopenq; + const struct in6_addr *dest, *src; + const struct inet_sock *inet; + unsigned long timer_expires; + const struct sock *sp; + __u16 destp, srcp; + int timer_active; + int rx_queue; + int state; + + icsk = &tp->tcp.inet_conn; + inet = &icsk->icsk_inet; + sp = &inet->sk; + fastopenq = &icsk->icsk_accept_queue.fastopenq; + + dest = &sp->sk_v6_daddr; + src = &sp->sk_v6_rcv_saddr; + destp = bpf_ntohs(inet->inet_dport); + srcp = bpf_ntohs(inet->inet_sport); + + if (icsk->icsk_pending == ICSK_TIME_RETRANS || + icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || + icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { + timer_active = 1; + timer_expires = icsk->icsk_timeout; + } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { + timer_active = 4; + timer_expires = icsk->icsk_timeout; + } else if (timer_pending(&sp->sk_timer)) { + timer_active = 2; + timer_expires = sp->sk_timer.expires; + } else { + timer_active = 0; + timer_expires = bpf_jiffies64(); + } + + state = sp->sk_state; + if (state == TCP_LISTEN) { + rx_queue = sp->sk_ack_backlog; + } else { + rx_queue = tp->tcp.rcv_nxt - tp->tcp.copied_seq; + if (rx_queue < 0) + rx_queue = 0; + } + + BPF_SEQ_PRINTF(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ", + seq_num, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], srcp, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], destp); + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d ", + state, + tp->tcp.write_seq - tp->tcp.snd_una, rx_queue, + timer_active, + jiffies_delta_to_clock_t(timer_expires - bpf_jiffies64()), + icsk->icsk_retransmits, uid, + icsk->icsk_probes_out, + sock_i_ino(sp), + sp->sk_refcnt.refs.counter); + BPF_SEQ_PRINTF(seq, "%pK %lu %lu %u %u %d\n", + tp, + jiffies_to_clock_t(icsk->icsk_rto), + jiffies_to_clock_t(icsk->icsk_ack.ato), + (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(icsk), + tp->tcp.snd_cwnd, + state == TCP_LISTEN ? fastopenq->max_qlen + : (tcp_in_initial_slowstart(&tp->tcp) ? -1 + : tp->tcp.snd_ssthresh) + ); + + return 0; +} + +static int dump_tw_sock(struct seq_file *seq, struct tcp_timewait_sock *ttw, + uid_t uid, __u32 seq_num) +{ + struct inet_timewait_sock *tw = &ttw->tw_sk; + const struct in6_addr *dest, *src; + __u16 destp, srcp; + long delta; + + delta = tw->tw_timer.expires - bpf_jiffies64(); + dest = &tw->tw_v6_daddr; + src = &tw->tw_v6_rcv_saddr; + destp = bpf_ntohs(tw->tw_dport); + srcp = bpf_ntohs(tw->tw_sport); + + BPF_SEQ_PRINTF(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ", + seq_num, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], srcp, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], destp); + + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", + tw->tw_substate, 0, 0, + 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, + tw->tw_refcnt.refs.counter, tw); + + return 0; +} + +static int dump_req_sock(struct seq_file *seq, struct tcp_request_sock *treq, + uid_t uid, __u32 seq_num) +{ + struct inet_request_sock *irsk = &treq->req; + struct request_sock *req = &irsk->req; + struct in6_addr *src, *dest; + long ttd; + + ttd = req->rsk_timer.expires - bpf_jiffies64(); + src = &irsk->ir_v6_loc_addr; + dest = &irsk->ir_v6_rmt_addr; + + if (ttd < 0) + ttd = 0; + + BPF_SEQ_PRINTF(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ", + seq_num, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], + irsk->ir_num, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], + bpf_ntohs(irsk->ir_rmt_port)); + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", + TCP_SYN_RECV, 0, 0, 1, jiffies_to_clock_t(ttd), + req->num_timeout, uid, 0, 0, 0, req); + + return 0; +} + +SEC("iter/tcp") +int dump_tcp6(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + struct seq_file *seq = ctx->meta->seq; + struct tcp_timewait_sock *tw; + struct tcp_request_sock *req; + struct tcp6_sock *tp; + uid_t uid = ctx->uid; + __u32 seq_num; + + if (sk_common == (void *)0) + return 0; + + seq_num = ctx->meta->seq_num; + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, " sl " + "local_address " + "remote_address " + "st tx_queue rx_queue tr tm->when retrnsmt" + " uid timeout inode\n"); + + if (sk_common->skc_family != AF_INET6) + return 0; + + tp = bpf_skc_to_tcp6_sock(sk_common); + if (tp) + return dump_tcp6_sock(seq, tp, uid, seq_num); + + tw = bpf_skc_to_tcp_timewait_sock(sk_common); + if (tw) + return dump_tw_sock(seq, tw, uid, seq_num); + + req = bpf_skc_to_tcp_request_sock(sk_common); + if (req) + return dump_req_sock(seq, req, uid, seq_num); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern1.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern1.c new file mode 100644 index 0000000000..c71a7c2831 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern1.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#define START_CHAR 'a' +#include "bpf_iter_test_kern_common.h" diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern2.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern2.c new file mode 100644 index 0000000000..8bdc8dc074 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern2.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#define START_CHAR 'A' +#include "bpf_iter_test_kern_common.h" diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c new file mode 100644 index 0000000000..2a4647f20c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +SEC("iter/task") +int dump_task(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + int tgid; + + tgid = task->tgid; + bpf_seq_write(seq, &tgid, sizeof(tgid)); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c new file mode 100644 index 0000000000..400fdf8d62 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +__u32 map1_id = 0, map2_id = 0; +__u32 map1_accessed = 0, map2_accessed = 0; +__u64 map1_seqnum = 0, map2_seqnum1 = 0, map2_seqnum2 = 0; + +volatile const __u32 print_len; +volatile const __u32 ret1; + +SEC("iter/bpf_map") +int dump_bpf_map(struct bpf_iter__bpf_map *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct bpf_map *map = ctx->map; + __u64 seq_num; + int i, ret = 0; + + if (map == (void *)0) + return 0; + + /* only dump map1_id and map2_id */ + if (map->id != map1_id && map->id != map2_id) + return 0; + + seq_num = ctx->meta->seq_num; + if (map->id == map1_id) { + map1_seqnum = seq_num; + map1_accessed++; + } + + if (map->id == map2_id) { + if (map2_accessed == 0) { + map2_seqnum1 = seq_num; + if (ret1) + ret = 1; + } else { + map2_seqnum2 = seq_num; + } + map2_accessed++; + } + + /* fill seq_file buffer */ + for (i = 0; i < print_len; i++) + bpf_seq_write(seq, &seq_num, sizeof(seq_num)); + + return ret; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c new file mode 100644 index 0000000000..e3a7575e81 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct key_t { + int a; + int b; + int c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, struct key_t); + __type(value, __u64); +} hashmap1 SEC(".maps"); + +__u32 key_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) +{ + void *key = ctx->key; + + if (key == (void *)0) + return 0; + + /* out of bound access w.r.t. hashmap1 */ + key_sum += *(__u32 *)(key + sizeof(struct key_t)); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c new file mode 100644 index 0000000000..1c7304f56b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +__u32 value_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) +{ + void *value = ctx->value; + + if (value == (void *)0) + return 0; + + /* negative offset, verifier failure. */ + value_sum += *(__u32 *)(value - 4); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h new file mode 100644 index 0000000000..d5e3df66ad --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; +int count = 0; + +SEC("iter/task") +int dump_task(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + char c; + + if (count < 4) { + c = START_CHAR + count; + bpf_seq_write(seq, &c, sizeof(c)); + count++; + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c new file mode 100644 index 0000000000..cf0c485b1e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +char _license[] SEC("license") = "GPL"; + +static long sock_i_ino(const struct sock *sk) +{ + const struct socket *sk_socket = sk->sk_socket; + const struct inode *inode; + unsigned long ino; + + if (!sk_socket) + return 0; + + inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); + return ino; +} + +SEC("iter/udp") +int dump_udp4(struct bpf_iter__udp *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct udp_sock *udp_sk = ctx->udp_sk; + struct inet_sock *inet; + __u16 srcp, destp; + __be32 dest, src; + __u32 seq_num; + int rqueue; + + if (udp_sk == (void *)0) + return 0; + + seq_num = ctx->meta->seq_num; + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, + " sl local_address rem_address st tx_queue " + "rx_queue tr tm->when retrnsmt uid timeout " + "inode ref pointer drops\n"); + + /* filter out udp6 sockets */ + inet = &udp_sk->inet; + if (inet->sk.sk_family == AF_INET6) + return 0; + + inet = &udp_sk->inet; + dest = inet->inet_daddr; + src = inet->inet_rcv_saddr; + srcp = bpf_ntohs(inet->inet_sport); + destp = bpf_ntohs(inet->inet_dport); + rqueue = inet->sk.sk_rmem_alloc.counter - udp_sk->forward_deficit; + + BPF_SEQ_PRINTF(seq, "%5d: %08X:%04X %08X:%04X ", + ctx->bucket, src, srcp, dest, destp); + + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u\n", + inet->sk.sk_state, + inet->sk.sk_wmem_alloc.refs.counter - 1, + rqueue, + 0, 0L, 0, ctx->uid, 0, + sock_i_ino(&inet->sk), + inet->sk.sk_refcnt.refs.counter, udp_sk, + inet->sk.sk_drops.counter); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c new file mode 100644 index 0000000000..5031e21c43 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +char _license[] SEC("license") = "GPL"; + +#define IPV6_SEQ_DGRAM_HEADER \ + " sl " \ + "local_address " \ + "remote_address " \ + "st tx_queue rx_queue tr tm->when retrnsmt" \ + " uid timeout inode ref pointer drops\n" + +static long sock_i_ino(const struct sock *sk) +{ + const struct socket *sk_socket = sk->sk_socket; + const struct inode *inode; + unsigned long ino; + + if (!sk_socket) + return 0; + + inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); + return ino; +} + +SEC("iter/udp") +int dump_udp6(struct bpf_iter__udp *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct udp_sock *udp_sk = ctx->udp_sk; + const struct in6_addr *dest, *src; + struct udp6_sock *udp6_sk; + struct inet_sock *inet; + __u16 srcp, destp; + __u32 seq_num; + int rqueue; + + if (udp_sk == (void *)0) + return 0; + + seq_num = ctx->meta->seq_num; + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, IPV6_SEQ_DGRAM_HEADER); + + udp6_sk = bpf_skc_to_udp6_sock(udp_sk); + if (udp6_sk == (void *)0) + return 0; + + inet = &udp_sk->inet; + srcp = bpf_ntohs(inet->inet_sport); + destp = bpf_ntohs(inet->inet_dport); + rqueue = inet->sk.sk_rmem_alloc.counter - udp_sk->forward_deficit; + dest = &inet->sk.sk_v6_daddr; + src = &inet->sk.sk_v6_rcv_saddr; + + BPF_SEQ_PRINTF(seq, "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ", + ctx->bucket, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], srcp, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], destp); + + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u\n", + inet->sk.sk_state, + inet->sk.sk_wmem_alloc.refs.counter - 1, + rqueue, + 0, 0L, 0, ctx->uid, 0, + sock_i_ino(&inet->sk), + inet->sk.sk_refcnt.refs.counter, udp_sk, + inet->sk.sk_drops.counter); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c new file mode 100644 index 0000000000..e6aefae388 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +char _license[] SEC("license") = "GPL"; + +static long sock_i_ino(const struct sock *sk) +{ + const struct socket *sk_socket = sk->sk_socket; + const struct inode *inode; + unsigned long ino; + + if (!sk_socket) + return 0; + + inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); + return ino; +} + +SEC("iter/unix") +int dump_unix(struct bpf_iter__unix *ctx) +{ + struct unix_sock *unix_sk = ctx->unix_sk; + struct sock *sk = (struct sock *)unix_sk; + struct seq_file *seq; + __u32 seq_num; + + if (!unix_sk) + return 0; + + seq = ctx->meta->seq; + seq_num = ctx->meta->seq_num; + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, "Num RefCount Protocol Flags Type St Inode Path\n"); + + BPF_SEQ_PRINTF(seq, "%pK: %08X %08X %08X %04X %02X %8lu", + unix_sk, + sk->sk_refcnt.refs.counter, + 0, + sk->sk_state == TCP_LISTEN ? __SO_ACCEPTCON : 0, + sk->sk_type, + sk->sk_socket ? + (sk->sk_state == TCP_ESTABLISHED ? SS_CONNECTED : SS_UNCONNECTED) : + (sk->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING), + sock_i_ino(sk)); + + if (unix_sk->addr) { + if (unix_sk->addr->name->sun_path[0]) { + BPF_SEQ_PRINTF(seq, " %s", unix_sk->addr->name->sun_path); + } else { + /* The name of the abstract UNIX domain socket starts + * with '\0' and can contain '\0'. The null bytes + * should be escaped as done in unix_seq_show(). + */ + __u64 i, len; + + len = unix_sk->addr->len - sizeof(short); + + BPF_SEQ_PRINTF(seq, " @"); + + for (i = 1; i < len; i++) { + /* unix_validate_addr() tests this upper bound. */ + if (i >= sizeof(struct sockaddr_un)) + break; + + BPF_SEQ_PRINTF(seq, "%c", + unix_sk->addr->name->sun_path[i] ?: + '@'); + } + } + } + + BPF_SEQ_PRINTF(seq, "\n"); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_vma_offset.c b/tools/testing/selftests/bpf/progs/bpf_iter_vma_offset.c new file mode 100644 index 0000000000..ee7455d262 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_vma_offset.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +__u32 unique_tgid_cnt = 0; +uintptr_t address = 0; +uintptr_t offset = 0; +__u32 last_tgid = 0; +__u32 pid = 0; +__u32 page_shift = 0; + +SEC("iter/task_vma") +int get_vma_offset(struct bpf_iter__task_vma *ctx) +{ + struct vm_area_struct *vma = ctx->vma; + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + + if (task == NULL || vma == NULL) + return 0; + + if (last_tgid != task->tgid) + unique_tgid_cnt++; + last_tgid = task->tgid; + + if (task->tgid != pid) + return 0; + + if (vma->vm_start <= address && vma->vm_end > address) { + offset = address - vma->vm_start + (vma->vm_pgoff << page_shift); + BPF_SEQ_PRINTF(seq, "OK\n"); + } + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_loop.c b/tools/testing/selftests/bpf/progs/bpf_loop.c new file mode 100644 index 0000000000..1d194455b1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_loop.c @@ -0,0 +1,225 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct callback_ctx { + int output; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 32); + __type(key, int); + __type(value, int); +} map1 SEC(".maps"); + +/* These should be set by the user program */ +u32 nested_callback_nr_loops; +u32 stop_index = -1; +u32 nr_loops; +int pid; +int callback_selector; + +/* Making these global variables so that the userspace program + * can verify the output through the skeleton + */ +int nr_loops_returned; +int g_output; +int err; + +static int callback(__u32 index, void *data) +{ + struct callback_ctx *ctx = data; + + if (index >= stop_index) + return 1; + + ctx->output += index; + + return 0; +} + +static int empty_callback(__u32 index, void *data) +{ + return 0; +} + +static int nested_callback2(__u32 index, void *data) +{ + nr_loops_returned += bpf_loop(nested_callback_nr_loops, callback, data, 0); + + return 0; +} + +static int nested_callback1(__u32 index, void *data) +{ + bpf_loop(nested_callback_nr_loops, nested_callback2, data, 0); + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int test_prog(void *ctx) +{ + struct callback_ctx data = {}; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + nr_loops_returned = bpf_loop(nr_loops, callback, &data, 0); + + if (nr_loops_returned < 0) + err = nr_loops_returned; + else + g_output = data.output; + + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int prog_null_ctx(void *ctx) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + nr_loops_returned = bpf_loop(nr_loops, empty_callback, NULL, 0); + + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int prog_invalid_flags(void *ctx) +{ + struct callback_ctx data = {}; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + err = bpf_loop(nr_loops, callback, &data, 1); + + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int prog_nested_calls(void *ctx) +{ + struct callback_ctx data = {}; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + nr_loops_returned = 0; + bpf_loop(nr_loops, nested_callback1, &data, 0); + + g_output = data.output; + + return 0; +} + +static int callback_set_f0(int i, void *ctx) +{ + g_output = 0xF0; + return 0; +} + +static int callback_set_0f(int i, void *ctx) +{ + g_output = 0x0F; + return 0; +} + +/* + * non-constant callback is a corner case for bpf_loop inline logic + */ +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int prog_non_constant_callback(void *ctx) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + int (*callback)(int i, void *ctx); + + g_output = 0; + + if (callback_selector == 0x0F) + callback = callback_set_0f; + else + callback = callback_set_f0; + + bpf_loop(1, callback, NULL, 0); + + return 0; +} + +static int stack_check_inner_callback(void *ctx) +{ + return 0; +} + +static int map1_lookup_elem(int key) +{ + int *val = bpf_map_lookup_elem(&map1, &key); + + return val ? *val : -1; +} + +static void map1_update_elem(int key, int val) +{ + bpf_map_update_elem(&map1, &key, &val, BPF_ANY); +} + +static int stack_check_outer_callback(void *ctx) +{ + int a = map1_lookup_elem(1); + int b = map1_lookup_elem(2); + int c = map1_lookup_elem(3); + int d = map1_lookup_elem(4); + int e = map1_lookup_elem(5); + int f = map1_lookup_elem(6); + + bpf_loop(1, stack_check_inner_callback, NULL, 0); + + map1_update_elem(1, a + 1); + map1_update_elem(2, b + 1); + map1_update_elem(3, c + 1); + map1_update_elem(4, d + 1); + map1_update_elem(5, e + 1); + map1_update_elem(6, f + 1); + + return 0; +} + +/* Some of the local variables in stack_check and + * stack_check_outer_callback would be allocated on stack by + * compiler. This test should verify that stack content for these + * variables is preserved between calls to bpf_loop (might be an issue + * if loop inlining allocates stack slots incorrectly). + */ +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int stack_check(void *ctx) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + int a = map1_lookup_elem(7); + int b = map1_lookup_elem(8); + int c = map1_lookup_elem(9); + int d = map1_lookup_elem(10); + int e = map1_lookup_elem(11); + int f = map1_lookup_elem(12); + + bpf_loop(1, stack_check_outer_callback, NULL, 0); + + map1_update_elem(7, a + 1); + map1_update_elem(8, b + 1); + map1_update_elem(9, c + 1); + map1_update_elem(10, d + 1); + map1_update_elem(11, e + 1); + map1_update_elem(12, f + 1); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c new file mode 100644 index 0000000000..d461746fd3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +u32 nr_loops; +long hits; + +static int empty_callback(__u32 index, void *data) +{ + return 0; +} + +static int outer_loop(__u32 index, void *data) +{ + bpf_loop(nr_loops, empty_callback, NULL, 0); + __sync_add_and_fetch(&hits, nr_loops); + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int benchmark(void *ctx) +{ + bpf_loop(1000, outer_loop, NULL, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h new file mode 100644 index 0000000000..799fff4995 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -0,0 +1,137 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __BPF_MISC_H__ +#define __BPF_MISC_H__ + +/* This set of attributes controls behavior of the + * test_loader.c:test_loader__run_subtests(). + * + * The test_loader sequentially loads each program in a skeleton. + * Programs could be loaded in privileged and unprivileged modes. + * - __success, __failure, __msg imply privileged mode; + * - __success_unpriv, __failure_unpriv, __msg_unpriv imply + * unprivileged mode. + * If combination of privileged and unprivileged attributes is present + * both modes are used. If none are present privileged mode is implied. + * + * See test_loader.c:drop_capabilities() for exact set of capabilities + * that differ between privileged and unprivileged modes. + * + * For test filtering purposes the name of the program loaded in + * unprivileged mode is derived from the usual program name by adding + * `@unpriv' suffix. + * + * __msg Message expected to be found in the verifier log. + * Multiple __msg attributes could be specified. + * __msg_unpriv Same as __msg but for unprivileged mode. + * + * __success Expect program load success in privileged mode. + * __success_unpriv Expect program load success in unprivileged mode. + * + * __failure Expect program load failure in privileged mode. + * __failure_unpriv Expect program load failure in unprivileged mode. + * + * __retval Execute the program using BPF_PROG_TEST_RUN command, + * expect return value to match passed parameter: + * - a decimal number + * - a hexadecimal number, when starts from 0x + * - literal INT_MIN + * - literal POINTER_VALUE (see definition below) + * - literal TEST_DATA_LEN (see definition below) + * __retval_unpriv Same, but load program in unprivileged mode. + * + * __description Text to be used instead of a program name for display + * and filtering purposes. + * + * __log_level Log level to use for the program, numeric value expected. + * + * __flag Adds one flag use for the program, the following values are valid: + * - BPF_F_STRICT_ALIGNMENT; + * - BPF_F_TEST_RND_HI32; + * - BPF_F_TEST_STATE_FREQ; + * - BPF_F_SLEEPABLE; + * - BPF_F_XDP_HAS_FRAGS; + * - A numeric value. + * Multiple __flag attributes could be specified, the final flags + * value is derived by applying binary "or" to all specified values. + * + * __auxiliary Annotated program is not a separate test, but used as auxiliary + * for some other test cases and should always be loaded. + * __auxiliary_unpriv Same, but load program in unprivileged mode. + */ +#define __msg(msg) __attribute__((btf_decl_tag("comment:test_expect_msg=" msg))) +#define __failure __attribute__((btf_decl_tag("comment:test_expect_failure"))) +#define __success __attribute__((btf_decl_tag("comment:test_expect_success"))) +#define __description(desc) __attribute__((btf_decl_tag("comment:test_description=" desc))) +#define __msg_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_msg_unpriv=" msg))) +#define __failure_unpriv __attribute__((btf_decl_tag("comment:test_expect_failure_unpriv"))) +#define __success_unpriv __attribute__((btf_decl_tag("comment:test_expect_success_unpriv"))) +#define __log_level(lvl) __attribute__((btf_decl_tag("comment:test_log_level="#lvl))) +#define __flag(flag) __attribute__((btf_decl_tag("comment:test_prog_flags="#flag))) +#define __retval(val) __attribute__((btf_decl_tag("comment:test_retval="#val))) +#define __retval_unpriv(val) __attribute__((btf_decl_tag("comment:test_retval_unpriv="#val))) +#define __auxiliary __attribute__((btf_decl_tag("comment:test_auxiliary"))) +#define __auxiliary_unpriv __attribute__((btf_decl_tag("comment:test_auxiliary_unpriv"))) + +/* Convenience macro for use with 'asm volatile' blocks */ +#define __naked __attribute__((naked)) +#define __clobber_all "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", "r8", "r9", "memory" +#define __clobber_common "r0", "r1", "r2", "r3", "r4", "r5", "memory" +#define __imm(name) [name]"i"(name) +#define __imm_const(name, expr) [name]"i"(expr) +#define __imm_addr(name) [name]"i"(&name) +#define __imm_ptr(name) [name]"p"(&name) +#define __imm_insn(name, expr) [name]"i"(*(long *)&(expr)) + +/* Magic constants used with __retval() */ +#define POINTER_VALUE 0xcafe4all +#define TEST_DATA_LEN 64 + +#ifndef __used +#define __used __attribute__((used)) +#endif + +#if defined(__TARGET_ARCH_x86) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__x64_" +#elif defined(__TARGET_ARCH_s390) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__s390x_" +#elif defined(__TARGET_ARCH_arm64) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__arm64_" +#elif defined(__TARGET_ARCH_riscv) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__riscv_" +#else +#define SYSCALL_WRAPPER 0 +#define SYS_PREFIX "__se_" +#endif + +/* How many arguments are passed to function in register */ +#if defined(__TARGET_ARCH_x86) || defined(__x86_64__) +#define FUNC_REG_ARG_CNT 6 +#elif defined(__i386__) +#define FUNC_REG_ARG_CNT 3 +#elif defined(__TARGET_ARCH_s390) || defined(__s390x__) +#define FUNC_REG_ARG_CNT 5 +#elif defined(__TARGET_ARCH_arm) || defined(__arm__) +#define FUNC_REG_ARG_CNT 4 +#elif defined(__TARGET_ARCH_arm64) || defined(__aarch64__) +#define FUNC_REG_ARG_CNT 8 +#elif defined(__TARGET_ARCH_mips) || defined(__mips__) +#define FUNC_REG_ARG_CNT 8 +#elif defined(__TARGET_ARCH_powerpc) || defined(__powerpc__) || defined(__powerpc64__) +#define FUNC_REG_ARG_CNT 8 +#elif defined(__TARGET_ARCH_sparc) || defined(__sparc__) +#define FUNC_REG_ARG_CNT 6 +#elif defined(__TARGET_ARCH_riscv) || defined(__riscv__) +#define FUNC_REG_ARG_CNT 8 +#else +/* default to 5 for others */ +#define FUNC_REG_ARG_CNT 5 +#endif + +/* make it look to compiler like value is read and written */ +#define __sink(expr) asm volatile("" : "+g"(expr)) + +#endif diff --git a/tools/testing/selftests/bpf/progs/bpf_mod_race.c b/tools/testing/selftests/bpf/progs/bpf_mod_race.c new file mode 100644 index 0000000000..82a5c6c6ba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_mod_race.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +const volatile struct { + /* thread to activate trace programs for */ + pid_t tgid; + /* return error from __init function */ + int inject_error; + /* uffd monitored range start address */ + void *fault_addr; +} bpf_mod_race_config = { -1 }; + +int bpf_blocking = 0; +int res_try_get_module = -1; + +static __always_inline bool check_thread_id(void) +{ + struct task_struct *task = bpf_get_current_task_btf(); + + return task->tgid == bpf_mod_race_config.tgid; +} + +/* The trace of execution is something like this: + * + * finit_module() + * load_module() + * prepare_coming_module() + * notifier_call(MODULE_STATE_COMING) + * btf_parse_module() + * btf_alloc_id() // Visible to userspace at this point + * list_add(btf_mod->list, &btf_modules) + * do_init_module() + * freeinit = kmalloc() + * ret = mod->init() + * bpf_prog_widen_race() + * bpf_copy_from_user() + * ...<sleep>... + * if (ret < 0) + * ... + * free_module() + * return ret + * + * At this point, module loading thread is blocked, we now load the program: + * + * bpf_check + * add_kfunc_call/check_pseudo_btf_id + * btf_try_get_module + * try_get_module_live == false + * return -ENXIO + * + * Without the fix (try_get_module_live in btf_try_get_module): + * + * bpf_check + * add_kfunc_call/check_pseudo_btf_id + * btf_try_get_module + * try_get_module == true + * <store module reference in btf_kfunc_tab or used_btf array> + * ... + * return fd + * + * Now, if we inject an error in the blocked program, our module will be freed + * (going straight from MODULE_STATE_COMING to MODULE_STATE_GOING). + * Later, when bpf program is freed, it will try to module_put already freed + * module. This is why try_get_module_live returns false if mod->state is not + * MODULE_STATE_LIVE. + */ + +SEC("fmod_ret.s/bpf_fentry_test1") +int BPF_PROG(widen_race, int a, int ret) +{ + char dst; + + if (!check_thread_id()) + return 0; + /* Indicate that we will attempt to block */ + bpf_blocking = 1; + bpf_copy_from_user(&dst, 1, bpf_mod_race_config.fault_addr); + return bpf_mod_race_config.inject_error; +} + +SEC("fexit/do_init_module") +int BPF_PROG(fexit_init_module, struct module *mod, int ret) +{ + if (!check_thread_id()) + return 0; + /* Indicate that we finished blocking */ + bpf_blocking = 2; + return 0; +} + +SEC("fexit/btf_try_get_module") +int BPF_PROG(fexit_module_get, const struct btf *btf, struct module *mod) +{ + res_try_get_module = !!mod; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c new file mode 100644 index 0000000000..1a476d8ed3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2022 Sony Group Corporation */ +#include <vmlinux.h> + +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +int arg1 = 0; +unsigned long arg2 = 0; +unsigned long arg3 = 0; +unsigned long arg4_cx = 0; +unsigned long arg4 = 0; +unsigned long arg5 = 0; + +int arg1_core = 0; +unsigned long arg2_core = 0; +unsigned long arg3_core = 0; +unsigned long arg4_core_cx = 0; +unsigned long arg4_core = 0; +unsigned long arg5_core = 0; + +int option_syscall = 0; +unsigned long arg2_syscall = 0; +unsigned long arg3_syscall = 0; +unsigned long arg4_syscall = 0; +unsigned long arg5_syscall = 0; + +const volatile pid_t filter_pid = 0; + +SEC("kprobe/" SYS_PREFIX "sys_prctl") +int BPF_KPROBE(handle_sys_prctl) +{ + struct pt_regs *real_regs; + pid_t pid = bpf_get_current_pid_tgid() >> 32; + unsigned long tmp = 0; + + if (pid != filter_pid) + return 0; + + real_regs = PT_REGS_SYSCALL_REGS(ctx); + + /* test for PT_REGS_PARM */ + +#if !defined(bpf_target_arm64) && !defined(bpf_target_s390) + bpf_probe_read_kernel(&tmp, sizeof(tmp), &PT_REGS_PARM1_SYSCALL(real_regs)); +#endif + arg1 = tmp; + bpf_probe_read_kernel(&arg2, sizeof(arg2), &PT_REGS_PARM2_SYSCALL(real_regs)); + bpf_probe_read_kernel(&arg3, sizeof(arg3), &PT_REGS_PARM3_SYSCALL(real_regs)); + bpf_probe_read_kernel(&arg4_cx, sizeof(arg4_cx), &PT_REGS_PARM4(real_regs)); + bpf_probe_read_kernel(&arg4, sizeof(arg4), &PT_REGS_PARM4_SYSCALL(real_regs)); + bpf_probe_read_kernel(&arg5, sizeof(arg5), &PT_REGS_PARM5_SYSCALL(real_regs)); + + /* test for the CORE variant of PT_REGS_PARM */ + arg1_core = PT_REGS_PARM1_CORE_SYSCALL(real_regs); + arg2_core = PT_REGS_PARM2_CORE_SYSCALL(real_regs); + arg3_core = PT_REGS_PARM3_CORE_SYSCALL(real_regs); + arg4_core_cx = PT_REGS_PARM4_CORE(real_regs); + arg4_core = PT_REGS_PARM4_CORE_SYSCALL(real_regs); + arg5_core = PT_REGS_PARM5_CORE_SYSCALL(real_regs); + + return 0; +} + +SEC("ksyscall/prctl") +int BPF_KSYSCALL(prctl_enter, int option, unsigned long arg2, + unsigned long arg3, unsigned long arg4, unsigned long arg5) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + + if (pid != filter_pid) + return 0; + + option_syscall = option; + arg2_syscall = arg2; + arg3_syscall = arg3; + arg4_syscall = arg4; + arg5_syscall = arg5; + return 0; +} + +__u64 splice_fd_in; +__u64 splice_off_in; +__u64 splice_fd_out; +__u64 splice_off_out; +__u64 splice_len; +__u64 splice_flags; + +SEC("ksyscall/splice") +int BPF_KSYSCALL(splice_enter, int fd_in, loff_t *off_in, int fd_out, + loff_t *off_out, size_t len, unsigned int flags) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + + if (pid != filter_pid) + return 0; + + splice_fd_in = fd_in; + splice_off_in = (__u64)off_in; + splice_fd_out = fd_out; + splice_off_out = (__u64)off_out; + splice_len = len; + splice_flags = flags; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c b/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c new file mode 100644 index 0000000000..2ecd833dcd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <linux/types.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "X"; + +void BPF_STRUCT_OPS(nogpltcp_init, struct sock *sk) +{ +} + +SEC(".struct_ops") +struct tcp_congestion_ops bpf_nogpltcp = { + .init = (void *)nogpltcp_init, + .name = "bpf_nogpltcp", +}; diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h new file mode 100644 index 0000000000..0b793a1027 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_TRACING_NET_H__ +#define __BPF_TRACING_NET_H__ + +#define AF_INET 2 +#define AF_INET6 10 + +#define SOL_SOCKET 1 +#define SO_REUSEADDR 2 +#define SO_SNDBUF 7 +#define SO_RCVBUF 8 +#define SO_KEEPALIVE 9 +#define SO_PRIORITY 12 +#define SO_REUSEPORT 15 +#define SO_RCVLOWAT 18 +#define SO_BINDTODEVICE 25 +#define SO_MARK 36 +#define SO_MAX_PACING_RATE 47 +#define SO_BINDTOIFINDEX 62 +#define SO_TXREHASH 74 +#define __SO_ACCEPTCON (1 << 16) + +#define IP_TOS 1 + +#define IPV6_TCLASS 67 +#define IPV6_AUTOFLOWLABEL 70 + +#define TC_ACT_UNSPEC (-1) +#define TC_ACT_SHOT 2 + +#define SOL_TCP 6 +#define TCP_NODELAY 1 +#define TCP_MAXSEG 2 +#define TCP_KEEPIDLE 4 +#define TCP_KEEPINTVL 5 +#define TCP_KEEPCNT 6 +#define TCP_SYNCNT 7 +#define TCP_WINDOW_CLAMP 10 +#define TCP_CONGESTION 13 +#define TCP_THIN_LINEAR_TIMEOUTS 16 +#define TCP_USER_TIMEOUT 18 +#define TCP_NOTSENT_LOWAT 25 +#define TCP_SAVE_SYN 27 +#define TCP_SAVED_SYN 28 +#define TCP_CA_NAME_MAX 16 +#define TCP_NAGLE_OFF 1 + +#define ICSK_TIME_RETRANS 1 +#define ICSK_TIME_PROBE0 3 +#define ICSK_TIME_LOSS_PROBE 5 +#define ICSK_TIME_REO_TIMEOUT 6 + +#define ETH_HLEN 14 +#define ETH_P_IPV6 0x86DD + +#define CHECKSUM_NONE 0 +#define CHECKSUM_PARTIAL 3 + +#define IFNAMSIZ 16 + +#define RTF_GATEWAY 0x0002 + +#define TCP_INFINITE_SSTHRESH 0x7fffffff +#define TCP_PINGPONG_THRESH 3 + +#define fib_nh_dev nh_common.nhc_dev +#define fib_nh_gw_family nh_common.nhc_gw_family +#define fib_nh_gw6 nh_common.nhc_gw.ipv6 + +#define inet_daddr sk.__sk_common.skc_daddr +#define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr +#define inet_dport sk.__sk_common.skc_dport + +#define ir_loc_addr req.__req_common.skc_rcv_saddr +#define ir_num req.__req_common.skc_num +#define ir_rmt_addr req.__req_common.skc_daddr +#define ir_rmt_port req.__req_common.skc_dport +#define ir_v6_rmt_addr req.__req_common.skc_v6_daddr +#define ir_v6_loc_addr req.__req_common.skc_v6_rcv_saddr + +#define sk_num __sk_common.skc_num +#define sk_dport __sk_common.skc_dport +#define sk_family __sk_common.skc_family +#define sk_rmem_alloc sk_backlog.rmem_alloc +#define sk_refcnt __sk_common.skc_refcnt +#define sk_state __sk_common.skc_state +#define sk_v6_daddr __sk_common.skc_v6_daddr +#define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr +#define sk_flags __sk_common.skc_flags +#define sk_reuse __sk_common.skc_reuse +#define sk_cookie __sk_common.skc_cookie + +#define s6_addr32 in6_u.u6_addr32 + +#define tw_daddr __tw_common.skc_daddr +#define tw_rcv_saddr __tw_common.skc_rcv_saddr +#define tw_dport __tw_common.skc_dport +#define tw_refcnt __tw_common.skc_refcnt +#define tw_v6_daddr __tw_common.skc_v6_daddr +#define tw_v6_rcv_saddr __tw_common.skc_v6_rcv_saddr + +#endif diff --git a/tools/testing/selftests/bpf/progs/bprm_opts.c b/tools/testing/selftests/bpf/progs/bprm_opts.c new file mode 100644 index 0000000000..418d9c6d49 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bprm_opts.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2020 Google LLC. + */ + +#include <linux/bpf.h> +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} secure_exec_task_map SEC(".maps"); + +SEC("lsm/bprm_creds_for_exec") +int BPF_PROG(secure_exec, struct linux_binprm *bprm) +{ + int *secureexec; + + secureexec = bpf_task_storage_get(&secure_exec_task_map, + bpf_get_current_task_btf(), 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + + if (secureexec && *secureexec) + bpf_bprm_opts_set(bprm, BPF_F_BPRM_SECUREEXEC); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays.c new file mode 100644 index 0000000000..018ed7fbba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_dim.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_dim.c new file mode 100644 index 0000000000..13d662c570 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_dim.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___diff_arr_dim x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_val_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_val_sz.c new file mode 100644 index 0000000000..a351f418c8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_val_sz.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___diff_arr_val_sz x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___equiv_zero_sz_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___equiv_zero_sz_arr.c new file mode 100644 index 0000000000..65eac371b0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___equiv_zero_sz_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___equiv_zero_sz_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_zero_sz_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_zero_sz_arr.c new file mode 100644 index 0000000000..ecda2b545a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_zero_sz_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_bad_zero_sz_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_non_array.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_non_array.c new file mode 100644 index 0000000000..a8735009be --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_non_array.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_non_array x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_shallow.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_shallow.c new file mode 100644 index 0000000000..2a67c28b1e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_shallow.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_too_shallow x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_small.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_small.c new file mode 100644 index 0000000000..1142c08c92 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_small.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_too_small x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type.c new file mode 100644 index 0000000000..f5a7c832d0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_wrong_val_type x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___fixed_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___fixed_arr.c new file mode 100644 index 0000000000..fe1d01232c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___fixed_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___fixed_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields.c new file mode 100644 index 0000000000..cff6f1836c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_bitfields x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___bit_sz_change.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___bit_sz_change.c new file mode 100644 index 0000000000..a1cd157d54 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___bit_sz_change.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_bitfields___bit_sz_change x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___bitfield_vs_int.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___bitfield_vs_int.c new file mode 100644 index 0000000000..3f2c7b07c4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___bitfield_vs_int.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_bitfields___bitfield_vs_int x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___err_too_big_bitfield.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___err_too_big_bitfield.c new file mode 100644 index 0000000000..f9746d6be3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___err_too_big_bitfield.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_bitfields___err_too_big_bitfield x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___just_big_enough.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___just_big_enough.c new file mode 100644 index 0000000000..e7c75a6953 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_bitfields___just_big_enough.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_bitfields___just_big_enough x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val.c new file mode 100644 index 0000000000..888e79db6a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_enum64val x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___diff.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___diff.c new file mode 100644 index 0000000000..194749130d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___diff.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_enum64val___diff x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___err_missing.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___err_missing.c new file mode 100644 index 0000000000..3d732d4193 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___err_missing.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_enum64val___err_missing x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___val3_missing.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___val3_missing.c new file mode 100644 index 0000000000..17cf5d6a84 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___val3_missing.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_enum64val___val3_missing x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval.c new file mode 100644 index 0000000000..48e62f3f07 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_enumval x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___diff.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___diff.c new file mode 100644 index 0000000000..53e5e5a768 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___diff.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_enumval___diff x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___err_missing.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___err_missing.c new file mode 100644 index 0000000000..d024fb2ac0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___err_missing.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_enumval___err_missing x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___val3_missing.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___val3_missing.c new file mode 100644 index 0000000000..9de6595d25 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enumval___val3_missing.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_enumval___val3_missing x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_existence.c new file mode 100644 index 0000000000..0b62315ad4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_existence.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_existence x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___minimal.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___minimal.c new file mode 100644 index 0000000000..aec2dec20e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___minimal.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_existence___minimal x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___wrong_field_defs.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___wrong_field_defs.c new file mode 100644 index 0000000000..d14b496190 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___wrong_field_defs.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_existence___wrong_field_defs x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors.c new file mode 100644 index 0000000000..b74455b912 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_flavors x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors__err_wrong_name.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors__err_wrong_name.c new file mode 100644 index 0000000000..7b6035f86e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors__err_wrong_name.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_flavors__err_wrong_name x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints.c new file mode 100644 index 0000000000..7d0f041042 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___bool.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___bool.c new file mode 100644 index 0000000000..f935945018 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___bool.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___bool x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___reverse_sign.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___reverse_sign.c new file mode 100644 index 0000000000..aafb1c5819 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___reverse_sign.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___reverse_sign x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_misc.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_misc.c new file mode 100644 index 0000000000..ed9ad8b5b4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_misc.c @@ -0,0 +1,5 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_misc___a x) {} +void f2(struct core_reloc_misc___b x) {} +void f3(struct core_reloc_misc_extensible x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_mods.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods.c new file mode 100644 index 0000000000..124197a2e8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_mods x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___mod_swap.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___mod_swap.c new file mode 100644 index 0000000000..f8a6592ca7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___mod_swap.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_mods___mod_swap x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___typedefs.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___typedefs.c new file mode 100644 index 0000000000..5c0d736872 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___typedefs.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_mods___typedefs x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting.c new file mode 100644 index 0000000000..4480fcc0f1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___anon_embed.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___anon_embed.c new file mode 100644 index 0000000000..13e108f76e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___anon_embed.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___anon_embed x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___dup_compat_types.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___dup_compat_types.c new file mode 100644 index 0000000000..76b54fda5f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___dup_compat_types.c @@ -0,0 +1,5 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_nesting___dup_compat_types x) {} +void f2(struct core_reloc_nesting___dup_compat_types__2 x) {} +void f3(struct core_reloc_nesting___dup_compat_types__3 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_container.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_container.c new file mode 100644 index 0000000000..975fb95db8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_container.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_array_container x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_field.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_field.c new file mode 100644 index 0000000000..ad66c67e79 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_field.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_array_field x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_dup_incompat_types.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_dup_incompat_types.c new file mode 100644 index 0000000000..35c5f8da68 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_dup_incompat_types.c @@ -0,0 +1,4 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_nesting___err_dup_incompat_types__1 x) {} +void f2(struct core_reloc_nesting___err_dup_incompat_types__2 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_container.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_container.c new file mode 100644 index 0000000000..142e332041 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_container.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_missing_container x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_field.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_field.c new file mode 100644 index 0000000000..efcae167fa --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_field.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_missing_field x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_nonstruct_container.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_nonstruct_container.c new file mode 100644 index 0000000000..97aaaedd8a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_nonstruct_container.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_nonstruct_container x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_partial_match_dups.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_partial_match_dups.c new file mode 100644 index 0000000000..ffde35086e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_partial_match_dups.c @@ -0,0 +1,4 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_nesting___err_partial_match_dups__a x) {} +void f2(struct core_reloc_nesting___err_partial_match_dups__b x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_too_deep.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_too_deep.c new file mode 100644 index 0000000000..39a2fadd8e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_too_deep.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_too_deep x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___extra_nesting.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___extra_nesting.c new file mode 100644 index 0000000000..a09d9dfb20 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___extra_nesting.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___extra_nesting x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___struct_union_mixup.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___struct_union_mixup.c new file mode 100644 index 0000000000..3d8a1a7401 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___struct_union_mixup.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___struct_union_mixup x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives.c new file mode 100644 index 0000000000..96b90e3924 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_enum_def.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_enum_def.c new file mode 100644 index 0000000000..6e87233a3e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_enum_def.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___diff_enum_def x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_func_proto.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_func_proto.c new file mode 100644 index 0000000000..d9f48e80b9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_func_proto.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___diff_func_proto x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_ptr_type.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_ptr_type.c new file mode 100644 index 0000000000..c718f75f8f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_ptr_type.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___diff_ptr_type x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_enum.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_enum.c new file mode 100644 index 0000000000..b8a1208308 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_enum.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___err_non_enum x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_int.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_int.c new file mode 100644 index 0000000000..ad8b3c9aa7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_int.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___err_non_int x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_ptr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_ptr.c new file mode 100644 index 0000000000..e20bc1d42d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_ptr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___err_non_ptr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr.c new file mode 100644 index 0000000000..8da52432ba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ptr_as_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr___diff_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr___diff_sz.c new file mode 100644 index 0000000000..003acfc9a3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr___diff_sz.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ptr_as_arr___diff_sz x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_size.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_size.c new file mode 100644 index 0000000000..3c80903da5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_size.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_size x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_size___diff_offs.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_size___diff_offs.c new file mode 100644 index 0000000000..3824345d82 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_size___diff_offs.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_size___diff_offs x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_size___diff_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_size___diff_sz.c new file mode 100644 index 0000000000..6dbd14436b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_size___diff_sz.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_size___diff_sz x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_size___err_ambiguous.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_size___err_ambiguous.c new file mode 100644 index 0000000000..f3e9904df9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_size___err_ambiguous.c @@ -0,0 +1,4 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_size___err_ambiguous1 x, + struct core_reloc_size___err_ambiguous2 y) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based.c new file mode 100644 index 0000000000..fc3f69e58c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_type_based x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___all_missing.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___all_missing.c new file mode 100644 index 0000000000..51511648b4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___all_missing.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_type_based___all_missing x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___diff.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___diff.c new file mode 100644 index 0000000000..57ae2c2589 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___diff.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_type_based___diff x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___diff_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___diff_sz.c new file mode 100644 index 0000000000..67db3dceb2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___diff_sz.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_type_based___diff_sz x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___fn_wrong_args.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___fn_wrong_args.c new file mode 100644 index 0000000000..b357fc6543 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___fn_wrong_args.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_type_based___fn_wrong_args x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___incompat.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___incompat.c new file mode 100644 index 0000000000..8ddf20d33d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_based___incompat.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_type_based___incompat x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_type_id.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_id.c new file mode 100644 index 0000000000..abbe5bddce --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_id.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_type_id x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_type_id___missing_targets.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_id___missing_targets.c new file mode 100644 index 0000000000..24e7caf4f0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_type_id___missing_targets.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_type_id___missing_targets x) {} diff --git a/tools/testing/selftests/bpf/progs/btf_data.c b/tools/testing/selftests/bpf/progs/btf_data.c new file mode 100644 index 0000000000..baa525275b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_data.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +struct S { + int a; + int b; + int c; +}; + +union U { + int a; + int b; + int c; +}; + +struct S1 { + int a; + int b; + int c; +}; + +union U1 { + int a; + int b; + int c; +}; + +typedef int T; +typedef int S; +typedef int U; +typedef int T1; +typedef int S1; +typedef int U1; + +struct root_struct { + S m_1; + T m_2; + U m_3; + S1 m_4; + T1 m_5; + U1 m_6; + struct S m_7; + struct S1 m_8; + union U m_9; + union U1 m_10; +}; + +int func(struct root_struct *root) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c new file mode 100644 index 0000000000..e01690618e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C dumper tests for bitfield. + * + * Copyright (c) 2019 Facebook + */ +#include <stdbool.h> + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct bitfields_only_mixed_types { + * int a: 3; + * long b: 2; + * _Bool c: 1; + * enum { + * A = 0, + * B = 1, + * } d: 1; + * short e: 5; + * int: 20; + * unsigned int f: 30; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct bitfields_only_mixed_types { + int a: 3; + long b: 2; + bool c: 1; /* it's really a _Bool type */ + enum { + A, /* A = 0, dumper is very explicit */ + B, /* B = 1, same */ + } d: 1; + short e: 5; + /* 20-bit padding here */ + unsigned f: 30; /* this gets aligned on 4-byte boundary */ +}; + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct bitfield_mixed_with_others { + * char: 4; + * int a: 4; + * short b; + * long c; + * long d: 8; + * int e; + * int f; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ +struct bitfield_mixed_with_others { + char: 4; /* char is enough as a backing field */ + int a: 4; + /* 8-bit implicit padding */ + short b; /* combined with previous bitfield */ + /* 4 more bytes of implicit padding */ + long c; + long d: 8; + /* 24 bits implicit padding */ + int e; /* combined with previous bitfield */ + int f; + /* 4 bytes of padding */ +}; + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct bitfield_flushed { + * int a: 4; + * long: 60; + * long b: 16; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ +struct bitfield_flushed { + int a: 4; + long: 0; /* flush until next natural alignment boundary */ + long b: 16; +}; + +int f(struct { + struct bitfields_only_mixed_types _1; + struct bitfield_mixed_with_others _2; + struct bitfield_flushed _3; +} *_) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c new file mode 100644 index 0000000000..ba97165bdb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C dumper test for multi-dimensional array output. + * + * Copyright (c) 2019 Facebook + */ +/* ----- START-EXPECTED-OUTPUT ----- */ +typedef int arr_t[2]; + +typedef int multiarr_t[3][4][5]; + +typedef int *ptr_arr_t[6]; + +typedef int *ptr_multiarr_t[7][8][9][10]; + +typedef int * (*fn_ptr_arr_t[11])(); + +typedef int * (*fn_ptr_multiarr_t[12][13])(); + +struct root_struct { + arr_t _1; + multiarr_t _2; + ptr_arr_t _3; + ptr_multiarr_t _4; + fn_ptr_arr_t _5; + fn_ptr_multiarr_t _6; +}; + +/* ------ END-EXPECTED-OUTPUT ------ */ + +int f(struct root_struct *s) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_namespacing.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_namespacing.c new file mode 100644 index 0000000000..92a4ad4287 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_namespacing.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C dumper test validating no name versioning happens between + * independent C namespaces (struct/union/enum vs typedef/enum values). + * + * Copyright (c) 2019 Facebook + */ +/* ----- START-EXPECTED-OUTPUT ----- */ +struct S { + int S; + int U; +}; + +typedef struct S S; + +union U { + int S; + int U; +}; + +typedef union U U; + +enum E { + V = 0, +}; + +typedef enum E E; + +struct A {}; + +union B {}; + +enum C { + A = 1, + B = 2, + C = 3, +}; + +struct X {}; + +union Y {}; + +enum Z; + +typedef int X; + +typedef int Y; + +typedef int Z; + +/*------ END-EXPECTED-OUTPUT ------ */ + +int f(struct { + struct S _1; + S _2; + union U _3; + U _4; + enum E _5; + E _6; + struct A a; + union B b; + enum C c; + struct X x; + union Y y; + enum Z *z; + X xx; + Y yy; + Z zz; +} *_) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_ordering.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_ordering.c new file mode 100644 index 0000000000..7c95702ee4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_ordering.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C dumper test for topological sorting of dependent structs. + * + * Copyright (c) 2019 Facebook + */ +/* ----- START-EXPECTED-OUTPUT ----- */ +struct s1 {}; + +struct s3; + +struct s4; + +struct s2 { + struct s2 *s2; + struct s3 *s3; + struct s4 *s4; +}; + +struct s3 { + struct s1 s1; + struct s2 s2; +}; + +struct s4 { + struct s1 s1; + struct s3 s3; +}; + +struct list_head { + struct list_head *next; + struct list_head *prev; +}; + +struct hlist_node { + struct hlist_node *next; + struct hlist_node **pprev; +}; + +struct hlist_head { + struct hlist_node *first; +}; + +struct callback_head { + struct callback_head *next; + void (*func)(struct callback_head *); +}; + +struct root_struct { + struct s4 s4; + struct list_head l; + struct hlist_node n; + struct hlist_head h; + struct callback_head cb; +}; + +/*------ END-EXPECTED-OUTPUT ------ */ + +int f(struct root_struct *root) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c new file mode 100644 index 0000000000..7998f27df7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c @@ -0,0 +1,153 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C dumper tests for struct packing determination. + * + * Copyright (c) 2019 Facebook + */ +/* ----- START-EXPECTED-OUTPUT ----- */ +struct packed_trailing_space { + int a; + short b; +} __attribute__((packed)); + +struct non_packed_trailing_space { + int a; + short b; +}; + +struct packed_fields { + short a; + int b; +} __attribute__((packed)); + +struct non_packed_fields { + short a; + int b; +}; + +struct nested_packed { + char: 4; + int a: 4; + long b; + struct { + char c; + int d; + } __attribute__((packed)) e; +} __attribute__((packed)); + +union union_is_never_packed { + int a: 4; + char b; + char c: 1; +}; + +union union_does_not_need_packing { + struct { + long a; + int b; + } __attribute__((packed)); + int c; +}; + +union jump_code_union { + char code[5]; + struct { + char jump; + int offset; + } __attribute__((packed)); +}; + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct nested_packed_but_aligned_struct { + * int x1; + * int x2; + *}; + * + *struct outer_implicitly_packed_struct { + * char y1; + * struct nested_packed_but_aligned_struct y2; + *} __attribute__((packed)); + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct nested_packed_but_aligned_struct { + int x1; + int x2; +} __attribute__((packed)); + +struct outer_implicitly_packed_struct { + char y1; + struct nested_packed_but_aligned_struct y2; +}; +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct usb_ss_ep_comp_descriptor { + * char: 8; + * char bDescriptorType; + * char bMaxBurst; + * short wBytesPerInterval; + *}; + * + *struct usb_host_endpoint { + * long: 64; + * char: 8; + * struct usb_ss_ep_comp_descriptor ss_ep_comp; + * long: 0; + *} __attribute__((packed)); + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct usb_ss_ep_comp_descriptor { + char: 8; + char bDescriptorType; + char bMaxBurst; + int: 0; + short wBytesPerInterval; +} __attribute__((packed)); + +struct usb_host_endpoint { + long: 64; + char: 8; + struct usb_ss_ep_comp_descriptor ss_ep_comp; + long: 0; +}; + +/* ----- START-EXPECTED-OUTPUT ----- */ +struct nested_packed_struct { + int a; + char b; +} __attribute__((packed)); + +struct outer_nonpacked_struct { + short a; + struct nested_packed_struct b; +}; + +struct outer_packed_struct { + short a; + struct nested_packed_struct b; +} __attribute__((packed)); + +/* ------ END-EXPECTED-OUTPUT ------ */ + +int f(struct { + struct packed_trailing_space _1; + struct non_packed_trailing_space _2; + struct packed_fields _3; + struct non_packed_fields _4; + struct nested_packed _5; + union union_is_never_packed _6; + union union_does_not_need_packing _7; + union jump_code_union _8; + struct outer_implicitly_packed_struct _9; + struct usb_host_endpoint _10; + struct outer_nonpacked_struct _11; + struct outer_packed_struct _12; +} *_) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c new file mode 100644 index 0000000000..79276fbe45 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c @@ -0,0 +1,249 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C dumper tests for implicit and explicit padding between fields and + * at the end of a struct. + * + * Copyright (c) 2019 Facebook + */ +/* ----- START-EXPECTED-OUTPUT ----- */ +struct padded_implicitly { + int a; + long b; + char c; +}; + +/* ------ END-EXPECTED-OUTPUT ------ */ + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct padded_explicitly { + * int a; + * long: 0; + * int b; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct padded_explicitly { + int a; + int: 1; /* algo will emit aligning `long: 0;` here */ + int b; +}; + +/* ----- START-EXPECTED-OUTPUT ----- */ +struct padded_a_lot { + int a; + long: 64; + long: 64; + int b; +}; + +/* ------ END-EXPECTED-OUTPUT ------ */ + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct padded_cache_line { + * int a; + * long: 64; + * long: 64; + * long: 64; + * int b; + * long: 64; + * long: 64; + * long: 64; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct padded_cache_line { + int a; + int b __attribute__((aligned(32))); +}; + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct zone_padding { + * char x[0]; + *}; + * + *struct zone { + * int a; + * short b; + * long: 0; + * struct zone_padding __pad__; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct zone_padding { + char x[0]; +} __attribute__((__aligned__(8))); + +struct zone { + int a; + short b; + struct zone_padding __pad__; +}; + +/* ----- START-EXPECTED-OUTPUT ----- */ +struct padding_wo_named_members { + long: 64; + long: 64; +}; + +struct padding_weird_1 { + int a; + long: 64; + short: 16; + short b; +}; + +/* ------ END-EXPECTED-OUTPUT ------ */ + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct padding_weird_2 { + * long: 56; + * char a; + * long: 56; + * char b; + * char: 8; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ +struct padding_weird_2 { + int: 32; /* these paddings will be collapsed into `long: 56;` */ + short: 16; + char: 8; + char a; + int: 32; /* these paddings will be collapsed into `long: 56;` */ + short: 16; + char: 8; + char b; + char: 8; +}; + +/* ----- START-EXPECTED-OUTPUT ----- */ +struct exact_1byte { + char x; +}; + +struct padded_1byte { + char: 8; +}; + +struct exact_2bytes { + short x; +}; + +struct padded_2bytes { + short: 16; +}; + +struct exact_4bytes { + int x; +}; + +struct padded_4bytes { + int: 32; +}; + +struct exact_8bytes { + long x; +}; + +struct padded_8bytes { + long: 64; +}; + +struct ff_periodic_effect { + int: 32; + short magnitude; + long: 0; + short phase; + long: 0; + int: 32; + int custom_len; + short *custom_data; +}; + +struct ib_wc { + long: 64; + long: 64; + int: 32; + int byte_len; + void *qp; + union {} ex; + long: 64; + int slid; + int wc_flags; + long: 64; + char smac[6]; + long: 0; + char network_hdr_type; +}; + +struct acpi_object_method { + long: 64; + char: 8; + char type; + short reference_count; + char flags; + short: 0; + char: 8; + char sync_level; + long: 64; + void *node; + void *aml_start; + union {} dispatch; + long: 64; + int aml_length; +}; + +struct nested_unpacked { + int x; +}; + +struct nested_packed { + struct nested_unpacked a; + char c; +} __attribute__((packed)); + +struct outer_mixed_but_unpacked { + struct nested_packed b1; + short a1; + struct nested_packed b2; +}; + +/* ------ END-EXPECTED-OUTPUT ------ */ + +int f(struct { + struct padded_implicitly _1; + struct padded_explicitly _2; + struct padded_a_lot _3; + struct padded_cache_line _4; + struct zone _5; + struct padding_wo_named_members _6; + struct padding_weird_1 _7; + struct padding_weird_2 _8; + struct exact_1byte _100; + struct padded_1byte _101; + struct exact_2bytes _102; + struct padded_2bytes _103; + struct exact_4bytes _104; + struct padded_4bytes _105; + struct exact_8bytes _106; + struct padded_8bytes _107; + struct ff_periodic_effect _200; + struct ib_wc _201; + struct acpi_object_method _202; + struct outer_mixed_but_unpacked _203; +} *_) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c new file mode 100644 index 0000000000..ad21ee8c7e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c @@ -0,0 +1,280 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C dumper test for majority of C syntax quirks. + * + * Copyright (c) 2019 Facebook + */ +/* ----- START-EXPECTED-OUTPUT ----- */ +enum e1 { + A = 0, + B = 1, +}; + +enum e2 { + C = 100, + D = 4294967295, + E = 0, +}; + +typedef enum e2 e2_t; + +typedef enum { + F = 0, + G = 1, + H = 2, +} e3_t; + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *enum e_byte { + * EBYTE_1 = 0, + * EBYTE_2 = 1, + *} __attribute__((mode(byte))); + * + */ +/* ----- END-EXPECTED-OUTPUT ----- */ +enum e_byte { + EBYTE_1, + EBYTE_2, +} __attribute__((mode(byte))); + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *enum e_word { + * EWORD_1 = 0LL, + * EWORD_2 = 1LL, + *} __attribute__((mode(word))); + * + */ +/* ----- END-EXPECTED-OUTPUT ----- */ +enum e_word { + EWORD_1, + EWORD_2, +} __attribute__((mode(word))); /* force to use 8-byte backing for this enum */ + +/* ----- START-EXPECTED-OUTPUT ----- */ +enum e_big { + EBIG_1 = 1000000000000ULL, +}; + +typedef int int_t; + +typedef volatile const int * volatile const crazy_ptr_t; + +typedef int *****we_need_to_go_deeper_ptr_t; + +typedef volatile const we_need_to_go_deeper_ptr_t * restrict * volatile * const * restrict volatile * restrict const * volatile const * restrict volatile const how_about_this_ptr_t; + +typedef int *ptr_arr_t[10]; + +typedef void (*fn_ptr1_t)(int); + +typedef void (*printf_fn_t)(const char *, ...); + +/* ------ END-EXPECTED-OUTPUT ------ */ +/* + * While previous function pointers are pretty trivial (C-syntax-level + * trivial), the following are deciphered here for future generations: + * + * - `fn_ptr2_t`: function, taking anonymous struct as a first arg and pointer + * to a function, that takes int and returns int, as a second arg; returning + * a pointer to a const pointer to a char. Equivalent to: + * typedef struct { int a; } s_t; + * typedef int (*fn_t)(int); + * typedef char * const * (*fn_ptr2_t)(s_t, fn_t); + * + * - `fn_complex_t`: pointer to a function returning struct and accepting + * union and struct. All structs and enum are anonymous and defined inline. + * + * - `signal_t: pointer to a function accepting a pointer to a function as an + * argument and returning pointer to a function as a result. Sane equivalent: + * typedef void (*signal_handler_t)(int); + * typedef signal_handler_t (*signal_ptr_t)(int, signal_handler_t); + * + * - fn_ptr_arr1_t: array of pointers to a function accepting pointer to + * a pointer to an int and returning pointer to a char. Easy. + * + * - fn_ptr_arr2_t: array of const pointers to a function taking no arguments + * and returning a const pointer to a function, that takes pointer to a + * `int -> char *` function and returns pointer to a char. Equivalent: + * typedef char * (*fn_input_t)(int); + * typedef char * (*fn_output_outer_t)(fn_input_t); + * typedef const fn_output_outer_t (* fn_output_inner_t)(); + * typedef const fn_output_inner_t fn_ptr_arr2_t[5]; + */ +/* ----- START-EXPECTED-OUTPUT ----- */ +typedef char * const * (*fn_ptr2_t)(struct { + int a; +}, int (*)(int)); + +typedef struct { + int a; + void (*b)(int, struct { + int c; + }, union { + char d; + int e[5]; + }); +} (*fn_complex_t)(union { + void *f; + char g[16]; +}, struct { + int h; +}); + +typedef void (* (*signal_t)(int, void (*)(int)))(int); + +typedef char * (*fn_ptr_arr1_t[10])(int **); + +typedef char * (* (* const fn_ptr_arr2_t[5])())(char * (*)(int)); + +struct struct_w_typedefs { + int_t a; + crazy_ptr_t b; + we_need_to_go_deeper_ptr_t c; + how_about_this_ptr_t d; + ptr_arr_t e; + fn_ptr1_t f; + printf_fn_t g; + fn_ptr2_t h; + fn_complex_t i; + signal_t j; + fn_ptr_arr1_t k; + fn_ptr_arr2_t l; +}; + +typedef struct { + int x; + int y; + int z; +} anon_struct_t; + +struct struct_fwd; + +typedef struct struct_fwd struct_fwd_t; + +typedef struct struct_fwd *struct_fwd_ptr_t; + +union union_fwd; + +typedef union union_fwd union_fwd_t; + +typedef union union_fwd *union_fwd_ptr_t; + +struct struct_empty {}; + +struct struct_simple { + int a; + char b; + const int_t *p; + struct struct_empty s; + enum e2 e; + enum { + ANON_VAL1 = 1, + ANON_VAL2 = 2, + } f; + int arr1[13]; + enum e2 arr2[5]; +}; + +union union_empty {}; + +union union_simple { + void *ptr; + int num; + int_t num2; + union union_empty u; +}; + +struct struct_in_struct { + struct struct_simple simple; + union union_simple also_simple; + struct { + int a; + } not_so_hard_as_well; + union { + int b; + int c; + } anon_union_is_good; + struct { + int d; + int e; + }; + union { + int f; + int g; + }; +}; + +struct struct_in_array {}; + +struct struct_in_array_typed {}; + +typedef struct struct_in_array_typed struct_in_array_t[2]; + +struct struct_with_embedded_stuff { + int a; + struct { + int b; + struct { + struct struct_with_embedded_stuff *c; + const char *d; + } e; + union { + volatile long f; + void * restrict g; + }; + }; + union { + const int_t *h; + void (*i)(char, int, void *); + } j; + enum { + K = 100, + L = 200, + } m; + char n[16]; + struct { + char o; + int p; + void (*q)(int); + } r[5]; + struct struct_in_struct s[10]; + int t[11]; + struct struct_in_array (*u)[2]; + struct_in_array_t *v; +}; + +struct float_struct { + float f; + const double *d; + volatile long double *ld; +}; + +struct root_struct { + enum e1 _1; + enum e2 _2; + e2_t _2_1; + e3_t _2_2; + enum e_byte _100; + enum e_word _101; + enum e_big _102; + struct struct_w_typedefs _3; + anon_struct_t _7; + struct struct_fwd *_8; + struct_fwd_t *_9; + struct_fwd_ptr_t _10; + union union_fwd *_11; + union_fwd_t *_12; + union_fwd_ptr_t _13; + struct struct_with_embedded_stuff _14; + struct float_struct _15; +}; + +/* ------ END-EXPECTED-OUTPUT ------ */ + +int f(struct root_struct *s) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_ptr.h b/tools/testing/selftests/bpf/progs/btf_ptr.h new file mode 100644 index 0000000000..c3c9797c67 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_ptr.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2020, Oracle and/or its affiliates. */ +/* "undefine" structs in vmlinux.h, because we "override" them below */ +#define btf_ptr btf_ptr___not_used +#define BTF_F_COMPACT BTF_F_COMPACT___not_used +#define BTF_F_NONAME BTF_F_NONAME___not_used +#define BTF_F_PTR_RAW BTF_F_PTR_RAW___not_used +#define BTF_F_ZERO BTF_F_ZERO___not_used +#include "vmlinux.h" +#undef btf_ptr +#undef BTF_F_COMPACT +#undef BTF_F_NONAME +#undef BTF_F_PTR_RAW +#undef BTF_F_ZERO + +struct btf_ptr { + void *ptr; + __u32 type_id; + __u32 flags; +}; + +enum { + BTF_F_COMPACT = (1ULL << 0), + BTF_F_NONAME = (1ULL << 1), + BTF_F_PTR_RAW = (1ULL << 2), + BTF_F_ZERO = (1ULL << 3), +}; diff --git a/tools/testing/selftests/bpf/progs/btf_type_tag.c b/tools/testing/selftests/bpf/progs/btf_type_tag.c new file mode 100644 index 0000000000..1d488da7e9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_type_tag.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#if __has_attribute(btf_type_tag) +#define __tag1 __attribute__((btf_type_tag("tag1"))) +#define __tag2 __attribute__((btf_type_tag("tag2"))) +volatile const bool skip_tests = false; +#else +#define __tag1 +#define __tag2 +volatile const bool skip_tests = true; +#endif + +struct btf_type_tag_test { + int __tag1 * __tag1 __tag2 *p; +} g; + +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(sub, int x) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c new file mode 100644 index 0000000000..38f78d9345 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Google */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct bpf_testmod_btf_type_tag_1 { + int a; +}; + +struct bpf_testmod_btf_type_tag_2 { + struct bpf_testmod_btf_type_tag_1 *p; +}; + +__u64 g; + +SEC("fentry/bpf_testmod_test_btf_type_tag_percpu_1") +int BPF_PROG(test_percpu1, struct bpf_testmod_btf_type_tag_1 *arg) +{ + g = arg->a; + return 0; +} + +SEC("fentry/bpf_testmod_test_btf_type_tag_percpu_2") +int BPF_PROG(test_percpu2, struct bpf_testmod_btf_type_tag_2 *arg) +{ + g = arg->p->a; + return 0; +} + +/* trace_cgroup_mkdir(struct cgroup *cgrp, const char *path) + * + * struct cgroup_rstat_cpu { + * ... + * struct cgroup *updated_children; + * ... + * }; + * + * struct cgroup { + * ... + * struct cgroup_rstat_cpu __percpu *rstat_cpu; + * ... + * }; + */ +SEC("tp_btf/cgroup_mkdir") +int BPF_PROG(test_percpu_load, struct cgroup *cgrp, const char *path) +{ + g = (__u64)cgrp->rstat_cpu->updated_children; + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +int BPF_PROG(test_percpu_helper, struct cgroup *cgrp, const char *path) +{ + struct cgroup_rstat_cpu *rstat; + __u32 cpu; + + cpu = bpf_get_smp_processor_id(); + rstat = (struct cgroup_rstat_cpu *)bpf_per_cpu_ptr(cgrp->rstat_cpu, cpu); + if (rstat) { + /* READ_ONCE */ + *(volatile int *)rstat; + } + + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/btf_type_tag_user.c b/tools/testing/selftests/bpf/progs/btf_type_tag_user.c new file mode 100644 index 0000000000..5523f77c5a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_type_tag_user.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct bpf_testmod_btf_type_tag_1 { + int a; +}; + +struct bpf_testmod_btf_type_tag_2 { + struct bpf_testmod_btf_type_tag_1 *p; +}; + +int g; + +SEC("fentry/bpf_testmod_test_btf_type_tag_user_1") +int BPF_PROG(test_user1, struct bpf_testmod_btf_type_tag_1 *arg) +{ + g = arg->a; + return 0; +} + +SEC("fentry/bpf_testmod_test_btf_type_tag_user_2") +int BPF_PROG(test_user2, struct bpf_testmod_btf_type_tag_2 *arg) +{ + g = arg->p->a; + return 0; +} + +/* int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, + * int __user *usockaddr_len); + */ +SEC("fentry/__sys_getsockname") +int BPF_PROG(test_sys_getsockname, int fd, struct sockaddr *usockaddr, + int *usockaddr_len) +{ + g = usockaddr->sa_family; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cb_refs.c b/tools/testing/selftests/bpf/progs/cb_refs.c new file mode 100644 index 0000000000..56c764df81 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cb_refs.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" + +struct map_value { + struct prog_test_ref_kfunc __kptr *ptr; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 16); +} array_map SEC(".maps"); + +static __noinline int cb1(void *map, void *key, void *value, void *ctx) +{ + void *p = *(void **)ctx; + bpf_kfunc_call_test_release(p); + /* Without the fix this would cause underflow */ + return 0; +} + +SEC("?tc") +int underflow_prog(void *ctx) +{ + struct prog_test_ref_kfunc *p; + unsigned long sl = 0; + + p = bpf_kfunc_call_test_acquire(&sl); + if (!p) + return 0; + bpf_for_each_map_elem(&array_map, cb1, &p, 0); + bpf_kfunc_call_test_release(p); + return 0; +} + +static __always_inline int cb2(void *map, void *key, void *value, void *ctx) +{ + unsigned long sl = 0; + + *(void **)ctx = bpf_kfunc_call_test_acquire(&sl); + /* Without the fix this would leak memory */ + return 0; +} + +SEC("?tc") +int leak_prog(void *ctx) +{ + struct prog_test_ref_kfunc *p; + struct map_value *v; + + v = bpf_map_lookup_elem(&array_map, &(int){0}); + if (!v) + return 0; + + p = NULL; + bpf_for_each_map_elem(&array_map, cb2, &p, 0); + p = bpf_kptr_xchg(&v->ptr, p); + if (p) + bpf_kfunc_call_test_release(p); + return 0; +} + +static __always_inline int cb(void *map, void *key, void *value, void *ctx) +{ + return 0; +} + +static __always_inline int cb3(void *map, void *key, void *value, void *ctx) +{ + unsigned long sl = 0; + void *p; + + bpf_kfunc_call_test_acquire(&sl); + bpf_for_each_map_elem(&array_map, cb, &p, 0); + /* It should only complain here, not in cb. This is why we need + * callback_ref to be set to frameno. + */ + return 0; +} + +SEC("?tc") +int nested_cb(void *ctx) +{ + struct prog_test_ref_kfunc *p; + unsigned long sl = 0; + int sp = 0; + + p = bpf_kfunc_call_test_acquire(&sl); + if (!p) + return 0; + bpf_for_each_map_elem(&array_map, cb3, &sp, 0); + bpf_kfunc_call_test_release(p); + return 0; +} + +SEC("?tc") +int non_cb_transfer_ref(void *ctx) +{ + struct prog_test_ref_kfunc *p; + unsigned long sl = 0; + + p = bpf_kfunc_call_test_acquire(&sl); + if (!p) + return 0; + cb1(NULL, NULL, NULL, &p); + bpf_kfunc_call_test_acquire(&sl); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi.h b/tools/testing/selftests/bpf/progs/cg_storage_multi.h new file mode 100644 index 0000000000..a0778fe785 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __PROGS_CG_STORAGE_MULTI_H +#define __PROGS_CG_STORAGE_MULTI_H + +#include <asm/types.h> + +struct cgroup_value { + __u32 egress_pkts; + __u32 ingress_pkts; +}; + +#endif diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c new file mode 100644 index 0000000000..44ad46b335 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2020 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <linux/ip.h> +#include <linux/udp.h> +#include <bpf/bpf_helpers.h> + +#include "progs/cg_storage_multi.h" + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, struct cgroup_value); +} cgroup_storage SEC(".maps"); + +__u32 invocations = 0; + +SEC("cgroup_skb/egress") +int egress(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c new file mode 100644 index 0000000000..3f81ff9218 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2020 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <linux/ip.h> +#include <linux/udp.h> +#include <bpf/bpf_helpers.h> + +#include "progs/cg_storage_multi.h" + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, struct cgroup_value); +} cgroup_storage SEC(".maps"); + +__u32 invocations = 0; + +SEC("cgroup_skb/egress") +int egress1(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup_skb/egress") +int egress2(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup_skb/ingress") +int ingress(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->ingress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c new file mode 100644 index 0000000000..d662db27fe --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2020 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <linux/ip.h> +#include <linux/udp.h> +#include <bpf/bpf_helpers.h> + +#include "progs/cg_storage_multi.h" + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, __u64); + __type(value, struct cgroup_value); +} cgroup_storage SEC(".maps"); + +__u32 invocations = 0; + +SEC("cgroup_skb/egress") +int egress1(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup_skb/egress") +int egress2(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup_skb/ingress") +int ingress(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->ingress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c new file mode 100644 index 0000000000..932b8ecd4a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2021 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__u32 invocations = 0; +__u32 assertion_error = 0; +__u32 retval_value = 0; +__u32 ctx_retval_value = 0; +__u32 page_size = 0; + +SEC("cgroup/getsockopt") +int get_retval(struct bpf_sockopt *ctx) +{ + retval_value = bpf_get_retval(); + ctx_retval_value = ctx->retval; + __sync_fetch_and_add(&invocations, 1); + + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + + return 1; +} + +SEC("cgroup/getsockopt") +int set_eisconn(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + if (bpf_set_retval(-EISCONN)) + assertion_error = 1; + + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + + return 1; +} + +SEC("cgroup/getsockopt") +int clear_retval(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + ctx->retval = 0; + + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_hooks.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_hooks.c new file mode 100644 index 0000000000..13dfb4bbfd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_hooks.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define BPF_RETVAL_HOOK(name, section, ctx, expected_err) \ + __attribute__((__section__("?" section))) \ + int name(struct ctx *_ctx) \ + { \ + bpf_set_retval(bpf_get_retval()); \ + return 1; \ + } + +#include "cgroup_getset_retval_hooks.h" + +#undef BPF_RETVAL_HOOK diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c new file mode 100644 index 0000000000..b7fa8804e1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2021 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__u32 invocations = 0; +__u32 assertion_error = 0; +__u32 retval_value = 0; +__u32 page_size = 0; + +SEC("cgroup/setsockopt") +int get_retval(struct bpf_sockopt *ctx) +{ + retval_value = bpf_get_retval(); + __sync_fetch_and_add(&invocations, 1); + + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + + return 1; +} + +SEC("cgroup/setsockopt") +int set_eunatch(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + if (bpf_set_retval(-EUNATCH)) + assertion_error = 1; + + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + + return 0; +} + +SEC("cgroup/setsockopt") +int set_eisconn(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + if (bpf_set_retval(-EISCONN)) + assertion_error = 1; + + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + + return 0; +} + +SEC("cgroup/setsockopt") +int legacy_eperm(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c b/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c new file mode 100644 index 0000000000..c743628549 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c @@ -0,0 +1,155 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022 Google LLC. + */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct percpu_attach_counter { + /* Previous percpu state, to figure out if we have new updates */ + __u64 prev; + /* Current percpu state */ + __u64 state; +}; + +struct attach_counter { + /* State propagated through children, pending aggregation */ + __u64 pending; + /* Total state, including all cpus and all children */ + __u64 state; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 1024); + __type(key, __u64); + __type(value, struct percpu_attach_counter); +} percpu_attach_counters SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1024); + __type(key, __u64); + __type(value, struct attach_counter); +} attach_counters SEC(".maps"); + +extern void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) __ksym; +extern void cgroup_rstat_flush(struct cgroup *cgrp) __ksym; + +static uint64_t cgroup_id(struct cgroup *cgrp) +{ + return cgrp->kn->id; +} + +static int create_percpu_attach_counter(__u64 cg_id, __u64 state) +{ + struct percpu_attach_counter pcpu_init = {.state = state, .prev = 0}; + + return bpf_map_update_elem(&percpu_attach_counters, &cg_id, + &pcpu_init, BPF_NOEXIST); +} + +static int create_attach_counter(__u64 cg_id, __u64 state, __u64 pending) +{ + struct attach_counter init = {.state = state, .pending = pending}; + + return bpf_map_update_elem(&attach_counters, &cg_id, + &init, BPF_NOEXIST); +} + +SEC("fentry/cgroup_attach_task") +int BPF_PROG(counter, struct cgroup *dst_cgrp, struct task_struct *leader, + bool threadgroup) +{ + __u64 cg_id = cgroup_id(dst_cgrp); + struct percpu_attach_counter *pcpu_counter = bpf_map_lookup_elem( + &percpu_attach_counters, + &cg_id); + + if (pcpu_counter) + pcpu_counter->state += 1; + else if (create_percpu_attach_counter(cg_id, 1)) + return 0; + + cgroup_rstat_updated(dst_cgrp, bpf_get_smp_processor_id()); + return 0; +} + +SEC("fentry/bpf_rstat_flush") +int BPF_PROG(flusher, struct cgroup *cgrp, struct cgroup *parent, int cpu) +{ + struct percpu_attach_counter *pcpu_counter; + struct attach_counter *total_counter, *parent_counter; + __u64 cg_id = cgroup_id(cgrp); + __u64 parent_cg_id = parent ? cgroup_id(parent) : 0; + __u64 state; + __u64 delta = 0; + + /* Add CPU changes on this level since the last flush */ + pcpu_counter = bpf_map_lookup_percpu_elem(&percpu_attach_counters, + &cg_id, cpu); + if (pcpu_counter) { + state = pcpu_counter->state; + delta += state - pcpu_counter->prev; + pcpu_counter->prev = state; + } + + total_counter = bpf_map_lookup_elem(&attach_counters, &cg_id); + if (!total_counter) { + if (create_attach_counter(cg_id, delta, 0)) + return 0; + goto update_parent; + } + + /* Collect pending stats from subtree */ + if (total_counter->pending) { + delta += total_counter->pending; + total_counter->pending = 0; + } + + /* Propagate changes to this cgroup's total */ + total_counter->state += delta; + +update_parent: + /* Skip if there are no changes to propagate, or no parent */ + if (!delta || !parent_cg_id) + return 0; + + /* Propagate changes to cgroup's parent */ + parent_counter = bpf_map_lookup_elem(&attach_counters, + &parent_cg_id); + if (parent_counter) + parent_counter->pending += delta; + else + create_attach_counter(parent_cg_id, 0, delta); + return 0; +} + +SEC("iter.s/cgroup") +int BPF_PROG(dumper, struct bpf_iter_meta *meta, struct cgroup *cgrp) +{ + struct seq_file *seq = meta->seq; + struct attach_counter *total_counter; + __u64 cg_id = cgrp ? cgroup_id(cgrp) : 0; + + /* Do nothing for the terminal call */ + if (!cg_id) + return 1; + + /* Flush the stats to make sure we get the most updated numbers */ + cgroup_rstat_flush(cgrp); + + total_counter = bpf_map_lookup_elem(&attach_counters, &cg_id); + if (!total_counter) { + BPF_SEQ_PRINTF(seq, "cg_id: %llu, attach_counter: 0\n", + cg_id); + } else { + BPF_SEQ_PRINTF(seq, "cg_id: %llu, attach_counter: %llu\n", + cg_id, total_counter->state); + } + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_iter.c b/tools/testing/selftests/bpf/progs/cgroup_iter.c new file mode 100644 index 0000000000..de03997322 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_iter.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Google */ + +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; +int terminate_early = 0; +u64 terminal_cgroup = 0; + +static inline u64 cgroup_id(struct cgroup *cgrp) +{ + return cgrp->kn->id; +} + +SEC("iter/cgroup") +int cgroup_id_printer(struct bpf_iter__cgroup *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct cgroup *cgrp = ctx->cgroup; + + /* epilogue */ + if (cgrp == NULL) { + BPF_SEQ_PRINTF(seq, "epilogue\n"); + return 0; + } + + /* prologue */ + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(seq, "prologue\n"); + + BPF_SEQ_PRINTF(seq, "%8llu\n", cgroup_id(cgrp)); + + if (terminal_cgroup == cgroup_id(cgrp)) + return 1; + + return terminate_early ? 1 : 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c new file mode 100644 index 0000000000..ac86a8a616 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> + +#include <sys/types.h> +#include <sys/socket.h> + +char _license[] SEC("license") = "GPL"; + +__u16 g_serv_port = 0; + +static inline void set_ip(__u32 *dst, const struct in6_addr *src) +{ + dst[0] = src->in6_u.u6_addr32[0]; + dst[1] = src->in6_u.u6_addr32[1]; + dst[2] = src->in6_u.u6_addr32[2]; + dst[3] = src->in6_u.u6_addr32[3]; +} + +static inline void set_tuple(struct bpf_sock_tuple *tuple, + const struct ipv6hdr *ip6h, + const struct tcphdr *tcph) +{ + set_ip(tuple->ipv6.saddr, &ip6h->daddr); + set_ip(tuple->ipv6.daddr, &ip6h->saddr); + tuple->ipv6.sport = tcph->dest; + tuple->ipv6.dport = tcph->source; +} + +static inline int is_allowed_peer_cg(struct __sk_buff *skb, + const struct ipv6hdr *ip6h, + const struct tcphdr *tcph) +{ + __u64 cgid, acgid, peer_cgid, peer_acgid; + struct bpf_sock_tuple tuple; + size_t tuple_len = sizeof(tuple.ipv6); + struct bpf_sock *peer_sk; + + set_tuple(&tuple, ip6h, tcph); + + peer_sk = bpf_sk_lookup_tcp(skb, &tuple, tuple_len, + BPF_F_CURRENT_NETNS, 0); + if (!peer_sk) + return 0; + + cgid = bpf_skb_cgroup_id(skb); + peer_cgid = bpf_sk_cgroup_id(peer_sk); + + acgid = bpf_skb_ancestor_cgroup_id(skb, 2); + peer_acgid = bpf_sk_ancestor_cgroup_id(peer_sk, 2); + + bpf_sk_release(peer_sk); + + return cgid && cgid == peer_cgid && acgid && acgid == peer_acgid; +} + +SEC("cgroup_skb/ingress") +int ingress_lookup(struct __sk_buff *skb) +{ + struct ipv6hdr ip6h; + struct tcphdr tcph; + + if (skb->protocol != bpf_htons(ETH_P_IPV6)) + return 1; + + /* For SYN packets coming to listening socket skb->remote_port will be + * zero, so IPv6/TCP headers are loaded to identify remote peer + * instead. + */ + if (bpf_skb_load_bytes(skb, 0, &ip6h, sizeof(ip6h))) + return 1; + + if (ip6h.nexthdr != IPPROTO_TCP) + return 1; + + if (bpf_skb_load_bytes(skb, sizeof(ip6h), &tcph, sizeof(tcph))) + return 1; + + if (!g_serv_port) + return 0; + + if (tcph.dest != g_serv_port) + return 1; + + return is_allowed_peer_cg(skb, &ip6h, &tcph); +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c b/tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c new file mode 100644 index 0000000000..1e2e73f3b7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c @@ -0,0 +1,382 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include <linux/bpf.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> + +#include <sys/types.h> +#include <sys/socket.h> + +#include "cgroup_tcp_skb.h" + +char _license[] SEC("license") = "GPL"; + +__u16 g_sock_port = 0; +__u32 g_sock_state = 0; +int g_unexpected = 0; +__u32 g_packet_count = 0; + +int needed_tcp_pkt(struct __sk_buff *skb, struct tcphdr *tcph) +{ + struct ipv6hdr ip6h; + + if (skb->protocol != bpf_htons(ETH_P_IPV6)) + return 0; + if (bpf_skb_load_bytes(skb, 0, &ip6h, sizeof(ip6h))) + return 0; + + if (ip6h.nexthdr != IPPROTO_TCP) + return 0; + + if (bpf_skb_load_bytes(skb, sizeof(ip6h), tcph, sizeof(*tcph))) + return 0; + + if (tcph->source != bpf_htons(g_sock_port) && + tcph->dest != bpf_htons(g_sock_port)) + return 0; + + return 1; +} + +/* Run accept() on a socket in the cgroup to receive a new connection. */ +static int egress_accept(struct tcphdr *tcph) +{ + if (g_sock_state == SYN_RECV_SENDING_SYN_ACK) { + if (tcph->fin || !tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = SYN_RECV; + return 1; + } + + return 0; +} + +static int ingress_accept(struct tcphdr *tcph) +{ + switch (g_sock_state) { + case INIT: + if (!tcph->syn || tcph->fin || tcph->ack) + g_unexpected++; + else + g_sock_state = SYN_RECV_SENDING_SYN_ACK; + break; + case SYN_RECV: + if (tcph->fin || tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = ESTABLISHED; + break; + default: + return 0; + } + + return 1; +} + +/* Run connect() on a socket in the cgroup to start a new connection. */ +static int egress_connect(struct tcphdr *tcph) +{ + if (g_sock_state == INIT) { + if (!tcph->syn || tcph->fin || tcph->ack) + g_unexpected++; + else + g_sock_state = SYN_SENT; + return 1; + } + + return 0; +} + +static int ingress_connect(struct tcphdr *tcph) +{ + if (g_sock_state == SYN_SENT) { + if (tcph->fin || !tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = ESTABLISHED; + return 1; + } + + return 0; +} + +/* The connection is closed by the peer outside the cgroup. */ +static int egress_close_remote(struct tcphdr *tcph) +{ + switch (g_sock_state) { + case ESTABLISHED: + break; + case CLOSE_WAIT_SENDING_ACK: + if (tcph->fin || tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = CLOSE_WAIT; + break; + case CLOSE_WAIT: + if (!tcph->fin) + g_unexpected++; + else + g_sock_state = LAST_ACK; + break; + default: + return 0; + } + + return 1; +} + +static int ingress_close_remote(struct tcphdr *tcph) +{ + switch (g_sock_state) { + case ESTABLISHED: + if (tcph->fin) + g_sock_state = CLOSE_WAIT_SENDING_ACK; + break; + case LAST_ACK: + if (tcph->fin || tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = CLOSED; + break; + default: + return 0; + } + + return 1; +} + +/* The connection is closed by the endpoint inside the cgroup. */ +static int egress_close_local(struct tcphdr *tcph) +{ + switch (g_sock_state) { + case ESTABLISHED: + if (tcph->fin) + g_sock_state = FIN_WAIT1; + break; + case TIME_WAIT_SENDING_ACK: + if (tcph->fin || tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = TIME_WAIT; + break; + default: + return 0; + } + + return 1; +} + +static int ingress_close_local(struct tcphdr *tcph) +{ + switch (g_sock_state) { + case ESTABLISHED: + break; + case FIN_WAIT1: + if (tcph->fin || tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = FIN_WAIT2; + break; + case FIN_WAIT2: + if (!tcph->fin || tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = TIME_WAIT_SENDING_ACK; + break; + default: + return 0; + } + + return 1; +} + +/* Check the types of outgoing packets of a server socket to make sure they + * are consistent with the state of the server socket. + * + * The connection is closed by the client side. + */ +SEC("cgroup_skb/egress") +int server_egress(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Egress of the server socket. */ + if (egress_accept(&tcph) || egress_close_remote(&tcph)) + return 1; + + g_unexpected++; + return 1; +} + +/* Check the types of incoming packets of a server socket to make sure they + * are consistent with the state of the server socket. + * + * The connection is closed by the client side. + */ +SEC("cgroup_skb/ingress") +int server_ingress(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Ingress of the server socket. */ + if (ingress_accept(&tcph) || ingress_close_remote(&tcph)) + return 1; + + g_unexpected++; + return 1; +} + +/* Check the types of outgoing packets of a server socket to make sure they + * are consistent with the state of the server socket. + * + * The connection is closed by the server side. + */ +SEC("cgroup_skb/egress") +int server_egress_srv(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Egress of the server socket. */ + if (egress_accept(&tcph) || egress_close_local(&tcph)) + return 1; + + g_unexpected++; + return 1; +} + +/* Check the types of incoming packets of a server socket to make sure they + * are consistent with the state of the server socket. + * + * The connection is closed by the server side. + */ +SEC("cgroup_skb/ingress") +int server_ingress_srv(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Ingress of the server socket. */ + if (ingress_accept(&tcph) || ingress_close_local(&tcph)) + return 1; + + g_unexpected++; + return 1; +} + +/* Check the types of outgoing packets of a client socket to make sure they + * are consistent with the state of the client socket. + * + * The connection is closed by the server side. + */ +SEC("cgroup_skb/egress") +int client_egress_srv(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Egress of the server socket. */ + if (egress_connect(&tcph) || egress_close_remote(&tcph)) + return 1; + + g_unexpected++; + return 1; +} + +/* Check the types of incoming packets of a client socket to make sure they + * are consistent with the state of the client socket. + * + * The connection is closed by the server side. + */ +SEC("cgroup_skb/ingress") +int client_ingress_srv(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Ingress of the server socket. */ + if (ingress_connect(&tcph) || ingress_close_remote(&tcph)) + return 1; + + g_unexpected++; + return 1; +} + +/* Check the types of outgoing packets of a client socket to make sure they + * are consistent with the state of the client socket. + * + * The connection is closed by the client side. + */ +SEC("cgroup_skb/egress") +int client_egress(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Egress of the server socket. */ + if (egress_connect(&tcph) || egress_close_local(&tcph)) + return 1; + + g_unexpected++; + return 1; +} + +/* Check the types of incoming packets of a client socket to make sure they + * are consistent with the state of the client socket. + * + * The connection is closed by the client side. + */ +SEC("cgroup_skb/ingress") +int client_ingress(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Ingress of the server socket. */ + if (ingress_connect(&tcph) || ingress_close_local(&tcph)) + return 1; + + g_unexpected++; + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/cgrp_kfunc_common.h b/tools/testing/selftests/bpf/progs/cgrp_kfunc_common.h new file mode 100644 index 0000000000..22914a70db --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgrp_kfunc_common.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#ifndef _CGRP_KFUNC_COMMON_H +#define _CGRP_KFUNC_COMMON_H + +#include <errno.h> +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct __cgrps_kfunc_map_value { + struct cgroup __kptr * cgrp; +}; + +struct hash_map { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, int); + __type(value, struct __cgrps_kfunc_map_value); + __uint(max_entries, 1); +} __cgrps_kfunc_map SEC(".maps"); + +struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; +struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) __ksym; +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +static inline struct __cgrps_kfunc_map_value *cgrps_kfunc_map_value_lookup(struct cgroup *cgrp) +{ + s32 id; + long status; + + status = bpf_probe_read_kernel(&id, sizeof(id), &cgrp->self.id); + if (status) + return NULL; + + return bpf_map_lookup_elem(&__cgrps_kfunc_map, &id); +} + +static inline int cgrps_kfunc_map_insert(struct cgroup *cgrp) +{ + struct __cgrps_kfunc_map_value local, *v; + long status; + struct cgroup *acquired, *old; + s32 id; + + status = bpf_probe_read_kernel(&id, sizeof(id), &cgrp->self.id); + if (status) + return status; + + local.cgrp = NULL; + status = bpf_map_update_elem(&__cgrps_kfunc_map, &id, &local, BPF_NOEXIST); + if (status) + return status; + + v = bpf_map_lookup_elem(&__cgrps_kfunc_map, &id); + if (!v) { + bpf_map_delete_elem(&__cgrps_kfunc_map, &id); + return -ENOENT; + } + + acquired = bpf_cgroup_acquire(cgrp); + if (!acquired) { + bpf_map_delete_elem(&__cgrps_kfunc_map, &id); + return -ENOENT; + } + + old = bpf_kptr_xchg(&v->cgrp, acquired); + if (old) { + bpf_cgroup_release(old); + return -EEXIST; + } + + return 0; +} + +#endif /* _CGRP_KFUNC_COMMON_H */ diff --git a/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c b/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c new file mode 100644 index 0000000000..0fa564a5cc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c @@ -0,0 +1,247 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" +#include "cgrp_kfunc_common.h" + +char _license[] SEC("license") = "GPL"; + +/* Prototype for all of the program trace events below: + * + * TRACE_EVENT(cgroup_mkdir, + * TP_PROTO(struct cgroup *cgrp, const char *path), + * TP_ARGS(cgrp, path) + */ + +static struct __cgrps_kfunc_map_value *insert_lookup_cgrp(struct cgroup *cgrp) +{ + int status; + + status = cgrps_kfunc_map_insert(cgrp); + if (status) + return NULL; + + return cgrps_kfunc_map_value_lookup(cgrp); +} + +SEC("tp_btf/cgroup_mkdir") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +int BPF_PROG(cgrp_kfunc_acquire_untrusted, struct cgroup *cgrp, const char *path) +{ + struct cgroup *acquired; + struct __cgrps_kfunc_map_value *v; + + v = insert_lookup_cgrp(cgrp); + if (!v) + return 0; + + /* Can't invoke bpf_cgroup_acquire() on an untrusted pointer. */ + acquired = bpf_cgroup_acquire(v->cgrp); + if (acquired) + bpf_cgroup_release(acquired); + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +int BPF_PROG(cgrp_kfunc_acquire_no_null_check, struct cgroup *cgrp, const char *path) +{ + struct cgroup *acquired; + + acquired = bpf_cgroup_acquire(cgrp); + /* + * Can't invoke bpf_cgroup_release() without checking the return value + * of bpf_cgroup_acquire(). + */ + bpf_cgroup_release(acquired); + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +__failure __msg("arg#0 pointer type STRUCT cgroup must point") +int BPF_PROG(cgrp_kfunc_acquire_fp, struct cgroup *cgrp, const char *path) +{ + struct cgroup *acquired, *stack_cgrp = (struct cgroup *)&path; + + /* Can't invoke bpf_cgroup_acquire() on a random frame pointer. */ + acquired = bpf_cgroup_acquire((struct cgroup *)&stack_cgrp); + if (acquired) + bpf_cgroup_release(acquired); + + return 0; +} + +SEC("kretprobe/cgroup_destroy_locked") +__failure __msg("reg type unsupported for arg#0 function") +int BPF_PROG(cgrp_kfunc_acquire_unsafe_kretprobe, struct cgroup *cgrp) +{ + struct cgroup *acquired; + + /* Can't acquire an untrusted struct cgroup * pointer. */ + acquired = bpf_cgroup_acquire(cgrp); + if (acquired) + bpf_cgroup_release(acquired); + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +__failure __msg("cgrp_kfunc_acquire_trusted_walked") +int BPF_PROG(cgrp_kfunc_acquire_trusted_walked, struct cgroup *cgrp, const char *path) +{ + struct cgroup *acquired; + + /* Can't invoke bpf_cgroup_acquire() on a pointer obtained from walking a trusted cgroup. */ + acquired = bpf_cgroup_acquire(cgrp->old_dom_cgrp); + if (acquired) + bpf_cgroup_release(acquired); + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +int BPF_PROG(cgrp_kfunc_acquire_null, struct cgroup *cgrp, const char *path) +{ + struct cgroup *acquired; + + /* Can't invoke bpf_cgroup_acquire() on a NULL pointer. */ + acquired = bpf_cgroup_acquire(NULL); + if (acquired) + bpf_cgroup_release(acquired); + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +__failure __msg("Unreleased reference") +int BPF_PROG(cgrp_kfunc_acquire_unreleased, struct cgroup *cgrp, const char *path) +{ + struct cgroup *acquired; + + acquired = bpf_cgroup_acquire(cgrp); + + /* Acquired cgroup is never released. */ + __sink(acquired); + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +__failure __msg("Unreleased reference") +int BPF_PROG(cgrp_kfunc_xchg_unreleased, struct cgroup *cgrp, const char *path) +{ + struct cgroup *kptr; + struct __cgrps_kfunc_map_value *v; + + v = insert_lookup_cgrp(cgrp); + if (!v) + return 0; + + kptr = bpf_kptr_xchg(&v->cgrp, NULL); + if (!kptr) + return 0; + + /* Kptr retrieved from map is never released. */ + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +__failure __msg("must be referenced or trusted") +int BPF_PROG(cgrp_kfunc_rcu_get_release, struct cgroup *cgrp, const char *path) +{ + struct cgroup *kptr; + struct __cgrps_kfunc_map_value *v; + + v = insert_lookup_cgrp(cgrp); + if (!v) + return 0; + + bpf_rcu_read_lock(); + kptr = v->cgrp; + if (kptr) + /* Can't release a cgroup kptr stored in a map. */ + bpf_cgroup_release(kptr); + bpf_rcu_read_unlock(); + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +int BPF_PROG(cgrp_kfunc_release_untrusted, struct cgroup *cgrp, const char *path) +{ + struct __cgrps_kfunc_map_value *v; + + v = insert_lookup_cgrp(cgrp); + if (!v) + return 0; + + /* Can't invoke bpf_cgroup_release() on an untrusted pointer. */ + bpf_cgroup_release(v->cgrp); + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +__failure __msg("arg#0 pointer type STRUCT cgroup must point") +int BPF_PROG(cgrp_kfunc_release_fp, struct cgroup *cgrp, const char *path) +{ + struct cgroup *acquired = (struct cgroup *)&path; + + /* Cannot release random frame pointer. */ + bpf_cgroup_release(acquired); + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +int BPF_PROG(cgrp_kfunc_release_null, struct cgroup *cgrp, const char *path) +{ + struct __cgrps_kfunc_map_value local, *v; + long status; + struct cgroup *acquired, *old; + s32 id; + + status = bpf_probe_read_kernel(&id, sizeof(id), &cgrp->self.id); + if (status) + return 0; + + local.cgrp = NULL; + status = bpf_map_update_elem(&__cgrps_kfunc_map, &id, &local, BPF_NOEXIST); + if (status) + return status; + + v = bpf_map_lookup_elem(&__cgrps_kfunc_map, &id); + if (!v) + return -ENOENT; + + acquired = bpf_cgroup_acquire(cgrp); + if (!acquired) + return -ENOENT; + + old = bpf_kptr_xchg(&v->cgrp, acquired); + + /* old cannot be passed to bpf_cgroup_release() without a NULL check. */ + bpf_cgroup_release(old); + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +__failure __msg("release kernel function bpf_cgroup_release expects") +int BPF_PROG(cgrp_kfunc_release_unacquired, struct cgroup *cgrp, const char *path) +{ + /* Cannot release trusted cgroup pointer which was not acquired. */ + bpf_cgroup_release(cgrp); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c b/tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c new file mode 100644 index 0000000000..5354455a01 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c @@ -0,0 +1,223 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "cgrp_kfunc_common.h" + +char _license[] SEC("license") = "GPL"; + +int err, pid, invocations; + +/* Prototype for all of the program trace events below: + * + * TRACE_EVENT(cgroup_mkdir, + * TP_PROTO(struct cgroup *cgrp, const char *path), + * TP_ARGS(cgrp, path) + */ + +static bool is_test_kfunc_task(void) +{ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + bool same = pid == cur_pid; + + if (same) + __sync_fetch_and_add(&invocations, 1); + + return same; +} + +SEC("tp_btf/cgroup_mkdir") +int BPF_PROG(test_cgrp_acquire_release_argument, struct cgroup *cgrp, const char *path) +{ + struct cgroup *acquired; + + if (!is_test_kfunc_task()) + return 0; + + acquired = bpf_cgroup_acquire(cgrp); + if (!acquired) + err = 1; + else + bpf_cgroup_release(acquired); + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +int BPF_PROG(test_cgrp_acquire_leave_in_map, struct cgroup *cgrp, const char *path) +{ + long status; + + if (!is_test_kfunc_task()) + return 0; + + status = cgrps_kfunc_map_insert(cgrp); + if (status) + err = 1; + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +int BPF_PROG(test_cgrp_xchg_release, struct cgroup *cgrp, const char *path) +{ + struct cgroup *kptr, *cg; + struct __cgrps_kfunc_map_value *v; + long status; + + if (!is_test_kfunc_task()) + return 0; + + status = cgrps_kfunc_map_insert(cgrp); + if (status) { + err = 1; + return 0; + } + + v = cgrps_kfunc_map_value_lookup(cgrp); + if (!v) { + err = 2; + return 0; + } + + kptr = v->cgrp; + if (!kptr) { + err = 4; + return 0; + } + + cg = bpf_cgroup_ancestor(kptr, 1); + if (cg) /* verifier only check */ + bpf_cgroup_release(cg); + + kptr = bpf_kptr_xchg(&v->cgrp, NULL); + if (!kptr) { + err = 3; + return 0; + } + + bpf_cgroup_release(kptr); + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +int BPF_PROG(test_cgrp_get_release, struct cgroup *cgrp, const char *path) +{ + struct cgroup *kptr; + struct __cgrps_kfunc_map_value *v; + long status; + + if (!is_test_kfunc_task()) + return 0; + + status = cgrps_kfunc_map_insert(cgrp); + if (status) { + err = 1; + return 0; + } + + v = cgrps_kfunc_map_value_lookup(cgrp); + if (!v) { + err = 2; + return 0; + } + + bpf_rcu_read_lock(); + kptr = v->cgrp; + if (!kptr) + err = 3; + bpf_rcu_read_unlock(); + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +int BPF_PROG(test_cgrp_get_ancestors, struct cgroup *cgrp, const char *path) +{ + struct cgroup *self, *ancestor1, *invalid; + + if (!is_test_kfunc_task()) + return 0; + + self = bpf_cgroup_ancestor(cgrp, cgrp->level); + if (!self) { + err = 1; + return 0; + } + + if (self->self.id != cgrp->self.id) { + bpf_cgroup_release(self); + err = 2; + return 0; + } + bpf_cgroup_release(self); + + ancestor1 = bpf_cgroup_ancestor(cgrp, cgrp->level - 1); + if (!ancestor1) { + err = 3; + return 0; + } + bpf_cgroup_release(ancestor1); + + invalid = bpf_cgroup_ancestor(cgrp, 10000); + if (invalid) { + bpf_cgroup_release(invalid); + err = 4; + return 0; + } + + invalid = bpf_cgroup_ancestor(cgrp, -1); + if (invalid) { + bpf_cgroup_release(invalid); + err = 5; + return 0; + } + + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +int BPF_PROG(test_cgrp_from_id, struct cgroup *cgrp, const char *path) +{ + struct cgroup *parent, *res; + u64 parent_cgid; + + if (!is_test_kfunc_task()) + return 0; + + /* @cgrp's ID is not visible yet, let's test with the parent */ + parent = bpf_cgroup_ancestor(cgrp, cgrp->level - 1); + if (!parent) { + err = 1; + return 0; + } + + parent_cgid = parent->kn->id; + bpf_cgroup_release(parent); + + res = bpf_cgroup_from_id(parent_cgid); + if (!res) { + err = 2; + return 0; + } + + bpf_cgroup_release(res); + + if (res != parent) { + err = 3; + return 0; + } + + res = bpf_cgroup_from_id((u64)-1); + if (res) { + bpf_cgroup_release(res); + err = 4; + return 0; + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_attach_cgroup.c b/tools/testing/selftests/bpf/progs/cgrp_ls_attach_cgroup.c new file mode 100644 index 0000000000..8aeba1b75c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgrp_ls_attach_cgroup.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_tracing_net.h" + +char _license[] SEC("license") = "GPL"; + +struct socket_cookie { + __u64 cookie_key; + __u64 cookie_value; +}; + +struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct socket_cookie); +} socket_cookies SEC(".maps"); + +SEC("cgroup/connect6") +int set_cookie(struct bpf_sock_addr *ctx) +{ + struct socket_cookie *p; + struct tcp_sock *tcp_sk; + struct bpf_sock *sk; + + if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6) + return 1; + + sk = ctx->sk; + if (!sk) + return 1; + + tcp_sk = bpf_skc_to_tcp_sock(sk); + if (!tcp_sk) + return 1; + + p = bpf_cgrp_storage_get(&socket_cookies, + tcp_sk->inet_conn.icsk_inet.sk.sk_cgrp_data.cgroup, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!p) + return 1; + + p->cookie_value = 0xF; + p->cookie_key = bpf_get_socket_cookie(ctx); + return 1; +} + +SEC("sockops") +int update_cookie_sockops(struct bpf_sock_ops *ctx) +{ + struct socket_cookie *p; + struct tcp_sock *tcp_sk; + struct bpf_sock *sk; + + if (ctx->family != AF_INET6 || ctx->op != BPF_SOCK_OPS_TCP_CONNECT_CB) + return 1; + + sk = ctx->sk; + if (!sk) + return 1; + + tcp_sk = bpf_skc_to_tcp_sock(sk); + if (!tcp_sk) + return 1; + + p = bpf_cgrp_storage_get(&socket_cookies, + tcp_sk->inet_conn.icsk_inet.sk.sk_cgrp_data.cgroup, 0, 0); + if (!p) + return 1; + + if (p->cookie_key != bpf_get_socket_cookie(ctx)) + return 1; + + p->cookie_value |= (ctx->local_port << 8); + return 1; +} + +SEC("fexit/inet_stream_connect") +int BPF_PROG(update_cookie_tracing, struct socket *sock, + struct sockaddr *uaddr, int addr_len, int flags) +{ + struct socket_cookie *p; + + if (uaddr->sa_family != AF_INET6) + return 0; + + p = bpf_cgrp_storage_get(&socket_cookies, sock->sk->sk_cgrp_data.cgroup, 0, 0); + if (!p) + return 0; + + if (p->cookie_key != bpf_get_socket_cookie(sock->sk)) + return 0; + + p->cookie_value |= 0xF0; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_negative.c b/tools/testing/selftests/bpf/progs/cgrp_ls_negative.c new file mode 100644 index 0000000000..d41f90e2ab --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgrp_ls_negative.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} map_a SEC(".maps"); + +SEC("tp_btf/sys_enter") +int BPF_PROG(on_enter, struct pt_regs *regs, long id) +{ + struct task_struct *task; + + task = bpf_get_current_task_btf(); + (void)bpf_cgrp_storage_get(&map_a, (struct cgroup *)task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c new file mode 100644 index 0000000000..a043d8fefd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} map_a SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} map_b SEC(".maps"); + +SEC("fentry/bpf_local_storage_lookup") +int BPF_PROG(on_lookup) +{ + struct task_struct *task = bpf_get_current_task_btf(); + + bpf_cgrp_storage_delete(&map_a, task->cgroups->dfl_cgrp); + bpf_cgrp_storage_delete(&map_b, task->cgroups->dfl_cgrp); + return 0; +} + +SEC("fentry/bpf_local_storage_update") +int BPF_PROG(on_update) +{ + struct task_struct *task = bpf_get_current_task_btf(); + long *ptr; + + ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + *ptr += 1; + + ptr = bpf_cgrp_storage_get(&map_b, task->cgroups->dfl_cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + *ptr += 1; + + return 0; +} + +SEC("tp_btf/sys_enter") +int BPF_PROG(on_enter, struct pt_regs *regs, long id) +{ + struct task_struct *task; + long *ptr; + + task = bpf_get_current_task_btf(); + ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + *ptr = 200; + + ptr = bpf_cgrp_storage_get(&map_b, task->cgroups->dfl_cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + *ptr = 100; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c b/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c new file mode 100644 index 0000000000..4c7844e1db --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} map_a SEC(".maps"); + +__u32 target_pid; +__u64 cgroup_id; + +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +SEC("?iter.s/cgroup") +int cgroup_iter(struct bpf_iter__cgroup *ctx) +{ + struct cgroup *cgrp = ctx->cgroup; + long *ptr; + + if (cgrp == NULL) + return 0; + + ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + cgroup_id = cgrp->kn->id; + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int no_rcu_lock(void *ctx) +{ + struct task_struct *task; + struct cgroup *cgrp; + long *ptr; + + task = bpf_get_current_task_btf(); + if (task->pid != target_pid) + return 0; + + /* task->cgroups is untrusted in sleepable prog outside of RCU CS */ + cgrp = task->cgroups->dfl_cgrp; + ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + cgroup_id = cgrp->kn->id; + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int yes_rcu_lock(void *ctx) +{ + struct task_struct *task; + struct cgroup *cgrp; + long *ptr; + + task = bpf_get_current_task_btf(); + if (task->pid != target_pid) + return 0; + + bpf_rcu_read_lock(); + cgrp = task->cgroups->dfl_cgrp; + /* cgrp is trusted under RCU CS */ + ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + cgroup_id = cgrp->kn->id; + bpf_rcu_read_unlock(); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c b/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c new file mode 100644 index 0000000000..9ebb8e2fe5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} map_a SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} map_b SEC(".maps"); + +#define MAGIC_VALUE 0xabcd1234 + +pid_t target_pid = 0; +int mismatch_cnt = 0; +int enter_cnt = 0; +int exit_cnt = 0; + +SEC("tp_btf/sys_enter") +int BPF_PROG(on_enter, struct pt_regs *regs, long id) +{ + struct task_struct *task; + long *ptr; + int err; + + task = bpf_get_current_task_btf(); + if (task->pid != target_pid) + return 0; + + /* populate value 0 */ + ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!ptr) + return 0; + + /* delete value 0 */ + err = bpf_cgrp_storage_delete(&map_a, task->cgroups->dfl_cgrp); + if (err) + return 0; + + /* value is not available */ + ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, 0); + if (ptr) + return 0; + + /* re-populate the value */ + ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!ptr) + return 0; + __sync_fetch_and_add(&enter_cnt, 1); + *ptr = MAGIC_VALUE + enter_cnt; + + return 0; +} + +SEC("tp_btf/sys_exit") +int BPF_PROG(on_exit, struct pt_regs *regs, long id) +{ + struct task_struct *task; + long *ptr; + + task = bpf_get_current_task_btf(); + if (task->pid != target_pid) + return 0; + + ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!ptr) + return 0; + + __sync_fetch_and_add(&exit_cnt, 1); + if (*ptr != MAGIC_VALUE + exit_cnt) + __sync_fetch_and_add(&mismatch_cnt, 1); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/connect4_dropper.c b/tools/testing/selftests/bpf/progs/connect4_dropper.c new file mode 100644 index 0000000000..d3f4c5e4fb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect4_dropper.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> + +#include <sys/socket.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define VERDICT_REJECT 0 +#define VERDICT_PROCEED 1 + +SEC("cgroup/connect4") +int connect_v4_dropper(struct bpf_sock_addr *ctx) +{ + if (ctx->type != SOCK_STREAM) + return VERDICT_PROCEED; + if (ctx->user_port == bpf_htons(60120)) + return VERDICT_REJECT; + return VERDICT_PROCEED; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c new file mode 100644 index 0000000000..7ef49ec048 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect4_prog.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/tcp.h> +#include <linux/if.h> +#include <errno.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include "bpf_tcp_helpers.h" + +#define SRC_REWRITE_IP4 0x7f000004U +#define DST_REWRITE_IP4 0x7f000001U +#define DST_REWRITE_PORT4 4444 + +#ifndef TCP_CA_NAME_MAX +#define TCP_CA_NAME_MAX 16 +#endif + +#ifndef TCP_NOTSENT_LOWAT +#define TCP_NOTSENT_LOWAT 25 +#endif + +#ifndef IFNAMSIZ +#define IFNAMSIZ 16 +#endif + +__attribute__ ((noinline)) __weak +int do_bind(struct bpf_sock_addr *ctx) +{ + struct sockaddr_in sa = {}; + + sa.sin_family = AF_INET; + sa.sin_port = bpf_htons(0); + sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4); + + if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0) + return 0; + + return 1; +} + +static __inline int verify_cc(struct bpf_sock_addr *ctx, + char expected[TCP_CA_NAME_MAX]) +{ + char buf[TCP_CA_NAME_MAX]; + int i; + + if (bpf_getsockopt(ctx, SOL_TCP, TCP_CONGESTION, &buf, sizeof(buf))) + return 1; + + for (i = 0; i < TCP_CA_NAME_MAX; i++) { + if (buf[i] != expected[i]) + return 1; + if (buf[i] == 0) + break; + } + + return 0; +} + +static __inline int set_cc(struct bpf_sock_addr *ctx) +{ + char reno[TCP_CA_NAME_MAX] = "reno"; + char cubic[TCP_CA_NAME_MAX] = "cubic"; + + if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &reno, sizeof(reno))) + return 1; + if (verify_cc(ctx, reno)) + return 1; + + if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &cubic, sizeof(cubic))) + return 1; + if (verify_cc(ctx, cubic)) + return 1; + + return 0; +} + +static __inline int bind_to_device(struct bpf_sock_addr *ctx) +{ + char veth1[IFNAMSIZ] = "test_sock_addr1"; + char veth2[IFNAMSIZ] = "test_sock_addr2"; + char missing[IFNAMSIZ] = "nonexistent_dev"; + char del_bind[IFNAMSIZ] = ""; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &veth1, sizeof(veth1))) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &veth2, sizeof(veth2))) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &missing, sizeof(missing)) != -ENODEV) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &del_bind, sizeof(del_bind))) + return 1; + + return 0; +} + +static __inline int set_keepalive(struct bpf_sock_addr *ctx) +{ + int zero = 0, one = 1; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_KEEPALIVE, &one, sizeof(one))) + return 1; + if (ctx->type == SOCK_STREAM) { + if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPIDLE, &one, sizeof(one))) + return 1; + if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPINTVL, &one, sizeof(one))) + return 1; + if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPCNT, &one, sizeof(one))) + return 1; + if (bpf_setsockopt(ctx, SOL_TCP, TCP_SYNCNT, &one, sizeof(one))) + return 1; + if (bpf_setsockopt(ctx, SOL_TCP, TCP_USER_TIMEOUT, &one, sizeof(one))) + return 1; + } + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_KEEPALIVE, &zero, sizeof(zero))) + return 1; + + return 0; +} + +static __inline int set_notsent_lowat(struct bpf_sock_addr *ctx) +{ + int lowat = 65535; + + if (ctx->type == SOCK_STREAM) { + if (bpf_setsockopt(ctx, SOL_TCP, TCP_NOTSENT_LOWAT, &lowat, sizeof(lowat))) + return 1; + } + + return 0; +} + +SEC("cgroup/connect4") +int connect_v4_prog(struct bpf_sock_addr *ctx) +{ + struct bpf_sock_tuple tuple = {}; + struct bpf_sock *sk; + + /* Verify that new destination is available. */ + memset(&tuple.ipv4.saddr, 0, sizeof(tuple.ipv4.saddr)); + memset(&tuple.ipv4.sport, 0, sizeof(tuple.ipv4.sport)); + + tuple.ipv4.daddr = bpf_htonl(DST_REWRITE_IP4); + tuple.ipv4.dport = bpf_htons(DST_REWRITE_PORT4); + + /* Bind to device and unbind it. */ + if (bind_to_device(ctx)) + return 0; + + if (set_keepalive(ctx)) + return 0; + + if (set_notsent_lowat(ctx)) + return 0; + + if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM) + return 0; + else if (ctx->type == SOCK_STREAM) + sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv4), + BPF_F_CURRENT_NETNS, 0); + else + sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv4), + BPF_F_CURRENT_NETNS, 0); + + if (!sk) + return 0; + + if (sk->src_ip4 != tuple.ipv4.daddr || + sk->src_port != DST_REWRITE_PORT4) { + bpf_sk_release(sk); + return 0; + } + + bpf_sk_release(sk); + + /* Rewrite congestion control. */ + if (ctx->type == SOCK_STREAM && set_cc(ctx)) + return 0; + + /* Rewrite destination. */ + ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4); + ctx->user_port = bpf_htons(DST_REWRITE_PORT4); + + return do_bind(ctx) ? 1 : 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/connect6_prog.c b/tools/testing/selftests/bpf/progs/connect6_prog.c new file mode 100644 index 0000000000..40266d2c73 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect6_prog.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <sys/socket.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define SRC_REWRITE_IP6_0 0 +#define SRC_REWRITE_IP6_1 0 +#define SRC_REWRITE_IP6_2 0 +#define SRC_REWRITE_IP6_3 6 + +#define DST_REWRITE_IP6_0 0 +#define DST_REWRITE_IP6_1 0 +#define DST_REWRITE_IP6_2 0 +#define DST_REWRITE_IP6_3 1 + +#define DST_REWRITE_PORT6 6666 + +SEC("cgroup/connect6") +int connect_v6_prog(struct bpf_sock_addr *ctx) +{ + struct bpf_sock_tuple tuple = {}; + struct sockaddr_in6 sa; + struct bpf_sock *sk; + + /* Verify that new destination is available. */ + memset(&tuple.ipv6.saddr, 0, sizeof(tuple.ipv6.saddr)); + memset(&tuple.ipv6.sport, 0, sizeof(tuple.ipv6.sport)); + + tuple.ipv6.daddr[0] = bpf_htonl(DST_REWRITE_IP6_0); + tuple.ipv6.daddr[1] = bpf_htonl(DST_REWRITE_IP6_1); + tuple.ipv6.daddr[2] = bpf_htonl(DST_REWRITE_IP6_2); + tuple.ipv6.daddr[3] = bpf_htonl(DST_REWRITE_IP6_3); + + tuple.ipv6.dport = bpf_htons(DST_REWRITE_PORT6); + + if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM) + return 0; + else if (ctx->type == SOCK_STREAM) + sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv6), + BPF_F_CURRENT_NETNS, 0); + else + sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv6), + BPF_F_CURRENT_NETNS, 0); + + if (!sk) + return 0; + + if (sk->src_ip6[0] != tuple.ipv6.daddr[0] || + sk->src_ip6[1] != tuple.ipv6.daddr[1] || + sk->src_ip6[2] != tuple.ipv6.daddr[2] || + sk->src_ip6[3] != tuple.ipv6.daddr[3] || + sk->src_port != DST_REWRITE_PORT6) { + bpf_sk_release(sk); + return 0; + } + + bpf_sk_release(sk); + + /* Rewrite destination. */ + ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0); + ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_1); + ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2); + ctx->user_ip6[3] = bpf_htonl(DST_REWRITE_IP6_3); + + ctx->user_port = bpf_htons(DST_REWRITE_PORT6); + + /* Rewrite source. */ + memset(&sa, 0, sizeof(sa)); + + sa.sin6_family = AF_INET6; + sa.sin6_port = bpf_htons(0); + + sa.sin6_addr.s6_addr32[0] = bpf_htonl(SRC_REWRITE_IP6_0); + sa.sin6_addr.s6_addr32[1] = bpf_htonl(SRC_REWRITE_IP6_1); + sa.sin6_addr.s6_addr32[2] = bpf_htonl(SRC_REWRITE_IP6_2); + sa.sin6_addr.s6_addr32[3] = bpf_htonl(SRC_REWRITE_IP6_3); + + if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0) + return 0; + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/connect_force_port4.c b/tools/testing/selftests/bpf/progs/connect_force_port4.c new file mode 100644 index 0000000000..27a632dd38 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect_force_port4.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include <stdbool.h> + +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <sys/socket.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include <bpf_sockopt_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct svc_addr { + __be32 addr; + __be16 port; +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct svc_addr); +} service_mapping SEC(".maps"); + +SEC("cgroup/connect4") +int connect4(struct bpf_sock_addr *ctx) +{ + struct sockaddr_in sa = {}; + struct svc_addr *orig; + + /* Force local address to 127.0.0.1:22222. */ + sa.sin_family = AF_INET; + sa.sin_port = bpf_htons(22222); + sa.sin_addr.s_addr = bpf_htonl(0x7f000001); + + if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0) + return 0; + + /* Rewire service 1.2.3.4:60000 to backend 127.0.0.1:60123. */ + if (ctx->user_port == bpf_htons(60000)) { + orig = bpf_sk_storage_get(&service_mapping, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!orig) + return 0; + + orig->addr = ctx->user_ip4; + orig->port = ctx->user_port; + + ctx->user_ip4 = bpf_htonl(0x7f000001); + ctx->user_port = bpf_htons(60123); + } + return 1; +} + +SEC("cgroup/getsockname4") +int getsockname4(struct bpf_sock_addr *ctx) +{ + if (!get_set_sk_priority(ctx)) + return 1; + + /* Expose local server as 1.2.3.4:60000 to client. */ + if (ctx->user_port == bpf_htons(60123)) { + ctx->user_ip4 = bpf_htonl(0x01020304); + ctx->user_port = bpf_htons(60000); + } + return 1; +} + +SEC("cgroup/getpeername4") +int getpeername4(struct bpf_sock_addr *ctx) +{ + struct svc_addr *orig; + + if (!get_set_sk_priority(ctx)) + return 1; + + /* Expose service 1.2.3.4:60000 as peer instead of backend. */ + if (ctx->user_port == bpf_htons(60123)) { + orig = bpf_sk_storage_get(&service_mapping, ctx->sk, 0, 0); + if (orig) { + ctx->user_ip4 = orig->addr; + ctx->user_port = orig->port; + } + } + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/connect_force_port6.c b/tools/testing/selftests/bpf/progs/connect_force_port6.c new file mode 100644 index 0000000000..19cad93e61 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect_force_port6.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> + +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <sys/socket.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include <bpf_sockopt_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct svc_addr { + __be32 addr[4]; + __be16 port; +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct svc_addr); +} service_mapping SEC(".maps"); + +SEC("cgroup/connect6") +int connect6(struct bpf_sock_addr *ctx) +{ + struct sockaddr_in6 sa = {}; + struct svc_addr *orig; + + /* Force local address to [::1]:22223. */ + sa.sin6_family = AF_INET6; + sa.sin6_port = bpf_htons(22223); + sa.sin6_addr.s6_addr32[3] = bpf_htonl(1); + + if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0) + return 0; + + /* Rewire service [fc00::1]:60000 to backend [::1]:60124. */ + if (ctx->user_port == bpf_htons(60000)) { + orig = bpf_sk_storage_get(&service_mapping, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!orig) + return 0; + + orig->addr[0] = ctx->user_ip6[0]; + orig->addr[1] = ctx->user_ip6[1]; + orig->addr[2] = ctx->user_ip6[2]; + orig->addr[3] = ctx->user_ip6[3]; + orig->port = ctx->user_port; + + ctx->user_ip6[0] = 0; + ctx->user_ip6[1] = 0; + ctx->user_ip6[2] = 0; + ctx->user_ip6[3] = bpf_htonl(1); + ctx->user_port = bpf_htons(60124); + } + return 1; +} + +SEC("cgroup/getsockname6") +int getsockname6(struct bpf_sock_addr *ctx) +{ + if (!get_set_sk_priority(ctx)) + return 1; + + /* Expose local server as [fc00::1]:60000 to client. */ + if (ctx->user_port == bpf_htons(60124)) { + ctx->user_ip6[0] = bpf_htonl(0xfc000000); + ctx->user_ip6[1] = 0; + ctx->user_ip6[2] = 0; + ctx->user_ip6[3] = bpf_htonl(1); + ctx->user_port = bpf_htons(60000); + } + return 1; +} + +SEC("cgroup/getpeername6") +int getpeername6(struct bpf_sock_addr *ctx) +{ + struct svc_addr *orig; + + if (!get_set_sk_priority(ctx)) + return 1; + + /* Expose service [fc00::1]:60000 as peer instead of backend. */ + if (ctx->user_port == bpf_htons(60124)) { + orig = bpf_sk_storage_get(&service_mapping, ctx->sk, 0, 0); + if (orig) { + ctx->user_ip6[0] = orig->addr[0]; + ctx->user_ip6[1] = orig->addr[1]; + ctx->user_ip6[2] = orig->addr[2]; + ctx->user_ip6[3] = orig->addr[3]; + ctx->user_port = orig->port; + } + } + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/connect_ping.c b/tools/testing/selftests/bpf/progs/connect_ping.c new file mode 100644 index 0000000000..60178192b6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect_ping.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2022 Google LLC. + */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include <netinet/in.h> +#include <sys/socket.h> + +/* 2001:db8::1 */ +#define BINDADDR_V6 { { { 0x20,0x01,0x0d,0xb8,0,0,0,0,0,0,0,0,0,0,0,1 } } } + +__u32 do_bind = 0; +__u32 has_error = 0; +__u32 invocations_v4 = 0; +__u32 invocations_v6 = 0; + +SEC("cgroup/connect4") +int connect_v4_prog(struct bpf_sock_addr *ctx) +{ + struct sockaddr_in sa = { + .sin_family = AF_INET, + .sin_addr.s_addr = bpf_htonl(0x01010101), + }; + + __sync_fetch_and_add(&invocations_v4, 1); + + if (do_bind && bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa))) + has_error = 1; + + return 1; +} + +SEC("cgroup/connect6") +int connect_v6_prog(struct bpf_sock_addr *ctx) +{ + struct sockaddr_in6 sa = { + .sin6_family = AF_INET6, + .sin6_addr = BINDADDR_V6, + }; + + __sync_fetch_and_add(&invocations_v6, 1); + + if (do_bind && bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa))) + has_error = 1; + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/core_kern.c b/tools/testing/selftests/bpf/progs/core_kern.c new file mode 100644 index 0000000000..004f2acef2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/core_kern.c @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +#define ATTR __always_inline +#include "test_jhash.h" + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u32); + __uint(max_entries, 256); +} array1 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u32); + __uint(max_entries, 256); +} array2 SEC(".maps"); + +static __noinline int randmap(int v, const struct net_device *dev) +{ + struct bpf_map *map = (struct bpf_map *)&array1; + int key = bpf_get_prandom_u32() & 0xff; + int *val; + + if (bpf_get_prandom_u32() & 1) + map = (struct bpf_map *)&array2; + + val = bpf_map_lookup_elem(map, &key); + if (val) + *val = bpf_get_prandom_u32() + v + dev->mtu; + + return 0; +} + +SEC("tp_btf/xdp_devmap_xmit") +int BPF_PROG(tp_xdp_devmap_xmit_multi, const struct net_device + *from_dev, const struct net_device *to_dev, int sent, int drops, + int err) +{ + return randmap(from_dev->ifindex, from_dev); +} + +SEC("fentry/eth_type_trans") +int BPF_PROG(fentry_eth_type_trans, struct sk_buff *skb, + struct net_device *dev, unsigned short protocol) +{ + return randmap(dev->ifindex + skb->len, dev); +} + +SEC("fexit/eth_type_trans") +int BPF_PROG(fexit_eth_type_trans, struct sk_buff *skb, + struct net_device *dev, unsigned short protocol) +{ + return randmap(dev->ifindex + skb->len, dev); +} + +volatile const int never; + +struct __sk_bUfF /* it will not exist in vmlinux */ { + int len; +} __attribute__((preserve_access_index)); + +struct bpf_testmod_test_read_ctx /* it exists in bpf_testmod */ { + size_t len; +} __attribute__((preserve_access_index)); + +SEC("tc") +int balancer_ingress(struct __sk_buff *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + void *ptr; + int nh_off, i = 0; + + nh_off = 14; + + /* pragma unroll doesn't work on large loops */ +#define C do { \ + ptr = data + i; \ + if (ptr + nh_off > data_end) \ + break; \ + ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \ + if (never) { \ + /* below is a dead code with unresolvable CO-RE relo */ \ + i += ((struct __sk_bUfF *)ctx)->len; \ + /* this CO-RE relo may or may not resolve + * depending on whether bpf_testmod is loaded. + */ \ + i += ((struct bpf_testmod_test_read_ctx *)ctx)->len; \ + } \ + } while (0); +#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C; + C30;C30;C30; /* 90 calls */ + return 0; +} + +typedef int (*func_proto_typedef___match)(long); +typedef int (*func_proto_typedef___doesnt_match)(char *); +typedef int (*func_proto_typedef_nested1)(func_proto_typedef___match); + +int proto_out[3]; + +SEC("raw_tracepoint/sys_enter") +int core_relo_proto(void *ctx) +{ + proto_out[0] = bpf_core_type_exists(func_proto_typedef___match); + proto_out[1] = bpf_core_type_exists(func_proto_typedef___doesnt_match); + proto_out[2] = bpf_core_type_exists(func_proto_typedef_nested1); + + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/core_kern_overflow.c b/tools/testing/selftests/bpf/progs/core_kern_overflow.c new file mode 100644 index 0000000000..f0d5652256 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/core_kern_overflow.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +typedef int (*func_proto_typedef)(long); +typedef int (*func_proto_typedef_nested1)(func_proto_typedef); +typedef int (*func_proto_typedef_nested2)(func_proto_typedef_nested1); + +int proto_out; + +SEC("raw_tracepoint/sys_enter") +int core_relo_proto(void *ctx) +{ + proto_out = bpf_core_type_exists(func_proto_typedef_nested2); + + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h new file mode 100644 index 0000000000..fd8e1b4c67 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h @@ -0,0 +1,1353 @@ +#include <stdint.h> +#include <stdbool.h> + +void preserce_ptr_sz_fn(long x) {} + +#define __bpf_aligned __attribute__((aligned(8))) + +/* + * KERNEL + */ + +struct core_reloc_kernel_output { + int valid[10]; + char comm[sizeof("test_progs")]; + int comm_len; + bool local_task_struct_matches; +}; + +/* + * MODULE + */ + +struct core_reloc_module_output { + long long len; + long long off; + int read_ctx_sz; + bool read_ctx_exists; + bool buf_exists; + bool len_exists; + bool off_exists; + /* we have test_progs[-flavor], so cut flavor part */ + char comm[sizeof("test_progs")]; + int comm_len; +}; + +/* + * FLAVORS + */ +struct core_reloc_flavors { + int a; + int b; + int c; +}; + +/* this is not a flavor, as it doesn't have triple underscore */ +struct core_reloc_flavors__err_wrong_name { + int a; + int b; + int c; +}; + +/* + * NESTING + */ +/* original set up, used to record relocations in BPF program */ +struct core_reloc_nesting_substruct { + int a; +}; + +union core_reloc_nesting_subunion { + int b; +}; + +struct core_reloc_nesting { + union { + struct core_reloc_nesting_substruct a; + } a; + struct { + union core_reloc_nesting_subunion b; + } b; +}; + +/* inlined anonymous struct/union instead of named structs in original */ +struct core_reloc_nesting___anon_embed { + int __just_for_padding; + union { + struct { + int a; + } a; + } a; + struct { + union { + int b; + } b; + } b; +}; + +/* different mix of nested structs/unions than in original */ +struct core_reloc_nesting___struct_union_mixup { + int __a; + struct { + int __a; + union { + char __a; + int a; + } a; + } a; + int __b; + union { + int __b; + union { + char __b; + int b; + } b; + } b; +}; + +/* extra anon structs/unions, but still valid a.a.a and b.b.b accessors */ +struct core_reloc_nesting___extra_nesting { + int __padding; + struct { + struct { + struct { + struct { + union { + int a; + } a; + }; + }; + } a; + int __some_more; + struct { + union { + union { + union { + struct { + int b; + }; + } b; + }; + } b; + }; + }; +}; + +/* three flavors of same struct with different structure but same layout for + * a.a.a and b.b.b, thus successfully resolved and relocatable */ +struct core_reloc_nesting___dup_compat_types { + char __just_for_padding; + /* 3 more bytes of padding */ + struct { + struct { + int a; /* offset 4 */ + } a; + } a; + long long __more_padding; + struct { + struct { + int b; /* offset 16 */ + } b; + } b; +}; + +struct core_reloc_nesting___dup_compat_types__2 { + int __aligned_padding; + struct { + int __trickier_noop[0]; + struct { + char __some_more_noops[0]; + int a; /* offset 4 */ + } a; + } a; + int __more_padding; + struct { + struct { + struct { + int __critical_padding; + int b; /* offset 16 */ + } b; + int __does_not_matter; + }; + } b; + int __more_irrelevant_stuff; +}; + +struct core_reloc_nesting___dup_compat_types__3 { + char __correct_padding[4]; + struct { + struct { + int a; /* offset 4 */ + } a; + } a; + /* 8 byte padding due to next struct's alignment */ + struct { + struct { + int b; + } b; + } b __attribute__((aligned(16))); +}; + +/* b.b.b field is missing */ +struct core_reloc_nesting___err_missing_field { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int x; + } b; + } b; +}; + +/* b.b.b field is an array of integers instead of plain int */ +struct core_reloc_nesting___err_array_field { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int b[1]; + } b; + } b; +}; + +/* middle b container is missing */ +struct core_reloc_nesting___err_missing_container { + struct { + struct { + int a; + } a; + } a; + struct { + int x; + } b; +}; + +/* middle b container is referenced through pointer instead of being embedded */ +struct core_reloc_nesting___err_nonstruct_container { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int b; + } *b; + } b; +}; + +/* middle b container is an array of structs instead of plain struct */ +struct core_reloc_nesting___err_array_container { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int b; + } b[1]; + } b; +}; + +/* two flavors of same struct with incompatible layout for b.b.b */ +struct core_reloc_nesting___err_dup_incompat_types__1 { + struct { + struct { + int a; /* offset 0 */ + } a; + } a; + struct { + struct { + int b; /* offset 4 */ + } b; + } b; +}; + +struct core_reloc_nesting___err_dup_incompat_types__2 { + struct { + struct { + int a; /* offset 0 */ + } a; + } a; + int __extra_padding; + struct { + struct { + int b; /* offset 8 (!) */ + } b; + } b; +}; + +/* two flavors of same struct having one of a.a.a and b.b.b, but not both */ +struct core_reloc_nesting___err_partial_match_dups__a { + struct { + struct { + int a; + } a; + } a; +}; + +struct core_reloc_nesting___err_partial_match_dups__b { + struct { + struct { + int b; + } b; + } b; +}; + +struct core_reloc_nesting___err_too_deep { + struct { + struct { + int a; + } a; + } a; + /* 65 levels of nestedness for b.b.b */ + struct { + struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + /* this one is one too much */ + struct { + int b; + }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + } b; + } b; +}; + +/* + * ARRAYS + */ +struct core_reloc_arrays_output { + int a2; + char b123; + int c1c; + int d00d; + int f10c; +}; + +struct core_reloc_arrays_substruct { + int c; + int d; +}; + +struct core_reloc_arrays { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; +}; + +/* bigger array dimensions */ +struct core_reloc_arrays___diff_arr_dim { + int a[7]; + char b[3][4][5]; + struct core_reloc_arrays_substruct c[4]; + struct core_reloc_arrays_substruct d[2][3]; + struct core_reloc_arrays_substruct f[1][3]; +}; + +/* different size of array's value (struct) */ +struct core_reloc_arrays___diff_arr_val_sz { + int a[5]; + char b[2][3][4]; + struct { + int __padding1; + int c; + int __padding2; + } c[3]; + struct { + int __padding1; + int d; + int __padding2; + } d[1][2]; + struct { + int __padding1; + int c; + int __padding2; + } f[][2]; +}; + +struct core_reloc_arrays___equiv_zero_sz_arr { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; + /* equivalent to flexible array */ + struct core_reloc_arrays_substruct f[][2]; +}; + +struct core_reloc_arrays___fixed_arr { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; + /* not a flexible array anymore, but within access bounds */ + struct core_reloc_arrays_substruct f[1][2]; +}; + +struct core_reloc_arrays___err_too_small { + int a[2]; /* this one is too small */ + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; +}; + +struct core_reloc_arrays___err_too_shallow { + int a[5]; + char b[2][3]; /* this one lacks one dimension */ + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; +}; + +struct core_reloc_arrays___err_non_array { + int a; /* not an array */ + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; +}; + +struct core_reloc_arrays___err_wrong_val_type { + int a[5]; + char b[2][3][4]; + int c[3]; /* value is not a struct */ + struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; +}; + +struct core_reloc_arrays___err_bad_zero_sz_arr { + /* zero-sized array, but not at the end */ + struct core_reloc_arrays_substruct f[0][2]; + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +/* + * PRIMITIVES + */ +enum core_reloc_primitives_enum { + A = 0, + B = 1, +}; + +struct core_reloc_primitives { + char a; + int b; + enum core_reloc_primitives_enum c; + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; +}; + +struct core_reloc_primitives___diff_enum_def { + char a; + int b; + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; + enum { + X = 100, + Y = 200, + } c __bpf_aligned; /* inline enum def with differing set of values */ +}; + +struct core_reloc_primitives___diff_func_proto { + void (*f)(int) __bpf_aligned; /* incompatible function prototype */ + void *d __bpf_aligned; + enum core_reloc_primitives_enum c __bpf_aligned; + int b; + char a; +}; + +struct core_reloc_primitives___diff_ptr_type { + const char * const d __bpf_aligned; /* different pointee type + modifiers */ + char a __bpf_aligned; + int b; + enum core_reloc_primitives_enum c; + int (*f)(const char *) __bpf_aligned; +}; + +struct core_reloc_primitives___err_non_enum { + char a[1]; + int b; + int c; /* int instead of enum */ + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; +}; + +struct core_reloc_primitives___err_non_int { + char a[1]; + int *b __bpf_aligned; /* ptr instead of int */ + enum core_reloc_primitives_enum c __bpf_aligned; + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; +}; + +struct core_reloc_primitives___err_non_ptr { + char a[1]; + int b; + enum core_reloc_primitives_enum c; + int d; /* int instead of ptr */ + int (*f)(const char *) __bpf_aligned; +}; + +/* + * MODS + */ +struct core_reloc_mods_output { + int a, b, c, d, e, f, g, h; +}; + +typedef const int int_t; +typedef const char *char_ptr_t __bpf_aligned; +typedef const int arr_t[7]; + +struct core_reloc_mods_substruct { + int x; + int y; +}; + +typedef struct { + int x; + int y; +} core_reloc_mods_substruct_t; + +struct core_reloc_mods { + int a; + int_t b; + char *c __bpf_aligned; + char_ptr_t d; + int e[3] __bpf_aligned; + arr_t f; + struct core_reloc_mods_substruct g; + core_reloc_mods_substruct_t h; +}; + +/* a/b, c/d, e/f, and g/h pairs are swapped */ +struct core_reloc_mods___mod_swap { + int b; + int_t a; + char *d __bpf_aligned; + char_ptr_t c; + int f[3] __bpf_aligned; + arr_t e; + struct { + int y; + int x; + } h; + core_reloc_mods_substruct_t g; +}; + +typedef int int1_t; +typedef int1_t int2_t; +typedef int2_t int3_t; + +typedef int arr1_t[5]; +typedef arr1_t arr2_t; +typedef arr2_t arr3_t; +typedef arr3_t arr4_t; + +typedef const char * const volatile fancy_char_ptr_t __bpf_aligned; + +typedef core_reloc_mods_substruct_t core_reloc_mods_substruct_tt; + +/* we need more typedefs */ +struct core_reloc_mods___typedefs { + core_reloc_mods_substruct_tt g; + core_reloc_mods_substruct_tt h; + arr4_t f; + arr4_t e; + fancy_char_ptr_t d; + fancy_char_ptr_t c; + int3_t b __bpf_aligned; + int3_t a; +}; + +/* + * PTR_AS_ARR + */ +struct core_reloc_ptr_as_arr { + int a; +}; + +struct core_reloc_ptr_as_arr___diff_sz { + int :32; /* padding */ + char __some_more_padding; + int a; +}; + +/* + * INTS + */ +struct core_reloc_ints { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +/* signed/unsigned types swap */ +struct core_reloc_ints___reverse_sign { + int8_t u8_field; + uint8_t s8_field; + int16_t u16_field; + uint16_t s16_field; + int32_t u32_field; + uint32_t s32_field; + int64_t u64_field; + uint64_t s64_field; +}; + +struct core_reloc_ints___bool { + bool u8_field; /* bool instead of uint8 */ + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +/* + * MISC + */ +struct core_reloc_misc_output { + int a, b, c; +}; + +struct core_reloc_misc___a { + int a1; + int a2; +}; + +struct core_reloc_misc___b { + int b1; + int b2; +}; + +/* this one extends core_reloc_misc_extensible struct from BPF prog */ +struct core_reloc_misc_extensible { + int a; + int b; + int c; + int d; +}; + +/* + * FIELD EXISTENCE + */ +struct core_reloc_existence_output { + int a_exists; + int a_value; + int b_exists; + int b_value; + int c_exists; + int c_value; + int arr_exists; + int arr_value; + int s_exists; + int s_value; +}; + +struct core_reloc_existence { + int a; + struct { + int b; + }; + int c; + int arr[1]; + struct { + int x; + } s; +}; + +struct core_reloc_existence___minimal { + int a; +}; + +struct core_reloc_existence___wrong_field_defs { + void *a; + int b[1]; + struct{ int x; } c; + int arr; + int s; +}; + +/* + * BITFIELDS + */ +/* bitfield read results, all as plain integers */ +struct core_reloc_bitfields_output { + int64_t ub1; + int64_t ub2; + int64_t ub7; + int64_t sb4; + int64_t sb20; + int64_t u32; + int64_t s32; +}; + +struct core_reloc_bitfields { + /* unsigned bitfields */ + uint8_t ub1: 1; + uint8_t ub2: 2; + uint32_t ub7: 7; + /* signed bitfields */ + int8_t sb4: 4; + int32_t sb20: 20; + /* non-bitfields */ + uint32_t u32; + int32_t s32; +}; + +/* different bit sizes (both up and down) */ +struct core_reloc_bitfields___bit_sz_change { + /* unsigned bitfields */ + uint16_t ub1: 3; /* 1 -> 3 */ + uint32_t ub2: 20; /* 2 -> 20 */ + uint8_t ub7: 1; /* 7 -> 1 */ + /* signed bitfields */ + int8_t sb4: 1; /* 4 -> 1 */ + int32_t sb20: 30; /* 20 -> 30 */ + /* non-bitfields */ + uint16_t u32; /* 32 -> 16 */ + int64_t s32 __bpf_aligned; /* 32 -> 64 */ +}; + +/* turn bitfield into non-bitfield and vice versa */ +struct core_reloc_bitfields___bitfield_vs_int { + uint64_t ub1; /* 3 -> 64 non-bitfield */ + uint8_t ub2; /* 20 -> 8 non-bitfield */ + int64_t ub7 __bpf_aligned; /* 7 -> 64 non-bitfield signed */ + int64_t sb4 __bpf_aligned; /* 4 -> 64 non-bitfield signed */ + uint64_t sb20 __bpf_aligned; /* 20 -> 16 non-bitfield unsigned */ + int32_t u32: 20; /* 32 non-bitfield -> 20 bitfield */ + uint64_t s32: 60 __bpf_aligned; /* 32 non-bitfield -> 60 bitfield */ +}; + +struct core_reloc_bitfields___just_big_enough { + uint64_t ub1: 4; + uint64_t ub2: 60; /* packed tightly */ + uint32_t ub7; + uint32_t sb4; + uint32_t sb20; + uint32_t u32; + uint32_t s32; +} __attribute__((packed)) ; + +struct core_reloc_bitfields___err_too_big_bitfield { + uint64_t ub1: 4; + uint64_t ub2: 61; /* packed tightly */ + uint32_t ub7; + uint32_t sb4; + uint32_t sb20; + uint32_t u32; + uint32_t s32; +} __attribute__((packed)) ; + +/* + * SIZE + */ +struct core_reloc_size_output { + int int_sz; + int int_off; + int struct_sz; + int struct_off; + int union_sz; + int union_off; + int arr_sz; + int arr_off; + int arr_elem_sz; + int arr_elem_off; + int ptr_sz; + int ptr_off; + int enum_sz; + int enum_off; + int float_sz; + int float_off; +}; + +struct core_reloc_size { + int int_field; + struct { int x; } struct_field; + union { int x; } union_field; + int arr_field[4]; + void *ptr_field; + enum { VALUE = 123 } enum_field; + float float_field; +}; + +struct core_reloc_size___diff_sz { + uint64_t int_field; + struct { int x; int y; int z; } struct_field; + union { int x; char bla[123]; } union_field; + char arr_field[10]; + void *ptr_field; + enum { OTHER_VALUE = 0xFFFFFFFFFFFFFFFF } enum_field; + double float_field; +}; + +struct core_reloc_size___diff_offs { + float float_field; + enum { YET_OTHER_VALUE = 123 } enum_field; + void *ptr_field; + int arr_field[4]; + union { int x; } union_field; + struct { int x; } struct_field; + int int_field; +}; + +/* Error case of two candidates with the fields (int_field) at the same + * offset, but with differing final relocation values: size 4 vs size 1 + */ +struct core_reloc_size___err_ambiguous1 { + /* int at offset 0 */ + int int_field; + + struct { int x; } struct_field; + union { int x; } union_field; + int arr_field[4]; + void *ptr_field; + enum { VALUE___1 = 123 } enum_field; + float float_field; +}; + +struct core_reloc_size___err_ambiguous2 { + /* char at offset 0 */ + char int_field; + + struct { int x; } struct_field; + union { int x; } union_field; + int arr_field[4]; + void *ptr_field; + enum { VALUE___2 = 123 } enum_field; + float float_field; +}; + +/* + * TYPE EXISTENCE, MATCH & SIZE + */ +struct core_reloc_type_based_output { + bool struct_exists; + bool complex_struct_exists; + bool union_exists; + bool enum_exists; + bool typedef_named_struct_exists; + bool typedef_anon_struct_exists; + bool typedef_struct_ptr_exists; + bool typedef_int_exists; + bool typedef_enum_exists; + bool typedef_void_ptr_exists; + bool typedef_restrict_ptr_exists; + bool typedef_func_proto_exists; + bool typedef_arr_exists; + + bool struct_matches; + bool complex_struct_matches; + bool union_matches; + bool enum_matches; + bool typedef_named_struct_matches; + bool typedef_anon_struct_matches; + bool typedef_struct_ptr_matches; + bool typedef_int_matches; + bool typedef_enum_matches; + bool typedef_void_ptr_matches; + bool typedef_restrict_ptr_matches; + bool typedef_func_proto_matches; + bool typedef_arr_matches; + + int struct_sz; + int union_sz; + int enum_sz; + int typedef_named_struct_sz; + int typedef_anon_struct_sz; + int typedef_struct_ptr_sz; + int typedef_int_sz; + int typedef_enum_sz; + int typedef_void_ptr_sz; + int typedef_func_proto_sz; + int typedef_arr_sz; +}; + +struct a_struct { + int x; +}; + +struct a_complex_struct { + union { + struct a_struct * restrict a; + void *b; + } x; + volatile long y; +}; + +union a_union { + int y; + int z; +}; + +typedef struct a_struct named_struct_typedef; + +typedef struct { int x, y, z; } anon_struct_typedef; + +typedef struct { + int a, b, c; +} *struct_ptr_typedef; + +enum an_enum { + AN_ENUM_VAL1 = 1, + AN_ENUM_VAL2 = 2, + AN_ENUM_VAL3 = 3, +}; + +typedef int int_typedef; + +typedef enum { TYPEDEF_ENUM_VAL1, TYPEDEF_ENUM_VAL2 } enum_typedef; + +typedef void *void_ptr_typedef; +typedef int *restrict restrict_ptr_typedef; + +typedef int (*func_proto_typedef)(long); + +typedef char arr_typedef[20]; + +struct core_reloc_type_based { + struct a_struct f1; + struct a_complex_struct f2; + union a_union f3; + enum an_enum f4; + named_struct_typedef f5; + anon_struct_typedef f6; + struct_ptr_typedef f7; + int_typedef f8; + enum_typedef f9; + void_ptr_typedef f10; + restrict_ptr_typedef f11; + func_proto_typedef f12; + arr_typedef f13; +}; + +/* no types in target */ +struct core_reloc_type_based___all_missing { +}; + +/* different member orders, enum variant values, signedness, etc */ +struct a_struct___diff { + int x; + int a; +}; + +struct a_struct___forward; + +struct a_complex_struct___diff { + union { + struct a_struct___forward *a; + void *b; + } x; + volatile long y; +}; + +union a_union___diff { + int z; + int y; +}; + +typedef struct a_struct___diff named_struct_typedef___diff; + +typedef struct { int z, x, y; } anon_struct_typedef___diff; + +typedef struct { + int c; + int b; + int a; +} *struct_ptr_typedef___diff; + +enum an_enum___diff { + AN_ENUM_VAL2___diff = 0, + AN_ENUM_VAL1___diff = 42, + AN_ENUM_VAL3___diff = 1, +}; + +typedef unsigned int int_typedef___diff; + +typedef enum { TYPEDEF_ENUM_VAL2___diff, TYPEDEF_ENUM_VAL1___diff = 50 } enum_typedef___diff; + +typedef const void *void_ptr_typedef___diff; + +typedef int_typedef___diff (*func_proto_typedef___diff)(long); + +typedef char arr_typedef___diff[3]; + +struct core_reloc_type_based___diff { + struct a_struct___diff f1; + struct a_complex_struct___diff f2; + union a_union___diff f3; + enum an_enum___diff f4; + named_struct_typedef___diff f5; + anon_struct_typedef___diff f6; + struct_ptr_typedef___diff f7; + int_typedef___diff f8; + enum_typedef___diff f9; + void_ptr_typedef___diff f10; + func_proto_typedef___diff f11; + arr_typedef___diff f12; +}; + +/* different type sizes, extra modifiers, anon vs named enums, etc */ +struct a_struct___diff_sz { + long x; + int y; + char z; +}; + +union a_union___diff_sz { + char yy; + char zz; +}; + +typedef struct a_struct___diff_sz named_struct_typedef___diff_sz; + +typedef struct { long xx, yy, zzz; } anon_struct_typedef___diff_sz; + +typedef struct { + char aa[1], bb[2], cc[3]; +} *struct_ptr_typedef___diff_sz; + +enum an_enum___diff_sz { + AN_ENUM_VAL1___diff_sz = 0x123412341234, + AN_ENUM_VAL2___diff_sz = 2, +}; + +typedef unsigned long int_typedef___diff_sz; + +typedef enum an_enum___diff_sz enum_typedef___diff_sz; + +typedef const void * const void_ptr_typedef___diff_sz; + +typedef int_typedef___diff_sz (*func_proto_typedef___diff_sz)(char); + +typedef int arr_typedef___diff_sz[2]; + +struct core_reloc_type_based___diff_sz { + struct a_struct___diff_sz f1; + union a_union___diff_sz f2; + enum an_enum___diff_sz f3; + named_struct_typedef___diff_sz f4; + anon_struct_typedef___diff_sz f5; + struct_ptr_typedef___diff_sz f6; + int_typedef___diff_sz f7; + enum_typedef___diff_sz f8; + void_ptr_typedef___diff_sz f9; + func_proto_typedef___diff_sz f10; + arr_typedef___diff_sz f11; +}; + +/* incompatibilities between target and local types */ +union a_struct___incompat { /* union instead of struct */ + int x; +}; + +struct a_union___incompat { /* struct instead of union */ + int y; + int z; +}; + +/* typedef to union, not to struct */ +typedef union a_struct___incompat named_struct_typedef___incompat; + +/* typedef to void pointer, instead of struct */ +typedef void *anon_struct_typedef___incompat; + +/* extra pointer indirection */ +typedef struct { + int a, b, c; +} **struct_ptr_typedef___incompat; + +/* typedef of a struct with int, instead of int */ +typedef struct { int x; } int_typedef___incompat; + +/* typedef to func_proto, instead of enum */ +typedef int (*enum_typedef___incompat)(void); + +/* pointer to char instead of void */ +typedef char *void_ptr_typedef___incompat; + +/* void return type instead of int */ +typedef void (*func_proto_typedef___incompat)(long); + +/* multi-dimensional array instead of a single-dimensional */ +typedef int arr_typedef___incompat[20][2]; + +struct core_reloc_type_based___incompat { + union a_struct___incompat f1; + struct a_union___incompat f2; + /* the only valid one is enum, to check that something still succeeds */ + enum an_enum f3; + named_struct_typedef___incompat f4; + anon_struct_typedef___incompat f5; + struct_ptr_typedef___incompat f6; + int_typedef___incompat f7; + enum_typedef___incompat f8; + void_ptr_typedef___incompat f9; + func_proto_typedef___incompat f10; + arr_typedef___incompat f11; +}; + +/* func_proto with incompatible signature */ +typedef void (*func_proto_typedef___fn_wrong_ret1)(long); +typedef int * (*func_proto_typedef___fn_wrong_ret2)(long); +typedef struct { int x; } int_struct_typedef; +typedef int_struct_typedef (*func_proto_typedef___fn_wrong_ret3)(long); +typedef int (*func_proto_typedef___fn_wrong_arg)(void *); +typedef int (*func_proto_typedef___fn_wrong_arg_cnt1)(long, long); +typedef int (*func_proto_typedef___fn_wrong_arg_cnt2)(void); + +struct core_reloc_type_based___fn_wrong_args { + /* one valid type to make sure relos still work */ + struct a_struct f1; + func_proto_typedef___fn_wrong_ret1 f2; + func_proto_typedef___fn_wrong_ret2 f3; + func_proto_typedef___fn_wrong_ret3 f4; + func_proto_typedef___fn_wrong_arg f5; + func_proto_typedef___fn_wrong_arg_cnt1 f6; + func_proto_typedef___fn_wrong_arg_cnt2 f7; +}; + +/* + * TYPE ID MAPPING (LOCAL AND TARGET) + */ +struct core_reloc_type_id_output { + int local_anon_struct; + int local_anon_union; + int local_anon_enum; + int local_anon_func_proto_ptr; + int local_anon_void_ptr; + int local_anon_arr; + + int local_struct; + int local_union; + int local_enum; + int local_int; + int local_struct_typedef; + int local_func_proto_typedef; + int local_arr_typedef; + + int targ_struct; + int targ_union; + int targ_enum; + int targ_int; + int targ_struct_typedef; + int targ_func_proto_typedef; + int targ_arr_typedef; +}; + +struct core_reloc_type_id { + struct a_struct f1; + union a_union f2; + enum an_enum f3; + named_struct_typedef f4; + func_proto_typedef f5; + arr_typedef f6; +}; + +struct core_reloc_type_id___missing_targets { + /* nothing */ +}; + +/* + * ENUMERATOR VALUE EXISTENCE AND VALUE RELOCATION + */ +struct core_reloc_enumval_output { + bool named_val1_exists; + bool named_val2_exists; + bool named_val3_exists; + bool anon_val1_exists; + bool anon_val2_exists; + bool anon_val3_exists; + + int named_val1; + int named_val2; + int anon_val1; + int anon_val2; +}; + +struct core_reloc_enum64val_output { + bool unsigned_val1_exists; + bool unsigned_val2_exists; + bool unsigned_val3_exists; + bool signed_val1_exists; + bool signed_val2_exists; + bool signed_val3_exists; + + long unsigned_val1; + long unsigned_val2; + long signed_val1; + long signed_val2; +}; + +enum named_enum { + NAMED_ENUM_VAL1 = 1, + NAMED_ENUM_VAL2 = 2, + NAMED_ENUM_VAL3 = 3, +}; + +typedef enum { + ANON_ENUM_VAL1 = 0x10, + ANON_ENUM_VAL2 = 0x20, + ANON_ENUM_VAL3 = 0x30, +} anon_enum; + +struct core_reloc_enumval { + enum named_enum f1; + anon_enum f2; +}; + +enum named_unsigned_enum64 { + UNSIGNED_ENUM64_VAL1 = 0x1ffffffffULL, + UNSIGNED_ENUM64_VAL2 = 0x2, + UNSIGNED_ENUM64_VAL3 = 0x3ffffffffULL, +}; + +enum named_signed_enum64 { + SIGNED_ENUM64_VAL1 = 0x1ffffffffLL, + SIGNED_ENUM64_VAL2 = -2, + SIGNED_ENUM64_VAL3 = 0x3ffffffffLL, +}; + +struct core_reloc_enum64val { + enum named_unsigned_enum64 f1; + enum named_signed_enum64 f2; +}; + +/* differing enumerator values */ +enum named_enum___diff { + NAMED_ENUM_VAL1___diff = 101, + NAMED_ENUM_VAL2___diff = 202, + NAMED_ENUM_VAL3___diff = 303, +}; + +typedef enum { + ANON_ENUM_VAL1___diff = 0x11, + ANON_ENUM_VAL2___diff = 0x22, + ANON_ENUM_VAL3___diff = 0x33, +} anon_enum___diff; + +struct core_reloc_enumval___diff { + enum named_enum___diff f1; + anon_enum___diff f2; +}; + +enum named_unsigned_enum64___diff { + UNSIGNED_ENUM64_VAL1___diff = 0x101ffffffffULL, + UNSIGNED_ENUM64_VAL2___diff = 0x202ffffffffULL, + UNSIGNED_ENUM64_VAL3___diff = 0x303ffffffffULL, +}; + +enum named_signed_enum64___diff { + SIGNED_ENUM64_VAL1___diff = -101, + SIGNED_ENUM64_VAL2___diff = -202, + SIGNED_ENUM64_VAL3___diff = -303, +}; + +struct core_reloc_enum64val___diff { + enum named_unsigned_enum64___diff f1; + enum named_signed_enum64___diff f2; +}; + +/* missing (optional) third enum value */ +enum named_enum___val3_missing { + NAMED_ENUM_VAL1___val3_missing = 111, + NAMED_ENUM_VAL2___val3_missing = 222, +}; + +typedef enum { + ANON_ENUM_VAL1___val3_missing = 0x111, + ANON_ENUM_VAL2___val3_missing = 0x222, +} anon_enum___val3_missing; + +struct core_reloc_enumval___val3_missing { + enum named_enum___val3_missing f1; + anon_enum___val3_missing f2; +}; + +enum named_unsigned_enum64___val3_missing { + UNSIGNED_ENUM64_VAL1___val3_missing = 0x111ffffffffULL, + UNSIGNED_ENUM64_VAL2___val3_missing = 0x222, +}; + +enum named_signed_enum64___val3_missing { + SIGNED_ENUM64_VAL1___val3_missing = 0x111ffffffffLL, + SIGNED_ENUM64_VAL2___val3_missing = -222, +}; + +struct core_reloc_enum64val___val3_missing { + enum named_unsigned_enum64___val3_missing f1; + enum named_signed_enum64___val3_missing f2; +}; + +/* missing (mandatory) second enum value, should fail */ +enum named_enum___err_missing { + NAMED_ENUM_VAL1___err_missing = 1, + NAMED_ENUM_VAL3___err_missing = 3, +}; + +typedef enum { + ANON_ENUM_VAL1___err_missing = 0x111, + ANON_ENUM_VAL3___err_missing = 0x222, +} anon_enum___err_missing; + +struct core_reloc_enumval___err_missing { + enum named_enum___err_missing f1; + anon_enum___err_missing f2; +}; + +enum named_unsigned_enum64___err_missing { + UNSIGNED_ENUM64_VAL1___err_missing = 0x1ffffffffULL, + UNSIGNED_ENUM64_VAL3___err_missing = 0x3ffffffffULL, +}; + +enum named_signed_enum64___err_missing { + SIGNED_ENUM64_VAL1___err_missing = 0x1ffffffffLL, + SIGNED_ENUM64_VAL3___err_missing = -3, +}; + +struct core_reloc_enum64val___err_missing { + enum named_unsigned_enum64___err_missing f1; + enum named_signed_enum64___err_missing f2; +}; diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h new file mode 100644 index 0000000000..b15c588ace --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cpumask_common.h @@ -0,0 +1,121 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#ifndef _CPUMASK_COMMON_H +#define _CPUMASK_COMMON_H + +#include "errno.h" +#include <stdbool.h> + +int err; + +#define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8))) +private(MASK) static struct bpf_cpumask __kptr * global_mask; + +struct __cpumask_map_value { + struct bpf_cpumask __kptr * cpumask; +}; + +struct array_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct __cpumask_map_value); + __uint(max_entries, 1); +} __cpumask_map SEC(".maps"); + +struct bpf_cpumask *bpf_cpumask_create(void) __ksym; +void bpf_cpumask_release(struct bpf_cpumask *cpumask) __ksym; +struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) __ksym; +u32 bpf_cpumask_first(const struct cpumask *cpumask) __ksym; +u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym; +u32 bpf_cpumask_first_and(const struct cpumask *src1, + const struct cpumask *src2) __ksym; +void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; +void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; +bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) __ksym; +bool bpf_cpumask_test_and_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; +bool bpf_cpumask_test_and_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; +void bpf_cpumask_setall(struct bpf_cpumask *cpumask) __ksym; +void bpf_cpumask_clear(struct bpf_cpumask *cpumask) __ksym; +bool bpf_cpumask_and(struct bpf_cpumask *cpumask, + const struct cpumask *src1, + const struct cpumask *src2) __ksym; +void bpf_cpumask_or(struct bpf_cpumask *cpumask, + const struct cpumask *src1, + const struct cpumask *src2) __ksym; +void bpf_cpumask_xor(struct bpf_cpumask *cpumask, + const struct cpumask *src1, + const struct cpumask *src2) __ksym; +bool bpf_cpumask_equal(const struct cpumask *src1, const struct cpumask *src2) __ksym; +bool bpf_cpumask_intersects(const struct cpumask *src1, const struct cpumask *src2) __ksym; +bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) __ksym; +bool bpf_cpumask_empty(const struct cpumask *cpumask) __ksym; +bool bpf_cpumask_full(const struct cpumask *cpumask) __ksym; +void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym; +u32 bpf_cpumask_any_distribute(const struct cpumask *src) __ksym; +u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, const struct cpumask *src2) __ksym; + +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +static inline const struct cpumask *cast(struct bpf_cpumask *cpumask) +{ + return (const struct cpumask *)cpumask; +} + +static inline struct bpf_cpumask *create_cpumask(void) +{ + struct bpf_cpumask *cpumask; + + cpumask = bpf_cpumask_create(); + if (!cpumask) { + err = 1; + return NULL; + } + + if (!bpf_cpumask_empty(cast(cpumask))) { + err = 2; + bpf_cpumask_release(cpumask); + return NULL; + } + + return cpumask; +} + +static inline struct __cpumask_map_value *cpumask_map_value_lookup(void) +{ + u32 key = 0; + + return bpf_map_lookup_elem(&__cpumask_map, &key); +} + +static inline int cpumask_map_insert(struct bpf_cpumask *mask) +{ + struct __cpumask_map_value local, *v; + long status; + struct bpf_cpumask *old; + u32 key = 0; + + local.cpumask = NULL; + status = bpf_map_update_elem(&__cpumask_map, &key, &local, 0); + if (status) { + bpf_cpumask_release(mask); + return status; + } + + v = bpf_map_lookup_elem(&__cpumask_map, &key); + if (!v) { + bpf_cpumask_release(mask); + return -ENOENT; + } + + old = bpf_kptr_xchg(&v->cpumask, mask); + if (old) { + bpf_cpumask_release(old); + return -EEXIST; + } + + return 0; +} + +#endif /* _CPUMASK_COMMON_H */ diff --git a/tools/testing/selftests/bpf/progs/cpumask_failure.c b/tools/testing/selftests/bpf/progs/cpumask_failure.c new file mode 100644 index 0000000000..a9bf6ea336 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cpumask_failure.c @@ -0,0 +1,192 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#include "cpumask_common.h" + +char _license[] SEC("license") = "GPL"; + +/* Prototype for all of the program trace events below: + * + * TRACE_EVENT(task_newtask, + * TP_PROTO(struct task_struct *p, u64 clone_flags) + */ + +SEC("tp_btf/task_newtask") +__failure __msg("Unreleased reference") +int BPF_PROG(test_alloc_no_release, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + cpumask = create_cpumask(); + __sink(cpumask); + + /* cpumask is never released. */ + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("NULL pointer passed to trusted arg0") +int BPF_PROG(test_alloc_double_release, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + cpumask = create_cpumask(); + + /* cpumask is released twice. */ + bpf_cpumask_release(cpumask); + bpf_cpumask_release(cpumask); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("must be referenced") +int BPF_PROG(test_acquire_wrong_cpumask, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + /* Can't acquire a non-struct bpf_cpumask. */ + cpumask = bpf_cpumask_acquire((struct bpf_cpumask *)task->cpus_ptr); + __sink(cpumask); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("bpf_cpumask_set_cpu args#1 expected pointer to STRUCT bpf_cpumask") +int BPF_PROG(test_mutate_cpumask, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + /* Can't set the CPU of a non-struct bpf_cpumask. */ + bpf_cpumask_set_cpu(0, (struct bpf_cpumask *)task->cpus_ptr); + __sink(cpumask); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("Unreleased reference") +int BPF_PROG(test_insert_remove_no_release, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + struct __cpumask_map_value *v; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + if (cpumask_map_insert(cpumask)) + return 0; + + v = cpumask_map_value_lookup(); + if (!v) + return 0; + + cpumask = bpf_kptr_xchg(&v->cpumask, NULL); + + /* cpumask is never released. */ + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("NULL pointer passed to trusted arg0") +int BPF_PROG(test_cpumask_null, struct task_struct *task, u64 clone_flags) +{ + /* NULL passed to KF_TRUSTED_ARGS kfunc. */ + bpf_cpumask_empty(NULL); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("R2 must be a rcu pointer") +int BPF_PROG(test_global_mask_out_of_rcu, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *local, *prev; + + local = create_cpumask(); + if (!local) + return 0; + + prev = bpf_kptr_xchg(&global_mask, local); + if (prev) { + bpf_cpumask_release(prev); + err = 3; + return 0; + } + + bpf_rcu_read_lock(); + local = global_mask; + if (!local) { + err = 4; + bpf_rcu_read_unlock(); + return 0; + } + + bpf_rcu_read_unlock(); + + /* RCU region is exited before calling KF_RCU kfunc. */ + + bpf_cpumask_test_cpu(0, (const struct cpumask *)local); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("NULL pointer passed to trusted arg1") +int BPF_PROG(test_global_mask_no_null_check, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *local, *prev; + + local = create_cpumask(); + if (!local) + return 0; + + prev = bpf_kptr_xchg(&global_mask, local); + if (prev) { + bpf_cpumask_release(prev); + err = 3; + return 0; + } + + bpf_rcu_read_lock(); + local = global_mask; + + /* No NULL check is performed on global cpumask kptr. */ + bpf_cpumask_test_cpu(0, (const struct cpumask *)local); + + bpf_rcu_read_unlock(); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("Possibly NULL pointer passed to helper arg2") +int BPF_PROG(test_global_mask_rcu_no_null_check, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *prev, *curr; + + curr = bpf_cpumask_create(); + if (!curr) + return 0; + + prev = bpf_kptr_xchg(&global_mask, curr); + if (prev) + bpf_cpumask_release(prev); + + bpf_rcu_read_lock(); + curr = global_mask; + /* PTR_TO_BTF_ID | PTR_MAYBE_NULL | MEM_RCU passed to bpf_kptr_xchg() */ + prev = bpf_kptr_xchg(&global_mask, curr); + bpf_rcu_read_unlock(); + if (prev) + bpf_cpumask_release(prev); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c new file mode 100644 index 0000000000..674a63424d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cpumask_success.c @@ -0,0 +1,484 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" +#include "cpumask_common.h" + +char _license[] SEC("license") = "GPL"; + +int pid, nr_cpus; + +static bool is_test_task(void) +{ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + + return pid == cur_pid; +} + +static bool create_cpumask_set(struct bpf_cpumask **out1, + struct bpf_cpumask **out2, + struct bpf_cpumask **out3, + struct bpf_cpumask **out4) +{ + struct bpf_cpumask *mask1, *mask2, *mask3, *mask4; + + mask1 = create_cpumask(); + if (!mask1) + return false; + + mask2 = create_cpumask(); + if (!mask2) { + bpf_cpumask_release(mask1); + err = 3; + return false; + } + + mask3 = create_cpumask(); + if (!mask3) { + bpf_cpumask_release(mask1); + bpf_cpumask_release(mask2); + err = 4; + return false; + } + + mask4 = create_cpumask(); + if (!mask4) { + bpf_cpumask_release(mask1); + bpf_cpumask_release(mask2); + bpf_cpumask_release(mask3); + err = 5; + return false; + } + + *out1 = mask1; + *out2 = mask2; + *out3 = mask3; + *out4 = mask4; + + return true; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_alloc_free_cpumask, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + if (!is_test_task()) + return 0; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + bpf_cpumask_release(cpumask); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_set_clear_cpu, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + if (!is_test_task()) + return 0; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + bpf_cpumask_set_cpu(0, cpumask); + if (!bpf_cpumask_test_cpu(0, cast(cpumask))) { + err = 3; + goto release_exit; + } + + bpf_cpumask_clear_cpu(0, cpumask); + if (bpf_cpumask_test_cpu(0, cast(cpumask))) { + err = 4; + goto release_exit; + } + +release_exit: + bpf_cpumask_release(cpumask); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_setall_clear_cpu, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + if (!is_test_task()) + return 0; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + bpf_cpumask_setall(cpumask); + if (!bpf_cpumask_full(cast(cpumask))) { + err = 3; + goto release_exit; + } + + bpf_cpumask_clear(cpumask); + if (!bpf_cpumask_empty(cast(cpumask))) { + err = 4; + goto release_exit; + } + +release_exit: + bpf_cpumask_release(cpumask); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_first_firstzero_cpu, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + if (!is_test_task()) + return 0; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + if (bpf_cpumask_first(cast(cpumask)) < nr_cpus) { + err = 3; + goto release_exit; + } + + if (bpf_cpumask_first_zero(cast(cpumask)) != 0) { + bpf_printk("first zero: %d", bpf_cpumask_first_zero(cast(cpumask))); + err = 4; + goto release_exit; + } + + bpf_cpumask_set_cpu(0, cpumask); + if (bpf_cpumask_first(cast(cpumask)) != 0) { + err = 5; + goto release_exit; + } + + if (bpf_cpumask_first_zero(cast(cpumask)) != 1) { + err = 6; + goto release_exit; + } + +release_exit: + bpf_cpumask_release(cpumask); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_firstand_nocpu, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *mask1, *mask2; + u32 first; + + if (!is_test_task()) + return 0; + + mask1 = create_cpumask(); + if (!mask1) + return 0; + + mask2 = create_cpumask(); + if (!mask2) + goto release_exit; + + bpf_cpumask_set_cpu(0, mask1); + bpf_cpumask_set_cpu(1, mask2); + + first = bpf_cpumask_first_and(cast(mask1), cast(mask2)); + if (first <= 1) + err = 3; + +release_exit: + if (mask1) + bpf_cpumask_release(mask1); + if (mask2) + bpf_cpumask_release(mask2); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_test_and_set_clear, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + if (!is_test_task()) + return 0; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + if (bpf_cpumask_test_and_set_cpu(0, cpumask)) { + err = 3; + goto release_exit; + } + + if (!bpf_cpumask_test_and_set_cpu(0, cpumask)) { + err = 4; + goto release_exit; + } + + if (!bpf_cpumask_test_and_clear_cpu(0, cpumask)) { + err = 5; + goto release_exit; + } + +release_exit: + bpf_cpumask_release(cpumask); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_and_or_xor, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *mask1, *mask2, *dst1, *dst2; + + if (!is_test_task()) + return 0; + + if (!create_cpumask_set(&mask1, &mask2, &dst1, &dst2)) + return 0; + + bpf_cpumask_set_cpu(0, mask1); + bpf_cpumask_set_cpu(1, mask2); + + if (bpf_cpumask_and(dst1, cast(mask1), cast(mask2))) { + err = 6; + goto release_exit; + } + if (!bpf_cpumask_empty(cast(dst1))) { + err = 7; + goto release_exit; + } + + bpf_cpumask_or(dst1, cast(mask1), cast(mask2)); + if (!bpf_cpumask_test_cpu(0, cast(dst1))) { + err = 8; + goto release_exit; + } + if (!bpf_cpumask_test_cpu(1, cast(dst1))) { + err = 9; + goto release_exit; + } + + bpf_cpumask_xor(dst2, cast(mask1), cast(mask2)); + if (!bpf_cpumask_equal(cast(dst1), cast(dst2))) { + err = 10; + goto release_exit; + } + +release_exit: + bpf_cpumask_release(mask1); + bpf_cpumask_release(mask2); + bpf_cpumask_release(dst1); + bpf_cpumask_release(dst2); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_intersects_subset, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *mask1, *mask2, *dst1, *dst2; + + if (!is_test_task()) + return 0; + + if (!create_cpumask_set(&mask1, &mask2, &dst1, &dst2)) + return 0; + + bpf_cpumask_set_cpu(0, mask1); + bpf_cpumask_set_cpu(1, mask2); + if (bpf_cpumask_intersects(cast(mask1), cast(mask2))) { + err = 6; + goto release_exit; + } + + bpf_cpumask_or(dst1, cast(mask1), cast(mask2)); + if (!bpf_cpumask_subset(cast(mask1), cast(dst1))) { + err = 7; + goto release_exit; + } + + if (!bpf_cpumask_subset(cast(mask2), cast(dst1))) { + err = 8; + goto release_exit; + } + + if (bpf_cpumask_subset(cast(dst1), cast(mask1))) { + err = 9; + goto release_exit; + } + +release_exit: + bpf_cpumask_release(mask1); + bpf_cpumask_release(mask2); + bpf_cpumask_release(dst1); + bpf_cpumask_release(dst2); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_copy_any_anyand, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *mask1, *mask2, *dst1, *dst2; + u32 cpu; + + if (!is_test_task()) + return 0; + + if (!create_cpumask_set(&mask1, &mask2, &dst1, &dst2)) + return 0; + + bpf_cpumask_set_cpu(0, mask1); + bpf_cpumask_set_cpu(1, mask2); + bpf_cpumask_or(dst1, cast(mask1), cast(mask2)); + + cpu = bpf_cpumask_any_distribute(cast(mask1)); + if (cpu != 0) { + err = 6; + goto release_exit; + } + + cpu = bpf_cpumask_any_distribute(cast(dst2)); + if (cpu < nr_cpus) { + err = 7; + goto release_exit; + } + + bpf_cpumask_copy(dst2, cast(dst1)); + if (!bpf_cpumask_equal(cast(dst1), cast(dst2))) { + err = 8; + goto release_exit; + } + + cpu = bpf_cpumask_any_distribute(cast(dst2)); + if (cpu > 1) { + err = 9; + goto release_exit; + } + + cpu = bpf_cpumask_any_and_distribute(cast(mask1), cast(mask2)); + if (cpu < nr_cpus) { + err = 10; + goto release_exit; + } + +release_exit: + bpf_cpumask_release(mask1); + bpf_cpumask_release(mask2); + bpf_cpumask_release(dst1); + bpf_cpumask_release(dst2); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_insert_leave, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + if (cpumask_map_insert(cpumask)) + err = 3; + + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_insert_remove_release, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + struct __cpumask_map_value *v; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + if (cpumask_map_insert(cpumask)) { + err = 3; + return 0; + } + + v = cpumask_map_value_lookup(); + if (!v) { + err = 4; + return 0; + } + + cpumask = bpf_kptr_xchg(&v->cpumask, NULL); + if (cpumask) + bpf_cpumask_release(cpumask); + else + err = 5; + + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_global_mask_rcu, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *local, *prev; + + if (!is_test_task()) + return 0; + + local = create_cpumask(); + if (!local) + return 0; + + prev = bpf_kptr_xchg(&global_mask, local); + if (prev) { + bpf_cpumask_release(prev); + err = 3; + return 0; + } + + bpf_rcu_read_lock(); + local = global_mask; + if (!local) { + err = 4; + bpf_rcu_read_unlock(); + return 0; + } + + bpf_cpumask_test_cpu(0, (const struct cpumask *)local); + bpf_rcu_read_unlock(); + + return 0; +} + +SEC("tp_btf/task_newtask") +__success +int BPF_PROG(test_refcount_null_tracking, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *mask1, *mask2; + + mask1 = bpf_cpumask_create(); + mask2 = bpf_cpumask_create(); + + if (!mask1 || !mask2) + goto free_masks_return; + + bpf_cpumask_test_cpu(0, (const struct cpumask *)mask1); + bpf_cpumask_test_cpu(0, (const struct cpumask *)mask2); + +free_masks_return: + if (mask1) + bpf_cpumask_release(mask1); + if (mask2) + bpf_cpumask_release(mask2); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/decap_sanity.c b/tools/testing/selftests/bpf/progs/decap_sanity.c new file mode 100644 index 0000000000..bd3c657c58 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/decap_sanity.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define UDP_TEST_PORT 7777 + +void *bpf_cast_to_kern_ctx(void *) __ksym; +bool init_csum_partial = false; +bool final_csum_none = false; +bool broken_csum_start = false; + +static unsigned int skb_headlen(const struct sk_buff *skb) +{ + return skb->len - skb->data_len; +} + +static unsigned int skb_headroom(const struct sk_buff *skb) +{ + return skb->data - skb->head; +} + +static int skb_checksum_start_offset(const struct sk_buff *skb) +{ + return skb->csum_start - skb_headroom(skb); +} + +SEC("tc") +int decap_sanity(struct __sk_buff *skb) +{ + struct sk_buff *kskb; + struct ipv6hdr ip6h; + struct udphdr udph; + int err; + + if (skb->protocol != __bpf_constant_htons(ETH_P_IPV6)) + return TC_ACT_SHOT; + + if (bpf_skb_load_bytes(skb, ETH_HLEN, &ip6h, sizeof(ip6h))) + return TC_ACT_SHOT; + + if (ip6h.nexthdr != IPPROTO_UDP) + return TC_ACT_SHOT; + + if (bpf_skb_load_bytes(skb, ETH_HLEN + sizeof(ip6h), &udph, sizeof(udph))) + return TC_ACT_SHOT; + + if (udph.dest != __bpf_constant_htons(UDP_TEST_PORT)) + return TC_ACT_SHOT; + + kskb = bpf_cast_to_kern_ctx(skb); + init_csum_partial = (kskb->ip_summed == CHECKSUM_PARTIAL); + err = bpf_skb_adjust_room(skb, -(s32)(ETH_HLEN + sizeof(ip6h) + sizeof(udph)), + 1, BPF_F_ADJ_ROOM_FIXED_GSO); + if (err) + return TC_ACT_SHOT; + final_csum_none = (kskb->ip_summed == CHECKSUM_NONE); + if (kskb->ip_summed == CHECKSUM_PARTIAL && + (unsigned int)skb_checksum_start_offset(kskb) >= skb_headlen(kskb)) + broken_csum_start = true; + + return TC_ACT_SHOT; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/dev_cgroup.c b/tools/testing/selftests/bpf/progs/dev_cgroup.c new file mode 100644 index 0000000000..79b54a4fa2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/dev_cgroup.c @@ -0,0 +1,59 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ + +#include <linux/bpf.h> +#include <linux/version.h> +#include <bpf/bpf_helpers.h> + +SEC("cgroup/dev") +int bpf_prog1(struct bpf_cgroup_dev_ctx *ctx) +{ + short type = ctx->access_type & 0xFFFF; +#ifdef DEBUG + short access = ctx->access_type >> 16; + char fmt[] = " %d:%d \n"; + + switch (type) { + case BPF_DEVCG_DEV_BLOCK: + fmt[0] = 'b'; + break; + case BPF_DEVCG_DEV_CHAR: + fmt[0] = 'c'; + break; + default: + fmt[0] = '?'; + break; + } + + if (access & BPF_DEVCG_ACC_READ) + fmt[8] = 'r'; + + if (access & BPF_DEVCG_ACC_WRITE) + fmt[9] = 'w'; + + if (access & BPF_DEVCG_ACC_MKNOD) + fmt[10] = 'm'; + + bpf_trace_printk(fmt, sizeof(fmt), ctx->major, ctx->minor); +#endif + + /* Allow access to /dev/zero and /dev/random. + * Forbid everything else. + */ + if (ctx->major != 1 || type != BPF_DEVCG_DEV_CHAR) + return 0; + + switch (ctx->minor) { + case 5: /* 1:5 /dev/zero */ + case 9: /* 1:9 /dev/urandom */ + return 1; + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/dummy_st_ops_fail.c b/tools/testing/selftests/bpf/progs/dummy_st_ops_fail.c new file mode 100644 index 0000000000..0bf969a0b5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/dummy_st_ops_fail.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +SEC("struct_ops.s/test_2") +__failure __msg("attach to unsupported member test_2 of struct bpf_dummy_ops") +int BPF_PROG(test_unsupported_field_sleepable, + struct bpf_dummy_ops_state *state, int a1, unsigned short a2, + char a3, unsigned long a4) +{ + /* Tries to mark an unsleepable field in struct bpf_dummy_ops as sleepable. */ + return 0; +} + +SEC(".struct_ops") +struct bpf_dummy_ops dummy_1 = { + .test_1 = NULL, + .test_2 = (void *)test_unsupported_field_sleepable, + .test_sleepable = (void *)NULL, +}; diff --git a/tools/testing/selftests/bpf/progs/dummy_st_ops_success.c b/tools/testing/selftests/bpf/progs/dummy_st_ops_success.c new file mode 100644 index 0000000000..1efa746c25 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/dummy_st_ops_success.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2021. Huawei Technologies Co., Ltd */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +SEC("struct_ops/test_1") +int BPF_PROG(test_1, struct bpf_dummy_ops_state *state) +{ + int ret; + + if (!state) + return 0xf2f3f4f5; + + ret = state->val; + state->val = 0x5a; + return ret; +} + +__u64 test_2_args[5]; + +SEC("struct_ops/test_2") +int BPF_PROG(test_2, struct bpf_dummy_ops_state *state, int a1, unsigned short a2, + char a3, unsigned long a4) +{ + test_2_args[0] = (unsigned long)state; + test_2_args[1] = a1; + test_2_args[2] = a2; + test_2_args[3] = a3; + test_2_args[4] = a4; + return 0; +} + +SEC("struct_ops.s/test_sleepable") +int BPF_PROG(test_sleepable, struct bpf_dummy_ops_state *state) +{ + return 0; +} + +SEC(".struct_ops") +struct bpf_dummy_ops dummy_1 = { + .test_1 = (void *)test_1, + .test_2 = (void *)test_2, + .test_sleepable = (void *)test_sleepable, +}; diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c new file mode 100644 index 0000000000..7ce7e827d5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -0,0 +1,1688 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Facebook */ + +#include <errno.h> +#include <string.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <linux/if_ether.h> +#include "bpf_misc.h" +#include "bpf_kfuncs.h" + +char _license[] SEC("license") = "GPL"; + +struct test_info { + int x; + struct bpf_dynptr ptr; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct bpf_dynptr); +} array_map1 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct test_info); +} array_map2 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} array_map3 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} array_map4 SEC(".maps"); + +struct sample { + int pid; + long value; + char comm[16]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 4096); +} ringbuf SEC(".maps"); + +int err, val; + +static int get_map_val_dynptr(struct bpf_dynptr *ptr) +{ + __u32 key = 0, *map_val; + + bpf_map_update_elem(&array_map3, &key, &val, 0); + + map_val = bpf_map_lookup_elem(&array_map3, &key); + if (!map_val) + return -ENOENT; + + bpf_dynptr_from_mem(map_val, sizeof(*map_val), 0, ptr); + + return 0; +} + +/* Every bpf_ringbuf_reserve_dynptr call must have a corresponding + * bpf_ringbuf_submit/discard_dynptr call + */ +SEC("?raw_tp") +__failure __msg("Unreleased reference id=2") +int ringbuf_missing_release1(void *ctx) +{ + struct bpf_dynptr ptr; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + /* missing a call to bpf_ringbuf_discard/submit_dynptr */ + + return 0; +} + +SEC("?raw_tp") +__failure __msg("Unreleased reference id=4") +int ringbuf_missing_release2(void *ctx) +{ + struct bpf_dynptr ptr1, ptr2; + struct sample *sample; + + bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(*sample), 0, &ptr1); + bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(*sample), 0, &ptr2); + + sample = bpf_dynptr_data(&ptr1, 0, sizeof(*sample)); + if (!sample) { + bpf_ringbuf_discard_dynptr(&ptr1, 0); + bpf_ringbuf_discard_dynptr(&ptr2, 0); + return 0; + } + + bpf_ringbuf_submit_dynptr(&ptr1, 0); + + /* missing a call to bpf_ringbuf_discard/submit_dynptr on ptr2 */ + + return 0; +} + +static int missing_release_callback_fn(__u32 index, void *data) +{ + struct bpf_dynptr ptr; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + /* missing a call to bpf_ringbuf_discard/submit_dynptr */ + + return 0; +} + +/* Any dynptr initialized within a callback must have bpf_dynptr_put called */ +SEC("?raw_tp") +__failure __msg("Unreleased reference id") +int ringbuf_missing_release_callback(void *ctx) +{ + bpf_loop(10, missing_release_callback_fn, NULL, 0); + return 0; +} + +/* Can't call bpf_ringbuf_submit/discard_dynptr on a non-initialized dynptr */ +SEC("?raw_tp") +__failure __msg("arg 1 is an unacquired reference") +int ringbuf_release_uninit_dynptr(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_ringbuf_submit_dynptr(&ptr, 0); + + return 0; +} + +/* A dynptr can't be used after it has been invalidated */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int use_after_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(read_data), 0, &ptr); + + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); + + bpf_ringbuf_submit_dynptr(&ptr, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); + + return 0; +} + +/* Can't call non-dynptr ringbuf APIs on a dynptr ringbuf sample */ +SEC("?raw_tp") +__failure __msg("type=mem expected=ringbuf_mem") +int ringbuf_invalid_api(void *ctx) +{ + struct bpf_dynptr ptr; + struct sample *sample; + + bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(*sample), 0, &ptr); + sample = bpf_dynptr_data(&ptr, 0, sizeof(*sample)); + if (!sample) + goto done; + + sample->pid = 123; + + /* invalid API use. need to use dynptr API to submit/discard */ + bpf_ringbuf_submit(sample, 0); + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +/* Can't add a dynptr to a map */ +SEC("?raw_tp") +__failure __msg("invalid indirect read from stack") +int add_dynptr_to_map1(void *ctx) +{ + struct bpf_dynptr ptr; + int key = 0; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + /* this should fail */ + bpf_map_update_elem(&array_map1, &key, &ptr, 0); + + bpf_ringbuf_submit_dynptr(&ptr, 0); + + return 0; +} + +/* Can't add a struct with an embedded dynptr to a map */ +SEC("?raw_tp") +__failure __msg("invalid indirect read from stack") +int add_dynptr_to_map2(void *ctx) +{ + struct test_info x; + int key = 0; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &x.ptr); + + /* this should fail */ + bpf_map_update_elem(&array_map2, &key, &x, 0); + + bpf_ringbuf_submit_dynptr(&x.ptr, 0); + + return 0; +} + +/* A data slice can't be accessed out of bounds */ +SEC("?raw_tp") +__failure __msg("value is outside of the allowed memory range") +int data_slice_out_of_bounds_ringbuf(void *ctx) +{ + struct bpf_dynptr ptr; + void *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 8, 0, &ptr); + + data = bpf_dynptr_data(&ptr, 0, 8); + if (!data) + goto done; + + /* can't index out of bounds of the data slice */ + val = *((char *)data + 8); + +done: + bpf_ringbuf_submit_dynptr(&ptr, 0); + return 0; +} + +/* A data 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(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + struct ethhdr *hdr; + char buffer[sizeof(*hdr)] = {}; + + bpf_dynptr_from_skb(skb, 0, &ptr); + + hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer)); + if (!hdr) + return SK_DROP; + + /* this should fail */ + *(__u8*)(hdr + 1) = 1; + + 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) +{ + __u32 map_val; + struct bpf_dynptr ptr; + void *data; + + get_map_val_dynptr(&ptr); + + data = bpf_dynptr_data(&ptr, 0, sizeof(map_val)); + if (!data) + return 0; + + /* can't index out of bounds of the data slice */ + val = *((char *)data + (sizeof(map_val) + 1)); + + return 0; +} + +/* A data slice can't be used after it has been released */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int data_slice_use_after_release1(void *ctx) +{ + struct bpf_dynptr ptr; + struct sample *sample; + + bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(*sample), 0, &ptr); + sample = bpf_dynptr_data(&ptr, 0, sizeof(*sample)); + if (!sample) + goto done; + + sample->pid = 123; + + bpf_ringbuf_submit_dynptr(&ptr, 0); + + /* this should fail */ + val = sample->pid; + + return 0; + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +/* A data slice can't be used after it has been released. + * + * This tests the case where the data slice tracks a dynptr (ptr2) + * that is at a non-zero offset from the frame pointer (ptr1 is at fp, + * ptr2 is at fp - 16). + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int data_slice_use_after_release2(void *ctx) +{ + struct bpf_dynptr ptr1, ptr2; + struct sample *sample; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr1); + bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(*sample), 0, &ptr2); + + sample = bpf_dynptr_data(&ptr2, 0, sizeof(*sample)); + if (!sample) + goto done; + + sample->pid = 23; + + bpf_ringbuf_submit_dynptr(&ptr2, 0); + + /* this should fail */ + sample->pid = 23; + + bpf_ringbuf_submit_dynptr(&ptr1, 0); + + return 0; + +done: + bpf_ringbuf_discard_dynptr(&ptr2, 0); + bpf_ringbuf_discard_dynptr(&ptr1, 0); + return 0; +} + +/* A data slice must be first checked for NULL */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'mem_or_null'") +int data_slice_missing_null_check1(void *ctx) +{ + struct bpf_dynptr ptr; + void *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 8, 0, &ptr); + + data = bpf_dynptr_data(&ptr, 0, 8); + + /* missing if (!data) check */ + + /* this should fail */ + *(__u8 *)data = 3; + + bpf_ringbuf_submit_dynptr(&ptr, 0); + return 0; +} + +/* A data slice can't be dereferenced if it wasn't checked for null */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'mem_or_null'") +int data_slice_missing_null_check2(void *ctx) +{ + struct bpf_dynptr ptr; + __u64 *data1, *data2; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 16, 0, &ptr); + + data1 = bpf_dynptr_data(&ptr, 0, 8); + data2 = bpf_dynptr_data(&ptr, 0, 8); + if (data1) + /* this should fail */ + *data2 = 3; + + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +/* Can't pass in a dynptr as an arg to a helper function that doesn't take in a + * dynptr argument + */ +SEC("?raw_tp") +__failure __msg("invalid indirect read from stack") +int invalid_helper1(void *ctx) +{ + struct bpf_dynptr ptr; + + get_map_val_dynptr(&ptr); + + /* this should fail */ + bpf_strncmp((const char *)&ptr, sizeof(ptr), "hello!"); + + return 0; +} + +/* A dynptr can't be passed into a helper function at a non-zero offset */ +SEC("?raw_tp") +__failure __msg("cannot pass in dynptr at an offset=-8") +int invalid_helper2(void *ctx) +{ + struct bpf_dynptr ptr; + char read_data[64]; + + get_map_val_dynptr(&ptr); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 8, 0, 0); + return 0; +} + +/* A bpf_dynptr is invalidated if it's been written into */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int invalid_write1(void *ctx) +{ + struct bpf_dynptr ptr; + void *data; + __u8 x = 0; + + get_map_val_dynptr(&ptr); + + memcpy(&ptr, &x, sizeof(x)); + + /* this should fail */ + data = bpf_dynptr_data(&ptr, 0, 1); + __sink(data); + + return 0; +} + +/* + * A bpf_dynptr can't be used as a dynptr if it has been written into at a fixed + * offset + */ +SEC("?raw_tp") +__failure __msg("cannot overwrite referenced dynptr") +int invalid_write2(void *ctx) +{ + struct bpf_dynptr ptr; + char read_data[64]; + __u8 x = 0; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr); + + memcpy((void *)&ptr + 8, &x, sizeof(x)); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); + + bpf_ringbuf_submit_dynptr(&ptr, 0); + + return 0; +} + +/* + * A bpf_dynptr can't be used as a dynptr if it has been written into at a + * non-const offset + */ +SEC("?raw_tp") +__failure __msg("cannot overwrite referenced dynptr") +int invalid_write3(void *ctx) +{ + struct bpf_dynptr ptr; + char stack_buf[16]; + unsigned long len; + __u8 x = 0; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 8, 0, &ptr); + + memcpy(stack_buf, &val, sizeof(val)); + len = stack_buf[0] & 0xf; + + memcpy((void *)&ptr + len, &x, sizeof(x)); + + /* this should fail */ + bpf_ringbuf_submit_dynptr(&ptr, 0); + + return 0; +} + +static int invalid_write4_callback(__u32 index, void *data) +{ + *(__u32 *)data = 123; + + return 0; +} + +/* If the dynptr is written into in a callback function, it should + * be invalidated as a dynptr + */ +SEC("?raw_tp") +__failure __msg("cannot overwrite referenced dynptr") +int invalid_write4(void *ctx) +{ + struct bpf_dynptr ptr; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr); + + bpf_loop(10, invalid_write4_callback, &ptr, 0); + + /* this should fail */ + bpf_ringbuf_submit_dynptr(&ptr, 0); + + return 0; +} + +/* A globally-defined bpf_dynptr can't be used (it must reside as a stack frame) */ +struct bpf_dynptr global_dynptr; + +SEC("?raw_tp") +__failure __msg("type=map_value expected=fp") +int global(void *ctx) +{ + /* this should fail */ + bpf_ringbuf_reserve_dynptr(&ringbuf, 16, 0, &global_dynptr); + + bpf_ringbuf_discard_dynptr(&global_dynptr, 0); + + return 0; +} + +/* A direct read should fail */ +SEC("?raw_tp") +__failure __msg("invalid read from stack") +int invalid_read1(void *ctx) +{ + struct bpf_dynptr ptr; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr); + + /* this should fail */ + val = *(int *)&ptr; + + bpf_ringbuf_discard_dynptr(&ptr, 0); + + return 0; +} + +/* A direct read at an offset should fail */ +SEC("?raw_tp") +__failure __msg("cannot pass in dynptr at an offset") +int invalid_read2(void *ctx) +{ + struct bpf_dynptr ptr; + char read_data[64]; + + get_map_val_dynptr(&ptr); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 1, 0, 0); + + return 0; +} + +/* A direct read at an offset into the lower stack slot should fail */ +SEC("?raw_tp") +__failure __msg("invalid read from stack") +int invalid_read3(void *ctx) +{ + struct bpf_dynptr ptr1, ptr2; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 16, 0, &ptr1); + bpf_ringbuf_reserve_dynptr(&ringbuf, 16, 0, &ptr2); + + /* this should fail */ + memcpy(&val, (void *)&ptr1 + 8, sizeof(val)); + + bpf_ringbuf_discard_dynptr(&ptr1, 0); + bpf_ringbuf_discard_dynptr(&ptr2, 0); + + return 0; +} + +static int invalid_read4_callback(__u32 index, void *data) +{ + /* this should fail */ + val = *(__u32 *)data; + + return 0; +} + +/* A direct read within a callback function should fail */ +SEC("?raw_tp") +__failure __msg("invalid read from stack") +int invalid_read4(void *ctx) +{ + struct bpf_dynptr ptr; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr); + + bpf_loop(10, invalid_read4_callback, &ptr, 0); + + bpf_ringbuf_submit_dynptr(&ptr, 0); + + return 0; +} + +/* Initializing a dynptr on an offset should fail */ +SEC("?raw_tp") +__failure __msg("cannot pass in dynptr at an offset=0") +int invalid_offset(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr + 1); + + bpf_ringbuf_discard_dynptr(&ptr, 0); + + return 0; +} + +/* Can't release a dynptr twice */ +SEC("?raw_tp") +__failure __msg("arg 1 is an unacquired reference") +int release_twice(void *ctx) +{ + struct bpf_dynptr ptr; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 16, 0, &ptr); + + bpf_ringbuf_discard_dynptr(&ptr, 0); + + /* this second release should fail */ + bpf_ringbuf_discard_dynptr(&ptr, 0); + + return 0; +} + +static int release_twice_callback_fn(__u32 index, void *data) +{ + /* this should fail */ + bpf_ringbuf_discard_dynptr(data, 0); + + return 0; +} + +/* Test that releasing a dynptr twice, where one of the releases happens + * within a callback function, fails + */ +SEC("?raw_tp") +__failure __msg("arg 1 is an unacquired reference") +int release_twice_callback(void *ctx) +{ + struct bpf_dynptr ptr; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 32, 0, &ptr); + + bpf_ringbuf_discard_dynptr(&ptr, 0); + + bpf_loop(10, release_twice_callback_fn, &ptr, 0); + + return 0; +} + +/* Reject unsupported local mem types for dynptr_from_mem API */ +SEC("?raw_tp") +__failure __msg("Unsupported reg type fp for bpf_dynptr_from_mem data") +int dynptr_from_mem_invalid_api(void *ctx) +{ + struct bpf_dynptr ptr; + int x = 0; + + /* this should fail */ + bpf_dynptr_from_mem(&x, sizeof(x), 0, &ptr); + + return 0; +} + +SEC("?tc") +__failure __msg("cannot overwrite referenced dynptr") __log_level(2) +int dynptr_pruning_overwrite(struct __sk_buff *ctx) +{ + asm volatile ( + "r9 = 0xeB9F; \ + r6 = %[ringbuf] ll; \ + r1 = r6; \ + r2 = 8; \ + r3 = 0; \ + r4 = r10; \ + r4 += -16; \ + call %[bpf_ringbuf_reserve_dynptr]; \ + if r0 == 0 goto pjmp1; \ + goto pjmp2; \ + pjmp1: \ + *(u64 *)(r10 - 16) = r9; \ + pjmp2: \ + r1 = r10; \ + r1 += -16; \ + r2 = 0; \ + call %[bpf_ringbuf_discard_dynptr]; " + : + : __imm(bpf_ringbuf_reserve_dynptr), + __imm(bpf_ringbuf_discard_dynptr), + __imm_addr(ringbuf) + : __clobber_all + ); + return 0; +} + +SEC("?tc") +__success __msg("12: safe") __log_level(2) +int dynptr_pruning_stacksafe(struct __sk_buff *ctx) +{ + asm volatile ( + "r9 = 0xeB9F; \ + r6 = %[ringbuf] ll; \ + r1 = r6; \ + r2 = 8; \ + r3 = 0; \ + r4 = r10; \ + r4 += -16; \ + call %[bpf_ringbuf_reserve_dynptr]; \ + if r0 == 0 goto stjmp1; \ + goto stjmp2; \ + stjmp1: \ + r9 = r9; \ + stjmp2: \ + r1 = r10; \ + r1 += -16; \ + r2 = 0; \ + call %[bpf_ringbuf_discard_dynptr]; " + : + : __imm(bpf_ringbuf_reserve_dynptr), + __imm(bpf_ringbuf_discard_dynptr), + __imm_addr(ringbuf) + : __clobber_all + ); + return 0; +} + +SEC("?tc") +__failure __msg("cannot overwrite referenced dynptr") __log_level(2) +int dynptr_pruning_type_confusion(struct __sk_buff *ctx) +{ + asm volatile ( + "r6 = %[array_map4] ll; \ + r7 = %[ringbuf] ll; \ + r1 = r6; \ + r2 = r10; \ + r2 += -8; \ + r9 = 0; \ + *(u64 *)(r2 + 0) = r9; \ + r3 = r10; \ + r3 += -24; \ + r9 = 0xeB9FeB9F; \ + *(u64 *)(r10 - 16) = r9; \ + *(u64 *)(r10 - 24) = r9; \ + r9 = 0; \ + r4 = 0; \ + r8 = r2; \ + call %[bpf_map_update_elem]; \ + r1 = r6; \ + r2 = r8; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto tjmp1; \ + exit; \ + tjmp1: \ + r8 = r0; \ + r1 = r7; \ + r2 = 8; \ + r3 = 0; \ + r4 = r10; \ + r4 += -16; \ + r0 = *(u64 *)(r0 + 0); \ + call %[bpf_ringbuf_reserve_dynptr]; \ + if r0 == 0 goto tjmp2; \ + r8 = r8; \ + r8 = r8; \ + r8 = r8; \ + r8 = r8; \ + r8 = r8; \ + r8 = r8; \ + r8 = r8; \ + goto tjmp3; \ + tjmp2: \ + *(u64 *)(r10 - 8) = r9; \ + *(u64 *)(r10 - 16) = r9; \ + r1 = r8; \ + r1 += 8; \ + r2 = 0; \ + r3 = 0; \ + r4 = r10; \ + r4 += -16; \ + call %[bpf_dynptr_from_mem]; \ + tjmp3: \ + r1 = r10; \ + r1 += -16; \ + r2 = 0; \ + call %[bpf_ringbuf_discard_dynptr]; " + : + : __imm(bpf_map_update_elem), + __imm(bpf_map_lookup_elem), + __imm(bpf_ringbuf_reserve_dynptr), + __imm(bpf_dynptr_from_mem), + __imm(bpf_ringbuf_discard_dynptr), + __imm_addr(array_map4), + __imm_addr(ringbuf) + : __clobber_all + ); + return 0; +} + +SEC("?tc") +__failure __msg("dynptr has to be at a constant offset") __log_level(2) +int dynptr_var_off_overwrite(struct __sk_buff *ctx) +{ + asm volatile ( + "r9 = 16; \ + *(u32 *)(r10 - 4) = r9; \ + r8 = *(u32 *)(r10 - 4); \ + if r8 >= 0 goto vjmp1; \ + r0 = 1; \ + exit; \ + vjmp1: \ + if r8 <= 16 goto vjmp2; \ + r0 = 1; \ + exit; \ + vjmp2: \ + r8 &= 16; \ + r1 = %[ringbuf] ll; \ + r2 = 8; \ + r3 = 0; \ + r4 = r10; \ + r4 += -32; \ + r4 += r8; \ + call %[bpf_ringbuf_reserve_dynptr]; \ + r9 = 0xeB9F; \ + *(u64 *)(r10 - 16) = r9; \ + r1 = r10; \ + r1 += -32; \ + r1 += r8; \ + r2 = 0; \ + call %[bpf_ringbuf_discard_dynptr]; " + : + : __imm(bpf_ringbuf_reserve_dynptr), + __imm(bpf_ringbuf_discard_dynptr), + __imm_addr(ringbuf) + : __clobber_all + ); + return 0; +} + +SEC("?tc") +__failure __msg("cannot overwrite referenced dynptr") __log_level(2) +int dynptr_partial_slot_invalidate(struct __sk_buff *ctx) +{ + asm volatile ( + "r6 = %[ringbuf] ll; \ + r7 = %[array_map4] ll; \ + r1 = r7; \ + r2 = r10; \ + r2 += -8; \ + r9 = 0; \ + *(u64 *)(r2 + 0) = r9; \ + r3 = r2; \ + r4 = 0; \ + r8 = r2; \ + call %[bpf_map_update_elem]; \ + r1 = r7; \ + r2 = r8; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto sjmp1; \ + exit; \ + sjmp1: \ + r7 = r0; \ + r1 = r6; \ + r2 = 8; \ + r3 = 0; \ + r4 = r10; \ + r4 += -24; \ + call %[bpf_ringbuf_reserve_dynptr]; \ + *(u64 *)(r10 - 16) = r9; \ + r1 = r7; \ + r2 = 8; \ + r3 = 0; \ + r4 = r10; \ + r4 += -16; \ + call %[bpf_dynptr_from_mem]; \ + r1 = r10; \ + r1 += -512; \ + r2 = 488; \ + r3 = r10; \ + r3 += -24; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_dynptr_read]; \ + r8 = 1; \ + if r0 != 0 goto sjmp2; \ + r8 = 0; \ + sjmp2: \ + r1 = r10; \ + r1 += -24; \ + r2 = 0; \ + call %[bpf_ringbuf_discard_dynptr]; " + : + : __imm(bpf_map_update_elem), + __imm(bpf_map_lookup_elem), + __imm(bpf_ringbuf_reserve_dynptr), + __imm(bpf_ringbuf_discard_dynptr), + __imm(bpf_dynptr_from_mem), + __imm(bpf_dynptr_read), + __imm_addr(ringbuf), + __imm_addr(array_map4) + : __clobber_all + ); + return 0; +} + +/* Test that it is allowed to overwrite unreferenced dynptr. */ +SEC("?raw_tp") +__success +int dynptr_overwrite_unref(void *ctx) +{ + struct bpf_dynptr ptr; + + if (get_map_val_dynptr(&ptr)) + return 0; + if (get_map_val_dynptr(&ptr)) + return 0; + if (get_map_val_dynptr(&ptr)) + return 0; + + return 0; +} + +/* Test that slices are invalidated on reinitializing a dynptr. */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int dynptr_invalidate_slice_reinit(void *ctx) +{ + struct bpf_dynptr ptr; + __u8 *p; + + if (get_map_val_dynptr(&ptr)) + return 0; + p = bpf_dynptr_data(&ptr, 0, 1); + if (!p) + return 0; + if (get_map_val_dynptr(&ptr)) + return 0; + /* this should fail */ + return *p; +} + +/* Invalidation of dynptr slices on destruction of dynptr should not miss + * mem_or_null pointers. + */ +SEC("?raw_tp") +__failure __msg("R1 type=scalar expected=percpu_ptr_") +int dynptr_invalidate_slice_or_null(void *ctx) +{ + struct bpf_dynptr ptr; + __u8 *p; + + if (get_map_val_dynptr(&ptr)) + return 0; + + p = bpf_dynptr_data(&ptr, 0, 1); + *(__u8 *)&ptr = 0; + /* this should fail */ + bpf_this_cpu_ptr(p); + return 0; +} + +/* Destruction of dynptr should also any slices obtained from it */ +SEC("?raw_tp") +__failure __msg("R7 invalid mem access 'scalar'") +int dynptr_invalidate_slice_failure(void *ctx) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + __u8 *p1, *p2; + + if (get_map_val_dynptr(&ptr1)) + return 0; + if (get_map_val_dynptr(&ptr2)) + return 0; + + p1 = bpf_dynptr_data(&ptr1, 0, 1); + if (!p1) + return 0; + p2 = bpf_dynptr_data(&ptr2, 0, 1); + if (!p2) + return 0; + + *(__u8 *)&ptr1 = 0; + /* this should fail */ + return *p1; +} + +/* Invalidation of slices should be scoped and should not prevent dereferencing + * slices of another dynptr after destroying unrelated dynptr + */ +SEC("?raw_tp") +__success +int dynptr_invalidate_slice_success(void *ctx) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + __u8 *p1, *p2; + + if (get_map_val_dynptr(&ptr1)) + return 1; + if (get_map_val_dynptr(&ptr2)) + return 1; + + p1 = bpf_dynptr_data(&ptr1, 0, 1); + if (!p1) + return 1; + p2 = bpf_dynptr_data(&ptr2, 0, 1); + if (!p2) + return 1; + + *(__u8 *)&ptr1 = 0; + return *p2; +} + +/* Overwriting referenced dynptr should be rejected */ +SEC("?raw_tp") +__failure __msg("cannot overwrite referenced dynptr") +int dynptr_overwrite_ref(void *ctx) +{ + struct bpf_dynptr ptr; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr); + /* this should fail */ + if (get_map_val_dynptr(&ptr)) + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +/* Reject writes to dynptr slot from bpf_dynptr_read */ +SEC("?raw_tp") +__failure __msg("potential write to dynptr at off=-16") +int dynptr_read_into_slot(void *ctx) +{ + union { + struct { + char _pad[48]; + struct bpf_dynptr ptr; + }; + char buf[64]; + } data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &data.ptr); + /* this should fail */ + bpf_dynptr_read(data.buf, sizeof(data.buf), &data.ptr, 0, 0); + + return 0; +} + +/* bpf_dynptr_slice()s are read-only and cannot be written to */ +SEC("?tc") +__failure __msg("R0 cannot write into rdonly_mem") +int skb_invalid_slice_write(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + struct ethhdr *hdr; + char buffer[sizeof(*hdr)] = {}; + + bpf_dynptr_from_skb(skb, 0, &ptr); + + hdr = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer)); + if (!hdr) + return SK_DROP; + + /* this should fail */ + hdr->h_proto = 1; + + return SK_PASS; +} + +/* The read-only data slice is invalidated whenever a helper changes packet data */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int skb_invalid_data_slice1(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + struct ethhdr *hdr; + char buffer[sizeof(*hdr)] = {}; + + bpf_dynptr_from_skb(skb, 0, &ptr); + + hdr = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer)); + if (!hdr) + return SK_DROP; + + val = hdr->h_proto; + + if (bpf_skb_pull_data(skb, skb->len)) + return SK_DROP; + + /* this should fail */ + val = hdr->h_proto; + + return SK_PASS; +} + +/* The read-write data slice is invalidated whenever a helper changes packet data */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int skb_invalid_data_slice2(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + struct ethhdr *hdr; + char buffer[sizeof(*hdr)] = {}; + + bpf_dynptr_from_skb(skb, 0, &ptr); + + hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer)); + if (!hdr) + return SK_DROP; + + hdr->h_proto = 123; + + if (bpf_skb_pull_data(skb, skb->len)) + return SK_DROP; + + /* this should fail */ + hdr->h_proto = 1; + + return SK_PASS; +} + +/* The read-only data slice is invalidated whenever bpf_dynptr_write() is called */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int skb_invalid_data_slice3(struct __sk_buff *skb) +{ + char write_data[64] = "hello there, world!!"; + struct bpf_dynptr ptr; + struct ethhdr *hdr; + char buffer[sizeof(*hdr)] = {}; + + bpf_dynptr_from_skb(skb, 0, &ptr); + + hdr = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer)); + if (!hdr) + return SK_DROP; + + val = hdr->h_proto; + + bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0); + + /* this should fail */ + val = hdr->h_proto; + + return SK_PASS; +} + +/* The read-write data slice is invalidated whenever bpf_dynptr_write() is called */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int skb_invalid_data_slice4(struct __sk_buff *skb) +{ + char write_data[64] = "hello there, world!!"; + struct bpf_dynptr ptr; + struct ethhdr *hdr; + char buffer[sizeof(*hdr)] = {}; + + bpf_dynptr_from_skb(skb, 0, &ptr); + hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer)); + if (!hdr) + return SK_DROP; + + hdr->h_proto = 123; + + bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0); + + /* this should fail */ + hdr->h_proto = 1; + + return SK_PASS; +} + +/* The read-only data slice is invalidated whenever a helper changes packet data */ +SEC("?xdp") +__failure __msg("invalid mem access 'scalar'") +int xdp_invalid_data_slice1(struct xdp_md *xdp) +{ + struct bpf_dynptr ptr; + struct ethhdr *hdr; + char buffer[sizeof(*hdr)] = {}; + + bpf_dynptr_from_xdp(xdp, 0, &ptr); + hdr = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer)); + if (!hdr) + return SK_DROP; + + val = hdr->h_proto; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(*hdr))) + return XDP_DROP; + + /* this should fail */ + val = hdr->h_proto; + + return XDP_PASS; +} + +/* The read-write data slice is invalidated whenever a helper changes packet data */ +SEC("?xdp") +__failure __msg("invalid mem access 'scalar'") +int xdp_invalid_data_slice2(struct xdp_md *xdp) +{ + struct bpf_dynptr ptr; + struct ethhdr *hdr; + char buffer[sizeof(*hdr)] = {}; + + bpf_dynptr_from_xdp(xdp, 0, &ptr); + hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer)); + if (!hdr) + return SK_DROP; + + hdr->h_proto = 9; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(*hdr))) + return XDP_DROP; + + /* this should fail */ + hdr->h_proto = 1; + + return XDP_PASS; +} + +/* Only supported prog type can create skb-type dynptrs */ +SEC("?raw_tp") +__failure __msg("calling kernel function bpf_dynptr_from_skb is not allowed") +int skb_invalid_ctx(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_from_skb(ctx, 0, &ptr); + + return 0; +} + +/* Reject writes to dynptr slot for uninit arg */ +SEC("?raw_tp") +__failure __msg("potential write to dynptr at off=-16") +int uninit_write_into_slot(void *ctx) +{ + struct { + char buf[64]; + struct bpf_dynptr ptr; + } data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 80, 0, &data.ptr); + /* this should fail */ + bpf_get_current_comm(data.buf, 80); + + return 0; +} + +/* Only supported prog type can create xdp-type dynptrs */ +SEC("?raw_tp") +__failure __msg("calling kernel function bpf_dynptr_from_xdp is not allowed") +int xdp_invalid_ctx(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_from_xdp(ctx, 0, &ptr); + + return 0; +} + +__u32 hdr_size = sizeof(struct ethhdr); +/* Can't pass in variable-sized len to bpf_dynptr_slice */ +SEC("?tc") +__failure __msg("unbounded memory access") +int dynptr_slice_var_len1(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + struct ethhdr *hdr; + char buffer[sizeof(*hdr)] = {}; + + bpf_dynptr_from_skb(skb, 0, &ptr); + + /* this should fail */ + hdr = bpf_dynptr_slice(&ptr, 0, buffer, hdr_size); + if (!hdr) + return SK_DROP; + + return SK_PASS; +} + +/* Can't pass in variable-sized len to bpf_dynptr_slice */ +SEC("?tc") +__failure __msg("must be a known constant") +int dynptr_slice_var_len2(struct __sk_buff *skb) +{ + char buffer[sizeof(struct ethhdr)] = {}; + struct bpf_dynptr ptr; + struct ethhdr *hdr; + + bpf_dynptr_from_skb(skb, 0, &ptr); + + if (hdr_size <= sizeof(buffer)) { + /* this should fail */ + hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, hdr_size); + if (!hdr) + return SK_DROP; + hdr->h_proto = 12; + } + + return SK_PASS; +} + +static int callback(__u32 index, void *data) +{ + *(__u32 *)data = 123; + + return 0; +} + +/* If the dynptr is written into in a callback function, its data + * slices should be invalidated as well. + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int invalid_data_slices(void *ctx) +{ + struct bpf_dynptr ptr; + __u32 *slice; + + if (get_map_val_dynptr(&ptr)) + return 0; + + slice = bpf_dynptr_data(&ptr, 0, sizeof(__u32)); + if (!slice) + return 0; + + bpf_loop(10, callback, &ptr, 0); + + /* this should fail */ + *slice = 1; + + return 0; +} + +/* Program types that don't allow writes to packet data should fail if + * bpf_dynptr_slice_rdwr is called + */ +SEC("cgroup_skb/ingress") +__failure __msg("the prog does not allow writes to packet data") +int invalid_slice_rdwr_rdonly(struct __sk_buff *skb) +{ + char buffer[sizeof(struct ethhdr)] = {}; + struct bpf_dynptr ptr; + struct ethhdr *hdr; + + bpf_dynptr_from_skb(skb, 0, &ptr); + + /* this should fail since cgroup_skb doesn't allow + * changing packet data + */ + hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer)); + __sink(hdr); + + return 0; +} + +/* bpf_dynptr_adjust can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_adjust_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_adjust(&ptr, 1, 2); + + return 0; +} + +/* bpf_dynptr_is_null can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_is_null_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_is_null(&ptr); + + return 0; +} + +/* bpf_dynptr_is_rdonly can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_is_rdonly_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_is_rdonly(&ptr); + + return 0; +} + +/* bpf_dynptr_size can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_size_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_size(&ptr); + + return 0; +} + +/* Only initialized dynptrs can be cloned */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int clone_invalid1(void *ctx) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + + /* this should fail */ + bpf_dynptr_clone(&ptr1, &ptr2); + + return 0; +} + +/* Can't overwrite an existing dynptr when cloning */ +SEC("?xdp") +__failure __msg("cannot overwrite referenced dynptr") +int clone_invalid2(struct xdp_md *xdp) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr clone; + + bpf_dynptr_from_xdp(xdp, 0, &ptr1); + + bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &clone); + + /* this should fail */ + bpf_dynptr_clone(&ptr1, &clone); + + bpf_ringbuf_submit_dynptr(&clone, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate its clones */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int clone_invalidate1(void *ctx) +{ + struct bpf_dynptr clone; + struct bpf_dynptr ptr; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + + bpf_ringbuf_submit_dynptr(&ptr, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &clone, 0, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate its parent */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int clone_invalidate2(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + + bpf_ringbuf_submit_dynptr(&clone, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate its siblings */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int clone_invalidate3(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone1; + struct bpf_dynptr clone2; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone1); + + bpf_dynptr_clone(&ptr, &clone2); + + bpf_ringbuf_submit_dynptr(&clone2, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &clone1, 0, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate any data slices + * of its clones + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int clone_invalidate4(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone; + int *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + data = bpf_dynptr_data(&clone, 0, sizeof(val)); + if (!data) + return 0; + + bpf_ringbuf_submit_dynptr(&ptr, 0); + + /* this should fail */ + *data = 123; + + return 0; +} + +/* Invalidating a dynptr should invalidate any data slices + * of its parent + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int clone_invalidate5(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone; + int *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + data = bpf_dynptr_data(&ptr, 0, sizeof(val)); + if (!data) + return 0; + + bpf_dynptr_clone(&ptr, &clone); + + bpf_ringbuf_submit_dynptr(&clone, 0); + + /* this should fail */ + *data = 123; + + return 0; +} + +/* Invalidating a dynptr should invalidate any data slices + * of its sibling + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int clone_invalidate6(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone1; + struct bpf_dynptr clone2; + int *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone1); + + bpf_dynptr_clone(&ptr, &clone2); + + data = bpf_dynptr_data(&clone1, 0, sizeof(val)); + if (!data) + return 0; + + bpf_ringbuf_submit_dynptr(&clone2, 0); + + /* this should fail */ + *data = 123; + + return 0; +} + +/* A skb clone's data slices should be invalid anytime packet data changes */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int clone_skb_packet_data(struct __sk_buff *skb) +{ + char buffer[sizeof(__u32)] = {}; + struct bpf_dynptr clone; + struct bpf_dynptr ptr; + __u32 *data; + + bpf_dynptr_from_skb(skb, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + data = bpf_dynptr_slice_rdwr(&clone, 0, buffer, sizeof(buffer)); + if (!data) + return XDP_DROP; + + if (bpf_skb_pull_data(skb, skb->len)) + return SK_DROP; + + /* this should fail */ + *data = 123; + + return 0; +} + +/* A xdp clone's data slices should be invalid anytime packet data changes */ +SEC("?xdp") +__failure __msg("invalid mem access 'scalar'") +int clone_xdp_packet_data(struct xdp_md *xdp) +{ + char buffer[sizeof(__u32)] = {}; + struct bpf_dynptr clone; + struct bpf_dynptr ptr; + struct ethhdr *hdr; + __u32 *data; + + bpf_dynptr_from_xdp(xdp, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + data = bpf_dynptr_slice_rdwr(&clone, 0, buffer, sizeof(buffer)); + if (!data) + return XDP_DROP; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(*hdr))) + return XDP_DROP; + + /* this should fail */ + *data = 123; + + return 0; +} + +/* Buffers that are provided must be sufficiently long */ +SEC("?cgroup_skb/egress") +__failure __msg("memory, len pair leads to invalid memory access") +int test_dynptr_skb_small_buff(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + char buffer[8] = {}; + __u64 *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This may return NULL. SKB may require a buffer */ + data = bpf_dynptr_slice(&ptr, 0, buffer, 9); + + return !!data; +} diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c new file mode 100644 index 0000000000..5985920d16 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/dynptr_success.c @@ -0,0 +1,546 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Facebook */ + +#include <string.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" +#include "bpf_kfuncs.h" +#include "errno.h" + +char _license[] SEC("license") = "GPL"; + +int pid, err, val; + +struct sample { + int pid; + int seq; + long value; + char comm[16]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 4096); +} ringbuf SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} array_map SEC(".maps"); + +SEC("?tp/syscalls/sys_enter_nanosleep") +int test_read_write(void *ctx) +{ + char write_data[64] = "hello there, world!!"; + char read_data[64] = {}; + struct bpf_dynptr ptr; + int i; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(write_data), 0, &ptr); + + /* Write data into the dynptr */ + err = bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0); + + /* Read the data that was written into the dynptr */ + err = err ?: bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); + + /* Ensure the data we read matches the data we wrote */ + for (i = 0; i < sizeof(read_data); i++) { + if (read_data[i] != write_data[i]) { + err = 1; + break; + } + } + + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("?tp/syscalls/sys_enter_nanosleep") +int test_dynptr_data(void *ctx) +{ + __u32 key = 0, val = 235, *map_val; + struct bpf_dynptr ptr; + __u32 map_val_size; + void *data; + + map_val_size = sizeof(*map_val); + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + bpf_map_update_elem(&array_map, &key, &val, 0); + + map_val = bpf_map_lookup_elem(&array_map, &key); + if (!map_val) { + err = 1; + return 0; + } + + bpf_dynptr_from_mem(map_val, map_val_size, 0, &ptr); + + /* Try getting a data slice that is out of range */ + data = bpf_dynptr_data(&ptr, map_val_size + 1, 1); + if (data) { + err = 2; + return 0; + } + + /* Try getting more bytes than available */ + data = bpf_dynptr_data(&ptr, 0, map_val_size + 1); + if (data) { + err = 3; + return 0; + } + + data = bpf_dynptr_data(&ptr, 0, sizeof(__u32)); + if (!data) { + err = 4; + return 0; + } + + *(__u32 *)data = 999; + + err = bpf_probe_read_kernel(&val, sizeof(val), data); + if (err) + return 0; + + if (val != *(int *)data) + err = 5; + + return 0; +} + +static int ringbuf_callback(__u32 index, void *data) +{ + struct sample *sample; + + struct bpf_dynptr *ptr = (struct bpf_dynptr *)data; + + sample = bpf_dynptr_data(ptr, 0, sizeof(*sample)); + if (!sample) + err = 2; + else + sample->pid += index; + + return 0; +} + +SEC("?tp/syscalls/sys_enter_nanosleep") +int test_ringbuf(void *ctx) +{ + struct bpf_dynptr ptr; + struct sample *sample; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + val = 100; + + /* check that you can reserve a dynamic size reservation */ + err = bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + sample = err ? NULL : bpf_dynptr_data(&ptr, 0, sizeof(*sample)); + if (!sample) { + err = 1; + goto done; + } + + sample->pid = 10; + + /* Can pass dynptr to callback functions */ + bpf_loop(10, ringbuf_callback, &ptr, 0); + + if (sample->pid != 55) + err = 2; + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("?cgroup_skb/egress") +int test_skb_readonly(struct __sk_buff *skb) +{ + __u8 write_data[2] = {1, 2}; + struct bpf_dynptr ptr; + int ret; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* since cgroup skbs are read only, writes should fail */ + ret = bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0); + if (ret != -EINVAL) { + err = 2; + return 1; + } + + return 1; +} + +SEC("?cgroup_skb/egress") +int test_dynptr_skb_data(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + __u64 *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This should return NULL. Must use bpf_dynptr_slice API */ + data = bpf_dynptr_data(&ptr, 0, 1); + if (data) { + err = 2; + return 1; + } + + return 1; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_adjust(void *ctx) +{ + struct bpf_dynptr ptr; + __u32 bytes = 64; + __u32 off = 10; + __u32 trim = 15; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + err = bpf_ringbuf_reserve_dynptr(&ringbuf, bytes, 0, &ptr); + if (err) { + err = 1; + goto done; + } + + if (bpf_dynptr_size(&ptr) != bytes) { + err = 2; + goto done; + } + + /* Advance the dynptr by off */ + err = bpf_dynptr_adjust(&ptr, off, bpf_dynptr_size(&ptr)); + if (err) { + err = 3; + goto done; + } + + if (bpf_dynptr_size(&ptr) != bytes - off) { + err = 4; + goto done; + } + + /* Trim the dynptr */ + err = bpf_dynptr_adjust(&ptr, off, 15); + if (err) { + err = 5; + goto done; + } + + /* Check that the size was adjusted correctly */ + if (bpf_dynptr_size(&ptr) != trim - off) { + err = 6; + goto done; + } + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_adjust_err(void *ctx) +{ + char write_data[45] = "hello there, world!!"; + struct bpf_dynptr ptr; + __u32 size = 64; + __u32 off = 20; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr)) { + err = 1; + goto done; + } + + /* Check that start can't be greater than end */ + if (bpf_dynptr_adjust(&ptr, 5, 1) != -EINVAL) { + err = 2; + goto done; + } + + /* Check that start can't be greater than size */ + if (bpf_dynptr_adjust(&ptr, size + 1, size + 1) != -ERANGE) { + err = 3; + goto done; + } + + /* Check that end can't be greater than size */ + if (bpf_dynptr_adjust(&ptr, 0, size + 1) != -ERANGE) { + err = 4; + goto done; + } + + if (bpf_dynptr_adjust(&ptr, off, size)) { + err = 5; + goto done; + } + + /* Check that you can't write more bytes than available into the dynptr + * after you've adjusted it + */ + if (bpf_dynptr_write(&ptr, 0, &write_data, sizeof(write_data), 0) != -E2BIG) { + err = 6; + goto done; + } + + /* Check that even after adjusting, submitting/discarding + * a ringbuf dynptr works + */ + bpf_ringbuf_submit_dynptr(&ptr, 0); + return 0; + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_zero_size_dynptr(void *ctx) +{ + char write_data = 'x', read_data; + struct bpf_dynptr ptr; + __u32 size = 64; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr)) { + err = 1; + goto done; + } + + /* After this, the dynptr has a size of 0 */ + if (bpf_dynptr_adjust(&ptr, size, size)) { + err = 2; + goto done; + } + + /* Test that reading + writing non-zero bytes is not ok */ + if (bpf_dynptr_read(&read_data, sizeof(read_data), &ptr, 0, 0) != -E2BIG) { + err = 3; + goto done; + } + + if (bpf_dynptr_write(&ptr, 0, &write_data, sizeof(write_data), 0) != -E2BIG) { + err = 4; + goto done; + } + + /* Test that reading + writing 0 bytes from a 0-size dynptr is ok */ + if (bpf_dynptr_read(&read_data, 0, &ptr, 0, 0)) { + err = 5; + goto done; + } + + if (bpf_dynptr_write(&ptr, 0, &write_data, 0, 0)) { + err = 6; + goto done; + } + + err = 0; + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_dynptr_is_null(void *ctx) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + __u64 size = 4; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + /* Pass in invalid flags, get back an invalid dynptr */ + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 123, &ptr1) != -EINVAL) { + err = 1; + goto exit_early; + } + + /* Test that the invalid dynptr is null */ + if (!bpf_dynptr_is_null(&ptr1)) { + err = 2; + goto exit_early; + } + + /* Get a valid dynptr */ + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr2)) { + err = 3; + goto exit; + } + + /* Test that the valid dynptr is not null */ + if (bpf_dynptr_is_null(&ptr2)) { + err = 4; + goto exit; + } + +exit: + bpf_ringbuf_discard_dynptr(&ptr2, 0); +exit_early: + bpf_ringbuf_discard_dynptr(&ptr1, 0); + return 0; +} + +SEC("cgroup_skb/egress") +int test_dynptr_is_rdonly(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + struct bpf_dynptr ptr3; + + /* Pass in invalid flags, get back an invalid dynptr */ + if (bpf_dynptr_from_skb(skb, 123, &ptr1) != -EINVAL) { + err = 1; + return 0; + } + + /* Test that an invalid dynptr is_rdonly returns false */ + if (bpf_dynptr_is_rdonly(&ptr1)) { + err = 2; + return 0; + } + + /* Get a read-only dynptr */ + if (bpf_dynptr_from_skb(skb, 0, &ptr2)) { + err = 3; + return 0; + } + + /* Test that the dynptr is read-only */ + if (!bpf_dynptr_is_rdonly(&ptr2)) { + err = 4; + return 0; + } + + /* Get a read-writeable dynptr */ + if (bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr3)) { + err = 5; + goto done; + } + + /* Test that the dynptr is read-only */ + if (bpf_dynptr_is_rdonly(&ptr3)) { + err = 6; + goto done; + } + +done: + bpf_ringbuf_discard_dynptr(&ptr3, 0); + return 0; +} + +SEC("cgroup_skb/egress") +int test_dynptr_clone(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + __u32 off = 2, size; + + /* Get a dynptr */ + if (bpf_dynptr_from_skb(skb, 0, &ptr1)) { + err = 1; + return 0; + } + + if (bpf_dynptr_adjust(&ptr1, off, bpf_dynptr_size(&ptr1))) { + err = 2; + return 0; + } + + /* Clone the dynptr */ + if (bpf_dynptr_clone(&ptr1, &ptr2)) { + err = 3; + return 0; + } + + size = bpf_dynptr_size(&ptr1); + + /* Check that the clone has the same size and rd-only */ + if (bpf_dynptr_size(&ptr2) != size) { + err = 4; + return 0; + } + + if (bpf_dynptr_is_rdonly(&ptr2) != bpf_dynptr_is_rdonly(&ptr1)) { + err = 5; + return 0; + } + + /* Advance and trim the original dynptr */ + bpf_dynptr_adjust(&ptr1, 5, 5); + + /* Check that only original dynptr was affected, and the clone wasn't */ + if (bpf_dynptr_size(&ptr2) != size) { + err = 6; + return 0; + } + + return 0; +} + +SEC("?cgroup_skb/egress") +int test_dynptr_skb_no_buff(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + __u64 *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This may return NULL. SKB may require a buffer */ + data = bpf_dynptr_slice(&ptr, 0, NULL, 1); + + return !!data; +} + +SEC("?cgroup_skb/egress") +int test_dynptr_skb_strcmp(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + char *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This may return NULL. SKB may require a buffer */ + data = bpf_dynptr_slice(&ptr, 0, NULL, 10); + if (data) { + bpf_strncmp(data, 10, "foo"); + return 1; + } + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/empty_skb.c b/tools/testing/selftests/bpf/progs/empty_skb.c new file mode 100644 index 0000000000..4b0cd67532 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/empty_skb.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +char _license[] SEC("license") = "GPL"; + +int ifindex; +int ret; + +SEC("lwt_xmit") +int redirect_ingress(struct __sk_buff *skb) +{ + ret = bpf_clone_redirect(skb, ifindex, BPF_F_INGRESS); + return 0; +} + +SEC("lwt_xmit") +int redirect_egress(struct __sk_buff *skb) +{ + ret = bpf_clone_redirect(skb, ifindex, 0); + return 0; +} + +SEC("tc") +int tc_redirect_ingress(struct __sk_buff *skb) +{ + ret = bpf_clone_redirect(skb, ifindex, BPF_F_INGRESS); + return 0; +} + +SEC("tc") +int tc_redirect_egress(struct __sk_buff *skb) +{ + ret = bpf_clone_redirect(skb, ifindex, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/err.h b/tools/testing/selftests/bpf/progs/err.h new file mode 100644 index 0000000000..d66d283d9e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/err.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ERR_H__ +#define __ERR_H__ + +#define MAX_ERRNO 4095 +#define IS_ERR_VALUE(x) (unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO + +static inline int IS_ERR_OR_NULL(const void *ptr) +{ + return !ptr || IS_ERR_VALUE((unsigned long)ptr); +} + +static inline long PTR_ERR(const void *ptr) +{ + return (long) ptr; +} + +#endif /* __ERR_H__ */ diff --git a/tools/testing/selftests/bpf/progs/exhandler_kern.c b/tools/testing/selftests/bpf/progs/exhandler_kern.c new file mode 100644 index 0000000000..20d009e2d2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/exhandler_kern.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021, Oracle and/or its affiliates. */ + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +unsigned int exception_triggered; +int test_pid; + +/* TRACE_EVENT(task_newtask, + * TP_PROTO(struct task_struct *p, u64 clone_flags) + */ +SEC("tp_btf/task_newtask") +int BPF_PROG(trace_task_newtask, struct task_struct *task, u64 clone_flags) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + struct callback_head *work; + void *func; + + if (test_pid != pid) + return 0; + + /* To verify we hit an exception we dereference task->task_works->func. + * If task work has been added, + * - task->task_works is non-NULL; and + * - task->task_works->func is non-NULL also (the callback function + * must be specified for the task work. + * + * However, for a newly-created task, task->task_works is NULLed, + * so we know the exception handler triggered if task_works is + * NULL and func is NULL. + */ + work = task->task_works; + func = work->func; + /* Currently verifier will fail for `btf_ptr |= btf_ptr` * instruction. + * To workaround the issue, use barrier_var() and rewrite as below to + * prevent compiler from generating verifier-unfriendly code. + */ + barrier_var(work); + if (work) + return 0; + barrier_var(func); + if (func) + return 0; + exception_triggered++; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/fentry_many_args.c b/tools/testing/selftests/bpf/progs/fentry_many_args.c new file mode 100644 index 0000000000..b61bb92fee --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fentry_many_args.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Tencent */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +__u64 test1_result = 0; +SEC("fentry/bpf_testmod_fentry_test7") +int BPF_PROG(test1, __u64 a, void *b, short c, int d, void *e, char f, + int g) +{ + test1_result = a == 16 && b == (void *)17 && c == 18 && d == 19 && + e == (void *)20 && f == 21 && g == 22; + return 0; +} + +__u64 test2_result = 0; +SEC("fentry/bpf_testmod_fentry_test11") +int BPF_PROG(test2, __u64 a, void *b, short c, int d, void *e, char f, + int g, unsigned int h, long i, __u64 j, unsigned long k) +{ + test2_result = a == 16 && b == (void *)17 && c == 18 && d == 19 && + e == (void *)20 && f == 21 && g == 22 && h == 23 && + i == 24 && j == 25 && k == 26; + return 0; +} + +__u64 test3_result = 0; +SEC("fentry/bpf_testmod_fentry_test11") +int BPF_PROG(test3, __u64 a, __u64 b, __u64 c, __u64 d, __u64 e, __u64 f, + __u64 g, __u64 h, __u64 i, __u64 j, __u64 k) +{ + test3_result = a == 16 && b == 17 && c == 18 && d == 19 && + e == 20 && f == 21 && g == 22 && h == 23 && + i == 24 && j == 25 && k == 26; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c new file mode 100644 index 0000000000..52a550d281 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fentry_test.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +__u64 test1_result = 0; +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(test1, int a) +{ + test1_result = a == 1; + return 0; +} + +__u64 test2_result = 0; +SEC("fentry/bpf_fentry_test2") +int BPF_PROG(test2, int a, __u64 b) +{ + test2_result = a == 2 && b == 3; + return 0; +} + +__u64 test3_result = 0; +SEC("fentry/bpf_fentry_test3") +int BPF_PROG(test3, char a, int b, __u64 c) +{ + test3_result = a == 4 && b == 5 && c == 6; + return 0; +} + +__u64 test4_result = 0; +SEC("fentry/bpf_fentry_test4") +int BPF_PROG(test4, void *a, char b, int c, __u64 d) +{ + test4_result = a == (void *)7 && b == 8 && c == 9 && d == 10; + return 0; +} + +__u64 test5_result = 0; +SEC("fentry/bpf_fentry_test5") +int BPF_PROG(test5, __u64 a, void *b, short c, int d, __u64 e) +{ + test5_result = a == 11 && b == (void *)12 && c == 13 && d == 14 && + e == 15; + return 0; +} + +__u64 test6_result = 0; +SEC("fentry/bpf_fentry_test6") +int BPF_PROG(test6, __u64 a, void *b, short c, int d, void * e, __u64 f) +{ + test6_result = a == 16 && b == (void *)17 && c == 18 && d == 19 && + e == (void *)20 && f == 21; + return 0; +} + +struct bpf_fentry_test_t { + struct bpf_fentry_test_t *a; +}; + +__u64 test7_result = 0; +SEC("fentry/bpf_fentry_test7") +int BPF_PROG(test7, struct bpf_fentry_test_t *arg) +{ + if (!arg) + test7_result = 1; + return 0; +} + +__u64 test8_result = 0; +SEC("fentry/bpf_fentry_test8") +int BPF_PROG(test8, struct bpf_fentry_test_t *arg) +{ + if (arg->a == 0) + test8_result = 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c new file mode 100644 index 0000000000..983b7c2333 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include <linux/stddef.h> +#include <linux/if_ether.h> +#include <linux/ipv6.h> +#include <linux/bpf.h> +#include <linux/tcp.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_tracing.h> + +struct sk_buff { + unsigned int len; +}; + +__u64 test_result = 0; +SEC("fexit/test_pkt_access") +int BPF_PROG(test_main, struct sk_buff *skb, int ret) +{ + int len; + + __builtin_preserve_access_index(({ + len = skb->len; + })); + if (len != 74 || ret != 0) + return 0; + test_result = 1; + return 0; +} + +__u64 test_result_subprog1 = 0; +SEC("fexit/test_pkt_access_subprog1") +int BPF_PROG(test_subprog1, struct sk_buff *skb, int ret) +{ + int len; + + __builtin_preserve_access_index(({ + len = skb->len; + })); + if (len != 74 || ret != 148) + return 0; + test_result_subprog1 = 1; + return 0; +} + +/* Though test_pkt_access_subprog2() is defined in C as: + * static __attribute__ ((noinline)) + * int test_pkt_access_subprog2(int val, volatile struct __sk_buff *skb) + * { + * return skb->len * val; + * } + * llvm optimizations remove 'int val' argument and generate BPF assembly: + * r0 = *(u32 *)(r1 + 0) + * w0 <<= 1 + * exit + * In such case the verifier falls back to conservative and + * tracing program can access arguments and return value as u64 + * instead of accurate types. + */ +struct args_subprog2 { + __u64 args[5]; + __u64 ret; +}; +__u64 test_result_subprog2 = 0; +SEC("fexit/test_pkt_access_subprog2") +int test_subprog2(struct args_subprog2 *ctx) +{ + struct sk_buff *skb = (void *)ctx->args[0]; + __u64 ret; + int len; + + bpf_probe_read_kernel(&len, sizeof(len), + __builtin_preserve_access_index(&skb->len)); + + ret = ctx->ret; + /* bpf_prog_test_load() loads "test_pkt_access.bpf.o" with + * BPF_F_TEST_RND_HI32 which randomizes upper 32 bits after BPF_ALU32 + * insns. Hence after 'w0 <<= 1' upper bits of $rax are random. That is + * expected and correct. Trim them. + */ + ret = (__u32) ret; + if (len != 74 || ret != 148) + return 0; + test_result_subprog2 = 1; + return 0; +} + +__u64 test_result_subprog3 = 0; +SEC("fexit/test_pkt_access_subprog3") +int BPF_PROG(test_subprog3, int val, struct sk_buff *skb, int ret) +{ + int len; + + __builtin_preserve_access_index(({ + len = skb->len; + })); + if (len != 74 || ret != 74 * val || val != 3) + return 0; + test_result_subprog3 = 1; + return 0; +} + +__u64 test_get_skb_len = 0; +SEC("freplace/get_skb_len") +int new_get_skb_len(struct __sk_buff *skb) +{ + int len = skb->len; + + if (len != 74) + return 0; + test_get_skb_len = 1; + return 74; /* original get_skb_len() returns skb->len */ +} + +__u64 test_get_skb_ifindex = 0; +SEC("freplace/get_skb_ifindex") +int new_get_skb_ifindex(int val, struct __sk_buff *skb, int var) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ipv6hdr ip6, *ip6p; + int ifindex = skb->ifindex; + + /* check that BPF extension can read packet via direct packet access */ + if (data + 14 + sizeof(ip6) > data_end) + return 0; + ip6p = data + 14; + + if (ip6p->nexthdr != 6 || ip6p->payload_len != __bpf_constant_htons(123)) + return 0; + + /* check that legacy packet access helper works too */ + if (bpf_skb_load_bytes(skb, 14, &ip6, sizeof(ip6)) < 0) + return 0; + ip6p = &ip6; + if (ip6p->nexthdr != 6 || ip6p->payload_len != __bpf_constant_htons(123)) + return 0; + + if (ifindex != 1 || val != 3 || var != 1) + return 0; + test_get_skb_ifindex = 1; + return 3; /* original get_skb_ifindex() returns val * ifindex * var */ +} + +volatile __u64 test_get_constant = 0; +SEC("freplace/get_constant") +int new_get_constant(long val) +{ + if (val != 123) + return 0; + test_get_constant = 1; + return test_get_constant; /* original get_constant() returns val - 122 */ +} + +__u64 test_pkt_write_access_subprog = 0; +SEC("freplace/test_pkt_write_access_subprog") +int new_test_pkt_write_access_subprog(struct __sk_buff *skb, __u32 off) +{ + + void *data = (void *)(long)skb->data; + void *data_end = (void *)(long)skb->data_end; + struct tcphdr *tcp; + + if (off > sizeof(struct ethhdr) + sizeof(struct ipv6hdr)) + return -1; + + tcp = data + off; + if (tcp + 1 > data_end) + return -1; + + /* make modifications to the packet data */ + tcp->check++; + tcp->syn = 0; + + test_pkt_write_access_subprog = 1; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c new file mode 100644 index 0000000000..85c0b516d6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct sk_buff { + unsigned int len; +}; + +__u64 test_result = 0; + +SEC("fexit/test_pkt_md_access") +int BPF_PROG(test_main2, struct sk_buff *skb, int ret) +{ + int len; + + __builtin_preserve_access_index(({ + len = skb->len; + })); + if (len != 74 || ret != 0) + return 0; + + test_result = 1; + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/fexit_many_args.c b/tools/testing/selftests/bpf/progs/fexit_many_args.c new file mode 100644 index 0000000000..53b335c2da --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fexit_many_args.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Tencent */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +__u64 test1_result = 0; +SEC("fexit/bpf_testmod_fentry_test7") +int BPF_PROG(test1, __u64 a, void *b, short c, int d, void *e, char f, + int g, int ret) +{ + test1_result = a == 16 && b == (void *)17 && c == 18 && d == 19 && + e == (void *)20 && f == 21 && g == 22 && ret == 133; + return 0; +} + +__u64 test2_result = 0; +SEC("fexit/bpf_testmod_fentry_test11") +int BPF_PROG(test2, __u64 a, void *b, short c, int d, void *e, char f, + int g, unsigned int h, long i, __u64 j, unsigned long k, + int ret) +{ + test2_result = a == 16 && b == (void *)17 && c == 18 && d == 19 && + e == (void *)20 && f == 21 && g == 22 && h == 23 && + i == 24 && j == 25 && k == 26 && ret == 231; + return 0; +} + +__u64 test3_result = 0; +SEC("fexit/bpf_testmod_fentry_test11") +int BPF_PROG(test3, __u64 a, __u64 b, __u64 c, __u64 d, __u64 e, __u64 f, + __u64 g, __u64 h, __u64 i, __u64 j, __u64 k, __u64 ret) +{ + test3_result = a == 16 && b == 17 && c == 18 && d == 19 && + e == 20 && f == 21 && g == 22 && h == 23 && + i == 24 && j == 25 && k == 26 && ret == 231; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/fexit_sleep.c b/tools/testing/selftests/bpf/progs/fexit_sleep.c new file mode 100644 index 0000000000..106dc75efc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fexit_sleep.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +char LICENSE[] SEC("license") = "GPL"; + +int pid = 0; +int fentry_cnt = 0; +int fexit_cnt = 0; + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int nanosleep_fentry(void *ctx) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + fentry_cnt++; + return 0; +} + +SEC("fexit/" SYS_PREFIX "sys_nanosleep") +int nanosleep_fexit(void *ctx) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + fexit_cnt++; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c new file mode 100644 index 0000000000..8f1ccb7302 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fexit_test.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +__u64 test1_result = 0; +SEC("fexit/bpf_fentry_test1") +int BPF_PROG(test1, int a, int ret) +{ + test1_result = a == 1 && ret == 2; + return 0; +} + +__u64 test2_result = 0; +SEC("fexit/bpf_fentry_test2") +int BPF_PROG(test2, int a, __u64 b, int ret) +{ + test2_result = a == 2 && b == 3 && ret == 5; + return 0; +} + +__u64 test3_result = 0; +SEC("fexit/bpf_fentry_test3") +int BPF_PROG(test3, char a, int b, __u64 c, int ret) +{ + test3_result = a == 4 && b == 5 && c == 6 && ret == 15; + return 0; +} + +__u64 test4_result = 0; +SEC("fexit/bpf_fentry_test4") +int BPF_PROG(test4, void *a, char b, int c, __u64 d, int ret) +{ + test4_result = a == (void *)7 && b == 8 && c == 9 && d == 10 && + ret == 34; + return 0; +} + +__u64 test5_result = 0; +SEC("fexit/bpf_fentry_test5") +int BPF_PROG(test5, __u64 a, void *b, short c, int d, __u64 e, int ret) +{ + test5_result = a == 11 && b == (void *)12 && c == 13 && d == 14 && + e == 15 && ret == 65; + return 0; +} + +__u64 test6_result = 0; +SEC("fexit/bpf_fentry_test6") +int BPF_PROG(test6, __u64 a, void *b, short c, int d, void *e, __u64 f, int ret) +{ + test6_result = a == 16 && b == (void *)17 && c == 18 && d == 19 && + e == (void *)20 && f == 21 && ret == 111; + return 0; +} + +struct bpf_fentry_test_t { + struct bpf_fentry_test *a; +}; + +__u64 test7_result = 0; +SEC("fexit/bpf_fentry_test7") +int BPF_PROG(test7, struct bpf_fentry_test_t *arg) +{ + if (!arg) + test7_result = 1; + return 0; +} + +__u64 test8_result = 0; +SEC("fexit/bpf_fentry_test8") +int BPF_PROG(test8, struct bpf_fentry_test_t *arg) +{ + if (!arg->a) + test8_result = 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/fib_lookup.c b/tools/testing/selftests/bpf/progs/fib_lookup.c new file mode 100644 index 0000000000..c4514dd58c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fib_lookup.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <linux/types.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_tracing_net.h" + +struct bpf_fib_lookup fib_params = {}; +int fib_lookup_ret = 0; +int lookup_flags = 0; + +SEC("tc") +int fib_lookup(struct __sk_buff *skb) +{ + fib_lookup_ret = bpf_fib_lookup(skb, &fib_params, sizeof(fib_params), + lookup_flags); + + return TC_ACT_SHOT; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/find_vma.c b/tools/testing/selftests/bpf/progs/find_vma.c new file mode 100644 index 0000000000..38034fb825 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/find_vma.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct callback_ctx { + int dummy; +}; + +#define VM_EXEC 0x00000004 +#define DNAME_INLINE_LEN 32 + +pid_t target_pid = 0; +char d_iname[DNAME_INLINE_LEN] = {0}; +__u32 found_vm_exec = 0; +__u64 addr = 0; +int find_zero_ret = -1; +int find_addr_ret = -1; + +static long check_vma(struct task_struct *task, struct vm_area_struct *vma, + struct callback_ctx *data) +{ + if (vma->vm_file) + bpf_probe_read_kernel_str(d_iname, DNAME_INLINE_LEN - 1, + vma->vm_file->f_path.dentry->d_iname); + + /* check for VM_EXEC */ + if (vma->vm_flags & VM_EXEC) + found_vm_exec = 1; + + return 0; +} + +SEC("raw_tp/sys_enter") +int handle_getpid(void) +{ + struct task_struct *task = bpf_get_current_task_btf(); + struct callback_ctx data = {}; + + if (task->pid != target_pid) + return 0; + + find_addr_ret = bpf_find_vma(task, addr, check_vma, &data, 0); + + /* this should return -ENOENT */ + find_zero_ret = bpf_find_vma(task, 0, check_vma, &data, 0); + return 0; +} + +SEC("perf_event") +int handle_pe(void) +{ + struct task_struct *task = bpf_get_current_task_btf(); + struct callback_ctx data = {}; + + if (task->pid != target_pid) + return 0; + + find_addr_ret = bpf_find_vma(task, addr, check_vma, &data, 0); + + /* In NMI, this should return -EBUSY, as the previous call is using + * the irq_work. + */ + find_zero_ret = bpf_find_vma(task, 0, check_vma, &data, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/find_vma_fail1.c b/tools/testing/selftests/bpf/progs/find_vma_fail1.c new file mode 100644 index 0000000000..7ba9a428f2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/find_vma_fail1.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#define vm_flags vm_start + +char _license[] SEC("license") = "GPL"; + +struct callback_ctx { + int dummy; +}; + +static long write_vma(struct task_struct *task, struct vm_area_struct *vma, + struct callback_ctx *data) +{ + /* writing to vma, which is illegal */ + vma->vm_start = 0xffffffffff600000; + + return 0; +} + +SEC("raw_tp/sys_enter") +int handle_getpid(void) +{ + struct task_struct *task = bpf_get_current_task_btf(); + struct callback_ctx data = {}; + + bpf_find_vma(task, 0, write_vma, &data, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/find_vma_fail2.c b/tools/testing/selftests/bpf/progs/find_vma_fail2.c new file mode 100644 index 0000000000..9bcf3203e2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/find_vma_fail2.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct callback_ctx { + int dummy; +}; + +static long write_task(struct task_struct *task, struct vm_area_struct *vma, + struct callback_ctx *data) +{ + /* writing to task, which is illegal */ + task->mm = NULL; + + return 0; +} + +SEC("raw_tp/sys_enter") +int handle_getpid(void) +{ + struct task_struct *task = bpf_get_current_task_btf(); + struct callback_ctx data = {}; + + bpf_find_vma(task, 0, write_task, &data, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/fmod_ret_freplace.c b/tools/testing/selftests/bpf/progs/fmod_ret_freplace.c new file mode 100644 index 0000000000..c8943ccee6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fmod_ret_freplace.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +volatile __u64 test_fmod_ret = 0; +SEC("fmod_ret/security_new_get_constant") +int BPF_PROG(fmod_ret_test, long val, int ret) +{ + test_fmod_ret = 1; + return 120; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c new file mode 100644 index 0000000000..52f6995ff2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 3); + __type(key, __u32); + __type(value, __u64); +} arraymap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} percpu_map SEC(".maps"); + +struct callback_ctx { + int output; +}; + +const volatile int bypass_unused = 1; + +static __u64 +unused_subprog(struct bpf_map *map, __u32 *key, __u64 *val, + struct callback_ctx *data) +{ + data->output = 0; + return 1; +} + +static __u64 +check_array_elem(struct bpf_map *map, __u32 *key, __u64 *val, + struct callback_ctx *data) +{ + data->output += *val; + if (*key == 1) + return 1; /* stop the iteration */ + return 0; +} + +__u32 cpu = 0; +__u64 percpu_val = 0; + +static __u64 +check_percpu_elem(struct bpf_map *map, __u32 *key, __u64 *val, + struct callback_ctx *data) +{ + cpu = bpf_get_smp_processor_id(); + percpu_val = *val; + return 0; +} + +u32 arraymap_output = 0; + +SEC("tc") +int test_pkt_access(struct __sk_buff *skb) +{ + struct callback_ctx data; + + data.output = 0; + bpf_for_each_map_elem(&arraymap, check_array_elem, &data, 0); + if (!bypass_unused) + bpf_for_each_map_elem(&arraymap, unused_subprog, &data, 0); + arraymap_output = data.output; + + bpf_for_each_map_elem(&percpu_map, check_percpu_elem, (void *)0, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c b/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c new file mode 100644 index 0000000000..276994d5c0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, __u32); + __type(value, __u64); +} hashmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} percpu_map SEC(".maps"); + +struct callback_ctx { + struct __sk_buff *ctx; + int input; + int output; +}; + +static __u64 +check_hash_elem(struct bpf_map *map, __u32 *key, __u64 *val, + struct callback_ctx *data) +{ + struct __sk_buff *skb = data->ctx; + __u32 k; + __u64 v; + + if (skb) { + k = *key; + v = *val; + if (skb->len == 10000 && k == 10 && v == 10) + data->output = 3; /* impossible path */ + else + data->output = 4; + } else { + data->output = data->input; + bpf_map_delete_elem(map, key); + } + + return 0; +} + +__u32 cpu = 0; +__u32 percpu_called = 0; +__u32 percpu_key = 0; +__u64 percpu_val = 0; +int percpu_output = 0; + +static __u64 +check_percpu_elem(struct bpf_map *map, __u32 *key, __u64 *val, + struct callback_ctx *unused) +{ + struct callback_ctx data; + + percpu_called++; + cpu = bpf_get_smp_processor_id(); + percpu_key = *key; + percpu_val = *val; + + data.ctx = 0; + data.input = 100; + data.output = 0; + bpf_for_each_map_elem(&hashmap, check_hash_elem, &data, 0); + percpu_output = data.output; + + return 0; +} + +int hashmap_output = 0; +int hashmap_elems = 0; +int percpu_map_elems = 0; + +SEC("tc") +int test_pkt_access(struct __sk_buff *skb) +{ + struct callback_ctx data; + + data.ctx = skb; + data.input = 10; + data.output = 0; + hashmap_elems = bpf_for_each_map_elem(&hashmap, check_hash_elem, &data, 0); + hashmap_output = data.output; + + percpu_map_elems = bpf_for_each_map_elem(&percpu_map, check_percpu_elem, + (void *)0, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/for_each_map_elem_write_key.c b/tools/testing/selftests/bpf/progs/for_each_map_elem_write_key.c new file mode 100644 index 0000000000..8e545865ea --- /dev/null +++ b/tools/testing/selftests/bpf/progs/for_each_map_elem_write_key.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} array_map SEC(".maps"); + +static __u64 +check_array_elem(struct bpf_map *map, __u32 *key, __u64 *val, + void *data) +{ + bpf_get_current_comm(key, sizeof(*key)); + return 0; +} + +SEC("raw_tp/sys_enter") +int test_map_key_write(const void *ctx) +{ + bpf_for_each_map_elem(&array_map, check_array_elem, NULL, 0); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/freplace_attach_probe.c b/tools/testing/selftests/bpf/progs/freplace_attach_probe.c new file mode 100644 index 0000000000..370a0e1922 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/freplace_attach_probe.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/ptrace.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define VAR_NUM 2 + +struct hmap_elem { + struct bpf_spin_lock lock; + int var[VAR_NUM]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct hmap_elem); +} hash_map SEC(".maps"); + +SEC("freplace/handle_kprobe") +int new_handle_kprobe(struct pt_regs *ctx) +{ + struct hmap_elem *val; + int key = 0; + + val = bpf_map_lookup_elem(&hash_map, &key); + if (!val) + return 1; + /* spin_lock in hash map */ + bpf_spin_lock(&val->lock); + val->var[0] = 99; + bpf_spin_unlock(&val->lock); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c b/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c new file mode 100644 index 0000000000..7e94412d47 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <linux/pkt_cls.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __type(key, int); + __type(value, int); + __uint(max_entries, 2); +} sock_map SEC(".maps"); + +SEC("freplace/cls_redirect") +int freplace_cls_redirect_test(struct __sk_buff *skb) +{ + int ret = 0; + const int zero = 0; + struct bpf_sock *sk; + + sk = bpf_map_lookup_elem(&sock_map, &zero); + if (!sk) + return TC_ACT_SHOT; + + ret = bpf_map_update_elem(&sock_map, &zero, sk, 0); + bpf_sk_release(sk); + + return ret == 0 ? TC_ACT_OK : TC_ACT_SHOT; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/freplace_connect4.c b/tools/testing/selftests/bpf/progs/freplace_connect4.c new file mode 100644 index 0000000000..a0ae842306 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/freplace_connect4.c @@ -0,0 +1,18 @@ +#include <linux/stddef.h> +#include <linux/ipv6.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <sys/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +SEC("freplace/do_bind") +int new_do_bind(struct bpf_sock_addr *ctx) +{ + struct sockaddr_in sa = {}; + + bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c b/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c new file mode 100644 index 0000000000..544e5ac904 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/stddef.h> +#include <linux/ipv6.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <sys/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +SEC("freplace/connect_v4_prog") +int new_connect_v4_prog(struct bpf_sock_addr *ctx) +{ + // return value thats in invalid range + return 255; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/freplace_get_constant.c b/tools/testing/selftests/bpf/progs/freplace_get_constant.c new file mode 100644 index 0000000000..705e4b64df --- /dev/null +++ b/tools/testing/selftests/bpf/progs/freplace_get_constant.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +volatile __u64 test_get_constant = 0; +SEC("freplace/get_constant") +int security_new_get_constant(long val) +{ + if (val != 123) + return 0; + test_get_constant = 1; + return test_get_constant; /* original get_constant() returns val - 122 */ +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/freplace_global_func.c b/tools/testing/selftests/bpf/progs/freplace_global_func.c new file mode 100644 index 0000000000..96cb61a6ce --- /dev/null +++ b/tools/testing/selftests/bpf/progs/freplace_global_func.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__noinline +int test_ctx_global_func(struct __sk_buff *skb) +{ + volatile int retval = 1; + return retval; +} + +SEC("freplace/test_pkt_access") +int new_test_pkt_access(struct __sk_buff *skb) +{ + return test_ctx_global_func(skb); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/freplace_progmap.c b/tools/testing/selftests/bpf/progs/freplace_progmap.c new file mode 100644 index 0000000000..81b56b9aa7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/freplace_progmap.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __type(key, __u32); + __type(value, struct bpf_cpumap_val); + __uint(max_entries, 1); +} cpu_map SEC(".maps"); + +SEC("xdp/cpumap") +int xdp_drop_prog(struct xdp_md *ctx) +{ + return XDP_DROP; +} + +SEC("freplace") +int xdp_cpumap_prog(struct xdp_md *ctx) +{ + return bpf_redirect_map(&cpu_map, 0, XDP_PASS); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/get_branch_snapshot.c b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c new file mode 100644 index 0000000000..511ac634ee --- /dev/null +++ b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +__u64 test1_hits = 0; +__u64 address_low = 0; +__u64 address_high = 0; +int wasted_entries = 0; +long total_entries = 0; + +#define ENTRY_CNT 32 +struct perf_branch_entry entries[ENTRY_CNT] = {}; + +static inline bool gbs_in_range(__u64 val) +{ + return (val >= address_low) && (val < address_high); +} + +SEC("fexit/bpf_testmod_loop_test") +int BPF_PROG(test1, int n, int ret) +{ + long i; + + total_entries = bpf_get_branch_snapshot(entries, sizeof(entries), 0); + total_entries /= sizeof(struct perf_branch_entry); + + for (i = 0; i < ENTRY_CNT; i++) { + if (i >= total_entries) + break; + if (gbs_in_range(entries[i].from) && gbs_in_range(entries[i].to)) + test1_hits++; + else if (!test1_hits) + wasted_entries++; + } + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c new file mode 100644 index 0000000000..68587b1de3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} cg_ids SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} pidmap SEC(".maps"); + +SEC("tracepoint/syscalls/sys_enter_nanosleep") +int trace(void *ctx) +{ + __u32 pid = bpf_get_current_pid_tgid(); + __u32 key = 0, *expected_pid; + __u64 *val; + + expected_pid = bpf_map_lookup_elem(&pidmap, &key); + if (!expected_pid || *expected_pid != pid) + return 0; + + val = bpf_map_lookup_elem(&cg_ids, &key); + if (val) + *val = bpf_get_current_cgroup_id(); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/get_func_args_test.c b/tools/testing/selftests/bpf/progs/get_func_args_test.c new file mode 100644 index 0000000000..e0f34a55e6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/get_func_args_test.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <errno.h> + +char _license[] SEC("license") = "GPL"; + +__u64 test1_result = 0; +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(test1) +{ + __u64 cnt = bpf_get_func_arg_cnt(ctx); + __u64 a = 0, z = 0, ret = 0; + __s64 err; + + test1_result = cnt == 1; + + /* valid arguments */ + err = bpf_get_func_arg(ctx, 0, &a); + + /* We need to cast access to traced function argument values with + * proper type cast, because trampoline uses type specific instruction + * to save it, like for 'int a' with 32-bit mov like: + * + * mov %edi,-0x8(%rbp) + * + * so the upper 4 bytes are not zeroed. + */ + test1_result &= err == 0 && ((int) a == 1); + + /* not valid argument */ + err = bpf_get_func_arg(ctx, 1, &z); + test1_result &= err == -EINVAL; + + /* return value fails in fentry */ + err = bpf_get_func_ret(ctx, &ret); + test1_result &= err == -EOPNOTSUPP; + return 0; +} + +__u64 test2_result = 0; +SEC("fexit/bpf_fentry_test2") +int BPF_PROG(test2) +{ + __u64 cnt = bpf_get_func_arg_cnt(ctx); + __u64 a = 0, b = 0, z = 0, ret = 0; + __s64 err; + + test2_result = cnt == 2; + + /* valid arguments */ + err = bpf_get_func_arg(ctx, 0, &a); + test2_result &= err == 0 && (int) a == 2; + + err = bpf_get_func_arg(ctx, 1, &b); + test2_result &= err == 0 && b == 3; + + /* not valid argument */ + err = bpf_get_func_arg(ctx, 2, &z); + test2_result &= err == -EINVAL; + + /* return value */ + err = bpf_get_func_ret(ctx, &ret); + test2_result &= err == 0 && ret == 5; + return 0; +} + +__u64 test3_result = 0; +SEC("fmod_ret/bpf_modify_return_test") +int BPF_PROG(fmod_ret_test, int _a, int *_b, int _ret) +{ + __u64 cnt = bpf_get_func_arg_cnt(ctx); + __u64 a = 0, b = 0, z = 0, ret = 0; + __s64 err; + + test3_result = cnt == 2; + + /* valid arguments */ + err = bpf_get_func_arg(ctx, 0, &a); + test3_result &= err == 0 && ((int) a == 1); + + err = bpf_get_func_arg(ctx, 1, &b); + test3_result &= err == 0 && ((int *) b == _b); + + /* not valid argument */ + err = bpf_get_func_arg(ctx, 2, &z); + test3_result &= err == -EINVAL; + + /* return value */ + err = bpf_get_func_ret(ctx, &ret); + test3_result &= err == 0 && ret == 0; + + /* change return value, it's checked in fexit_test program */ + return 1234; +} + +__u64 test4_result = 0; +SEC("fexit/bpf_modify_return_test") +int BPF_PROG(fexit_test, int _a, int *_b, int _ret) +{ + __u64 cnt = bpf_get_func_arg_cnt(ctx); + __u64 a = 0, b = 0, z = 0, ret = 0; + __s64 err; + + test4_result = cnt == 2; + + /* valid arguments */ + err = bpf_get_func_arg(ctx, 0, &a); + test4_result &= err == 0 && ((int) a == 1); + + err = bpf_get_func_arg(ctx, 1, &b); + test4_result &= err == 0 && ((int *) b == _b); + + /* not valid argument */ + err = bpf_get_func_arg(ctx, 2, &z); + test4_result &= err == -EINVAL; + + /* return value */ + err = bpf_get_func_ret(ctx, &ret); + test4_result &= err == 0 && ret == 1234; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/get_func_ip_test.c b/tools/testing/selftests/bpf/progs/get_func_ip_test.c new file mode 100644 index 0000000000..8956eb78a2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/get_func_ip_test.c @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +extern const void bpf_fentry_test1 __ksym; +extern const void bpf_fentry_test2 __ksym; +extern const void bpf_fentry_test3 __ksym; +extern const void bpf_fentry_test4 __ksym; +extern const void bpf_modify_return_test __ksym; +extern const void bpf_fentry_test6 __ksym; +extern const void bpf_fentry_test7 __ksym; + +extern bool CONFIG_X86_KERNEL_IBT __kconfig __weak; + +/* This function is here to have CONFIG_X86_KERNEL_IBT + * used and added to object BTF. + */ +int unused(void) +{ + return CONFIG_X86_KERNEL_IBT ? 0 : 1; +} + +__u64 test1_result = 0; +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(test1, int a) +{ + __u64 addr = bpf_get_func_ip(ctx); + + test1_result = (const void *) addr == &bpf_fentry_test1; + return 0; +} + +__u64 test2_result = 0; +SEC("fexit/bpf_fentry_test2") +int BPF_PROG(test2, int a) +{ + __u64 addr = bpf_get_func_ip(ctx); + + test2_result = (const void *) addr == &bpf_fentry_test2; + return 0; +} + +__u64 test3_result = 0; +SEC("kprobe/bpf_fentry_test3") +int test3(struct pt_regs *ctx) +{ + __u64 addr = bpf_get_func_ip(ctx); + + test3_result = (const void *) addr == &bpf_fentry_test3; + return 0; +} + +__u64 test4_result = 0; +SEC("kretprobe/bpf_fentry_test4") +int BPF_KRETPROBE(test4) +{ + __u64 addr = bpf_get_func_ip(ctx); + + test4_result = (const void *) addr == &bpf_fentry_test4; + return 0; +} + +__u64 test5_result = 0; +SEC("fmod_ret/bpf_modify_return_test") +int BPF_PROG(test5, int a, int *b, int ret) +{ + __u64 addr = bpf_get_func_ip(ctx); + + test5_result = (const void *) addr == &bpf_modify_return_test; + return ret; +} + +__u64 test6_result = 0; +SEC("?kprobe") +int test6(struct pt_regs *ctx) +{ + __u64 addr = bpf_get_func_ip(ctx); + + test6_result = (const void *) addr == 0; + return 0; +} + +unsigned long uprobe_trigger; + +__u64 test7_result = 0; +SEC("uprobe//proc/self/exe:uprobe_trigger") +int BPF_UPROBE(test7) +{ + __u64 addr = bpf_get_func_ip(ctx); + + test7_result = (const void *) addr == (const void *) uprobe_trigger; + return 0; +} + +__u64 test8_result = 0; +SEC("uretprobe//proc/self/exe:uprobe_trigger") +int BPF_URETPROBE(test8, int ret) +{ + __u64 addr = bpf_get_func_ip(ctx); + + test8_result = (const void *) addr == (const void *) uprobe_trigger; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/get_func_ip_uprobe_test.c b/tools/testing/selftests/bpf/progs/get_func_ip_uprobe_test.c new file mode 100644 index 0000000000..052f8a4345 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/get_func_ip_uprobe_test.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +unsigned long uprobe_trigger_body; + +__u64 test1_result = 0; +SEC("uprobe//proc/self/exe:uprobe_trigger_body+1") +int BPF_UPROBE(test1) +{ + __u64 addr = bpf_get_func_ip(ctx); + + test1_result = (const void *) addr == (const void *) uprobe_trigger_body + 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/htab_mem_bench.c b/tools/testing/selftests/bpf/progs/htab_mem_bench.c new file mode 100644 index 0000000000..b1b721b14d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/htab_mem_bench.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#include <stdbool.h> +#include <errno.h> +#include <linux/types.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define OP_BATCH 64 + +struct update_ctx { + unsigned int from; + unsigned int step; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, 4); + __uint(map_flags, BPF_F_NO_PREALLOC); +} htab SEC(".maps"); + +char _license[] SEC("license") = "GPL"; + +unsigned char zeroed_value[4096]; +unsigned int nr_thread = 0; +long op_cnt = 0; + +static int write_htab(unsigned int i, struct update_ctx *ctx, unsigned int flags) +{ + bpf_map_update_elem(&htab, &ctx->from, zeroed_value, flags); + ctx->from += ctx->step; + + return 0; +} + +static int overwrite_htab(unsigned int i, struct update_ctx *ctx) +{ + return write_htab(i, ctx, 0); +} + +static int newwrite_htab(unsigned int i, struct update_ctx *ctx) +{ + return write_htab(i, ctx, BPF_NOEXIST); +} + +static int del_htab(unsigned int i, struct update_ctx *ctx) +{ + bpf_map_delete_elem(&htab, &ctx->from); + ctx->from += ctx->step; + + return 0; +} + +SEC("?tp/syscalls/sys_enter_getpgid") +int overwrite(void *ctx) +{ + struct update_ctx update; + + update.from = bpf_get_smp_processor_id(); + update.step = nr_thread; + bpf_loop(OP_BATCH, overwrite_htab, &update, 0); + __sync_fetch_and_add(&op_cnt, 1); + return 0; +} + +SEC("?tp/syscalls/sys_enter_getpgid") +int batch_add_batch_del(void *ctx) +{ + struct update_ctx update; + + update.from = bpf_get_smp_processor_id(); + update.step = nr_thread; + bpf_loop(OP_BATCH, overwrite_htab, &update, 0); + + update.from = bpf_get_smp_processor_id(); + bpf_loop(OP_BATCH, del_htab, &update, 0); + + __sync_fetch_and_add(&op_cnt, 2); + return 0; +} + +SEC("?tp/syscalls/sys_enter_getpgid") +int add_only(void *ctx) +{ + struct update_ctx update; + + update.from = bpf_get_smp_processor_id() / 2; + update.step = nr_thread / 2; + bpf_loop(OP_BATCH, newwrite_htab, &update, 0); + __sync_fetch_and_add(&op_cnt, 1); + return 0; +} + +SEC("?tp/syscalls/sys_enter_getppid") +int del_only(void *ctx) +{ + struct update_ctx update; + + update.from = bpf_get_smp_processor_id() / 2; + update.step = nr_thread / 2; + bpf_loop(OP_BATCH, del_htab, &update, 0); + __sync_fetch_and_add(&op_cnt, 1); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/htab_reuse.c b/tools/testing/selftests/bpf/progs/htab_reuse.c new file mode 100644 index 0000000000..7f7368cb30 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/htab_reuse.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct htab_val { + struct bpf_spin_lock lock; + unsigned int data; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 64); + __type(key, unsigned int); + __type(value, struct htab_val); + __uint(map_flags, BPF_F_NO_PREALLOC); +} htab SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/htab_update.c b/tools/testing/selftests/bpf/progs/htab_update.c new file mode 100644 index 0000000000..7481bb30b2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/htab_update.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2022. Huawei Technologies Co., Ltd */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} htab SEC(".maps"); + +int pid = 0; +int update_err = 0; + +SEC("?fentry/lookup_elem_raw") +int lookup_elem_raw(void *ctx) +{ + __u32 key = 0, value = 1; + + if ((bpf_get_current_pid_tgid() >> 32) != pid) + return 0; + + update_err = bpf_map_update_elem(&htab, &key, &value, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/ima.c b/tools/testing/selftests/bpf/progs/ima.c new file mode 100644 index 0000000000..e16a2c2084 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/ima.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2020 Google LLC. + */ + +#include "vmlinux.h" +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +u32 monitored_pid = 0; + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 1 << 12); +} ringbuf SEC(".maps"); + +char _license[] SEC("license") = "GPL"; + +bool use_ima_file_hash; +bool enable_bprm_creds_for_exec; +bool enable_kernel_read_file; +bool test_deny; + +static void ima_test_common(struct file *file) +{ + u64 ima_hash = 0; + u64 *sample; + int ret; + u32 pid; + + pid = bpf_get_current_pid_tgid() >> 32; + if (pid == monitored_pid) { + if (!use_ima_file_hash) + ret = bpf_ima_inode_hash(file->f_inode, &ima_hash, + sizeof(ima_hash)); + else + ret = bpf_ima_file_hash(file, &ima_hash, + sizeof(ima_hash)); + if (ret < 0 || ima_hash == 0) + return; + + sample = bpf_ringbuf_reserve(&ringbuf, sizeof(u64), 0); + if (!sample) + return; + + *sample = ima_hash; + bpf_ringbuf_submit(sample, 0); + } + + return; +} + +static int ima_test_deny(void) +{ + u32 pid; + + pid = bpf_get_current_pid_tgid() >> 32; + if (pid == monitored_pid && test_deny) + return -EPERM; + + return 0; +} + +SEC("lsm.s/bprm_committed_creds") +void BPF_PROG(bprm_committed_creds, struct linux_binprm *bprm) +{ + ima_test_common(bprm->file); +} + +SEC("lsm.s/bprm_creds_for_exec") +int BPF_PROG(bprm_creds_for_exec, struct linux_binprm *bprm) +{ + if (!enable_bprm_creds_for_exec) + return 0; + + ima_test_common(bprm->file); + return 0; +} + +SEC("lsm.s/kernel_read_file") +int BPF_PROG(kernel_read_file, struct file *file, enum kernel_read_file_id id, + bool contents) +{ + int ret; + + if (!enable_kernel_read_file) + return 0; + + if (!contents) + return 0; + + if (id != READING_POLICY) + return 0; + + ret = ima_test_deny(); + if (ret < 0) + return ret; + + ima_test_common(file); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/inner_array_lookup.c b/tools/testing/selftests/bpf/progs/inner_array_lookup.c new file mode 100644 index 0000000000..c2c8f2fa45 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/inner_array_lookup.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct inner_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, int); + __type(value, int); +} inner_map1 SEC(".maps"); + +struct outer_map { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 3); + __type(key, int); + __array(values, struct inner_map); +} outer_map1 SEC(".maps") = { + .values = { + [2] = &inner_map1, + }, +}; + +SEC("raw_tp/sys_enter") +int handle__sys_enter(void *ctx) +{ + int outer_key = 2, inner_key = 3; + int *val; + void *map; + + map = bpf_map_lookup_elem(&outer_map1, &outer_key); + if (!map) + return 1; + + val = bpf_map_lookup_elem(map, &inner_key); + if (!val) + return 1; + + if (*val == 1) + *val = 2; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/ip_check_defrag.c b/tools/testing/selftests/bpf/progs/ip_check_defrag.c new file mode 100644 index 0000000000..1c2b6c1616 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/ip_check_defrag.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include "bpf_tracing_net.h" + +#define NF_DROP 0 +#define NF_ACCEPT 1 +#define ETH_P_IP 0x0800 +#define ETH_P_IPV6 0x86DD +#define IP_MF 0x2000 +#define IP_OFFSET 0x1FFF +#define NEXTHDR_FRAGMENT 44 + +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; + +volatile int shootdowns = 0; + +static bool is_frag_v4(struct iphdr *iph) +{ + int offset; + int flags; + + offset = bpf_ntohs(iph->frag_off); + flags = offset & ~IP_OFFSET; + offset &= IP_OFFSET; + offset <<= 3; + + return (flags & IP_MF) || offset; +} + +static bool is_frag_v6(struct ipv6hdr *ip6h) +{ + /* Simplifying assumption that there are no extension headers + * between fixed header and fragmentation header. This assumption + * is only valid in this test case. It saves us the hassle of + * searching all potential extension headers. + */ + return ip6h->nexthdr == NEXTHDR_FRAGMENT; +} + +static int handle_v4(struct sk_buff *skb) +{ + struct bpf_dynptr ptr; + u8 iph_buf[20] = {}; + struct iphdr *iph; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) + return NF_DROP; + + iph = bpf_dynptr_slice(&ptr, 0, iph_buf, sizeof(iph_buf)); + if (!iph) + return NF_DROP; + + /* Shootdown any frags */ + if (is_frag_v4(iph)) { + shootdowns++; + return NF_DROP; + } + + return NF_ACCEPT; +} + +static int handle_v6(struct sk_buff *skb) +{ + struct bpf_dynptr ptr; + struct ipv6hdr *ip6h; + u8 ip6h_buf[40] = {}; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) + return NF_DROP; + + ip6h = bpf_dynptr_slice(&ptr, 0, ip6h_buf, sizeof(ip6h_buf)); + if (!ip6h) + return NF_DROP; + + /* Shootdown any frags */ + if (is_frag_v6(ip6h)) { + shootdowns++; + return NF_DROP; + } + + return NF_ACCEPT; +} + +SEC("netfilter") +int defrag(struct bpf_nf_ctx *ctx) +{ + struct sk_buff *skb = ctx->skb; + + switch (bpf_ntohs(skb->protocol)) { + case ETH_P_IP: + return handle_v4(skb); + case ETH_P_IPV6: + return handle_v6(skb); + default: + return NF_ACCEPT; + } +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c new file mode 100644 index 0000000000..c20c4e38b7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -0,0 +1,1414 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +static volatile int zero = 0; + +int my_pid; +int arr[256]; +int small_arr[16] SEC(".data.small_arr"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 10); + __type(key, int); + __type(value, int); +} amap SEC(".maps"); + +#ifdef REAL_TEST +#define MY_PID_GUARD() if (my_pid != (bpf_get_current_pid_tgid() >> 32)) return 0 +#else +#define MY_PID_GUARD() ({ }) +#endif + +SEC("?raw_tp") +__failure __msg("math between map_value pointer and register with unbounded min value is not allowed") +int iter_err_unsafe_c_loop(const void *ctx) +{ + struct bpf_iter_num it; + int *v, i = zero; /* obscure initial value of i */ + + MY_PID_GUARD(); + + bpf_iter_num_new(&it, 0, 1000); + while ((v = bpf_iter_num_next(&it))) { + i++; + } + bpf_iter_num_destroy(&it); + + small_arr[i] = 123; /* invalid */ + + return 0; +} + +SEC("?raw_tp") +__failure __msg("unbounded memory access") +int iter_err_unsafe_asm_loop(const void *ctx) +{ + struct bpf_iter_num it; + + MY_PID_GUARD(); + + asm volatile ( + "r6 = %[zero];" /* iteration counter */ + "r1 = %[it];" /* iterator state */ + "r2 = 0;" + "r3 = 1000;" + "r4 = 1;" + "call %[bpf_iter_num_new];" + "loop:" + "r1 = %[it];" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto out;" + "r6 += 1;" + "goto loop;" + "out:" + "r1 = %[it];" + "call %[bpf_iter_num_destroy];" + "r1 = %[small_arr];" + "r2 = r6;" + "r2 <<= 2;" + "r1 += r2;" + "*(u32 *)(r1 + 0) = r6;" /* invalid */ + : + : [it]"r"(&it), + [small_arr]"p"(small_arr), + [zero]"p"(zero), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy) + : __clobber_common, "r6" + ); + + return 0; +} + +SEC("raw_tp") +__success +int iter_while_loop(const void *ctx) +{ + struct bpf_iter_num it; + int *v; + + MY_PID_GUARD(); + + bpf_iter_num_new(&it, 0, 3); + while ((v = bpf_iter_num_next(&it))) { + bpf_printk("ITER_BASIC: E1 VAL: v=%d", *v); + } + bpf_iter_num_destroy(&it); + + return 0; +} + +SEC("raw_tp") +__success +int iter_while_loop_auto_cleanup(const void *ctx) +{ + __attribute__((cleanup(bpf_iter_num_destroy))) struct bpf_iter_num it; + int *v; + + MY_PID_GUARD(); + + bpf_iter_num_new(&it, 0, 3); + while ((v = bpf_iter_num_next(&it))) { + bpf_printk("ITER_BASIC: E1 VAL: v=%d", *v); + } + /* (!) no explicit bpf_iter_num_destroy() */ + + return 0; +} + +SEC("raw_tp") +__success +int iter_for_loop(const void *ctx) +{ + struct bpf_iter_num it; + int *v; + + MY_PID_GUARD(); + + bpf_iter_num_new(&it, 5, 10); + for (v = bpf_iter_num_next(&it); v; v = bpf_iter_num_next(&it)) { + bpf_printk("ITER_BASIC: E2 VAL: v=%d", *v); + } + bpf_iter_num_destroy(&it); + + return 0; +} + +SEC("raw_tp") +__success +int iter_bpf_for_each_macro(const void *ctx) +{ + int *v; + + MY_PID_GUARD(); + + bpf_for_each(num, v, 5, 10) { + bpf_printk("ITER_BASIC: E2 VAL: v=%d", *v); + } + + return 0; +} + +SEC("raw_tp") +__success +int iter_bpf_for_macro(const void *ctx) +{ + int i; + + MY_PID_GUARD(); + + bpf_for(i, 5, 10) { + bpf_printk("ITER_BASIC: E2 VAL: v=%d", i); + } + + return 0; +} + +SEC("raw_tp") +__success +int iter_pragma_unroll_loop(const void *ctx) +{ + struct bpf_iter_num it; + int *v, i; + + MY_PID_GUARD(); + + bpf_iter_num_new(&it, 0, 2); +#pragma nounroll + for (i = 0; i < 3; i++) { + v = bpf_iter_num_next(&it); + bpf_printk("ITER_BASIC: E3 VAL: i=%d v=%d", i, v ? *v : -1); + } + bpf_iter_num_destroy(&it); + + return 0; +} + +SEC("raw_tp") +__success +int iter_manual_unroll_loop(const void *ctx) +{ + struct bpf_iter_num it; + int *v; + + MY_PID_GUARD(); + + bpf_iter_num_new(&it, 100, 200); + v = bpf_iter_num_next(&it); + bpf_printk("ITER_BASIC: E4 VAL: v=%d", v ? *v : -1); + v = bpf_iter_num_next(&it); + bpf_printk("ITER_BASIC: E4 VAL: v=%d", v ? *v : -1); + v = bpf_iter_num_next(&it); + bpf_printk("ITER_BASIC: E4 VAL: v=%d", v ? *v : -1); + v = bpf_iter_num_next(&it); + bpf_printk("ITER_BASIC: E4 VAL: v=%d\n", v ? *v : -1); + bpf_iter_num_destroy(&it); + + return 0; +} + +SEC("raw_tp") +__success +int iter_multiple_sequential_loops(const void *ctx) +{ + struct bpf_iter_num it; + int *v, i; + + MY_PID_GUARD(); + + bpf_iter_num_new(&it, 0, 3); + while ((v = bpf_iter_num_next(&it))) { + bpf_printk("ITER_BASIC: E1 VAL: v=%d", *v); + } + bpf_iter_num_destroy(&it); + + bpf_iter_num_new(&it, 5, 10); + for (v = bpf_iter_num_next(&it); v; v = bpf_iter_num_next(&it)) { + bpf_printk("ITER_BASIC: E2 VAL: v=%d", *v); + } + bpf_iter_num_destroy(&it); + + bpf_iter_num_new(&it, 0, 2); +#pragma nounroll + for (i = 0; i < 3; i++) { + v = bpf_iter_num_next(&it); + bpf_printk("ITER_BASIC: E3 VAL: i=%d v=%d", i, v ? *v : -1); + } + bpf_iter_num_destroy(&it); + + bpf_iter_num_new(&it, 100, 200); + v = bpf_iter_num_next(&it); + bpf_printk("ITER_BASIC: E4 VAL: v=%d", v ? *v : -1); + v = bpf_iter_num_next(&it); + bpf_printk("ITER_BASIC: E4 VAL: v=%d", v ? *v : -1); + v = bpf_iter_num_next(&it); + bpf_printk("ITER_BASIC: E4 VAL: v=%d", v ? *v : -1); + v = bpf_iter_num_next(&it); + bpf_printk("ITER_BASIC: E4 VAL: v=%d\n", v ? *v : -1); + bpf_iter_num_destroy(&it); + + return 0; +} + +SEC("raw_tp") +__success +int iter_limit_cond_break_loop(const void *ctx) +{ + struct bpf_iter_num it; + int *v, i = 0, sum = 0; + + MY_PID_GUARD(); + + bpf_iter_num_new(&it, 0, 10); + while ((v = bpf_iter_num_next(&it))) { + bpf_printk("ITER_SIMPLE: i=%d v=%d", i, *v); + sum += *v; + + i++; + if (i > 3) + break; + } + bpf_iter_num_destroy(&it); + + bpf_printk("ITER_SIMPLE: sum=%d\n", sum); + + return 0; +} + +SEC("raw_tp") +__success +int iter_obfuscate_counter(const void *ctx) +{ + struct bpf_iter_num it; + int *v, sum = 0; + /* Make i's initial value unknowable for verifier to prevent it from + * pruning if/else branch inside the loop body and marking i as precise. + */ + int i = zero; + + MY_PID_GUARD(); + + bpf_iter_num_new(&it, 0, 10); + while ((v = bpf_iter_num_next(&it))) { + int x; + + i += 1; + + /* If we initialized i as `int i = 0;` above, verifier would + * track that i becomes 1 on first iteration after increment + * above, and here verifier would eagerly prune else branch + * and mark i as precise, ruining open-coded iterator logic + * completely, as each next iteration would have a different + * *precise* value of i, and thus there would be no + * convergence of state. This would result in reaching maximum + * instruction limit, no matter what the limit is. + */ + if (i == 1) + x = 123; + else + x = i * 3 + 1; + + bpf_printk("ITER_OBFUSCATE_COUNTER: i=%d v=%d x=%d", i, *v, x); + + sum += x; + } + bpf_iter_num_destroy(&it); + + bpf_printk("ITER_OBFUSCATE_COUNTER: sum=%d\n", sum); + + return 0; +} + +SEC("raw_tp") +__success +int iter_search_loop(const void *ctx) +{ + struct bpf_iter_num it; + int *v, *elem = NULL; + bool found = false; + + MY_PID_GUARD(); + + bpf_iter_num_new(&it, 0, 10); + + while ((v = bpf_iter_num_next(&it))) { + bpf_printk("ITER_SEARCH_LOOP: v=%d", *v); + + if (*v == 2) { + found = true; + elem = v; + barrier_var(elem); + } + } + + /* should fail to verify if bpf_iter_num_destroy() is here */ + + if (found) + /* here found element will be wrong, we should have copied + * value to a variable, but here we want to make sure we can + * access memory after the loop anyways + */ + bpf_printk("ITER_SEARCH_LOOP: FOUND IT = %d!\n", *elem); + else + bpf_printk("ITER_SEARCH_LOOP: NOT FOUND IT!\n"); + + bpf_iter_num_destroy(&it); + + return 0; +} + +SEC("raw_tp") +__success +int iter_array_fill(const void *ctx) +{ + int sum, i; + + MY_PID_GUARD(); + + bpf_for(i, 0, ARRAY_SIZE(arr)) { + arr[i] = i * 2; + } + + sum = 0; + bpf_for(i, 0, ARRAY_SIZE(arr)) { + sum += arr[i]; + } + + bpf_printk("ITER_ARRAY_FILL: sum=%d (should be %d)\n", sum, 255 * 256); + + return 0; +} + +static int arr2d[4][5]; +static int arr2d_row_sums[4]; +static int arr2d_col_sums[5]; + +SEC("raw_tp") +__success +int iter_nested_iters(const void *ctx) +{ + int sum, row, col; + + MY_PID_GUARD(); + + bpf_for(row, 0, ARRAY_SIZE(arr2d)) { + bpf_for( col, 0, ARRAY_SIZE(arr2d[0])) { + arr2d[row][col] = row * col; + } + } + + /* zero-initialize sums */ + sum = 0; + bpf_for(row, 0, ARRAY_SIZE(arr2d)) { + arr2d_row_sums[row] = 0; + } + bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) { + arr2d_col_sums[col] = 0; + } + + /* calculate sums */ + bpf_for(row, 0, ARRAY_SIZE(arr2d)) { + bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) { + sum += arr2d[row][col]; + arr2d_row_sums[row] += arr2d[row][col]; + arr2d_col_sums[col] += arr2d[row][col]; + } + } + + bpf_printk("ITER_NESTED_ITERS: total sum=%d", sum); + bpf_for(row, 0, ARRAY_SIZE(arr2d)) { + bpf_printk("ITER_NESTED_ITERS: row #%d sum=%d", row, arr2d_row_sums[row]); + } + bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) { + bpf_printk("ITER_NESTED_ITERS: col #%d sum=%d%s", + col, arr2d_col_sums[col], + col == ARRAY_SIZE(arr2d[0]) - 1 ? "\n" : ""); + } + + return 0; +} + +SEC("raw_tp") +__success +int iter_nested_deeply_iters(const void *ctx) +{ + int sum = 0; + + MY_PID_GUARD(); + + bpf_repeat(10) { + bpf_repeat(10) { + bpf_repeat(10) { + bpf_repeat(10) { + bpf_repeat(10) { + sum += 1; + } + } + } + } + /* validate that we can break from inside bpf_repeat() */ + break; + } + + return sum; +} + +static __noinline void fill_inner_dimension(int row) +{ + int col; + + bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) { + arr2d[row][col] = row * col; + } +} + +static __noinline int sum_inner_dimension(int row) +{ + int sum = 0, col; + + bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) { + sum += arr2d[row][col]; + arr2d_row_sums[row] += arr2d[row][col]; + arr2d_col_sums[col] += arr2d[row][col]; + } + + return sum; +} + +SEC("raw_tp") +__success +int iter_subprog_iters(const void *ctx) +{ + int sum, row, col; + + MY_PID_GUARD(); + + bpf_for(row, 0, ARRAY_SIZE(arr2d)) { + fill_inner_dimension(row); + } + + /* zero-initialize sums */ + sum = 0; + bpf_for(row, 0, ARRAY_SIZE(arr2d)) { + arr2d_row_sums[row] = 0; + } + bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) { + arr2d_col_sums[col] = 0; + } + + /* calculate sums */ + bpf_for(row, 0, ARRAY_SIZE(arr2d)) { + sum += sum_inner_dimension(row); + } + + bpf_printk("ITER_SUBPROG_ITERS: total sum=%d", sum); + bpf_for(row, 0, ARRAY_SIZE(arr2d)) { + bpf_printk("ITER_SUBPROG_ITERS: row #%d sum=%d", + row, arr2d_row_sums[row]); + } + bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) { + bpf_printk("ITER_SUBPROG_ITERS: col #%d sum=%d%s", + col, arr2d_col_sums[col], + col == ARRAY_SIZE(arr2d[0]) - 1 ? "\n" : ""); + } + + return 0; +} + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, int); + __uint(max_entries, 1000); +} arr_map SEC(".maps"); + +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int iter_err_too_permissive1(const void *ctx) +{ + int *map_val = NULL; + int key = 0; + + MY_PID_GUARD(); + + map_val = bpf_map_lookup_elem(&arr_map, &key); + if (!map_val) + return 0; + + bpf_repeat(1000000) { + map_val = NULL; + } + + *map_val = 123; + + return 0; +} + +SEC("?raw_tp") +__failure __msg("invalid mem access 'map_value_or_null'") +int iter_err_too_permissive2(const void *ctx) +{ + int *map_val = NULL; + int key = 0; + + MY_PID_GUARD(); + + map_val = bpf_map_lookup_elem(&arr_map, &key); + if (!map_val) + return 0; + + bpf_repeat(1000000) { + map_val = bpf_map_lookup_elem(&arr_map, &key); + } + + *map_val = 123; + + return 0; +} + +SEC("?raw_tp") +__failure __msg("invalid mem access 'map_value_or_null'") +int iter_err_too_permissive3(const void *ctx) +{ + int *map_val = NULL; + int key = 0; + bool found = false; + + MY_PID_GUARD(); + + bpf_repeat(1000000) { + map_val = bpf_map_lookup_elem(&arr_map, &key); + found = true; + } + + if (found) + *map_val = 123; + + return 0; +} + +SEC("raw_tp") +__success +int iter_tricky_but_fine(const void *ctx) +{ + int *map_val = NULL; + int key = 0; + bool found = false; + + MY_PID_GUARD(); + + bpf_repeat(1000000) { + map_val = bpf_map_lookup_elem(&arr_map, &key); + if (map_val) { + found = true; + break; + } + } + + if (found) + *map_val = 123; + + return 0; +} + +#define __bpf_memzero(p, sz) bpf_probe_read_kernel((p), (sz), 0) + +SEC("raw_tp") +__success +int iter_stack_array_loop(const void *ctx) +{ + long arr1[16], arr2[16], sum = 0; + int i; + + MY_PID_GUARD(); + + /* zero-init arr1 and arr2 in such a way that verifier doesn't know + * it's all zeros; if we don't do that, we'll make BPF verifier track + * all combination of zero/non-zero stack slots for arr1/arr2, which + * will lead to O(2^(ARRAY_SIZE(arr1)+ARRAY_SIZE(arr2))) different + * states + */ + __bpf_memzero(arr1, sizeof(arr1)); + __bpf_memzero(arr2, sizeof(arr1)); + + /* validate that we can break and continue when using bpf_for() */ + bpf_for(i, 0, ARRAY_SIZE(arr1)) { + if (i & 1) { + arr1[i] = i; + continue; + } else { + arr2[i] = i; + break; + } + } + + bpf_for(i, 0, ARRAY_SIZE(arr1)) { + sum += arr1[i] + arr2[i]; + } + + return sum; +} + +static __noinline void fill(struct bpf_iter_num *it, int *arr, __u32 n, int mul) +{ + int *t, i; + + while ((t = bpf_iter_num_next(it))) { + i = *t; + if (i >= n) + break; + arr[i] = i * mul; + } +} + +static __noinline int sum(struct bpf_iter_num *it, int *arr, __u32 n) +{ + int *t, i, sum = 0;; + + while ((t = bpf_iter_num_next(it))) { + i = *t; + if (i >= n) + break; + sum += arr[i]; + } + + return sum; +} + +SEC("raw_tp") +__success +int iter_pass_iter_ptr_to_subprog(const void *ctx) +{ + int arr1[16], arr2[32]; + struct bpf_iter_num it; + int n, sum1, sum2; + + MY_PID_GUARD(); + + /* fill arr1 */ + n = ARRAY_SIZE(arr1); + bpf_iter_num_new(&it, 0, n); + fill(&it, arr1, n, 2); + bpf_iter_num_destroy(&it); + + /* fill arr2 */ + n = ARRAY_SIZE(arr2); + bpf_iter_num_new(&it, 0, n); + fill(&it, arr2, n, 10); + bpf_iter_num_destroy(&it); + + /* sum arr1 */ + n = ARRAY_SIZE(arr1); + bpf_iter_num_new(&it, 0, n); + sum1 = sum(&it, arr1, n); + bpf_iter_num_destroy(&it); + + /* sum arr2 */ + n = ARRAY_SIZE(arr2); + bpf_iter_num_new(&it, 0, n); + sum2 = sum(&it, arr2, n); + bpf_iter_num_destroy(&it); + + bpf_printk("sum1=%d, sum2=%d", sum1, sum2); + + return 0; +} + +SEC("?raw_tp") +__failure +__msg("R1 type=scalar expected=fp") +__naked int delayed_read_mark(void) +{ + /* This is equivalent to C program below. + * The call to bpf_iter_num_next() is reachable with r7 values &fp[-16] and 0xdead. + * State with r7=&fp[-16] is visited first and follows r6 != 42 ... continue branch. + * At this point iterator next() call is reached with r7 that has no read mark. + * Loop body with r7=0xdead would only be visited if verifier would decide to continue + * with second loop iteration. Absence of read mark on r7 might affect state + * equivalent logic used for iterator convergence tracking. + * + * r7 = &fp[-16] + * fp[-16] = 0 + * r6 = bpf_get_prandom_u32() + * bpf_iter_num_new(&fp[-8], 0, 10) + * while (bpf_iter_num_next(&fp[-8])) { + * r6++ + * if (r6 != 42) { + * r7 = 0xdead + * continue; + * } + * bpf_probe_read_user(r7, 8, 0xdeadbeef); // this is not safe + * } + * bpf_iter_num_destroy(&fp[-8]) + * return 0 + */ + asm volatile ( + "r7 = r10;" + "r7 += -16;" + "r0 = 0;" + "*(u64 *)(r7 + 0) = r0;" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "1:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto 2f;" + "r6 += 1;" + "if r6 != 42 goto 3f;" + "r7 = 0xdead;" + "goto 1b;" + "3:" + "r1 = r7;" + "r2 = 8;" + "r3 = 0xdeadbeef;" + "call %[bpf_probe_read_user];" + "goto 1b;" + "2:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy), + __imm(bpf_probe_read_user) + : __clobber_all + ); +} + +SEC("?raw_tp") +__failure +__msg("math between fp pointer and register with unbounded") +__naked int delayed_precision_mark(void) +{ + /* This is equivalent to C program below. + * The test is similar to delayed_iter_mark but verifies that incomplete + * precision don't fool verifier. + * The call to bpf_iter_num_next() is reachable with r7 values -16 and -32. + * State with r7=-16 is visited first and follows r6 != 42 ... continue branch. + * At this point iterator next() call is reached with r7 that has no read + * and precision marks. + * Loop body with r7=-32 would only be visited if verifier would decide to continue + * with second loop iteration. Absence of precision mark on r7 might affect state + * equivalent logic used for iterator convergence tracking. + * + * r8 = 0 + * fp[-16] = 0 + * r7 = -16 + * r6 = bpf_get_prandom_u32() + * bpf_iter_num_new(&fp[-8], 0, 10) + * while (bpf_iter_num_next(&fp[-8])) { + * if (r6 != 42) { + * r7 = -32 + * r6 = bpf_get_prandom_u32() + * continue; + * } + * r0 = r10 + * r0 += r7 + * r8 = *(u64 *)(r0 + 0) // this is not safe + * r6 = bpf_get_prandom_u32() + * } + * bpf_iter_num_destroy(&fp[-8]) + * return r8 + */ + asm volatile ( + "r8 = 0;" + "*(u64 *)(r10 - 16) = r8;" + "r7 = -16;" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "1:" + "r1 = r10;" + "r1 += -8;\n" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto 2f;" + "if r6 != 42 goto 3f;" + "r7 = -32;" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "goto 1b;\n" + "3:" + "r0 = r10;" + "r0 += r7;" + "r8 = *(u64 *)(r0 + 0);" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "goto 1b;\n" + "2:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = r8;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy), + __imm(bpf_probe_read_user) + : __clobber_all + ); +} + +SEC("?raw_tp") +__failure +__msg("math between fp pointer and register with unbounded") +__flag(BPF_F_TEST_STATE_FREQ) +__naked int loop_state_deps1(void) +{ + /* This is equivalent to C program below. + * + * The case turns out to be tricky in a sense that: + * - states with c=-25 are explored only on a second iteration + * of the outer loop; + * - states with read+precise mark on c are explored only on + * second iteration of the inner loop and in a state which + * is pushed to states stack first. + * + * Depending on the details of iterator convergence logic + * verifier might stop states traversal too early and miss + * unsafe c=-25 memory access. + * + * j = iter_new(); // fp[-16] + * a = 0; // r6 + * b = 0; // r7 + * c = -24; // r8 + * while (iter_next(j)) { + * i = iter_new(); // fp[-8] + * a = 0; // r6 + * b = 0; // r7 + * while (iter_next(i)) { + * if (a == 1) { + * a = 0; + * b = 1; + * } else if (a == 0) { + * a = 1; + * if (random() == 42) + * continue; + * if (b == 1) { + * *(r10 + c) = 7; // this is not safe + * iter_destroy(i); + * iter_destroy(j); + * return; + * } + * } + * } + * iter_destroy(i); + * a = 0; + * b = 0; + * c = -25; + * } + * iter_destroy(j); + * return; + */ + asm volatile ( + "r1 = r10;" + "r1 += -16;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r6 = 0;" + "r7 = 0;" + "r8 = -24;" + "j_loop_%=:" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto j_loop_end_%=;" + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r6 = 0;" + "r7 = 0;" + "i_loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto i_loop_end_%=;" + "check_one_r6_%=:" + "if r6 != 1 goto check_zero_r6_%=;" + "r6 = 0;" + "r7 = 1;" + "goto i_loop_%=;" + "check_zero_r6_%=:" + "if r6 != 0 goto i_loop_%=;" + "r6 = 1;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto check_one_r7_%=;" + "goto i_loop_%=;" + "check_one_r7_%=:" + "if r7 != 1 goto i_loop_%=;" + "r0 = r10;" + "r0 += r8;" + "r1 = 7;" + "*(u64 *)(r0 + 0) = r1;" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + "i_loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r6 = 0;" + "r7 = 0;" + "r8 = -25;" + "goto j_loop_%=;" + "j_loop_end_%=:" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy) + : __clobber_all + ); +} + +SEC("?raw_tp") +__failure +__msg("math between fp pointer and register with unbounded") +__flag(BPF_F_TEST_STATE_FREQ) +__naked int loop_state_deps2(void) +{ + /* This is equivalent to C program below. + * + * The case turns out to be tricky in a sense that: + * - states with read+precise mark on c are explored only on a second + * iteration of the first inner loop and in a state which is pushed to + * states stack first. + * - states with c=-25 are explored only on a second iteration of the + * second inner loop and in a state which is pushed to states stack + * first. + * + * Depending on the details of iterator convergence logic + * verifier might stop states traversal too early and miss + * unsafe c=-25 memory access. + * + * j = iter_new(); // fp[-16] + * a = 0; // r6 + * b = 0; // r7 + * c = -24; // r8 + * while (iter_next(j)) { + * i = iter_new(); // fp[-8] + * a = 0; // r6 + * b = 0; // r7 + * while (iter_next(i)) { + * if (a == 1) { + * a = 0; + * b = 1; + * } else if (a == 0) { + * a = 1; + * if (random() == 42) + * continue; + * if (b == 1) { + * *(r10 + c) = 7; // this is not safe + * iter_destroy(i); + * iter_destroy(j); + * return; + * } + * } + * } + * iter_destroy(i); + * i = iter_new(); // fp[-8] + * a = 0; // r6 + * b = 0; // r7 + * while (iter_next(i)) { + * if (a == 1) { + * a = 0; + * b = 1; + * } else if (a == 0) { + * a = 1; + * if (random() == 42) + * continue; + * if (b == 1) { + * a = 0; + * c = -25; + * } + * } + * } + * iter_destroy(i); + * } + * iter_destroy(j); + * return; + */ + asm volatile ( + "r1 = r10;" + "r1 += -16;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r6 = 0;" + "r7 = 0;" + "r8 = -24;" + "j_loop_%=:" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto j_loop_end_%=;" + + /* first inner loop */ + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r6 = 0;" + "r7 = 0;" + "i_loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto i_loop_end_%=;" + "check_one_r6_%=:" + "if r6 != 1 goto check_zero_r6_%=;" + "r6 = 0;" + "r7 = 1;" + "goto i_loop_%=;" + "check_zero_r6_%=:" + "if r6 != 0 goto i_loop_%=;" + "r6 = 1;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto check_one_r7_%=;" + "goto i_loop_%=;" + "check_one_r7_%=:" + "if r7 != 1 goto i_loop_%=;" + "r0 = r10;" + "r0 += r8;" + "r1 = 7;" + "*(u64 *)(r0 + 0) = r1;" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + "i_loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + + /* second inner loop */ + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r6 = 0;" + "r7 = 0;" + "i2_loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto i2_loop_end_%=;" + "check2_one_r6_%=:" + "if r6 != 1 goto check2_zero_r6_%=;" + "r6 = 0;" + "r7 = 1;" + "goto i2_loop_%=;" + "check2_zero_r6_%=:" + "if r6 != 0 goto i2_loop_%=;" + "r6 = 1;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto check2_one_r7_%=;" + "goto i2_loop_%=;" + "check2_one_r7_%=:" + "if r7 != 1 goto i2_loop_%=;" + "r6 = 0;" + "r8 = -25;" + "goto i2_loop_%=;" + "i2_loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + + "r6 = 0;" + "r7 = 0;" + "goto j_loop_%=;" + "j_loop_end_%=:" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy) + : __clobber_all + ); +} + +SEC("?raw_tp") +__success +__naked int triple_continue(void) +{ + /* This is equivalent to C program below. + * High branching factor of the loop body turned out to be + * problematic for one of the iterator convergence tracking + * algorithms explored. + * + * r6 = bpf_get_prandom_u32() + * bpf_iter_num_new(&fp[-8], 0, 10) + * while (bpf_iter_num_next(&fp[-8])) { + * if (bpf_get_prandom_u32() != 42) + * continue; + * if (bpf_get_prandom_u32() != 42) + * continue; + * if (bpf_get_prandom_u32() != 42) + * continue; + * r0 += 0; + * } + * bpf_iter_num_destroy(&fp[-8]) + * return 0 + */ + asm volatile ( + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto loop_end_%=;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto loop_%=;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto loop_%=;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto loop_%=;" + "r0 += 0;" + "goto loop_%=;" + "loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy) + : __clobber_all + ); +} + +SEC("?raw_tp") +__success +__naked int widen_spill(void) +{ + /* This is equivalent to C program below. + * The counter is stored in fp[-16], if this counter is not widened + * verifier states representing loop iterations would never converge. + * + * fp[-16] = 0 + * bpf_iter_num_new(&fp[-8], 0, 10) + * while (bpf_iter_num_next(&fp[-8])) { + * r0 = fp[-16]; + * r0 += 1; + * fp[-16] = r0; + * } + * bpf_iter_num_destroy(&fp[-8]) + * return 0 + */ + asm volatile ( + "r0 = 0;" + "*(u64 *)(r10 - 16) = r0;" + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto loop_end_%=;" + "r0 = *(u64 *)(r10 - 16);" + "r0 += 1;" + "*(u64 *)(r10 - 16) = r0;" + "goto loop_%=;" + "loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy) + : __clobber_all + ); +} + +SEC("raw_tp") +__success +__naked int checkpoint_states_deletion(void) +{ + /* This is equivalent to C program below. + * + * int *a, *b, *c, *d, *e, *f; + * int i, sum = 0; + * bpf_for(i, 0, 10) { + * a = bpf_map_lookup_elem(&amap, &i); + * b = bpf_map_lookup_elem(&amap, &i); + * c = bpf_map_lookup_elem(&amap, &i); + * d = bpf_map_lookup_elem(&amap, &i); + * e = bpf_map_lookup_elem(&amap, &i); + * f = bpf_map_lookup_elem(&amap, &i); + * if (a) sum += 1; + * if (b) sum += 1; + * if (c) sum += 1; + * if (d) sum += 1; + * if (e) sum += 1; + * if (f) sum += 1; + * } + * return 0; + * + * The body of the loop spawns multiple simulation paths + * with different combination of NULL/non-NULL information for a/b/c/d/e/f. + * Each combination is unique from states_equal() point of view. + * Explored states checkpoint is created after each iterator next call. + * Iterator convergence logic expects that eventually current state + * would get equal to one of the explored states and thus loop + * exploration would be finished (at-least for a specific path). + * Verifier evicts explored states with high miss to hit ratio + * to to avoid comparing current state with too many explored + * states per instruction. + * This test is designed to "stress test" eviction policy defined using formula: + * + * sl->miss_cnt > sl->hit_cnt * N + N // if true sl->state is evicted + * + * Currently N is set to 64, which allows for 6 variables in this test. + */ + asm volatile ( + "r6 = 0;" /* a */ + "r7 = 0;" /* b */ + "r8 = 0;" /* c */ + "*(u64 *)(r10 - 24) = r6;" /* d */ + "*(u64 *)(r10 - 32) = r6;" /* e */ + "*(u64 *)(r10 - 40) = r6;" /* f */ + "r9 = 0;" /* sum */ + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto loop_end_%=;" + + "*(u64 *)(r10 - 16) = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "r6 = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "r7 = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "r8 = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "*(u64 *)(r10 - 24) = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "*(u64 *)(r10 - 32) = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "*(u64 *)(r10 - 40) = r0;" + + "if r6 == 0 goto +1;" + "r9 += 1;" + "if r7 == 0 goto +1;" + "r9 += 1;" + "if r8 == 0 goto +1;" + "r9 += 1;" + "r0 = *(u64 *)(r10 - 24);" + "if r0 == 0 goto +1;" + "r9 += 1;" + "r0 = *(u64 *)(r10 - 32);" + "if r0 == 0 goto +1;" + "r9 += 1;" + "r0 = *(u64 *)(r10 - 40);" + "if r0 == 0 goto +1;" + "r9 += 1;" + + "goto loop_%=;" + "loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_map_lookup_elem), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy), + __imm_addr(amap) + : __clobber_all + ); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters_looping.c b/tools/testing/selftests/bpf/progs/iters_looping.c new file mode 100644 index 0000000000..05fa5ce7fc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_looping.c @@ -0,0 +1,163 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <errno.h> +#include <string.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +#define ITER_HELPERS \ + __imm(bpf_iter_num_new), \ + __imm(bpf_iter_num_next), \ + __imm(bpf_iter_num_destroy) + +SEC("?raw_tp") +__success +int force_clang_to_emit_btf_for_externs(void *ctx) +{ + /* we need this as a workaround to enforce compiler emitting BTF + * information for bpf_iter_num_{new,next,destroy}() kfuncs, + * as, apparently, it doesn't emit it for symbols only referenced from + * assembly (or cleanup attribute, for that matter, as well) + */ + bpf_repeat(0); + + return 0; +} + +SEC("?raw_tp") +__success +int consume_first_item_only(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile ( + /* create iterator */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + + /* consume first item */ + "r1 = %[iter];" + "call %[bpf_iter_num_next];" + + "if r0 == 0 goto +1;" + "r0 = *(u32 *)(r0 + 0);" + + /* destroy iterator */ + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + : + : __imm_ptr(iter), ITER_HELPERS + : __clobber_common + ); + + return 0; +} + +SEC("?raw_tp") +__failure __msg("R0 invalid mem access 'scalar'") +int missing_null_check_fail(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile ( + /* create iterator */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + + /* consume first element */ + "r1 = %[iter];" + "call %[bpf_iter_num_next];" + + /* FAIL: deref with no NULL check */ + "r1 = *(u32 *)(r0 + 0);" + + /* destroy iterator */ + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + : + : __imm_ptr(iter), ITER_HELPERS + : __clobber_common + ); + + return 0; +} + +SEC("?raw_tp") +__failure +__msg("invalid access to memory, mem_size=4 off=0 size=8") +__msg("R0 min value is outside of the allowed memory range") +int wrong_sized_read_fail(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile ( + /* create iterator */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + + /* consume first element */ + "r1 = %[iter];" + "call %[bpf_iter_num_next];" + + "if r0 == 0 goto +1;" + /* FAIL: deref more than available 4 bytes */ + "r0 = *(u64 *)(r0 + 0);" + + /* destroy iterator */ + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + : + : __imm_ptr(iter), ITER_HELPERS + : __clobber_common + ); + + return 0; +} + +SEC("?raw_tp") +__success __log_level(2) +__flag(BPF_F_TEST_STATE_FREQ) +int simplest_loop(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile ( + "r6 = 0;" /* init sum */ + + /* create iterator */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + + "1:" + /* consume next item */ + "r1 = %[iter];" + "call %[bpf_iter_num_next];" + + "if r0 == 0 goto 2f;" + "r0 = *(u32 *)(r0 + 0);" + "r6 += r0;" /* accumulate sum */ + "goto 1b;" + + "2:" + /* destroy iterator */ + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + : + : __imm_ptr(iter), ITER_HELPERS + : __clobber_common, "r6" + ); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/iters_num.c b/tools/testing/selftests/bpf/progs/iters_num.c new file mode 100644 index 0000000000..7a77a8daee --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_num.c @@ -0,0 +1,242 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <limits.h> +#include <linux/errno.h> +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +const volatile __s64 exp_empty_zero = 0 + 1; +__s64 res_empty_zero; + +SEC("raw_tp/sys_enter") +int num_empty_zero(const void *ctx) +{ + __s64 sum = 0, i; + + bpf_for(i, 0, 0) sum += i; + res_empty_zero = 1 + sum; + + return 0; +} + +const volatile __s64 exp_empty_int_min = 0 + 2; +__s64 res_empty_int_min; + +SEC("raw_tp/sys_enter") +int num_empty_int_min(const void *ctx) +{ + __s64 sum = 0, i; + + bpf_for(i, INT_MIN, INT_MIN) sum += i; + res_empty_int_min = 2 + sum; + + return 0; +} + +const volatile __s64 exp_empty_int_max = 0 + 3; +__s64 res_empty_int_max; + +SEC("raw_tp/sys_enter") +int num_empty_int_max(const void *ctx) +{ + __s64 sum = 0, i; + + bpf_for(i, INT_MAX, INT_MAX) sum += i; + res_empty_int_max = 3 + sum; + + return 0; +} + +const volatile __s64 exp_empty_minus_one = 0 + 4; +__s64 res_empty_minus_one; + +SEC("raw_tp/sys_enter") +int num_empty_minus_one(const void *ctx) +{ + __s64 sum = 0, i; + + bpf_for(i, -1, -1) sum += i; + res_empty_minus_one = 4 + sum; + + return 0; +} + +const volatile __s64 exp_simple_sum = 9 * 10 / 2; +__s64 res_simple_sum; + +SEC("raw_tp/sys_enter") +int num_simple_sum(const void *ctx) +{ + __s64 sum = 0, i; + + bpf_for(i, 0, 10) sum += i; + res_simple_sum = sum; + + return 0; +} + +const volatile __s64 exp_neg_sum = -11 * 10 / 2; +__s64 res_neg_sum; + +SEC("raw_tp/sys_enter") +int num_neg_sum(const void *ctx) +{ + __s64 sum = 0, i; + + bpf_for(i, -10, 0) sum += i; + res_neg_sum = sum; + + return 0; +} + +const volatile __s64 exp_very_neg_sum = INT_MIN + (__s64)(INT_MIN + 1); +__s64 res_very_neg_sum; + +SEC("raw_tp/sys_enter") +int num_very_neg_sum(const void *ctx) +{ + __s64 sum = 0, i; + + bpf_for(i, INT_MIN, INT_MIN + 2) sum += i; + res_very_neg_sum = sum; + + return 0; +} + +const volatile __s64 exp_very_big_sum = (__s64)(INT_MAX - 1) + (__s64)(INT_MAX - 2); +__s64 res_very_big_sum; + +SEC("raw_tp/sys_enter") +int num_very_big_sum(const void *ctx) +{ + __s64 sum = 0, i; + + bpf_for(i, INT_MAX - 2, INT_MAX) sum += i; + res_very_big_sum = sum; + + return 0; +} + +const volatile __s64 exp_neg_pos_sum = -3; +__s64 res_neg_pos_sum; + +SEC("raw_tp/sys_enter") +int num_neg_pos_sum(const void *ctx) +{ + __s64 sum = 0, i; + + bpf_for(i, -3, 3) sum += i; + res_neg_pos_sum = sum; + + return 0; +} + +const volatile __s64 exp_invalid_range = -EINVAL; +__s64 res_invalid_range; + +SEC("raw_tp/sys_enter") +int num_invalid_range(const void *ctx) +{ + struct bpf_iter_num it; + + res_invalid_range = bpf_iter_num_new(&it, 1, 0); + bpf_iter_num_destroy(&it); + + return 0; +} + +const volatile __s64 exp_max_range = 0 + 10; +__s64 res_max_range; + +SEC("raw_tp/sys_enter") +int num_max_range(const void *ctx) +{ + struct bpf_iter_num it; + + res_max_range = 10 + bpf_iter_num_new(&it, 0, BPF_MAX_LOOPS); + bpf_iter_num_destroy(&it); + + return 0; +} + +const volatile __s64 exp_e2big_range = -E2BIG; +__s64 res_e2big_range; + +SEC("raw_tp/sys_enter") +int num_e2big_range(const void *ctx) +{ + struct bpf_iter_num it; + + res_e2big_range = bpf_iter_num_new(&it, -1, BPF_MAX_LOOPS); + bpf_iter_num_destroy(&it); + + return 0; +} + +const volatile __s64 exp_succ_elem_cnt = 10; +__s64 res_succ_elem_cnt; + +SEC("raw_tp/sys_enter") +int num_succ_elem_cnt(const void *ctx) +{ + struct bpf_iter_num it; + int cnt = 0, *v; + + bpf_iter_num_new(&it, 0, 10); + while ((v = bpf_iter_num_next(&it))) { + cnt++; + } + bpf_iter_num_destroy(&it); + + res_succ_elem_cnt = cnt; + + return 0; +} + +const volatile __s64 exp_overfetched_elem_cnt = 5; +__s64 res_overfetched_elem_cnt; + +SEC("raw_tp/sys_enter") +int num_overfetched_elem_cnt(const void *ctx) +{ + struct bpf_iter_num it; + int cnt = 0, *v, i; + + bpf_iter_num_new(&it, 0, 5); + for (i = 0; i < 10; i++) { + v = bpf_iter_num_next(&it); + if (v) + cnt++; + } + bpf_iter_num_destroy(&it); + + res_overfetched_elem_cnt = cnt; + + return 0; +} + +const volatile __s64 exp_fail_elem_cnt = 20 + 0; +__s64 res_fail_elem_cnt; + +SEC("raw_tp/sys_enter") +int num_fail_elem_cnt(const void *ctx) +{ + struct bpf_iter_num it; + int cnt = 0, *v, i; + + bpf_iter_num_new(&it, 100, 10); + for (i = 0; i < 10; i++) { + v = bpf_iter_num_next(&it); + if (v) + cnt++; + } + bpf_iter_num_destroy(&it); + + res_fail_elem_cnt = 20 + cnt; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters_state_safety.c b/tools/testing/selftests/bpf/progs/iters_state_safety.c new file mode 100644 index 0000000000..d47e59aba6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_state_safety.c @@ -0,0 +1,426 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Facebook */ + +#include <errno.h> +#include <string.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +#define ITER_HELPERS \ + __imm(bpf_iter_num_new), \ + __imm(bpf_iter_num_next), \ + __imm(bpf_iter_num_destroy) + +SEC("?raw_tp") +__success +int force_clang_to_emit_btf_for_externs(void *ctx) +{ + /* we need this as a workaround to enforce compiler emitting BTF + * information for bpf_iter_num_{new,next,destroy}() kfuncs, + * as, apparently, it doesn't emit it for symbols only referenced from + * assembly (or cleanup attribute, for that matter, as well) + */ + bpf_repeat(0); + + return 0; +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("fp-8_w=iter_num(ref_id=1,state=active,depth=0)") +int create_and_destroy(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile ( + /* create iterator */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + /* destroy iterator */ + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + : + : __imm_ptr(iter), ITER_HELPERS + : __clobber_common + ); + + return 0; +} + +SEC("?raw_tp") +__failure __msg("Unreleased reference id=1") +int create_and_forget_to_destroy_fail(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile ( + /* create iterator */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + : + : __imm_ptr(iter), ITER_HELPERS + : __clobber_common + ); + + return 0; +} + +SEC("?raw_tp") +__failure __msg("expected an initialized iter_num as arg #1") +int destroy_without_creating_fail(void *ctx) +{ + /* init with zeros to stop verifier complaining about uninit stack */ + struct bpf_iter_num iter; + + asm volatile ( + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + : + : __imm_ptr(iter), ITER_HELPERS + : __clobber_common + ); + + return 0; +} + +SEC("?raw_tp") +__failure __msg("expected an initialized iter_num as arg #1") +int compromise_iter_w_direct_write_fail(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile ( + /* create iterator */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + + /* directly write over first half of iter state */ + "*(u64 *)(%[iter] + 0) = r0;" + + /* (attempt to) destroy iterator */ + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + : + : __imm_ptr(iter), ITER_HELPERS + : __clobber_common + ); + + return 0; +} + +SEC("?raw_tp") +__failure __msg("Unreleased reference id=1") +int compromise_iter_w_direct_write_and_skip_destroy_fail(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile ( + /* create iterator */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + + /* directly write over first half of iter state */ + "*(u64 *)(%[iter] + 0) = r0;" + + /* don't destroy iter, leaking ref, which should fail */ + : + : __imm_ptr(iter), ITER_HELPERS + : __clobber_common + ); + + return 0; +} + +SEC("?raw_tp") +__failure __msg("expected an initialized iter_num as arg #1") +int compromise_iter_w_helper_write_fail(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile ( + /* create iterator */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + + /* overwrite 8th byte with bpf_probe_read_kernel() */ + "r1 = %[iter];" + "r1 += 7;" + "r2 = 1;" + "r3 = 0;" /* NULL */ + "call %[bpf_probe_read_kernel];" + + /* (attempt to) destroy iterator */ + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + : + : __imm_ptr(iter), ITER_HELPERS, __imm(bpf_probe_read_kernel) + : __clobber_common + ); + + return 0; +} + +static __noinline void subprog_with_iter(void) +{ + struct bpf_iter_num iter; + + bpf_iter_num_new(&iter, 0, 1); + + return; +} + +SEC("?raw_tp") +__failure +/* ensure there was a call to subprog, which might happen without __noinline */ +__msg("returning from callee:") +__msg("Unreleased reference id=1") +int leak_iter_from_subprog_fail(void *ctx) +{ + subprog_with_iter(); + + return 0; +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("fp-8_w=iter_num(ref_id=1,state=active,depth=0)") +int valid_stack_reuse(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile ( + /* create iterator */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + /* destroy iterator */ + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + + /* now reuse same stack slots */ + + /* create iterator */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + /* destroy iterator */ + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + : + : __imm_ptr(iter), ITER_HELPERS + : __clobber_common + ); + + return 0; +} + +SEC("?raw_tp") +__failure __msg("expected uninitialized iter_num as arg #1") +int double_create_fail(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile ( + /* create iterator */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + /* (attempt to) create iterator again */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + /* destroy iterator */ + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + : + : __imm_ptr(iter), ITER_HELPERS + : __clobber_common + ); + + return 0; +} + +SEC("?raw_tp") +__failure __msg("expected an initialized iter_num as arg #1") +int double_destroy_fail(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile ( + /* create iterator */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + /* destroy iterator */ + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + /* (attempt to) destroy iterator again */ + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + : + : __imm_ptr(iter), ITER_HELPERS + : __clobber_common + ); + + return 0; +} + +SEC("?raw_tp") +__failure __msg("expected an initialized iter_num as arg #1") +int next_without_new_fail(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile ( + /* don't create iterator and try to iterate*/ + "r1 = %[iter];" + "call %[bpf_iter_num_next];" + /* destroy iterator */ + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + : + : __imm_ptr(iter), ITER_HELPERS + : __clobber_common + ); + + return 0; +} + +SEC("?raw_tp") +__failure __msg("expected an initialized iter_num as arg #1") +int next_after_destroy_fail(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile ( + /* create iterator */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + /* destroy iterator */ + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + /* don't create iterator and try to iterate*/ + "r1 = %[iter];" + "call %[bpf_iter_num_next];" + : + : __imm_ptr(iter), ITER_HELPERS + : __clobber_common + ); + + return 0; +} + +SEC("?raw_tp") +__failure __msg("invalid read from stack") +int __naked read_from_iter_slot_fail(void) +{ + asm volatile ( + /* r6 points to struct bpf_iter_num on the stack */ + "r6 = r10;" + "r6 += -24;" + + /* create iterator */ + "r1 = r6;" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + + /* attemp to leak bpf_iter_num state */ + "r7 = *(u64 *)(r6 + 0);" + "r8 = *(u64 *)(r6 + 8);" + + /* destroy iterator */ + "r1 = r6;" + "call %[bpf_iter_num_destroy];" + + /* leak bpf_iter_num state */ + "r0 = r7;" + "if r7 > r8 goto +1;" + "r0 = r8;" + "exit;" + : + : ITER_HELPERS + : __clobber_common, "r6", "r7", "r8" + ); +} + +int zero; + +SEC("?raw_tp") +__failure +__flag(BPF_F_TEST_STATE_FREQ) +__msg("Unreleased reference") +int stacksafe_should_not_conflate_stack_spill_and_iter(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile ( + /* Create a fork in logic, with general setup as follows: + * - fallthrough (first) path is valid; + * - branch (second) path is invalid. + * Then depending on what we do in fallthrough vs branch path, + * we try to detect bugs in func_states_equal(), regsafe(), + * refsafe(), stack_safe(), and similar by tricking verifier + * into believing that branch state is a valid subset of + * a fallthrough state. Verifier should reject overall + * validation, unless there is a bug somewhere in verifier + * logic. + */ + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "call %[bpf_get_prandom_u32];" + "r7 = r0;" + + "if r6 > r7 goto bad;" /* fork */ + + /* spill r6 into stack slot of bpf_iter_num var */ + "*(u64 *)(%[iter] + 0) = r6;" + + "goto skip_bad;" + + "bad:" + /* create iterator in the same stack slot */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 1000;" + "call %[bpf_iter_num_new];" + + /* but then forget about it and overwrite it back to r6 spill */ + "*(u64 *)(%[iter] + 0) = r6;" + + "skip_bad:" + "goto +0;" /* force checkpoint */ + + /* corrupt stack slots, if they are really dynptr */ + "*(u64 *)(%[iter] + 0) = r6;" + : + : __imm_ptr(iter), + __imm_addr(zero), + __imm(bpf_get_prandom_u32), + __imm(bpf_dynptr_from_mem), + ITER_HELPERS + : __clobber_common, "r6", "r7" + ); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c new file mode 100644 index 0000000000..3873fb6c29 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct bpf_iter_testmod_seq { + u64 :64; + u64 :64; +}; + +extern int bpf_iter_testmod_seq_new(struct bpf_iter_testmod_seq *it, s64 value, int cnt) __ksym; +extern s64 *bpf_iter_testmod_seq_next(struct bpf_iter_testmod_seq *it) __ksym; +extern void bpf_iter_testmod_seq_destroy(struct bpf_iter_testmod_seq *it) __ksym; + +const volatile __s64 exp_empty = 0 + 1; +__s64 res_empty; + +SEC("raw_tp/sys_enter") +__success __log_level(2) +__msg("fp-16_w=iter_testmod_seq(ref_id=1,state=active,depth=0)") +__msg("fp-16=iter_testmod_seq(ref_id=1,state=drained,depth=0)") +__msg("call bpf_iter_testmod_seq_destroy") +int testmod_seq_empty(const void *ctx) +{ + __s64 sum = 0, *i; + + bpf_for_each(testmod_seq, i, 1000, 0) sum += *i; + res_empty = 1 + sum; + + return 0; +} + +const volatile __s64 exp_full = 1000000; +__s64 res_full; + +SEC("raw_tp/sys_enter") +__success __log_level(2) +__msg("fp-16_w=iter_testmod_seq(ref_id=1,state=active,depth=0)") +__msg("fp-16=iter_testmod_seq(ref_id=1,state=drained,depth=0)") +__msg("call bpf_iter_testmod_seq_destroy") +int testmod_seq_full(const void *ctx) +{ + __s64 sum = 0, *i; + + bpf_for_each(testmod_seq, i, 1000, 1000) sum += *i; + res_full = sum; + + return 0; +} + +const volatile __s64 exp_truncated = 10 * 1000000; +__s64 res_truncated; + +static volatile int zero = 0; + +SEC("raw_tp/sys_enter") +__success __log_level(2) +__msg("fp-16_w=iter_testmod_seq(ref_id=1,state=active,depth=0)") +__msg("fp-16=iter_testmod_seq(ref_id=1,state=drained,depth=0)") +__msg("call bpf_iter_testmod_seq_destroy") +int testmod_seq_truncated(const void *ctx) +{ + __s64 sum = 0, *i; + int cnt = zero; + + bpf_for_each(testmod_seq, i, 10, 2000000) { + sum += *i; + cnt++; + if (cnt >= 1000000) + break; + } + res_truncated = sum; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c b/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c new file mode 100644 index 0000000000..f46965053a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, u64); + __type(value, u64); +} m_hash SEC(".maps"); + +SEC("?raw_tp") +__failure __msg("R8 invalid mem access 'map_value_or_null") +int jeq_infer_not_null_ptr_to_btfid(void *ctx) +{ + struct bpf_map *map = (struct bpf_map *)&m_hash; + struct bpf_map *inner_map = map->inner_map_meta; + u64 key = 0, ret = 0, *val; + + val = bpf_map_lookup_elem(map, &key); + /* Do not mark ptr as non-null if one of them is + * PTR_TO_BTF_ID (R9), reject because of invalid + * access to map value (R8). + * + * Here, we need to inline those insns to access + * R8 directly, since compiler may use other reg + * once it figures out val==inner_map. + */ + asm volatile("r8 = %[val];\n" + "r9 = %[inner_map];\n" + "if r8 != r9 goto +1;\n" + "%[ret] = *(u64 *)(r8 +0);\n" + : [ret] "+r"(ret) + : [inner_map] "r"(inner_map), [val] "r"(val) + : "r8", "r9"); + + return ret; +} diff --git a/tools/testing/selftests/bpf/progs/jit_probe_mem.c b/tools/testing/selftests/bpf/progs/jit_probe_mem.c new file mode 100644 index 0000000000..f9789e6682 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/jit_probe_mem.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" + +static struct prog_test_ref_kfunc __kptr *v; +long total_sum = -1; + +SEC("tc") +int test_jit_probe_mem(struct __sk_buff *ctx) +{ + struct prog_test_ref_kfunc *p; + unsigned long zero = 0, sum; + + p = bpf_kfunc_call_test_acquire(&zero); + if (!p) + return 1; + + p = bpf_kptr_xchg(&v, p); + if (p) + goto release_out; + + /* Direct map value access of kptr, should be PTR_UNTRUSTED */ + p = v; + if (!p) + return 1; + + asm volatile ( + "r9 = %[p];" + "%[sum] = 0;" + + /* r8 = p->a */ + "r8 = *(u32 *)(r9 + 0);" + "%[sum] += r8;" + + /* r8 = p->b */ + "r8 = *(u32 *)(r9 + 4);" + "%[sum] += r8;" + + "r9 += 8;" + /* r9 = p->a */ + "r9 = *(u32 *)(r9 - 8);" + "%[sum] += r9;" + + : [sum] "=r"(sum) + : [p] "r"(p) + : "r8", "r9" + ); + + total_sum = sum; + return 0; +release_out: + bpf_kfunc_call_test_release(p); + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c new file mode 100644 index 0000000000..7236da72ce --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kfree_skb.c @@ -0,0 +1,153 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include <stdbool.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __type(key, int); + __type(value, int); +} perf_buf_map SEC(".maps"); + +#define _(P) (__builtin_preserve_access_index(P)) + +/* define few struct-s that bpf program needs to access */ +struct callback_head { + struct callback_head *next; + void (*func)(struct callback_head *head); +}; +struct dev_ifalias { + struct callback_head rcuhead; +}; + +struct net_device /* same as kernel's struct net_device */ { + int ifindex; + struct dev_ifalias *ifalias; +}; + +typedef struct { + int counter; +} atomic_t; +typedef struct refcount_struct { + atomic_t refs; +} refcount_t; + +struct sk_buff { + /* field names and sizes should match to those in the kernel */ + unsigned int len, data_len; + __u16 mac_len, hdr_len, queue_mapping; + struct net_device *dev; + /* order of the fields doesn't matter */ + refcount_t users; + unsigned char *data; + char __pkt_type_offset[0]; + char cb[48]; +}; + +struct meta { + int ifindex; + __u32 cb32_0; + __u8 cb8_0; +}; + +/* TRACE_EVENT(kfree_skb, + * TP_PROTO(struct sk_buff *skb, void *location), + */ +SEC("tp_btf/kfree_skb") +int BPF_PROG(trace_kfree_skb, struct sk_buff *skb, void *location) +{ + struct net_device *dev; + struct callback_head *ptr; + void *func; + int users; + unsigned char *data; + unsigned short pkt_data; + struct meta meta = {}; + char pkt_type; + __u32 *cb32; + __u8 *cb8; + + __builtin_preserve_access_index(({ + users = skb->users.refs.counter; + data = skb->data; + dev = skb->dev; + ptr = dev->ifalias->rcuhead.next; + func = ptr->func; + cb8 = (__u8 *)&skb->cb; + cb32 = (__u32 *)&skb->cb; + })); + + meta.ifindex = _(dev->ifindex); + meta.cb8_0 = cb8[8]; + meta.cb32_0 = cb32[2]; + + bpf_probe_read_kernel(&pkt_type, sizeof(pkt_type), _(&skb->__pkt_type_offset)); + pkt_type &= 7; + + /* read eth proto */ + bpf_probe_read_kernel(&pkt_data, sizeof(pkt_data), data + 12); + + bpf_printk("rcuhead.next %llx func %llx\n", ptr, func); + bpf_printk("skb->len %d users %d pkt_type %x\n", + _(skb->len), users, pkt_type); + bpf_printk("skb->queue_mapping %d\n", _(skb->queue_mapping)); + bpf_printk("dev->ifindex %d data %llx pkt_data %x\n", + meta.ifindex, data, pkt_data); + bpf_printk("cb8_0:%x cb32_0:%x\n", meta.cb8_0, meta.cb32_0); + + if (users != 1 || pkt_data != bpf_htons(0x86dd) || meta.ifindex != 1) + /* raw tp ignores return value */ + return 0; + + /* send first 72 byte of the packet to user space */ + bpf_skb_output(skb, &perf_buf_map, (72ull << 32) | BPF_F_CURRENT_CPU, + &meta, sizeof(meta)); + return 0; +} + +struct { + bool fentry_test_ok; + bool fexit_test_ok; +} result = {}; + +SEC("fentry/eth_type_trans") +int BPF_PROG(fentry_eth_type_trans, struct sk_buff *skb, struct net_device *dev, + unsigned short protocol) +{ + int len, ifindex; + + __builtin_preserve_access_index(({ + len = skb->len; + ifindex = dev->ifindex; + })); + + /* fentry sees full packet including L2 header */ + if (len != 74 || ifindex != 1) + return 0; + result.fentry_test_ok = true; + return 0; +} + +SEC("fexit/eth_type_trans") +int BPF_PROG(fexit_eth_type_trans, struct sk_buff *skb, struct net_device *dev, + unsigned short protocol) +{ + int len, ifindex; + + __builtin_preserve_access_index(({ + len = skb->len; + ifindex = dev->ifindex; + })); + + /* fexit sees packet without L2 header that eth_type_trans should have + * consumed. + */ + if (len != 60 || protocol != bpf_htons(0x86dd) || ifindex != 1) + return 0; + result.fexit_test_ok = true; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c new file mode 100644 index 0000000000..7632d9ecb2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" + +SEC("tc") +int kfunc_destructive_test(void) +{ + bpf_kfunc_call_test_destructive(); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c new file mode 100644 index 0000000000..4b0b7b79cd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c @@ -0,0 +1,153 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" + +struct syscall_test_args { + __u8 data[16]; + size_t size; +}; + +SEC("?syscall") +int kfunc_syscall_test_fail(struct syscall_test_args *args) +{ + bpf_kfunc_call_test_mem_len_pass1(&args->data, sizeof(*args) + 1); + + return 0; +} + +SEC("?syscall") +int kfunc_syscall_test_null_fail(struct syscall_test_args *args) +{ + /* Must be called with args as a NULL pointer + * we do not check for it to have the verifier consider that + * the pointer might not be null, and so we can load it. + * + * So the following can not be added: + * + * if (args) + * return -22; + */ + + bpf_kfunc_call_test_mem_len_pass1(args, sizeof(*args)); + + return 0; +} + +SEC("?tc") +int kfunc_call_test_get_mem_fail_rdonly(struct __sk_buff *skb) +{ + struct prog_test_ref_kfunc *pt; + unsigned long s = 0; + int *p = NULL; + int ret = 0; + + pt = bpf_kfunc_call_test_acquire(&s); + if (pt) { + p = bpf_kfunc_call_test_get_rdonly_mem(pt, 2 * sizeof(int)); + if (p) + p[0] = 42; /* this is a read-only buffer, so -EACCES */ + else + ret = -1; + + bpf_kfunc_call_test_release(pt); + } + return ret; +} + +SEC("?tc") +int kfunc_call_test_get_mem_fail_use_after_free(struct __sk_buff *skb) +{ + struct prog_test_ref_kfunc *pt; + unsigned long s = 0; + int *p = NULL; + int ret = 0; + + pt = bpf_kfunc_call_test_acquire(&s); + if (pt) { + p = bpf_kfunc_call_test_get_rdwr_mem(pt, 2 * sizeof(int)); + if (p) { + p[0] = 42; + ret = p[1]; /* 108 */ + } else { + ret = -1; + } + + bpf_kfunc_call_test_release(pt); + } + if (p) + ret = p[0]; /* p is not valid anymore */ + + return ret; +} + +SEC("?tc") +int kfunc_call_test_get_mem_fail_oob(struct __sk_buff *skb) +{ + struct prog_test_ref_kfunc *pt; + unsigned long s = 0; + int *p = NULL; + int ret = 0; + + pt = bpf_kfunc_call_test_acquire(&s); + if (pt) { + p = bpf_kfunc_call_test_get_rdonly_mem(pt, 2 * sizeof(int)); + if (p) + ret = p[2 * sizeof(int)]; /* oob access, so -EACCES */ + else + ret = -1; + + bpf_kfunc_call_test_release(pt); + } + return ret; +} + +int not_const_size = 2 * sizeof(int); + +SEC("?tc") +int kfunc_call_test_get_mem_fail_not_const(struct __sk_buff *skb) +{ + struct prog_test_ref_kfunc *pt; + unsigned long s = 0; + int *p = NULL; + int ret = 0; + + pt = bpf_kfunc_call_test_acquire(&s); + if (pt) { + p = bpf_kfunc_call_test_get_rdonly_mem(pt, not_const_size); /* non const size, -EINVAL */ + if (p) + ret = p[0]; + else + ret = -1; + + bpf_kfunc_call_test_release(pt); + } + return ret; +} + +SEC("?tc") +int kfunc_call_test_mem_acquire_fail(struct __sk_buff *skb) +{ + struct prog_test_ref_kfunc *pt; + unsigned long s = 0; + int *p = NULL; + int ret = 0; + + pt = bpf_kfunc_call_test_acquire(&s); + if (pt) { + /* we are failing on this one, because we are not acquiring a PTR_TO_BTF_ID (a struct ptr) */ + p = bpf_kfunc_call_test_acq_rdonly_mem(pt, 2 * sizeof(int)); + if (p) + ret = p[0]; + else + ret = -1; + + bpf_kfunc_call_int_mem_release(p); + + bpf_kfunc_call_test_release(pt); + } + return ret; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_race.c b/tools/testing/selftests/bpf/progs/kfunc_call_race.c new file mode 100644 index 0000000000..d532af07de --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kfunc_call_race.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" + +SEC("tc") +int kfunc_call_fail(struct __sk_buff *ctx) +{ + bpf_testmod_test_mod_kfunc(0); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c new file mode 100644 index 0000000000..cf68d1e48a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" + +SEC("tc") +int kfunc_call_test4(struct __sk_buff *skb) +{ + struct bpf_sock *sk = skb->sk; + long tmp; + + if (!sk) + return -1; + + sk = bpf_sk_fullsock(sk); + if (!sk) + return -1; + + tmp = bpf_kfunc_call_test4(-3, -30, -200, -1000); + return (tmp >> 32) + tmp; +} + +SEC("tc") +int kfunc_call_test2(struct __sk_buff *skb) +{ + struct bpf_sock *sk = skb->sk; + + if (!sk) + return -1; + + sk = bpf_sk_fullsock(sk); + if (!sk) + return -1; + + return bpf_kfunc_call_test2((struct sock *)sk, 1, 2); +} + +SEC("tc") +int kfunc_call_test1(struct __sk_buff *skb) +{ + struct bpf_sock *sk = skb->sk; + __u64 a = 1ULL << 32; + __u32 ret; + + if (!sk) + return -1; + + sk = bpf_sk_fullsock(sk); + if (!sk) + return -1; + + a = bpf_kfunc_call_test1((struct sock *)sk, 1, a | 2, 3, a | 4); + ret = a >> 32; /* ret should be 2 */ + ret += (__u32)a; /* ret should be 12 */ + + return ret; +} + +SEC("tc") +int kfunc_call_test_ref_btf_id(struct __sk_buff *skb) +{ + struct prog_test_ref_kfunc *pt; + unsigned long s = 0; + int ret = 0; + + pt = bpf_kfunc_call_test_acquire(&s); + if (pt) { + if (pt->a != 42 || pt->b != 108) + ret = -1; + bpf_kfunc_call_test_release(pt); + } + return ret; +} + +SEC("tc") +int kfunc_call_test_pass(struct __sk_buff *skb) +{ + struct prog_test_pass1 p1 = {}; + struct prog_test_pass2 p2 = {}; + short a = 0; + __u64 b = 0; + long c = 0; + char d = 0; + int e = 0; + + bpf_kfunc_call_test_pass_ctx(skb); + bpf_kfunc_call_test_pass1(&p1); + bpf_kfunc_call_test_pass2(&p2); + + bpf_kfunc_call_test_mem_len_pass1(&a, sizeof(a)); + bpf_kfunc_call_test_mem_len_pass1(&b, sizeof(b)); + bpf_kfunc_call_test_mem_len_pass1(&c, sizeof(c)); + bpf_kfunc_call_test_mem_len_pass1(&d, sizeof(d)); + bpf_kfunc_call_test_mem_len_pass1(&e, sizeof(e)); + bpf_kfunc_call_test_mem_len_fail2(&b, -1); + + return 0; +} + +struct syscall_test_args { + __u8 data[16]; + size_t size; +}; + +SEC("syscall") +int kfunc_syscall_test(struct syscall_test_args *args) +{ + const long size = args->size; + + if (size > sizeof(args->data)) + return -7; /* -E2BIG */ + + bpf_kfunc_call_test_mem_len_pass1(&args->data, sizeof(args->data)); + bpf_kfunc_call_test_mem_len_pass1(&args->data, sizeof(*args)); + bpf_kfunc_call_test_mem_len_pass1(&args->data, size); + + return 0; +} + +SEC("syscall") +int kfunc_syscall_test_null(struct syscall_test_args *args) +{ + /* Must be called with args as a NULL pointer + * we do not check for it to have the verifier consider that + * the pointer might not be null, and so we can load it. + * + * So the following can not be added: + * + * if (args) + * return -22; + */ + + bpf_kfunc_call_test_mem_len_pass1(args, 0); + + return 0; +} + +SEC("tc") +int kfunc_call_test_get_mem(struct __sk_buff *skb) +{ + struct prog_test_ref_kfunc *pt; + unsigned long s = 0; + int *p = NULL; + int ret = 0; + + pt = bpf_kfunc_call_test_acquire(&s); + if (pt) { + p = bpf_kfunc_call_test_get_rdwr_mem(pt, 2 * sizeof(int)); + if (p) { + p[0] = 42; + ret = p[1]; /* 108 */ + } else { + ret = -1; + } + + if (ret >= 0) { + p = bpf_kfunc_call_test_get_rdonly_mem(pt, 2 * sizeof(int)); + if (p) + ret = p[0]; /* 42 */ + else + ret = -1; + } + + bpf_kfunc_call_test_release(pt); + } + return ret; +} + +SEC("tc") +int kfunc_call_test_static_unused_arg(struct __sk_buff *skb) +{ + + u32 expected = 5, actual; + + actual = bpf_kfunc_call_test_static_unused_arg(expected, 0xdeadbeef); + return actual != expected ? -1 : 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c new file mode 100644 index 0000000000..2380c75e74 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "../bpf_testmod/bpf_testmod_kfunc.h" + +extern const int bpf_prog_active __ksym; +int active_res = -1; +int sk_state_res = -1; + +int __noinline f1(struct __sk_buff *skb) +{ + struct bpf_sock *sk = skb->sk; + int *active; + + if (!sk) + return -1; + + sk = bpf_sk_fullsock(sk); + if (!sk) + return -1; + + active = (int *)bpf_per_cpu_ptr(&bpf_prog_active, + bpf_get_smp_processor_id()); + if (active) + active_res = *active; + + sk_state_res = bpf_kfunc_call_test3((struct sock *)sk)->__sk_common.skc_state; + + return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4); +} + +SEC("tc") +int kfunc_call_test1(struct __sk_buff *skb) +{ + return f1(skb); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi.c b/tools/testing/selftests/bpf/progs/kprobe_multi.c new file mode 100644 index 0000000000..9e1ca8e349 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kprobe_multi.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <stdbool.h> + +char _license[] SEC("license") = "GPL"; + +extern const void bpf_fentry_test1 __ksym; +extern const void bpf_fentry_test2 __ksym; +extern const void bpf_fentry_test3 __ksym; +extern const void bpf_fentry_test4 __ksym; +extern const void bpf_fentry_test5 __ksym; +extern const void bpf_fentry_test6 __ksym; +extern const void bpf_fentry_test7 __ksym; +extern const void bpf_fentry_test8 __ksym; + +int pid = 0; +bool test_cookie = false; + +__u64 kprobe_test1_result = 0; +__u64 kprobe_test2_result = 0; +__u64 kprobe_test3_result = 0; +__u64 kprobe_test4_result = 0; +__u64 kprobe_test5_result = 0; +__u64 kprobe_test6_result = 0; +__u64 kprobe_test7_result = 0; +__u64 kprobe_test8_result = 0; + +__u64 kretprobe_test1_result = 0; +__u64 kretprobe_test2_result = 0; +__u64 kretprobe_test3_result = 0; +__u64 kretprobe_test4_result = 0; +__u64 kretprobe_test5_result = 0; +__u64 kretprobe_test6_result = 0; +__u64 kretprobe_test7_result = 0; +__u64 kretprobe_test8_result = 0; + +static void kprobe_multi_check(void *ctx, bool is_return) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return; + + __u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0; + __u64 addr = bpf_get_func_ip(ctx); + +#define SET(__var, __addr, __cookie) ({ \ + if (((const void *) addr == __addr) && \ + (!test_cookie || (cookie == __cookie))) \ + __var = 1; \ +}) + + if (is_return) { + SET(kretprobe_test1_result, &bpf_fentry_test1, 8); + SET(kretprobe_test2_result, &bpf_fentry_test2, 2); + SET(kretprobe_test3_result, &bpf_fentry_test3, 7); + SET(kretprobe_test4_result, &bpf_fentry_test4, 6); + SET(kretprobe_test5_result, &bpf_fentry_test5, 5); + SET(kretprobe_test6_result, &bpf_fentry_test6, 4); + SET(kretprobe_test7_result, &bpf_fentry_test7, 3); + SET(kretprobe_test8_result, &bpf_fentry_test8, 1); + } else { + SET(kprobe_test1_result, &bpf_fentry_test1, 1); + SET(kprobe_test2_result, &bpf_fentry_test2, 7); + SET(kprobe_test3_result, &bpf_fentry_test3, 2); + SET(kprobe_test4_result, &bpf_fentry_test4, 3); + SET(kprobe_test5_result, &bpf_fentry_test5, 4); + SET(kprobe_test6_result, &bpf_fentry_test6, 5); + SET(kprobe_test7_result, &bpf_fentry_test7, 6); + SET(kprobe_test8_result, &bpf_fentry_test8, 8); + } + +#undef SET +} + +/* + * No tests in here, just to trigger 'bpf_fentry_test*' + * through tracing test_run + */ +SEC("fentry/bpf_modify_return_test") +int BPF_PROG(trigger) +{ + return 0; +} + +SEC("kprobe.multi/bpf_fentry_tes??") +int test_kprobe(struct pt_regs *ctx) +{ + kprobe_multi_check(ctx, false); + return 0; +} + +SEC("kretprobe.multi/bpf_fentry_test*") +int test_kretprobe(struct pt_regs *ctx) +{ + kprobe_multi_check(ctx, true); + return 0; +} + +SEC("kprobe.multi") +int test_kprobe_manual(struct pt_regs *ctx) +{ + kprobe_multi_check(ctx, false); + return 0; +} + +SEC("kretprobe.multi") +int test_kretprobe_manual(struct pt_regs *ctx) +{ + kprobe_multi_check(ctx, true); + return 0; +} + +extern const void bpf_testmod_fentry_test1 __ksym; +extern const void bpf_testmod_fentry_test2 __ksym; +extern const void bpf_testmod_fentry_test3 __ksym; + +__u64 kprobe_testmod_test1_result = 0; +__u64 kprobe_testmod_test2_result = 0; +__u64 kprobe_testmod_test3_result = 0; + +__u64 kretprobe_testmod_test1_result = 0; +__u64 kretprobe_testmod_test2_result = 0; +__u64 kretprobe_testmod_test3_result = 0; + +static void kprobe_multi_testmod_check(void *ctx, bool is_return) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return; + + __u64 addr = bpf_get_func_ip(ctx); + + if (is_return) { + if ((const void *) addr == &bpf_testmod_fentry_test1) + kretprobe_testmod_test1_result = 1; + if ((const void *) addr == &bpf_testmod_fentry_test2) + kretprobe_testmod_test2_result = 1; + if ((const void *) addr == &bpf_testmod_fentry_test3) + kretprobe_testmod_test3_result = 1; + } else { + if ((const void *) addr == &bpf_testmod_fentry_test1) + kprobe_testmod_test1_result = 1; + if ((const void *) addr == &bpf_testmod_fentry_test2) + kprobe_testmod_test2_result = 1; + if ((const void *) addr == &bpf_testmod_fentry_test3) + kprobe_testmod_test3_result = 1; + } +} + +SEC("kprobe.multi") +int test_kprobe_testmod(struct pt_regs *ctx) +{ + kprobe_multi_testmod_check(ctx, false); + return 0; +} + +SEC("kretprobe.multi") +int test_kretprobe_testmod(struct pt_regs *ctx) +{ + kprobe_multi_testmod_check(ctx, true); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi_empty.c b/tools/testing/selftests/bpf/progs/kprobe_multi_empty.c new file mode 100644 index 0000000000..e76e499aca --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kprobe_multi_empty.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +SEC("kprobe.multi/") +int test_kprobe_empty(struct pt_regs *ctx) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi_override.c b/tools/testing/selftests/bpf/progs/kprobe_multi_override.c new file mode 100644 index 0000000000..28f8487c90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kprobe_multi_override.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +SEC("kprobe.multi") +int test_override(struct pt_regs *ctx) +{ + bpf_override_return(ctx, 123); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/ksym_race.c b/tools/testing/selftests/bpf/progs/ksym_race.c new file mode 100644 index 0000000000..def97f2fed --- /dev/null +++ b/tools/testing/selftests/bpf/progs/ksym_race.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +extern int bpf_testmod_ksym_percpu __ksym; + +SEC("tc") +int ksym_fail(struct __sk_buff *ctx) +{ + return *(int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/linked_funcs1.c b/tools/testing/selftests/bpf/progs/linked_funcs1.c new file mode 100644 index 0000000000..c4b49ceea9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/linked_funcs1.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" + +/* weak and shared between two files */ +const volatile int my_tid __weak; +long syscall_id __weak; + +int output_val1; +int output_ctx1; +int output_weak1; + +/* same "subprog" name in all files, but it's ok because they all are static */ +static __noinline int subprog(int x) +{ + /* but different formula */ + return x * 1; +} + +/* Global functions can't be void */ +int set_output_val1(int x) +{ + output_val1 = x + subprog(x); + return x; +} + +/* This function can't be verified as global, as it assumes raw_tp/sys_enter + * context and accesses syscall id (second argument). So we mark it as + * __hidden, so that libbpf will mark it as static in the final object file, + * right before verifying it in the kernel. + * + * But we don't mark it as __hidden here, rather at extern site. __hidden is + * "contaminating" visibility, so it will get propagated from either extern or + * actual definition (including from the losing __weak definition). + */ +void set_output_ctx1(__u64 *ctx) +{ + output_ctx1 = ctx[1]; /* long id, same as in BPF_PROG below */ +} + +/* this weak instance should win because it's the first one */ +__weak int set_output_weak(int x) +{ + static volatile int whatever; + + /* make sure we use CO-RE relocations in a weak function, this used to + * cause problems for BPF static linker + */ + whatever = bpf_core_type_size(struct task_struct); + __sink(whatever); + + output_weak1 = x; + return x; +} + +extern int set_output_val2(int x); + +/* here we'll force set_output_ctx2() to be __hidden in the final obj file */ +__hidden extern void set_output_ctx2(__u64 *ctx); + +SEC("?raw_tp/sys_enter") +int BPF_PROG(handler1, struct pt_regs *regs, long id) +{ + static volatile int whatever; + + if (my_tid != (u32)bpf_get_current_pid_tgid() || id != syscall_id) + return 0; + + /* make sure we have CO-RE relocations in main program */ + whatever = bpf_core_type_size(struct task_struct); + __sink(whatever); + + set_output_val2(1000); + set_output_ctx2(ctx); /* ctx definition is hidden in BPF_PROG macro */ + + /* keep input value the same across both files to avoid dependency on + * handler call order; differentiate by output_weak1 vs output_weak2. + */ + set_output_weak(42); + + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/linked_funcs2.c b/tools/testing/selftests/bpf/progs/linked_funcs2.c new file mode 100644 index 0000000000..013ff0645f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/linked_funcs2.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" + +/* weak and shared between both files */ +const volatile int my_tid __weak; +long syscall_id __weak; + +int output_val2; +int output_ctx2; +int output_weak2; /* should stay zero */ + +/* same "subprog" name in all files, but it's ok because they all are static */ +static __noinline int subprog(int x) +{ + /* but different formula */ + return x * 2; +} + +/* Global functions can't be void */ +int set_output_val2(int x) +{ + output_val2 = 2 * x + 2 * subprog(x); + return 2 * x; +} + +/* This function can't be verified as global, as it assumes raw_tp/sys_enter + * context and accesses syscall id (second argument). So we mark it as + * __hidden, so that libbpf will mark it as static in the final object file, + * right before verifying it in the kernel. + * + * But we don't mark it as __hidden here, rather at extern site. __hidden is + * "contaminating" visibility, so it will get propagated from either extern or + * actual definition (including from the losing __weak definition). + */ +void set_output_ctx2(__u64 *ctx) +{ + output_ctx2 = ctx[1]; /* long id, same as in BPF_PROG below */ +} + +/* this weak instance should lose, because it will be processed second */ +__weak int set_output_weak(int x) +{ + static volatile int whatever; + + /* make sure we use CO-RE relocations in a weak function, this used to + * cause problems for BPF static linker + */ + whatever = 2 * bpf_core_type_size(struct task_struct); + __sink(whatever); + + output_weak2 = x; + return 2 * x; +} + +extern int set_output_val1(int x); + +/* here we'll force set_output_ctx1() to be __hidden in the final obj file */ +__hidden extern void set_output_ctx1(__u64 *ctx); + +SEC("?raw_tp/sys_enter") +int BPF_PROG(handler2, struct pt_regs *regs, long id) +{ + static volatile int whatever; + + if (my_tid != (u32)bpf_get_current_pid_tgid() || id != syscall_id) + return 0; + + /* make sure we have CO-RE relocations in main program */ + whatever = bpf_core_type_size(struct task_struct); + __sink(whatever); + + set_output_val1(2000); + set_output_ctx1(ctx); /* ctx definition is hidden in BPF_PROG macro */ + + /* keep input value the same across both files to avoid dependency on + * handler call order; differentiate by output_weak1 vs output_weak2. + */ + set_output_weak(42); + + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/linked_list.c b/tools/testing/selftests/bpf/progs/linked_list.c new file mode 100644 index 0000000000..84d1777a9e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/linked_list.c @@ -0,0 +1,381 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_experimental.h" + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +#include "linked_list.h" + +static __always_inline +int list_push_pop(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool leave_in_map) +{ + struct bpf_list_node *n; + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 2; + + bpf_spin_lock(lock); + n = bpf_list_pop_front(head); + bpf_spin_unlock(lock); + if (n) { + bpf_obj_drop(container_of(n, struct foo, node2)); + bpf_obj_drop(f); + return 3; + } + + bpf_spin_lock(lock); + n = bpf_list_pop_back(head); + bpf_spin_unlock(lock); + if (n) { + bpf_obj_drop(container_of(n, struct foo, node2)); + bpf_obj_drop(f); + return 4; + } + + + bpf_spin_lock(lock); + f->data = 42; + bpf_list_push_front(head, &f->node2); + bpf_spin_unlock(lock); + if (leave_in_map) + return 0; + bpf_spin_lock(lock); + n = bpf_list_pop_back(head); + bpf_spin_unlock(lock); + if (!n) + return 5; + f = container_of(n, struct foo, node2); + if (f->data != 42) { + bpf_obj_drop(f); + return 6; + } + + bpf_spin_lock(lock); + f->data = 13; + bpf_list_push_front(head, &f->node2); + bpf_spin_unlock(lock); + bpf_spin_lock(lock); + n = bpf_list_pop_front(head); + bpf_spin_unlock(lock); + if (!n) + return 7; + f = container_of(n, struct foo, node2); + if (f->data != 13) { + bpf_obj_drop(f); + return 8; + } + bpf_obj_drop(f); + + bpf_spin_lock(lock); + n = bpf_list_pop_front(head); + bpf_spin_unlock(lock); + if (n) { + bpf_obj_drop(container_of(n, struct foo, node2)); + return 9; + } + + bpf_spin_lock(lock); + n = bpf_list_pop_back(head); + bpf_spin_unlock(lock); + if (n) { + bpf_obj_drop(container_of(n, struct foo, node2)); + return 10; + } + return 0; +} + + +static __always_inline +int list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool leave_in_map) +{ + struct bpf_list_node *n; + struct foo *f[200], *pf; + int i; + + /* Loop following this check adds nodes 2-at-a-time in order to + * validate multiple release_on_unlock release logic + */ + if (ARRAY_SIZE(f) % 2) + return 10; + + for (i = 0; i < ARRAY_SIZE(f); i += 2) { + f[i] = bpf_obj_new(typeof(**f)); + if (!f[i]) + return 2; + f[i]->data = i; + + f[i + 1] = bpf_obj_new(typeof(**f)); + if (!f[i + 1]) { + bpf_obj_drop(f[i]); + return 9; + } + f[i + 1]->data = i + 1; + + bpf_spin_lock(lock); + bpf_list_push_front(head, &f[i]->node2); + bpf_list_push_front(head, &f[i + 1]->node2); + bpf_spin_unlock(lock); + } + + for (i = 0; i < ARRAY_SIZE(f); i++) { + bpf_spin_lock(lock); + n = bpf_list_pop_front(head); + bpf_spin_unlock(lock); + if (!n) + return 3; + pf = container_of(n, struct foo, node2); + if (pf->data != (ARRAY_SIZE(f) - i - 1)) { + bpf_obj_drop(pf); + return 4; + } + bpf_spin_lock(lock); + bpf_list_push_back(head, &pf->node2); + bpf_spin_unlock(lock); + } + + if (leave_in_map) + return 0; + + for (i = 0; i < ARRAY_SIZE(f); i++) { + bpf_spin_lock(lock); + n = bpf_list_pop_back(head); + bpf_spin_unlock(lock); + if (!n) + return 5; + pf = container_of(n, struct foo, node2); + if (pf->data != i) { + bpf_obj_drop(pf); + return 6; + } + bpf_obj_drop(pf); + } + bpf_spin_lock(lock); + n = bpf_list_pop_back(head); + bpf_spin_unlock(lock); + if (n) { + bpf_obj_drop(container_of(n, struct foo, node2)); + return 7; + } + + bpf_spin_lock(lock); + n = bpf_list_pop_front(head); + bpf_spin_unlock(lock); + if (n) { + bpf_obj_drop(container_of(n, struct foo, node2)); + return 8; + } + return 0; +} + +static __always_inline +int list_in_list(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool leave_in_map) +{ + struct bpf_list_node *n; + struct bar *ba[8], *b; + struct foo *f; + int i; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 2; + for (i = 0; i < ARRAY_SIZE(ba); i++) { + b = bpf_obj_new(typeof(*b)); + if (!b) { + bpf_obj_drop(f); + return 3; + } + b->data = i; + bpf_spin_lock(&f->lock); + bpf_list_push_back(&f->head, &b->node); + bpf_spin_unlock(&f->lock); + } + + bpf_spin_lock(lock); + f->data = 42; + bpf_list_push_front(head, &f->node2); + bpf_spin_unlock(lock); + + if (leave_in_map) + return 0; + + bpf_spin_lock(lock); + n = bpf_list_pop_front(head); + bpf_spin_unlock(lock); + if (!n) + return 4; + f = container_of(n, struct foo, node2); + if (f->data != 42) { + bpf_obj_drop(f); + return 5; + } + + for (i = 0; i < ARRAY_SIZE(ba); i++) { + bpf_spin_lock(&f->lock); + n = bpf_list_pop_front(&f->head); + bpf_spin_unlock(&f->lock); + if (!n) { + bpf_obj_drop(f); + return 6; + } + b = container_of(n, struct bar, node); + if (b->data != i) { + bpf_obj_drop(f); + bpf_obj_drop(b); + return 7; + } + bpf_obj_drop(b); + } + bpf_spin_lock(&f->lock); + n = bpf_list_pop_front(&f->head); + bpf_spin_unlock(&f->lock); + if (n) { + bpf_obj_drop(f); + bpf_obj_drop(container_of(n, struct bar, node)); + return 8; + } + bpf_obj_drop(f); + return 0; +} + +static __always_inline +int test_list_push_pop(struct bpf_spin_lock *lock, struct bpf_list_head *head) +{ + int ret; + + ret = list_push_pop(lock, head, false); + if (ret) + return ret; + return list_push_pop(lock, head, true); +} + +static __always_inline +int test_list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *head) +{ + int ret; + + ret = list_push_pop_multiple(lock, head, false); + if (ret) + return ret; + return list_push_pop_multiple(lock, head, true); +} + +static __always_inline +int test_list_in_list(struct bpf_spin_lock *lock, struct bpf_list_head *head) +{ + int ret; + + ret = list_in_list(lock, head, false); + if (ret) + return ret; + return list_in_list(lock, head, true); +} + +SEC("tc") +int map_list_push_pop(void *ctx) +{ + struct map_value *v; + + v = bpf_map_lookup_elem(&array_map, &(int){0}); + if (!v) + return 1; + return test_list_push_pop(&v->lock, &v->head); +} + +SEC("tc") +int inner_map_list_push_pop(void *ctx) +{ + struct map_value *v; + void *map; + + map = bpf_map_lookup_elem(&map_of_maps, &(int){0}); + if (!map) + return 1; + v = bpf_map_lookup_elem(map, &(int){0}); + if (!v) + return 1; + return test_list_push_pop(&v->lock, &v->head); +} + +SEC("tc") +int global_list_push_pop(void *ctx) +{ + return test_list_push_pop(&glock, &ghead); +} + +SEC("tc") +int map_list_push_pop_multiple(void *ctx) +{ + struct map_value *v; + + v = bpf_map_lookup_elem(&array_map, &(int){0}); + if (!v) + return 1; + return test_list_push_pop_multiple(&v->lock, &v->head); +} + +SEC("tc") +int inner_map_list_push_pop_multiple(void *ctx) +{ + struct map_value *v; + void *map; + + map = bpf_map_lookup_elem(&map_of_maps, &(int){0}); + if (!map) + return 1; + v = bpf_map_lookup_elem(map, &(int){0}); + if (!v) + return 1; + return test_list_push_pop_multiple(&v->lock, &v->head); +} + +SEC("tc") +int global_list_push_pop_multiple(void *ctx) +{ + int ret; + + ret = list_push_pop_multiple(&glock, &ghead, false); + if (ret) + return ret; + return list_push_pop_multiple(&glock, &ghead, true); +} + +SEC("tc") +int map_list_in_list(void *ctx) +{ + struct map_value *v; + + v = bpf_map_lookup_elem(&array_map, &(int){0}); + if (!v) + return 1; + return test_list_in_list(&v->lock, &v->head); +} + +SEC("tc") +int inner_map_list_in_list(void *ctx) +{ + struct map_value *v; + void *map; + + map = bpf_map_lookup_elem(&map_of_maps, &(int){0}); + if (!map) + return 1; + v = bpf_map_lookup_elem(map, &(int){0}); + if (!v) + return 1; + return test_list_in_list(&v->lock, &v->head); +} + +SEC("tc") +int global_list_in_list(void *ctx) +{ + return test_list_in_list(&glock, &ghead); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/linked_list.h b/tools/testing/selftests/bpf/progs/linked_list.h new file mode 100644 index 0000000000..c0f3609a7f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/linked_list.h @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef LINKED_LIST_H +#define LINKED_LIST_H + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "bpf_experimental.h" + +struct bar { + struct bpf_list_node node; + int data; +}; + +struct foo { + struct bpf_list_node node; + struct bpf_list_head head __contains(bar, node); + struct bpf_spin_lock lock; + int data; + struct bpf_list_node node2; +}; + +struct map_value { + struct bpf_spin_lock lock; + int data; + struct bpf_list_head head __contains(foo, node2); +}; + +struct array_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +}; + +struct array_map array_map SEC(".maps"); +struct array_map inner_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); + __array(values, struct array_map); +} map_of_maps SEC(".maps") = { + .values = { + [0] = &inner_map, + }, +}; + +#define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8))) + +private(A) struct bpf_spin_lock glock; +private(A) struct bpf_list_head ghead __contains(foo, node2); +private(B) struct bpf_spin_lock glock2; + +#endif diff --git a/tools/testing/selftests/bpf/progs/linked_list_fail.c b/tools/testing/selftests/bpf/progs/linked_list_fail.c new file mode 100644 index 0000000000..6438982b92 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/linked_list_fail.c @@ -0,0 +1,612 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_experimental.h" + +#include "linked_list.h" + +#define INIT \ + struct map_value *v, *v2, *iv, *iv2; \ + struct foo *f, *f1, *f2; \ + struct bar *b; \ + void *map; \ + \ + map = bpf_map_lookup_elem(&map_of_maps, &(int){ 0 }); \ + if (!map) \ + return 0; \ + v = bpf_map_lookup_elem(&array_map, &(int){ 0 }); \ + if (!v) \ + return 0; \ + v2 = bpf_map_lookup_elem(&array_map, &(int){ 0 }); \ + if (!v2) \ + return 0; \ + iv = bpf_map_lookup_elem(map, &(int){ 0 }); \ + if (!iv) \ + return 0; \ + iv2 = bpf_map_lookup_elem(map, &(int){ 0 }); \ + if (!iv2) \ + return 0; \ + f = bpf_obj_new(typeof(*f)); \ + if (!f) \ + return 0; \ + f1 = f; \ + f2 = bpf_obj_new(typeof(*f2)); \ + if (!f2) { \ + bpf_obj_drop(f1); \ + return 0; \ + } \ + b = bpf_obj_new(typeof(*b)); \ + if (!b) { \ + bpf_obj_drop(f2); \ + bpf_obj_drop(f1); \ + return 0; \ + } + +#define CHECK(test, op, hexpr) \ + SEC("?tc") \ + int test##_missing_lock_##op(void *ctx) \ + { \ + INIT; \ + void (*p)(void *) = (void *)&bpf_list_##op; \ + p(hexpr); \ + return 0; \ + } + +CHECK(kptr, pop_front, &f->head); +CHECK(kptr, pop_back, &f->head); + +CHECK(global, pop_front, &ghead); +CHECK(global, pop_back, &ghead); + +CHECK(map, pop_front, &v->head); +CHECK(map, pop_back, &v->head); + +CHECK(inner_map, pop_front, &iv->head); +CHECK(inner_map, pop_back, &iv->head); + +#undef CHECK + +#define CHECK(test, op, hexpr, nexpr) \ + SEC("?tc") \ + int test##_missing_lock_##op(void *ctx) \ + { \ + INIT; \ + bpf_list_##op(hexpr, nexpr); \ + return 0; \ + } + +CHECK(kptr, push_front, &f->head, &b->node); +CHECK(kptr, push_back, &f->head, &b->node); + +CHECK(global, push_front, &ghead, &f->node2); +CHECK(global, push_back, &ghead, &f->node2); + +CHECK(map, push_front, &v->head, &f->node2); +CHECK(map, push_back, &v->head, &f->node2); + +CHECK(inner_map, push_front, &iv->head, &f->node2); +CHECK(inner_map, push_back, &iv->head, &f->node2); + +#undef CHECK + +#define CHECK(test, op, lexpr, hexpr) \ + SEC("?tc") \ + int test##_incorrect_lock_##op(void *ctx) \ + { \ + INIT; \ + void (*p)(void *) = (void *)&bpf_list_##op; \ + bpf_spin_lock(lexpr); \ + p(hexpr); \ + return 0; \ + } + +#define CHECK_OP(op) \ + CHECK(kptr_kptr, op, &f1->lock, &f2->head); \ + CHECK(kptr_global, op, &f1->lock, &ghead); \ + CHECK(kptr_map, op, &f1->lock, &v->head); \ + CHECK(kptr_inner_map, op, &f1->lock, &iv->head); \ + \ + CHECK(global_global, op, &glock2, &ghead); \ + CHECK(global_kptr, op, &glock, &f1->head); \ + CHECK(global_map, op, &glock, &v->head); \ + CHECK(global_inner_map, op, &glock, &iv->head); \ + \ + CHECK(map_map, op, &v->lock, &v2->head); \ + CHECK(map_kptr, op, &v->lock, &f2->head); \ + CHECK(map_global, op, &v->lock, &ghead); \ + CHECK(map_inner_map, op, &v->lock, &iv->head); \ + \ + CHECK(inner_map_inner_map, op, &iv->lock, &iv2->head); \ + CHECK(inner_map_kptr, op, &iv->lock, &f2->head); \ + CHECK(inner_map_global, op, &iv->lock, &ghead); \ + CHECK(inner_map_map, op, &iv->lock, &v->head); + +CHECK_OP(pop_front); +CHECK_OP(pop_back); + +#undef CHECK +#undef CHECK_OP + +#define CHECK(test, op, lexpr, hexpr, nexpr) \ + SEC("?tc") \ + int test##_incorrect_lock_##op(void *ctx) \ + { \ + INIT; \ + bpf_spin_lock(lexpr); \ + bpf_list_##op(hexpr, nexpr); \ + return 0; \ + } + +#define CHECK_OP(op) \ + CHECK(kptr_kptr, op, &f1->lock, &f2->head, &b->node); \ + CHECK(kptr_global, op, &f1->lock, &ghead, &f->node2); \ + CHECK(kptr_map, op, &f1->lock, &v->head, &f->node2); \ + CHECK(kptr_inner_map, op, &f1->lock, &iv->head, &f->node2); \ + \ + CHECK(global_global, op, &glock2, &ghead, &f->node2); \ + CHECK(global_kptr, op, &glock, &f1->head, &b->node); \ + CHECK(global_map, op, &glock, &v->head, &f->node2); \ + CHECK(global_inner_map, op, &glock, &iv->head, &f->node2); \ + \ + CHECK(map_map, op, &v->lock, &v2->head, &f->node2); \ + CHECK(map_kptr, op, &v->lock, &f2->head, &b->node); \ + CHECK(map_global, op, &v->lock, &ghead, &f->node2); \ + CHECK(map_inner_map, op, &v->lock, &iv->head, &f->node2); \ + \ + CHECK(inner_map_inner_map, op, &iv->lock, &iv2->head, &f->node2);\ + CHECK(inner_map_kptr, op, &iv->lock, &f2->head, &b->node); \ + CHECK(inner_map_global, op, &iv->lock, &ghead, &f->node2); \ + CHECK(inner_map_map, op, &iv->lock, &v->head, &f->node2); + +CHECK_OP(push_front); +CHECK_OP(push_back); + +#undef CHECK +#undef CHECK_OP +#undef INIT + +SEC("?kprobe/xyz") +int map_compat_kprobe(void *ctx) +{ + bpf_list_push_front(&ghead, NULL); + return 0; +} + +SEC("?kretprobe/xyz") +int map_compat_kretprobe(void *ctx) +{ + bpf_list_push_front(&ghead, NULL); + return 0; +} + +SEC("?tracepoint/xyz") +int map_compat_tp(void *ctx) +{ + bpf_list_push_front(&ghead, NULL); + return 0; +} + +SEC("?perf_event") +int map_compat_perf(void *ctx) +{ + bpf_list_push_front(&ghead, NULL); + return 0; +} + +SEC("?raw_tp/xyz") +int map_compat_raw_tp(void *ctx) +{ + bpf_list_push_front(&ghead, NULL); + return 0; +} + +SEC("?raw_tp.w/xyz") +int map_compat_raw_tp_w(void *ctx) +{ + bpf_list_push_front(&ghead, NULL); + return 0; +} + +SEC("?tc") +int obj_type_id_oor(void *ctx) +{ + bpf_obj_new_impl(~0UL, NULL); + return 0; +} + +SEC("?tc") +int obj_new_no_composite(void *ctx) +{ + bpf_obj_new_impl(bpf_core_type_id_local(int), (void *)42); + return 0; +} + +SEC("?tc") +int obj_new_no_struct(void *ctx) +{ + + bpf_obj_new(union { int data; unsigned udata; }); + return 0; +} + +SEC("?tc") +int obj_drop_non_zero_off(void *ctx) +{ + void *f; + + f = bpf_obj_new(struct foo); + if (!f) + return 0; + bpf_obj_drop(f+1); + return 0; +} + +SEC("?tc") +int new_null_ret(void *ctx) +{ + return bpf_obj_new(struct foo)->data; +} + +SEC("?tc") +int obj_new_acq(void *ctx) +{ + bpf_obj_new(struct foo); + return 0; +} + +SEC("?tc") +int use_after_drop(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_obj_drop(f); + return f->data; +} + +SEC("?tc") +int ptr_walk_scalar(void *ctx) +{ + struct test1 { + struct test2 { + struct test2 *next; + } *ptr; + } *p; + + p = bpf_obj_new(typeof(*p)); + if (!p) + return 0; + bpf_this_cpu_ptr(p->ptr); + return 0; +} + +SEC("?tc") +int direct_read_lock(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + return *(int *)&f->lock; +} + +SEC("?tc") +int direct_write_lock(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + *(int *)&f->lock = 0; + return 0; +} + +SEC("?tc") +int direct_read_head(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + return *(int *)&f->head; +} + +SEC("?tc") +int direct_write_head(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + *(int *)&f->head = 0; + return 0; +} + +SEC("?tc") +int direct_read_node(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + return *(int *)&f->node2; +} + +SEC("?tc") +int direct_write_node(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + *(int *)&f->node2 = 0; + return 0; +} + +static __always_inline +int use_after_unlock(bool push_front) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&glock); + f->data = 42; + if (push_front) + bpf_list_push_front(&ghead, &f->node2); + else + bpf_list_push_back(&ghead, &f->node2); + bpf_spin_unlock(&glock); + + return f->data; +} + +SEC("?tc") +int use_after_unlock_push_front(void *ctx) +{ + return use_after_unlock(true); +} + +SEC("?tc") +int use_after_unlock_push_back(void *ctx) +{ + return use_after_unlock(false); +} + +static __always_inline +int list_double_add(bool push_front) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&glock); + if (push_front) { + bpf_list_push_front(&ghead, &f->node2); + bpf_list_push_front(&ghead, &f->node2); + } else { + bpf_list_push_back(&ghead, &f->node2); + bpf_list_push_back(&ghead, &f->node2); + } + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int double_push_front(void *ctx) +{ + return list_double_add(true); +} + +SEC("?tc") +int double_push_back(void *ctx) +{ + return list_double_add(false); +} + +SEC("?tc") +int no_node_value_type(void *ctx) +{ + void *p; + + p = bpf_obj_new(struct { int data; }); + if (!p) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front(&ghead, p); + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int incorrect_value_type(void *ctx) +{ + struct bar *b; + + b = bpf_obj_new(typeof(*b)); + if (!b) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front(&ghead, &b->node); + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int incorrect_node_var_off(struct __sk_buff *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front(&ghead, (void *)&f->node2 + ctx->protocol); + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int incorrect_node_off1(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front(&ghead, (void *)&f->node2 + 1); + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int incorrect_node_off2(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front(&ghead, &f->node); + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int no_head_type(void *ctx) +{ + void *p; + + p = bpf_obj_new(typeof(struct { int data; })); + if (!p) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front(p, NULL); + bpf_spin_lock(&glock); + + return 0; +} + +SEC("?tc") +int incorrect_head_var_off1(struct __sk_buff *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front((void *)&ghead + ctx->protocol, &f->node2); + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int incorrect_head_var_off2(struct __sk_buff *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front((void *)&f->head + ctx->protocol, &f->node2); + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int incorrect_head_off1(void *ctx) +{ + struct foo *f; + struct bar *b; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + b = bpf_obj_new(typeof(*b)); + if (!b) { + bpf_obj_drop(f); + return 0; + } + + bpf_spin_lock(&f->lock); + bpf_list_push_front((void *)&f->head + 1, &b->node); + bpf_spin_unlock(&f->lock); + + return 0; +} + +SEC("?tc") +int incorrect_head_off2(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + + bpf_spin_lock(&glock); + bpf_list_push_front((void *)&ghead + 1, &f->node2); + bpf_spin_unlock(&glock); + + return 0; +} + +static __always_inline +int pop_ptr_off(void *(*op)(void *head)) +{ + struct { + struct bpf_list_head head __contains(foo, node2); + struct bpf_spin_lock lock; + } *p; + struct bpf_list_node *n; + + p = bpf_obj_new(typeof(*p)); + if (!p) + return 0; + bpf_spin_lock(&p->lock); + n = op(&p->head); + bpf_spin_unlock(&p->lock); + + if (!n) + return 0; + bpf_spin_lock((void *)n); + return 0; +} + +SEC("?tc") +int pop_front_off(void *ctx) +{ + return pop_ptr_off((void *)bpf_list_pop_front); +} + +SEC("?tc") +int pop_back_off(void *ctx) +{ + return pop_ptr_off((void *)bpf_list_pop_back); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/linked_maps1.c b/tools/testing/selftests/bpf/progs/linked_maps1.c new file mode 100644 index 0000000000..00bf1ca959 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/linked_maps1.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct my_key { long x; }; +struct my_value { long x; }; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, struct my_key); + __type(value, struct my_value); + __uint(max_entries, 16); +} map1 SEC(".maps"); + + /* Matches map2 definition in linked_maps2.c. Order of the attributes doesn't + * matter. + */ +typedef struct { + __uint(max_entries, 8); + __type(key, int); + __type(value, int); + __uint(type, BPF_MAP_TYPE_ARRAY); +} map2_t; + +extern map2_t map2 SEC(".maps"); + +/* This should be the winning map definition, but we have no way of verifying, + * so we just make sure that it links and works without errors + */ +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, int); + __uint(max_entries, 16); +} map_weak __weak SEC(".maps"); + +int output_first1; +int output_second1; +int output_weak1; + +SEC("raw_tp/sys_enter") +int BPF_PROG(handler_enter1) +{ + /* update values with key = 1 */ + int key = 1, val = 1; + struct my_key key_struct = { .x = 1 }; + struct my_value val_struct = { .x = 1000 }; + + bpf_map_update_elem(&map1, &key_struct, &val_struct, 0); + bpf_map_update_elem(&map2, &key, &val, 0); + bpf_map_update_elem(&map_weak, &key, &val, 0); + + return 0; +} + +SEC("raw_tp/sys_exit") +int BPF_PROG(handler_exit1) +{ + /* lookup values with key = 2, set in another file */ + int key = 2, *val; + struct my_key key_struct = { .x = 2 }; + struct my_value *value_struct; + + value_struct = bpf_map_lookup_elem(&map1, &key_struct); + if (value_struct) + output_first1 = value_struct->x; + + val = bpf_map_lookup_elem(&map2, &key); + if (val) + output_second1 = *val; + + val = bpf_map_lookup_elem(&map_weak, &key); + if (val) + output_weak1 = *val; + + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/linked_maps2.c b/tools/testing/selftests/bpf/progs/linked_maps2.c new file mode 100644 index 0000000000..0693687474 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/linked_maps2.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +/* modifiers and typedefs are ignored when comparing key/value types */ +typedef struct my_key { long x; } key_type; +typedef struct my_value { long x; } value_type; + +extern struct { + __uint(max_entries, 16); + __type(key, key_type); + __type(value, value_type); + __uint(type, BPF_MAP_TYPE_HASH); +} map1 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, int); + __uint(max_entries, 8); +} map2 SEC(".maps"); + +/* this definition will lose, but it has to exactly match the winner */ +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, int); + __uint(max_entries, 16); +} map_weak __weak SEC(".maps"); + +int output_first2; +int output_second2; +int output_weak2; + +SEC("raw_tp/sys_enter") +int BPF_PROG(handler_enter2) +{ + /* update values with key = 2 */ + int key = 2, val = 2; + key_type key_struct = { .x = 2 }; + value_type val_struct = { .x = 2000 }; + + bpf_map_update_elem(&map1, &key_struct, &val_struct, 0); + bpf_map_update_elem(&map2, &key, &val, 0); + bpf_map_update_elem(&map_weak, &key, &val, 0); + + return 0; +} + +SEC("raw_tp/sys_exit") +int BPF_PROG(handler_exit2) +{ + /* lookup values with key = 1, set in another file */ + int key = 1, *val; + key_type key_struct = { .x = 1 }; + value_type *value_struct; + + value_struct = bpf_map_lookup_elem(&map1, &key_struct); + if (value_struct) + output_first2 = value_struct->x; + + val = bpf_map_lookup_elem(&map2, &key); + if (val) + output_second2 = *val; + + val = bpf_map_lookup_elem(&map_weak, &key); + if (val) + output_weak2 = *val; + + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/linked_vars1.c b/tools/testing/selftests/bpf/progs/linked_vars1.c new file mode 100644 index 0000000000..ef9e9d0bb0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/linked_vars1.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +extern int LINUX_KERNEL_VERSION __kconfig; +/* this weak extern will be strict due to the other file's strong extern */ +extern bool CONFIG_BPF_SYSCALL __kconfig __weak; +extern const void bpf_link_fops __ksym __weak; + +int input_bss1; +int input_data1 = 1; +const volatile int input_rodata1 = 11; + +int input_bss_weak __weak; +/* these two definitions should win */ +int input_data_weak __weak = 10; +const volatile int input_rodata_weak __weak = 100; + +extern int input_bss2; +extern int input_data2; +extern const int input_rodata2; + +int output_bss1; +int output_data1; +int output_rodata1; + +long output_sink1; + +static __noinline int get_bss_res(void) +{ + /* just make sure all the relocations work against .text as well */ + return input_bss1 + input_bss2 + input_bss_weak; +} + +SEC("raw_tp/sys_enter") +int BPF_PROG(handler1) +{ + output_bss1 = get_bss_res(); + output_data1 = input_data1 + input_data2 + input_data_weak; + output_rodata1 = input_rodata1 + input_rodata2 + input_rodata_weak; + + /* make sure we actually use above special externs, otherwise compiler + * will optimize them out + */ + output_sink1 = LINUX_KERNEL_VERSION + + CONFIG_BPF_SYSCALL + + (long)&bpf_link_fops; + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/linked_vars2.c b/tools/testing/selftests/bpf/progs/linked_vars2.c new file mode 100644 index 0000000000..e4f5bd388a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/linked_vars2.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +extern int LINUX_KERNEL_VERSION __kconfig; +/* when an extern is defined as both strong and weak, resulting symbol will be strong */ +extern bool CONFIG_BPF_SYSCALL __kconfig; +extern const void __start_BTF __ksym; + +int input_bss2; +int input_data2 = 2; +const volatile int input_rodata2 = 22; + +int input_bss_weak __weak; +/* these two weak variables should lose */ +int input_data_weak __weak = 20; +const volatile int input_rodata_weak __weak = 200; + +extern int input_bss1; +extern int input_data1; +extern const int input_rodata1; + +int output_bss2; +int output_data2; +int output_rodata2; + +int output_sink2; + +static __noinline int get_data_res(void) +{ + /* just make sure all the relocations work against .text as well */ + return input_data1 + input_data2 + input_data_weak; +} + +SEC("raw_tp/sys_enter") +int BPF_PROG(handler2) +{ + output_bss2 = input_bss1 + input_bss2 + input_bss_weak; + output_data2 = get_data_res(); + output_rodata2 = input_rodata1 + input_rodata2 + input_rodata_weak; + + /* make sure we actually use above special externs, otherwise compiler + * will optimize them out + */ + output_sink2 = LINUX_KERNEL_VERSION + + CONFIG_BPF_SYSCALL + + (long)&__start_BTF; + + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/load_bytes_relative.c b/tools/testing/selftests/bpf/progs/load_bytes_relative.c new file mode 100644 index 0000000000..dc1d04a7a3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/load_bytes_relative.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2020 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} test_result SEC(".maps"); + +SEC("cgroup_skb/egress") +int load_bytes_relative(struct __sk_buff *skb) +{ + struct ethhdr eth; + struct iphdr iph; + + __u32 map_key = 0; + __u32 test_passed = 0; + + /* MAC header is not set by the time cgroup_skb/egress triggers */ + if (bpf_skb_load_bytes_relative(skb, 0, ð, sizeof(eth), + BPF_HDR_START_MAC) != -EFAULT) + goto fail; + + if (bpf_skb_load_bytes_relative(skb, 0, &iph, sizeof(iph), + BPF_HDR_START_NET)) + goto fail; + + if (bpf_skb_load_bytes_relative(skb, 0xffff, &iph, sizeof(iph), + BPF_HDR_START_NET) != -EFAULT) + goto fail; + + test_passed = 1; + +fail: + bpf_map_update_elem(&test_result, &map_key, &test_passed, BPF_ANY); + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash.c b/tools/testing/selftests/bpf/progs/local_kptr_stash.c new file mode 100644 index 0000000000..b567a666d2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/local_kptr_stash.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "../bpf_experimental.h" +#include "../bpf_testmod/bpf_testmod_kfunc.h" + +struct node_data { + long key; + long data; + struct bpf_rb_node node; +}; + +struct plain_local { + long key; + long data; +}; + +struct map_value { + struct prog_test_ref_kfunc *not_kptr; + struct prog_test_ref_kfunc __kptr *val; + struct node_data __kptr *node; + struct plain_local __kptr *plain; +}; + +/* This is necessary so that LLVM generates BTF for node_data struct + * If it's not included, a fwd reference for node_data will be generated but + * no struct. Example BTF of "node" field in map_value when not included: + * + * [10] PTR '(anon)' type_id=35 + * [34] FWD 'node_data' fwd_kind=struct + * [35] TYPE_TAG 'kptr_ref' type_id=34 + * + * (with no node_data struct defined) + * Had to do the same w/ bpf_kfunc_call_test_release below + */ +struct node_data *just_here_because_btf_bug; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 2); +} some_nodes SEC(".maps"); + +static int create_and_stash(int idx, int val) +{ + struct map_value *mapval; + struct node_data *res; + + mapval = bpf_map_lookup_elem(&some_nodes, &idx); + if (!mapval) + return 1; + + res = bpf_obj_new(typeof(*res)); + if (!res) + return 1; + res->key = val; + + res = bpf_kptr_xchg(&mapval->node, res); + if (res) + bpf_obj_drop(res); + return 0; +} + +SEC("tc") +long stash_rb_nodes(void *ctx) +{ + return create_and_stash(0, 41) ?: create_and_stash(1, 42); +} + +SEC("tc") +long stash_plain(void *ctx) +{ + struct map_value *mapval; + struct plain_local *res; + int idx = 0; + + mapval = bpf_map_lookup_elem(&some_nodes, &idx); + if (!mapval) + return 1; + + res = bpf_obj_new(typeof(*res)); + if (!res) + return 1; + res->key = 41; + + res = bpf_kptr_xchg(&mapval->plain, res); + if (res) + bpf_obj_drop(res); + return 0; +} + +SEC("tc") +long unstash_rb_node(void *ctx) +{ + struct map_value *mapval; + struct node_data *res; + long retval; + int key = 1; + + mapval = bpf_map_lookup_elem(&some_nodes, &key); + if (!mapval) + return 1; + + res = bpf_kptr_xchg(&mapval->node, NULL); + if (res) { + retval = res->key; + bpf_obj_drop(res); + return retval; + } + return 1; +} + +SEC("tc") +long stash_test_ref_kfunc(void *ctx) +{ + struct prog_test_ref_kfunc *res; + struct map_value *mapval; + int key = 0; + + mapval = bpf_map_lookup_elem(&some_nodes, &key); + if (!mapval) + return 1; + + res = bpf_kptr_xchg(&mapval->val, NULL); + if (res) + bpf_kfunc_call_test_release(res); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c b/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c new file mode 100644 index 0000000000..fcf7a7567d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "../bpf_experimental.h" +#include "bpf_misc.h" + +struct node_data { + long key; + long data; + struct bpf_rb_node node; +}; + +struct map_value { + struct node_data __kptr *node; +}; + +struct node_data2 { + long key[4]; +}; + +/* This is necessary so that LLVM generates BTF for node_data struct + * If it's not included, a fwd reference for node_data will be generated but + * no struct. Example BTF of "node" field in map_value when not included: + * + * [10] PTR '(anon)' type_id=35 + * [34] FWD 'node_data' fwd_kind=struct + * [35] TYPE_TAG 'kptr_ref' type_id=34 + */ +struct node_data *just_here_because_btf_bug; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 2); +} some_nodes SEC(".maps"); + +SEC("tc") +__failure __msg("invalid kptr access, R2 type=ptr_node_data2 expected=ptr_node_data") +long stash_rb_nodes(void *ctx) +{ + struct map_value *mapval; + struct node_data2 *res; + int idx = 0; + + mapval = bpf_map_lookup_elem(&some_nodes, &idx); + if (!mapval) + return 1; + + res = bpf_obj_new(typeof(*res)); + if (!res) + return 1; + res->key[0] = 40; + + res = bpf_kptr_xchg(&mapval->node, res); + if (res) + bpf_obj_drop(res); + return 0; +} + +SEC("tc") +__failure __msg("R1 must have zero offset when passed to release func") +long drop_rb_node_off(void *ctx) +{ + struct map_value *mapval; + struct node_data *res; + int idx = 0; + + mapval = bpf_map_lookup_elem(&some_nodes, &idx); + if (!mapval) + return 1; + + res = bpf_obj_new(typeof(*res)); + if (!res) + return 1; + /* Try releasing with graph node offset */ + bpf_obj_drop(&res->node); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c new file mode 100644 index 0000000000..bc8ea56671 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/local_storage.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2020 Google LLC. + */ + +#include "vmlinux.h" +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +#define DUMMY_STORAGE_VALUE 0xdeadbeef + +int monitored_pid = 0; +int inode_storage_result = -1; +int sk_storage_result = -1; +int task_storage_result = -1; + +struct local_storage { + struct inode *exec_inode; + __u32 value; +}; + +struct { + __uint(type, BPF_MAP_TYPE_INODE_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct local_storage); +} inode_storage_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC | BPF_F_CLONE); + __type(key, int); + __type(value, struct local_storage); +} sk_storage_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC | BPF_F_CLONE); + __type(key, int); + __type(value, struct local_storage); +} sk_storage_map2 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct local_storage); +} task_storage_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct local_storage); +} task_storage_map2 SEC(".maps"); + +SEC("lsm/inode_unlink") +int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim) +{ + __u32 pid = bpf_get_current_pid_tgid() >> 32; + struct bpf_local_storage *local_storage; + struct local_storage *storage; + struct task_struct *task; + bool is_self_unlink; + + if (pid != monitored_pid) + return 0; + + task = bpf_get_current_task_btf(); + if (!task) + return 0; + + task_storage_result = -1; + + storage = bpf_task_storage_get(&task_storage_map, task, 0, 0); + if (!storage) + return 0; + + /* Don't let an executable delete itself */ + is_self_unlink = storage->exec_inode == victim->d_inode; + + storage = bpf_task_storage_get(&task_storage_map2, task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!storage || storage->value) + return 0; + + if (bpf_task_storage_delete(&task_storage_map, task)) + return 0; + + /* Ensure that the task_storage_map is disconnected from the storage. + * The storage memory should not be freed back to the + * bpf_mem_alloc. + */ + local_storage = task->bpf_storage; + if (!local_storage || local_storage->smap) + return 0; + + task_storage_result = 0; + + return is_self_unlink ? -EPERM : 0; +} + +SEC("lsm.s/inode_rename") +int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) +{ + struct local_storage *storage; + int err; + + /* new_dentry->d_inode can be NULL when the inode is renamed to a file + * that did not exist before. The helper should be able to handle this + * NULL pointer. + */ + bpf_inode_storage_get(&inode_storage_map, new_dentry->d_inode, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + + storage = bpf_inode_storage_get(&inode_storage_map, old_dentry->d_inode, + 0, 0); + if (!storage) + return 0; + + if (storage->value != DUMMY_STORAGE_VALUE) + inode_storage_result = -1; + + err = bpf_inode_storage_delete(&inode_storage_map, old_dentry->d_inode); + if (!err) + inode_storage_result = err; + + return 0; +} + +SEC("lsm.s/socket_bind") +int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address, + int addrlen) +{ + __u32 pid = bpf_get_current_pid_tgid() >> 32; + struct local_storage *storage; + + if (pid != monitored_pid) + return 0; + + storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0, 0); + if (!storage) + return 0; + + sk_storage_result = -1; + if (storage->value != DUMMY_STORAGE_VALUE) + return 0; + + /* This tests that we can associate multiple elements + * with the local storage. + */ + storage = bpf_sk_storage_get(&sk_storage_map2, sock->sk, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!storage) + return 0; + + if (bpf_sk_storage_delete(&sk_storage_map2, sock->sk)) + return 0; + + storage = bpf_sk_storage_get(&sk_storage_map2, sock->sk, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!storage) + return 0; + + if (bpf_sk_storage_delete(&sk_storage_map, sock->sk)) + return 0; + + /* Ensure that the sk_storage_map is disconnected from the storage. */ + if (!sock->sk->sk_bpf_storage || sock->sk->sk_bpf_storage->smap) + return 0; + + sk_storage_result = 0; + return 0; +} + +SEC("lsm.s/socket_post_create") +int BPF_PROG(socket_post_create, struct socket *sock, int family, int type, + int protocol, int kern) +{ + __u32 pid = bpf_get_current_pid_tgid() >> 32; + struct local_storage *storage; + + if (pid != monitored_pid) + return 0; + + storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!storage) + return 0; + + storage->value = DUMMY_STORAGE_VALUE; + + return 0; +} + +/* This uses the local storage to remember the inode of the binary that a + * process was originally executing. + */ +SEC("lsm.s/bprm_committed_creds") +void BPF_PROG(exec, struct linux_binprm *bprm) +{ + __u32 pid = bpf_get_current_pid_tgid() >> 32; + struct local_storage *storage; + + if (pid != monitored_pid) + return; + + storage = bpf_task_storage_get(&task_storage_map, + bpf_get_current_task_btf(), 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (storage) + storage->exec_inode = bprm->file->f_inode; + + storage = bpf_inode_storage_get(&inode_storage_map, bprm->file->f_inode, + 0, BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!storage) + return; + + storage->value = DUMMY_STORAGE_VALUE; +} diff --git a/tools/testing/selftests/bpf/progs/local_storage_bench.c b/tools/testing/selftests/bpf/progs/local_storage_bench.c new file mode 100644 index 0000000000..2c3234c5b7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/local_storage_bench.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define HASHMAP_SZ 4194304 + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1000); + __type(key, int); + __type(value, int); + __array(values, struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); + }); +} array_of_local_storage_maps SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1000); + __type(key, int); + __type(value, int); + __array(values, struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, HASHMAP_SZ); + __type(key, int); + __type(value, int); + }); +} array_of_hash_maps SEC(".maps"); + +long important_hits; +long hits; + +/* set from user-space */ +const volatile unsigned int use_hashmap; +const volatile unsigned int hashmap_num_keys; +const volatile unsigned int num_maps; +const volatile unsigned int interleave; + +struct loop_ctx { + struct task_struct *task; + long loop_hits; + long loop_important_hits; +}; + +static int do_lookup(unsigned int elem, struct loop_ctx *lctx) +{ + void *map, *inner_map; + int idx = 0; + + if (use_hashmap) + map = &array_of_hash_maps; + else + map = &array_of_local_storage_maps; + + inner_map = bpf_map_lookup_elem(map, &elem); + if (!inner_map) + return -1; + + if (use_hashmap) { + idx = bpf_get_prandom_u32() % hashmap_num_keys; + bpf_map_lookup_elem(inner_map, &idx); + } else { + bpf_task_storage_get(inner_map, lctx->task, &idx, + BPF_LOCAL_STORAGE_GET_F_CREATE); + } + + lctx->loop_hits++; + if (!elem) + lctx->loop_important_hits++; + return 0; +} + +static long loop(u32 index, void *ctx) +{ + struct loop_ctx *lctx = (struct loop_ctx *)ctx; + unsigned int map_idx = index % num_maps; + + do_lookup(map_idx, lctx); + if (interleave && map_idx % 3 == 0) + do_lookup(0, lctx); + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int get_local(void *ctx) +{ + struct loop_ctx lctx; + + lctx.task = bpf_get_current_task_btf(); + lctx.loop_hits = 0; + lctx.loop_important_hits = 0; + bpf_loop(10000, &loop, &lctx, 0); + __sync_add_and_fetch(&hits, lctx.loop_hits); + __sync_add_and_fetch(&important_hits, lctx.loop_important_hits); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/local_storage_rcu_tasks_trace_bench.c b/tools/testing/selftests/bpf/progs/local_storage_rcu_tasks_trace_bench.c new file mode 100644 index 0000000000..03bf69f490 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/local_storage_rcu_tasks_trace_bench.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} task_storage SEC(".maps"); + +long hits; +long gp_hits; +long gp_times; +long current_gp_start; +long unexpected; +bool postgp_seen; + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int get_local(void *ctx) +{ + struct task_struct *task; + int idx; + int *s; + + idx = 0; + task = bpf_get_current_task_btf(); + s = bpf_task_storage_get(&task_storage, task, &idx, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!s) + return 0; + + *s = 3; + bpf_task_storage_delete(&task_storage, task); + __sync_add_and_fetch(&hits, 1); + return 0; +} + +SEC("fentry/rcu_tasks_trace_pregp_step") +int pregp_step(struct pt_regs *ctx) +{ + current_gp_start = bpf_ktime_get_ns(); + return 0; +} + +SEC("fentry/rcu_tasks_trace_postgp") +int postgp(struct pt_regs *ctx) +{ + if (!current_gp_start && postgp_seen) { + /* Will only happen if prog tracing rcu_tasks_trace_pregp_step doesn't + * execute before this prog + */ + __sync_add_and_fetch(&unexpected, 1); + return 0; + } + + __sync_add_and_fetch(&gp_times, bpf_ktime_get_ns() - current_gp_start); + __sync_add_and_fetch(&gp_hits, 1); + current_gp_start = 0; + postgp_seen = true; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c new file mode 100644 index 0000000000..50e66772c0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop1.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <stdint.h> +#include <stddef.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +SEC("raw_tracepoint/kfree_skb") +int nested_loops(volatile struct pt_regs* ctx) +{ + int i, j, sum = 0, m; + + for (j = 0; j < 300; j++) + for (i = 0; i < j; i++) { + if (j & 1) + m = PT_REGS_RC(ctx); + else + m = j; + sum += i * m; + } + + return sum; +} diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c new file mode 100644 index 0000000000..947bb7e988 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop2.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <stdint.h> +#include <stddef.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +SEC("raw_tracepoint/consume_skb") +int while_true(volatile struct pt_regs* ctx) +{ + int i = 0; + + while (true) { + if (PT_REGS_RC(ctx) & 1) + i += 3; + else + i += 7; + if (i > 40) + break; + } + + return i; +} diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c new file mode 100644 index 0000000000..717dab1432 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop3.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <stdint.h> +#include <stddef.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +SEC("raw_tracepoint/consume_skb") +int while_true(struct pt_regs *ctx) +{ + volatile __u64 i = 0, sum = 0; + do { + i++; + sum += PT_REGS_RC(ctx); + } while (i < 0x100000000ULL); + return sum; +} diff --git a/tools/testing/selftests/bpf/progs/loop4.c b/tools/testing/selftests/bpf/progs/loop4.c new file mode 100644 index 0000000000..b35337926d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop4.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +SEC("socket") +int combinations(volatile struct __sk_buff* skb) +{ + int ret = 0, i; + +#pragma nounroll + for (i = 0; i < 20; i++) + if (skb->len) + ret |= 1 << i; + return ret; +} diff --git a/tools/testing/selftests/bpf/progs/loop5.c b/tools/testing/selftests/bpf/progs/loop5.c new file mode 100644 index 0000000000..1b13f37f85 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop5.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +SEC("socket") +int while_true(volatile struct __sk_buff* skb) +{ + int i = 0; + + while (1) { + if (skb->len) + i += 3; + else + i += 7; + if (i == 9) + break; + barrier(); + if (i == 10) + break; + barrier(); + if (i == 13) + break; + barrier(); + if (i == 14) + break; + } + return i; +} diff --git a/tools/testing/selftests/bpf/progs/loop6.c b/tools/testing/selftests/bpf/progs/loop6.c new file mode 100644 index 0000000000..e4ff97fbcc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop6.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/ptrace.h> +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +/* typically virtio scsi has max SGs of 6 */ +#define VIRTIO_MAX_SGS 6 + +/* Verifier will fail with SG_MAX = 128. The failure can be + * workarounded with a smaller SG_MAX, e.g. 10. + */ +#define WORKAROUND +#ifdef WORKAROUND +#define SG_MAX 10 +#else +/* typically virtio blk has max SEG of 128 */ +#define SG_MAX 128 +#endif + +#define SG_CHAIN 0x01UL +#define SG_END 0x02UL + +struct scatterlist { + unsigned long page_link; + unsigned int offset; + unsigned int length; +}; + +#define sg_is_chain(sg) ((sg)->page_link & SG_CHAIN) +#define sg_is_last(sg) ((sg)->page_link & SG_END) +#define sg_chain_ptr(sg) \ + ((struct scatterlist *) ((sg)->page_link & ~(SG_CHAIN | SG_END))) + +static inline struct scatterlist *__sg_next(struct scatterlist *sgp) +{ + struct scatterlist sg; + + bpf_probe_read_kernel(&sg, sizeof(sg), sgp); + if (sg_is_last(&sg)) + return NULL; + + sgp++; + + bpf_probe_read_kernel(&sg, sizeof(sg), sgp); + if (sg_is_chain(&sg)) + sgp = sg_chain_ptr(&sg); + + return sgp; +} + +static inline struct scatterlist *get_sgp(struct scatterlist **sgs, int i) +{ + struct scatterlist *sgp; + + bpf_probe_read_kernel(&sgp, sizeof(sgp), sgs + i); + return sgp; +} + +int config = 0; +int result = 0; + +SEC("kprobe/virtqueue_add_sgs") +int BPF_KPROBE(trace_virtqueue_add_sgs, void *unused, struct scatterlist **sgs, + unsigned int out_sgs, unsigned int in_sgs) +{ + struct scatterlist *sgp = NULL; + __u64 length1 = 0, length2 = 0; + unsigned int i, n, len; + + if (config != 0) + return 0; + + for (i = 0; (i < VIRTIO_MAX_SGS) && (i < out_sgs); i++) { + __sink(out_sgs); + for (n = 0, sgp = get_sgp(sgs, i); sgp && (n < SG_MAX); + sgp = __sg_next(sgp)) { + bpf_probe_read_kernel(&len, sizeof(len), &sgp->length); + length1 += len; + n++; + } + } + + for (i = 0; (i < VIRTIO_MAX_SGS) && (i < in_sgs); i++) { + __sink(in_sgs); + for (n = 0, sgp = get_sgp(sgs, i); sgp && (n < SG_MAX); + sgp = __sg_next(sgp)) { + bpf_probe_read_kernel(&len, sizeof(len), &sgp->length); + length2 += len; + n++; + } + } + + config = 1; + result = length2 - length1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/lru_bug.c b/tools/testing/selftests/bpf/progs/lru_bug.c new file mode 100644 index 0000000000..ad73029cb1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lru_bug.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +struct map_value { + struct task_struct __kptr_untrusted *ptr; +}; + +struct { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct map_value); +} lru_map SEC(".maps"); + +int pid = 0; +int result = 1; + +SEC("fentry/bpf_ktime_get_ns") +int printk(void *ctx) +{ + struct map_value v = {}; + + if (pid == bpf_get_current_task_btf()->pid) + bpf_map_update_elem(&lru_map, &(int){0}, &v, 0); + return 0; +} + +SEC("fentry/do_nanosleep") +int nanosleep(void *ctx) +{ + struct map_value val = {}, *v; + struct task_struct *current; + + bpf_map_update_elem(&lru_map, &(int){0}, &val, 0); + v = bpf_map_lookup_elem(&lru_map, &(int){0}); + if (!v) + return 0; + bpf_map_delete_elem(&lru_map, &(int){0}); + current = bpf_get_current_task_btf(); + v->ptr = current; + pid = current->pid; + bpf_ktime_get_ns(); + result = !v->ptr; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c new file mode 100644 index 0000000000..fadfdd9870 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lsm.c @@ -0,0 +1,181 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2020 Google LLC. + */ + +#include "vmlinux.h" +#include <errno.h> +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} array SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} hash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} lru_hash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} percpu_array SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} percpu_hash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LRU_PERCPU_HASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} lru_percpu_hash SEC(".maps"); + +struct inner_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, __u64); +} inner_map SEC(".maps"); + +struct outer_arr { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); + __array(values, struct inner_map); +} outer_arr SEC(".maps") = { + .values = { [0] = &inner_map }, +}; + +struct outer_hash { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 1); + __uint(key_size, sizeof(int)); + __array(values, struct inner_map); +} outer_hash SEC(".maps") = { + .values = { [0] = &inner_map }, +}; + +char _license[] SEC("license") = "GPL"; + +int monitored_pid = 0; +int mprotect_count = 0; +int bprm_count = 0; + +SEC("lsm/file_mprotect") +int BPF_PROG(test_int_hook, struct vm_area_struct *vma, + unsigned long reqprot, unsigned long prot, int ret) +{ + if (ret != 0) + return ret; + + __u32 pid = bpf_get_current_pid_tgid() >> 32; + int is_stack = 0; + + is_stack = (vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack); + + if (is_stack && monitored_pid == pid) { + mprotect_count++; + ret = -EPERM; + } + + return ret; +} + +SEC("lsm.s/bprm_committed_creds") +int BPF_PROG(test_void_hook, struct linux_binprm *bprm) +{ + __u32 pid = bpf_get_current_pid_tgid() >> 32; + struct inner_map *inner_map; + char args[64]; + __u32 key = 0; + __u64 *value; + + if (monitored_pid == pid) + bprm_count++; + + bpf_copy_from_user(args, sizeof(args), (void *)bprm->vma->vm_mm->arg_start); + bpf_copy_from_user(args, sizeof(args), (void *)bprm->mm->arg_start); + + value = bpf_map_lookup_elem(&array, &key); + if (value) + *value = 0; + value = bpf_map_lookup_elem(&hash, &key); + if (value) + *value = 0; + value = bpf_map_lookup_elem(&lru_hash, &key); + if (value) + *value = 0; + value = bpf_map_lookup_elem(&percpu_array, &key); + if (value) + *value = 0; + value = bpf_map_lookup_elem(&percpu_hash, &key); + if (value) + *value = 0; + value = bpf_map_lookup_elem(&lru_percpu_hash, &key); + if (value) + *value = 0; + inner_map = bpf_map_lookup_elem(&outer_arr, &key); + if (inner_map) { + value = bpf_map_lookup_elem(inner_map, &key); + if (value) + *value = 0; + } + inner_map = bpf_map_lookup_elem(&outer_hash, &key); + if (inner_map) { + value = bpf_map_lookup_elem(inner_map, &key); + if (value) + *value = 0; + } + + return 0; +} +SEC("lsm/task_free") /* lsm/ is ok, lsm.s/ fails */ +int BPF_PROG(test_task_free, struct task_struct *task) +{ + return 0; +} + +int copy_test = 0; + +SEC("fentry.s/" SYS_PREFIX "sys_setdomainname") +int BPF_PROG(test_sys_setdomainname, struct pt_regs *regs) +{ + void *ptr = (void *)PT_REGS_PARM1_SYSCALL(regs); + int len = PT_REGS_PARM2_SYSCALL(regs); + int buf = 0; + long ret; + + ret = bpf_copy_from_user(&buf, sizeof(buf), ptr); + if (len == -2 && ret == 0 && buf == 1234) + copy_test++; + if (len == -3 && ret == -EFAULT) + copy_test++; + if (len == -4 && ret == -EFAULT) + copy_test++; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/lsm_cgroup.c b/tools/testing/selftests/bpf/progs/lsm_cgroup.c new file mode 100644 index 0000000000..02c11d16b6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lsm_cgroup.c @@ -0,0 +1,188 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +extern bool CONFIG_SECURITY_SELINUX __kconfig __weak; +extern bool CONFIG_SECURITY_SMACK __kconfig __weak; +extern bool CONFIG_SECURITY_APPARMOR __kconfig __weak; + +#ifndef AF_PACKET +#define AF_PACKET 17 +#endif + +#ifndef AF_UNIX +#define AF_UNIX 1 +#endif + +#ifndef EPERM +#define EPERM 1 +#endif + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, __u64); + __type(value, __u64); +} cgroup_storage SEC(".maps"); + +int called_socket_post_create; +int called_socket_post_create2; +int called_socket_bind; +int called_socket_bind2; +int called_socket_alloc; +int called_socket_clone; + +static __always_inline int test_local_storage(void) +{ + __u64 *val; + + val = bpf_get_local_storage(&cgroup_storage, 0); + if (!val) + return 0; + *val += 1; + + return 1; +} + +static __always_inline int real_create(struct socket *sock, int family, + int protocol) +{ + struct sock *sk; + int prio = 123; + + /* Reject non-tx-only AF_PACKET. */ + if (family == AF_PACKET && protocol != 0) + return 0; /* EPERM */ + + sk = sock->sk; + if (!sk) + return 1; + + /* The rest of the sockets get default policy. */ + if (bpf_setsockopt(sk, SOL_SOCKET, SO_PRIORITY, &prio, sizeof(prio))) + return 0; /* EPERM */ + + /* Make sure bpf_getsockopt is allowed and works. */ + prio = 0; + if (bpf_getsockopt(sk, SOL_SOCKET, SO_PRIORITY, &prio, sizeof(prio))) + return 0; /* EPERM */ + if (prio != 123) + return 0; /* EPERM */ + + /* Can access cgroup local storage. */ + if (!test_local_storage()) + return 0; /* EPERM */ + + return 1; +} + +/* __cgroup_bpf_run_lsm_socket */ +SEC("lsm_cgroup/socket_post_create") +int BPF_PROG(socket_post_create, struct socket *sock, int family, + int type, int protocol, int kern) +{ + called_socket_post_create++; + return real_create(sock, family, protocol); +} + +/* __cgroup_bpf_run_lsm_socket */ +SEC("lsm_cgroup/socket_post_create") +int BPF_PROG(socket_post_create2, struct socket *sock, int family, + int type, int protocol, int kern) +{ + called_socket_post_create2++; + return real_create(sock, family, protocol); +} + +static __always_inline int real_bind(struct socket *sock, + struct sockaddr *address, + int addrlen) +{ + struct sockaddr_ll sa = {}; + + if (sock->sk->__sk_common.skc_family != AF_PACKET) + return 1; + + if (sock->sk->sk_kern_sock) + return 1; + + bpf_probe_read_kernel(&sa, sizeof(sa), address); + if (sa.sll_protocol) + return 0; /* EPERM */ + + /* Can access cgroup local storage. */ + if (!test_local_storage()) + return 0; /* EPERM */ + + return 1; +} + +/* __cgroup_bpf_run_lsm_socket */ +SEC("lsm_cgroup/socket_bind") +int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address, + int addrlen) +{ + called_socket_bind++; + return real_bind(sock, address, addrlen); +} + +/* __cgroup_bpf_run_lsm_socket */ +SEC("lsm_cgroup/socket_bind") +int BPF_PROG(socket_bind2, struct socket *sock, struct sockaddr *address, + int addrlen) +{ + called_socket_bind2++; + return real_bind(sock, address, addrlen); +} + +/* __cgroup_bpf_run_lsm_current (via bpf_lsm_current_hooks) */ +SEC("lsm_cgroup/sk_alloc_security") +int BPF_PROG(socket_alloc, struct sock *sk, int family, gfp_t priority) +{ + called_socket_alloc++; + /* if already have non-bpf lsms installed, EPERM will cause memory leak of non-bpf lsms */ + if (CONFIG_SECURITY_SELINUX || CONFIG_SECURITY_SMACK || CONFIG_SECURITY_APPARMOR) + return 1; + + if (family == AF_UNIX) + return 0; /* EPERM */ + + /* Can access cgroup local storage. */ + if (!test_local_storage()) + return 0; /* EPERM */ + + return 1; +} + +/* __cgroup_bpf_run_lsm_sock */ +SEC("lsm_cgroup/inet_csk_clone") +int BPF_PROG(socket_clone, struct sock *newsk, const struct request_sock *req) +{ + int prio = 234; + + if (!newsk) + return 1; + + /* Accepted request sockets get a different priority. */ + if (bpf_setsockopt(newsk, SOL_SOCKET, SO_PRIORITY, &prio, sizeof(prio))) + return 1; + + /* Make sure bpf_getsockopt is allowed and works. */ + prio = 0; + if (bpf_getsockopt(newsk, SOL_SOCKET, SO_PRIORITY, &prio, sizeof(prio))) + return 1; + if (prio != 234) + return 1; + + /* Can access cgroup local storage. */ + if (!test_local_storage()) + return 1; + + called_socket_clone++; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/lsm_cgroup_nonvoid.c b/tools/testing/selftests/bpf/progs/lsm_cgroup_nonvoid.c new file mode 100644 index 0000000000..6cb0f161f4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lsm_cgroup_nonvoid.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +SEC("lsm_cgroup/inet_csk_clone") +int BPF_PROG(nonvoid_socket_clone, struct sock *newsk, const struct request_sock *req) +{ + /* Can not return any errors from void LSM hooks. */ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/map_kptr.c b/tools/testing/selftests/bpf/progs/map_kptr.c new file mode 100644 index 0000000000..da30f0d593 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/map_kptr.c @@ -0,0 +1,530 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" + +struct map_value { + struct prog_test_ref_kfunc __kptr_untrusted *unref_ptr; + struct prog_test_ref_kfunc __kptr *ref_ptr; +}; + +struct array_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +} array_map SEC(".maps"); + +struct pcpu_array_map { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +} pcpu_array_map SEC(".maps"); + +struct hash_map { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +} hash_map SEC(".maps"); + +struct pcpu_hash_map { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +} pcpu_hash_map SEC(".maps"); + +struct hash_malloc_map { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); + __uint(map_flags, BPF_F_NO_PREALLOC); +} hash_malloc_map SEC(".maps"); + +struct pcpu_hash_malloc_map { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); + __uint(map_flags, BPF_F_NO_PREALLOC); +} pcpu_hash_malloc_map SEC(".maps"); + +struct lru_hash_map { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +} lru_hash_map SEC(".maps"); + +struct lru_pcpu_hash_map { + __uint(type, BPF_MAP_TYPE_LRU_PERCPU_HASH); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +} lru_pcpu_hash_map SEC(".maps"); + +struct cgrp_ls_map { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct map_value); +} cgrp_ls_map SEC(".maps"); + +struct task_ls_map { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct map_value); +} task_ls_map SEC(".maps"); + +struct inode_ls_map { + __uint(type, BPF_MAP_TYPE_INODE_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct map_value); +} inode_ls_map SEC(".maps"); + +struct sk_ls_map { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct map_value); +} sk_ls_map SEC(".maps"); + +#define DEFINE_MAP_OF_MAP(map_type, inner_map_type, name) \ + struct { \ + __uint(type, map_type); \ + __uint(max_entries, 1); \ + __uint(key_size, sizeof(int)); \ + __uint(value_size, sizeof(int)); \ + __array(values, struct inner_map_type); \ + } name SEC(".maps") = { \ + .values = { [0] = &inner_map_type }, \ + } + +DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_map, array_of_array_maps); +DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_ARRAY_OF_MAPS, hash_map, array_of_hash_maps); +DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_ARRAY_OF_MAPS, hash_malloc_map, array_of_hash_malloc_maps); +DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_ARRAY_OF_MAPS, lru_hash_map, array_of_lru_hash_maps); +DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, array_map, hash_of_array_maps); +DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, hash_map, hash_of_hash_maps); +DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, hash_malloc_map, hash_of_hash_malloc_maps); +DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, lru_hash_map, hash_of_lru_hash_maps); + +#define WRITE_ONCE(x, val) ((*(volatile typeof(x) *) &(x)) = (val)) + +static void test_kptr_unref(struct map_value *v) +{ + struct prog_test_ref_kfunc *p; + + p = v->unref_ptr; + /* store untrusted_ptr_or_null_ */ + WRITE_ONCE(v->unref_ptr, p); + if (!p) + return; + if (p->a + p->b > 100) + return; + /* store untrusted_ptr_ */ + WRITE_ONCE(v->unref_ptr, p); + /* store NULL */ + WRITE_ONCE(v->unref_ptr, NULL); +} + +static void test_kptr_ref(struct map_value *v) +{ + struct prog_test_ref_kfunc *p; + + p = v->ref_ptr; + /* store ptr_or_null_ */ + WRITE_ONCE(v->unref_ptr, p); + if (!p) + return; + /* + * p is rcu_ptr_prog_test_ref_kfunc, + * because bpf prog is non-sleepable and runs in RCU CS. + * p can be passed to kfunc that requires KF_RCU. + */ + bpf_kfunc_call_test_ref(p); + if (p->a + p->b > 100) + return; + /* store NULL */ + p = bpf_kptr_xchg(&v->ref_ptr, NULL); + if (!p) + return; + /* + * p is trusted_ptr_prog_test_ref_kfunc. + * p can be passed to kfunc that requires KF_RCU. + */ + bpf_kfunc_call_test_ref(p); + if (p->a + p->b > 100) { + bpf_kfunc_call_test_release(p); + return; + } + /* store ptr_ */ + WRITE_ONCE(v->unref_ptr, p); + bpf_kfunc_call_test_release(p); + + p = bpf_kfunc_call_test_acquire(&(unsigned long){0}); + if (!p) + return; + /* store ptr_ */ + p = bpf_kptr_xchg(&v->ref_ptr, p); + if (!p) + return; + if (p->a + p->b > 100) { + bpf_kfunc_call_test_release(p); + return; + } + bpf_kfunc_call_test_release(p); +} + +static void test_kptr(struct map_value *v) +{ + test_kptr_unref(v); + test_kptr_ref(v); +} + +SEC("tc") +int test_map_kptr(struct __sk_buff *ctx) +{ + struct map_value *v; + int key = 0; + +#define TEST(map) \ + v = bpf_map_lookup_elem(&map, &key); \ + if (!v) \ + return 0; \ + test_kptr(v) + + TEST(array_map); + TEST(hash_map); + TEST(hash_malloc_map); + TEST(lru_hash_map); + +#undef TEST + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +int BPF_PROG(test_cgrp_map_kptr, struct cgroup *cgrp, const char *path) +{ + struct map_value *v; + + v = bpf_cgrp_storage_get(&cgrp_ls_map, cgrp, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE); + if (v) + test_kptr(v); + return 0; +} + +SEC("lsm/inode_unlink") +int BPF_PROG(test_task_map_kptr, struct inode *inode, struct dentry *victim) +{ + struct task_struct *task; + struct map_value *v; + + task = bpf_get_current_task_btf(); + if (!task) + return 0; + v = bpf_task_storage_get(&task_ls_map, task, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE); + if (v) + test_kptr(v); + return 0; +} + +SEC("lsm/inode_unlink") +int BPF_PROG(test_inode_map_kptr, struct inode *inode, struct dentry *victim) +{ + struct map_value *v; + + v = bpf_inode_storage_get(&inode_ls_map, inode, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE); + if (v) + test_kptr(v); + return 0; +} + +SEC("tc") +int test_sk_map_kptr(struct __sk_buff *ctx) +{ + struct map_value *v; + struct bpf_sock *sk; + + sk = ctx->sk; + if (!sk) + return 0; + v = bpf_sk_storage_get(&sk_ls_map, sk, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE); + if (v) + test_kptr(v); + return 0; +} + +SEC("tc") +int test_map_in_map_kptr(struct __sk_buff *ctx) +{ + struct map_value *v; + int key = 0; + void *map; + +#define TEST(map_in_map) \ + map = bpf_map_lookup_elem(&map_in_map, &key); \ + if (!map) \ + return 0; \ + v = bpf_map_lookup_elem(map, &key); \ + if (!v) \ + return 0; \ + test_kptr(v) + + TEST(array_of_array_maps); + TEST(array_of_hash_maps); + TEST(array_of_hash_malloc_maps); + TEST(array_of_lru_hash_maps); + TEST(hash_of_array_maps); + TEST(hash_of_hash_maps); + TEST(hash_of_hash_malloc_maps); + TEST(hash_of_lru_hash_maps); + +#undef TEST + return 0; +} + +int ref = 1; + +static __always_inline +int test_map_kptr_ref_pre(struct map_value *v) +{ + struct prog_test_ref_kfunc *p, *p_st; + unsigned long arg = 0; + int ret; + + p = bpf_kfunc_call_test_acquire(&arg); + if (!p) + return 1; + ref++; + + p_st = p->next; + if (p_st->cnt.refs.counter != ref) { + ret = 2; + goto end; + } + + p = bpf_kptr_xchg(&v->ref_ptr, p); + if (p) { + ret = 3; + goto end; + } + if (p_st->cnt.refs.counter != ref) + return 4; + + p = bpf_kptr_xchg(&v->ref_ptr, NULL); + if (!p) + return 5; + bpf_kfunc_call_test_release(p); + ref--; + if (p_st->cnt.refs.counter != ref) + return 6; + + p = bpf_kfunc_call_test_acquire(&arg); + if (!p) + return 7; + ref++; + p = bpf_kptr_xchg(&v->ref_ptr, p); + if (p) { + ret = 8; + goto end; + } + if (p_st->cnt.refs.counter != ref) + return 9; + /* Leave in map */ + + return 0; +end: + ref--; + bpf_kfunc_call_test_release(p); + return ret; +} + +static __always_inline +int test_map_kptr_ref_post(struct map_value *v) +{ + struct prog_test_ref_kfunc *p, *p_st; + + p_st = v->ref_ptr; + if (!p_st || p_st->cnt.refs.counter != ref) + return 1; + + p = bpf_kptr_xchg(&v->ref_ptr, NULL); + if (!p) + return 2; + if (p_st->cnt.refs.counter != ref) { + bpf_kfunc_call_test_release(p); + return 3; + } + + p = bpf_kptr_xchg(&v->ref_ptr, p); + if (p) { + bpf_kfunc_call_test_release(p); + return 4; + } + if (p_st->cnt.refs.counter != ref) + return 5; + + return 0; +} + +#define TEST(map) \ + v = bpf_map_lookup_elem(&map, &key); \ + if (!v) \ + return -1; \ + ret = test_map_kptr_ref_pre(v); \ + if (ret) \ + return ret; + +#define TEST_PCPU(map) \ + v = bpf_map_lookup_percpu_elem(&map, &key, 0); \ + if (!v) \ + return -1; \ + ret = test_map_kptr_ref_pre(v); \ + if (ret) \ + return ret; + +SEC("tc") +int test_map_kptr_ref1(struct __sk_buff *ctx) +{ + struct map_value *v, val = {}; + int key = 0, ret; + + bpf_map_update_elem(&hash_map, &key, &val, 0); + bpf_map_update_elem(&hash_malloc_map, &key, &val, 0); + bpf_map_update_elem(&lru_hash_map, &key, &val, 0); + + bpf_map_update_elem(&pcpu_hash_map, &key, &val, 0); + bpf_map_update_elem(&pcpu_hash_malloc_map, &key, &val, 0); + bpf_map_update_elem(&lru_pcpu_hash_map, &key, &val, 0); + + TEST(array_map); + TEST(hash_map); + TEST(hash_malloc_map); + TEST(lru_hash_map); + + TEST_PCPU(pcpu_array_map); + TEST_PCPU(pcpu_hash_map); + TEST_PCPU(pcpu_hash_malloc_map); + TEST_PCPU(lru_pcpu_hash_map); + + return 0; +} + +#undef TEST +#undef TEST_PCPU + +#define TEST(map) \ + v = bpf_map_lookup_elem(&map, &key); \ + if (!v) \ + return -1; \ + ret = test_map_kptr_ref_post(v); \ + if (ret) \ + return ret; + +#define TEST_PCPU(map) \ + v = bpf_map_lookup_percpu_elem(&map, &key, 0); \ + if (!v) \ + return -1; \ + ret = test_map_kptr_ref_post(v); \ + if (ret) \ + return ret; + +SEC("tc") +int test_map_kptr_ref2(struct __sk_buff *ctx) +{ + struct map_value *v; + int key = 0, ret; + + TEST(array_map); + TEST(hash_map); + TEST(hash_malloc_map); + TEST(lru_hash_map); + + TEST_PCPU(pcpu_array_map); + TEST_PCPU(pcpu_hash_map); + TEST_PCPU(pcpu_hash_malloc_map); + TEST_PCPU(lru_pcpu_hash_map); + + return 0; +} + +#undef TEST +#undef TEST_PCPU + +SEC("tc") +int test_map_kptr_ref3(struct __sk_buff *ctx) +{ + struct prog_test_ref_kfunc *p; + unsigned long sp = 0; + + p = bpf_kfunc_call_test_acquire(&sp); + if (!p) + return 1; + ref++; + if (p->cnt.refs.counter != ref) { + bpf_kfunc_call_test_release(p); + return 2; + } + bpf_kfunc_call_test_release(p); + ref--; + return 0; +} + +SEC("syscall") +int test_ls_map_kptr_ref1(void *ctx) +{ + struct task_struct *current; + struct map_value *v; + + current = bpf_get_current_task_btf(); + if (!current) + return 100; + v = bpf_task_storage_get(&task_ls_map, current, NULL, 0); + if (v) + return 150; + v = bpf_task_storage_get(&task_ls_map, current, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!v) + return 200; + return test_map_kptr_ref_pre(v); +} + +SEC("syscall") +int test_ls_map_kptr_ref2(void *ctx) +{ + struct task_struct *current; + struct map_value *v; + + current = bpf_get_current_task_btf(); + if (!current) + return 100; + v = bpf_task_storage_get(&task_ls_map, current, NULL, 0); + if (!v) + return 200; + return test_map_kptr_ref_post(v); +} + +SEC("syscall") +int test_ls_map_kptr_ref_del(void *ctx) +{ + struct task_struct *current; + struct map_value *v; + + current = bpf_get_current_task_btf(); + if (!current) + return 100; + v = bpf_task_storage_get(&task_ls_map, current, NULL, 0); + if (!v) + return 200; + if (!v->ref_ptr) + return 300; + return bpf_task_storage_delete(&task_ls_map, current); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/map_kptr_fail.c b/tools/testing/selftests/bpf/progs/map_kptr_fail.c new file mode 100644 index 0000000000..450bb373b1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/map_kptr_fail.c @@ -0,0 +1,388 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" +#include "../bpf_testmod/bpf_testmod_kfunc.h" + +struct map_value { + char buf[8]; + struct prog_test_ref_kfunc __kptr_untrusted *unref_ptr; + struct prog_test_ref_kfunc __kptr *ref_ptr; + struct prog_test_member __kptr *ref_memb_ptr; +}; + +struct array_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +} array_map SEC(".maps"); + +SEC("?tc") +__failure __msg("kptr access size must be BPF_DW") +int size_not_bpf_dw(struct __sk_buff *ctx) +{ + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + *(u32 *)&v->unref_ptr = 0; + return 0; +} + +SEC("?tc") +__failure __msg("kptr access cannot have variable offset") +int non_const_var_off(struct __sk_buff *ctx) +{ + struct map_value *v; + int key = 0, id; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + id = ctx->protocol; + if (id < 4 || id > 12) + return 0; + *(u64 *)((void *)v + id) = 0; + + return 0; +} + +SEC("?tc") +__failure __msg("R1 doesn't have constant offset. kptr has to be") +int non_const_var_off_kptr_xchg(struct __sk_buff *ctx) +{ + struct map_value *v; + int key = 0, id; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + id = ctx->protocol; + if (id < 4 || id > 12) + return 0; + bpf_kptr_xchg((void *)v + id, NULL); + + return 0; +} + +SEC("?tc") +__failure __msg("kptr access misaligned expected=8 off=7") +int misaligned_access_write(struct __sk_buff *ctx) +{ + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + *(void **)((void *)v + 7) = NULL; + + return 0; +} + +SEC("?tc") +__failure __msg("kptr access misaligned expected=8 off=1") +int misaligned_access_read(struct __sk_buff *ctx) +{ + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + return *(u64 *)((void *)v + 1); +} + +SEC("?tc") +__failure __msg("variable untrusted_ptr_ access var_off=(0x0; 0x1e0)") +int reject_var_off_store(struct __sk_buff *ctx) +{ + struct prog_test_ref_kfunc *unref_ptr; + struct map_value *v; + int key = 0, id; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + unref_ptr = v->unref_ptr; + if (!unref_ptr) + return 0; + id = ctx->protocol; + if (id < 4 || id > 12) + return 0; + unref_ptr += id; + v->unref_ptr = unref_ptr; + + return 0; +} + +SEC("?tc") +__failure __msg("invalid kptr access, R1 type=untrusted_ptr_prog_test_ref_kfunc") +int reject_bad_type_match(struct __sk_buff *ctx) +{ + struct prog_test_ref_kfunc *unref_ptr; + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + unref_ptr = v->unref_ptr; + if (!unref_ptr) + return 0; + unref_ptr = (void *)unref_ptr + 4; + v->unref_ptr = unref_ptr; + + return 0; +} + +SEC("?tc") +__failure __msg("R1 type=untrusted_ptr_or_null_ expected=percpu_ptr_") +int marked_as_untrusted_or_null(struct __sk_buff *ctx) +{ + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + bpf_this_cpu_ptr(v->unref_ptr); + return 0; +} + +SEC("?tc") +__failure __msg("access beyond struct prog_test_ref_kfunc at off 32 size 4") +int correct_btf_id_check_size(struct __sk_buff *ctx) +{ + struct prog_test_ref_kfunc *p; + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + p = v->unref_ptr; + if (!p) + return 0; + return *(int *)((void *)p + bpf_core_type_size(struct prog_test_ref_kfunc)); +} + +SEC("?tc") +__failure __msg("R1 type=untrusted_ptr_ expected=percpu_ptr_") +int inherit_untrusted_on_walk(struct __sk_buff *ctx) +{ + struct prog_test_ref_kfunc *unref_ptr; + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + unref_ptr = v->unref_ptr; + if (!unref_ptr) + return 0; + unref_ptr = unref_ptr->next; + bpf_this_cpu_ptr(unref_ptr); + return 0; +} + +SEC("?tc") +__failure __msg("off=8 kptr isn't referenced kptr") +int reject_kptr_xchg_on_unref(struct __sk_buff *ctx) +{ + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + bpf_kptr_xchg(&v->unref_ptr, NULL); + return 0; +} + +SEC("?tc") +__failure __msg("R1 type=rcu_ptr_or_null_ expected=percpu_ptr_") +int mark_ref_as_untrusted_or_null(struct __sk_buff *ctx) +{ + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + bpf_this_cpu_ptr(v->ref_ptr); + return 0; +} + +SEC("?tc") +__failure __msg("store to referenced kptr disallowed") +int reject_untrusted_store_to_ref(struct __sk_buff *ctx) +{ + struct prog_test_ref_kfunc *p; + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + p = v->ref_ptr; + if (!p) + return 0; + /* Checkmate, clang */ + *(struct prog_test_ref_kfunc * volatile *)&v->ref_ptr = p; + return 0; +} + +SEC("?tc") +__failure __msg("R2 must be referenced") +int reject_untrusted_xchg(struct __sk_buff *ctx) +{ + struct prog_test_ref_kfunc *p; + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + p = v->ref_ptr; + if (!p) + return 0; + bpf_kptr_xchg(&v->ref_ptr, p); + return 0; +} + +SEC("?tc") +__failure +__msg("invalid kptr access, R2 type=ptr_prog_test_ref_kfunc expected=ptr_prog_test_member") +int reject_bad_type_xchg(struct __sk_buff *ctx) +{ + struct prog_test_ref_kfunc *ref_ptr; + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + ref_ptr = bpf_kfunc_call_test_acquire(&(unsigned long){0}); + if (!ref_ptr) + return 0; + bpf_kptr_xchg(&v->ref_memb_ptr, ref_ptr); + return 0; +} + +SEC("?tc") +__failure __msg("invalid kptr access, R2 type=ptr_prog_test_ref_kfunc") +int reject_member_of_ref_xchg(struct __sk_buff *ctx) +{ + struct prog_test_ref_kfunc *ref_ptr; + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + ref_ptr = bpf_kfunc_call_test_acquire(&(unsigned long){0}); + if (!ref_ptr) + return 0; + bpf_kptr_xchg(&v->ref_memb_ptr, &ref_ptr->memb); + return 0; +} + +SEC("?syscall") +__failure __msg("kptr cannot be accessed indirectly by helper") +int reject_indirect_helper_access(struct __sk_buff *ctx) +{ + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + bpf_get_current_comm(v, sizeof(v->buf) + 1); + return 0; +} + +__noinline +int write_func(int *p) +{ + return p ? *p = 42 : 0; +} + +SEC("?tc") +__failure __msg("kptr cannot be accessed indirectly by helper") +int reject_indirect_global_func_access(struct __sk_buff *ctx) +{ + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + return write_func((void *)v + 5); +} + +SEC("?tc") +__failure __msg("Unreleased reference id=5 alloc_insn=") +int kptr_xchg_ref_state(struct __sk_buff *ctx) +{ + struct prog_test_ref_kfunc *p; + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + p = bpf_kfunc_call_test_acquire(&(unsigned long){0}); + if (!p) + return 0; + bpf_kptr_xchg(&v->ref_ptr, p); + return 0; +} + +SEC("?tc") +__failure __msg("Possibly NULL pointer passed to helper arg2") +int kptr_xchg_possibly_null(struct __sk_buff *ctx) +{ + struct prog_test_ref_kfunc *p; + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&array_map, &key); + if (!v) + return 0; + + p = bpf_kfunc_call_test_acquire(&(unsigned long){0}); + + /* PTR_TO_BTF_ID | PTR_MAYBE_NULL passed to bpf_kptr_xchg() */ + p = bpf_kptr_xchg(&v->ref_ptr, p); + if (p) + bpf_kfunc_call_test_release(p); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/map_percpu_stats.c b/tools/testing/selftests/bpf/progs/map_percpu_stats.c new file mode 100644 index 0000000000..10b2325c17 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/map_percpu_stats.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +__u32 target_id; + +__s64 bpf_map_sum_elem_count(struct bpf_map *map) __ksym; + +SEC("iter/bpf_map") +int dump_bpf_map(struct bpf_iter__bpf_map *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct bpf_map *map = ctx->map; + + if (map && map->id == target_id) + BPF_SEQ_PRINTF(seq, "%lld", bpf_map_sum_elem_count(map)); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c new file mode 100644 index 0000000000..3325da17ec --- /dev/null +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -0,0 +1,703 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define LOOP_BOUND 0xf +#define MAX_ENTRIES 8 +#define HALF_ENTRIES (MAX_ENTRIES >> 1) + +_Static_assert(MAX_ENTRIES < LOOP_BOUND, "MAX_ENTRIES must be < LOOP_BOUND"); + +enum bpf_map_type g_map_type = BPF_MAP_TYPE_UNSPEC; +__u32 g_line = 0; +int page_size = 0; /* userspace should set it */ + +#define VERIFY_TYPE(type, func) ({ \ + g_map_type = type; \ + if (!func()) \ + return 0; \ +}) + + +#define VERIFY(expr) ({ \ + g_line = __LINE__; \ + if (!(expr)) \ + return 0; \ +}) + +struct bpf_map { + enum bpf_map_type map_type; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 id; +} __attribute__((preserve_access_index)); + +static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size, + __u32 value_size, __u32 max_entries) +{ + VERIFY(map->map_type == g_map_type); + VERIFY(map->key_size == key_size); + VERIFY(map->value_size == value_size); + VERIFY(map->max_entries == max_entries); + VERIFY(map->id > 0); + + return 1; +} + +static inline int check_bpf_map_ptr(struct bpf_map *indirect, + struct bpf_map *direct) +{ + VERIFY(indirect->map_type == direct->map_type); + VERIFY(indirect->key_size == direct->key_size); + VERIFY(indirect->value_size == direct->value_size); + VERIFY(indirect->max_entries == direct->max_entries); + VERIFY(indirect->id == direct->id); + + return 1; +} + +static inline int check(struct bpf_map *indirect, struct bpf_map *direct, + __u32 key_size, __u32 value_size, __u32 max_entries) +{ + VERIFY(check_bpf_map_ptr(indirect, direct)); + VERIFY(check_bpf_map_fields(indirect, key_size, value_size, + max_entries)); + return 1; +} + +static inline int check_default(struct bpf_map *indirect, + struct bpf_map *direct) +{ + VERIFY(check(indirect, direct, sizeof(__u32), sizeof(__u32), + MAX_ENTRIES)); + return 1; +} + +static __noinline int +check_default_noinline(struct bpf_map *indirect, struct bpf_map *direct) +{ + VERIFY(check(indirect, direct, sizeof(__u32), sizeof(__u32), + MAX_ENTRIES)); + return 1; +} + +typedef struct { + int counter; +} atomic_t; + +struct bpf_htab { + struct bpf_map map; + atomic_t count; + __u32 n_buckets; + __u32 elem_size; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(map_flags, BPF_F_NO_PREALLOC); /* to test bpf_htab.count */ + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_hash SEC(".maps"); + +__s64 bpf_map_sum_elem_count(struct bpf_map *map) __ksym; + +static inline int check_hash(void) +{ + struct bpf_htab *hash = (struct bpf_htab *)&m_hash; + struct bpf_map *map = (struct bpf_map *)&m_hash; + int i; + + VERIFY(check_default_noinline(&hash->map, map)); + + VERIFY(hash->n_buckets == MAX_ENTRIES); + VERIFY(hash->elem_size == 64); + + VERIFY(hash->count.counter == 0); + VERIFY(bpf_map_sum_elem_count(map) == 0); + + for (i = 0; i < HALF_ENTRIES; ++i) { + const __u32 key = i; + const __u32 val = 1; + + if (bpf_map_update_elem(hash, &key, &val, 0)) + return 0; + } + VERIFY(hash->count.counter == HALF_ENTRIES); + VERIFY(bpf_map_sum_elem_count(map) == HALF_ENTRIES); + + return 1; +} + +struct bpf_array { + struct bpf_map map; + __u32 elem_size; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_array SEC(".maps"); + +static inline int check_array(void) +{ + struct bpf_array *array = (struct bpf_array *)&m_array; + struct bpf_map *map = (struct bpf_map *)&m_array; + int i, n_lookups = 0, n_keys = 0; + + VERIFY(check_default(&array->map, map)); + + VERIFY(array->elem_size == 8); + + for (i = 0; i < array->map.max_entries && i < LOOP_BOUND; ++i) { + const __u32 key = i; + __u32 *val = bpf_map_lookup_elem(array, &key); + + ++n_lookups; + if (val) + ++n_keys; + } + + VERIFY(n_lookups == MAX_ENTRIES); + VERIFY(n_keys == MAX_ENTRIES); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_prog_array SEC(".maps"); + +static inline int check_prog_array(void) +{ + struct bpf_array *prog_array = (struct bpf_array *)&m_prog_array; + struct bpf_map *map = (struct bpf_map *)&m_prog_array; + + VERIFY(check_default(&prog_array->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_perf_event_array SEC(".maps"); + +static inline int check_perf_event_array(void) +{ + struct bpf_array *perf_event_array = (struct bpf_array *)&m_perf_event_array; + struct bpf_map *map = (struct bpf_map *)&m_perf_event_array; + + VERIFY(check_default(&perf_event_array->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_percpu_hash SEC(".maps"); + +static inline int check_percpu_hash(void) +{ + struct bpf_htab *percpu_hash = (struct bpf_htab *)&m_percpu_hash; + struct bpf_map *map = (struct bpf_map *)&m_percpu_hash; + + VERIFY(check_default(&percpu_hash->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_percpu_array SEC(".maps"); + +static inline int check_percpu_array(void) +{ + struct bpf_array *percpu_array = (struct bpf_array *)&m_percpu_array; + struct bpf_map *map = (struct bpf_map *)&m_percpu_array; + + VERIFY(check_default(&percpu_array->map, map)); + + return 1; +} + +struct bpf_stack_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u64); +} m_stack_trace SEC(".maps"); + +static inline int check_stack_trace(void) +{ + struct bpf_stack_map *stack_trace = + (struct bpf_stack_map *)&m_stack_trace; + struct bpf_map *map = (struct bpf_map *)&m_stack_trace; + + VERIFY(check(&stack_trace->map, map, sizeof(__u32), sizeof(__u64), + MAX_ENTRIES)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_ARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_cgroup_array SEC(".maps"); + +static inline int check_cgroup_array(void) +{ + struct bpf_array *cgroup_array = (struct bpf_array *)&m_cgroup_array; + struct bpf_map *map = (struct bpf_map *)&m_cgroup_array; + + VERIFY(check_default(&cgroup_array->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_lru_hash SEC(".maps"); + +static inline int check_lru_hash(void) +{ + struct bpf_htab *lru_hash = (struct bpf_htab *)&m_lru_hash; + struct bpf_map *map = (struct bpf_map *)&m_lru_hash; + + VERIFY(check_default(&lru_hash->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_LRU_PERCPU_HASH); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_lru_percpu_hash SEC(".maps"); + +static inline int check_lru_percpu_hash(void) +{ + struct bpf_htab *lru_percpu_hash = (struct bpf_htab *)&m_lru_percpu_hash; + struct bpf_map *map = (struct bpf_map *)&m_lru_percpu_hash; + + VERIFY(check_default(&lru_percpu_hash->map, map)); + + return 1; +} + +struct lpm_trie { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct lpm_key { + struct bpf_lpm_trie_key trie_key; + __u32 data; +}; + +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, MAX_ENTRIES); + __type(key, struct lpm_key); + __type(value, __u32); +} m_lpm_trie SEC(".maps"); + +static inline int check_lpm_trie(void) +{ + struct lpm_trie *lpm_trie = (struct lpm_trie *)&m_lpm_trie; + struct bpf_map *map = (struct bpf_map *)&m_lpm_trie; + + VERIFY(check(&lpm_trie->map, map, sizeof(struct lpm_key), sizeof(__u32), + MAX_ENTRIES)); + + return 1; +} + +#define INNER_MAX_ENTRIES 1234 + +struct inner_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, INNER_MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} inner_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); + __array(values, struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, INNER_MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); + }); +} m_array_of_maps SEC(".maps") = { + .values = { (void *)&inner_map, 0, 0, 0, 0, 0, 0, 0, 0 }, +}; + +static inline int check_array_of_maps(void) +{ + struct bpf_array *array_of_maps = (struct bpf_array *)&m_array_of_maps; + struct bpf_map *map = (struct bpf_map *)&m_array_of_maps; + struct bpf_array *inner_map; + int key = 0; + + VERIFY(check_default(&array_of_maps->map, map)); + inner_map = bpf_map_lookup_elem(array_of_maps, &key); + VERIFY(inner_map != NULL); + VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); + __array(values, struct inner_map); +} m_hash_of_maps SEC(".maps") = { + .values = { + [2] = &inner_map, + }, +}; + +static inline int check_hash_of_maps(void) +{ + struct bpf_htab *hash_of_maps = (struct bpf_htab *)&m_hash_of_maps; + struct bpf_map *map = (struct bpf_map *)&m_hash_of_maps; + struct bpf_htab *inner_map; + int key = 2; + + VERIFY(check_default(&hash_of_maps->map, map)); + inner_map = bpf_map_lookup_elem(hash_of_maps, &key); + VERIFY(inner_map != NULL); + VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES); + + return 1; +} + +struct bpf_dtab { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_devmap SEC(".maps"); + +static inline int check_devmap(void) +{ + struct bpf_dtab *devmap = (struct bpf_dtab *)&m_devmap; + struct bpf_map *map = (struct bpf_map *)&m_devmap; + + VERIFY(check_default(&devmap->map, map)); + + return 1; +} + +struct bpf_stab { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_sockmap SEC(".maps"); + +static inline int check_sockmap(void) +{ + struct bpf_stab *sockmap = (struct bpf_stab *)&m_sockmap; + struct bpf_map *map = (struct bpf_map *)&m_sockmap; + + VERIFY(check_default(&sockmap->map, map)); + + return 1; +} + +struct bpf_cpu_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_cpumap SEC(".maps"); + +static inline int check_cpumap(void) +{ + struct bpf_cpu_map *cpumap = (struct bpf_cpu_map *)&m_cpumap; + struct bpf_map *map = (struct bpf_map *)&m_cpumap; + + VERIFY(check_default(&cpumap->map, map)); + + return 1; +} + +struct xsk_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_XSKMAP); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_xskmap SEC(".maps"); + +static inline int check_xskmap(void) +{ + struct xsk_map *xskmap = (struct xsk_map *)&m_xskmap; + struct bpf_map *map = (struct bpf_map *)&m_xskmap; + + VERIFY(check_default(&xskmap->map, map)); + + return 1; +} + +struct bpf_shtab { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_sockhash SEC(".maps"); + +static inline int check_sockhash(void) +{ + struct bpf_shtab *sockhash = (struct bpf_shtab *)&m_sockhash; + struct bpf_map *map = (struct bpf_map *)&m_sockhash; + + VERIFY(check_default(&sockhash->map, map)); + + return 1; +} + +struct bpf_cgroup_storage_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, __u32); +} m_cgroup_storage SEC(".maps"); + +static inline int check_cgroup_storage(void) +{ + struct bpf_cgroup_storage_map *cgroup_storage = + (struct bpf_cgroup_storage_map *)&m_cgroup_storage; + struct bpf_map *map = (struct bpf_map *)&m_cgroup_storage; + + VERIFY(check(&cgroup_storage->map, map, + sizeof(struct bpf_cgroup_storage_key), sizeof(__u32), 0)); + + return 1; +} + +struct reuseport_array { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_reuseport_sockarray SEC(".maps"); + +static inline int check_reuseport_sockarray(void) +{ + struct reuseport_array *reuseport_sockarray = + (struct reuseport_array *)&m_reuseport_sockarray; + struct bpf_map *map = (struct bpf_map *)&m_reuseport_sockarray; + + VERIFY(check_default(&reuseport_sockarray->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, __u32); +} m_percpu_cgroup_storage SEC(".maps"); + +static inline int check_percpu_cgroup_storage(void) +{ + struct bpf_cgroup_storage_map *percpu_cgroup_storage = + (struct bpf_cgroup_storage_map *)&m_percpu_cgroup_storage; + struct bpf_map *map = (struct bpf_map *)&m_percpu_cgroup_storage; + + VERIFY(check(&percpu_cgroup_storage->map, map, + sizeof(struct bpf_cgroup_storage_key), sizeof(__u32), 0)); + + return 1; +} + +struct bpf_queue_stack { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_QUEUE); + __uint(max_entries, MAX_ENTRIES); + __type(value, __u32); +} m_queue SEC(".maps"); + +static inline int check_queue(void) +{ + struct bpf_queue_stack *queue = (struct bpf_queue_stack *)&m_queue; + struct bpf_map *map = (struct bpf_map *)&m_queue; + + VERIFY(check(&queue->map, map, 0, sizeof(__u32), MAX_ENTRIES)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_STACK); + __uint(max_entries, MAX_ENTRIES); + __type(value, __u32); +} m_stack SEC(".maps"); + +static inline int check_stack(void) +{ + struct bpf_queue_stack *stack = (struct bpf_queue_stack *)&m_stack; + struct bpf_map *map = (struct bpf_map *)&m_stack; + + VERIFY(check(&stack->map, map, 0, sizeof(__u32), MAX_ENTRIES)); + + return 1; +} + +struct bpf_local_storage_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, __u32); + __type(value, __u32); +} m_sk_storage SEC(".maps"); + +static inline int check_sk_storage(void) +{ + struct bpf_local_storage_map *sk_storage = + (struct bpf_local_storage_map *)&m_sk_storage; + struct bpf_map *map = (struct bpf_map *)&m_sk_storage; + + VERIFY(check(&sk_storage->map, map, sizeof(__u32), sizeof(__u32), 0)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP_HASH); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_devmap_hash SEC(".maps"); + +static inline int check_devmap_hash(void) +{ + struct bpf_dtab *devmap_hash = (struct bpf_dtab *)&m_devmap_hash; + struct bpf_map *map = (struct bpf_map *)&m_devmap_hash; + + VERIFY(check_default(&devmap_hash->map, map)); + + return 1; +} + +struct bpf_ringbuf_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); +} m_ringbuf SEC(".maps"); + +static inline int check_ringbuf(void) +{ + struct bpf_ringbuf_map *ringbuf = (struct bpf_ringbuf_map *)&m_ringbuf; + struct bpf_map *map = (struct bpf_map *)&m_ringbuf; + + VERIFY(check(&ringbuf->map, map, 0, 0, page_size)); + + return 1; +} + +SEC("cgroup_skb/egress") +int cg_skb(void *ctx) +{ + VERIFY_TYPE(BPF_MAP_TYPE_HASH, check_hash); + VERIFY_TYPE(BPF_MAP_TYPE_ARRAY, check_array); + VERIFY_TYPE(BPF_MAP_TYPE_PROG_ARRAY, check_prog_array); + VERIFY_TYPE(BPF_MAP_TYPE_PERF_EVENT_ARRAY, check_perf_event_array); + VERIFY_TYPE(BPF_MAP_TYPE_PERCPU_HASH, check_percpu_hash); + VERIFY_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, check_percpu_array); + VERIFY_TYPE(BPF_MAP_TYPE_STACK_TRACE, check_stack_trace); + VERIFY_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, check_cgroup_array); + VERIFY_TYPE(BPF_MAP_TYPE_LRU_HASH, check_lru_hash); + VERIFY_TYPE(BPF_MAP_TYPE_LRU_PERCPU_HASH, check_lru_percpu_hash); + VERIFY_TYPE(BPF_MAP_TYPE_LPM_TRIE, check_lpm_trie); + VERIFY_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, check_array_of_maps); + VERIFY_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, check_hash_of_maps); + VERIFY_TYPE(BPF_MAP_TYPE_DEVMAP, check_devmap); + VERIFY_TYPE(BPF_MAP_TYPE_SOCKMAP, check_sockmap); + VERIFY_TYPE(BPF_MAP_TYPE_CPUMAP, check_cpumap); + VERIFY_TYPE(BPF_MAP_TYPE_XSKMAP, check_xskmap); + VERIFY_TYPE(BPF_MAP_TYPE_SOCKHASH, check_sockhash); + VERIFY_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, check_cgroup_storage); + VERIFY_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, + check_reuseport_sockarray); + VERIFY_TYPE(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + check_percpu_cgroup_storage); + VERIFY_TYPE(BPF_MAP_TYPE_QUEUE, check_queue); + VERIFY_TYPE(BPF_MAP_TYPE_STACK, check_stack); + VERIFY_TYPE(BPF_MAP_TYPE_SK_STORAGE, check_sk_storage); + VERIFY_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, check_devmap_hash); + VERIFY_TYPE(BPF_MAP_TYPE_RINGBUF, check_ringbuf); + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/metadata_unused.c b/tools/testing/selftests/bpf/progs/metadata_unused.c new file mode 100644 index 0000000000..672a0d19f8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/metadata_unused.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +volatile const char bpf_metadata_a[] SEC(".rodata") = "foo"; +volatile const int bpf_metadata_b SEC(".rodata") = 1; + +SEC("cgroup_skb/egress") +int prog(struct xdp_md *ctx) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/metadata_used.c b/tools/testing/selftests/bpf/progs/metadata_used.c new file mode 100644 index 0000000000..b7198e6538 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/metadata_used.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +volatile const char bpf_metadata_a[] SEC(".rodata") = "bar"; +volatile const int bpf_metadata_b SEC(".rodata") = 2; + +SEC("cgroup_skb/egress") +int prog(struct xdp_md *ctx) +{ + return bpf_metadata_b ? 1 : 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/modify_return.c b/tools/testing/selftests/bpf/progs/modify_return.c new file mode 100644 index 0000000000..3376d4849f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/modify_return.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2020 Google LLC. + */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +static int sequence = 0; +__s32 input_retval = 0; + +__u64 fentry_result = 0; +SEC("fentry/bpf_modify_return_test") +int BPF_PROG(fentry_test, int a, __u64 b) +{ + sequence++; + fentry_result = (sequence == 1); + return 0; +} + +__u64 fmod_ret_result = 0; +SEC("fmod_ret/bpf_modify_return_test") +int BPF_PROG(fmod_ret_test, int a, int *b, int ret) +{ + sequence++; + /* This is the first fmod_ret program, the ret passed should be 0 */ + fmod_ret_result = (sequence == 2 && ret == 0); + return input_retval; +} + +__u64 fexit_result = 0; +SEC("fexit/bpf_modify_return_test") +int BPF_PROG(fexit_test, int a, __u64 b, int ret) +{ + sequence++; + /* If the input_reval is non-zero a successful modification should have + * occurred. + */ + if (input_retval) + fexit_result = (sequence == 3 && ret == input_retval); + else + fexit_result = (sequence == 3 && ret == 4); + + return 0; +} + +static int sequence2; + +__u64 fentry_result2 = 0; +SEC("fentry/bpf_modify_return_test2") +int BPF_PROG(fentry_test2, int a, int *b, short c, int d, void *e, char f, + int g) +{ + sequence2++; + fentry_result2 = (sequence2 == 1); + return 0; +} + +__u64 fmod_ret_result2 = 0; +SEC("fmod_ret/bpf_modify_return_test2") +int BPF_PROG(fmod_ret_test2, int a, int *b, short c, int d, void *e, char f, + int g, int ret) +{ + sequence2++; + /* This is the first fmod_ret program, the ret passed should be 0 */ + fmod_ret_result2 = (sequence2 == 2 && ret == 0); + return input_retval; +} + +__u64 fexit_result2 = 0; +SEC("fexit/bpf_modify_return_test2") +int BPF_PROG(fexit_test2, int a, int *b, short c, int d, void *e, char f, + int g, int ret) +{ + sequence2++; + /* If the input_reval is non-zero a successful modification should have + * occurred. + */ + if (input_retval) + fexit_result2 = (sequence2 == 3 && ret == input_retval); + else + fexit_result2 = (sequence2 == 3 && ret == 29); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/mptcp_sock.c b/tools/testing/selftests/bpf/progs/mptcp_sock.c new file mode 100644 index 0000000000..91a0d7eff2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/mptcp_sock.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020, Tessares SA. */ +/* Copyright (c) 2022, SUSE. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; +__u32 token = 0; + +struct mptcp_storage { + __u32 invoked; + __u32 is_mptcp; + struct sock *sk; + __u32 token; + struct sock *first; + char ca_name[TCP_CA_NAME_MAX]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct mptcp_storage); +} socket_storage_map SEC(".maps"); + +SEC("sockops") +int _sockops(struct bpf_sock_ops *ctx) +{ + struct mptcp_storage *storage; + struct mptcp_sock *msk; + int op = (int)ctx->op; + struct tcp_sock *tsk; + struct bpf_sock *sk; + bool is_mptcp; + + if (op != BPF_SOCK_OPS_TCP_CONNECT_CB) + return 1; + + sk = ctx->sk; + if (!sk) + return 1; + + tsk = bpf_skc_to_tcp_sock(sk); + if (!tsk) + return 1; + + is_mptcp = bpf_core_field_exists(tsk->is_mptcp) ? tsk->is_mptcp : 0; + if (!is_mptcp) { + storage = bpf_sk_storage_get(&socket_storage_map, sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!storage) + return 1; + + storage->token = 0; + __builtin_memset(storage->ca_name, 0, TCP_CA_NAME_MAX); + storage->first = NULL; + } else { + msk = bpf_skc_to_mptcp_sock(sk); + if (!msk) + return 1; + + storage = bpf_sk_storage_get(&socket_storage_map, msk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!storage) + return 1; + + storage->token = msk->token; + __builtin_memcpy(storage->ca_name, msk->ca_name, TCP_CA_NAME_MAX); + storage->first = msk->first; + } + storage->invoked++; + storage->is_mptcp = is_mptcp; + storage->sk = (struct sock *)sk; + + return 1; +} + +SEC("fentry/mptcp_pm_new_connection") +int BPF_PROG(trace_mptcp_pm_new_connection, struct mptcp_sock *msk, + const struct sock *ssk, int server_side) +{ + if (!server_side) + token = msk->token; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/mptcpify.c b/tools/testing/selftests/bpf/progs/mptcpify.c new file mode 100644 index 0000000000..53301ae8a8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/mptcpify.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023, SUSE. */ + +#include "vmlinux.h" +#include <bpf/bpf_tracing.h> +#include "bpf_tracing_net.h" + +char _license[] SEC("license") = "GPL"; + +SEC("fmod_ret/update_socket_protocol") +int BPF_PROG(mptcpify, int family, int type, int protocol) +{ + if ((family == AF_INET || family == AF_INET6) && + type == SOCK_STREAM && + (!protocol || protocol == IPPROTO_TCP)) { + return IPPROTO_MPTCP; + } + + return protocol; +} diff --git a/tools/testing/selftests/bpf/progs/nested_trust_common.h b/tools/testing/selftests/bpf/progs/nested_trust_common.h new file mode 100644 index 0000000000..83d3393113 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/nested_trust_common.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#ifndef _NESTED_TRUST_COMMON_H +#define _NESTED_TRUST_COMMON_H + +#include <stdbool.h> + +bool bpf_cpumask_test_cpu(unsigned int cpu, const struct cpumask *cpumask) __ksym; +bool bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym; + +#endif /* _NESTED_TRUST_COMMON_H */ diff --git a/tools/testing/selftests/bpf/progs/nested_trust_failure.c b/tools/testing/selftests/bpf/progs/nested_trust_failure.c new file mode 100644 index 0000000000..ea39497f11 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/nested_trust_failure.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#include "nested_trust_common.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, u64); +} sk_storage_map SEC(".maps"); + +/* Prototype for all of the program trace events below: + * + * TRACE_EVENT(task_newtask, + * TP_PROTO(struct task_struct *p, u64 clone_flags) + */ + +SEC("tp_btf/task_newtask") +__failure __msg("R2 must be") +int BPF_PROG(test_invalid_nested_user_cpus, struct task_struct *task, u64 clone_flags) +{ + bpf_cpumask_test_cpu(0, task->user_cpus_ptr); + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("R1 must have zero offset when passed to release func or trusted arg to kfunc") +int BPF_PROG(test_invalid_nested_offset, struct task_struct *task, u64 clone_flags) +{ + bpf_cpumask_first_zero(&task->cpus_mask); + return 0; +} + +/* Although R2 is of type sk_buff but sock_common is expected, we will hit untrusted ptr first. */ +SEC("tp_btf/tcp_probe") +__failure __msg("R2 type=untrusted_ptr_ expected=ptr_, trusted_ptr_, rcu_ptr_") +int BPF_PROG(test_invalid_skb_field, struct sock *sk, struct sk_buff *skb) +{ + bpf_sk_storage_get(&sk_storage_map, skb->next, 0, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/nested_trust_success.c b/tools/testing/selftests/bpf/progs/nested_trust_success.c new file mode 100644 index 0000000000..833840bffd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/nested_trust_success.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#include "nested_trust_common.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, u64); +} sk_storage_map SEC(".maps"); + +SEC("tp_btf/task_newtask") +__success +int BPF_PROG(test_read_cpumask, struct task_struct *task, u64 clone_flags) +{ + bpf_cpumask_test_cpu(0, task->cpus_ptr); + return 0; +} + +SEC("tp_btf/tcp_probe") +__success +int BPF_PROG(test_skb_field, struct sock *sk, struct sk_buff *skb) +{ + bpf_sk_storage_get(&sk_storage_map, skb->sk, 0, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/netcnt_prog.c b/tools/testing/selftests/bpf/progs/netcnt_prog.c new file mode 100644 index 0000000000..f9ef8aee56 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <linux/version.h> + +#include <bpf/bpf_helpers.h> +#include "netcnt_common.h" + +#define MAX_BPS (3 * 1024 * 1024) + +#define REFRESH_TIME_NS 100000000 +#define NS_PER_SEC 1000000000 + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, union percpu_net_cnt); +} percpu_netcnt SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, union net_cnt); +} netcnt SEC(".maps"); + +SEC("cgroup/skb") +int bpf_nextcnt(struct __sk_buff *skb) +{ + union percpu_net_cnt *percpu_cnt; + union net_cnt *cnt; + __u64 ts, dt; + int ret; + + cnt = bpf_get_local_storage(&netcnt, 0); + percpu_cnt = bpf_get_local_storage(&percpu_netcnt, 0); + + percpu_cnt->packets++; + percpu_cnt->bytes += skb->len; + + if (percpu_cnt->packets > MAX_PERCPU_PACKETS) { + __sync_fetch_and_add(&cnt->packets, + percpu_cnt->packets); + percpu_cnt->packets = 0; + + __sync_fetch_and_add(&cnt->bytes, + percpu_cnt->bytes); + percpu_cnt->bytes = 0; + } + + ts = bpf_ktime_get_ns(); + dt = ts - percpu_cnt->prev_ts; + + dt *= MAX_BPS; + dt /= NS_PER_SEC; + + if (cnt->bytes + percpu_cnt->bytes - percpu_cnt->prev_bytes < dt) + ret = 1; + else + ret = 0; + + if (dt > REFRESH_TIME_NS) { + percpu_cnt->prev_ts = ts; + percpu_cnt->prev_packets = cnt->packets; + percpu_cnt->prev_bytes = cnt->bytes; + } + + return !!ret; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/netif_receive_skb.c b/tools/testing/selftests/bpf/progs/netif_receive_skb.c new file mode 100644 index 0000000000..c0062645fc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/netif_receive_skb.c @@ -0,0 +1,255 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020, Oracle and/or its affiliates. */ + +#include "btf_ptr.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +#include <errno.h> + +long ret = 0; +int num_subtests = 0; +int ran_subtests = 0; +bool skip = false; + +#define STRSIZE 2048 +#define EXPECTED_STRSIZE 256 + +#if defined(bpf_target_s390) +/* NULL points to a readable struct lowcore on s390, so take the last page */ +#define BADPTR ((void *)0xFFFFFFFFFFFFF000ULL) +#else +#define BADPTR 0 +#endif + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, char[STRSIZE]); +} strdata SEC(".maps"); + +static int __strncmp(const void *m1, const void *m2, size_t len) +{ + const unsigned char *s1 = m1; + const unsigned char *s2 = m2; + int i, delta = 0; + + for (i = 0; i < len; i++) { + delta = s1[i] - s2[i]; + if (delta || s1[i] == 0 || s2[i] == 0) + break; + } + return delta; +} + +#if __has_builtin(__builtin_btf_type_id) +#define TEST_BTF(_str, _type, _flags, _expected, ...) \ + do { \ + static const char _expectedval[EXPECTED_STRSIZE] = \ + _expected; \ + __u64 _hflags = _flags | BTF_F_COMPACT; \ + static _type _ptrdata = __VA_ARGS__; \ + static struct btf_ptr _ptr = { }; \ + int _cmp; \ + \ + ++num_subtests; \ + if (ret < 0) \ + break; \ + ++ran_subtests; \ + _ptr.ptr = &_ptrdata; \ + _ptr.type_id = bpf_core_type_id_kernel(_type); \ + if (_ptr.type_id <= 0) { \ + ret = -EINVAL; \ + break; \ + } \ + ret = bpf_snprintf_btf(_str, STRSIZE, \ + &_ptr, sizeof(_ptr), _hflags); \ + if (ret) \ + break; \ + _cmp = __strncmp(_str, _expectedval, EXPECTED_STRSIZE); \ + if (_cmp != 0) { \ + bpf_printk("(%d) got %s", _cmp, _str); \ + bpf_printk("(%d) expected %s", _cmp, \ + _expectedval); \ + ret = -EBADMSG; \ + break; \ + } \ + } while (0) +#endif + +/* Use where expected data string matches its stringified declaration */ +#define TEST_BTF_C(_str, _type, _flags, ...) \ + TEST_BTF(_str, _type, _flags, "(" #_type ")" #__VA_ARGS__, \ + __VA_ARGS__) + +/* TRACE_EVENT(netif_receive_skb, + * TP_PROTO(struct sk_buff *skb), + */ +SEC("tp_btf/netif_receive_skb") +int BPF_PROG(trace_netif_receive_skb, struct sk_buff *skb) +{ + static __u64 flags[] = { 0, BTF_F_COMPACT, BTF_F_ZERO, BTF_F_PTR_RAW, + BTF_F_NONAME, BTF_F_COMPACT | BTF_F_ZERO | + BTF_F_PTR_RAW | BTF_F_NONAME }; + static struct btf_ptr p = { }; + __u32 key = 0; + int i, __ret; + char *str; + +#if __has_builtin(__builtin_btf_type_id) + str = bpf_map_lookup_elem(&strdata, &key); + if (!str) + return 0; + + /* Ensure we can write skb string representation */ + p.type_id = bpf_core_type_id_kernel(struct sk_buff); + p.ptr = skb; + for (i = 0; i < ARRAY_SIZE(flags); i++) { + ++num_subtests; + ret = bpf_snprintf_btf(str, STRSIZE, &p, sizeof(p), 0); + if (ret < 0) + bpf_printk("returned %d when writing skb", ret); + ++ran_subtests; + } + + /* Check invalid ptr value */ + p.ptr = BADPTR; + __ret = bpf_snprintf_btf(str, STRSIZE, &p, sizeof(p), 0); + if (__ret >= 0) { + bpf_printk("printing %llx should generate error, got (%d)", + (unsigned long long)BADPTR, __ret); + ret = -ERANGE; + } + + /* Verify type display for various types. */ + + /* simple int */ + TEST_BTF_C(str, int, 0, 1234); + TEST_BTF(str, int, BTF_F_NONAME, "1234", 1234); + /* zero value should be printed at toplevel */ + TEST_BTF(str, int, 0, "(int)0", 0); + TEST_BTF(str, int, BTF_F_NONAME, "0", 0); + TEST_BTF(str, int, BTF_F_ZERO, "(int)0", 0); + TEST_BTF(str, int, BTF_F_NONAME | BTF_F_ZERO, "0", 0); + TEST_BTF_C(str, int, 0, -4567); + TEST_BTF(str, int, BTF_F_NONAME, "-4567", -4567); + + /* simple char */ + TEST_BTF_C(str, char, 0, 100); + TEST_BTF(str, char, BTF_F_NONAME, "100", 100); + /* zero value should be printed at toplevel */ + TEST_BTF(str, char, 0, "(char)0", 0); + TEST_BTF(str, char, BTF_F_NONAME, "0", 0); + TEST_BTF(str, char, BTF_F_ZERO, "(char)0", 0); + TEST_BTF(str, char, BTF_F_NONAME | BTF_F_ZERO, "0", 0); + + /* simple typedef */ + TEST_BTF_C(str, uint64_t, 0, 100); + TEST_BTF(str, u64, BTF_F_NONAME, "1", 1); + /* zero value should be printed at toplevel */ + TEST_BTF(str, u64, 0, "(u64)0", 0); + TEST_BTF(str, u64, BTF_F_NONAME, "0", 0); + TEST_BTF(str, u64, BTF_F_ZERO, "(u64)0", 0); + TEST_BTF(str, u64, BTF_F_NONAME|BTF_F_ZERO, "0", 0); + + /* typedef struct */ + TEST_BTF_C(str, atomic_t, 0, {.counter = (int)1,}); + TEST_BTF(str, atomic_t, BTF_F_NONAME, "{1,}", {.counter = 1,}); + /* typedef with 0 value should be printed at toplevel */ + TEST_BTF(str, atomic_t, 0, "(atomic_t){}", {.counter = 0,}); + TEST_BTF(str, atomic_t, BTF_F_NONAME, "{}", {.counter = 0,}); + TEST_BTF(str, atomic_t, BTF_F_ZERO, "(atomic_t){.counter = (int)0,}", + {.counter = 0,}); + TEST_BTF(str, atomic_t, BTF_F_NONAME|BTF_F_ZERO, + "{0,}", {.counter = 0,}); + + /* enum where enum value does (and does not) exist */ + TEST_BTF_C(str, enum bpf_cmd, 0, BPF_MAP_CREATE); + TEST_BTF(str, enum bpf_cmd, 0, "(enum bpf_cmd)BPF_MAP_CREATE", 0); + TEST_BTF(str, enum bpf_cmd, BTF_F_NONAME, "BPF_MAP_CREATE", + BPF_MAP_CREATE); + TEST_BTF(str, enum bpf_cmd, BTF_F_NONAME|BTF_F_ZERO, + "BPF_MAP_CREATE", 0); + + TEST_BTF(str, enum bpf_cmd, BTF_F_ZERO, "(enum bpf_cmd)BPF_MAP_CREATE", + BPF_MAP_CREATE); + TEST_BTF(str, enum bpf_cmd, BTF_F_NONAME|BTF_F_ZERO, + "BPF_MAP_CREATE", BPF_MAP_CREATE); + TEST_BTF_C(str, enum bpf_cmd, 0, 2000); + TEST_BTF(str, enum bpf_cmd, BTF_F_NONAME, "2000", 2000); + + /* simple struct */ + TEST_BTF_C(str, struct btf_enum, 0, + {.name_off = (__u32)3,.val = (__s32)-1,}); + TEST_BTF(str, struct btf_enum, BTF_F_NONAME, "{3,-1,}", + { .name_off = 3, .val = -1,}); + TEST_BTF(str, struct btf_enum, BTF_F_NONAME, "{-1,}", + { .name_off = 0, .val = -1,}); + TEST_BTF(str, struct btf_enum, BTF_F_NONAME|BTF_F_ZERO, "{0,-1,}", + { .name_off = 0, .val = -1,}); + /* empty struct should be printed */ + TEST_BTF(str, struct btf_enum, 0, "(struct btf_enum){}", + { .name_off = 0, .val = 0,}); + TEST_BTF(str, struct btf_enum, BTF_F_NONAME, "{}", + { .name_off = 0, .val = 0,}); + TEST_BTF(str, struct btf_enum, BTF_F_ZERO, + "(struct btf_enum){.name_off = (__u32)0,.val = (__s32)0,}", + { .name_off = 0, .val = 0,}); + + /* struct with pointers */ + TEST_BTF(str, struct list_head, BTF_F_PTR_RAW, + "(struct list_head){.next = (struct list_head *)0x0000000000000001,}", + { .next = (struct list_head *)1 }); + /* NULL pointer should not be displayed */ + TEST_BTF(str, struct list_head, BTF_F_PTR_RAW, + "(struct list_head){}", + { .next = (struct list_head *)0 }); + + /* struct with char array */ + TEST_BTF(str, struct bpf_prog_info, 0, + "(struct bpf_prog_info){.name = (char[])['f','o','o',],}", + { .name = "foo",}); + TEST_BTF(str, struct bpf_prog_info, BTF_F_NONAME, + "{['f','o','o',],}", + {.name = "foo",}); + /* leading null char means do not display string */ + TEST_BTF(str, struct bpf_prog_info, 0, + "(struct bpf_prog_info){}", + {.name = {'\0', 'f', 'o', 'o'}}); + /* handle non-printable characters */ + TEST_BTF(str, struct bpf_prog_info, 0, + "(struct bpf_prog_info){.name = (char[])[1,2,3,],}", + { .name = {1, 2, 3, 0}}); + + /* struct with non-char array */ + TEST_BTF(str, struct __sk_buff, 0, + "(struct __sk_buff){.cb = (__u32[])[1,2,3,4,5,],}", + { .cb = {1, 2, 3, 4, 5,},}); + TEST_BTF(str, struct __sk_buff, BTF_F_NONAME, + "{[1,2,3,4,5,],}", + { .cb = { 1, 2, 3, 4, 5},}); + /* For non-char, arrays, show non-zero values only */ + TEST_BTF(str, struct __sk_buff, 0, + "(struct __sk_buff){.cb = (__u32[])[1,],}", + { .cb = { 0, 0, 1, 0, 0},}); + + /* struct with bitfields */ + TEST_BTF_C(str, struct bpf_insn, 0, + {.code = (__u8)1,.dst_reg = (__u8)0x2,.src_reg = (__u8)0x3,.off = (__s16)4,.imm = (__s32)5,}); + TEST_BTF(str, struct bpf_insn, BTF_F_NONAME, "{1,0x2,0x3,4,5,}", + {.code = 1, .dst_reg = 0x2, .src_reg = 0x3, .off = 4, + .imm = 5,}); +#else + skip = true; +#endif + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/netns_cookie_prog.c b/tools/testing/selftests/bpf/progs/netns_cookie_prog.c new file mode 100644 index 0000000000..aeff3a4f92 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/netns_cookie_prog.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> + +#define AF_INET6 10 + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} sockops_netns_cookies SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} sk_msg_netns_cookies SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, __u64); +} sock_map SEC(".maps"); + +SEC("sockops") +int get_netns_cookie_sockops(struct bpf_sock_ops *ctx) +{ + struct bpf_sock *sk = ctx->sk; + int *cookie; + __u32 key = 0; + + if (ctx->family != AF_INET6) + return 1; + + if (!sk) + return 1; + + switch (ctx->op) { + case BPF_SOCK_OPS_TCP_CONNECT_CB: + cookie = bpf_sk_storage_get(&sockops_netns_cookies, sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!cookie) + return 1; + + *cookie = bpf_get_netns_cookie(ctx); + break; + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + bpf_sock_map_update(ctx, &sock_map, &key, BPF_NOEXIST); + break; + default: + break; + } + + return 1; +} + +SEC("sk_msg") +int get_netns_cookie_sk_msg(struct sk_msg_md *msg) +{ + struct bpf_sock *sk = msg->sk; + int *cookie; + + if (msg->family != AF_INET6) + return 1; + + if (!sk) + return 1; + + cookie = bpf_sk_storage_get(&sk_msg_netns_cookies, sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!cookie) + return 1; + + *cookie = bpf_get_netns_cookie(msg); + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c new file mode 100644 index 0000000000..f793280a32 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +#ifndef PERF_MAX_STACK_DEPTH +#define PERF_MAX_STACK_DEPTH 127 +#endif + +typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, 16384); + __type(key, __u32); + __type(value, stack_trace_t); +} stackmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, stack_trace_t); +} stackdata_map SEC(".maps"); + +long stackid_kernel = 1; +long stackid_user = 1; +long stack_kernel = 1; +long stack_user = 1; + +SEC("perf_event") +int oncpu(void *ctx) +{ + stack_trace_t *trace; + __u32 key = 0; + long val; + + val = bpf_get_stackid(ctx, &stackmap, 0); + if (val >= 0) + stackid_kernel = 2; + val = bpf_get_stackid(ctx, &stackmap, BPF_F_USER_STACK); + if (val >= 0) + stackid_user = 2; + + trace = bpf_map_lookup_elem(&stackdata_map, &key); + if (!trace) + return 0; + + val = bpf_get_stack(ctx, trace, sizeof(stack_trace_t), 0); + if (val > 0) + stack_kernel = 2; + + val = bpf_get_stack(ctx, trace, sizeof(stack_trace_t), BPF_F_USER_STACK); + if (val > 0) + stack_user = 2; + + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/perfbuf_bench.c b/tools/testing/selftests/bpf/progs/perfbuf_bench.c new file mode 100644 index 0000000000..29c1639fc7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/perfbuf_bench.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(value_size, sizeof(int)); + __uint(key_size, sizeof(int)); +} perfbuf SEC(".maps"); + +const volatile int batch_cnt = 0; + +long sample_val = 42; +long dropped __attribute__((aligned(128))) = 0; + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int bench_perfbuf(void *ctx) +{ + int i; + + for (i = 0; i < batch_cnt; i++) { + if (bpf_perf_event_output(ctx, &perfbuf, BPF_F_CURRENT_CPU, + &sample_val, sizeof(sample_val))) + __sync_add_and_fetch(&dropped, 1); + } + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/profiler.h b/tools/testing/selftests/bpf/progs/profiler.h new file mode 100644 index 0000000000..3bac4fdd4b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/profiler.h @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#pragma once + +#define TASK_COMM_LEN 16 +#define MAX_ANCESTORS 4 +#define MAX_PATH 256 +#define KILL_TARGET_LEN 64 +#define CTL_MAXNAME 10 +#define MAX_ARGS_LEN 4096 +#define MAX_FILENAME_LEN 512 +#define MAX_ENVIRON_LEN 8192 +#define MAX_PATH_DEPTH 32 +#define MAX_FILEPATH_LENGTH (MAX_PATH_DEPTH * MAX_PATH) +#define MAX_CGROUPS_PATH_DEPTH 8 + +#define MAX_METADATA_PAYLOAD_LEN TASK_COMM_LEN + +#define MAX_CGROUP_PAYLOAD_LEN \ + (MAX_PATH * 2 + (MAX_PATH * MAX_CGROUPS_PATH_DEPTH)) + +#define MAX_CAP_PAYLOAD_LEN (MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN) + +#define MAX_SYSCTL_PAYLOAD_LEN \ + (MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN + CTL_MAXNAME + MAX_PATH) + +#define MAX_KILL_PAYLOAD_LEN \ + (MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN + TASK_COMM_LEN + \ + KILL_TARGET_LEN) + +#define MAX_EXEC_PAYLOAD_LEN \ + (MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN + MAX_FILENAME_LEN + \ + MAX_ARGS_LEN + MAX_ENVIRON_LEN) + +#define MAX_FILEMOD_PAYLOAD_LEN \ + (MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN + MAX_FILEPATH_LENGTH + \ + MAX_FILEPATH_LENGTH) + +enum data_type { + INVALID_EVENT, + EXEC_EVENT, + FORK_EVENT, + KILL_EVENT, + SYSCTL_EVENT, + FILEMOD_EVENT, + MAX_DATA_TYPE_EVENT +}; + +enum filemod_type { + FMOD_OPEN, + FMOD_LINK, + FMOD_SYMLINK, +}; + +struct ancestors_data_t { + pid_t ancestor_pids[MAX_ANCESTORS]; + uint32_t ancestor_exec_ids[MAX_ANCESTORS]; + uint64_t ancestor_start_times[MAX_ANCESTORS]; + uint32_t num_ancestors; +}; + +struct var_metadata_t { + enum data_type type; + pid_t pid; + uint32_t exec_id; + uid_t uid; + gid_t gid; + uint64_t start_time; + uint32_t cpu_id; + uint64_t bpf_stats_num_perf_events; + uint64_t bpf_stats_start_ktime_ns; + uint8_t comm_length; +}; + +struct cgroup_data_t { + ino_t cgroup_root_inode; + ino_t cgroup_proc_inode; + uint64_t cgroup_root_mtime; + uint64_t cgroup_proc_mtime; + uint16_t cgroup_root_length; + uint16_t cgroup_proc_length; + uint16_t cgroup_full_length; + int cgroup_full_path_root_pos; +}; + +struct var_sysctl_data_t { + struct var_metadata_t meta; + struct cgroup_data_t cgroup_data; + struct ancestors_data_t ancestors_info; + uint8_t sysctl_val_length; + uint16_t sysctl_path_length; + char payload[MAX_SYSCTL_PAYLOAD_LEN]; +}; + +struct var_kill_data_t { + struct var_metadata_t meta; + struct cgroup_data_t cgroup_data; + struct ancestors_data_t ancestors_info; + pid_t kill_target_pid; + int kill_sig; + uint32_t kill_count; + uint64_t last_kill_time; + uint8_t kill_target_name_length; + uint8_t kill_target_cgroup_proc_length; + char payload[MAX_KILL_PAYLOAD_LEN]; + size_t payload_length; +}; + +struct var_exec_data_t { + struct var_metadata_t meta; + struct cgroup_data_t cgroup_data; + pid_t parent_pid; + uint32_t parent_exec_id; + uid_t parent_uid; + uint64_t parent_start_time; + uint16_t bin_path_length; + uint16_t cmdline_length; + uint16_t environment_length; + char payload[MAX_EXEC_PAYLOAD_LEN]; +}; + +struct var_fork_data_t { + struct var_metadata_t meta; + pid_t parent_pid; + uint32_t parent_exec_id; + uint64_t parent_start_time; + char payload[MAX_METADATA_PAYLOAD_LEN]; +}; + +struct var_filemod_data_t { + struct var_metadata_t meta; + struct cgroup_data_t cgroup_data; + enum filemod_type fmod_type; + unsigned int dst_flags; + uint32_t src_device_id; + uint32_t dst_device_id; + ino_t src_inode; + ino_t dst_inode; + uint16_t src_filepath_length; + uint16_t dst_filepath_length; + char payload[MAX_FILEMOD_PAYLOAD_LEN]; +}; + +struct profiler_config_struct { + bool fetch_cgroups_from_bpf; + ino_t cgroup_fs_inode; + ino_t cgroup_login_session_inode; + uint64_t kill_signals_mask; + ino_t inode_filter; + uint32_t stale_info_secs; + bool use_variable_buffers; + bool read_environ_from_exec; + bool enable_cgroup_v1_resolver; +}; + +struct bpf_func_stats_data { + uint64_t time_elapsed_ns; + uint64_t num_executions; + uint64_t num_perf_events; +}; + +struct bpf_func_stats_ctx { + uint64_t start_time_ns; + struct bpf_func_stats_data* bpf_func_stats_data_val; +}; + +enum bpf_function_id { + profiler_bpf_proc_sys_write, + profiler_bpf_sched_process_exec, + profiler_bpf_sched_process_exit, + profiler_bpf_sys_enter_kill, + profiler_bpf_do_filp_open_ret, + profiler_bpf_sched_process_fork, + profiler_bpf_vfs_link, + profiler_bpf_vfs_symlink, + profiler_bpf_max_function_id +}; diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h new file mode 100644 index 0000000000..f799d87e87 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -0,0 +1,990 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include <vmlinux.h> +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#include "profiler.h" +#include "err.h" + +#ifndef NULL +#define NULL 0 +#endif + +#define O_WRONLY 00000001 +#define O_RDWR 00000002 +#define O_DIRECTORY 00200000 +#define __O_TMPFILE 020000000 +#define O_TMPFILE (__O_TMPFILE | O_DIRECTORY) +#define S_IFMT 00170000 +#define S_IFSOCK 0140000 +#define S_IFLNK 0120000 +#define S_IFREG 0100000 +#define S_IFBLK 0060000 +#define S_IFDIR 0040000 +#define S_IFCHR 0020000 +#define S_IFIFO 0010000 +#define S_ISUID 0004000 +#define S_ISGID 0002000 +#define S_ISVTX 0001000 +#define S_ISLNK(m) (((m)&S_IFMT) == S_IFLNK) +#define S_ISDIR(m) (((m)&S_IFMT) == S_IFDIR) +#define S_ISCHR(m) (((m)&S_IFMT) == S_IFCHR) +#define S_ISBLK(m) (((m)&S_IFMT) == S_IFBLK) +#define S_ISFIFO(m) (((m)&S_IFMT) == S_IFIFO) +#define S_ISSOCK(m) (((m)&S_IFMT) == S_IFSOCK) + +#define KILL_DATA_ARRAY_SIZE 8 + +struct var_kill_data_arr_t { + struct var_kill_data_t array[KILL_DATA_ARRAY_SIZE]; +}; + +union any_profiler_data_t { + struct var_exec_data_t var_exec; + struct var_kill_data_t var_kill; + struct var_sysctl_data_t var_sysctl; + struct var_filemod_data_t var_filemod; + struct var_fork_data_t var_fork; + struct var_kill_data_arr_t var_kill_data_arr; +}; + +volatile struct profiler_config_struct bpf_config = {}; + +#define FETCH_CGROUPS_FROM_BPF (bpf_config.fetch_cgroups_from_bpf) +#define CGROUP_FS_INODE (bpf_config.cgroup_fs_inode) +#define CGROUP_LOGIN_SESSION_INODE \ + (bpf_config.cgroup_login_session_inode) +#define KILL_SIGNALS (bpf_config.kill_signals_mask) +#define STALE_INFO (bpf_config.stale_info_secs) +#define INODE_FILTER (bpf_config.inode_filter) +#define READ_ENVIRON_FROM_EXEC (bpf_config.read_environ_from_exec) +#define ENABLE_CGROUP_V1_RESOLVER (bpf_config.enable_cgroup_v1_resolver) + +struct kernfs_iattrs___52 { + struct iattr ia_iattr; +}; + +struct kernfs_node___52 { + union /* kernfs_node_id */ { + struct { + u32 ino; + u32 generation; + }; + u64 id; + } id; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, u32); + __type(value, union any_profiler_data_t); +} data_heap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); +} events SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, KILL_DATA_ARRAY_SIZE); + __type(key, u32); + __type(value, struct var_kill_data_arr_t); +} var_tpid_to_data SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, profiler_bpf_max_function_id); + __type(key, u32); + __type(value, struct bpf_func_stats_data); +} bpf_func_stats SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, bool); + __uint(max_entries, 16); +} allowed_devices SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u64); + __type(value, bool); + __uint(max_entries, 1024); +} allowed_file_inodes SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u64); + __type(value, bool); + __uint(max_entries, 1024); +} allowed_directory_inodes SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, bool); + __uint(max_entries, 16); +} disallowed_exec_inodes SEC(".maps"); + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0])) +#endif + +static INLINE bool IS_ERR(const void* ptr) +{ + return IS_ERR_VALUE((unsigned long)ptr); +} + +static INLINE u32 get_userspace_pid() +{ + return bpf_get_current_pid_tgid() >> 32; +} + +static INLINE bool is_init_process(u32 tgid) +{ + return tgid == 1 || tgid == 0; +} + +static INLINE unsigned long +probe_read_lim(void* dst, void* src, unsigned long len, unsigned long max) +{ + len = len < max ? len : max; + if (len > 1) { + if (bpf_probe_read_kernel(dst, len, src)) + return 0; + } else if (len == 1) { + if (bpf_probe_read_kernel(dst, 1, src)) + return 0; + } + return len; +} + +static INLINE int get_var_spid_index(struct var_kill_data_arr_t* arr_struct, + int spid) +{ +#ifdef UNROLL +#pragma unroll +#endif + for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++) + if (arr_struct->array[i].meta.pid == spid) + return i; + return -1; +} + +static INLINE void populate_ancestors(struct task_struct* task, + struct ancestors_data_t* ancestors_data) +{ + struct task_struct* parent = task; + u32 num_ancestors, ppid; + + ancestors_data->num_ancestors = 0; +#ifdef UNROLL +#pragma unroll +#endif + for (num_ancestors = 0; num_ancestors < MAX_ANCESTORS; num_ancestors++) { + parent = BPF_CORE_READ(parent, real_parent); + if (parent == NULL) + break; + ppid = BPF_CORE_READ(parent, tgid); + if (is_init_process(ppid)) + break; + ancestors_data->ancestor_pids[num_ancestors] = ppid; + ancestors_data->ancestor_exec_ids[num_ancestors] = + BPF_CORE_READ(parent, self_exec_id); + ancestors_data->ancestor_start_times[num_ancestors] = + BPF_CORE_READ(parent, start_time); + ancestors_data->num_ancestors = num_ancestors; + } +} + +static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node, + struct kernfs_node* cgroup_root_node, + void* payload, + int* root_pos) +{ + void* payload_start = payload; + size_t filepart_length; + +#ifdef UNROLL +#pragma unroll +#endif + for (int i = 0; i < MAX_CGROUPS_PATH_DEPTH; i++) { + filepart_length = + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(cgroup_node, name)); + if (!cgroup_node) + return payload; + if (cgroup_node == cgroup_root_node) + *root_pos = payload - payload_start; + if (filepart_length <= MAX_PATH) { + barrier_var(filepart_length); + payload += filepart_length; + } + cgroup_node = BPF_CORE_READ(cgroup_node, parent); + } + return payload; +} + +static ino_t get_inode_from_kernfs(struct kernfs_node* node) +{ + struct kernfs_node___52* node52 = (void*)node; + + if (bpf_core_field_exists(node52->id.ino)) { + barrier_var(node52); + return BPF_CORE_READ(node52, id.ino); + } else { + barrier_var(node); + return (u64)BPF_CORE_READ(node, id); + } +} + +extern bool CONFIG_CGROUP_PIDS __kconfig __weak; +enum cgroup_subsys_id___local { + pids_cgrp_id___local = 123, /* value doesn't matter */ +}; + +static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, + struct task_struct* task, + void* payload) +{ + struct kernfs_node* root_kernfs = + BPF_CORE_READ(task, nsproxy, cgroup_ns, root_cset, dfl_cgrp, kn); + struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn); + +#if __has_builtin(__builtin_preserve_enum_value) + if (ENABLE_CGROUP_V1_RESOLVER && CONFIG_CGROUP_PIDS) { + int cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id___local, + pids_cgrp_id___local); +#ifdef UNROLL +#pragma unroll +#endif + for (int i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + struct cgroup_subsys_state* subsys = + BPF_CORE_READ(task, cgroups, subsys[i]); + if (subsys != NULL) { + int subsys_id = BPF_CORE_READ(subsys, ss, id); + if (subsys_id == cgrp_id) { + proc_kernfs = BPF_CORE_READ(subsys, cgroup, kn); + root_kernfs = BPF_CORE_READ(subsys, ss, root, kf_root, kn); + break; + } + } + } + } +#endif + + cgroup_data->cgroup_root_inode = get_inode_from_kernfs(root_kernfs); + cgroup_data->cgroup_proc_inode = get_inode_from_kernfs(proc_kernfs); + + if (bpf_core_field_exists(root_kernfs->iattr->ia_mtime)) { + cgroup_data->cgroup_root_mtime = + BPF_CORE_READ(root_kernfs, iattr, ia_mtime.tv_nsec); + cgroup_data->cgroup_proc_mtime = + BPF_CORE_READ(proc_kernfs, iattr, ia_mtime.tv_nsec); + } else { + struct kernfs_iattrs___52* root_iattr = + (struct kernfs_iattrs___52*)BPF_CORE_READ(root_kernfs, iattr); + cgroup_data->cgroup_root_mtime = + BPF_CORE_READ(root_iattr, ia_iattr.ia_mtime.tv_nsec); + + struct kernfs_iattrs___52* proc_iattr = + (struct kernfs_iattrs___52*)BPF_CORE_READ(proc_kernfs, iattr); + cgroup_data->cgroup_proc_mtime = + BPF_CORE_READ(proc_iattr, ia_iattr.ia_mtime.tv_nsec); + } + + cgroup_data->cgroup_root_length = 0; + cgroup_data->cgroup_proc_length = 0; + cgroup_data->cgroup_full_length = 0; + + size_t cgroup_root_length = + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(root_kernfs, name)); + barrier_var(cgroup_root_length); + if (cgroup_root_length <= MAX_PATH) { + barrier_var(cgroup_root_length); + cgroup_data->cgroup_root_length = cgroup_root_length; + payload += cgroup_root_length; + } + + size_t cgroup_proc_length = + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(proc_kernfs, name)); + barrier_var(cgroup_proc_length); + if (cgroup_proc_length <= MAX_PATH) { + barrier_var(cgroup_proc_length); + cgroup_data->cgroup_proc_length = cgroup_proc_length; + payload += cgroup_proc_length; + } + + if (FETCH_CGROUPS_FROM_BPF) { + cgroup_data->cgroup_full_path_root_pos = -1; + void* payload_end_pos = read_full_cgroup_path(proc_kernfs, root_kernfs, payload, + &cgroup_data->cgroup_full_path_root_pos); + cgroup_data->cgroup_full_length = payload_end_pos - payload; + payload = payload_end_pos; + } + + return (void*)payload; +} + +static INLINE void* populate_var_metadata(struct var_metadata_t* metadata, + struct task_struct* task, + u32 pid, void* payload) +{ + u64 uid_gid = bpf_get_current_uid_gid(); + + metadata->uid = (u32)uid_gid; + metadata->gid = uid_gid >> 32; + metadata->pid = pid; + metadata->exec_id = BPF_CORE_READ(task, self_exec_id); + metadata->start_time = BPF_CORE_READ(task, start_time); + metadata->comm_length = 0; + + size_t comm_length = bpf_core_read_str(payload, TASK_COMM_LEN, &task->comm); + barrier_var(comm_length); + if (comm_length <= TASK_COMM_LEN) { + barrier_var(comm_length); + metadata->comm_length = comm_length; + payload += comm_length; + } + + return (void*)payload; +} + +static INLINE struct var_kill_data_t* +get_var_kill_data(struct pt_regs* ctx, int spid, int tpid, int sig) +{ + int zero = 0; + struct var_kill_data_t* kill_data = bpf_map_lookup_elem(&data_heap, &zero); + + if (kill_data == NULL) + return NULL; + struct task_struct* task = (struct task_struct*)bpf_get_current_task(); + + void* payload = populate_var_metadata(&kill_data->meta, task, spid, kill_data->payload); + payload = populate_cgroup_info(&kill_data->cgroup_data, task, payload); + size_t payload_length = payload - (void*)kill_data->payload; + kill_data->payload_length = payload_length; + populate_ancestors(task, &kill_data->ancestors_info); + kill_data->meta.type = KILL_EVENT; + kill_data->kill_target_pid = tpid; + kill_data->kill_sig = sig; + kill_data->kill_count = 1; + kill_data->last_kill_time = bpf_ktime_get_ns(); + return kill_data; +} + +static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig) +{ + if ((KILL_SIGNALS & (1ULL << sig)) == 0) + return 0; + + u32 spid = get_userspace_pid(); + struct var_kill_data_arr_t* arr_struct = bpf_map_lookup_elem(&var_tpid_to_data, &tpid); + + if (arr_struct == NULL) { + struct var_kill_data_t* kill_data = get_var_kill_data(ctx, spid, tpid, sig); + int zero = 0; + + if (kill_data == NULL) + return 0; + arr_struct = bpf_map_lookup_elem(&data_heap, &zero); + if (arr_struct == NULL) + return 0; + bpf_probe_read_kernel(&arr_struct->array[0], + sizeof(arr_struct->array[0]), kill_data); + } else { + int index = get_var_spid_index(arr_struct, spid); + + if (index == -1) { + struct var_kill_data_t* kill_data = + get_var_kill_data(ctx, spid, tpid, sig); + if (kill_data == NULL) + return 0; +#ifdef UNROLL +#pragma unroll +#endif + for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++) + if (arr_struct->array[i].meta.pid == 0) { + bpf_probe_read_kernel(&arr_struct->array[i], + sizeof(arr_struct->array[i]), + kill_data); + bpf_map_update_elem(&var_tpid_to_data, &tpid, + arr_struct, 0); + + return 0; + } + return 0; + } + + struct var_kill_data_t* kill_data = &arr_struct->array[index]; + + u64 delta_sec = + (bpf_ktime_get_ns() - kill_data->last_kill_time) / 1000000000; + + if (delta_sec < STALE_INFO) { + kill_data->kill_count++; + kill_data->last_kill_time = bpf_ktime_get_ns(); + bpf_probe_read_kernel(&arr_struct->array[index], + sizeof(arr_struct->array[index]), + kill_data); + } else { + struct var_kill_data_t* kill_data = + get_var_kill_data(ctx, spid, tpid, sig); + if (kill_data == NULL) + return 0; + bpf_probe_read_kernel(&arr_struct->array[index], + sizeof(arr_struct->array[index]), + kill_data); + } + } + bpf_map_update_elem(&var_tpid_to_data, &tpid, arr_struct, 0); + return 0; +} + +static INLINE void bpf_stats_enter(struct bpf_func_stats_ctx* bpf_stat_ctx, + enum bpf_function_id func_id) +{ + int func_id_key = func_id; + + bpf_stat_ctx->start_time_ns = bpf_ktime_get_ns(); + bpf_stat_ctx->bpf_func_stats_data_val = + bpf_map_lookup_elem(&bpf_func_stats, &func_id_key); + if (bpf_stat_ctx->bpf_func_stats_data_val) + bpf_stat_ctx->bpf_func_stats_data_val->num_executions++; +} + +static INLINE void bpf_stats_exit(struct bpf_func_stats_ctx* bpf_stat_ctx) +{ + if (bpf_stat_ctx->bpf_func_stats_data_val) + bpf_stat_ctx->bpf_func_stats_data_val->time_elapsed_ns += + bpf_ktime_get_ns() - bpf_stat_ctx->start_time_ns; +} + +static INLINE void +bpf_stats_pre_submit_var_perf_event(struct bpf_func_stats_ctx* bpf_stat_ctx, + struct var_metadata_t* meta) +{ + if (bpf_stat_ctx->bpf_func_stats_data_val) { + bpf_stat_ctx->bpf_func_stats_data_val->num_perf_events++; + meta->bpf_stats_num_perf_events = + bpf_stat_ctx->bpf_func_stats_data_val->num_perf_events; + } + meta->bpf_stats_start_ktime_ns = bpf_stat_ctx->start_time_ns; + meta->cpu_id = bpf_get_smp_processor_id(); +} + +static INLINE size_t +read_absolute_file_path_from_dentry(struct dentry* filp_dentry, void* payload) +{ + size_t length = 0; + size_t filepart_length; + struct dentry* parent_dentry; + +#ifdef UNROLL +#pragma unroll +#endif + for (int i = 0; i < MAX_PATH_DEPTH; i++) { + filepart_length = + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(filp_dentry, d_name.name)); + barrier_var(filepart_length); + if (filepart_length > MAX_PATH) + break; + barrier_var(filepart_length); + payload += filepart_length; + length += filepart_length; + + parent_dentry = BPF_CORE_READ(filp_dentry, d_parent); + if (filp_dentry == parent_dentry) + break; + filp_dentry = parent_dentry; + } + + return length; +} + +static INLINE bool +is_ancestor_in_allowed_inodes(struct dentry* filp_dentry) +{ + struct dentry* parent_dentry; +#ifdef UNROLL +#pragma unroll +#endif + for (int i = 0; i < MAX_PATH_DEPTH; i++) { + u64 dir_ino = BPF_CORE_READ(filp_dentry, d_inode, i_ino); + bool* allowed_dir = bpf_map_lookup_elem(&allowed_directory_inodes, &dir_ino); + + if (allowed_dir != NULL) + return true; + parent_dentry = BPF_CORE_READ(filp_dentry, d_parent); + if (filp_dentry == parent_dentry) + break; + filp_dentry = parent_dentry; + } + return false; +} + +static INLINE bool is_dentry_allowed_for_filemod(struct dentry* file_dentry, + u32* device_id, + u64* file_ino) +{ + u32 dev_id = BPF_CORE_READ(file_dentry, d_sb, s_dev); + *device_id = dev_id; + bool* allowed_device = bpf_map_lookup_elem(&allowed_devices, &dev_id); + + if (allowed_device == NULL) + return false; + + u64 ino = BPF_CORE_READ(file_dentry, d_inode, i_ino); + *file_ino = ino; + bool* allowed_file = bpf_map_lookup_elem(&allowed_file_inodes, &ino); + + if (allowed_file == NULL) + if (!is_ancestor_in_allowed_inodes(BPF_CORE_READ(file_dentry, d_parent))) + return false; + return true; +} + +SEC("kprobe/proc_sys_write") +ssize_t BPF_KPROBE(kprobe__proc_sys_write, + struct file* filp, const char* buf, + size_t count, loff_t* ppos) +{ + struct bpf_func_stats_ctx stats_ctx; + bpf_stats_enter(&stats_ctx, profiler_bpf_proc_sys_write); + + u32 pid = get_userspace_pid(); + int zero = 0; + struct var_sysctl_data_t* sysctl_data = + bpf_map_lookup_elem(&data_heap, &zero); + if (!sysctl_data) + goto out; + + struct task_struct* task = (struct task_struct*)bpf_get_current_task(); + sysctl_data->meta.type = SYSCTL_EVENT; + void* payload = populate_var_metadata(&sysctl_data->meta, task, pid, sysctl_data->payload); + payload = populate_cgroup_info(&sysctl_data->cgroup_data, task, payload); + + populate_ancestors(task, &sysctl_data->ancestors_info); + + sysctl_data->sysctl_val_length = 0; + sysctl_data->sysctl_path_length = 0; + + size_t sysctl_val_length = bpf_probe_read_kernel_str(payload, + CTL_MAXNAME, buf); + barrier_var(sysctl_val_length); + if (sysctl_val_length <= CTL_MAXNAME) { + barrier_var(sysctl_val_length); + sysctl_data->sysctl_val_length = sysctl_val_length; + payload += sysctl_val_length; + } + + size_t sysctl_path_length = + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(filp, f_path.dentry, + d_name.name)); + barrier_var(sysctl_path_length); + if (sysctl_path_length <= MAX_PATH) { + barrier_var(sysctl_path_length); + sysctl_data->sysctl_path_length = sysctl_path_length; + payload += sysctl_path_length; + } + + bpf_stats_pre_submit_var_perf_event(&stats_ctx, &sysctl_data->meta); + unsigned long data_len = payload - (void*)sysctl_data; + data_len = data_len > sizeof(struct var_sysctl_data_t) + ? sizeof(struct var_sysctl_data_t) + : data_len; + bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, sysctl_data, data_len); +out: + bpf_stats_exit(&stats_ctx); + return 0; +} + +SEC("tracepoint/syscalls/sys_enter_kill") +int tracepoint__syscalls__sys_enter_kill(struct trace_event_raw_sys_enter* ctx) +{ + struct bpf_func_stats_ctx stats_ctx; + + bpf_stats_enter(&stats_ctx, profiler_bpf_sys_enter_kill); + int pid = ctx->args[0]; + int sig = ctx->args[1]; + int ret = trace_var_sys_kill(ctx, pid, sig); + bpf_stats_exit(&stats_ctx); + return ret; +}; + +SEC("raw_tracepoint/sched_process_exit") +int raw_tracepoint__sched_process_exit(void* ctx) +{ + int zero = 0; + struct bpf_func_stats_ctx stats_ctx; + bpf_stats_enter(&stats_ctx, profiler_bpf_sched_process_exit); + + u32 tpid = get_userspace_pid(); + + struct var_kill_data_arr_t* arr_struct = bpf_map_lookup_elem(&var_tpid_to_data, &tpid); + struct var_kill_data_t* kill_data = bpf_map_lookup_elem(&data_heap, &zero); + + if (arr_struct == NULL || kill_data == NULL) + goto out; + + struct task_struct* task = (struct task_struct*)bpf_get_current_task(); + struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn); + +#ifdef UNROLL +#pragma unroll +#endif + for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++) { + struct var_kill_data_t* past_kill_data = &arr_struct->array[i]; + + if (past_kill_data != NULL && past_kill_data->kill_target_pid == tpid) { + bpf_probe_read_kernel(kill_data, sizeof(*past_kill_data), + past_kill_data); + void* payload = kill_data->payload; + size_t offset = kill_data->payload_length; + if (offset >= MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN) + return 0; + payload += offset; + + kill_data->kill_target_name_length = 0; + kill_data->kill_target_cgroup_proc_length = 0; + + size_t comm_length = bpf_core_read_str(payload, TASK_COMM_LEN, &task->comm); + barrier_var(comm_length); + if (comm_length <= TASK_COMM_LEN) { + barrier_var(comm_length); + kill_data->kill_target_name_length = comm_length; + payload += comm_length; + } + + size_t cgroup_proc_length = + bpf_probe_read_kernel_str(payload, + KILL_TARGET_LEN, + BPF_CORE_READ(proc_kernfs, name)); + barrier_var(cgroup_proc_length); + if (cgroup_proc_length <= KILL_TARGET_LEN) { + barrier_var(cgroup_proc_length); + kill_data->kill_target_cgroup_proc_length = cgroup_proc_length; + payload += cgroup_proc_length; + } + + bpf_stats_pre_submit_var_perf_event(&stats_ctx, &kill_data->meta); + unsigned long data_len = (void*)payload - (void*)kill_data; + data_len = data_len > sizeof(struct var_kill_data_t) + ? sizeof(struct var_kill_data_t) + : data_len; + bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, kill_data, data_len); + } + } + bpf_map_delete_elem(&var_tpid_to_data, &tpid); +out: + bpf_stats_exit(&stats_ctx); + return 0; +} + +SEC("raw_tracepoint/sched_process_exec") +int raw_tracepoint__sched_process_exec(struct bpf_raw_tracepoint_args* ctx) +{ + struct bpf_func_stats_ctx stats_ctx; + bpf_stats_enter(&stats_ctx, profiler_bpf_sched_process_exec); + + struct linux_binprm* bprm = (struct linux_binprm*)ctx->args[2]; + u64 inode = BPF_CORE_READ(bprm, file, f_inode, i_ino); + + bool* should_filter_binprm = bpf_map_lookup_elem(&disallowed_exec_inodes, &inode); + if (should_filter_binprm != NULL) + goto out; + + int zero = 0; + struct var_exec_data_t* proc_exec_data = bpf_map_lookup_elem(&data_heap, &zero); + if (!proc_exec_data) + goto out; + + if (INODE_FILTER && inode != INODE_FILTER) + return 0; + + u32 pid = get_userspace_pid(); + struct task_struct* task = (struct task_struct*)bpf_get_current_task(); + + proc_exec_data->meta.type = EXEC_EVENT; + proc_exec_data->bin_path_length = 0; + proc_exec_data->cmdline_length = 0; + proc_exec_data->environment_length = 0; + void* payload = populate_var_metadata(&proc_exec_data->meta, task, pid, + proc_exec_data->payload); + payload = populate_cgroup_info(&proc_exec_data->cgroup_data, task, payload); + + struct task_struct* parent_task = BPF_CORE_READ(task, real_parent); + proc_exec_data->parent_pid = BPF_CORE_READ(parent_task, tgid); + proc_exec_data->parent_uid = BPF_CORE_READ(parent_task, real_cred, uid.val); + proc_exec_data->parent_exec_id = BPF_CORE_READ(parent_task, self_exec_id); + proc_exec_data->parent_start_time = BPF_CORE_READ(parent_task, start_time); + + const char* filename = BPF_CORE_READ(bprm, filename); + size_t bin_path_length = + bpf_probe_read_kernel_str(payload, MAX_FILENAME_LEN, filename); + barrier_var(bin_path_length); + if (bin_path_length <= MAX_FILENAME_LEN) { + barrier_var(bin_path_length); + proc_exec_data->bin_path_length = bin_path_length; + payload += bin_path_length; + } + + void* arg_start = (void*)BPF_CORE_READ(task, mm, arg_start); + void* arg_end = (void*)BPF_CORE_READ(task, mm, arg_end); + unsigned int cmdline_length = probe_read_lim(payload, arg_start, + arg_end - arg_start, MAX_ARGS_LEN); + + if (cmdline_length <= MAX_ARGS_LEN) { + barrier_var(cmdline_length); + proc_exec_data->cmdline_length = cmdline_length; + payload += cmdline_length; + } + + if (READ_ENVIRON_FROM_EXEC) { + void* env_start = (void*)BPF_CORE_READ(task, mm, env_start); + void* env_end = (void*)BPF_CORE_READ(task, mm, env_end); + unsigned long env_len = probe_read_lim(payload, env_start, + env_end - env_start, MAX_ENVIRON_LEN); + if (cmdline_length <= MAX_ENVIRON_LEN) { + proc_exec_data->environment_length = env_len; + payload += env_len; + } + } + + bpf_stats_pre_submit_var_perf_event(&stats_ctx, &proc_exec_data->meta); + unsigned long data_len = payload - (void*)proc_exec_data; + data_len = data_len > sizeof(struct var_exec_data_t) + ? sizeof(struct var_exec_data_t) + : data_len; + bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, proc_exec_data, data_len); +out: + bpf_stats_exit(&stats_ctx); + return 0; +} + +SEC("kretprobe/do_filp_open") +int kprobe_ret__do_filp_open(struct pt_regs* ctx) +{ + struct bpf_func_stats_ctx stats_ctx; + bpf_stats_enter(&stats_ctx, profiler_bpf_do_filp_open_ret); + + struct file* filp = (struct file*)PT_REGS_RC_CORE(ctx); + + if (filp == NULL || IS_ERR(filp)) + goto out; + unsigned int flags = BPF_CORE_READ(filp, f_flags); + if ((flags & (O_RDWR | O_WRONLY)) == 0) + goto out; + if ((flags & O_TMPFILE) > 0) + goto out; + struct inode* file_inode = BPF_CORE_READ(filp, f_inode); + umode_t mode = BPF_CORE_READ(file_inode, i_mode); + if (S_ISDIR(mode) || S_ISCHR(mode) || S_ISBLK(mode) || S_ISFIFO(mode) || + S_ISSOCK(mode)) + goto out; + + struct dentry* filp_dentry = BPF_CORE_READ(filp, f_path.dentry); + u32 device_id = 0; + u64 file_ino = 0; + if (!is_dentry_allowed_for_filemod(filp_dentry, &device_id, &file_ino)) + goto out; + + int zero = 0; + struct var_filemod_data_t* filemod_data = bpf_map_lookup_elem(&data_heap, &zero); + if (!filemod_data) + goto out; + + u32 pid = get_userspace_pid(); + struct task_struct* task = (struct task_struct*)bpf_get_current_task(); + + filemod_data->meta.type = FILEMOD_EVENT; + filemod_data->fmod_type = FMOD_OPEN; + filemod_data->dst_flags = flags; + filemod_data->src_inode = 0; + filemod_data->dst_inode = file_ino; + filemod_data->src_device_id = 0; + filemod_data->dst_device_id = device_id; + filemod_data->src_filepath_length = 0; + filemod_data->dst_filepath_length = 0; + + void* payload = populate_var_metadata(&filemod_data->meta, task, pid, + filemod_data->payload); + payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload); + + size_t len = read_absolute_file_path_from_dentry(filp_dentry, payload); + barrier_var(len); + if (len <= MAX_FILEPATH_LENGTH) { + barrier_var(len); + payload += len; + filemod_data->dst_filepath_length = len; + } + bpf_stats_pre_submit_var_perf_event(&stats_ctx, &filemod_data->meta); + unsigned long data_len = payload - (void*)filemod_data; + data_len = data_len > sizeof(*filemod_data) ? sizeof(*filemod_data) : data_len; + bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, filemod_data, data_len); +out: + bpf_stats_exit(&stats_ctx); + return 0; +} + +SEC("kprobe/vfs_link") +int BPF_KPROBE(kprobe__vfs_link, + struct dentry* old_dentry, struct mnt_idmap *idmap, + struct inode* dir, struct dentry* new_dentry, + struct inode** delegated_inode) +{ + struct bpf_func_stats_ctx stats_ctx; + bpf_stats_enter(&stats_ctx, profiler_bpf_vfs_link); + + u32 src_device_id = 0; + u64 src_file_ino = 0; + u32 dst_device_id = 0; + u64 dst_file_ino = 0; + if (!is_dentry_allowed_for_filemod(old_dentry, &src_device_id, &src_file_ino) && + !is_dentry_allowed_for_filemod(new_dentry, &dst_device_id, &dst_file_ino)) + goto out; + + int zero = 0; + struct var_filemod_data_t* filemod_data = bpf_map_lookup_elem(&data_heap, &zero); + if (!filemod_data) + goto out; + + u32 pid = get_userspace_pid(); + struct task_struct* task = (struct task_struct*)bpf_get_current_task(); + + filemod_data->meta.type = FILEMOD_EVENT; + filemod_data->fmod_type = FMOD_LINK; + filemod_data->dst_flags = 0; + filemod_data->src_inode = src_file_ino; + filemod_data->dst_inode = dst_file_ino; + filemod_data->src_device_id = src_device_id; + filemod_data->dst_device_id = dst_device_id; + filemod_data->src_filepath_length = 0; + filemod_data->dst_filepath_length = 0; + + void* payload = populate_var_metadata(&filemod_data->meta, task, pid, + filemod_data->payload); + payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload); + + size_t len = read_absolute_file_path_from_dentry(old_dentry, payload); + barrier_var(len); + if (len <= MAX_FILEPATH_LENGTH) { + barrier_var(len); + payload += len; + filemod_data->src_filepath_length = len; + } + + len = read_absolute_file_path_from_dentry(new_dentry, payload); + barrier_var(len); + if (len <= MAX_FILEPATH_LENGTH) { + barrier_var(len); + payload += len; + filemod_data->dst_filepath_length = len; + } + + bpf_stats_pre_submit_var_perf_event(&stats_ctx, &filemod_data->meta); + unsigned long data_len = payload - (void*)filemod_data; + data_len = data_len > sizeof(*filemod_data) ? sizeof(*filemod_data) : data_len; + bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, filemod_data, data_len); +out: + bpf_stats_exit(&stats_ctx); + return 0; +} + +SEC("kprobe/vfs_symlink") +int BPF_KPROBE(kprobe__vfs_symlink, struct inode* dir, struct dentry* dentry, + const char* oldname) +{ + struct bpf_func_stats_ctx stats_ctx; + bpf_stats_enter(&stats_ctx, profiler_bpf_vfs_symlink); + + u32 dst_device_id = 0; + u64 dst_file_ino = 0; + if (!is_dentry_allowed_for_filemod(dentry, &dst_device_id, &dst_file_ino)) + goto out; + + int zero = 0; + struct var_filemod_data_t* filemod_data = bpf_map_lookup_elem(&data_heap, &zero); + if (!filemod_data) + goto out; + + u32 pid = get_userspace_pid(); + struct task_struct* task = (struct task_struct*)bpf_get_current_task(); + + filemod_data->meta.type = FILEMOD_EVENT; + filemod_data->fmod_type = FMOD_SYMLINK; + filemod_data->dst_flags = 0; + filemod_data->src_inode = 0; + filemod_data->dst_inode = dst_file_ino; + filemod_data->src_device_id = 0; + filemod_data->dst_device_id = dst_device_id; + filemod_data->src_filepath_length = 0; + filemod_data->dst_filepath_length = 0; + + void* payload = populate_var_metadata(&filemod_data->meta, task, pid, + filemod_data->payload); + payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload); + + size_t len = bpf_probe_read_kernel_str(payload, MAX_FILEPATH_LENGTH, + oldname); + barrier_var(len); + if (len <= MAX_FILEPATH_LENGTH) { + barrier_var(len); + payload += len; + filemod_data->src_filepath_length = len; + } + len = read_absolute_file_path_from_dentry(dentry, payload); + barrier_var(len); + if (len <= MAX_FILEPATH_LENGTH) { + barrier_var(len); + payload += len; + filemod_data->dst_filepath_length = len; + } + bpf_stats_pre_submit_var_perf_event(&stats_ctx, &filemod_data->meta); + unsigned long data_len = payload - (void*)filemod_data; + data_len = data_len > sizeof(*filemod_data) ? sizeof(*filemod_data) : data_len; + bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, filemod_data, data_len); +out: + bpf_stats_exit(&stats_ctx); + return 0; +} + +SEC("raw_tracepoint/sched_process_fork") +int raw_tracepoint__sched_process_fork(struct bpf_raw_tracepoint_args* ctx) +{ + struct bpf_func_stats_ctx stats_ctx; + bpf_stats_enter(&stats_ctx, profiler_bpf_sched_process_fork); + + int zero = 0; + struct var_fork_data_t* fork_data = bpf_map_lookup_elem(&data_heap, &zero); + if (!fork_data) + goto out; + + struct task_struct* parent = (struct task_struct*)ctx->args[0]; + struct task_struct* child = (struct task_struct*)ctx->args[1]; + fork_data->meta.type = FORK_EVENT; + + void* payload = populate_var_metadata(&fork_data->meta, child, + BPF_CORE_READ(child, pid), fork_data->payload); + fork_data->parent_pid = BPF_CORE_READ(parent, pid); + fork_data->parent_exec_id = BPF_CORE_READ(parent, self_exec_id); + fork_data->parent_start_time = BPF_CORE_READ(parent, start_time); + bpf_stats_pre_submit_var_perf_event(&stats_ctx, &fork_data->meta); + + unsigned long data_len = payload - (void*)fork_data; + data_len = data_len > sizeof(*fork_data) ? sizeof(*fork_data) : data_len; + bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, fork_data, data_len); +out: + bpf_stats_exit(&stats_ctx); + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/profiler1.c b/tools/testing/selftests/bpf/progs/profiler1.c new file mode 100644 index 0000000000..fb6b135229 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/profiler1.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#define UNROLL +#define INLINE __always_inline +#include "profiler.inc.h" diff --git a/tools/testing/selftests/bpf/progs/profiler2.c b/tools/testing/selftests/bpf/progs/profiler2.c new file mode 100644 index 0000000000..0f32a3cbf5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/profiler2.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#define barrier_var(var) /**/ +/* undef #define UNROLL */ +#define INLINE /**/ +#include "profiler.inc.h" diff --git a/tools/testing/selftests/bpf/progs/profiler3.c b/tools/testing/selftests/bpf/progs/profiler3.c new file mode 100644 index 0000000000..6249fc31cc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/profiler3.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#define barrier_var(var) /**/ +#define UNROLL +#define INLINE __noinline +#include "profiler.inc.h" diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h new file mode 100644 index 0000000000..026d573ce1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf.h @@ -0,0 +1,357 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <stdint.h> +#include <stddef.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define FUNCTION_NAME_LEN 64 +#define FILE_NAME_LEN 128 +#define TASK_COMM_LEN 16 + +typedef struct { + int PyThreadState_frame; + int PyThreadState_thread; + int PyFrameObject_back; + int PyFrameObject_code; + int PyFrameObject_lineno; + int PyCodeObject_filename; + int PyCodeObject_name; + int String_data; + int String_size; +} OffsetConfig; + +typedef struct { + uintptr_t current_state_addr; + uintptr_t tls_key_addr; + OffsetConfig offsets; + bool use_tls; +} PidData; + +typedef struct { + uint32_t success; +} Stats; + +typedef struct { + char name[FUNCTION_NAME_LEN]; + char file[FILE_NAME_LEN]; +} Symbol; + +typedef struct { + uint32_t pid; + uint32_t tid; + char comm[TASK_COMM_LEN]; + int32_t kernel_stack_id; + int32_t user_stack_id; + bool thread_current; + bool pthread_match; + bool stack_complete; + int16_t stack_len; + int32_t stack[STACK_MAX_LEN]; + + int has_meta; + int metadata; + char dummy_safeguard; +} Event; + + +typedef int pid_t; + +typedef struct { + void* f_back; // PyFrameObject.f_back, previous frame + void* f_code; // PyFrameObject.f_code, pointer to PyCodeObject + void* co_filename; // PyCodeObject.co_filename + void* co_name; // PyCodeObject.co_name +} FrameData; + +#ifdef SUBPROGS +__noinline +#else +__always_inline +#endif +static void *get_thread_state(void *tls_base, PidData *pidData) +{ + void* thread_state; + int key; + + bpf_probe_read_user(&key, sizeof(key), (void*)(long)pidData->tls_key_addr); + bpf_probe_read_user(&thread_state, sizeof(thread_state), + tls_base + 0x310 + key * 0x10 + 0x08); + return thread_state; +} + +static __always_inline bool get_frame_data(void *frame_ptr, PidData *pidData, + FrameData *frame, Symbol *symbol) +{ + // read data from PyFrameObject + bpf_probe_read_user(&frame->f_back, + sizeof(frame->f_back), + frame_ptr + pidData->offsets.PyFrameObject_back); + bpf_probe_read_user(&frame->f_code, + sizeof(frame->f_code), + frame_ptr + pidData->offsets.PyFrameObject_code); + + // read data from PyCodeObject + if (!frame->f_code) + return false; + bpf_probe_read_user(&frame->co_filename, + sizeof(frame->co_filename), + frame->f_code + pidData->offsets.PyCodeObject_filename); + bpf_probe_read_user(&frame->co_name, + sizeof(frame->co_name), + frame->f_code + pidData->offsets.PyCodeObject_name); + // read actual names into symbol + if (frame->co_filename) + bpf_probe_read_user_str(&symbol->file, + sizeof(symbol->file), + frame->co_filename + + pidData->offsets.String_data); + if (frame->co_name) + bpf_probe_read_user_str(&symbol->name, + sizeof(symbol->name), + frame->co_name + + pidData->offsets.String_data); + return true; +} + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, PidData); +} pidmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, Event); +} eventmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, Symbol); + __type(value, int); +} symbolmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, Stats); +} statsmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(max_entries, 32); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); +} perfmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, 1000); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(long long) * 127); +} stackmap SEC(".maps"); + +#ifdef USE_BPF_LOOP +struct process_frame_ctx { + int cur_cpu; + int32_t *symbol_counter; + void *frame_ptr; + FrameData *frame; + PidData *pidData; + Symbol *sym; + Event *event; + bool done; +}; + +static int process_frame_callback(__u32 i, struct process_frame_ctx *ctx) +{ + int zero = 0; + void *frame_ptr = ctx->frame_ptr; + PidData *pidData = ctx->pidData; + FrameData *frame = ctx->frame; + int32_t *symbol_counter = ctx->symbol_counter; + int cur_cpu = ctx->cur_cpu; + Event *event = ctx->event; + Symbol *sym = ctx->sym; + + if (frame_ptr && get_frame_data(frame_ptr, pidData, frame, sym)) { + int32_t new_symbol_id = *symbol_counter * 64 + cur_cpu; + int32_t *symbol_id = bpf_map_lookup_elem(&symbolmap, sym); + + if (!symbol_id) { + bpf_map_update_elem(&symbolmap, sym, &zero, 0); + symbol_id = bpf_map_lookup_elem(&symbolmap, sym); + if (!symbol_id) { + ctx->done = true; + return 1; + } + } + if (*symbol_id == new_symbol_id) + (*symbol_counter)++; + + barrier_var(i); + if (i >= STACK_MAX_LEN) + return 1; + + event->stack[i] = *symbol_id; + + event->stack_len = i + 1; + frame_ptr = frame->f_back; + } + return 0; +} +#endif /* USE_BPF_LOOP */ + +#ifdef GLOBAL_FUNC +__noinline +#elif defined(SUBPROGS) +static __noinline +#else +static __always_inline +#endif +int __on_event(struct bpf_raw_tracepoint_args *ctx) +{ + uint64_t pid_tgid = bpf_get_current_pid_tgid(); + pid_t pid = (pid_t)(pid_tgid >> 32); + PidData* pidData = bpf_map_lookup_elem(&pidmap, &pid); + if (!pidData) + return 0; + + int zero = 0; + Event* event = bpf_map_lookup_elem(&eventmap, &zero); + if (!event) + return 0; + + event->pid = pid; + + event->tid = (pid_t)pid_tgid; + bpf_get_current_comm(&event->comm, sizeof(event->comm)); + + event->user_stack_id = bpf_get_stackid(ctx, &stackmap, BPF_F_USER_STACK); + event->kernel_stack_id = bpf_get_stackid(ctx, &stackmap, 0); + + void* thread_state_current = (void*)0; + bpf_probe_read_user(&thread_state_current, + sizeof(thread_state_current), + (void*)(long)pidData->current_state_addr); + + struct task_struct* task = (struct task_struct*)bpf_get_current_task(); + void* tls_base = (void*)task; + + void* thread_state = pidData->use_tls ? get_thread_state(tls_base, pidData) + : thread_state_current; + event->thread_current = thread_state == thread_state_current; + + if (pidData->use_tls) { + uint64_t pthread_created; + uint64_t pthread_self; + bpf_probe_read_user(&pthread_self, sizeof(pthread_self), + tls_base + 0x10); + + bpf_probe_read_user(&pthread_created, + sizeof(pthread_created), + thread_state + + pidData->offsets.PyThreadState_thread); + event->pthread_match = pthread_created == pthread_self; + } else { + event->pthread_match = 1; + } + + if (event->pthread_match || !pidData->use_tls) { + void* frame_ptr; + FrameData frame; + Symbol sym = {}; + int cur_cpu = bpf_get_smp_processor_id(); + + bpf_probe_read_user(&frame_ptr, + sizeof(frame_ptr), + thread_state + + pidData->offsets.PyThreadState_frame); + + int32_t* symbol_counter = bpf_map_lookup_elem(&symbolmap, &sym); + if (symbol_counter == NULL) + return 0; +#ifdef USE_BPF_LOOP + struct process_frame_ctx ctx = { + .cur_cpu = cur_cpu, + .symbol_counter = symbol_counter, + .frame_ptr = frame_ptr, + .frame = &frame, + .pidData = pidData, + .sym = &sym, + .event = event, + }; + + bpf_loop(STACK_MAX_LEN, process_frame_callback, &ctx, 0); + if (ctx.done) + return 0; +#else +#if defined(USE_ITER) +/* no for loop, no unrolling */ +#elif defined(NO_UNROLL) +#pragma clang loop unroll(disable) +#elif defined(UNROLL_COUNT) +#pragma clang loop unroll_count(UNROLL_COUNT) +#else +#pragma clang loop unroll(full) +#endif /* NO_UNROLL */ + /* Unwind python stack */ +#ifdef USE_ITER + int i; + bpf_for(i, 0, STACK_MAX_LEN) { +#else /* !USE_ITER */ + for (int i = 0; i < STACK_MAX_LEN; ++i) { +#endif + if (frame_ptr && get_frame_data(frame_ptr, pidData, &frame, &sym)) { + int32_t new_symbol_id = *symbol_counter * 64 + cur_cpu; + int32_t *symbol_id = bpf_map_lookup_elem(&symbolmap, &sym); + if (!symbol_id) { + bpf_map_update_elem(&symbolmap, &sym, &zero, 0); + symbol_id = bpf_map_lookup_elem(&symbolmap, &sym); + if (!symbol_id) + return 0; + } + if (*symbol_id == new_symbol_id) + (*symbol_counter)++; + event->stack[i] = *symbol_id; + event->stack_len = i + 1; + frame_ptr = frame.f_back; + } + } +#endif /* USE_BPF_LOOP */ + event->stack_complete = frame_ptr == NULL; + } else { + event->stack_complete = 1; + } + + Stats* stats = bpf_map_lookup_elem(&statsmap, &zero); + if (stats) + stats->success++; + + event->has_meta = 0; + bpf_perf_event_output(ctx, &perfmap, 0, event, offsetof(Event, metadata)); + return 0; +} + +SEC("raw_tracepoint/kfree_skb") +int on_event(struct bpf_raw_tracepoint_args* ctx) +{ + int ret = 0; + ret |= __on_event(ctx); + ret |= __on_event(ctx); + ret |= __on_event(ctx); + ret |= __on_event(ctx); + ret |= __on_event(ctx); + return ret; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/pyperf100.c b/tools/testing/selftests/bpf/progs/pyperf100.c new file mode 100644 index 0000000000..29786325db --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf100.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#define STACK_MAX_LEN 100 +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/pyperf180.c b/tools/testing/selftests/bpf/progs/pyperf180.c new file mode 100644 index 0000000000..c39f559d31 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf180.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#define STACK_MAX_LEN 180 +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/pyperf50.c b/tools/testing/selftests/bpf/progs/pyperf50.c new file mode 100644 index 0000000000..ef7ce340a2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf50.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#define STACK_MAX_LEN 50 +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/pyperf600.c b/tools/testing/selftests/bpf/progs/pyperf600.c new file mode 100644 index 0000000000..ce1aa5189c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf600.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#define STACK_MAX_LEN 600 +/* Full unroll of 600 iterations will have total + * program size close to 298k insns and this may + * cause BPF_JMP insn out of 16-bit integer range. + * So limit the unroll size to 150 so the + * total program size is around 80k insns but + * the loop will still execute 600 times. + */ +#define UNROLL_COUNT 150 +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/pyperf600_bpf_loop.c b/tools/testing/selftests/bpf/progs/pyperf600_bpf_loop.c new file mode 100644 index 0000000000..5c2059dc01 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf600_bpf_loop.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#define STACK_MAX_LEN 600 +#define USE_BPF_LOOP +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/pyperf600_iter.c b/tools/testing/selftests/bpf/progs/pyperf600_iter.c new file mode 100644 index 0000000000..d62e1b200c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf600_iter.c @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2023 Meta Platforms, Inc. and affiliates. +#define STACK_MAX_LEN 600 +#define SUBPROGS +#define NO_UNROLL +#define USE_ITER +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c b/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c new file mode 100644 index 0000000000..520b58c4f8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#define STACK_MAX_LEN 600 +#define NO_UNROLL +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/pyperf_global.c b/tools/testing/selftests/bpf/progs/pyperf_global.c new file mode 100644 index 0000000000..079e78a756 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf_global.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#define STACK_MAX_LEN 50 +#define GLOBAL_FUNC +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/pyperf_subprogs.c b/tools/testing/selftests/bpf/progs/pyperf_subprogs.c new file mode 100644 index 0000000000..60e27a7f0c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf_subprogs.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#define STACK_MAX_LEN 50 +#define SUBPROGS +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/rbtree.c b/tools/testing/selftests/bpf/progs/rbtree.c new file mode 100644 index 0000000000..b09f4fffe5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/rbtree.c @@ -0,0 +1,246 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_experimental.h" + +struct node_data { + long key; + long data; + struct bpf_rb_node node; +}; + +long less_callback_ran = -1; +long removed_key = -1; +long first_data[2] = {-1, -1}; + +#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) +private(A) struct bpf_spin_lock glock; +private(A) struct bpf_rb_root groot __contains(node_data, node); + +static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = container_of(a, struct node_data, node); + node_b = container_of(b, struct node_data, node); + less_callback_ran = 1; + + return node_a->key < node_b->key; +} + +static long __add_three(struct bpf_rb_root *root, struct bpf_spin_lock *lock) +{ + struct node_data *n, *m; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + n->key = 5; + + m = bpf_obj_new(typeof(*m)); + if (!m) { + bpf_obj_drop(n); + return 2; + } + m->key = 1; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_rbtree_add(&groot, &m->node, less); + bpf_spin_unlock(&glock); + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 3; + n->key = 3; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_spin_unlock(&glock); + return 0; +} + +SEC("tc") +long rbtree_add_nodes(void *ctx) +{ + return __add_three(&groot, &glock); +} + +SEC("tc") +long rbtree_add_and_remove(void *ctx) +{ + struct bpf_rb_node *res = NULL; + struct node_data *n, *m = NULL; + + n = bpf_obj_new(typeof(*n)); + if (!n) + goto err_out; + n->key = 5; + + m = bpf_obj_new(typeof(*m)); + if (!m) + goto err_out; + m->key = 3; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_rbtree_add(&groot, &m->node, less); + res = bpf_rbtree_remove(&groot, &n->node); + bpf_spin_unlock(&glock); + + if (!res) + return 1; + + n = container_of(res, struct node_data, node); + removed_key = n->key; + bpf_obj_drop(n); + + return 0; +err_out: + if (n) + bpf_obj_drop(n); + if (m) + bpf_obj_drop(m); + return 1; +} + +SEC("tc") +long rbtree_first_and_remove(void *ctx) +{ + struct bpf_rb_node *res = NULL; + struct node_data *n, *m, *o; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + n->key = 3; + n->data = 4; + + m = bpf_obj_new(typeof(*m)); + if (!m) + goto err_out; + m->key = 5; + m->data = 6; + + o = bpf_obj_new(typeof(*o)); + if (!o) + goto err_out; + o->key = 1; + o->data = 2; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_rbtree_add(&groot, &m->node, less); + bpf_rbtree_add(&groot, &o->node, less); + + res = bpf_rbtree_first(&groot); + if (!res) { + bpf_spin_unlock(&glock); + return 2; + } + + o = container_of(res, struct node_data, node); + first_data[0] = o->data; + + res = bpf_rbtree_remove(&groot, &o->node); + bpf_spin_unlock(&glock); + + if (!res) + return 5; + + o = container_of(res, struct node_data, node); + removed_key = o->key; + bpf_obj_drop(o); + + bpf_spin_lock(&glock); + res = bpf_rbtree_first(&groot); + if (!res) { + bpf_spin_unlock(&glock); + return 3; + } + + o = container_of(res, struct node_data, node); + first_data[1] = o->data; + bpf_spin_unlock(&glock); + + return 0; +err_out: + if (n) + bpf_obj_drop(n); + if (m) + bpf_obj_drop(m); + return 1; +} + +SEC("tc") +long rbtree_api_release_aliasing(void *ctx) +{ + struct node_data *n, *m, *o; + struct bpf_rb_node *res, *res2; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + n->key = 41; + n->data = 42; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_spin_unlock(&glock); + + bpf_spin_lock(&glock); + + /* m and o point to the same node, + * but verifier doesn't know this + */ + res = bpf_rbtree_first(&groot); + if (!res) + goto err_out; + o = container_of(res, struct node_data, node); + + res = bpf_rbtree_first(&groot); + if (!res) + goto err_out; + m = container_of(res, struct node_data, node); + + res = bpf_rbtree_remove(&groot, &m->node); + /* Retval of previous remove returns an owning reference to m, + * which is the same node non-owning ref o is pointing at. + * We can safely try to remove o as the second rbtree_remove will + * return NULL since the node isn't in a tree. + * + * Previously we relied on the verifier type system + rbtree_remove + * invalidating non-owning refs to ensure that rbtree_remove couldn't + * fail, but now rbtree_remove does runtime checking so we no longer + * invalidate non-owning refs after remove. + */ + res2 = bpf_rbtree_remove(&groot, &o->node); + + bpf_spin_unlock(&glock); + + if (res) { + o = container_of(res, struct node_data, node); + first_data[0] = o->data; + bpf_obj_drop(o); + } + if (res2) { + /* The second remove fails, so res2 is null and this doesn't + * execute + */ + m = container_of(res2, struct node_data, node); + first_data[1] = m->data; + bpf_obj_drop(m); + } + return 0; + +err_out: + bpf_spin_unlock(&glock); + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/rbtree_btf_fail__add_wrong_type.c b/tools/testing/selftests/bpf/progs/rbtree_btf_fail__add_wrong_type.c new file mode 100644 index 0000000000..60079b202c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/rbtree_btf_fail__add_wrong_type.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_experimental.h" + +struct node_data { + int key; + int data; + struct bpf_rb_node node; +}; + +struct node_data2 { + int key; + struct bpf_rb_node node; + int data; +}; + +static bool less2(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data2 *node_a; + struct node_data2 *node_b; + + node_a = container_of(a, struct node_data2, node); + node_b = container_of(b, struct node_data2, node); + + return node_a->key < node_b->key; +} + +#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) +private(A) struct bpf_spin_lock glock; +private(A) struct bpf_rb_root groot __contains(node_data, node); + +SEC("tc") +long rbtree_api_add__add_wrong_type(void *ctx) +{ + struct node_data2 *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less2); + bpf_spin_unlock(&glock); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/rbtree_btf_fail__wrong_node_type.c b/tools/testing/selftests/bpf/progs/rbtree_btf_fail__wrong_node_type.c new file mode 100644 index 0000000000..7651843f5a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/rbtree_btf_fail__wrong_node_type.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_experimental.h" + +/* BTF load should fail as bpf_rb_root __contains this type and points to + * 'node', but 'node' is not a bpf_rb_node + */ +struct node_data { + int key; + int data; + struct bpf_list_node node; +}; + +#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) +private(A) struct bpf_spin_lock glock; +private(A) struct bpf_rb_root groot __contains(node_data, node); + +SEC("tc") +long rbtree_api_add__wrong_node_type(void *ctx) +{ + struct node_data *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&glock); + bpf_rbtree_first(&groot); + bpf_spin_unlock(&glock); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/rbtree_fail.c b/tools/testing/selftests/bpf/progs/rbtree_fail.c new file mode 100644 index 0000000000..3fecf1c6df --- /dev/null +++ b/tools/testing/selftests/bpf/progs/rbtree_fail.c @@ -0,0 +1,303 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_experimental.h" +#include "bpf_misc.h" + +struct node_data { + long key; + long data; + struct bpf_rb_node node; +}; + +#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) +private(A) struct bpf_spin_lock glock; +private(A) struct bpf_rb_root groot __contains(node_data, node); +private(A) struct bpf_rb_root groot2 __contains(node_data, node); + +static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = container_of(a, struct node_data, node); + node_b = container_of(b, struct node_data, node); + + return node_a->key < node_b->key; +} + +SEC("?tc") +__failure __msg("bpf_spin_lock at off=16 must be held for bpf_rb_root") +long rbtree_api_nolock_add(void *ctx) +{ + struct node_data *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_rbtree_add(&groot, &n->node, less); + return 0; +} + +SEC("?tc") +__failure __msg("bpf_spin_lock at off=16 must be held for bpf_rb_root") +long rbtree_api_nolock_remove(void *ctx) +{ + struct node_data *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_spin_unlock(&glock); + + bpf_rbtree_remove(&groot, &n->node); + return 0; +} + +SEC("?tc") +__failure __msg("bpf_spin_lock at off=16 must be held for bpf_rb_root") +long rbtree_api_nolock_first(void *ctx) +{ + bpf_rbtree_first(&groot); + return 0; +} + +SEC("?tc") +__failure __msg("rbtree_remove node input must be non-owning ref") +long rbtree_api_remove_unadded_node(void *ctx) +{ + struct node_data *n, *m; + struct bpf_rb_node *res; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + m = bpf_obj_new(typeof(*m)); + if (!m) { + bpf_obj_drop(n); + return 1; + } + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + + /* This remove should pass verifier */ + res = bpf_rbtree_remove(&groot, &n->node); + n = container_of(res, struct node_data, node); + + /* This remove shouldn't, m isn't in an rbtree */ + res = bpf_rbtree_remove(&groot, &m->node); + m = container_of(res, struct node_data, node); + bpf_spin_unlock(&glock); + + if (n) + bpf_obj_drop(n); + if (m) + bpf_obj_drop(m); + return 0; +} + +SEC("?tc") +__failure __msg("Unreleased reference id=3 alloc_insn=10") +long rbtree_api_remove_no_drop(void *ctx) +{ + struct bpf_rb_node *res; + struct node_data *n; + + bpf_spin_lock(&glock); + res = bpf_rbtree_first(&groot); + if (!res) + goto unlock_err; + + res = bpf_rbtree_remove(&groot, res); + + if (res) { + n = container_of(res, struct node_data, node); + __sink(n); + } + bpf_spin_unlock(&glock); + + /* if (res) { bpf_obj_drop(n); } is missing here */ + return 0; + +unlock_err: + bpf_spin_unlock(&glock); + return 1; +} + +SEC("?tc") +__failure __msg("arg#1 expected pointer to allocated object") +long rbtree_api_add_to_multiple_trees(void *ctx) +{ + struct node_data *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + + /* This add should fail since n already in groot's tree */ + bpf_rbtree_add(&groot2, &n->node, less); + bpf_spin_unlock(&glock); + return 0; +} + +SEC("?tc") +__failure __msg("dereference of modified ptr_or_null_ ptr R2 off=16 disallowed") +long rbtree_api_use_unchecked_remove_retval(void *ctx) +{ + struct bpf_rb_node *res; + + bpf_spin_lock(&glock); + + res = bpf_rbtree_first(&groot); + if (!res) + goto err_out; + res = bpf_rbtree_remove(&groot, res); + + bpf_spin_unlock(&glock); + + bpf_spin_lock(&glock); + /* Must check res for NULL before using in rbtree_add below */ + bpf_rbtree_add(&groot, res, less); + bpf_spin_unlock(&glock); + return 0; + +err_out: + bpf_spin_unlock(&glock); + return 1; +} + +SEC("?tc") +__failure __msg("rbtree_remove node input must be non-owning ref") +long rbtree_api_add_release_unlock_escape(void *ctx) +{ + struct node_data *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_spin_unlock(&glock); + + bpf_spin_lock(&glock); + /* After add() in previous critical section, n should be + * release_on_unlock and released after previous spin_unlock, + * so should not be possible to use it here + */ + bpf_rbtree_remove(&groot, &n->node); + bpf_spin_unlock(&glock); + return 0; +} + +SEC("?tc") +__failure __msg("rbtree_remove node input must be non-owning ref") +long rbtree_api_first_release_unlock_escape(void *ctx) +{ + struct bpf_rb_node *res; + struct node_data *n; + + bpf_spin_lock(&glock); + res = bpf_rbtree_first(&groot); + if (!res) { + bpf_spin_unlock(&glock); + return 1; + } + n = container_of(res, struct node_data, node); + bpf_spin_unlock(&glock); + + bpf_spin_lock(&glock); + /* After first() in previous critical section, n should be + * release_on_unlock and released after previous spin_unlock, + * so should not be possible to use it here + */ + bpf_rbtree_remove(&groot, &n->node); + bpf_spin_unlock(&glock); + return 0; +} + +static bool less__bad_fn_call_add(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = container_of(a, struct node_data, node); + node_b = container_of(b, struct node_data, node); + bpf_rbtree_add(&groot, &node_a->node, less); + + return node_a->key < node_b->key; +} + +static bool less__bad_fn_call_remove(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = container_of(a, struct node_data, node); + node_b = container_of(b, struct node_data, node); + bpf_rbtree_remove(&groot, &node_a->node); + + return node_a->key < node_b->key; +} + +static bool less__bad_fn_call_first_unlock_after(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = container_of(a, struct node_data, node); + node_b = container_of(b, struct node_data, node); + bpf_rbtree_first(&groot); + bpf_spin_unlock(&glock); + + return node_a->key < node_b->key; +} + +static __always_inline +long add_with_cb(bool (cb)(struct bpf_rb_node *a, const struct bpf_rb_node *b)) +{ + struct node_data *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, cb); + bpf_spin_unlock(&glock); + return 0; +} + +SEC("?tc") +__failure __msg("arg#1 expected pointer to allocated object") +long rbtree_api_add_bad_cb_bad_fn_call_add(void *ctx) +{ + return add_with_cb(less__bad_fn_call_add); +} + +SEC("?tc") +__failure __msg("rbtree_remove not allowed in rbtree cb") +long rbtree_api_add_bad_cb_bad_fn_call_remove(void *ctx) +{ + return add_with_cb(less__bad_fn_call_remove); +} + +SEC("?tc") +__failure __msg("can't spin_{lock,unlock} in rbtree cb") +long rbtree_api_add_bad_cb_bad_fn_call_first_unlock_after(void *ctx) +{ + return add_with_cb(less__bad_fn_call_first_unlock_after); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c new file mode 100644 index 0000000000..14fb01437f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c @@ -0,0 +1,321 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_tracing_net.h" +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} map_a SEC(".maps"); + +__u32 user_data, key_serial, target_pid; +__u64 flags, task_storage_val, cgroup_id; + +struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym; +void bpf_key_put(struct bpf_key *key) __ksym; +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; +struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int get_cgroup_id(void *ctx) +{ + struct task_struct *task; + struct css_set *cgroups; + + task = bpf_get_current_task_btf(); + if (task->pid != target_pid) + return 0; + + /* simulate bpf_get_current_cgroup_id() helper */ + bpf_rcu_read_lock(); + cgroups = task->cgroups; + if (!cgroups) + goto unlock; + cgroup_id = cgroups->dfl_cgrp->kn->id; +unlock: + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int task_succ(void *ctx) +{ + struct task_struct *task, *real_parent; + long init_val = 2; + long *ptr; + + task = bpf_get_current_task_btf(); + if (task->pid != target_pid) + return 0; + + bpf_rcu_read_lock(); + /* region including helper using rcu ptr real_parent */ + real_parent = task->real_parent; + if (!real_parent) + goto out; + ptr = bpf_task_storage_get(&map_a, real_parent, &init_val, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!ptr) + goto out; + ptr = bpf_task_storage_get(&map_a, real_parent, 0, 0); + if (!ptr) + goto out; + task_storage_val = *ptr; +out: + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_nanosleep") +int no_lock(void *ctx) +{ + struct task_struct *task, *real_parent; + + /* old style ptr_to_btf_id is not allowed in sleepable */ + task = bpf_get_current_task_btf(); + real_parent = task->real_parent; + (void)bpf_task_storage_get(&map_a, real_parent, 0, 0); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_nanosleep") +int two_regions(void *ctx) +{ + struct task_struct *task, *real_parent; + + /* two regions */ + task = bpf_get_current_task_btf(); + bpf_rcu_read_lock(); + bpf_rcu_read_unlock(); + bpf_rcu_read_lock(); + real_parent = task->real_parent; + if (!real_parent) + goto out; + (void)bpf_task_storage_get(&map_a, real_parent, 0, 0); +out: + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry/" SYS_PREFIX "sys_getpgid") +int non_sleepable_1(void *ctx) +{ + struct task_struct *task, *real_parent; + + task = bpf_get_current_task_btf(); + bpf_rcu_read_lock(); + real_parent = task->real_parent; + if (!real_parent) + goto out; + (void)bpf_task_storage_get(&map_a, real_parent, 0, 0); +out: + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry/" SYS_PREFIX "sys_getpgid") +int non_sleepable_2(void *ctx) +{ + struct task_struct *task, *real_parent; + + bpf_rcu_read_lock(); + task = bpf_get_current_task_btf(); + bpf_rcu_read_unlock(); + + bpf_rcu_read_lock(); + real_parent = task->real_parent; + if (!real_parent) + goto out; + (void)bpf_task_storage_get(&map_a, real_parent, 0, 0); +out: + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_nanosleep") +int task_acquire(void *ctx) +{ + struct task_struct *task, *real_parent, *gparent; + + task = bpf_get_current_task_btf(); + bpf_rcu_read_lock(); + real_parent = task->real_parent; + if (!real_parent) + goto out; + + /* rcu_ptr->rcu_field */ + gparent = real_parent->real_parent; + if (!gparent) + goto out; + + /* acquire a reference which can be used outside rcu read lock region */ + gparent = bpf_task_acquire(gparent); + if (!gparent) + goto out; + + (void)bpf_task_storage_get(&map_a, gparent, 0, 0); + bpf_task_release(gparent); +out: + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int miss_lock(void *ctx) +{ + struct task_struct *task; + + /* missing bpf_rcu_read_lock() */ + task = bpf_get_current_task_btf(); + bpf_rcu_read_lock(); + (void)bpf_task_storage_get(&map_a, task, 0, 0); + bpf_rcu_read_unlock(); + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int miss_unlock(void *ctx) +{ + struct task_struct *task; + + /* missing bpf_rcu_read_unlock() */ + task = bpf_get_current_task_btf(); + bpf_rcu_read_lock(); + (void)bpf_task_storage_get(&map_a, task, 0, 0); + return 0; +} + +SEC("?fentry/" SYS_PREFIX "sys_getpgid") +int non_sleepable_rcu_mismatch(void *ctx) +{ + struct task_struct *task, *real_parent; + + task = bpf_get_current_task_btf(); + /* non-sleepable: missing bpf_rcu_read_unlock() in one path */ + bpf_rcu_read_lock(); + real_parent = task->real_parent; + if (!real_parent) + goto out; + (void)bpf_task_storage_get(&map_a, real_parent, 0, 0); + if (real_parent) + bpf_rcu_read_unlock(); +out: + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int inproper_sleepable_helper(void *ctx) +{ + struct task_struct *task, *real_parent; + struct pt_regs *regs; + __u32 value = 0; + void *ptr; + + task = bpf_get_current_task_btf(); + /* sleepable helper in rcu read lock region */ + bpf_rcu_read_lock(); + real_parent = task->real_parent; + if (!real_parent) + goto out; + regs = (struct pt_regs *)bpf_task_pt_regs(real_parent); + if (!regs) + goto out; + + ptr = (void *)PT_REGS_IP(regs); + (void)bpf_copy_from_user_task(&value, sizeof(uint32_t), ptr, task, 0); + user_data = value; + (void)bpf_task_storage_get(&map_a, real_parent, 0, 0); +out: + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?lsm.s/bpf") +int BPF_PROG(inproper_sleepable_kfunc, int cmd, union bpf_attr *attr, unsigned int size) +{ + struct bpf_key *bkey; + + /* sleepable kfunc in rcu read lock region */ + bpf_rcu_read_lock(); + bkey = bpf_lookup_user_key(key_serial, flags); + bpf_rcu_read_unlock(); + if (!bkey) + return -1; + bpf_key_put(bkey); + + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_nanosleep") +int nested_rcu_region(void *ctx) +{ + struct task_struct *task, *real_parent; + + /* nested rcu read lock regions */ + task = bpf_get_current_task_btf(); + bpf_rcu_read_lock(); + bpf_rcu_read_lock(); + real_parent = task->real_parent; + if (!real_parent) + goto out; + (void)bpf_task_storage_get(&map_a, real_parent, 0, 0); +out: + bpf_rcu_read_unlock(); + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int task_trusted_non_rcuptr(void *ctx) +{ + struct task_struct *task, *group_leader; + + task = bpf_get_current_task_btf(); + bpf_rcu_read_lock(); + /* the pointer group_leader is explicitly marked as trusted */ + group_leader = task->real_parent->group_leader; + (void)bpf_task_storage_get(&map_a, group_leader, 0, 0); + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int task_untrusted_rcuptr(void *ctx) +{ + struct task_struct *task, *real_parent; + + task = bpf_get_current_task_btf(); + bpf_rcu_read_lock(); + real_parent = task->real_parent; + bpf_rcu_read_unlock(); + /* helper use of rcu ptr outside the rcu read lock region */ + (void)bpf_task_storage_get(&map_a, real_parent, 0, 0); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_nanosleep") +int cross_rcu_region(void *ctx) +{ + struct task_struct *task, *real_parent; + + /* rcu ptr define/use in different regions */ + task = bpf_get_current_task_btf(); + bpf_rcu_read_lock(); + real_parent = task->real_parent; + bpf_rcu_read_unlock(); + bpf_rcu_read_lock(); + (void)bpf_task_storage_get(&map_a, real_parent, 0, 0); + bpf_rcu_read_unlock(); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/rcu_tasks_trace_gp.c b/tools/testing/selftests/bpf/progs/rcu_tasks_trace_gp.c new file mode 100644 index 0000000000..df48735586 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/rcu_tasks_trace_gp.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +struct task_ls_map { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} task_ls_map SEC(".maps"); + +long gp_seq; + +SEC("syscall") +int do_call_rcu_tasks_trace(void *ctx) +{ + struct task_struct *current; + int *v; + + current = bpf_get_current_task_btf(); + v = bpf_task_storage_get(&task_ls_map, current, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!v) + return 1; + /* Invoke call_rcu_tasks_trace */ + return bpf_task_storage_delete(&task_ls_map, current); +} + +SEC("kprobe/rcu_tasks_trace_postgp") +int rcu_tasks_trace_postgp(void *ctx) +{ + __sync_add_and_fetch(&gp_seq, 1); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c b/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c new file mode 100644 index 0000000000..76556e0b42 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2022. Huawei Technologies Co., Ltd */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +extern bool CONFIG_PREEMPT __kconfig __weak; +extern const int bpf_task_storage_busy __ksym; + +char _license[] SEC("license") = "GPL"; + +int pid = 0; +int busy = 0; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} task SEC(".maps"); + +SEC("raw_tp/sys_enter") +int BPF_PROG(read_bpf_task_storage_busy) +{ + int *value; + + if (!CONFIG_PREEMPT) + return 0; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + value = bpf_this_cpu_ptr(&bpf_task_storage_busy); + if (value) + busy = *value; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/recursion.c b/tools/testing/selftests/bpf/progs/recursion.c new file mode 100644 index 0000000000..3c2423bb19 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/recursion.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, long); +} hash1 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, long); +} hash2 SEC(".maps"); + +int pass1 = 0; +int pass2 = 0; + +SEC("fentry/htab_map_delete_elem") +int BPF_PROG(on_delete, struct bpf_map *map) +{ + int key = 0; + + if (map == (void *)&hash1) { + pass1++; + return 0; + } + if (map == (void *)&hash2) { + pass2++; + bpf_map_delete_elem(&hash2, &key); + return 0; + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/recvmsg4_prog.c b/tools/testing/selftests/bpf/progs/recvmsg4_prog.c new file mode 100644 index 0000000000..59748c9547 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/recvmsg4_prog.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <sys/socket.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include <bpf_sockopt_helpers.h> + +#define SERV4_IP 0xc0a801feU /* 192.168.1.254 */ +#define SERV4_PORT 4040 + +SEC("cgroup/recvmsg4") +int recvmsg4_prog(struct bpf_sock_addr *ctx) +{ + struct bpf_sock *sk; + + sk = ctx->sk; + if (!sk) + return 1; + + if (sk->family != AF_INET) + return 1; + + if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM) + return 1; + + if (!get_set_sk_priority(ctx)) + return 1; + + ctx->user_ip4 = bpf_htonl(SERV4_IP); + ctx->user_port = bpf_htons(SERV4_PORT); + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/recvmsg6_prog.c b/tools/testing/selftests/bpf/progs/recvmsg6_prog.c new file mode 100644 index 0000000000..d9a4016596 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/recvmsg6_prog.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <linux/in6.h> +#include <sys/socket.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include <bpf_sockopt_helpers.h> + +#define SERV6_IP_0 0xfaceb00c /* face:b00c:1234:5678::abcd */ +#define SERV6_IP_1 0x12345678 +#define SERV6_IP_2 0x00000000 +#define SERV6_IP_3 0x0000abcd +#define SERV6_PORT 6060 + +SEC("cgroup/recvmsg6") +int recvmsg6_prog(struct bpf_sock_addr *ctx) +{ + struct bpf_sock *sk; + + sk = ctx->sk; + if (!sk) + return 1; + + if (sk->family != AF_INET6) + return 1; + + if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM) + return 1; + + if (!get_set_sk_priority(ctx)) + return 1; + + ctx->user_ip6[0] = bpf_htonl(SERV6_IP_0); + ctx->user_ip6[1] = bpf_htonl(SERV6_IP_1); + ctx->user_ip6[2] = bpf_htonl(SERV6_IP_2); + ctx->user_ip6[3] = bpf_htonl(SERV6_IP_3); + ctx->user_port = bpf_htons(SERV6_PORT); + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr.c b/tools/testing/selftests/bpf/progs/refcounted_kptr.c new file mode 100644 index 0000000000..893a4fdb4b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr.c @@ -0,0 +1,571 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" +#include "bpf_experimental.h" + +extern void bpf_rcu_read_lock(void) __ksym; +extern void bpf_rcu_read_unlock(void) __ksym; + +struct node_data { + long key; + long list_data; + struct bpf_rb_node r; + struct bpf_list_node l; + struct bpf_refcount ref; +}; + +struct map_value { + struct node_data __kptr *node; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 2); +} stashed_nodes SEC(".maps"); + +struct node_acquire { + long key; + long data; + struct bpf_rb_node node; + struct bpf_refcount refcount; +}; + +#define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8))) +private(A) struct bpf_spin_lock lock; +private(A) struct bpf_rb_root root __contains(node_data, r); +private(A) struct bpf_list_head head __contains(node_data, l); + +private(B) struct bpf_spin_lock alock; +private(B) struct bpf_rb_root aroot __contains(node_acquire, node); + +private(C) struct bpf_spin_lock block; +private(C) struct bpf_rb_root broot __contains(node_data, r); + +static bool less(struct bpf_rb_node *node_a, const struct bpf_rb_node *node_b) +{ + struct node_data *a; + struct node_data *b; + + a = container_of(node_a, struct node_data, r); + b = container_of(node_b, struct node_data, r); + + return a->key < b->key; +} + +static bool less_a(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_acquire *node_a; + struct node_acquire *node_b; + + node_a = container_of(a, struct node_acquire, node); + node_b = container_of(b, struct node_acquire, node); + + return node_a->key < node_b->key; +} + +static long __insert_in_tree_and_list(struct bpf_list_head *head, + struct bpf_rb_root *root, + struct bpf_spin_lock *lock) +{ + struct node_data *n, *m; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return -1; + + m = bpf_refcount_acquire(n); + m->key = 123; + m->list_data = 456; + + bpf_spin_lock(lock); + if (bpf_rbtree_add(root, &n->r, less)) { + /* Failure to insert - unexpected */ + bpf_spin_unlock(lock); + bpf_obj_drop(m); + return -2; + } + bpf_spin_unlock(lock); + + bpf_spin_lock(lock); + if (bpf_list_push_front(head, &m->l)) { + /* Failure to insert - unexpected */ + bpf_spin_unlock(lock); + return -3; + } + bpf_spin_unlock(lock); + return 0; +} + +static long __stash_map_insert_tree(int idx, int val, struct bpf_rb_root *root, + struct bpf_spin_lock *lock) +{ + struct map_value *mapval; + struct node_data *n, *m; + + mapval = bpf_map_lookup_elem(&stashed_nodes, &idx); + if (!mapval) + return -1; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return -2; + + n->key = val; + m = bpf_refcount_acquire(n); + + n = bpf_kptr_xchg(&mapval->node, n); + if (n) { + bpf_obj_drop(n); + bpf_obj_drop(m); + return -3; + } + + bpf_spin_lock(lock); + if (bpf_rbtree_add(root, &m->r, less)) { + /* Failure to insert - unexpected */ + bpf_spin_unlock(lock); + return -4; + } + bpf_spin_unlock(lock); + return 0; +} + +static long __read_from_tree(struct bpf_rb_root *root, + struct bpf_spin_lock *lock, + bool remove_from_tree) +{ + struct bpf_rb_node *rb; + struct node_data *n; + long res = -99; + + bpf_spin_lock(lock); + + rb = bpf_rbtree_first(root); + if (!rb) { + bpf_spin_unlock(lock); + return -1; + } + + n = container_of(rb, struct node_data, r); + res = n->key; + + if (!remove_from_tree) { + bpf_spin_unlock(lock); + return res; + } + + rb = bpf_rbtree_remove(root, rb); + bpf_spin_unlock(lock); + if (!rb) + return -2; + n = container_of(rb, struct node_data, r); + bpf_obj_drop(n); + return res; +} + +static long __read_from_list(struct bpf_list_head *head, + struct bpf_spin_lock *lock, + bool remove_from_list) +{ + struct bpf_list_node *l; + struct node_data *n; + long res = -99; + + bpf_spin_lock(lock); + + l = bpf_list_pop_front(head); + if (!l) { + bpf_spin_unlock(lock); + return -1; + } + + n = container_of(l, struct node_data, l); + res = n->list_data; + + if (!remove_from_list) { + if (bpf_list_push_back(head, &n->l)) { + bpf_spin_unlock(lock); + return -2; + } + } + + bpf_spin_unlock(lock); + + if (remove_from_list) + bpf_obj_drop(n); + return res; +} + +static long __read_from_unstash(int idx) +{ + struct node_data *n = NULL; + struct map_value *mapval; + long val = -99; + + mapval = bpf_map_lookup_elem(&stashed_nodes, &idx); + if (!mapval) + return -1; + + n = bpf_kptr_xchg(&mapval->node, n); + if (!n) + return -2; + + val = n->key; + bpf_obj_drop(n); + return val; +} + +#define INSERT_READ_BOTH(rem_tree, rem_list, desc) \ +SEC("tc") \ +__description(desc) \ +__success __retval(579) \ +long insert_and_remove_tree_##rem_tree##_list_##rem_list(void *ctx) \ +{ \ + long err, tree_data, list_data; \ + \ + err = __insert_in_tree_and_list(&head, &root, &lock); \ + if (err) \ + return err; \ + \ + err = __read_from_tree(&root, &lock, rem_tree); \ + if (err < 0) \ + return err; \ + else \ + tree_data = err; \ + \ + err = __read_from_list(&head, &lock, rem_list); \ + if (err < 0) \ + return err; \ + else \ + list_data = err; \ + \ + return tree_data + list_data; \ +} + +/* After successful insert of struct node_data into both collections: + * - it should have refcount = 2 + * - removing / not removing the node_data from a collection after + * reading should have no effect on ability to read / remove from + * the other collection + */ +INSERT_READ_BOTH(true, true, "insert_read_both: remove from tree + list"); +INSERT_READ_BOTH(false, false, "insert_read_both: remove from neither"); +INSERT_READ_BOTH(true, false, "insert_read_both: remove from tree"); +INSERT_READ_BOTH(false, true, "insert_read_both: remove from list"); + +#undef INSERT_READ_BOTH +#define INSERT_READ_BOTH(rem_tree, rem_list, desc) \ +SEC("tc") \ +__description(desc) \ +__success __retval(579) \ +long insert_and_remove_lf_tree_##rem_tree##_list_##rem_list(void *ctx) \ +{ \ + long err, tree_data, list_data; \ + \ + err = __insert_in_tree_and_list(&head, &root, &lock); \ + if (err) \ + return err; \ + \ + err = __read_from_list(&head, &lock, rem_list); \ + if (err < 0) \ + return err; \ + else \ + list_data = err; \ + \ + err = __read_from_tree(&root, &lock, rem_tree); \ + if (err < 0) \ + return err; \ + else \ + tree_data = err; \ + \ + return tree_data + list_data; \ +} + +/* Similar to insert_read_both, but list data is read and possibly removed + * first + * + * Results should be no different than reading and possibly removing rbtree + * node first + */ +INSERT_READ_BOTH(true, true, "insert_read_both_list_first: remove from tree + list"); +INSERT_READ_BOTH(false, false, "insert_read_both_list_first: remove from neither"); +INSERT_READ_BOTH(true, false, "insert_read_both_list_first: remove from tree"); +INSERT_READ_BOTH(false, true, "insert_read_both_list_first: remove from list"); + +#define INSERT_DOUBLE_READ_AND_DEL(read_fn, read_root, desc) \ +SEC("tc") \ +__description(desc) \ +__success __retval(-1) \ +long insert_double_##read_fn##_and_del_##read_root(void *ctx) \ +{ \ + long err, list_data; \ + \ + err = __insert_in_tree_and_list(&head, &root, &lock); \ + if (err) \ + return err; \ + \ + err = read_fn(&read_root, &lock, true); \ + if (err < 0) \ + return err; \ + else \ + list_data = err; \ + \ + err = read_fn(&read_root, &lock, true); \ + if (err < 0) \ + return err; \ + \ + return err + list_data; \ +} + +/* Insert into both tree and list, then try reading-and-removing from either twice + * + * The second read-and-remove should fail on read step since the node has + * already been removed + */ +INSERT_DOUBLE_READ_AND_DEL(__read_from_tree, root, "insert_double_del: 2x read-and-del from tree"); +INSERT_DOUBLE_READ_AND_DEL(__read_from_list, head, "insert_double_del: 2x read-and-del from list"); + +#define INSERT_STASH_READ(rem_tree, desc) \ +SEC("tc") \ +__description(desc) \ +__success __retval(84) \ +long insert_rbtree_and_stash__del_tree_##rem_tree(void *ctx) \ +{ \ + long err, tree_data, map_data; \ + \ + err = __stash_map_insert_tree(0, 42, &root, &lock); \ + if (err) \ + return err; \ + \ + err = __read_from_tree(&root, &lock, rem_tree); \ + if (err < 0) \ + return err; \ + else \ + tree_data = err; \ + \ + err = __read_from_unstash(0); \ + if (err < 0) \ + return err; \ + else \ + map_data = err; \ + \ + return tree_data + map_data; \ +} + +/* Stash a refcounted node in map_val, insert same node into tree, then try + * reading data from tree then unstashed map_val, possibly removing from tree + * + * Removing from tree should have no effect on map_val kptr validity + */ +INSERT_STASH_READ(true, "insert_stash_read: remove from tree"); +INSERT_STASH_READ(false, "insert_stash_read: don't remove from tree"); + +SEC("tc") +__success +long rbtree_refcounted_node_ref_escapes(void *ctx) +{ + struct node_acquire *n, *m; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&alock); + bpf_rbtree_add(&aroot, &n->node, less_a); + m = bpf_refcount_acquire(n); + bpf_spin_unlock(&alock); + if (!m) + return 2; + + m->key = 2; + bpf_obj_drop(m); + return 0; +} + +SEC("tc") +__success +long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx) +{ + struct node_acquire *n, *m; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + m = bpf_refcount_acquire(n); + m->key = 2; + + bpf_spin_lock(&alock); + bpf_rbtree_add(&aroot, &n->node, less_a); + bpf_spin_unlock(&alock); + + bpf_obj_drop(m); + + return 0; +} + +static long __stash_map_empty_xchg(struct node_data *n, int idx) +{ + struct map_value *mapval = bpf_map_lookup_elem(&stashed_nodes, &idx); + + if (!mapval) { + bpf_obj_drop(n); + return 1; + } + n = bpf_kptr_xchg(&mapval->node, n); + if (n) { + bpf_obj_drop(n); + return 2; + } + return 0; +} + +SEC("tc") +long rbtree_wrong_owner_remove_fail_a1(void *ctx) +{ + struct node_data *n, *m; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + m = bpf_refcount_acquire(n); + + if (__stash_map_empty_xchg(n, 0)) { + bpf_obj_drop(m); + return 2; + } + + if (__stash_map_empty_xchg(m, 1)) + return 3; + + return 0; +} + +SEC("tc") +long rbtree_wrong_owner_remove_fail_b(void *ctx) +{ + struct map_value *mapval; + struct node_data *n; + int idx = 0; + + mapval = bpf_map_lookup_elem(&stashed_nodes, &idx); + if (!mapval) + return 1; + + n = bpf_kptr_xchg(&mapval->node, NULL); + if (!n) + return 2; + + bpf_spin_lock(&block); + + bpf_rbtree_add(&broot, &n->r, less); + + bpf_spin_unlock(&block); + return 0; +} + +SEC("tc") +long rbtree_wrong_owner_remove_fail_a2(void *ctx) +{ + struct map_value *mapval; + struct bpf_rb_node *res; + struct node_data *m; + int idx = 1; + + mapval = bpf_map_lookup_elem(&stashed_nodes, &idx); + if (!mapval) + return 1; + + m = bpf_kptr_xchg(&mapval->node, NULL); + if (!m) + return 2; + bpf_spin_lock(&lock); + + /* make m non-owning ref */ + bpf_list_push_back(&head, &m->l); + res = bpf_rbtree_remove(&root, &m->r); + + bpf_spin_unlock(&lock); + if (res) { + bpf_obj_drop(container_of(res, struct node_data, r)); + return 3; + } + return 0; +} + +SEC("?fentry.s/bpf_testmod_test_read") +__success +int BPF_PROG(rbtree_sleepable_rcu, + struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) +{ + struct bpf_rb_node *rb; + struct node_data *n, *m = NULL; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 0; + + bpf_rcu_read_lock(); + bpf_spin_lock(&lock); + bpf_rbtree_add(&root, &n->r, less); + rb = bpf_rbtree_first(&root); + if (!rb) + goto err_out; + + rb = bpf_rbtree_remove(&root, rb); + if (!rb) + goto err_out; + + m = container_of(rb, struct node_data, r); + +err_out: + bpf_spin_unlock(&lock); + bpf_rcu_read_unlock(); + if (m) + bpf_obj_drop(m); + return 0; +} + +SEC("?fentry.s/bpf_testmod_test_read") +__success +int BPF_PROG(rbtree_sleepable_rcu_no_explicit_rcu_lock, + struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) +{ + struct bpf_rb_node *rb; + struct node_data *n, *m = NULL; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 0; + + /* No explicit bpf_rcu_read_lock */ + bpf_spin_lock(&lock); + bpf_rbtree_add(&root, &n->r, less); + rb = bpf_rbtree_first(&root); + if (!rb) + goto err_out; + + rb = bpf_rbtree_remove(&root, rb); + if (!rb) + goto err_out; + + m = container_of(rb, struct node_data, r); + +err_out: + bpf_spin_unlock(&lock); + /* No explicit bpf_rcu_read_unlock */ + if (m) + bpf_obj_drop(m); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c new file mode 100644 index 0000000000..1ef07f6ee5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_experimental.h" +#include "bpf_misc.h" + +struct node_acquire { + long key; + long data; + struct bpf_rb_node node; + struct bpf_refcount refcount; +}; + +extern void bpf_rcu_read_lock(void) __ksym; +extern void bpf_rcu_read_unlock(void) __ksym; + +#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) +private(A) struct bpf_spin_lock glock; +private(A) struct bpf_rb_root groot __contains(node_acquire, node); + +static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_acquire *node_a; + struct node_acquire *node_b; + + node_a = container_of(a, struct node_acquire, node); + node_b = container_of(b, struct node_acquire, node); + + return node_a->key < node_b->key; +} + +SEC("?tc") +__failure __msg("Unreleased reference id=4 alloc_insn=21") +long rbtree_refcounted_node_ref_escapes(void *ctx) +{ + struct node_acquire *n, *m; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + /* m becomes an owning ref but is never drop'd or added to a tree */ + m = bpf_refcount_acquire(n); + bpf_spin_unlock(&glock); + if (!m) + return 2; + + m->key = 2; + return 0; +} + +SEC("?tc") +__failure __msg("Unreleased reference id=3 alloc_insn=9") +long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx) +{ + struct node_acquire *n, *m; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + /* m becomes an owning ref but is never drop'd or added to a tree */ + m = bpf_refcount_acquire(n); + m->key = 2; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?fentry.s/bpf_testmod_test_read") +__failure __msg("function calls are not allowed while holding a lock") +int BPF_PROG(rbtree_fail_sleepable_lock_across_rcu, + struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) +{ + struct node_acquire *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 0; + + /* spin_{lock,unlock} are in different RCU CS */ + bpf_rcu_read_lock(); + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_rcu_read_unlock(); + + bpf_rcu_read_lock(); + bpf_spin_unlock(&glock); + bpf_rcu_read_unlock(); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/ringbuf_bench.c b/tools/testing/selftests/bpf/progs/ringbuf_bench.c new file mode 100644 index 0000000000..6a468496f5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/ringbuf_bench.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); +} ringbuf SEC(".maps"); + +const volatile int batch_cnt = 0; +const volatile long use_output = 0; + +long sample_val = 42; +long dropped __attribute__((aligned(128))) = 0; + +const volatile long wakeup_data_size = 0; + +static __always_inline long get_flags() +{ + long sz; + + if (!wakeup_data_size) + return 0; + + sz = bpf_ringbuf_query(&ringbuf, BPF_RB_AVAIL_DATA); + return sz >= wakeup_data_size ? BPF_RB_FORCE_WAKEUP : BPF_RB_NO_WAKEUP; +} + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int bench_ringbuf(void *ctx) +{ + long *sample, flags; + int i; + + if (!use_output) { + for (i = 0; i < batch_cnt; i++) { + sample = bpf_ringbuf_reserve(&ringbuf, + sizeof(sample_val), 0); + if (!sample) { + __sync_add_and_fetch(&dropped, 1); + } else { + *sample = sample_val; + flags = get_flags(); + bpf_ringbuf_submit(sample, flags); + } + } + } else { + for (i = 0; i < batch_cnt; i++) { + flags = get_flags(); + if (bpf_ringbuf_output(&ringbuf, &sample_val, + sizeof(sample_val), flags)) + __sync_add_and_fetch(&dropped, 1); + } + } + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/sample_map_ret0.c b/tools/testing/selftests/bpf/progs/sample_map_ret0.c new file mode 100644 index 0000000000..495990d355 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sample_map_ret0.c @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, long); + __uint(max_entries, 2); +} htab SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, long); + __uint(max_entries, 2); +} array SEC(".maps"); + +/* Sample program which should always load for testing control paths. */ +SEC(".text") int func() +{ + __u64 key64 = 0; + __u32 key = 0; + long *value; + + value = bpf_map_lookup_elem(&htab, &key); + if (!value) + return 1; + value = bpf_map_lookup_elem(&array, &key64); + if (!value) + return 1; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/sample_ret0.c b/tools/testing/selftests/bpf/progs/sample_ret0.c new file mode 100644 index 0000000000..fec99750d6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sample_ret0.c @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */ + +/* Sample program which should always load for testing control paths. */ +int func() +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c new file mode 100644 index 0000000000..351e79aef2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <sys/socket.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include <bpf_sockopt_helpers.h> + +#define SRC1_IP4 0xAC100001U /* 172.16.0.1 */ +#define SRC2_IP4 0x00000000U +#define SRC_REWRITE_IP4 0x7f000004U +#define DST_IP4 0xC0A801FEU /* 192.168.1.254 */ +#define DST_REWRITE_IP4 0x7f000001U +#define DST_PORT 4040 +#define DST_REWRITE_PORT4 4444 + +SEC("cgroup/sendmsg4") +int sendmsg_v4_prog(struct bpf_sock_addr *ctx) +{ + if (ctx->type != SOCK_DGRAM) + return 0; + + if (!get_set_sk_priority(ctx)) + return 0; + + /* Rewrite source. */ + if (ctx->msg_src_ip4 == bpf_htonl(SRC1_IP4) || + ctx->msg_src_ip4 == bpf_htonl(SRC2_IP4)) { + ctx->msg_src_ip4 = bpf_htonl(SRC_REWRITE_IP4); + } else { + /* Unexpected source. Reject sendmsg. */ + return 0; + } + + /* Rewrite destination. */ + if ((ctx->user_ip4 >> 24) == (bpf_htonl(DST_IP4) >> 24) && + ctx->user_port == bpf_htons(DST_PORT)) { + ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4); + ctx->user_port = bpf_htons(DST_REWRITE_PORT4); + } else { + /* Unexpected source. Reject sendmsg. */ + return 0; + } + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c new file mode 100644 index 0000000000..bf9b46b806 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <sys/socket.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include <bpf_sockopt_helpers.h> + +#define SRC_REWRITE_IP6_0 0 +#define SRC_REWRITE_IP6_1 0 +#define SRC_REWRITE_IP6_2 0 +#define SRC_REWRITE_IP6_3 6 + +#define DST_REWRITE_IP6_0 0 +#define DST_REWRITE_IP6_1 0 +#define DST_REWRITE_IP6_2 0 +#define DST_REWRITE_IP6_3 1 + +#define DST_REWRITE_PORT6 6666 + +SEC("cgroup/sendmsg6") +int sendmsg_v6_prog(struct bpf_sock_addr *ctx) +{ + if (ctx->type != SOCK_DGRAM) + return 0; + + if (!get_set_sk_priority(ctx)) + return 0; + + /* Rewrite source. */ + if (ctx->msg_src_ip6[3] == bpf_htonl(1) || + ctx->msg_src_ip6[3] == bpf_htonl(0)) { + ctx->msg_src_ip6[0] = bpf_htonl(SRC_REWRITE_IP6_0); + ctx->msg_src_ip6[1] = bpf_htonl(SRC_REWRITE_IP6_1); + ctx->msg_src_ip6[2] = bpf_htonl(SRC_REWRITE_IP6_2); + ctx->msg_src_ip6[3] = bpf_htonl(SRC_REWRITE_IP6_3); + } else { + /* Unexpected source. Reject sendmsg. */ + return 0; + } + + /* Rewrite destination. */ + if (ctx->user_ip6[0] == bpf_htonl(0xFACEB00C)) { + ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0); + ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_1); + ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2); + ctx->user_ip6[3] = bpf_htonl(DST_REWRITE_IP6_3); + + ctx->user_port = bpf_htons(DST_REWRITE_PORT6); + } else { + /* Unexpected destination. Reject sendmsg. */ + return 0; + } + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/setget_sockopt.c b/tools/testing/selftests/bpf/progs/setget_sockopt.c new file mode 100644 index 0000000000..7a438600ae --- /dev/null +++ b/tools/testing/selftests/bpf/progs/setget_sockopt.c @@ -0,0 +1,403 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +extern unsigned long CONFIG_HZ __kconfig; + +const volatile char veth[IFNAMSIZ]; +const volatile int veth_ifindex; + +int nr_listen; +int nr_passive; +int nr_active; +int nr_connect; +int nr_binddev; +int nr_socket_post_create; +int nr_fin_wait1; + +struct sockopt_test { + int opt; + int new; + int restore; + int expected; + int tcp_expected; + unsigned int flip:1; +}; + +static const char not_exist_cc[] = "not_exist"; +static const char cubic_cc[] = "cubic"; +static const char reno_cc[] = "reno"; + +static const struct sockopt_test sol_socket_tests[] = { + { .opt = SO_REUSEADDR, .flip = 1, }, + { .opt = SO_SNDBUF, .new = 8123, .expected = 8123 * 2, }, + { .opt = SO_RCVBUF, .new = 8123, .expected = 8123 * 2, }, + { .opt = SO_KEEPALIVE, .flip = 1, }, + { .opt = SO_PRIORITY, .new = 0xeb9f, .expected = 0xeb9f, }, + { .opt = SO_REUSEPORT, .flip = 1, }, + { .opt = SO_RCVLOWAT, .new = 8123, .expected = 8123, }, + { .opt = SO_MARK, .new = 0xeb9f, .expected = 0xeb9f, }, + { .opt = SO_MAX_PACING_RATE, .new = 0xeb9f, .expected = 0xeb9f, }, + { .opt = SO_TXREHASH, .flip = 1, }, + { .opt = 0, }, +}; + +static const struct sockopt_test sol_tcp_tests[] = { + { .opt = TCP_NODELAY, .flip = 1, }, + { .opt = TCP_KEEPIDLE, .new = 123, .expected = 123, .restore = 321, }, + { .opt = TCP_KEEPINTVL, .new = 123, .expected = 123, .restore = 321, }, + { .opt = TCP_KEEPCNT, .new = 123, .expected = 123, .restore = 124, }, + { .opt = TCP_SYNCNT, .new = 123, .expected = 123, .restore = 124, }, + { .opt = TCP_WINDOW_CLAMP, .new = 8123, .expected = 8123, .restore = 8124, }, + { .opt = TCP_CONGESTION, }, + { .opt = TCP_THIN_LINEAR_TIMEOUTS, .flip = 1, }, + { .opt = TCP_USER_TIMEOUT, .new = 123400, .expected = 123400, }, + { .opt = TCP_NOTSENT_LOWAT, .new = 1314, .expected = 1314, }, + { .opt = 0, }, +}; + +static const struct sockopt_test sol_ip_tests[] = { + { .opt = IP_TOS, .new = 0xe1, .expected = 0xe1, .tcp_expected = 0xe0, }, + { .opt = 0, }, +}; + +static const struct sockopt_test sol_ipv6_tests[] = { + { .opt = IPV6_TCLASS, .new = 0xe1, .expected = 0xe1, .tcp_expected = 0xe0, }, + { .opt = IPV6_AUTOFLOWLABEL, .flip = 1, }, + { .opt = 0, }, +}; + +struct loop_ctx { + void *ctx; + struct sock *sk; +}; + +static int bpf_test_sockopt_flip(void *ctx, struct sock *sk, + const struct sockopt_test *t, + int level) +{ + int old, tmp, new, opt = t->opt; + + opt = t->opt; + + if (bpf_getsockopt(ctx, level, opt, &old, sizeof(old))) + return 1; + /* kernel initialized txrehash to 255 */ + if (level == SOL_SOCKET && opt == SO_TXREHASH && old != 0 && old != 1) + old = 1; + + new = !old; + if (bpf_setsockopt(ctx, level, opt, &new, sizeof(new))) + return 1; + if (bpf_getsockopt(ctx, level, opt, &tmp, sizeof(tmp)) || + tmp != new) + return 1; + + if (bpf_setsockopt(ctx, level, opt, &old, sizeof(old))) + return 1; + + return 0; +} + +static int bpf_test_sockopt_int(void *ctx, struct sock *sk, + const struct sockopt_test *t, + int level) +{ + int old, tmp, new, expected, opt; + + opt = t->opt; + new = t->new; + if (sk->sk_type == SOCK_STREAM && t->tcp_expected) + expected = t->tcp_expected; + else + expected = t->expected; + + if (bpf_getsockopt(ctx, level, opt, &old, sizeof(old)) || + old == new) + return 1; + + if (bpf_setsockopt(ctx, level, opt, &new, sizeof(new))) + return 1; + if (bpf_getsockopt(ctx, level, opt, &tmp, sizeof(tmp)) || + tmp != expected) + return 1; + + if (t->restore) + old = t->restore; + if (bpf_setsockopt(ctx, level, opt, &old, sizeof(old))) + return 1; + + return 0; +} + +static int bpf_test_socket_sockopt(__u32 i, struct loop_ctx *lc) +{ + const struct sockopt_test *t; + + if (i >= ARRAY_SIZE(sol_socket_tests)) + return 1; + + t = &sol_socket_tests[i]; + if (!t->opt) + return 1; + + if (t->flip) + return bpf_test_sockopt_flip(lc->ctx, lc->sk, t, SOL_SOCKET); + + return bpf_test_sockopt_int(lc->ctx, lc->sk, t, SOL_SOCKET); +} + +static int bpf_test_ip_sockopt(__u32 i, struct loop_ctx *lc) +{ + const struct sockopt_test *t; + + if (i >= ARRAY_SIZE(sol_ip_tests)) + return 1; + + t = &sol_ip_tests[i]; + if (!t->opt) + return 1; + + if (t->flip) + return bpf_test_sockopt_flip(lc->ctx, lc->sk, t, IPPROTO_IP); + + return bpf_test_sockopt_int(lc->ctx, lc->sk, t, IPPROTO_IP); +} + +static int bpf_test_ipv6_sockopt(__u32 i, struct loop_ctx *lc) +{ + const struct sockopt_test *t; + + if (i >= ARRAY_SIZE(sol_ipv6_tests)) + return 1; + + t = &sol_ipv6_tests[i]; + if (!t->opt) + return 1; + + if (t->flip) + return bpf_test_sockopt_flip(lc->ctx, lc->sk, t, IPPROTO_IPV6); + + return bpf_test_sockopt_int(lc->ctx, lc->sk, t, IPPROTO_IPV6); +} + +static int bpf_test_tcp_sockopt(__u32 i, struct loop_ctx *lc) +{ + const struct sockopt_test *t; + struct sock *sk; + void *ctx; + + if (i >= ARRAY_SIZE(sol_tcp_tests)) + return 1; + + t = &sol_tcp_tests[i]; + if (!t->opt) + return 1; + + ctx = lc->ctx; + sk = lc->sk; + + if (t->opt == TCP_CONGESTION) { + char old_cc[16], tmp_cc[16]; + const char *new_cc; + int new_cc_len; + + if (!bpf_setsockopt(ctx, IPPROTO_TCP, TCP_CONGESTION, + (void *)not_exist_cc, sizeof(not_exist_cc))) + return 1; + if (bpf_getsockopt(ctx, IPPROTO_TCP, TCP_CONGESTION, old_cc, sizeof(old_cc))) + return 1; + if (!bpf_strncmp(old_cc, sizeof(old_cc), cubic_cc)) { + new_cc = reno_cc; + new_cc_len = sizeof(reno_cc); + } else { + new_cc = cubic_cc; + new_cc_len = sizeof(cubic_cc); + } + if (bpf_setsockopt(ctx, IPPROTO_TCP, TCP_CONGESTION, (void *)new_cc, + new_cc_len)) + return 1; + if (bpf_getsockopt(ctx, IPPROTO_TCP, TCP_CONGESTION, tmp_cc, sizeof(tmp_cc))) + return 1; + if (bpf_strncmp(tmp_cc, sizeof(tmp_cc), new_cc)) + return 1; + if (bpf_setsockopt(ctx, IPPROTO_TCP, TCP_CONGESTION, old_cc, sizeof(old_cc))) + return 1; + return 0; + } + + if (t->flip) + return bpf_test_sockopt_flip(ctx, sk, t, IPPROTO_TCP); + + return bpf_test_sockopt_int(ctx, sk, t, IPPROTO_TCP); +} + +static int bpf_test_sockopt(void *ctx, struct sock *sk) +{ + struct loop_ctx lc = { .ctx = ctx, .sk = sk, }; + __u16 family, proto; + int n; + + family = sk->sk_family; + proto = sk->sk_protocol; + + n = bpf_loop(ARRAY_SIZE(sol_socket_tests), bpf_test_socket_sockopt, &lc, 0); + if (n != ARRAY_SIZE(sol_socket_tests)) + return -1; + + if (proto == IPPROTO_TCP) { + n = bpf_loop(ARRAY_SIZE(sol_tcp_tests), bpf_test_tcp_sockopt, &lc, 0); + if (n != ARRAY_SIZE(sol_tcp_tests)) + return -1; + } + + if (family == AF_INET) { + n = bpf_loop(ARRAY_SIZE(sol_ip_tests), bpf_test_ip_sockopt, &lc, 0); + if (n != ARRAY_SIZE(sol_ip_tests)) + return -1; + } else { + n = bpf_loop(ARRAY_SIZE(sol_ipv6_tests), bpf_test_ipv6_sockopt, &lc, 0); + if (n != ARRAY_SIZE(sol_ipv6_tests)) + return -1; + } + + return 0; +} + +static int binddev_test(void *ctx) +{ + const char empty_ifname[] = ""; + int ifindex, zero = 0; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + (void *)veth, sizeof(veth))) + return -1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &ifindex, sizeof(int)) || + ifindex != veth_ifindex) + return -1; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + (void *)empty_ifname, sizeof(empty_ifname))) + return -1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &ifindex, sizeof(int)) || + ifindex != 0) + return -1; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + (void *)&veth_ifindex, sizeof(int))) + return -1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &ifindex, sizeof(int)) || + ifindex != veth_ifindex) + return -1; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &zero, sizeof(int))) + return -1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &ifindex, sizeof(int)) || + ifindex != 0) + return -1; + + return 0; +} + +static int test_tcp_maxseg(void *ctx, struct sock *sk) +{ + int val = 1314, tmp; + + if (sk->sk_state != TCP_ESTABLISHED) + return bpf_setsockopt(ctx, IPPROTO_TCP, TCP_MAXSEG, + &val, sizeof(val)); + + if (bpf_getsockopt(ctx, IPPROTO_TCP, TCP_MAXSEG, &tmp, sizeof(tmp)) || + tmp > val) + return -1; + + return 0; +} + +static int test_tcp_saved_syn(void *ctx, struct sock *sk) +{ + __u8 saved_syn[20]; + int one = 1; + + if (sk->sk_state == TCP_LISTEN) + return bpf_setsockopt(ctx, IPPROTO_TCP, TCP_SAVE_SYN, + &one, sizeof(one)); + + return bpf_getsockopt(ctx, IPPROTO_TCP, TCP_SAVED_SYN, + saved_syn, sizeof(saved_syn)); +} + +SEC("lsm_cgroup/socket_post_create") +int BPF_PROG(socket_post_create, struct socket *sock, int family, + int type, int protocol, int kern) +{ + struct sock *sk = sock->sk; + + if (!sk) + return 1; + + nr_socket_post_create += !bpf_test_sockopt(sk, sk); + nr_binddev += !binddev_test(sk); + + return 1; +} + +SEC("sockops") +int skops_sockopt(struct bpf_sock_ops *skops) +{ + struct bpf_sock *bpf_sk = skops->sk; + struct sock *sk; + + if (!bpf_sk) + return 1; + + sk = (struct sock *)bpf_skc_to_tcp_sock(bpf_sk); + if (!sk) + return 1; + + switch (skops->op) { + case BPF_SOCK_OPS_TCP_LISTEN_CB: + nr_listen += !(bpf_test_sockopt(skops, sk) || + test_tcp_maxseg(skops, sk) || + test_tcp_saved_syn(skops, sk)); + break; + case BPF_SOCK_OPS_TCP_CONNECT_CB: + nr_connect += !(bpf_test_sockopt(skops, sk) || + test_tcp_maxseg(skops, sk)); + break; + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + nr_active += !(bpf_test_sockopt(skops, sk) || + test_tcp_maxseg(skops, sk)); + break; + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + nr_passive += !(bpf_test_sockopt(skops, sk) || + test_tcp_maxseg(skops, sk) || + test_tcp_saved_syn(skops, sk)); + bpf_sock_ops_cb_flags_set(skops, + skops->bpf_sock_ops_cb_flags | + BPF_SOCK_OPS_STATE_CB_FLAG); + break; + case BPF_SOCK_OPS_STATE_CB: + if (skops->args[1] == BPF_TCP_CLOSE_WAIT) + nr_fin_wait1 += !bpf_test_sockopt(skops, sk); + break; + } + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c b/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c new file mode 100644 index 0000000000..3e745793b2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Facebook */ +#include "vmlinux.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +void *local_storage_ptr = NULL; +void *sk_ptr = NULL; +int cookie_found = 0; +__u64 cookie = 0; +__u32 omem = 0; + +void *bpf_rdonly_cast(void *, __u32) __ksym; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} sk_storage SEC(".maps"); + +SEC("fexit/bpf_local_storage_destroy") +int BPF_PROG(bpf_local_storage_destroy, struct bpf_local_storage *local_storage) +{ + struct sock *sk; + + if (local_storage_ptr != local_storage) + return 0; + + sk = bpf_rdonly_cast(sk_ptr, bpf_core_type_id_kernel(struct sock)); + if (sk->sk_cookie.counter != cookie) + return 0; + + cookie_found++; + omem = sk->sk_omem_alloc.counter; + local_storage_ptr = NULL; + + return 0; +} + +SEC("fentry/inet6_sock_destruct") +int BPF_PROG(inet6_sock_destruct, struct sock *sk) +{ + int *value; + + if (!cookie || sk->sk_cookie.counter != cookie) + return 0; + + value = bpf_sk_storage_get(&sk_storage, sk, 0, 0); + if (value && *value == 0xdeadbeef) { + cookie_found++; + sk_ptr = sk; + local_storage_ptr = sk->sk_bpf_storage; + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/skb_load_bytes.c b/tools/testing/selftests/bpf/progs/skb_load_bytes.c new file mode 100644 index 0000000000..e4252fd973 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/skb_load_bytes.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +__u32 load_offset = 0; +int test_result = 0; + +SEC("tc") +int skb_process(struct __sk_buff *skb) +{ + char buf[16]; + + test_result = bpf_skb_load_bytes(skb, load_offset, buf, 10); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/skb_pkt_end.c b/tools/testing/selftests/bpf/progs/skb_pkt_end.c new file mode 100644 index 0000000000..992b786100 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/skb_pkt_end.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +#define BPF_NO_PRESERVE_ACCESS_INDEX +#include <vmlinux.h> +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_helpers.h> + +#define INLINE __always_inline + +#define skb_shorter(skb, len) ((void *)(long)(skb)->data + (len) > (void *)(long)skb->data_end) + +#define ETH_IPV4_TCP_SIZE (14 + sizeof(struct iphdr) + sizeof(struct tcphdr)) + +static INLINE struct iphdr *get_iphdr(struct __sk_buff *skb) +{ + struct iphdr *ip = NULL; + struct ethhdr *eth; + + if (skb_shorter(skb, ETH_IPV4_TCP_SIZE)) + goto out; + + eth = (void *)(long)skb->data; + ip = (void *)(eth + 1); + +out: + return ip; +} + +SEC("tc") +int main_prog(struct __sk_buff *skb) +{ + struct iphdr *ip = NULL; + struct tcphdr *tcp; + __u8 proto = 0; + + if (!(ip = get_iphdr(skb))) + goto out; + + proto = ip->protocol; + + if (proto != IPPROTO_TCP) + goto out; + + tcp = (void*)(ip + 1); + if (tcp->dest != 0) + goto out; + if (!tcp) + goto out; + + return tcp->urg_ptr; +out: + return -1; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c new file mode 100644 index 0000000000..9e0bf7a54c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include "bpf_tracing_net.h" + +__be16 serv_port = 0; + +int bpf_sock_destroy(struct sock_common *sk) __ksym; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} tcp_conn_sockets SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} udp_conn_sockets SEC(".maps"); + +SEC("cgroup/connect6") +int sock_connect(struct bpf_sock_addr *ctx) +{ + __u64 sock_cookie = 0; + int key = 0; + __u32 keyc = 0; + + if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6) + return 1; + + sock_cookie = bpf_get_socket_cookie(ctx); + if (ctx->protocol == IPPROTO_TCP) + bpf_map_update_elem(&tcp_conn_sockets, &key, &sock_cookie, 0); + else if (ctx->protocol == IPPROTO_UDP) + bpf_map_update_elem(&udp_conn_sockets, &keyc, &sock_cookie, 0); + else + return 1; + + return 1; +} + +SEC("iter/tcp") +int iter_tcp6_client(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + __u64 sock_cookie = 0; + __u64 *val; + int key = 0; + + if (!sk_common) + return 0; + + if (sk_common->skc_family != AF_INET6) + return 0; + + sock_cookie = bpf_get_socket_cookie(sk_common); + val = bpf_map_lookup_elem(&tcp_conn_sockets, &key); + if (!val) + return 0; + /* Destroy connected client sockets. */ + if (sock_cookie == *val) + bpf_sock_destroy(sk_common); + + return 0; +} + +SEC("iter/tcp") +int iter_tcp6_server(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + const struct inet_connection_sock *icsk; + const struct inet_sock *inet; + struct tcp6_sock *tcp_sk; + __be16 srcp; + + if (!sk_common) + return 0; + + if (sk_common->skc_family != AF_INET6) + return 0; + + tcp_sk = bpf_skc_to_tcp6_sock(sk_common); + if (!tcp_sk) + return 0; + + icsk = &tcp_sk->tcp.inet_conn; + inet = &icsk->icsk_inet; + srcp = inet->inet_sport; + + /* Destroy server sockets. */ + if (srcp == serv_port) + bpf_sock_destroy(sk_common); + + return 0; +} + + +SEC("iter/udp") +int iter_udp6_client(struct bpf_iter__udp *ctx) +{ + struct udp_sock *udp_sk = ctx->udp_sk; + struct sock *sk = (struct sock *) udp_sk; + __u64 sock_cookie = 0, *val; + int key = 0; + + if (!sk) + return 0; + + sock_cookie = bpf_get_socket_cookie(sk); + val = bpf_map_lookup_elem(&udp_conn_sockets, &key); + if (!val) + return 0; + /* Destroy connected client sockets. */ + if (sock_cookie == *val) + bpf_sock_destroy((struct sock_common *)sk); + + return 0; +} + +SEC("iter/udp") +int iter_udp6_server(struct bpf_iter__udp *ctx) +{ + struct udp_sock *udp_sk = ctx->udp_sk; + struct sock *sk = (struct sock *) udp_sk; + struct inet_sock *inet; + __be16 srcp; + + if (!sk) + return 0; + + inet = &udp_sk->inet; + srcp = inet->inet_sport; + if (srcp == serv_port) + bpf_sock_destroy((struct sock_common *)sk); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c new file mode 100644 index 0000000000..dd6850b58e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +int bpf_sock_destroy(struct sock_common *sk) __ksym; + +SEC("tp_btf/tcp_destroy_sock") +__failure __msg("calling kernel function bpf_sock_destroy is not allowed") +int BPF_PROG(trace_tcp_destroy_sock, struct sock *sk) +{ + /* should not load */ + bpf_sock_destroy((struct sock_common *)sk); + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c new file mode 100644 index 0000000000..35630a5aaf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_tracing.h> + +#define AF_INET6 10 + +struct socket_cookie { + __u64 cookie_key; + __u32 cookie_value; +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct socket_cookie); +} socket_cookies SEC(".maps"); + +/* + * These three programs get executed in a row on connect() syscalls. The + * userspace side of the test creates a client socket, issues a connect() on it + * and then checks that the local storage associated with this socket has: + * cookie_value == local_port << 8 | 0xFF + * The different parts of this cookie_value are appended by those hooks if they + * all agree on the output of bpf_get_socket_cookie(). + */ +SEC("cgroup/connect6") +int set_cookie(struct bpf_sock_addr *ctx) +{ + struct socket_cookie *p; + + if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6) + return 1; + + p = bpf_sk_storage_get(&socket_cookies, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!p) + return 1; + + p->cookie_value = 0xF; + p->cookie_key = bpf_get_socket_cookie(ctx); + + return 1; +} + +SEC("sockops") +int update_cookie_sockops(struct bpf_sock_ops *ctx) +{ + struct bpf_sock *sk = ctx->sk; + struct socket_cookie *p; + + if (ctx->family != AF_INET6) + return 1; + + if (ctx->op != BPF_SOCK_OPS_TCP_CONNECT_CB) + return 1; + + if (!sk) + return 1; + + p = bpf_sk_storage_get(&socket_cookies, sk, 0, 0); + if (!p) + return 1; + + if (p->cookie_key != bpf_get_socket_cookie(ctx)) + return 1; + + p->cookie_value |= (ctx->local_port << 8); + + return 1; +} + +SEC("fexit/inet_stream_connect") +int BPF_PROG(update_cookie_tracing, struct socket *sock, + struct sockaddr *uaddr, int addr_len, int flags) +{ + struct socket_cookie *p; + + if (uaddr->sa_family != AF_INET6) + return 0; + + p = bpf_sk_storage_get(&socket_cookies, sock->sk, 0, 0); + if (!p) + return 0; + + if (p->cookie_key != bpf_get_socket_cookie(sock->sk)) + return 0; + + p->cookie_value |= 0xF0; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c new file mode 100644 index 0000000000..c9abfe3a11 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c @@ -0,0 +1,33 @@ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +SEC("sk_skb1") +int bpf_prog1(struct __sk_buff *skb) +{ + void *data_end = (void *)(long) skb->data_end; + void *data = (void *)(long) skb->data; + __u8 *d = data; + int err; + + if (data + 10 > data_end) { + err = bpf_skb_pull_data(skb, 10); + if (err) + return SK_DROP; + + data_end = (void *)(long)skb->data_end; + data = (void *)(long)skb->data; + if (data + 10 > data_end) + return SK_DROP; + } + + /* This write/read is a bit pointless but tests the verifier and + * strparser handler for read/write pkt data and access into sk + * fields. + */ + d = data; + d[7] = 1; + return skb->len; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c new file mode 100644 index 0000000000..80632954c5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c @@ -0,0 +1,12 @@ +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +SEC("sk_msg1") +int bpf_prog1(struct sk_msg_md *msg) +{ + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c new file mode 100644 index 0000000000..0660f29dca --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c @@ -0,0 +1,67 @@ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_tx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_msg SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_break SEC(".maps"); + +SEC("sk_skb2") +int bpf_prog2(struct __sk_buff *skb) +{ + void *data_end = (void *)(long) skb->data_end; + void *data = (void *)(long) skb->data; + __u32 lport = skb->local_port; + __u32 rport = skb->remote_port; + __u8 *d = data; + __u8 sk, map; + + __sink(lport); + __sink(rport); + + if (data + 8 > data_end) + return SK_DROP; + + map = d[0]; + sk = d[1]; + + d[0] = 0xd; + d[1] = 0xe; + d[2] = 0xa; + d[3] = 0xd; + d[4] = 0xb; + d[5] = 0xe; + d[6] = 0xe; + d[7] = 0xf; + + if (!map) + return bpf_sk_redirect_map(skb, &sock_map_rx, sk, 0); + return bpf_sk_redirect_map(skb, &sock_map_tx, sk, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c new file mode 100644 index 0000000000..c8f59caa46 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +#define SOL_CUSTOM 0xdeadbeef +#define CUSTOM_INHERIT1 0 +#define CUSTOM_INHERIT2 1 +#define CUSTOM_LISTENER 2 + +__u32 page_size = 0; + +struct sockopt_inherit { + __u8 val; +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC | BPF_F_CLONE); + __type(key, int); + __type(value, struct sockopt_inherit); +} cloned1_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC | BPF_F_CLONE); + __type(key, int); + __type(value, struct sockopt_inherit); +} cloned2_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct sockopt_inherit); +} listener_only_map SEC(".maps"); + +static __inline struct sockopt_inherit *get_storage(struct bpf_sockopt *ctx) +{ + if (ctx->optname == CUSTOM_INHERIT1) + return bpf_sk_storage_get(&cloned1_map, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + else if (ctx->optname == CUSTOM_INHERIT2) + return bpf_sk_storage_get(&cloned2_map, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + else + return bpf_sk_storage_get(&listener_only_map, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); +} + +SEC("cgroup/getsockopt") +int _getsockopt(struct bpf_sockopt *ctx) +{ + __u8 *optval_end = ctx->optval_end; + struct sockopt_inherit *storage; + __u8 *optval = ctx->optval; + + if (ctx->level != SOL_CUSTOM) + goto out; /* only interested in SOL_CUSTOM */ + + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + storage = get_storage(ctx); + if (!storage) + return 0; /* EPERM, couldn't get sk storage */ + + ctx->retval = 0; /* Reset system call return value to zero */ + + optval[0] = storage->val; + ctx->optlen = 1; + + return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; +} + +SEC("cgroup/setsockopt") +int _setsockopt(struct bpf_sockopt *ctx) +{ + __u8 *optval_end = ctx->optval_end; + struct sockopt_inherit *storage; + __u8 *optval = ctx->optval; + + if (ctx->level != SOL_CUSTOM) + goto out; /* only interested in SOL_CUSTOM */ + + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + storage = get_storage(ctx); + if (!storage) + return 0; /* EPERM, couldn't get sk storage */ + + storage->val = optval[0]; + ctx->optlen = -1; + + return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c new file mode 100644 index 0000000000..96f29fce05 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <netinet/in.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +__u32 page_size = 0; + +SEC("cgroup/getsockopt") +int _getsockopt_child(struct bpf_sockopt *ctx) +{ + __u8 *optval_end = ctx->optval_end; + __u8 *optval = ctx->optval; + + if (ctx->level != SOL_IP || ctx->optname != IP_TOS) + goto out; + + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + if (optval[0] != 0x80) + return 0; /* EPERM, unexpected optval from the kernel */ + + ctx->retval = 0; /* Reset system call return value to zero */ + + optval[0] = 0x90; + ctx->optlen = 1; + + return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; +} + +SEC("cgroup/getsockopt") +int _getsockopt_parent(struct bpf_sockopt *ctx) +{ + __u8 *optval_end = ctx->optval_end; + __u8 *optval = ctx->optval; + + if (ctx->level != SOL_IP || ctx->optname != IP_TOS) + goto out; + + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + if (optval[0] != 0x90) + return 0; /* EPERM, unexpected optval from the kernel */ + + ctx->retval = 0; /* Reset system call return value to zero */ + + optval[0] = 0xA0; + ctx->optlen = 1; + + return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; +} + +SEC("cgroup/setsockopt") +int _setsockopt(struct bpf_sockopt *ctx) +{ + __u8 *optval_end = ctx->optval_end; + __u8 *optval = ctx->optval; + + if (ctx->level != SOL_IP || ctx->optname != IP_TOS) + goto out; + + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + optval[0] += 0x10; + ctx->optlen = 1; + + return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c new file mode 100644 index 0000000000..dbe235ede7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <string.h> +#include <linux/tcp.h> +#include <netinet/in.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; + +__u32 page_size = 0; + +SEC("cgroup/setsockopt") +int sockopt_qos_to_cc(struct bpf_sockopt *ctx) +{ + void *optval_end = ctx->optval_end; + int *optval = ctx->optval; + char buf[TCP_CA_NAME_MAX]; + char cc_reno[TCP_CA_NAME_MAX] = "reno"; + char cc_cubic[TCP_CA_NAME_MAX] = "cubic"; + + if (ctx->level != SOL_IPV6 || ctx->optname != IPV6_TCLASS) + goto out; + + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + if (bpf_getsockopt(ctx->sk, SOL_TCP, TCP_CONGESTION, &buf, sizeof(buf))) + return 0; + + if (!tcp_cc_eq(buf, cc_cubic)) + return 0; + + if (*optval == 0x2d) { + if (bpf_setsockopt(ctx->sk, SOL_TCP, TCP_CONGESTION, &cc_reno, + sizeof(cc_reno))) + return 0; + } + return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c new file mode 100644 index 0000000000..cb990a7d3d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -0,0 +1,238 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include <linux/tcp.h> +#include <linux/bpf.h> +#include <netinet/in.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +int page_size = 0; /* userspace should set it */ + +#ifndef SOL_TCP +#define SOL_TCP IPPROTO_TCP +#endif + +#define SOL_CUSTOM 0xdeadbeef + +struct sockopt_sk { + __u8 val; +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct sockopt_sk); +} socket_storage_map SEC(".maps"); + +SEC("cgroup/getsockopt") +int _getsockopt(struct bpf_sockopt *ctx) +{ + __u8 *optval_end = ctx->optval_end; + __u8 *optval = ctx->optval; + struct sockopt_sk *storage; + struct bpf_sock *sk; + + /* Bypass AF_NETLINK. */ + sk = ctx->sk; + if (sk && sk->family == AF_NETLINK) + goto out; + + /* Make sure bpf_get_netns_cookie is callable. + */ + if (bpf_get_netns_cookie(NULL) == 0) + return 0; + + if (bpf_get_netns_cookie(ctx) == 0) + return 0; + + if (ctx->level == SOL_IP && ctx->optname == IP_TOS) { + /* Not interested in SOL_IP:IP_TOS; + * let next BPF program in the cgroup chain or kernel + * handle it. + */ + goto out; + } + + if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) { + /* Not interested in SOL_SOCKET:SO_SNDBUF; + * let next BPF program in the cgroup chain or kernel + * handle it. + */ + goto out; + } + + if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) { + /* Not interested in SOL_TCP:TCP_CONGESTION; + * let next BPF program in the cgroup chain or kernel + * handle it. + */ + goto out; + } + + if (ctx->level == SOL_TCP && ctx->optname == TCP_ZEROCOPY_RECEIVE) { + /* Verify that TCP_ZEROCOPY_RECEIVE triggers. + * It has a custom implementation for performance + * reasons. + */ + + /* Check that optval contains address (__u64) */ + if (optval + sizeof(__u64) > optval_end) + return 0; /* bounds check */ + + if (((struct tcp_zerocopy_receive *)optval)->address != 0) + return 0; /* unexpected data */ + + goto out; + } + + if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { + if (optval + 1 > optval_end) + return 0; /* bounds check */ + + ctx->retval = 0; /* Reset system call return value to zero */ + + /* Always export 0x55 */ + optval[0] = 0x55; + ctx->optlen = 1; + + /* Userspace buffer is PAGE_SIZE * 2, but BPF + * program can only see the first PAGE_SIZE + * bytes of data. + */ + if (optval_end - optval != page_size) + return 0; /* unexpected data size */ + + return 1; + } + + if (ctx->level != SOL_CUSTOM) + return 0; /* deny everything except custom level */ + + if (optval + 1 > optval_end) + return 0; /* bounds check */ + + storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!storage) + return 0; /* couldn't get sk storage */ + + if (!ctx->retval) + return 0; /* kernel should not have handled + * SOL_CUSTOM, something is wrong! + */ + ctx->retval = 0; /* Reset system call return value to zero */ + + optval[0] = storage->val; + ctx->optlen = 1; + + return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; +} + +SEC("cgroup/setsockopt") +int _setsockopt(struct bpf_sockopt *ctx) +{ + __u8 *optval_end = ctx->optval_end; + __u8 *optval = ctx->optval; + struct sockopt_sk *storage; + struct bpf_sock *sk; + + /* Bypass AF_NETLINK. */ + sk = ctx->sk; + if (sk && sk->family == AF_NETLINK) + goto out; + + /* Make sure bpf_get_netns_cookie is callable. + */ + if (bpf_get_netns_cookie(NULL) == 0) + return 0; + + if (bpf_get_netns_cookie(ctx) == 0) + return 0; + + if (ctx->level == SOL_IP && ctx->optname == IP_TOS) { + /* Not interested in SOL_IP:IP_TOS; + * let next BPF program in the cgroup chain or kernel + * handle it. + */ + ctx->optlen = 0; /* bypass optval>PAGE_SIZE */ + return 1; + } + + if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) { + /* Overwrite SO_SNDBUF value */ + + if (optval + sizeof(__u32) > optval_end) + return 0; /* bounds check */ + + *(__u32 *)optval = 0x55AA; + ctx->optlen = 4; + + return 1; + } + + if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) { + /* Always use cubic */ + + if (optval + 5 > optval_end) + return 0; /* bounds check */ + + memcpy(optval, "cubic", 5); + ctx->optlen = 5; + + return 1; + } + + if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { + /* Original optlen is larger than PAGE_SIZE. */ + if (ctx->optlen != page_size * 2) + return 0; /* unexpected data size */ + + if (optval + 1 > optval_end) + return 0; /* bounds check */ + + /* Make sure we can trim the buffer. */ + optval[0] = 0; + ctx->optlen = 1; + + /* Usepace buffer is PAGE_SIZE * 2, but BPF + * program can only see the first PAGE_SIZE + * bytes of data. + */ + if (optval_end - optval != page_size) + return 0; /* unexpected data size */ + + return 1; + } + + if (ctx->level != SOL_CUSTOM) + return 0; /* deny everything except custom level */ + + if (optval + 1 > optval_end) + return 0; /* bounds check */ + + storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!storage) + return 0; /* couldn't get sk storage */ + + storage->val = optval[0]; + ctx->optlen = -1; /* BPF has consumed this option, don't call kernel + * setsockopt handler. + */ + + return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/stacktrace_map_skip.c b/tools/testing/selftests/bpf/progs/stacktrace_map_skip.c new file mode 100644 index 0000000000..2eb297df3d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/stacktrace_map_skip.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +#define TEST_STACK_DEPTH 2 +#define TEST_MAX_ENTRIES 16384 + +typedef __u64 stack_trace_t[TEST_STACK_DEPTH]; + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, TEST_MAX_ENTRIES); + __type(key, __u32); + __type(value, stack_trace_t); +} stackmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, TEST_MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} stackid_hmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, TEST_MAX_ENTRIES); + __type(key, __u32); + __type(value, stack_trace_t); +} stack_amap SEC(".maps"); + +int pid = 0; +int control = 0; +int failed = 0; + +SEC("tracepoint/sched/sched_switch") +int oncpu(struct trace_event_raw_sched_switch *ctx) +{ + __u32 max_len = TEST_STACK_DEPTH * sizeof(__u64); + __u32 key = 0, val = 0; + __u64 *stack_p; + + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + if (control) + return 0; + + /* it should allow skipping whole buffer size entries */ + key = bpf_get_stackid(ctx, &stackmap, TEST_STACK_DEPTH); + if ((int)key >= 0) { + /* The size of stackmap and stack_amap should be the same */ + bpf_map_update_elem(&stackid_hmap, &key, &val, 0); + stack_p = bpf_map_lookup_elem(&stack_amap, &key); + if (stack_p) { + bpf_get_stack(ctx, stack_p, max_len, TEST_STACK_DEPTH); + /* it wrongly skipped all the entries and filled zero */ + if (stack_p[0] == 0) + failed = 1; + } + } else { + /* old kernel doesn't support skipping that many entries */ + failed = 2; + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/strncmp_bench.c b/tools/testing/selftests/bpf/progs/strncmp_bench.c new file mode 100644 index 0000000000..18373a7df7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strncmp_bench.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2021. Huawei Technologies Co., Ltd */ +#include <linux/types.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define STRNCMP_STR_SZ 4096 + +/* Will be updated by benchmark before program loading */ +const volatile unsigned int cmp_str_len = 1; +const char target[STRNCMP_STR_SZ]; + +long hits = 0; +char str[STRNCMP_STR_SZ]; + +char _license[] SEC("license") = "GPL"; + +static __always_inline int local_strncmp(const char *s1, unsigned int sz, + const char *s2) +{ + int ret = 0; + unsigned int i; + + for (i = 0; i < sz; i++) { + /* E.g. 0xff > 0x31 */ + ret = (unsigned char)s1[i] - (unsigned char)s2[i]; + if (ret || !s1[i]) + break; + } + + return ret; +} + +SEC("tp/syscalls/sys_enter_getpgid") +int strncmp_no_helper(void *ctx) +{ + if (local_strncmp(str, cmp_str_len + 1, target) < 0) + __sync_add_and_fetch(&hits, 1); + return 0; +} + +SEC("tp/syscalls/sys_enter_getpgid") +int strncmp_helper(void *ctx) +{ + if (bpf_strncmp(str, cmp_str_len + 1, target) < 0) + __sync_add_and_fetch(&hits, 1); + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/strncmp_test.c b/tools/testing/selftests/bpf/progs/strncmp_test.c new file mode 100644 index 0000000000..769668feed --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strncmp_test.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2021. Huawei Technologies Co., Ltd */ +#include <stdbool.h> +#include <linux/types.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define STRNCMP_STR_SZ 8 + +const char target[STRNCMP_STR_SZ] = "EEEEEEE"; +char str[STRNCMP_STR_SZ]; +int cmp_ret = 0; +int target_pid = 0; + +const char no_str_target[STRNCMP_STR_SZ] = "12345678"; +char writable_target[STRNCMP_STR_SZ]; +unsigned int no_const_str_size = STRNCMP_STR_SZ; + +char _license[] SEC("license") = "GPL"; + +SEC("?tp/syscalls/sys_enter_nanosleep") +int do_strncmp(void *ctx) +{ + if ((bpf_get_current_pid_tgid() >> 32) != target_pid) + return 0; + + cmp_ret = bpf_strncmp(str, STRNCMP_STR_SZ, target); + return 0; +} + +SEC("?tp/syscalls/sys_enter_nanosleep") +int strncmp_bad_not_const_str_size(void *ctx) +{ + /* The value of string size is not const, so will fail */ + cmp_ret = bpf_strncmp(str, no_const_str_size, target); + return 0; +} + +SEC("?tp/syscalls/sys_enter_nanosleep") +int strncmp_bad_writable_target(void *ctx) +{ + /* Compared target is not read-only, so will fail */ + cmp_ret = bpf_strncmp(str, STRNCMP_STR_SZ, writable_target); + return 0; +} + +SEC("?tp/syscalls/sys_enter_nanosleep") +int strncmp_bad_not_null_term_target(void *ctx) +{ + /* Compared target is not null-terminated, so will fail */ + cmp_ret = bpf_strncmp(str, STRNCMP_STR_SZ, no_str_target); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/strobemeta.c b/tools/testing/selftests/bpf/progs/strobemeta.c new file mode 100644 index 0000000000..d3df3d86f0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook + +#define STROBE_MAX_INTS 2 +#define STROBE_MAX_STRS 25 +#define STROBE_MAX_MAPS 100 +#define STROBE_MAX_MAP_ENTRIES 20 +/* full unroll by llvm #undef NO_UNROLL */ +#include "strobemeta.h" + diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h new file mode 100644 index 0000000000..40df2cc26e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta.h @@ -0,0 +1,633 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <stdint.h> +#include <stddef.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include <linux/ptrace.h> +#include <linux/sched.h> +#include <linux/types.h> +#include <bpf/bpf_helpers.h> + +typedef uint32_t pid_t; +struct task_struct {}; + +#define TASK_COMM_LEN 16 +#define PERF_MAX_STACK_DEPTH 127 + +#define STROBE_TYPE_INVALID 0 +#define STROBE_TYPE_INT 1 +#define STROBE_TYPE_STR 2 +#define STROBE_TYPE_MAP 3 + +#define STACK_TABLE_EPOCH_SHIFT 20 +#define STROBE_MAX_STR_LEN 1 +#define STROBE_MAX_CFGS 32 +#define READ_MAP_VAR_PAYLOAD_CAP \ + ((1 + STROBE_MAX_MAP_ENTRIES * 2) * STROBE_MAX_STR_LEN) +#define STROBE_MAX_PAYLOAD \ + (STROBE_MAX_STRS * STROBE_MAX_STR_LEN + \ + STROBE_MAX_MAPS * READ_MAP_VAR_PAYLOAD_CAP) + +struct strobe_value_header { + /* + * meaning depends on type: + * 1. int: 0, if value not set, 1 otherwise + * 2. str: 1 always, whether value is set or not is determined by ptr + * 3. map: 1 always, pointer points to additional struct with number + * of entries (up to STROBE_MAX_MAP_ENTRIES) + */ + uint16_t len; + /* + * _reserved might be used for some future fields/flags, but we always + * want to keep strobe_value_header to be 8 bytes, so BPF can read 16 + * bytes in one go and get both header and value + */ + uint8_t _reserved[6]; +}; + +/* + * strobe_value_generic is used from BPF probe only, but needs to be a union + * of strobe_value_int/strobe_value_str/strobe_value_map + */ +struct strobe_value_generic { + struct strobe_value_header header; + union { + int64_t val; + void *ptr; + }; +}; + +struct strobe_value_int { + struct strobe_value_header header; + int64_t value; +}; + +struct strobe_value_str { + struct strobe_value_header header; + const char* value; +}; + +struct strobe_value_map { + struct strobe_value_header header; + const struct strobe_map_raw* value; +}; + +struct strobe_map_entry { + const char* key; + const char* val; +}; + +/* + * Map of C-string key/value pairs with fixed maximum capacity. Each map has + * corresponding int64 ID, which application can use (or ignore) in whatever + * way appropriate. Map is "write-only", there is no way to get data out of + * map. Map is intended to be used to provide metadata for profilers and is + * not to be used for internal in-app communication. All methods are + * thread-safe. + */ +struct strobe_map_raw { + /* + * general purpose unique ID that's up to application to decide + * whether and how to use; for request metadata use case id is unique + * request ID that's used to match metadata with stack traces on + * Strobelight backend side + */ + int64_t id; + /* number of used entries in map */ + int64_t cnt; + /* + * having volatile doesn't change anything on BPF side, but clang + * emits warnings for passing `volatile const char *` into + * bpf_probe_read_user_str that expects just `const char *` + */ + const char* tag; + /* + * key/value entries, each consisting of 2 pointers to key and value + * C strings + */ + struct strobe_map_entry entries[STROBE_MAX_MAP_ENTRIES]; +}; + +/* Following values define supported values of TLS mode */ +#define TLS_NOT_SET -1 +#define TLS_LOCAL_EXEC 0 +#define TLS_IMM_EXEC 1 +#define TLS_GENERAL_DYN 2 + +/* + * structure that universally represents TLS location (both for static + * executables and shared libraries) + */ +struct strobe_value_loc { + /* + * tls_mode defines what TLS mode was used for particular metavariable: + * - -1 (TLS_NOT_SET) - no metavariable; + * - 0 (TLS_LOCAL_EXEC) - Local Executable mode; + * - 1 (TLS_IMM_EXEC) - Immediate Executable mode; + * - 2 (TLS_GENERAL_DYN) - General Dynamic mode; + * Local Dynamic mode is not yet supported, because never seen in + * practice. Mode defines how offset field is interpreted. See + * calc_location() in below for details. + */ + int64_t tls_mode; + /* + * TLS_LOCAL_EXEC: offset from thread pointer (fs:0 for x86-64, + * tpidr_el0 for aarch64). + * TLS_IMM_EXEC: absolute address of GOT entry containing offset + * from thread pointer; + * TLS_GENERAL_DYN: absolute address of double GOT entry + * containing tls_index_t struct; + */ + int64_t offset; +}; + +struct strobemeta_cfg { + int64_t req_meta_idx; + struct strobe_value_loc int_locs[STROBE_MAX_INTS]; + struct strobe_value_loc str_locs[STROBE_MAX_STRS]; + struct strobe_value_loc map_locs[STROBE_MAX_MAPS]; +}; + +struct strobe_map_descr { + uint64_t id; + int16_t tag_len; + /* + * cnt <0 - map value isn't set; + * 0 - map has id set, but no key/value entries + */ + int16_t cnt; + /* + * both key_lens[i] and val_lens[i] should be >0 for present key/value + * entry + */ + uint16_t key_lens[STROBE_MAX_MAP_ENTRIES]; + uint16_t val_lens[STROBE_MAX_MAP_ENTRIES]; +}; + +struct strobemeta_payload { + /* req_id has valid request ID, if req_meta_valid == 1 */ + int64_t req_id; + uint8_t req_meta_valid; + /* + * mask has Nth bit set to 1, if Nth metavar was present and + * successfully read + */ + uint64_t int_vals_set_mask; + int64_t int_vals[STROBE_MAX_INTS]; + /* len is >0 for present values */ + uint16_t str_lens[STROBE_MAX_STRS]; + /* if map_descrs[i].cnt == -1, metavar is not present/set */ + struct strobe_map_descr map_descrs[STROBE_MAX_MAPS]; + /* + * payload has compactly packed values of str and map variables in the + * form: strval1\0strval2\0map1key1\0map1val1\0map2key1\0map2val1\0 + * (and so on); str_lens[i], key_lens[i] and val_lens[i] determines + * value length + */ + char payload[STROBE_MAX_PAYLOAD]; +}; + +struct strobelight_bpf_sample { + uint64_t ktime; + char comm[TASK_COMM_LEN]; + pid_t pid; + int user_stack_id; + int kernel_stack_id; + int has_meta; + struct strobemeta_payload metadata; + /* + * makes it possible to pass (<real payload size> + 1) as data size to + * perf_submit() to avoid perf_submit's paranoia about passing zero as + * size, as it deduces that <real payload size> might be + * **theoretically** zero + */ + char dummy_safeguard; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(max_entries, 32); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); +} samples SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, 16); + __uint(key_size, sizeof(uint32_t)); + __uint(value_size, sizeof(uint64_t) * PERF_MAX_STACK_DEPTH); +} stacks_0 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, 16); + __uint(key_size, sizeof(uint32_t)); + __uint(value_size, sizeof(uint64_t) * PERF_MAX_STACK_DEPTH); +} stacks_1 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, uint32_t); + __type(value, struct strobelight_bpf_sample); +} sample_heap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, STROBE_MAX_CFGS); + __type(key, pid_t); + __type(value, struct strobemeta_cfg); +} strobemeta_cfgs SEC(".maps"); + +/* Type for the dtv. */ +/* https://github.com/lattera/glibc/blob/master/nptl/sysdeps/x86_64/tls.h#L34 */ +typedef union dtv { + size_t counter; + struct { + void* val; + bool is_static; + } pointer; +} dtv_t; + +/* Partial definition for tcbhead_t */ +/* https://github.com/bminor/glibc/blob/master/sysdeps/x86_64/nptl/tls.h#L42 */ +struct tcbhead { + void* tcb; + dtv_t* dtv; +}; + +/* + * TLS module/offset information for shared library case. + * For x86-64, this is mapped onto two entries in GOT. + * For aarch64, this is pointed to by second GOT entry. + */ +struct tls_index { + uint64_t module; + uint64_t offset; +}; + +#ifdef SUBPROGS +__noinline +#else +__always_inline +#endif +static void *calc_location(struct strobe_value_loc *loc, void *tls_base) +{ + /* + * tls_mode value is: + * - -1 (TLS_NOT_SET), if no metavar is present; + * - 0 (TLS_LOCAL_EXEC), if metavar uses Local Executable mode of TLS + * (offset from fs:0 for x86-64 or tpidr_el0 for aarch64); + * - 1 (TLS_IMM_EXEC), if metavar uses Immediate Executable mode of TLS; + * - 2 (TLS_GENERAL_DYN), if metavar uses General Dynamic mode of TLS; + * This schema allows to use something like: + * (tls_mode + 1) * (tls_base + offset) + * to get NULL for "no metavar" location, or correct pointer for local + * executable mode without doing extra ifs. + */ + if (loc->tls_mode <= TLS_LOCAL_EXEC) { + /* static executable is simple, we just have offset from + * tls_base */ + void *addr = tls_base + loc->offset; + /* multiply by (tls_mode + 1) to get NULL, if we have no + * metavar in this slot */ + return (void *)((loc->tls_mode + 1) * (int64_t)addr); + } + /* + * Other modes are more complicated, we need to jump through few hoops. + * + * For immediate executable mode (currently supported only for aarch64): + * - loc->offset is pointing to a GOT entry containing fixed offset + * relative to tls_base; + * + * For general dynamic mode: + * - loc->offset is pointing to a beginning of double GOT entries; + * - (for aarch64 only) second entry points to tls_index_t struct; + * - (for x86-64 only) two GOT entries are already tls_index_t; + * - tls_index_t->module is used to find start of TLS section in + * which variable resides; + * - tls_index_t->offset provides offset within that TLS section, + * pointing to value of variable. + */ + struct tls_index tls_index; + dtv_t *dtv; + void *tls_ptr; + + bpf_probe_read_user(&tls_index, sizeof(struct tls_index), + (void *)loc->offset); + /* valid module index is always positive */ + if (tls_index.module > 0) { + /* dtv = ((struct tcbhead *)tls_base)->dtv[tls_index.module] */ + bpf_probe_read_user(&dtv, sizeof(dtv), + &((struct tcbhead *)tls_base)->dtv); + dtv += tls_index.module; + } else { + dtv = NULL; + } + bpf_probe_read_user(&tls_ptr, sizeof(void *), dtv); + /* if pointer has (void *)-1 value, then TLS wasn't initialized yet */ + return tls_ptr && tls_ptr != (void *)-1 + ? tls_ptr + tls_index.offset + : NULL; +} + +#ifdef SUBPROGS +__noinline +#else +__always_inline +#endif +static void read_int_var(struct strobemeta_cfg *cfg, + size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload *data) +{ + void *location = calc_location(&cfg->int_locs[idx], tls_base); + if (!location) + return; + + bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location); + data->int_vals[idx] = value->val; + if (value->header.len) + data->int_vals_set_mask |= (1 << idx); +} + +static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg, + size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload *data, + size_t off) +{ + void *location; + uint64_t len; + + data->str_lens[idx] = 0; + location = calc_location(&cfg->str_locs[idx], tls_base); + if (!location) + return 0; + + bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location); + len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, value->ptr); + /* + * if bpf_probe_read_user_str returns error (<0), due to casting to + * unsinged int, it will become big number, so next check is + * sufficient to check for errors AND prove to BPF verifier, that + * bpf_probe_read_user_str won't return anything bigger than + * STROBE_MAX_STR_LEN + */ + if (len > STROBE_MAX_STR_LEN) + return 0; + + data->str_lens[idx] = len; + return off + len; +} + +static __always_inline uint64_t read_map_var(struct strobemeta_cfg *cfg, + size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload *data, + size_t off) +{ + struct strobe_map_descr* descr = &data->map_descrs[idx]; + struct strobe_map_raw map; + void *location; + uint64_t len; + + descr->tag_len = 0; /* presume no tag is set */ + descr->cnt = -1; /* presume no value is set */ + + location = calc_location(&cfg->map_locs[idx], tls_base); + if (!location) + return off; + + bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location); + if (bpf_probe_read_user(&map, sizeof(struct strobe_map_raw), value->ptr)) + return off; + + descr->id = map.id; + descr->cnt = map.cnt; + if (cfg->req_meta_idx == idx) { + data->req_id = map.id; + data->req_meta_valid = 1; + } + + len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, map.tag); + if (len <= STROBE_MAX_STR_LEN) { + descr->tag_len = len; + off += len; + } + +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif + for (int i = 0; i < STROBE_MAX_MAP_ENTRIES; ++i) { + if (i >= map.cnt) + break; + + descr->key_lens[i] = 0; + len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, + map.entries[i].key); + if (len <= STROBE_MAX_STR_LEN) { + descr->key_lens[i] = len; + off += len; + } + descr->val_lens[i] = 0; + len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, + map.entries[i].val); + if (len <= STROBE_MAX_STR_LEN) { + descr->val_lens[i] = len; + off += len; + } + } + + return off; +} + +#ifdef USE_BPF_LOOP +enum read_type { + READ_INT_VAR, + READ_MAP_VAR, + READ_STR_VAR, +}; + +struct read_var_ctx { + struct strobemeta_payload *data; + void *tls_base; + struct strobemeta_cfg *cfg; + size_t payload_off; + /* value gets mutated */ + struct strobe_value_generic *value; + enum read_type type; +}; + +static int read_var_callback(__u64 index, struct read_var_ctx *ctx) +{ + /* lose precision info for ctx->payload_off, verifier won't track + * double xor, barrier_var() is needed to force clang keep both xors. + */ + ctx->payload_off ^= index; + barrier_var(ctx->payload_off); + ctx->payload_off ^= index; + switch (ctx->type) { + case READ_INT_VAR: + if (index >= STROBE_MAX_INTS) + return 1; + read_int_var(ctx->cfg, index, ctx->tls_base, ctx->value, ctx->data); + break; + case READ_MAP_VAR: + if (index >= STROBE_MAX_MAPS) + return 1; + if (ctx->payload_off > sizeof(ctx->data->payload) - READ_MAP_VAR_PAYLOAD_CAP) + return 1; + ctx->payload_off = read_map_var(ctx->cfg, index, ctx->tls_base, + ctx->value, ctx->data, ctx->payload_off); + break; + case READ_STR_VAR: + if (index >= STROBE_MAX_STRS) + return 1; + if (ctx->payload_off > sizeof(ctx->data->payload) - STROBE_MAX_STR_LEN) + return 1; + ctx->payload_off = read_str_var(ctx->cfg, index, ctx->tls_base, + ctx->value, ctx->data, ctx->payload_off); + break; + } + return 0; +} +#endif /* USE_BPF_LOOP */ + +/* + * read_strobe_meta returns NULL, if no metadata was read; otherwise returns + * pointer to *right after* payload ends + */ +#ifdef SUBPROGS +__noinline +#else +__always_inline +#endif +static void *read_strobe_meta(struct task_struct *task, + struct strobemeta_payload *data) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + struct strobe_value_generic value = {0}; + struct strobemeta_cfg *cfg; + size_t payload_off; + void *tls_base; + + cfg = bpf_map_lookup_elem(&strobemeta_cfgs, &pid); + if (!cfg) + return NULL; + + data->int_vals_set_mask = 0; + data->req_meta_valid = 0; + payload_off = 0; + /* + * we don't have struct task_struct definition, it should be: + * tls_base = (void *)task->thread.fsbase; + */ + tls_base = (void *)task; + +#ifdef USE_BPF_LOOP + struct read_var_ctx ctx = { + .cfg = cfg, + .tls_base = tls_base, + .value = &value, + .data = data, + .payload_off = 0, + }; + int err; + + ctx.type = READ_INT_VAR; + err = bpf_loop(STROBE_MAX_INTS, read_var_callback, &ctx, 0); + if (err != STROBE_MAX_INTS) + return NULL; + + ctx.type = READ_STR_VAR; + err = bpf_loop(STROBE_MAX_STRS, read_var_callback, &ctx, 0); + if (err != STROBE_MAX_STRS) + return NULL; + + ctx.type = READ_MAP_VAR; + err = bpf_loop(STROBE_MAX_MAPS, read_var_callback, &ctx, 0); + if (err != STROBE_MAX_MAPS) + return NULL; + + payload_off = ctx.payload_off; + /* this should not really happen, here only to satisfy verifer */ + if (payload_off > sizeof(data->payload)) + payload_off = sizeof(data->payload); +#else +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif /* NO_UNROLL */ + for (int i = 0; i < STROBE_MAX_INTS; ++i) { + read_int_var(cfg, i, tls_base, &value, data); + } +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif /* NO_UNROLL */ + for (int i = 0; i < STROBE_MAX_STRS; ++i) { + payload_off = read_str_var(cfg, i, tls_base, &value, data, payload_off); + } +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif /* NO_UNROLL */ + for (int i = 0; i < STROBE_MAX_MAPS; ++i) { + payload_off = read_map_var(cfg, i, tls_base, &value, data, payload_off); + } +#endif /* USE_BPF_LOOP */ + + /* + * return pointer right after end of payload, so it's possible to + * calculate exact amount of useful data that needs to be sent + */ + return &data->payload[payload_off]; +} + +SEC("raw_tracepoint/kfree_skb") +int on_event(struct pt_regs *ctx) { + pid_t pid = bpf_get_current_pid_tgid() >> 32; + struct strobelight_bpf_sample* sample; + struct task_struct *task; + uint32_t zero = 0; + uint64_t ktime_ns; + void *sample_end; + + sample = bpf_map_lookup_elem(&sample_heap, &zero); + if (!sample) + return 0; /* this will never happen */ + + sample->pid = pid; + bpf_get_current_comm(&sample->comm, TASK_COMM_LEN); + ktime_ns = bpf_ktime_get_ns(); + sample->ktime = ktime_ns; + + task = (struct task_struct *)bpf_get_current_task(); + sample_end = read_strobe_meta(task, &sample->metadata); + sample->has_meta = sample_end != NULL; + sample_end = sample_end ? : &sample->metadata; + + if ((ktime_ns >> STACK_TABLE_EPOCH_SHIFT) & 1) { + sample->kernel_stack_id = bpf_get_stackid(ctx, &stacks_1, 0); + sample->user_stack_id = bpf_get_stackid(ctx, &stacks_1, BPF_F_USER_STACK); + } else { + sample->kernel_stack_id = bpf_get_stackid(ctx, &stacks_0, 0); + sample->user_stack_id = bpf_get_stackid(ctx, &stacks_0, BPF_F_USER_STACK); + } + + uint64_t sample_size = sample_end - (void *)sample; + /* should always be true */ + if (sample_size < sizeof(struct strobelight_bpf_sample)) + bpf_perf_event_output(ctx, &samples, 0, sample, 1 + sample_size); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/strobemeta_bpf_loop.c b/tools/testing/selftests/bpf/progs/strobemeta_bpf_loop.c new file mode 100644 index 0000000000..d18b992f01 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta_bpf_loop.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2021 Facebook */ + +#define STROBE_MAX_INTS 2 +#define STROBE_MAX_STRS 25 +#define STROBE_MAX_MAPS 100 +#define STROBE_MAX_MAP_ENTRIES 20 +#define USE_BPF_LOOP +#include "strobemeta.h" diff --git a/tools/testing/selftests/bpf/progs/strobemeta_nounroll1.c b/tools/testing/selftests/bpf/progs/strobemeta_nounroll1.c new file mode 100644 index 0000000000..f0a1669e11 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta_nounroll1.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook + +#define STROBE_MAX_INTS 2 +#define STROBE_MAX_STRS 25 +#define STROBE_MAX_MAPS 13 +#define STROBE_MAX_MAP_ENTRIES 20 +#define NO_UNROLL +#include "strobemeta.h" diff --git a/tools/testing/selftests/bpf/progs/strobemeta_nounroll2.c b/tools/testing/selftests/bpf/progs/strobemeta_nounroll2.c new file mode 100644 index 0000000000..4291a7d642 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta_nounroll2.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook + +#define STROBE_MAX_INTS 2 +#define STROBE_MAX_STRS 25 +#define STROBE_MAX_MAPS 30 +#define STROBE_MAX_MAP_ENTRIES 20 +#define NO_UNROLL +#include "strobemeta.h" diff --git a/tools/testing/selftests/bpf/progs/strobemeta_subprogs.c b/tools/testing/selftests/bpf/progs/strobemeta_subprogs.c new file mode 100644 index 0000000000..b6c01f8fc5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta_subprogs.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook + +#define STROBE_MAX_INTS 2 +#define STROBE_MAX_STRS 25 +#define STROBE_MAX_MAPS 13 +#define STROBE_MAX_MAP_ENTRIES 20 +#define NO_UNROLL +#define SUBPROGS +#include "strobemeta.h" diff --git a/tools/testing/selftests/bpf/progs/syscall.c b/tools/testing/selftests/bpf/progs/syscall.c new file mode 100644 index 0000000000..e550f72896 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/syscall.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <../../../tools/include/linux/filter.h> +#include <linux/btf.h> + +char _license[] SEC("license") = "GPL"; + +struct args { + __u64 log_buf; + __u32 log_size; + int max_entries; + int map_fd; + int prog_fd; + int btf_fd; +}; + +#define BTF_INFO_ENC(kind, kind_flag, vlen) \ + ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) +#define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type) +#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ + ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) +#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ + BTF_INT_ENC(encoding, bits_offset, bits) + +static int btf_load(void) +{ + struct btf_blob { + struct btf_header btf_hdr; + __u32 types[8]; + __u32 str; + } raw_btf = { + .btf_hdr = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), + .type_len = sizeof(__u32) * 8, + .str_off = sizeof(__u32) * 8, + .str_len = sizeof(__u32), + }, + .types = { + /* long */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 64, 8), /* [1] */ + /* unsigned long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + }, + }; + static union bpf_attr btf_load_attr = { + .btf_size = sizeof(raw_btf), + }; + + btf_load_attr.btf = (long)&raw_btf; + return bpf_sys_bpf(BPF_BTF_LOAD, &btf_load_attr, sizeof(btf_load_attr)); +} + +SEC("syscall") +int bpf_prog(struct args *ctx) +{ + static char license[] = "GPL"; + static struct bpf_insn insns[] = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + static union bpf_attr map_create_attr = { + .map_type = BPF_MAP_TYPE_HASH, + .key_size = 8, + .value_size = 8, + .btf_key_type_id = 1, + .btf_value_type_id = 2, + }; + static union bpf_attr map_update_attr = { .map_fd = 1, }; + static __u64 key = 12; + static __u64 value = 34; + static union bpf_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + .insn_cnt = sizeof(insns) / sizeof(insns[0]), + }; + int ret; + + ret = btf_load(); + if (ret <= 0) + return ret; + + ctx->btf_fd = ret; + map_create_attr.max_entries = ctx->max_entries; + map_create_attr.btf_fd = ret; + + prog_load_attr.license = (long) license; + prog_load_attr.insns = (long) insns; + prog_load_attr.log_buf = ctx->log_buf; + prog_load_attr.log_size = ctx->log_size; + prog_load_attr.log_level = 1; + + ret = bpf_sys_bpf(BPF_MAP_CREATE, &map_create_attr, sizeof(map_create_attr)); + if (ret <= 0) + return ret; + ctx->map_fd = ret; + insns[3].imm = ret; + + map_update_attr.map_fd = ret; + map_update_attr.key = (long) &key; + map_update_attr.value = (long) &value; + ret = bpf_sys_bpf(BPF_MAP_UPDATE_ELEM, &map_update_attr, sizeof(map_update_attr)); + if (ret < 0) + return ret; + + ret = bpf_sys_bpf(BPF_PROG_LOAD, &prog_load_attr, sizeof(prog_load_attr)); + if (ret <= 0) + return ret; + ctx->prog_fd = ret; + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/tailcall1.c b/tools/testing/selftests/bpf/progs/tailcall1.c new file mode 100644 index 0000000000..8159a0b4a6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tailcall1.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 3); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +#define TAIL_FUNC(x) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ + { \ + return x; \ + } +TAIL_FUNC(0) +TAIL_FUNC(1) +TAIL_FUNC(2) + +SEC("tc") +int entry(struct __sk_buff *skb) +{ + /* Multiple locations to make sure we patch + * all of them. + */ + bpf_tail_call_static(skb, &jmp_table, 0); + bpf_tail_call_static(skb, &jmp_table, 0); + bpf_tail_call_static(skb, &jmp_table, 0); + bpf_tail_call_static(skb, &jmp_table, 0); + + bpf_tail_call_static(skb, &jmp_table, 1); + bpf_tail_call_static(skb, &jmp_table, 1); + bpf_tail_call_static(skb, &jmp_table, 1); + bpf_tail_call_static(skb, &jmp_table, 1); + + bpf_tail_call_static(skb, &jmp_table, 2); + bpf_tail_call_static(skb, &jmp_table, 2); + bpf_tail_call_static(skb, &jmp_table, 2); + bpf_tail_call_static(skb, &jmp_table, 2); + + return 3; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/tailcall2.c b/tools/testing/selftests/bpf/progs/tailcall2.c new file mode 100644 index 0000000000..a5ff53e617 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tailcall2.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 5); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +SEC("tc") +int classifier_0(struct __sk_buff *skb) +{ + bpf_tail_call_static(skb, &jmp_table, 1); + return 0; +} + +SEC("tc") +int classifier_1(struct __sk_buff *skb) +{ + bpf_tail_call_static(skb, &jmp_table, 2); + return 1; +} + +SEC("tc") +int classifier_2(struct __sk_buff *skb) +{ + return 2; +} + +SEC("tc") +int classifier_3(struct __sk_buff *skb) +{ + bpf_tail_call_static(skb, &jmp_table, 4); + return 3; +} + +SEC("tc") +int classifier_4(struct __sk_buff *skb) +{ + bpf_tail_call_static(skb, &jmp_table, 3); + return 4; +} + +SEC("tc") +int entry(struct __sk_buff *skb) +{ + bpf_tail_call_static(skb, &jmp_table, 0); + /* Check multi-prog update. */ + bpf_tail_call_static(skb, &jmp_table, 2); + /* Check tail call limit. */ + bpf_tail_call_static(skb, &jmp_table, 3); + return 3; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/tailcall3.c b/tools/testing/selftests/bpf/progs/tailcall3.c new file mode 100644 index 0000000000..f60bcd7b8d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tailcall3.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +int count = 0; + +SEC("tc") +int classifier_0(struct __sk_buff *skb) +{ + count++; + bpf_tail_call_static(skb, &jmp_table, 0); + return 1; +} + +SEC("tc") +int entry(struct __sk_buff *skb) +{ + bpf_tail_call_static(skb, &jmp_table, 0); + return 0; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/tailcall4.c b/tools/testing/selftests/bpf/progs/tailcall4.c new file mode 100644 index 0000000000..a56bbc2313 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tailcall4.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 3); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +int selector = 0; + +#define TAIL_FUNC(x) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ + { \ + return x; \ + } +TAIL_FUNC(0) +TAIL_FUNC(1) +TAIL_FUNC(2) + +SEC("tc") +int entry(struct __sk_buff *skb) +{ + bpf_tail_call(skb, &jmp_table, selector); + return 3; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/tailcall5.c b/tools/testing/selftests/bpf/progs/tailcall5.c new file mode 100644 index 0000000000..8d03496eb6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tailcall5.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 3); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +int selector = 0; + +#define TAIL_FUNC(x) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ + { \ + return x; \ + } +TAIL_FUNC(0) +TAIL_FUNC(1) +TAIL_FUNC(2) + +SEC("tc") +int entry(struct __sk_buff *skb) +{ + int idx = 0; + + if (selector == 1234) + idx = 1; + else if (selector == 5678) + idx = 2; + + bpf_tail_call(skb, &jmp_table, idx); + return 3; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/tailcall6.c b/tools/testing/selftests/bpf/progs/tailcall6.c new file mode 100644 index 0000000000..d77b8abd62 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tailcall6.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +int count, which; + +SEC("tc") +int classifier_0(struct __sk_buff *skb) +{ + count++; + if (__builtin_constant_p(which)) + __bpf_unreachable(); + bpf_tail_call(skb, &jmp_table, which); + return 1; +} + +SEC("tc") +int entry(struct __sk_buff *skb) +{ + if (__builtin_constant_p(which)) + __bpf_unreachable(); + bpf_tail_call(skb, &jmp_table, which); + return 0; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c new file mode 100644 index 0000000000..8c91428deb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 2); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +#define TAIL_FUNC(x) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ + { \ + return x; \ + } +TAIL_FUNC(0) +TAIL_FUNC(1) + +static __noinline +int subprog_tail(struct __sk_buff *skb) +{ + bpf_tail_call_static(skb, &jmp_table, 0); + + return skb->len * 2; +} + +SEC("tc") +int entry(struct __sk_buff *skb) +{ + bpf_tail_call_static(skb, &jmp_table, 1); + + return subprog_tail(skb); +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c new file mode 100644 index 0000000000..ce97d141da --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_legacy.h" + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +static __noinline +int subprog_tail(struct __sk_buff *skb) +{ + if (load_byte(skb, 0)) + bpf_tail_call_static(skb, &jmp_table, 1); + else + bpf_tail_call_static(skb, &jmp_table, 0); + return 1; +} + +int count = 0; + +SEC("tc") +int classifier_0(struct __sk_buff *skb) +{ + count++; + return subprog_tail(skb); +} + +SEC("tc") +int entry(struct __sk_buff *skb) +{ + bpf_tail_call_static(skb, &jmp_table, 0); + + return 0; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c new file mode 100644 index 0000000000..99c8d1d8a1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_legacy.h" +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 2); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +__noinline +int subprog_tail2(struct __sk_buff *skb) +{ + volatile char arr[64] = {}; + + if (load_word(skb, 0) || load_half(skb, 0)) + bpf_tail_call_static(skb, &jmp_table, 10); + else + bpf_tail_call_static(skb, &jmp_table, 1); + + __sink(arr[sizeof(arr) - 1]); + + return skb->len; +} + +static __noinline +int subprog_tail(struct __sk_buff *skb) +{ + volatile char arr[64] = {}; + + bpf_tail_call_static(skb, &jmp_table, 0); + + __sink(arr[sizeof(arr) - 1]); + + return skb->len * 2; +} + +SEC("tc") +int classifier_0(struct __sk_buff *skb) +{ + volatile char arr[128] = {}; + + __sink(arr[sizeof(arr) - 1]); + + return subprog_tail2(skb); +} + +SEC("tc") +int classifier_1(struct __sk_buff *skb) +{ + volatile char arr[128] = {}; + + __sink(arr[sizeof(arr) - 1]); + + return skb->len * 3; +} + +SEC("tc") +int entry(struct __sk_buff *skb) +{ + volatile char arr[128] = {}; + + __sink(arr[sizeof(arr) - 1]); + + return subprog_tail(skb); +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c new file mode 100644 index 0000000000..a017d6b2f1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} nop_table SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 3); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +int count = 0; +int noise = 0; + +static __always_inline int subprog_noise(void) +{ + __u32 key = 0; + + bpf_map_lookup_elem(&nop_table, &key); + return 0; +} + +__noinline +int subprog_tail_2(struct __sk_buff *skb) +{ + if (noise) + subprog_noise(); + bpf_tail_call_static(skb, &jmp_table, 2); + return skb->len * 3; +} + +__noinline +int subprog_tail_1(struct __sk_buff *skb) +{ + bpf_tail_call_static(skb, &jmp_table, 1); + return skb->len * 2; +} + +__noinline +int subprog_tail(struct __sk_buff *skb) +{ + bpf_tail_call_static(skb, &jmp_table, 0); + return skb->len; +} + +SEC("tc") +int classifier_1(struct __sk_buff *skb) +{ + return subprog_tail_2(skb); +} + +SEC("tc") +int classifier_2(struct __sk_buff *skb) +{ + count++; + return subprog_tail_2(skb); +} + +SEC("tc") +int classifier_0(struct __sk_buff *skb) +{ + return subprog_tail_1(skb); +} + +SEC("tc") +int entry(struct __sk_buff *skb) +{ + return subprog_tail(skb); +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c new file mode 100644 index 0000000000..4a9f63bea6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define __unused __attribute__((unused)) + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +int done = 0; + +SEC("tc") +int classifier_0(struct __sk_buff *skb __unused) +{ + done = 1; + return 0; +} + +static __noinline +int subprog_tail(struct __sk_buff *skb) +{ + /* Don't propagate the constant to the caller */ + volatile int ret = 1; + + bpf_tail_call_static(skb, &jmp_table, 0); + return ret; +} + +SEC("tc") +int entry(struct __sk_buff *skb) +{ + /* Have data on stack which size is not a multiple of 8 */ + volatile char arr[1] = {}; + + __sink(arr[0]); + + return subprog_tail(skb); +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_common.h b/tools/testing/selftests/bpf/progs/task_kfunc_common.h new file mode 100644 index 0000000000..41f2d44f49 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/task_kfunc_common.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#ifndef _TASK_KFUNC_COMMON_H +#define _TASK_KFUNC_COMMON_H + +#include <errno.h> +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct __tasks_kfunc_map_value { + struct task_struct __kptr * task; +}; + +struct hash_map { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, int); + __type(value, struct __tasks_kfunc_map_value); + __uint(max_entries, 1); +} __tasks_kfunc_map SEC(".maps"); + +struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; +struct task_struct *bpf_task_from_pid(s32 pid) __ksym; +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +static inline struct __tasks_kfunc_map_value *tasks_kfunc_map_value_lookup(struct task_struct *p) +{ + s32 pid; + long status; + + status = bpf_probe_read_kernel(&pid, sizeof(pid), &p->pid); + if (status) + return NULL; + + return bpf_map_lookup_elem(&__tasks_kfunc_map, &pid); +} + +static inline int tasks_kfunc_map_insert(struct task_struct *p) +{ + struct __tasks_kfunc_map_value local, *v; + long status; + struct task_struct *acquired, *old; + s32 pid; + + status = bpf_probe_read_kernel(&pid, sizeof(pid), &p->pid); + if (status) + return status; + + local.task = NULL; + status = bpf_map_update_elem(&__tasks_kfunc_map, &pid, &local, BPF_NOEXIST); + if (status) + return status; + + v = bpf_map_lookup_elem(&__tasks_kfunc_map, &pid); + if (!v) { + bpf_map_delete_elem(&__tasks_kfunc_map, &pid); + return -ENOENT; + } + + acquired = bpf_task_acquire(p); + if (!acquired) + return -ENOENT; + + old = bpf_kptr_xchg(&v->task, acquired); + if (old) { + bpf_task_release(old); + return -EEXIST; + } + + return 0; +} + +#endif /* _TASK_KFUNC_COMMON_H */ diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c new file mode 100644 index 0000000000..dcdea31270 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c @@ -0,0 +1,326 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" +#include "task_kfunc_common.h" + +char _license[] SEC("license") = "GPL"; + +/* Prototype for all of the program trace events below: + * + * TRACE_EVENT(task_newtask, + * TP_PROTO(struct task_struct *p, u64 clone_flags) + */ + +static struct __tasks_kfunc_map_value *insert_lookup_task(struct task_struct *task) +{ + int status; + + status = tasks_kfunc_map_insert(task); + if (status) + return NULL; + + return tasks_kfunc_map_value_lookup(task); +} + +SEC("tp_btf/task_newtask") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +int BPF_PROG(task_kfunc_acquire_untrusted, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *acquired; + struct __tasks_kfunc_map_value *v; + + v = insert_lookup_task(task); + if (!v) + return 0; + + /* Can't invoke bpf_task_acquire() on an untrusted pointer. */ + acquired = bpf_task_acquire(v->task); + if (!acquired) + return 0; + + bpf_task_release(acquired); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("arg#0 pointer type STRUCT task_struct must point") +int BPF_PROG(task_kfunc_acquire_fp, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *acquired, *stack_task = (struct task_struct *)&clone_flags; + + /* Can't invoke bpf_task_acquire() on a random frame pointer. */ + acquired = bpf_task_acquire((struct task_struct *)&stack_task); + if (!acquired) + return 0; + + bpf_task_release(acquired); + + return 0; +} + +SEC("kretprobe/free_task") +__failure __msg("calling kernel function bpf_task_acquire is not allowed") +int BPF_PROG(task_kfunc_acquire_unsafe_kretprobe, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *acquired; + + /* Can't call bpf_task_acquire() or bpf_task_release() in an untrusted prog. */ + acquired = bpf_task_acquire(task); + if (!acquired) + return 0; + bpf_task_release(acquired); + + return 0; +} + +SEC("kretprobe/free_task") +__failure __msg("calling kernel function bpf_task_acquire is not allowed") +int BPF_PROG(task_kfunc_acquire_unsafe_kretprobe_rcu, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *acquired; + + bpf_rcu_read_lock(); + if (!task) { + bpf_rcu_read_unlock(); + return 0; + } + /* Can't call bpf_task_acquire() or bpf_task_release() in an untrusted prog. */ + acquired = bpf_task_acquire(task); + if (acquired) + bpf_task_release(acquired); + bpf_rcu_read_unlock(); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +int BPF_PROG(task_kfunc_acquire_null, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *acquired; + + /* Can't invoke bpf_task_acquire() on a NULL pointer. */ + acquired = bpf_task_acquire(NULL); + if (!acquired) + return 0; + bpf_task_release(acquired); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("Unreleased reference") +int BPF_PROG(task_kfunc_acquire_unreleased, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *acquired; + + acquired = bpf_task_acquire(task); + + /* Acquired task is never released. */ + __sink(acquired); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("Unreleased reference") +int BPF_PROG(task_kfunc_xchg_unreleased, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *kptr; + struct __tasks_kfunc_map_value *v; + + v = insert_lookup_task(task); + if (!v) + return 0; + + kptr = bpf_kptr_xchg(&v->task, NULL); + if (!kptr) + return 0; + + /* Kptr retrieved from map is never released. */ + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +int BPF_PROG(task_kfunc_acquire_release_no_null_check, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *acquired; + + acquired = bpf_task_acquire(task); + /* Can't invoke bpf_task_release() on an acquired task without a NULL check. */ + bpf_task_release(acquired); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +int BPF_PROG(task_kfunc_release_untrusted, struct task_struct *task, u64 clone_flags) +{ + struct __tasks_kfunc_map_value *v; + + v = insert_lookup_task(task); + if (!v) + return 0; + + /* Can't invoke bpf_task_release() on an untrusted pointer. */ + bpf_task_release(v->task); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("arg#0 pointer type STRUCT task_struct must point") +int BPF_PROG(task_kfunc_release_fp, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *acquired = (struct task_struct *)&clone_flags; + + /* Cannot release random frame pointer. */ + bpf_task_release(acquired); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +int BPF_PROG(task_kfunc_release_null, struct task_struct *task, u64 clone_flags) +{ + struct __tasks_kfunc_map_value local, *v; + long status; + struct task_struct *acquired, *old; + s32 pid; + + status = bpf_probe_read_kernel(&pid, sizeof(pid), &task->pid); + if (status) + return 0; + + local.task = NULL; + status = bpf_map_update_elem(&__tasks_kfunc_map, &pid, &local, BPF_NOEXIST); + if (status) + return status; + + v = bpf_map_lookup_elem(&__tasks_kfunc_map, &pid); + if (!v) + return -ENOENT; + + acquired = bpf_task_acquire(task); + if (!acquired) + return -EEXIST; + + old = bpf_kptr_xchg(&v->task, acquired); + + /* old cannot be passed to bpf_task_release() without a NULL check. */ + bpf_task_release(old); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("release kernel function bpf_task_release expects") +int BPF_PROG(task_kfunc_release_unacquired, struct task_struct *task, u64 clone_flags) +{ + /* Cannot release trusted task pointer which was not acquired. */ + bpf_task_release(task); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +int BPF_PROG(task_kfunc_from_pid_no_null_check, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *acquired; + + acquired = bpf_task_from_pid(task->pid); + + /* Releasing bpf_task_from_pid() lookup without a NULL check. */ + bpf_task_release(acquired); + + return 0; +} + +SEC("lsm/task_free") +__failure __msg("reg type unsupported for arg#0 function") +int BPF_PROG(task_kfunc_from_lsm_task_free, struct task_struct *task) +{ + struct task_struct *acquired; + + /* the argument of lsm task_free hook is untrusted. */ + acquired = bpf_task_acquire(task); + if (!acquired) + return 0; + + bpf_task_release(acquired); + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("access beyond the end of member comm") +int BPF_PROG(task_access_comm1, struct task_struct *task, u64 clone_flags) +{ + bpf_strncmp(task->comm, 17, "foo"); + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("access beyond the end of member comm") +int BPF_PROG(task_access_comm2, struct task_struct *task, u64 clone_flags) +{ + bpf_strncmp(task->comm + 1, 16, "foo"); + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("write into memory") +int BPF_PROG(task_access_comm3, struct task_struct *task, u64 clone_flags) +{ + bpf_probe_read_kernel(task->comm, 16, task->comm); + return 0; +} + +SEC("fentry/__set_task_comm") +__failure __msg("R1 type=ptr_ expected") +int BPF_PROG(task_access_comm4, struct task_struct *task, const char *buf, bool exec) +{ + /* + * task->comm is a legacy ptr_to_btf_id. The verifier cannot guarantee + * its safety. Hence it cannot be accessed with normal load insns. + */ + bpf_strncmp(task->comm, 16, "foo"); + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("R1 must be referenced or trusted") +int BPF_PROG(task_kfunc_release_in_map, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *local; + struct __tasks_kfunc_map_value *v; + + if (tasks_kfunc_map_insert(task)) + return 0; + + v = tasks_kfunc_map_value_lookup(task); + if (!v) + return 0; + + bpf_rcu_read_lock(); + local = v->task; + if (!local) { + bpf_rcu_read_unlock(); + return 0; + } + /* Can't release a kptr that's still stored in a map. */ + bpf_task_release(local); + bpf_rcu_read_unlock(); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_success.c b/tools/testing/selftests/bpf/progs/task_kfunc_success.c new file mode 100644 index 0000000000..70df695312 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/task_kfunc_success.c @@ -0,0 +1,316 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "task_kfunc_common.h" + +char _license[] SEC("license") = "GPL"; + +int err, pid; + +/* Prototype for all of the program trace events below: + * + * TRACE_EVENT(task_newtask, + * TP_PROTO(struct task_struct *p, u64 clone_flags) + */ + +struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym __weak; + +struct task_struct *bpf_task_acquire___one(struct task_struct *task) __ksym __weak; +/* The two-param bpf_task_acquire doesn't exist */ +struct task_struct *bpf_task_acquire___two(struct task_struct *p, void *ctx) __ksym __weak; +/* Incorrect type for first param */ +struct task_struct *bpf_task_acquire___three(void *ctx) __ksym __weak; + +void invalid_kfunc(void) __ksym __weak; +void bpf_testmod_test_mod_kfunc(int i) __ksym __weak; + +static bool is_test_kfunc_task(void) +{ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + + return pid == cur_pid; +} + +static int test_acquire_release(struct task_struct *task) +{ + struct task_struct *acquired = NULL; + + if (!bpf_ksym_exists(bpf_task_acquire)) { + err = 3; + return 0; + } + if (!bpf_ksym_exists(bpf_testmod_test_mod_kfunc)) { + err = 4; + return 0; + } + if (bpf_ksym_exists(invalid_kfunc)) { + /* the verifier's dead code elimination should remove this */ + err = 5; + asm volatile ("goto -1"); /* for (;;); */ + } + + acquired = bpf_task_acquire(task); + if (acquired) + bpf_task_release(acquired); + else + err = 6; + + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_kfunc_flavor_relo, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *acquired = NULL; + int fake_ctx = 42; + + if (bpf_ksym_exists(bpf_task_acquire___one)) { + acquired = bpf_task_acquire___one(task); + } else if (bpf_ksym_exists(bpf_task_acquire___two)) { + /* Here, bpf_object__resolve_ksym_func_btf_id's find_ksym_btf_id + * call will find vmlinux's bpf_task_acquire, but subsequent + * bpf_core_types_are_compat will fail + */ + acquired = bpf_task_acquire___two(task, &fake_ctx); + err = 3; + return 0; + } else if (bpf_ksym_exists(bpf_task_acquire___three)) { + /* bpf_core_types_are_compat will fail similarly to above case */ + acquired = bpf_task_acquire___three(&fake_ctx); + err = 4; + return 0; + } + + if (acquired) + bpf_task_release(acquired); + else + err = 5; + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_kfunc_flavor_relo_not_found, struct task_struct *task, u64 clone_flags) +{ + /* Neither symbol should successfully resolve. + * Success or failure of one ___flavor should not affect others + */ + if (bpf_ksym_exists(bpf_task_acquire___two)) + err = 1; + else if (bpf_ksym_exists(bpf_task_acquire___three)) + err = 2; + + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_acquire_release_argument, struct task_struct *task, u64 clone_flags) +{ + if (!is_test_kfunc_task()) + return 0; + + return test_acquire_release(task); +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_acquire_release_current, struct task_struct *task, u64 clone_flags) +{ + if (!is_test_kfunc_task()) + return 0; + + return test_acquire_release(bpf_get_current_task_btf()); +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_acquire_leave_in_map, struct task_struct *task, u64 clone_flags) +{ + long status; + + if (!is_test_kfunc_task()) + return 0; + + status = tasks_kfunc_map_insert(task); + if (status) + err = 1; + + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_xchg_release, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *kptr; + struct __tasks_kfunc_map_value *v; + long status; + + if (!is_test_kfunc_task()) + return 0; + + status = tasks_kfunc_map_insert(task); + if (status) { + err = 1; + return 0; + } + + v = tasks_kfunc_map_value_lookup(task); + if (!v) { + err = 2; + return 0; + } + + kptr = bpf_kptr_xchg(&v->task, NULL); + if (!kptr) { + err = 3; + return 0; + } + + bpf_task_release(kptr); + + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_map_acquire_release, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *kptr; + struct __tasks_kfunc_map_value *v; + long status; + + if (!is_test_kfunc_task()) + return 0; + + status = tasks_kfunc_map_insert(task); + if (status) { + err = 1; + return 0; + } + + v = tasks_kfunc_map_value_lookup(task); + if (!v) { + err = 2; + return 0; + } + + bpf_rcu_read_lock(); + kptr = v->task; + if (!kptr) { + err = 3; + } else { + kptr = bpf_task_acquire(kptr); + if (!kptr) + err = 4; + else + bpf_task_release(kptr); + } + bpf_rcu_read_unlock(); + + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_current_acquire_release, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *current, *acquired; + + if (!is_test_kfunc_task()) + return 0; + + current = bpf_get_current_task_btf(); + acquired = bpf_task_acquire(current); + if (acquired) + bpf_task_release(acquired); + else + err = 1; + + return 0; +} + +static void lookup_compare_pid(const struct task_struct *p) +{ + struct task_struct *acquired; + + acquired = bpf_task_from_pid(p->pid); + if (!acquired) { + err = 1; + return; + } + + if (acquired->pid != p->pid) + err = 2; + bpf_task_release(acquired); +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_from_pid_arg, struct task_struct *task, u64 clone_flags) +{ + if (!is_test_kfunc_task()) + return 0; + + lookup_compare_pid(task); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_from_pid_current, struct task_struct *task, u64 clone_flags) +{ + if (!is_test_kfunc_task()) + return 0; + + lookup_compare_pid(bpf_get_current_task_btf()); + return 0; +} + +static int is_pid_lookup_valid(s32 pid) +{ + struct task_struct *acquired; + + acquired = bpf_task_from_pid(pid); + if (acquired) { + bpf_task_release(acquired); + return 1; + } + + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_from_pid_invalid, struct task_struct *task, u64 clone_flags) +{ + if (!is_test_kfunc_task()) + return 0; + + bpf_strncmp(task->comm, 12, "foo"); + bpf_strncmp(task->comm, 16, "foo"); + bpf_strncmp(&task->comm[8], 4, "foo"); + + if (is_pid_lookup_valid(-1)) { + err = 1; + return 0; + } + + if (is_pid_lookup_valid(0xcafef00d)) { + err = 2; + return 0; + } + + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(task_kfunc_acquire_trusted_walked, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *acquired; + + /* task->group_leader is listed as a trusted, non-NULL field of task struct. */ + acquired = bpf_task_acquire(task->group_leader); + if (acquired) + bpf_task_release(acquired); + else + err = 1; + + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/task_local_storage.c b/tools/testing/selftests/bpf/progs/task_local_storage.c new file mode 100644 index 0000000000..80a0a20db8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/task_local_storage.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} enter_id SEC(".maps"); + +#define MAGIC_VALUE 0xabcd1234 + +pid_t target_pid = 0; +int mismatch_cnt = 0; +int enter_cnt = 0; +int exit_cnt = 0; + +SEC("tp_btf/sys_enter") +int BPF_PROG(on_enter, struct pt_regs *regs, long id) +{ + struct task_struct *task; + long *ptr; + + task = bpf_get_current_task_btf(); + if (task->pid != target_pid) + return 0; + + ptr = bpf_task_storage_get(&enter_id, task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!ptr) + return 0; + + __sync_fetch_and_add(&enter_cnt, 1); + *ptr = MAGIC_VALUE + enter_cnt; + + return 0; +} + +SEC("tp_btf/sys_exit") +int BPF_PROG(on_exit, struct pt_regs *regs, long id) +{ + struct task_struct *task; + long *ptr; + + task = bpf_get_current_task_btf(); + if (task->pid != target_pid) + return 0; + + ptr = bpf_task_storage_get(&enter_id, task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!ptr) + return 0; + + __sync_fetch_and_add(&exit_cnt, 1); + if (*ptr != MAGIC_VALUE + exit_cnt) + __sync_fetch_and_add(&mismatch_cnt, 1); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/task_local_storage_exit_creds.c b/tools/testing/selftests/bpf/progs/task_local_storage_exit_creds.c new file mode 100644 index 0000000000..41d88ed222 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/task_local_storage_exit_creds.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, __u64); +} task_storage SEC(".maps"); + +int run_count = 0; +int valid_ptr_count = 0; +int null_ptr_count = 0; + +SEC("fentry/exit_creds") +int BPF_PROG(trace_exit_creds, struct task_struct *task) +{ + __u64 *ptr; + + ptr = bpf_task_storage_get(&task_storage, task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + __sync_fetch_and_add(&valid_ptr_count, 1); + else + __sync_fetch_and_add(&null_ptr_count, 1); + + __sync_fetch_and_add(&run_count, 1); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/task_ls_recursion.c b/tools/testing/selftests/bpf/progs/task_ls_recursion.c new file mode 100644 index 0000000000..4542dc683b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/task_ls_recursion.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#ifndef EBUSY +#define EBUSY 16 +#endif + +char _license[] SEC("license") = "GPL"; +int nr_del_errs = 0; +int test_pid = 0; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} map_a SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} map_b SEC(".maps"); + +SEC("fentry/bpf_local_storage_lookup") +int BPF_PROG(on_lookup) +{ + struct task_struct *task = bpf_get_current_task_btf(); + + if (!test_pid || task->pid != test_pid) + return 0; + + /* The bpf_task_storage_delete will call + * bpf_local_storage_lookup. The prog->active will + * stop the recursion. + */ + bpf_task_storage_delete(&map_a, task); + bpf_task_storage_delete(&map_b, task); + return 0; +} + +SEC("fentry/bpf_local_storage_update") +int BPF_PROG(on_update) +{ + struct task_struct *task = bpf_get_current_task_btf(); + long *ptr; + + if (!test_pid || task->pid != test_pid) + return 0; + + ptr = bpf_task_storage_get(&map_a, task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + /* ptr will not be NULL when it is called from + * the bpf_task_storage_get(&map_b,...F_CREATE) in + * the BPF_PROG(on_enter) below. It is because + * the value can be found in map_a and the kernel + * does not need to acquire any spin_lock. + */ + if (ptr) { + int err; + + *ptr += 1; + err = bpf_task_storage_delete(&map_a, task); + if (err == -EBUSY) + nr_del_errs++; + } + + /* This will still fail because map_b is empty and + * this BPF_PROG(on_update) has failed to acquire + * the percpu busy lock => meaning potential + * deadlock is detected and it will fail to create + * new storage. + */ + ptr = bpf_task_storage_get(&map_b, task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + *ptr += 1; + + return 0; +} + +SEC("tp_btf/sys_enter") +int BPF_PROG(on_enter, struct pt_regs *regs, long id) +{ + struct task_struct *task; + long *ptr; + + task = bpf_get_current_task_btf(); + if (!test_pid || task->pid != test_pid) + return 0; + + ptr = bpf_task_storage_get(&map_a, task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr && !*ptr) + *ptr = 200; + + ptr = bpf_task_storage_get(&map_b, task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr && !*ptr) + *ptr = 100; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c b/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c new file mode 100644 index 0000000000..ea2dbb80f7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +#ifndef EBUSY +#define EBUSY 16 +#endif + +extern bool CONFIG_PREEMPT __kconfig __weak; +int nr_get_errs = 0; +int nr_del_errs = 0; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} task_storage SEC(".maps"); + +SEC("lsm.s/socket_post_create") +int BPF_PROG(socket_post_create, struct socket *sock, int family, int type, + int protocol, int kern) +{ + struct task_struct *task; + int ret, zero = 0; + int *value; + + if (!CONFIG_PREEMPT) + return 0; + + task = bpf_get_current_task_btf(); + value = bpf_task_storage_get(&task_storage, task, &zero, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!value) + __sync_fetch_and_add(&nr_get_errs, 1); + + ret = bpf_task_storage_delete(&task_storage, + bpf_get_current_task_btf()); + if (ret == -EBUSY) + __sync_fetch_and_add(&nr_del_errs, 1); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_incompl_cong_ops.c b/tools/testing/selftests/bpf/progs/tcp_ca_incompl_cong_ops.c new file mode 100644 index 0000000000..7bb872fb22 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tcp_ca_incompl_cong_ops.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +static inline struct tcp_sock *tcp_sk(const struct sock *sk) +{ + return (struct tcp_sock *)sk; +} + +SEC("struct_ops/incompl_cong_ops_ssthresh") +__u32 BPF_PROG(incompl_cong_ops_ssthresh, struct sock *sk) +{ + return tcp_sk(sk)->snd_ssthresh; +} + +SEC("struct_ops/incompl_cong_ops_undo_cwnd") +__u32 BPF_PROG(incompl_cong_ops_undo_cwnd, struct sock *sk) +{ + return tcp_sk(sk)->snd_cwnd; +} + +SEC(".struct_ops") +struct tcp_congestion_ops incompl_cong_ops = { + /* Intentionally leaving out any of the required cong_avoid() and + * cong_control() here. + */ + .ssthresh = (void *)incompl_cong_ops_ssthresh, + .undo_cwnd = (void *)incompl_cong_ops_undo_cwnd, + .name = "bpf_incompl_ops", +}; diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_unsupp_cong_op.c b/tools/testing/selftests/bpf/progs/tcp_ca_unsupp_cong_op.c new file mode 100644 index 0000000000..c06f4a41c2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tcp_ca_unsupp_cong_op.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +SEC("struct_ops/unsupp_cong_op_get_info") +size_t BPF_PROG(unsupp_cong_op_get_info, struct sock *sk, u32 ext, int *attr, + union tcp_cc_info *info) +{ + return 0; +} + +SEC(".struct_ops") +struct tcp_congestion_ops unsupp_cong_op = { + .get_info = (void *)unsupp_cong_op_get_info, + .name = "bpf_unsupp_op", +}; diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_update.c b/tools/testing/selftests/bpf/progs/tcp_ca_update.c new file mode 100644 index 0000000000..b93a0ed330 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tcp_ca_update.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +int ca1_cnt = 0; +int ca2_cnt = 0; + +static inline struct tcp_sock *tcp_sk(const struct sock *sk) +{ + return (struct tcp_sock *)sk; +} + +SEC("struct_ops/ca_update_1_init") +void BPF_PROG(ca_update_1_init, struct sock *sk) +{ + ca1_cnt++; +} + +SEC("struct_ops/ca_update_2_init") +void BPF_PROG(ca_update_2_init, struct sock *sk) +{ + ca2_cnt++; +} + +SEC("struct_ops/ca_update_cong_control") +void BPF_PROG(ca_update_cong_control, struct sock *sk, + const struct rate_sample *rs) +{ +} + +SEC("struct_ops/ca_update_ssthresh") +__u32 BPF_PROG(ca_update_ssthresh, struct sock *sk) +{ + return tcp_sk(sk)->snd_ssthresh; +} + +SEC("struct_ops/ca_update_undo_cwnd") +__u32 BPF_PROG(ca_update_undo_cwnd, struct sock *sk) +{ + return tcp_sk(sk)->snd_cwnd; +} + +SEC(".struct_ops.link") +struct tcp_congestion_ops ca_update_1 = { + .init = (void *)ca_update_1_init, + .cong_control = (void *)ca_update_cong_control, + .ssthresh = (void *)ca_update_ssthresh, + .undo_cwnd = (void *)ca_update_undo_cwnd, + .name = "tcp_ca_update", +}; + +SEC(".struct_ops.link") +struct tcp_congestion_ops ca_update_2 = { + .init = (void *)ca_update_2_init, + .cong_control = (void *)ca_update_cong_control, + .ssthresh = (void *)ca_update_ssthresh, + .undo_cwnd = (void *)ca_update_undo_cwnd, + .name = "tcp_ca_update", +}; + +SEC(".struct_ops.link") +struct tcp_congestion_ops ca_wrong = { + .cong_control = (void *)ca_update_cong_control, + .ssthresh = (void *)ca_update_ssthresh, + .undo_cwnd = (void *)ca_update_undo_cwnd, + .name = "tcp_ca_wrong", +}; + +SEC(".struct_ops") +struct tcp_congestion_ops ca_no_link = { + .cong_control = (void *)ca_update_cong_control, + .ssthresh = (void *)ca_update_ssthresh, + .undo_cwnd = (void *)ca_update_undo_cwnd, + .name = "tcp_ca_no_link", +}; diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_write_sk_pacing.c b/tools/testing/selftests/bpf/progs/tcp_ca_write_sk_pacing.c new file mode 100644 index 0000000000..0724a79cec --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tcp_ca_write_sk_pacing.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +#define USEC_PER_SEC 1000000UL + +#define min(a, b) ((a) < (b) ? (a) : (b)) + +static inline struct tcp_sock *tcp_sk(const struct sock *sk) +{ + return (struct tcp_sock *)sk; +} + +static inline unsigned int tcp_left_out(const struct tcp_sock *tp) +{ + return tp->sacked_out + tp->lost_out; +} + +static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) +{ + return tp->packets_out - tcp_left_out(tp) + tp->retrans_out; +} + +SEC("struct_ops/write_sk_pacing_init") +void BPF_PROG(write_sk_pacing_init, struct sock *sk) +{ +#ifdef ENABLE_ATOMICS_TESTS + __sync_bool_compare_and_swap(&sk->sk_pacing_status, SK_PACING_NONE, + SK_PACING_NEEDED); +#else + sk->sk_pacing_status = SK_PACING_NEEDED; +#endif +} + +SEC("struct_ops/write_sk_pacing_cong_control") +void BPF_PROG(write_sk_pacing_cong_control, struct sock *sk, + const struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + unsigned long rate = + ((tp->snd_cwnd * tp->mss_cache * USEC_PER_SEC) << 3) / + (tp->srtt_us ?: 1U << 3); + sk->sk_pacing_rate = min(rate, sk->sk_max_pacing_rate); + tp->app_limited = (tp->delivered + tcp_packets_in_flight(tp)) ?: 1; +} + +SEC("struct_ops/write_sk_pacing_ssthresh") +__u32 BPF_PROG(write_sk_pacing_ssthresh, struct sock *sk) +{ + return tcp_sk(sk)->snd_ssthresh; +} + +SEC("struct_ops/write_sk_pacing_undo_cwnd") +__u32 BPF_PROG(write_sk_pacing_undo_cwnd, struct sock *sk) +{ + return tcp_sk(sk)->snd_cwnd; +} + +SEC(".struct_ops") +struct tcp_congestion_ops write_sk_pacing = { + .init = (void *)write_sk_pacing_init, + .cong_control = (void *)write_sk_pacing_cong_control, + .ssthresh = (void *)write_sk_pacing_ssthresh, + .undo_cwnd = (void *)write_sk_pacing_undo_cwnd, + .name = "bpf_w_sk_pacing", +}; diff --git a/tools/testing/selftests/bpf/progs/tcp_rtt.c b/tools/testing/selftests/bpf/progs/tcp_rtt.c new file mode 100644 index 0000000000..0988d79f15 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tcp_rtt.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct tcp_rtt_storage { + __u32 invoked; + __u32 dsack_dups; + __u32 delivered; + __u32 delivered_ce; + __u32 icsk_retransmits; +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct tcp_rtt_storage); +} socket_storage_map SEC(".maps"); + +SEC("sockops") +int _sockops(struct bpf_sock_ops *ctx) +{ + struct tcp_rtt_storage *storage; + struct bpf_tcp_sock *tcp_sk; + int op = (int) ctx->op; + struct bpf_sock *sk; + + sk = ctx->sk; + if (!sk) + return 1; + + storage = bpf_sk_storage_get(&socket_storage_map, sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!storage) + return 1; + + if (op == BPF_SOCK_OPS_TCP_CONNECT_CB) { + bpf_sock_ops_cb_flags_set(ctx, BPF_SOCK_OPS_RTT_CB_FLAG); + return 1; + } + + if (op != BPF_SOCK_OPS_RTT_CB) + return 1; + + tcp_sk = bpf_tcp_sock(sk); + if (!tcp_sk) + return 1; + + storage->invoked++; + + storage->dsack_dups = tcp_sk->dsack_dups; + storage->delivered = tcp_sk->delivered; + storage->delivered_ce = tcp_sk->delivered_ce; + storage->icsk_retransmits = tcp_sk->icsk_retransmits; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/test_access_variable_array.c b/tools/testing/selftests/bpf/progs/test_access_variable_array.c new file mode 100644 index 0000000000..808c49b798 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_access_variable_array.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Bytedance */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +unsigned long span = 0; + +SEC("fentry/load_balance") +int BPF_PROG(fentry_fentry, int this_cpu, struct rq *this_rq, + struct sched_domain *sd) +{ + span = sd->span[0]; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_assign_reuse.c b/tools/testing/selftests/bpf/progs/test_assign_reuse.c new file mode 100644 index 0000000000..4f2e2321ea --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_assign_reuse.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ +#include <stdbool.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> +#include <linux/pkt_cls.h> + +char LICENSE[] SEC("license") = "GPL"; + +__u64 sk_cookie_seen; +__u64 reuseport_executed; +union { + struct tcphdr tcp; + struct udphdr udp; +} headers; + +const volatile __u16 dest_port; + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} sk_map SEC(".maps"); + +SEC("sk_reuseport") +int reuse_accept(struct sk_reuseport_md *ctx) +{ + reuseport_executed++; + + if (ctx->ip_protocol == IPPROTO_TCP) { + if (ctx->data + sizeof(headers.tcp) > ctx->data_end) + return SK_DROP; + + if (__builtin_memcmp(&headers.tcp, ctx->data, sizeof(headers.tcp)) != 0) + return SK_DROP; + } else if (ctx->ip_protocol == IPPROTO_UDP) { + if (ctx->data + sizeof(headers.udp) > ctx->data_end) + return SK_DROP; + + if (__builtin_memcmp(&headers.udp, ctx->data, sizeof(headers.udp)) != 0) + return SK_DROP; + } else { + return SK_DROP; + } + + sk_cookie_seen = bpf_get_socket_cookie(ctx->sk); + return SK_PASS; +} + +SEC("sk_reuseport") +int reuse_drop(struct sk_reuseport_md *ctx) +{ + reuseport_executed++; + sk_cookie_seen = 0; + return SK_DROP; +} + +static int +assign_sk(struct __sk_buff *skb) +{ + int zero = 0, ret = 0; + struct bpf_sock *sk; + + sk = bpf_map_lookup_elem(&sk_map, &zero); + if (!sk) + return TC_ACT_SHOT; + ret = bpf_sk_assign(skb, sk, 0); + bpf_sk_release(sk); + return ret ? TC_ACT_SHOT : TC_ACT_OK; +} + +static bool +maybe_assign_tcp(struct __sk_buff *skb, struct tcphdr *th) +{ + if (th + 1 > (void *)(long)(skb->data_end)) + return TC_ACT_SHOT; + + if (!th->syn || th->ack || th->dest != bpf_htons(dest_port)) + return TC_ACT_OK; + + __builtin_memcpy(&headers.tcp, th, sizeof(headers.tcp)); + return assign_sk(skb); +} + +static bool +maybe_assign_udp(struct __sk_buff *skb, struct udphdr *uh) +{ + if (uh + 1 > (void *)(long)(skb->data_end)) + return TC_ACT_SHOT; + + if (uh->dest != bpf_htons(dest_port)) + return TC_ACT_OK; + + __builtin_memcpy(&headers.udp, uh, sizeof(headers.udp)); + return assign_sk(skb); +} + +SEC("tc") +int tc_main(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ethhdr *eth; + + eth = (struct ethhdr *)(data); + if (eth + 1 > data_end) + return TC_ACT_SHOT; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)(data + sizeof(*eth)); + + if (iph + 1 > data_end) + return TC_ACT_SHOT; + + if (iph->protocol == IPPROTO_TCP) + return maybe_assign_tcp(skb, (struct tcphdr *)(iph + 1)); + else if (iph->protocol == IPPROTO_UDP) + return maybe_assign_udp(skb, (struct udphdr *)(iph + 1)); + else + return TC_ACT_SHOT; + } else { + struct ipv6hdr *ip6h = (struct ipv6hdr *)(data + sizeof(*eth)); + + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + + if (ip6h->nexthdr == IPPROTO_TCP) + return maybe_assign_tcp(skb, (struct tcphdr *)(ip6h + 1)); + else if (ip6h->nexthdr == IPPROTO_UDP) + return maybe_assign_udp(skb, (struct udphdr *)(ip6h + 1)); + else + return TC_ACT_SHOT; + } +} diff --git a/tools/testing/selftests/bpf/progs/test_attach_kprobe_sleepable.c b/tools/testing/selftests/bpf/progs/test_attach_kprobe_sleepable.c new file mode 100644 index 0000000000..f548b74462 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_attach_kprobe_sleepable.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Facebook + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" + +int kprobe_res = 0; + +/** + * This program will be manually made sleepable on the userspace side + * and should thus be unattachable. + */ +SEC("kprobe/" SYS_PREFIX "sys_nanosleep") +int handle_kprobe_sleepable(struct pt_regs *ctx) +{ + kprobe_res = 1; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c new file mode 100644 index 0000000000..68466a6ad1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Facebook + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" + +int kprobe2_res = 0; +int kretprobe2_res = 0; +int uprobe_byname_res = 0; +int uretprobe_byname_res = 0; +int uprobe_byname2_res = 0; +int uretprobe_byname2_res = 0; +int uprobe_byname3_sleepable_res = 0; +int uprobe_byname3_res = 0; +int uretprobe_byname3_sleepable_res = 0; +int uretprobe_byname3_res = 0; +void *user_ptr = 0; + +SEC("ksyscall/nanosleep") +int BPF_KSYSCALL(handle_kprobe_auto, struct __kernel_timespec *req, struct __kernel_timespec *rem) +{ + kprobe2_res = 11; + return 0; +} + +SEC("kretsyscall/nanosleep") +int BPF_KRETPROBE(handle_kretprobe_auto, int ret) +{ + kretprobe2_res = 22; + return ret; +} + +SEC("uprobe") +int handle_uprobe_ref_ctr(struct pt_regs *ctx) +{ + return 0; +} + +SEC("uretprobe") +int handle_uretprobe_ref_ctr(struct pt_regs *ctx) +{ + return 0; +} + +SEC("uprobe") +int handle_uprobe_byname(struct pt_regs *ctx) +{ + uprobe_byname_res = 5; + return 0; +} + +/* use auto-attach format for section definition. */ +SEC("uretprobe//proc/self/exe:trigger_func2") +int handle_uretprobe_byname(struct pt_regs *ctx) +{ + uretprobe_byname_res = 6; + return 0; +} + +SEC("uprobe") +int BPF_UPROBE(handle_uprobe_byname2, const char *pathname, const char *mode) +{ + char mode_buf[2] = {}; + + /* verify fopen mode */ + bpf_probe_read_user(mode_buf, sizeof(mode_buf), mode); + if (mode_buf[0] == 'r' && mode_buf[1] == 0) + uprobe_byname2_res = 7; + return 0; +} + +SEC("uretprobe") +int BPF_URETPROBE(handle_uretprobe_byname2, void *ret) +{ + uretprobe_byname2_res = 8; + return 0; +} + +static __always_inline bool verify_sleepable_user_copy(void) +{ + char data[9]; + + bpf_copy_from_user(data, sizeof(data), user_ptr); + return bpf_strncmp(data, sizeof(data), "test_data") == 0; +} + +SEC("uprobe.s//proc/self/exe:trigger_func3") +int handle_uprobe_byname3_sleepable(struct pt_regs *ctx) +{ + if (verify_sleepable_user_copy()) + uprobe_byname3_sleepable_res = 9; + return 0; +} + +/** + * same target as the uprobe.s above to force sleepable and non-sleepable + * programs in the same bpf_prog_array + */ +SEC("uprobe//proc/self/exe:trigger_func3") +int handle_uprobe_byname3(struct pt_regs *ctx) +{ + uprobe_byname3_res = 10; + return 0; +} + +SEC("uretprobe.s//proc/self/exe:trigger_func3") +int handle_uretprobe_byname3_sleepable(struct pt_regs *ctx) +{ + if (verify_sleepable_user_copy()) + uretprobe_byname3_sleepable_res = 11; + return 0; +} + +SEC("uretprobe//proc/self/exe:trigger_func3") +int handle_uretprobe_byname3(struct pt_regs *ctx) +{ + uretprobe_byname3_res = 12; + return 0; +} + + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe_manual.c b/tools/testing/selftests/bpf/progs/test_attach_probe_manual.c new file mode 100644 index 0000000000..7f08bce945 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_attach_probe_manual.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Facebook + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" + +int kprobe_res = 0; +int kretprobe_res = 0; +int uprobe_res = 0; +int uretprobe_res = 0; +int uprobe_byname_res = 0; +void *user_ptr = 0; + +SEC("kprobe") +int handle_kprobe(struct pt_regs *ctx) +{ + kprobe_res = 1; + return 0; +} + +SEC("kretprobe") +int handle_kretprobe(struct pt_regs *ctx) +{ + kretprobe_res = 2; + return 0; +} + +SEC("uprobe") +int handle_uprobe(struct pt_regs *ctx) +{ + uprobe_res = 3; + return 0; +} + +SEC("uretprobe") +int handle_uretprobe(struct pt_regs *ctx) +{ + uretprobe_res = 4; + return 0; +} + +SEC("uprobe") +int handle_uprobe_byname(struct pt_regs *ctx) +{ + uprobe_byname_res = 5; + return 0; +} + + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_autoattach.c b/tools/testing/selftests/bpf/progs/test_autoattach.c new file mode 100644 index 0000000000..11a44493eb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_autoattach.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Google */ + +#include "vmlinux.h" +#include <bpf/bpf_tracing.h> + +bool prog1_called = false; +bool prog2_called = false; + +SEC("raw_tp/sys_enter") +int prog1(const void *ctx) +{ + prog1_called = true; + return 0; +} + +SEC("raw_tp/sys_exit") +int prog2(const void *ctx) +{ + prog2_called = true; + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_autoload.c b/tools/testing/selftests/bpf/progs/test_autoload.c new file mode 100644 index 0000000000..62c8cdec6d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_autoload.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +bool prog1_called = false; +bool prog2_called = false; +bool prog3_called = false; + +SEC("raw_tp/sys_enter") +int prog1(const void *ctx) +{ + prog1_called = true; + return 0; +} + +SEC("raw_tp/sys_exit") +int prog2(const void *ctx) +{ + prog2_called = true; + return 0; +} + +struct fake_kernel_struct { + int whatever; +} __attribute__((preserve_access_index)); + +SEC("fentry/unexisting-kprobe-will-fail-if-loaded") +int prog3(const void *ctx) +{ + struct fake_kernel_struct *fake = (void *)ctx; + fake->whatever = 123; + prog3_called = true; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_bpf_cookie.c b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c new file mode 100644 index 0000000000..5a3a80f751 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <errno.h> + +int my_tid; + +__u64 kprobe_res; +__u64 kprobe_multi_res; +__u64 kretprobe_res; +__u64 uprobe_res; +__u64 uretprobe_res; +__u64 tp_res; +__u64 pe_res; +__u64 fentry_res; +__u64 fexit_res; +__u64 fmod_ret_res; +__u64 lsm_res; + +static void update(void *ctx, __u64 *res) +{ + if (my_tid != (u32)bpf_get_current_pid_tgid()) + return; + + *res |= bpf_get_attach_cookie(ctx); +} + +SEC("kprobe") +int handle_kprobe(struct pt_regs *ctx) +{ + update(ctx, &kprobe_res); + return 0; +} + +SEC("kretprobe") +int handle_kretprobe(struct pt_regs *ctx) +{ + update(ctx, &kretprobe_res); + return 0; +} + +SEC("uprobe") +int handle_uprobe(struct pt_regs *ctx) +{ + update(ctx, &uprobe_res); + return 0; +} + +SEC("uretprobe") +int handle_uretprobe(struct pt_regs *ctx) +{ + update(ctx, &uretprobe_res); + return 0; +} + +/* bpf_prog_array, used by kernel internally to keep track of attached BPF + * programs to a given BPF hook (e.g., for tracepoints) doesn't allow the same + * BPF program to be attached multiple times. So have three identical copies + * ready to attach to the same tracepoint. + */ +SEC("tp/syscalls/sys_enter_nanosleep") +int handle_tp1(struct pt_regs *ctx) +{ + update(ctx, &tp_res); + return 0; +} +SEC("tp/syscalls/sys_enter_nanosleep") +int handle_tp2(struct pt_regs *ctx) +{ + update(ctx, &tp_res); + return 0; +} +SEC("tp/syscalls/sys_enter_nanosleep") +int handle_tp3(void *ctx) +{ + update(ctx, &tp_res); + return 1; +} + +SEC("perf_event") +int handle_pe(struct pt_regs *ctx) +{ + update(ctx, &pe_res); + return 0; +} + +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(fentry_test1, int a) +{ + update(ctx, &fentry_res); + return 0; +} + +SEC("fexit/bpf_fentry_test1") +int BPF_PROG(fexit_test1, int a, int ret) +{ + update(ctx, &fexit_res); + return 0; +} + +SEC("fmod_ret/bpf_modify_return_test") +int BPF_PROG(fmod_ret_test, int _a, int *_b, int _ret) +{ + update(ctx, &fmod_ret_res); + return 1234; +} + +SEC("lsm/file_mprotect") +int BPF_PROG(test_int_hook, struct vm_area_struct *vma, + unsigned long reqprot, unsigned long prot, int ret) +{ + if (my_tid != (u32)bpf_get_current_pid_tgid()) + return ret; + update(ctx, &lsm_res); + return -EPERM; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_bpf_ma.c b/tools/testing/selftests/bpf/progs/test_bpf_ma.c new file mode 100644 index 0000000000..ecde41ae0f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_bpf_ma.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_experimental.h" +#include "bpf_misc.h" + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +struct generic_map_value { + void *data; +}; + +char _license[] SEC("license") = "GPL"; + +const unsigned int data_sizes[] = {8, 16, 32, 64, 96, 128, 192, 256, 512, 1024, 2048, 4096}; +const volatile unsigned int data_btf_ids[ARRAY_SIZE(data_sizes)] = {}; + +int err = 0; +int pid = 0; + +#define DEFINE_ARRAY_WITH_KPTR(_size) \ + struct bin_data_##_size { \ + char data[_size - sizeof(void *)]; \ + }; \ + struct map_value_##_size { \ + struct bin_data_##_size __kptr * data; \ + /* To emit BTF info for bin_data_xx */ \ + struct bin_data_##_size not_used; \ + }; \ + struct { \ + __uint(type, BPF_MAP_TYPE_ARRAY); \ + __type(key, int); \ + __type(value, struct map_value_##_size); \ + __uint(max_entries, 128); \ + } array_##_size SEC(".maps"); + +static __always_inline void batch_alloc_free(struct bpf_map *map, unsigned int batch, + unsigned int idx) +{ + struct generic_map_value *value; + unsigned int i, key; + void *old, *new; + + for (i = 0; i < batch; i++) { + key = i; + value = bpf_map_lookup_elem(map, &key); + if (!value) { + err = 1; + return; + } + new = bpf_obj_new_impl(data_btf_ids[idx], NULL); + if (!new) { + err = 2; + return; + } + old = bpf_kptr_xchg(&value->data, new); + if (old) { + bpf_obj_drop(old); + err = 3; + return; + } + } + for (i = 0; i < batch; i++) { + key = i; + value = bpf_map_lookup_elem(map, &key); + if (!value) { + err = 4; + return; + } + old = bpf_kptr_xchg(&value->data, NULL); + if (!old) { + err = 5; + return; + } + bpf_obj_drop(old); + } +} + +#define CALL_BATCH_ALLOC_FREE(size, batch, idx) \ + batch_alloc_free((struct bpf_map *)(&array_##size), batch, idx) + +DEFINE_ARRAY_WITH_KPTR(8); +DEFINE_ARRAY_WITH_KPTR(16); +DEFINE_ARRAY_WITH_KPTR(32); +DEFINE_ARRAY_WITH_KPTR(64); +DEFINE_ARRAY_WITH_KPTR(96); +DEFINE_ARRAY_WITH_KPTR(128); +DEFINE_ARRAY_WITH_KPTR(192); +DEFINE_ARRAY_WITH_KPTR(256); +DEFINE_ARRAY_WITH_KPTR(512); +DEFINE_ARRAY_WITH_KPTR(1024); +DEFINE_ARRAY_WITH_KPTR(2048); +DEFINE_ARRAY_WITH_KPTR(4096); + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int test_bpf_mem_alloc_free(void *ctx) +{ + if ((u32)bpf_get_current_pid_tgid() != pid) + return 0; + + /* Alloc 128 8-bytes objects in batch to trigger refilling, + * then free 128 8-bytes objects in batch to trigger freeing. + */ + CALL_BATCH_ALLOC_FREE(8, 128, 0); + CALL_BATCH_ALLOC_FREE(16, 128, 1); + CALL_BATCH_ALLOC_FREE(32, 128, 2); + CALL_BATCH_ALLOC_FREE(64, 128, 3); + CALL_BATCH_ALLOC_FREE(96, 128, 4); + CALL_BATCH_ALLOC_FREE(128, 128, 5); + CALL_BATCH_ALLOC_FREE(192, 128, 6); + CALL_BATCH_ALLOC_FREE(256, 128, 7); + CALL_BATCH_ALLOC_FREE(512, 64, 8); + CALL_BATCH_ALLOC_FREE(1024, 32, 9); + CALL_BATCH_ALLOC_FREE(2048, 16, 10); + CALL_BATCH_ALLOC_FREE(4096, 8, 11); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c new file mode 100644 index 0000000000..77ad8adf68 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define EAFNOSUPPORT 97 +#define EPROTO 71 +#define ENONET 64 +#define EINVAL 22 +#define ENOENT 2 + +extern unsigned long CONFIG_HZ __kconfig; + +int test_einval_bpf_tuple = 0; +int test_einval_reserved = 0; +int test_einval_netns_id = 0; +int test_einval_len_opts = 0; +int test_eproto_l4proto = 0; +int test_enonet_netns_id = 0; +int test_enoent_lookup = 0; +int test_eafnosupport = 0; +int test_alloc_entry = -EINVAL; +int test_insert_entry = -EAFNOSUPPORT; +int test_succ_lookup = -ENOENT; +u32 test_delta_timeout = 0; +u32 test_status = 0; +u32 test_insert_lookup_mark = 0; +int test_snat_addr = -EINVAL; +int test_dnat_addr = -EINVAL; +__be32 saddr = 0; +__be16 sport = 0; +__be32 daddr = 0; +__be16 dport = 0; +int test_exist_lookup = -ENOENT; +u32 test_exist_lookup_mark = 0; + +enum nf_nat_manip_type___local { + NF_NAT_MANIP_SRC___local, + NF_NAT_MANIP_DST___local +}; + +struct nf_conn; + +struct bpf_ct_opts___local { + s32 netns_id; + s32 error; + u8 l4proto; + u8 reserved[3]; +} __attribute__((preserve_access_index)); + +struct nf_conn *bpf_xdp_ct_alloc(struct xdp_md *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32) __ksym; +struct nf_conn *bpf_xdp_ct_lookup(struct xdp_md *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32) __ksym; +struct nf_conn *bpf_skb_ct_alloc(struct __sk_buff *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32) __ksym; +struct nf_conn *bpf_skb_ct_lookup(struct __sk_buff *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32) __ksym; +struct nf_conn *bpf_ct_insert_entry(struct nf_conn *) __ksym; +void bpf_ct_release(struct nf_conn *) __ksym; +void bpf_ct_set_timeout(struct nf_conn *, u32) __ksym; +int bpf_ct_change_timeout(struct nf_conn *, u32) __ksym; +int bpf_ct_set_status(struct nf_conn *, u32) __ksym; +int bpf_ct_change_status(struct nf_conn *, u32) __ksym; +int bpf_ct_set_nat_info(struct nf_conn *, union nf_inet_addr *, + int port, enum nf_nat_manip_type___local) __ksym; + +static __always_inline void +nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32), + struct nf_conn *(*alloc_fn)(void *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32), + void *ctx) +{ + struct bpf_ct_opts___local opts_def = { .l4proto = IPPROTO_TCP, .netns_id = -1 }; + struct bpf_sock_tuple bpf_tuple; + struct nf_conn *ct; + + __builtin_memset(&bpf_tuple, 0, sizeof(bpf_tuple.ipv4)); + + ct = lookup_fn(ctx, NULL, 0, &opts_def, sizeof(opts_def)); + if (ct) + bpf_ct_release(ct); + else + test_einval_bpf_tuple = opts_def.error; + + opts_def.reserved[0] = 1; + ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, + sizeof(opts_def)); + opts_def.reserved[0] = 0; + opts_def.l4proto = IPPROTO_TCP; + if (ct) + bpf_ct_release(ct); + else + test_einval_reserved = opts_def.error; + + opts_def.netns_id = -2; + ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, + sizeof(opts_def)); + opts_def.netns_id = -1; + if (ct) + bpf_ct_release(ct); + else + test_einval_netns_id = opts_def.error; + + ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, + sizeof(opts_def) - 1); + if (ct) + bpf_ct_release(ct); + else + test_einval_len_opts = opts_def.error; + + opts_def.l4proto = IPPROTO_ICMP; + ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, + sizeof(opts_def)); + opts_def.l4proto = IPPROTO_TCP; + if (ct) + bpf_ct_release(ct); + else + test_eproto_l4proto = opts_def.error; + + opts_def.netns_id = 0xf00f; + ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, + sizeof(opts_def)); + opts_def.netns_id = -1; + if (ct) + bpf_ct_release(ct); + else + test_enonet_netns_id = opts_def.error; + + ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, + sizeof(opts_def)); + if (ct) + bpf_ct_release(ct); + else + test_enoent_lookup = opts_def.error; + + ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4) - 1, &opts_def, + sizeof(opts_def)); + if (ct) + bpf_ct_release(ct); + else + test_eafnosupport = opts_def.error; + + bpf_tuple.ipv4.saddr = bpf_get_prandom_u32(); /* src IP */ + bpf_tuple.ipv4.daddr = bpf_get_prandom_u32(); /* dst IP */ + bpf_tuple.ipv4.sport = bpf_get_prandom_u32(); /* src port */ + bpf_tuple.ipv4.dport = bpf_get_prandom_u32(); /* dst port */ + + ct = alloc_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, + sizeof(opts_def)); + if (ct) { + __u16 sport = bpf_get_prandom_u32(); + __u16 dport = bpf_get_prandom_u32(); + union nf_inet_addr saddr = {}; + union nf_inet_addr daddr = {}; + struct nf_conn *ct_ins; + + bpf_ct_set_timeout(ct, 10000); + ct->mark = 77; + + /* snat */ + saddr.ip = bpf_get_prandom_u32(); + bpf_ct_set_nat_info(ct, &saddr, sport, NF_NAT_MANIP_SRC___local); + /* dnat */ + daddr.ip = bpf_get_prandom_u32(); + bpf_ct_set_nat_info(ct, &daddr, dport, NF_NAT_MANIP_DST___local); + + ct_ins = bpf_ct_insert_entry(ct); + if (ct_ins) { + struct nf_conn *ct_lk; + + ct_lk = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), + &opts_def, sizeof(opts_def)); + if (ct_lk) { + struct nf_conntrack_tuple *tuple; + + /* check snat and dnat addresses */ + tuple = &ct_lk->tuplehash[IP_CT_DIR_REPLY].tuple; + if (tuple->dst.u3.ip == saddr.ip && + tuple->dst.u.all == bpf_htons(sport)) + test_snat_addr = 0; + if (tuple->src.u3.ip == daddr.ip && + tuple->src.u.all == bpf_htons(dport)) + test_dnat_addr = 0; + + /* update ct entry timeout */ + bpf_ct_change_timeout(ct_lk, 10000); + test_delta_timeout = ct_lk->timeout - bpf_jiffies64(); + test_delta_timeout /= CONFIG_HZ; + test_insert_lookup_mark = ct_lk->mark; + bpf_ct_change_status(ct_lk, + IPS_CONFIRMED | IPS_SEEN_REPLY); + test_status = ct_lk->status; + + bpf_ct_release(ct_lk); + test_succ_lookup = 0; + } + bpf_ct_release(ct_ins); + test_insert_entry = 0; + } + test_alloc_entry = 0; + } + + bpf_tuple.ipv4.saddr = saddr; + bpf_tuple.ipv4.daddr = daddr; + bpf_tuple.ipv4.sport = sport; + bpf_tuple.ipv4.dport = dport; + ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, + sizeof(opts_def)); + if (ct) { + test_exist_lookup = 0; + if (ct->mark == 42) { + ct->mark++; + test_exist_lookup_mark = ct->mark; + } + bpf_ct_release(ct); + } else { + test_exist_lookup = opts_def.error; + } +} + +SEC("xdp") +int nf_xdp_ct_test(struct xdp_md *ctx) +{ + nf_ct_test((void *)bpf_xdp_ct_lookup, (void *)bpf_xdp_ct_alloc, ctx); + return 0; +} + +SEC("tc") +int nf_skb_ct_test(struct __sk_buff *ctx) +{ + nf_ct_test((void *)bpf_skb_ct_lookup, (void *)bpf_skb_ct_alloc, ctx); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c b/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c new file mode 100644 index 0000000000..0e4759ab38 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c @@ -0,0 +1,148 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +struct nf_conn; + +struct bpf_ct_opts___local { + s32 netns_id; + s32 error; + u8 l4proto; + u8 reserved[3]; +} __attribute__((preserve_access_index)); + +struct nf_conn *bpf_skb_ct_alloc(struct __sk_buff *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32) __ksym; +struct nf_conn *bpf_skb_ct_lookup(struct __sk_buff *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32) __ksym; +struct nf_conn *bpf_ct_insert_entry(struct nf_conn *) __ksym; +void bpf_ct_release(struct nf_conn *) __ksym; +void bpf_ct_set_timeout(struct nf_conn *, u32) __ksym; +int bpf_ct_change_timeout(struct nf_conn *, u32) __ksym; +int bpf_ct_set_status(struct nf_conn *, u32) __ksym; +int bpf_ct_change_status(struct nf_conn *, u32) __ksym; + +SEC("?tc") +int alloc_release(struct __sk_buff *ctx) +{ + struct bpf_ct_opts___local opts = {}; + struct bpf_sock_tuple tup = {}; + struct nf_conn *ct; + + ct = bpf_skb_ct_alloc(ctx, &tup, sizeof(tup.ipv4), &opts, sizeof(opts)); + if (!ct) + return 0; + bpf_ct_release(ct); + return 0; +} + +SEC("?tc") +int insert_insert(struct __sk_buff *ctx) +{ + struct bpf_ct_opts___local opts = {}; + struct bpf_sock_tuple tup = {}; + struct nf_conn *ct; + + ct = bpf_skb_ct_alloc(ctx, &tup, sizeof(tup.ipv4), &opts, sizeof(opts)); + if (!ct) + return 0; + ct = bpf_ct_insert_entry(ct); + if (!ct) + return 0; + ct = bpf_ct_insert_entry(ct); + return 0; +} + +SEC("?tc") +int lookup_insert(struct __sk_buff *ctx) +{ + struct bpf_ct_opts___local opts = {}; + struct bpf_sock_tuple tup = {}; + struct nf_conn *ct; + + ct = bpf_skb_ct_lookup(ctx, &tup, sizeof(tup.ipv4), &opts, sizeof(opts)); + if (!ct) + return 0; + bpf_ct_insert_entry(ct); + return 0; +} + +SEC("?tc") +int write_not_allowlisted_field(struct __sk_buff *ctx) +{ + struct bpf_ct_opts___local opts = {}; + struct bpf_sock_tuple tup = {}; + struct nf_conn *ct; + + ct = bpf_skb_ct_lookup(ctx, &tup, sizeof(tup.ipv4), &opts, sizeof(opts)); + if (!ct) + return 0; + ct->status = 0xF00; + return 0; +} + +SEC("?tc") +int set_timeout_after_insert(struct __sk_buff *ctx) +{ + struct bpf_ct_opts___local opts = {}; + struct bpf_sock_tuple tup = {}; + struct nf_conn *ct; + + ct = bpf_skb_ct_alloc(ctx, &tup, sizeof(tup.ipv4), &opts, sizeof(opts)); + if (!ct) + return 0; + ct = bpf_ct_insert_entry(ct); + if (!ct) + return 0; + bpf_ct_set_timeout(ct, 0); + return 0; +} + +SEC("?tc") +int set_status_after_insert(struct __sk_buff *ctx) +{ + struct bpf_ct_opts___local opts = {}; + struct bpf_sock_tuple tup = {}; + struct nf_conn *ct; + + ct = bpf_skb_ct_alloc(ctx, &tup, sizeof(tup.ipv4), &opts, sizeof(opts)); + if (!ct) + return 0; + ct = bpf_ct_insert_entry(ct); + if (!ct) + return 0; + bpf_ct_set_status(ct, 0); + return 0; +} + +SEC("?tc") +int change_timeout_after_alloc(struct __sk_buff *ctx) +{ + struct bpf_ct_opts___local opts = {}; + struct bpf_sock_tuple tup = {}; + struct nf_conn *ct; + + ct = bpf_skb_ct_alloc(ctx, &tup, sizeof(tup.ipv4), &opts, sizeof(opts)); + if (!ct) + return 0; + bpf_ct_change_timeout(ct, 0); + return 0; +} + +SEC("?tc") +int change_status_after_alloc(struct __sk_buff *ctx) +{ + struct bpf_ct_opts___local opts = {}; + struct bpf_sock_tuple tup = {}; + struct nf_conn *ct; + + ct = bpf_skb_ct_alloc(ctx, &tup, sizeof(tup.ipv4), &opts, sizeof(opts)); + if (!ct) + return 0; + bpf_ct_change_status(ct, 0); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_btf_decl_tag.c b/tools/testing/selftests/bpf/progs/test_btf_decl_tag.c new file mode 100644 index 0000000000..c88ccc5352 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_btf_decl_tag.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#if __has_attribute(btf_decl_tag) +#define __tag1 __attribute__((btf_decl_tag("tag1"))) +#define __tag2 __attribute__((btf_decl_tag("tag2"))) +volatile const bool skip_tests __tag1 __tag2 = false; +#else +#define __tag1 +#define __tag2 +volatile const bool skip_tests = true; +#endif + +struct key_t { + int a; + int b __tag1 __tag2; + int c; +} __tag1 __tag2; + +typedef struct { + int a; + int b; +} value_t __tag1 __tag2; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, struct key_t); + __type(value, value_t); +} hashmap1 SEC(".maps"); + + +static __noinline int foo(int x __tag1 __tag2) __tag1 __tag2 +{ + struct key_t key; + value_t val = {}; + + key.a = key.b = key.c = x; + bpf_map_update_elem(&hashmap1, &key, &val, 0); + return 0; +} + +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(sub, int x) +{ + return foo(x); +} diff --git a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c new file mode 100644 index 0000000000..c218cf8989 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c @@ -0,0 +1,150 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2020 Facebook */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct inner_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} inner_map1 SEC(".maps"), + inner_map2 SEC(".maps"); + +struct inner_map_sz2 { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 2); + __type(key, int); + __type(value, int); +} inner_map_sz2 SEC(".maps"); + +struct outer_arr { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 3); + __type(key, int); + __type(value, int); + /* it's possible to use anonymous struct as inner map definition here */ + __array(values, struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + /* changing max_entries to 2 will fail during load + * due to incompatibility with inner_map definition */ + __uint(max_entries, 1); + __type(key, int); + __type(value, int); + }); +} outer_arr SEC(".maps") = { + /* (void *) cast is necessary because we didn't use `struct inner_map` + * in __inner(values, ...) + * Actually, a conscious effort is required to screw up initialization + * of inner map slots, which is a great thing! + */ + .values = { (void *)&inner_map1, 0, (void *)&inner_map2 }, +}; + +struct inner_map_sz3 { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(map_flags, BPF_F_INNER_MAP); + __uint(max_entries, 3); + __type(key, int); + __type(value, int); +} inner_map3 SEC(".maps"), + inner_map4 SEC(".maps"); + +struct inner_map_sz4 { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(map_flags, BPF_F_INNER_MAP); + __uint(max_entries, 5); + __type(key, int); + __type(value, int); +} inner_map5 SEC(".maps"); + +struct outer_arr_dyn { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 3); + __type(key, int); + __type(value, int); + __array(values, struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(map_flags, BPF_F_INNER_MAP); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); + }); +} outer_arr_dyn SEC(".maps") = { + .values = { + [0] = (void *)&inner_map3, + [1] = (void *)&inner_map4, + [2] = (void *)&inner_map5, + }, +}; + +struct outer_hash { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 5); + __type(key, int); + /* Here everything works flawlessly due to reuse of struct inner_map + * and compiler will complain at the attempt to use non-inner_map + * references below. This is great experience. + */ + __array(values, struct inner_map); +} outer_hash SEC(".maps") = { + .values = { + [0] = &inner_map2, + [4] = &inner_map1, + }, +}; + +struct sockarr_sz1 { + __uint(type, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} sockarr_sz1 SEC(".maps"); + +struct sockarr_sz2 { + __uint(type, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY); + __uint(max_entries, 2); + __type(key, int); + __type(value, int); +} sockarr_sz2 SEC(".maps"); + +struct outer_sockarr_sz1 { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); + __array(values, struct sockarr_sz1); +} outer_sockarr SEC(".maps") = { + .values = { (void *)&sockarr_sz1 }, +}; + +int input = 0; + +SEC("raw_tp/sys_enter") +int handle__sys_enter(void *ctx) +{ + struct inner_map *inner_map; + int key = 0, val; + + inner_map = bpf_map_lookup_elem(&outer_arr, &key); + if (!inner_map) + return 1; + val = input; + bpf_map_update_elem(inner_map, &key, &val, 0); + + inner_map = bpf_map_lookup_elem(&outer_hash, &key); + if (!inner_map) + return 1; + val = input + 1; + bpf_map_update_elem(inner_map, &key, &val, 0); + + inner_map = bpf_map_lookup_elem(&outer_arr_dyn, &key); + if (!inner_map) + return 1; + val = input + 2; + bpf_map_update_elem(inner_map, &key, &val, 0); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c new file mode 100644 index 0000000000..251854a041 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_legacy.h" + +struct ipv_counts { + unsigned int v4; + unsigned int v6; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 4); + __type(key, int); + __type(value, struct ipv_counts); +} btf_map SEC(".maps"); + +__attribute__((noinline)) +int test_long_fname_2(void) +{ + struct ipv_counts *counts; + int key = 0; + + counts = bpf_map_lookup_elem(&btf_map, &key); + if (!counts) + return 0; + + counts->v6++; + + return 0; +} + +__attribute__((noinline)) +int test_long_fname_1(void) +{ + return test_long_fname_2(); +} + +SEC("dummy_tracepoint") +int _dummy_tracepoint(void *arg) +{ + return test_long_fname_1(); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c new file mode 100644 index 0000000000..1dabb88f8c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct ipv_counts { + unsigned int v4; + unsigned int v6; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(struct ipv_counts)); + __uint(max_entries, 4); +} btf_map SEC(".maps"); + +__attribute__((noinline)) +int test_long_fname_2(void) +{ + struct ipv_counts *counts; + int key = 0; + + counts = bpf_map_lookup_elem(&btf_map, &key); + if (!counts) + return 0; + + counts->v6++; + + return 0; +} + +__attribute__((noinline)) +int test_long_fname_1(void) +{ + return test_long_fname_2(); +} + +SEC("dummy_tracepoint") +int _dummy_tracepoint(void *arg) +{ + return test_long_fname_1(); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c new file mode 100644 index 0000000000..e2bea4da19 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c @@ -0,0 +1,174 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <string.h> +#include <errno.h> +#include <netinet/in.h> +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include <linux/if_ether.h> +#include <linux/pkt_cls.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include "bpf_tcp_helpers.h" + +struct sockaddr_in6 srv_sa6 = {}; +__u16 listen_tp_sport = 0; +__u16 req_sk_sport = 0; +__u32 recv_cookie = 0; +__u32 gen_cookie = 0; +__u32 linum = 0; + +#define LOG() ({ if (!linum) linum = __LINE__; }) + +static void test_syncookie_helper(struct ipv6hdr *ip6h, struct tcphdr *th, + struct tcp_sock *tp, + struct __sk_buff *skb) +{ + if (th->syn) { + __s64 mss_cookie; + void *data_end; + + data_end = (void *)(long)(skb->data_end); + + if (th->doff * 4 != 40) { + LOG(); + return; + } + + if ((void *)th + 40 > data_end) { + LOG(); + return; + } + + mss_cookie = bpf_tcp_gen_syncookie(tp, ip6h, sizeof(*ip6h), + th, 40); + if (mss_cookie < 0) { + if (mss_cookie != -ENOENT) + LOG(); + } else { + gen_cookie = (__u32)mss_cookie; + } + } else if (gen_cookie) { + /* It was in cookie mode */ + int ret = bpf_tcp_check_syncookie(tp, ip6h, sizeof(*ip6h), + th, sizeof(*th)); + + if (ret < 0) { + if (ret != -ENOENT) + LOG(); + } else { + recv_cookie = bpf_ntohl(th->ack_seq) - 1; + } + } +} + +static int handle_ip6_tcp(struct ipv6hdr *ip6h, struct __sk_buff *skb) +{ + struct bpf_sock_tuple *tuple; + struct bpf_sock *bpf_skc; + unsigned int tuple_len; + struct tcphdr *th; + void *data_end; + + data_end = (void *)(long)(skb->data_end); + + th = (struct tcphdr *)(ip6h + 1); + if (th + 1 > data_end) + return TC_ACT_OK; + + /* Is it the testing traffic? */ + if (th->dest != srv_sa6.sin6_port) + return TC_ACT_OK; + + tuple_len = sizeof(tuple->ipv6); + tuple = (struct bpf_sock_tuple *)&ip6h->saddr; + if ((void *)tuple + tuple_len > data_end) { + LOG(); + return TC_ACT_OK; + } + + bpf_skc = bpf_skc_lookup_tcp(skb, tuple, tuple_len, + BPF_F_CURRENT_NETNS, 0); + if (!bpf_skc) { + LOG(); + return TC_ACT_OK; + } + + if (bpf_skc->state == BPF_TCP_NEW_SYN_RECV) { + struct request_sock *req_sk; + + req_sk = (struct request_sock *)bpf_skc_to_tcp_request_sock(bpf_skc); + if (!req_sk) { + LOG(); + goto release; + } + + if (bpf_sk_assign(skb, req_sk, 0)) { + LOG(); + goto release; + } + + req_sk_sport = req_sk->__req_common.skc_num; + + bpf_sk_release(req_sk); + return TC_ACT_OK; + } else if (bpf_skc->state == BPF_TCP_LISTEN) { + struct tcp_sock *tp; + + tp = bpf_skc_to_tcp_sock(bpf_skc); + if (!tp) { + LOG(); + goto release; + } + + if (bpf_sk_assign(skb, tp, 0)) { + LOG(); + goto release; + } + + listen_tp_sport = tp->inet_conn.icsk_inet.sk.__sk_common.skc_num; + + test_syncookie_helper(ip6h, th, tp, skb); + bpf_sk_release(tp); + return TC_ACT_OK; + } + + if (bpf_sk_assign(skb, bpf_skc, 0)) + LOG(); + +release: + bpf_sk_release(bpf_skc); + return TC_ACT_OK; +} + +SEC("tc") +int cls_ingress(struct __sk_buff *skb) +{ + struct ipv6hdr *ip6h; + struct ethhdr *eth; + void *data_end; + + data_end = (void *)(long)(skb->data_end); + + eth = (struct ethhdr *)(long)(skb->data); + if (eth + 1 > data_end) + return TC_ACT_OK; + + if (eth->h_proto != bpf_htons(ETH_P_IPV6)) + return TC_ACT_OK; + + ip6h = (struct ipv6hdr *)(eth + 1); + if (ip6h + 1 > data_end) + return TC_ACT_OK; + + if (ip6h->nexthdr == IPPROTO_TCP) + return handle_ip6_tcp(ip6h, skb); + + return TC_ACT_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_cgroup_link.c b/tools/testing/selftests/bpf/progs/test_cgroup_link.c new file mode 100644 index 0000000000..4faba88e45 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_cgroup_link.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +int calls = 0; +int alt_calls = 0; + +SEC("cgroup_skb/egress") +int egress(struct __sk_buff *skb) +{ + __sync_fetch_and_add(&calls, 1); + return 1; +} + +SEC("cgroup_skb/egress") +int egress_alt(struct __sk_buff *skb) +{ + __sync_fetch_and_add(&alt_calls, 1); + return 1; +} + +char _license[] SEC("license") = "GPL"; + diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c new file mode 100644 index 0000000000..2ec1de11a3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c @@ -0,0 +1,290 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Jesper Dangaard Brouer */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <linux/if_ether.h> + +#include <stddef.h> +#include <stdint.h> + +char _license[] SEC("license") = "GPL"; + +/* Userspace will update with MTU it can see on device */ +volatile const int GLOBAL_USER_MTU; +volatile const __u32 GLOBAL_USER_IFINDEX; + +/* BPF-prog will update these with MTU values it can see */ +__u32 global_bpf_mtu_xdp = 0; +__u32 global_bpf_mtu_tc = 0; + +SEC("xdp") +int xdp_use_helper_basic(struct xdp_md *ctx) +{ + __u32 mtu_len = 0; + + if (bpf_check_mtu(ctx, 0, &mtu_len, 0, 0)) + return XDP_ABORTED; + + return XDP_PASS; +} + +SEC("xdp") +int xdp_use_helper(struct xdp_md *ctx) +{ + int retval = XDP_PASS; /* Expected retval on successful test */ + __u32 mtu_len = 0; + __u32 ifindex = 0; + int delta = 0; + + /* When ifindex is zero, save net_device lookup and use ctx netdev */ + if (GLOBAL_USER_IFINDEX > 0) + ifindex = GLOBAL_USER_IFINDEX; + + if (bpf_check_mtu(ctx, ifindex, &mtu_len, delta, 0)) { + /* mtu_len is also valid when check fail */ + retval = XDP_ABORTED; + goto out; + } + + if (mtu_len != GLOBAL_USER_MTU) + retval = XDP_DROP; + +out: + global_bpf_mtu_xdp = mtu_len; + return retval; +} + +SEC("xdp") +int xdp_exceed_mtu(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + __u32 ifindex = GLOBAL_USER_IFINDEX; + __u32 data_len = data_end - data; + int retval = XDP_ABORTED; /* Fail */ + __u32 mtu_len = 0; + int delta; + int err; + + /* Exceed MTU with 1 via delta adjust */ + delta = GLOBAL_USER_MTU - (data_len - ETH_HLEN) + 1; + + err = bpf_check_mtu(ctx, ifindex, &mtu_len, delta, 0); + if (err) { + retval = XDP_PASS; /* Success in exceeding MTU check */ + if (err != BPF_MTU_CHK_RET_FRAG_NEEDED) + retval = XDP_DROP; + } + + global_bpf_mtu_xdp = mtu_len; + return retval; +} + +SEC("xdp") +int xdp_minus_delta(struct xdp_md *ctx) +{ + int retval = XDP_PASS; /* Expected retval on successful test */ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + __u32 ifindex = GLOBAL_USER_IFINDEX; + __u32 data_len = data_end - data; + __u32 mtu_len = 0; + int delta; + + /* Borderline test case: Minus delta exceeding packet length allowed */ + delta = -((data_len - ETH_HLEN) + 1); + + /* Minus length (adjusted via delta) still pass MTU check, other helpers + * are responsible for catching this, when doing actual size adjust + */ + if (bpf_check_mtu(ctx, ifindex, &mtu_len, delta, 0)) + retval = XDP_ABORTED; + + global_bpf_mtu_xdp = mtu_len; + return retval; +} + +SEC("xdp") +int xdp_input_len(struct xdp_md *ctx) +{ + int retval = XDP_PASS; /* Expected retval on successful test */ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + __u32 ifindex = GLOBAL_USER_IFINDEX; + __u32 data_len = data_end - data; + + /* API allow user give length to check as input via mtu_len param, + * resulting MTU value is still output in mtu_len param after call. + * + * Input len is L3, like MTU and iph->tot_len. + * Remember XDP data_len is L2. + */ + __u32 mtu_len = data_len - ETH_HLEN; + + if (bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0)) + retval = XDP_ABORTED; + + global_bpf_mtu_xdp = mtu_len; + return retval; +} + +SEC("xdp") +int xdp_input_len_exceed(struct xdp_md *ctx) +{ + int retval = XDP_ABORTED; /* Fail */ + __u32 ifindex = GLOBAL_USER_IFINDEX; + int err; + + /* API allow user give length to check as input via mtu_len param, + * resulting MTU value is still output in mtu_len param after call. + * + * Input length value is L3 size like MTU. + */ + __u32 mtu_len = GLOBAL_USER_MTU; + + mtu_len += 1; /* Exceed with 1 */ + + err = bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0); + if (err == BPF_MTU_CHK_RET_FRAG_NEEDED) + retval = XDP_PASS ; /* Success in exceeding MTU check */ + + global_bpf_mtu_xdp = mtu_len; + return retval; +} + +SEC("tc") +int tc_use_helper(struct __sk_buff *ctx) +{ + int retval = BPF_OK; /* Expected retval on successful test */ + __u32 mtu_len = 0; + int delta = 0; + + if (bpf_check_mtu(ctx, 0, &mtu_len, delta, 0)) { + retval = BPF_DROP; + goto out; + } + + if (mtu_len != GLOBAL_USER_MTU) + retval = BPF_REDIRECT; +out: + global_bpf_mtu_tc = mtu_len; + return retval; +} + +SEC("tc") +int tc_exceed_mtu(struct __sk_buff *ctx) +{ + __u32 ifindex = GLOBAL_USER_IFINDEX; + int retval = BPF_DROP; /* Fail */ + __u32 skb_len = ctx->len; + __u32 mtu_len = 0; + int delta; + int err; + + /* Exceed MTU with 1 via delta adjust */ + delta = GLOBAL_USER_MTU - (skb_len - ETH_HLEN) + 1; + + err = bpf_check_mtu(ctx, ifindex, &mtu_len, delta, 0); + if (err) { + retval = BPF_OK; /* Success in exceeding MTU check */ + if (err != BPF_MTU_CHK_RET_FRAG_NEEDED) + retval = BPF_DROP; + } + + global_bpf_mtu_tc = mtu_len; + return retval; +} + +SEC("tc") +int tc_exceed_mtu_da(struct __sk_buff *ctx) +{ + /* SKB Direct-Access variant */ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + __u32 ifindex = GLOBAL_USER_IFINDEX; + __u32 data_len = data_end - data; + int retval = BPF_DROP; /* Fail */ + __u32 mtu_len = 0; + int delta; + int err; + + /* Exceed MTU with 1 via delta adjust */ + delta = GLOBAL_USER_MTU - (data_len - ETH_HLEN) + 1; + + err = bpf_check_mtu(ctx, ifindex, &mtu_len, delta, 0); + if (err) { + retval = BPF_OK; /* Success in exceeding MTU check */ + if (err != BPF_MTU_CHK_RET_FRAG_NEEDED) + retval = BPF_DROP; + } + + global_bpf_mtu_tc = mtu_len; + return retval; +} + +SEC("tc") +int tc_minus_delta(struct __sk_buff *ctx) +{ + int retval = BPF_OK; /* Expected retval on successful test */ + __u32 ifindex = GLOBAL_USER_IFINDEX; + __u32 skb_len = ctx->len; + __u32 mtu_len = 0; + int delta; + + /* Borderline test case: Minus delta exceeding packet length allowed */ + delta = -((skb_len - ETH_HLEN) + 1); + + /* Minus length (adjusted via delta) still pass MTU check, other helpers + * are responsible for catching this, when doing actual size adjust + */ + if (bpf_check_mtu(ctx, ifindex, &mtu_len, delta, 0)) + retval = BPF_DROP; + + global_bpf_mtu_xdp = mtu_len; + return retval; +} + +SEC("tc") +int tc_input_len(struct __sk_buff *ctx) +{ + int retval = BPF_OK; /* Expected retval on successful test */ + __u32 ifindex = GLOBAL_USER_IFINDEX; + + /* API allow user give length to check as input via mtu_len param, + * resulting MTU value is still output in mtu_len param after call. + * + * Input length value is L3 size. + */ + __u32 mtu_len = GLOBAL_USER_MTU; + + if (bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0)) + retval = BPF_DROP; + + global_bpf_mtu_xdp = mtu_len; + return retval; +} + +SEC("tc") +int tc_input_len_exceed(struct __sk_buff *ctx) +{ + int retval = BPF_DROP; /* Fail */ + __u32 ifindex = GLOBAL_USER_IFINDEX; + int err; + + /* API allow user give length to check as input via mtu_len param, + * resulting MTU value is still output in mtu_len param after call. + * + * Input length value is L3 size like MTU. + */ + __u32 mtu_len = GLOBAL_USER_MTU; + + mtu_len += 1; /* Exceed with 1 */ + + err = bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0); + if (err == BPF_MTU_CHK_RET_FRAG_NEEDED) + retval = BPF_OK; /* Success in exceeding MTU check */ + + global_bpf_mtu_xdp = mtu_len; + return retval; +} diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c new file mode 100644 index 0000000000..66b3049822 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c @@ -0,0 +1,1075 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// Copyright (c) 2019, 2020 Cloudflare + +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> +#include <string.h> + +#include <linux/bpf.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/pkt_cls.h> +#include <linux/tcp.h> +#include <linux/udp.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include "test_cls_redirect.h" + +#ifdef SUBPROGS +#define INLINING __noinline +#else +#define INLINING __always_inline +#endif + +#define offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER))) + +#define IP_OFFSET_MASK (0x1FFF) +#define IP_MF (0x2000) + +char _license[] SEC("license") = "Dual BSD/GPL"; + +/** + * Destination port and IP used for UDP encapsulation. + */ +volatile const __be16 ENCAPSULATION_PORT; +volatile const __be32 ENCAPSULATION_IP; + +typedef struct { + uint64_t processed_packets_total; + uint64_t l3_protocol_packets_total_ipv4; + uint64_t l3_protocol_packets_total_ipv6; + uint64_t l4_protocol_packets_total_tcp; + uint64_t l4_protocol_packets_total_udp; + uint64_t accepted_packets_total_syn; + uint64_t accepted_packets_total_syn_cookies; + uint64_t accepted_packets_total_last_hop; + uint64_t accepted_packets_total_icmp_echo_request; + uint64_t accepted_packets_total_established; + uint64_t forwarded_packets_total_gue; + uint64_t forwarded_packets_total_gre; + + uint64_t errors_total_unknown_l3_proto; + uint64_t errors_total_unknown_l4_proto; + uint64_t errors_total_malformed_ip; + uint64_t errors_total_fragmented_ip; + uint64_t errors_total_malformed_icmp; + uint64_t errors_total_unwanted_icmp; + uint64_t errors_total_malformed_icmp_pkt_too_big; + uint64_t errors_total_malformed_tcp; + uint64_t errors_total_malformed_udp; + uint64_t errors_total_icmp_echo_replies; + uint64_t errors_total_malformed_encapsulation; + uint64_t errors_total_encap_adjust_failed; + uint64_t errors_total_encap_buffer_too_small; + uint64_t errors_total_redirect_loop; + uint64_t errors_total_encap_mtu_violate; +} metrics_t; + +typedef enum { + INVALID = 0, + UNKNOWN, + ECHO_REQUEST, + SYN, + SYN_COOKIE, + ESTABLISHED, +} verdict_t; + +typedef struct { + uint16_t src, dst; +} flow_ports_t; + +_Static_assert( + sizeof(flow_ports_t) != + offsetofend(struct bpf_sock_tuple, ipv4.dport) - + offsetof(struct bpf_sock_tuple, ipv4.sport) - 1, + "flow_ports_t must match sport and dport in struct bpf_sock_tuple"); +_Static_assert( + sizeof(flow_ports_t) != + offsetofend(struct bpf_sock_tuple, ipv6.dport) - + offsetof(struct bpf_sock_tuple, ipv6.sport) - 1, + "flow_ports_t must match sport and dport in struct bpf_sock_tuple"); + +typedef int ret_t; + +/* This is a bit of a hack. We need a return value which allows us to + * indicate that the regular flow of the program should continue, + * while allowing functions to use XDP_PASS and XDP_DROP, etc. + */ +static const ret_t CONTINUE_PROCESSING = -1; + +/* Convenience macro to call functions which return ret_t. + */ +#define MAYBE_RETURN(x) \ + do { \ + ret_t __ret = x; \ + if (__ret != CONTINUE_PROCESSING) \ + return __ret; \ + } while (0) + +/* Linux packet pointers are either aligned to NET_IP_ALIGN (aka 2 bytes), + * or not aligned if the arch supports efficient unaligned access. + * + * Since the verifier ensures that eBPF packet accesses follow these rules, + * we can tell LLVM to emit code as if we always had a larger alignment. + * It will yell at us if we end up on a platform where this is not valid. + */ +typedef uint8_t *net_ptr __attribute__((align_value(8))); + +typedef struct buf { + struct __sk_buff *skb; + net_ptr head; + /* NB: tail musn't have alignment other than 1, otherwise + * LLVM will go and eliminate code, e.g. when checking packet lengths. + */ + uint8_t *const tail; +} buf_t; + +static __always_inline size_t buf_off(const buf_t *buf) +{ + /* Clang seems to optimize constructs like + * a - b + c + * if c is known: + * r? = c + * r? -= b + * r? += a + * + * This is a problem if a and b are packet pointers, + * since the verifier allows subtracting two pointers to + * get a scalar, but not a scalar and a pointer. + * + * Use inline asm to break this optimization. + */ + size_t off = (size_t)buf->head; + asm("%0 -= %1" : "+r"(off) : "r"(buf->skb->data)); + return off; +} + +static __always_inline bool buf_copy(buf_t *buf, void *dst, size_t len) +{ + if (bpf_skb_load_bytes(buf->skb, buf_off(buf), dst, len)) { + return false; + } + + buf->head += len; + return true; +} + +static __always_inline bool buf_skip(buf_t *buf, const size_t len) +{ + /* Check whether off + len is valid in the non-linear part. */ + if (buf_off(buf) + len > buf->skb->len) { + return false; + } + + buf->head += len; + return true; +} + +/* Returns a pointer to the start of buf, or NULL if len is + * larger than the remaining data. Consumes len bytes on a successful + * call. + * + * If scratch is not NULL, the function will attempt to load non-linear + * data via bpf_skb_load_bytes. On success, scratch is returned. + */ +static __always_inline void *buf_assign(buf_t *buf, const size_t len, void *scratch) +{ + if (buf->head + len > buf->tail) { + if (scratch == NULL) { + return NULL; + } + + return buf_copy(buf, scratch, len) ? scratch : NULL; + } + + void *ptr = buf->head; + buf->head += len; + return ptr; +} + +static INLINING bool pkt_skip_ipv4_options(buf_t *buf, const struct iphdr *ipv4) +{ + if (ipv4->ihl <= 5) { + return true; + } + + return buf_skip(buf, (ipv4->ihl - 5) * 4); +} + +static INLINING bool ipv4_is_fragment(const struct iphdr *ip) +{ + uint16_t frag_off = ip->frag_off & bpf_htons(IP_OFFSET_MASK); + return (ip->frag_off & bpf_htons(IP_MF)) != 0 || frag_off > 0; +} + +static __always_inline struct iphdr *pkt_parse_ipv4(buf_t *pkt, struct iphdr *scratch) +{ + struct iphdr *ipv4 = buf_assign(pkt, sizeof(*ipv4), scratch); + if (ipv4 == NULL) { + return NULL; + } + + if (ipv4->ihl < 5) { + return NULL; + } + + if (!pkt_skip_ipv4_options(pkt, ipv4)) { + return NULL; + } + + return ipv4; +} + +/* Parse the L4 ports from a packet, assuming a layout like TCP or UDP. */ +static INLINING bool pkt_parse_icmp_l4_ports(buf_t *pkt, flow_ports_t *ports) +{ + if (!buf_copy(pkt, ports, sizeof(*ports))) { + return false; + } + + /* Ports in the L4 headers are reversed, since we are parsing an ICMP + * payload which is going towards the eyeball. + */ + uint16_t dst = ports->src; + ports->src = ports->dst; + ports->dst = dst; + return true; +} + +static INLINING uint16_t pkt_checksum_fold(uint32_t csum) +{ + /* The highest reasonable value for an IPv4 header + * checksum requires two folds, so we just do that always. + */ + csum = (csum & 0xffff) + (csum >> 16); + csum = (csum & 0xffff) + (csum >> 16); + return (uint16_t)~csum; +} + +static INLINING void pkt_ipv4_checksum(struct iphdr *iph) +{ + iph->check = 0; + + /* An IP header without options is 20 bytes. Two of those + * are the checksum, which we always set to zero. Hence, + * the maximum accumulated value is 18 / 2 * 0xffff = 0x8fff7, + * which fits in 32 bit. + */ + _Static_assert(sizeof(struct iphdr) == 20, "iphdr must be 20 bytes"); + uint32_t acc = 0; + uint16_t *ipw = (uint16_t *)iph; + +#pragma clang loop unroll(full) + for (size_t i = 0; i < sizeof(struct iphdr) / 2; i++) { + acc += ipw[i]; + } + + iph->check = pkt_checksum_fold(acc); +} + +static INLINING +bool pkt_skip_ipv6_extension_headers(buf_t *pkt, + const struct ipv6hdr *ipv6, + uint8_t *upper_proto, + bool *is_fragment) +{ + /* We understand five extension headers. + * https://tools.ietf.org/html/rfc8200#section-4.1 states that all + * headers should occur once, except Destination Options, which may + * occur twice. Hence we give up after 6 headers. + */ + struct { + uint8_t next; + uint8_t len; + } exthdr = { + .next = ipv6->nexthdr, + }; + *is_fragment = false; + +#pragma clang loop unroll(full) + for (int i = 0; i < 6; i++) { + switch (exthdr.next) { + case IPPROTO_FRAGMENT: + *is_fragment = true; + /* NB: We don't check that hdrlen == 0 as per spec. */ + /* fallthrough; */ + + case IPPROTO_HOPOPTS: + case IPPROTO_ROUTING: + case IPPROTO_DSTOPTS: + case IPPROTO_MH: + if (!buf_copy(pkt, &exthdr, sizeof(exthdr))) { + return false; + } + + /* hdrlen is in 8-octet units, and excludes the first 8 octets. */ + if (!buf_skip(pkt, + (exthdr.len + 1) * 8 - sizeof(exthdr))) { + return false; + } + + /* Decode next header */ + break; + + default: + /* The next header is not one of the known extension + * headers, treat it as the upper layer header. + * + * This handles IPPROTO_NONE. + * + * Encapsulating Security Payload (50) and Authentication + * Header (51) also end up here (and will trigger an + * unknown proto error later). They have a custom header + * format and seem too esoteric to care about. + */ + *upper_proto = exthdr.next; + return true; + } + } + + /* We never found an upper layer header. */ + return false; +} + +/* This function has to be inlined, because the verifier otherwise rejects it + * due to returning a pointer to the stack. This is technically correct, since + * scratch is allocated on the stack. However, this usage should be safe since + * it's the callers stack after all. + */ +static __always_inline struct ipv6hdr * +pkt_parse_ipv6(buf_t *pkt, struct ipv6hdr *scratch, uint8_t *proto, + bool *is_fragment) +{ + struct ipv6hdr *ipv6 = buf_assign(pkt, sizeof(*ipv6), scratch); + if (ipv6 == NULL) { + return NULL; + } + + if (!pkt_skip_ipv6_extension_headers(pkt, ipv6, proto, is_fragment)) { + return NULL; + } + + return ipv6; +} + +/* Global metrics, per CPU + */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, unsigned int); + __type(value, metrics_t); +} metrics_map SEC(".maps"); + +static INLINING metrics_t *get_global_metrics(void) +{ + uint64_t key = 0; + return bpf_map_lookup_elem(&metrics_map, &key); +} + +static INLINING ret_t accept_locally(struct __sk_buff *skb, encap_headers_t *encap) +{ + const int payload_off = + sizeof(*encap) + + sizeof(struct in_addr) * encap->unigue.hop_count; + int32_t encap_overhead = payload_off - sizeof(struct ethhdr); + + // Changing the ethertype if the encapsulated packet is ipv6 + if (encap->gue.proto_ctype == IPPROTO_IPV6) { + encap->eth.h_proto = bpf_htons(ETH_P_IPV6); + } + + if (bpf_skb_adjust_room(skb, -encap_overhead, BPF_ADJ_ROOM_MAC, + BPF_F_ADJ_ROOM_FIXED_GSO | + BPF_F_ADJ_ROOM_NO_CSUM_RESET) || + bpf_csum_level(skb, BPF_CSUM_LEVEL_DEC)) + return TC_ACT_SHOT; + + return bpf_redirect(skb->ifindex, BPF_F_INGRESS); +} + +static INLINING ret_t forward_with_gre(struct __sk_buff *skb, encap_headers_t *encap, + struct in_addr *next_hop, metrics_t *metrics) +{ + metrics->forwarded_packets_total_gre++; + + const int payload_off = + sizeof(*encap) + + sizeof(struct in_addr) * encap->unigue.hop_count; + int32_t encap_overhead = + payload_off - sizeof(struct ethhdr) - sizeof(struct iphdr); + int32_t delta = sizeof(struct gre_base_hdr) - encap_overhead; + uint16_t proto = ETH_P_IP; + uint32_t mtu_len = 0; + + /* Loop protection: the inner packet's TTL is decremented as a safeguard + * against any forwarding loop. As the only interesting field is the TTL + * hop limit for IPv6, it is easier to use bpf_skb_load_bytes/bpf_skb_store_bytes + * as they handle the split packets if needed (no need for the data to be + * in the linear section). + */ + if (encap->gue.proto_ctype == IPPROTO_IPV6) { + proto = ETH_P_IPV6; + uint8_t ttl; + int rc; + + rc = bpf_skb_load_bytes( + skb, payload_off + offsetof(struct ipv6hdr, hop_limit), + &ttl, 1); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (ttl == 0) { + metrics->errors_total_redirect_loop++; + return TC_ACT_SHOT; + } + + ttl--; + rc = bpf_skb_store_bytes( + skb, payload_off + offsetof(struct ipv6hdr, hop_limit), + &ttl, 1, 0); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + } else { + uint8_t ttl; + int rc; + + rc = bpf_skb_load_bytes( + skb, payload_off + offsetof(struct iphdr, ttl), &ttl, + 1); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (ttl == 0) { + metrics->errors_total_redirect_loop++; + return TC_ACT_SHOT; + } + + /* IPv4 also has a checksum to patch. While the TTL is only one byte, + * this function only works for 2 and 4 bytes arguments (the result is + * the same). + */ + rc = bpf_l3_csum_replace( + skb, payload_off + offsetof(struct iphdr, check), ttl, + ttl - 1, 2); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + ttl--; + rc = bpf_skb_store_bytes( + skb, payload_off + offsetof(struct iphdr, ttl), &ttl, 1, + 0); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + } + + if (bpf_check_mtu(skb, skb->ifindex, &mtu_len, delta, 0)) { + metrics->errors_total_encap_mtu_violate++; + return TC_ACT_SHOT; + } + + if (bpf_skb_adjust_room(skb, delta, BPF_ADJ_ROOM_NET, + BPF_F_ADJ_ROOM_FIXED_GSO | + BPF_F_ADJ_ROOM_NO_CSUM_RESET) || + bpf_csum_level(skb, BPF_CSUM_LEVEL_INC)) { + metrics->errors_total_encap_adjust_failed++; + return TC_ACT_SHOT; + } + + if (bpf_skb_pull_data(skb, sizeof(encap_gre_t))) { + metrics->errors_total_encap_buffer_too_small++; + return TC_ACT_SHOT; + } + + buf_t pkt = { + .skb = skb, + .head = (uint8_t *)(long)skb->data, + .tail = (uint8_t *)(long)skb->data_end, + }; + + encap_gre_t *encap_gre = buf_assign(&pkt, sizeof(encap_gre_t), NULL); + if (encap_gre == NULL) { + metrics->errors_total_encap_buffer_too_small++; + return TC_ACT_SHOT; + } + + encap_gre->ip.protocol = IPPROTO_GRE; + encap_gre->ip.daddr = next_hop->s_addr; + encap_gre->ip.saddr = ENCAPSULATION_IP; + encap_gre->ip.tot_len = + bpf_htons(bpf_ntohs(encap_gre->ip.tot_len) + delta); + encap_gre->gre.flags = 0; + encap_gre->gre.protocol = bpf_htons(proto); + pkt_ipv4_checksum((void *)&encap_gre->ip); + + return bpf_redirect(skb->ifindex, 0); +} + +static INLINING ret_t forward_to_next_hop(struct __sk_buff *skb, encap_headers_t *encap, + struct in_addr *next_hop, metrics_t *metrics) +{ + /* swap L2 addresses */ + /* This assumes that packets are received from a router. + * So just swapping the MAC addresses here will make the packet go back to + * the router, which will send it to the appropriate machine. + */ + unsigned char temp[ETH_ALEN]; + memcpy(temp, encap->eth.h_dest, sizeof(temp)); + memcpy(encap->eth.h_dest, encap->eth.h_source, + sizeof(encap->eth.h_dest)); + memcpy(encap->eth.h_source, temp, sizeof(encap->eth.h_source)); + + if (encap->unigue.next_hop == encap->unigue.hop_count - 1 && + encap->unigue.last_hop_gre) { + return forward_with_gre(skb, encap, next_hop, metrics); + } + + metrics->forwarded_packets_total_gue++; + uint32_t old_saddr = encap->ip.saddr; + encap->ip.saddr = encap->ip.daddr; + encap->ip.daddr = next_hop->s_addr; + if (encap->unigue.next_hop < encap->unigue.hop_count) { + encap->unigue.next_hop++; + } + + /* Remove ip->saddr, add next_hop->s_addr */ + const uint64_t off = offsetof(typeof(*encap), ip.check); + int ret = bpf_l3_csum_replace(skb, off, old_saddr, next_hop->s_addr, 4); + if (ret < 0) { + return TC_ACT_SHOT; + } + + return bpf_redirect(skb->ifindex, 0); +} + +static INLINING ret_t skip_next_hops(buf_t *pkt, int n) +{ + switch (n) { + case 1: + if (!buf_skip(pkt, sizeof(struct in_addr))) + return TC_ACT_SHOT; + case 0: + return CONTINUE_PROCESSING; + + default: + return TC_ACT_SHOT; + } +} + +/* Get the next hop from the GLB header. + * + * Sets next_hop->s_addr to 0 if there are no more hops left. + * pkt is positioned just after the variable length GLB header + * iff the call is successful. + */ +static INLINING ret_t get_next_hop(buf_t *pkt, encap_headers_t *encap, + struct in_addr *next_hop) +{ + if (encap->unigue.next_hop > encap->unigue.hop_count) { + return TC_ACT_SHOT; + } + + /* Skip "used" next hops. */ + MAYBE_RETURN(skip_next_hops(pkt, encap->unigue.next_hop)); + + if (encap->unigue.next_hop == encap->unigue.hop_count) { + /* No more next hops, we are at the end of the GLB header. */ + next_hop->s_addr = 0; + return CONTINUE_PROCESSING; + } + + if (!buf_copy(pkt, next_hop, sizeof(*next_hop))) { + return TC_ACT_SHOT; + } + + /* Skip the remaining next hops (may be zero). */ + return skip_next_hops(pkt, encap->unigue.hop_count - + encap->unigue.next_hop - 1); +} + +/* Fill a bpf_sock_tuple to be used with the socket lookup functions. + * This is a kludge that let's us work around verifier limitations: + * + * fill_tuple(&t, foo, sizeof(struct iphdr), 123, 321) + * + * clang will substitute a constant for sizeof, which allows the verifier + * to track its value. Based on this, it can figure out the constant + * return value, and calling code works while still being "generic" to + * IPv4 and IPv6. + */ +static INLINING uint64_t fill_tuple(struct bpf_sock_tuple *tuple, void *iph, + uint64_t iphlen, uint16_t sport, uint16_t dport) +{ + switch (iphlen) { + case sizeof(struct iphdr): { + struct iphdr *ipv4 = (struct iphdr *)iph; + tuple->ipv4.daddr = ipv4->daddr; + tuple->ipv4.saddr = ipv4->saddr; + tuple->ipv4.sport = sport; + tuple->ipv4.dport = dport; + return sizeof(tuple->ipv4); + } + + case sizeof(struct ipv6hdr): { + struct ipv6hdr *ipv6 = (struct ipv6hdr *)iph; + memcpy(&tuple->ipv6.daddr, &ipv6->daddr, + sizeof(tuple->ipv6.daddr)); + memcpy(&tuple->ipv6.saddr, &ipv6->saddr, + sizeof(tuple->ipv6.saddr)); + tuple->ipv6.sport = sport; + tuple->ipv6.dport = dport; + return sizeof(tuple->ipv6); + } + + default: + return 0; + } +} + +static INLINING verdict_t classify_tcp(struct __sk_buff *skb, + struct bpf_sock_tuple *tuple, uint64_t tuplen, + void *iph, struct tcphdr *tcp) +{ + struct bpf_sock *sk = + bpf_skc_lookup_tcp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0); + if (sk == NULL) { + return UNKNOWN; + } + + if (sk->state != BPF_TCP_LISTEN) { + bpf_sk_release(sk); + return ESTABLISHED; + } + + if (iph != NULL && tcp != NULL) { + /* Kludge: we've run out of arguments, but need the length of the ip header. */ + uint64_t iphlen = sizeof(struct iphdr); + if (tuplen == sizeof(tuple->ipv6)) { + iphlen = sizeof(struct ipv6hdr); + } + + if (bpf_tcp_check_syncookie(sk, iph, iphlen, tcp, + sizeof(*tcp)) == 0) { + bpf_sk_release(sk); + return SYN_COOKIE; + } + } + + bpf_sk_release(sk); + return UNKNOWN; +} + +static INLINING verdict_t classify_udp(struct __sk_buff *skb, + struct bpf_sock_tuple *tuple, uint64_t tuplen) +{ + struct bpf_sock *sk = + bpf_sk_lookup_udp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0); + if (sk == NULL) { + return UNKNOWN; + } + + if (sk->state == BPF_TCP_ESTABLISHED) { + bpf_sk_release(sk); + return ESTABLISHED; + } + + bpf_sk_release(sk); + return UNKNOWN; +} + +static INLINING verdict_t classify_icmp(struct __sk_buff *skb, uint8_t proto, + struct bpf_sock_tuple *tuple, uint64_t tuplen, + metrics_t *metrics) +{ + switch (proto) { + case IPPROTO_TCP: + return classify_tcp(skb, tuple, tuplen, NULL, NULL); + + case IPPROTO_UDP: + return classify_udp(skb, tuple, tuplen); + + default: + metrics->errors_total_malformed_icmp++; + return INVALID; + } +} + +static INLINING verdict_t process_icmpv4(buf_t *pkt, metrics_t *metrics) +{ + struct icmphdr icmp; + if (!buf_copy(pkt, &icmp, sizeof(icmp))) { + metrics->errors_total_malformed_icmp++; + return INVALID; + } + + /* We should never receive encapsulated echo replies. */ + if (icmp.type == ICMP_ECHOREPLY) { + metrics->errors_total_icmp_echo_replies++; + return INVALID; + } + + if (icmp.type == ICMP_ECHO) { + return ECHO_REQUEST; + } + + if (icmp.type != ICMP_DEST_UNREACH || icmp.code != ICMP_FRAG_NEEDED) { + metrics->errors_total_unwanted_icmp++; + return INVALID; + } + + struct iphdr _ip4; + const struct iphdr *ipv4 = pkt_parse_ipv4(pkt, &_ip4); + if (ipv4 == NULL) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + /* The source address in the outer IP header is from the entity that + * originated the ICMP message. Use the original IP header to restore + * the correct flow tuple. + */ + struct bpf_sock_tuple tuple; + tuple.ipv4.saddr = ipv4->daddr; + tuple.ipv4.daddr = ipv4->saddr; + + if (!pkt_parse_icmp_l4_ports(pkt, (flow_ports_t *)&tuple.ipv4.sport)) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + return classify_icmp(pkt->skb, ipv4->protocol, &tuple, + sizeof(tuple.ipv4), metrics); +} + +static INLINING verdict_t process_icmpv6(buf_t *pkt, metrics_t *metrics) +{ + struct icmp6hdr icmp6; + if (!buf_copy(pkt, &icmp6, sizeof(icmp6))) { + metrics->errors_total_malformed_icmp++; + return INVALID; + } + + /* We should never receive encapsulated echo replies. */ + if (icmp6.icmp6_type == ICMPV6_ECHO_REPLY) { + metrics->errors_total_icmp_echo_replies++; + return INVALID; + } + + if (icmp6.icmp6_type == ICMPV6_ECHO_REQUEST) { + return ECHO_REQUEST; + } + + if (icmp6.icmp6_type != ICMPV6_PKT_TOOBIG) { + metrics->errors_total_unwanted_icmp++; + return INVALID; + } + + bool is_fragment; + uint8_t l4_proto; + struct ipv6hdr _ipv6; + const struct ipv6hdr *ipv6 = + pkt_parse_ipv6(pkt, &_ipv6, &l4_proto, &is_fragment); + if (ipv6 == NULL) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + if (is_fragment) { + metrics->errors_total_fragmented_ip++; + return INVALID; + } + + /* Swap source and dest addresses. */ + struct bpf_sock_tuple tuple; + memcpy(&tuple.ipv6.saddr, &ipv6->daddr, sizeof(tuple.ipv6.saddr)); + memcpy(&tuple.ipv6.daddr, &ipv6->saddr, sizeof(tuple.ipv6.daddr)); + + if (!pkt_parse_icmp_l4_ports(pkt, (flow_ports_t *)&tuple.ipv6.sport)) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + return classify_icmp(pkt->skb, l4_proto, &tuple, sizeof(tuple.ipv6), + metrics); +} + +static INLINING verdict_t process_tcp(buf_t *pkt, void *iph, uint64_t iphlen, + metrics_t *metrics) +{ + metrics->l4_protocol_packets_total_tcp++; + + struct tcphdr _tcp; + struct tcphdr *tcp = buf_assign(pkt, sizeof(_tcp), &_tcp); + if (tcp == NULL) { + metrics->errors_total_malformed_tcp++; + return INVALID; + } + + if (tcp->syn) { + return SYN; + } + + struct bpf_sock_tuple tuple; + uint64_t tuplen = + fill_tuple(&tuple, iph, iphlen, tcp->source, tcp->dest); + return classify_tcp(pkt->skb, &tuple, tuplen, iph, tcp); +} + +static INLINING verdict_t process_udp(buf_t *pkt, void *iph, uint64_t iphlen, + metrics_t *metrics) +{ + metrics->l4_protocol_packets_total_udp++; + + struct udphdr _udp; + struct udphdr *udph = buf_assign(pkt, sizeof(_udp), &_udp); + if (udph == NULL) { + metrics->errors_total_malformed_udp++; + return INVALID; + } + + struct bpf_sock_tuple tuple; + uint64_t tuplen = + fill_tuple(&tuple, iph, iphlen, udph->source, udph->dest); + return classify_udp(pkt->skb, &tuple, tuplen); +} + +static INLINING verdict_t process_ipv4(buf_t *pkt, metrics_t *metrics) +{ + metrics->l3_protocol_packets_total_ipv4++; + + struct iphdr _ip4; + struct iphdr *ipv4 = pkt_parse_ipv4(pkt, &_ip4); + if (ipv4 == NULL) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (ipv4->version != 4) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (ipv4_is_fragment(ipv4)) { + metrics->errors_total_fragmented_ip++; + return INVALID; + } + + switch (ipv4->protocol) { + case IPPROTO_ICMP: + return process_icmpv4(pkt, metrics); + + case IPPROTO_TCP: + return process_tcp(pkt, ipv4, sizeof(*ipv4), metrics); + + case IPPROTO_UDP: + return process_udp(pkt, ipv4, sizeof(*ipv4), metrics); + + default: + metrics->errors_total_unknown_l4_proto++; + return INVALID; + } +} + +static INLINING verdict_t process_ipv6(buf_t *pkt, metrics_t *metrics) +{ + metrics->l3_protocol_packets_total_ipv6++; + + uint8_t l4_proto; + bool is_fragment; + struct ipv6hdr _ipv6; + struct ipv6hdr *ipv6 = + pkt_parse_ipv6(pkt, &_ipv6, &l4_proto, &is_fragment); + if (ipv6 == NULL) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (ipv6->version != 6) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (is_fragment) { + metrics->errors_total_fragmented_ip++; + return INVALID; + } + + switch (l4_proto) { + case IPPROTO_ICMPV6: + return process_icmpv6(pkt, metrics); + + case IPPROTO_TCP: + return process_tcp(pkt, ipv6, sizeof(*ipv6), metrics); + + case IPPROTO_UDP: + return process_udp(pkt, ipv6, sizeof(*ipv6), metrics); + + default: + metrics->errors_total_unknown_l4_proto++; + return INVALID; + } +} + +SEC("tc") +int cls_redirect(struct __sk_buff *skb) +{ + metrics_t *metrics = get_global_metrics(); + if (metrics == NULL) { + return TC_ACT_SHOT; + } + + metrics->processed_packets_total++; + + /* Pass bogus packets as long as we're not sure they're + * destined for us. + */ + if (skb->protocol != bpf_htons(ETH_P_IP)) { + return TC_ACT_OK; + } + + encap_headers_t *encap; + + /* Make sure that all encapsulation headers are available in + * the linear portion of the skb. This makes it easy to manipulate them. + */ + if (bpf_skb_pull_data(skb, sizeof(*encap))) { + return TC_ACT_OK; + } + + buf_t pkt = { + .skb = skb, + .head = (uint8_t *)(long)skb->data, + .tail = (uint8_t *)(long)skb->data_end, + }; + + encap = buf_assign(&pkt, sizeof(*encap), NULL); + if (encap == NULL) { + return TC_ACT_OK; + } + + if (encap->ip.ihl != 5) { + /* We never have any options. */ + return TC_ACT_OK; + } + + if (encap->ip.daddr != ENCAPSULATION_IP || + encap->ip.protocol != IPPROTO_UDP) { + return TC_ACT_OK; + } + + /* TODO Check UDP length? */ + if (encap->udp.dest != ENCAPSULATION_PORT) { + return TC_ACT_OK; + } + + /* We now know that the packet is destined to us, we can + * drop bogus ones. + */ + if (ipv4_is_fragment((void *)&encap->ip)) { + metrics->errors_total_fragmented_ip++; + return TC_ACT_SHOT; + } + + if (encap->gue.variant != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->gue.control != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->gue.flags != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->gue.hlen != + sizeof(encap->unigue) / 4 + encap->unigue.hop_count) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->unigue.version != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->unigue.reserved != 0) { + return TC_ACT_SHOT; + } + + struct in_addr next_hop; + MAYBE_RETURN(get_next_hop(&pkt, encap, &next_hop)); + + if (next_hop.s_addr == 0) { + metrics->accepted_packets_total_last_hop++; + return accept_locally(skb, encap); + } + + verdict_t verdict; + switch (encap->gue.proto_ctype) { + case IPPROTO_IPIP: + verdict = process_ipv4(&pkt, metrics); + break; + + case IPPROTO_IPV6: + verdict = process_ipv6(&pkt, metrics); + break; + + default: + metrics->errors_total_unknown_l3_proto++; + return TC_ACT_SHOT; + } + + switch (verdict) { + case INVALID: + /* metrics have already been bumped */ + return TC_ACT_SHOT; + + case UNKNOWN: + return forward_to_next_hop(skb, encap, &next_hop, metrics); + + case ECHO_REQUEST: + metrics->accepted_packets_total_icmp_echo_request++; + break; + + case SYN: + if (encap->unigue.forward_syn) { + return forward_to_next_hop(skb, encap, &next_hop, + metrics); + } + + metrics->accepted_packets_total_syn++; + break; + + case SYN_COOKIE: + metrics->accepted_packets_total_syn_cookies++; + break; + + case ESTABLISHED: + metrics->accepted_packets_total_established++; + break; + } + + return accept_locally(skb, encap); +} diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.h b/tools/testing/selftests/bpf/progs/test_cls_redirect.h new file mode 100644 index 0000000000..233b089d1f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* Copyright 2019, 2020 Cloudflare */ + +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> +#include <string.h> + +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/udp.h> + +/* offsetof() is used in static asserts, and the libbpf-redefined CO-RE + * friendly version breaks compilation for older clang versions <= 15 + * when invoked in a static assert. Restore original here. + */ +#ifdef offsetof +#undef offsetof +#define offsetof(type, member) __builtin_offsetof(type, member) +#endif + +struct gre_base_hdr { + uint16_t flags; + uint16_t protocol; +} __attribute__((packed)); + +struct guehdr { +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + uint8_t hlen : 5, control : 1, variant : 2; +#else + uint8_t variant : 2, control : 1, hlen : 5; +#endif + uint8_t proto_ctype; + uint16_t flags; +}; + +struct unigue { +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + uint8_t _r : 2, last_hop_gre : 1, forward_syn : 1, version : 4; +#else + uint8_t version : 4, forward_syn : 1, last_hop_gre : 1, _r : 2; +#endif + uint8_t reserved; + uint8_t next_hop; + uint8_t hop_count; + // Next hops go here +} __attribute__((packed)); + +typedef struct { + struct ethhdr eth; + struct iphdr ip; + struct gre_base_hdr gre; +} __attribute__((packed)) encap_gre_t; + +typedef struct { + struct ethhdr eth; + struct iphdr ip; + struct udphdr udp; + struct guehdr gue; + struct unigue unigue; +} __attribute__((packed)) encap_headers_t; diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c new file mode 100644 index 0000000000..f41c81212e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c @@ -0,0 +1,979 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// Copyright (c) 2019, 2020 Cloudflare + +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> +#include <string.h> + +#include <linux/bpf.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/pkt_cls.h> +#include <linux/tcp.h> +#include <linux/udp.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include "test_cls_redirect.h" +#include "bpf_kfuncs.h" + +#define offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER))) + +#define IP_OFFSET_MASK (0x1FFF) +#define IP_MF (0x2000) + +char _license[] SEC("license") = "Dual BSD/GPL"; + +/** + * Destination port and IP used for UDP encapsulation. + */ +volatile const __be16 ENCAPSULATION_PORT; +volatile const __be32 ENCAPSULATION_IP; + +typedef struct { + uint64_t processed_packets_total; + uint64_t l3_protocol_packets_total_ipv4; + uint64_t l3_protocol_packets_total_ipv6; + uint64_t l4_protocol_packets_total_tcp; + uint64_t l4_protocol_packets_total_udp; + uint64_t accepted_packets_total_syn; + uint64_t accepted_packets_total_syn_cookies; + uint64_t accepted_packets_total_last_hop; + uint64_t accepted_packets_total_icmp_echo_request; + uint64_t accepted_packets_total_established; + uint64_t forwarded_packets_total_gue; + uint64_t forwarded_packets_total_gre; + + uint64_t errors_total_unknown_l3_proto; + uint64_t errors_total_unknown_l4_proto; + uint64_t errors_total_malformed_ip; + uint64_t errors_total_fragmented_ip; + uint64_t errors_total_malformed_icmp; + uint64_t errors_total_unwanted_icmp; + uint64_t errors_total_malformed_icmp_pkt_too_big; + uint64_t errors_total_malformed_tcp; + uint64_t errors_total_malformed_udp; + uint64_t errors_total_icmp_echo_replies; + uint64_t errors_total_malformed_encapsulation; + uint64_t errors_total_encap_adjust_failed; + uint64_t errors_total_encap_buffer_too_small; + uint64_t errors_total_redirect_loop; + uint64_t errors_total_encap_mtu_violate; +} metrics_t; + +typedef enum { + INVALID = 0, + UNKNOWN, + ECHO_REQUEST, + SYN, + SYN_COOKIE, + ESTABLISHED, +} verdict_t; + +typedef struct { + uint16_t src, dst; +} flow_ports_t; + +_Static_assert( + sizeof(flow_ports_t) != + offsetofend(struct bpf_sock_tuple, ipv4.dport) - + offsetof(struct bpf_sock_tuple, ipv4.sport) - 1, + "flow_ports_t must match sport and dport in struct bpf_sock_tuple"); +_Static_assert( + sizeof(flow_ports_t) != + offsetofend(struct bpf_sock_tuple, ipv6.dport) - + offsetof(struct bpf_sock_tuple, ipv6.sport) - 1, + "flow_ports_t must match sport and dport in struct bpf_sock_tuple"); + +struct iphdr_info { + void *hdr; + __u64 len; +}; + +typedef int ret_t; + +/* This is a bit of a hack. We need a return value which allows us to + * indicate that the regular flow of the program should continue, + * while allowing functions to use XDP_PASS and XDP_DROP, etc. + */ +static const ret_t CONTINUE_PROCESSING = -1; + +/* Convenience macro to call functions which return ret_t. + */ +#define MAYBE_RETURN(x) \ + do { \ + ret_t __ret = x; \ + if (__ret != CONTINUE_PROCESSING) \ + return __ret; \ + } while (0) + +static bool ipv4_is_fragment(const struct iphdr *ip) +{ + uint16_t frag_off = ip->frag_off & bpf_htons(IP_OFFSET_MASK); + return (ip->frag_off & bpf_htons(IP_MF)) != 0 || frag_off > 0; +} + +static int pkt_parse_ipv4(struct bpf_dynptr *dynptr, __u64 *offset, struct iphdr *iphdr) +{ + if (bpf_dynptr_read(iphdr, sizeof(*iphdr), dynptr, *offset, 0)) + return -1; + + *offset += sizeof(*iphdr); + + if (iphdr->ihl < 5) + return -1; + + /* skip ipv4 options */ + *offset += (iphdr->ihl - 5) * 4; + + return 0; +} + +/* Parse the L4 ports from a packet, assuming a layout like TCP or UDP. */ +static bool pkt_parse_icmp_l4_ports(struct bpf_dynptr *dynptr, __u64 *offset, flow_ports_t *ports) +{ + if (bpf_dynptr_read(ports, sizeof(*ports), dynptr, *offset, 0)) + return false; + + *offset += sizeof(*ports); + + /* Ports in the L4 headers are reversed, since we are parsing an ICMP + * payload which is going towards the eyeball. + */ + uint16_t dst = ports->src; + ports->src = ports->dst; + ports->dst = dst; + return true; +} + +static uint16_t pkt_checksum_fold(uint32_t csum) +{ + /* The highest reasonable value for an IPv4 header + * checksum requires two folds, so we just do that always. + */ + csum = (csum & 0xffff) + (csum >> 16); + csum = (csum & 0xffff) + (csum >> 16); + return (uint16_t)~csum; +} + +static void pkt_ipv4_checksum(struct iphdr *iph) +{ + iph->check = 0; + + /* An IP header without options is 20 bytes. Two of those + * are the checksum, which we always set to zero. Hence, + * the maximum accumulated value is 18 / 2 * 0xffff = 0x8fff7, + * which fits in 32 bit. + */ + _Static_assert(sizeof(struct iphdr) == 20, "iphdr must be 20 bytes"); + uint32_t acc = 0; + uint16_t *ipw = (uint16_t *)iph; + + for (size_t i = 0; i < sizeof(struct iphdr) / 2; i++) + acc += ipw[i]; + + iph->check = pkt_checksum_fold(acc); +} + +static bool pkt_skip_ipv6_extension_headers(struct bpf_dynptr *dynptr, __u64 *offset, + const struct ipv6hdr *ipv6, uint8_t *upper_proto, + bool *is_fragment) +{ + /* We understand five extension headers. + * https://tools.ietf.org/html/rfc8200#section-4.1 states that all + * headers should occur once, except Destination Options, which may + * occur twice. Hence we give up after 6 headers. + */ + struct { + uint8_t next; + uint8_t len; + } exthdr = { + .next = ipv6->nexthdr, + }; + *is_fragment = false; + + for (int i = 0; i < 6; i++) { + switch (exthdr.next) { + case IPPROTO_FRAGMENT: + *is_fragment = true; + /* NB: We don't check that hdrlen == 0 as per spec. */ + /* fallthrough; */ + + case IPPROTO_HOPOPTS: + case IPPROTO_ROUTING: + case IPPROTO_DSTOPTS: + case IPPROTO_MH: + if (bpf_dynptr_read(&exthdr, sizeof(exthdr), dynptr, *offset, 0)) + return false; + + /* hdrlen is in 8-octet units, and excludes the first 8 octets. */ + *offset += (exthdr.len + 1) * 8; + + /* Decode next header */ + break; + + default: + /* The next header is not one of the known extension + * headers, treat it as the upper layer header. + * + * This handles IPPROTO_NONE. + * + * Encapsulating Security Payload (50) and Authentication + * Header (51) also end up here (and will trigger an + * unknown proto error later). They have a custom header + * format and seem too esoteric to care about. + */ + *upper_proto = exthdr.next; + return true; + } + } + + /* We never found an upper layer header. */ + return false; +} + +static int pkt_parse_ipv6(struct bpf_dynptr *dynptr, __u64 *offset, struct ipv6hdr *ipv6, + uint8_t *proto, bool *is_fragment) +{ + if (bpf_dynptr_read(ipv6, sizeof(*ipv6), dynptr, *offset, 0)) + return -1; + + *offset += sizeof(*ipv6); + + if (!pkt_skip_ipv6_extension_headers(dynptr, offset, ipv6, proto, is_fragment)) + return -1; + + return 0; +} + +/* Global metrics, per CPU + */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, unsigned int); + __type(value, metrics_t); +} metrics_map SEC(".maps"); + +static metrics_t *get_global_metrics(void) +{ + uint64_t key = 0; + return bpf_map_lookup_elem(&metrics_map, &key); +} + +static ret_t accept_locally(struct __sk_buff *skb, encap_headers_t *encap) +{ + const int payload_off = + sizeof(*encap) + + sizeof(struct in_addr) * encap->unigue.hop_count; + int32_t encap_overhead = payload_off - sizeof(struct ethhdr); + + /* Changing the ethertype if the encapsulated packet is ipv6 */ + if (encap->gue.proto_ctype == IPPROTO_IPV6) + encap->eth.h_proto = bpf_htons(ETH_P_IPV6); + + if (bpf_skb_adjust_room(skb, -encap_overhead, BPF_ADJ_ROOM_MAC, + BPF_F_ADJ_ROOM_FIXED_GSO | + BPF_F_ADJ_ROOM_NO_CSUM_RESET) || + bpf_csum_level(skb, BPF_CSUM_LEVEL_DEC)) + return TC_ACT_SHOT; + + return bpf_redirect(skb->ifindex, BPF_F_INGRESS); +} + +static ret_t forward_with_gre(struct __sk_buff *skb, struct bpf_dynptr *dynptr, + encap_headers_t *encap, struct in_addr *next_hop, + metrics_t *metrics) +{ + const int payload_off = + sizeof(*encap) + + sizeof(struct in_addr) * encap->unigue.hop_count; + int32_t encap_overhead = + payload_off - sizeof(struct ethhdr) - sizeof(struct iphdr); + int32_t delta = sizeof(struct gre_base_hdr) - encap_overhead; + __u8 encap_buffer[sizeof(encap_gre_t)] = {}; + uint16_t proto = ETH_P_IP; + uint32_t mtu_len = 0; + encap_gre_t *encap_gre; + + metrics->forwarded_packets_total_gre++; + + /* Loop protection: the inner packet's TTL is decremented as a safeguard + * against any forwarding loop. As the only interesting field is the TTL + * hop limit for IPv6, it is easier to use bpf_skb_load_bytes/bpf_skb_store_bytes + * as they handle the split packets if needed (no need for the data to be + * in the linear section). + */ + if (encap->gue.proto_ctype == IPPROTO_IPV6) { + proto = ETH_P_IPV6; + uint8_t ttl; + int rc; + + rc = bpf_skb_load_bytes( + skb, payload_off + offsetof(struct ipv6hdr, hop_limit), + &ttl, 1); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (ttl == 0) { + metrics->errors_total_redirect_loop++; + return TC_ACT_SHOT; + } + + ttl--; + rc = bpf_skb_store_bytes( + skb, payload_off + offsetof(struct ipv6hdr, hop_limit), + &ttl, 1, 0); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + } else { + uint8_t ttl; + int rc; + + rc = bpf_skb_load_bytes( + skb, payload_off + offsetof(struct iphdr, ttl), &ttl, + 1); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (ttl == 0) { + metrics->errors_total_redirect_loop++; + return TC_ACT_SHOT; + } + + /* IPv4 also has a checksum to patch. While the TTL is only one byte, + * this function only works for 2 and 4 bytes arguments (the result is + * the same). + */ + rc = bpf_l3_csum_replace( + skb, payload_off + offsetof(struct iphdr, check), ttl, + ttl - 1, 2); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + ttl--; + rc = bpf_skb_store_bytes( + skb, payload_off + offsetof(struct iphdr, ttl), &ttl, 1, + 0); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + } + + if (bpf_check_mtu(skb, skb->ifindex, &mtu_len, delta, 0)) { + metrics->errors_total_encap_mtu_violate++; + return TC_ACT_SHOT; + } + + if (bpf_skb_adjust_room(skb, delta, BPF_ADJ_ROOM_NET, + BPF_F_ADJ_ROOM_FIXED_GSO | + BPF_F_ADJ_ROOM_NO_CSUM_RESET) || + bpf_csum_level(skb, BPF_CSUM_LEVEL_INC)) { + metrics->errors_total_encap_adjust_failed++; + return TC_ACT_SHOT; + } + + if (bpf_skb_pull_data(skb, sizeof(encap_gre_t))) { + metrics->errors_total_encap_buffer_too_small++; + return TC_ACT_SHOT; + } + + encap_gre = bpf_dynptr_slice_rdwr(dynptr, 0, encap_buffer, sizeof(encap_buffer)); + if (!encap_gre) { + metrics->errors_total_encap_buffer_too_small++; + return TC_ACT_SHOT; + } + + encap_gre->ip.protocol = IPPROTO_GRE; + encap_gre->ip.daddr = next_hop->s_addr; + encap_gre->ip.saddr = ENCAPSULATION_IP; + encap_gre->ip.tot_len = + bpf_htons(bpf_ntohs(encap_gre->ip.tot_len) + delta); + encap_gre->gre.flags = 0; + encap_gre->gre.protocol = bpf_htons(proto); + pkt_ipv4_checksum((void *)&encap_gre->ip); + + if (encap_gre == encap_buffer) + bpf_dynptr_write(dynptr, 0, encap_buffer, sizeof(encap_buffer), 0); + + return bpf_redirect(skb->ifindex, 0); +} + +static ret_t forward_to_next_hop(struct __sk_buff *skb, struct bpf_dynptr *dynptr, + encap_headers_t *encap, struct in_addr *next_hop, + metrics_t *metrics) +{ + /* swap L2 addresses */ + /* This assumes that packets are received from a router. + * So just swapping the MAC addresses here will make the packet go back to + * the router, which will send it to the appropriate machine. + */ + unsigned char temp[ETH_ALEN]; + memcpy(temp, encap->eth.h_dest, sizeof(temp)); + memcpy(encap->eth.h_dest, encap->eth.h_source, + sizeof(encap->eth.h_dest)); + memcpy(encap->eth.h_source, temp, sizeof(encap->eth.h_source)); + + if (encap->unigue.next_hop == encap->unigue.hop_count - 1 && + encap->unigue.last_hop_gre) { + return forward_with_gre(skb, dynptr, encap, next_hop, metrics); + } + + metrics->forwarded_packets_total_gue++; + uint32_t old_saddr = encap->ip.saddr; + encap->ip.saddr = encap->ip.daddr; + encap->ip.daddr = next_hop->s_addr; + if (encap->unigue.next_hop < encap->unigue.hop_count) { + encap->unigue.next_hop++; + } + + /* Remove ip->saddr, add next_hop->s_addr */ + const uint64_t off = offsetof(typeof(*encap), ip.check); + int ret = bpf_l3_csum_replace(skb, off, old_saddr, next_hop->s_addr, 4); + if (ret < 0) { + return TC_ACT_SHOT; + } + + return bpf_redirect(skb->ifindex, 0); +} + +static ret_t skip_next_hops(__u64 *offset, int n) +{ + switch (n) { + case 1: + *offset += sizeof(struct in_addr); + case 0: + return CONTINUE_PROCESSING; + + default: + return TC_ACT_SHOT; + } +} + +/* Get the next hop from the GLB header. + * + * Sets next_hop->s_addr to 0 if there are no more hops left. + * pkt is positioned just after the variable length GLB header + * iff the call is successful. + */ +static ret_t get_next_hop(struct bpf_dynptr *dynptr, __u64 *offset, encap_headers_t *encap, + struct in_addr *next_hop) +{ + if (encap->unigue.next_hop > encap->unigue.hop_count) + return TC_ACT_SHOT; + + /* Skip "used" next hops. */ + MAYBE_RETURN(skip_next_hops(offset, encap->unigue.next_hop)); + + if (encap->unigue.next_hop == encap->unigue.hop_count) { + /* No more next hops, we are at the end of the GLB header. */ + next_hop->s_addr = 0; + return CONTINUE_PROCESSING; + } + + if (bpf_dynptr_read(next_hop, sizeof(*next_hop), dynptr, *offset, 0)) + return TC_ACT_SHOT; + + *offset += sizeof(*next_hop); + + /* Skip the remainig next hops (may be zero). */ + return skip_next_hops(offset, encap->unigue.hop_count - encap->unigue.next_hop - 1); +} + +/* Fill a bpf_sock_tuple to be used with the socket lookup functions. + * This is a kludge that let's us work around verifier limitations: + * + * fill_tuple(&t, foo, sizeof(struct iphdr), 123, 321) + * + * clang will substitue a costant for sizeof, which allows the verifier + * to track it's value. Based on this, it can figure out the constant + * return value, and calling code works while still being "generic" to + * IPv4 and IPv6. + */ +static uint64_t fill_tuple(struct bpf_sock_tuple *tuple, void *iph, + uint64_t iphlen, uint16_t sport, uint16_t dport) +{ + switch (iphlen) { + case sizeof(struct iphdr): { + struct iphdr *ipv4 = (struct iphdr *)iph; + tuple->ipv4.daddr = ipv4->daddr; + tuple->ipv4.saddr = ipv4->saddr; + tuple->ipv4.sport = sport; + tuple->ipv4.dport = dport; + return sizeof(tuple->ipv4); + } + + case sizeof(struct ipv6hdr): { + struct ipv6hdr *ipv6 = (struct ipv6hdr *)iph; + memcpy(&tuple->ipv6.daddr, &ipv6->daddr, + sizeof(tuple->ipv6.daddr)); + memcpy(&tuple->ipv6.saddr, &ipv6->saddr, + sizeof(tuple->ipv6.saddr)); + tuple->ipv6.sport = sport; + tuple->ipv6.dport = dport; + return sizeof(tuple->ipv6); + } + + default: + return 0; + } +} + +static verdict_t classify_tcp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, + uint64_t tuplen, void *iph, struct tcphdr *tcp) +{ + struct bpf_sock *sk = + bpf_skc_lookup_tcp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0); + + if (sk == NULL) + return UNKNOWN; + + if (sk->state != BPF_TCP_LISTEN) { + bpf_sk_release(sk); + return ESTABLISHED; + } + + if (iph != NULL && tcp != NULL) { + /* Kludge: we've run out of arguments, but need the length of the ip header. */ + uint64_t iphlen = sizeof(struct iphdr); + + if (tuplen == sizeof(tuple->ipv6)) + iphlen = sizeof(struct ipv6hdr); + + if (bpf_tcp_check_syncookie(sk, iph, iphlen, tcp, + sizeof(*tcp)) == 0) { + bpf_sk_release(sk); + return SYN_COOKIE; + } + } + + bpf_sk_release(sk); + return UNKNOWN; +} + +static verdict_t classify_udp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, uint64_t tuplen) +{ + struct bpf_sock *sk = + bpf_sk_lookup_udp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0); + + if (sk == NULL) + return UNKNOWN; + + if (sk->state == BPF_TCP_ESTABLISHED) { + bpf_sk_release(sk); + return ESTABLISHED; + } + + bpf_sk_release(sk); + return UNKNOWN; +} + +static verdict_t classify_icmp(struct __sk_buff *skb, uint8_t proto, struct bpf_sock_tuple *tuple, + uint64_t tuplen, metrics_t *metrics) +{ + switch (proto) { + case IPPROTO_TCP: + return classify_tcp(skb, tuple, tuplen, NULL, NULL); + + case IPPROTO_UDP: + return classify_udp(skb, tuple, tuplen); + + default: + metrics->errors_total_malformed_icmp++; + return INVALID; + } +} + +static verdict_t process_icmpv4(struct __sk_buff *skb, struct bpf_dynptr *dynptr, __u64 *offset, + metrics_t *metrics) +{ + struct icmphdr icmp; + struct iphdr ipv4; + + if (bpf_dynptr_read(&icmp, sizeof(icmp), dynptr, *offset, 0)) { + metrics->errors_total_malformed_icmp++; + return INVALID; + } + + *offset += sizeof(icmp); + + /* We should never receive encapsulated echo replies. */ + if (icmp.type == ICMP_ECHOREPLY) { + metrics->errors_total_icmp_echo_replies++; + return INVALID; + } + + if (icmp.type == ICMP_ECHO) + return ECHO_REQUEST; + + if (icmp.type != ICMP_DEST_UNREACH || icmp.code != ICMP_FRAG_NEEDED) { + metrics->errors_total_unwanted_icmp++; + return INVALID; + } + + if (pkt_parse_ipv4(dynptr, offset, &ipv4)) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + /* The source address in the outer IP header is from the entity that + * originated the ICMP message. Use the original IP header to restore + * the correct flow tuple. + */ + struct bpf_sock_tuple tuple; + tuple.ipv4.saddr = ipv4.daddr; + tuple.ipv4.daddr = ipv4.saddr; + + if (!pkt_parse_icmp_l4_ports(dynptr, offset, (flow_ports_t *)&tuple.ipv4.sport)) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + return classify_icmp(skb, ipv4.protocol, &tuple, + sizeof(tuple.ipv4), metrics); +} + +static verdict_t process_icmpv6(struct bpf_dynptr *dynptr, __u64 *offset, struct __sk_buff *skb, + metrics_t *metrics) +{ + struct bpf_sock_tuple tuple; + struct ipv6hdr ipv6; + struct icmp6hdr icmp6; + bool is_fragment; + uint8_t l4_proto; + + if (bpf_dynptr_read(&icmp6, sizeof(icmp6), dynptr, *offset, 0)) { + metrics->errors_total_malformed_icmp++; + return INVALID; + } + + /* We should never receive encapsulated echo replies. */ + if (icmp6.icmp6_type == ICMPV6_ECHO_REPLY) { + metrics->errors_total_icmp_echo_replies++; + return INVALID; + } + + if (icmp6.icmp6_type == ICMPV6_ECHO_REQUEST) { + return ECHO_REQUEST; + } + + if (icmp6.icmp6_type != ICMPV6_PKT_TOOBIG) { + metrics->errors_total_unwanted_icmp++; + return INVALID; + } + + if (pkt_parse_ipv6(dynptr, offset, &ipv6, &l4_proto, &is_fragment)) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + if (is_fragment) { + metrics->errors_total_fragmented_ip++; + return INVALID; + } + + /* Swap source and dest addresses. */ + memcpy(&tuple.ipv6.saddr, &ipv6.daddr, sizeof(tuple.ipv6.saddr)); + memcpy(&tuple.ipv6.daddr, &ipv6.saddr, sizeof(tuple.ipv6.daddr)); + + if (!pkt_parse_icmp_l4_ports(dynptr, offset, (flow_ports_t *)&tuple.ipv6.sport)) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + return classify_icmp(skb, l4_proto, &tuple, sizeof(tuple.ipv6), + metrics); +} + +static verdict_t process_tcp(struct bpf_dynptr *dynptr, __u64 *offset, struct __sk_buff *skb, + struct iphdr_info *info, metrics_t *metrics) +{ + struct bpf_sock_tuple tuple; + struct tcphdr tcp; + uint64_t tuplen; + + metrics->l4_protocol_packets_total_tcp++; + + if (bpf_dynptr_read(&tcp, sizeof(tcp), dynptr, *offset, 0)) { + metrics->errors_total_malformed_tcp++; + return INVALID; + } + + *offset += sizeof(tcp); + + if (tcp.syn) + return SYN; + + tuplen = fill_tuple(&tuple, info->hdr, info->len, tcp.source, tcp.dest); + return classify_tcp(skb, &tuple, tuplen, info->hdr, &tcp); +} + +static verdict_t process_udp(struct bpf_dynptr *dynptr, __u64 *offset, struct __sk_buff *skb, + struct iphdr_info *info, metrics_t *metrics) +{ + struct bpf_sock_tuple tuple; + struct udphdr udph; + uint64_t tuplen; + + metrics->l4_protocol_packets_total_udp++; + + if (bpf_dynptr_read(&udph, sizeof(udph), dynptr, *offset, 0)) { + metrics->errors_total_malformed_udp++; + return INVALID; + } + *offset += sizeof(udph); + + tuplen = fill_tuple(&tuple, info->hdr, info->len, udph.source, udph.dest); + return classify_udp(skb, &tuple, tuplen); +} + +static verdict_t process_ipv4(struct __sk_buff *skb, struct bpf_dynptr *dynptr, + __u64 *offset, metrics_t *metrics) +{ + struct iphdr ipv4; + struct iphdr_info info = { + .hdr = &ipv4, + .len = sizeof(ipv4), + }; + + metrics->l3_protocol_packets_total_ipv4++; + + if (pkt_parse_ipv4(dynptr, offset, &ipv4)) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (ipv4.version != 4) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (ipv4_is_fragment(&ipv4)) { + metrics->errors_total_fragmented_ip++; + return INVALID; + } + + switch (ipv4.protocol) { + case IPPROTO_ICMP: + return process_icmpv4(skb, dynptr, offset, metrics); + + case IPPROTO_TCP: + return process_tcp(dynptr, offset, skb, &info, metrics); + + case IPPROTO_UDP: + return process_udp(dynptr, offset, skb, &info, metrics); + + default: + metrics->errors_total_unknown_l4_proto++; + return INVALID; + } +} + +static verdict_t process_ipv6(struct __sk_buff *skb, struct bpf_dynptr *dynptr, + __u64 *offset, metrics_t *metrics) +{ + struct ipv6hdr ipv6; + struct iphdr_info info = { + .hdr = &ipv6, + .len = sizeof(ipv6), + }; + uint8_t l4_proto; + bool is_fragment; + + metrics->l3_protocol_packets_total_ipv6++; + + if (pkt_parse_ipv6(dynptr, offset, &ipv6, &l4_proto, &is_fragment)) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (ipv6.version != 6) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (is_fragment) { + metrics->errors_total_fragmented_ip++; + return INVALID; + } + + switch (l4_proto) { + case IPPROTO_ICMPV6: + return process_icmpv6(dynptr, offset, skb, metrics); + + case IPPROTO_TCP: + return process_tcp(dynptr, offset, skb, &info, metrics); + + case IPPROTO_UDP: + return process_udp(dynptr, offset, skb, &info, metrics); + + default: + metrics->errors_total_unknown_l4_proto++; + return INVALID; + } +} + +SEC("tc") +int cls_redirect(struct __sk_buff *skb) +{ + __u8 encap_buffer[sizeof(encap_headers_t)] = {}; + struct bpf_dynptr dynptr; + struct in_addr next_hop; + /* Tracks offset of the dynptr. This will be unnecessary once + * bpf_dynptr_advance() is available. + */ + __u64 off = 0; + ret_t ret; + + bpf_dynptr_from_skb(skb, 0, &dynptr); + + metrics_t *metrics = get_global_metrics(); + if (metrics == NULL) + return TC_ACT_SHOT; + + metrics->processed_packets_total++; + + /* Pass bogus packets as long as we're not sure they're + * destined for us. + */ + if (skb->protocol != bpf_htons(ETH_P_IP)) + return TC_ACT_OK; + + encap_headers_t *encap; + + /* Make sure that all encapsulation headers are available in + * the linear portion of the skb. This makes it easy to manipulate them. + */ + if (bpf_skb_pull_data(skb, sizeof(*encap))) + return TC_ACT_OK; + + encap = bpf_dynptr_slice_rdwr(&dynptr, 0, encap_buffer, sizeof(encap_buffer)); + if (!encap) + return TC_ACT_OK; + + off += sizeof(*encap); + + if (encap->ip.ihl != 5) + /* We never have any options. */ + return TC_ACT_OK; + + if (encap->ip.daddr != ENCAPSULATION_IP || + encap->ip.protocol != IPPROTO_UDP) + return TC_ACT_OK; + + /* TODO Check UDP length? */ + if (encap->udp.dest != ENCAPSULATION_PORT) + return TC_ACT_OK; + + /* We now know that the packet is destined to us, we can + * drop bogus ones. + */ + if (ipv4_is_fragment((void *)&encap->ip)) { + metrics->errors_total_fragmented_ip++; + return TC_ACT_SHOT; + } + + if (encap->gue.variant != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->gue.control != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->gue.flags != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->gue.hlen != + sizeof(encap->unigue) / 4 + encap->unigue.hop_count) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->unigue.version != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->unigue.reserved != 0) + return TC_ACT_SHOT; + + MAYBE_RETURN(get_next_hop(&dynptr, &off, encap, &next_hop)); + + if (next_hop.s_addr == 0) { + metrics->accepted_packets_total_last_hop++; + return accept_locally(skb, encap); + } + + verdict_t verdict; + switch (encap->gue.proto_ctype) { + case IPPROTO_IPIP: + verdict = process_ipv4(skb, &dynptr, &off, metrics); + break; + + case IPPROTO_IPV6: + verdict = process_ipv6(skb, &dynptr, &off, metrics); + break; + + default: + metrics->errors_total_unknown_l3_proto++; + return TC_ACT_SHOT; + } + + switch (verdict) { + case INVALID: + /* metrics have already been bumped */ + return TC_ACT_SHOT; + + case UNKNOWN: + return forward_to_next_hop(skb, &dynptr, encap, &next_hop, metrics); + + case ECHO_REQUEST: + metrics->accepted_packets_total_icmp_echo_request++; + break; + + case SYN: + if (encap->unigue.forward_syn) { + return forward_to_next_hop(skb, &dynptr, encap, &next_hop, + metrics); + } + + metrics->accepted_packets_total_syn++; + break; + + case SYN_COOKIE: + metrics->accepted_packets_total_syn_cookies++; + break; + + case ESTABLISHED: + metrics->accepted_packets_total_established++; + break; + } + + ret = accept_locally(skb, encap); + + if (encap == encap_buffer) + bpf_dynptr_write(&dynptr, 0, encap_buffer, sizeof(encap_buffer), 0); + + return ret; +} diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect_subprogs.c b/tools/testing/selftests/bpf/progs/test_cls_redirect_subprogs.c new file mode 100644 index 0000000000..eed26b70e3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect_subprogs.c @@ -0,0 +1,2 @@ +#define SUBPROGS +#include "test_cls_redirect.c" diff --git a/tools/testing/selftests/bpf/progs/test_core_autosize.c b/tools/testing/selftests/bpf/progs/test_core_autosize.c new file mode 100644 index 0000000000..9a7829c5e4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_autosize.c @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +/* fields of exactly the same size */ +struct test_struct___samesize { + void *ptr; + unsigned long long val1; + unsigned int val2; + unsigned short val3; + unsigned char val4; +} __attribute((preserve_access_index)); + +/* unsigned fields that have to be downsized by libbpf */ +struct test_struct___downsize { + void *ptr; + unsigned long val1; + unsigned long val2; + unsigned long val3; + unsigned long val4; + /* total sz: 40 */ +} __attribute__((preserve_access_index)); + +/* fields with signed integers of wrong size, should be rejected */ +struct test_struct___signed { + void *ptr; + long val1; + long val2; + long val3; + long val4; +} __attribute((preserve_access_index)); + +/* real layout and sizes according to test's (32-bit) BTF */ +struct test_struct___real { + unsigned int ptr; /* can't use `void *`, it is always 8 byte in BPF target */ + unsigned int val2; + unsigned long long val1; + unsigned short val3; + unsigned char val4; + unsigned char _pad; + /* total sz: 20 */ +}; + +struct test_struct___real input = { + .ptr = 0x01020304, + .val1 = 0x1020304050607080, + .val2 = 0x0a0b0c0d, + .val3 = 0xfeed, + .val4 = 0xb9, + ._pad = 0xff, /* make sure no accidental zeros are present */ +}; + +unsigned long long ptr_samesized = 0; +unsigned long long val1_samesized = 0; +unsigned long long val2_samesized = 0; +unsigned long long val3_samesized = 0; +unsigned long long val4_samesized = 0; +struct test_struct___real output_samesized = {}; + +unsigned long long ptr_downsized = 0; +unsigned long long val1_downsized = 0; +unsigned long long val2_downsized = 0; +unsigned long long val3_downsized = 0; +unsigned long long val4_downsized = 0; +struct test_struct___real output_downsized = {}; + +unsigned long long ptr_probed = 0; +unsigned long long val1_probed = 0; +unsigned long long val2_probed = 0; +unsigned long long val3_probed = 0; +unsigned long long val4_probed = 0; + +unsigned long long ptr_signed = 0; +unsigned long long val1_signed = 0; +unsigned long long val2_signed = 0; +unsigned long long val3_signed = 0; +unsigned long long val4_signed = 0; +struct test_struct___real output_signed = {}; + +SEC("raw_tp/sys_exit") +int handle_samesize(void *ctx) +{ + struct test_struct___samesize *in = (void *)&input; + struct test_struct___samesize *out = (void *)&output_samesized; + + ptr_samesized = (unsigned long long)in->ptr; + val1_samesized = in->val1; + val2_samesized = in->val2; + val3_samesized = in->val3; + val4_samesized = in->val4; + + out->ptr = in->ptr; + out->val1 = in->val1; + out->val2 = in->val2; + out->val3 = in->val3; + out->val4 = in->val4; + + return 0; +} + +SEC("raw_tp/sys_exit") +int handle_downsize(void *ctx) +{ + struct test_struct___downsize *in = (void *)&input; + struct test_struct___downsize *out = (void *)&output_downsized; + + ptr_downsized = (unsigned long long)in->ptr; + val1_downsized = in->val1; + val2_downsized = in->val2; + val3_downsized = in->val3; + val4_downsized = in->val4; + + out->ptr = in->ptr; + out->val1 = in->val1; + out->val2 = in->val2; + out->val3 = in->val3; + out->val4 = in->val4; + + return 0; +} + +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#define bpf_core_read_int bpf_core_read +#else +#define bpf_core_read_int(dst, sz, src) ({ \ + /* Prevent "subtraction from stack pointer prohibited" */ \ + volatile long __off = sizeof(*dst) - (sz); \ + bpf_core_read((char *)(dst) + __off, sz, src); \ +}) +#endif + +SEC("raw_tp/sys_enter") +int handle_probed(void *ctx) +{ + struct test_struct___downsize *in = (void *)&input; + __u64 tmp; + + tmp = 0; + bpf_core_read_int(&tmp, bpf_core_field_size(in->ptr), &in->ptr); + ptr_probed = tmp; + + tmp = 0; + bpf_core_read_int(&tmp, bpf_core_field_size(in->val1), &in->val1); + val1_probed = tmp; + + tmp = 0; + bpf_core_read_int(&tmp, bpf_core_field_size(in->val2), &in->val2); + val2_probed = tmp; + + tmp = 0; + bpf_core_read_int(&tmp, bpf_core_field_size(in->val3), &in->val3); + val3_probed = tmp; + + tmp = 0; + bpf_core_read_int(&tmp, bpf_core_field_size(in->val4), &in->val4); + val4_probed = tmp; + + return 0; +} + +SEC("raw_tp/sys_enter") +int handle_signed(void *ctx) +{ + struct test_struct___signed *in = (void *)&input; + struct test_struct___signed *out = (void *)&output_signed; + + val2_signed = in->val2; + val3_signed = in->val3; + val4_signed = in->val4; + + out->val2= in->val2; + out->val3= in->val3; + out->val4= in->val4; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_core_extern.c b/tools/testing/selftests/bpf/progs/test_core_extern.c new file mode 100644 index 0000000000..a3c7c1042f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_extern.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <stdint.h> +#include <stdbool.h> +#include <linux/ptrace.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* non-existing BPF helper, to test dead code elimination */ +static int (*bpf_missing_helper)(const void *arg1, int arg2) = (void *) 999; + +extern int LINUX_KERNEL_VERSION __kconfig; +extern int LINUX_UNKNOWN_VIRTUAL_EXTERN __kconfig __weak; +extern bool CONFIG_BPF_SYSCALL __kconfig; /* strong */ +extern enum libbpf_tristate CONFIG_TRISTATE __kconfig __weak; +extern bool CONFIG_BOOL __kconfig __weak; +extern char CONFIG_CHAR __kconfig __weak; +extern uint16_t CONFIG_USHORT __kconfig __weak; +extern int CONFIG_INT __kconfig __weak; +extern uint64_t CONFIG_ULONG __kconfig __weak; +extern const char CONFIG_STR[8] __kconfig __weak; +extern uint64_t CONFIG_MISSING __kconfig __weak; + +uint64_t kern_ver = -1; +uint64_t unkn_virt_val = -1; +uint64_t bpf_syscall = -1; +uint64_t tristate_val = -1; +uint64_t bool_val = -1; +uint64_t char_val = -1; +uint64_t ushort_val = -1; +uint64_t int_val = -1; +uint64_t ulong_val = -1; +char str_val[8] = {-1, -1, -1, -1, -1, -1, -1, -1}; +uint64_t missing_val = -1; + +SEC("raw_tp/sys_enter") +int handle_sys_enter(struct pt_regs *ctx) +{ + int i; + + kern_ver = LINUX_KERNEL_VERSION; + unkn_virt_val = LINUX_UNKNOWN_VIRTUAL_EXTERN; + bpf_syscall = CONFIG_BPF_SYSCALL; + tristate_val = CONFIG_TRISTATE; + bool_val = CONFIG_BOOL; + char_val = CONFIG_CHAR; + ushort_val = CONFIG_USHORT; + int_val = CONFIG_INT; + ulong_val = CONFIG_ULONG; + + for (i = 0; i < sizeof(CONFIG_STR); i++) { + str_val[i] = CONFIG_STR[i]; + } + + if (CONFIG_MISSING) + /* invalid, but dead code - never executed */ + missing_val = bpf_missing_helper(ctx, 123); + else + missing_val = 0xDEADC0DE; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_read_macros.c b/tools/testing/selftests/bpf/progs/test_core_read_macros.c new file mode 100644 index 0000000000..fd54caa173 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_read_macros.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +/* shuffled layout for relocatable (CO-RE) reads */ +struct callback_head___shuffled { + void (*func)(struct callback_head___shuffled *head); + struct callback_head___shuffled *next; +}; + +struct callback_head k_probe_in = {}; +struct callback_head___shuffled k_core_in = {}; + +struct callback_head *u_probe_in = 0; +struct callback_head___shuffled *u_core_in = 0; + +long k_probe_out = 0; +long u_probe_out = 0; + +long k_core_out = 0; +long u_core_out = 0; + +int my_pid = 0; + +SEC("raw_tracepoint/sys_enter") +int handler(void *ctx) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + + if (my_pid != pid) + return 0; + + /* next pointers for kernel address space have to be initialized from + * BPF side, user-space mmaped addresses are stil user-space addresses + */ + k_probe_in.next = &k_probe_in; + __builtin_preserve_access_index(({k_core_in.next = &k_core_in;})); + + k_probe_out = (long)BPF_PROBE_READ(&k_probe_in, next, next, func); + k_core_out = (long)BPF_CORE_READ(&k_core_in, next, next, func); + u_probe_out = (long)BPF_PROBE_READ_USER(u_probe_in, next, next, func); + u_core_out = (long)BPF_CORE_READ_USER(u_core_in, next, next, func); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c new file mode 100644 index 0000000000..51b3f79df5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; +} data = {}; + +struct core_reloc_arrays_output { + int a2; + char b123; + int c1c; + int d00d; + int f01c; +}; + +struct core_reloc_arrays_substruct { + int c; + int d; +}; + +struct core_reloc_arrays { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; +}; + +#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src) + +SEC("raw_tracepoint/sys_enter") +int test_core_arrays(void *ctx) +{ + struct core_reloc_arrays *in = (void *)&data.in; + struct core_reloc_arrays_output *out = (void *)&data.out; + + if (CORE_READ(&out->a2, &in->a[2])) + return 1; + if (CORE_READ(&out->b123, &in->b[1][2][3])) + return 1; + if (CORE_READ(&out->c1c, &in->c[1].c)) + return 1; + if (CORE_READ(&out->d00d, &in->d[0][0].d)) + return 1; + if (CORE_READ(&out->f01c, &in->f[0][1].c)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c new file mode 100644 index 0000000000..56aec20212 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; +} data = {}; + +struct core_reloc_bitfields { + /* unsigned bitfields */ + uint8_t ub1: 1; + uint8_t ub2: 2; + uint32_t ub7: 7; + /* signed bitfields */ + int8_t sb4: 4; + int32_t sb20: 20; + /* non-bitfields */ + uint32_t u32; + int32_t s32; +}; + +/* bitfield read results, all as plain integers */ +struct core_reloc_bitfields_output { + int64_t ub1; + int64_t ub2; + int64_t ub7; + int64_t sb4; + int64_t sb20; + int64_t u32; + int64_t s32; +}; + +struct pt_regs; + +struct trace_sys_enter { + struct pt_regs *regs; + long id; +}; + +SEC("tp_btf/sys_enter") +int test_core_bitfields_direct(void *ctx) +{ + struct core_reloc_bitfields *in = (void *)&data.in; + struct core_reloc_bitfields_output *out = (void *)&data.out; + + out->ub1 = BPF_CORE_READ_BITFIELD(in, ub1); + out->ub2 = BPF_CORE_READ_BITFIELD(in, ub2); + out->ub7 = BPF_CORE_READ_BITFIELD(in, ub7); + out->sb4 = BPF_CORE_READ_BITFIELD(in, sb4); + out->sb20 = BPF_CORE_READ_BITFIELD(in, sb20); + out->u32 = BPF_CORE_READ_BITFIELD(in, u32); + out->s32 = BPF_CORE_READ_BITFIELD(in, s32); + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c new file mode 100644 index 0000000000..b86fdda2a6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; +} data = {}; + +struct core_reloc_bitfields { + /* unsigned bitfields */ + uint8_t ub1: 1; + uint8_t ub2: 2; + uint32_t ub7: 7; + /* signed bitfields */ + int8_t sb4: 4; + int32_t sb20: 20; + /* non-bitfields */ + uint32_t u32; + int32_t s32; +}; + +/* bitfield read results, all as plain integers */ +struct core_reloc_bitfields_output { + int64_t ub1; + int64_t ub2; + int64_t ub7; + int64_t sb4; + int64_t sb20; + int64_t u32; + int64_t s32; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_bitfields(void *ctx) +{ + struct core_reloc_bitfields *in = (void *)&data.in; + struct core_reloc_bitfields_output *out = (void *)&data.out; + + out->ub1 = BPF_CORE_READ_BITFIELD_PROBED(in, ub1); + out->ub2 = BPF_CORE_READ_BITFIELD_PROBED(in, ub2); + out->ub7 = BPF_CORE_READ_BITFIELD_PROBED(in, ub7); + out->sb4 = BPF_CORE_READ_BITFIELD_PROBED(in, sb4); + out->sb20 = BPF_CORE_READ_BITFIELD_PROBED(in, sb20); + out->u32 = BPF_CORE_READ_BITFIELD_PROBED(in, u32); + out->s32 = BPF_CORE_READ_BITFIELD_PROBED(in, s32); + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_enum64val.c b/tools/testing/selftests/bpf/progs/test_core_reloc_enum64val.c new file mode 100644 index 0000000000..63147fbfae --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_enum64val.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf.h> +#include <stdint.h> +#include <stdbool.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; + bool skip; +} data = {}; + +enum named_unsigned_enum64 { + UNSIGNED_ENUM64_VAL1 = 0x1ffffffffULL, + UNSIGNED_ENUM64_VAL2 = 0x2ffffffffULL, + UNSIGNED_ENUM64_VAL3 = 0x3ffffffffULL, +}; + +enum named_signed_enum64 { + SIGNED_ENUM64_VAL1 = 0x1ffffffffLL, + SIGNED_ENUM64_VAL2 = -2, + SIGNED_ENUM64_VAL3 = 0x3ffffffffLL, +}; + +struct core_reloc_enum64val_output { + bool unsigned_val1_exists; + bool unsigned_val2_exists; + bool unsigned_val3_exists; + bool signed_val1_exists; + bool signed_val2_exists; + bool signed_val3_exists; + + long unsigned_val1; + long unsigned_val2; + long signed_val1; + long signed_val2; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_enum64val(void *ctx) +{ +#if __clang_major__ >= 15 + struct core_reloc_enum64val_output *out = (void *)&data.out; + enum named_unsigned_enum64 named_unsigned = 0; + enum named_signed_enum64 named_signed = 0; + + out->unsigned_val1_exists = bpf_core_enum_value_exists(named_unsigned, UNSIGNED_ENUM64_VAL1); + out->unsigned_val2_exists = bpf_core_enum_value_exists(enum named_unsigned_enum64, UNSIGNED_ENUM64_VAL2); + out->unsigned_val3_exists = bpf_core_enum_value_exists(enum named_unsigned_enum64, UNSIGNED_ENUM64_VAL3); + out->signed_val1_exists = bpf_core_enum_value_exists(named_signed, SIGNED_ENUM64_VAL1); + out->signed_val2_exists = bpf_core_enum_value_exists(enum named_signed_enum64, SIGNED_ENUM64_VAL2); + out->signed_val3_exists = bpf_core_enum_value_exists(enum named_signed_enum64, SIGNED_ENUM64_VAL3); + + out->unsigned_val1 = bpf_core_enum_value(named_unsigned, UNSIGNED_ENUM64_VAL1); + out->unsigned_val2 = bpf_core_enum_value(named_unsigned, UNSIGNED_ENUM64_VAL2); + out->signed_val1 = bpf_core_enum_value(named_signed, SIGNED_ENUM64_VAL1); + out->signed_val2 = bpf_core_enum_value(named_signed, SIGNED_ENUM64_VAL2); + /* NAMED_ENUM64_VAL3 value is optional */ + +#else + data.skip = true; +#endif + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_enumval.c b/tools/testing/selftests/bpf/progs/test_core_reloc_enumval.c new file mode 100644 index 0000000000..e7ef3dada2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_enumval.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <stdbool.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; + bool skip; +} data = {}; + +enum named_enum { + NAMED_ENUM_VAL1 = 1, + NAMED_ENUM_VAL2 = 2, + NAMED_ENUM_VAL3 = 3, +}; + +typedef enum { + ANON_ENUM_VAL1 = 0x10, + ANON_ENUM_VAL2 = 0x20, + ANON_ENUM_VAL3 = 0x30, +} anon_enum; + +struct core_reloc_enumval_output { + bool named_val1_exists; + bool named_val2_exists; + bool named_val3_exists; + bool anon_val1_exists; + bool anon_val2_exists; + bool anon_val3_exists; + + int named_val1; + int named_val2; + int anon_val1; + int anon_val2; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_enumval(void *ctx) +{ +#if __has_builtin(__builtin_preserve_enum_value) + struct core_reloc_enumval_output *out = (void *)&data.out; + enum named_enum named = 0; + anon_enum anon = 0; + + out->named_val1_exists = bpf_core_enum_value_exists(named, NAMED_ENUM_VAL1); + out->named_val2_exists = bpf_core_enum_value_exists(enum named_enum, NAMED_ENUM_VAL2); + out->named_val3_exists = bpf_core_enum_value_exists(enum named_enum, NAMED_ENUM_VAL3); + + out->anon_val1_exists = bpf_core_enum_value_exists(anon, ANON_ENUM_VAL1); + out->anon_val2_exists = bpf_core_enum_value_exists(anon_enum, ANON_ENUM_VAL2); + out->anon_val3_exists = bpf_core_enum_value_exists(anon_enum, ANON_ENUM_VAL3); + + out->named_val1 = bpf_core_enum_value(named, NAMED_ENUM_VAL1); + out->named_val2 = bpf_core_enum_value(named, NAMED_ENUM_VAL2); + /* NAMED_ENUM_VAL3 value is optional */ + + out->anon_val1 = bpf_core_enum_value(anon, ANON_ENUM_VAL1); + out->anon_val2 = bpf_core_enum_value(anon, ANON_ENUM_VAL2); + /* ANON_ENUM_VAL3 value is optional */ +#else + data.skip = true; +#endif + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c b/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c new file mode 100644 index 0000000000..5b8a75097e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; +} data = {}; + +struct core_reloc_existence_output { + int a_exists; + int a_value; + int b_exists; + int b_value; + int c_exists; + int c_value; + int arr_exists; + int arr_value; + int s_exists; + int s_value; +}; + +struct core_reloc_existence { + struct { + int x; + } s; + int arr[1]; + int a; + struct { + int b; + }; + int c; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_existence(void *ctx) +{ + struct core_reloc_existence *in = (void *)&data.in; + struct core_reloc_existence_output *out = (void *)&data.out; + + out->a_exists = bpf_core_field_exists(in->a); + if (bpf_core_field_exists(struct core_reloc_existence, a)) + out->a_value = BPF_CORE_READ(in, a); + else + out->a_value = 0xff000001u; + + out->b_exists = bpf_core_field_exists(in->b); + if (bpf_core_field_exists(struct core_reloc_existence, b)) + out->b_value = BPF_CORE_READ(in, b); + else + out->b_value = 0xff000002u; + + out->c_exists = bpf_core_field_exists(in->c); + if (bpf_core_field_exists(struct core_reloc_existence, c)) + out->c_value = BPF_CORE_READ(in, c); + else + out->c_value = 0xff000003u; + + out->arr_exists = bpf_core_field_exists(in->arr); + if (bpf_core_field_exists(struct core_reloc_existence, arr)) + out->arr_value = BPF_CORE_READ(in, arr[0]); + else + out->arr_value = 0xff000004u; + + out->s_exists = bpf_core_field_exists(in->s); + if (bpf_core_field_exists(struct core_reloc_existence, s)) + out->s_value = BPF_CORE_READ(in, s.x); + else + out->s_value = 0xff000005u; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c new file mode 100644 index 0000000000..525acc2f84 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; +} data = {}; + +struct core_reloc_flavors { + int a; + int b; + int c; +}; + +/* local flavor with reversed layout */ +struct core_reloc_flavors___reversed { + int c; + int b; + int a; +}; + +/* local flavor with nested/overlapping layout */ +struct core_reloc_flavors___weird { + struct { + int b; + }; + /* a and c overlap in local flavor, but this should still work + * correctly with target original flavor + */ + union { + int a; + int c; + }; +}; + +#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src) + +SEC("raw_tracepoint/sys_enter") +int test_core_flavors(void *ctx) +{ + struct core_reloc_flavors *in_orig = (void *)&data.in; + struct core_reloc_flavors___reversed *in_rev = (void *)&data.in; + struct core_reloc_flavors___weird *in_weird = (void *)&data.in; + struct core_reloc_flavors *out = (void *)&data.out; + + /* read a using weird layout */ + if (CORE_READ(&out->a, &in_weird->a)) + return 1; + /* read b using reversed layout */ + if (CORE_READ(&out->b, &in_rev->b)) + return 1; + /* read c using original layout */ + if (CORE_READ(&out->c, &in_orig->c)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c new file mode 100644 index 0000000000..6b52907398 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; +} data = {}; + +struct core_reloc_ints { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src) + +SEC("raw_tracepoint/sys_enter") +int test_core_ints(void *ctx) +{ + struct core_reloc_ints *in = (void *)&data.in; + struct core_reloc_ints *out = (void *)&data.out; + + if (CORE_READ(&out->u8_field, &in->u8_field) || + CORE_READ(&out->s8_field, &in->s8_field) || + CORE_READ(&out->u16_field, &in->u16_field) || + CORE_READ(&out->s16_field, &in->s16_field) || + CORE_READ(&out->u32_field, &in->u32_field) || + CORE_READ(&out->s32_field, &in->s32_field) || + CORE_READ(&out->u64_field, &in->u64_field) || + CORE_READ(&out->s64_field, &in->s64_field)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c new file mode 100644 index 0000000000..a17dd83eae --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <stdbool.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; + bool skip; + uint64_t my_pid_tgid; +} data = {}; + +struct core_reloc_kernel_output { + int valid[10]; + /* we have test_progs[-flavor], so cut flavor part */ + char comm[sizeof("test_progs")]; + int comm_len; + bool local_task_struct_matches; +}; + +struct task_struct { + int pid; + int tgid; + char comm[16]; + struct task_struct *group_leader; +}; + +struct mm_struct___wrong { + int abc_whatever_should_not_exist; +}; + +struct task_struct___local { + int pid; + struct mm_struct___wrong *mm; +}; + +#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src) + +SEC("raw_tracepoint/sys_enter") +int test_core_kernel(void *ctx) +{ + /* Support for the BPF_TYPE_MATCHES argument to the + * __builtin_preserve_type_info builtin was added at some point during + * development of clang 15 and it's what we require for this test. + */ +#if __has_builtin(__builtin_preserve_type_info) && __clang_major__ >= 15 + struct task_struct *task = (void *)bpf_get_current_task(); + struct core_reloc_kernel_output *out = (void *)&data.out; + uint64_t pid_tgid = bpf_get_current_pid_tgid(); + uint32_t real_tgid = (uint32_t)pid_tgid; + int pid, tgid; + + if (data.my_pid_tgid != pid_tgid) + return 0; + + if (CORE_READ(&pid, &task->pid) || + CORE_READ(&tgid, &task->tgid)) + return 1; + + /* validate pid + tgid matches */ + out->valid[0] = (((uint64_t)pid << 32) | tgid) == pid_tgid; + + /* test variadic BPF_CORE_READ macros */ + out->valid[1] = BPF_CORE_READ(task, + tgid) == real_tgid; + out->valid[2] = BPF_CORE_READ(task, + group_leader, + tgid) == real_tgid; + out->valid[3] = BPF_CORE_READ(task, + group_leader, group_leader, + tgid) == real_tgid; + out->valid[4] = BPF_CORE_READ(task, + group_leader, group_leader, group_leader, + tgid) == real_tgid; + out->valid[5] = BPF_CORE_READ(task, + group_leader, group_leader, group_leader, + group_leader, + tgid) == real_tgid; + out->valid[6] = BPF_CORE_READ(task, + group_leader, group_leader, group_leader, + group_leader, group_leader, + tgid) == real_tgid; + out->valid[7] = BPF_CORE_READ(task, + group_leader, group_leader, group_leader, + group_leader, group_leader, group_leader, + tgid) == real_tgid; + out->valid[8] = BPF_CORE_READ(task, + group_leader, group_leader, group_leader, + group_leader, group_leader, group_leader, + group_leader, + tgid) == real_tgid; + out->valid[9] = BPF_CORE_READ(task, + group_leader, group_leader, group_leader, + group_leader, group_leader, group_leader, + group_leader, group_leader, + tgid) == real_tgid; + + /* test BPF_CORE_READ_STR_INTO() returns correct code and contents */ + out->comm_len = BPF_CORE_READ_STR_INTO( + &out->comm, task, + group_leader, group_leader, group_leader, group_leader, + group_leader, group_leader, group_leader, group_leader, + comm); + + out->local_task_struct_matches = bpf_core_type_matches(struct task_struct___local); +#else + data.skip = true; +#endif + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c new file mode 100644 index 0000000000..d5756dbdef --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; +} data = {}; + +struct core_reloc_misc_output { + int a, b, c; +}; + +struct core_reloc_misc___a { + int a1; + int a2; +}; + +struct core_reloc_misc___b { + int b1; + int b2; +}; + +/* fixed two first members, can be extended with new fields */ +struct core_reloc_misc_extensible { + int a; + int b; +}; + +#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src) + +SEC("raw_tracepoint/sys_enter") +int test_core_misc(void *ctx) +{ + struct core_reloc_misc___a *in_a = (void *)&data.in; + struct core_reloc_misc___b *in_b = (void *)&data.in; + struct core_reloc_misc_extensible *in_ext = (void *)&data.in; + struct core_reloc_misc_output *out = (void *)&data.out; + + /* record two different relocations with the same accessor string */ + if (CORE_READ(&out->a, &in_a->a1) || /* accessor: 0:0 */ + CORE_READ(&out->b, &in_b->b1)) /* accessor: 0:0 */ + return 1; + + /* Validate relocations capture array-only accesses for structs with + * fixed header, but with potentially extendable tail. This will read + * first 4 bytes of 2nd element of in_ext array of potentially + * variably sized struct core_reloc_misc_extensible. */ + if (CORE_READ(&out->c, &in_ext[2])) /* accessor: 2 */ + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c new file mode 100644 index 0000000000..b2ded49757 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; +} data = {}; + +struct core_reloc_mods_output { + int a, b, c, d, e, f, g, h; +}; + +typedef const int int_t; +typedef const char *char_ptr_t; +typedef const int arr_t[7]; + +struct core_reloc_mods_substruct { + int x; + int y; +}; + +typedef struct { + int x; + int y; +} core_reloc_mods_substruct_t; + +struct core_reloc_mods { + int a; + int_t b; + char *c; + char_ptr_t d; + int e[3]; + arr_t f; + struct core_reloc_mods_substruct g; + core_reloc_mods_substruct_t h; +}; + +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src) +#else +#define CORE_READ(dst, src) ({ \ + int __sz = sizeof(*(dst)) < sizeof(*(src)) ? sizeof(*(dst)) : \ + sizeof(*(src)); \ + bpf_core_read((char *)(dst) + sizeof(*(dst)) - __sz, __sz, \ + (const char *)(src) + sizeof(*(src)) - __sz); \ +}) +#endif + +SEC("raw_tracepoint/sys_enter") +int test_core_mods(void *ctx) +{ + struct core_reloc_mods *in = (void *)&data.in; + struct core_reloc_mods_output *out = (void *)&data.out; + + if (CORE_READ(&out->a, &in->a) || + CORE_READ(&out->b, &in->b) || + CORE_READ(&out->c, &in->c) || + CORE_READ(&out->d, &in->d) || + CORE_READ(&out->e, &in->e[2]) || + CORE_READ(&out->f, &in->f[1]) || + CORE_READ(&out->g, &in->g.x) || + CORE_READ(&out->h, &in->h.y)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_module.c b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c new file mode 100644 index 0000000000..f59f175c7b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct bpf_testmod_test_read_ctx { + /* field order is mixed up */ + size_t len; + char *buf; + loff_t off; +} __attribute__((preserve_access_index)); + +struct { + char in[256]; + char out[256]; + bool skip; + uint64_t my_pid_tgid; +} data = {}; + +struct core_reloc_module_output { + long long len; + long long off; + int read_ctx_sz; + bool read_ctx_exists; + bool buf_exists; + bool len_exists; + bool off_exists; + /* we have test_progs[-flavor], so cut flavor part */ + char comm[sizeof("test_progs")]; + int comm_len; +}; + +SEC("raw_tp/bpf_testmod_test_read") +int BPF_PROG(test_core_module_probed, + struct task_struct *task, + struct bpf_testmod_test_read_ctx *read_ctx) +{ +#if __has_builtin(__builtin_preserve_enum_value) + struct core_reloc_module_output *out = (void *)&data.out; + __u64 pid_tgid = bpf_get_current_pid_tgid(); + __u32 real_tgid = (__u32)(pid_tgid >> 32); + __u32 real_pid = (__u32)pid_tgid; + + if (data.my_pid_tgid != pid_tgid) + return 0; + + if (BPF_CORE_READ(task, pid) != real_pid || BPF_CORE_READ(task, tgid) != real_tgid) + return 0; + + out->len = BPF_CORE_READ(read_ctx, len); + out->off = BPF_CORE_READ(read_ctx, off); + + out->read_ctx_sz = bpf_core_type_size(struct bpf_testmod_test_read_ctx); + out->read_ctx_exists = bpf_core_type_exists(struct bpf_testmod_test_read_ctx); + out->buf_exists = bpf_core_field_exists(read_ctx->buf); + out->off_exists = bpf_core_field_exists(read_ctx->off); + out->len_exists = bpf_core_field_exists(read_ctx->len); + + out->comm_len = BPF_CORE_READ_STR_INTO(&out->comm, task, comm); +#else + data.skip = true; +#endif + + return 0; +} + +SEC("tp_btf/bpf_testmod_test_read") +int BPF_PROG(test_core_module_direct, + struct task_struct *task, + struct bpf_testmod_test_read_ctx *read_ctx) +{ +#if __has_builtin(__builtin_preserve_enum_value) + struct core_reloc_module_output *out = (void *)&data.out; + __u64 pid_tgid = bpf_get_current_pid_tgid(); + __u32 real_tgid = (__u32)(pid_tgid >> 32); + __u32 real_pid = (__u32)pid_tgid; + + if (data.my_pid_tgid != pid_tgid) + return 0; + + if (task->pid != real_pid || task->tgid != real_tgid) + return 0; + + out->len = read_ctx->len; + out->off = read_ctx->off; + + out->read_ctx_sz = bpf_core_type_size(struct bpf_testmod_test_read_ctx); + out->read_ctx_exists = bpf_core_type_exists(struct bpf_testmod_test_read_ctx); + out->buf_exists = bpf_core_field_exists(read_ctx->buf); + out->off_exists = bpf_core_field_exists(read_ctx->off); + out->len_exists = bpf_core_field_exists(read_ctx->len); + + out->comm_len = BPF_CORE_READ_STR_INTO(&out->comm, task, comm); +#else + data.skip = true; +#endif + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c new file mode 100644 index 0000000000..2b4b6d49c6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; +} data = {}; + +struct core_reloc_nesting_substruct { + int a; +}; + +union core_reloc_nesting_subunion { + int b; +}; + +/* int a.a.a and b.b.b accesses */ +struct core_reloc_nesting { + union { + struct core_reloc_nesting_substruct a; + } a; + struct { + union core_reloc_nesting_subunion b; + } b; +}; + +#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src) + +SEC("raw_tracepoint/sys_enter") +int test_core_nesting(void *ctx) +{ + struct core_reloc_nesting *in = (void *)&data.in; + struct core_reloc_nesting *out = (void *)&data.out; + + if (CORE_READ(&out->a.a.a, &in->a.a.a)) + return 1; + if (CORE_READ(&out->b.b.b, &in->b.b.b)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c new file mode 100644 index 0000000000..2a8975678a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; +} data = {}; + +enum core_reloc_primitives_enum { + A = 0, + B = 1, +}; + +struct core_reloc_primitives { + char a; + int b; + enum core_reloc_primitives_enum c; + void *d; + int (*f)(const char *); +}; + +#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src) + +SEC("raw_tracepoint/sys_enter") +int test_core_primitives(void *ctx) +{ + struct core_reloc_primitives *in = (void *)&data.in; + struct core_reloc_primitives *out = (void *)&data.out; + + if (CORE_READ(&out->a, &in->a) || + CORE_READ(&out->b, &in->b) || + CORE_READ(&out->c, &in->c) || + CORE_READ(&out->d, &in->d) || + CORE_READ(&out->f, &in->f)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c new file mode 100644 index 0000000000..ca61a5183b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; +} data = {}; + +struct core_reloc_ptr_as_arr { + int a; +}; + +#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src) + +SEC("raw_tracepoint/sys_enter") +int test_core_ptr_as_arr(void *ctx) +{ + struct core_reloc_ptr_as_arr *in = (void *)&data.in; + struct core_reloc_ptr_as_arr *out = (void *)&data.out; + + if (CORE_READ(&out->a, &in[2].a)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_size.c b/tools/testing/selftests/bpf/progs/test_core_reloc_size.c new file mode 100644 index 0000000000..5b686053ce --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_size.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; +} data = {}; + +struct core_reloc_size_output { + int int_sz; + int int_off; + int struct_sz; + int struct_off; + int union_sz; + int union_off; + int arr_sz; + int arr_off; + int arr_elem_sz; + int arr_elem_off; + int ptr_sz; + int ptr_off; + int enum_sz; + int enum_off; + int float_sz; + int float_off; +}; + +struct core_reloc_size { + int int_field; + struct { int x; } struct_field; + union { int x; } union_field; + int arr_field[4]; + void *ptr_field; + enum { VALUE = 123 } enum_field; + float float_field; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_size(void *ctx) +{ + struct core_reloc_size *in = (void *)&data.in; + struct core_reloc_size_output *out = (void *)&data.out; + + out->int_sz = bpf_core_field_size(in->int_field); + out->int_off = bpf_core_field_offset(in->int_field); + + out->struct_sz = bpf_core_field_size(in->struct_field); + out->struct_off = bpf_core_field_offset(in->struct_field); + + out->union_sz = bpf_core_field_size(in->union_field); + out->union_off = bpf_core_field_offset(in->union_field); + + out->arr_sz = bpf_core_field_size(in->arr_field); + out->arr_off = bpf_core_field_offset(in->arr_field); + + out->arr_elem_sz = bpf_core_field_size(struct core_reloc_size, arr_field[1]); + out->arr_elem_off = bpf_core_field_offset(struct core_reloc_size, arr_field[1]); + + out->ptr_sz = bpf_core_field_size(struct core_reloc_size, ptr_field); + out->ptr_off = bpf_core_field_offset(struct core_reloc_size, ptr_field); + + out->enum_sz = bpf_core_field_size(struct core_reloc_size, enum_field); + out->enum_off = bpf_core_field_offset(struct core_reloc_size, enum_field); + + out->float_sz = bpf_core_field_size(struct core_reloc_size, float_field); + out->float_off = bpf_core_field_offset(struct core_reloc_size, float_field); + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_type_based.c b/tools/testing/selftests/bpf/progs/test_core_reloc_type_based.c new file mode 100644 index 0000000000..2edb4df35e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_type_based.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <stdbool.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; + bool skip; +} data = {}; + +struct a_struct { + int x; +}; + +struct a_complex_struct { + union { + struct a_struct *a; + void *b; + } x; + volatile long y; +}; + +union a_union { + int y; + int z; +}; + +typedef struct a_struct named_struct_typedef; + +typedef struct { int x, y, z; } anon_struct_typedef; + +typedef struct { + int a, b, c; +} *struct_ptr_typedef; + +enum an_enum { + AN_ENUM_VAL1 = 1, + AN_ENUM_VAL2 = 2, + AN_ENUM_VAL3 = 3, +}; + +typedef int int_typedef; + +typedef enum { TYPEDEF_ENUM_VAL1, TYPEDEF_ENUM_VAL2 } enum_typedef; + +typedef void *void_ptr_typedef; +typedef int *restrict restrict_ptr_typedef; + +typedef int (*func_proto_typedef)(long); + +typedef char arr_typedef[20]; + +struct core_reloc_type_based_output { + bool struct_exists; + bool complex_struct_exists; + bool union_exists; + bool enum_exists; + bool typedef_named_struct_exists; + bool typedef_anon_struct_exists; + bool typedef_struct_ptr_exists; + bool typedef_int_exists; + bool typedef_enum_exists; + bool typedef_void_ptr_exists; + bool typedef_restrict_ptr_exists; + bool typedef_func_proto_exists; + bool typedef_arr_exists; + + bool struct_matches; + bool complex_struct_matches; + bool union_matches; + bool enum_matches; + bool typedef_named_struct_matches; + bool typedef_anon_struct_matches; + bool typedef_struct_ptr_matches; + bool typedef_int_matches; + bool typedef_enum_matches; + bool typedef_void_ptr_matches; + bool typedef_restrict_ptr_matches; + bool typedef_func_proto_matches; + bool typedef_arr_matches; + + int struct_sz; + int union_sz; + int enum_sz; + int typedef_named_struct_sz; + int typedef_anon_struct_sz; + int typedef_struct_ptr_sz; + int typedef_int_sz; + int typedef_enum_sz; + int typedef_void_ptr_sz; + int typedef_func_proto_sz; + int typedef_arr_sz; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_type_based(void *ctx) +{ + /* Support for the BPF_TYPE_MATCHES argument to the + * __builtin_preserve_type_info builtin was added at some point during + * development of clang 15 and it's what we require for this test. Part of it + * could run with merely __builtin_preserve_type_info (which could be checked + * separately), but we have to find an upper bound. + */ +#if __has_builtin(__builtin_preserve_type_info) && __clang_major__ >= 15 + struct core_reloc_type_based_output *out = (void *)&data.out; + + out->struct_exists = bpf_core_type_exists(struct a_struct); + out->complex_struct_exists = bpf_core_type_exists(struct a_complex_struct); + out->union_exists = bpf_core_type_exists(union a_union); + out->enum_exists = bpf_core_type_exists(enum an_enum); + out->typedef_named_struct_exists = bpf_core_type_exists(named_struct_typedef); + out->typedef_anon_struct_exists = bpf_core_type_exists(anon_struct_typedef); + out->typedef_struct_ptr_exists = bpf_core_type_exists(struct_ptr_typedef); + out->typedef_int_exists = bpf_core_type_exists(int_typedef); + out->typedef_enum_exists = bpf_core_type_exists(enum_typedef); + out->typedef_void_ptr_exists = bpf_core_type_exists(void_ptr_typedef); + out->typedef_restrict_ptr_exists = bpf_core_type_exists(restrict_ptr_typedef); + out->typedef_func_proto_exists = bpf_core_type_exists(func_proto_typedef); + out->typedef_arr_exists = bpf_core_type_exists(arr_typedef); + + out->struct_matches = bpf_core_type_matches(struct a_struct); + out->complex_struct_matches = bpf_core_type_matches(struct a_complex_struct); + out->union_matches = bpf_core_type_matches(union a_union); + out->enum_matches = bpf_core_type_matches(enum an_enum); + out->typedef_named_struct_matches = bpf_core_type_matches(named_struct_typedef); + out->typedef_anon_struct_matches = bpf_core_type_matches(anon_struct_typedef); + out->typedef_struct_ptr_matches = bpf_core_type_matches(struct_ptr_typedef); + out->typedef_int_matches = bpf_core_type_matches(int_typedef); + out->typedef_enum_matches = bpf_core_type_matches(enum_typedef); + out->typedef_void_ptr_matches = bpf_core_type_matches(void_ptr_typedef); + out->typedef_restrict_ptr_matches = bpf_core_type_matches(restrict_ptr_typedef); + out->typedef_func_proto_matches = bpf_core_type_matches(func_proto_typedef); + out->typedef_arr_matches = bpf_core_type_matches(arr_typedef); + + out->struct_sz = bpf_core_type_size(struct a_struct); + out->union_sz = bpf_core_type_size(union a_union); + out->enum_sz = bpf_core_type_size(enum an_enum); + out->typedef_named_struct_sz = bpf_core_type_size(named_struct_typedef); + out->typedef_anon_struct_sz = bpf_core_type_size(anon_struct_typedef); + out->typedef_struct_ptr_sz = bpf_core_type_size(struct_ptr_typedef); + out->typedef_int_sz = bpf_core_type_size(int_typedef); + out->typedef_enum_sz = bpf_core_type_size(enum_typedef); + out->typedef_void_ptr_sz = bpf_core_type_size(void_ptr_typedef); + out->typedef_func_proto_sz = bpf_core_type_size(func_proto_typedef); + out->typedef_arr_sz = bpf_core_type_size(arr_typedef); +#else + data.skip = true; +#endif + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c b/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c new file mode 100644 index 0000000000..22aba3f6e3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <stdbool.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +struct { + char in[256]; + char out[256]; + bool skip; +} data = {}; + +/* some types are shared with test_core_reloc_type_based.c */ +struct a_struct { + int x; +}; + +union a_union { + int y; + int z; +}; + +enum an_enum { + AN_ENUM_VAL1 = 1, + AN_ENUM_VAL2 = 2, + AN_ENUM_VAL3 = 3, +}; + +typedef struct a_struct named_struct_typedef; + +typedef int (*func_proto_typedef)(long); + +typedef char arr_typedef[20]; + +struct core_reloc_type_id_output { + int local_anon_struct; + int local_anon_union; + int local_anon_enum; + int local_anon_func_proto_ptr; + int local_anon_void_ptr; + int local_anon_arr; + + int local_struct; + int local_union; + int local_enum; + int local_int; + int local_struct_typedef; + int local_func_proto_typedef; + int local_arr_typedef; + + int targ_struct; + int targ_union; + int targ_enum; + int targ_int; + int targ_struct_typedef; + int targ_func_proto_typedef; + int targ_arr_typedef; +}; + +/* preserve types even if Clang doesn't support built-in */ +struct a_struct t1 = {}; +union a_union t2 = {}; +enum an_enum t3 = 0; +named_struct_typedef t4 = {}; +func_proto_typedef t5 = 0; +arr_typedef t6 = {}; + +SEC("raw_tracepoint/sys_enter") +int test_core_type_id(void *ctx) +{ + /* We use __builtin_btf_type_id() in this tests, but up until the time + * __builtin_preserve_type_info() was added it contained a bug that + * would make this test fail. The bug was fixed ([0]) with addition of + * __builtin_preserve_type_info(), though, so that's what we are using + * to detect whether this test has to be executed, however strange + * that might look like. + * + * [0] https://reviews.llvm.org/D85174 + */ +#if __has_builtin(__builtin_preserve_type_info) + struct core_reloc_type_id_output *out = (void *)&data.out; + + out->local_anon_struct = bpf_core_type_id_local(struct { int marker_field; }); + out->local_anon_union = bpf_core_type_id_local(union { int marker_field; }); + out->local_anon_enum = bpf_core_type_id_local(enum { MARKER_ENUM_VAL = 123 }); + out->local_anon_func_proto_ptr = bpf_core_type_id_local(_Bool(*)(int)); + out->local_anon_void_ptr = bpf_core_type_id_local(void *); + out->local_anon_arr = bpf_core_type_id_local(_Bool[47]); + + out->local_struct = bpf_core_type_id_local(struct a_struct); + out->local_union = bpf_core_type_id_local(union a_union); + out->local_enum = bpf_core_type_id_local(enum an_enum); + out->local_int = bpf_core_type_id_local(int); + out->local_struct_typedef = bpf_core_type_id_local(named_struct_typedef); + out->local_func_proto_typedef = bpf_core_type_id_local(func_proto_typedef); + out->local_arr_typedef = bpf_core_type_id_local(arr_typedef); + + out->targ_struct = bpf_core_type_id_kernel(struct a_struct); + out->targ_union = bpf_core_type_id_kernel(union a_union); + out->targ_enum = bpf_core_type_id_kernel(enum an_enum); + out->targ_int = bpf_core_type_id_kernel(int); + out->targ_struct_typedef = bpf_core_type_id_kernel(named_struct_typedef); + out->targ_func_proto_typedef = bpf_core_type_id_kernel(func_proto_typedef); + out->targ_arr_typedef = bpf_core_type_id_kernel(arr_typedef); +#else + data.skip = true; +#endif + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_core_retro.c b/tools/testing/selftests/bpf/progs/test_core_retro.c new file mode 100644 index 0000000000..20861ec2f6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_retro.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +struct task_struct { + int tgid; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} exp_tgid_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} results SEC(".maps"); + +SEC("tp/raw_syscalls/sys_enter") +int handle_sys_enter(void *ctx) +{ + struct task_struct *task = (void *)bpf_get_current_task(); + int tgid = BPF_CORE_READ(task, tgid); + int zero = 0; + int real_tgid = bpf_get_current_pid_tgid() >> 32; + int *exp_tgid = bpf_map_lookup_elem(&exp_tgid_map, &zero); + + /* only pass through sys_enters from test process */ + if (!exp_tgid || *exp_tgid != real_tgid) + return 0; + + bpf_map_update_elem(&results, &zero, &tgid, 0); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_custom_sec_handlers.c b/tools/testing/selftests/bpf/progs/test_custom_sec_handlers.c new file mode 100644 index 0000000000..4061f701ca --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_custom_sec_handlers.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +const volatile int my_pid; + +bool abc1_called; +bool abc2_called; +bool custom1_called; +bool custom2_called; +bool kprobe1_called; +bool xyz_called; + +SEC("abc") +int abc1(void *ctx) +{ + abc1_called = true; + return 0; +} + +SEC("abc/whatever") +int abc2(void *ctx) +{ + abc2_called = true; + return 0; +} + +SEC("custom") +int custom1(void *ctx) +{ + custom1_called = true; + return 0; +} + +SEC("custom/something") +int custom2(void *ctx) +{ + custom2_called = true; + return 0; +} + +SEC("kprobe") +int kprobe1(void *ctx) +{ + kprobe1_called = true; + return 0; +} + +SEC("xyz/blah") +int xyz(void *ctx) +{ + int whatever; + + /* use sleepable helper, custom handler should set sleepable flag */ + bpf_copy_from_user(&whatever, sizeof(whatever), NULL); + xyz_called = true; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_d_path.c b/tools/testing/selftests/bpf/progs/test_d_path.c new file mode 100644 index 0000000000..84e1f883f9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_d_path.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define MAX_PATH_LEN 128 +#define MAX_FILES 7 + +pid_t my_pid = 0; +__u32 cnt_stat = 0; +__u32 cnt_close = 0; +char paths_stat[MAX_FILES][MAX_PATH_LEN] = {}; +char paths_close[MAX_FILES][MAX_PATH_LEN] = {}; +int rets_stat[MAX_FILES] = {}; +int rets_close[MAX_FILES] = {}; + +int called_stat = 0; +int called_close = 0; + +SEC("fentry/security_inode_getattr") +int BPF_PROG(prog_stat, struct path *path, struct kstat *stat, + __u32 request_mask, unsigned int query_flags) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + __u32 cnt = cnt_stat; + int ret; + + called_stat = 1; + + if (pid != my_pid) + return 0; + + if (cnt >= MAX_FILES) + return 0; + ret = bpf_d_path(path, paths_stat[cnt], MAX_PATH_LEN); + + rets_stat[cnt] = ret; + cnt_stat++; + return 0; +} + +SEC("fentry/filp_close") +int BPF_PROG(prog_close, struct file *file, void *id) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + __u32 cnt = cnt_close; + int ret; + + called_close = 1; + + if (pid != my_pid) + return 0; + + if (cnt >= MAX_FILES) + return 0; + ret = bpf_d_path(&file->f_path, + paths_close[cnt], MAX_PATH_LEN); + + rets_close[cnt] = ret; + cnt_close++; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_d_path_check_rdonly_mem.c b/tools/testing/selftests/bpf/progs/test_d_path_check_rdonly_mem.c new file mode 100644 index 0000000000..27c27cff6a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_d_path_check_rdonly_mem.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Google */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +extern const int bpf_prog_active __ksym; + +SEC("fentry/security_inode_getattr") +int BPF_PROG(d_path_check_rdonly_mem, struct path *path, struct kstat *stat, + __u32 request_mask, unsigned int query_flags) +{ + void *active; + __u32 cpu; + + cpu = bpf_get_smp_processor_id(); + active = (void *)bpf_per_cpu_ptr(&bpf_prog_active, cpu); + if (active) { + /* FAIL here! 'active' points to readonly memory. bpf helpers + * that update its arguments can not write into it. + */ + bpf_d_path(path, active, sizeof(int)); + } + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_d_path_check_types.c b/tools/testing/selftests/bpf/progs/test_d_path_check_types.c new file mode 100644 index 0000000000..7e02b73613 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_d_path_check_types.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +extern const int bpf_prog_active __ksym; + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 1 << 12); +} ringbuf SEC(".maps"); + +SEC("fentry/security_inode_getattr") +int BPF_PROG(d_path_check_rdonly_mem, struct path *path, struct kstat *stat, + __u32 request_mask, unsigned int query_flags) +{ + void *active; + u32 cpu; + + cpu = bpf_get_smp_processor_id(); + active = (void *)bpf_per_cpu_ptr(&bpf_prog_active, cpu); + if (active) { + /* FAIL here! 'active' points to 'regular' memory. It + * cannot be submitted to ring buffer. + */ + bpf_ringbuf_submit(active, 0); + } + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_deny_namespace.c b/tools/testing/selftests/bpf/progs/test_deny_namespace.c new file mode 100644 index 0000000000..e96b901a73 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_deny_namespace.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <errno.h> +#include <linux/capability.h> + +typedef struct { unsigned long long val; } kernel_cap_t; + +struct cred { + kernel_cap_t cap_effective; +} __attribute__((preserve_access_index)); + +char _license[] SEC("license") = "GPL"; + +SEC("lsm.s/userns_create") +int BPF_PROG(test_userns_create, const struct cred *cred, int ret) +{ + kernel_cap_t caps = cred->cap_effective; + __u64 cap_mask = 1ULL << CAP_SYS_ADMIN; + + if (ret) + return 0; + + ret = -EPERM; + if (caps.val & cap_mask) + return 0; + + return -EPERM; +} diff --git a/tools/testing/selftests/bpf/progs/test_enable_stats.c b/tools/testing/selftests/bpf/progs/test_enable_stats.c new file mode 100644 index 0000000000..1705097d01 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_enable_stats.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <linux/types.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +__u64 count = 0; + +SEC("raw_tracepoint/sys_enter") +int test_enable_stats(void *ctx) +{ + __sync_fetch_and_add(&count, 1); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_endian.c b/tools/testing/selftests/bpf/progs/test_endian.c new file mode 100644 index 0000000000..ddb687c5d1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_endian.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define IN16 0x1234 +#define IN32 0x12345678U +#define IN64 0x123456789abcdef0ULL + +__u16 in16 = 0; +__u32 in32 = 0; +__u64 in64 = 0; + +__u16 out16 = 0; +__u32 out32 = 0; +__u64 out64 = 0; + +__u16 const16 = 0; +__u32 const32 = 0; +__u64 const64 = 0; + +SEC("raw_tp/sys_enter") +int sys_enter(const void *ctx) +{ + out16 = __builtin_bswap16(in16); + out32 = __builtin_bswap32(in32); + out64 = __builtin_bswap64(in64); + const16 = ___bpf_swab16(IN16); + const32 = ___bpf_swab32(IN32); + const64 = ___bpf_swab64(IN64); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_fill_link_info.c b/tools/testing/selftests/bpf/progs/test_fill_link_info.c new file mode 100644 index 0000000000..564f402d56 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_fill_link_info.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */ + +#include "vmlinux.h" +#include <bpf/bpf_tracing.h> +#include <stdbool.h> + +extern bool CONFIG_X86_KERNEL_IBT __kconfig __weak; + +/* This function is here to have CONFIG_X86_KERNEL_IBT + * used and added to object BTF. + */ +int unused(void) +{ + return CONFIG_X86_KERNEL_IBT ? 0 : 1; +} + +SEC("kprobe") +int BPF_PROG(kprobe_run) +{ + return 0; +} + +SEC("uprobe") +int BPF_PROG(uprobe_run) +{ + return 0; +} + +SEC("tracepoint") +int BPF_PROG(tp_run) +{ + return 0; +} + +SEC("kprobe.multi") +int BPF_PROG(kmulti_run) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c new file mode 100644 index 0000000000..b6a6eb279e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* Permit pretty deep stack traces */ +#define MAX_STACK_RAWTP 100 +struct stack_trace_t { + int pid; + int kern_stack_size; + int user_stack_size; + int user_stack_buildid_size; + __u64 kern_stack[MAX_STACK_RAWTP]; + __u64 user_stack[MAX_STACK_RAWTP]; + struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(max_entries, 2); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(__u32)); +} perfmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct stack_trace_t); +} stackdata_map SEC(".maps"); + +/* Allocate per-cpu space twice the needed. For the code below + * usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK); + * if (usize < 0) + * return 0; + * ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); + * + * If we have value_size = MAX_STACK_RAWTP * sizeof(__u64), + * verifier will complain that access "raw_data + usize" + * with size "max_len - usize" may be out of bound. + * The maximum "raw_data + usize" is "raw_data + max_len" + * and the maximum "max_len - usize" is "max_len", verifier + * concludes that the maximum buffer access range is + * "raw_data[0...max_len * 2 - 1]" and hence reject the program. + * + * Doubling the to-be-used max buffer size can fix this verifier + * issue and avoid complicated C programming massaging. + * This is an acceptable workaround since there is one entry here. + */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64[2 * MAX_STACK_RAWTP]); +} rawdata_map SEC(".maps"); + +SEC("raw_tracepoint/sys_enter") +int bpf_prog1(void *ctx) +{ + int max_len, max_buildid_len, total_size; + struct stack_trace_t *data; + long usize, ksize; + void *raw_data; + __u32 key = 0; + + data = bpf_map_lookup_elem(&stackdata_map, &key); + if (!data) + return 0; + + max_len = MAX_STACK_RAWTP * sizeof(__u64); + max_buildid_len = MAX_STACK_RAWTP * sizeof(struct bpf_stack_build_id); + data->pid = bpf_get_current_pid_tgid(); + data->kern_stack_size = bpf_get_stack(ctx, data->kern_stack, + max_len, 0); + data->user_stack_size = bpf_get_stack(ctx, data->user_stack, max_len, + BPF_F_USER_STACK); + data->user_stack_buildid_size = bpf_get_stack( + ctx, data->user_stack_buildid, max_buildid_len, + BPF_F_USER_STACK | BPF_F_USER_BUILD_ID); + bpf_perf_event_output(ctx, &perfmap, 0, data, sizeof(*data)); + + /* write both kernel and user stacks to the same buffer */ + raw_data = bpf_map_lookup_elem(&rawdata_map, &key); + if (!raw_data) + return 0; + + usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK); + if (usize < 0) + return 0; + + ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); + if (ksize < 0) + return 0; + + total_size = usize + ksize; + if (total_size > 0 && total_size <= max_len) + bpf_perf_event_output(ctx, &perfmap, 0, raw_data, total_size); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp_err.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp_err.c new file mode 100644 index 0000000000..8941a41c2a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp_err.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define MAX_STACK_RAWTP 10 + +SEC("raw_tracepoint/sys_enter") +int bpf_prog2(void *ctx) +{ + __u64 stack[MAX_STACK_RAWTP]; + int error; + + /* set all the flags which should return -EINVAL */ + error = bpf_get_stack(ctx, stack, 0, -1); + if (error < 0) + goto loop; + + return error; +loop: + while (1) { + error++; + } +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c new file mode 100644 index 0000000000..719e314ef3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_data.c @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Isovalent, Inc. + +#include <linux/bpf.h> +#include <linux/pkt_cls.h> +#include <string.h> + +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 11); + __type(key, __u32); + __type(value, __u64); +} result_number SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, __u32); + const char (*value)[32]; +} result_string SEC(".maps"); + +struct foo { + __u8 a; + __u32 b; + __u64 c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, __u32); + __type(value, struct foo); +} result_struct SEC(".maps"); + +/* Relocation tests for __u64s. */ +static __u64 num0; +static __u64 num1 = 42; +static const __u64 num2 = 24; +static __u64 num3 = 0; +static __u64 num4 = 0xffeeff; +static const __u64 num5 = 0xabab; +static const __u64 num6 = 0xab; + +/* Relocation tests for strings. */ +static const char str0[32] = "abcdefghijklmnopqrstuvwxyz"; +static char str1[32] = "abcdefghijklmnopqrstuvwxyz"; +static char str2[32]; + +/* Relocation tests for structs. */ +static const struct foo struct0 = { + .a = 42, + .b = 0xfefeefef, + .c = 0x1111111111111111ULL, +}; +static struct foo struct1; +static const struct foo struct2; +static struct foo struct3 = { + .a = 41, + .b = 0xeeeeefef, + .c = 0x2111111111111111ULL, +}; + +#define test_reloc(map, num, var) \ + do { \ + __u32 key = num; \ + bpf_map_update_elem(&result_##map, &key, var, 0); \ + } while (0) + +SEC("tc") +int load_static_data(struct __sk_buff *skb) +{ + static const __u64 bar = ~0; + + test_reloc(number, 0, &num0); + test_reloc(number, 1, &num1); + test_reloc(number, 2, &num2); + test_reloc(number, 3, &num3); + test_reloc(number, 4, &num4); + test_reloc(number, 5, &num5); + num4 = 1234; + test_reloc(number, 6, &num4); + test_reloc(number, 7, &num0); + test_reloc(number, 8, &num6); + + test_reloc(string, 0, str0); + test_reloc(string, 1, str1); + test_reloc(string, 2, str2); + str1[5] = 'x'; + test_reloc(string, 3, str1); + __builtin_memcpy(&str2[2], "hello", sizeof("hello")); + test_reloc(string, 4, str2); + + test_reloc(struct, 0, &struct0); + test_reloc(struct, 1, &struct1); + test_reloc(struct, 2, &struct2); + test_reloc(struct, 3, &struct3); + + test_reloc(number, 9, &struct0.c); + test_reloc(number, 10, &bar); + + return TC_ACT_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c new file mode 100644 index 0000000000..17a9f59bf5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func1.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define MAX_STACK (512 - 3 * 32 + 8) + +static __attribute__ ((noinline)) +int f0(int var, struct __sk_buff *skb) +{ + asm volatile (""); + + return skb->len; +} + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + volatile char buf[MAX_STACK] = {}; + + __sink(buf[MAX_STACK - 1]); + + return f0(0, skb) + skb->len; +} + +int f3(int, struct __sk_buff *skb, int); + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + f3(val, skb, 1); +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb, int var) +{ + volatile char buf[MAX_STACK] = {}; + + __sink(buf[MAX_STACK - 1]); + + return skb->ifindex * val * var; +} + +SEC("tc") +__failure __msg("combined stack size of 4 calls is 544") +int global_func1(struct __sk_buff *skb) +{ + return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func10.c b/tools/testing/selftests/bpf/progs/test_global_func10.c new file mode 100644 index 0000000000..8fba3f3649 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func10.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct Small { + long x; +}; + +struct Big { + long x; + long y; +}; + +__noinline int foo(const struct Big *big) +{ + if (!big) + return 0; + + return bpf_get_prandom_u32() < big->y; +} + +SEC("cgroup_skb/ingress") +__failure __msg("invalid indirect access to stack") +int global_func10(struct __sk_buff *skb) +{ + const struct Small small = {.x = skb->len }; + + return foo((struct Big *)&small) ? 1 : 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func11.c b/tools/testing/selftests/bpf/progs/test_global_func11.c new file mode 100644 index 0000000000..283e036dc4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func11.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct S { + int x; +}; + +__noinline int foo(const struct S *s) +{ + return s ? bpf_get_prandom_u32() < s->x : 0; +} + +SEC("cgroup_skb/ingress") +__failure __msg("Caller passes invalid args into func#1") +int global_func11(struct __sk_buff *skb) +{ + return foo((const void *)skb); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func12.c b/tools/testing/selftests/bpf/progs/test_global_func12.c new file mode 100644 index 0000000000..7f159d83c6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func12.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct S { + int x; +}; + +__noinline int foo(const struct S *s) +{ + return bpf_get_prandom_u32() < s->x; +} + +SEC("cgroup_skb/ingress") +__failure __msg("invalid mem access 'mem_or_null'") +int global_func12(struct __sk_buff *skb) +{ + const struct S s = {.x = skb->len }; + + return foo(&s); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func13.c b/tools/testing/selftests/bpf/progs/test_global_func13.c new file mode 100644 index 0000000000..02ea80da75 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func13.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct S { + int x; +}; + +__noinline int foo(const struct S *s) +{ + if (s) + return bpf_get_prandom_u32() < s->x; + + return 0; +} + +SEC("cgroup_skb/ingress") +__failure __msg("Caller passes invalid args into func#1") +int global_func13(struct __sk_buff *skb) +{ + const struct S *s = (const struct S *)(0xbedabeda); + + return foo(s); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func14.c b/tools/testing/selftests/bpf/progs/test_global_func14.c new file mode 100644 index 0000000000..33b7d5efd7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func14.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct S; + +__noinline int foo(const struct S *s) +{ + if (s) + return bpf_get_prandom_u32() < *(const int *) s; + + return 0; +} + +SEC("cgroup_skb/ingress") +__failure __msg("reference type('FWD S') size cannot be determined") +int global_func14(struct __sk_buff *skb) +{ + + return foo(NULL); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func15.c b/tools/testing/selftests/bpf/progs/test_global_func15.c new file mode 100644 index 0000000000..b512d6a6c7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func15.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +__noinline int foo(unsigned int *v) +{ + if (v) + *v = bpf_get_prandom_u32(); + + return 0; +} + +SEC("cgroup_skb/ingress") +__failure __msg("At program exit the register R0 has value") +int global_func15(struct __sk_buff *skb) +{ + unsigned int v = 1; + + foo(&v); + + return v; +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func16.c b/tools/testing/selftests/bpf/progs/test_global_func16.c new file mode 100644 index 0000000000..e3e64bc472 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func16.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +__noinline int foo(int (*arr)[10]) +{ + if (arr) + return (*arr)[9]; + + return 0; +} + +SEC("cgroup_skb/ingress") +__success +int global_func16(struct __sk_buff *skb) +{ + int array[10]; + + const int rv = foo(&array); + + return rv ? 1 : 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func17.c b/tools/testing/selftests/bpf/progs/test_global_func17.c new file mode 100644 index 0000000000..a32e11c7d9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func17.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +__noinline int foo(int *p) +{ + return p ? (*p = 42) : 0; +} + +const volatile int i; + +SEC("tc") +__failure __msg("Caller passes invalid args into func#1") +int global_func17(struct __sk_buff *skb) +{ + return foo((int *)&i); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func2.c b/tools/testing/selftests/bpf/progs/test_global_func2.c new file mode 100644 index 0000000000..2beab9c3b6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func2.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define MAX_STACK (512 - 3 * 32) + +static __attribute__ ((noinline)) +int f0(int var, struct __sk_buff *skb) +{ + return skb->len; +} + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + volatile char buf[MAX_STACK] = {}; + + __sink(buf[MAX_STACK - 1]); + + return f0(0, skb) + skb->len; +} + +int f3(int, struct __sk_buff *skb, int); + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + f3(val, skb, 1); +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb, int var) +{ + volatile char buf[MAX_STACK] = {}; + + __sink(buf[MAX_STACK - 1]); + + return skb->ifindex * val * var; +} + +SEC("tc") +__success +int global_func2(struct __sk_buff *skb) +{ + return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func3.c b/tools/testing/selftests/bpf/progs/test_global_func3.c new file mode 100644 index 0000000000..142b682d3c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func3.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + return skb->len; +} + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + val; +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb, int var) +{ + return f2(var, skb) + val; +} + +__attribute__ ((noinline)) +int f4(struct __sk_buff *skb) +{ + return f3(1, skb, 2); +} + +__attribute__ ((noinline)) +int f5(struct __sk_buff *skb) +{ + return f4(skb); +} + +__attribute__ ((noinline)) +int f6(struct __sk_buff *skb) +{ + return f5(skb); +} + +__attribute__ ((noinline)) +int f7(struct __sk_buff *skb) +{ + return f6(skb); +} + +__attribute__ ((noinline)) +int f8(struct __sk_buff *skb) +{ + return f7(skb); +} + +SEC("tc") +__failure __msg("the call stack of 8 frames") +int global_func3(struct __sk_buff *skb) +{ + return f8(skb); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func4.c b/tools/testing/selftests/bpf/progs/test_global_func4.c new file mode 100644 index 0000000000..1733d87ad3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func4.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + return skb->len; +} + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + val; +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb, int var) +{ + return f2(var, skb) + val; +} + +__attribute__ ((noinline)) +int f4(struct __sk_buff *skb) +{ + return f3(1, skb, 2); +} + +__attribute__ ((noinline)) +int f5(struct __sk_buff *skb) +{ + return f4(skb); +} + +__attribute__ ((noinline)) +int f6(struct __sk_buff *skb) +{ + return f5(skb); +} + +__attribute__ ((noinline)) +int f7(struct __sk_buff *skb) +{ + return f6(skb); +} + +SEC("tc") +__success +int global_func4(struct __sk_buff *skb) +{ + return f7(skb); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func5.c b/tools/testing/selftests/bpf/progs/test_global_func5.c new file mode 100644 index 0000000000..cc55aedaf8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func5.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + return skb->len; +} + +int f3(int, struct __sk_buff *skb); + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + f3(val, (void *)&val); /* type mismatch */ +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb) +{ + return skb->ifindex * val; +} + +SEC("tc") +__failure __msg("expected pointer to ctx, but got PTR") +int global_func5(struct __sk_buff *skb) +{ + return f1(skb) + f2(2, skb) + f3(3, skb); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func6.c b/tools/testing/selftests/bpf/progs/test_global_func6.c new file mode 100644 index 0000000000..46c38c8f2c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func6.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + return skb->len; +} + +int f3(int, struct __sk_buff *skb); + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + f3(val, skb + 1); /* type mismatch */ +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb) +{ + return skb->ifindex * val; +} + +SEC("tc") +__failure __msg("modified ctx ptr R2") +int global_func6(struct __sk_buff *skb) +{ + return f1(skb) + f2(2, skb) + f3(3, skb); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func7.c b/tools/testing/selftests/bpf/progs/test_global_func7.c new file mode 100644 index 0000000000..f182febfde --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func7.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +__attribute__ ((noinline)) +void foo(struct __sk_buff *skb) +{ + skb->tc_index = 0; +} + +SEC("tc") +__failure __msg("foo() doesn't return scalar") +int global_func7(struct __sk_buff *skb) +{ + foo(skb); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func8.c b/tools/testing/selftests/bpf/progs/test_global_func8.c new file mode 100644 index 0000000000..9b9c57fa2d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func8.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +__noinline int foo(struct __sk_buff *skb) +{ + return bpf_get_prandom_u32(); +} + +SEC("cgroup_skb/ingress") +__success +int global_func8(struct __sk_buff *skb) +{ + if (!foo(skb)) + return 0; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func9.c b/tools/testing/selftests/bpf/progs/test_global_func9.c new file mode 100644 index 0000000000..1f2cb0159b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func9.c @@ -0,0 +1,134 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct S { + int x; +}; + +struct C { + int x; + int y; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct S); +} map SEC(".maps"); + +enum E { + E_ITEM +}; + +static int global_data_x = 100; +static int volatile global_data_y = 500; + +__noinline int foo(const struct S *s) +{ + if (s) + return bpf_get_prandom_u32() < s->x; + + return 0; +} + +__noinline int bar(int *x) +{ + if (x) + *x &= bpf_get_prandom_u32(); + + return 0; +} +__noinline int baz(volatile int *x) +{ + if (x) + *x &= bpf_get_prandom_u32(); + + return 0; +} + +__noinline int qux(enum E *e) +{ + if (e) + return *e; + + return 0; +} + +__noinline int quux(int (*arr)[10]) +{ + if (arr) + return (*arr)[9]; + + return 0; +} + +__noinline int quuz(int **p) +{ + if (p) + *p = NULL; + + return 0; +} + +SEC("cgroup_skb/ingress") +__success +int global_func9(struct __sk_buff *skb) +{ + int result = 0; + + { + const struct S s = {.x = skb->len }; + + result |= foo(&s); + } + + { + const __u32 key = 1; + const struct S *s = bpf_map_lookup_elem(&map, &key); + + result |= foo(s); + } + + { + const struct C c = {.x = skb->len, .y = skb->family }; + + result |= foo((const struct S *)&c); + } + + { + result |= foo(NULL); + } + + { + bar(&result); + bar(&global_data_x); + } + + { + result |= baz(&global_data_y); + } + + { + enum E e = E_ITEM; + + result |= qux(&e); + } + + { + int array[10] = {0}; + + result |= quux(&array); + } + + { + int *p; + + result |= quuz(&p); + } + + return result ? 1 : 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func_args.c b/tools/testing/selftests/bpf/progs/test_global_func_args.c new file mode 100644 index 0000000000..e712bf77da --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func_args.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> + +struct S { + int v; +}; + +struct S global_variable = {}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 7); + __type(key, __u32); + __type(value, int); +} values SEC(".maps"); + +static void save_value(__u32 index, int value) +{ + bpf_map_update_elem(&values, &index, &value, 0); +} + +__noinline int foo(__u32 index, struct S *s) +{ + if (s) { + save_value(index, s->v); + return ++s->v; + } + + save_value(index, 0); + + return 1; +} + +__noinline int bar(__u32 index, volatile struct S *s) +{ + if (s) { + save_value(index, s->v); + return ++s->v; + } + + save_value(index, 0); + + return 1; +} + +__noinline int baz(struct S **s) +{ + if (s) + *s = 0; + + return 0; +} + +SEC("cgroup_skb/ingress") +int test_cls(struct __sk_buff *skb) +{ + __u32 index = 0; + + { + const int v = foo(index++, 0); + + save_value(index++, v); + } + + { + struct S s = { .v = 100 }; + + foo(index++, &s); + save_value(index++, s.v); + } + + { + global_variable.v = 42; + bar(index++, &global_variable); + save_value(index++, global_variable.v); + } + + { + struct S v, *p = &v; + + baz(&p); + save_value(index++, !p); + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c b/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c new file mode 100644 index 0000000000..7faa8eef05 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +static long stack[256]; + +/* + * KPROBE contexts + */ + +__weak int kprobe_typedef_ctx_subprog(bpf_user_pt_regs_t *ctx) +{ + return bpf_get_stack(ctx, &stack, sizeof(stack), 0); +} + +SEC("?kprobe") +__success +int kprobe_typedef_ctx(void *ctx) +{ + return kprobe_typedef_ctx_subprog(ctx); +} + +#define pt_regs_struct_t typeof(*(__PT_REGS_CAST((struct pt_regs *)NULL))) + +__weak int kprobe_struct_ctx_subprog(pt_regs_struct_t *ctx) +{ + return bpf_get_stack((void *)ctx, &stack, sizeof(stack), 0); +} + +SEC("?kprobe") +__success +int kprobe_resolved_ctx(void *ctx) +{ + return kprobe_struct_ctx_subprog(ctx); +} + +/* this is current hack to make this work on old kernels */ +struct bpf_user_pt_regs_t {}; + +__weak int kprobe_workaround_ctx_subprog(struct bpf_user_pt_regs_t *ctx) +{ + return bpf_get_stack(ctx, &stack, sizeof(stack), 0); +} + +SEC("?kprobe") +__success +int kprobe_workaround_ctx(void *ctx) +{ + return kprobe_workaround_ctx_subprog(ctx); +} + +/* + * RAW_TRACEPOINT contexts + */ + +__weak int raw_tp_ctx_subprog(struct bpf_raw_tracepoint_args *ctx) +{ + return bpf_get_stack(ctx, &stack, sizeof(stack), 0); +} + +SEC("?raw_tp") +__success +int raw_tp_ctx(void *ctx) +{ + return raw_tp_ctx_subprog(ctx); +} + +/* + * RAW_TRACEPOINT_WRITABLE contexts + */ + +__weak int raw_tp_writable_ctx_subprog(struct bpf_raw_tracepoint_args *ctx) +{ + return bpf_get_stack(ctx, &stack, sizeof(stack), 0); +} + +SEC("?raw_tp") +__success +int raw_tp_writable_ctx(void *ctx) +{ + return raw_tp_writable_ctx_subprog(ctx); +} + +/* + * PERF_EVENT contexts + */ + +__weak int perf_event_ctx_subprog(struct bpf_perf_event_data *ctx) +{ + return bpf_get_stack(ctx, &stack, sizeof(stack), 0); +} + +SEC("?perf_event") +__success +int perf_event_ctx(void *ctx) +{ + return perf_event_ctx_subprog(ctx); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_map_resize.c b/tools/testing/selftests/bpf/progs/test_global_map_resize.c new file mode 100644 index 0000000000..1fbb73d3e5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_map_resize.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +/* rodata section */ +const volatile pid_t pid; +const volatile size_t bss_array_len; +const volatile size_t data_array_len; + +/* bss section */ +int sum = 0; +int array[1]; + +/* custom data secton */ +int my_array[1] SEC(".data.custom"); + +/* custom data section which should NOT be resizable, + * since it contains a single var which is not an array + */ +int my_int SEC(".data.non_array"); + +/* custom data section which should NOT be resizable, + * since its last var is not an array + */ +int my_array_first[1] SEC(".data.array_not_last"); +int my_int_last SEC(".data.array_not_last"); + +int percpu_arr[1] SEC(".data.percpu_arr"); + +SEC("tp/syscalls/sys_enter_getpid") +int bss_array_sum(void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + /* this will be zero, we just rely on verifier not rejecting this */ + sum = percpu_arr[bpf_get_smp_processor_id()]; + + for (size_t i = 0; i < bss_array_len; ++i) + sum += array[i]; + + return 0; +} + +SEC("tp/syscalls/sys_enter_getuid") +int data_array_sum(void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + /* this will be zero, we just rely on verifier not rejecting this */ + sum = percpu_arr[bpf_get_smp_processor_id()]; + + for (size_t i = 0; i < data_array_len; ++i) + sum += my_array[i]; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_hash_large_key.c b/tools/testing/selftests/bpf/progs/test_hash_large_key.c new file mode 100644 index 0000000000..8b438128f4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_hash_large_key.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 2); + __type(key, struct bigelement); + __type(value, __u32); +} hash_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct bigelement); +} key_map SEC(".maps"); + +struct bigelement { + int a; + char b[4096]; + long long c; +}; + +SEC("raw_tracepoint/sys_enter") +int bpf_hash_large_key_test(void *ctx) +{ + int zero = 0, value = 42; + struct bigelement *key; + + key = bpf_map_lookup_elem(&key_map, &zero); + if (!key) + return 0; + + key->c = 1; + if (bpf_map_update_elem(&hash_map, key, &value, BPF_ANY)) + return 0; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_helper_restricted.c b/tools/testing/selftests/bpf/progs/test_helper_restricted.c new file mode 100644 index 0000000000..5715c569ec --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_helper_restricted.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <time.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct timer { + struct bpf_timer t; +}; + +struct lock { + struct bpf_spin_lock l; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct timer); +} timers SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct lock); +} locks SEC(".maps"); + +static int timer_cb(void *map, int *key, struct timer *timer) +{ + return 0; +} + +static void timer_work(void) +{ + struct timer *timer; + const int key = 0; + + timer = bpf_map_lookup_elem(&timers, &key); + if (timer) { + bpf_timer_init(&timer->t, &timers, CLOCK_MONOTONIC); + bpf_timer_set_callback(&timer->t, timer_cb); + bpf_timer_start(&timer->t, 10E9, 0); + bpf_timer_cancel(&timer->t); + } +} + +static void spin_lock_work(void) +{ + const int key = 0; + struct lock *lock; + + lock = bpf_map_lookup_elem(&locks, &key); + if (lock) { + bpf_spin_lock(&lock->l); + bpf_spin_unlock(&lock->l); + } +} + +SEC("?raw_tp/sys_enter") +int raw_tp_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("?tp/syscalls/sys_enter_nanosleep") +int tp_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("?kprobe") +int kprobe_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("?perf_event") +int perf_event_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("?raw_tp/sys_enter") +int raw_tp_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +SEC("?tp/syscalls/sys_enter_nanosleep") +int tp_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +SEC("?kprobe") +int kprobe_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +SEC("?perf_event") +int perf_event_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +const char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_jhash.h b/tools/testing/selftests/bpf/progs/test_jhash.h new file mode 100644 index 0000000000..c300734d26 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_jhash.h @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <features.h> + +typedef unsigned int u32; + +static __always_inline u32 rol32(u32 word, unsigned int shift) +{ + return (word << shift) | (word >> ((-shift) & 31)); +} + +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} + +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ +} + +#define JHASH_INITVAL 0xdeadbeef + +static ATTR +u32 jhash(const void *key, u32 length, u32 initval) +{ + u32 a, b, c; + const unsigned char *k = key; + + a = b = c = JHASH_INITVAL + length + initval; + + while (length > 12) { + a += *(volatile u32 *)(k); + b += *(volatile u32 *)(k + 4); + c += *(volatile u32 *)(k + 8); + __jhash_mix(a, b, c); + length -= 12; + k += 12; + } + switch (length) { + case 12: c += (u32)k[11]<<24; + case 11: c += (u32)k[10]<<16; + case 10: c += (u32)k[9]<<8; + case 9: c += k[8]; + case 8: b += (u32)k[7]<<24; + case 7: b += (u32)k[6]<<16; + case 6: b += (u32)k[5]<<8; + case 5: b += k[4]; + case 4: a += (u32)k[3]<<24; + case 3: a += (u32)k[2]<<16; + case 2: a += (u32)k[1]<<8; + case 1: a += k[0]; + c ^= a; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c new file mode 100644 index 0000000000..2dde8e3fe4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (C) 2022 Huawei Technologies Duesseldorf GmbH + * + * Author: Roberto Sassu <roberto.sassu@huawei.com> + */ + +#include "vmlinux.h" +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym; +extern void bpf_key_put(struct bpf_key *key) __ksym; +extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr, + struct bpf_dynptr *sig_ptr, + struct bpf_key *trusted_keyring) __ksym; + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 4096); +} ringbuf SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} array_map SEC(".maps"); + +int err, pid; + +char _license[] SEC("license") = "GPL"; + +SEC("?lsm.s/bpf") +__failure __msg("cannot pass in dynptr at an offset=-8") +int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size) +{ + unsigned long val; + + return bpf_verify_pkcs7_signature((struct bpf_dynptr *)&val, + (struct bpf_dynptr *)&val, NULL); +} + +SEC("?lsm.s/bpf") +__failure __msg("arg#0 expected pointer to stack or dynptr_ptr") +int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size) +{ + unsigned long val = 0; + + return bpf_verify_pkcs7_signature((struct bpf_dynptr *)val, + (struct bpf_dynptr *)val, NULL); +} + +SEC("lsm.s/bpf") +int BPF_PROG(dynptr_data_null, int cmd, union bpf_attr *attr, unsigned int size) +{ + struct bpf_key *trusted_keyring; + struct bpf_dynptr ptr; + __u32 *value; + int ret, zero = 0; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + value = bpf_map_lookup_elem(&array_map, &zero); + if (!value) + return 0; + + /* Pass invalid flags. */ + ret = bpf_dynptr_from_mem(value, sizeof(*value), ((__u64)~0ULL), &ptr); + if (ret != -EINVAL) + return 0; + + trusted_keyring = bpf_lookup_system_key(0); + if (!trusted_keyring) + return 0; + + err = bpf_verify_pkcs7_signature(&ptr, &ptr, trusted_keyring); + + bpf_key_put(trusted_keyring); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_ksyms.c b/tools/testing/selftests/bpf/progs/test_ksyms.c new file mode 100644 index 0000000000..6c9cbb5a3b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ksyms.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__u64 out__bpf_link_fops = -1; +__u64 out__bpf_link_fops1 = -1; +__u64 out__btf_size = -1; +__u64 out__per_cpu_start = -1; + +extern const void bpf_link_fops __ksym; +extern const void __start_BTF __ksym; +extern const void __stop_BTF __ksym; +extern const void __per_cpu_start __ksym; +/* non-existing symbol, weak, default to zero */ +extern const void bpf_link_fops1 __ksym __weak; + +SEC("raw_tp/sys_enter") +int handler(const void *ctx) +{ + out__bpf_link_fops = (__u64)&bpf_link_fops; + out__btf_size = (__u64)(&__stop_BTF - &__start_BTF); + out__per_cpu_start = (__u64)&__per_cpu_start; + + out__bpf_link_fops1 = (__u64)&bpf_link_fops1; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_btf.c b/tools/testing/selftests/bpf/progs/test_ksyms_btf.c new file mode 100644 index 0000000000..bb8ea9270f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ksyms_btf.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Google */ + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> + +__u64 out__runqueues_addr = -1; +__u64 out__bpf_prog_active_addr = -1; + +__u32 out__rq_cpu = -1; /* percpu struct fields */ +int out__bpf_prog_active = -1; /* percpu int */ + +__u32 out__this_rq_cpu = -1; +int out__this_bpf_prog_active = -1; + +__u32 out__cpu_0_rq_cpu = -1; /* cpu_rq(0)->cpu */ + +extern const struct rq runqueues __ksym; /* struct type global var. */ +extern const int bpf_prog_active __ksym; /* int type global var. */ + +SEC("raw_tp/sys_enter") +int handler(const void *ctx) +{ + struct rq *rq; + int *active; + __u32 cpu; + + out__runqueues_addr = (__u64)&runqueues; + out__bpf_prog_active_addr = (__u64)&bpf_prog_active; + + cpu = bpf_get_smp_processor_id(); + + /* test bpf_per_cpu_ptr() */ + rq = (struct rq *)bpf_per_cpu_ptr(&runqueues, cpu); + if (rq) + out__rq_cpu = rq->cpu; + active = (int *)bpf_per_cpu_ptr(&bpf_prog_active, cpu); + if (active) + out__bpf_prog_active = *active; + + rq = (struct rq *)bpf_per_cpu_ptr(&runqueues, 0); + if (rq) /* should always be valid, but we can't spare the check. */ + out__cpu_0_rq_cpu = rq->cpu; + + /* test bpf_this_cpu_ptr */ + rq = (struct rq *)bpf_this_cpu_ptr(&runqueues); + out__this_rq_cpu = rq->cpu; + active = (int *)bpf_this_cpu_ptr(&bpf_prog_active); + out__this_bpf_prog_active = *active; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_btf_null_check.c b/tools/testing/selftests/bpf/progs/test_ksyms_btf_null_check.c new file mode 100644 index 0000000000..8bc8f7c637 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ksyms_btf_null_check.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> + +extern const struct rq runqueues __ksym; /* struct type global var. */ +extern const int bpf_prog_active __ksym; /* int type global var. */ + +SEC("raw_tp/sys_enter") +int handler(const void *ctx) +{ + struct rq *rq; + int *active; + __u32 cpu; + + cpu = bpf_get_smp_processor_id(); + rq = (struct rq *)bpf_per_cpu_ptr(&runqueues, cpu); + active = (int *)bpf_per_cpu_ptr(&bpf_prog_active, cpu); + if (active) { + /* READ_ONCE */ + *(volatile int *)active; + /* !rq has not been tested, so verifier should reject. */ + *(volatile int *)(&rq->cpu); + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c b/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c new file mode 100644 index 0000000000..27109b8777 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Google */ + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> + +extern const int bpf_prog_active __ksym; /* int type global var. */ + +SEC("raw_tp/sys_enter") +int handler1(const void *ctx) +{ + int *active; + __u32 cpu; + + cpu = bpf_get_smp_processor_id(); + active = (int *)bpf_per_cpu_ptr(&bpf_prog_active, cpu); + if (active) { + /* Kernel memory obtained from bpf_{per,this}_cpu_ptr + * is read-only, should _not_ pass verification. + */ + /* WRITE_ONCE */ + *(volatile int *)active = -1; + } + + return 0; +} + +__noinline int write_active(int *p) +{ + return p ? (*p = 42) : 0; +} + +SEC("raw_tp/sys_enter") +int handler2(const void *ctx) +{ + int *active; + + active = bpf_this_cpu_ptr(&bpf_prog_active); + write_active(active); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_module.c b/tools/testing/selftests/bpf/progs/test_ksyms_module.c new file mode 100644 index 0000000000..0650d918c0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ksyms_module.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +#define X_0(x) +#define X_1(x) x X_0(x) +#define X_2(x) x X_1(x) +#define X_3(x) x X_2(x) +#define X_4(x) x X_3(x) +#define X_5(x) x X_4(x) +#define X_6(x) x X_5(x) +#define X_7(x) x X_6(x) +#define X_8(x) x X_7(x) +#define X_9(x) x X_8(x) +#define X_10(x) x X_9(x) +#define REPEAT_256(Y) X_2(X_10(X_10(Y))) X_5(X_10(Y)) X_6(Y) + +extern const int bpf_testmod_ksym_percpu __ksym; +extern void bpf_testmod_test_mod_kfunc(int i) __ksym; +extern void bpf_testmod_invalid_mod_kfunc(void) __ksym __weak; + +int out_bpf_testmod_ksym = 0; +const volatile int x = 0; + +SEC("tc") +int load(struct __sk_buff *skb) +{ + /* This will be kept by clang, but removed by verifier. Since it is + * marked as __weak, libbpf and gen_loader don't error out if BTF ID + * is not found for it, instead imm and off is set to 0 for it. + */ + if (x) + bpf_testmod_invalid_mod_kfunc(); + bpf_testmod_test_mod_kfunc(42); + out_bpf_testmod_ksym = *(int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu); + return 0; +} + +SEC("tc") +int load_256(struct __sk_buff *skb) +{ + /* this will fail if kfunc doesn't reuse its own btf fd index */ + REPEAT_256(bpf_testmod_test_mod_kfunc(42);); + bpf_testmod_test_mod_kfunc(42); + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_weak.c b/tools/testing/selftests/bpf/progs/test_ksyms_weak.c new file mode 100644 index 0000000000..d00268c91e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ksyms_weak.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test weak ksyms. + * + * Copyright (c) 2021 Google + */ + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> + +int out__existing_typed = -1; +__u64 out__existing_typeless = -1; + +__u64 out__non_existent_typeless = -1; +__u64 out__non_existent_typed = -1; + +/* existing weak symbols */ + +/* test existing weak symbols can be resolved. */ +extern const struct rq runqueues __ksym __weak; /* typed */ +extern const void bpf_prog_active __ksym __weak; /* typeless */ +struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym __weak; +void bpf_testmod_test_mod_kfunc(int i) __ksym __weak; + + +/* non-existent weak symbols. */ + +/* typeless symbols, default to zero. */ +extern const void bpf_link_fops1 __ksym __weak; + +/* typed symbols, default to zero. */ +extern const int bpf_link_fops2 __ksym __weak; +void invalid_kfunc(void) __ksym __weak; + +SEC("raw_tp/sys_enter") +int pass_handler(const void *ctx) +{ + struct rq *rq; + + /* tests existing symbols. */ + rq = (struct rq *)bpf_per_cpu_ptr(&runqueues, 0); + if (rq && bpf_ksym_exists(&runqueues)) + out__existing_typed = rq->cpu; + out__existing_typeless = (__u64)&bpf_prog_active; + + /* tests non-existent symbols. */ + out__non_existent_typeless = (__u64)&bpf_link_fops1; + + /* tests non-existent symbols. */ + out__non_existent_typed = (__u64)&bpf_link_fops2; + + if (&bpf_link_fops2) /* can't happen */ + out__non_existent_typed = (__u64)bpf_per_cpu_ptr(&bpf_link_fops2, 0); + + if (!bpf_ksym_exists(bpf_task_acquire)) + /* dead code won't be seen by the verifier */ + bpf_task_acquire(0); + + if (!bpf_ksym_exists(bpf_testmod_test_mod_kfunc)) + /* dead code won't be seen by the verifier */ + bpf_testmod_test_mod_kfunc(0); + + if (bpf_ksym_exists(invalid_kfunc)) + /* dead code won't be seen by the verifier */ + invalid_kfunc(); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_l4lb.c b/tools/testing/selftests/bpf/progs/test_l4lb.c new file mode 100644 index 0000000000..c26057ec46 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_l4lb.c @@ -0,0 +1,471 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <stddef.h> +#include <stdbool.h> +#include <string.h> +#include <linux/pkt_cls.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <bpf/bpf_helpers.h> +#include "test_iptunnel_common.h" +#include <bpf/bpf_endian.h> + +static inline __u32 rol32(__u32 word, unsigned int shift) +{ + return (word << shift) | (word >> ((-shift) & 31)); +} + +/* copy paste of jhash from kernel sources to make sure llvm + * can compile it into valid sequence of bpf instructions + */ +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} + +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ +} + +#define JHASH_INITVAL 0xdeadbeef + +typedef unsigned int u32; + +static inline u32 jhash(const void *key, u32 length, u32 initval) +{ + u32 a, b, c; + const unsigned char *k = key; + + a = b = c = JHASH_INITVAL + length + initval; + + while (length > 12) { + a += *(u32 *)(k); + b += *(u32 *)(k + 4); + c += *(u32 *)(k + 8); + __jhash_mix(a, b, c); + length -= 12; + k += 12; + } + switch (length) { + case 12: c += (u32)k[11]<<24; + case 11: c += (u32)k[10]<<16; + case 10: c += (u32)k[9]<<8; + case 9: c += k[8]; + case 8: b += (u32)k[7]<<24; + case 7: b += (u32)k[6]<<16; + case 6: b += (u32)k[5]<<8; + case 5: b += k[4]; + case 4: a += (u32)k[3]<<24; + case 3: a += (u32)k[2]<<16; + case 2: a += (u32)k[1]<<8; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} + +static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) +{ + a += initval; + b += initval; + c += initval; + __jhash_final(a, b, c); + return c; +} + +static inline u32 jhash_2words(u32 a, u32 b, u32 initval) +{ + return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); +} + +#define PCKT_FRAGMENTED 65343 +#define IPV4_HDR_LEN_NO_OPT 20 +#define IPV4_PLUS_ICMP_HDR 28 +#define IPV6_PLUS_ICMP_HDR 48 +#define RING_SIZE 2 +#define MAX_VIPS 12 +#define MAX_REALS 5 +#define CTL_MAP_SIZE 16 +#define CH_RINGS_SIZE (MAX_VIPS * RING_SIZE) +#define F_IPV6 (1 << 0) +#define F_HASH_NO_SRC_PORT (1 << 0) +#define F_ICMP (1 << 0) +#define F_SYN_SET (1 << 1) + +struct packet_description { + union { + __be32 src; + __be32 srcv6[4]; + }; + union { + __be32 dst; + __be32 dstv6[4]; + }; + union { + __u32 ports; + __u16 port16[2]; + }; + __u8 proto; + __u8 flags; +}; + +struct ctl_value { + union { + __u64 value; + __u32 ifindex; + __u8 mac[6]; + }; +}; + +struct vip_meta { + __u32 flags; + __u32 vip_num; +}; + +struct real_definition { + union { + __be32 dst; + __be32 dstv6[4]; + }; + __u8 flags; +}; + +struct vip_stats { + __u64 bytes; + __u64 pkts; +}; + +struct eth_hdr { + unsigned char eth_dest[ETH_ALEN]; + unsigned char eth_source[ETH_ALEN]; + unsigned short eth_proto; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, MAX_VIPS); + __type(key, struct vip); + __type(value, struct vip_meta); +} vip_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, CH_RINGS_SIZE); + __type(key, __u32); + __type(value, __u32); +} ch_rings SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, MAX_REALS); + __type(key, __u32); + __type(value, struct real_definition); +} reals SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, MAX_VIPS); + __type(key, __u32); + __type(value, struct vip_stats); +} stats SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, CTL_MAP_SIZE); + __type(key, __u32); + __type(value, struct ctl_value); +} ctl_array SEC(".maps"); + +static __always_inline __u32 get_packet_hash(struct packet_description *pckt, + bool ipv6) +{ + if (ipv6) + return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS), + pckt->ports, CH_RINGS_SIZE); + else + return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE); +} + +static __always_inline bool get_packet_dst(struct real_definition **real, + struct packet_description *pckt, + struct vip_meta *vip_info, + bool is_ipv6) +{ + __u32 hash = get_packet_hash(pckt, is_ipv6) % RING_SIZE; + __u32 key = RING_SIZE * vip_info->vip_num + hash; + __u32 *real_pos; + + real_pos = bpf_map_lookup_elem(&ch_rings, &key); + if (!real_pos) + return false; + key = *real_pos; + *real = bpf_map_lookup_elem(&reals, &key); + if (!(*real)) + return false; + return true; +} + +static __always_inline int parse_icmpv6(void *data, void *data_end, __u64 off, + struct packet_description *pckt) +{ + struct icmp6hdr *icmp_hdr; + struct ipv6hdr *ip6h; + + icmp_hdr = data + off; + if (icmp_hdr + 1 > data_end) + return TC_ACT_SHOT; + if (icmp_hdr->icmp6_type != ICMPV6_PKT_TOOBIG) + return TC_ACT_OK; + off += sizeof(struct icmp6hdr); + ip6h = data + off; + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + pckt->proto = ip6h->nexthdr; + pckt->flags |= F_ICMP; + memcpy(pckt->srcv6, ip6h->daddr.s6_addr32, 16); + memcpy(pckt->dstv6, ip6h->saddr.s6_addr32, 16); + return TC_ACT_UNSPEC; +} + +static __always_inline int parse_icmp(void *data, void *data_end, __u64 off, + struct packet_description *pckt) +{ + struct icmphdr *icmp_hdr; + struct iphdr *iph; + + icmp_hdr = data + off; + if (icmp_hdr + 1 > data_end) + return TC_ACT_SHOT; + if (icmp_hdr->type != ICMP_DEST_UNREACH || + icmp_hdr->code != ICMP_FRAG_NEEDED) + return TC_ACT_OK; + off += sizeof(struct icmphdr); + iph = data + off; + if (iph + 1 > data_end) + return TC_ACT_SHOT; + if (iph->ihl != 5) + return TC_ACT_SHOT; + pckt->proto = iph->protocol; + pckt->flags |= F_ICMP; + pckt->src = iph->daddr; + pckt->dst = iph->saddr; + return TC_ACT_UNSPEC; +} + +static __always_inline bool parse_udp(void *data, __u64 off, void *data_end, + struct packet_description *pckt) +{ + struct udphdr *udp; + udp = data + off; + + if (udp + 1 > data_end) + return false; + + if (!(pckt->flags & F_ICMP)) { + pckt->port16[0] = udp->source; + pckt->port16[1] = udp->dest; + } else { + pckt->port16[0] = udp->dest; + pckt->port16[1] = udp->source; + } + return true; +} + +static __always_inline bool parse_tcp(void *data, __u64 off, void *data_end, + struct packet_description *pckt) +{ + struct tcphdr *tcp; + + tcp = data + off; + if (tcp + 1 > data_end) + return false; + + if (tcp->syn) + pckt->flags |= F_SYN_SET; + + if (!(pckt->flags & F_ICMP)) { + pckt->port16[0] = tcp->source; + pckt->port16[1] = tcp->dest; + } else { + pckt->port16[0] = tcp->dest; + pckt->port16[1] = tcp->source; + } + return true; +} + +static __always_inline int process_packet(void *data, __u64 off, void *data_end, + bool is_ipv6, struct __sk_buff *skb) +{ + void *pkt_start = (void *)(long)skb->data; + struct packet_description pckt = {}; + struct eth_hdr *eth = pkt_start; + struct bpf_tunnel_key tkey = {}; + struct vip_stats *data_stats; + struct real_definition *dst; + struct vip_meta *vip_info; + struct ctl_value *cval; + __u32 v4_intf_pos = 1; + __u32 v6_intf_pos = 2; + struct ipv6hdr *ip6h; + struct vip vip = {}; + struct iphdr *iph; + int tun_flag = 0; + __u16 pkt_bytes; + __u64 iph_len; + __u32 ifindex; + __u8 protocol; + __u32 vip_num; + int action; + + tkey.tunnel_ttl = 64; + if (is_ipv6) { + ip6h = data + off; + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + + iph_len = sizeof(struct ipv6hdr); + protocol = ip6h->nexthdr; + pckt.proto = protocol; + pkt_bytes = bpf_ntohs(ip6h->payload_len); + off += iph_len; + if (protocol == IPPROTO_FRAGMENT) { + return TC_ACT_SHOT; + } else if (protocol == IPPROTO_ICMPV6) { + action = parse_icmpv6(data, data_end, off, &pckt); + if (action >= 0) + return action; + off += IPV6_PLUS_ICMP_HDR; + } else { + memcpy(pckt.srcv6, ip6h->saddr.s6_addr32, 16); + memcpy(pckt.dstv6, ip6h->daddr.s6_addr32, 16); + } + } else { + iph = data + off; + if (iph + 1 > data_end) + return TC_ACT_SHOT; + if (iph->ihl != 5) + return TC_ACT_SHOT; + + protocol = iph->protocol; + pckt.proto = protocol; + pkt_bytes = bpf_ntohs(iph->tot_len); + off += IPV4_HDR_LEN_NO_OPT; + + if (iph->frag_off & PCKT_FRAGMENTED) + return TC_ACT_SHOT; + if (protocol == IPPROTO_ICMP) { + action = parse_icmp(data, data_end, off, &pckt); + if (action >= 0) + return action; + off += IPV4_PLUS_ICMP_HDR; + } else { + pckt.src = iph->saddr; + pckt.dst = iph->daddr; + } + } + protocol = pckt.proto; + + if (protocol == IPPROTO_TCP) { + if (!parse_tcp(data, off, data_end, &pckt)) + return TC_ACT_SHOT; + } else if (protocol == IPPROTO_UDP) { + if (!parse_udp(data, off, data_end, &pckt)) + return TC_ACT_SHOT; + } else { + return TC_ACT_SHOT; + } + + if (is_ipv6) + memcpy(vip.daddr.v6, pckt.dstv6, 16); + else + vip.daddr.v4 = pckt.dst; + + vip.dport = pckt.port16[1]; + vip.protocol = pckt.proto; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) { + vip.dport = 0; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) + return TC_ACT_SHOT; + pckt.port16[1] = 0; + } + + if (vip_info->flags & F_HASH_NO_SRC_PORT) + pckt.port16[0] = 0; + + if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6)) + return TC_ACT_SHOT; + + if (dst->flags & F_IPV6) { + cval = bpf_map_lookup_elem(&ctl_array, &v6_intf_pos); + if (!cval) + return TC_ACT_SHOT; + ifindex = cval->ifindex; + memcpy(tkey.remote_ipv6, dst->dstv6, 16); + tun_flag = BPF_F_TUNINFO_IPV6; + } else { + cval = bpf_map_lookup_elem(&ctl_array, &v4_intf_pos); + if (!cval) + return TC_ACT_SHOT; + ifindex = cval->ifindex; + tkey.remote_ipv4 = dst->dst; + } + vip_num = vip_info->vip_num; + data_stats = bpf_map_lookup_elem(&stats, &vip_num); + if (!data_stats) + return TC_ACT_SHOT; + data_stats->pkts++; + data_stats->bytes += pkt_bytes; + bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), tun_flag); + *(u32 *)eth->eth_dest = tkey.remote_ipv4; + return bpf_redirect(ifindex, 0); +} + +SEC("tc") +int balancer_ingress(struct __sk_buff *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct eth_hdr *eth = data; + __u32 eth_proto; + __u32 nh_off; + + nh_off = sizeof(struct eth_hdr); + if (data + nh_off > data_end) + return TC_ACT_SHOT; + eth_proto = eth->eth_proto; + if (eth_proto == bpf_htons(ETH_P_IP)) + return process_packet(data, nh_off, data_end, false, ctx); + else if (eth_proto == bpf_htons(ETH_P_IPV6)) + return process_packet(data, nh_off, data_end, true, ctx); + else + return TC_ACT_SHOT; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c new file mode 100644 index 0000000000..c8bc0c6947 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c @@ -0,0 +1,470 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Facebook +#include <stddef.h> +#include <stdbool.h> +#include <string.h> +#include <linux/pkt_cls.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <bpf/bpf_helpers.h> +#include "test_iptunnel_common.h" +#include <bpf/bpf_endian.h> + +static __always_inline __u32 rol32(__u32 word, unsigned int shift) +{ + return (word << shift) | (word >> ((-shift) & 31)); +} + +/* copy paste of jhash from kernel sources to make sure llvm + * can compile it into valid sequence of bpf instructions + */ +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} + +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ +} + +#define JHASH_INITVAL 0xdeadbeef + +typedef unsigned int u32; + +static __noinline u32 jhash(const void *key, u32 length, u32 initval) +{ + u32 a, b, c; + const unsigned char *k = key; + + a = b = c = JHASH_INITVAL + length + initval; + + while (length > 12) { + a += *(u32 *)(k); + b += *(u32 *)(k + 4); + c += *(u32 *)(k + 8); + __jhash_mix(a, b, c); + length -= 12; + k += 12; + } + switch (length) { + case 12: c += (u32)k[11]<<24; + case 11: c += (u32)k[10]<<16; + case 10: c += (u32)k[9]<<8; + case 9: c += k[8]; + case 8: b += (u32)k[7]<<24; + case 7: b += (u32)k[6]<<16; + case 6: b += (u32)k[5]<<8; + case 5: b += k[4]; + case 4: a += (u32)k[3]<<24; + case 3: a += (u32)k[2]<<16; + case 2: a += (u32)k[1]<<8; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} + +static __noinline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) +{ + a += initval; + b += initval; + c += initval; + __jhash_final(a, b, c); + return c; +} + +static __noinline u32 jhash_2words(u32 a, u32 b, u32 initval) +{ + return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); +} + +#define PCKT_FRAGMENTED 65343 +#define IPV4_HDR_LEN_NO_OPT 20 +#define IPV4_PLUS_ICMP_HDR 28 +#define IPV6_PLUS_ICMP_HDR 48 +#define RING_SIZE 2 +#define MAX_VIPS 12 +#define MAX_REALS 5 +#define CTL_MAP_SIZE 16 +#define CH_RINGS_SIZE (MAX_VIPS * RING_SIZE) +#define F_IPV6 (1 << 0) +#define F_HASH_NO_SRC_PORT (1 << 0) +#define F_ICMP (1 << 0) +#define F_SYN_SET (1 << 1) + +struct packet_description { + union { + __be32 src; + __be32 srcv6[4]; + }; + union { + __be32 dst; + __be32 dstv6[4]; + }; + union { + __u32 ports; + __u16 port16[2]; + }; + __u8 proto; + __u8 flags; +}; + +struct ctl_value { + union { + __u64 value; + __u32 ifindex; + __u8 mac[6]; + }; +}; + +struct vip_meta { + __u32 flags; + __u32 vip_num; +}; + +struct real_definition { + union { + __be32 dst; + __be32 dstv6[4]; + }; + __u8 flags; +}; + +struct vip_stats { + __u64 bytes; + __u64 pkts; +}; + +struct eth_hdr { + unsigned char eth_dest[ETH_ALEN]; + unsigned char eth_source[ETH_ALEN]; + unsigned short eth_proto; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, MAX_VIPS); + __type(key, struct vip); + __type(value, struct vip_meta); +} vip_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, CH_RINGS_SIZE); + __type(key, __u32); + __type(value, __u32); +} ch_rings SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, MAX_REALS); + __type(key, __u32); + __type(value, struct real_definition); +} reals SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, MAX_VIPS); + __type(key, __u32); + __type(value, struct vip_stats); +} stats SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, CTL_MAP_SIZE); + __type(key, __u32); + __type(value, struct ctl_value); +} ctl_array SEC(".maps"); + +static __noinline __u32 get_packet_hash(struct packet_description *pckt, bool ipv6) +{ + if (ipv6) + return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS), + pckt->ports, CH_RINGS_SIZE); + else + return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE); +} + +static __noinline bool get_packet_dst(struct real_definition **real, + struct packet_description *pckt, + struct vip_meta *vip_info, + bool is_ipv6) +{ + __u32 hash = get_packet_hash(pckt, is_ipv6); + __u32 key = RING_SIZE * vip_info->vip_num + hash % RING_SIZE; + __u32 *real_pos; + + if (hash != 0x358459b7 /* jhash of ipv4 packet */ && + hash != 0x2f4bc6bb /* jhash of ipv6 packet */) + return false; + + real_pos = bpf_map_lookup_elem(&ch_rings, &key); + if (!real_pos) + return false; + key = *real_pos; + *real = bpf_map_lookup_elem(&reals, &key); + if (!(*real)) + return false; + return true; +} + +static __noinline int parse_icmpv6(void *data, void *data_end, __u64 off, + struct packet_description *pckt) +{ + struct icmp6hdr *icmp_hdr; + struct ipv6hdr *ip6h; + + icmp_hdr = data + off; + if (icmp_hdr + 1 > data_end) + return TC_ACT_SHOT; + if (icmp_hdr->icmp6_type != ICMPV6_PKT_TOOBIG) + return TC_ACT_OK; + off += sizeof(struct icmp6hdr); + ip6h = data + off; + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + pckt->proto = ip6h->nexthdr; + pckt->flags |= F_ICMP; + memcpy(pckt->srcv6, ip6h->daddr.s6_addr32, 16); + memcpy(pckt->dstv6, ip6h->saddr.s6_addr32, 16); + return TC_ACT_UNSPEC; +} + +static __noinline int parse_icmp(void *data, void *data_end, __u64 off, + struct packet_description *pckt) +{ + struct icmphdr *icmp_hdr; + struct iphdr *iph; + + icmp_hdr = data + off; + if (icmp_hdr + 1 > data_end) + return TC_ACT_SHOT; + if (icmp_hdr->type != ICMP_DEST_UNREACH || + icmp_hdr->code != ICMP_FRAG_NEEDED) + return TC_ACT_OK; + off += sizeof(struct icmphdr); + iph = data + off; + if (iph + 1 > data_end) + return TC_ACT_SHOT; + if (iph->ihl != 5) + return TC_ACT_SHOT; + pckt->proto = iph->protocol; + pckt->flags |= F_ICMP; + pckt->src = iph->daddr; + pckt->dst = iph->saddr; + return TC_ACT_UNSPEC; +} + +static __noinline bool parse_udp(void *data, __u64 off, void *data_end, + struct packet_description *pckt) +{ + struct udphdr *udp; + udp = data + off; + + if (udp + 1 > data_end) + return false; + + if (!(pckt->flags & F_ICMP)) { + pckt->port16[0] = udp->source; + pckt->port16[1] = udp->dest; + } else { + pckt->port16[0] = udp->dest; + pckt->port16[1] = udp->source; + } + return true; +} + +static __noinline bool parse_tcp(void *data, __u64 off, void *data_end, + struct packet_description *pckt) +{ + struct tcphdr *tcp; + + tcp = data + off; + if (tcp + 1 > data_end) + return false; + + if (tcp->syn) + pckt->flags |= F_SYN_SET; + + if (!(pckt->flags & F_ICMP)) { + pckt->port16[0] = tcp->source; + pckt->port16[1] = tcp->dest; + } else { + pckt->port16[0] = tcp->dest; + pckt->port16[1] = tcp->source; + } + return true; +} + +static __noinline int process_packet(void *data, __u64 off, void *data_end, + bool is_ipv6, struct __sk_buff *skb) +{ + void *pkt_start = (void *)(long)skb->data; + struct packet_description pckt = {}; + struct eth_hdr *eth = pkt_start; + struct bpf_tunnel_key tkey = {}; + struct vip_stats *data_stats; + struct real_definition *dst; + struct vip_meta *vip_info; + struct ctl_value *cval; + __u32 v4_intf_pos = 1; + __u32 v6_intf_pos = 2; + struct ipv6hdr *ip6h; + struct vip vip = {}; + struct iphdr *iph; + int tun_flag = 0; + __u16 pkt_bytes; + __u64 iph_len; + __u32 ifindex; + __u8 protocol; + __u32 vip_num; + int action; + + tkey.tunnel_ttl = 64; + if (is_ipv6) { + ip6h = data + off; + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + + iph_len = sizeof(struct ipv6hdr); + protocol = ip6h->nexthdr; + pckt.proto = protocol; + pkt_bytes = bpf_ntohs(ip6h->payload_len); + off += iph_len; + if (protocol == IPPROTO_FRAGMENT) { + return TC_ACT_SHOT; + } else if (protocol == IPPROTO_ICMPV6) { + action = parse_icmpv6(data, data_end, off, &pckt); + if (action >= 0) + return action; + off += IPV6_PLUS_ICMP_HDR; + } else { + memcpy(pckt.srcv6, ip6h->saddr.s6_addr32, 16); + memcpy(pckt.dstv6, ip6h->daddr.s6_addr32, 16); + } + } else { + iph = data + off; + if (iph + 1 > data_end) + return TC_ACT_SHOT; + if (iph->ihl != 5) + return TC_ACT_SHOT; + + protocol = iph->protocol; + pckt.proto = protocol; + pkt_bytes = bpf_ntohs(iph->tot_len); + off += IPV4_HDR_LEN_NO_OPT; + + if (iph->frag_off & PCKT_FRAGMENTED) + return TC_ACT_SHOT; + if (protocol == IPPROTO_ICMP) { + action = parse_icmp(data, data_end, off, &pckt); + if (action >= 0) + return action; + off += IPV4_PLUS_ICMP_HDR; + } else { + pckt.src = iph->saddr; + pckt.dst = iph->daddr; + } + } + protocol = pckt.proto; + + if (protocol == IPPROTO_TCP) { + if (!parse_tcp(data, off, data_end, &pckt)) + return TC_ACT_SHOT; + } else if (protocol == IPPROTO_UDP) { + if (!parse_udp(data, off, data_end, &pckt)) + return TC_ACT_SHOT; + } else { + return TC_ACT_SHOT; + } + + if (is_ipv6) + memcpy(vip.daddr.v6, pckt.dstv6, 16); + else + vip.daddr.v4 = pckt.dst; + + vip.dport = pckt.port16[1]; + vip.protocol = pckt.proto; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) { + vip.dport = 0; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) + return TC_ACT_SHOT; + pckt.port16[1] = 0; + } + + if (vip_info->flags & F_HASH_NO_SRC_PORT) + pckt.port16[0] = 0; + + if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6)) + return TC_ACT_SHOT; + + if (dst->flags & F_IPV6) { + cval = bpf_map_lookup_elem(&ctl_array, &v6_intf_pos); + if (!cval) + return TC_ACT_SHOT; + ifindex = cval->ifindex; + memcpy(tkey.remote_ipv6, dst->dstv6, 16); + tun_flag = BPF_F_TUNINFO_IPV6; + } else { + cval = bpf_map_lookup_elem(&ctl_array, &v4_intf_pos); + if (!cval) + return TC_ACT_SHOT; + ifindex = cval->ifindex; + tkey.remote_ipv4 = dst->dst; + } + vip_num = vip_info->vip_num; + data_stats = bpf_map_lookup_elem(&stats, &vip_num); + if (!data_stats) + return TC_ACT_SHOT; + data_stats->pkts++; + data_stats->bytes += pkt_bytes; + bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), tun_flag); + *(u32 *)eth->eth_dest = tkey.remote_ipv4; + return bpf_redirect(ifindex, 0); +} + +SEC("tc") +int balancer_ingress(struct __sk_buff *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct eth_hdr *eth = data; + __u32 eth_proto; + __u32 nh_off; + + nh_off = sizeof(struct eth_hdr); + if (data + nh_off > data_end) + return TC_ACT_SHOT; + eth_proto = eth->eth_proto; + if (eth_proto == bpf_htons(ETH_P_IP)) + return process_packet(data, nh_off, data_end, false, ctx); + else if (eth_proto == bpf_htons(ETH_P_IPV6)) + return process_packet(data, nh_off, data_end, true, ctx); + else + return TC_ACT_SHOT; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_l4lb_noinline_dynptr.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline_dynptr.c new file mode 100644 index 0000000000..f997f50807 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline_dynptr.c @@ -0,0 +1,487 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Facebook +#include <stddef.h> +#include <stdbool.h> +#include <string.h> +#include <linux/pkt_cls.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <bpf/bpf_helpers.h> +#include "test_iptunnel_common.h" +#include <bpf/bpf_endian.h> + +#include "bpf_kfuncs.h" + +static __always_inline __u32 rol32(__u32 word, unsigned int shift) +{ + return (word << shift) | (word >> ((-shift) & 31)); +} + +/* copy paste of jhash from kernel sources to make sure llvm + * can compile it into valid sequence of bpf instructions + */ +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} + +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ +} + +#define JHASH_INITVAL 0xdeadbeef + +typedef unsigned int u32; + +static __noinline u32 jhash(const void *key, u32 length, u32 initval) +{ + u32 a, b, c; + const unsigned char *k = key; + + a = b = c = JHASH_INITVAL + length + initval; + + while (length > 12) { + a += *(u32 *)(k); + b += *(u32 *)(k + 4); + c += *(u32 *)(k + 8); + __jhash_mix(a, b, c); + length -= 12; + k += 12; + } + switch (length) { + case 12: c += (u32)k[11]<<24; + case 11: c += (u32)k[10]<<16; + case 10: c += (u32)k[9]<<8; + case 9: c += k[8]; + case 8: b += (u32)k[7]<<24; + case 7: b += (u32)k[6]<<16; + case 6: b += (u32)k[5]<<8; + case 5: b += k[4]; + case 4: a += (u32)k[3]<<24; + case 3: a += (u32)k[2]<<16; + case 2: a += (u32)k[1]<<8; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} + +static __noinline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) +{ + a += initval; + b += initval; + c += initval; + __jhash_final(a, b, c); + return c; +} + +static __noinline u32 jhash_2words(u32 a, u32 b, u32 initval) +{ + return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); +} + +#define PCKT_FRAGMENTED 65343 +#define IPV4_HDR_LEN_NO_OPT 20 +#define IPV4_PLUS_ICMP_HDR 28 +#define IPV6_PLUS_ICMP_HDR 48 +#define RING_SIZE 2 +#define MAX_VIPS 12 +#define MAX_REALS 5 +#define CTL_MAP_SIZE 16 +#define CH_RINGS_SIZE (MAX_VIPS * RING_SIZE) +#define F_IPV6 (1 << 0) +#define F_HASH_NO_SRC_PORT (1 << 0) +#define F_ICMP (1 << 0) +#define F_SYN_SET (1 << 1) + +struct packet_description { + union { + __be32 src; + __be32 srcv6[4]; + }; + union { + __be32 dst; + __be32 dstv6[4]; + }; + union { + __u32 ports; + __u16 port16[2]; + }; + __u8 proto; + __u8 flags; +}; + +struct ctl_value { + union { + __u64 value; + __u32 ifindex; + __u8 mac[6]; + }; +}; + +struct vip_meta { + __u32 flags; + __u32 vip_num; +}; + +struct real_definition { + union { + __be32 dst; + __be32 dstv6[4]; + }; + __u8 flags; +}; + +struct vip_stats { + __u64 bytes; + __u64 pkts; +}; + +struct eth_hdr { + unsigned char eth_dest[ETH_ALEN]; + unsigned char eth_source[ETH_ALEN]; + unsigned short eth_proto; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, MAX_VIPS); + __type(key, struct vip); + __type(value, struct vip_meta); +} vip_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, CH_RINGS_SIZE); + __type(key, __u32); + __type(value, __u32); +} ch_rings SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, MAX_REALS); + __type(key, __u32); + __type(value, struct real_definition); +} reals SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, MAX_VIPS); + __type(key, __u32); + __type(value, struct vip_stats); +} stats SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, CTL_MAP_SIZE); + __type(key, __u32); + __type(value, struct ctl_value); +} ctl_array SEC(".maps"); + +static __noinline __u32 get_packet_hash(struct packet_description *pckt, bool ipv6) +{ + if (ipv6) + return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS), + pckt->ports, CH_RINGS_SIZE); + else + return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE); +} + +static __noinline bool get_packet_dst(struct real_definition **real, + struct packet_description *pckt, + struct vip_meta *vip_info, + bool is_ipv6) +{ + __u32 hash = get_packet_hash(pckt, is_ipv6); + __u32 key = RING_SIZE * vip_info->vip_num + hash % RING_SIZE; + __u32 *real_pos; + + if (hash != 0x358459b7 /* jhash of ipv4 packet */ && + hash != 0x2f4bc6bb /* jhash of ipv6 packet */) + return false; + + real_pos = bpf_map_lookup_elem(&ch_rings, &key); + if (!real_pos) + return false; + key = *real_pos; + *real = bpf_map_lookup_elem(&reals, &key); + if (!(*real)) + return false; + return true; +} + +static __noinline int parse_icmpv6(struct bpf_dynptr *skb_ptr, __u64 off, + struct packet_description *pckt) +{ + __u8 buffer[sizeof(struct ipv6hdr)] = {}; + struct icmp6hdr *icmp_hdr; + struct ipv6hdr *ip6h; + + icmp_hdr = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer)); + if (!icmp_hdr) + return TC_ACT_SHOT; + + if (icmp_hdr->icmp6_type != ICMPV6_PKT_TOOBIG) + return TC_ACT_OK; + off += sizeof(struct icmp6hdr); + ip6h = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer)); + if (!ip6h) + return TC_ACT_SHOT; + pckt->proto = ip6h->nexthdr; + pckt->flags |= F_ICMP; + memcpy(pckt->srcv6, ip6h->daddr.s6_addr32, 16); + memcpy(pckt->dstv6, ip6h->saddr.s6_addr32, 16); + return TC_ACT_UNSPEC; +} + +static __noinline int parse_icmp(struct bpf_dynptr *skb_ptr, __u64 off, + struct packet_description *pckt) +{ + __u8 buffer_icmp[sizeof(struct iphdr)] = {}; + __u8 buffer_ip[sizeof(struct iphdr)] = {}; + struct icmphdr *icmp_hdr; + struct iphdr *iph; + + icmp_hdr = bpf_dynptr_slice(skb_ptr, off, buffer_icmp, sizeof(buffer_icmp)); + if (!icmp_hdr) + return TC_ACT_SHOT; + if (icmp_hdr->type != ICMP_DEST_UNREACH || + icmp_hdr->code != ICMP_FRAG_NEEDED) + return TC_ACT_OK; + off += sizeof(struct icmphdr); + iph = bpf_dynptr_slice(skb_ptr, off, buffer_ip, sizeof(buffer_ip)); + if (!iph || iph->ihl != 5) + return TC_ACT_SHOT; + pckt->proto = iph->protocol; + pckt->flags |= F_ICMP; + pckt->src = iph->daddr; + pckt->dst = iph->saddr; + return TC_ACT_UNSPEC; +} + +static __noinline bool parse_udp(struct bpf_dynptr *skb_ptr, __u64 off, + struct packet_description *pckt) +{ + __u8 buffer[sizeof(struct udphdr)] = {}; + struct udphdr *udp; + + udp = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer)); + if (!udp) + return false; + + if (!(pckt->flags & F_ICMP)) { + pckt->port16[0] = udp->source; + pckt->port16[1] = udp->dest; + } else { + pckt->port16[0] = udp->dest; + pckt->port16[1] = udp->source; + } + return true; +} + +static __noinline bool parse_tcp(struct bpf_dynptr *skb_ptr, __u64 off, + struct packet_description *pckt) +{ + __u8 buffer[sizeof(struct tcphdr)] = {}; + struct tcphdr *tcp; + + tcp = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer)); + if (!tcp) + return false; + + if (tcp->syn) + pckt->flags |= F_SYN_SET; + + if (!(pckt->flags & F_ICMP)) { + pckt->port16[0] = tcp->source; + pckt->port16[1] = tcp->dest; + } else { + pckt->port16[0] = tcp->dest; + pckt->port16[1] = tcp->source; + } + return true; +} + +static __noinline int process_packet(struct bpf_dynptr *skb_ptr, + struct eth_hdr *eth, __u64 off, + bool is_ipv6, struct __sk_buff *skb) +{ + struct packet_description pckt = {}; + struct bpf_tunnel_key tkey = {}; + struct vip_stats *data_stats; + struct real_definition *dst; + struct vip_meta *vip_info; + struct ctl_value *cval; + __u32 v4_intf_pos = 1; + __u32 v6_intf_pos = 2; + struct ipv6hdr *ip6h; + struct vip vip = {}; + struct iphdr *iph; + int tun_flag = 0; + __u16 pkt_bytes; + __u64 iph_len; + __u32 ifindex; + __u8 protocol; + __u32 vip_num; + int action; + + tkey.tunnel_ttl = 64; + if (is_ipv6) { + __u8 buffer[sizeof(struct ipv6hdr)] = {}; + + ip6h = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer)); + if (!ip6h) + return TC_ACT_SHOT; + + iph_len = sizeof(struct ipv6hdr); + protocol = ip6h->nexthdr; + pckt.proto = protocol; + pkt_bytes = bpf_ntohs(ip6h->payload_len); + off += iph_len; + if (protocol == IPPROTO_FRAGMENT) { + return TC_ACT_SHOT; + } else if (protocol == IPPROTO_ICMPV6) { + action = parse_icmpv6(skb_ptr, off, &pckt); + if (action >= 0) + return action; + off += IPV6_PLUS_ICMP_HDR; + } else { + memcpy(pckt.srcv6, ip6h->saddr.s6_addr32, 16); + memcpy(pckt.dstv6, ip6h->daddr.s6_addr32, 16); + } + } else { + __u8 buffer[sizeof(struct iphdr)] = {}; + + iph = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer)); + if (!iph || iph->ihl != 5) + return TC_ACT_SHOT; + + protocol = iph->protocol; + pckt.proto = protocol; + pkt_bytes = bpf_ntohs(iph->tot_len); + off += IPV4_HDR_LEN_NO_OPT; + + if (iph->frag_off & PCKT_FRAGMENTED) + return TC_ACT_SHOT; + if (protocol == IPPROTO_ICMP) { + action = parse_icmp(skb_ptr, off, &pckt); + if (action >= 0) + return action; + off += IPV4_PLUS_ICMP_HDR; + } else { + pckt.src = iph->saddr; + pckt.dst = iph->daddr; + } + } + protocol = pckt.proto; + + if (protocol == IPPROTO_TCP) { + if (!parse_tcp(skb_ptr, off, &pckt)) + return TC_ACT_SHOT; + } else if (protocol == IPPROTO_UDP) { + if (!parse_udp(skb_ptr, off, &pckt)) + return TC_ACT_SHOT; + } else { + return TC_ACT_SHOT; + } + + if (is_ipv6) + memcpy(vip.daddr.v6, pckt.dstv6, 16); + else + vip.daddr.v4 = pckt.dst; + + vip.dport = pckt.port16[1]; + vip.protocol = pckt.proto; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) { + vip.dport = 0; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) + return TC_ACT_SHOT; + pckt.port16[1] = 0; + } + + if (vip_info->flags & F_HASH_NO_SRC_PORT) + pckt.port16[0] = 0; + + if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6)) + return TC_ACT_SHOT; + + if (dst->flags & F_IPV6) { + cval = bpf_map_lookup_elem(&ctl_array, &v6_intf_pos); + if (!cval) + return TC_ACT_SHOT; + ifindex = cval->ifindex; + memcpy(tkey.remote_ipv6, dst->dstv6, 16); + tun_flag = BPF_F_TUNINFO_IPV6; + } else { + cval = bpf_map_lookup_elem(&ctl_array, &v4_intf_pos); + if (!cval) + return TC_ACT_SHOT; + ifindex = cval->ifindex; + tkey.remote_ipv4 = dst->dst; + } + vip_num = vip_info->vip_num; + data_stats = bpf_map_lookup_elem(&stats, &vip_num); + if (!data_stats) + return TC_ACT_SHOT; + data_stats->pkts++; + data_stats->bytes += pkt_bytes; + bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), tun_flag); + *(u32 *)eth->eth_dest = tkey.remote_ipv4; + return bpf_redirect(ifindex, 0); +} + +SEC("tc") +int balancer_ingress(struct __sk_buff *ctx) +{ + __u8 buffer[sizeof(struct eth_hdr)] = {}; + struct bpf_dynptr ptr; + struct eth_hdr *eth; + __u32 eth_proto; + __u32 nh_off; + int err; + + nh_off = sizeof(struct eth_hdr); + + bpf_dynptr_from_skb(ctx, 0, &ptr); + eth = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer)); + if (!eth) + return TC_ACT_SHOT; + eth_proto = eth->eth_proto; + if (eth_proto == bpf_htons(ETH_P_IP)) + err = process_packet(&ptr, eth, nh_off, false, ctx); + else if (eth_proto == bpf_htons(ETH_P_IPV6)) + err = process_packet(&ptr, eth, nh_off, true, ctx); + else + return TC_ACT_SHOT; + + if (eth == buffer) + bpf_dynptr_write(&ptr, 0, buffer, sizeof(buffer), 0); + + return err; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c new file mode 100644 index 0000000000..67c14ba1e8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18 +const volatile int skip = 0; +#else +const volatile int skip = 1; +#endif + +volatile const short val1 = -1; +volatile const int val2 = -1; +short val3 = -1; +int val4 = -1; +int done1, done2, ret1, ret2; + +SEC("?raw_tp/sys_enter") +int rdonly_map_prog(const void *ctx) +{ + if (done1) + return 0; + + done1 = 1; + /* val1/val2 readonly map */ + if (val1 == val2) + ret1 = 1; + return 0; + +} + +SEC("?raw_tp/sys_enter") +int map_val_prog(const void *ctx) +{ + if (done2) + return 0; + + done2 = 1; + /* val1/val2 regular read/write map */ + if (val3 == val4) + ret2 = 1; + return 0; + +} + +struct bpf_testmod_struct_arg_1 { + int a; +}; + +long long int_member; + +SEC("?fentry/bpf_testmod_test_arg_ptr_to_struct") +int BPF_PROG2(test_ptr_struct_arg, struct bpf_testmod_struct_arg_1 *, p) +{ + /* probed memory access */ + int_member = p->a; + return 0; +} + +long long set_optlen, set_retval; + +SEC("?cgroup/getsockopt") +int _getsockopt(volatile struct bpf_sockopt *ctx) +{ + int old_optlen, old_retval; + + old_optlen = ctx->optlen; + old_retval = ctx->retval; + + ctx->optlen = -1; + ctx->retval = -1; + + /* sign extension for ctx member */ + set_optlen = ctx->optlen; + set_retval = ctx->retval; + + ctx->optlen = old_optlen; + ctx->retval = old_retval; + + return 0; +} + +long long set_mark; + +SEC("?tc") +int _tc(volatile struct __sk_buff *skb) +{ + long long tmp_mark; + int old_mark; + + old_mark = skb->mark; + + skb->mark = 0xf6fe; + + /* narrowed sign extension for ctx member */ +#if __clang_major__ >= 18 + /* force narrow one-byte signed load. Otherwise, compiler may + * generate a 32-bit unsigned load followed by an s8 movsx. + */ + asm volatile ("r1 = *(s8 *)(%[ctx] + %[off_mark])\n\t" + "%[tmp_mark] = r1" + : [tmp_mark]"=r"(tmp_mark) + : [ctx]"r"(skb), + [off_mark]"i"(offsetof(struct __sk_buff, mark)) + : "r1"); +#else + tmp_mark = (char)skb->mark; +#endif + set_mark = tmp_mark; + + skb->mark = old_mark; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_legacy_printk.c b/tools/testing/selftests/bpf/progs/test_legacy_printk.c new file mode 100644 index 0000000000..42718cd8e6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_legacy_printk.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <linux/bpf.h> +#define BPF_NO_GLOBAL_DATA +#include <bpf/bpf_helpers.h> + +char LICENSE[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, int); + __uint(max_entries, 1); +} my_pid_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, int); + __uint(max_entries, 1); +} res_map SEC(".maps"); + +volatile int my_pid_var = 0; +volatile int res_var = 0; + +SEC("tp/raw_syscalls/sys_enter") +int handle_legacy(void *ctx) +{ + int zero = 0, *my_pid, cur_pid, *my_res; + + my_pid = bpf_map_lookup_elem(&my_pid_map, &zero); + if (!my_pid) + return 1; + + cur_pid = bpf_get_current_pid_tgid() >> 32; + if (cur_pid != *my_pid) + return 1; + + my_res = bpf_map_lookup_elem(&res_map, &zero); + if (!my_res) + return 1; + + if (*my_res == 0) + /* use bpf_printk() in combination with BPF_NO_GLOBAL_DATA to + * force .rodata.str1.1 section that previously caused + * problems on old kernels due to libbpf always tried to + * create a global data map for it + */ + bpf_printk("Legacy-case bpf_printk test, pid %d\n", cur_pid); + *my_res = 1; + + return *my_res; +} + +SEC("tp/raw_syscalls/sys_enter") +int handle_modern(void *ctx) +{ + int cur_pid; + + cur_pid = bpf_get_current_pid_tgid() >> 32; + if (cur_pid != my_pid_var) + return 1; + + if (res_var == 0) + /* we need bpf_printk() to validate libbpf logic around unused + * global maps and legacy kernels; see comment in handle_legacy() + */ + bpf_printk("Modern-case bpf_printk test, pid %d\n", cur_pid); + res_var = 1; + + return res_var; +} diff --git a/tools/testing/selftests/bpf/progs/test_libbpf_get_fd_by_id_opts.c b/tools/testing/selftests/bpf/progs/test_libbpf_get_fd_by_id_opts.c new file mode 100644 index 0000000000..f5ac5f3e89 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_libbpf_get_fd_by_id_opts.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (C) 2022 Huawei Technologies Duesseldorf GmbH + * + * Author: Roberto Sassu <roberto.sassu@huawei.com> + */ + +#include "vmlinux.h" +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +/* From include/linux/mm.h. */ +#define FMODE_WRITE 0x2 + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} data_input SEC(".maps"); + +char _license[] SEC("license") = "GPL"; + +SEC("lsm/bpf_map") +int BPF_PROG(check_access, struct bpf_map *map, fmode_t fmode) +{ + if (map != (struct bpf_map *)&data_input) + return 0; + + if (fmode & FMODE_WRITE) + return -EACCES; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_link_pinning.c b/tools/testing/selftests/bpf/progs/test_link_pinning.c new file mode 100644 index 0000000000..bbf2a5264d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_link_pinning.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +int in = 0; +int out = 0; + +SEC("raw_tp/sys_enter") +int raw_tp_prog(const void *ctx) +{ + out = in; + return 0; +} + +SEC("tp_btf/sys_enter") +int tp_btf_prog(const void *ctx) +{ + out = in; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c b/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c new file mode 100644 index 0000000000..7a6620671a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +// test ir decoder +// +// Copyright (C) 2018 Sean Young <sean@mess.org> + +#include <linux/bpf.h> +#include <linux/lirc.h> +#include <bpf/bpf_helpers.h> + +SEC("lirc_mode2") +int bpf_decoder(unsigned int *sample) +{ + if (LIRC_IS_PULSE(*sample)) { + unsigned int duration = LIRC_VALUE(*sample); + + if (duration & 0x10000) + bpf_rc_keydown(sample, 0x40, duration & 0xffff, 0); + if (duration & 0x20000) + bpf_rc_pointer_rel(sample, (duration >> 8) & 0xff, + duration & 0xff); + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_log_buf.c b/tools/testing/selftests/bpf/progs/test_log_buf.c new file mode 100644 index 0000000000..199f459bd5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_log_buf.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +int a[4]; +const volatile int off = 4000; + +SEC("raw_tp/sys_enter") +int good_prog(const void *ctx) +{ + a[0] = (int)(long)ctx; + return a[1]; +} + +SEC("raw_tp/sys_enter") +int bad_prog(const void *ctx) +{ + /* out of bounds access */ + return a[off]; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_log_fixup.c b/tools/testing/selftests/bpf/progs/test_log_fixup.c new file mode 100644 index 0000000000..1bd48feaaa --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_log_fixup.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +struct task_struct___bad { + int pid; + int fake_field; + void *fake_field_subprog; +} __attribute__((preserve_access_index)); + +SEC("?raw_tp/sys_enter") +int bad_relo(const void *ctx) +{ + static struct task_struct___bad *t; + + return bpf_core_field_size(t->fake_field); +} + +static __noinline int bad_subprog(void) +{ + static struct task_struct___bad *t; + + /* ugliness below is a field offset relocation */ + return (void *)&t->fake_field_subprog - (void *)t; +} + +SEC("?raw_tp/sys_enter") +int bad_relo_subprog(const void *ctx) +{ + static struct task_struct___bad *t; + + return bad_subprog() + bpf_core_field_size(t->pid); +} + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} existing_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} missing_map SEC(".maps"); + +SEC("?raw_tp/sys_enter") +int use_missing_map(const void *ctx) +{ + int zero = 0, *value; + + value = bpf_map_lookup_elem(&existing_map, &zero); + + value = bpf_map_lookup_elem(&missing_map, &zero); + + return value != NULL; +} + +extern int bpf_nonexistent_kfunc(void) __ksym __weak; + +SEC("?raw_tp/sys_enter") +int use_missing_kfunc(const void *ctx) +{ + bpf_nonexistent_kfunc(); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_lookup_and_delete.c b/tools/testing/selftests/bpf/progs/test_lookup_and_delete.c new file mode 100644 index 0000000000..3a193f42c7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_lookup_and_delete.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +__u32 set_pid = 0; +__u64 set_key = 0; +__u64 set_value = 0; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 2); + __type(key, __u64); + __type(value, __u64); +} hash_map SEC(".maps"); + +SEC("tp/syscalls/sys_enter_getpgid") +int bpf_lookup_and_delete_test(const void *ctx) +{ + if (set_pid == bpf_get_current_pid_tgid() >> 32) + bpf_map_update_elem(&hash_map, &set_key, &set_value, BPF_NOEXIST); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_lookup_key.c b/tools/testing/selftests/bpf/progs/test_lookup_key.c new file mode 100644 index 0000000000..c73776990a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_lookup_key.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (C) 2022 Huawei Technologies Duesseldorf GmbH + * + * Author: Roberto Sassu <roberto.sassu@huawei.com> + */ + +#include "vmlinux.h" +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +__u32 monitored_pid; +__u32 key_serial; +__u32 key_id; +__u64 flags; + +extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym; +extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym; +extern void bpf_key_put(struct bpf_key *key) __ksym; + +SEC("lsm.s/bpf") +int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size) +{ + struct bpf_key *bkey; + __u32 pid; + + pid = bpf_get_current_pid_tgid() >> 32; + if (pid != monitored_pid) + return 0; + + if (key_serial) + bkey = bpf_lookup_user_key(key_serial, flags); + else + bkey = bpf_lookup_system_key(key_id); + + if (!bkey) + return -ENOENT; + + bpf_key_put(bkey); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c new file mode 100644 index 0000000000..d6cb986e75 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct grehdr { + __be16 flags; + __be16 protocol; +}; + +SEC("encap_gre") +int bpf_lwt_encap_gre(struct __sk_buff *skb) +{ + struct encap_hdr { + struct iphdr iph; + struct grehdr greh; + } hdr; + int err; + + memset(&hdr, 0, sizeof(struct encap_hdr)); + + hdr.iph.ihl = 5; + hdr.iph.version = 4; + hdr.iph.ttl = 0x40; + hdr.iph.protocol = 47; /* IPPROTO_GRE */ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + hdr.iph.saddr = 0x640110ac; /* 172.16.1.100 */ + hdr.iph.daddr = 0x641010ac; /* 172.16.16.100 */ +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + hdr.iph.saddr = 0xac100164; /* 172.16.1.100 */ + hdr.iph.daddr = 0xac101064; /* 172.16.16.100 */ +#else +#error "Fix your compiler's __BYTE_ORDER__?!" +#endif + hdr.iph.tot_len = bpf_htons(skb->len + sizeof(struct encap_hdr)); + + hdr.greh.protocol = skb->protocol; + + err = bpf_lwt_push_encap(skb, BPF_LWT_ENCAP_IP, &hdr, + sizeof(struct encap_hdr)); + if (err) + return BPF_DROP; + + return BPF_LWT_REROUTE; +} + +SEC("encap_gre6") +int bpf_lwt_encap_gre6(struct __sk_buff *skb) +{ + struct encap_hdr { + struct ipv6hdr ip6hdr; + struct grehdr greh; + } hdr; + int err; + + memset(&hdr, 0, sizeof(struct encap_hdr)); + + hdr.ip6hdr.version = 6; + hdr.ip6hdr.payload_len = bpf_htons(skb->len + sizeof(struct grehdr)); + hdr.ip6hdr.nexthdr = 47; /* IPPROTO_GRE */ + hdr.ip6hdr.hop_limit = 0x40; + /* fb01::1 */ + hdr.ip6hdr.saddr.s6_addr[0] = 0xfb; + hdr.ip6hdr.saddr.s6_addr[1] = 1; + hdr.ip6hdr.saddr.s6_addr[15] = 1; + /* fb10::1 */ + hdr.ip6hdr.daddr.s6_addr[0] = 0xfb; + hdr.ip6hdr.daddr.s6_addr[1] = 0x10; + hdr.ip6hdr.daddr.s6_addr[15] = 1; + + hdr.greh.protocol = skb->protocol; + + err = bpf_lwt_push_encap(skb, BPF_LWT_ENCAP_IP, &hdr, + sizeof(struct encap_hdr)); + if (err) + return BPF_DROP; + + return BPF_LWT_REROUTE; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_lwt_redirect.c b/tools/testing/selftests/bpf/progs/test_lwt_redirect.c new file mode 100644 index 0000000000..8c895122f2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_lwt_redirect.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> +#include <linux/ip.h> +#include "bpf_tracing_net.h" + +/* We don't care about whether the packet can be received by network stack. + * Just care if the packet is sent to the correct device at correct direction + * and not panic the kernel. + */ +static int prepend_dummy_mac(struct __sk_buff *skb) +{ + char mac[] = {0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0xf, + 0xe, 0xd, 0xc, 0xb, 0xa, 0x08, 0x00}; + + if (bpf_skb_change_head(skb, ETH_HLEN, 0)) + return -1; + + if (bpf_skb_store_bytes(skb, 0, mac, sizeof(mac), 0)) + return -1; + + return 0; +} + +/* Use the last byte of IP address to redirect the packet */ +static int get_redirect_target(struct __sk_buff *skb) +{ + struct iphdr *iph = NULL; + void *start = (void *)(long)skb->data; + void *end = (void *)(long)skb->data_end; + + if (start + sizeof(*iph) > end) + return -1; + + iph = (struct iphdr *)start; + return bpf_ntohl(iph->daddr) & 0xff; +} + +SEC("redir_ingress") +int test_lwt_redirect_in(struct __sk_buff *skb) +{ + int target = get_redirect_target(skb); + + if (target < 0) + return BPF_OK; + + if (prepend_dummy_mac(skb)) + return BPF_DROP; + + return bpf_redirect(target, BPF_F_INGRESS); +} + +SEC("redir_egress") +int test_lwt_redirect_out(struct __sk_buff *skb) +{ + int target = get_redirect_target(skb); + + if (target < 0) + return BPF_OK; + + if (prepend_dummy_mac(skb)) + return BPF_DROP; + + return bpf_redirect(target, 0); +} + +SEC("redir_egress_nomac") +int test_lwt_redirect_out_nomac(struct __sk_buff *skb) +{ + int target = get_redirect_target(skb); + + if (target < 0) + return BPF_OK; + + return bpf_redirect(target, 0); +} + +SEC("redir_ingress_nomac") +int test_lwt_redirect_in_nomac(struct __sk_buff *skb) +{ + int target = get_redirect_target(skb); + + if (target < 0) + return BPF_OK; + + return bpf_redirect(target, BPF_F_INGRESS); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_lwt_reroute.c b/tools/testing/selftests/bpf/progs/test_lwt_reroute.c new file mode 100644 index 0000000000..1dc6435192 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_lwt_reroute.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <inttypes.h> +#include <linux/bpf.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> +#include <linux/if_ether.h> +#include <linux/ip.h> + +/* This function extracts the last byte of the daddr, and uses it + * as output dev index. + */ +SEC("lwt_xmit") +int test_lwt_reroute(struct __sk_buff *skb) +{ + struct iphdr *iph = NULL; + void *start = (void *)(long)skb->data; + void *end = (void *)(long)skb->data_end; + + /* set mark at most once */ + if (skb->mark != 0) + return BPF_OK; + + if (start + sizeof(*iph) > end) + return BPF_DROP; + + iph = (struct iphdr *)start; + skb->mark = bpf_ntohl(iph->daddr) & 0xff; + + /* do not reroute x.x.x.0 packets */ + if (skb->mark == 0) + return BPF_OK; + + return BPF_LWT_REROUTE; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c new file mode 100644 index 0000000000..48ff2b2ad5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c @@ -0,0 +1,426 @@ +#include <stddef.h> +#include <inttypes.h> +#include <errno.h> +#include <linux/seg6_local.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +/* Packet parsing state machine helpers. */ +#define cursor_advance(_cursor, _len) \ + ({ void *_tmp = _cursor; _cursor += _len; _tmp; }) + +#define SR6_FLAG_ALERT (1 << 4) + +#define BPF_PACKET_HEADER __attribute__((packed)) + +struct ip6_t { + unsigned int ver:4; + unsigned int priority:8; + unsigned int flow_label:20; + unsigned short payload_len; + unsigned char next_header; + unsigned char hop_limit; + unsigned long long src_hi; + unsigned long long src_lo; + unsigned long long dst_hi; + unsigned long long dst_lo; +} BPF_PACKET_HEADER; + +struct ip6_addr_t { + unsigned long long hi; + unsigned long long lo; +} BPF_PACKET_HEADER; + +struct ip6_srh_t { + unsigned char nexthdr; + unsigned char hdrlen; + unsigned char type; + unsigned char segments_left; + unsigned char first_segment; + unsigned char flags; + unsigned short tag; + + struct ip6_addr_t segments[0]; +} BPF_PACKET_HEADER; + +struct sr6_tlv_t { + unsigned char type; + unsigned char len; + unsigned char value[0]; +} BPF_PACKET_HEADER; + +static __always_inline struct ip6_srh_t *get_srh(struct __sk_buff *skb) +{ + void *cursor, *data_end; + struct ip6_srh_t *srh; + struct ip6_t *ip; + uint8_t *ipver; + + data_end = (void *)(long)skb->data_end; + cursor = (void *)(long)skb->data; + ipver = (uint8_t *)cursor; + + if ((void *)ipver + sizeof(*ipver) > data_end) + return NULL; + + if ((*ipver >> 4) != 6) + return NULL; + + ip = cursor_advance(cursor, sizeof(*ip)); + if ((void *)ip + sizeof(*ip) > data_end) + return NULL; + + if (ip->next_header != 43) + return NULL; + + srh = cursor_advance(cursor, sizeof(*srh)); + if ((void *)srh + sizeof(*srh) > data_end) + return NULL; + + if (srh->type != 4) + return NULL; + + return srh; +} + +static __always_inline +int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad, + uint32_t old_pad, uint32_t pad_off) +{ + int err; + + if (new_pad != old_pad) { + err = bpf_lwt_seg6_adjust_srh(skb, pad_off, + (int) new_pad - (int) old_pad); + if (err) + return err; + } + + if (new_pad > 0) { + char pad_tlv_buf[16] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0}; + struct sr6_tlv_t *pad_tlv = (struct sr6_tlv_t *) pad_tlv_buf; + + pad_tlv->type = SR6_TLV_PADDING; + pad_tlv->len = new_pad - 2; + + err = bpf_lwt_seg6_store_bytes(skb, pad_off, + (void *)pad_tlv_buf, new_pad); + if (err) + return err; + } + + return 0; +} + +static __always_inline +int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh, + uint32_t *tlv_off, uint32_t *pad_size, + uint32_t *pad_off) +{ + uint32_t srh_off, cur_off; + int offset_valid = 0; + int err; + + srh_off = (char *)srh - (char *)(long)skb->data; + // cur_off = end of segments, start of possible TLVs + cur_off = srh_off + sizeof(*srh) + + sizeof(struct ip6_addr_t) * (srh->first_segment + 1); + + *pad_off = 0; + + // we can only go as far as ~10 TLVs due to the BPF max stack size + #pragma clang loop unroll(full) + for (int i = 0; i < 10; i++) { + struct sr6_tlv_t tlv; + + if (cur_off == *tlv_off) + offset_valid = 1; + + if (cur_off >= srh_off + ((srh->hdrlen + 1) << 3)) + break; + + err = bpf_skb_load_bytes(skb, cur_off, &tlv, sizeof(tlv)); + if (err) + return err; + + if (tlv.type == SR6_TLV_PADDING) { + *pad_size = tlv.len + sizeof(tlv); + *pad_off = cur_off; + + if (*tlv_off == srh_off) { + *tlv_off = cur_off; + offset_valid = 1; + } + break; + + } else if (tlv.type == SR6_TLV_HMAC) { + break; + } + + cur_off += sizeof(tlv) + tlv.len; + } // we reached the padding or HMAC TLVs, or the end of the SRH + + if (*pad_off == 0) + *pad_off = cur_off; + + if (*tlv_off == -1) + *tlv_off = cur_off; + else if (!offset_valid) + return -EINVAL; + + return 0; +} + +static __always_inline +int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off, + struct sr6_tlv_t *itlv, uint8_t tlv_size) +{ + uint32_t srh_off = (char *)srh - (char *)(long)skb->data; + uint8_t len_remaining, new_pad; + uint32_t pad_off = 0; + uint32_t pad_size = 0; + uint32_t partial_srh_len; + int err; + + if (tlv_off != -1) + tlv_off += srh_off; + + if (itlv->type == SR6_TLV_PADDING || itlv->type == SR6_TLV_HMAC) + return -EINVAL; + + err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off); + if (err) + return err; + + err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, sizeof(*itlv) + itlv->len); + if (err) + return err; + + err = bpf_lwt_seg6_store_bytes(skb, tlv_off, (void *)itlv, tlv_size); + if (err) + return err; + + // the following can't be moved inside update_tlv_pad because the + // bpf verifier has some issues with it + pad_off += sizeof(*itlv) + itlv->len; + partial_srh_len = pad_off - srh_off; + len_remaining = partial_srh_len % 8; + new_pad = 8 - len_remaining; + + if (new_pad == 1) // cannot pad for 1 byte only + new_pad = 9; + else if (new_pad == 8) + new_pad = 0; + + return update_tlv_pad(skb, new_pad, pad_size, pad_off); +} + +static __always_inline +int delete_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, + uint32_t tlv_off) +{ + uint32_t srh_off = (char *)srh - (char *)(long)skb->data; + uint8_t len_remaining, new_pad; + uint32_t partial_srh_len; + uint32_t pad_off = 0; + uint32_t pad_size = 0; + struct sr6_tlv_t tlv; + int err; + + tlv_off += srh_off; + + err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off); + if (err) + return err; + + err = bpf_skb_load_bytes(skb, tlv_off, &tlv, sizeof(tlv)); + if (err) + return err; + + err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, -(sizeof(tlv) + tlv.len)); + if (err) + return err; + + pad_off -= sizeof(tlv) + tlv.len; + partial_srh_len = pad_off - srh_off; + len_remaining = partial_srh_len % 8; + new_pad = 8 - len_remaining; + if (new_pad == 1) // cannot pad for 1 byte only + new_pad = 9; + else if (new_pad == 8) + new_pad = 0; + + return update_tlv_pad(skb, new_pad, pad_size, pad_off); +} + +static __always_inline +int has_egr_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh) +{ + int tlv_offset = sizeof(struct ip6_t) + sizeof(struct ip6_srh_t) + + ((srh->first_segment + 1) << 4); + struct sr6_tlv_t tlv; + + if (bpf_skb_load_bytes(skb, tlv_offset, &tlv, sizeof(struct sr6_tlv_t))) + return 0; + + if (tlv.type == SR6_TLV_EGRESS && tlv.len == 18) { + struct ip6_addr_t egr_addr; + + if (bpf_skb_load_bytes(skb, tlv_offset + 4, &egr_addr, 16)) + return 0; + + // check if egress TLV value is correct + if (bpf_be64_to_cpu(egr_addr.hi) == 0xfd00000000000000 && + bpf_be64_to_cpu(egr_addr.lo) == 0x4) + return 1; + } + + return 0; +} + +// This function will push a SRH with segments fd00::1, fd00::2, fd00::3, +// fd00::4 +SEC("encap_srh") +int __encap_srh(struct __sk_buff *skb) +{ + unsigned long long hi = 0xfd00000000000000; + struct ip6_addr_t *seg; + struct ip6_srh_t *srh; + char srh_buf[72]; // room for 4 segments + int err; + + srh = (struct ip6_srh_t *)srh_buf; + srh->nexthdr = 0; + srh->hdrlen = 8; + srh->type = 4; + srh->segments_left = 3; + srh->first_segment = 3; + srh->flags = 0; + srh->tag = 0; + + seg = (struct ip6_addr_t *)((char *)srh + sizeof(*srh)); + + #pragma clang loop unroll(full) + for (unsigned long long lo = 0; lo < 4; lo++) { + seg->lo = bpf_cpu_to_be64(4 - lo); + seg->hi = bpf_cpu_to_be64(hi); + seg = (struct ip6_addr_t *)((char *)seg + sizeof(*seg)); + } + + err = bpf_lwt_push_encap(skb, 0, (void *)srh, sizeof(srh_buf)); + if (err) + return BPF_DROP; + + return BPF_REDIRECT; +} + +// Add an Egress TLV fc00::4, add the flag A, +// and apply End.X action to fc42::1 +SEC("add_egr_x") +int __add_egr_x(struct __sk_buff *skb) +{ + unsigned long long hi = 0xfc42000000000000; + unsigned long long lo = 0x1; + struct ip6_srh_t *srh = get_srh(skb); + uint8_t new_flags = SR6_FLAG_ALERT; + struct ip6_addr_t addr; + int err, offset; + + if (srh == NULL) + return BPF_DROP; + + uint8_t tlv[20] = {2, 18, 0, 0, 0xfd, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x4}; + + err = add_tlv(skb, srh, (srh->hdrlen+1) << 3, + (struct sr6_tlv_t *)&tlv, 20); + if (err) + return BPF_DROP; + + offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags); + err = bpf_lwt_seg6_store_bytes(skb, offset, + (void *)&new_flags, sizeof(new_flags)); + if (err) + return BPF_DROP; + + addr.lo = bpf_cpu_to_be64(lo); + addr.hi = bpf_cpu_to_be64(hi); + err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_X, + (void *)&addr, sizeof(addr)); + if (err) + return BPF_DROP; + return BPF_REDIRECT; +} + +// Pop the Egress TLV, reset the flags, change the tag 2442 and finally do a +// simple End action +SEC("pop_egr") +int __pop_egr(struct __sk_buff *skb) +{ + struct ip6_srh_t *srh = get_srh(skb); + uint16_t new_tag = bpf_htons(2442); + uint8_t new_flags = 0; + int err, offset; + + if (srh == NULL) + return BPF_DROP; + + if (srh->flags != SR6_FLAG_ALERT) + return BPF_DROP; + + if (srh->hdrlen != 11) // 4 segments + Egress TLV + Padding TLV + return BPF_DROP; + + if (!has_egr_tlv(skb, srh)) + return BPF_DROP; + + err = delete_tlv(skb, srh, 8 + (srh->first_segment + 1) * 16); + if (err) + return BPF_DROP; + + offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags); + if (bpf_lwt_seg6_store_bytes(skb, offset, (void *)&new_flags, + sizeof(new_flags))) + return BPF_DROP; + + offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, tag); + if (bpf_lwt_seg6_store_bytes(skb, offset, (void *)&new_tag, + sizeof(new_tag))) + return BPF_DROP; + + return BPF_OK; +} + +// Inspect if the Egress TLV and flag have been removed, if the tag is correct, +// then apply a End.T action to reach the last segment +SEC("inspect_t") +int __inspect_t(struct __sk_buff *skb) +{ + struct ip6_srh_t *srh = get_srh(skb); + int table = 117; + int err; + + if (srh == NULL) + return BPF_DROP; + + if (srh->flags != 0) + return BPF_DROP; + + if (srh->tag != bpf_htons(2442)) + return BPF_DROP; + + if (srh->hdrlen != 8) // 4 segments + return BPF_DROP; + + err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_T, + (void *)&table, sizeof(table)); + + if (err) + return BPF_DROP; + + return BPF_REDIRECT; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c new file mode 100644 index 0000000000..f416032ba8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/types.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1); + __uint(map_flags, 0); + __type(key, __u32); + __type(value, __u32); +} mim_array SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 1); + __uint(map_flags, 0); + __type(key, int); + __type(value, __u32); +} mim_hash SEC(".maps"); + +SEC("xdp") +int xdp_mimtest0(struct xdp_md *ctx) +{ + int value = 123; + int *value_p; + int key = 0; + void *map; + + map = bpf_map_lookup_elem(&mim_array, &key); + if (!map) + return XDP_DROP; + + bpf_map_update_elem(map, &key, &value, 0); + value_p = bpf_map_lookup_elem(map, &key); + if (!value_p || *value_p != 123) + return XDP_DROP; + + map = bpf_map_lookup_elem(&mim_hash, &key); + if (!map) + return XDP_DROP; + + bpf_map_update_elem(map, &key, &value, 0); + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c b/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c new file mode 100644 index 0000000000..9c7d75cf0b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Isovalent, Inc. */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct inner { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, int); + __uint(max_entries, 4); +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 0); /* This will make map creation to fail */ + __type(key, __u32); + __array(values, struct inner); +} mim SEC(".maps"); + +SEC("xdp") +int xdp_noop0(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_map_init.c b/tools/testing/selftests/bpf/progs/test_map_init.c new file mode 100644 index 0000000000..c89d28ead6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_map_init.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +__u64 inKey = 0; +__u64 inValue = 0; +__u32 inPid = 0; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 2); + __type(key, __u64); + __type(value, __u64); +} hashmap1 SEC(".maps"); + + +SEC("tp/syscalls/sys_enter_getpgid") +int sysenter_getpgid(const void *ctx) +{ + /* Just do it for once, when called from our own test prog. This + * ensures the map value is only updated for a single CPU. + */ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + + if (cur_pid == inPid) + bpf_map_update_elem(&hashmap1, &inKey, &inValue, BPF_NOEXIST); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_map_lock.c b/tools/testing/selftests/bpf/progs/test_map_lock.c new file mode 100644 index 0000000000..1c02511b73 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_map_lock.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include <linux/version.h> +#include <bpf/bpf_helpers.h> + +#define VAR_NUM 16 + +struct hmap_elem { + struct bpf_spin_lock lock; + int var[VAR_NUM]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct hmap_elem); +} hash_map SEC(".maps"); + +struct array_elem { + struct bpf_spin_lock lock; + int var[VAR_NUM]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct array_elem); +} array_map SEC(".maps"); + +SEC("cgroup/skb") +int bpf_map_lock_test(struct __sk_buff *skb) +{ + struct hmap_elem *val; + int rnd = bpf_get_prandom_u32(); + int key = 0, err = 1, i; + struct array_elem *q; + + val = bpf_map_lookup_elem(&hash_map, &key); + if (!val) + goto err; + /* spin_lock in hash map */ + bpf_spin_lock(&val->lock); + for (i = 0; i < VAR_NUM; i++) + val->var[i] = rnd; + bpf_spin_unlock(&val->lock); + + /* spin_lock in array */ + q = bpf_map_lookup_elem(&array_map, &key); + if (!q) + goto err; + bpf_spin_lock(&q->lock); + for (i = 0; i < VAR_NUM; i++) + q->var[i] = rnd; + bpf_spin_unlock(&q->lock); + err = 0; +err: + return err; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_map_lookup_percpu_elem.c b/tools/testing/selftests/bpf/progs/test_map_lookup_percpu_elem.c new file mode 100644 index 0000000000..ca827b1092 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_map_lookup_percpu_elem.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Bytedance */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +__u64 percpu_array_elem_sum = 0; +__u64 percpu_hash_elem_sum = 0; +__u64 percpu_lru_hash_elem_sum = 0; +const volatile int nr_cpus; +const volatile int my_pid; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} percpu_array_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 1); + __type(key, __u64); + __type(value, __u64); +} percpu_hash_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LRU_PERCPU_HASH); + __uint(max_entries, 1); + __type(key, __u64); + __type(value, __u64); +} percpu_lru_hash_map SEC(".maps"); + +struct read_percpu_elem_ctx { + void *map; + __u64 sum; +}; + +static int read_percpu_elem_callback(__u32 index, struct read_percpu_elem_ctx *ctx) +{ + __u64 key = 0; + __u64 *value; + + value = bpf_map_lookup_percpu_elem(ctx->map, &key, index); + if (value) + ctx->sum += *value; + return 0; +} + +SEC("tp/syscalls/sys_enter_getuid") +int sysenter_getuid(const void *ctx) +{ + struct read_percpu_elem_ctx map_ctx; + + if (my_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + map_ctx.map = &percpu_array_map; + map_ctx.sum = 0; + bpf_loop(nr_cpus, read_percpu_elem_callback, &map_ctx, 0); + percpu_array_elem_sum = map_ctx.sum; + + map_ctx.map = &percpu_hash_map; + map_ctx.sum = 0; + bpf_loop(nr_cpus, read_percpu_elem_callback, &map_ctx, 0); + percpu_hash_elem_sum = map_ctx.sum; + + map_ctx.map = &percpu_lru_hash_map; + map_ctx.sum = 0; + bpf_loop(nr_cpus, read_percpu_elem_callback, &map_ctx, 0); + percpu_lru_hash_elem_sum = map_ctx.sum; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_map_ops.c b/tools/testing/selftests/bpf/progs/test_map_ops.c new file mode 100644 index 0000000000..b53b46a090 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_map_ops.c @@ -0,0 +1,138 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} hash_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_STACK); + __uint(max_entries, 1); + __type(value, int); +} stack_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} array_map SEC(".maps"); + +const volatile pid_t pid; +long err = 0; + +static u64 callback(u64 map, u64 key, u64 val, u64 ctx, u64 flags) +{ + return 0; +} + +SEC("tp/syscalls/sys_enter_getpid") +int map_update(void *ctx) +{ + const int key = 0; + const int val = 1; + + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + err = bpf_map_update_elem(&hash_map, &key, &val, BPF_NOEXIST); + + return 0; +} + +SEC("tp/syscalls/sys_enter_getppid") +int map_delete(void *ctx) +{ + const int key = 0; + + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + err = bpf_map_delete_elem(&hash_map, &key); + + return 0; +} + +SEC("tp/syscalls/sys_enter_getuid") +int map_push(void *ctx) +{ + const int val = 1; + + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + err = bpf_map_push_elem(&stack_map, &val, 0); + + return 0; +} + +SEC("tp/syscalls/sys_enter_geteuid") +int map_pop(void *ctx) +{ + int val; + + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + err = bpf_map_pop_elem(&stack_map, &val); + + return 0; +} + +SEC("tp/syscalls/sys_enter_getgid") +int map_peek(void *ctx) +{ + int val; + + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + err = bpf_map_peek_elem(&stack_map, &val); + + return 0; +} + +SEC("tp/syscalls/sys_enter_gettid") +int map_for_each_pass(void *ctx) +{ + const int key = 0; + const int val = 1; + const u64 flags = 0; + int callback_ctx; + + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + bpf_map_update_elem(&array_map, &key, &val, flags); + + err = bpf_for_each_map_elem(&array_map, callback, &callback_ctx, flags); + + return 0; +} + +SEC("tp/syscalls/sys_enter_getpgid") +int map_for_each_fail(void *ctx) +{ + const int key = 0; + const int val = 1; + const u64 flags = BPF_NOEXIST; + int callback_ctx; + + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + bpf_map_update_elem(&array_map, &key, &val, flags); + + /* calling for_each with non-zero flags will return error */ + err = bpf_for_each_map_elem(&array_map, callback, &callback_ctx, flags); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_migrate_reuseport.c b/tools/testing/selftests/bpf/progs/test_migrate_reuseport.c new file mode 100644 index 0000000000..27df571abf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_migrate_reuseport.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Check if we can migrate child sockets. + * + * 1. If reuse_md->migrating_sk is NULL (SYN packet), + * return SK_PASS without selecting a listener. + * 2. If reuse_md->migrating_sk is not NULL (socket migration), + * select a listener (reuseport_map[migrate_map[cookie]]) + * + * Author: Kuniyuki Iwashima <kuniyu@amazon.co.jp> + */ + +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include <linux/in.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY); + __uint(max_entries, 256); + __type(key, int); + __type(value, __u64); +} reuseport_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 256); + __type(key, __u64); + __type(value, int); +} migrate_map SEC(".maps"); + +int migrated_at_close = 0; +int migrated_at_close_fastopen = 0; +int migrated_at_send_synack = 0; +int migrated_at_recv_ack = 0; +__be16 server_port; + +SEC("xdp") +int drop_ack(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eth = data; + struct tcphdr *tcp = NULL; + + if (eth + 1 > data_end) + goto pass; + + switch (bpf_ntohs(eth->h_proto)) { + case ETH_P_IP: { + struct iphdr *ip = (struct iphdr *)(eth + 1); + + if (ip + 1 > data_end) + goto pass; + + if (ip->protocol != IPPROTO_TCP) + goto pass; + + tcp = (struct tcphdr *)((void *)ip + ip->ihl * 4); + break; + } + case ETH_P_IPV6: { + struct ipv6hdr *ipv6 = (struct ipv6hdr *)(eth + 1); + + if (ipv6 + 1 > data_end) + goto pass; + + if (ipv6->nexthdr != IPPROTO_TCP) + goto pass; + + tcp = (struct tcphdr *)(ipv6 + 1); + break; + } + default: + goto pass; + } + + if (tcp + 1 > data_end) + goto pass; + + if (tcp->dest != server_port) + goto pass; + + if (!tcp->syn && tcp->ack) + return XDP_DROP; + +pass: + return XDP_PASS; +} + +SEC("sk_reuseport/migrate") +int migrate_reuseport(struct sk_reuseport_md *reuse_md) +{ + int *key, flags = 0, state, err; + __u64 cookie; + + if (!reuse_md->migrating_sk) + return SK_PASS; + + state = reuse_md->migrating_sk->state; + cookie = bpf_get_socket_cookie(reuse_md->sk); + + key = bpf_map_lookup_elem(&migrate_map, &cookie); + if (!key) + return SK_DROP; + + err = bpf_sk_select_reuseport(reuse_md, &reuseport_map, key, flags); + if (err) + return SK_PASS; + + switch (state) { + case BPF_TCP_ESTABLISHED: + __sync_fetch_and_add(&migrated_at_close, 1); + break; + case BPF_TCP_SYN_RECV: + __sync_fetch_and_add(&migrated_at_close_fastopen, 1); + break; + case BPF_TCP_NEW_SYN_RECV: + if (!reuse_md->len) + __sync_fetch_and_add(&migrated_at_send_synack, 1); + else + __sync_fetch_and_add(&migrated_at_recv_ack, 1); + break; + } + + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c new file mode 100644 index 0000000000..d487153a83 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c @@ -0,0 +1,329 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <stddef.h> +#include <errno.h> +#include <stdbool.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include <linux/socket.h> +#include <linux/bpf.h> +#include <linux/types.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#define BPF_PROG_TEST_TCP_HDR_OPTIONS +#include "test_tcp_hdr_options.h" + +__u16 last_addr16_n = __bpf_htons(1); +__u16 active_lport_n = 0; +__u16 active_lport_h = 0; +__u16 passive_lport_n = 0; +__u16 passive_lport_h = 0; + +/* options received at passive side */ +unsigned int nr_pure_ack = 0; +unsigned int nr_data = 0; +unsigned int nr_syn = 0; +unsigned int nr_fin = 0; +unsigned int nr_hwtstamp = 0; + +/* Check the header received from the active side */ +static int __check_active_hdr_in(struct bpf_sock_ops *skops, bool check_syn) +{ + union { + struct tcphdr th; + struct ipv6hdr ip6; + struct tcp_exprm_opt exprm_opt; + struct tcp_opt reg_opt; + __u8 data[100]; /* IPv6 (40) + Max TCP hdr (60) */ + } hdr = {}; + __u64 load_flags = check_syn ? BPF_LOAD_HDR_OPT_TCP_SYN : 0; + struct tcphdr *pth; + int ret; + + hdr.reg_opt.kind = 0xB9; + + /* The option is 4 bytes long instead of 2 bytes */ + ret = bpf_load_hdr_opt(skops, &hdr.reg_opt, 2, load_flags); + if (ret != -ENOSPC) + RET_CG_ERR(ret); + + /* Test searching magic with regular kind */ + hdr.reg_opt.len = 4; + ret = bpf_load_hdr_opt(skops, &hdr.reg_opt, sizeof(hdr.reg_opt), + load_flags); + if (ret != -EINVAL) + RET_CG_ERR(ret); + + hdr.reg_opt.len = 0; + ret = bpf_load_hdr_opt(skops, &hdr.reg_opt, sizeof(hdr.reg_opt), + load_flags); + if (ret != 4 || hdr.reg_opt.len != 4 || hdr.reg_opt.kind != 0xB9 || + hdr.reg_opt.data[0] != 0xfa || hdr.reg_opt.data[1] != 0xce) + RET_CG_ERR(ret); + + /* Test searching experimental option with invalid kind length */ + hdr.exprm_opt.kind = TCPOPT_EXP; + hdr.exprm_opt.len = 5; + hdr.exprm_opt.magic = 0; + ret = bpf_load_hdr_opt(skops, &hdr.exprm_opt, sizeof(hdr.exprm_opt), + load_flags); + if (ret != -EINVAL) + RET_CG_ERR(ret); + + /* Test searching experimental option with 0 magic value */ + hdr.exprm_opt.len = 4; + ret = bpf_load_hdr_opt(skops, &hdr.exprm_opt, sizeof(hdr.exprm_opt), + load_flags); + if (ret != -ENOMSG) + RET_CG_ERR(ret); + + hdr.exprm_opt.magic = __bpf_htons(0xeB9F); + ret = bpf_load_hdr_opt(skops, &hdr.exprm_opt, sizeof(hdr.exprm_opt), + load_flags); + if (ret != 4 || hdr.exprm_opt.len != 4 || + hdr.exprm_opt.kind != TCPOPT_EXP || + hdr.exprm_opt.magic != __bpf_htons(0xeB9F)) + RET_CG_ERR(ret); + + if (!check_syn) + return CG_OK; + + /* Test loading from skops->syn_skb if sk_state == TCP_NEW_SYN_RECV + * + * Test loading from tp->saved_syn for other sk_state. + */ + ret = bpf_getsockopt(skops, SOL_TCP, TCP_BPF_SYN_IP, &hdr.ip6, + sizeof(hdr.ip6)); + if (ret != -ENOSPC) + RET_CG_ERR(ret); + + if (hdr.ip6.saddr.s6_addr16[7] != last_addr16_n || + hdr.ip6.daddr.s6_addr16[7] != last_addr16_n) + RET_CG_ERR(0); + + ret = bpf_getsockopt(skops, SOL_TCP, TCP_BPF_SYN_IP, &hdr, sizeof(hdr)); + if (ret < 0) + RET_CG_ERR(ret); + + pth = (struct tcphdr *)(&hdr.ip6 + 1); + if (pth->dest != passive_lport_n || pth->source != active_lport_n) + RET_CG_ERR(0); + + ret = bpf_getsockopt(skops, SOL_TCP, TCP_BPF_SYN, &hdr, sizeof(hdr)); + if (ret < 0) + RET_CG_ERR(ret); + + if (hdr.th.dest != passive_lport_n || hdr.th.source != active_lport_n) + RET_CG_ERR(0); + + return CG_OK; +} + +static int check_active_syn_in(struct bpf_sock_ops *skops) +{ + return __check_active_hdr_in(skops, true); +} + +static int check_active_hdr_in(struct bpf_sock_ops *skops) +{ + struct tcphdr *th; + + if (__check_active_hdr_in(skops, false) == CG_ERR) + return CG_ERR; + + th = skops->skb_data; + if (th + 1 > skops->skb_data_end) + RET_CG_ERR(0); + + if (tcp_hdrlen(th) < skops->skb_len) + nr_data++; + + if (th->fin) + nr_fin++; + + if (th->ack && !th->fin && tcp_hdrlen(th) == skops->skb_len) + nr_pure_ack++; + + if (skops->skb_hwtstamp) + nr_hwtstamp++; + + return CG_OK; +} + +static int active_opt_len(struct bpf_sock_ops *skops) +{ + int err; + + /* Reserve more than enough to allow the -EEXIST test in + * the write_active_opt(). + */ + err = bpf_reserve_hdr_opt(skops, 12, 0); + if (err) + RET_CG_ERR(err); + + return CG_OK; +} + +static int write_active_opt(struct bpf_sock_ops *skops) +{ + struct tcp_exprm_opt exprm_opt = {}; + struct tcp_opt win_scale_opt = {}; + struct tcp_opt reg_opt = {}; + struct tcphdr *th; + int err, ret; + + exprm_opt.kind = TCPOPT_EXP; + exprm_opt.len = 4; + exprm_opt.magic = __bpf_htons(0xeB9F); + + reg_opt.kind = 0xB9; + reg_opt.len = 4; + reg_opt.data[0] = 0xfa; + reg_opt.data[1] = 0xce; + + win_scale_opt.kind = TCPOPT_WINDOW; + + err = bpf_store_hdr_opt(skops, &exprm_opt, sizeof(exprm_opt), 0); + if (err) + RET_CG_ERR(err); + + /* Store the same exprm option */ + err = bpf_store_hdr_opt(skops, &exprm_opt, sizeof(exprm_opt), 0); + if (err != -EEXIST) + RET_CG_ERR(err); + + err = bpf_store_hdr_opt(skops, ®_opt, sizeof(reg_opt), 0); + if (err) + RET_CG_ERR(err); + err = bpf_store_hdr_opt(skops, ®_opt, sizeof(reg_opt), 0); + if (err != -EEXIST) + RET_CG_ERR(err); + + /* Check the option has been written and can be searched */ + ret = bpf_load_hdr_opt(skops, &exprm_opt, sizeof(exprm_opt), 0); + if (ret != 4 || exprm_opt.len != 4 || exprm_opt.kind != TCPOPT_EXP || + exprm_opt.magic != __bpf_htons(0xeB9F)) + RET_CG_ERR(ret); + + reg_opt.len = 0; + ret = bpf_load_hdr_opt(skops, ®_opt, sizeof(reg_opt), 0); + if (ret != 4 || reg_opt.len != 4 || reg_opt.kind != 0xB9 || + reg_opt.data[0] != 0xfa || reg_opt.data[1] != 0xce) + RET_CG_ERR(ret); + + th = skops->skb_data; + if (th + 1 > skops->skb_data_end) + RET_CG_ERR(0); + + if (th->syn) { + active_lport_h = skops->local_port; + active_lport_n = th->source; + + /* Search the win scale option written by kernel + * in the SYN packet. + */ + ret = bpf_load_hdr_opt(skops, &win_scale_opt, + sizeof(win_scale_opt), 0); + if (ret != 3 || win_scale_opt.len != 3 || + win_scale_opt.kind != TCPOPT_WINDOW) + RET_CG_ERR(ret); + + /* Write the win scale option that kernel + * has already written. + */ + err = bpf_store_hdr_opt(skops, &win_scale_opt, + sizeof(win_scale_opt), 0); + if (err != -EEXIST) + RET_CG_ERR(err); + } + + return CG_OK; +} + +static int handle_hdr_opt_len(struct bpf_sock_ops *skops) +{ + __u8 tcp_flags = skops_tcp_flags(skops); + + if ((tcp_flags & TCPHDR_SYNACK) == TCPHDR_SYNACK) + /* Check the SYN from bpf_sock_ops_kern->syn_skb */ + return check_active_syn_in(skops); + + /* Passive side should have cleared the write hdr cb by now */ + if (skops->local_port == passive_lport_h) + RET_CG_ERR(0); + + return active_opt_len(skops); +} + +static int handle_write_hdr_opt(struct bpf_sock_ops *skops) +{ + if (skops->local_port == passive_lport_h) + RET_CG_ERR(0); + + return write_active_opt(skops); +} + +static int handle_parse_hdr(struct bpf_sock_ops *skops) +{ + /* Passive side is not writing any non-standard/unknown + * option, so the active side should never be called. + */ + if (skops->local_port == active_lport_h) + RET_CG_ERR(0); + + return check_active_hdr_in(skops); +} + +static int handle_passive_estab(struct bpf_sock_ops *skops) +{ + int err; + + /* No more write hdr cb */ + bpf_sock_ops_cb_flags_set(skops, + skops->bpf_sock_ops_cb_flags & + ~BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG); + + /* Recheck the SYN but check the tp->saved_syn this time */ + err = check_active_syn_in(skops); + if (err == CG_ERR) + return err; + + nr_syn++; + + /* The ack has header option written by the active side also */ + return check_active_hdr_in(skops); +} + +SEC("sockops") +int misc_estab(struct bpf_sock_ops *skops) +{ + int true_val = 1; + + switch (skops->op) { + case BPF_SOCK_OPS_TCP_LISTEN_CB: + passive_lport_h = skops->local_port; + passive_lport_n = __bpf_htons(passive_lport_h); + bpf_setsockopt(skops, SOL_TCP, TCP_SAVE_SYN, + &true_val, sizeof(true_val)); + set_hdr_cb_flags(skops, 0); + break; + case BPF_SOCK_OPS_TCP_CONNECT_CB: + set_hdr_cb_flags(skops, 0); + break; + case BPF_SOCK_OPS_PARSE_HDR_OPT_CB: + return handle_parse_hdr(skops); + case BPF_SOCK_OPS_HDR_OPT_LEN_CB: + return handle_hdr_opt_len(skops); + case BPF_SOCK_OPS_WRITE_HDR_OPT_CB: + return handle_write_hdr_opt(skops); + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + return handle_passive_estab(skops); + } + + return CG_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_mmap.c b/tools/testing/selftests/bpf/progs/test_mmap.c new file mode 100644 index 0000000000..5a5cc19a15 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_mmap.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(map_flags, BPF_F_MMAPABLE | BPF_F_RDONLY_PROG); + __type(key, __u32); + __type(value, char); +} rdonly_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(map_flags, BPF_F_MMAPABLE); + __type(key, __u32); + __type(value, __u64); +} data_map SEC(".maps"); + +__u64 in_val = 0; +__u64 out_val = 0; + +SEC("raw_tracepoint/sys_enter") +int test_mmap(void *ctx) +{ + int zero = 0, one = 1, two = 2, far = 1500; + __u64 val, *p; + + out_val = in_val; + + /* data_map[2] = in_val; */ + bpf_map_update_elem(&data_map, &two, (const void *)&in_val, 0); + + /* data_map[1] = data_map[0] * 2; */ + p = bpf_map_lookup_elem(&data_map, &zero); + if (p) { + val = (*p) * 2; + bpf_map_update_elem(&data_map, &one, &val, 0); + } + + /* data_map[far] = in_val * 3; */ + val = in_val * 3; + bpf_map_update_elem(&data_map, &far, &val, 0); + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c new file mode 100644 index 0000000000..8a1b50f3a0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_module_attach.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "../bpf_testmod/bpf_testmod.h" + +__u32 raw_tp_read_sz = 0; + +SEC("raw_tp/bpf_testmod_test_read") +int BPF_PROG(handle_raw_tp, + struct task_struct *task, struct bpf_testmod_test_read_ctx *read_ctx) +{ + raw_tp_read_sz = BPF_CORE_READ(read_ctx, len); + return 0; +} + +__u32 raw_tp_bare_write_sz = 0; + +SEC("raw_tp/bpf_testmod_test_write_bare") +int BPF_PROG(handle_raw_tp_bare, + struct task_struct *task, struct bpf_testmod_test_write_ctx *write_ctx) +{ + raw_tp_bare_write_sz = BPF_CORE_READ(write_ctx, len); + return 0; +} + +int raw_tp_writable_bare_in_val = 0; +int raw_tp_writable_bare_early_ret = 0; +int raw_tp_writable_bare_out_val = 0; + +SEC("raw_tp.w/bpf_testmod_test_writable_bare") +int BPF_PROG(handle_raw_tp_writable_bare, + struct bpf_testmod_test_writable_ctx *writable) +{ + raw_tp_writable_bare_in_val = writable->val; + writable->early_ret = raw_tp_writable_bare_early_ret; + writable->val = raw_tp_writable_bare_out_val; + return 0; +} + +__u32 tp_btf_read_sz = 0; + +SEC("tp_btf/bpf_testmod_test_read") +int BPF_PROG(handle_tp_btf, + struct task_struct *task, struct bpf_testmod_test_read_ctx *read_ctx) +{ + tp_btf_read_sz = read_ctx->len; + return 0; +} + +__u32 fentry_read_sz = 0; + +SEC("fentry/bpf_testmod_test_read") +int BPF_PROG(handle_fentry, + struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) +{ + fentry_read_sz = len; + return 0; +} + +__u32 fentry_manual_read_sz = 0; + +SEC("fentry") +int BPF_PROG(handle_fentry_manual, + struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) +{ + fentry_manual_read_sz = len; + return 0; +} + +__u32 fexit_read_sz = 0; +int fexit_ret = 0; + +SEC("fexit/bpf_testmod_test_read") +int BPF_PROG(handle_fexit, + struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len, + int ret) +{ + fexit_read_sz = len; + fexit_ret = ret; + return 0; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret, int arg, struct file *ret) +{ + long buf = 0; + + bpf_probe_read_kernel(&buf, 8, ret); + bpf_probe_read_kernel(&buf, 8, (char *)ret + 256); + *(volatile long long *)ret; + *(volatile int *)&ret->f_mode; + return 0; +} + +__u32 fmod_ret_read_sz = 0; + +SEC("fmod_ret/bpf_testmod_test_read") +int BPF_PROG(handle_fmod_ret, + struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) +{ + fmod_ret_read_sz = len; + return 0; /* don't override the exit code */ +} + +SEC("kprobe.multi/bpf_testmod_test_read") +int BPF_PROG(kprobe_multi) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c b/tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c new file mode 100644 index 0000000000..03a475160a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +#define NF_ACCEPT 1 + +SEC("netfilter") +int nf_link_attach_test(struct bpf_nf_ctx *ctx) +{ + return NF_ACCEPT; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c b/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c new file mode 100644 index 0000000000..0763d49f9c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Carlos Neira cneirabustos@gmail.com */ + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> + +__u64 user_pid = 0; +__u64 user_tgid = 0; +__u64 dev = 0; +__u64 ino = 0; + +SEC("tracepoint/syscalls/sys_enter_nanosleep") +int handler(const void *ctx) +{ + struct bpf_pidns_info nsdata; + + if (bpf_get_ns_current_pid_tgid(dev, ino, &nsdata, sizeof(struct bpf_pidns_info))) + return 0; + + user_pid = nsdata.pid; + user_tgid = nsdata.tgid; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_obj_id.c b/tools/testing/selftests/bpf/progs/test_obj_id.c new file mode 100644 index 0000000000..2850ae788a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_obj_id.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2017 Facebook + */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} test_map_id SEC(".maps"); + +SEC("raw_tp/sys_enter") +int test_obj_id(void *ctx) +{ + __u32 key = 0; + __u64 *value; + + value = bpf_map_lookup_elem(&test_map_id, &key); + __sink(value); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c new file mode 100644 index 0000000000..abb7344b53 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_overhead.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include <stdbool.h> +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/ptrace.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct task_struct; + +SEC("kprobe/__set_task_comm") +int BPF_KPROBE(prog1, struct task_struct *tsk, const char *buf, bool exec) +{ + return !tsk; +} + +SEC("kretprobe/__set_task_comm") +int BPF_KRETPROBE(prog2, int ret) +{ + return ret; +} + +SEC("raw_tp/task_rename") +int prog3(struct bpf_raw_tracepoint_args *ctx) +{ + return !ctx->args[0]; +} + +SEC("fentry/__set_task_comm") +int BPF_PROG(prog4, struct task_struct *tsk, const char *buf, bool exec) +{ + return 0; +} + +SEC("fexit/__set_task_comm") +int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt.c b/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt.c new file mode 100644 index 0000000000..d9b2ba7ac3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* This parsing logic is taken from the open source library katran, a layer 4 + * load balancer. + * + * This code logic using dynptrs can be found in test_parse_tcp_hdr_opt_dynptr.c + * + * https://github.com/facebookincubator/katran/blob/main/katran/lib/bpf/pckt_parsing.h + */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <linux/tcp.h> +#include <stdbool.h> +#include <linux/ipv6.h> +#include <linux/if_ether.h> +#include "test_tcp_hdr_options.h" + +char _license[] SEC("license") = "GPL"; + +/* Kind number used for experiments */ +const __u32 tcp_hdr_opt_kind_tpr = 0xFD; +/* Length of the tcp header option */ +const __u32 tcp_hdr_opt_len_tpr = 6; +/* maximum number of header options to check to lookup server_id */ +const __u32 tcp_hdr_opt_max_opt_checks = 15; + +__u32 server_id; + +struct hdr_opt_state { + __u32 server_id; + __u8 byte_offset; + __u8 hdr_bytes_remaining; +}; + +static int parse_hdr_opt(const struct xdp_md *xdp, struct hdr_opt_state *state) +{ + const void *data = (void *)(long)xdp->data; + const void *data_end = (void *)(long)xdp->data_end; + __u8 *tcp_opt, kind, hdr_len; + + tcp_opt = (__u8 *)(data + state->byte_offset); + if (tcp_opt + 1 > data_end) + return -1; + + kind = tcp_opt[0]; + + if (kind == TCPOPT_EOL) + return -1; + + if (kind == TCPOPT_NOP) { + state->hdr_bytes_remaining--; + state->byte_offset++; + return 0; + } + + if (state->hdr_bytes_remaining < 2 || + tcp_opt + sizeof(__u8) + sizeof(__u8) > data_end) + return -1; + + hdr_len = tcp_opt[1]; + if (hdr_len > state->hdr_bytes_remaining) + return -1; + + if (kind == tcp_hdr_opt_kind_tpr) { + if (hdr_len != tcp_hdr_opt_len_tpr) + return -1; + + if (tcp_opt + tcp_hdr_opt_len_tpr > data_end) + return -1; + + state->server_id = *(__u32 *)&tcp_opt[2]; + return 1; + } + + state->hdr_bytes_remaining -= hdr_len; + state->byte_offset += hdr_len; + return 0; +} + +SEC("xdp") +int xdp_ingress_v6(struct xdp_md *xdp) +{ + const void *data = (void *)(long)xdp->data; + const void *data_end = (void *)(long)xdp->data_end; + struct hdr_opt_state opt_state = {}; + __u8 tcp_hdr_opt_len = 0; + struct tcphdr *tcp_hdr; + __u64 tcp_offset = 0; + int err; + + tcp_offset = sizeof(struct ethhdr) + sizeof(struct ipv6hdr); + tcp_hdr = (struct tcphdr *)(data + tcp_offset); + if (tcp_hdr + 1 > data_end) + return XDP_DROP; + + tcp_hdr_opt_len = (tcp_hdr->doff * 4) - sizeof(struct tcphdr); + if (tcp_hdr_opt_len < tcp_hdr_opt_len_tpr) + return XDP_DROP; + + opt_state.hdr_bytes_remaining = tcp_hdr_opt_len; + opt_state.byte_offset = sizeof(struct tcphdr) + tcp_offset; + + /* max number of bytes of options in tcp header is 40 bytes */ + for (int i = 0; i < tcp_hdr_opt_max_opt_checks; i++) { + err = parse_hdr_opt(xdp, &opt_state); + + if (err || !opt_state.hdr_bytes_remaining) + break; + } + + if (!opt_state.server_id) + return XDP_DROP; + + server_id = opt_state.server_id; + + return XDP_PASS; +} diff --git a/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt_dynptr.c b/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt_dynptr.c new file mode 100644 index 0000000000..dc6e43bc6a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt_dynptr.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* This logic is lifted from a real-world use case of packet parsing, used in + * the open source library katran, a layer 4 load balancer. + * + * This test demonstrates how to parse packet contents using dynptrs. The + * original code (parsing without dynptrs) can be found in test_parse_tcp_hdr_opt.c + */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <linux/tcp.h> +#include <stdbool.h> +#include <linux/ipv6.h> +#include <linux/if_ether.h> +#include "test_tcp_hdr_options.h" +#include "bpf_kfuncs.h" + +char _license[] SEC("license") = "GPL"; + +/* Kind number used for experiments */ +const __u32 tcp_hdr_opt_kind_tpr = 0xFD; +/* Length of the tcp header option */ +const __u32 tcp_hdr_opt_len_tpr = 6; +/* maximum number of header options to check to lookup server_id */ +const __u32 tcp_hdr_opt_max_opt_checks = 15; + +__u32 server_id; + +static int parse_hdr_opt(struct bpf_dynptr *ptr, __u32 *off, __u8 *hdr_bytes_remaining, + __u32 *server_id) +{ + __u8 kind, hdr_len; + __u8 buffer[sizeof(kind) + sizeof(hdr_len) + sizeof(*server_id)]; + __u8 *data; + + __builtin_memset(buffer, 0, sizeof(buffer)); + + data = bpf_dynptr_slice(ptr, *off, buffer, sizeof(buffer)); + if (!data) + return -1; + + kind = data[0]; + + if (kind == TCPOPT_EOL) + return -1; + + if (kind == TCPOPT_NOP) { + *off += 1; + *hdr_bytes_remaining -= 1; + return 0; + } + + if (*hdr_bytes_remaining < 2) + return -1; + + hdr_len = data[1]; + if (hdr_len > *hdr_bytes_remaining) + return -1; + + if (kind == tcp_hdr_opt_kind_tpr) { + if (hdr_len != tcp_hdr_opt_len_tpr) + return -1; + + __builtin_memcpy(server_id, (__u32 *)(data + 2), sizeof(*server_id)); + return 1; + } + + *off += hdr_len; + *hdr_bytes_remaining -= hdr_len; + return 0; +} + +SEC("xdp") +int xdp_ingress_v6(struct xdp_md *xdp) +{ + __u8 buffer[sizeof(struct tcphdr)] = {}; + __u8 hdr_bytes_remaining; + struct tcphdr *tcp_hdr; + __u8 tcp_hdr_opt_len; + int err = 0; + __u32 off; + + struct bpf_dynptr ptr; + + bpf_dynptr_from_xdp(xdp, 0, &ptr); + + off = sizeof(struct ethhdr) + sizeof(struct ipv6hdr); + + tcp_hdr = bpf_dynptr_slice(&ptr, off, buffer, sizeof(buffer)); + if (!tcp_hdr) + return XDP_DROP; + + tcp_hdr_opt_len = (tcp_hdr->doff * 4) - sizeof(struct tcphdr); + if (tcp_hdr_opt_len < tcp_hdr_opt_len_tpr) + return XDP_DROP; + + hdr_bytes_remaining = tcp_hdr_opt_len; + + off += sizeof(struct tcphdr); + + /* max number of bytes of options in tcp header is 40 bytes */ + for (int i = 0; i < tcp_hdr_opt_max_opt_checks; i++) { + err = parse_hdr_opt(&ptr, &off, &hdr_bytes_remaining, &server_id); + + if (err || !hdr_bytes_remaining) + break; + } + + if (!server_id) + return XDP_DROP; + + return XDP_PASS; +} diff --git a/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c b/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c new file mode 100644 index 0000000000..1249a94569 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} array_1 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); + __uint(map_flags, BPF_F_PRESERVE_ELEMS); +} array_2 SEC(".maps"); + +SEC("raw_tp/sched_switch") +int BPF_PROG(read_array_1) +{ + struct bpf_perf_event_value val; + + return bpf_perf_event_read_value(&array_1, 0, &val, sizeof(val)); +} + +SEC("raw_tp/task_rename") +int BPF_PROG(read_array_2) +{ + struct bpf_perf_event_value val; + + return bpf_perf_event_read_value(&array_2, 0, &val, sizeof(val)); +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_perf_branches.c b/tools/testing/selftests/bpf/progs/test_perf_branches.c new file mode 100644 index 0000000000..a1ccc831c8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_perf_branches.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <stddef.h> +#include <linux/ptrace.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +int valid = 0; +int required_size_out = 0; +int written_stack_out = 0; +int written_global_out = 0; + +struct { + __u64 _a; + __u64 _b; + __u64 _c; +} fpbe[30] = {0}; + +SEC("perf_event") +int perf_branches(void *ctx) +{ + __u64 entries[4 * 3] = {0}; + int required_size, written_stack, written_global; + + /* write to stack */ + written_stack = bpf_read_branch_records(ctx, entries, sizeof(entries), 0); + /* ignore spurious events */ + if (!written_stack) + return 1; + + /* get required size */ + required_size = bpf_read_branch_records(ctx, NULL, 0, + BPF_F_GET_BRANCH_RECORDS_SIZE); + + written_global = bpf_read_branch_records(ctx, fpbe, sizeof(fpbe), 0); + /* ignore spurious events */ + if (!written_global) + return 1; + + required_size_out = required_size; + written_stack_out = written_stack; + written_global_out = written_global; + valid = 1; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c new file mode 100644 index 0000000000..17d5b67744 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/ptrace.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, int); + __uint(max_entries, 1); +} my_pid_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __type(key, int); + __type(value, int); +} perf_buf_map SEC(".maps"); + +SEC("tp/raw_syscalls/sys_enter") +int handle_sys_enter(void *ctx) +{ + int zero = 0, *my_pid, cur_pid; + int cpu = bpf_get_smp_processor_id(); + + my_pid = bpf_map_lookup_elem(&my_pid_map, &zero); + if (!my_pid) + return 1; + + cur_pid = bpf_get_current_pid_tgid() >> 32; + if (cur_pid != *my_pid) + return 1; + + bpf_perf_event_output(ctx, &perf_buf_map, BPF_F_CURRENT_CPU, + &cpu, sizeof(cpu)); + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_perf_link.c b/tools/testing/selftests/bpf/progs/test_perf_link.c new file mode 100644 index 0000000000..c1db9fd98d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_perf_link.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +int run_cnt = 0; + +SEC("perf_event") +int handler(struct pt_regs *ctx) +{ + __sync_fetch_and_add(&run_cnt, 1); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_pinning.c b/tools/testing/selftests/bpf/progs/test_pinning.c new file mode 100644 index 0000000000..0facea6cbb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_pinning.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); + __uint(pinning, LIBBPF_PIN_BY_NAME); +} pinmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} nopinmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); + __uint(pinning, LIBBPF_PIN_NONE); +} nopinmap2 SEC(".maps"); + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_pinning_invalid.c b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c new file mode 100644 index 0000000000..2a56db1094 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); + __uint(pinning, 2); /* invalid */ +} nopinmap3 SEC(".maps"); + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c new file mode 100644 index 0000000000..bce7173152 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c @@ -0,0 +1,152 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2017 Facebook + */ +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/tcp.h> +#include <linux/pkt_cls.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include "bpf_misc.h" + +/* llvm will optimize both subprograms into exactly the same BPF assembly + * + * Disassembly of section .text: + * + * 0000000000000000 test_pkt_access_subprog1: + * ; return skb->len * 2; + * 0: 61 10 00 00 00 00 00 00 r0 = *(u32 *)(r1 + 0) + * 1: 64 00 00 00 01 00 00 00 w0 <<= 1 + * 2: 95 00 00 00 00 00 00 00 exit + * + * 0000000000000018 test_pkt_access_subprog2: + * ; return skb->len * val; + * 3: 61 10 00 00 00 00 00 00 r0 = *(u32 *)(r1 + 0) + * 4: 64 00 00 00 01 00 00 00 w0 <<= 1 + * 5: 95 00 00 00 00 00 00 00 exit + * + * Which makes it an interesting test for BTF-enabled verifier. + */ +static __attribute__ ((noinline)) +int test_pkt_access_subprog1(volatile struct __sk_buff *skb) +{ + return skb->len * 2; +} + +static __attribute__ ((noinline)) +int test_pkt_access_subprog2(int val, volatile struct __sk_buff *skb) +{ + return skb->len * val; +} + +#define MAX_STACK (512 - 2 * 32) + +__attribute__ ((noinline)) +int get_skb_len(struct __sk_buff *skb) +{ + volatile char buf[MAX_STACK] = {}; + + __sink(buf[MAX_STACK - 1]); + + return skb->len; +} + +__attribute__ ((noinline)) +int get_constant(long val) +{ + return val - 122; +} + +int get_skb_ifindex(int, struct __sk_buff *skb, int); + +__attribute__ ((noinline)) +int test_pkt_access_subprog3(int val, struct __sk_buff *skb) +{ + return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123)); +} + +__attribute__ ((noinline)) +int get_skb_ifindex(int val, struct __sk_buff *skb, int var) +{ + volatile char buf[MAX_STACK] = {}; + + __sink(buf[MAX_STACK - 1]); + + return skb->ifindex * val * var; +} + +__attribute__ ((noinline)) +int test_pkt_write_access_subprog(struct __sk_buff *skb, __u32 off) +{ + void *data = (void *)(long)skb->data; + void *data_end = (void *)(long)skb->data_end; + struct tcphdr *tcp = NULL; + + if (off > sizeof(struct ethhdr) + sizeof(struct ipv6hdr)) + return -1; + + tcp = data + off; + if (tcp + 1 > data_end) + return -1; + /* make modification to the packet data */ + tcp->check++; + return 0; +} + +SEC("tc") +int test_pkt_access(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ethhdr *eth = (struct ethhdr *)(data); + struct tcphdr *tcp = NULL; + __u8 proto = 255; + __u64 ihl_len; + + if (eth + 1 > data_end) + return TC_ACT_SHOT; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)(eth + 1); + + if (iph + 1 > data_end) + return TC_ACT_SHOT; + ihl_len = iph->ihl * 4; + proto = iph->protocol; + tcp = (struct tcphdr *)((void *)(iph) + ihl_len); + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ip6h = (struct ipv6hdr *)(eth + 1); + + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + ihl_len = sizeof(*ip6h); + proto = ip6h->nexthdr; + tcp = (struct tcphdr *)((void *)(ip6h) + ihl_len); + } + + if (test_pkt_access_subprog1(skb) != skb->len * 2) + return TC_ACT_SHOT; + if (test_pkt_access_subprog2(2, skb) != skb->len * 2) + return TC_ACT_SHOT; + if (test_pkt_access_subprog3(3, skb) != skb->len * 3 * skb->ifindex) + return TC_ACT_SHOT; + if (tcp) { + if (test_pkt_write_access_subprog(skb, (void *)tcp - data)) + return TC_ACT_SHOT; + if (((void *)(tcp) + 20) > data_end || proto != 6) + return TC_ACT_SHOT; + barrier(); /* to force ordering of checks */ + if (((void *)(tcp) + 18) > data_end) + return TC_ACT_SHOT; + if (tcp->urg_ptr == 123) + return TC_ACT_OK; + } + + return TC_ACT_UNSPEC; +} diff --git a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c new file mode 100644 index 0000000000..d1839366f3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2017 Facebook + */ +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/pkt_cls.h> +#include <bpf/bpf_helpers.h> + +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#define TEST_FIELD(TYPE, FIELD, MASK) \ + { \ + TYPE tmp = *(volatile TYPE *)&skb->FIELD; \ + if (tmp != ((*(volatile __u32 *)&skb->FIELD) & MASK)) \ + return TC_ACT_SHOT; \ + } +#else +#define TEST_FIELD_OFFSET(a, b) ((sizeof(a) - sizeof(b)) / sizeof(b)) +#define TEST_FIELD(TYPE, FIELD, MASK) \ + { \ + TYPE tmp = *((volatile TYPE *)&skb->FIELD + \ + TEST_FIELD_OFFSET(skb->FIELD, TYPE)); \ + if (tmp != ((*(volatile __u32 *)&skb->FIELD) & MASK)) \ + return TC_ACT_SHOT; \ + } +#endif + +SEC("tc") +int test_pkt_md_access(struct __sk_buff *skb) +{ + TEST_FIELD(__u8, len, 0xFF); + TEST_FIELD(__u16, len, 0xFFFF); + TEST_FIELD(__u32, len, 0xFFFFFFFF); + TEST_FIELD(__u16, protocol, 0xFFFF); + TEST_FIELD(__u32, protocol, 0xFFFFFFFF); + TEST_FIELD(__u8, hash, 0xFF); + TEST_FIELD(__u16, hash, 0xFFFF); + TEST_FIELD(__u32, hash, 0xFFFFFFFF); + + return TC_ACT_OK; +} diff --git a/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c b/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c new file mode 100644 index 0000000000..3ae398b75d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#include <sys/types.h> + +pid_t pid = 0; +long ret = 0; +void *user_ptr = 0; +char buf[256] = {}; + +SEC("tracepoint/syscalls/sys_enter_nanosleep") +int on_write(void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + ret = bpf_probe_read_user_str(buf, sizeof(buf), user_ptr); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c new file mode 100644 index 0000000000..a8e501af96 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_probe_user.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" + +static struct sockaddr_in old; + +static int handle_sys_connect_common(struct sockaddr_in *uservaddr) +{ + struct sockaddr_in new; + + bpf_probe_read_user(&old, sizeof(old), uservaddr); + __builtin_memset(&new, 0xab, sizeof(new)); + bpf_probe_write_user(uservaddr, &new, sizeof(new)); + + return 0; +} + +SEC("ksyscall/connect") +int BPF_KSYSCALL(handle_sys_connect, int fd, struct sockaddr_in *uservaddr, + int addrlen) +{ + return handle_sys_connect_common(uservaddr); +} + +#if defined(bpf_target_s390) +#ifndef SYS_CONNECT +#define SYS_CONNECT 3 +#endif + +SEC("ksyscall/socketcall") +int BPF_KSYSCALL(handle_sys_socketcall, int call, unsigned long *args) +{ + if (call == SYS_CONNECT) { + struct sockaddr_in *uservaddr; + + bpf_probe_read_user(&uservaddr, sizeof(uservaddr), &args[1]); + return handle_sys_connect_common(uservaddr); + } + + return 0; +} +#endif + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_prog_array_init.c b/tools/testing/selftests/bpf/progs/test_prog_array_init.c new file mode 100644 index 0000000000..2cd1383561 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_prog_array_init.c @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2021 Hengqi Chen */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +const volatile pid_t my_pid = 0; +int value = 0; + +SEC("raw_tp/sys_enter") +int tailcall_1(void *ctx) +{ + value = 42; + return 0; +} + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 2); + __uint(key_size, sizeof(__u32)); + __array(values, int (void *)); +} prog_array_init SEC(".maps") = { + .values = { + [1] = (void *)&tailcall_1, + }, +}; + +SEC("raw_tp/sys_enter") +int entry(void *ctx) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + + if (pid != my_pid) + return 0; + + bpf_tail_call(ctx, &prog_array_init, 1); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c new file mode 100644 index 0000000000..4bdd65b5aa --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */ + +#include "vmlinux.h" +#include <bpf/bpf_tracing.h> + +char tp_name[128]; + +SEC("lsm/bpf") +int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size) +{ + switch (cmd) { + case BPF_RAW_TRACEPOINT_OPEN: + bpf_probe_read_user_str(tp_name, sizeof(tp_name) - 1, + (void *)attr->raw_tracepoint.name); + break; + default: + break; + } + return 0; +} + +SEC("raw_tracepoint") +int BPF_PROG(raw_tp_run) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_queue_map.c b/tools/testing/selftests/bpf/progs/test_queue_map.c new file mode 100644 index 0000000000..87db1f9da3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_queue_map.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Politecnico di Torino +#define MAP_TYPE BPF_MAP_TYPE_QUEUE +#include "test_queue_stack_map.h" diff --git a/tools/testing/selftests/bpf/progs/test_queue_stack_map.h b/tools/testing/selftests/bpf/progs/test_queue_stack_map.h new file mode 100644 index 0000000000..648e8cab7a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_queue_stack_map.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +// Copyright (c) 2018 Politecnico di Torino +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/pkt_cls.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, MAP_TYPE); + __uint(max_entries, 32); + __uint(map_flags, 0); + __uint(key_size, 0); + __uint(value_size, sizeof(__u32)); +} map_in SEC(".maps"); + +struct { + __uint(type, MAP_TYPE); + __uint(max_entries, 32); + __uint(map_flags, 0); + __uint(key_size, 0); + __uint(value_size, sizeof(__u32)); +} map_out SEC(".maps"); + +SEC("tc") +int _test(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ethhdr *eth = (struct ethhdr *)(data); + __u32 value; + int err; + + if (eth + 1 > data_end) + return TC_ACT_SHOT; + + struct iphdr *iph = (struct iphdr *)(eth + 1); + + if (iph + 1 > data_end) + return TC_ACT_SHOT; + + err = bpf_map_pop_elem(&map_in, &value); + if (err) + return TC_ACT_SHOT; + + iph->daddr = value; + + err = bpf_map_push_elem(&map_out, &iph->saddr, 0); + if (err) + return TC_ACT_SHOT; + + return TC_ACT_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_raw_tp_test_run.c b/tools/testing/selftests/bpf/progs/test_raw_tp_test_run.c new file mode 100644 index 0000000000..4c63cc87b9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_raw_tp_test_run.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +__u32 count = 0; +__u32 on_cpu = 0xffffffff; + +SEC("raw_tp/task_rename") +int BPF_PROG(rename, struct task_struct *task, char *comm) +{ + + count++; + if ((__u64) task == 0x1234ULL && (__u64) comm == 0x5678ULL) { + on_cpu = bpf_get_smp_processor_id(); + return (long)task + (long)comm; + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c new file mode 100644 index 0000000000..fc8e8a34a3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c @@ -0,0 +1,83 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/ptrace.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +const struct { + unsigned a[4]; + /* + * if the struct's size is multiple of 16, compiler will put it into + * .rodata.cst16 section, which is not recognized by libbpf; work + * around this by ensuring we don't have 16-aligned struct + */ + char _y; +} rdonly_values = { .a = {2, 3, 4, 5} }; + +struct { + unsigned did_run; + unsigned iters; + unsigned sum; +} res = {}; + +SEC("raw_tracepoint/sys_enter:skip_loop") +int skip_loop(struct pt_regs *ctx) +{ + /* prevent compiler to optimize everything out */ + unsigned * volatile p = (void *)&rdonly_values.a; + unsigned iters = 0, sum = 0; + + /* we should never enter this loop */ + while (*p & 1) { + iters++; + sum += *p; + p++; + } + res.did_run = 1; + res.iters = iters; + res.sum = sum; + return 0; +} + +SEC("raw_tracepoint/sys_enter:part_loop") +int part_loop(struct pt_regs *ctx) +{ + /* prevent compiler to optimize everything out */ + unsigned * volatile p = (void *)&rdonly_values.a; + unsigned iters = 0, sum = 0; + + /* validate verifier can derive loop termination */ + while (*p < 5) { + iters++; + sum += *p; + p++; + } + res.did_run = 1; + res.iters = iters; + res.sum = sum; + return 0; +} + +SEC("raw_tracepoint/sys_enter:full_loop") +int full_loop(struct pt_regs *ctx) +{ + /* prevent compiler to optimize everything out */ + unsigned * volatile p = (void *)&rdonly_values.a; + int i = sizeof(rdonly_values.a) / sizeof(rdonly_values.a[0]); + unsigned iters = 0, sum = 0; + + /* validate verifier can allow full loop as well */ + while (i > 0 ) { + iters++; + sum += *p; + p++; + i--; + } + res.did_run = 1; + res.iters = iters; + res.sum = sum; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf.c b/tools/testing/selftests/bpf/progs/test_ringbuf.c new file mode 100644 index 0000000000..501cefa976 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ringbuf.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct sample { + int pid; + int seq; + long value; + char comm[16]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); +} ringbuf SEC(".maps"); + +/* inputs */ +int pid = 0; +long value = 0; +long flags = 0; + +/* outputs */ +long total = 0; +long discarded = 0; +long dropped = 0; + +long avail_data = 0; +long ring_size = 0; +long cons_pos = 0; +long prod_pos = 0; + +/* inner state */ +long seq = 0; + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int test_ringbuf(void *ctx) +{ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + struct sample *sample; + + if (cur_pid != pid) + return 0; + + sample = bpf_ringbuf_reserve(&ringbuf, sizeof(*sample), 0); + if (!sample) { + __sync_fetch_and_add(&dropped, 1); + return 0; + } + + sample->pid = pid; + bpf_get_current_comm(sample->comm, sizeof(sample->comm)); + sample->value = value; + + sample->seq = seq++; + __sync_fetch_and_add(&total, 1); + + if (sample->seq & 1) { + /* copy from reserved sample to a new one... */ + bpf_ringbuf_output(&ringbuf, sample, sizeof(*sample), flags); + /* ...and then discard reserved sample */ + bpf_ringbuf_discard(sample, flags); + __sync_fetch_and_add(&discarded, 1); + } else { + bpf_ringbuf_submit(sample, flags); + } + + avail_data = bpf_ringbuf_query(&ringbuf, BPF_RB_AVAIL_DATA); + ring_size = bpf_ringbuf_query(&ringbuf, BPF_RB_RING_SIZE); + cons_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_CONS_POS); + prod_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_PROD_POS); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_map_key.c b/tools/testing/selftests/bpf/progs/test_ringbuf_map_key.c new file mode 100644 index 0000000000..21bb7da90e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ringbuf_map_key.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct sample { + int pid; + int seq; + long value; + char comm[16]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); +} ringbuf SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1000); + __type(key, struct sample); + __type(value, int); +} hash_map SEC(".maps"); + +/* inputs */ +int pid = 0; + +/* inner state */ +long seq = 0; + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int test_ringbuf_mem_map_key(void *ctx) +{ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + struct sample *sample, sample_copy; + int *lookup_val; + + if (cur_pid != pid) + return 0; + + sample = bpf_ringbuf_reserve(&ringbuf, sizeof(*sample), 0); + if (!sample) + return 0; + + sample->pid = pid; + bpf_get_current_comm(sample->comm, sizeof(sample->comm)); + sample->seq = ++seq; + sample->value = 42; + + /* test using 'sample' (PTR_TO_MEM | MEM_ALLOC) as map key arg + */ + lookup_val = (int *)bpf_map_lookup_elem(&hash_map, sample); + __sink(lookup_val); + + /* workaround - memcpy is necessary so that verifier doesn't + * complain with: + * verifier internal error: more than one arg with ref_obj_id R3 + * when trying to do bpf_map_update_elem(&hash_map, sample, &sample->seq, BPF_ANY); + * + * Since bpf_map_lookup_elem above uses 'sample' as key, test using + * sample field as value below + */ + __builtin_memcpy(&sample_copy, sample, sizeof(struct sample)); + bpf_map_update_elem(&hash_map, &sample_copy, &sample->seq, BPF_ANY); + + bpf_ringbuf_submit(sample, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c b/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c new file mode 100644 index 0000000000..9626baa677 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct sample { + int pid; + int seq; + long value; + char comm[16]; +}; + +struct ringbuf_map { + __uint(type, BPF_MAP_TYPE_RINGBUF); + /* libbpf will adjust to valid page size */ + __uint(max_entries, 1000); +} ringbuf1 SEC(".maps"), + ringbuf2 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 4); + __type(key, int); + __array(values, struct ringbuf_map); +} ringbuf_arr SEC(".maps") = { + .values = { + [0] = &ringbuf1, + [2] = &ringbuf2, + }, +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 1); + __type(key, int); + __array(values, struct ringbuf_map); +} ringbuf_hash SEC(".maps") = { + .values = { + [0] = &ringbuf1, + }, +}; + +/* inputs */ +int pid = 0; +int target_ring = 0; +long value = 0; + +/* outputs */ +long total = 0; +long dropped = 0; +long skipped = 0; + +SEC("tp/syscalls/sys_enter_getpgid") +int test_ringbuf(void *ctx) +{ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + struct sample *sample; + void *rb; + + if (cur_pid != pid) + return 0; + + rb = bpf_map_lookup_elem(&ringbuf_arr, &target_ring); + if (!rb) { + skipped += 1; + return 1; + } + + sample = bpf_ringbuf_reserve(rb, sizeof(*sample), 0); + if (!sample) { + dropped += 1; + return 1; + } + + sample->pid = pid; + bpf_get_current_comm(sample->comm, sizeof(sample->comm)); + sample->value = value; + + sample->seq = total; + total += 1; + + bpf_ringbuf_submit(sample, 0); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c new file mode 100644 index 0000000000..a7278f0643 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c @@ -0,0 +1,260 @@ +#include <stddef.h> +#include <inttypes.h> +#include <errno.h> +#include <linux/seg6_local.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +/* Packet parsing state machine helpers. */ +#define cursor_advance(_cursor, _len) \ + ({ void *_tmp = _cursor; _cursor += _len; _tmp; }) + +#define SR6_FLAG_ALERT (1 << 4) + +#define BPF_PACKET_HEADER __attribute__((packed)) + +struct ip6_t { + unsigned int ver:4; + unsigned int priority:8; + unsigned int flow_label:20; + unsigned short payload_len; + unsigned char next_header; + unsigned char hop_limit; + unsigned long long src_hi; + unsigned long long src_lo; + unsigned long long dst_hi; + unsigned long long dst_lo; +} BPF_PACKET_HEADER; + +struct ip6_addr_t { + unsigned long long hi; + unsigned long long lo; +} BPF_PACKET_HEADER; + +struct ip6_srh_t { + unsigned char nexthdr; + unsigned char hdrlen; + unsigned char type; + unsigned char segments_left; + unsigned char first_segment; + unsigned char flags; + unsigned short tag; + + struct ip6_addr_t segments[0]; +} BPF_PACKET_HEADER; + +struct sr6_tlv_t { + unsigned char type; + unsigned char len; + unsigned char value[0]; +} BPF_PACKET_HEADER; + +static __always_inline struct ip6_srh_t *get_srh(struct __sk_buff *skb) +{ + void *cursor, *data_end; + struct ip6_srh_t *srh; + struct ip6_t *ip; + uint8_t *ipver; + + data_end = (void *)(long)skb->data_end; + cursor = (void *)(long)skb->data; + ipver = (uint8_t *)cursor; + + if ((void *)ipver + sizeof(*ipver) > data_end) + return NULL; + + if ((*ipver >> 4) != 6) + return NULL; + + ip = cursor_advance(cursor, sizeof(*ip)); + if ((void *)ip + sizeof(*ip) > data_end) + return NULL; + + if (ip->next_header != 43) + return NULL; + + srh = cursor_advance(cursor, sizeof(*srh)); + if ((void *)srh + sizeof(*srh) > data_end) + return NULL; + + if (srh->type != 4) + return NULL; + + return srh; +} + +static __always_inline int update_tlv_pad(struct __sk_buff *skb, + uint32_t new_pad, uint32_t old_pad, + uint32_t pad_off) +{ + int err; + + if (new_pad != old_pad) { + err = bpf_lwt_seg6_adjust_srh(skb, pad_off, + (int) new_pad - (int) old_pad); + if (err) + return err; + } + + if (new_pad > 0) { + char pad_tlv_buf[16] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0}; + struct sr6_tlv_t *pad_tlv = (struct sr6_tlv_t *) pad_tlv_buf; + + pad_tlv->type = SR6_TLV_PADDING; + pad_tlv->len = new_pad - 2; + + err = bpf_lwt_seg6_store_bytes(skb, pad_off, + (void *)pad_tlv_buf, new_pad); + if (err) + return err; + } + + return 0; +} + +static __always_inline int is_valid_tlv_boundary(struct __sk_buff *skb, + struct ip6_srh_t *srh, + uint32_t *tlv_off, + uint32_t *pad_size, + uint32_t *pad_off) +{ + uint32_t srh_off, cur_off; + int offset_valid = 0; + int err; + + srh_off = (char *)srh - (char *)(long)skb->data; + // cur_off = end of segments, start of possible TLVs + cur_off = srh_off + sizeof(*srh) + + sizeof(struct ip6_addr_t) * (srh->first_segment + 1); + + *pad_off = 0; + + // we can only go as far as ~10 TLVs due to the BPF max stack size + // workaround: define induction variable "i" as "long" instead + // of "int" to prevent alu32 sub-register spilling. + #pragma clang loop unroll(disable) + for (long i = 0; i < 100; i++) { + struct sr6_tlv_t tlv; + + if (cur_off == *tlv_off) + offset_valid = 1; + + if (cur_off >= srh_off + ((srh->hdrlen + 1) << 3)) + break; + + err = bpf_skb_load_bytes(skb, cur_off, &tlv, sizeof(tlv)); + if (err) + return err; + + if (tlv.type == SR6_TLV_PADDING) { + *pad_size = tlv.len + sizeof(tlv); + *pad_off = cur_off; + + if (*tlv_off == srh_off) { + *tlv_off = cur_off; + offset_valid = 1; + } + break; + + } else if (tlv.type == SR6_TLV_HMAC) { + break; + } + + cur_off += sizeof(tlv) + tlv.len; + } // we reached the padding or HMAC TLVs, or the end of the SRH + + if (*pad_off == 0) + *pad_off = cur_off; + + if (*tlv_off == -1) + *tlv_off = cur_off; + else if (!offset_valid) + return -EINVAL; + + return 0; +} + +static __always_inline int add_tlv(struct __sk_buff *skb, + struct ip6_srh_t *srh, uint32_t tlv_off, + struct sr6_tlv_t *itlv, uint8_t tlv_size) +{ + uint32_t srh_off = (char *)srh - (char *)(long)skb->data; + uint8_t len_remaining, new_pad; + uint32_t pad_off = 0; + uint32_t pad_size = 0; + uint32_t partial_srh_len; + int err; + + if (tlv_off != -1) + tlv_off += srh_off; + + if (itlv->type == SR6_TLV_PADDING || itlv->type == SR6_TLV_HMAC) + return -EINVAL; + + err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off); + if (err) + return err; + + err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, sizeof(*itlv) + itlv->len); + if (err) + return err; + + err = bpf_lwt_seg6_store_bytes(skb, tlv_off, (void *)itlv, tlv_size); + if (err) + return err; + + // the following can't be moved inside update_tlv_pad because the + // bpf verifier has some issues with it + pad_off += sizeof(*itlv) + itlv->len; + partial_srh_len = pad_off - srh_off; + len_remaining = partial_srh_len % 8; + new_pad = 8 - len_remaining; + + if (new_pad == 1) // cannot pad for 1 byte only + new_pad = 9; + else if (new_pad == 8) + new_pad = 0; + + return update_tlv_pad(skb, new_pad, pad_size, pad_off); +} + +// Add an Egress TLV fc00::4, add the flag A, +// and apply End.X action to fc42::1 +SEC("lwt_seg6local") +int __add_egr_x(struct __sk_buff *skb) +{ + unsigned long long hi = 0xfc42000000000000; + unsigned long long lo = 0x1; + struct ip6_srh_t *srh = get_srh(skb); + uint8_t new_flags = SR6_FLAG_ALERT; + struct ip6_addr_t addr; + int err, offset; + + if (srh == NULL) + return BPF_DROP; + + uint8_t tlv[20] = {2, 18, 0, 0, 0xfd, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x4}; + + err = add_tlv(skb, srh, (srh->hdrlen+1) << 3, + (struct sr6_tlv_t *)&tlv, 20); + if (err) + return BPF_DROP; + + offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags); + err = bpf_lwt_seg6_store_bytes(skb, offset, + (void *)&new_flags, sizeof(new_flags)); + if (err) + return BPF_DROP; + + addr.lo = bpf_cpu_to_be64(lo); + addr.hi = bpf_cpu_to_be64(hi); + err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_X, + (void *)&addr, sizeof(addr)); + if (err) + return BPF_DROP; + return BPF_REDIRECT; +} +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c new file mode 100644 index 0000000000..5eb25c6ad7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c @@ -0,0 +1,184 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 Facebook */ + +#include <stdlib.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/bpf.h> +#include <linux/types.h> +#include <linux/if_ether.h> + +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> +#include "test_select_reuseport_common.h" + +#ifndef offsetof +#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) +#endif + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} outer_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, NR_RESULTS); + __type(key, __u32); + __type(value, __u32); +} result_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, int); +} tmp_index_ovr_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} linum_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct data_check); +} data_check_map SEC(".maps"); + +#define GOTO_DONE(_result) ({ \ + result = (_result); \ + linum = __LINE__; \ + goto done; \ +}) + +SEC("sk_reuseport") +int _select_by_skb_data(struct sk_reuseport_md *reuse_md) +{ + __u32 linum, index = 0, flags = 0, index_zero = 0; + __u32 *result_cnt; + struct data_check data_check = {}; + struct cmd *cmd, cmd_copy; + void *data, *data_end; + void *reuseport_array; + enum result result; + int *index_ovr; + int err; + + data = reuse_md->data; + data_end = reuse_md->data_end; + data_check.len = reuse_md->len; + data_check.eth_protocol = reuse_md->eth_protocol; + data_check.ip_protocol = reuse_md->ip_protocol; + data_check.hash = reuse_md->hash; + data_check.bind_inany = reuse_md->bind_inany; + if (data_check.eth_protocol == bpf_htons(ETH_P_IP)) { + if (bpf_skb_load_bytes_relative(reuse_md, + offsetof(struct iphdr, saddr), + data_check.skb_addrs, 8, + BPF_HDR_START_NET)) + GOTO_DONE(DROP_MISC); + } else { + if (bpf_skb_load_bytes_relative(reuse_md, + offsetof(struct ipv6hdr, saddr), + data_check.skb_addrs, 32, + BPF_HDR_START_NET)) + GOTO_DONE(DROP_MISC); + } + + /* + * The ip_protocol could be a compile time decision + * if the bpf_prog.o is dedicated to either TCP or + * UDP. + * + * Otherwise, reuse_md->ip_protocol or + * the protocol field in the iphdr can be used. + */ + if (data_check.ip_protocol == IPPROTO_TCP) { + struct tcphdr *th = data; + + if (th + 1 > data_end) + GOTO_DONE(DROP_MISC); + + data_check.skb_ports[0] = th->source; + data_check.skb_ports[1] = th->dest; + + if (th->fin) + /* The connection is being torn down at the end of a + * test. It can't contain a cmd, so return early. + */ + return SK_PASS; + + if ((th->doff << 2) + sizeof(*cmd) > data_check.len) + GOTO_DONE(DROP_ERR_SKB_DATA); + if (bpf_skb_load_bytes(reuse_md, th->doff << 2, &cmd_copy, + sizeof(cmd_copy))) + GOTO_DONE(DROP_MISC); + cmd = &cmd_copy; + } else if (data_check.ip_protocol == IPPROTO_UDP) { + struct udphdr *uh = data; + + if (uh + 1 > data_end) + GOTO_DONE(DROP_MISC); + + data_check.skb_ports[0] = uh->source; + data_check.skb_ports[1] = uh->dest; + + if (sizeof(struct udphdr) + sizeof(*cmd) > data_check.len) + GOTO_DONE(DROP_ERR_SKB_DATA); + if (data + sizeof(struct udphdr) + sizeof(*cmd) > data_end) { + if (bpf_skb_load_bytes(reuse_md, sizeof(struct udphdr), + &cmd_copy, sizeof(cmd_copy))) + GOTO_DONE(DROP_MISC); + cmd = &cmd_copy; + } else { + cmd = data + sizeof(struct udphdr); + } + } else { + GOTO_DONE(DROP_MISC); + } + + reuseport_array = bpf_map_lookup_elem(&outer_map, &index_zero); + if (!reuseport_array) + GOTO_DONE(DROP_ERR_INNER_MAP); + + index = cmd->reuseport_index; + index_ovr = bpf_map_lookup_elem(&tmp_index_ovr_map, &index_zero); + if (!index_ovr) + GOTO_DONE(DROP_MISC); + + if (*index_ovr != -1) { + index = *index_ovr; + *index_ovr = -1; + } + err = bpf_sk_select_reuseport(reuse_md, reuseport_array, &index, + flags); + if (!err) + GOTO_DONE(PASS); + + if (cmd->pass_on_failure) + GOTO_DONE(PASS_ERR_SK_SELECT_REUSEPORT); + else + GOTO_DONE(DROP_ERR_SK_SELECT_REUSEPORT); + +done: + result_cnt = bpf_map_lookup_elem(&result_map, &result); + if (!result_cnt) + return SK_DROP; + + bpf_map_update_elem(&linum_map, &index_zero, &linum, BPF_ANY); + bpf_map_update_elem(&data_check_map, &index_zero, &data_check, BPF_ANY); + + (*result_cnt)++; + return result < PASS ? SK_DROP : SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c new file mode 100644 index 0000000000..92354cd720 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include <linux/version.h> +#include <bpf/bpf_helpers.h> + +__u32 sig = 0, pid = 0, status = 0, signal_thread = 0; + +static __always_inline int bpf_send_signal_test(void *ctx) +{ + int ret; + + if (status != 0 || pid == 0) + return 0; + + if ((bpf_get_current_pid_tgid() >> 32) == pid) { + if (signal_thread) + ret = bpf_send_signal_thread(sig); + else + ret = bpf_send_signal(sig); + if (ret == 0) + status = 1; + } + + return 0; +} + +SEC("tracepoint/syscalls/sys_enter_nanosleep") +int send_signal_tp(void *ctx) +{ + return bpf_send_signal_test(ctx); +} + +SEC("tracepoint/sched/sched_switch") +int send_signal_tp_sched(void *ctx) +{ + return bpf_send_signal_test(ctx); +} + +SEC("perf_event") +int send_signal_perf(void *ctx) +{ + return bpf_send_signal_test(ctx); +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c new file mode 100644 index 0000000000..3079244c7f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c @@ -0,0 +1,194 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Cloudflare Ltd. +// Copyright (c) 2020 Isovalent, Inc. + +#include <stddef.h> +#include <stdbool.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/pkt_cls.h> +#include <linux/tcp.h> +#include <sys/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include "bpf_misc.h" + +#if defined(IPROUTE2_HAVE_LIBBPF) +/* Use a new-style map definition. */ +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __type(key, int); + __type(value, __u64); + __uint(pinning, LIBBPF_PIN_BY_NAME); + __uint(max_entries, 1); +} server_map SEC(".maps"); +#else +/* Pin map under /sys/fs/bpf/tc/globals/<map name> */ +#define PIN_GLOBAL_NS 2 + +/* Must match struct bpf_elf_map layout from iproute2 */ +struct { + __u32 type; + __u32 size_key; + __u32 size_value; + __u32 max_elem; + __u32 flags; + __u32 id; + __u32 pinning; +} server_map SEC("maps") = { + .type = BPF_MAP_TYPE_SOCKMAP, + .size_key = sizeof(int), + .size_value = sizeof(__u64), + .max_elem = 1, + .pinning = PIN_GLOBAL_NS, +}; +#endif + +char _license[] SEC("license") = "GPL"; + +/* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */ +static inline struct bpf_sock_tuple * +get_tuple(struct __sk_buff *skb, bool *ipv4, bool *tcp) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct bpf_sock_tuple *result; + struct ethhdr *eth; + __u8 proto = 0; + __u64 ihl_len; + + eth = (struct ethhdr *)(data); + if (eth + 1 > data_end) + return NULL; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)(data + sizeof(*eth)); + + if (iph + 1 > data_end) + return NULL; + if (iph->ihl != 5) + /* Options are not supported */ + return NULL; + ihl_len = iph->ihl * 4; + proto = iph->protocol; + *ipv4 = true; + result = (struct bpf_sock_tuple *)&iph->saddr; + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ip6h = (struct ipv6hdr *)(data + sizeof(*eth)); + + if (ip6h + 1 > data_end) + return NULL; + ihl_len = sizeof(*ip6h); + proto = ip6h->nexthdr; + *ipv4 = false; + result = (struct bpf_sock_tuple *)&ip6h->saddr; + } else { + return (struct bpf_sock_tuple *)data; + } + + if (proto != IPPROTO_TCP && proto != IPPROTO_UDP) + return NULL; + + *tcp = (proto == IPPROTO_TCP); + __sink(ihl_len); + return result; +} + +static inline int +handle_udp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4) +{ + struct bpf_sock *sk; + const int zero = 0; + size_t tuple_len; + __be16 dport; + int ret; + + tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6); + if ((void *)tuple + tuple_len > (void *)(long)skb->data_end) + return TC_ACT_SHOT; + + sk = bpf_sk_lookup_udp(skb, tuple, tuple_len, BPF_F_CURRENT_NETNS, 0); + if (sk) + goto assign; + + dport = ipv4 ? tuple->ipv4.dport : tuple->ipv6.dport; + if (dport != bpf_htons(4321)) + return TC_ACT_OK; + + sk = bpf_map_lookup_elem(&server_map, &zero); + if (!sk) + return TC_ACT_SHOT; + +assign: + ret = bpf_sk_assign(skb, sk, 0); + bpf_sk_release(sk); + return ret; +} + +static inline int +handle_tcp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4) +{ + struct bpf_sock *sk; + const int zero = 0; + size_t tuple_len; + __be16 dport; + int ret; + + tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6); + if ((void *)tuple + tuple_len > (void *)(long)skb->data_end) + return TC_ACT_SHOT; + + sk = bpf_skc_lookup_tcp(skb, tuple, tuple_len, BPF_F_CURRENT_NETNS, 0); + if (sk) { + if (sk->state != BPF_TCP_LISTEN) + goto assign; + bpf_sk_release(sk); + } + + dport = ipv4 ? tuple->ipv4.dport : tuple->ipv6.dport; + if (dport != bpf_htons(4321)) + return TC_ACT_OK; + + sk = bpf_map_lookup_elem(&server_map, &zero); + if (!sk) + return TC_ACT_SHOT; + + if (sk->state != BPF_TCP_LISTEN) { + bpf_sk_release(sk); + return TC_ACT_SHOT; + } + +assign: + ret = bpf_sk_assign(skb, sk, 0); + bpf_sk_release(sk); + return ret; +} + +SEC("tc") +int bpf_sk_assign_test(struct __sk_buff *skb) +{ + struct bpf_sock_tuple *tuple; + bool ipv4 = false; + bool tcp = false; + int ret = 0; + + tuple = get_tuple(skb, &ipv4, &tcp); + if (!tuple) + return TC_ACT_SHOT; + + /* Note that the verifier socket return type for bpf_skc_lookup_tcp() + * differs from bpf_sk_lookup_udp(), so even though the C-level type is + * the same here, if we try to share the implementations they will + * fail to verify because we're crossing pointer types. + */ + if (tcp) + ret = handle_tcp(skb, tuple, ipv4); + else + ret = handle_udp(skb, tuple, ipv4); + + return ret == 0 ? TC_ACT_OK : TC_ACT_SHOT; +} diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c b/tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c new file mode 100644 index 0000000000..dcf46adfda --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 +#define IPROUTE2_HAVE_LIBBPF +#include "test_sk_assign.c" diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c new file mode 100644 index 0000000000..71f844b9b9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c @@ -0,0 +1,660 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// Copyright (c) 2020 Cloudflare + +#include <errno.h> +#include <stdbool.h> +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <sys/socket.h> + +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +#define IP4(a, b, c, d) \ + bpf_htonl((((__u32)(a) & 0xffU) << 24) | \ + (((__u32)(b) & 0xffU) << 16) | \ + (((__u32)(c) & 0xffU) << 8) | \ + (((__u32)(d) & 0xffU) << 0)) +#define IP6(aaaa, bbbb, cccc, dddd) \ + { bpf_htonl(aaaa), bpf_htonl(bbbb), bpf_htonl(cccc), bpf_htonl(dddd) } + +/* Macros for least-significant byte and word accesses. */ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#define LSE_INDEX(index, size) (index) +#else +#define LSE_INDEX(index, size) ((size) - (index) - 1) +#endif +#define LSB(value, index) \ + (((__u8 *)&(value))[LSE_INDEX((index), sizeof(value))]) +#define LSW(value, index) \ + (((__u16 *)&(value))[LSE_INDEX((index), sizeof(value) / 2)]) + +#define MAX_SOCKS 32 + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, MAX_SOCKS); + __type(key, __u32); + __type(value, __u64); +} redir_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 2); + __type(key, int); + __type(value, int); +} run_map SEC(".maps"); + +enum { + PROG1 = 0, + PROG2, +}; + +enum { + SERVER_A = 0, + SERVER_B, +}; + +/* Addressable key/value constants for convenience */ +static const int KEY_PROG1 = PROG1; +static const int KEY_PROG2 = PROG2; +static const int PROG_DONE = 1; + +static const __u32 KEY_SERVER_A = SERVER_A; +static const __u32 KEY_SERVER_B = SERVER_B; + +static const __u16 SRC_PORT = bpf_htons(8008); +static const __u32 SRC_IP4 = IP4(127, 0, 0, 2); +static const __u32 SRC_IP6[] = IP6(0xfd000000, 0x0, 0x0, 0x00000002); + +static const __u16 DST_PORT = 7007; /* Host byte order */ +static const __u32 DST_IP4 = IP4(127, 0, 0, 1); +static const __u32 DST_IP6[] = IP6(0xfd000000, 0x0, 0x0, 0x00000001); + +SEC("sk_lookup") +int lookup_pass(struct bpf_sk_lookup *ctx) +{ + return SK_PASS; +} + +SEC("sk_lookup") +int lookup_drop(struct bpf_sk_lookup *ctx) +{ + return SK_DROP; +} + +SEC("sk_lookup") +int check_ifindex(struct bpf_sk_lookup *ctx) +{ + if (ctx->ingress_ifindex == 1) + return SK_DROP; + return SK_PASS; +} + +SEC("sk_reuseport") +int reuseport_pass(struct sk_reuseport_md *ctx) +{ + return SK_PASS; +} + +SEC("sk_reuseport") +int reuseport_drop(struct sk_reuseport_md *ctx) +{ + return SK_DROP; +} + +/* Redirect packets destined for port DST_PORT to socket at redir_map[0]. */ +SEC("sk_lookup") +int redir_port(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + if (ctx->local_port != DST_PORT) + return SK_PASS; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_PASS; + + err = bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + return err ? SK_DROP : SK_PASS; +} + +/* Redirect packets destined for DST_IP4 address to socket at redir_map[0]. */ +SEC("sk_lookup") +int redir_ip4(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + if (ctx->family != AF_INET) + return SK_PASS; + if (ctx->local_port != DST_PORT) + return SK_PASS; + if (ctx->local_ip4 != DST_IP4) + return SK_PASS; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_PASS; + + err = bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + return err ? SK_DROP : SK_PASS; +} + +/* Redirect packets destined for DST_IP6 address to socket at redir_map[0]. */ +SEC("sk_lookup") +int redir_ip6(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + if (ctx->family != AF_INET6) + return SK_PASS; + if (ctx->local_port != DST_PORT) + return SK_PASS; + if (ctx->local_ip6[0] != DST_IP6[0] || + ctx->local_ip6[1] != DST_IP6[1] || + ctx->local_ip6[2] != DST_IP6[2] || + ctx->local_ip6[3] != DST_IP6[3]) + return SK_PASS; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_PASS; + + err = bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + return err ? SK_DROP : SK_PASS; +} + +SEC("sk_lookup") +int select_sock_a(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_PASS; + + err = bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + return err ? SK_DROP : SK_PASS; +} + +SEC("sk_lookup") +int select_sock_a_no_reuseport(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_DROP; + + err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_NO_REUSEPORT); + bpf_sk_release(sk); + return err ? SK_DROP : SK_PASS; +} + +SEC("sk_reuseport") +int select_sock_b(struct sk_reuseport_md *ctx) +{ + __u32 key = KEY_SERVER_B; + int err; + + err = bpf_sk_select_reuseport(ctx, &redir_map, &key, 0); + return err ? SK_DROP : SK_PASS; +} + +/* Check that bpf_sk_assign() returns -EEXIST if socket already selected. */ +SEC("sk_lookup") +int sk_assign_eexist(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err, ret; + + ret = SK_DROP; + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B); + if (!sk) + goto out; + err = bpf_sk_assign(ctx, sk, 0); + if (err) + goto out; + bpf_sk_release(sk); + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + goto out; + err = bpf_sk_assign(ctx, sk, 0); + if (err != -EEXIST) { + bpf_printk("sk_assign returned %d, expected %d\n", + err, -EEXIST); + goto out; + } + + ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */ +out: + if (sk) + bpf_sk_release(sk); + return ret; +} + +/* Check that bpf_sk_assign(BPF_SK_LOOKUP_F_REPLACE) can override selection. */ +SEC("sk_lookup") +int sk_assign_replace_flag(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err, ret; + + ret = SK_DROP; + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + goto out; + err = bpf_sk_assign(ctx, sk, 0); + if (err) + goto out; + bpf_sk_release(sk); + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B); + if (!sk) + goto out; + err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_REPLACE); + if (err) { + bpf_printk("sk_assign returned %d, expected 0\n", err); + goto out; + } + + ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */ +out: + if (sk) + bpf_sk_release(sk); + return ret; +} + +/* Check that bpf_sk_assign(sk=NULL) is accepted. */ +SEC("sk_lookup") +int sk_assign_null(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk = NULL; + int err, ret; + + ret = SK_DROP; + + err = bpf_sk_assign(ctx, NULL, 0); + if (err) { + bpf_printk("sk_assign returned %d, expected 0\n", err); + goto out; + } + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B); + if (!sk) + goto out; + err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_REPLACE); + if (err) { + bpf_printk("sk_assign returned %d, expected 0\n", err); + goto out; + } + + if (ctx->sk != sk) + goto out; + err = bpf_sk_assign(ctx, NULL, 0); + if (err != -EEXIST) + goto out; + err = bpf_sk_assign(ctx, NULL, BPF_SK_LOOKUP_F_REPLACE); + if (err) + goto out; + err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_REPLACE); + if (err) + goto out; + + ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */ +out: + if (sk) + bpf_sk_release(sk); + return ret; +} + +/* Check that selected sk is accessible through context. */ +SEC("sk_lookup") +int access_ctx_sk(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk1 = NULL, *sk2 = NULL; + int err, ret; + + ret = SK_DROP; + + /* Try accessing unassigned (NULL) ctx->sk field */ + if (ctx->sk && ctx->sk->family != AF_INET) + goto out; + + /* Assign a value to ctx->sk */ + sk1 = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk1) + goto out; + err = bpf_sk_assign(ctx, sk1, 0); + if (err) + goto out; + if (ctx->sk != sk1) + goto out; + + /* Access ctx->sk fields */ + if (ctx->sk->family != AF_INET || + ctx->sk->type != SOCK_STREAM || + ctx->sk->state != BPF_TCP_LISTEN) + goto out; + + /* Reset selection */ + err = bpf_sk_assign(ctx, NULL, BPF_SK_LOOKUP_F_REPLACE); + if (err) + goto out; + if (ctx->sk) + goto out; + + /* Assign another socket */ + sk2 = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B); + if (!sk2) + goto out; + err = bpf_sk_assign(ctx, sk2, BPF_SK_LOOKUP_F_REPLACE); + if (err) + goto out; + if (ctx->sk != sk2) + goto out; + + /* Access reassigned ctx->sk fields */ + if (ctx->sk->family != AF_INET || + ctx->sk->type != SOCK_STREAM || + ctx->sk->state != BPF_TCP_LISTEN) + goto out; + + ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */ +out: + if (sk1) + bpf_sk_release(sk1); + if (sk2) + bpf_sk_release(sk2); + return ret; +} + +/* Check narrow loads from ctx fields that support them. + * + * Narrow loads of size >= target field size from a non-zero offset + * are not covered because they give bogus results, that is the + * verifier ignores the offset. + */ +SEC("sk_lookup") +int ctx_narrow_access(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + __u32 val_u32; + bool v4; + + v4 = (ctx->family == AF_INET); + + /* Narrow loads from family field */ + if (LSB(ctx->family, 0) != (v4 ? AF_INET : AF_INET6) || + LSB(ctx->family, 1) != 0 || LSB(ctx->family, 2) != 0 || LSB(ctx->family, 3) != 0) + return SK_DROP; + if (LSW(ctx->family, 0) != (v4 ? AF_INET : AF_INET6)) + return SK_DROP; + + /* Narrow loads from protocol field */ + if (LSB(ctx->protocol, 0) != IPPROTO_TCP || + LSB(ctx->protocol, 1) != 0 || LSB(ctx->protocol, 2) != 0 || LSB(ctx->protocol, 3) != 0) + return SK_DROP; + if (LSW(ctx->protocol, 0) != IPPROTO_TCP) + return SK_DROP; + + /* Narrow loads from remote_port field. Expect SRC_PORT. */ + if (LSB(ctx->remote_port, 0) != ((SRC_PORT >> 0) & 0xff) || + LSB(ctx->remote_port, 1) != ((SRC_PORT >> 8) & 0xff)) + return SK_DROP; + if (LSW(ctx->remote_port, 0) != SRC_PORT) + return SK_DROP; + + /* + * NOTE: 4-byte load from bpf_sk_lookup at remote_port offset + * is quirky. It gets rewritten by the access converter to a + * 2-byte load for backward compatibility. Treating the load + * result as a be16 value makes the code portable across + * little- and big-endian platforms. + */ + val_u32 = *(__u32 *)&ctx->remote_port; + if (val_u32 != SRC_PORT) + return SK_DROP; + + /* Narrow loads from local_port field. Expect DST_PORT. */ + if (LSB(ctx->local_port, 0) != ((DST_PORT >> 0) & 0xff) || + LSB(ctx->local_port, 1) != ((DST_PORT >> 8) & 0xff) || + LSB(ctx->local_port, 2) != 0 || LSB(ctx->local_port, 3) != 0) + return SK_DROP; + if (LSW(ctx->local_port, 0) != DST_PORT) + return SK_DROP; + + /* Narrow loads from IPv4 fields */ + if (v4) { + /* Expect SRC_IP4 in remote_ip4 */ + if (LSB(ctx->remote_ip4, 0) != ((SRC_IP4 >> 0) & 0xff) || + LSB(ctx->remote_ip4, 1) != ((SRC_IP4 >> 8) & 0xff) || + LSB(ctx->remote_ip4, 2) != ((SRC_IP4 >> 16) & 0xff) || + LSB(ctx->remote_ip4, 3) != ((SRC_IP4 >> 24) & 0xff)) + return SK_DROP; + if (LSW(ctx->remote_ip4, 0) != ((SRC_IP4 >> 0) & 0xffff) || + LSW(ctx->remote_ip4, 1) != ((SRC_IP4 >> 16) & 0xffff)) + return SK_DROP; + + /* Expect DST_IP4 in local_ip4 */ + if (LSB(ctx->local_ip4, 0) != ((DST_IP4 >> 0) & 0xff) || + LSB(ctx->local_ip4, 1) != ((DST_IP4 >> 8) & 0xff) || + LSB(ctx->local_ip4, 2) != ((DST_IP4 >> 16) & 0xff) || + LSB(ctx->local_ip4, 3) != ((DST_IP4 >> 24) & 0xff)) + return SK_DROP; + if (LSW(ctx->local_ip4, 0) != ((DST_IP4 >> 0) & 0xffff) || + LSW(ctx->local_ip4, 1) != ((DST_IP4 >> 16) & 0xffff)) + return SK_DROP; + } else { + /* Expect 0.0.0.0 IPs when family != AF_INET */ + if (LSB(ctx->remote_ip4, 0) != 0 || LSB(ctx->remote_ip4, 1) != 0 || + LSB(ctx->remote_ip4, 2) != 0 || LSB(ctx->remote_ip4, 3) != 0) + return SK_DROP; + if (LSW(ctx->remote_ip4, 0) != 0 || LSW(ctx->remote_ip4, 1) != 0) + return SK_DROP; + + if (LSB(ctx->local_ip4, 0) != 0 || LSB(ctx->local_ip4, 1) != 0 || + LSB(ctx->local_ip4, 2) != 0 || LSB(ctx->local_ip4, 3) != 0) + return SK_DROP; + if (LSW(ctx->local_ip4, 0) != 0 || LSW(ctx->local_ip4, 1) != 0) + return SK_DROP; + } + + /* Narrow loads from IPv6 fields */ + if (!v4) { + /* Expect SRC_IP6 in remote_ip6 */ + if (LSB(ctx->remote_ip6[0], 0) != ((SRC_IP6[0] >> 0) & 0xff) || + LSB(ctx->remote_ip6[0], 1) != ((SRC_IP6[0] >> 8) & 0xff) || + LSB(ctx->remote_ip6[0], 2) != ((SRC_IP6[0] >> 16) & 0xff) || + LSB(ctx->remote_ip6[0], 3) != ((SRC_IP6[0] >> 24) & 0xff) || + LSB(ctx->remote_ip6[1], 0) != ((SRC_IP6[1] >> 0) & 0xff) || + LSB(ctx->remote_ip6[1], 1) != ((SRC_IP6[1] >> 8) & 0xff) || + LSB(ctx->remote_ip6[1], 2) != ((SRC_IP6[1] >> 16) & 0xff) || + LSB(ctx->remote_ip6[1], 3) != ((SRC_IP6[1] >> 24) & 0xff) || + LSB(ctx->remote_ip6[2], 0) != ((SRC_IP6[2] >> 0) & 0xff) || + LSB(ctx->remote_ip6[2], 1) != ((SRC_IP6[2] >> 8) & 0xff) || + LSB(ctx->remote_ip6[2], 2) != ((SRC_IP6[2] >> 16) & 0xff) || + LSB(ctx->remote_ip6[2], 3) != ((SRC_IP6[2] >> 24) & 0xff) || + LSB(ctx->remote_ip6[3], 0) != ((SRC_IP6[3] >> 0) & 0xff) || + LSB(ctx->remote_ip6[3], 1) != ((SRC_IP6[3] >> 8) & 0xff) || + LSB(ctx->remote_ip6[3], 2) != ((SRC_IP6[3] >> 16) & 0xff) || + LSB(ctx->remote_ip6[3], 3) != ((SRC_IP6[3] >> 24) & 0xff)) + return SK_DROP; + if (LSW(ctx->remote_ip6[0], 0) != ((SRC_IP6[0] >> 0) & 0xffff) || + LSW(ctx->remote_ip6[0], 1) != ((SRC_IP6[0] >> 16) & 0xffff) || + LSW(ctx->remote_ip6[1], 0) != ((SRC_IP6[1] >> 0) & 0xffff) || + LSW(ctx->remote_ip6[1], 1) != ((SRC_IP6[1] >> 16) & 0xffff) || + LSW(ctx->remote_ip6[2], 0) != ((SRC_IP6[2] >> 0) & 0xffff) || + LSW(ctx->remote_ip6[2], 1) != ((SRC_IP6[2] >> 16) & 0xffff) || + LSW(ctx->remote_ip6[3], 0) != ((SRC_IP6[3] >> 0) & 0xffff) || + LSW(ctx->remote_ip6[3], 1) != ((SRC_IP6[3] >> 16) & 0xffff)) + return SK_DROP; + /* Expect DST_IP6 in local_ip6 */ + if (LSB(ctx->local_ip6[0], 0) != ((DST_IP6[0] >> 0) & 0xff) || + LSB(ctx->local_ip6[0], 1) != ((DST_IP6[0] >> 8) & 0xff) || + LSB(ctx->local_ip6[0], 2) != ((DST_IP6[0] >> 16) & 0xff) || + LSB(ctx->local_ip6[0], 3) != ((DST_IP6[0] >> 24) & 0xff) || + LSB(ctx->local_ip6[1], 0) != ((DST_IP6[1] >> 0) & 0xff) || + LSB(ctx->local_ip6[1], 1) != ((DST_IP6[1] >> 8) & 0xff) || + LSB(ctx->local_ip6[1], 2) != ((DST_IP6[1] >> 16) & 0xff) || + LSB(ctx->local_ip6[1], 3) != ((DST_IP6[1] >> 24) & 0xff) || + LSB(ctx->local_ip6[2], 0) != ((DST_IP6[2] >> 0) & 0xff) || + LSB(ctx->local_ip6[2], 1) != ((DST_IP6[2] >> 8) & 0xff) || + LSB(ctx->local_ip6[2], 2) != ((DST_IP6[2] >> 16) & 0xff) || + LSB(ctx->local_ip6[2], 3) != ((DST_IP6[2] >> 24) & 0xff) || + LSB(ctx->local_ip6[3], 0) != ((DST_IP6[3] >> 0) & 0xff) || + LSB(ctx->local_ip6[3], 1) != ((DST_IP6[3] >> 8) & 0xff) || + LSB(ctx->local_ip6[3], 2) != ((DST_IP6[3] >> 16) & 0xff) || + LSB(ctx->local_ip6[3], 3) != ((DST_IP6[3] >> 24) & 0xff)) + return SK_DROP; + if (LSW(ctx->local_ip6[0], 0) != ((DST_IP6[0] >> 0) & 0xffff) || + LSW(ctx->local_ip6[0], 1) != ((DST_IP6[0] >> 16) & 0xffff) || + LSW(ctx->local_ip6[1], 0) != ((DST_IP6[1] >> 0) & 0xffff) || + LSW(ctx->local_ip6[1], 1) != ((DST_IP6[1] >> 16) & 0xffff) || + LSW(ctx->local_ip6[2], 0) != ((DST_IP6[2] >> 0) & 0xffff) || + LSW(ctx->local_ip6[2], 1) != ((DST_IP6[2] >> 16) & 0xffff) || + LSW(ctx->local_ip6[3], 0) != ((DST_IP6[3] >> 0) & 0xffff) || + LSW(ctx->local_ip6[3], 1) != ((DST_IP6[3] >> 16) & 0xffff)) + return SK_DROP; + } else { + /* Expect :: IPs when family != AF_INET6 */ + if (LSB(ctx->remote_ip6[0], 0) != 0 || LSB(ctx->remote_ip6[0], 1) != 0 || + LSB(ctx->remote_ip6[0], 2) != 0 || LSB(ctx->remote_ip6[0], 3) != 0 || + LSB(ctx->remote_ip6[1], 0) != 0 || LSB(ctx->remote_ip6[1], 1) != 0 || + LSB(ctx->remote_ip6[1], 2) != 0 || LSB(ctx->remote_ip6[1], 3) != 0 || + LSB(ctx->remote_ip6[2], 0) != 0 || LSB(ctx->remote_ip6[2], 1) != 0 || + LSB(ctx->remote_ip6[2], 2) != 0 || LSB(ctx->remote_ip6[2], 3) != 0 || + LSB(ctx->remote_ip6[3], 0) != 0 || LSB(ctx->remote_ip6[3], 1) != 0 || + LSB(ctx->remote_ip6[3], 2) != 0 || LSB(ctx->remote_ip6[3], 3) != 0) + return SK_DROP; + if (LSW(ctx->remote_ip6[0], 0) != 0 || LSW(ctx->remote_ip6[0], 1) != 0 || + LSW(ctx->remote_ip6[1], 0) != 0 || LSW(ctx->remote_ip6[1], 1) != 0 || + LSW(ctx->remote_ip6[2], 0) != 0 || LSW(ctx->remote_ip6[2], 1) != 0 || + LSW(ctx->remote_ip6[3], 0) != 0 || LSW(ctx->remote_ip6[3], 1) != 0) + return SK_DROP; + + if (LSB(ctx->local_ip6[0], 0) != 0 || LSB(ctx->local_ip6[0], 1) != 0 || + LSB(ctx->local_ip6[0], 2) != 0 || LSB(ctx->local_ip6[0], 3) != 0 || + LSB(ctx->local_ip6[1], 0) != 0 || LSB(ctx->local_ip6[1], 1) != 0 || + LSB(ctx->local_ip6[1], 2) != 0 || LSB(ctx->local_ip6[1], 3) != 0 || + LSB(ctx->local_ip6[2], 0) != 0 || LSB(ctx->local_ip6[2], 1) != 0 || + LSB(ctx->local_ip6[2], 2) != 0 || LSB(ctx->local_ip6[2], 3) != 0 || + LSB(ctx->local_ip6[3], 0) != 0 || LSB(ctx->local_ip6[3], 1) != 0 || + LSB(ctx->local_ip6[3], 2) != 0 || LSB(ctx->local_ip6[3], 3) != 0) + return SK_DROP; + if (LSW(ctx->remote_ip6[0], 0) != 0 || LSW(ctx->remote_ip6[0], 1) != 0 || + LSW(ctx->remote_ip6[1], 0) != 0 || LSW(ctx->remote_ip6[1], 1) != 0 || + LSW(ctx->remote_ip6[2], 0) != 0 || LSW(ctx->remote_ip6[2], 1) != 0 || + LSW(ctx->remote_ip6[3], 0) != 0 || LSW(ctx->remote_ip6[3], 1) != 0) + return SK_DROP; + } + + /* Success, redirect to KEY_SERVER_B */ + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B); + if (sk) { + bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + } + return SK_PASS; +} + +/* Check that sk_assign rejects SERVER_A socket with -ESOCKNOSUPPORT */ +SEC("sk_lookup") +int sk_assign_esocknosupport(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err, ret; + + ret = SK_DROP; + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + goto out; + + err = bpf_sk_assign(ctx, sk, 0); + if (err != -ESOCKTNOSUPPORT) { + bpf_printk("sk_assign returned %d, expected %d\n", + err, -ESOCKTNOSUPPORT); + goto out; + } + + ret = SK_PASS; /* Success, pass to regular lookup */ +out: + if (sk) + bpf_sk_release(sk); + return ret; +} + +SEC("sk_lookup") +int multi_prog_pass1(struct bpf_sk_lookup *ctx) +{ + bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); + return SK_PASS; +} + +SEC("sk_lookup") +int multi_prog_pass2(struct bpf_sk_lookup *ctx) +{ + bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); + return SK_PASS; +} + +SEC("sk_lookup") +int multi_prog_drop1(struct bpf_sk_lookup *ctx) +{ + bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); + return SK_DROP; +} + +SEC("sk_lookup") +int multi_prog_drop2(struct bpf_sk_lookup *ctx) +{ + bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); + return SK_DROP; +} + +static __always_inline int select_server_a(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_DROP; + + err = bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + if (err) + return SK_DROP; + + return SK_PASS; +} + +SEC("sk_lookup") +int multi_prog_redir1(struct bpf_sk_lookup *ctx) +{ + (void)select_server_a(ctx); + bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); + return SK_PASS; +} + +SEC("sk_lookup") +int multi_prog_redir2(struct bpf_sk_lookup *ctx) +{ + (void)select_server_a(ctx); + bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); + return SK_PASS; +} + +char _license[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c new file mode 100644 index 0000000000..e9efc32630 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c @@ -0,0 +1,178 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io + +#include <stddef.h> +#include <stdbool.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/pkt_cls.h> +#include <linux/tcp.h> +#include <sys/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +char _license[] SEC("license") = "GPL"; + +/* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */ +static struct bpf_sock_tuple *get_tuple(void *data, __u64 nh_off, + void *data_end, __u16 eth_proto, + bool *ipv4) +{ + struct bpf_sock_tuple *result; + __u64 ihl_len = 0; + __u8 proto = 0; + + if (eth_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)(data + nh_off); + + if (iph + 1 > data_end) + return NULL; + ihl_len = iph->ihl * 4; + proto = iph->protocol; + *ipv4 = true; + result = (struct bpf_sock_tuple *)&iph->saddr; + } else if (eth_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ip6h = (struct ipv6hdr *)(data + nh_off); + + if (ip6h + 1 > data_end) + return NULL; + ihl_len = sizeof(*ip6h); + proto = ip6h->nexthdr; + *ipv4 = true; + result = (struct bpf_sock_tuple *)&ip6h->saddr; + } + + if (data + nh_off + ihl_len > data_end || proto != IPPROTO_TCP) + return NULL; + + return result; +} + +SEC("?tc") +int sk_lookup_success(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ethhdr *eth = (struct ethhdr *)(data); + struct bpf_sock_tuple *tuple; + struct bpf_sock *sk; + size_t tuple_len; + bool ipv4; + + if (eth + 1 > data_end) + return TC_ACT_SHOT; + + tuple = get_tuple(data, sizeof(*eth), data_end, eth->h_proto, &ipv4); + if (!tuple || tuple + sizeof *tuple > data_end) + return TC_ACT_SHOT; + + tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6); + sk = bpf_sk_lookup_tcp(skb, tuple, tuple_len, BPF_F_CURRENT_NETNS, 0); + bpf_printk("sk=%d\n", sk ? 1 : 0); + if (sk) + bpf_sk_release(sk); + return sk ? TC_ACT_OK : TC_ACT_UNSPEC; +} + +SEC("?tc") +int sk_lookup_success_simple(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + struct bpf_sock *sk; + + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); + if (sk) + bpf_sk_release(sk); + return 0; +} + +SEC("?tc") +int err_use_after_free(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + struct bpf_sock *sk; + __u32 family = 0; + + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); + if (sk) { + bpf_sk_release(sk); + family = sk->family; + } + return family; +} + +SEC("?tc") +int err_modify_sk_pointer(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + struct bpf_sock *sk; + + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); + if (sk) { + sk += 1; + bpf_sk_release(sk); + } + return 0; +} + +SEC("?tc") +int err_modify_sk_or_null_pointer(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + struct bpf_sock *sk; + + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); + sk += 1; + if (sk) + bpf_sk_release(sk); + return 0; +} + +SEC("?tc") +int err_no_release(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + + bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); + return 0; +} + +SEC("?tc") +int err_release_twice(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + struct bpf_sock *sk; + + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); + bpf_sk_release(sk); + bpf_sk_release(sk); + return 0; +} + +SEC("?tc") +int err_release_unchecked(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + struct bpf_sock *sk; + + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); + bpf_sk_release(sk); + return 0; +} + +void lookup_no_release(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); +} + +SEC("?tc") +int err_no_release_subcall(struct __sk_buff *skb) +{ + lookup_no_release(skb); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_sk_storage_trace_itself.c b/tools/testing/selftests/bpf/progs/test_sk_storage_trace_itself.c new file mode 100644 index 0000000000..59ef72d02a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sk_storage_trace_itself.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} sk_stg_map SEC(".maps"); + +SEC("fentry/bpf_sk_storage_free") +int BPF_PROG(trace_bpf_sk_storage_free, struct sock *sk) +{ + int *value; + + value = bpf_sk_storage_get(&sk_stg_map, sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + + if (value) + *value = 1; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c new file mode 100644 index 0000000000..02e718f06e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_helpers.h> + +struct sk_stg { + __u32 pid; + __u32 last_notclose_state; + char comm[16]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct sk_stg); +} sk_stg_map SEC(".maps"); + +/* Testing delete */ +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} del_sk_stg_map SEC(".maps"); + +char task_comm[16] = ""; + +SEC("tp_btf/inet_sock_set_state") +int BPF_PROG(trace_inet_sock_set_state, struct sock *sk, int oldstate, + int newstate) +{ + struct sk_stg *stg; + + if (newstate == BPF_TCP_CLOSE) + return 0; + + stg = bpf_sk_storage_get(&sk_stg_map, sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!stg) + return 0; + + stg->last_notclose_state = newstate; + + bpf_sk_storage_delete(&del_sk_stg_map, sk); + + return 0; +} + +static void set_task_info(struct sock *sk) +{ + struct task_struct *task; + struct sk_stg *stg; + + stg = bpf_sk_storage_get(&sk_stg_map, sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!stg) + return; + + stg->pid = bpf_get_current_pid_tgid(); + + task = (struct task_struct *)bpf_get_current_task(); + bpf_core_read_str(&stg->comm, sizeof(stg->comm), &task->comm); + bpf_core_read_str(&task_comm, sizeof(task_comm), &task->comm); +} + +SEC("fentry/inet_csk_listen_start") +int BPF_PROG(trace_inet_csk_listen_start, struct sock *sk) +{ + set_task_info(sk); + + return 0; +} + +SEC("fentry/tcp_connect") +int BPF_PROG(trace_tcp_connect, struct sock *sk) +{ + set_task_info(sk); + + return 0; +} + +SEC("fexit/inet_csk_accept") +int BPF_PROG(inet_csk_accept, struct sock *sk, int flags, int *err, bool kern, + struct sock *accepted_sk) +{ + set_task_info(accepted_sk); + + return 0; +} + +SEC("tp_btf/tcp_retransmit_synack") +int BPF_PROG(tcp_retransmit_synack, struct sock* sk, struct request_sock* req) +{ + /* load only test */ + bpf_sk_storage_get(&sk_stg_map, sk, 0, 0); + bpf_sk_storage_get(&sk_stg_map, req->sk, 0, 0); + return 0; +} + +SEC("tp_btf/tcp_bad_csum") +int BPF_PROG(tcp_bad_csum, struct sk_buff* skb) +{ + bpf_sk_storage_get(&sk_stg_map, skb->sk, 0, 0); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c new file mode 100644 index 0000000000..37aacc66cd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <linux/bpf.h> +#include <linux/pkt_cls.h> + +#include <string.h> + +#include <bpf/bpf_helpers.h> + +#define NUM_CGROUP_LEVELS 4 + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u64); + __uint(max_entries, NUM_CGROUP_LEVELS); +} cgroup_ids SEC(".maps"); + +static __always_inline void log_nth_level(struct __sk_buff *skb, __u32 level) +{ + __u64 id; + + /* [1] &level passed to external function that may change it, it's + * incompatible with loop unroll. + */ + id = bpf_skb_ancestor_cgroup_id(skb, level); + bpf_map_update_elem(&cgroup_ids, &level, &id, 0); +} + +SEC("cgroup_id_logger") +int log_cgroup_id(struct __sk_buff *skb) +{ + /* Loop unroll can't be used here due to [1]. Unrolling manually. + * Number of calls should be in sync with NUM_CGROUP_LEVELS. + */ + log_nth_level(skb, 0); + log_nth_level(skb, 1); + log_nth_level(skb, 2); + log_nth_level(skb, 3); + + return TC_ACT_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c new file mode 100644 index 0000000000..c482110cfc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +SEC("tc") +int process(struct __sk_buff *skb) +{ + #pragma clang loop unroll(full) + for (int i = 0; i < 5; i++) { + if (skb->cb[i] != i + 1) + return 1; + skb->cb[i]++; + } + skb->priority++; + skb->tstamp++; + skb->mark++; + + if (skb->wire_len != 100) + return 1; + if (skb->gso_segs != 8) + return 1; + if (skb->gso_size != 10) + return 1; + if (skb->ingress_ifindex != 11) + return 1; + if (skb->ifindex != 1) + return 1; + if (skb->hwtstamp != 11) + return 1; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_skb_helpers.c b/tools/testing/selftests/bpf/progs/test_skb_helpers.c new file mode 100644 index 0000000000..507215791c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_skb_helpers.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define TEST_COMM_LEN 16 + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_ARRAY); + __uint(max_entries, 1); + __type(key, u32); + __type(value, u32); +} cgroup_map SEC(".maps"); + +char _license[] SEC("license") = "GPL"; + +SEC("tc") +int test_skb_helpers(struct __sk_buff *skb) +{ + struct task_struct *task; + char comm[TEST_COMM_LEN]; + __u32 tpid; + + task = (struct task_struct *)bpf_get_current_task(); + bpf_probe_read_kernel(&tpid , sizeof(tpid), &task->tgid); + bpf_probe_read_kernel_str(&comm, sizeof(comm), &task->comm); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c b/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c new file mode 100644 index 0000000000..eacda9fe07 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2021 Hengqi Chen */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_tracing_net.h" + +const volatile pid_t my_pid = 0; +char path[256] = {}; + +SEC("fentry/unix_listen") +int BPF_PROG(unix_listen, struct socket *sock, int backlog) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + struct unix_sock *unix_sk; + int i, len; + + if (pid != my_pid) + return 0; + + unix_sk = (struct unix_sock *)bpf_skc_to_unix_sock(sock->sk); + if (!unix_sk) + return 0; + + if (unix_sk->addr->name->sun_path[0]) + return 0; + + len = unix_sk->addr->len - sizeof(short); + path[0] = '@'; + for (i = 1; i < len; i++) { + if (i >= sizeof(struct sockaddr_un)) + break; + + path[i] = unix_sk->addr->name->sun_path[i]; + } + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_skeleton.c b/tools/testing/selftests/bpf/progs/test_skeleton.c new file mode 100644 index 0000000000..adece9f91f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_skeleton.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define __read_mostly SEC(".data.read_mostly") + +struct s { + int a; + long long b; +} __attribute__((packed)); + +/* .data section */ +int in1 = -1; +long long in2 = -1; + +/* .bss section */ +char in3 = '\0'; +long long in4 __attribute__((aligned(64))) = 0; +struct s in5 = {}; + +/* .rodata section */ +const volatile struct { + const int in6; +} in = {}; + +/* .data section */ +int out1 = -1; +long long out2 = -1; + +/* .bss section */ +char out3 = 0; +long long out4 = 0; +int out6 = 0; + +extern bool CONFIG_BPF_SYSCALL __kconfig; +extern int LINUX_KERNEL_VERSION __kconfig; +bool bpf_syscall = 0; +int kern_ver = 0; + +struct s out5 = {}; + + +const volatile int in_dynarr_sz SEC(".rodata.dyn"); +const volatile int in_dynarr[4] SEC(".rodata.dyn") = { -1, -2, -3, -4 }; + +int out_dynarr[4] SEC(".data.dyn") = { 1, 2, 3, 4 }; + +int read_mostly_var __read_mostly; +int out_mostly_var; + +char huge_arr[16 * 1024 * 1024]; + +/* non-mmapable custom .data section */ + +struct my_value { int x, y, z; }; + +__hidden int zero_key SEC(".data.non_mmapable"); +static struct my_value zero_value SEC(".data.non_mmapable"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct my_value); + __uint(max_entries, 1); +} my_map SEC(".maps"); + +SEC("raw_tp/sys_enter") +int handler(const void *ctx) +{ + int i; + + out1 = in1; + out2 = in2; + out3 = in3; + out4 = in4; + out5 = in5; + out6 = in.in6; + + bpf_syscall = CONFIG_BPF_SYSCALL; + kern_ver = LINUX_KERNEL_VERSION; + + for (i = 0; i < in_dynarr_sz; i++) + out_dynarr[i] = in_dynarr[i]; + + out_mostly_var = read_mostly_var; + + huge_arr[sizeof(huge_arr) - 1] = 123; + + /* make sure zero_key and zero_value are not optimized out */ + bpf_map_update_elem(&my_map, &zero_key, &zero_value, BPF_ANY); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c b/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c new file mode 100644 index 0000000000..45e8fc75a7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Isovalent, Inc. +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, __u64); +} sock_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, __u64); +} sock_hash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, __u32); + __type(value, __u64); +} socket_storage SEC(".maps"); + +SEC("sk_msg") +int prog_msg_verdict(struct sk_msg_md *msg) +{ + struct task_struct *task = (struct task_struct *)bpf_get_current_task(); + int verdict = SK_PASS; + __u32 pid, tpid; + __u64 *sk_stg; + + pid = bpf_get_current_pid_tgid() >> 32; + sk_stg = bpf_sk_storage_get(&socket_storage, msg->sk, 0, BPF_SK_STORAGE_GET_F_CREATE); + if (!sk_stg) + return SK_DROP; + *sk_stg = pid; + bpf_probe_read_kernel(&tpid , sizeof(tpid), &task->tgid); + if (pid != tpid) + verdict = SK_DROP; + bpf_sk_storage_delete(&socket_storage, (void *)msg->sk); + return verdict; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_snprintf.c b/tools/testing/selftests/bpf/progs/test_snprintf.c new file mode 100644 index 0000000000..8fda075440 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_snprintf.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Google LLC. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__u32 pid = 0; + +char num_out[64] = {}; +long num_ret = 0; + +char ip_out[64] = {}; +long ip_ret = 0; + +char sym_out[64] = {}; +long sym_ret = 0; + +char addr_out[64] = {}; +long addr_ret = 0; + +char str_out[64] = {}; +long str_ret = 0; + +char over_out[6] = {}; +long over_ret = 0; + +char pad_out[10] = {}; +long pad_ret = 0; + +char noarg_out[64] = {}; +long noarg_ret = 0; + +long nobuf_ret = 0; + +extern const void schedule __ksym; + +SEC("raw_tp/sys_enter") +int handler(const void *ctx) +{ + /* Convenient values to pretty-print */ + const __u8 ex_ipv4[] = {127, 0, 0, 1}; + const __u8 ex_ipv6[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1}; + static const char str1[] = "str1"; + static const char longstr[] = "longstr"; + + if ((int)bpf_get_current_pid_tgid() != pid) + return 0; + + /* Integer types */ + num_ret = BPF_SNPRINTF(num_out, sizeof(num_out), + "%d %u %x %li %llu %lX", + -8, 9, 150, -424242, 1337, 0xDABBAD00); + /* IP addresses */ + ip_ret = BPF_SNPRINTF(ip_out, sizeof(ip_out), "%pi4 %pI6", + &ex_ipv4, &ex_ipv6); + /* Symbol lookup formatting */ + sym_ret = BPF_SNPRINTF(sym_out, sizeof(sym_out), "%ps %pS %pB", + &schedule, &schedule, &schedule); + /* Kernel pointers */ + addr_ret = BPF_SNPRINTF(addr_out, sizeof(addr_out), "%pK %px %p", + 0, 0xFFFF00000ADD4E55, 0xFFFF00000ADD4E55); + /* Strings and single-byte character embedding */ + str_ret = BPF_SNPRINTF(str_out, sizeof(str_out), "%s % 9c %+2c %-3c %04c %0c %+05s", + str1, 'a', 'b', 'c', 'd', 'e', longstr); + /* Overflow */ + over_ret = BPF_SNPRINTF(over_out, sizeof(over_out), "%%overflow"); + /* Padding of fixed width numbers */ + pad_ret = BPF_SNPRINTF(pad_out, sizeof(pad_out), "%5d %0900000X", 4, 4); + /* No args */ + noarg_ret = BPF_SNPRINTF(noarg_out, sizeof(noarg_out), "simple case"); + /* No buffer */ + nobuf_ret = BPF_SNPRINTF(NULL, 0, "only interested in length %d", 60); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_snprintf_single.c b/tools/testing/selftests/bpf/progs/test_snprintf_single.c new file mode 100644 index 0000000000..3095837334 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_snprintf_single.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Google LLC. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* The format string is filled from the userspace such that loading fails */ +const char fmt[10]; + +SEC("raw_tp/sys_enter") +int handler(const void *ctx) +{ + unsigned long long arg = 42; + + bpf_snprintf(NULL, 0, fmt, &arg, sizeof(arg)); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c new file mode 100644 index 0000000000..f75e531bf3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c @@ -0,0 +1,307 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <linux/bpf.h> +#include <netinet/in.h> +#include <stdbool.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include "bpf_tcp_helpers.h" + +enum bpf_linum_array_idx { + EGRESS_LINUM_IDX, + INGRESS_LINUM_IDX, + READ_SK_DST_PORT_LINUM_IDX, + __NR_BPF_LINUM_ARRAY_IDX, +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, __NR_BPF_LINUM_ARRAY_IDX); + __type(key, __u32); + __type(value, __u32); +} linum_map SEC(".maps"); + +struct bpf_spinlock_cnt { + struct bpf_spin_lock lock; + __u32 cnt; +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct bpf_spinlock_cnt); +} sk_pkt_out_cnt SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct bpf_spinlock_cnt); +} sk_pkt_out_cnt10 SEC(".maps"); + +struct bpf_tcp_sock listen_tp = {}; +struct sockaddr_in6 srv_sa6 = {}; +struct bpf_tcp_sock cli_tp = {}; +struct bpf_tcp_sock srv_tp = {}; +struct bpf_sock listen_sk = {}; +struct bpf_sock srv_sk = {}; +struct bpf_sock cli_sk = {}; +__u64 parent_cg_id = 0; +__u64 child_cg_id = 0; +__u64 lsndtime = 0; + +static bool is_loopback6(__u32 *a6) +{ + return !a6[0] && !a6[1] && !a6[2] && a6[3] == bpf_htonl(1); +} + +static void skcpy(struct bpf_sock *dst, + const struct bpf_sock *src) +{ + dst->bound_dev_if = src->bound_dev_if; + dst->family = src->family; + dst->type = src->type; + dst->protocol = src->protocol; + dst->mark = src->mark; + dst->priority = src->priority; + dst->src_ip4 = src->src_ip4; + dst->src_ip6[0] = src->src_ip6[0]; + dst->src_ip6[1] = src->src_ip6[1]; + dst->src_ip6[2] = src->src_ip6[2]; + dst->src_ip6[3] = src->src_ip6[3]; + dst->src_port = src->src_port; + dst->dst_ip4 = src->dst_ip4; + dst->dst_ip6[0] = src->dst_ip6[0]; + dst->dst_ip6[1] = src->dst_ip6[1]; + dst->dst_ip6[2] = src->dst_ip6[2]; + dst->dst_ip6[3] = src->dst_ip6[3]; + dst->dst_port = src->dst_port; + dst->state = src->state; +} + +static void tpcpy(struct bpf_tcp_sock *dst, + const struct bpf_tcp_sock *src) +{ + dst->snd_cwnd = src->snd_cwnd; + dst->srtt_us = src->srtt_us; + dst->rtt_min = src->rtt_min; + dst->snd_ssthresh = src->snd_ssthresh; + dst->rcv_nxt = src->rcv_nxt; + dst->snd_nxt = src->snd_nxt; + dst->snd_una = src->snd_una; + dst->mss_cache = src->mss_cache; + dst->ecn_flags = src->ecn_flags; + dst->rate_delivered = src->rate_delivered; + dst->rate_interval_us = src->rate_interval_us; + dst->packets_out = src->packets_out; + dst->retrans_out = src->retrans_out; + dst->total_retrans = src->total_retrans; + dst->segs_in = src->segs_in; + dst->data_segs_in = src->data_segs_in; + dst->segs_out = src->segs_out; + dst->data_segs_out = src->data_segs_out; + dst->lost_out = src->lost_out; + dst->sacked_out = src->sacked_out; + dst->bytes_received = src->bytes_received; + dst->bytes_acked = src->bytes_acked; +} + +/* Always return CG_OK so that no pkt will be filtered out */ +#define CG_OK 1 + +#define RET_LOG() ({ \ + linum = __LINE__; \ + bpf_map_update_elem(&linum_map, &linum_idx, &linum, BPF_ANY); \ + return CG_OK; \ +}) + +SEC("cgroup_skb/egress") +int egress_read_sock_fields(struct __sk_buff *skb) +{ + struct bpf_spinlock_cnt cli_cnt_init = { .lock = {}, .cnt = 0xeB9F }; + struct bpf_spinlock_cnt *pkt_out_cnt, *pkt_out_cnt10; + struct bpf_tcp_sock *tp, *tp_ret; + struct bpf_sock *sk, *sk_ret; + __u32 linum, linum_idx; + struct tcp_sock *ktp; + + linum_idx = EGRESS_LINUM_IDX; + + sk = skb->sk; + if (!sk) + RET_LOG(); + + /* Not testing the egress traffic or the listening socket, + * which are covered by the cgroup_skb/ingress test program. + */ + if (sk->family != AF_INET6 || !is_loopback6(sk->src_ip6) || + sk->state == BPF_TCP_LISTEN) + return CG_OK; + + if (sk->src_port == bpf_ntohs(srv_sa6.sin6_port)) { + /* Server socket */ + sk_ret = &srv_sk; + tp_ret = &srv_tp; + } else if (sk->dst_port == srv_sa6.sin6_port) { + /* Client socket */ + sk_ret = &cli_sk; + tp_ret = &cli_tp; + } else { + /* Not the testing egress traffic */ + return CG_OK; + } + + /* It must be a fullsock for cgroup_skb/egress prog */ + sk = bpf_sk_fullsock(sk); + if (!sk) + RET_LOG(); + + /* Not the testing egress traffic */ + if (sk->protocol != IPPROTO_TCP) + return CG_OK; + + tp = bpf_tcp_sock(sk); + if (!tp) + RET_LOG(); + + skcpy(sk_ret, sk); + tpcpy(tp_ret, tp); + + if (sk_ret == &srv_sk) { + ktp = bpf_skc_to_tcp_sock(sk); + + if (!ktp) + RET_LOG(); + + lsndtime = ktp->lsndtime; + + child_cg_id = bpf_sk_cgroup_id(ktp); + if (!child_cg_id) + RET_LOG(); + + parent_cg_id = bpf_sk_ancestor_cgroup_id(ktp, 2); + if (!parent_cg_id) + RET_LOG(); + + /* The userspace has created it for srv sk */ + pkt_out_cnt = bpf_sk_storage_get(&sk_pkt_out_cnt, ktp, 0, 0); + pkt_out_cnt10 = bpf_sk_storage_get(&sk_pkt_out_cnt10, ktp, + 0, 0); + } else { + pkt_out_cnt = bpf_sk_storage_get(&sk_pkt_out_cnt, sk, + &cli_cnt_init, + BPF_SK_STORAGE_GET_F_CREATE); + pkt_out_cnt10 = bpf_sk_storage_get(&sk_pkt_out_cnt10, + sk, &cli_cnt_init, + BPF_SK_STORAGE_GET_F_CREATE); + } + + if (!pkt_out_cnt || !pkt_out_cnt10) + RET_LOG(); + + /* Even both cnt and cnt10 have lock defined in their BTF, + * intentionally one cnt takes lock while one does not + * as a test for the spinlock support in BPF_MAP_TYPE_SK_STORAGE. + */ + pkt_out_cnt->cnt += 1; + bpf_spin_lock(&pkt_out_cnt10->lock); + pkt_out_cnt10->cnt += 10; + bpf_spin_unlock(&pkt_out_cnt10->lock); + + return CG_OK; +} + +SEC("cgroup_skb/ingress") +int ingress_read_sock_fields(struct __sk_buff *skb) +{ + struct bpf_tcp_sock *tp; + __u32 linum, linum_idx; + struct bpf_sock *sk; + + linum_idx = INGRESS_LINUM_IDX; + + sk = skb->sk; + if (!sk) + RET_LOG(); + + /* Not the testing ingress traffic to the server */ + if (sk->family != AF_INET6 || !is_loopback6(sk->src_ip6) || + sk->src_port != bpf_ntohs(srv_sa6.sin6_port)) + return CG_OK; + + /* Only interested in the listening socket */ + if (sk->state != BPF_TCP_LISTEN) + return CG_OK; + + /* It must be a fullsock for cgroup_skb/ingress prog */ + sk = bpf_sk_fullsock(sk); + if (!sk) + RET_LOG(); + + tp = bpf_tcp_sock(sk); + if (!tp) + RET_LOG(); + + skcpy(&listen_sk, sk); + tpcpy(&listen_tp, tp); + + return CG_OK; +} + +/* + * NOTE: 4-byte load from bpf_sock at dst_port offset is quirky. It + * gets rewritten by the access converter to a 2-byte load for + * backward compatibility. Treating the load result as a be16 value + * makes the code portable across little- and big-endian platforms. + */ +static __noinline bool sk_dst_port__load_word(struct bpf_sock *sk) +{ + __u32 *word = (__u32 *)&sk->dst_port; + return word[0] == bpf_htons(0xcafe); +} + +static __noinline bool sk_dst_port__load_half(struct bpf_sock *sk) +{ + __u16 *half; + + asm volatile (""); + half = (__u16 *)&sk->dst_port; + return half[0] == bpf_htons(0xcafe); +} + +static __noinline bool sk_dst_port__load_byte(struct bpf_sock *sk) +{ + __u8 *byte = (__u8 *)&sk->dst_port; + return byte[0] == 0xca && byte[1] == 0xfe; +} + +SEC("cgroup_skb/egress") +int read_sk_dst_port(struct __sk_buff *skb) +{ + __u32 linum, linum_idx; + struct bpf_sock *sk; + + linum_idx = READ_SK_DST_PORT_LINUM_IDX; + + sk = skb->sk; + if (!sk) + RET_LOG(); + + /* Ignore everything but the SYN from the client socket */ + if (sk->state != BPF_TCP_SYN_SENT) + return CG_OK; + + if (!sk_dst_port__load_word(sk)) + RET_LOG(); + if (!sk_dst_port__load_half(sk)) + RET_LOG(); + if (!sk_dst_port__load_byte(sk)) + RET_LOG(); + + return CG_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockhash_kern.c b/tools/testing/selftests/bpf/progs/test_sockhash_kern.c new file mode 100644 index 0000000000..e675591644 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockhash_kern.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io +#undef SOCKMAP +#define TEST_MAP_TYPE BPF_MAP_TYPE_SOCKHASH +#include "./test_sockmap_kern.h" diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c b/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c new file mode 100644 index 0000000000..29314805ce --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c @@ -0,0 +1,32 @@ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_tx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_msg SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_invalid_update.c b/tools/testing/selftests/bpf/progs/test_sockmap_invalid_update.c new file mode 100644 index 0000000000..02a59e220c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_invalid_update.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Cloudflare +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} map SEC(".maps"); + +SEC("sockops") +int bpf_sockmap(struct bpf_sock_ops *skops) +{ + __u32 key = 0; + + if (skops->sk) + bpf_map_update_elem(&map, &key, skops->sk, 0); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.c b/tools/testing/selftests/bpf/progs/test_sockmap_kern.c new file mode 100644 index 0000000000..677b2ed1cc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io +#define SOCKMAP +#define TEST_MAP_TYPE BPF_MAP_TYPE_SOCKMAP +#include "./test_sockmap_kern.h" diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h new file mode 100644 index 0000000000..99d2ea9fb6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -0,0 +1,380 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io */ +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/udp.h> +#include <linux/tcp.h> +#include <linux/pkt_cls.h> +#include <sys/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include "bpf_misc.h" + +/* Sockmap sample program connects a client and a backend together + * using cgroups. + * + * client:X <---> frontend:80 client:X <---> backend:80 + * + * For simplicity we hard code values here and bind 1:1. The hard + * coded values are part of the setup in sockmap.sh script that + * is associated with this BPF program. + * + * The bpf_printk is verbose and prints information as connections + * are established and verdicts are decided. + */ + +struct { + __uint(type, TEST_MAP_TYPE); + __uint(max_entries, 20); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); +} sock_map SEC(".maps"); + +struct { + __uint(type, TEST_MAP_TYPE); + __uint(max_entries, 20); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); +} sock_map_txmsg SEC(".maps"); + +struct { + __uint(type, TEST_MAP_TYPE); + __uint(max_entries, 20); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); +} sock_map_redir SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} sock_apply_bytes SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} sock_cork_bytes SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 6); + __type(key, int); + __type(value, int); +} sock_bytes SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} sock_redir_flags SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 3); + __type(key, int); + __type(value, int); +} sock_skb_opts SEC(".maps"); + +struct { + __uint(type, TEST_MAP_TYPE); + __uint(max_entries, 20); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); +} tls_sock_map SEC(".maps"); + +SEC("sk_skb1") +int bpf_prog1(struct __sk_buff *skb) +{ + int *f, two = 2; + + f = bpf_map_lookup_elem(&sock_skb_opts, &two); + if (f && *f) { + return *f; + } + return skb->len; +} + +SEC("sk_skb2") +int bpf_prog2(struct __sk_buff *skb) +{ + __u32 lport = skb->local_port; + __u32 rport = skb->remote_port; + int len, *f, ret, zero = 0; + __u64 flags = 0; + + __sink(rport); + if (lport == 10000) + ret = 10; + else + ret = 1; + + len = (__u32)skb->data_end - (__u32)skb->data; + __sink(len); + + f = bpf_map_lookup_elem(&sock_skb_opts, &zero); + if (f && *f) { + ret = 3; + flags = *f; + } + +#ifdef SOCKMAP + return bpf_sk_redirect_map(skb, &sock_map, ret, flags); +#else + return bpf_sk_redirect_hash(skb, &sock_map, &ret, flags); +#endif + +} + +static inline void bpf_write_pass(struct __sk_buff *skb, int offset) +{ + int err = bpf_skb_pull_data(skb, 6 + offset); + void *data_end; + char *c; + + if (err) + return; + + c = (char *)(long)skb->data; + data_end = (void *)(long)skb->data_end; + + if (c + 5 + offset < data_end) + memcpy(c + offset, "PASS", 4); +} + +SEC("sk_skb3") +int bpf_prog3(struct __sk_buff *skb) +{ + int err, *f, ret = SK_PASS; + const int one = 1; + + f = bpf_map_lookup_elem(&sock_skb_opts, &one); + if (f && *f) { + __u64 flags = 0; + + ret = 0; + flags = *f; + + err = bpf_skb_adjust_room(skb, -13, 0, 0); + if (err) + return SK_DROP; + err = bpf_skb_adjust_room(skb, 4, 0, 0); + if (err) + return SK_DROP; + bpf_write_pass(skb, 0); +#ifdef SOCKMAP + return bpf_sk_redirect_map(skb, &tls_sock_map, ret, flags); +#else + return bpf_sk_redirect_hash(skb, &tls_sock_map, &ret, flags); +#endif + } + f = bpf_map_lookup_elem(&sock_skb_opts, &one); + if (f && *f) + ret = SK_DROP; + err = bpf_skb_adjust_room(skb, 4, 0, 0); + if (err) + return SK_DROP; + bpf_write_pass(skb, 13); + return ret; +} + +SEC("sockops") +int bpf_sockmap(struct bpf_sock_ops *skops) +{ + __u32 lport, rport; + int op, ret; + + op = (int) skops->op; + + switch (op) { + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + lport = skops->local_port; + rport = skops->remote_port; + + if (lport == 10000) { + ret = 1; +#ifdef SOCKMAP + bpf_sock_map_update(skops, &sock_map, &ret, + BPF_NOEXIST); +#else + bpf_sock_hash_update(skops, &sock_map, &ret, + BPF_NOEXIST); +#endif + } + break; + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + lport = skops->local_port; + rport = skops->remote_port; + + if (bpf_ntohl(rport) == 10001) { + ret = 10; +#ifdef SOCKMAP + bpf_sock_map_update(skops, &sock_map, &ret, + BPF_NOEXIST); +#else + bpf_sock_hash_update(skops, &sock_map, &ret, + BPF_NOEXIST); +#endif + } + break; + default: + break; + } + + return 0; +} + +SEC("sk_msg1") +int bpf_prog4(struct sk_msg_md *msg) +{ + int *bytes, zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5; + int *start, *end, *start_push, *end_push, *start_pop, *pop, err = 0; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + bpf_msg_cork_bytes(msg, *bytes); + start = bpf_map_lookup_elem(&sock_bytes, &zero); + end = bpf_map_lookup_elem(&sock_bytes, &one); + if (start && end) + bpf_msg_pull_data(msg, *start, *end, 0); + start_push = bpf_map_lookup_elem(&sock_bytes, &two); + end_push = bpf_map_lookup_elem(&sock_bytes, &three); + if (start_push && end_push) { + err = bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (err) + return SK_DROP; + } + start_pop = bpf_map_lookup_elem(&sock_bytes, &four); + pop = bpf_map_lookup_elem(&sock_bytes, &five); + if (start_pop && pop) + bpf_msg_pop_data(msg, *start_pop, *pop, 0); + return SK_PASS; +} + +SEC("sk_msg2") +int bpf_prog6(struct sk_msg_md *msg) +{ + int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, key = 0; + int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop, *f; + int err = 0; + __u64 flags = 0; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + bpf_msg_cork_bytes(msg, *bytes); + + start = bpf_map_lookup_elem(&sock_bytes, &zero); + end = bpf_map_lookup_elem(&sock_bytes, &one); + if (start && end) + bpf_msg_pull_data(msg, *start, *end, 0); + + start_push = bpf_map_lookup_elem(&sock_bytes, &two); + end_push = bpf_map_lookup_elem(&sock_bytes, &three); + if (start_push && end_push) { + err = bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (err) + return SK_DROP; + } + + start_pop = bpf_map_lookup_elem(&sock_bytes, &four); + pop = bpf_map_lookup_elem(&sock_bytes, &five); + if (start_pop && pop) + bpf_msg_pop_data(msg, *start_pop, *pop, 0); + + f = bpf_map_lookup_elem(&sock_redir_flags, &zero); + if (f && *f) { + key = 2; + flags = *f; + } +#ifdef SOCKMAP + return bpf_msg_redirect_map(msg, &sock_map_redir, key, flags); +#else + return bpf_msg_redirect_hash(msg, &sock_map_redir, &key, flags); +#endif +} + +SEC("sk_msg3") +int bpf_prog8(struct sk_msg_md *msg) +{ + void *data_end = (void *)(long) msg->data_end; + void *data = (void *)(long) msg->data; + int ret = 0, *bytes, zero = 0; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) { + ret = bpf_msg_apply_bytes(msg, *bytes); + if (ret) + return SK_DROP; + } else { + return SK_DROP; + } + + __sink(data_end); + __sink(data); + + return SK_PASS; +} +SEC("sk_msg4") +int bpf_prog9(struct sk_msg_md *msg) +{ + void *data_end = (void *)(long) msg->data_end; + void *data = (void *)(long) msg->data; + int ret = 0, *bytes, zero = 0; + + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) { + if (((__u64)data_end - (__u64)data) >= *bytes) + return SK_PASS; + ret = bpf_msg_cork_bytes(msg, *bytes); + if (ret) + return SK_DROP; + } + return SK_PASS; +} + +SEC("sk_msg5") +int bpf_prog10(struct sk_msg_md *msg) +{ + int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop; + int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, err = 0; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + bpf_msg_cork_bytes(msg, *bytes); + start = bpf_map_lookup_elem(&sock_bytes, &zero); + end = bpf_map_lookup_elem(&sock_bytes, &one); + if (start && end) + bpf_msg_pull_data(msg, *start, *end, 0); + start_push = bpf_map_lookup_elem(&sock_bytes, &two); + end_push = bpf_map_lookup_elem(&sock_bytes, &three); + if (start_push && end_push) { + err = bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (err) + return SK_PASS; + } + start_pop = bpf_map_lookup_elem(&sock_bytes, &four); + pop = bpf_map_lookup_elem(&sock_bytes, &five); + if (start_pop && pop) + bpf_msg_pop_data(msg, *start_pop, *pop, 0); + return SK_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c new file mode 100644 index 0000000000..464d35bd57 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c @@ -0,0 +1,133 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Cloudflare + +#include <errno.h> +#include <stdbool.h> +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, __u64); +} sock_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, __u64); +} sock_hash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 2); + __type(key, int); + __type(value, unsigned int); +} verdict_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} parser_map SEC(".maps"); + +bool test_sockmap = false; /* toggled by user-space */ +bool test_ingress = false; /* toggled by user-space */ + +SEC("sk_skb/stream_parser") +int prog_stream_parser(struct __sk_buff *skb) +{ + int *value; + __u32 key = 0; + + value = bpf_map_lookup_elem(&parser_map, &key); + if (value && *value) + return *value; + + return skb->len; +} + +SEC("sk_skb/stream_verdict") +int prog_stream_verdict(struct __sk_buff *skb) +{ + unsigned int *count; + __u32 zero = 0; + int verdict; + + if (test_sockmap) + verdict = bpf_sk_redirect_map(skb, &sock_map, zero, 0); + else + verdict = bpf_sk_redirect_hash(skb, &sock_hash, &zero, 0); + + count = bpf_map_lookup_elem(&verdict_map, &verdict); + if (count) + (*count)++; + + return verdict; +} + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + unsigned int *count; + __u32 zero = 0; + int verdict; + + if (test_sockmap) + verdict = bpf_sk_redirect_map(skb, &sock_map, zero, + test_ingress ? BPF_F_INGRESS : 0); + else + verdict = bpf_sk_redirect_hash(skb, &sock_hash, &zero, + test_ingress ? BPF_F_INGRESS : 0); + + count = bpf_map_lookup_elem(&verdict_map, &verdict); + if (count) + (*count)++; + + return verdict; +} + +SEC("sk_msg") +int prog_msg_verdict(struct sk_msg_md *msg) +{ + unsigned int *count; + __u32 zero = 0; + int verdict; + + if (test_sockmap) + verdict = bpf_msg_redirect_map(msg, &sock_map, zero, 0); + else + verdict = bpf_msg_redirect_hash(msg, &sock_hash, &zero, 0); + + count = bpf_map_lookup_elem(&verdict_map, &verdict); + if (count) + (*count)++; + + return verdict; +} + +SEC("sk_reuseport") +int prog_reuseport(struct sk_reuseport_md *reuse) +{ + unsigned int *count; + int err, verdict; + __u32 zero = 0; + + if (test_sockmap) + err = bpf_sk_select_reuseport(reuse, &sock_map, &zero, 0); + else + err = bpf_sk_select_reuseport(reuse, &sock_hash, &zero, 0); + verdict = err ? SK_DROP : SK_PASS; + + count = bpf_map_lookup_elem(&verdict_map, &verdict); + if (count) + (*count)++; + + return verdict; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c new file mode 100644 index 0000000000..1d86a717a2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c @@ -0,0 +1,32 @@ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_tx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_msg SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_progs_query.c b/tools/testing/selftests/bpf/progs/test_sockmap_progs_query.c new file mode 100644 index 0000000000..9d58d61c0d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_progs_query.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} sock_map SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_PASS; +} + +SEC("sk_msg") +int prog_skmsg_verdict(struct sk_msg_md *msg) +{ + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c new file mode 100644 index 0000000000..3c69aa9717 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, __u64); +} sock_map SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_update.c b/tools/testing/selftests/bpf/progs/test_sockmap_update.c new file mode 100644 index 0000000000..6d64ea536e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_update.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Cloudflare +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} src SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} dst_sock_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} dst_sock_hash SEC(".maps"); + +SEC("tc") +int copy_sock_map(void *ctx) +{ + struct bpf_sock *sk; + bool failed = false; + __u32 key = 0; + + sk = bpf_map_lookup_elem(&src, &key); + if (!sk) + return SK_DROP; + + if (bpf_map_update_elem(&dst_sock_map, &key, sk, 0)) + failed = true; + + if (bpf_map_update_elem(&dst_sock_hash, &key, sk, 0)) + failed = true; + + bpf_sk_release(sk); + return failed ? SK_DROP : SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c new file mode 100644 index 0000000000..b2440a0ff4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include <linux/version.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct hmap_elem { + volatile int cnt; + struct bpf_spin_lock lock; + int test_padding; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct hmap_elem); +} hmap SEC(".maps"); + +struct cls_elem { + struct bpf_spin_lock lock; + volatile int cnt; +}; + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, struct cls_elem); +} cls_map SEC(".maps"); + +struct bpf_vqueue { + struct bpf_spin_lock lock; + /* 4 byte hole */ + unsigned long long lasttime; + int credit; + unsigned int rate; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct bpf_vqueue); +} vqueue SEC(".maps"); + +#define CREDIT_PER_NS(delta, rate) (((delta) * rate) >> 20) + +SEC("cgroup_skb/ingress") +int bpf_spin_lock_test(struct __sk_buff *skb) +{ + volatile int credit = 0, max_credit = 100, pkt_len = 64; + struct hmap_elem zero = {}, *val; + unsigned long long curtime; + struct bpf_vqueue *q; + struct cls_elem *cls; + int key = 0; + int err = 0; + + val = bpf_map_lookup_elem(&hmap, &key); + if (!val) { + bpf_map_update_elem(&hmap, &key, &zero, 0); + val = bpf_map_lookup_elem(&hmap, &key); + if (!val) { + err = 1; + goto err; + } + } + /* spin_lock in hash map run time test */ + bpf_spin_lock(&val->lock); + if (val->cnt) + val->cnt--; + else + val->cnt++; + if (val->cnt != 0 && val->cnt != 1) + err = 1; + bpf_spin_unlock(&val->lock); + + /* spin_lock in array. virtual queue demo */ + q = bpf_map_lookup_elem(&vqueue, &key); + if (!q) + goto err; + curtime = bpf_ktime_get_ns(); + bpf_spin_lock(&q->lock); + q->credit += CREDIT_PER_NS(curtime - q->lasttime, q->rate); + q->lasttime = curtime; + if (q->credit > max_credit) + q->credit = max_credit; + q->credit -= pkt_len; + credit = q->credit; + bpf_spin_unlock(&q->lock); + + __sink(credit); + + /* spin_lock in cgroup local storage */ + cls = bpf_get_local_storage(&cls_map, 0); + bpf_spin_lock(&cls->lock); + cls->cnt++; + bpf_spin_unlock(&cls->lock); + +err: + return err; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c new file mode 100644 index 0000000000..86cd183ef6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include "bpf_experimental.h" + +struct foo { + struct bpf_spin_lock lock; + int data; +}; + +struct array_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct foo); + __uint(max_entries, 1); +} array_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); + __array(values, struct array_map); +} map_of_maps SEC(".maps") = { + .values = { + [0] = &array_map, + }, +}; + +SEC(".data.A") struct bpf_spin_lock lockA; +SEC(".data.B") struct bpf_spin_lock lockB; + +SEC("?tc") +int lock_id_kptr_preserve(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_this_cpu_ptr(f); + return 0; +} + +SEC("?tc") +int lock_id_global_zero(void *ctx) +{ + bpf_this_cpu_ptr(&lockA); + return 0; +} + +SEC("?tc") +int lock_id_mapval_preserve(void *ctx) +{ + struct foo *f; + int key = 0; + + f = bpf_map_lookup_elem(&array_map, &key); + if (!f) + return 0; + bpf_this_cpu_ptr(f); + return 0; +} + +SEC("?tc") +int lock_id_innermapval_preserve(void *ctx) +{ + struct foo *f; + int key = 0; + void *map; + + map = bpf_map_lookup_elem(&map_of_maps, &key); + if (!map) + return 0; + f = bpf_map_lookup_elem(map, &key); + if (!f) + return 0; + bpf_this_cpu_ptr(f); + return 0; +} + +#define CHECK(test, A, B) \ + SEC("?tc") \ + int lock_id_mismatch_##test(void *ctx) \ + { \ + struct foo *f1, *f2, *v, *iv; \ + int key = 0; \ + void *map; \ + \ + map = bpf_map_lookup_elem(&map_of_maps, &key); \ + if (!map) \ + return 0; \ + iv = bpf_map_lookup_elem(map, &key); \ + if (!iv) \ + return 0; \ + v = bpf_map_lookup_elem(&array_map, &key); \ + if (!v) \ + return 0; \ + f1 = bpf_obj_new(typeof(*f1)); \ + if (!f1) \ + return 0; \ + f2 = bpf_obj_new(typeof(*f2)); \ + if (!f2) { \ + bpf_obj_drop(f1); \ + return 0; \ + } \ + bpf_spin_lock(A); \ + bpf_spin_unlock(B); \ + return 0; \ + } + +CHECK(kptr_kptr, &f1->lock, &f2->lock); +CHECK(kptr_global, &f1->lock, &lockA); +CHECK(kptr_mapval, &f1->lock, &v->lock); +CHECK(kptr_innermapval, &f1->lock, &iv->lock); + +CHECK(global_global, &lockA, &lockB); +CHECK(global_kptr, &lockA, &f1->lock); +CHECK(global_mapval, &lockA, &v->lock); +CHECK(global_innermapval, &lockA, &iv->lock); + +SEC("?tc") +int lock_id_mismatch_mapval_mapval(void *ctx) +{ + struct foo *f1, *f2; + int key = 0; + + f1 = bpf_map_lookup_elem(&array_map, &key); + if (!f1) + return 0; + f2 = bpf_map_lookup_elem(&array_map, &key); + if (!f2) + return 0; + + bpf_spin_lock(&f1->lock); + f1->data = 42; + bpf_spin_unlock(&f2->lock); + + return 0; +} + +CHECK(mapval_kptr, &v->lock, &f1->lock); +CHECK(mapval_global, &v->lock, &lockB); +CHECK(mapval_innermapval, &v->lock, &iv->lock); + +SEC("?tc") +int lock_id_mismatch_innermapval_innermapval1(void *ctx) +{ + struct foo *f1, *f2; + int key = 0; + void *map; + + map = bpf_map_lookup_elem(&map_of_maps, &key); + if (!map) + return 0; + f1 = bpf_map_lookup_elem(map, &key); + if (!f1) + return 0; + f2 = bpf_map_lookup_elem(map, &key); + if (!f2) + return 0; + + bpf_spin_lock(&f1->lock); + f1->data = 42; + bpf_spin_unlock(&f2->lock); + + return 0; +} + +SEC("?tc") +int lock_id_mismatch_innermapval_innermapval2(void *ctx) +{ + struct foo *f1, *f2; + int key = 0; + void *map; + + map = bpf_map_lookup_elem(&map_of_maps, &key); + if (!map) + return 0; + f1 = bpf_map_lookup_elem(map, &key); + if (!f1) + return 0; + map = bpf_map_lookup_elem(&map_of_maps, &key); + if (!map) + return 0; + f2 = bpf_map_lookup_elem(map, &key); + if (!f2) + return 0; + + bpf_spin_lock(&f1->lock); + f1->data = 42; + bpf_spin_unlock(&f2->lock); + + return 0; +} + +CHECK(innermapval_kptr, &iv->lock, &f1->lock); +CHECK(innermapval_global, &iv->lock, &lockA); +CHECK(innermapval_mapval, &iv->lock, &v->lock); + +#undef CHECK + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_stack_map.c b/tools/testing/selftests/bpf/progs/test_stack_map.c new file mode 100644 index 0000000000..31c3880e6d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_stack_map.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Politecnico di Torino +#define MAP_TYPE BPF_MAP_TYPE_STACK +#include "test_queue_stack_map.h" diff --git a/tools/testing/selftests/bpf/progs/test_stack_var_off.c b/tools/testing/selftests/bpf/progs/test_stack_var_off.c new file mode 100644 index 0000000000..665e6ae09d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_stack_var_off.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +int probe_res; + +char input[4] = {}; +int test_pid; + +SEC("tracepoint/syscalls/sys_enter_nanosleep") +int probe(void *ctx) +{ + /* This BPF program performs variable-offset reads and writes on a + * stack-allocated buffer. + */ + char stack_buf[16]; + unsigned long len; + unsigned long last; + + if ((bpf_get_current_pid_tgid() >> 32) != test_pid) + return 0; + + /* Copy the input to the stack. */ + __builtin_memcpy(stack_buf, input, 4); + + /* The first byte in the buffer indicates the length. */ + len = stack_buf[0] & 0xf; + last = (len - 1) & 0xf; + + /* Append something to the buffer. The offset where we write is not + * statically known; this is a variable-offset stack write. + */ + stack_buf[len] = 42; + + /* Index into the buffer at an unknown offset. This is a + * variable-offset stack read. + * + * Note that if it wasn't for the preceding variable-offset write, this + * read would be rejected because the stack slot cannot be verified as + * being initialized. With the preceding variable-offset write, the + * stack slot still cannot be verified, but the write inhibits the + * respective check on the reasoning that, if there was a + * variable-offset to a higher-or-equal spot, we're probably reading + * what we just wrote. + */ + probe_res = stack_buf[last]; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c new file mode 100644 index 0000000000..0c4426592a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#ifndef PERF_MAX_STACK_DEPTH +#define PERF_MAX_STACK_DEPTH 127 +#endif + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} control_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 16384); + __type(key, __u32); + __type(value, __u32); +} stackid_hmap SEC(".maps"); + +typedef struct bpf_stack_build_id stack_trace_t[PERF_MAX_STACK_DEPTH]; + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, 128); + __uint(map_flags, BPF_F_STACK_BUILD_ID); + __type(key, __u32); + __type(value, stack_trace_t); +} stackmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 128); + __type(key, __u32); + __type(value, stack_trace_t); +} stack_amap SEC(".maps"); + +SEC("kprobe/urandom_read_iter") +int oncpu(struct pt_regs *args) +{ + __u32 max_len = sizeof(struct bpf_stack_build_id) + * PERF_MAX_STACK_DEPTH; + __u32 key = 0, val = 0, *value_p; + void *stack_p; + + value_p = bpf_map_lookup_elem(&control_map, &key); + if (value_p && *value_p) + return 0; /* skip if non-zero *value_p */ + + /* The size of stackmap and stackid_hmap should be the same */ + key = bpf_get_stackid(args, &stackmap, BPF_F_USER_STACK); + if ((int)key >= 0) { + bpf_map_update_elem(&stackid_hmap, &key, &val, 0); + stack_p = bpf_map_lookup_elem(&stack_amap, &key); + if (stack_p) + bpf_get_stack(args, stack_p, max_len, + BPF_F_USER_STACK | BPF_F_USER_BUILD_ID); + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c new file mode 100644 index 0000000000..47568007b6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +#ifndef PERF_MAX_STACK_DEPTH +#define PERF_MAX_STACK_DEPTH 127 +#endif + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} control_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 16384); + __type(key, __u32); + __type(value, __u32); +} stackid_hmap SEC(".maps"); + +typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, 16384); + __type(key, __u32); + __type(value, stack_trace_t); +} stackmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 16384); + __type(key, __u32); + __type(value, stack_trace_t); +} stack_amap SEC(".maps"); + +/* taken from /sys/kernel/tracing/events/sched/sched_switch/format */ +struct sched_switch_args { + unsigned long long pad; + char prev_comm[TASK_COMM_LEN]; + int prev_pid; + int prev_prio; + long long prev_state; + char next_comm[TASK_COMM_LEN]; + int next_pid; + int next_prio; +}; + +SEC("tracepoint/sched/sched_switch") +int oncpu(struct sched_switch_args *ctx) +{ + __u32 max_len = PERF_MAX_STACK_DEPTH * sizeof(__u64); + __u32 key = 0, val = 0, *value_p; + void *stack_p; + + value_p = bpf_map_lookup_elem(&control_map, &key); + if (value_p && *value_p) + return 0; /* skip if non-zero *value_p */ + + /* The size of stackmap and stackid_hmap should be the same */ + key = bpf_get_stackid(ctx, &stackmap, 0); + if ((int)key >= 0) { + bpf_map_update_elem(&stackid_hmap, &key, &val, 0); + stack_p = bpf_map_lookup_elem(&stack_amap, &key); + if (stack_p) + bpf_get_stack(ctx, stack_p, max_len, 0); + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_static_linked1.c b/tools/testing/selftests/bpf/progs/test_static_linked1.c new file mode 100644 index 0000000000..4f0b612e16 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_static_linked1.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* 8-byte aligned .data */ +static volatile long static_var1 = 2; +static volatile int static_var2 = 3; +int var1 = -1; +/* 4-byte aligned .rodata */ +const volatile int rovar1; + +/* same "subprog" name in both files */ +static __noinline int subprog(int x) +{ + /* but different formula */ + return x * 2; +} + +SEC("raw_tp/sys_enter") +int handler1(const void *ctx) +{ + var1 = subprog(rovar1) + static_var1 + static_var2; + + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; +int VERSION SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_static_linked2.c b/tools/testing/selftests/bpf/progs/test_static_linked2.c new file mode 100644 index 0000000000..766ebd502a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_static_linked2.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* 4-byte aligned .data */ +static volatile int static_var1 = 5; +static volatile int static_var2 = 6; +int var2 = -1; +/* 8-byte aligned .rodata */ +const volatile long rovar2; + +/* same "subprog" name in both files */ +static __noinline int subprog(int x) +{ + /* but different formula */ + return x * 3; +} + +SEC("raw_tp/sys_enter") +int handler2(const void *ctx) +{ + var2 = subprog(rovar2) + static_var1 + static_var2; + + return 0; +} + +/* different name and/or type of the variable doesn't matter */ +char _license[] SEC("license") = "GPL"; +int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_subprogs.c b/tools/testing/selftests/bpf/progs/test_subprogs.c new file mode 100644 index 0000000000..a8d602d7c8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subprogs.c @@ -0,0 +1,124 @@ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +const char LICENSE[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} array SEC(".maps"); + +__noinline int sub1(int x) +{ + int key = 0; + + bpf_map_lookup_elem(&array, &key); + return x + 1; +} + +static __noinline int sub5(int v); + +__noinline int sub2(int y) +{ + return sub5(y + 2); +} + +static __noinline int sub3(int z) +{ + return z + 3 + sub1(4); +} + +static __noinline int sub4(int w) +{ + int key = 0; + + bpf_map_lookup_elem(&array, &key); + return w + sub3(5) + sub1(6); +} + +/* sub5() is an identitify function, just to test weirder functions layout and + * call patterns + */ +static __noinline int sub5(int v) +{ + return sub1(v) - 1; /* compensates sub1()'s + 1 */ +} + +/* unfortunately verifier rejects `struct task_struct *t` as an unknown pointer + * type, so we need to accept pointer as integer and then cast it inside the + * function + */ +__noinline int get_task_tgid(uintptr_t t) +{ + /* this ensures that CO-RE relocs work in multi-subprogs .text */ + return BPF_CORE_READ((struct task_struct *)(void *)t, tgid); +} + +int res1 = 0; +int res2 = 0; +int res3 = 0; +int res4 = 0; + +SEC("raw_tp/sys_enter") +int prog1(void *ctx) +{ + /* perform some CO-RE relocations to ensure they work with multi-prog + * sections correctly + */ + struct task_struct *t = (void *)bpf_get_current_task(); + + if (!BPF_CORE_READ(t, pid) || !get_task_tgid((uintptr_t)t)) + return 1; + + res1 = sub1(1) + sub3(2); /* (1 + 1) + (2 + 3 + (4 + 1)) = 12 */ + return 0; +} + +SEC("raw_tp/sys_exit") +int prog2(void *ctx) +{ + struct task_struct *t = (void *)bpf_get_current_task(); + + if (!BPF_CORE_READ(t, pid) || !get_task_tgid((uintptr_t)t)) + return 1; + + res2 = sub2(3) + sub3(4); /* (3 + 2) + (4 + 3 + (4 + 1)) = 17 */ + return 0; +} + +static int empty_callback(__u32 index, void *data) +{ + return 0; +} + +/* prog3 has the same section name as prog1 */ +SEC("raw_tp/sys_enter") +int prog3(void *ctx) +{ + struct task_struct *t = (void *)bpf_get_current_task(); + + if (!BPF_CORE_READ(t, pid) || !get_task_tgid((uintptr_t)t)) + return 1; + + /* test that ld_imm64 with BPF_PSEUDO_FUNC doesn't get blinded */ + bpf_loop(1, empty_callback, NULL, 0); + + res3 = sub3(5) + 6; /* (5 + 3 + (4 + 1)) + 6 = 19 */ + return 0; +} + +/* prog4 has the same section name as prog2 */ +SEC("raw_tp/sys_exit") +int prog4(void *ctx) +{ + struct task_struct *t = (void *)bpf_get_current_task(); + + if (!BPF_CORE_READ(t, pid) || !get_task_tgid((uintptr_t)t)) + return 1; + + res4 = sub4(7) + sub1(8); /* (7 + (5 + 3 + (4 + 1)) + (6 + 1)) + (8 + 1) = 36 */ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_subprogs_extable.c b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c new file mode 100644 index 0000000000..e2a21fbd4e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 8); + __type(key, __u32); + __type(value, __u64); +} test_array SEC(".maps"); + +unsigned int triggered; + +static __u64 test_cb(struct bpf_map *map, __u32 *key, __u64 *val, void *data) +{ + return 1; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret_subprogs, int arg, struct file *ret) +{ + *(volatile long *)ret; + *(volatile int *)&ret->f_mode; + bpf_for_each_map_elem(&test_array, test_cb, NULL, 0); + triggered++; + return 0; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret_subprogs2, int arg, struct file *ret) +{ + *(volatile long *)ret; + *(volatile int *)&ret->f_mode; + bpf_for_each_map_elem(&test_array, test_cb, NULL, 0); + triggered++; + return 0; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret_subprogs3, int arg, struct file *ret) +{ + *(volatile long *)ret; + *(volatile int *)&ret->f_mode; + bpf_for_each_map_elem(&test_array, test_cb, NULL, 0); + triggered++; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subprogs_unused.c b/tools/testing/selftests/bpf/progs/test_subprogs_unused.c new file mode 100644 index 0000000000..bc49e050d3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subprogs_unused.c @@ -0,0 +1,21 @@ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +const char LICENSE[] SEC("license") = "GPL"; + +__attribute__((unused)) __noinline int unused1(int x) +{ + return x + 1; +} + +static __attribute__((unused)) __noinline int unused2(int x) +{ + return x + 2; +} + +SEC("raw_tp/sys_enter") +int main_prog(void *ctx) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_subskeleton.c b/tools/testing/selftests/bpf/progs/test_subskeleton.c new file mode 100644 index 0000000000..0064179743 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subskeleton.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* volatile to force a read, compiler may assume 0 otherwise */ +const volatile int rovar1; +int out1; + +/* Override weak symbol in test_subskeleton_lib */ +int var5 = 5; + +extern volatile bool CONFIG_BPF_SYSCALL __kconfig; + +extern int lib_routine(void); + +SEC("raw_tp/sys_enter") +int handler1(const void *ctx) +{ + (void) CONFIG_BPF_SYSCALL; + + out1 = lib_routine() * rovar1; + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subskeleton_lib.c b/tools/testing/selftests/bpf/progs/test_subskeleton_lib.c new file mode 100644 index 0000000000..ecfafe812c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subskeleton_lib.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* volatile to force a read */ +const volatile int var1; +volatile int var2 = 1; +struct { + int var3_1; + __s64 var3_2; +} var3; +int libout1; + +extern volatile bool CONFIG_BPF_SYSCALL __kconfig; + +int var4[4]; + +__weak int var5 SEC(".data"); + +/* Fully contained within library extern-and-definition */ +extern int var6; + +int var7 SEC(".data.custom"); + +int (*fn_ptr)(void); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 16); +} map1 SEC(".maps"); + +extern struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 16); +} map2 SEC(".maps"); + +int lib_routine(void) +{ + __u32 key = 1, value = 2; + + (void) CONFIG_BPF_SYSCALL; + bpf_map_update_elem(&map2, &key, &value, BPF_ANY); + + libout1 = var1 + var2 + var3.var3_1 + var3.var3_2 + var5 + var6; + return libout1; +} + +SEC("perf_event") +int lib_perf_handler(struct pt_regs *ctx) +{ + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subskeleton_lib2.c b/tools/testing/selftests/bpf/progs/test_subskeleton_lib2.c new file mode 100644 index 0000000000..80238486b7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subskeleton_lib2.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +int var6 = 6; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 16); +} map2 SEC(".maps"); + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c new file mode 100644 index 0000000000..553a282d81 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <stdint.h> +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +/* tcp_mem sysctl has only 3 ints, but this test is doing TCP_MEM_LOOPS */ +#define TCP_MEM_LOOPS 28 /* because 30 doesn't fit into 512 bytes of stack */ +#define MAX_ULONG_STR_LEN 7 +#define MAX_VALUE_STR_LEN (TCP_MEM_LOOPS * MAX_ULONG_STR_LEN) + +const char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string"; +static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx) +{ + unsigned char i; + char name[sizeof(tcp_mem_name)]; + int ret; + + memset(name, 0, sizeof(name)); + ret = bpf_sysctl_get_name(ctx, name, sizeof(name), 0); + if (ret < 0 || ret != sizeof(tcp_mem_name) - 1) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < sizeof(tcp_mem_name); ++i) + if (name[i] != tcp_mem_name[i]) + return 0; + + return 1; +} + +SEC("cgroup/sysctl") +int sysctl_tcp_mem(struct bpf_sysctl *ctx) +{ + unsigned long tcp_mem[TCP_MEM_LOOPS] = {}; + char value[MAX_VALUE_STR_LEN]; + unsigned char i, off = 0; + /* a workaround to prevent compiler from generating + * codes verifier cannot handle yet. + */ + volatile int ret; + + if (ctx->write) + return 0; + + if (!is_tcp_mem(ctx)) + return 0; + + ret = bpf_sysctl_get_current_value(ctx, value, MAX_VALUE_STR_LEN); + if (ret < 0 || ret >= MAX_VALUE_STR_LEN) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) { + ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0, + tcp_mem + i); + if (ret <= 0 || ret > MAX_ULONG_STR_LEN) + return 0; + off += ret & MAX_ULONG_STR_LEN; + } + + return tcp_mem[0] < tcp_mem[1] && tcp_mem[1] < tcp_mem[2]; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c new file mode 100644 index 0000000000..2b64bc563a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <stdint.h> +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +/* tcp_mem sysctl has only 3 ints, but this test is doing TCP_MEM_LOOPS */ +#define TCP_MEM_LOOPS 20 /* because 30 doesn't fit into 512 bytes of stack */ +#define MAX_ULONG_STR_LEN 7 +#define MAX_VALUE_STR_LEN (TCP_MEM_LOOPS * MAX_ULONG_STR_LEN) + +const char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string_to_stress_byte_loop"; +static __attribute__((noinline)) int is_tcp_mem(struct bpf_sysctl *ctx) +{ + unsigned char i; + char name[sizeof(tcp_mem_name)]; + int ret; + + memset(name, 0, sizeof(name)); + ret = bpf_sysctl_get_name(ctx, name, sizeof(name), 0); + if (ret < 0 || ret != sizeof(tcp_mem_name) - 1) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < sizeof(tcp_mem_name); ++i) + if (name[i] != tcp_mem_name[i]) + return 0; + + return 1; +} + + +SEC("cgroup/sysctl") +int sysctl_tcp_mem(struct bpf_sysctl *ctx) +{ + unsigned long tcp_mem[TCP_MEM_LOOPS] = {}; + char value[MAX_VALUE_STR_LEN]; + unsigned char i, off = 0; + int ret; + + if (ctx->write) + return 0; + + if (!is_tcp_mem(ctx)) + return 0; + + ret = bpf_sysctl_get_current_value(ctx, value, MAX_VALUE_STR_LEN); + if (ret < 0 || ret >= MAX_VALUE_STR_LEN) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) { + ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0, + tcp_mem + i); + if (ret <= 0 || ret > MAX_ULONG_STR_LEN) + return 0; + off += ret & MAX_ULONG_STR_LEN; + } + + return tcp_mem[0] < tcp_mem[1] && tcp_mem[1] < tcp_mem[2]; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c new file mode 100644 index 0000000000..5489823c83 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <stdint.h> +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> + +/* Max supported length of a string with unsigned long in base 10 (pow2 - 1). */ +#define MAX_ULONG_STR_LEN 0xF + +/* Max supported length of sysctl value string (pow2). */ +#define MAX_VALUE_STR_LEN 0x40 + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +const char tcp_mem_name[] = "net/ipv4/tcp_mem"; +static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx) +{ + unsigned char i; + char name[sizeof(tcp_mem_name)]; + int ret; + + memset(name, 0, sizeof(name)); + ret = bpf_sysctl_get_name(ctx, name, sizeof(name), 0); + if (ret < 0 || ret != sizeof(tcp_mem_name) - 1) + return 0; + +#pragma clang loop unroll(full) + for (i = 0; i < sizeof(tcp_mem_name); ++i) + if (name[i] != tcp_mem_name[i]) + return 0; + + return 1; +} + +SEC("cgroup/sysctl") +int sysctl_tcp_mem(struct bpf_sysctl *ctx) +{ + unsigned long tcp_mem[3] = {0, 0, 0}; + char value[MAX_VALUE_STR_LEN]; + unsigned char i, off = 0; + volatile int ret; + + if (ctx->write) + return 0; + + if (!is_tcp_mem(ctx)) + return 0; + + ret = bpf_sysctl_get_current_value(ctx, value, MAX_VALUE_STR_LEN); + if (ret < 0 || ret >= MAX_VALUE_STR_LEN) + return 0; + +#pragma clang loop unroll(full) + for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) { + ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0, + tcp_mem + i); + if (ret <= 0 || ret > MAX_ULONG_STR_LEN) + return 0; + off += ret & MAX_ULONG_STR_LEN; + } + + + return tcp_mem[0] < tcp_mem[1] && tcp_mem[1] < tcp_mem[2]; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_task_pt_regs.c b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c new file mode 100644 index 0000000000..1926facba1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define PT_REGS_SIZE sizeof(struct pt_regs) + +/* + * The kernel struct pt_regs isn't exported in its entirety to userspace. + * Pass it as an array to task_pt_regs.c + */ +char current_regs[PT_REGS_SIZE] = {}; +char ctx_regs[PT_REGS_SIZE] = {}; +int uprobe_res = 0; + +SEC("uprobe") +int handle_uprobe(struct pt_regs *ctx) +{ + struct task_struct *current; + struct pt_regs *regs; + + current = bpf_get_current_task_btf(); + regs = (struct pt_regs *) bpf_task_pt_regs(current); + if (bpf_probe_read_kernel(current_regs, PT_REGS_SIZE, regs)) + return 0; + if (bpf_probe_read_kernel(ctx_regs, PT_REGS_SIZE, ctx)) + return 0; + + /* Prove that uprobe was run */ + uprobe_res = 1; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c new file mode 100644 index 0000000000..56cdc0a553 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Bytedance */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +long bpf_task_under_cgroup(struct task_struct *task, struct cgroup *ancestor) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; +struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; + +const volatile int local_pid; +const volatile __u64 cgid; +int remote_pid; + +SEC("tp_btf/task_newtask") +int BPF_PROG(handle__task_newtask, struct task_struct *task, u64 clone_flags) +{ + struct cgroup *cgrp = NULL; + struct task_struct *acquired; + + if (local_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + acquired = bpf_task_acquire(task); + if (!acquired) + return 0; + + if (local_pid == acquired->tgid) + goto out; + + cgrp = bpf_cgroup_from_id(cgid); + if (!cgrp) + goto out; + + if (bpf_task_under_cgroup(acquired, cgrp)) + remote_pid = acquired->tgid; + +out: + if (cgrp) + bpf_cgroup_release(cgrp); + bpf_task_release(acquired); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_bpf.c b/tools/testing/selftests/bpf/progs/test_tc_bpf.c new file mode 100644 index 0000000000..ef7da41963 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_bpf.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <linux/if_ether.h> +#include <linux/ip.h> + +/* Dummy prog to test TC-BPF API */ + +SEC("tc") +int cls(struct __sk_buff *skb) +{ + return 0; +} + +/* Prog to verify tc-bpf without cap_sys_admin and cap_perfmon */ +SEC("tcx/ingress") +int pkt_ptr(struct __sk_buff *skb) +{ + struct iphdr *iph = (void *)(long)skb->data + sizeof(struct ethhdr); + + if ((long)(iph + 1) > (long)skb->data_end) + return 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_tc_dtime.c b/tools/testing/selftests/bpf/progs/test_tc_dtime.c new file mode 100644 index 0000000000..74ec09f040 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_dtime.c @@ -0,0 +1,397 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2022 Meta + +#include <stddef.h> +#include <stdint.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include <linux/stddef.h> +#include <linux/pkt_cls.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +/* veth_src --- veth_src_fwd --- veth_det_fwd --- veth_dst + * | | + * ns_src | ns_fwd | ns_dst + * + * ns_src and ns_dst: ENDHOST namespace + * ns_fwd: Fowarding namespace + */ + +#define ctx_ptr(field) (void *)(long)(field) + +#define ip4_src __bpf_htonl(0xac100164) /* 172.16.1.100 */ +#define ip4_dst __bpf_htonl(0xac100264) /* 172.16.2.100 */ + +#define ip6_src { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x01, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe } +#define ip6_dst { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x02, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe } + +#define v6_equal(a, b) (a.s6_addr32[0] == b.s6_addr32[0] && \ + a.s6_addr32[1] == b.s6_addr32[1] && \ + a.s6_addr32[2] == b.s6_addr32[2] && \ + a.s6_addr32[3] == b.s6_addr32[3]) + +volatile const __u32 IFINDEX_SRC; +volatile const __u32 IFINDEX_DST; + +#define EGRESS_ENDHOST_MAGIC 0x0b9fbeef +#define INGRESS_FWDNS_MAGIC 0x1b9fbeef +#define EGRESS_FWDNS_MAGIC 0x2b9fbeef + +enum { + INGRESS_FWDNS_P100, + INGRESS_FWDNS_P101, + EGRESS_FWDNS_P100, + EGRESS_FWDNS_P101, + INGRESS_ENDHOST, + EGRESS_ENDHOST, + SET_DTIME, + __MAX_CNT, +}; + +enum { + TCP_IP6_CLEAR_DTIME, + TCP_IP4, + TCP_IP6, + UDP_IP4, + UDP_IP6, + TCP_IP4_RT_FWD, + TCP_IP6_RT_FWD, + UDP_IP4_RT_FWD, + UDP_IP6_RT_FWD, + UKN_TEST, + __NR_TESTS, +}; + +enum { + SRC_NS = 1, + DST_NS, +}; + +__u32 dtimes[__NR_TESTS][__MAX_CNT] = {}; +__u32 errs[__NR_TESTS][__MAX_CNT] = {}; +__u32 test = 0; + +static void inc_dtimes(__u32 idx) +{ + if (test < __NR_TESTS) + dtimes[test][idx]++; + else + dtimes[UKN_TEST][idx]++; +} + +static void inc_errs(__u32 idx) +{ + if (test < __NR_TESTS) + errs[test][idx]++; + else + errs[UKN_TEST][idx]++; +} + +static int skb_proto(int type) +{ + return type & 0xff; +} + +static int skb_ns(int type) +{ + return (type >> 8) & 0xff; +} + +static bool fwdns_clear_dtime(void) +{ + return test == TCP_IP6_CLEAR_DTIME; +} + +static bool bpf_fwd(void) +{ + return test < TCP_IP4_RT_FWD; +} + +static __u8 get_proto(void) +{ + switch (test) { + case UDP_IP4: + case UDP_IP6: + case UDP_IP4_RT_FWD: + case UDP_IP6_RT_FWD: + return IPPROTO_UDP; + default: + return IPPROTO_TCP; + } +} + +/* -1: parse error: TC_ACT_SHOT + * 0: not testing traffic: TC_ACT_OK + * >0: first byte is the inet_proto, second byte has the netns + * of the sender + */ +static int skb_get_type(struct __sk_buff *skb) +{ + __u16 dst_ns_port = __bpf_htons(50000 + test); + void *data_end = ctx_ptr(skb->data_end); + void *data = ctx_ptr(skb->data); + __u8 inet_proto = 0, ns = 0; + struct ipv6hdr *ip6h; + __u16 sport, dport; + struct iphdr *iph; + struct tcphdr *th; + struct udphdr *uh; + void *trans; + + switch (skb->protocol) { + case __bpf_htons(ETH_P_IP): + iph = data + sizeof(struct ethhdr); + if (iph + 1 > data_end) + return -1; + if (iph->saddr == ip4_src) + ns = SRC_NS; + else if (iph->saddr == ip4_dst) + ns = DST_NS; + inet_proto = iph->protocol; + trans = iph + 1; + break; + case __bpf_htons(ETH_P_IPV6): + ip6h = data + sizeof(struct ethhdr); + if (ip6h + 1 > data_end) + return -1; + if (v6_equal(ip6h->saddr, (struct in6_addr){{ip6_src}})) + ns = SRC_NS; + else if (v6_equal(ip6h->saddr, (struct in6_addr){{ip6_dst}})) + ns = DST_NS; + inet_proto = ip6h->nexthdr; + trans = ip6h + 1; + break; + default: + return 0; + } + + /* skb is not from src_ns or dst_ns. + * skb is not the testing IPPROTO. + */ + if (!ns || inet_proto != get_proto()) + return 0; + + switch (inet_proto) { + case IPPROTO_TCP: + th = trans; + if (th + 1 > data_end) + return -1; + sport = th->source; + dport = th->dest; + break; + case IPPROTO_UDP: + uh = trans; + if (uh + 1 > data_end) + return -1; + sport = uh->source; + dport = uh->dest; + break; + default: + return 0; + } + + /* The skb is the testing traffic */ + if ((ns == SRC_NS && dport == dst_ns_port) || + (ns == DST_NS && sport == dst_ns_port)) + return (ns << 8 | inet_proto); + + return 0; +} + +/* format: direction@iface@netns + * egress@veth_(src|dst)@ns_(src|dst) + */ +SEC("tc") +int egress_host(struct __sk_buff *skb) +{ + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1) + return TC_ACT_SHOT; + if (!skb_type) + return TC_ACT_OK; + + if (skb_proto(skb_type) == IPPROTO_TCP) { + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO && + skb->tstamp) + inc_dtimes(EGRESS_ENDHOST); + else + inc_errs(EGRESS_ENDHOST); + } else { + if (skb->tstamp_type == BPF_SKB_TSTAMP_UNSPEC && + skb->tstamp) + inc_dtimes(EGRESS_ENDHOST); + else + inc_errs(EGRESS_ENDHOST); + } + + skb->tstamp = EGRESS_ENDHOST_MAGIC; + + return TC_ACT_OK; +} + +/* ingress@veth_(src|dst)@ns_(src|dst) */ +SEC("tc") +int ingress_host(struct __sk_buff *skb) +{ + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1) + return TC_ACT_SHOT; + if (!skb_type) + return TC_ACT_OK; + + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO && + skb->tstamp == EGRESS_FWDNS_MAGIC) + inc_dtimes(INGRESS_ENDHOST); + else + inc_errs(INGRESS_ENDHOST); + + return TC_ACT_OK; +} + +/* ingress@veth_(src|dst)_fwd@ns_fwd priority 100 */ +SEC("tc") +int ingress_fwdns_prio100(struct __sk_buff *skb) +{ + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1) + return TC_ACT_SHOT; + if (!skb_type) + return TC_ACT_OK; + + /* delivery_time is only available to the ingress + * if the tc-bpf checks the skb->tstamp_type. + */ + if (skb->tstamp == EGRESS_ENDHOST_MAGIC) + inc_errs(INGRESS_FWDNS_P100); + + if (fwdns_clear_dtime()) + skb->tstamp = 0; + + return TC_ACT_UNSPEC; +} + +/* egress@veth_(src|dst)_fwd@ns_fwd priority 100 */ +SEC("tc") +int egress_fwdns_prio100(struct __sk_buff *skb) +{ + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1) + return TC_ACT_SHOT; + if (!skb_type) + return TC_ACT_OK; + + /* delivery_time is always available to egress even + * the tc-bpf did not use the tstamp_type. + */ + if (skb->tstamp == INGRESS_FWDNS_MAGIC) + inc_dtimes(EGRESS_FWDNS_P100); + else + inc_errs(EGRESS_FWDNS_P100); + + if (fwdns_clear_dtime()) + skb->tstamp = 0; + + return TC_ACT_UNSPEC; +} + +/* ingress@veth_(src|dst)_fwd@ns_fwd priority 101 */ +SEC("tc") +int ingress_fwdns_prio101(struct __sk_buff *skb) +{ + __u64 expected_dtime = EGRESS_ENDHOST_MAGIC; + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1 || !skb_type) + /* Should have handled in prio100 */ + return TC_ACT_SHOT; + + if (skb_proto(skb_type) == IPPROTO_UDP) + expected_dtime = 0; + + if (skb->tstamp_type) { + if (fwdns_clear_dtime() || + skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO || + skb->tstamp != expected_dtime) + inc_errs(INGRESS_FWDNS_P101); + else + inc_dtimes(INGRESS_FWDNS_P101); + } else { + if (!fwdns_clear_dtime() && expected_dtime) + inc_errs(INGRESS_FWDNS_P101); + } + + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) { + skb->tstamp = INGRESS_FWDNS_MAGIC; + } else { + if (bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_DELIVERY_MONO)) + inc_errs(SET_DTIME); + if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_UNSPEC)) + inc_errs(SET_DTIME); + } + + if (skb_ns(skb_type) == SRC_NS) + return bpf_fwd() ? + bpf_redirect_neigh(IFINDEX_DST, NULL, 0, 0) : TC_ACT_OK; + else + return bpf_fwd() ? + bpf_redirect_neigh(IFINDEX_SRC, NULL, 0, 0) : TC_ACT_OK; +} + +/* egress@veth_(src|dst)_fwd@ns_fwd priority 101 */ +SEC("tc") +int egress_fwdns_prio101(struct __sk_buff *skb) +{ + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1 || !skb_type) + /* Should have handled in prio100 */ + return TC_ACT_SHOT; + + if (skb->tstamp_type) { + if (fwdns_clear_dtime() || + skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO || + skb->tstamp != INGRESS_FWDNS_MAGIC) + inc_errs(EGRESS_FWDNS_P101); + else + inc_dtimes(EGRESS_FWDNS_P101); + } else { + if (!fwdns_clear_dtime()) + inc_errs(EGRESS_FWDNS_P101); + } + + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) { + skb->tstamp = EGRESS_FWDNS_MAGIC; + } else { + if (bpf_skb_set_tstamp(skb, EGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_DELIVERY_MONO)) + inc_errs(SET_DTIME); + if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_UNSPEC)) + inc_errs(SET_DTIME); + } + + return TC_ACT_OK; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_edt.c b/tools/testing/selftests/bpf/progs/test_tc_edt.c new file mode 100644 index 0000000000..950a70b61e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_edt.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdint.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/stddef.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/pkt_cls.h> +#include <linux/tcp.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +/* the maximum delay we are willing to add (drop packets beyond that) */ +#define TIME_HORIZON_NS (2000 * 1000 * 1000) +#define NS_PER_SEC 1000000000 +#define ECN_HORIZON_NS 5000000 +#define THROTTLE_RATE_BPS (5 * 1000 * 1000) + +/* flow_key => last_tstamp timestamp used */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, uint32_t); + __type(value, uint64_t); + __uint(max_entries, 1); +} flow_map SEC(".maps"); + +static inline int throttle_flow(struct __sk_buff *skb) +{ + int key = 0; + uint64_t *last_tstamp = bpf_map_lookup_elem(&flow_map, &key); + uint64_t delay_ns = ((uint64_t)skb->len) * NS_PER_SEC / + THROTTLE_RATE_BPS; + uint64_t now = bpf_ktime_get_ns(); + uint64_t tstamp, next_tstamp = 0; + + if (last_tstamp) + next_tstamp = *last_tstamp + delay_ns; + + tstamp = skb->tstamp; + if (tstamp < now) + tstamp = now; + + /* should we throttle? */ + if (next_tstamp <= tstamp) { + if (bpf_map_update_elem(&flow_map, &key, &tstamp, BPF_ANY)) + return TC_ACT_SHOT; + return TC_ACT_OK; + } + + /* do not queue past the time horizon */ + if (next_tstamp - now >= TIME_HORIZON_NS) + return TC_ACT_SHOT; + + /* set ecn bit, if needed */ + if (next_tstamp - now >= ECN_HORIZON_NS) + bpf_skb_ecn_set_ce(skb); + + if (bpf_map_update_elem(&flow_map, &key, &next_tstamp, BPF_EXIST)) + return TC_ACT_SHOT; + skb->tstamp = next_tstamp; + + return TC_ACT_OK; +} + +static inline int handle_tcp(struct __sk_buff *skb, struct tcphdr *tcp) +{ + void *data_end = (void *)(long)skb->data_end; + + /* drop malformed packets */ + if ((void *)(tcp + 1) > data_end) + return TC_ACT_SHOT; + + if (tcp->dest == bpf_htons(9000)) + return throttle_flow(skb); + + return TC_ACT_OK; +} + +static inline int handle_ipv4(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct iphdr *iph; + uint32_t ihl; + + /* drop malformed packets */ + if (data + sizeof(struct ethhdr) > data_end) + return TC_ACT_SHOT; + iph = (struct iphdr *)(data + sizeof(struct ethhdr)); + if ((void *)(iph + 1) > data_end) + return TC_ACT_SHOT; + ihl = iph->ihl * 4; + if (((void *)iph) + ihl > data_end) + return TC_ACT_SHOT; + + if (iph->protocol == IPPROTO_TCP) + return handle_tcp(skb, (struct tcphdr *)(((void *)iph) + ihl)); + + return TC_ACT_OK; +} + +SEC("cls_test") int tc_prog(struct __sk_buff *skb) +{ + if (skb->protocol == bpf_htons(ETH_P_IP)) + return handle_ipv4(skb); + + return TC_ACT_OK; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c new file mode 100644 index 0000000000..30e7124c49 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_link.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char LICENSE[] SEC("license") = "GPL"; + +bool seen_tc1; +bool seen_tc2; +bool seen_tc3; +bool seen_tc4; +bool seen_tc5; +bool seen_tc6; + +SEC("tc/ingress") +int tc1(struct __sk_buff *skb) +{ + seen_tc1 = true; + return TCX_NEXT; +} + +SEC("tc/egress") +int tc2(struct __sk_buff *skb) +{ + seen_tc2 = true; + return TCX_NEXT; +} + +SEC("tc/egress") +int tc3(struct __sk_buff *skb) +{ + seen_tc3 = true; + return TCX_NEXT; +} + +SEC("tc/egress") +int tc4(struct __sk_buff *skb) +{ + seen_tc4 = true; + return TCX_NEXT; +} + +SEC("tc/egress") +int tc5(struct __sk_buff *skb) +{ + seen_tc5 = true; + return TCX_PASS; +} + +SEC("tc/egress") +int tc6(struct __sk_buff *skb) +{ + seen_tc6 = true; + return TCX_PASS; +} diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh.c b/tools/testing/selftests/bpf/progs/test_tc_neigh.c new file mode 100644 index 0000000000..de15155f26 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stddef.h> +#include <stdint.h> +#include <stdbool.h> + +#include <linux/bpf.h> +#include <linux/stddef.h> +#include <linux/pkt_cls.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#ifndef ctx_ptr +# define ctx_ptr(field) (void *)(long)(field) +#endif + +#define ip4_src 0xac100164 /* 172.16.1.100 */ +#define ip4_dst 0xac100264 /* 172.16.2.100 */ + +#define ip6_src { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x01, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe } +#define ip6_dst { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x02, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe } + +#ifndef v6_equal +# define v6_equal(a, b) (a.s6_addr32[0] == b.s6_addr32[0] && \ + a.s6_addr32[1] == b.s6_addr32[1] && \ + a.s6_addr32[2] == b.s6_addr32[2] && \ + a.s6_addr32[3] == b.s6_addr32[3]) +#endif + +volatile const __u32 IFINDEX_SRC; +volatile const __u32 IFINDEX_DST; + +static __always_inline bool is_remote_ep_v4(struct __sk_buff *skb, + __be32 addr) +{ + void *data_end = ctx_ptr(skb->data_end); + void *data = ctx_ptr(skb->data); + struct iphdr *ip4h; + + if (data + sizeof(struct ethhdr) > data_end) + return false; + + ip4h = (struct iphdr *)(data + sizeof(struct ethhdr)); + if ((void *)(ip4h + 1) > data_end) + return false; + + return ip4h->daddr == addr; +} + +static __always_inline bool is_remote_ep_v6(struct __sk_buff *skb, + struct in6_addr addr) +{ + void *data_end = ctx_ptr(skb->data_end); + void *data = ctx_ptr(skb->data); + struct ipv6hdr *ip6h; + + if (data + sizeof(struct ethhdr) > data_end) + return false; + + ip6h = (struct ipv6hdr *)(data + sizeof(struct ethhdr)); + if ((void *)(ip6h + 1) > data_end) + return false; + + return v6_equal(ip6h->daddr, addr); +} + +SEC("tc") +int tc_chk(struct __sk_buff *skb) +{ + void *data_end = ctx_ptr(skb->data_end); + void *data = ctx_ptr(skb->data); + __u32 *raw = data; + + if (data + sizeof(struct ethhdr) > data_end) + return TC_ACT_SHOT; + + return !raw[0] && !raw[1] && !raw[2] ? TC_ACT_SHOT : TC_ACT_OK; +} + +SEC("tc") +int tc_dst(struct __sk_buff *skb) +{ + __u8 zero[ETH_ALEN * 2]; + bool redirect = false; + + switch (skb->protocol) { + case __bpf_constant_htons(ETH_P_IP): + redirect = is_remote_ep_v4(skb, __bpf_constant_htonl(ip4_src)); + break; + case __bpf_constant_htons(ETH_P_IPV6): + redirect = is_remote_ep_v6(skb, (struct in6_addr){{ip6_src}}); + break; + } + + if (!redirect) + return TC_ACT_OK; + + __builtin_memset(&zero, 0, sizeof(zero)); + if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0) + return TC_ACT_SHOT; + + return bpf_redirect_neigh(IFINDEX_SRC, NULL, 0, 0); +} + +SEC("tc") +int tc_src(struct __sk_buff *skb) +{ + __u8 zero[ETH_ALEN * 2]; + bool redirect = false; + + switch (skb->protocol) { + case __bpf_constant_htons(ETH_P_IP): + redirect = is_remote_ep_v4(skb, __bpf_constant_htonl(ip4_dst)); + break; + case __bpf_constant_htons(ETH_P_IPV6): + redirect = is_remote_ep_v6(skb, (struct in6_addr){{ip6_dst}}); + break; + } + + if (!redirect) + return TC_ACT_OK; + + __builtin_memset(&zero, 0, sizeof(zero)); + if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0) + return TC_ACT_SHOT; + + return bpf_redirect_neigh(IFINDEX_DST, NULL, 0, 0); +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c new file mode 100644 index 0000000000..ec4cce1936 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdint.h> +#include <stdbool.h> +#include <stddef.h> + +#include <linux/bpf.h> +#include <linux/stddef.h> +#include <linux/pkt_cls.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#ifndef ctx_ptr +# define ctx_ptr(field) (void *)(long)(field) +#endif + +#define AF_INET 2 +#define AF_INET6 10 + +static __always_inline int fill_fib_params_v4(struct __sk_buff *skb, + struct bpf_fib_lookup *fib_params) +{ + void *data_end = ctx_ptr(skb->data_end); + void *data = ctx_ptr(skb->data); + struct iphdr *ip4h; + + if (data + sizeof(struct ethhdr) > data_end) + return -1; + + ip4h = (struct iphdr *)(data + sizeof(struct ethhdr)); + if ((void *)(ip4h + 1) > data_end) + return -1; + + fib_params->family = AF_INET; + fib_params->tos = ip4h->tos; + fib_params->l4_protocol = ip4h->protocol; + fib_params->sport = 0; + fib_params->dport = 0; + fib_params->tot_len = bpf_ntohs(ip4h->tot_len); + fib_params->ipv4_src = ip4h->saddr; + fib_params->ipv4_dst = ip4h->daddr; + + return 0; +} + +static __always_inline int fill_fib_params_v6(struct __sk_buff *skb, + struct bpf_fib_lookup *fib_params) +{ + struct in6_addr *src = (struct in6_addr *)fib_params->ipv6_src; + struct in6_addr *dst = (struct in6_addr *)fib_params->ipv6_dst; + void *data_end = ctx_ptr(skb->data_end); + void *data = ctx_ptr(skb->data); + struct ipv6hdr *ip6h; + + if (data + sizeof(struct ethhdr) > data_end) + return -1; + + ip6h = (struct ipv6hdr *)(data + sizeof(struct ethhdr)); + if ((void *)(ip6h + 1) > data_end) + return -1; + + fib_params->family = AF_INET6; + fib_params->flowinfo = 0; + fib_params->l4_protocol = ip6h->nexthdr; + fib_params->sport = 0; + fib_params->dport = 0; + fib_params->tot_len = bpf_ntohs(ip6h->payload_len); + *src = ip6h->saddr; + *dst = ip6h->daddr; + + return 0; +} + +SEC("tc") +int tc_chk(struct __sk_buff *skb) +{ + void *data_end = ctx_ptr(skb->data_end); + void *data = ctx_ptr(skb->data); + __u32 *raw = data; + + if (data + sizeof(struct ethhdr) > data_end) + return TC_ACT_SHOT; + + return !raw[0] && !raw[1] && !raw[2] ? TC_ACT_SHOT : TC_ACT_OK; +} + +static __always_inline int tc_redir(struct __sk_buff *skb) +{ + struct bpf_fib_lookup fib_params = { .ifindex = skb->ingress_ifindex }; + __u8 zero[ETH_ALEN * 2]; + int ret = -1; + + switch (skb->protocol) { + case __bpf_constant_htons(ETH_P_IP): + ret = fill_fib_params_v4(skb, &fib_params); + break; + case __bpf_constant_htons(ETH_P_IPV6): + ret = fill_fib_params_v6(skb, &fib_params); + break; + } + + if (ret) + return TC_ACT_OK; + + ret = bpf_fib_lookup(skb, &fib_params, sizeof(fib_params), 0); + if (ret == BPF_FIB_LKUP_RET_NOT_FWDED || ret < 0) + return TC_ACT_OK; + + __builtin_memset(&zero, 0, sizeof(zero)); + if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0) + return TC_ACT_SHOT; + + if (ret == BPF_FIB_LKUP_RET_NO_NEIGH) { + struct bpf_redir_neigh nh_params = {}; + + nh_params.nh_family = fib_params.family; + __builtin_memcpy(&nh_params.ipv6_nh, &fib_params.ipv6_dst, + sizeof(nh_params.ipv6_nh)); + + return bpf_redirect_neigh(fib_params.ifindex, &nh_params, + sizeof(nh_params), 0); + + } else if (ret == BPF_FIB_LKUP_RET_SUCCESS) { + void *data_end = ctx_ptr(skb->data_end); + struct ethhdr *eth = ctx_ptr(skb->data); + + if (eth + 1 > data_end) + return TC_ACT_SHOT; + + __builtin_memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN); + __builtin_memcpy(eth->h_source, fib_params.smac, ETH_ALEN); + + return bpf_redirect(fib_params.ifindex, 0); + } + + return TC_ACT_SHOT; +} + +/* these are identical, but keep them separate for compatibility with the + * section names expected by test_tc_redirect.sh + */ +SEC("tc") +int tc_dst(struct __sk_buff *skb) +{ + return tc_redir(skb); +} + +SEC("tc") +int tc_src(struct __sk_buff *skb) +{ + return tc_redir(skb); +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_peer.c b/tools/testing/selftests/bpf/progs/test_tc_peer.c new file mode 100644 index 0000000000..365eacb5dc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_peer.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdint.h> +#include <stdbool.h> + +#include <linux/bpf.h> +#include <linux/stddef.h> +#include <linux/pkt_cls.h> +#include <linux/if_ether.h> +#include <linux/ip.h> + +#include <bpf/bpf_helpers.h> + +volatile const __u32 IFINDEX_SRC; +volatile const __u32 IFINDEX_DST; + +static const __u8 src_mac[] = {0x00, 0x11, 0x22, 0x33, 0x44, 0x55}; +static const __u8 dst_mac[] = {0x00, 0x22, 0x33, 0x44, 0x55, 0x66}; + +SEC("tc") +int tc_chk(struct __sk_buff *skb) +{ + return TC_ACT_SHOT; +} + +SEC("tc") +int tc_dst(struct __sk_buff *skb) +{ + return bpf_redirect_peer(IFINDEX_SRC, 0); +} + +SEC("tc") +int tc_src(struct __sk_buff *skb) +{ + return bpf_redirect_peer(IFINDEX_DST, 0); +} + +SEC("tc") +int tc_dst_l3(struct __sk_buff *skb) +{ + return bpf_redirect(IFINDEX_SRC, 0); +} + +SEC("tc") +int tc_src_l3(struct __sk_buff *skb) +{ + __u16 proto = skb->protocol; + + if (bpf_skb_change_head(skb, ETH_HLEN, 0) != 0) + return TC_ACT_SHOT; + + if (bpf_skb_store_bytes(skb, 0, &src_mac, ETH_ALEN, 0) != 0) + return TC_ACT_SHOT; + + if (bpf_skb_store_bytes(skb, ETH_ALEN, &dst_mac, ETH_ALEN, 0) != 0) + return TC_ACT_SHOT; + + if (bpf_skb_store_bytes(skb, ETH_ALEN + ETH_ALEN, &proto, sizeof(__u16), 0) != 0) + return TC_ACT_SHOT; + + return bpf_redirect_peer(IFINDEX_DST, 0); +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c new file mode 100644 index 0000000000..e6e678aa98 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c @@ -0,0 +1,707 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* In-place tunneling */ + +#include <stdbool.h> +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/mpls.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/pkt_cls.h> +#include <linux/types.h> + +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +static const int cfg_port = 8000; + +static const int cfg_udp_src = 20000; + +#define L2_PAD_SZ (sizeof(struct vxlanhdr) + ETH_HLEN) + +#define UDP_PORT 5555 +#define MPLS_OVER_UDP_PORT 6635 +#define ETH_OVER_UDP_PORT 7777 +#define VXLAN_UDP_PORT 8472 + +#define EXTPROTO_VXLAN 0x1 + +#define VXLAN_N_VID (1u << 24) +#define VXLAN_VNI_MASK bpf_htonl((VXLAN_N_VID - 1) << 8) +#define VXLAN_FLAGS 0x8 +#define VXLAN_VNI 1 + +#ifndef NEXTHDR_DEST +#define NEXTHDR_DEST 60 +#endif + +/* MPLS label 1000 with S bit (last label) set and ttl of 255. */ +static const __u32 mpls_label = __bpf_constant_htonl(1000 << 12 | + MPLS_LS_S_MASK | 0xff); + +struct vxlanhdr { + __be32 vx_flags; + __be32 vx_vni; +} __attribute__((packed)); + +struct gre_hdr { + __be16 flags; + __be16 protocol; +} __attribute__((packed)); + +union l4hdr { + struct udphdr udp; + struct gre_hdr gre; +}; + +struct v4hdr { + struct iphdr ip; + union l4hdr l4hdr; + __u8 pad[L2_PAD_SZ]; /* space for L2 header / vxlan header ... */ +} __attribute__((packed)); + +struct v6hdr { + struct ipv6hdr ip; + union l4hdr l4hdr; + __u8 pad[L2_PAD_SZ]; /* space for L2 header / vxlan header ... */ +} __attribute__((packed)); + +static __always_inline void set_ipv4_csum(struct iphdr *iph) +{ + __u16 *iph16 = (__u16 *)iph; + __u32 csum; + int i; + + iph->check = 0; + +#pragma clang loop unroll(full) + for (i = 0, csum = 0; i < sizeof(*iph) >> 1; i++) + csum += *iph16++; + + iph->check = ~((csum & 0xffff) + (csum >> 16)); +} + +static __always_inline int __encap_ipv4(struct __sk_buff *skb, __u8 encap_proto, + __u16 l2_proto, __u16 ext_proto) +{ + __u16 udp_dst = UDP_PORT; + struct iphdr iph_inner; + struct v4hdr h_outer; + struct tcphdr tcph; + int olen, l2_len; + __u8 *l2_hdr = NULL; + int tcp_off; + __u64 flags; + + /* Most tests encapsulate a packet into a tunnel with the same + * network protocol, and derive the outer header fields from + * the inner header. + * + * The 6in4 case tests different inner and outer protocols. As + * the inner is ipv6, but the outer expects an ipv4 header as + * input, manually build a struct iphdr based on the ipv6hdr. + */ + if (encap_proto == IPPROTO_IPV6) { + const __u32 saddr = (192 << 24) | (168 << 16) | (1 << 8) | 1; + const __u32 daddr = (192 << 24) | (168 << 16) | (1 << 8) | 2; + struct ipv6hdr iph6_inner; + + /* Read the IPv6 header */ + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph6_inner, + sizeof(iph6_inner)) < 0) + return TC_ACT_OK; + + /* Derive the IPv4 header fields from the IPv6 header */ + memset(&iph_inner, 0, sizeof(iph_inner)); + iph_inner.version = 4; + iph_inner.ihl = 5; + iph_inner.tot_len = bpf_htons(sizeof(iph6_inner) + + bpf_ntohs(iph6_inner.payload_len)); + iph_inner.ttl = iph6_inner.hop_limit - 1; + iph_inner.protocol = iph6_inner.nexthdr; + iph_inner.saddr = __bpf_constant_htonl(saddr); + iph_inner.daddr = __bpf_constant_htonl(daddr); + + tcp_off = sizeof(iph6_inner); + } else { + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner, + sizeof(iph_inner)) < 0) + return TC_ACT_OK; + + tcp_off = sizeof(iph_inner); + } + + /* filter only packets we want */ + if (iph_inner.ihl != 5 || iph_inner.protocol != IPPROTO_TCP) + return TC_ACT_OK; + + if (bpf_skb_load_bytes(skb, ETH_HLEN + tcp_off, + &tcph, sizeof(tcph)) < 0) + return TC_ACT_OK; + + if (tcph.dest != __bpf_constant_htons(cfg_port)) + return TC_ACT_OK; + + olen = sizeof(h_outer.ip); + l2_len = 0; + + flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV4; + + switch (l2_proto) { + case ETH_P_MPLS_UC: + l2_len = sizeof(mpls_label); + udp_dst = MPLS_OVER_UDP_PORT; + break; + case ETH_P_TEB: + l2_len = ETH_HLEN; + if (ext_proto & EXTPROTO_VXLAN) { + udp_dst = VXLAN_UDP_PORT; + l2_len += sizeof(struct vxlanhdr); + } else + udp_dst = ETH_OVER_UDP_PORT; + break; + } + flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len); + + switch (encap_proto) { + case IPPROTO_GRE: + flags |= BPF_F_ADJ_ROOM_ENCAP_L4_GRE; + olen += sizeof(h_outer.l4hdr.gre); + h_outer.l4hdr.gre.protocol = bpf_htons(l2_proto); + h_outer.l4hdr.gre.flags = 0; + break; + case IPPROTO_UDP: + flags |= BPF_F_ADJ_ROOM_ENCAP_L4_UDP; + olen += sizeof(h_outer.l4hdr.udp); + h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src); + h_outer.l4hdr.udp.dest = bpf_htons(udp_dst); + h_outer.l4hdr.udp.check = 0; + h_outer.l4hdr.udp.len = bpf_htons(bpf_ntohs(iph_inner.tot_len) + + sizeof(h_outer.l4hdr.udp) + + l2_len); + break; + case IPPROTO_IPIP: + case IPPROTO_IPV6: + break; + default: + return TC_ACT_OK; + } + + /* add L2 encap (if specified) */ + l2_hdr = (__u8 *)&h_outer + olen; + switch (l2_proto) { + case ETH_P_MPLS_UC: + *(__u32 *)l2_hdr = mpls_label; + break; + case ETH_P_TEB: + flags |= BPF_F_ADJ_ROOM_ENCAP_L2_ETH; + + if (ext_proto & EXTPROTO_VXLAN) { + struct vxlanhdr *vxlan_hdr = (struct vxlanhdr *)l2_hdr; + + vxlan_hdr->vx_flags = VXLAN_FLAGS; + vxlan_hdr->vx_vni = bpf_htonl((VXLAN_VNI & VXLAN_VNI_MASK) << 8); + + l2_hdr += sizeof(struct vxlanhdr); + } + + if (bpf_skb_load_bytes(skb, 0, l2_hdr, ETH_HLEN)) + return TC_ACT_SHOT; + + break; + } + olen += l2_len; + + /* add room between mac and network header */ + if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags)) + return TC_ACT_SHOT; + + /* prepare new outer network header */ + h_outer.ip = iph_inner; + h_outer.ip.tot_len = bpf_htons(olen + + bpf_ntohs(h_outer.ip.tot_len)); + h_outer.ip.protocol = encap_proto; + + set_ipv4_csum((void *)&h_outer.ip); + + /* store new outer network header */ + if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen, + BPF_F_INVALIDATE_HASH) < 0) + return TC_ACT_SHOT; + + /* if changing outer proto type, update eth->h_proto */ + if (encap_proto == IPPROTO_IPV6) { + struct ethhdr eth; + + if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth)) < 0) + return TC_ACT_SHOT; + eth.h_proto = bpf_htons(ETH_P_IP); + if (bpf_skb_store_bytes(skb, 0, ð, sizeof(eth), 0) < 0) + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto, + __u16 l2_proto) +{ + return __encap_ipv4(skb, encap_proto, l2_proto, 0); +} + +static __always_inline int __encap_ipv6(struct __sk_buff *skb, __u8 encap_proto, + __u16 l2_proto, __u16 ext_proto) +{ + __u16 udp_dst = UDP_PORT; + struct ipv6hdr iph_inner; + struct v6hdr h_outer; + struct tcphdr tcph; + int olen, l2_len; + __u8 *l2_hdr = NULL; + __u16 tot_len; + __u64 flags; + + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner, + sizeof(iph_inner)) < 0) + return TC_ACT_OK; + + /* filter only packets we want */ + if (bpf_skb_load_bytes(skb, ETH_HLEN + sizeof(iph_inner), + &tcph, sizeof(tcph)) < 0) + return TC_ACT_OK; + + if (tcph.dest != __bpf_constant_htons(cfg_port)) + return TC_ACT_OK; + + olen = sizeof(h_outer.ip); + l2_len = 0; + + flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV6; + + switch (l2_proto) { + case ETH_P_MPLS_UC: + l2_len = sizeof(mpls_label); + udp_dst = MPLS_OVER_UDP_PORT; + break; + case ETH_P_TEB: + l2_len = ETH_HLEN; + if (ext_proto & EXTPROTO_VXLAN) { + udp_dst = VXLAN_UDP_PORT; + l2_len += sizeof(struct vxlanhdr); + } else + udp_dst = ETH_OVER_UDP_PORT; + break; + } + flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len); + + switch (encap_proto) { + case IPPROTO_GRE: + flags |= BPF_F_ADJ_ROOM_ENCAP_L4_GRE; + olen += sizeof(h_outer.l4hdr.gre); + h_outer.l4hdr.gre.protocol = bpf_htons(l2_proto); + h_outer.l4hdr.gre.flags = 0; + break; + case IPPROTO_UDP: + flags |= BPF_F_ADJ_ROOM_ENCAP_L4_UDP; + olen += sizeof(h_outer.l4hdr.udp); + h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src); + h_outer.l4hdr.udp.dest = bpf_htons(udp_dst); + tot_len = bpf_ntohs(iph_inner.payload_len) + sizeof(iph_inner) + + sizeof(h_outer.l4hdr.udp) + l2_len; + h_outer.l4hdr.udp.check = 0; + h_outer.l4hdr.udp.len = bpf_htons(tot_len); + break; + case IPPROTO_IPV6: + break; + default: + return TC_ACT_OK; + } + + /* add L2 encap (if specified) */ + l2_hdr = (__u8 *)&h_outer + olen; + switch (l2_proto) { + case ETH_P_MPLS_UC: + *(__u32 *)l2_hdr = mpls_label; + break; + case ETH_P_TEB: + flags |= BPF_F_ADJ_ROOM_ENCAP_L2_ETH; + + if (ext_proto & EXTPROTO_VXLAN) { + struct vxlanhdr *vxlan_hdr = (struct vxlanhdr *)l2_hdr; + + vxlan_hdr->vx_flags = VXLAN_FLAGS; + vxlan_hdr->vx_vni = bpf_htonl((VXLAN_VNI & VXLAN_VNI_MASK) << 8); + + l2_hdr += sizeof(struct vxlanhdr); + } + + if (bpf_skb_load_bytes(skb, 0, l2_hdr, ETH_HLEN)) + return TC_ACT_SHOT; + break; + } + olen += l2_len; + + /* add room between mac and network header */ + if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags)) + return TC_ACT_SHOT; + + /* prepare new outer network header */ + h_outer.ip = iph_inner; + h_outer.ip.payload_len = bpf_htons(olen + + bpf_ntohs(h_outer.ip.payload_len)); + + h_outer.ip.nexthdr = encap_proto; + + /* store new outer network header */ + if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen, + BPF_F_INVALIDATE_HASH) < 0) + return TC_ACT_SHOT; + + return TC_ACT_OK; +} + +static int encap_ipv6_ipip6(struct __sk_buff *skb) +{ + struct iphdr iph_inner; + struct v6hdr h_outer; + struct tcphdr tcph; + struct ethhdr eth; + __u64 flags; + int olen; + + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner, + sizeof(iph_inner)) < 0) + return TC_ACT_OK; + + /* filter only packets we want */ + if (bpf_skb_load_bytes(skb, ETH_HLEN + (iph_inner.ihl << 2), + &tcph, sizeof(tcph)) < 0) + return TC_ACT_OK; + + if (tcph.dest != __bpf_constant_htons(cfg_port)) + return TC_ACT_OK; + + olen = sizeof(h_outer.ip); + + flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV6; + + /* add room between mac and network header */ + if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags)) + return TC_ACT_SHOT; + + /* prepare new outer network header */ + memset(&h_outer.ip, 0, sizeof(h_outer.ip)); + h_outer.ip.version = 6; + h_outer.ip.hop_limit = iph_inner.ttl; + h_outer.ip.saddr.s6_addr[1] = 0xfd; + h_outer.ip.saddr.s6_addr[15] = 1; + h_outer.ip.daddr.s6_addr[1] = 0xfd; + h_outer.ip.daddr.s6_addr[15] = 2; + h_outer.ip.payload_len = iph_inner.tot_len; + h_outer.ip.nexthdr = IPPROTO_IPIP; + + /* store new outer network header */ + if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen, + BPF_F_INVALIDATE_HASH) < 0) + return TC_ACT_SHOT; + + /* update eth->h_proto */ + if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth)) < 0) + return TC_ACT_SHOT; + eth.h_proto = bpf_htons(ETH_P_IPV6); + if (bpf_skb_store_bytes(skb, 0, ð, sizeof(eth), 0) < 0) + return TC_ACT_SHOT; + + return TC_ACT_OK; +} + +static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto, + __u16 l2_proto) +{ + return __encap_ipv6(skb, encap_proto, l2_proto, 0); +} + +SEC("encap_ipip_none") +int __encap_ipip_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_IPIP, ETH_P_IP); + else + return TC_ACT_OK; +} + +SEC("encap_gre_none") +int __encap_gre_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_GRE, ETH_P_IP); + else + return TC_ACT_OK; +} + +SEC("encap_gre_mpls") +int __encap_gre_mpls(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_GRE, ETH_P_MPLS_UC); + else + return TC_ACT_OK; +} + +SEC("encap_gre_eth") +int __encap_gre_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_GRE, ETH_P_TEB); + else + return TC_ACT_OK; +} + +SEC("encap_udp_none") +int __encap_udp_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_UDP, ETH_P_IP); + else + return TC_ACT_OK; +} + +SEC("encap_udp_mpls") +int __encap_udp_mpls(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_UDP, ETH_P_MPLS_UC); + else + return TC_ACT_OK; +} + +SEC("encap_udp_eth") +int __encap_udp_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_UDP, ETH_P_TEB); + else + return TC_ACT_OK; +} + +SEC("encap_vxlan_eth") +int __encap_vxlan_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return __encap_ipv4(skb, IPPROTO_UDP, + ETH_P_TEB, + EXTPROTO_VXLAN); + else + return TC_ACT_OK; +} + +SEC("encap_sit_none") +int __encap_sit_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv4(skb, IPPROTO_IPV6, ETH_P_IP); + else + return TC_ACT_OK; +} + +SEC("encap_ip6tnl_none") +int __encap_ip6tnl_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_IPV6, ETH_P_IPV6); + else + return TC_ACT_OK; +} + +SEC("encap_ipip6_none") +int __encap_ipip6_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv6_ipip6(skb); + else + return TC_ACT_OK; +} + +SEC("encap_ip6gre_none") +int __encap_ip6gre_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_GRE, ETH_P_IPV6); + else + return TC_ACT_OK; +} + +SEC("encap_ip6gre_mpls") +int __encap_ip6gre_mpls(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_GRE, ETH_P_MPLS_UC); + else + return TC_ACT_OK; +} + +SEC("encap_ip6gre_eth") +int __encap_ip6gre_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_GRE, ETH_P_TEB); + else + return TC_ACT_OK; +} + +SEC("encap_ip6udp_none") +int __encap_ip6udp_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_UDP, ETH_P_IPV6); + else + return TC_ACT_OK; +} + +SEC("encap_ip6udp_mpls") +int __encap_ip6udp_mpls(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_UDP, ETH_P_MPLS_UC); + else + return TC_ACT_OK; +} + +SEC("encap_ip6udp_eth") +int __encap_ip6udp_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_UDP, ETH_P_TEB); + else + return TC_ACT_OK; +} + +SEC("encap_ip6vxlan_eth") +int __encap_ip6vxlan_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return __encap_ipv6(skb, IPPROTO_UDP, + ETH_P_TEB, + EXTPROTO_VXLAN); + else + return TC_ACT_OK; +} + +static int decap_internal(struct __sk_buff *skb, int off, int len, char proto) +{ + __u64 flags = BPF_F_ADJ_ROOM_FIXED_GSO; + struct ipv6_opt_hdr ip6_opt_hdr; + struct gre_hdr greh; + struct udphdr udph; + int olen = len; + + switch (proto) { + case IPPROTO_IPIP: + flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4; + break; + case IPPROTO_IPV6: + flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6; + break; + case NEXTHDR_DEST: + if (bpf_skb_load_bytes(skb, off + len, &ip6_opt_hdr, + sizeof(ip6_opt_hdr)) < 0) + return TC_ACT_OK; + switch (ip6_opt_hdr.nexthdr) { + case IPPROTO_IPIP: + flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4; + break; + case IPPROTO_IPV6: + flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6; + break; + default: + return TC_ACT_OK; + } + break; + case IPPROTO_GRE: + olen += sizeof(struct gre_hdr); + if (bpf_skb_load_bytes(skb, off + len, &greh, sizeof(greh)) < 0) + return TC_ACT_OK; + switch (bpf_ntohs(greh.protocol)) { + case ETH_P_MPLS_UC: + olen += sizeof(mpls_label); + break; + case ETH_P_TEB: + olen += ETH_HLEN; + break; + } + break; + case IPPROTO_UDP: + olen += sizeof(struct udphdr); + if (bpf_skb_load_bytes(skb, off + len, &udph, sizeof(udph)) < 0) + return TC_ACT_OK; + switch (bpf_ntohs(udph.dest)) { + case MPLS_OVER_UDP_PORT: + olen += sizeof(mpls_label); + break; + case ETH_OVER_UDP_PORT: + olen += ETH_HLEN; + break; + case VXLAN_UDP_PORT: + olen += ETH_HLEN + sizeof(struct vxlanhdr); + break; + } + break; + default: + return TC_ACT_OK; + } + + if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC, flags)) + return TC_ACT_SHOT; + + return TC_ACT_OK; +} + +static int decap_ipv4(struct __sk_buff *skb) +{ + struct iphdr iph_outer; + + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_outer, + sizeof(iph_outer)) < 0) + return TC_ACT_OK; + + if (iph_outer.ihl != 5) + return TC_ACT_OK; + + return decap_internal(skb, ETH_HLEN, sizeof(iph_outer), + iph_outer.protocol); +} + +static int decap_ipv6(struct __sk_buff *skb) +{ + struct ipv6hdr iph_outer; + + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_outer, + sizeof(iph_outer)) < 0) + return TC_ACT_OK; + + return decap_internal(skb, ETH_HLEN, sizeof(iph_outer), + iph_outer.nexthdr); +} + +SEC("decap") +int decap_f(struct __sk_buff *skb) +{ + switch (skb->protocol) { + case __bpf_constant_htons(ETH_P_IP): + return decap_ipv4(skb); + case __bpf_constant_htons(ETH_P_IPV6): + return decap_ipv6(skb); + default: + /* does not match, ignore */ + return TC_ACT_OK; + } +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c new file mode 100644 index 0000000000..6edebce563 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook +// Copyright (c) 2019 Cloudflare + +#include <string.h> + +#include <linux/bpf.h> +#include <linux/pkt_cls.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <sys/socket.h> +#include <linux/tcp.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 3); +} results SEC(".maps"); + +static __always_inline __s64 gen_syncookie(void *data_end, struct bpf_sock *sk, + void *iph, __u32 ip_size, + struct tcphdr *tcph) +{ + __u32 thlen = tcph->doff * 4; + + if (tcph->syn && !tcph->ack) { + // packet should only have an MSS option + if (thlen != 24) + return 0; + + if ((void *)tcph + thlen > data_end) + return 0; + + return bpf_tcp_gen_syncookie(sk, iph, ip_size, tcph, thlen); + } + return 0; +} + +static __always_inline void check_syncookie(void *ctx, void *data, + void *data_end) +{ + struct bpf_sock_tuple tup; + struct bpf_sock *sk; + struct ethhdr *ethh; + struct iphdr *ipv4h; + struct ipv6hdr *ipv6h; + struct tcphdr *tcph; + int ret; + __u32 key_mss = 2; + __u32 key_gen = 1; + __u32 key = 0; + __s64 seq_mss; + + ethh = data; + if (ethh + 1 > data_end) + return; + + switch (bpf_ntohs(ethh->h_proto)) { + case ETH_P_IP: + ipv4h = data + sizeof(struct ethhdr); + if (ipv4h + 1 > data_end) + return; + + if (ipv4h->ihl != 5) + return; + + tcph = data + sizeof(struct ethhdr) + sizeof(struct iphdr); + if (tcph + 1 > data_end) + return; + + tup.ipv4.saddr = ipv4h->saddr; + tup.ipv4.daddr = ipv4h->daddr; + tup.ipv4.sport = tcph->source; + tup.ipv4.dport = tcph->dest; + + sk = bpf_skc_lookup_tcp(ctx, &tup, sizeof(tup.ipv4), + BPF_F_CURRENT_NETNS, 0); + if (!sk) + return; + + if (sk->state != BPF_TCP_LISTEN) + goto release; + + seq_mss = gen_syncookie(data_end, sk, ipv4h, sizeof(*ipv4h), + tcph); + + ret = bpf_tcp_check_syncookie(sk, ipv4h, sizeof(*ipv4h), + tcph, sizeof(*tcph)); + break; + + case ETH_P_IPV6: + ipv6h = data + sizeof(struct ethhdr); + if (ipv6h + 1 > data_end) + return; + + if (ipv6h->nexthdr != IPPROTO_TCP) + return; + + tcph = data + sizeof(struct ethhdr) + sizeof(struct ipv6hdr); + if (tcph + 1 > data_end) + return; + + memcpy(tup.ipv6.saddr, &ipv6h->saddr, sizeof(tup.ipv6.saddr)); + memcpy(tup.ipv6.daddr, &ipv6h->daddr, sizeof(tup.ipv6.daddr)); + tup.ipv6.sport = tcph->source; + tup.ipv6.dport = tcph->dest; + + sk = bpf_skc_lookup_tcp(ctx, &tup, sizeof(tup.ipv6), + BPF_F_CURRENT_NETNS, 0); + if (!sk) + return; + + if (sk->state != BPF_TCP_LISTEN) + goto release; + + seq_mss = gen_syncookie(data_end, sk, ipv6h, sizeof(*ipv6h), + tcph); + + ret = bpf_tcp_check_syncookie(sk, ipv6h, sizeof(*ipv6h), + tcph, sizeof(*tcph)); + break; + + default: + return; + } + + if (seq_mss > 0) { + __u32 cookie = (__u32)seq_mss; + __u32 mss = seq_mss >> 32; + + bpf_map_update_elem(&results, &key_gen, &cookie, 0); + bpf_map_update_elem(&results, &key_mss, &mss, 0); + } + + if (ret == 0) { + __u32 cookie = bpf_ntohl(tcph->ack_seq) - 1; + + bpf_map_update_elem(&results, &key, &cookie, 0); + } + +release: + bpf_sk_release(sk); +} + +SEC("tc") +int check_syncookie_clsact(struct __sk_buff *skb) +{ + check_syncookie(skb, (void *)(long)skb->data, + (void *)(long)skb->data_end); + return TC_ACT_OK; +} + +SEC("xdp") +int check_syncookie_xdp(struct xdp_md *ctx) +{ + check_syncookie(ctx, (void *)(long)ctx->data, + (void *)(long)ctx->data_end); + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_estats.c b/tools/testing/selftests/bpf/progs/test_tcp_estats.c new file mode 100644 index 0000000000..e2ae049c2f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tcp_estats.c @@ -0,0 +1,257 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ + +/* This program shows clang/llvm is able to generate code pattern + * like: + * _tcp_send_active_reset: + * 0: bf 16 00 00 00 00 00 00 r6 = r1 + * ...... + * 335: b7 01 00 00 0f 00 00 00 r1 = 15 + * 336: 05 00 48 00 00 00 00 00 goto 72 + * + * LBB0_3: + * 337: b7 01 00 00 01 00 00 00 r1 = 1 + * 338: 63 1a d0 ff 00 00 00 00 *(u32 *)(r10 - 48) = r1 + * 408: b7 01 00 00 03 00 00 00 r1 = 3 + * + * LBB0_4: + * 409: 71 a2 fe ff 00 00 00 00 r2 = *(u8 *)(r10 - 2) + * 410: bf a7 00 00 00 00 00 00 r7 = r10 + * 411: 07 07 00 00 b8 ff ff ff r7 += -72 + * 412: bf 73 00 00 00 00 00 00 r3 = r7 + * 413: 0f 13 00 00 00 00 00 00 r3 += r1 + * 414: 73 23 2d 00 00 00 00 00 *(u8 *)(r3 + 45) = r2 + * + * From the above code snippet, the code generated by the compiler + * is reasonable. The "r1" is assigned to different values in basic + * blocks "_tcp_send_active_reset" and "LBB0_3", and used in "LBB0_4". + * The verifier should be able to handle such code patterns. + */ +#include <string.h> +#include <linux/bpf.h> +#include <linux/ipv6.h> +#include <linux/version.h> +#include <sys/socket.h> +#include <bpf/bpf_helpers.h> + +#define _(P) ({typeof(P) val = 0; bpf_probe_read_kernel(&val, sizeof(val), &P); val;}) +#define TCP_ESTATS_MAGIC 0xBAADBEEF + +/* This test case needs "sock" and "pt_regs" data structure. + * Recursively, "sock" needs "sock_common" and "inet_sock". + * However, this is a unit test case only for + * verifier purpose without bpf program execution. + * We can safely mock much simpler data structures, basically + * only taking the necessary fields from kernel headers. + */ +typedef __u32 __bitwise __portpair; +typedef __u64 __bitwise __addrpair; + +struct sock_common { + unsigned short skc_family; + union { + __addrpair skc_addrpair; + struct { + __be32 skc_daddr; + __be32 skc_rcv_saddr; + }; + }; + union { + __portpair skc_portpair; + struct { + __be16 skc_dport; + __u16 skc_num; + }; + }; + struct in6_addr skc_v6_daddr; + struct in6_addr skc_v6_rcv_saddr; +}; + +struct sock { + struct sock_common __sk_common; +#define sk_family __sk_common.skc_family +#define sk_v6_daddr __sk_common.skc_v6_daddr +#define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr +}; + +struct inet_sock { + struct sock sk; +#define inet_daddr sk.__sk_common.skc_daddr +#define inet_dport sk.__sk_common.skc_dport + __be32 inet_saddr; + __be16 inet_sport; +}; + +struct pt_regs { + long di; +}; + +static inline struct inet_sock *inet_sk(const struct sock *sk) +{ + return (struct inet_sock *)sk; +} + +/* Define various data structures for state recording. + * Some fields are not used due to test simplification. + */ +enum tcp_estats_addrtype { + TCP_ESTATS_ADDRTYPE_IPV4 = 1, + TCP_ESTATS_ADDRTYPE_IPV6 = 2 +}; + +enum tcp_estats_event_type { + TCP_ESTATS_ESTABLISH, + TCP_ESTATS_PERIODIC, + TCP_ESTATS_TIMEOUT, + TCP_ESTATS_RETRANSMIT_TIMEOUT, + TCP_ESTATS_RETRANSMIT_OTHER, + TCP_ESTATS_SYN_RETRANSMIT, + TCP_ESTATS_SYNACK_RETRANSMIT, + TCP_ESTATS_TERM, + TCP_ESTATS_TX_RESET, + TCP_ESTATS_RX_RESET, + TCP_ESTATS_WRITE_TIMEOUT, + TCP_ESTATS_CONN_TIMEOUT, + TCP_ESTATS_ACK_LATENCY, + TCP_ESTATS_NEVENTS, +}; + +struct tcp_estats_event { + int pid; + int cpu; + unsigned long ts; + unsigned int magic; + enum tcp_estats_event_type event_type; +}; + +/* The below data structure is packed in order for + * llvm compiler to generate expected code. + */ +struct tcp_estats_conn_id { + unsigned int localaddressType; + struct { + unsigned char data[16]; + } localaddress; + struct { + unsigned char data[16]; + } remaddress; + unsigned short localport; + unsigned short remport; +} __attribute__((__packed__)); + +struct tcp_estats_basic_event { + struct tcp_estats_event event; + struct tcp_estats_conn_id conn_id; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1024); + __type(key, __u32); + __type(value, struct tcp_estats_basic_event); +} ev_record_map SEC(".maps"); + +struct dummy_tracepoint_args { + unsigned long long pad; + struct sock *sock; +}; + +static __always_inline void tcp_estats_ev_init(struct tcp_estats_event *event, + enum tcp_estats_event_type type) +{ + event->magic = TCP_ESTATS_MAGIC; + event->ts = bpf_ktime_get_ns(); + event->event_type = type; +} + +static __always_inline void unaligned_u32_set(unsigned char *to, __u8 *from) +{ + to[0] = _(from[0]); + to[1] = _(from[1]); + to[2] = _(from[2]); + to[3] = _(from[3]); +} + +static __always_inline void conn_id_ipv4_init(struct tcp_estats_conn_id *conn_id, + __be32 *saddr, __be32 *daddr) +{ + conn_id->localaddressType = TCP_ESTATS_ADDRTYPE_IPV4; + + unaligned_u32_set(conn_id->localaddress.data, (__u8 *)saddr); + unaligned_u32_set(conn_id->remaddress.data, (__u8 *)daddr); +} + +static __always_inline void conn_id_ipv6_init(struct tcp_estats_conn_id *conn_id, + __be32 *saddr, __be32 *daddr) +{ + conn_id->localaddressType = TCP_ESTATS_ADDRTYPE_IPV6; + + unaligned_u32_set(conn_id->localaddress.data, (__u8 *)saddr); + unaligned_u32_set(conn_id->localaddress.data + sizeof(__u32), + (__u8 *)(saddr + 1)); + unaligned_u32_set(conn_id->localaddress.data + sizeof(__u32) * 2, + (__u8 *)(saddr + 2)); + unaligned_u32_set(conn_id->localaddress.data + sizeof(__u32) * 3, + (__u8 *)(saddr + 3)); + + unaligned_u32_set(conn_id->remaddress.data, + (__u8 *)(daddr)); + unaligned_u32_set(conn_id->remaddress.data + sizeof(__u32), + (__u8 *)(daddr + 1)); + unaligned_u32_set(conn_id->remaddress.data + sizeof(__u32) * 2, + (__u8 *)(daddr + 2)); + unaligned_u32_set(conn_id->remaddress.data + sizeof(__u32) * 3, + (__u8 *)(daddr + 3)); +} + +static __always_inline void tcp_estats_conn_id_init(struct tcp_estats_conn_id *conn_id, + struct sock *sk) +{ + conn_id->localport = _(inet_sk(sk)->inet_sport); + conn_id->remport = _(inet_sk(sk)->inet_dport); + + if (_(sk->sk_family) == AF_INET6) + conn_id_ipv6_init(conn_id, + sk->sk_v6_rcv_saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32); + else + conn_id_ipv4_init(conn_id, + &inet_sk(sk)->inet_saddr, + &inet_sk(sk)->inet_daddr); +} + +static __always_inline void tcp_estats_init(struct sock *sk, + struct tcp_estats_event *event, + struct tcp_estats_conn_id *conn_id, + enum tcp_estats_event_type type) +{ + tcp_estats_ev_init(event, type); + tcp_estats_conn_id_init(conn_id, sk); +} + +static __always_inline void send_basic_event(struct sock *sk, + enum tcp_estats_event_type type) +{ + struct tcp_estats_basic_event ev; + __u32 key = bpf_get_prandom_u32(); + + memset(&ev, 0, sizeof(ev)); + tcp_estats_init(sk, &ev.event, &ev.conn_id, type); + bpf_map_update_elem(&ev_record_map, &key, &ev, BPF_ANY); +} + +SEC("tp/dummy/tracepoint") +int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +{ + if (!arg->sock) + return 0; + + send_basic_event(arg->sock, TCP_ESTATS_TX_RESET); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c new file mode 100644 index 0000000000..5f4e87ee94 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c @@ -0,0 +1,626 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <stddef.h> +#include <errno.h> +#include <stdbool.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <linux/tcp.h> +#include <linux/socket.h> +#include <linux/bpf.h> +#include <linux/types.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#define BPF_PROG_TEST_TCP_HDR_OPTIONS +#include "test_tcp_hdr_options.h" + +#ifndef sizeof_field +#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER)) +#endif + +__u8 test_kind = TCPOPT_EXP; +__u16 test_magic = 0xeB9F; +__u32 inherit_cb_flags = 0; + +struct bpf_test_option passive_synack_out = {}; +struct bpf_test_option passive_fin_out = {}; + +struct bpf_test_option passive_estab_in = {}; +struct bpf_test_option passive_fin_in = {}; + +struct bpf_test_option active_syn_out = {}; +struct bpf_test_option active_fin_out = {}; + +struct bpf_test_option active_estab_in = {}; +struct bpf_test_option active_fin_in = {}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct hdr_stg); +} hdr_stg_map SEC(".maps"); + +static bool skops_want_cookie(const struct bpf_sock_ops *skops) +{ + return skops->args[0] == BPF_WRITE_HDR_TCP_SYNACK_COOKIE; +} + +static bool skops_current_mss(const struct bpf_sock_ops *skops) +{ + return skops->args[0] == BPF_WRITE_HDR_TCP_CURRENT_MSS; +} + +static __u8 option_total_len(__u8 flags) +{ + __u8 i, len = 1; /* +1 for flags */ + + if (!flags) + return 0; + + /* RESEND bit does not use a byte */ + for (i = OPTION_RESEND + 1; i < __NR_OPTION_FLAGS; i++) + len += !!TEST_OPTION_FLAGS(flags, i); + + if (test_kind == TCPOPT_EXP) + return len + TCP_BPF_EXPOPT_BASE_LEN; + else + return len + 2; /* +1 kind, +1 kind-len */ +} + +static void write_test_option(const struct bpf_test_option *test_opt, + __u8 *data) +{ + __u8 offset = 0; + + data[offset++] = test_opt->flags; + if (TEST_OPTION_FLAGS(test_opt->flags, OPTION_MAX_DELACK_MS)) + data[offset++] = test_opt->max_delack_ms; + + if (TEST_OPTION_FLAGS(test_opt->flags, OPTION_RAND)) + data[offset++] = test_opt->rand; +} + +static int store_option(struct bpf_sock_ops *skops, + const struct bpf_test_option *test_opt) +{ + union { + struct tcp_exprm_opt exprm; + struct tcp_opt regular; + } write_opt; + int err; + + if (test_kind == TCPOPT_EXP) { + write_opt.exprm.kind = TCPOPT_EXP; + write_opt.exprm.len = option_total_len(test_opt->flags); + write_opt.exprm.magic = __bpf_htons(test_magic); + write_opt.exprm.data32 = 0; + write_test_option(test_opt, write_opt.exprm.data); + err = bpf_store_hdr_opt(skops, &write_opt.exprm, + sizeof(write_opt.exprm), 0); + } else { + write_opt.regular.kind = test_kind; + write_opt.regular.len = option_total_len(test_opt->flags); + write_opt.regular.data32 = 0; + write_test_option(test_opt, write_opt.regular.data); + err = bpf_store_hdr_opt(skops, &write_opt.regular, + sizeof(write_opt.regular), 0); + } + + if (err) + RET_CG_ERR(err); + + return CG_OK; +} + +static int parse_test_option(struct bpf_test_option *opt, const __u8 *start) +{ + opt->flags = *start++; + + if (TEST_OPTION_FLAGS(opt->flags, OPTION_MAX_DELACK_MS)) + opt->max_delack_ms = *start++; + + if (TEST_OPTION_FLAGS(opt->flags, OPTION_RAND)) + opt->rand = *start++; + + return 0; +} + +static int load_option(struct bpf_sock_ops *skops, + struct bpf_test_option *test_opt, bool from_syn) +{ + union { + struct tcp_exprm_opt exprm; + struct tcp_opt regular; + } search_opt; + int ret, load_flags = from_syn ? BPF_LOAD_HDR_OPT_TCP_SYN : 0; + + if (test_kind == TCPOPT_EXP) { + search_opt.exprm.kind = TCPOPT_EXP; + search_opt.exprm.len = 4; + search_opt.exprm.magic = __bpf_htons(test_magic); + search_opt.exprm.data32 = 0; + ret = bpf_load_hdr_opt(skops, &search_opt.exprm, + sizeof(search_opt.exprm), load_flags); + if (ret < 0) + return ret; + return parse_test_option(test_opt, search_opt.exprm.data); + } else { + search_opt.regular.kind = test_kind; + search_opt.regular.len = 0; + search_opt.regular.data32 = 0; + ret = bpf_load_hdr_opt(skops, &search_opt.regular, + sizeof(search_opt.regular), load_flags); + if (ret < 0) + return ret; + return parse_test_option(test_opt, search_opt.regular.data); + } +} + +static int synack_opt_len(struct bpf_sock_ops *skops) +{ + struct bpf_test_option test_opt = {}; + __u8 optlen; + int err; + + if (!passive_synack_out.flags) + return CG_OK; + + err = load_option(skops, &test_opt, true); + + /* bpf_test_option is not found */ + if (err == -ENOMSG) + return CG_OK; + + if (err) + RET_CG_ERR(err); + + optlen = option_total_len(passive_synack_out.flags); + if (optlen) { + err = bpf_reserve_hdr_opt(skops, optlen, 0); + if (err) + RET_CG_ERR(err); + } + + return CG_OK; +} + +static int write_synack_opt(struct bpf_sock_ops *skops) +{ + struct bpf_test_option opt; + + if (!passive_synack_out.flags) + /* We should not even be called since no header + * space has been reserved. + */ + RET_CG_ERR(0); + + opt = passive_synack_out; + if (skops_want_cookie(skops)) + SET_OPTION_FLAGS(opt.flags, OPTION_RESEND); + + return store_option(skops, &opt); +} + +static int syn_opt_len(struct bpf_sock_ops *skops) +{ + __u8 optlen; + int err; + + if (!active_syn_out.flags) + return CG_OK; + + optlen = option_total_len(active_syn_out.flags); + if (optlen) { + err = bpf_reserve_hdr_opt(skops, optlen, 0); + if (err) + RET_CG_ERR(err); + } + + return CG_OK; +} + +static int write_syn_opt(struct bpf_sock_ops *skops) +{ + if (!active_syn_out.flags) + RET_CG_ERR(0); + + return store_option(skops, &active_syn_out); +} + +static int fin_opt_len(struct bpf_sock_ops *skops) +{ + struct bpf_test_option *opt; + struct hdr_stg *hdr_stg; + __u8 optlen; + int err; + + if (!skops->sk) + RET_CG_ERR(0); + + hdr_stg = bpf_sk_storage_get(&hdr_stg_map, skops->sk, NULL, 0); + if (!hdr_stg) + RET_CG_ERR(0); + + if (hdr_stg->active) + opt = &active_fin_out; + else + opt = &passive_fin_out; + + optlen = option_total_len(opt->flags); + if (optlen) { + err = bpf_reserve_hdr_opt(skops, optlen, 0); + if (err) + RET_CG_ERR(err); + } + + return CG_OK; +} + +static int write_fin_opt(struct bpf_sock_ops *skops) +{ + struct bpf_test_option *opt; + struct hdr_stg *hdr_stg; + + if (!skops->sk) + RET_CG_ERR(0); + + hdr_stg = bpf_sk_storage_get(&hdr_stg_map, skops->sk, NULL, 0); + if (!hdr_stg) + RET_CG_ERR(0); + + if (hdr_stg->active) + opt = &active_fin_out; + else + opt = &passive_fin_out; + + if (!opt->flags) + RET_CG_ERR(0); + + return store_option(skops, opt); +} + +static int resend_in_ack(struct bpf_sock_ops *skops) +{ + struct hdr_stg *hdr_stg; + + if (!skops->sk) + return -1; + + hdr_stg = bpf_sk_storage_get(&hdr_stg_map, skops->sk, NULL, 0); + if (!hdr_stg) + return -1; + + return !!hdr_stg->resend_syn; +} + +static int nodata_opt_len(struct bpf_sock_ops *skops) +{ + int resend; + + resend = resend_in_ack(skops); + if (resend < 0) + RET_CG_ERR(0); + + if (resend) + return syn_opt_len(skops); + + return CG_OK; +} + +static int write_nodata_opt(struct bpf_sock_ops *skops) +{ + int resend; + + resend = resend_in_ack(skops); + if (resend < 0) + RET_CG_ERR(0); + + if (resend) + return write_syn_opt(skops); + + return CG_OK; +} + +static int data_opt_len(struct bpf_sock_ops *skops) +{ + /* Same as the nodata version. Mostly to show + * an example usage on skops->skb_len. + */ + return nodata_opt_len(skops); +} + +static int write_data_opt(struct bpf_sock_ops *skops) +{ + return write_nodata_opt(skops); +} + +static int current_mss_opt_len(struct bpf_sock_ops *skops) +{ + /* Reserve maximum that may be needed */ + int err; + + err = bpf_reserve_hdr_opt(skops, option_total_len(OPTION_MASK), 0); + if (err) + RET_CG_ERR(err); + + return CG_OK; +} + +static int handle_hdr_opt_len(struct bpf_sock_ops *skops) +{ + __u8 tcp_flags = skops_tcp_flags(skops); + + if ((tcp_flags & TCPHDR_SYNACK) == TCPHDR_SYNACK) + return synack_opt_len(skops); + + if (tcp_flags & TCPHDR_SYN) + return syn_opt_len(skops); + + if (tcp_flags & TCPHDR_FIN) + return fin_opt_len(skops); + + if (skops_current_mss(skops)) + /* The kernel is calculating the MSS */ + return current_mss_opt_len(skops); + + if (skops->skb_len) + return data_opt_len(skops); + + return nodata_opt_len(skops); +} + +static int handle_write_hdr_opt(struct bpf_sock_ops *skops) +{ + __u8 tcp_flags = skops_tcp_flags(skops); + struct tcphdr *th; + + if ((tcp_flags & TCPHDR_SYNACK) == TCPHDR_SYNACK) + return write_synack_opt(skops); + + if (tcp_flags & TCPHDR_SYN) + return write_syn_opt(skops); + + if (tcp_flags & TCPHDR_FIN) + return write_fin_opt(skops); + + th = skops->skb_data; + if (th + 1 > skops->skb_data_end) + RET_CG_ERR(0); + + if (skops->skb_len > tcp_hdrlen(th)) + return write_data_opt(skops); + + return write_nodata_opt(skops); +} + +static int set_delack_max(struct bpf_sock_ops *skops, __u8 max_delack_ms) +{ + __u32 max_delack_us = max_delack_ms * 1000; + + return bpf_setsockopt(skops, SOL_TCP, TCP_BPF_DELACK_MAX, + &max_delack_us, sizeof(max_delack_us)); +} + +static int set_rto_min(struct bpf_sock_ops *skops, __u8 peer_max_delack_ms) +{ + __u32 min_rto_us = peer_max_delack_ms * 1000; + + return bpf_setsockopt(skops, SOL_TCP, TCP_BPF_RTO_MIN, &min_rto_us, + sizeof(min_rto_us)); +} + +static int handle_active_estab(struct bpf_sock_ops *skops) +{ + struct hdr_stg init_stg = { + .active = true, + }; + int err; + + err = load_option(skops, &active_estab_in, false); + if (err && err != -ENOMSG) + RET_CG_ERR(err); + + init_stg.resend_syn = TEST_OPTION_FLAGS(active_estab_in.flags, + OPTION_RESEND); + if (!skops->sk || !bpf_sk_storage_get(&hdr_stg_map, skops->sk, + &init_stg, + BPF_SK_STORAGE_GET_F_CREATE)) + RET_CG_ERR(0); + + if (init_stg.resend_syn) + /* Don't clear the write_hdr cb now because + * the ACK may get lost and retransmit may + * be needed. + * + * PARSE_ALL_HDR cb flag is set to learn if this + * resend_syn option has received by the peer. + * + * The header option will be resent until a valid + * packet is received at handle_parse_hdr() + * and all hdr cb flags will be cleared in + * handle_parse_hdr(). + */ + set_parse_all_hdr_cb_flags(skops); + else if (!active_fin_out.flags) + /* No options will be written from now */ + clear_hdr_cb_flags(skops); + + if (active_syn_out.max_delack_ms) { + err = set_delack_max(skops, active_syn_out.max_delack_ms); + if (err) + RET_CG_ERR(err); + } + + if (active_estab_in.max_delack_ms) { + err = set_rto_min(skops, active_estab_in.max_delack_ms); + if (err) + RET_CG_ERR(err); + } + + return CG_OK; +} + +static int handle_passive_estab(struct bpf_sock_ops *skops) +{ + struct hdr_stg init_stg = {}; + struct tcphdr *th; + int err; + + inherit_cb_flags = skops->bpf_sock_ops_cb_flags; + + err = load_option(skops, &passive_estab_in, true); + if (err == -ENOENT) { + /* saved_syn is not found. It was in syncookie mode. + * We have asked the active side to resend the options + * in ACK, so try to find the bpf_test_option from ACK now. + */ + err = load_option(skops, &passive_estab_in, false); + init_stg.syncookie = true; + } + + /* ENOMSG: The bpf_test_option is not found which is fine. + * Bail out now for all other errors. + */ + if (err && err != -ENOMSG) + RET_CG_ERR(err); + + th = skops->skb_data; + if (th + 1 > skops->skb_data_end) + RET_CG_ERR(0); + + if (th->syn) { + /* Fastopen */ + + /* Cannot clear cb_flags to stop write_hdr cb. + * synack is not sent yet for fast open. + * Even it was, the synack may need to be retransmitted. + * + * PARSE_ALL_HDR cb flag is set to learn + * if synack has reached the peer. + * All cb_flags will be cleared in handle_parse_hdr(). + */ + set_parse_all_hdr_cb_flags(skops); + init_stg.fastopen = true; + } else if (!passive_fin_out.flags) { + /* No options will be written from now */ + clear_hdr_cb_flags(skops); + } + + if (!skops->sk || + !bpf_sk_storage_get(&hdr_stg_map, skops->sk, &init_stg, + BPF_SK_STORAGE_GET_F_CREATE)) + RET_CG_ERR(0); + + if (passive_synack_out.max_delack_ms) { + err = set_delack_max(skops, passive_synack_out.max_delack_ms); + if (err) + RET_CG_ERR(err); + } + + if (passive_estab_in.max_delack_ms) { + err = set_rto_min(skops, passive_estab_in.max_delack_ms); + if (err) + RET_CG_ERR(err); + } + + return CG_OK; +} + +static int handle_parse_hdr(struct bpf_sock_ops *skops) +{ + struct hdr_stg *hdr_stg; + struct tcphdr *th; + + if (!skops->sk) + RET_CG_ERR(0); + + th = skops->skb_data; + if (th + 1 > skops->skb_data_end) + RET_CG_ERR(0); + + hdr_stg = bpf_sk_storage_get(&hdr_stg_map, skops->sk, NULL, 0); + if (!hdr_stg) + RET_CG_ERR(0); + + if (hdr_stg->resend_syn || hdr_stg->fastopen) + /* The PARSE_ALL_HDR cb flag was turned on + * to ensure that the previously written + * options have reached the peer. + * Those previously written option includes: + * - Active side: resend_syn in ACK during syncookie + * or + * - Passive side: SYNACK during fastopen + * + * A valid packet has been received here after + * the 3WHS, so the PARSE_ALL_HDR cb flag + * can be cleared now. + */ + clear_parse_all_hdr_cb_flags(skops); + + if (hdr_stg->resend_syn && !active_fin_out.flags) + /* Active side resent the syn option in ACK + * because the server was in syncookie mode. + * A valid packet has been received, so + * clear header cb flags if there is no + * more option to send. + */ + clear_hdr_cb_flags(skops); + + if (hdr_stg->fastopen && !passive_fin_out.flags) + /* Passive side was in fastopen. + * A valid packet has been received, so + * the SYNACK has reached the peer. + * Clear header cb flags if there is no more + * option to send. + */ + clear_hdr_cb_flags(skops); + + if (th->fin) { + struct bpf_test_option *fin_opt; + int err; + + if (hdr_stg->active) + fin_opt = &active_fin_in; + else + fin_opt = &passive_fin_in; + + err = load_option(skops, fin_opt, false); + if (err && err != -ENOMSG) + RET_CG_ERR(err); + } + + return CG_OK; +} + +SEC("sockops") +int estab(struct bpf_sock_ops *skops) +{ + int true_val = 1; + + switch (skops->op) { + case BPF_SOCK_OPS_TCP_LISTEN_CB: + bpf_setsockopt(skops, SOL_TCP, TCP_SAVE_SYN, + &true_val, sizeof(true_val)); + set_hdr_cb_flags(skops, BPF_SOCK_OPS_STATE_CB_FLAG); + break; + case BPF_SOCK_OPS_TCP_CONNECT_CB: + set_hdr_cb_flags(skops, 0); + break; + case BPF_SOCK_OPS_PARSE_HDR_OPT_CB: + return handle_parse_hdr(skops); + case BPF_SOCK_OPS_HDR_OPT_LEN_CB: + return handle_hdr_opt_len(skops); + case BPF_SOCK_OPS_WRITE_HDR_OPT_CB: + return handle_write_hdr_opt(skops); + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + return handle_passive_estab(skops); + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + return handle_active_estab(skops); + } + + return CG_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c new file mode 100644 index 0000000000..cf7ed8cbb1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stddef.h> +#include <string.h> +#include <netinet/in.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/types.h> +#include <linux/socket.h> +#include <linux/tcp.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include "bpf_tcp_helpers.h" +#include "test_tcpbpf.h" + +struct tcpbpf_globals global = {}; + +/** + * SOL_TCP is defined in <netinet/tcp.h> while + * TCP_SAVED_SYN is defined in already included <linux/tcp.h> + */ +#ifndef SOL_TCP +#define SOL_TCP 6 +#endif + +static __always_inline int get_tp_window_clamp(struct bpf_sock_ops *skops) +{ + struct bpf_sock *sk; + struct tcp_sock *tp; + + sk = skops->sk; + if (!sk) + return -1; + tp = bpf_skc_to_tcp_sock(sk); + if (!tp) + return -1; + return tp->window_clamp; +} + +SEC("sockops") +int bpf_testcb(struct bpf_sock_ops *skops) +{ + char header[sizeof(struct ipv6hdr) + sizeof(struct tcphdr)]; + struct bpf_sock_ops *reuse = skops; + struct tcphdr *thdr; + int window_clamp = 9216; + int save_syn = 1; + int rv = -1; + int v = 0; + int op; + + /* Test reading fields in bpf_sock_ops using single register */ + asm volatile ( + "%[reuse] = *(u32 *)(%[reuse] +96)" + : [reuse] "+r"(reuse) + :); + + asm volatile ( + "%[op] = *(u32 *)(%[skops] +96)" + : [op] "+r"(op) + : [skops] "r"(skops) + :); + + asm volatile ( + "r9 = %[skops];\n" + "r8 = *(u32 *)(r9 +164);\n" + "*(u32 *)(r9 +164) = r8;\n" + :: [skops] "r"(skops) + : "r9", "r8"); + + asm volatile ( + "r1 = %[skops];\n" + "r1 = *(u64 *)(r1 +184);\n" + "if r1 == 0 goto +1;\n" + "r1 = *(u32 *)(r1 +4);\n" + :: [skops] "r"(skops):"r1"); + + asm volatile ( + "r9 = %[skops];\n" + "r9 = *(u64 *)(r9 +184);\n" + "if r9 == 0 goto +1;\n" + "r9 = *(u32 *)(r9 +4);\n" + :: [skops] "r"(skops):"r9"); + + asm volatile ( + "r1 = %[skops];\n" + "r2 = *(u64 *)(r1 +184);\n" + "if r2 == 0 goto +1;\n" + "r2 = *(u32 *)(r2 +4);\n" + :: [skops] "r"(skops):"r1", "r2"); + + op = (int) skops->op; + + global.event_map |= (1 << op); + + switch (op) { + case BPF_SOCK_OPS_TCP_CONNECT_CB: + rv = bpf_setsockopt(skops, SOL_TCP, TCP_WINDOW_CLAMP, + &window_clamp, sizeof(window_clamp)); + global.window_clamp_client = get_tp_window_clamp(skops); + break; + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + /* Test failure to set largest cb flag (assumes not defined) */ + global.bad_cb_test_rv = bpf_sock_ops_cb_flags_set(skops, 0x80); + /* Set callback */ + global.good_cb_test_rv = bpf_sock_ops_cb_flags_set(skops, + BPF_SOCK_OPS_STATE_CB_FLAG); + break; + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + skops->sk_txhash = 0x12345f; + v = 0xff; + rv = bpf_setsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v, + sizeof(v)); + if (skops->family == AF_INET6) { + v = bpf_getsockopt(skops, IPPROTO_TCP, TCP_SAVED_SYN, + header, (sizeof(struct ipv6hdr) + + sizeof(struct tcphdr))); + if (!v) { + int offset = sizeof(struct ipv6hdr); + + thdr = (struct tcphdr *)(header + offset); + v = thdr->syn; + + global.tcp_saved_syn = v; + } + } + rv = bpf_setsockopt(skops, SOL_TCP, TCP_WINDOW_CLAMP, + &window_clamp, sizeof(window_clamp)); + + global.window_clamp_server = get_tp_window_clamp(skops); + break; + case BPF_SOCK_OPS_RTO_CB: + break; + case BPF_SOCK_OPS_RETRANS_CB: + break; + case BPF_SOCK_OPS_STATE_CB: + if (skops->args[1] == BPF_TCP_CLOSE) { + if (skops->args[0] == BPF_TCP_LISTEN) { + global.num_listen++; + } else { + global.total_retrans = skops->total_retrans; + global.data_segs_in = skops->data_segs_in; + global.data_segs_out = skops->data_segs_out; + global.bytes_received = skops->bytes_received; + global.bytes_acked = skops->bytes_acked; + } + global.num_close_events++; + } + break; + case BPF_SOCK_OPS_TCP_LISTEN_CB: + bpf_sock_ops_cb_flags_set(skops, BPF_SOCK_OPS_STATE_CB_FLAG); + v = bpf_setsockopt(skops, IPPROTO_TCP, TCP_SAVE_SYN, + &save_syn, sizeof(save_syn)); + /* Update global map w/ result of setsock opt */ + global.tcp_save_syn = v; + break; + default: + rv = -1; + } + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c new file mode 100644 index 0000000000..540181c115 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stddef.h> +#include <string.h> +#include <netinet/in.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/types.h> +#include <linux/socket.h> +#include <linux/tcp.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include "test_tcpnotify.h" + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 4); + __type(key, __u32); + __type(value, struct tcpnotify_globals); +} global_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(max_entries, 2); + __type(key, int); + __type(value, __u32); +} perf_event_map SEC(".maps"); + +SEC("sockops") +int bpf_testcb(struct bpf_sock_ops *skops) +{ + int rv = -1; + int op; + + op = (int) skops->op; + + if (bpf_ntohl(skops->remote_port) != TESTPORT) { + skops->reply = -1; + return 0; + } + + switch (op) { + case BPF_SOCK_OPS_TIMEOUT_INIT: + case BPF_SOCK_OPS_RWND_INIT: + case BPF_SOCK_OPS_NEEDS_ECN: + case BPF_SOCK_OPS_BASE_RTT: + case BPF_SOCK_OPS_RTO_CB: + rv = 1; + break; + + case BPF_SOCK_OPS_TCP_CONNECT_CB: + case BPF_SOCK_OPS_TCP_LISTEN_CB: + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + bpf_sock_ops_cb_flags_set(skops, (BPF_SOCK_OPS_RETRANS_CB_FLAG| + BPF_SOCK_OPS_RTO_CB_FLAG)); + rv = 1; + break; + case BPF_SOCK_OPS_RETRANS_CB: { + __u32 key = 0; + struct tcpnotify_globals g, *gp; + struct tcp_notifier msg = { + .type = 0xde, + .subtype = 0xad, + .source = 0xbe, + .hash = 0xef, + }; + + rv = 1; + + /* Update results */ + gp = bpf_map_lookup_elem(&global_map, &key); + if (!gp) + break; + g = *gp; + g.total_retrans = skops->total_retrans; + g.ncalls++; + bpf_map_update_elem(&global_map, &key, &g, + BPF_ANY); + bpf_perf_event_output(skops, &perf_event_map, + BPF_F_CURRENT_CPU, + &msg, sizeof(msg)); + } + break; + default: + rv = -1; + } + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_time_tai.c b/tools/testing/selftests/bpf/progs/test_time_tai.c new file mode 100644 index 0000000000..7ea0863f3d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_time_tai.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2022 Linutronix GmbH */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +SEC("tc") +int time_tai(struct __sk_buff *skb) +{ + __u64 ts1, ts2; + + /* Get TAI timestamps */ + ts1 = bpf_ktime_get_tai_ns(); + ts2 = bpf_ktime_get_tai_ns(); + + /* Save TAI timestamps (Note: skb->hwtstamp is read-only) */ + skb->tstamp = ts1; + skb->cb[0] = ts2 & 0xffffffff; + skb->cb[1] = ts2 >> 32; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_trace_ext.c b/tools/testing/selftests/bpf/progs/test_trace_ext.c new file mode 100644 index 0000000000..d19a634d0e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_trace_ext.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include <stdbool.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_tracing.h> + +__u64 ext_called = 0; + +SEC("freplace/test_pkt_md_access") +int test_pkt_md_access_new(struct __sk_buff *skb) +{ + ext_called = skb->len; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_trace_ext_tracing.c b/tools/testing/selftests/bpf/progs/test_trace_ext_tracing.c new file mode 100644 index 0000000000..52f3baf98f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_trace_ext_tracing.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +__u64 fentry_called = 0; + +SEC("fentry/test_pkt_md_access_new") +int BPF_PROG(fentry, struct sk_buff *skb) +{ + fentry_called = skb->len; + return 0; +} + +__u64 fexit_called = 0; + +SEC("fexit/test_pkt_md_access_new") +int BPF_PROG(fexit, struct sk_buff *skb) +{ + fexit_called = skb->len; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c new file mode 100644 index 0000000000..4cb8bbb6a3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tracepoint.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Facebook + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +/* taken from /sys/kernel/tracing/events/sched/sched_switch/format */ +struct sched_switch_args { + unsigned long long pad; + char prev_comm[TASK_COMM_LEN]; + int prev_pid; + int prev_prio; + long long prev_state; + char next_comm[TASK_COMM_LEN]; + int next_pid; + int next_prio; +}; + +SEC("tracepoint/sched/sched_switch") +int oncpu(struct sched_switch_args *ctx) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_trampoline_count.c b/tools/testing/selftests/bpf/progs/test_trampoline_count.c new file mode 100644 index 0000000000..7765720da7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_trampoline_count.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +SEC("fentry/bpf_modify_return_test") +int BPF_PROG(fentry_test, int a, int *b) +{ + return 0; +} + +SEC("fmod_ret/bpf_modify_return_test") +int BPF_PROG(fmod_ret_test, int a, int *b, int ret) +{ + return 0; +} + +SEC("fexit/bpf_modify_return_test") +int BPF_PROG(fexit_test, int a, int *b, int ret) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c new file mode 100644 index 0000000000..f66af753bb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -0,0 +1,982 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2016 VMware + * Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <stddef.h> +#include <string.h> +#include <arpa/inet.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_tunnel.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/icmp.h> +#include <linux/types.h> +#include <linux/socket.h> +#include <linux/pkt_cls.h> +#include <linux/erspan.h> +#include <linux/udp.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define log_err(__ret) bpf_printk("ERROR line:%d ret:%d\n", __LINE__, __ret) + +#define VXLAN_UDP_PORT 4789 + +/* Only IPv4 address assigned to veth1. + * 172.16.1.200 + */ +#define ASSIGNED_ADDR_VETH1 0xac1001c8 + +struct geneve_opt { + __be16 opt_class; + __u8 type; + __u8 length:5; + __u8 r3:1; + __u8 r2:1; + __u8 r1:1; + __u8 opt_data[8]; /* hard-coded to 8 byte */ +}; + +struct vxlanhdr { + __be32 vx_flags; + __be32 vx_vni; +} __attribute__((packed)); + +struct vxlan_metadata { + __u32 gbp; +}; + +struct bpf_fou_encap { + __be16 sport; + __be16 dport; +}; + +enum bpf_fou_encap_type { + FOU_BPF_ENCAP_FOU, + FOU_BPF_ENCAP_GUE, +}; + +int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx, + struct bpf_fou_encap *encap, int type) __ksym; +int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx, + struct bpf_fou_encap *encap) __ksym; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} local_ip_map SEC(".maps"); + +SEC("tc") +int gre_set_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX | BPF_F_SEQ_NUMBER); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int gre_set_tunnel_no_key(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX | BPF_F_SEQ_NUMBER | + BPF_F_NO_TUNNEL_KEY); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int gre_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + bpf_printk("key %d remote ip 0x%x\n", key.tunnel_id, key.remote_ipv4); + return TC_ACT_OK; +} + +SEC("tc") +int ip6gretap_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + key.tunnel_label = 0xabcde; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX | + BPF_F_SEQ_NUMBER); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int ip6gretap_get_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + bpf_printk("key %d remote ip6 ::%x label %x\n", + key.tunnel_id, key.remote_ipv6[3], key.tunnel_label); + + return TC_ACT_OK; +} + +SEC("tc") +int erspan_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct erspan_metadata md; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&md, 0, sizeof(md)); +#ifdef ERSPAN_V1 + md.version = 1; + md.u.index = bpf_htonl(123); +#else + __u8 direction = 1; + __u8 hwid = 7; + + md.version = 2; + md.u.md2.dir = direction; + md.u.md2.hwid = hwid & 0xf; + md.u.md2.hwid_upper = (hwid >> 4) & 0x3; +#endif + + ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int erspan_get_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct erspan_metadata md; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + bpf_printk("key %d remote ip 0x%x erspan version %d\n", + key.tunnel_id, key.remote_ipv4, md.version); + +#ifdef ERSPAN_V1 + index = bpf_ntohl(md.u.index); + bpf_printk("\tindex %x\n", index); +#else + bpf_printk("\tdirection %d hwid %x timestamp %u\n", + md.u.md2.dir, + (md.u.md2.hwid_upper << 4) + md.u.md2.hwid, + bpf_ntohl(md.u.md2.timestamp)); +#endif + + return TC_ACT_OK; +} + +SEC("tc") +int ip4ip6erspan_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct erspan_metadata md; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&md, 0, sizeof(md)); + +#ifdef ERSPAN_V1 + md.u.index = bpf_htonl(123); + md.version = 1; +#else + __u8 direction = 0; + __u8 hwid = 17; + + md.version = 2; + md.u.md2.dir = direction; + md.u.md2.hwid = hwid & 0xf; + md.u.md2.hwid_upper = (hwid >> 4) & 0x3; +#endif + + ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int ip4ip6erspan_get_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct erspan_metadata md; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + bpf_printk("ip6erspan get key %d remote ip6 ::%x erspan version %d\n", + key.tunnel_id, key.remote_ipv4, md.version); + +#ifdef ERSPAN_V1 + index = bpf_ntohl(md.u.index); + bpf_printk("\tindex %x\n", index); +#else + bpf_printk("\tdirection %d hwid %x timestamp %u\n", + md.u.md2.dir, + (md.u.md2.hwid_upper << 4) + md.u.md2.hwid, + bpf_ntohl(md.u.md2.timestamp)); +#endif + + return TC_ACT_OK; +} + +SEC("tc") +int vxlan_set_tunnel_dst(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct vxlan_metadata md; + __u32 index = 0; + __u32 *local_ip = NULL; + int ret = 0; + + local_ip = bpf_map_lookup_elem(&local_ip_map, &index); + if (!local_ip) { + log_err(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&key, 0x0, sizeof(key)); + key.local_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.remote_ipv4 = *local_ip; + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + md.gbp = 0x800FF; /* Set VXLAN Group Policy extension */ + ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int vxlan_set_tunnel_src(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct vxlan_metadata md; + __u32 index = 0; + __u32 *local_ip = NULL; + int ret = 0; + + local_ip = bpf_map_lookup_elem(&local_ip_map, &index); + if (!local_ip) { + log_err(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&key, 0x0, sizeof(key)); + key.local_ipv4 = *local_ip; + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + md.gbp = 0x800FF; /* Set VXLAN Group Policy extension */ + ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int vxlan_get_tunnel_src(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + struct vxlan_metadata md; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_FLAGS); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + if (key.local_ipv4 != ASSIGNED_ADDR_VETH1 || md.gbp != 0x800FF || + !(key.tunnel_flags & TUNNEL_KEY) || + (key.tunnel_flags & TUNNEL_CSUM)) { + bpf_printk("vxlan key %d local ip 0x%x remote ip 0x%x gbp 0x%x flags 0x%x\n", + key.tunnel_id, key.local_ipv4, + key.remote_ipv4, md.gbp, + bpf_ntohs(key.tunnel_flags)); + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int veth_set_outer_dst(struct __sk_buff *skb) +{ + struct ethhdr *eth = (struct ethhdr *)(long)skb->data; + __u32 assigned_ip = bpf_htonl(ASSIGNED_ADDR_VETH1); + void *data_end = (void *)(long)skb->data_end; + struct udphdr *udph; + struct iphdr *iph; + int ret = 0; + __s64 csum; + + if ((void *)eth + sizeof(*eth) > data_end) { + log_err(ret); + return TC_ACT_SHOT; + } + + if (eth->h_proto != bpf_htons(ETH_P_IP)) + return TC_ACT_OK; + + iph = (struct iphdr *)(eth + 1); + if ((void *)iph + sizeof(*iph) > data_end) { + log_err(ret); + return TC_ACT_SHOT; + } + if (iph->protocol != IPPROTO_UDP) + return TC_ACT_OK; + + udph = (struct udphdr *)(iph + 1); + if ((void *)udph + sizeof(*udph) > data_end) { + log_err(ret); + return TC_ACT_SHOT; + } + if (udph->dest != bpf_htons(VXLAN_UDP_PORT)) + return TC_ACT_OK; + + if (iph->daddr != assigned_ip) { + csum = bpf_csum_diff(&iph->daddr, sizeof(__u32), &assigned_ip, + sizeof(__u32), 0); + if (bpf_skb_store_bytes(skb, ETH_HLEN + offsetof(struct iphdr, daddr), + &assigned_ip, sizeof(__u32), 0) < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + if (bpf_l3_csum_replace(skb, ETH_HLEN + offsetof(struct iphdr, check), + 0, csum, 0) < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + bpf_skb_change_type(skb, PACKET_HOST); + } + return TC_ACT_OK; +} + +SEC("tc") +int ip6vxlan_set_tunnel_dst(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + __u32 index = 0; + __u32 *local_ip; + int ret = 0; + + local_ip = bpf_map_lookup_elem(&local_ip_map, &index); + if (!local_ip) { + log_err(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&key, 0x0, sizeof(key)); + key.local_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.remote_ipv6[3] = bpf_htonl(*local_ip); + key.tunnel_id = 22; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int ip6vxlan_set_tunnel_src(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + __u32 index = 0; + __u32 *local_ip; + int ret = 0; + + local_ip = bpf_map_lookup_elem(&local_ip_map, &index); + if (!local_ip) { + log_err(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&key, 0x0, sizeof(key)); + key.local_ipv6[3] = bpf_htonl(*local_ip); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_id = 22; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int ip6vxlan_get_tunnel_src(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + __u32 index = 0; + __u32 *local_ip; + int ret = 0; + + local_ip = bpf_map_lookup_elem(&local_ip_map, &index); + if (!local_ip) { + log_err(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6 | BPF_F_TUNINFO_FLAGS); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + if (bpf_ntohl(key.local_ipv6[3]) != *local_ip || + !(key.tunnel_flags & TUNNEL_KEY) || + !(key.tunnel_flags & TUNNEL_CSUM)) { + bpf_printk("ip6vxlan key %d local ip6 ::%x remote ip6 ::%x label 0x%x flags 0x%x\n", + key.tunnel_id, bpf_ntohl(key.local_ipv6[3]), + bpf_ntohl(key.remote_ipv6[3]), key.tunnel_label, + bpf_ntohs(key.tunnel_flags)); + bpf_printk("local_ip 0x%x\n", *local_ip); + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int geneve_set_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + struct geneve_opt gopt; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + __builtin_memset(&gopt, 0x0, sizeof(gopt)); + gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ + gopt.type = 0x08; + gopt.r1 = 0; + gopt.r2 = 0; + gopt.r3 = 0; + gopt.length = 2; /* 4-byte multiple */ + *(int *) &gopt.opt_data = bpf_htonl(0xdeadbeef); + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int geneve_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + struct geneve_opt gopt; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) + gopt.opt_class = 0; + + bpf_printk("key %d remote ip 0x%x geneve class 0x%x\n", + key.tunnel_id, key.remote_ipv4, gopt.opt_class); + return TC_ACT_OK; +} + +SEC("tc") +int ip6geneve_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct geneve_opt gopt; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_id = 22; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&gopt, 0x0, sizeof(gopt)); + gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ + gopt.type = 0x08; + gopt.r1 = 0; + gopt.r2 = 0; + gopt.r3 = 0; + gopt.length = 2; /* 4-byte multiple */ + *(int *) &gopt.opt_data = bpf_htonl(0xfeedbeef); + + ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int ip6geneve_get_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct geneve_opt gopt; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) + gopt.opt_class = 0; + + bpf_printk("key %d remote ip 0x%x geneve class 0x%x\n", + key.tunnel_id, key.remote_ipv4, gopt.opt_class); + + return TC_ACT_OK; +} + +SEC("tc") +int ipip_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key = {}; + void *data = (void *)(long)skb->data; + struct iphdr *iph = data; + void *data_end = (void *)(long)skb->data_end; + int ret; + + /* single length check */ + if (data + sizeof(*iph) > data_end) { + log_err(1); + return TC_ACT_SHOT; + } + + key.tunnel_ttl = 64; + if (iph->protocol == IPPROTO_ICMP) { + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + } + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int ipip_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + bpf_printk("remote ip 0x%x\n", key.remote_ipv4); + return TC_ACT_OK; +} + +SEC("tc") +int ipip_gue_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key = {}; + struct bpf_fou_encap encap = {}; + void *data = (void *)(long)skb->data; + struct iphdr *iph = data; + void *data_end = (void *)(long)skb->data_end; + int ret; + + if (data + sizeof(*iph) > data_end) { + log_err(1); + return TC_ACT_SHOT; + } + + key.tunnel_ttl = 64; + if (iph->protocol == IPPROTO_ICMP) + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + encap.sport = 0; + encap.dport = bpf_htons(5555); + + ret = bpf_skb_set_fou_encap(skb, &encap, FOU_BPF_ENCAP_GUE); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int ipip_fou_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key = {}; + struct bpf_fou_encap encap = {}; + void *data = (void *)(long)skb->data; + struct iphdr *iph = data; + void *data_end = (void *)(long)skb->data_end; + int ret; + + if (data + sizeof(*iph) > data_end) { + log_err(1); + return TC_ACT_SHOT; + } + + key.tunnel_ttl = 64; + if (iph->protocol == IPPROTO_ICMP) + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + encap.sport = 0; + encap.dport = bpf_htons(5555); + + ret = bpf_skb_set_fou_encap(skb, &encap, FOU_BPF_ENCAP_FOU); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int ipip_encap_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key = {}; + struct bpf_fou_encap encap = {}; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_fou_encap(skb, &encap); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + if (bpf_ntohs(encap.dport) != 5555) + return TC_ACT_SHOT; + + bpf_printk("%d remote ip 0x%x, sport %d, dport %d\n", ret, + key.remote_ipv4, bpf_ntohs(encap.sport), + bpf_ntohs(encap.dport)); + return TC_ACT_OK; +} + +SEC("tc") +int ipip6_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key = {}; + void *data = (void *)(long)skb->data; + struct iphdr *iph = data; + void *data_end = (void *)(long)skb->data_end; + int ret; + + /* single length check */ + if (data + sizeof(*iph) > data_end) { + log_err(1); + return TC_ACT_SHOT; + } + + __builtin_memset(&key, 0x0, sizeof(key)); + key.tunnel_ttl = 64; + if (iph->protocol == IPPROTO_ICMP) { + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + } + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int ipip6_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + bpf_printk("remote ip6 %x::%x\n", bpf_htonl(key.remote_ipv6[0]), + bpf_htonl(key.remote_ipv6[3])); + return TC_ACT_OK; +} + +SEC("tc") +int ip6ip6_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key = {}; + void *data = (void *)(long)skb->data; + struct ipv6hdr *iph = data; + void *data_end = (void *)(long)skb->data_end; + int ret; + + /* single length check */ + if (data + sizeof(*iph) > data_end) { + log_err(1); + return TC_ACT_SHOT; + } + + key.tunnel_ttl = 64; + if (iph->nexthdr == 58 /* NEXTHDR_ICMP */) { + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + } + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") +int ip6ip6_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + bpf_printk("remote ip6 %x::%x\n", bpf_htonl(key.remote_ipv6[0]), + bpf_htonl(key.remote_ipv6[3])); + return TC_ACT_OK; +} + +SEC("tc") +int xfrm_get_state(struct __sk_buff *skb) +{ + struct bpf_xfrm_state x; + int ret; + + ret = bpf_skb_get_xfrm_state(skb, 0, &x, sizeof(x), 0); + if (ret < 0) + return TC_ACT_OK; + + bpf_printk("reqid %d spi 0x%x remote ip 0x%x\n", + x.reqid, bpf_ntohl(x.spi), + bpf_ntohl(x.remote_ipv4)); + return TC_ACT_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_unpriv_bpf_disabled.c b/tools/testing/selftests/bpf/progs/test_unpriv_bpf_disabled.c new file mode 100644 index 0000000000..fc423e43a3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_unpriv_bpf_disabled.c @@ -0,0 +1,83 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022, Oracle and/or its affiliates. */ + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +__u32 perfbuf_val = 0; +__u32 ringbuf_val = 0; + +int test_pid; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} array SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} percpu_array SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} hash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} percpu_hash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __type(key, __u32); + __type(value, __u32); +} perfbuf SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 1 << 12); +} ringbuf SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} prog_array SEC(".maps"); + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int sys_nanosleep_enter(void *ctx) +{ + int cur_pid; + + cur_pid = bpf_get_current_pid_tgid() >> 32; + + if (cur_pid != test_pid) + return 0; + + bpf_perf_event_output(ctx, &perfbuf, BPF_F_CURRENT_CPU, &perfbuf_val, sizeof(perfbuf_val)); + bpf_ringbuf_output(&ringbuf, &ringbuf_val, sizeof(ringbuf_val), 0); + + return 0; +} + +SEC("perf_event") +int handle_perf_event(void *ctx) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c b/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c new file mode 100644 index 0000000000..da4bf89d00 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022, Oracle and/or its affiliates. */ + +#include "vmlinux.h" + +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +int uprobe_byname_parm1 = 0; +int uprobe_byname_ran = 0; +int uretprobe_byname_rc = 0; +int uretprobe_byname_ret = 0; +int uretprobe_byname_ran = 0; +u64 uprobe_byname2_parm1 = 0; +int uprobe_byname2_ran = 0; +u64 uretprobe_byname2_rc = 0; +int uretprobe_byname2_ran = 0; + +int test_pid; + +int a[8]; + +/* This program cannot auto-attach, but that should not stop other + * programs from attaching. + */ +SEC("uprobe") +int handle_uprobe_noautoattach(struct pt_regs *ctx) +{ + return 0; +} + +SEC("uprobe//proc/self/exe:autoattach_trigger_func") +int BPF_UPROBE(handle_uprobe_byname + , int arg1 + , int arg2 + , int arg3 +#if FUNC_REG_ARG_CNT > 3 + , int arg4 +#endif +#if FUNC_REG_ARG_CNT > 4 + , int arg5 +#endif +#if FUNC_REG_ARG_CNT > 5 + , int arg6 +#endif +#if FUNC_REG_ARG_CNT > 6 + , int arg7 +#endif +#if FUNC_REG_ARG_CNT > 7 + , int arg8 +#endif +) +{ + uprobe_byname_parm1 = PT_REGS_PARM1_CORE(ctx); + uprobe_byname_ran = 1; + + a[0] = arg1; + a[1] = arg2; + a[2] = arg3; +#if FUNC_REG_ARG_CNT > 3 + a[3] = arg4; +#endif +#if FUNC_REG_ARG_CNT > 4 + a[4] = arg5; +#endif +#if FUNC_REG_ARG_CNT > 5 + a[5] = arg6; +#endif +#if FUNC_REG_ARG_CNT > 6 + a[6] = arg7; +#endif +#if FUNC_REG_ARG_CNT > 7 + a[7] = arg8; +#endif + return 0; +} + +SEC("uretprobe//proc/self/exe:autoattach_trigger_func") +int BPF_URETPROBE(handle_uretprobe_byname, int ret) +{ + uretprobe_byname_rc = PT_REGS_RC_CORE(ctx); + uretprobe_byname_ret = ret; + uretprobe_byname_ran = 2; + + return 0; +} + + +SEC("uprobe/libc.so.6:fopen") +int BPF_UPROBE(handle_uprobe_byname2, const char *pathname, const char *mode) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + + /* ignore irrelevant invocations */ + if (test_pid != pid) + return 0; + uprobe_byname2_parm1 = (u64)(long)pathname; + uprobe_byname2_ran = 3; + return 0; +} + +SEC("uretprobe/libc.so.6:fopen") +int BPF_URETPROBE(handle_uretprobe_byname2, void *ret) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + + /* ignore irrelevant invocations */ + if (test_pid != pid) + return 0; + uretprobe_byname2_rc = (u64)(long)ret; + uretprobe_byname2_ran = 4; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_urandom_usdt.c b/tools/testing/selftests/bpf/progs/test_urandom_usdt.c new file mode 100644 index 0000000000..3539b02bd5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_urandom_usdt.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/usdt.bpf.h> + +int urand_pid; + +int urand_read_without_sema_call_cnt; +int urand_read_without_sema_buf_sz_sum; + +SEC("usdt/./urandom_read:urand:read_without_sema") +int BPF_USDT(urand_read_without_sema, int iter_num, int iter_cnt, int buf_sz) +{ + if (urand_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + __sync_fetch_and_add(&urand_read_without_sema_call_cnt, 1); + __sync_fetch_and_add(&urand_read_without_sema_buf_sz_sum, buf_sz); + + return 0; +} + +int urand_read_with_sema_call_cnt; +int urand_read_with_sema_buf_sz_sum; + +SEC("usdt/./urandom_read:urand:read_with_sema") +int BPF_USDT(urand_read_with_sema, int iter_num, int iter_cnt, int buf_sz) +{ + if (urand_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + __sync_fetch_and_add(&urand_read_with_sema_call_cnt, 1); + __sync_fetch_and_add(&urand_read_with_sema_buf_sz_sum, buf_sz); + + return 0; +} + +int urandlib_read_without_sema_call_cnt; +int urandlib_read_without_sema_buf_sz_sum; + +SEC("usdt/./liburandom_read.so:urandlib:read_without_sema") +int BPF_USDT(urandlib_read_without_sema, int iter_num, int iter_cnt, int buf_sz) +{ + if (urand_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + __sync_fetch_and_add(&urandlib_read_without_sema_call_cnt, 1); + __sync_fetch_and_add(&urandlib_read_without_sema_buf_sz_sum, buf_sz); + + return 0; +} + +int urandlib_read_with_sema_call_cnt; +int urandlib_read_with_sema_buf_sz_sum; + +SEC("usdt/./liburandom_read.so:urandlib:read_with_sema") +int BPF_USDT(urandlib_read_with_sema, int iter_num, int iter_cnt, int buf_sz) +{ + if (urand_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + __sync_fetch_and_add(&urandlib_read_with_sema_call_cnt, 1); + __sync_fetch_and_add(&urandlib_read_with_sema_buf_sz_sum, buf_sz); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_usdt.c b/tools/testing/selftests/bpf/progs/test_usdt.c new file mode 100644 index 0000000000..505aab9a52 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_usdt.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/usdt.bpf.h> + +int my_pid; + +int usdt0_called; +u64 usdt0_cookie; +int usdt0_arg_cnt; +int usdt0_arg_ret; + +SEC("usdt") +int usdt0(struct pt_regs *ctx) +{ + long tmp; + + if (my_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + __sync_fetch_and_add(&usdt0_called, 1); + + usdt0_cookie = bpf_usdt_cookie(ctx); + usdt0_arg_cnt = bpf_usdt_arg_cnt(ctx); + /* should return -ENOENT for any arg_num */ + usdt0_arg_ret = bpf_usdt_arg(ctx, bpf_get_prandom_u32(), &tmp); + return 0; +} + +int usdt3_called; +u64 usdt3_cookie; +int usdt3_arg_cnt; +int usdt3_arg_rets[3]; +u64 usdt3_args[3]; + +SEC("usdt//proc/self/exe:test:usdt3") +int usdt3(struct pt_regs *ctx) +{ + long tmp; + + if (my_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + __sync_fetch_and_add(&usdt3_called, 1); + + usdt3_cookie = bpf_usdt_cookie(ctx); + usdt3_arg_cnt = bpf_usdt_arg_cnt(ctx); + + usdt3_arg_rets[0] = bpf_usdt_arg(ctx, 0, &tmp); + usdt3_args[0] = (int)tmp; + + usdt3_arg_rets[1] = bpf_usdt_arg(ctx, 1, &tmp); + usdt3_args[1] = (long)tmp; + + usdt3_arg_rets[2] = bpf_usdt_arg(ctx, 2, &tmp); + usdt3_args[2] = (uintptr_t)tmp; + + return 0; +} + +int usdt12_called; +u64 usdt12_cookie; +int usdt12_arg_cnt; +u64 usdt12_args[12]; + +SEC("usdt//proc/self/exe:test:usdt12") +int BPF_USDT(usdt12, int a1, int a2, long a3, long a4, unsigned a5, + long a6, __u64 a7, uintptr_t a8, int a9, short a10, + short a11, signed char a12) +{ + if (my_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + __sync_fetch_and_add(&usdt12_called, 1); + + usdt12_cookie = bpf_usdt_cookie(ctx); + usdt12_arg_cnt = bpf_usdt_arg_cnt(ctx); + + usdt12_args[0] = a1; + usdt12_args[1] = a2; + usdt12_args[2] = a3; + usdt12_args[3] = a4; + usdt12_args[4] = a5; + usdt12_args[5] = a6; + usdt12_args[6] = a7; + usdt12_args[7] = a8; + usdt12_args[8] = a9; + usdt12_args[9] = a10; + usdt12_args[10] = a11; + usdt12_args[11] = a12; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_usdt_multispec.c b/tools/testing/selftests/bpf/progs/test_usdt_multispec.c new file mode 100644 index 0000000000..962f346206 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_usdt_multispec.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/usdt.bpf.h> + +/* this file is linked together with test_usdt.c to validate that usdt.bpf.h + * can be included in multiple .bpf.c files forming single final BPF object + * file + */ + +extern int my_pid; + +int usdt_100_called; +int usdt_100_sum; + +SEC("usdt//proc/self/exe:test:usdt_100") +int BPF_USDT(usdt_100, int x) +{ + if (my_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + __sync_fetch_and_add(&usdt_100_called, 1); + __sync_fetch_and_add(&usdt_100_sum, x); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_user_ringbuf.h b/tools/testing/selftests/bpf/progs/test_user_ringbuf.h new file mode 100644 index 0000000000..1643b4d59b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_user_ringbuf.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#ifndef _TEST_USER_RINGBUF_H +#define _TEST_USER_RINGBUF_H + +#define TEST_OP_64 4 +#define TEST_OP_32 2 + +enum test_msg_op { + TEST_MSG_OP_INC64, + TEST_MSG_OP_INC32, + TEST_MSG_OP_MUL64, + TEST_MSG_OP_MUL32, + + // Must come last. + TEST_MSG_OP_NUM_OPS, +}; + +struct test_msg { + enum test_msg_op msg_op; + union { + __s64 operand_64; + __s32 operand_32; + }; +}; + +struct sample { + int pid; + int seq; + long value; + char comm[16]; +}; + +#endif /* _TEST_USER_RINGBUF_H */ diff --git a/tools/testing/selftests/bpf/progs/test_varlen.c b/tools/testing/selftests/bpf/progs/test_varlen.c new file mode 100644 index 0000000000..20eb7d422c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_varlen.c @@ -0,0 +1,163 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +#define MAX_LEN 256 + +char buf_in1[MAX_LEN] = {}; +char buf_in2[MAX_LEN] = {}; + +int test_pid = 0; +bool capture = false; + +/* .bss */ +__u64 payload1_len1 = 0; +__u64 payload1_len2 = 0; +__u64 total1 = 0; +char payload1[MAX_LEN + MAX_LEN] = {}; +__u64 ret_bad_read = 0; + +/* .data */ +int payload2_len1 = -1; +int payload2_len2 = -1; +int total2 = -1; +char payload2[MAX_LEN + MAX_LEN] = { 1 }; + +int payload3_len1 = -1; +int payload3_len2 = -1; +int total3= -1; +char payload3[MAX_LEN + MAX_LEN] = { 1 }; + +int payload4_len1 = -1; +int payload4_len2 = -1; +int total4= -1; +char payload4[MAX_LEN + MAX_LEN] = { 1 }; + +char payload_bad[5] = { 0x42, 0x42, 0x42, 0x42, 0x42 }; + +SEC("raw_tp/sys_enter") +int handler64_unsigned(void *regs) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + void *payload = payload1; + long len; + + /* ignore irrelevant invocations */ + if (test_pid != pid || !capture) + return 0; + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]); + if (len >= 0) { + payload += len; + payload1_len1 = len; + } + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]); + if (len >= 0) { + payload += len; + payload1_len2 = len; + } + + total1 = payload - (void *)payload1; + + ret_bad_read = bpf_probe_read_kernel_str(payload_bad + 2, 1, (void *) -1); + + return 0; +} + +SEC("raw_tp/sys_exit") +int handler64_signed(void *regs) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + void *payload = payload3; + long len; + + /* ignore irrelevant invocations */ + if (test_pid != pid || !capture) + return 0; + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]); + if (len >= 0) { + payload += len; + payload3_len1 = len; + } + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]); + if (len >= 0) { + payload += len; + payload3_len2 = len; + } + total3 = payload - (void *)payload3; + + return 0; +} + +SEC("tp/raw_syscalls/sys_enter") +int handler32_unsigned(void *regs) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + void *payload = payload2; + u32 len; + + /* ignore irrelevant invocations */ + if (test_pid != pid || !capture) + return 0; + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]); + if (len <= MAX_LEN) { + payload += len; + payload2_len1 = len; + } + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]); + if (len <= MAX_LEN) { + payload += len; + payload2_len2 = len; + } + + total2 = payload - (void *)payload2; + + return 0; +} + +SEC("tp/raw_syscalls/sys_exit") +int handler32_signed(void *regs) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + void *payload = payload4; + long len; + + /* ignore irrelevant invocations */ + if (test_pid != pid || !capture) + return 0; + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]); + if (len >= 0) { + payload += len; + payload4_len1 = len; + } + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]); + if (len >= 0) { + payload += len; + payload4_len2 = len; + } + total4 = payload - (void *)payload4; + + return 0; +} + +SEC("tp/syscalls/sys_exit_getpid") +int handler_exit(void *regs) +{ + long bla; + + if (bpf_probe_read_kernel(&bla, sizeof(bla), 0)) + return 1; + else + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale1.c b/tools/testing/selftests/bpf/progs/test_verif_scale1.c new file mode 100644 index 0000000000..323a73fb2e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_verif_scale1.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#define ATTR __attribute__((noinline)) +#include "test_jhash.h" + +SEC("tc") +int balancer_ingress(struct __sk_buff *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + void *ptr; + int nh_off, i = 0; + + nh_off = 14; + + /* pragma unroll doesn't work on large loops */ + +#define C do { \ + ptr = data + i; \ + if (ptr + nh_off > data_end) \ + break; \ + ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \ + } while (0); +#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C; + C30;C30;C30; /* 90 calls */ + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale2.c b/tools/testing/selftests/bpf/progs/test_verif_scale2.c new file mode 100644 index 0000000000..f5318f7570 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_verif_scale2.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#define ATTR __always_inline +#include "test_jhash.h" + +SEC("tc") +int balancer_ingress(struct __sk_buff *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + void *ptr; + int nh_off, i = 0; + + nh_off = 14; + + /* pragma unroll doesn't work on large loops */ + +#define C do { \ + ptr = data + i; \ + if (ptr + nh_off > data_end) \ + break; \ + ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \ + } while (0); +#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C; + C30;C30;C30; /* 90 calls */ + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale3.c b/tools/testing/selftests/bpf/progs/test_verif_scale3.c new file mode 100644 index 0000000000..2e06dbb1ad --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_verif_scale3.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#define ATTR __attribute__((noinline)) +#include "test_jhash.h" + +SEC("tc") +int balancer_ingress(struct __sk_buff *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + void *ptr; + int nh_off, i = 0; + + nh_off = 32; + + /* pragma unroll doesn't work on large loops */ + +#define C do { \ + ptr = data + i; \ + if (ptr + nh_off > data_end) \ + break; \ + ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \ + } while (0); +#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C; + C30;C30;C30; /* 90 calls */ + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c new file mode 100644 index 0000000000..7748cc23de --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (C) 2022 Huawei Technologies Duesseldorf GmbH + * + * Author: Roberto Sassu <roberto.sassu@huawei.com> + */ + +#include "vmlinux.h" +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define MAX_DATA_SIZE (1024 * 1024) +#define MAX_SIG_SIZE 1024 + +extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym; +extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym; +extern void bpf_key_put(struct bpf_key *key) __ksym; +extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr, + struct bpf_dynptr *sig_ptr, + struct bpf_key *trusted_keyring) __ksym; + +__u32 monitored_pid; +__u32 user_keyring_serial; +__u64 system_keyring_id; + +struct data { + __u8 data[MAX_DATA_SIZE]; + __u32 data_len; + __u8 sig[MAX_SIG_SIZE]; + __u32 sig_len; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct data); +} data_input SEC(".maps"); + +char _license[] SEC("license") = "GPL"; + +SEC("lsm.s/bpf") +int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size) +{ + struct bpf_dynptr data_ptr, sig_ptr; + struct data *data_val; + struct bpf_key *trusted_keyring; + __u32 pid; + __u64 value; + int ret, zero = 0; + + pid = bpf_get_current_pid_tgid() >> 32; + if (pid != monitored_pid) + return 0; + + data_val = bpf_map_lookup_elem(&data_input, &zero); + if (!data_val) + return 0; + + ret = bpf_probe_read_kernel(&value, sizeof(value), &attr->value); + if (ret) + return ret; + + ret = bpf_copy_from_user(data_val, sizeof(struct data), + (void *)(unsigned long)value); + if (ret) + return ret; + + if (data_val->data_len > sizeof(data_val->data)) + return -EINVAL; + + bpf_dynptr_from_mem(data_val->data, data_val->data_len, 0, &data_ptr); + + if (data_val->sig_len > sizeof(data_val->sig)) + return -EINVAL; + + bpf_dynptr_from_mem(data_val->sig, data_val->sig_len, 0, &sig_ptr); + + if (user_keyring_serial) + trusted_keyring = bpf_lookup_user_key(user_keyring_serial, 0); + else + trusted_keyring = bpf_lookup_system_key(system_keyring_id); + + if (!trusted_keyring) + return -ENOENT; + + ret = bpf_verify_pkcs7_signature(&data_ptr, &sig_ptr, trusted_keyring); + + bpf_key_put(trusted_keyring); + + return ret; +} diff --git a/tools/testing/selftests/bpf/progs/test_vmlinux.c b/tools/testing/selftests/bpf/progs/test_vmlinux.c new file mode 100644 index 0000000000..4b8e37f7fd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_vmlinux.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include <asm/unistd.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +#define MY_TV_NSEC 1337 + +bool tp_called = false; +bool raw_tp_called = false; +bool tp_btf_called = false; +bool kprobe_called = false; +bool fentry_called = false; + +SEC("tp/syscalls/sys_enter_nanosleep") +int handle__tp(struct trace_event_raw_sys_enter *args) +{ + struct __kernel_timespec *ts; + long tv_nsec; + + if (args->id != __NR_nanosleep) + return 0; + + ts = (void *)args->args[0]; + if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) || + tv_nsec != MY_TV_NSEC) + return 0; + + tp_called = true; + return 0; +} + +SEC("raw_tp/sys_enter") +int BPF_PROG(handle__raw_tp, struct pt_regs *regs, long id) +{ + struct __kernel_timespec *ts; + long tv_nsec; + + if (id != __NR_nanosleep) + return 0; + + ts = (void *)PT_REGS_PARM1_CORE_SYSCALL(regs); + if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) || + tv_nsec != MY_TV_NSEC) + return 0; + + raw_tp_called = true; + return 0; +} + +SEC("tp_btf/sys_enter") +int BPF_PROG(handle__tp_btf, struct pt_regs *regs, long id) +{ + struct __kernel_timespec *ts; + long tv_nsec; + + if (id != __NR_nanosleep) + return 0; + + ts = (void *)PT_REGS_PARM1_CORE_SYSCALL(regs); + if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) || + tv_nsec != MY_TV_NSEC) + return 0; + + tp_btf_called = true; + return 0; +} + +SEC("kprobe/hrtimer_start_range_ns") +int BPF_KPROBE(handle__kprobe, struct hrtimer *timer, ktime_t tim, u64 delta_ns, + const enum hrtimer_mode mode) +{ + if (tim == MY_TV_NSEC) + kprobe_called = true; + return 0; +} + +SEC("fentry/hrtimer_start_range_ns") +int BPF_PROG(handle__fentry, struct hrtimer *timer, ktime_t tim, u64 delta_ns, + const enum hrtimer_mode mode) +{ + if (tim == MY_TV_NSEC) + fentry_called = true; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c new file mode 100644 index 0000000000..d7a9a74b72 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp.c @@ -0,0 +1,233 @@ +/* Copyright (c) 2016,2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/udp.h> +#include <linux/tcp.h> +#include <linux/pkt_cls.h> +#include <sys/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include "test_iptunnel_common.h" + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 256); + __type(key, __u32); + __type(value, __u64); +} rxcnt SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, MAX_IPTNL_ENTRIES); + __type(key, struct vip); + __type(value, struct iptnl_info); +} vip2tnl SEC(".maps"); + +static __always_inline void count_tx(__u32 protocol) +{ + __u64 *rxcnt_count; + + rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol); + if (rxcnt_count) + *rxcnt_count += 1; +} + +static __always_inline int get_dport(void *trans_data, void *data_end, + __u8 protocol) +{ + struct tcphdr *th; + struct udphdr *uh; + + switch (protocol) { + case IPPROTO_TCP: + th = (struct tcphdr *)trans_data; + if (th + 1 > data_end) + return -1; + return th->dest; + case IPPROTO_UDP: + uh = (struct udphdr *)trans_data; + if (uh + 1 > data_end) + return -1; + return uh->dest; + default: + return 0; + } +} + +static __always_inline void set_ethhdr(struct ethhdr *new_eth, + const struct ethhdr *old_eth, + const struct iptnl_info *tnl, + __be16 h_proto) +{ + memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source)); + memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest)); + new_eth->h_proto = h_proto; +} + +static __always_inline int handle_ipv4(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct iphdr *iph = data + sizeof(struct ethhdr); + __u16 *next_iph; + __u16 payload_len; + struct vip vip = {}; + int dport; + __u32 csum = 0; + int i; + + if (iph + 1 > data_end) + return XDP_DROP; + + dport = get_dport(iph + 1, data_end, iph->protocol); + if (dport == -1) + return XDP_DROP; + + vip.protocol = iph->protocol; + vip.family = AF_INET; + vip.daddr.v4 = iph->daddr; + vip.dport = dport; + payload_len = bpf_ntohs(iph->tot_len); + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v4-in-v4 */ + if (!tnl || tnl->family != AF_INET) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + iph = data + sizeof(*new_eth); + old_eth = data + sizeof(*iph); + + if (new_eth + 1 > data_end || + old_eth + 1 > data_end || + iph + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IP)); + + iph->version = 4; + iph->ihl = sizeof(*iph) >> 2; + iph->frag_off = 0; + iph->protocol = IPPROTO_IPIP; + iph->check = 0; + iph->tos = 0; + iph->tot_len = bpf_htons(payload_len + sizeof(*iph)); + iph->daddr = tnl->daddr.v4; + iph->saddr = tnl->saddr.v4; + iph->ttl = 8; + + next_iph = (__u16 *)iph; +#pragma clang loop unroll(full) + for (i = 0; i < sizeof(*iph) >> 1; i++) + csum += *next_iph++; + + iph->check = ~((csum & 0xffff) + (csum >> 16)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +static __always_inline int handle_ipv6(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct ipv6hdr *ip6h = data + sizeof(struct ethhdr); + __u16 payload_len; + struct vip vip = {}; + int dport; + + if (ip6h + 1 > data_end) + return XDP_DROP; + + dport = get_dport(ip6h + 1, data_end, ip6h->nexthdr); + if (dport == -1) + return XDP_DROP; + + vip.protocol = ip6h->nexthdr; + vip.family = AF_INET6; + memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr)); + vip.dport = dport; + payload_len = ip6h->payload_len; + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v6-in-v6 */ + if (!tnl || tnl->family != AF_INET6) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + ip6h = data + sizeof(*new_eth); + old_eth = data + sizeof(*ip6h); + + if (new_eth + 1 > data_end || old_eth + 1 > data_end || + ip6h + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IPV6)); + + ip6h->version = 6; + ip6h->priority = 0; + memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl)); + ip6h->payload_len = bpf_htons(bpf_ntohs(payload_len) + sizeof(*ip6h)); + ip6h->nexthdr = IPPROTO_IPV6; + ip6h->hop_limit = 8; + memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6)); + memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +SEC("xdp") +int _xdp_tx_iptunnel(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eth = data; + __u16 h_proto; + + if (eth + 1 > data_end) + return XDP_DROP; + + h_proto = eth->h_proto; + + if (h_proto == bpf_htons(ETH_P_IP)) + return handle_ipv4(xdp); + else if (h_proto == bpf_htons(ETH_P_IPV6)) + + return handle_ipv6(xdp); + else + return XDP_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c new file mode 100644 index 0000000000..81bb38d72c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("xdp") +int _xdp_adjust_tail_grow(struct xdp_md *xdp) +{ + int data_len = bpf_xdp_get_buff_len(xdp); + int offset = 0; + /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */ +#if defined(__TARGET_ARCH_s390) + int tailroom = 512; +#else + int tailroom = 320; +#endif + + /* Data length determine test case */ + + if (data_len == 54) { /* sizeof(pkt_v4) */ + offset = 4096; /* test too large offset */ + } else if (data_len == 74) { /* sizeof(pkt_v6) */ + offset = 40; + } else if (data_len == 64) { + offset = 128; + } else if (data_len == 128) { + /* Max tail grow 3520 */ + offset = 4096 - 256 - tailroom - data_len; + } else if (data_len == 9000) { + offset = 10; + } else if (data_len == 9001) { + offset = 4096; + } else { + return XDP_ABORTED; /* No matching test */ + } + + if (bpf_xdp_adjust_tail(xdp, offset)) + return XDP_DROP; + return XDP_TX; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c new file mode 100644 index 0000000000..ca68c03835 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <bpf/bpf_helpers.h> + +SEC("xdp") +int _xdp_adjust_tail_shrink(struct xdp_md *xdp) +{ + __u8 *data_end = (void *)(long)xdp->data_end; + __u8 *data = (void *)(long)xdp->data; + int offset = 0; + + switch (bpf_xdp_get_buff_len(xdp)) { + case 54: + /* sizeof(pkt_v4) */ + offset = 256; /* shrink too much */ + break; + case 9000: + /* non-linear buff test cases */ + if (data + 1 > data_end) + return XDP_DROP; + + switch (data[0]) { + case 0: + offset = 10; + break; + case 1: + offset = 4100; + break; + case 2: + offset = 8200; + break; + default: + return XDP_DROP; + } + break; + default: + offset = 20; + break; + } + if (bpf_xdp_adjust_tail(xdp, 0 - offset)) + return XDP_DROP; + return XDP_TX; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c b/tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c new file mode 100644 index 0000000000..2ff1b596e8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Leon Hwang */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define ERRMSG_LEN 64 + +struct xdp_errmsg { + char msg[ERRMSG_LEN]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __type(key, int); + __type(value, int); +} xdp_errmsg_pb SEC(".maps"); + +struct xdp_attach_error_ctx { + unsigned long unused; + + /* + * bpf does not support tracepoint __data_loc directly. + * + * Actually, this field is a 32 bit integer whose value encodes + * information on where to find the actual data. The first 2 bytes is + * the size of the data. The last 2 bytes is the offset from the start + * of the tracepoint struct where the data begins. + * -- https://github.com/iovisor/bpftrace/pull/1542 + */ + __u32 msg; // __data_loc char[] msg; +}; + +/* + * Catch the error message at the tracepoint. + */ + +SEC("tp/xdp/bpf_xdp_link_attach_failed") +int tp__xdp__bpf_xdp_link_attach_failed(struct xdp_attach_error_ctx *ctx) +{ + char *msg = (void *)(__u64) ((void *) ctx + (__u16) ctx->msg); + struct xdp_errmsg errmsg = {}; + + bpf_probe_read_kernel_str(&errmsg.msg, ERRMSG_LEN, msg); + bpf_perf_event_output(ctx, &xdp_errmsg_pb, BPF_F_CURRENT_CPU, &errmsg, + ERRMSG_LEN); + return 0; +} + +/* + * Reuse the XDP program in xdp_dummy.c. + */ + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c new file mode 100644 index 0000000000..ee48c49639 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct net_device { + /* Structure does not need to contain all entries, + * as "preserve_access_index" will use BTF to fix this... + */ + int ifindex; +} __attribute__((preserve_access_index)); + +struct xdp_rxq_info { + /* Structure does not need to contain all entries, + * as "preserve_access_index" will use BTF to fix this... + */ + struct net_device *dev; + __u32 queue_index; +} __attribute__((preserve_access_index)); + +struct xdp_buff { + void *data; + void *data_end; + void *data_meta; + void *data_hard_start; + unsigned long handle; + struct xdp_rxq_info *rxq; +} __attribute__((preserve_access_index)); + +struct meta { + int ifindex; + int pkt_len; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __type(key, int); + __type(value, int); +} perf_buf_map SEC(".maps"); + +__u64 test_result_fentry = 0; +SEC("fentry/FUNC") +int BPF_PROG(trace_on_entry, struct xdp_buff *xdp) +{ + struct meta meta; + + meta.ifindex = xdp->rxq->dev->ifindex; + meta.pkt_len = bpf_xdp_get_buff_len((struct xdp_md *)xdp); + bpf_xdp_output(xdp, &perf_buf_map, + ((__u64) meta.pkt_len << 32) | + BPF_F_CURRENT_CPU, + &meta, sizeof(meta)); + + test_result_fentry = xdp->rxq->dev->ifindex; + return 0; +} + +__u64 test_result_fexit = 0; +SEC("fexit/FUNC") +int BPF_PROG(trace_on_exit, struct xdp_buff *xdp, int ret) +{ + test_result_fexit = ret; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_xdp_context_test_run.c b/tools/testing/selftests/bpf/progs/test_xdp_context_test_run.c new file mode 100644 index 0000000000..d7b88cd05a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_context_test_run.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("xdp") +int xdp_context(struct xdp_md *xdp) +{ + void *data = (void *)(long)xdp->data; + __u32 *metadata = (void *)(long)xdp->data_meta; + __u32 ret; + + if (metadata + 1 > data) + return XDP_ABORTED; + ret = *metadata; + if (bpf_xdp_adjust_meta(xdp, 4)) + return XDP_ABORTED; + return ret; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c new file mode 100644 index 0000000000..807bf895f4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +/* fails to load without expected_attach_type = BPF_XDP_DEVMAP + * because of access to egress_ifindex + */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("xdp") +int xdpdm_devlog(struct xdp_md *ctx) +{ + char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n"; + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + unsigned int len = data_end - data; + + bpf_trace_printk(fmt, sizeof(fmt), + ctx->ingress_ifindex, ctx->egress_ifindex, len); + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c new file mode 100644 index 0000000000..5baaafed0d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +#define ETH_ALEN 6 +#define HDR_SZ (sizeof(struct ethhdr) + sizeof(struct ipv6hdr) + sizeof(struct udphdr)) + +/** + * enum frame_mark - magics to distinguish page/packet paths + * @MARK_XMIT: page was recycled due to the frame being "xmitted" by the NIC. + * @MARK_IN: frame is being processed by the input XDP prog. + * @MARK_SKB: frame did hit the TC ingress hook as an skb. + */ +enum frame_mark { + MARK_XMIT = 0U, + MARK_IN = 0x42, + MARK_SKB = 0x45, +}; + +const volatile int ifindex_out; +const volatile int ifindex_in; +const volatile __u8 expect_dst[ETH_ALEN]; +volatile int pkts_seen_xdp = 0; +volatile int pkts_seen_zero = 0; +volatile int pkts_seen_tc = 0; +volatile int retcode = XDP_REDIRECT; + +SEC("xdp") +int xdp_redirect(struct xdp_md *xdp) +{ + __u32 *metadata = (void *)(long)xdp->data_meta; + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + + __u8 *payload = data + HDR_SZ; + int ret = retcode; + + if (payload + 1 > data_end) + return XDP_ABORTED; + + if (xdp->ingress_ifindex != ifindex_in) + return XDP_ABORTED; + + if (metadata + 1 > data) + return XDP_ABORTED; + + if (*metadata != 0x42) + return XDP_ABORTED; + + if (*payload == MARK_XMIT) + pkts_seen_zero++; + + *payload = MARK_IN; + + if (bpf_xdp_adjust_meta(xdp, sizeof(__u64))) + return XDP_ABORTED; + + if (retcode > XDP_PASS) + retcode--; + + if (ret == XDP_REDIRECT) + return bpf_redirect(ifindex_out, 0); + + return ret; +} + +static bool check_pkt(void *data, void *data_end, const __u32 mark) +{ + struct ipv6hdr *iph = data + sizeof(struct ethhdr); + __u8 *payload = data + HDR_SZ; + + if (payload + 1 > data_end) + return false; + + if (iph->nexthdr != IPPROTO_UDP || *payload != MARK_IN) + return false; + + /* reset the payload so the same packet doesn't get counted twice when + * it cycles back through the kernel path and out the dst veth + */ + *payload = mark; + return true; +} + +SEC("xdp") +int xdp_count_pkts(struct xdp_md *xdp) +{ + void *data = (void *)(long)xdp->data; + void *data_end = (void *)(long)xdp->data_end; + + if (check_pkt(data, data_end, MARK_XMIT)) + pkts_seen_xdp++; + + /* Return %XDP_DROP to recycle the data page with %MARK_XMIT, like + * it exited a physical NIC. Those pages will be counted in the + * pkts_seen_zero counter above. + */ + return XDP_DROP; +} + +SEC("tc") +int tc_count_pkts(struct __sk_buff *skb) +{ + void *data = (void *)(long)skb->data; + void *data_end = (void *)(long)skb->data_end; + + if (check_pkt(data, data_end, MARK_SKB)) + pkts_seen_tc++; + + /* Will be either recycled or freed, %MARK_SKB makes sure it won't + * hit any of the counters above. + */ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c new file mode 100644 index 0000000000..78c368e717 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta */ +#include <stddef.h> +#include <string.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/udp.h> +#include <linux/tcp.h> +#include <linux/pkt_cls.h> +#include <sys/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include "test_iptunnel_common.h" +#include "bpf_kfuncs.h" + +const size_t tcphdr_sz = sizeof(struct tcphdr); +const size_t udphdr_sz = sizeof(struct udphdr); +const size_t ethhdr_sz = sizeof(struct ethhdr); +const size_t iphdr_sz = sizeof(struct iphdr); +const size_t ipv6hdr_sz = sizeof(struct ipv6hdr); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 256); + __type(key, __u32); + __type(value, __u64); +} rxcnt SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, MAX_IPTNL_ENTRIES); + __type(key, struct vip); + __type(value, struct iptnl_info); +} vip2tnl SEC(".maps"); + +static __always_inline void count_tx(__u32 protocol) +{ + __u64 *rxcnt_count; + + rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol); + if (rxcnt_count) + *rxcnt_count += 1; +} + +static __always_inline int get_dport(void *trans_data, __u8 protocol) +{ + struct tcphdr *th; + struct udphdr *uh; + + switch (protocol) { + case IPPROTO_TCP: + th = (struct tcphdr *)trans_data; + return th->dest; + case IPPROTO_UDP: + uh = (struct udphdr *)trans_data; + return uh->dest; + default: + return 0; + } +} + +static __always_inline void set_ethhdr(struct ethhdr *new_eth, + const struct ethhdr *old_eth, + const struct iptnl_info *tnl, + __be16 h_proto) +{ + memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source)); + memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest)); + new_eth->h_proto = h_proto; +} + +static __always_inline int handle_ipv4(struct xdp_md *xdp, struct bpf_dynptr *xdp_ptr) +{ + __u8 eth_buffer[ethhdr_sz + iphdr_sz + ethhdr_sz]; + __u8 iph_buffer_tcp[iphdr_sz + tcphdr_sz]; + __u8 iph_buffer_udp[iphdr_sz + udphdr_sz]; + struct bpf_dynptr new_xdp_ptr; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct iphdr *iph; + __u16 *next_iph; + __u16 payload_len; + struct vip vip = {}; + int dport; + __u32 csum = 0; + int i; + + __builtin_memset(eth_buffer, 0, sizeof(eth_buffer)); + __builtin_memset(iph_buffer_tcp, 0, sizeof(iph_buffer_tcp)); + __builtin_memset(iph_buffer_udp, 0, sizeof(iph_buffer_udp)); + + if (ethhdr_sz + iphdr_sz + tcphdr_sz > xdp->data_end - xdp->data) + iph = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, iph_buffer_udp, sizeof(iph_buffer_udp)); + else + iph = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, iph_buffer_tcp, sizeof(iph_buffer_tcp)); + + if (!iph) + return XDP_DROP; + + dport = get_dport(iph + 1, iph->protocol); + if (dport == -1) + return XDP_DROP; + + vip.protocol = iph->protocol; + vip.family = AF_INET; + vip.daddr.v4 = iph->daddr; + vip.dport = dport; + payload_len = bpf_ntohs(iph->tot_len); + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v4-in-v4 */ + if (!tnl || tnl->family != AF_INET) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)iphdr_sz)) + return XDP_DROP; + + bpf_dynptr_from_xdp(xdp, 0, &new_xdp_ptr); + new_eth = bpf_dynptr_slice_rdwr(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer)); + if (!new_eth) + return XDP_DROP; + + iph = (struct iphdr *)(new_eth + 1); + old_eth = (struct ethhdr *)(iph + 1); + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IP)); + + if (new_eth == eth_buffer) + bpf_dynptr_write(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer), 0); + + iph->version = 4; + iph->ihl = iphdr_sz >> 2; + iph->frag_off = 0; + iph->protocol = IPPROTO_IPIP; + iph->check = 0; + iph->tos = 0; + iph->tot_len = bpf_htons(payload_len + iphdr_sz); + iph->daddr = tnl->daddr.v4; + iph->saddr = tnl->saddr.v4; + iph->ttl = 8; + + next_iph = (__u16 *)iph; + for (i = 0; i < iphdr_sz >> 1; i++) + csum += *next_iph++; + + iph->check = ~((csum & 0xffff) + (csum >> 16)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +static __always_inline int handle_ipv6(struct xdp_md *xdp, struct bpf_dynptr *xdp_ptr) +{ + __u8 eth_buffer[ethhdr_sz + ipv6hdr_sz + ethhdr_sz]; + __u8 ip6h_buffer_tcp[ipv6hdr_sz + tcphdr_sz]; + __u8 ip6h_buffer_udp[ipv6hdr_sz + udphdr_sz]; + struct bpf_dynptr new_xdp_ptr; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct ipv6hdr *ip6h; + __u16 payload_len; + struct vip vip = {}; + int dport; + + __builtin_memset(eth_buffer, 0, sizeof(eth_buffer)); + __builtin_memset(ip6h_buffer_tcp, 0, sizeof(ip6h_buffer_tcp)); + __builtin_memset(ip6h_buffer_udp, 0, sizeof(ip6h_buffer_udp)); + + if (ethhdr_sz + iphdr_sz + tcphdr_sz > xdp->data_end - xdp->data) + ip6h = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, ip6h_buffer_udp, sizeof(ip6h_buffer_udp)); + else + ip6h = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, ip6h_buffer_tcp, sizeof(ip6h_buffer_tcp)); + + if (!ip6h) + return XDP_DROP; + + dport = get_dport(ip6h + 1, ip6h->nexthdr); + if (dport == -1) + return XDP_DROP; + + vip.protocol = ip6h->nexthdr; + vip.family = AF_INET6; + memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr)); + vip.dport = dport; + payload_len = ip6h->payload_len; + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v6-in-v6 */ + if (!tnl || tnl->family != AF_INET6) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)ipv6hdr_sz)) + return XDP_DROP; + + bpf_dynptr_from_xdp(xdp, 0, &new_xdp_ptr); + new_eth = bpf_dynptr_slice_rdwr(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer)); + if (!new_eth) + return XDP_DROP; + + ip6h = (struct ipv6hdr *)(new_eth + 1); + old_eth = (struct ethhdr *)(ip6h + 1); + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IPV6)); + + if (new_eth == eth_buffer) + bpf_dynptr_write(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer), 0); + + ip6h->version = 6; + ip6h->priority = 0; + memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl)); + ip6h->payload_len = bpf_htons(bpf_ntohs(payload_len) + ipv6hdr_sz); + ip6h->nexthdr = IPPROTO_IPV6; + ip6h->hop_limit = 8; + memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6)); + memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +SEC("xdp") +int _xdp_tx_iptunnel(struct xdp_md *xdp) +{ + __u8 buffer[ethhdr_sz]; + struct bpf_dynptr ptr; + struct ethhdr *eth; + __u16 h_proto; + + __builtin_memset(buffer, 0, sizeof(buffer)); + + bpf_dynptr_from_xdp(xdp, 0, &ptr); + eth = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer)); + if (!eth) + return XDP_DROP; + + h_proto = eth->h_proto; + + if (h_proto == bpf_htons(ETH_P_IP)) + return handle_ipv4(xdp, &ptr); + else if (h_proto == bpf_htons(ETH_P_IPV6)) + + return handle_ipv6(xdp, &ptr); + else + return XDP_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_link.c b/tools/testing/selftests/bpf/progs/test_xdp_link.c new file mode 100644 index 0000000000..64ff32eaae --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_link.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char LICENSE[] SEC("license") = "GPL"; + +SEC("xdp") +int xdp_handler(struct xdp_md *xdp) +{ + return 0; +} + +SEC("tc") +int tc_handler(struct __sk_buff *skb) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c new file mode 100644 index 0000000000..c98fb44156 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c @@ -0,0 +1,229 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/udp.h> +#include <linux/tcp.h> +#include <linux/pkt_cls.h> +#include <sys/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include "test_iptunnel_common.h" + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 256); + __type(key, __u32); + __type(value, __u64); +} rxcnt SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, MAX_IPTNL_ENTRIES); + __type(key, struct vip); + __type(value, struct iptnl_info); +} vip2tnl SEC(".maps"); + +static __always_inline void count_tx(__u32 protocol) +{ + __u64 *rxcnt_count; + + rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol); + if (rxcnt_count) + *rxcnt_count += 1; +} + +static __always_inline int get_dport(void *trans_data, void *data_end, + __u8 protocol) +{ + struct tcphdr *th; + struct udphdr *uh; + + switch (protocol) { + case IPPROTO_TCP: + th = (struct tcphdr *)trans_data; + if (th + 1 > data_end) + return -1; + return th->dest; + case IPPROTO_UDP: + uh = (struct udphdr *)trans_data; + if (uh + 1 > data_end) + return -1; + return uh->dest; + default: + return 0; + } +} + +static __always_inline void set_ethhdr(struct ethhdr *new_eth, + const struct ethhdr *old_eth, + const struct iptnl_info *tnl, + __be16 h_proto) +{ + memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source)); + memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest)); + new_eth->h_proto = h_proto; +} + +static __always_inline int handle_ipv4(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct iphdr *iph = data + sizeof(struct ethhdr); + __u16 *next_iph; + __u16 payload_len; + struct vip vip = {}; + int dport; + __u32 csum = 0; + int i; + + if (iph + 1 > data_end) + return XDP_DROP; + + dport = get_dport(iph + 1, data_end, iph->protocol); + if (dport == -1) + return XDP_DROP; + + vip.protocol = iph->protocol; + vip.family = AF_INET; + vip.daddr.v4 = iph->daddr; + vip.dport = dport; + payload_len = bpf_ntohs(iph->tot_len); + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v4-in-v4 */ + if (!tnl || tnl->family != AF_INET) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + iph = data + sizeof(*new_eth); + old_eth = data + sizeof(*iph); + + if (new_eth + 1 > data_end || + old_eth + 1 > data_end || + iph + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IP)); + + iph->version = 4; + iph->ihl = sizeof(*iph) >> 2; + iph->frag_off = 0; + iph->protocol = IPPROTO_IPIP; + iph->check = 0; + iph->tos = 0; + iph->tot_len = bpf_htons(payload_len + sizeof(*iph)); + iph->daddr = tnl->daddr.v4; + iph->saddr = tnl->saddr.v4; + iph->ttl = 8; + + next_iph = (__u16 *)iph; +#pragma clang loop unroll(disable) + for (i = 0; i < sizeof(*iph) >> 1; i++) + csum += *next_iph++; + + iph->check = ~((csum & 0xffff) + (csum >> 16)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +static __always_inline int handle_ipv6(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct ipv6hdr *ip6h = data + sizeof(struct ethhdr); + __u16 payload_len; + struct vip vip = {}; + int dport; + + if (ip6h + 1 > data_end) + return XDP_DROP; + + dport = get_dport(ip6h + 1, data_end, ip6h->nexthdr); + if (dport == -1) + return XDP_DROP; + + vip.protocol = ip6h->nexthdr; + vip.family = AF_INET6; + memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr)); + vip.dport = dport; + payload_len = ip6h->payload_len; + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v6-in-v6 */ + if (!tnl || tnl->family != AF_INET6) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + ip6h = data + sizeof(*new_eth); + old_eth = data + sizeof(*ip6h); + + if (new_eth + 1 > data_end || old_eth + 1 > data_end || + ip6h + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IPV6)); + + ip6h->version = 6; + ip6h->priority = 0; + memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl)); + ip6h->payload_len = bpf_htons(bpf_ntohs(payload_len) + sizeof(*ip6h)); + ip6h->nexthdr = IPPROTO_IPV6; + ip6h->hop_limit = 8; + memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6)); + memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +SEC("xdp") +int _xdp_tx_iptunnel(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eth = data; + __u16 h_proto; + + if (eth + 1 > data_end) + return XDP_DROP; + + h_proto = eth->h_proto; + + if (h_proto == bpf_htons(ETH_P_IP)) + return handle_ipv4(xdp); + else if (h_proto == bpf_htons(ETH_P_IPV6)) + + return handle_ipv6(xdp); + else + return XDP_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c new file mode 100644 index 0000000000..a7c4a7d49f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c @@ -0,0 +1,53 @@ +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/pkt_cls.h> + +#include <bpf/bpf_helpers.h> + +#define __round_mask(x, y) ((__typeof__(x))((y) - 1)) +#define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1) +#define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem + +SEC("t") +int ing_cls(struct __sk_buff *ctx) +{ + __u8 *data, *data_meta, *data_end; + __u32 diff = 0; + + data_meta = ctx_ptr(ctx, data_meta); + data_end = ctx_ptr(ctx, data_end); + data = ctx_ptr(ctx, data); + + if (data + ETH_ALEN > data_end || + data_meta + round_up(ETH_ALEN, 4) > data) + return TC_ACT_SHOT; + + diff |= ((__u32 *)data_meta)[0] ^ ((__u32 *)data)[0]; + diff |= ((__u16 *)data_meta)[2] ^ ((__u16 *)data)[2]; + + return diff ? TC_ACT_SHOT : TC_ACT_OK; +} + +SEC("x") +int ing_xdp(struct xdp_md *ctx) +{ + __u8 *data, *data_meta, *data_end; + int ret; + + ret = bpf_xdp_adjust_meta(ctx, -round_up(ETH_ALEN, 4)); + if (ret < 0) + return XDP_DROP; + + data_meta = ctx_ptr(ctx, data_meta); + data_end = ctx_ptr(ctx, data_end); + data = ctx_ptr(ctx, data); + + if (data + ETH_ALEN > data_end || + data_meta + round_up(ETH_ALEN, 4) > data) + return XDP_DROP; + + __builtin_memcpy(data_meta, data, ETH_ALEN); + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c new file mode 100644 index 0000000000..42c8f6ded0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c @@ -0,0 +1,795 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Facebook +#include <stddef.h> +#include <stdbool.h> +#include <string.h> +#include <linux/pkt_cls.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +static __always_inline __u32 rol32(__u32 word, unsigned int shift) +{ + return (word << shift) | (word >> ((-shift) & 31)); +} + +/* copy paste of jhash from kernel sources to make sure llvm + * can compile it into valid sequence of bpf instructions + */ +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} + +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ +} + +#define JHASH_INITVAL 0xdeadbeef + +typedef unsigned int u32; + +static __noinline +u32 jhash(const void *key, u32 length, u32 initval) +{ + u32 a, b, c; + const unsigned char *k = key; + + a = b = c = JHASH_INITVAL + length + initval; + + while (length > 12) { + a += *(u32 *)(k); + b += *(u32 *)(k + 4); + c += *(u32 *)(k + 8); + __jhash_mix(a, b, c); + length -= 12; + k += 12; + } + switch (length) { + case 12: c += (u32)k[11]<<24; + case 11: c += (u32)k[10]<<16; + case 10: c += (u32)k[9]<<8; + case 9: c += k[8]; + case 8: b += (u32)k[7]<<24; + case 7: b += (u32)k[6]<<16; + case 6: b += (u32)k[5]<<8; + case 5: b += k[4]; + case 4: a += (u32)k[3]<<24; + case 3: a += (u32)k[2]<<16; + case 2: a += (u32)k[1]<<8; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} + +__noinline +u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) +{ + a += initval; + b += initval; + c += initval; + __jhash_final(a, b, c); + return c; +} + +__noinline +u32 jhash_2words(u32 a, u32 b, u32 initval) +{ + return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); +} + +struct flow_key { + union { + __be32 src; + __be32 srcv6[4]; + }; + union { + __be32 dst; + __be32 dstv6[4]; + }; + union { + __u32 ports; + __u16 port16[2]; + }; + __u8 proto; +}; + +struct packet_description { + struct flow_key flow; + __u8 flags; +}; + +struct ctl_value { + union { + __u64 value; + __u32 ifindex; + __u8 mac[6]; + }; +}; + +struct vip_definition { + union { + __be32 vip; + __be32 vipv6[4]; + }; + __u16 port; + __u16 family; + __u8 proto; +}; + +struct vip_meta { + __u32 flags; + __u32 vip_num; +}; + +struct real_pos_lru { + __u32 pos; + __u64 atime; +}; + +struct real_definition { + union { + __be32 dst; + __be32 dstv6[4]; + }; + __u8 flags; +}; + +struct lb_stats { + __u64 v2; + __u64 v1; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 512); + __type(key, struct vip_definition); + __type(value, struct vip_meta); +} vip_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __uint(max_entries, 300); + __uint(map_flags, 1U << 1); + __type(key, struct flow_key); + __type(value, struct real_pos_lru); +} lru_cache SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 12 * 655); + __type(key, __u32); + __type(value, __u32); +} ch_rings SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 40); + __type(key, __u32); + __type(value, struct real_definition); +} reals SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 515); + __type(key, __u32); + __type(value, struct lb_stats); +} stats SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 16); + __type(key, __u32); + __type(value, struct ctl_value); +} ctl_array SEC(".maps"); + +struct eth_hdr { + unsigned char eth_dest[6]; + unsigned char eth_source[6]; + unsigned short eth_proto; +}; + +static __noinline __u64 calc_offset(bool is_ipv6, bool is_icmp) +{ + __u64 off = sizeof(struct eth_hdr); + if (is_ipv6) { + off += sizeof(struct ipv6hdr); + if (is_icmp) + off += sizeof(struct icmp6hdr) + sizeof(struct ipv6hdr); + } else { + off += sizeof(struct iphdr); + if (is_icmp) + off += sizeof(struct icmphdr) + sizeof(struct iphdr); + } + return off; +} + +static __attribute__ ((noinline)) +bool parse_udp(void *data, void *data_end, + bool is_ipv6, struct packet_description *pckt) +{ + + bool is_icmp = !((pckt->flags & (1 << 0)) == 0); + __u64 off = calc_offset(is_ipv6, is_icmp); + struct udphdr *udp; + udp = data + off; + + if (udp + 1 > data_end) + return false; + if (!is_icmp) { + pckt->flow.port16[0] = udp->source; + pckt->flow.port16[1] = udp->dest; + } else { + pckt->flow.port16[0] = udp->dest; + pckt->flow.port16[1] = udp->source; + } + return true; +} + +static __attribute__ ((noinline)) +bool parse_tcp(void *data, void *data_end, + bool is_ipv6, struct packet_description *pckt) +{ + + bool is_icmp = !((pckt->flags & (1 << 0)) == 0); + __u64 off = calc_offset(is_ipv6, is_icmp); + struct tcphdr *tcp; + + tcp = data + off; + if (tcp + 1 > data_end) + return false; + if (tcp->syn) + pckt->flags |= (1 << 1); + if (!is_icmp) { + pckt->flow.port16[0] = tcp->source; + pckt->flow.port16[1] = tcp->dest; + } else { + pckt->flow.port16[0] = tcp->dest; + pckt->flow.port16[1] = tcp->source; + } + return true; +} + +static __attribute__ ((noinline)) +bool encap_v6(struct xdp_md *xdp, struct ctl_value *cval, + struct packet_description *pckt, + struct real_definition *dst, __u32 pkt_bytes) +{ + struct eth_hdr *new_eth; + struct eth_hdr *old_eth; + struct ipv6hdr *ip6h; + __u32 ip_suffix; + void *data_end; + void *data; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr))) + return false; + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + new_eth = data; + ip6h = data + sizeof(struct eth_hdr); + old_eth = data + sizeof(struct ipv6hdr); + if (new_eth + 1 > data_end || + old_eth + 1 > data_end || ip6h + 1 > data_end) + return false; + memcpy(new_eth->eth_dest, cval->mac, 6); + memcpy(new_eth->eth_source, old_eth->eth_dest, 6); + new_eth->eth_proto = 56710; + ip6h->version = 6; + ip6h->priority = 0; + memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl)); + + ip6h->nexthdr = IPPROTO_IPV6; + ip_suffix = pckt->flow.srcv6[3] ^ pckt->flow.port16[0]; + ip6h->payload_len = + bpf_htons(pkt_bytes + sizeof(struct ipv6hdr)); + ip6h->hop_limit = 4; + + ip6h->saddr.in6_u.u6_addr32[0] = 1; + ip6h->saddr.in6_u.u6_addr32[1] = 2; + ip6h->saddr.in6_u.u6_addr32[2] = 3; + ip6h->saddr.in6_u.u6_addr32[3] = ip_suffix; + memcpy(ip6h->daddr.in6_u.u6_addr32, dst->dstv6, 16); + return true; +} + +static __attribute__ ((noinline)) +bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval, + struct packet_description *pckt, + struct real_definition *dst, __u32 pkt_bytes) +{ + + __u32 ip_suffix = bpf_ntohs(pckt->flow.port16[0]); + struct eth_hdr *new_eth; + struct eth_hdr *old_eth; + __u16 *next_iph_u16; + struct iphdr *iph; + __u32 csum = 0; + void *data_end; + void *data; + + ip_suffix <<= 15; + ip_suffix ^= pckt->flow.src; + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr))) + return false; + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + new_eth = data; + iph = data + sizeof(struct eth_hdr); + old_eth = data + sizeof(struct iphdr); + if (new_eth + 1 > data_end || + old_eth + 1 > data_end || iph + 1 > data_end) + return false; + memcpy(new_eth->eth_dest, cval->mac, 6); + memcpy(new_eth->eth_source, old_eth->eth_dest, 6); + new_eth->eth_proto = 8; + iph->version = 4; + iph->ihl = 5; + iph->frag_off = 0; + iph->protocol = IPPROTO_IPIP; + iph->check = 0; + iph->tos = 1; + iph->tot_len = bpf_htons(pkt_bytes + sizeof(struct iphdr)); + /* don't update iph->daddr, since it will overwrite old eth_proto + * and multiple iterations of bpf_prog_run() will fail + */ + + iph->saddr = ((0xFFFF0000 & ip_suffix) | 4268) ^ dst->dst; + iph->ttl = 4; + + next_iph_u16 = (__u16 *) iph; +#pragma clang loop unroll(full) + for (int i = 0; i < sizeof(struct iphdr) >> 1; i++) + csum += *next_iph_u16++; + iph->check = ~((csum & 0xffff) + (csum >> 16)); + if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct iphdr))) + return false; + return true; +} + +static __attribute__ ((noinline)) +int swap_mac_and_send(void *data, void *data_end) +{ + unsigned char tmp_mac[6]; + struct eth_hdr *eth; + + eth = data; + memcpy(tmp_mac, eth->eth_source, 6); + memcpy(eth->eth_source, eth->eth_dest, 6); + memcpy(eth->eth_dest, tmp_mac, 6); + return XDP_TX; +} + +static __attribute__ ((noinline)) +int send_icmp_reply(void *data, void *data_end) +{ + struct icmphdr *icmp_hdr; + __u16 *next_iph_u16; + __u32 tmp_addr = 0; + struct iphdr *iph; + __u32 csum = 0; + __u64 off = 0; + + if (data + sizeof(struct eth_hdr) + + sizeof(struct iphdr) + sizeof(struct icmphdr) > data_end) + return XDP_DROP; + off += sizeof(struct eth_hdr); + iph = data + off; + off += sizeof(struct iphdr); + icmp_hdr = data + off; + icmp_hdr->type = 0; + icmp_hdr->checksum += 0x0007; + iph->ttl = 4; + tmp_addr = iph->daddr; + iph->daddr = iph->saddr; + iph->saddr = tmp_addr; + iph->check = 0; + next_iph_u16 = (__u16 *) iph; +#pragma clang loop unroll(full) + for (int i = 0; i < sizeof(struct iphdr) >> 1; i++) + csum += *next_iph_u16++; + iph->check = ~((csum & 0xffff) + (csum >> 16)); + return swap_mac_and_send(data, data_end); +} + +static __attribute__ ((noinline)) +int send_icmp6_reply(void *data, void *data_end) +{ + struct icmp6hdr *icmp_hdr; + struct ipv6hdr *ip6h; + __be32 tmp_addr[4]; + __u64 off = 0; + + if (data + sizeof(struct eth_hdr) + + sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) > data_end) + return XDP_DROP; + off += sizeof(struct eth_hdr); + ip6h = data + off; + off += sizeof(struct ipv6hdr); + icmp_hdr = data + off; + icmp_hdr->icmp6_type = 129; + icmp_hdr->icmp6_cksum -= 0x0001; + ip6h->hop_limit = 4; + memcpy(tmp_addr, ip6h->saddr.in6_u.u6_addr32, 16); + memcpy(ip6h->saddr.in6_u.u6_addr32, ip6h->daddr.in6_u.u6_addr32, 16); + memcpy(ip6h->daddr.in6_u.u6_addr32, tmp_addr, 16); + return swap_mac_and_send(data, data_end); +} + +static __attribute__ ((noinline)) +int parse_icmpv6(void *data, void *data_end, __u64 off, + struct packet_description *pckt) +{ + struct icmp6hdr *icmp_hdr; + struct ipv6hdr *ip6h; + + icmp_hdr = data + off; + if (icmp_hdr + 1 > data_end) + return XDP_DROP; + if (icmp_hdr->icmp6_type == 128) + return send_icmp6_reply(data, data_end); + if (icmp_hdr->icmp6_type != 3) + return XDP_PASS; + off += sizeof(struct icmp6hdr); + ip6h = data + off; + if (ip6h + 1 > data_end) + return XDP_DROP; + pckt->flow.proto = ip6h->nexthdr; + pckt->flags |= (1 << 0); + memcpy(pckt->flow.srcv6, ip6h->daddr.in6_u.u6_addr32, 16); + memcpy(pckt->flow.dstv6, ip6h->saddr.in6_u.u6_addr32, 16); + return -1; +} + +static __attribute__ ((noinline)) +int parse_icmp(void *data, void *data_end, __u64 off, + struct packet_description *pckt) +{ + struct icmphdr *icmp_hdr; + struct iphdr *iph; + + icmp_hdr = data + off; + if (icmp_hdr + 1 > data_end) + return XDP_DROP; + if (icmp_hdr->type == 8) + return send_icmp_reply(data, data_end); + if ((icmp_hdr->type != 3) || (icmp_hdr->code != 4)) + return XDP_PASS; + off += sizeof(struct icmphdr); + iph = data + off; + if (iph + 1 > data_end) + return XDP_DROP; + if (iph->ihl != 5) + return XDP_DROP; + pckt->flow.proto = iph->protocol; + pckt->flags |= (1 << 0); + pckt->flow.src = iph->daddr; + pckt->flow.dst = iph->saddr; + return -1; +} + +static __attribute__ ((noinline)) +__u32 get_packet_hash(struct packet_description *pckt, + bool hash_16bytes) +{ + if (hash_16bytes) + return jhash_2words(jhash(pckt->flow.srcv6, 16, 12), + pckt->flow.ports, 24); + else + return jhash_2words(pckt->flow.src, pckt->flow.ports, + 24); +} + +__attribute__ ((noinline)) +static bool get_packet_dst(struct real_definition **real, + struct packet_description *pckt, + struct vip_meta *vip_info, + bool is_ipv6, void *lru_map) +{ + struct real_pos_lru new_dst_lru = { }; + bool hash_16bytes = is_ipv6; + __u32 *real_pos, hash, key; + __u64 cur_time; + + if (vip_info->flags & (1 << 2)) + hash_16bytes = 1; + if (vip_info->flags & (1 << 3)) { + pckt->flow.port16[0] = pckt->flow.port16[1]; + memset(pckt->flow.srcv6, 0, 16); + } + hash = get_packet_hash(pckt, hash_16bytes); + if (hash != 0x358459b7 /* jhash of ipv4 packet */ && + hash != 0x2f4bc6bb /* jhash of ipv6 packet */) + return false; + key = 2 * vip_info->vip_num + hash % 2; + real_pos = bpf_map_lookup_elem(&ch_rings, &key); + if (!real_pos) + return false; + key = *real_pos; + *real = bpf_map_lookup_elem(&reals, &key); + if (!(*real)) + return false; + if (!(vip_info->flags & (1 << 1))) { + __u32 conn_rate_key = 512 + 2; + struct lb_stats *conn_rate_stats = + bpf_map_lookup_elem(&stats, &conn_rate_key); + + if (!conn_rate_stats) + return true; + cur_time = bpf_ktime_get_ns(); + if ((cur_time - conn_rate_stats->v2) >> 32 > 0xffFFFF) { + conn_rate_stats->v1 = 1; + conn_rate_stats->v2 = cur_time; + } else { + conn_rate_stats->v1 += 1; + if (conn_rate_stats->v1 >= 1) + return true; + } + if (pckt->flow.proto == IPPROTO_UDP) + new_dst_lru.atime = cur_time; + new_dst_lru.pos = key; + bpf_map_update_elem(lru_map, &pckt->flow, &new_dst_lru, 0); + } + return true; +} + +__attribute__ ((noinline)) +static void connection_table_lookup(struct real_definition **real, + struct packet_description *pckt, + void *lru_map) +{ + + struct real_pos_lru *dst_lru; + __u64 cur_time; + __u32 key; + + dst_lru = bpf_map_lookup_elem(lru_map, &pckt->flow); + if (!dst_lru) + return; + if (pckt->flow.proto == IPPROTO_UDP) { + cur_time = bpf_ktime_get_ns(); + if (cur_time - dst_lru->atime > 300000) + return; + dst_lru->atime = cur_time; + } + key = dst_lru->pos; + *real = bpf_map_lookup_elem(&reals, &key); +} + +/* don't believe your eyes! + * below function has 6 arguments whereas bpf and llvm allow maximum of 5 + * but since it's _static_ llvm can optimize one argument away + */ +__attribute__ ((noinline)) +static int process_l3_headers_v6(struct packet_description *pckt, + __u8 *protocol, __u64 off, + __u16 *pkt_bytes, void *data, + void *data_end) +{ + struct ipv6hdr *ip6h; + __u64 iph_len; + int action; + + ip6h = data + off; + if (ip6h + 1 > data_end) + return XDP_DROP; + iph_len = sizeof(struct ipv6hdr); + *protocol = ip6h->nexthdr; + pckt->flow.proto = *protocol; + *pkt_bytes = bpf_ntohs(ip6h->payload_len); + off += iph_len; + if (*protocol == 45) { + return XDP_DROP; + } else if (*protocol == 59) { + action = parse_icmpv6(data, data_end, off, pckt); + if (action >= 0) + return action; + } else { + memcpy(pckt->flow.srcv6, ip6h->saddr.in6_u.u6_addr32, 16); + memcpy(pckt->flow.dstv6, ip6h->daddr.in6_u.u6_addr32, 16); + } + return -1; +} + +__attribute__ ((noinline)) +static int process_l3_headers_v4(struct packet_description *pckt, + __u8 *protocol, __u64 off, + __u16 *pkt_bytes, void *data, + void *data_end) +{ + struct iphdr *iph; + int action; + + iph = data + off; + if (iph + 1 > data_end) + return XDP_DROP; + if (iph->ihl != 5) + return XDP_DROP; + *protocol = iph->protocol; + pckt->flow.proto = *protocol; + *pkt_bytes = bpf_ntohs(iph->tot_len); + off += 20; + if (iph->frag_off & 65343) + return XDP_DROP; + if (*protocol == IPPROTO_ICMP) { + action = parse_icmp(data, data_end, off, pckt); + if (action >= 0) + return action; + } else { + pckt->flow.src = iph->saddr; + pckt->flow.dst = iph->daddr; + } + return -1; +} + +__attribute__ ((noinline)) +static int process_packet(void *data, __u64 off, void *data_end, + bool is_ipv6, struct xdp_md *xdp) +{ + + struct real_definition *dst = NULL; + struct packet_description pckt = { }; + struct vip_definition vip = { }; + struct lb_stats *data_stats; + void *lru_map = &lru_cache; + struct vip_meta *vip_info; + __u32 lru_stats_key = 513; + __u32 mac_addr_pos = 0; + __u32 stats_key = 512; + struct ctl_value *cval; + __u16 pkt_bytes; + __u8 protocol; + __u32 vip_num; + int action; + + if (is_ipv6) + action = process_l3_headers_v6(&pckt, &protocol, off, + &pkt_bytes, data, data_end); + else + action = process_l3_headers_v4(&pckt, &protocol, off, + &pkt_bytes, data, data_end); + if (action >= 0) + return action; + protocol = pckt.flow.proto; + if (protocol == IPPROTO_TCP) { + if (!parse_tcp(data, data_end, is_ipv6, &pckt)) + return XDP_DROP; + } else if (protocol == IPPROTO_UDP) { + if (!parse_udp(data, data_end, is_ipv6, &pckt)) + return XDP_DROP; + } else { + return XDP_TX; + } + + if (is_ipv6) + memcpy(vip.vipv6, pckt.flow.dstv6, 16); + else + vip.vip = pckt.flow.dst; + vip.port = pckt.flow.port16[1]; + vip.proto = pckt.flow.proto; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) { + vip.port = 0; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) + return XDP_PASS; + if (!(vip_info->flags & (1 << 4))) + pckt.flow.port16[1] = 0; + } + if (data_end - data > 1400) + return XDP_DROP; + data_stats = bpf_map_lookup_elem(&stats, &stats_key); + if (!data_stats) + return XDP_DROP; + data_stats->v1 += 1; + if (!dst) { + if (vip_info->flags & (1 << 0)) + pckt.flow.port16[0] = 0; + if (!(pckt.flags & (1 << 1)) && !(vip_info->flags & (1 << 1))) + connection_table_lookup(&dst, &pckt, lru_map); + if (dst) + goto out; + if (pckt.flow.proto == IPPROTO_TCP) { + struct lb_stats *lru_stats = + bpf_map_lookup_elem(&stats, &lru_stats_key); + + if (!lru_stats) + return XDP_DROP; + if (pckt.flags & (1 << 1)) + lru_stats->v1 += 1; + else + lru_stats->v2 += 1; + } + if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6, lru_map)) + return XDP_DROP; + data_stats->v2 += 1; + } +out: + cval = bpf_map_lookup_elem(&ctl_array, &mac_addr_pos); + if (!cval) + return XDP_DROP; + if (dst->flags & (1 << 0)) { + if (!encap_v6(xdp, cval, &pckt, dst, pkt_bytes)) + return XDP_DROP; + } else { + if (!encap_v4(xdp, cval, &pckt, dst, pkt_bytes)) + return XDP_DROP; + } + vip_num = vip_info->vip_num; + data_stats = bpf_map_lookup_elem(&stats, &vip_num); + if (!data_stats) + return XDP_DROP; + data_stats->v1 += 1; + data_stats->v2 += pkt_bytes; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + if (data + 4 > data_end) + return XDP_DROP; + *(u32 *)data = dst->dst; + return XDP_DROP; +} + +SEC("xdp") +int balancer_ingress_v4(struct xdp_md *ctx) +{ + void *data = (void *)(long)ctx->data; + void *data_end = (void *)(long)ctx->data_end; + struct eth_hdr *eth = data; + __u32 eth_proto; + __u32 nh_off; + + nh_off = sizeof(struct eth_hdr); + if (data + nh_off > data_end) + return XDP_DROP; + eth_proto = bpf_ntohs(eth->eth_proto); + if (eth_proto == ETH_P_IP) + return process_packet(data, nh_off, data_end, 0, ctx); + else + return XDP_DROP; +} + +SEC("xdp") +int balancer_ingress_v6(struct xdp_md *ctx) +{ + void *data = (void *)(long)ctx->data; + void *data_end = (void *)(long)ctx->data_end; + struct eth_hdr *eth = data; + __u32 eth_proto; + __u32 nh_off; + + nh_off = sizeof(struct eth_hdr); + if (data + nh_off > data_end) + return XDP_DROP; + eth_proto = bpf_ntohs(eth->eth_proto); + if (eth_proto == ETH_P_IPV6) + return process_packet(data, nh_off, data_end, 1, ctx); + else + return XDP_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c new file mode 100644 index 0000000000..b778cad454 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c @@ -0,0 +1,26 @@ +/* Copyright (c) 2017 VMware + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("redirect_to_111") +int xdp_redirect_to_111(struct xdp_md *xdp) +{ + return bpf_redirect(111, 0); +} +SEC("redirect_to_222") +int xdp_redirect_to_222(struct xdp_md *xdp) +{ + return bpf_redirect(222, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_update_frags.c b/tools/testing/selftests/bpf/progs/test_xdp_update_frags.c new file mode 100644 index 0000000000..2a3496d8e3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_update_frags.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <bpf/bpf_helpers.h> + +int _version SEC("version") = 1; + +SEC("xdp.frags") +int xdp_adjust_frags(struct xdp_md *xdp) +{ + __u8 *data_end = (void *)(long)xdp->data_end; + __u8 *data = (void *)(long)xdp->data; + __u8 val[16] = {}; + __u32 offset; + int err; + + if (data + sizeof(__u32) > data_end) + return XDP_DROP; + + offset = *(__u32 *)data; + err = bpf_xdp_load_bytes(xdp, offset, val, sizeof(val)); + if (err < 0) + return XDP_DROP; + + if (val[0] != 0xaa || val[15] != 0xaa) /* marker */ + return XDP_DROP; + + val[0] = 0xbb; /* update the marker */ + val[15] = 0xbb; + err = bpf_xdp_store_bytes(xdp, offset, val, sizeof(val)); + if (err < 0) + return XDP_DROP; + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c new file mode 100644 index 0000000000..f3ec808648 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c @@ -0,0 +1,279 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright(c) 2018 Jesper Dangaard Brouer. + * + * XDP/TC VLAN manipulation example + * + * GOTCHA: Remember to disable NIC hardware offloading of VLANs, + * else the VLAN tags are NOT inlined in the packet payload: + * + * # ethtool -K ixgbe2 rxvlan off + * + * Verify setting: + * # ethtool -k ixgbe2 | grep rx-vlan-offload + * rx-vlan-offload: off + * + */ +#include <stddef.h> +#include <stdbool.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_vlan.h> +#include <linux/in.h> +#include <linux/pkt_cls.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +/* linux/if_vlan.h have not exposed this as UAPI, thus mirror some here + * + * struct vlan_hdr - vlan header + * @h_vlan_TCI: priority and VLAN ID + * @h_vlan_encapsulated_proto: packet type ID or len + */ +struct _vlan_hdr { + __be16 h_vlan_TCI; + __be16 h_vlan_encapsulated_proto; +}; +#define VLAN_PRIO_MASK 0xe000 /* Priority Code Point */ +#define VLAN_PRIO_SHIFT 13 +#define VLAN_CFI_MASK 0x1000 /* Canonical Format Indicator */ +#define VLAN_TAG_PRESENT VLAN_CFI_MASK +#define VLAN_VID_MASK 0x0fff /* VLAN Identifier */ +#define VLAN_N_VID 4096 + +struct parse_pkt { + __u16 l3_proto; + __u16 l3_offset; + __u16 vlan_outer; + __u16 vlan_inner; + __u8 vlan_outer_offset; + __u8 vlan_inner_offset; +}; + +char _license[] SEC("license") = "GPL"; + +static __always_inline +bool parse_eth_frame(struct ethhdr *eth, void *data_end, struct parse_pkt *pkt) +{ + __u16 eth_type; + __u8 offset; + + offset = sizeof(*eth); + /* Make sure packet is large enough for parsing eth + 2 VLAN headers */ + if ((void *)eth + offset + (2*sizeof(struct _vlan_hdr)) > data_end) + return false; + + eth_type = eth->h_proto; + + /* Handle outer VLAN tag */ + if (eth_type == bpf_htons(ETH_P_8021Q) + || eth_type == bpf_htons(ETH_P_8021AD)) { + struct _vlan_hdr *vlan_hdr; + + vlan_hdr = (void *)eth + offset; + pkt->vlan_outer_offset = offset; + pkt->vlan_outer = bpf_ntohs(vlan_hdr->h_vlan_TCI) + & VLAN_VID_MASK; + eth_type = vlan_hdr->h_vlan_encapsulated_proto; + offset += sizeof(*vlan_hdr); + } + + /* Handle inner (double) VLAN tag */ + if (eth_type == bpf_htons(ETH_P_8021Q) + || eth_type == bpf_htons(ETH_P_8021AD)) { + struct _vlan_hdr *vlan_hdr; + + vlan_hdr = (void *)eth + offset; + pkt->vlan_inner_offset = offset; + pkt->vlan_inner = bpf_ntohs(vlan_hdr->h_vlan_TCI) + & VLAN_VID_MASK; + eth_type = vlan_hdr->h_vlan_encapsulated_proto; + offset += sizeof(*vlan_hdr); + } + + pkt->l3_proto = bpf_ntohs(eth_type); /* Convert to host-byte-order */ + pkt->l3_offset = offset; + + return true; +} + +/* Hint, VLANs are chosen to hit network-byte-order issues */ +#define TESTVLAN 4011 /* 0xFAB */ +// #define TO_VLAN 4000 /* 0xFA0 (hint 0xOA0 = 160) */ + +SEC("xdp_drop_vlan_4011") +int xdp_prognum0(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct parse_pkt pkt = { 0 }; + + if (!parse_eth_frame(data, data_end, &pkt)) + return XDP_ABORTED; + + /* Drop specific VLAN ID example */ + if (pkt.vlan_outer == TESTVLAN) + return XDP_ABORTED; + /* + * Using XDP_ABORTED makes it possible to record this event, + * via tracepoint xdp:xdp_exception like: + * # perf record -a -e xdp:xdp_exception + * # perf script + */ + return XDP_PASS; +} +/* +Commands to setup VLAN on Linux to test packets gets dropped: + + export ROOTDEV=ixgbe2 + export VLANID=4011 + ip link add link $ROOTDEV name $ROOTDEV.$VLANID type vlan id $VLANID + ip link set dev $ROOTDEV.$VLANID up + + ip link set dev $ROOTDEV mtu 1508 + ip addr add 100.64.40.11/24 dev $ROOTDEV.$VLANID + +Load prog with ip tool: + + ip link set $ROOTDEV xdp off + ip link set $ROOTDEV xdp object xdp_vlan01_kern.o section xdp_drop_vlan_4011 + +*/ + +/* Changing VLAN to zero, have same practical effect as removing the VLAN. */ +#define TO_VLAN 0 + +SEC("xdp_vlan_change") +int xdp_prognum1(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct parse_pkt pkt = { 0 }; + + if (!parse_eth_frame(data, data_end, &pkt)) + return XDP_ABORTED; + + /* Change specific VLAN ID */ + if (pkt.vlan_outer == TESTVLAN) { + struct _vlan_hdr *vlan_hdr = data + pkt.vlan_outer_offset; + + /* Modifying VLAN, preserve top 4 bits */ + vlan_hdr->h_vlan_TCI = + bpf_htons((bpf_ntohs(vlan_hdr->h_vlan_TCI) & 0xf000) + | TO_VLAN); + } + + return XDP_PASS; +} + +/* + * Show XDP+TC can cooperate, on creating a VLAN rewriter. + * 1. Create a XDP prog that can "pop"/remove a VLAN header. + * 2. Create a TC-bpf prog that egress can add a VLAN header. + */ + +#ifndef ETH_ALEN /* Ethernet MAC address length */ +#define ETH_ALEN 6 /* bytes */ +#endif +#define VLAN_HDR_SZ 4 /* bytes */ + +SEC("xdp_vlan_remove_outer") +int xdp_prognum2(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct parse_pkt pkt = { 0 }; + char *dest; + + if (!parse_eth_frame(data, data_end, &pkt)) + return XDP_ABORTED; + + /* Skip packet if no outer VLAN was detected */ + if (pkt.vlan_outer_offset == 0) + return XDP_PASS; + + /* Moving Ethernet header, dest overlap with src, memmove handle this */ + dest = data; + dest += VLAN_HDR_SZ; + /* + * Notice: Taking over vlan_hdr->h_vlan_encapsulated_proto, by + * only moving two MAC addrs (12 bytes), not overwriting last 2 bytes + */ + __builtin_memmove(dest, data, ETH_ALEN * 2); + /* Note: LLVM built-in memmove inlining require size to be constant */ + + /* Move start of packet header seen by Linux kernel stack */ + bpf_xdp_adjust_head(ctx, VLAN_HDR_SZ); + + return XDP_PASS; +} + +static __always_inline +void shift_mac_4bytes_32bit(void *data) +{ + __u32 *p = data; + + /* Assuming VLAN hdr present. The 4 bytes in p[3] that gets + * overwritten, is ethhdr->h_proto and vlan_hdr->h_vlan_TCI. + * The vlan_hdr->h_vlan_encapsulated_proto take over role as + * ethhdr->h_proto. + */ + p[3] = p[2]; + p[2] = p[1]; + p[1] = p[0]; +} + +SEC("xdp_vlan_remove_outer2") +int xdp_prognum3(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *orig_eth = data; + struct parse_pkt pkt = { 0 }; + + if (!parse_eth_frame(orig_eth, data_end, &pkt)) + return XDP_ABORTED; + + /* Skip packet if no outer VLAN was detected */ + if (pkt.vlan_outer_offset == 0) + return XDP_PASS; + + /* Simply shift down MAC addrs 4 bytes, overwrite h_proto + TCI */ + shift_mac_4bytes_32bit(data); + + /* Move start of packet header seen by Linux kernel stack */ + bpf_xdp_adjust_head(ctx, VLAN_HDR_SZ); + + return XDP_PASS; +} + +/*===================================== + * BELOW: TC-hook based ebpf programs + * ==================================== + * The TC-clsact eBPF programs (currently) need to be attach via TC commands + */ + +SEC("tc_vlan_push") +int _tc_progA(struct __sk_buff *ctx) +{ + bpf_skb_vlan_push(ctx, bpf_htons(ETH_P_8021Q), TESTVLAN); + + return TC_ACT_OK; +} +/* +Commands to setup TC to use above bpf prog: + +export ROOTDEV=ixgbe2 +export FILE=xdp_vlan01_kern.o + +# Re-attach clsact to clear/flush existing role +tc qdisc del dev $ROOTDEV clsact 2> /dev/null ;\ +tc qdisc add dev $ROOTDEV clsact + +# Attach BPF prog EGRESS +tc filter add dev $ROOTDEV egress \ + prio 1 handle 1 bpf da obj $FILE sec tc_vlan_push + +tc filter show dev $ROOTDEV egress +*/ diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_frags_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_frags_helpers.c new file mode 100644 index 0000000000..97ed625bb7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_frags_helpers.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define IFINDEX_LO 1 + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_cpumap_val)); + __uint(max_entries, 4); +} cpu_map SEC(".maps"); + +SEC("xdp/cpumap") +int xdp_dummy_cm(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +SEC("xdp.frags/cpumap") +int xdp_dummy_cm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c new file mode 100644 index 0000000000..20ec6723df --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define IFINDEX_LO 1 + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_cpumap_val)); + __uint(max_entries, 4); +} cpu_map SEC(".maps"); + +SEC("xdp") +int xdp_redir_prog(struct xdp_md *ctx) +{ + return bpf_redirect_map(&cpu_map, 1, 0); +} + +SEC("xdp") +int xdp_dummy_prog(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +SEC("xdp/cpumap") +int xdp_dummy_cm(struct xdp_md *ctx) +{ + if (ctx->ingress_ifindex == IFINDEX_LO) + return XDP_DROP; + + return XDP_PASS; +} + +SEC("xdp.frags/cpumap") +int xdp_dummy_cm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_frags_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_frags_helpers.c new file mode 100644 index 0000000000..cdcf7de7ec --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_frags_helpers.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 4); +} dm_ports SEC(".maps"); + +/* valid program on DEVMAP entry via SEC name; + * has access to egress and ingress ifindex + */ +SEC("xdp/devmap") +int xdp_dummy_dm(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +SEC("xdp.frags/devmap") +int xdp_dummy_dm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c new file mode 100644 index 0000000000..4139a14f99 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 4); +} dm_ports SEC(".maps"); + +SEC("xdp") +int xdp_redir_prog(struct xdp_md *ctx) +{ + return bpf_redirect_map(&dm_ports, 1, 0); +} + +/* invalid program on DEVMAP entry; + * SEC name means expected attach type not set + */ +SEC("xdp") +int xdp_dummy_prog(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +/* valid program on DEVMAP entry via SEC name; + * has access to egress and ingress ifindex + */ +SEC("xdp/devmap") +int xdp_dummy_dm(struct xdp_md *ctx) +{ + char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n"; + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + unsigned int len = data_end - data; + + bpf_trace_printk(fmt, sizeof(fmt), + ctx->ingress_ifindex, ctx->egress_ifindex, len); + + return XDP_PASS; +} + +SEC("xdp.frags/devmap") +int xdp_dummy_dm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/timer.c b/tools/testing/selftests/bpf/progs/timer.c new file mode 100644 index 0000000000..9a16d95213 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/timer.c @@ -0,0 +1,331 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <linux/bpf.h> +#include <time.h> +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; +struct hmap_elem { + int counter; + struct bpf_timer timer; + struct bpf_spin_lock lock; /* unused */ +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1000); + __type(key, int); + __type(value, struct hmap_elem); +} hmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, 1000); + __type(key, int); + __type(value, struct hmap_elem); +} hmap_malloc SEC(".maps"); + +struct elem { + struct bpf_timer t; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 2); + __type(key, int); + __type(value, struct elem); +} array SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __uint(max_entries, 4); + __type(key, int); + __type(value, struct elem); +} lru SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct elem); +} abs_timer SEC(".maps"); + +__u64 bss_data; +__u64 abs_data; +__u64 err; +__u64 ok; +__u64 callback_check = 52; +__u64 callback2_check = 52; + +#define ARRAY 1 +#define HTAB 2 +#define HTAB_MALLOC 3 +#define LRU 4 + +/* callback for array and lru timers */ +static int timer_cb1(void *map, int *key, struct bpf_timer *timer) +{ + /* increment bss variable twice. + * Once via array timer callback and once via lru timer callback + */ + bss_data += 5; + + /* *key == 0 - the callback was called for array timer. + * *key == 4 - the callback was called from lru timer. + */ + if (*key == ARRAY) { + struct bpf_timer *lru_timer; + int lru_key = LRU; + + /* rearm array timer to be called again in ~35 seconds */ + if (bpf_timer_start(timer, 1ull << 35, 0) != 0) + err |= 1; + + lru_timer = bpf_map_lookup_elem(&lru, &lru_key); + if (!lru_timer) + return 0; + bpf_timer_set_callback(lru_timer, timer_cb1); + if (bpf_timer_start(lru_timer, 0, 0) != 0) + err |= 2; + } else if (*key == LRU) { + int lru_key, i; + + for (i = LRU + 1; + i <= 100 /* for current LRU eviction algorithm this number + * should be larger than ~ lru->max_entries * 2 + */; + i++) { + struct elem init = {}; + + /* lru_key cannot be used as loop induction variable + * otherwise the loop will be unbounded. + */ + lru_key = i; + + /* add more elements into lru map to push out current + * element and force deletion of this timer + */ + bpf_map_update_elem(map, &lru_key, &init, 0); + /* look it up to bump it into active list */ + bpf_map_lookup_elem(map, &lru_key); + + /* keep adding until *key changes underneath, + * which means that key/timer memory was reused + */ + if (*key != LRU) + break; + } + + /* check that the timer was removed */ + if (bpf_timer_cancel(timer) != -EINVAL) + err |= 4; + ok |= 1; + } + return 0; +} + +SEC("fentry/bpf_fentry_test1") +int BPF_PROG2(test1, int, a) +{ + struct bpf_timer *arr_timer, *lru_timer; + struct elem init = {}; + int lru_key = LRU; + int array_key = ARRAY; + + arr_timer = bpf_map_lookup_elem(&array, &array_key); + if (!arr_timer) + return 0; + bpf_timer_init(arr_timer, &array, CLOCK_MONOTONIC); + + bpf_map_update_elem(&lru, &lru_key, &init, 0); + lru_timer = bpf_map_lookup_elem(&lru, &lru_key); + if (!lru_timer) + return 0; + bpf_timer_init(lru_timer, &lru, CLOCK_MONOTONIC); + + bpf_timer_set_callback(arr_timer, timer_cb1); + bpf_timer_start(arr_timer, 0 /* call timer_cb1 asap */, 0); + + /* init more timers to check that array destruction + * doesn't leak timer memory. + */ + array_key = 0; + arr_timer = bpf_map_lookup_elem(&array, &array_key); + if (!arr_timer) + return 0; + bpf_timer_init(arr_timer, &array, CLOCK_MONOTONIC); + return 0; +} + +/* callback for prealloc and non-prealloca hashtab timers */ +static int timer_cb2(void *map, int *key, struct hmap_elem *val) +{ + if (*key == HTAB) + callback_check--; + else + callback2_check--; + if (val->counter > 0 && --val->counter) { + /* re-arm the timer again to execute after 1 usec */ + bpf_timer_start(&val->timer, 1000, 0); + } else if (*key == HTAB) { + struct bpf_timer *arr_timer; + int array_key = ARRAY; + + /* cancel arr_timer otherwise bpf_fentry_test1 prog + * will stay alive forever. + */ + arr_timer = bpf_map_lookup_elem(&array, &array_key); + if (!arr_timer) + return 0; + if (bpf_timer_cancel(arr_timer) != 1) + /* bpf_timer_cancel should return 1 to indicate + * that arr_timer was active at this time + */ + err |= 8; + + /* try to cancel ourself. It shouldn't deadlock. */ + if (bpf_timer_cancel(&val->timer) != -EDEADLK) + err |= 16; + + /* delete this key and this timer anyway. + * It shouldn't deadlock either. + */ + bpf_map_delete_elem(map, key); + + /* in preallocated hashmap both 'key' and 'val' could have been + * reused to store another map element (like in LRU above), + * but in controlled test environment the below test works. + * It's not a use-after-free. The memory is owned by the map. + */ + if (bpf_timer_start(&val->timer, 1000, 0) != -EINVAL) + err |= 32; + ok |= 2; + } else { + if (*key != HTAB_MALLOC) + err |= 64; + + /* try to cancel ourself. It shouldn't deadlock. */ + if (bpf_timer_cancel(&val->timer) != -EDEADLK) + err |= 128; + + /* delete this key and this timer anyway. + * It shouldn't deadlock either. + */ + bpf_map_delete_elem(map, key); + + ok |= 4; + } + return 0; +} + +int bpf_timer_test(void) +{ + struct hmap_elem *val; + int key = HTAB, key_malloc = HTAB_MALLOC; + + val = bpf_map_lookup_elem(&hmap, &key); + if (val) { + if (bpf_timer_init(&val->timer, &hmap, CLOCK_BOOTTIME) != 0) + err |= 512; + bpf_timer_set_callback(&val->timer, timer_cb2); + bpf_timer_start(&val->timer, 1000, 0); + } + val = bpf_map_lookup_elem(&hmap_malloc, &key_malloc); + if (val) { + if (bpf_timer_init(&val->timer, &hmap_malloc, CLOCK_BOOTTIME) != 0) + err |= 1024; + bpf_timer_set_callback(&val->timer, timer_cb2); + bpf_timer_start(&val->timer, 1000, 0); + } + return 0; +} + +SEC("fentry/bpf_fentry_test2") +int BPF_PROG2(test2, int, a, int, b) +{ + struct hmap_elem init = {}, *val; + int key = HTAB, key_malloc = HTAB_MALLOC; + + init.counter = 10; /* number of times to trigger timer_cb2 */ + bpf_map_update_elem(&hmap, &key, &init, 0); + val = bpf_map_lookup_elem(&hmap, &key); + if (val) + bpf_timer_init(&val->timer, &hmap, CLOCK_BOOTTIME); + /* update the same key to free the timer */ + bpf_map_update_elem(&hmap, &key, &init, 0); + + bpf_map_update_elem(&hmap_malloc, &key_malloc, &init, 0); + val = bpf_map_lookup_elem(&hmap_malloc, &key_malloc); + if (val) + bpf_timer_init(&val->timer, &hmap_malloc, CLOCK_BOOTTIME); + /* update the same key to free the timer */ + bpf_map_update_elem(&hmap_malloc, &key_malloc, &init, 0); + + /* init more timers to check that htab operations + * don't leak timer memory. + */ + key = 0; + bpf_map_update_elem(&hmap, &key, &init, 0); + val = bpf_map_lookup_elem(&hmap, &key); + if (val) + bpf_timer_init(&val->timer, &hmap, CLOCK_BOOTTIME); + bpf_map_delete_elem(&hmap, &key); + bpf_map_update_elem(&hmap, &key, &init, 0); + val = bpf_map_lookup_elem(&hmap, &key); + if (val) + bpf_timer_init(&val->timer, &hmap, CLOCK_BOOTTIME); + + /* and with non-prealloc htab */ + key_malloc = 0; + bpf_map_update_elem(&hmap_malloc, &key_malloc, &init, 0); + val = bpf_map_lookup_elem(&hmap_malloc, &key_malloc); + if (val) + bpf_timer_init(&val->timer, &hmap_malloc, CLOCK_BOOTTIME); + bpf_map_delete_elem(&hmap_malloc, &key_malloc); + bpf_map_update_elem(&hmap_malloc, &key_malloc, &init, 0); + val = bpf_map_lookup_elem(&hmap_malloc, &key_malloc); + if (val) + bpf_timer_init(&val->timer, &hmap_malloc, CLOCK_BOOTTIME); + + return bpf_timer_test(); +} + +/* callback for absolute timer */ +static int timer_cb3(void *map, int *key, struct bpf_timer *timer) +{ + abs_data += 6; + + if (abs_data < 12) { + bpf_timer_start(timer, bpf_ktime_get_boot_ns() + 1000, + BPF_F_TIMER_ABS); + } else { + /* Re-arm timer ~35 seconds in future */ + bpf_timer_start(timer, bpf_ktime_get_boot_ns() + (1ull << 35), + BPF_F_TIMER_ABS); + } + + return 0; +} + +SEC("fentry/bpf_fentry_test3") +int BPF_PROG2(test3, int, a) +{ + int key = 0; + struct bpf_timer *timer; + + bpf_printk("test3"); + + timer = bpf_map_lookup_elem(&abs_timer, &key); + if (timer) { + if (bpf_timer_init(timer, &abs_timer, CLOCK_BOOTTIME) != 0) + err |= 2048; + bpf_timer_set_callback(timer, timer_cb3); + bpf_timer_start(timer, bpf_ktime_get_boot_ns() + 1000, + BPF_F_TIMER_ABS); + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/timer_crash.c b/tools/testing/selftests/bpf/progs/timer_crash.c new file mode 100644 index 0000000000..f8f7944e70 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/timer_crash.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +struct map_elem { + struct bpf_timer timer; + struct bpf_spin_lock lock; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct map_elem); +} amap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct map_elem); +} hmap SEC(".maps"); + +int pid = 0; +int crash_map = 0; /* 0 for amap, 1 for hmap */ + +SEC("fentry/do_nanosleep") +int sys_enter(void *ctx) +{ + struct map_elem *e, value = {}; + void *map = crash_map ? (void *)&hmap : (void *)&amap; + + if (bpf_get_current_task_btf()->tgid != pid) + return 0; + + *(void **)&value = (void *)0xdeadcaf3; + + bpf_map_update_elem(map, &(int){0}, &value, 0); + /* For array map, doing bpf_map_update_elem will do a + * check_and_free_timer_in_array, which will trigger the crash if timer + * pointer was overwritten, for hmap we need to use bpf_timer_cancel. + */ + if (crash_map == 1) { + e = bpf_map_lookup_elem(map, &(int){0}); + if (!e) + return 0; + bpf_timer_cancel(&e->timer); + } + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/timer_failure.c b/tools/testing/selftests/bpf/progs/timer_failure.c new file mode 100644 index 0000000000..226d33b5a0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/timer_failure.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf.h> +#include <time.h> +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; + +struct elem { + struct bpf_timer t; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct elem); +} timer_map SEC(".maps"); + +static int timer_cb_ret1(void *map, int *key, struct bpf_timer *timer) +{ + if (bpf_get_smp_processor_id() % 2) + return 1; + else + return 0; +} + +SEC("fentry/bpf_fentry_test1") +__failure __msg("should have been in (0x0; 0x0)") +int BPF_PROG2(test_ret_1, int, a) +{ + int key = 0; + struct bpf_timer *timer; + + timer = bpf_map_lookup_elem(&timer_map, &key); + if (timer) { + bpf_timer_init(timer, &timer_map, CLOCK_BOOTTIME); + bpf_timer_set_callback(timer, timer_cb_ret1); + bpf_timer_start(timer, 1000, 0); + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/timer_mim.c b/tools/testing/selftests/bpf/progs/timer_mim.c new file mode 100644 index 0000000000..2fee7ab105 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/timer_mim.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <linux/bpf.h> +#include <time.h> +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; +struct hmap_elem { + int pad; /* unused */ + struct bpf_timer timer; +}; + +struct inner_map { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1024); + __type(key, int); + __type(value, struct hmap_elem); +} inner_htab SEC(".maps"); + +#define ARRAY_KEY 1 +#define HASH_KEY 1234 + +struct outer_arr { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 2); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); + __array(values, struct inner_map); +} outer_arr SEC(".maps") = { + .values = { [ARRAY_KEY] = &inner_htab }, +}; + +__u64 err; +__u64 ok; +__u64 cnt; + +static int timer_cb1(void *map, int *key, struct hmap_elem *val); + +static int timer_cb2(void *map, int *key, struct hmap_elem *val) +{ + cnt++; + bpf_timer_set_callback(&val->timer, timer_cb1); + if (bpf_timer_start(&val->timer, 1000, 0)) + err |= 1; + ok |= 1; + return 0; +} + +/* callback for inner hash map */ +static int timer_cb1(void *map, int *key, struct hmap_elem *val) +{ + cnt++; + bpf_timer_set_callback(&val->timer, timer_cb2); + if (bpf_timer_start(&val->timer, 1000, 0)) + err |= 2; + /* Do a lookup to make sure 'map' and 'key' pointers are correct */ + bpf_map_lookup_elem(map, key); + ok |= 2; + return 0; +} + +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(test1, int a) +{ + struct hmap_elem init = {}; + struct bpf_map *inner_map; + struct hmap_elem *val; + int array_key = ARRAY_KEY; + int hash_key = HASH_KEY; + + inner_map = bpf_map_lookup_elem(&outer_arr, &array_key); + if (!inner_map) + return 0; + + bpf_map_update_elem(inner_map, &hash_key, &init, 0); + val = bpf_map_lookup_elem(inner_map, &hash_key); + if (!val) + return 0; + + bpf_timer_init(&val->timer, inner_map, CLOCK_MONOTONIC); + if (bpf_timer_set_callback(&val->timer, timer_cb1)) + err |= 4; + if (bpf_timer_start(&val->timer, 0, 0)) + err |= 8; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/timer_mim_reject.c b/tools/testing/selftests/bpf/progs/timer_mim_reject.c new file mode 100644 index 0000000000..5d648e3d8a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/timer_mim_reject.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <linux/bpf.h> +#include <time.h> +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; +struct hmap_elem { + int pad; /* unused */ + struct bpf_timer timer; +}; + +struct inner_map { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1024); + __type(key, int); + __type(value, struct hmap_elem); +} inner_htab SEC(".maps"); + +#define ARRAY_KEY 1 +#define ARRAY_KEY2 2 +#define HASH_KEY 1234 + +struct outer_arr { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 2); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); + __array(values, struct inner_map); +} outer_arr SEC(".maps") = { + .values = { [ARRAY_KEY] = &inner_htab }, +}; + +__u64 err; +__u64 ok; +__u64 cnt; + +/* callback for inner hash map */ +static int timer_cb(void *map, int *key, struct hmap_elem *val) +{ + return 0; +} + +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(test1, int a) +{ + struct hmap_elem init = {}; + struct bpf_map *inner_map, *inner_map2; + struct hmap_elem *val; + int array_key = ARRAY_KEY; + int array_key2 = ARRAY_KEY2; + int hash_key = HASH_KEY; + + inner_map = bpf_map_lookup_elem(&outer_arr, &array_key); + if (!inner_map) + return 0; + + inner_map2 = bpf_map_lookup_elem(&outer_arr, &array_key2); + if (!inner_map2) + return 0; + bpf_map_update_elem(inner_map, &hash_key, &init, 0); + val = bpf_map_lookup_elem(inner_map, &hash_key); + if (!val) + return 0; + + bpf_timer_init(&val->timer, inner_map2, CLOCK_MONOTONIC); + if (bpf_timer_set_callback(&val->timer, timer_cb)) + err |= 4; + if (bpf_timer_start(&val->timer, 0, 0)) + err |= 8; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c b/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c new file mode 100644 index 0000000000..00a4be9d30 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +int val = 0; + +SEC("fentry/test_1") +int BPF_PROG(fentry_test_1, __u64 *st_ops_ctx) +{ + __u64 state; + + /* Read the traced st_ops arg1 which is a pointer */ + bpf_probe_read_kernel(&state, sizeof(__u64), (void *)st_ops_ctx); + /* Read state->val */ + bpf_probe_read_kernel(&val, sizeof(__u32), (void *)state); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/trace_printk.c b/tools/testing/selftests/bpf/progs/trace_printk.c new file mode 100644 index 0000000000..6695478c2b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/trace_printk.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020, Oracle and/or its affiliates. + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +int trace_printk_ret = 0; +int trace_printk_ran = 0; + +const char fmt[] = "Testing,testing %d\n"; + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int sys_enter(void *ctx) +{ + trace_printk_ret = bpf_trace_printk(fmt, sizeof(fmt), + ++trace_printk_ran); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/trace_vprintk.c b/tools/testing/selftests/bpf/progs/trace_vprintk.c new file mode 100644 index 0000000000..969306cd4f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/trace_vprintk.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +int null_data_vprintk_ret = 0; +int trace_vprintk_ret = 0; +int trace_vprintk_ran = 0; + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int sys_enter(void *ctx) +{ + static const char one[] = "1"; + static const char three[] = "3"; + static const char five[] = "5"; + static const char seven[] = "7"; + static const char nine[] = "9"; + static const char f[] = "%pS\n"; + + /* runner doesn't search for \t, just ensure it compiles */ + bpf_printk("\t"); + + trace_vprintk_ret = __bpf_vprintk("%s,%d,%s,%d,%s,%d,%s,%d,%s,%d %d\n", + one, 2, three, 4, five, 6, seven, 8, nine, 10, ++trace_vprintk_ran); + + /* non-NULL fmt w/ NULL data should result in error */ + null_data_vprintk_ret = bpf_trace_vprintk(f, sizeof(f), NULL, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/tracing_struct.c b/tools/testing/selftests/bpf/progs/tracing_struct.c new file mode 100644 index 0000000000..515daef3c8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tracing_struct.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +struct bpf_testmod_struct_arg_1 { + int a; +}; +struct bpf_testmod_struct_arg_2 { + long a; + long b; +}; + +struct bpf_testmod_struct_arg_3 { + int a; + int b[]; +}; + +struct bpf_testmod_struct_arg_4 { + u64 a; + int b; +}; + +long t1_a_a, t1_a_b, t1_b, t1_c, t1_ret, t1_nregs; +__u64 t1_reg0, t1_reg1, t1_reg2, t1_reg3; +long t2_a, t2_b_a, t2_b_b, t2_c, t2_ret; +long t3_a, t3_b, t3_c_a, t3_c_b, t3_ret; +long t4_a_a, t4_b, t4_c, t4_d, t4_e_a, t4_e_b, t4_ret; +long t5_ret; +int t6; +long t7_a, t7_b, t7_c, t7_d, t7_e, t7_f_a, t7_f_b, t7_ret; +long t8_a, t8_b, t8_c, t8_d, t8_e, t8_f_a, t8_f_b, t8_g, t8_ret; + + +SEC("fentry/bpf_testmod_test_struct_arg_1") +int BPF_PROG2(test_struct_arg_1, struct bpf_testmod_struct_arg_2, a, int, b, int, c) +{ + t1_a_a = a.a; + t1_a_b = a.b; + t1_b = b; + t1_c = c; + return 0; +} + +SEC("fexit/bpf_testmod_test_struct_arg_1") +int BPF_PROG2(test_struct_arg_2, struct bpf_testmod_struct_arg_2, a, int, b, int, c, int, ret) +{ + t1_nregs = bpf_get_func_arg_cnt(ctx); + /* a.a */ + bpf_get_func_arg(ctx, 0, &t1_reg0); + /* a.b */ + bpf_get_func_arg(ctx, 1, &t1_reg1); + /* b */ + bpf_get_func_arg(ctx, 2, &t1_reg2); + t1_reg2 = (int)t1_reg2; + /* c */ + bpf_get_func_arg(ctx, 3, &t1_reg3); + t1_reg3 = (int)t1_reg3; + + t1_ret = ret; + return 0; +} + +SEC("fentry/bpf_testmod_test_struct_arg_2") +int BPF_PROG2(test_struct_arg_3, int, a, struct bpf_testmod_struct_arg_2, b, int, c) +{ + t2_a = a; + t2_b_a = b.a; + t2_b_b = b.b; + t2_c = c; + return 0; +} + +SEC("fexit/bpf_testmod_test_struct_arg_2") +int BPF_PROG2(test_struct_arg_4, int, a, struct bpf_testmod_struct_arg_2, b, int, c, int, ret) +{ + t2_ret = ret; + return 0; +} + +SEC("fentry/bpf_testmod_test_struct_arg_3") +int BPF_PROG2(test_struct_arg_5, int, a, int, b, struct bpf_testmod_struct_arg_2, c) +{ + t3_a = a; + t3_b = b; + t3_c_a = c.a; + t3_c_b = c.b; + return 0; +} + +SEC("fexit/bpf_testmod_test_struct_arg_3") +int BPF_PROG2(test_struct_arg_6, int, a, int, b, struct bpf_testmod_struct_arg_2, c, int, ret) +{ + t3_ret = ret; + return 0; +} + +SEC("fentry/bpf_testmod_test_struct_arg_4") +int BPF_PROG2(test_struct_arg_7, struct bpf_testmod_struct_arg_1, a, int, b, + int, c, int, d, struct bpf_testmod_struct_arg_2, e) +{ + t4_a_a = a.a; + t4_b = b; + t4_c = c; + t4_d = d; + t4_e_a = e.a; + t4_e_b = e.b; + return 0; +} + +SEC("fexit/bpf_testmod_test_struct_arg_4") +int BPF_PROG2(test_struct_arg_8, struct bpf_testmod_struct_arg_1, a, int, b, + int, c, int, d, struct bpf_testmod_struct_arg_2, e, int, ret) +{ + t4_ret = ret; + return 0; +} + +SEC("fentry/bpf_testmod_test_struct_arg_5") +int BPF_PROG2(test_struct_arg_9) +{ + return 0; +} + +SEC("fexit/bpf_testmod_test_struct_arg_5") +int BPF_PROG2(test_struct_arg_10, int, ret) +{ + t5_ret = ret; + return 0; +} + +SEC("fentry/bpf_testmod_test_struct_arg_6") +int BPF_PROG2(test_struct_arg_11, struct bpf_testmod_struct_arg_3 *, a) +{ + t6 = a->b[0]; + return 0; +} + +SEC("fentry/bpf_testmod_test_struct_arg_7") +int BPF_PROG2(test_struct_arg_12, __u64, a, void *, b, short, c, int, d, + void *, e, struct bpf_testmod_struct_arg_4, f) +{ + t7_a = a; + t7_b = (long)b; + t7_c = c; + t7_d = d; + t7_e = (long)e; + t7_f_a = f.a; + t7_f_b = f.b; + return 0; +} + +SEC("fexit/bpf_testmod_test_struct_arg_7") +int BPF_PROG2(test_struct_arg_13, __u64, a, void *, b, short, c, int, d, + void *, e, struct bpf_testmod_struct_arg_4, f, int, ret) +{ + t7_ret = ret; + return 0; +} + +SEC("fentry/bpf_testmod_test_struct_arg_8") +int BPF_PROG2(test_struct_arg_14, __u64, a, void *, b, short, c, int, d, + void *, e, struct bpf_testmod_struct_arg_4, f, int, g) +{ + t8_a = a; + t8_b = (long)b; + t8_c = c; + t8_d = d; + t8_e = (long)e; + t8_f_a = f.a; + t8_f_b = f.b; + t8_g = g; + return 0; +} + +SEC("fexit/bpf_testmod_test_struct_arg_8") +int BPF_PROG2(test_struct_arg_15, __u64, a, void *, b, short, c, int, d, + void *, e, struct bpf_testmod_struct_arg_4, f, int, g, + int, ret) +{ + t8_ret = ret; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c new file mode 100644 index 0000000000..694e7cec18 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/trigger_bench.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <asm/unistd.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +long hits = 0; + +SEC("tp/syscalls/sys_enter_getpgid") +int bench_trigger_tp(void *ctx) +{ + __sync_add_and_fetch(&hits, 1); + return 0; +} + +SEC("raw_tp/sys_enter") +int BPF_PROG(bench_trigger_raw_tp, struct pt_regs *regs, long id) +{ + if (id == __NR_getpgid) + __sync_add_and_fetch(&hits, 1); + return 0; +} + +SEC("kprobe/" SYS_PREFIX "sys_getpgid") +int bench_trigger_kprobe(void *ctx) +{ + __sync_add_and_fetch(&hits, 1); + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int bench_trigger_fentry(void *ctx) +{ + __sync_add_and_fetch(&hits, 1); + return 0; +} + +SEC("fentry.s/" SYS_PREFIX "sys_getpgid") +int bench_trigger_fentry_sleep(void *ctx) +{ + __sync_add_and_fetch(&hits, 1); + return 0; +} + +SEC("fmod_ret/" SYS_PREFIX "sys_getpgid") +int bench_trigger_fmodret(void *ctx) +{ + __sync_add_and_fetch(&hits, 1); + return -22; +} + +SEC("uprobe") +int bench_trigger_uprobe(void *ctx) +{ + __sync_add_and_fetch(&hits, 1); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/twfw.c b/tools/testing/selftests/bpf/progs/twfw.c new file mode 100644 index 0000000000..de1b18a62b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/twfw.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <linux/types.h> +#include <bpf/bpf_helpers.h> +#include <linux/bpf.h> +#include <stdint.h> + +#define TWFW_MAX_TIERS (64) +/* + * load is successful + * #define TWFW_MAX_TIERS (64u)$ + */ + +struct twfw_tier_value { + unsigned long mask[1]; +}; + +struct rule { + uint8_t seqnum; +}; + +struct rules_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, struct rule); + __uint(max_entries, 1); +}; + +struct tiers_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, struct twfw_tier_value); + __uint(max_entries, 1); +}; + +struct rules_map rules SEC(".maps"); +struct tiers_map tiers SEC(".maps"); + +SEC("cgroup_skb/ingress") +int twfw_verifier(struct __sk_buff* skb) +{ + const uint32_t key = 0; + const struct twfw_tier_value* tier = bpf_map_lookup_elem(&tiers, &key); + if (!tier) + return 1; + + struct rule* rule = bpf_map_lookup_elem(&rules, &key); + if (!rule) + return 1; + + if (rule && rule->seqnum < TWFW_MAX_TIERS) { + /* rule->seqnum / 64 should always be 0 */ + unsigned long mask = tier->mask[rule->seqnum / 64]; + if (mask) + return 0; + } + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/type_cast.c b/tools/testing/selftests/bpf/progs/type_cast.c new file mode 100644 index 0000000000..a9629ac230 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/type_cast.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} enter_id SEC(".maps"); + +#define IFNAMSIZ 16 + +int ifindex, ingress_ifindex; +char name[IFNAMSIZ]; +unsigned int inum; +unsigned int meta_len, frag0_len, kskb_len, kskb2_len; + +void *bpf_cast_to_kern_ctx(void *) __ksym; +void *bpf_rdonly_cast(void *, __u32) __ksym; + +SEC("?xdp") +int md_xdp(struct xdp_md *ctx) +{ + struct xdp_buff *kctx = bpf_cast_to_kern_ctx(ctx); + struct net_device *dev; + + dev = kctx->rxq->dev; + ifindex = dev->ifindex; + inum = dev->nd_net.net->ns.inum; + __builtin_memcpy(name, dev->name, IFNAMSIZ); + ingress_ifindex = ctx->ingress_ifindex; + return XDP_PASS; +} + +SEC("?tc") +int md_skb(struct __sk_buff *skb) +{ + struct sk_buff *kskb = bpf_cast_to_kern_ctx(skb); + struct skb_shared_info *shared_info; + struct sk_buff *kskb2; + + kskb_len = kskb->len; + + /* Simulate the following kernel macro: + * #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) + */ + shared_info = bpf_rdonly_cast(kskb->head + kskb->end, + bpf_core_type_id_kernel(struct skb_shared_info)); + meta_len = shared_info->meta_len; + frag0_len = shared_info->frag_list->len; + + /* kskb2 should be equal to kskb */ + kskb2 = bpf_rdonly_cast(kskb, bpf_core_type_id_kernel(struct sk_buff)); + kskb2_len = kskb2->len; + return 0; +} + +SEC("?tp_btf/sys_enter") +int BPF_PROG(untrusted_ptr, struct pt_regs *regs, long id) +{ + struct task_struct *task, *task_dup; + + task = bpf_get_current_task_btf(); + task_dup = bpf_rdonly_cast(task, bpf_core_type_id_kernel(struct task_struct)); + (void)bpf_task_storage_get(&enter_id, task_dup, 0, 0); + return 0; +} + +SEC("?tracepoint/syscalls/sys_enter_nanosleep") +int kctx_u64(void *ctx) +{ + u64 *kctx = bpf_rdonly_cast(ctx, bpf_core_type_id_kernel(u64)); + + (void)kctx; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/udp_limit.c b/tools/testing/selftests/bpf/progs/udp_limit.c new file mode 100644 index 0000000000..4767451b59 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/udp_limit.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <sys/socket.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +int invocations = 0, in_use = 0; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} sk_map SEC(".maps"); + +SEC("cgroup/sock_create") +int sock(struct bpf_sock *ctx) +{ + int *sk_storage; + + if (ctx->type != SOCK_DGRAM) + return 1; + + sk_storage = bpf_sk_storage_get(&sk_map, ctx, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!sk_storage) + return 0; + *sk_storage = 0xdeadbeef; + + __sync_fetch_and_add(&invocations, 1); + + if (in_use > 0) { + /* BPF_CGROUP_INET_SOCK_RELEASE is _not_ called + * when we return an error from the BPF + * program! + */ + return 0; + } + + __sync_fetch_and_add(&in_use, 1); + return 1; +} + +SEC("cgroup/sock_release") +int sock_release(struct bpf_sock *ctx) +{ + int *sk_storage; + + if (ctx->type != SOCK_DGRAM) + return 1; + + sk_storage = bpf_sk_storage_get(&sk_map, ctx, 0, 0); + if (!sk_storage || *sk_storage != 0xdeadbeef) + return 0; + + __sync_fetch_and_add(&invocations, 1); + __sync_fetch_and_add(&in_use, -1); + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/uninit_stack.c b/tools/testing/selftests/bpf/progs/uninit_stack.c new file mode 100644 index 0000000000..8a403470e5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/uninit_stack.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +/* Read an uninitialized value from stack at a fixed offset */ +SEC("socket") +__naked int read_uninit_stack_fixed_off(void *ctx) +{ + asm volatile (" \ + r0 = 0; \ + /* force stack depth to be 128 */ \ + *(u64*)(r10 - 128) = r1; \ + r1 = *(u8 *)(r10 - 8 ); \ + r0 += r1; \ + r1 = *(u8 *)(r10 - 11); \ + r1 = *(u8 *)(r10 - 13); \ + r1 = *(u8 *)(r10 - 15); \ + r1 = *(u16*)(r10 - 16); \ + r1 = *(u32*)(r10 - 32); \ + r1 = *(u64*)(r10 - 64); \ + /* read from a spill of a wrong size, it is a separate \ + * branch in check_stack_read_fixed_off() \ + */ \ + *(u32*)(r10 - 72) = r1; \ + r1 = *(u64*)(r10 - 72); \ + r0 = 0; \ + exit; \ +" + ::: __clobber_all); +} + +/* Read an uninitialized value from stack at a variable offset */ +SEC("socket") +__naked int read_uninit_stack_var_off(void *ctx) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + /* force stack depth to be 64 */ \ + *(u64*)(r10 - 64) = r0; \ + r0 = -r0; \ + /* give r0 a range [-31, -1] */ \ + if r0 s<= -32 goto exit_%=; \ + if r0 s>= 0 goto exit_%=; \ + /* access stack using r0 */ \ + r1 = r10; \ + r1 += r0; \ + r2 = *(u8*)(r1 + 0); \ +exit_%=: r0 = 0; \ + exit; \ +" + : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +static __noinline void dummy(void) {} + +/* Pass a pointer to uninitialized stack memory to a helper. + * Passed memory block should be marked as STACK_MISC after helper call. + */ +SEC("socket") +__log_level(7) __msg("fp-104=mmmmmmmm") +__naked int helper_uninit_to_misc(void *ctx) +{ + asm volatile (" \ + /* force stack depth to be 128 */ \ + *(u64*)(r10 - 128) = r1; \ + r1 = r10; \ + r1 += -128; \ + r2 = 32; \ + call %[bpf_trace_printk]; \ + /* Call to dummy() forces print_verifier_state(..., true), \ + * thus showing the stack state, matched by __msg(). \ + */ \ + call %[dummy]; \ + r0 = 0; \ + exit; \ +" + : + : __imm(bpf_trace_printk), + __imm(dummy) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi.c b/tools/testing/selftests/bpf/progs/uprobe_multi.c new file mode 100644 index 0000000000..419d9aa28f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/uprobe_multi.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <stdbool.h> + +char _license[] SEC("license") = "GPL"; + +__u64 uprobe_multi_func_1_addr = 0; +__u64 uprobe_multi_func_2_addr = 0; +__u64 uprobe_multi_func_3_addr = 0; + +__u64 uprobe_multi_func_1_result = 0; +__u64 uprobe_multi_func_2_result = 0; +__u64 uprobe_multi_func_3_result = 0; + +__u64 uretprobe_multi_func_1_result = 0; +__u64 uretprobe_multi_func_2_result = 0; +__u64 uretprobe_multi_func_3_result = 0; + +__u64 uprobe_multi_sleep_result = 0; + +int pid = 0; +int child_pid = 0; + +bool test_cookie = false; +void *user_ptr = 0; + +static __always_inline bool verify_sleepable_user_copy(void) +{ + char data[9]; + + bpf_copy_from_user(data, sizeof(data), user_ptr); + return bpf_strncmp(data, sizeof(data), "test_data") == 0; +} + +static void uprobe_multi_check(void *ctx, bool is_return, bool is_sleep) +{ + child_pid = bpf_get_current_pid_tgid() >> 32; + + if (pid && child_pid != pid) + return; + + __u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0; + __u64 addr = bpf_get_func_ip(ctx); + +#define SET(__var, __addr, __cookie) ({ \ + if (addr == __addr && \ + (!test_cookie || (cookie == __cookie))) \ + __var += 1; \ +}) + + if (is_return) { + SET(uretprobe_multi_func_1_result, uprobe_multi_func_1_addr, 2); + SET(uretprobe_multi_func_2_result, uprobe_multi_func_2_addr, 3); + SET(uretprobe_multi_func_3_result, uprobe_multi_func_3_addr, 1); + } else { + SET(uprobe_multi_func_1_result, uprobe_multi_func_1_addr, 3); + SET(uprobe_multi_func_2_result, uprobe_multi_func_2_addr, 1); + SET(uprobe_multi_func_3_result, uprobe_multi_func_3_addr, 2); + } + +#undef SET + + if (is_sleep && verify_sleepable_user_copy()) + uprobe_multi_sleep_result += 1; +} + +SEC("uprobe.multi//proc/self/exe:uprobe_multi_func_*") +int uprobe(struct pt_regs *ctx) +{ + uprobe_multi_check(ctx, false, false); + return 0; +} + +SEC("uretprobe.multi//proc/self/exe:uprobe_multi_func_*") +int uretprobe(struct pt_regs *ctx) +{ + uprobe_multi_check(ctx, true, false); + return 0; +} + +SEC("uprobe.multi.s//proc/self/exe:uprobe_multi_func_*") +int uprobe_sleep(struct pt_regs *ctx) +{ + uprobe_multi_check(ctx, false, true); + return 0; +} + +SEC("uretprobe.multi.s//proc/self/exe:uprobe_multi_func_*") +int uretprobe_sleep(struct pt_regs *ctx) +{ + uprobe_multi_check(ctx, true, true); + return 0; +} + +SEC("uprobe.multi//proc/self/exe:uprobe_multi_func_*") +int uprobe_extra(struct pt_regs *ctx) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_bench.c b/tools/testing/selftests/bpf/progs/uprobe_multi_bench.c new file mode 100644 index 0000000000..5367f6105e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/uprobe_multi_bench.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +int count; + +SEC("uprobe.multi/./uprobe_multi:uprobe_multi_func_*") +int uprobe_bench(struct pt_regs *ctx) +{ + count++; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_usdt.c b/tools/testing/selftests/bpf/progs/uprobe_multi_usdt.c new file mode 100644 index 0000000000..9e1c33d0bd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/uprobe_multi_usdt.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/usdt.bpf.h> + +char _license[] SEC("license") = "GPL"; + +int count; + +SEC("usdt") +int usdt0(struct pt_regs *ctx) +{ + count++; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c b/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c new file mode 100644 index 0000000000..03ee946c6b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c @@ -0,0 +1,223 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct sample { + int pid; + int seq; + long value; + char comm[16]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_USER_RINGBUF); + __uint(max_entries, 4096); +} user_ringbuf SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 2); +} ringbuf SEC(".maps"); + +static int map_value; + +static long +bad_access1(struct bpf_dynptr *dynptr, void *context) +{ + const struct sample *sample; + + sample = bpf_dynptr_data(dynptr - 1, 0, sizeof(*sample)); + bpf_printk("Was able to pass bad pointer %lx\n", (__u64)dynptr - 1); + + return 0; +} + +/* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should + * not be able to read before the pointer. + */ +SEC("?raw_tp") +__failure __msg("negative offset dynptr_ptr ptr") +int user_ringbuf_callback_bad_access1(void *ctx) +{ + bpf_user_ringbuf_drain(&user_ringbuf, bad_access1, NULL, 0); + + return 0; +} + +static long +bad_access2(struct bpf_dynptr *dynptr, void *context) +{ + const struct sample *sample; + + sample = bpf_dynptr_data(dynptr + 1, 0, sizeof(*sample)); + bpf_printk("Was able to pass bad pointer %lx\n", (__u64)dynptr + 1); + + return 0; +} + +/* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should + * not be able to read past the end of the pointer. + */ +SEC("?raw_tp") +__failure __msg("dereference of modified dynptr_ptr ptr") +int user_ringbuf_callback_bad_access2(void *ctx) +{ + bpf_user_ringbuf_drain(&user_ringbuf, bad_access2, NULL, 0); + + return 0; +} + +static long +write_forbidden(struct bpf_dynptr *dynptr, void *context) +{ + *((long *)dynptr) = 0; + + return 0; +} + +/* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should + * not be able to write to that pointer. + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'dynptr_ptr'") +int user_ringbuf_callback_write_forbidden(void *ctx) +{ + bpf_user_ringbuf_drain(&user_ringbuf, write_forbidden, NULL, 0); + + return 0; +} + +static long +null_context_write(struct bpf_dynptr *dynptr, void *context) +{ + *((__u64 *)context) = 0; + + return 0; +} + +/* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should + * not be able to write to that pointer. + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int user_ringbuf_callback_null_context_write(void *ctx) +{ + bpf_user_ringbuf_drain(&user_ringbuf, null_context_write, NULL, 0); + + return 0; +} + +static long +null_context_read(struct bpf_dynptr *dynptr, void *context) +{ + __u64 id = *((__u64 *)context); + + bpf_printk("Read id %lu\n", id); + + return 0; +} + +/* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should + * not be able to write to that pointer. + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int user_ringbuf_callback_null_context_read(void *ctx) +{ + bpf_user_ringbuf_drain(&user_ringbuf, null_context_read, NULL, 0); + + return 0; +} + +static long +try_discard_dynptr(struct bpf_dynptr *dynptr, void *context) +{ + bpf_ringbuf_discard_dynptr(dynptr, 0); + + return 0; +} + +/* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should + * not be able to read past the end of the pointer. + */ +SEC("?raw_tp") +__failure __msg("cannot release unowned const bpf_dynptr") +int user_ringbuf_callback_discard_dynptr(void *ctx) +{ + bpf_user_ringbuf_drain(&user_ringbuf, try_discard_dynptr, NULL, 0); + + return 0; +} + +static long +try_submit_dynptr(struct bpf_dynptr *dynptr, void *context) +{ + bpf_ringbuf_submit_dynptr(dynptr, 0); + + return 0; +} + +/* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should + * not be able to read past the end of the pointer. + */ +SEC("?raw_tp") +__failure __msg("cannot release unowned const bpf_dynptr") +int user_ringbuf_callback_submit_dynptr(void *ctx) +{ + bpf_user_ringbuf_drain(&user_ringbuf, try_submit_dynptr, NULL, 0); + + return 0; +} + +static long +invalid_drain_callback_return(struct bpf_dynptr *dynptr, void *context) +{ + return 2; +} + +/* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should + * not be able to write to that pointer. + */ +SEC("?raw_tp") +__failure __msg("At callback return the register R0 has value") +int user_ringbuf_callback_invalid_return(void *ctx) +{ + bpf_user_ringbuf_drain(&user_ringbuf, invalid_drain_callback_return, NULL, 0); + + return 0; +} + +static long +try_reinit_dynptr_mem(struct bpf_dynptr *dynptr, void *context) +{ + bpf_dynptr_from_mem(&map_value, 4, 0, dynptr); + return 0; +} + +static long +try_reinit_dynptr_ringbuf(struct bpf_dynptr *dynptr, void *context) +{ + bpf_ringbuf_reserve_dynptr(&ringbuf, 8, 0, dynptr); + return 0; +} + +SEC("?raw_tp") +__failure __msg("Dynptr has to be an uninitialized dynptr") +int user_ringbuf_callback_reinit_dynptr_mem(void *ctx) +{ + bpf_user_ringbuf_drain(&user_ringbuf, try_reinit_dynptr_mem, NULL, 0); + return 0; +} + +SEC("?raw_tp") +__failure __msg("Dynptr has to be an uninitialized dynptr") +int user_ringbuf_callback_reinit_dynptr_ringbuf(void *ctx) +{ + bpf_user_ringbuf_drain(&user_ringbuf, try_reinit_dynptr_ringbuf, NULL, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/user_ringbuf_success.c b/tools/testing/selftests/bpf/progs/user_ringbuf_success.c new file mode 100644 index 0000000000..dd3bdf6726 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/user_ringbuf_success.c @@ -0,0 +1,212 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" +#include "test_user_ringbuf.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_USER_RINGBUF); +} user_ringbuf SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); +} kernel_ringbuf SEC(".maps"); + +/* inputs */ +int pid, err, val; + +int read = 0; + +/* Counter used for end-to-end protocol test */ +__u64 kern_mutated = 0; +__u64 user_mutated = 0; +__u64 expected_user_mutated = 0; + +static int +is_test_process(void) +{ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + + return cur_pid == pid; +} + +static long +record_sample(struct bpf_dynptr *dynptr, void *context) +{ + const struct sample *sample = NULL; + struct sample stack_sample; + int status; + static int num_calls; + + if (num_calls++ % 2 == 0) { + status = bpf_dynptr_read(&stack_sample, sizeof(stack_sample), dynptr, 0, 0); + if (status) { + bpf_printk("bpf_dynptr_read() failed: %d\n", status); + err = 1; + return 1; + } + } else { + sample = bpf_dynptr_data(dynptr, 0, sizeof(*sample)); + if (!sample) { + bpf_printk("Unexpectedly failed to get sample\n"); + err = 2; + return 1; + } + stack_sample = *sample; + } + + __sync_fetch_and_add(&read, 1); + return 0; +} + +static void +handle_sample_msg(const struct test_msg *msg) +{ + switch (msg->msg_op) { + case TEST_MSG_OP_INC64: + kern_mutated += msg->operand_64; + break; + case TEST_MSG_OP_INC32: + kern_mutated += msg->operand_32; + break; + case TEST_MSG_OP_MUL64: + kern_mutated *= msg->operand_64; + break; + case TEST_MSG_OP_MUL32: + kern_mutated *= msg->operand_32; + break; + default: + bpf_printk("Unrecognized op %d\n", msg->msg_op); + err = 2; + } +} + +static long +read_protocol_msg(struct bpf_dynptr *dynptr, void *context) +{ + const struct test_msg *msg = NULL; + + msg = bpf_dynptr_data(dynptr, 0, sizeof(*msg)); + if (!msg) { + err = 1; + bpf_printk("Unexpectedly failed to get msg\n"); + return 0; + } + + handle_sample_msg(msg); + + return 0; +} + +static int publish_next_kern_msg(__u32 index, void *context) +{ + struct test_msg *msg = NULL; + int operand_64 = TEST_OP_64; + int operand_32 = TEST_OP_32; + + msg = bpf_ringbuf_reserve(&kernel_ringbuf, sizeof(*msg), 0); + if (!msg) { + err = 4; + return 1; + } + + switch (index % TEST_MSG_OP_NUM_OPS) { + case TEST_MSG_OP_INC64: + msg->operand_64 = operand_64; + msg->msg_op = TEST_MSG_OP_INC64; + expected_user_mutated += operand_64; + break; + case TEST_MSG_OP_INC32: + msg->operand_32 = operand_32; + msg->msg_op = TEST_MSG_OP_INC32; + expected_user_mutated += operand_32; + break; + case TEST_MSG_OP_MUL64: + msg->operand_64 = operand_64; + msg->msg_op = TEST_MSG_OP_MUL64; + expected_user_mutated *= operand_64; + break; + case TEST_MSG_OP_MUL32: + msg->operand_32 = operand_32; + msg->msg_op = TEST_MSG_OP_MUL32; + expected_user_mutated *= operand_32; + break; + default: + bpf_ringbuf_discard(msg, 0); + err = 5; + return 1; + } + + bpf_ringbuf_submit(msg, 0); + + return 0; +} + +static void +publish_kern_messages(void) +{ + if (expected_user_mutated != user_mutated) { + bpf_printk("%lu != %lu\n", expected_user_mutated, user_mutated); + err = 3; + return; + } + + bpf_loop(8, publish_next_kern_msg, NULL, 0); +} + +SEC("fentry/" SYS_PREFIX "sys_prctl") +int test_user_ringbuf_protocol(void *ctx) +{ + long status = 0; + + if (!is_test_process()) + return 0; + + status = bpf_user_ringbuf_drain(&user_ringbuf, read_protocol_msg, NULL, 0); + if (status < 0) { + bpf_printk("Drain returned: %ld\n", status); + err = 1; + return 0; + } + + publish_kern_messages(); + + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int test_user_ringbuf(void *ctx) +{ + if (!is_test_process()) + return 0; + + err = bpf_user_ringbuf_drain(&user_ringbuf, record_sample, NULL, 0); + + return 0; +} + +static long +do_nothing_cb(struct bpf_dynptr *dynptr, void *context) +{ + __sync_fetch_and_add(&read, 1); + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_prlimit64") +int test_user_ringbuf_epoll(void *ctx) +{ + long num_samples; + + if (!is_test_process()) + return 0; + + num_samples = bpf_user_ringbuf_drain(&user_ringbuf, do_nothing_cb, NULL, 0); + if (num_samples <= 0) + err = 1; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/verifier_and.c b/tools/testing/selftests/bpf/progs/verifier_and.c new file mode 100644 index 0000000000..e97e518516 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_and.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/and.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct test_val); +} map_hash_48b SEC(".maps"); + +SEC("socket") +__description("invalid and of negative number") +__failure __msg("R0 max value is outside of the allowed memory range") +__failure_unpriv +__flag(BPF_F_ANY_ALIGNMENT) +__naked void invalid_and_of_negative_number(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u8*)(r0 + 0); \ + r1 &= -4; \ + r1 <<= 2; \ + r0 += r1; \ +l0_%=: r1 = %[test_val_foo]; \ + *(u64*)(r0 + 0) = r1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("socket") +__description("invalid range check") +__failure __msg("R0 max value is outside of the allowed memory range") +__failure_unpriv +__flag(BPF_F_ANY_ALIGNMENT) +__naked void invalid_range_check(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u32*)(r0 + 0); \ + r9 = 1; \ + w1 %%= 2; \ + w1 += 1; \ + w9 &= w1; \ + w9 += 1; \ + w9 >>= 1; \ + w3 = 1; \ + w3 -= w9; \ + w3 *= 0x10000000; \ + r0 += r3; \ + *(u32*)(r0 + 0) = r3; \ +l0_%=: r0 = r0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("socket") +__description("check known subreg with unknown reg") +__success __failure_unpriv __msg_unpriv("R1 !read_ok") +__retval(0) +__naked void known_subreg_with_unknown_reg(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r0 <<= 32; \ + r0 += 1; \ + r0 &= 0xFFFF1234; \ + /* Upper bits are unknown but AND above masks out 1 zero'ing lower bits */\ + if w0 < 1 goto l0_%=; \ + r1 = *(u32*)(r1 + 512); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_array_access.c b/tools/testing/selftests/bpf/progs/verifier_array_access.c new file mode 100644 index 0000000000..95d7ecc129 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_array_access.c @@ -0,0 +1,529 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/array_access.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct test_val); + __uint(map_flags, BPF_F_RDONLY_PROG); +} map_array_ro SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct test_val); + __uint(map_flags, BPF_F_WRONLY_PROG); +} map_array_wo SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct test_val); +} map_hash_48b SEC(".maps"); + +SEC("socket") +__description("valid map access into an array with a constant") +__success __failure_unpriv __msg_unpriv("R0 leaks addr") +__retval(0) +__naked void an_array_with_a_constant_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = %[test_val_foo]; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("socket") +__description("valid map access into an array with a register") +__success __failure_unpriv __msg_unpriv("R0 leaks addr") +__retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void an_array_with_a_register_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 4; \ + r1 <<= 2; \ + r0 += r1; \ + r1 = %[test_val_foo]; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("socket") +__description("valid map access into an array with a variable") +__success __failure_unpriv __msg_unpriv("R0 leaks addr") +__retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void an_array_with_a_variable_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u32*)(r0 + 0); \ + if r1 >= %[max_entries] goto l0_%=; \ + r1 <<= 2; \ + r0 += r1; \ + r1 = %[test_val_foo]; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(max_entries, MAX_ENTRIES), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("socket") +__description("valid map access into an array with a signed variable") +__success __failure_unpriv __msg_unpriv("R0 leaks addr") +__retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void array_with_a_signed_variable(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u32*)(r0 + 0); \ + if w1 s> 0xffffffff goto l1_%=; \ + w1 = 0; \ +l1_%=: w2 = %[max_entries]; \ + if r2 s> r1 goto l2_%=; \ + w1 = 0; \ +l2_%=: w1 <<= 2; \ + r0 += r1; \ + r1 = %[test_val_foo]; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(max_entries, MAX_ENTRIES), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("socket") +__description("invalid map access into an array with a constant") +__failure __msg("invalid access to map value, value_size=48 off=48 size=8") +__failure_unpriv +__naked void an_array_with_a_constant_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = %[test_val_foo]; \ + *(u64*)(r0 + %[__imm_0]) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(__imm_0, (MAX_ENTRIES + 1) << 2), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("socket") +__description("invalid map access into an array with a register") +__failure __msg("R0 min value is outside of the allowed memory range") +__failure_unpriv +__flag(BPF_F_ANY_ALIGNMENT) +__naked void an_array_with_a_register_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = %[__imm_0]; \ + r1 <<= 2; \ + r0 += r1; \ + r1 = %[test_val_foo]; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(__imm_0, MAX_ENTRIES + 1), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("socket") +__description("invalid map access into an array with a variable") +__failure +__msg("R0 unbounded memory access, make sure to bounds check any such access") +__failure_unpriv +__flag(BPF_F_ANY_ALIGNMENT) +__naked void an_array_with_a_variable_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u32*)(r0 + 0); \ + r1 <<= 2; \ + r0 += r1; \ + r1 = %[test_val_foo]; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("socket") +__description("invalid map access into an array with no floor check") +__failure __msg("R0 unbounded memory access") +__failure_unpriv __msg_unpriv("R0 leaks addr") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void array_with_no_floor_check(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r0 + 0); \ + w2 = %[max_entries]; \ + if r2 s> r1 goto l1_%=; \ + w1 = 0; \ +l1_%=: w1 <<= 2; \ + r0 += r1; \ + r1 = %[test_val_foo]; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(max_entries, MAX_ENTRIES), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("socket") +__description("invalid map access into an array with a invalid max check") +__failure __msg("invalid access to map value, value_size=48 off=44 size=8") +__failure_unpriv __msg_unpriv("R0 leaks addr") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void with_a_invalid_max_check_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u32*)(r0 + 0); \ + w2 = %[__imm_0]; \ + if r2 > r1 goto l1_%=; \ + w1 = 0; \ +l1_%=: w1 <<= 2; \ + r0 += r1; \ + r1 = %[test_val_foo]; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(__imm_0, MAX_ENTRIES + 1), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("socket") +__description("invalid map access into an array with a invalid max check") +__failure __msg("R0 pointer += pointer") +__failure_unpriv +__flag(BPF_F_ANY_ALIGNMENT) +__naked void with_a_invalid_max_check_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r8 = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r0 += r8; \ + r0 = *(u32*)(r0 + %[test_val_foo]); \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("socket") +__description("valid read map access into a read-only array 1") +__success __success_unpriv __retval(28) +__naked void a_read_only_array_1_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_ro] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r0 = *(u32*)(r0 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_ro) + : __clobber_all); +} + +SEC("tc") +__description("valid read map access into a read-only array 2") +__success __retval(65507) +__naked void a_read_only_array_2_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_ro] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = 4; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ +l0_%=: r0 &= 0xffff; \ + exit; \ +" : + : __imm(bpf_csum_diff), + __imm(bpf_map_lookup_elem), + __imm_addr(map_array_ro) + : __clobber_all); +} + +SEC("socket") +__description("invalid write map access into a read-only array 1") +__failure __msg("write into map forbidden") +__failure_unpriv +__naked void a_read_only_array_1_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_ro] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 42; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_ro) + : __clobber_all); +} + +SEC("tc") +__description("invalid write map access into a read-only array 2") +__failure __msg("write into map forbidden") +__naked void a_read_only_array_2_2(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_ro] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r6; \ + r2 = 0; \ + r3 = r0; \ + r4 = 8; \ + call %[bpf_skb_load_bytes]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_skb_load_bytes), + __imm_addr(map_array_ro) + : __clobber_all); +} + +SEC("socket") +__description("valid write map access into a write-only array 1") +__success __success_unpriv __retval(1) +__naked void a_write_only_array_1_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_wo] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 42; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_wo) + : __clobber_all); +} + +SEC("tc") +__description("valid write map access into a write-only array 2") +__success __retval(0) +__naked void a_write_only_array_2_1(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_wo] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r6; \ + r2 = 0; \ + r3 = r0; \ + r4 = 8; \ + call %[bpf_skb_load_bytes]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_skb_load_bytes), + __imm_addr(map_array_wo) + : __clobber_all); +} + +SEC("socket") +__description("invalid read map access into a write-only array 1") +__failure __msg("read from map forbidden") +__failure_unpriv +__naked void a_write_only_array_1_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_wo] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r0 = *(u64*)(r0 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_wo) + : __clobber_all); +} + +SEC("tc") +__description("invalid read map access into a write-only array 2") +__failure __msg("read from map forbidden") +__naked void a_write_only_array_2_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_wo] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = 4; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ +l0_%=: exit; \ +" : + : __imm(bpf_csum_diff), + __imm(bpf_map_lookup_elem), + __imm_addr(map_array_wo) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_basic_stack.c b/tools/testing/selftests/bpf/progs/verifier_basic_stack.c new file mode 100644 index 0000000000..8d77cc5323 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_basic_stack.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/basic_stack.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +SEC("socket") +__description("stack out of bounds") +__failure __msg("invalid write to stack") +__failure_unpriv +__naked void stack_out_of_bounds(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 + 8) = r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("uninitialized stack1") +__success __log_level(4) __msg("stack depth 8") +__failure_unpriv __msg_unpriv("invalid indirect read from stack") +__naked void uninitialized_stack1(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("uninitialized stack2") +__success __log_level(4) __msg("stack depth 8") +__failure_unpriv __msg_unpriv("invalid read from stack") +__naked void uninitialized_stack2(void) +{ + asm volatile (" \ + r2 = r10; \ + r0 = *(u64*)(r2 - 8); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("invalid fp arithmetic") +__failure __msg("R1 subtraction from stack pointer") +__failure_unpriv +__naked void invalid_fp_arithmetic(void) +{ + /* If this gets ever changed, make sure JITs can deal with it. */ + asm volatile (" \ + r0 = 0; \ + r1 = r10; \ + r1 -= 8; \ + *(u64*)(r1 + 0) = r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("non-invalid fp arithmetic") +__success __success_unpriv __retval(0) +__naked void non_invalid_fp_arithmetic(void) +{ + asm volatile (" \ + r0 = 0; \ + *(u64*)(r10 - 8) = r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("misaligned read from stack") +__failure __msg("misaligned stack access") +__failure_unpriv +__naked void misaligned_read_from_stack(void) +{ + asm volatile (" \ + r2 = r10; \ + r0 = *(u64*)(r2 - 4); \ + exit; \ +" ::: __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c new file mode 100644 index 0000000000..c5588a14fe --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c @@ -0,0 +1,1076 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/bounds.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +SEC("socket") +__description("subtraction bounds (map value) variant 1") +__failure __msg("R0 max value is outside of the allowed memory range") +__failure_unpriv +__naked void bounds_map_value_variant_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u8*)(r0 + 0); \ + if r1 > 0xff goto l0_%=; \ + r3 = *(u8*)(r0 + 1); \ + if r3 > 0xff goto l0_%=; \ + r1 -= r3; \ + r1 >>= 56; \ + r0 += r1; \ + r0 = *(u8*)(r0 + 0); \ + exit; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("subtraction bounds (map value) variant 2") +__failure +__msg("R0 min value is negative, either use unsigned index or do a if (index >=0) check.") +__msg_unpriv("R1 has unknown scalar with mixed signed bounds") +__naked void bounds_map_value_variant_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u8*)(r0 + 0); \ + if r1 > 0xff goto l0_%=; \ + r3 = *(u8*)(r0 + 1); \ + if r3 > 0xff goto l0_%=; \ + r1 -= r3; \ + r0 += r1; \ + r0 = *(u8*)(r0 + 0); \ + exit; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("check subtraction on pointers for unpriv") +__success __failure_unpriv __msg_unpriv("R9 pointer -= pointer prohibited") +__retval(0) +__naked void subtraction_on_pointers_for_unpriv(void) +{ + asm volatile (" \ + r0 = 0; \ + r1 = %[map_hash_8b] ll; \ + r2 = r10; \ + r2 += -8; \ + r6 = 9; \ + *(u64*)(r2 + 0) = r6; \ + call %[bpf_map_lookup_elem]; \ + r9 = r10; \ + r9 -= r0; \ + r1 = %[map_hash_8b] ll; \ + r2 = r10; \ + r2 += -8; \ + r6 = 0; \ + *(u64*)(r2 + 0) = r6; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: *(u64*)(r0 + 0) = r9; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check based on zero-extended MOV") +__success __success_unpriv __retval(0) +__naked void based_on_zero_extended_mov(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + /* r2 = 0x0000'0000'ffff'ffff */ \ + w2 = 0xffffffff; \ + /* r2 = 0 */ \ + r2 >>= 32; \ + /* no-op */ \ + r0 += r2; \ + /* access at offset 0 */ \ + r0 = *(u8*)(r0 + 0); \ +l0_%=: /* exit */ \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check based on sign-extended MOV. test1") +__failure __msg("map_value pointer and 4294967295") +__failure_unpriv +__naked void on_sign_extended_mov_test1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + /* r2 = 0xffff'ffff'ffff'ffff */ \ + r2 = 0xffffffff; \ + /* r2 = 0xffff'ffff */ \ + r2 >>= 32; \ + /* r0 = <oob pointer> */ \ + r0 += r2; \ + /* access to OOB pointer */ \ + r0 = *(u8*)(r0 + 0); \ +l0_%=: /* exit */ \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check based on sign-extended MOV. test2") +__failure __msg("R0 min value is outside of the allowed memory range") +__failure_unpriv +__naked void on_sign_extended_mov_test2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + /* r2 = 0xffff'ffff'ffff'ffff */ \ + r2 = 0xffffffff; \ + /* r2 = 0xfff'ffff */ \ + r2 >>= 36; \ + /* r0 = <oob pointer> */ \ + r0 += r2; \ + /* access to OOB pointer */ \ + r0 = *(u8*)(r0 + 0); \ +l0_%=: /* exit */ \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("tc") +__description("bounds check based on reg_off + var_off + insn_off. test1") +__failure __msg("value_size=8 off=1073741825") +__naked void var_off_insn_off_test1(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_mark]); \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r6 &= 1; \ + r6 += %[__imm_0]; \ + r0 += r6; \ + r0 += %[__imm_0]; \ +l0_%=: r0 = *(u8*)(r0 + 3); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm_const(__imm_0, (1 << 29) - 1), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +SEC("tc") +__description("bounds check based on reg_off + var_off + insn_off. test2") +__failure __msg("value 1073741823") +__naked void var_off_insn_off_test2(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_mark]); \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r6 &= 1; \ + r6 += %[__imm_0]; \ + r0 += r6; \ + r0 += %[__imm_1]; \ +l0_%=: r0 = *(u8*)(r0 + 3); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm_const(__imm_0, (1 << 30) - 1), + __imm_const(__imm_1, (1 << 29) - 1), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +SEC("socket") +__description("bounds check after truncation of non-boundary-crossing range") +__success __success_unpriv __retval(0) +__naked void of_non_boundary_crossing_range(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + /* r1 = [0x00, 0xff] */ \ + r1 = *(u8*)(r0 + 0); \ + r2 = 1; \ + /* r2 = 0x10'0000'0000 */ \ + r2 <<= 36; \ + /* r1 = [0x10'0000'0000, 0x10'0000'00ff] */ \ + r1 += r2; \ + /* r1 = [0x10'7fff'ffff, 0x10'8000'00fe] */ \ + r1 += 0x7fffffff; \ + /* r1 = [0x00, 0xff] */ \ + w1 -= 0x7fffffff; \ + /* r1 = 0 */ \ + r1 >>= 8; \ + /* no-op */ \ + r0 += r1; \ + /* access at offset 0 */ \ + r0 = *(u8*)(r0 + 0); \ +l0_%=: /* exit */ \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check after truncation of boundary-crossing range (1)") +__failure +/* not actually fully unbounded, but the bound is very high */ +__msg("value -4294967168 makes map_value pointer be out of bounds") +__failure_unpriv +__naked void of_boundary_crossing_range_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + /* r1 = [0x00, 0xff] */ \ + r1 = *(u8*)(r0 + 0); \ + r1 += %[__imm_0]; \ + /* r1 = [0xffff'ff80, 0x1'0000'007f] */ \ + r1 += %[__imm_0]; \ + /* r1 = [0xffff'ff80, 0xffff'ffff] or \ + * [0x0000'0000, 0x0000'007f] \ + */ \ + w1 += 0; \ + r1 -= %[__imm_0]; \ + /* r1 = [0x00, 0xff] or \ + * [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff]\ + */ \ + r1 -= %[__imm_0]; \ + /* error on OOB pointer computation */ \ + r0 += r1; \ + /* exit */ \ + r0 = 0; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm_const(__imm_0, 0xffffff80 >> 1) + : __clobber_all); +} + +SEC("socket") +__description("bounds check after truncation of boundary-crossing range (2)") +__failure __msg("value -4294967168 makes map_value pointer be out of bounds") +__failure_unpriv +__naked void of_boundary_crossing_range_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + /* r1 = [0x00, 0xff] */ \ + r1 = *(u8*)(r0 + 0); \ + r1 += %[__imm_0]; \ + /* r1 = [0xffff'ff80, 0x1'0000'007f] */ \ + r1 += %[__imm_0]; \ + /* r1 = [0xffff'ff80, 0xffff'ffff] or \ + * [0x0000'0000, 0x0000'007f] \ + * difference to previous test: truncation via MOV32\ + * instead of ALU32. \ + */ \ + w1 = w1; \ + r1 -= %[__imm_0]; \ + /* r1 = [0x00, 0xff] or \ + * [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff]\ + */ \ + r1 -= %[__imm_0]; \ + /* error on OOB pointer computation */ \ + r0 += r1; \ + /* exit */ \ + r0 = 0; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm_const(__imm_0, 0xffffff80 >> 1) + : __clobber_all); +} + +SEC("socket") +__description("bounds check after wrapping 32-bit addition") +__success __success_unpriv __retval(0) +__naked void after_wrapping_32_bit_addition(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + /* r1 = 0x7fff'ffff */ \ + r1 = 0x7fffffff; \ + /* r1 = 0xffff'fffe */ \ + r1 += 0x7fffffff; \ + /* r1 = 0 */ \ + w1 += 2; \ + /* no-op */ \ + r0 += r1; \ + /* access at offset 0 */ \ + r0 = *(u8*)(r0 + 0); \ +l0_%=: /* exit */ \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check after shift with oversized count operand") +__failure __msg("R0 max value is outside of the allowed memory range") +__failure_unpriv +__naked void shift_with_oversized_count_operand(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r2 = 32; \ + r1 = 1; \ + /* r1 = (u32)1 << (u32)32 = ? */ \ + w1 <<= w2; \ + /* r1 = [0x0000, 0xffff] */ \ + r1 &= 0xffff; \ + /* computes unknown pointer, potentially OOB */ \ + r0 += r1; \ + /* potentially OOB access */ \ + r0 = *(u8*)(r0 + 0); \ +l0_%=: /* exit */ \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check after right shift of maybe-negative number") +__failure __msg("R0 unbounded memory access") +__failure_unpriv +__naked void shift_of_maybe_negative_number(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + /* r1 = [0x00, 0xff] */ \ + r1 = *(u8*)(r0 + 0); \ + /* r1 = [-0x01, 0xfe] */ \ + r1 -= 1; \ + /* r1 = 0 or 0xff'ffff'ffff'ffff */ \ + r1 >>= 8; \ + /* r1 = 0 or 0xffff'ffff'ffff */ \ + r1 >>= 8; \ + /* computes unknown pointer, potentially OOB */ \ + r0 += r1; \ + /* potentially OOB access */ \ + r0 = *(u8*)(r0 + 0); \ +l0_%=: /* exit */ \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check after 32-bit right shift with 64-bit input") +__failure __msg("math between map_value pointer and 4294967294 is not allowed") +__failure_unpriv +__naked void shift_with_64_bit_input(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 2; \ + /* r1 = 1<<32 */ \ + r1 <<= 31; \ + /* r1 = 0 (NOT 2!) */ \ + w1 >>= 31; \ + /* r1 = 0xffff'fffe (NOT 0!) */ \ + w1 -= 2; \ + /* error on computing OOB pointer */ \ + r0 += r1; \ + /* exit */ \ + r0 = 0; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check map access with off+size signed 32bit overflow. test1") +__failure __msg("map_value pointer and 2147483646") +__failure_unpriv +__naked void size_signed_32bit_overflow_test1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r0 += 0x7ffffffe; \ + r0 = *(u64*)(r0 + 0); \ + goto l1_%=; \ +l1_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check map access with off+size signed 32bit overflow. test2") +__failure __msg("pointer offset 1073741822") +__msg_unpriv("R0 pointer arithmetic of map value goes out of range") +__naked void size_signed_32bit_overflow_test2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r0 += 0x1fffffff; \ + r0 += 0x1fffffff; \ + r0 += 0x1fffffff; \ + r0 = *(u64*)(r0 + 0); \ + goto l1_%=; \ +l1_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check map access with off+size signed 32bit overflow. test3") +__failure __msg("pointer offset -1073741822") +__msg_unpriv("R0 pointer arithmetic of map value goes out of range") +__naked void size_signed_32bit_overflow_test3(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r0 -= 0x1fffffff; \ + r0 -= 0x1fffffff; \ + r0 = *(u64*)(r0 + 2); \ + goto l1_%=; \ +l1_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check map access with off+size signed 32bit overflow. test4") +__failure __msg("map_value pointer and 1000000000000") +__failure_unpriv +__naked void size_signed_32bit_overflow_test4(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r1 = 1000000; \ + r1 *= 1000000; \ + r0 += r1; \ + r0 = *(u64*)(r0 + 2); \ + goto l1_%=; \ +l1_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check mixed 32bit and 64bit arithmetic. test1") +__success __failure_unpriv __msg_unpriv("R0 invalid mem access 'scalar'") +__retval(0) +__naked void _32bit_and_64bit_arithmetic_test1(void) +{ + asm volatile (" \ + r0 = 0; \ + r1 = -1; \ + r1 <<= 32; \ + r1 += 1; \ + /* r1 = 0xffffFFFF00000001 */ \ + if w1 > 1 goto l0_%=; \ + /* check ALU64 op keeps 32bit bounds */ \ + r1 += 1; \ + if w1 > 2 goto l0_%=; \ + goto l1_%=; \ +l0_%=: /* invalid ldx if bounds are lost above */ \ + r0 = *(u64*)(r0 - 1); \ +l1_%=: exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("bounds check mixed 32bit and 64bit arithmetic. test2") +__success __failure_unpriv __msg_unpriv("R0 invalid mem access 'scalar'") +__retval(0) +__naked void _32bit_and_64bit_arithmetic_test2(void) +{ + asm volatile (" \ + r0 = 0; \ + r1 = -1; \ + r1 <<= 32; \ + r1 += 1; \ + /* r1 = 0xffffFFFF00000001 */ \ + r2 = 3; \ + /* r1 = 0x2 */ \ + w1 += 1; \ + /* check ALU32 op zero extends 64bit bounds */ \ + if r1 > r2 goto l0_%=; \ + goto l1_%=; \ +l0_%=: /* invalid ldx if bounds are lost above */ \ + r0 = *(u64*)(r0 - 1); \ +l1_%=: exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("assigning 32bit bounds to 64bit for wA = 0, wB = wA") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void for_wa_0_wb_wa(void) +{ + asm volatile (" \ + r8 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r7 = *(u32*)(r1 + %[__sk_buff_data]); \ + w9 = 0; \ + w2 = w9; \ + r6 = r7; \ + r6 += r2; \ + r3 = r6; \ + r3 += 8; \ + if r3 > r8 goto l0_%=; \ + r5 = *(u32*)(r6 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("socket") +__description("bounds check for reg = 0, reg xor 1") +__success __failure_unpriv +__msg_unpriv("R0 min value is outside of the allowed memory range") +__retval(0) +__naked void reg_0_reg_xor_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r1 = 0; \ + r1 ^= 1; \ + if r1 != 0 goto l1_%=; \ + r0 = *(u64*)(r0 + 8); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check for reg32 = 0, reg32 xor 1") +__success __failure_unpriv +__msg_unpriv("R0 min value is outside of the allowed memory range") +__retval(0) +__naked void reg32_0_reg32_xor_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: w1 = 0; \ + w1 ^= 1; \ + if w1 != 0 goto l1_%=; \ + r0 = *(u64*)(r0 + 8); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check for reg = 2, reg xor 3") +__success __failure_unpriv +__msg_unpriv("R0 min value is outside of the allowed memory range") +__retval(0) +__naked void reg_2_reg_xor_3(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r1 = 2; \ + r1 ^= 3; \ + if r1 > 0 goto l1_%=; \ + r0 = *(u64*)(r0 + 8); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check for reg = any, reg xor 3") +__failure __msg("invalid access to map value") +__msg_unpriv("invalid access to map value") +__naked void reg_any_reg_xor_3(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r1 = *(u64*)(r0 + 0); \ + r1 ^= 3; \ + if r1 != 0 goto l1_%=; \ + r0 = *(u64*)(r0 + 8); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check for reg32 = any, reg32 xor 3") +__failure __msg("invalid access to map value") +__msg_unpriv("invalid access to map value") +__naked void reg32_any_reg32_xor_3(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r1 = *(u64*)(r0 + 0); \ + w1 ^= 3; \ + if w1 != 0 goto l1_%=; \ + r0 = *(u64*)(r0 + 8); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check for reg > 0, reg xor 3") +__success __failure_unpriv +__msg_unpriv("R0 min value is outside of the allowed memory range") +__retval(0) +__naked void reg_0_reg_xor_3(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r1 = *(u64*)(r0 + 0); \ + if r1 <= 0 goto l1_%=; \ + r1 ^= 3; \ + if r1 >= 0 goto l1_%=; \ + r0 = *(u64*)(r0 + 8); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds check for reg32 > 0, reg32 xor 3") +__success __failure_unpriv +__msg_unpriv("R0 min value is outside of the allowed memory range") +__retval(0) +__naked void reg32_0_reg32_xor_3(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r1 = *(u64*)(r0 + 0); \ + if w1 <= 0 goto l1_%=; \ + w1 ^= 3; \ + if w1 >= 0 goto l1_%=; \ + r0 = *(u64*)(r0 + 8); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks after 32-bit truncation. test 1") +__success __failure_unpriv __msg_unpriv("R0 leaks addr") +__retval(0) +__naked void _32_bit_truncation_test_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u32*)(r0 + 0); \ + /* This used to reduce the max bound to 0x7fffffff */\ + if r1 == 0 goto l1_%=; \ + if r1 > 0x7fffffff goto l0_%=; \ +l1_%=: r0 = 0; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks after 32-bit truncation. test 2") +__success __failure_unpriv __msg_unpriv("R0 leaks addr") +__retval(0) +__naked void _32_bit_truncation_test_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u32*)(r0 + 0); \ + if r1 s< 1 goto l1_%=; \ + if w1 s< 0 goto l0_%=; \ +l1_%=: r0 = 0; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("xdp") +__description("bound check with JMP_JLT for crossing 64-bit signed boundary") +__success __retval(0) +__naked void crossing_64_bit_signed_boundary_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 1; \ + if r1 > r3 goto l0_%=; \ + r1 = *(u8*)(r2 + 0); \ + r0 = 0x7fffffffffffff10 ll; \ + r1 += r0; \ + r0 = 0x8000000000000000 ll; \ +l1_%=: r0 += 1; \ + /* r1 unsigned range is [0x7fffffffffffff10, 0x800000000000000f] */\ + if r0 < r1 goto l1_%=; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("bound check with JMP_JSLT for crossing 64-bit signed boundary") +__success __retval(0) +__naked void crossing_64_bit_signed_boundary_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 1; \ + if r1 > r3 goto l0_%=; \ + r1 = *(u8*)(r2 + 0); \ + r0 = 0x7fffffffffffff10 ll; \ + r1 += r0; \ + r2 = 0x8000000000000fff ll; \ + r0 = 0x8000000000000000 ll; \ +l1_%=: r0 += 1; \ + if r0 s> r2 goto l0_%=; \ + /* r1 signed range is [S64_MIN, S64_MAX] */ \ + if r0 s< r1 goto l1_%=; \ + r0 = 1; \ + exit; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("bound check for loop upper bound greater than U32_MAX") +__success __retval(0) +__naked void bound_greater_than_u32_max(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 1; \ + if r1 > r3 goto l0_%=; \ + r1 = *(u8*)(r2 + 0); \ + r0 = 0x100000000 ll; \ + r1 += r0; \ + r0 = 0x100000000 ll; \ +l1_%=: r0 += 1; \ + if r0 < r1 goto l1_%=; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("bound check with JMP32_JLT for crossing 32-bit signed boundary") +__success __retval(0) +__naked void crossing_32_bit_signed_boundary_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 1; \ + if r1 > r3 goto l0_%=; \ + r1 = *(u8*)(r2 + 0); \ + w0 = 0x7fffff10; \ + w1 += w0; \ + w0 = 0x80000000; \ +l1_%=: w0 += 1; \ + /* r1 unsigned range is [0, 0x8000000f] */ \ + if w0 < w1 goto l1_%=; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("bound check with JMP32_JSLT for crossing 32-bit signed boundary") +__success __retval(0) +__naked void crossing_32_bit_signed_boundary_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 1; \ + if r1 > r3 goto l0_%=; \ + r1 = *(u8*)(r2 + 0); \ + w0 = 0x7fffff10; \ + w1 += w0; \ + w2 = 0x80000fff; \ + w0 = 0x80000000; \ +l1_%=: w0 += 1; \ + if w0 s> w2 goto l0_%=; \ + /* r1 signed range is [S32_MIN, S32_MAX] */ \ + if w0 s< w1 goto l1_%=; \ + r0 = 1; \ + exit; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c b/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c new file mode 100644 index 0000000000..c506afbdd9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c @@ -0,0 +1,171 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/bounds_deduction.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("socket") +__description("check deducing bounds from const, 1") +__failure __msg("R0 tried to subtract pointer from scalar") +__msg_unpriv("R1 has pointer with unsupported alu operation") +__naked void deducing_bounds_from_const_1(void) +{ + asm volatile (" \ + r0 = 1; \ + if r0 s>= 1 goto l0_%=; \ +l0_%=: r0 -= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from const, 2") +__success __failure_unpriv +__msg_unpriv("R1 has pointer with unsupported alu operation") +__retval(1) +__naked void deducing_bounds_from_const_2(void) +{ + asm volatile (" \ + r0 = 1; \ + if r0 s>= 1 goto l0_%=; \ + exit; \ +l0_%=: if r0 s<= 1 goto l1_%=; \ + exit; \ +l1_%=: r1 -= r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from const, 3") +__failure __msg("R0 tried to subtract pointer from scalar") +__msg_unpriv("R1 has pointer with unsupported alu operation") +__naked void deducing_bounds_from_const_3(void) +{ + asm volatile (" \ + r0 = 0; \ + if r0 s<= 0 goto l0_%=; \ +l0_%=: r0 -= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from const, 4") +__success __failure_unpriv +__msg_unpriv("R6 has pointer with unsupported alu operation") +__retval(0) +__naked void deducing_bounds_from_const_4(void) +{ + asm volatile (" \ + r6 = r1; \ + r0 = 0; \ + if r0 s<= 0 goto l0_%=; \ + exit; \ +l0_%=: if r0 s>= 0 goto l1_%=; \ + exit; \ +l1_%=: r6 -= r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from const, 5") +__failure __msg("R0 tried to subtract pointer from scalar") +__msg_unpriv("R1 has pointer with unsupported alu operation") +__naked void deducing_bounds_from_const_5(void) +{ + asm volatile (" \ + r0 = 0; \ + if r0 s>= 1 goto l0_%=; \ + r0 -= r1; \ +l0_%=: exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from const, 6") +__failure __msg("R0 tried to subtract pointer from scalar") +__msg_unpriv("R1 has pointer with unsupported alu operation") +__naked void deducing_bounds_from_const_6(void) +{ + asm volatile (" \ + r0 = 0; \ + if r0 s>= 0 goto l0_%=; \ + exit; \ +l0_%=: r0 -= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from const, 7") +__failure __msg("dereference of modified ctx ptr") +__msg_unpriv("R1 has pointer with unsupported alu operation") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void deducing_bounds_from_const_7(void) +{ + asm volatile (" \ + r0 = %[__imm_0]; \ + if r0 s>= 0 goto l0_%=; \ +l0_%=: r1 -= r0; \ + r0 = *(u32*)(r1 + %[__sk_buff_mark]); \ + exit; \ +" : + : __imm_const(__imm_0, ~0), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from const, 8") +__failure __msg("negative offset ctx ptr R1 off=-1 disallowed") +__msg_unpriv("R1 has pointer with unsupported alu operation") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void deducing_bounds_from_const_8(void) +{ + asm volatile (" \ + r0 = %[__imm_0]; \ + if r0 s>= 0 goto l0_%=; \ + r1 += r0; \ +l0_%=: r0 = *(u32*)(r1 + %[__sk_buff_mark]); \ + exit; \ +" : + : __imm_const(__imm_0, ~0), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from const, 9") +__failure __msg("R0 tried to subtract pointer from scalar") +__msg_unpriv("R1 has pointer with unsupported alu operation") +__naked void deducing_bounds_from_const_9(void) +{ + asm volatile (" \ + r0 = 0; \ + if r0 s>= 0 goto l0_%=; \ +l0_%=: r0 -= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from const, 10") +__failure +__msg("math between ctx pointer and register with unbounded min value is not allowed") +__failure_unpriv +__naked void deducing_bounds_from_const_10(void) +{ + asm volatile (" \ + r0 = 0; \ + if r0 s<= 0 goto l0_%=; \ +l0_%=: /* Marks reg as unknown. */ \ + r0 = -r0; \ + r0 -= r1; \ + exit; \ +" ::: __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds_deduction_non_const.c b/tools/testing/selftests/bpf/progs/verifier_bounds_deduction_non_const.c new file mode 100644 index 0000000000..823f727cf2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_bounds_deduction_non_const.c @@ -0,0 +1,639 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("socket") +__description("check deducing bounds from non-const, jmp64, <non_const> == <const>, 1") +__success __retval(0) +__naked void deducing_bounds_from_non_const_1(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 < 3 goto l0_%=; \ + r2 = 2; \ + if r0 == r2 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp64, <non_const> == <const>, 2") +__success __retval(0) +__naked void deducing_bounds_from_non_const_2(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 > 3 goto l0_%=; \ + r2 = 4; \ + if r0 == r2 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp64, <non_const> != <const>, 1") +__success __retval(0) +__naked void deducing_bounds_from_non_const_3(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 < 3 goto l0_%=; \ + r2 = 2; \ + if r0 != r2 goto l0_%=; \ + goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp64, <non_const> != <const>, 2") +__success __retval(0) +__naked void deducing_bounds_from_non_const_4(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 > 3 goto l0_%=; \ + r2 = 4; \ + if r0 != r2 goto l0_%=; \ + goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp32, <non_const> == <const>, 1") +__success __retval(0) +__naked void deducing_bounds_from_non_const_5(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if w0 < 4 goto l0_%=; \ + w2 = 3; \ + if w0 == w2 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp32, <non_const> == <const>, 2") +__success __retval(0) +__naked void deducing_bounds_from_non_const_6(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if w0 > 4 goto l0_%=; \ + w2 = 5; \ + if w0 == w2 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp32, <non_const> != <const>, 1") +__success __retval(0) +__naked void deducing_bounds_from_non_const_7(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if w0 < 3 goto l0_%=; \ + w2 = 2; \ + if w0 != w2 goto l0_%=; \ + goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp32, <non_const> != <const>, 2") +__success __retval(0) +__naked void deducing_bounds_from_non_const_8(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if w0 > 3 goto l0_%=; \ + w2 = 4; \ + if w0 != w2 goto l0_%=; \ + goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp64, <const> > <non_const>, 1") +__success __retval(0) +__naked void deducing_bounds_from_non_const_9(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + r2 = 0; \ + if r2 > r0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp64, <const> > <non_const>, 2") +__success __retval(0) +__naked void deducing_bounds_from_non_const_10(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 < 4 goto l0_%=; \ + r2 = 4; \ + if r2 > r0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp64, <const> >= <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_11(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 < 4 goto l0_%=; \ + r2 = 3; \ + if r2 >= r0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp64, <const> < <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_12(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 > 4 goto l0_%=; \ + r2 = 4; \ + if r2 < r0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp64, <const> <= <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_13(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 >= 4 goto l0_%=; \ + r2 = 4; \ + if r2 <= r0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp64, <const> == <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_14(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 < 3 goto l0_%=; \ + r2 = 2; \ + if r2 == r0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp64, <const> s> <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_15(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 s< 4 goto l0_%=; \ + r2 = 4; \ + if r2 s> r0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp64, <const> s>= <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_16(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 s< 4 goto l0_%=; \ + r2 = 3; \ + if r2 s>= r0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp64, <const> s< <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_17(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 s> 4 goto l0_%=; \ + r2 = 4; \ + if r2 s< r0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp64, <const> s<= <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_18(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 s> 4 goto l0_%=; \ + r2 = 5; \ + if r2 s<= r0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp64, <const> != <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_19(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 < 3 goto l0_%=; \ + r2 = 2; \ + if r2 != r0 goto l0_%=; \ + goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp32, <const> > <non_const>, 1") +__success __retval(0) +__naked void deducing_bounds_from_non_const_20(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + w2 = 0; \ + if w2 > w0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp32, <const> > <non_const>, 2") +__success __retval(0) +__naked void deducing_bounds_from_non_const_21(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if w0 < 4 goto l0_%=; \ + w2 = 4; \ + if w2 > w0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp32, <const> >= <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_22(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if w0 < 4 goto l0_%=; \ + w2 = 3; \ + if w2 >= w0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp32, <const> < <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_23(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if w0 > 4 goto l0_%=; \ + w2 = 4; \ + if w2 < w0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp32, <const> <= <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_24(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if w0 >= 4 goto l0_%=; \ + w2 = 4; \ + if w2 <= w0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp32, <const> == <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_25(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if w0 < 4 goto l0_%=; \ + w2 = 3; \ + if w2 == w0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp32, <const> s> <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_26(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if w0 s< 4 goto l0_%=; \ + w2 = 4; \ + if w2 s> w0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp32, <const> s>= <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_27(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if w0 s< 4 goto l0_%=; \ + w2 = 3; \ + if w2 s>= w0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp32, <const> s< <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_28(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if w0 s> 4 goto l0_%=; \ + w2 = 5; \ + if w2 s< w0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp32, <const> s<= <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_29(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if w0 s>= 4 goto l0_%=; \ + w2 = 4; \ + if w2 s<= w0 goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check deducing bounds from non-const, jmp32, <const> != <non_const>") +__success __retval(0) +__naked void deducing_bounds_from_non_const_30(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if w0 < 3 goto l0_%=; \ + w2 = 2; \ + if w2 != w0 goto l0_%=; \ + goto l1_%=; \ +l0_%=: \ + r0 = 0; \ + exit; \ +l1_%=: \ + r0 -= r1; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds_mix_sign_unsign.c b/tools/testing/selftests/bpf/progs/verifier_bounds_mix_sign_unsign.c new file mode 100644 index 0000000000..4f40144748 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_bounds_mix_sign_unsign.c @@ -0,0 +1,554 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +SEC("socket") +__description("bounds checks mixing signed and unsigned, positive bounds") +__failure __msg("unbounded min value") +__failure_unpriv +__naked void signed_and_unsigned_positive_bounds(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = 2; \ + if r2 >= r1 goto l0_%=; \ + if r1 s> 4 goto l0_%=; \ + r0 += r1; \ + r1 = 0; \ + *(u8*)(r0 + 0) = r1; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks mixing signed and unsigned") +__failure __msg("unbounded min value") +__failure_unpriv +__naked void checks_mixing_signed_and_unsigned(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = -1; \ + if r1 > r2 goto l0_%=; \ + if r1 s> 1 goto l0_%=; \ + r0 += r1; \ + r1 = 0; \ + *(u8*)(r0 + 0) = r1; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks mixing signed and unsigned, variant 2") +__failure __msg("unbounded min value") +__failure_unpriv +__naked void signed_and_unsigned_variant_2(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = -1; \ + if r1 > r2 goto l0_%=; \ + r8 = 0; \ + r8 += r1; \ + if r8 s> 1 goto l0_%=; \ + r0 += r8; \ + r0 = 0; \ + *(u8*)(r8 + 0) = r0; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks mixing signed and unsigned, variant 3") +__failure __msg("unbounded min value") +__failure_unpriv +__naked void signed_and_unsigned_variant_3(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = -1; \ + if r1 > r2 goto l0_%=; \ + r8 = r1; \ + if r8 s> 1 goto l0_%=; \ + r0 += r8; \ + r0 = 0; \ + *(u8*)(r8 + 0) = r0; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks mixing signed and unsigned, variant 4") +__success __success_unpriv __retval(0) +__naked void signed_and_unsigned_variant_4(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = 1; \ + r1 &= r2; \ + if r1 s> 1 goto l0_%=; \ + r0 += r1; \ + r1 = 0; \ + *(u8*)(r0 + 0) = r1; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks mixing signed and unsigned, variant 5") +__failure __msg("unbounded min value") +__failure_unpriv +__naked void signed_and_unsigned_variant_5(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = -1; \ + if r1 > r2 goto l0_%=; \ + if r1 s> 1 goto l0_%=; \ + r0 += 4; \ + r0 -= r1; \ + r1 = 0; \ + *(u8*)(r0 + 0) = r1; \ + r0 = 0; \ +l0_%=: exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks mixing signed and unsigned, variant 6") +__failure __msg("R4 min value is negative, either use unsigned") +__failure_unpriv +__naked void signed_and_unsigned_variant_6(void) +{ + asm volatile (" \ + r9 = r1; \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = r9; \ + r2 = 0; \ + r3 = r10; \ + r3 += -512; \ + r4 = *(u64*)(r10 - 16); \ + r6 = -1; \ + if r4 > r6 goto l0_%=; \ + if r4 s> 1 goto l0_%=; \ + r4 += 1; \ + r5 = 0; \ + r6 = 0; \ + *(u16*)(r10 - 512) = r6; \ + call %[bpf_skb_load_bytes]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_skb_load_bytes) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks mixing signed and unsigned, variant 7") +__success __success_unpriv __retval(0) +__naked void signed_and_unsigned_variant_7(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = %[__imm_0]; \ + if r1 > r2 goto l0_%=; \ + if r1 s> 1 goto l0_%=; \ + r0 += r1; \ + r1 = 0; \ + *(u8*)(r0 + 0) = r1; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm_const(__imm_0, 1024 * 1024 * 1024) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks mixing signed and unsigned, variant 8") +__failure __msg("unbounded min value") +__failure_unpriv +__naked void signed_and_unsigned_variant_8(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = -1; \ + if r2 > r1 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: if r1 s> 1 goto l0_%=; \ + r0 += r1; \ + r1 = 0; \ + *(u8*)(r0 + 0) = r1; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks mixing signed and unsigned, variant 9") +__success __success_unpriv __retval(0) +__naked void signed_and_unsigned_variant_9(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = -9223372036854775808ULL ll; \ + if r2 > r1 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: if r1 s> 1 goto l0_%=; \ + r0 += r1; \ + r1 = 0; \ + *(u8*)(r0 + 0) = r1; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks mixing signed and unsigned, variant 10") +__failure __msg("unbounded min value") +__failure_unpriv +__naked void signed_and_unsigned_variant_10(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = -1; \ + if r2 > r1 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: if r1 s> 1 goto l0_%=; \ + r0 += r1; \ + r1 = 0; \ + *(u8*)(r0 + 0) = r1; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks mixing signed and unsigned, variant 11") +__failure __msg("unbounded min value") +__failure_unpriv +__naked void signed_and_unsigned_variant_11(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = -1; \ + if r2 >= r1 goto l1_%=; \ + /* Dead branch. */ \ + r0 = 0; \ + exit; \ +l1_%=: if r1 s> 1 goto l0_%=; \ + r0 += r1; \ + r1 = 0; \ + *(u8*)(r0 + 0) = r1; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks mixing signed and unsigned, variant 12") +__failure __msg("unbounded min value") +__failure_unpriv +__naked void signed_and_unsigned_variant_12(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = -6; \ + if r2 >= r1 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: if r1 s> 1 goto l0_%=; \ + r0 += r1; \ + r1 = 0; \ + *(u8*)(r0 + 0) = r1; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks mixing signed and unsigned, variant 13") +__failure __msg("unbounded min value") +__failure_unpriv +__naked void signed_and_unsigned_variant_13(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = 2; \ + if r2 >= r1 goto l0_%=; \ + r7 = 1; \ + if r7 s> 0 goto l1_%=; \ +l0_%=: r0 = 0; \ + exit; \ +l1_%=: r7 += r1; \ + if r7 s> 4 goto l2_%=; \ + r0 += r7; \ + r1 = 0; \ + *(u8*)(r0 + 0) = r1; \ +l2_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks mixing signed and unsigned, variant 14") +__failure __msg("unbounded min value") +__failure_unpriv +__naked void signed_and_unsigned_variant_14(void) +{ + asm volatile (" \ + r9 = *(u32*)(r1 + %[__sk_buff_mark]); \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = -1; \ + r8 = 2; \ + if r9 == 42 goto l1_%=; \ + if r8 s> r1 goto l2_%=; \ +l3_%=: if r1 s> 1 goto l2_%=; \ + r0 += r1; \ +l0_%=: r1 = 0; \ + *(u8*)(r0 + 0) = r1; \ +l2_%=: r0 = 0; \ + exit; \ +l1_%=: if r1 > r2 goto l2_%=; \ + goto l3_%=; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +SEC("socket") +__description("bounds checks mixing signed and unsigned, variant 15") +__failure __msg("unbounded min value") +__failure_unpriv +__naked void signed_and_unsigned_variant_15(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = -6; \ + if r2 >= r1 goto l1_%=; \ +l0_%=: r0 = 0; \ + exit; \ +l1_%=: r0 += r1; \ + if r0 > 1 goto l2_%=; \ + r0 = 0; \ + exit; \ +l2_%=: r1 = 0; \ + *(u8*)(r0 + 0) = r1; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_get_stack.c b/tools/testing/selftests/bpf/progs/verifier_bpf_get_stack.c new file mode 100644 index 0000000000..325a2bab4a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_bpf_get_stack.c @@ -0,0 +1,124 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/bpf_get_stack.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct test_val); +} map_array_48b SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct test_val); +} map_hash_48b SEC(".maps"); + +SEC("tracepoint") +__description("bpf_get_stack return R0 within range") +__success +__naked void stack_return_r0_within_range(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r7 = r0; \ + r9 = %[__imm_0]; \ + r1 = r6; \ + r2 = r7; \ + r3 = %[__imm_0]; \ + r4 = 256; \ + call %[bpf_get_stack]; \ + r1 = 0; \ + r8 = r0; \ + r8 <<= 32; \ + r8 s>>= 32; \ + if r1 s> r8 goto l0_%=; \ + r9 -= r8; \ + r2 = r7; \ + r2 += r8; \ + r1 = r9; \ + r1 <<= 32; \ + r1 s>>= 32; \ + r3 = r2; \ + r3 += r1; \ + r1 = r7; \ + r5 = %[__imm_0]; \ + r1 += r5; \ + if r3 >= r1 goto l0_%=; \ + r1 = r6; \ + r3 = r9; \ + r4 = 0; \ + call %[bpf_get_stack]; \ +l0_%=: exit; \ +" : + : __imm(bpf_get_stack), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(__imm_0, sizeof(struct test_val) / 2) + : __clobber_all); +} + +SEC("iter/task") +__description("bpf_get_task_stack return R0 range is refined") +__success +__naked void return_r0_range_is_refined(void) +{ + asm volatile (" \ + r6 = *(u64*)(r1 + 0); \ + r6 = *(u64*)(r6 + 0); /* ctx->meta->seq */\ + r7 = *(u64*)(r1 + 8); /* ctx->task */\ + r1 = %[map_array_48b] ll; /* fixup_map_array_48b */\ + r2 = 0; \ + *(u64*)(r10 - 8) = r2; \ + r2 = r10; \ + r2 += -8; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: if r7 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r1 = r7; \ + r2 = r0; \ + r9 = r0; /* keep buf for seq_write */\ + r3 = 48; \ + r4 = 0; \ + call %[bpf_get_task_stack]; \ + if r0 s> 0 goto l2_%=; \ + r0 = 0; \ + exit; \ +l2_%=: r1 = r6; \ + r2 = r9; \ + r3 = r0; \ + call %[bpf_seq_write]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_task_stack), + __imm(bpf_map_lookup_elem), + __imm(bpf_seq_write), + __imm_addr(map_array_48b) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_bswap.c b/tools/testing/selftests/bpf/progs/verifier_bswap.c new file mode 100644 index 0000000000..8893094725 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_bswap.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18 + +SEC("socket") +__description("BSWAP, 16") +__success __success_unpriv __retval(0x23ff) +__naked void bswap_16(void) +{ + asm volatile (" \ + r0 = 0xff23; \ + r0 = bswap16 r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("BSWAP, 32") +__success __success_unpriv __retval(0x23ff0000) +__naked void bswap_32(void) +{ + asm volatile (" \ + r0 = 0xff23; \ + r0 = bswap32 r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("BSWAP, 64") +__success __success_unpriv __retval(0x34ff12ff) +__naked void bswap_64(void) +{ + asm volatile (" \ + r0 = %[u64_val] ll; \ + r0 = bswap64 r0; \ + exit; \ +" : + : [u64_val]"i"(0xff12ff34ff56ff78ull) + : __clobber_all); +} + +#else + +SEC("socket") +__description("cpuv4 is not supported by compiler or jit, use a dummy test") +__success +int dummy_test(void) +{ + return 0; +} + +#endif + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c new file mode 100644 index 0000000000..a570e48b91 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/btf_ctx_access.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("fentry/bpf_modify_return_test") +__description("btf_ctx_access accept") +__success __retval(0) +__naked void btf_ctx_access_accept(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + 8); /* load 2nd argument value (int pointer) */\ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("fentry/bpf_fentry_test9") +__description("btf_ctx_access u32 pointer accept") +__success __retval(0) +__naked void ctx_access_u32_pointer_accept(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + 0); /* load 1nd argument value (u32 pointer) */\ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_cfg.c b/tools/testing/selftests/bpf/progs/verifier_cfg.c new file mode 100644 index 0000000000..df7697b940 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_cfg.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/cfg.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("socket") +__description("unreachable") +__failure __msg("unreachable") +__failure_unpriv +__naked void unreachable(void) +{ + asm volatile (" \ + exit; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unreachable2") +__failure __msg("unreachable") +__failure_unpriv +__naked void unreachable2(void) +{ + asm volatile (" \ + goto l0_%=; \ + goto l0_%=; \ +l0_%=: exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("out of range jump") +__failure __msg("jump out of range") +__failure_unpriv +__naked void out_of_range_jump(void) +{ + asm volatile (" \ + goto l0_%=; \ + exit; \ +l0_%=: \ +" ::: __clobber_all); +} + +SEC("socket") +__description("out of range jump2") +__failure __msg("jump out of range") +__failure_unpriv +__naked void out_of_range_jump2(void) +{ + asm volatile (" \ + goto -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("loop (back-edge)") +__failure __msg("unreachable insn 1") +__msg_unpriv("back-edge") +__naked void loop_back_edge(void) +{ + asm volatile (" \ +l0_%=: goto l0_%=; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("loop2 (back-edge)") +__failure __msg("unreachable insn 4") +__msg_unpriv("back-edge") +__naked void loop2_back_edge(void) +{ + asm volatile (" \ +l0_%=: r1 = r0; \ + r2 = r0; \ + r3 = r0; \ + goto l0_%=; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("conditional loop") +__failure __msg("infinite loop detected") +__msg_unpriv("back-edge") +__naked void conditional_loop(void) +{ + asm volatile (" \ + r0 = r1; \ +l0_%=: r2 = r0; \ + r3 = r0; \ + if r1 == 0 goto l0_%=; \ + exit; \ +" ::: __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c b/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c new file mode 100644 index 0000000000..d6c4a7f3f7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/cgroup_inv_retcode.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("cgroup/sock") +__description("bpf_exit with invalid return code. test1") +__failure __msg("R0 has value (0x0; 0xffffffff)") +__naked void with_invalid_return_code_test1(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + 0); \ + exit; \ +" ::: __clobber_all); +} + +SEC("cgroup/sock") +__description("bpf_exit with invalid return code. test2") +__success +__naked void with_invalid_return_code_test2(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + 0); \ + r0 &= 1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("cgroup/sock") +__description("bpf_exit with invalid return code. test3") +__failure __msg("R0 has value (0x0; 0x3)") +__naked void with_invalid_return_code_test3(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + 0); \ + r0 &= 3; \ + exit; \ +" ::: __clobber_all); +} + +SEC("cgroup/sock") +__description("bpf_exit with invalid return code. test4") +__success +__naked void with_invalid_return_code_test4(void) +{ + asm volatile (" \ + r0 = 1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("cgroup/sock") +__description("bpf_exit with invalid return code. test5") +__failure __msg("R0 has value (0x2; 0x0)") +__naked void with_invalid_return_code_test5(void) +{ + asm volatile (" \ + r0 = 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("cgroup/sock") +__description("bpf_exit with invalid return code. test6") +__failure __msg("R0 is not a known value (ctx)") +__naked void with_invalid_return_code_test6(void) +{ + asm volatile (" \ + r0 = r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("cgroup/sock") +__description("bpf_exit with invalid return code. test7") +__failure __msg("R0 has unknown scalar value") +__naked void with_invalid_return_code_test7(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + 0); \ + r2 = *(u32*)(r1 + 4); \ + r0 *= r2; \ + exit; \ +" ::: __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_cgroup_skb.c b/tools/testing/selftests/bpf/progs/verifier_cgroup_skb.c new file mode 100644 index 0000000000..5ee3d349d6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_cgroup_skb.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/cgroup_skb.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("cgroup/skb") +__description("direct packet read test#1 for CGROUP_SKB") +__success __failure_unpriv +__msg_unpriv("invalid bpf_context access off=76 size=4") +__retval(0) +__naked void test_1_for_cgroup_skb(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r4 = *(u32*)(r1 + %[__sk_buff_len]); \ + r5 = *(u32*)(r1 + %[__sk_buff_pkt_type]); \ + r6 = *(u32*)(r1 + %[__sk_buff_mark]); \ + *(u32*)(r1 + %[__sk_buff_mark]) = r6; \ + r7 = *(u32*)(r1 + %[__sk_buff_queue_mapping]); \ + r8 = *(u32*)(r1 + %[__sk_buff_protocol]); \ + r9 = *(u32*)(r1 + %[__sk_buff_vlan_present]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)), + __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)), + __imm_const(__sk_buff_pkt_type, offsetof(struct __sk_buff, pkt_type)), + __imm_const(__sk_buff_protocol, offsetof(struct __sk_buff, protocol)), + __imm_const(__sk_buff_queue_mapping, offsetof(struct __sk_buff, queue_mapping)), + __imm_const(__sk_buff_vlan_present, offsetof(struct __sk_buff, vlan_present)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("direct packet read test#2 for CGROUP_SKB") +__success __success_unpriv __retval(0) +__naked void test_2_for_cgroup_skb(void) +{ + asm volatile (" \ + r4 = *(u32*)(r1 + %[__sk_buff_vlan_tci]); \ + r5 = *(u32*)(r1 + %[__sk_buff_vlan_proto]); \ + r6 = *(u32*)(r1 + %[__sk_buff_priority]); \ + *(u32*)(r1 + %[__sk_buff_priority]) = r6; \ + r7 = *(u32*)(r1 + %[__sk_buff_ingress_ifindex]);\ + r8 = *(u32*)(r1 + %[__sk_buff_tc_index]); \ + r9 = *(u32*)(r1 + %[__sk_buff_hash]); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_hash, offsetof(struct __sk_buff, hash)), + __imm_const(__sk_buff_ingress_ifindex, offsetof(struct __sk_buff, ingress_ifindex)), + __imm_const(__sk_buff_priority, offsetof(struct __sk_buff, priority)), + __imm_const(__sk_buff_tc_index, offsetof(struct __sk_buff, tc_index)), + __imm_const(__sk_buff_vlan_proto, offsetof(struct __sk_buff, vlan_proto)), + __imm_const(__sk_buff_vlan_tci, offsetof(struct __sk_buff, vlan_tci)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("direct packet read test#3 for CGROUP_SKB") +__success __success_unpriv __retval(0) +__naked void test_3_for_cgroup_skb(void) +{ + asm volatile (" \ + r4 = *(u32*)(r1 + %[__sk_buff_cb_0]); \ + r5 = *(u32*)(r1 + %[__sk_buff_cb_1]); \ + r6 = *(u32*)(r1 + %[__sk_buff_cb_2]); \ + r7 = *(u32*)(r1 + %[__sk_buff_cb_3]); \ + r8 = *(u32*)(r1 + %[__sk_buff_cb_4]); \ + r9 = *(u32*)(r1 + %[__sk_buff_napi_id]); \ + *(u32*)(r1 + %[__sk_buff_cb_0]) = r4; \ + *(u32*)(r1 + %[__sk_buff_cb_1]) = r5; \ + *(u32*)(r1 + %[__sk_buff_cb_2]) = r6; \ + *(u32*)(r1 + %[__sk_buff_cb_3]) = r7; \ + *(u32*)(r1 + %[__sk_buff_cb_4]) = r8; \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0])), + __imm_const(__sk_buff_cb_1, offsetof(struct __sk_buff, cb[1])), + __imm_const(__sk_buff_cb_2, offsetof(struct __sk_buff, cb[2])), + __imm_const(__sk_buff_cb_3, offsetof(struct __sk_buff, cb[3])), + __imm_const(__sk_buff_cb_4, offsetof(struct __sk_buff, cb[4])), + __imm_const(__sk_buff_napi_id, offsetof(struct __sk_buff, napi_id)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("direct packet read test#4 for CGROUP_SKB") +__success __success_unpriv __retval(0) +__naked void test_4_for_cgroup_skb(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_family]); \ + r3 = *(u32*)(r1 + %[__sk_buff_remote_ip4]); \ + r4 = *(u32*)(r1 + %[__sk_buff_local_ip4]); \ + r5 = *(u32*)(r1 + %[__sk_buff_remote_ip6_0]); \ + r5 = *(u32*)(r1 + %[__sk_buff_remote_ip6_1]); \ + r5 = *(u32*)(r1 + %[__sk_buff_remote_ip6_2]); \ + r5 = *(u32*)(r1 + %[__sk_buff_remote_ip6_3]); \ + r6 = *(u32*)(r1 + %[__sk_buff_local_ip6_0]); \ + r6 = *(u32*)(r1 + %[__sk_buff_local_ip6_1]); \ + r6 = *(u32*)(r1 + %[__sk_buff_local_ip6_2]); \ + r6 = *(u32*)(r1 + %[__sk_buff_local_ip6_3]); \ + r7 = *(u32*)(r1 + %[__sk_buff_remote_port]); \ + r8 = *(u32*)(r1 + %[__sk_buff_local_port]); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_family, offsetof(struct __sk_buff, family)), + __imm_const(__sk_buff_local_ip4, offsetof(struct __sk_buff, local_ip4)), + __imm_const(__sk_buff_local_ip6_0, offsetof(struct __sk_buff, local_ip6[0])), + __imm_const(__sk_buff_local_ip6_1, offsetof(struct __sk_buff, local_ip6[1])), + __imm_const(__sk_buff_local_ip6_2, offsetof(struct __sk_buff, local_ip6[2])), + __imm_const(__sk_buff_local_ip6_3, offsetof(struct __sk_buff, local_ip6[3])), + __imm_const(__sk_buff_local_port, offsetof(struct __sk_buff, local_port)), + __imm_const(__sk_buff_remote_ip4, offsetof(struct __sk_buff, remote_ip4)), + __imm_const(__sk_buff_remote_ip6_0, offsetof(struct __sk_buff, remote_ip6[0])), + __imm_const(__sk_buff_remote_ip6_1, offsetof(struct __sk_buff, remote_ip6[1])), + __imm_const(__sk_buff_remote_ip6_2, offsetof(struct __sk_buff, remote_ip6[2])), + __imm_const(__sk_buff_remote_ip6_3, offsetof(struct __sk_buff, remote_ip6[3])), + __imm_const(__sk_buff_remote_port, offsetof(struct __sk_buff, remote_port)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid access of tc_classid for CGROUP_SKB") +__failure __msg("invalid bpf_context access") +__failure_unpriv +__naked void tc_classid_for_cgroup_skb(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_tc_classid]); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_tc_classid, offsetof(struct __sk_buff, tc_classid)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid access of data_meta for CGROUP_SKB") +__failure __msg("invalid bpf_context access") +__failure_unpriv +__naked void data_meta_for_cgroup_skb(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_data_meta]); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data_meta, offsetof(struct __sk_buff, data_meta)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid access of flow_keys for CGROUP_SKB") +__failure __msg("invalid bpf_context access") +__failure_unpriv +__naked void flow_keys_for_cgroup_skb(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_flow_keys]); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_flow_keys, offsetof(struct __sk_buff, flow_keys)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid write access to napi_id for CGROUP_SKB") +__failure __msg("invalid bpf_context access") +__failure_unpriv +__naked void napi_id_for_cgroup_skb(void) +{ + asm volatile (" \ + r9 = *(u32*)(r1 + %[__sk_buff_napi_id]); \ + *(u32*)(r1 + %[__sk_buff_napi_id]) = r9; \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_napi_id, offsetof(struct __sk_buff, napi_id)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("write tstamp from CGROUP_SKB") +__success __failure_unpriv +__msg_unpriv("invalid bpf_context access off=152 size=8") +__retval(0) +__naked void write_tstamp_from_cgroup_skb(void) +{ + asm volatile (" \ + r0 = 0; \ + *(u64*)(r1 + %[__sk_buff_tstamp]) = r0; \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_tstamp, offsetof(struct __sk_buff, tstamp)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("read tstamp from CGROUP_SKB") +__success __success_unpriv __retval(0) +__naked void read_tstamp_from_cgroup_skb(void) +{ + asm volatile (" \ + r0 = *(u64*)(r1 + %[__sk_buff_tstamp]); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_tstamp, offsetof(struct __sk_buff, tstamp)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_cgroup_storage.c b/tools/testing/selftests/bpf/progs/verifier_cgroup_storage.c new file mode 100644 index 0000000000..9a13f5c11a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_cgroup_storage.c @@ -0,0 +1,308 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/cgroup_storage.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "../../../include/linux/filter.h" +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __uint(max_entries, 0); + __type(key, struct bpf_cgroup_storage_key); + __type(value, char[TEST_DATA_LEN]); +} cgroup_storage SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); + __uint(max_entries, 0); + __type(key, struct bpf_cgroup_storage_key); + __type(value, char[64]); +} percpu_cgroup_storage SEC(".maps"); + +SEC("cgroup/skb") +__description("valid cgroup storage access") +__success __success_unpriv __retval(0) +__naked void valid_cgroup_storage_access(void) +{ + asm volatile (" \ + r2 = 0; \ + r1 = %[cgroup_storage] ll; \ + call %[bpf_get_local_storage]; \ + r1 = *(u32*)(r0 + 0); \ + r0 = r1; \ + r0 &= 1; \ + exit; \ +" : + : __imm(bpf_get_local_storage), + __imm_addr(cgroup_storage) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid cgroup storage access 1") +__failure __msg("cannot pass map_type 1 into func bpf_get_local_storage") +__failure_unpriv +__naked void invalid_cgroup_storage_access_1(void) +{ + asm volatile (" \ + r2 = 0; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_get_local_storage]; \ + r1 = *(u32*)(r0 + 0); \ + r0 = r1; \ + r0 &= 1; \ + exit; \ +" : + : __imm(bpf_get_local_storage), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid cgroup storage access 2") +__failure __msg("fd 1 is not pointing to valid bpf_map") +__failure_unpriv +__naked void invalid_cgroup_storage_access_2(void) +{ + asm volatile (" \ + r2 = 0; \ + .8byte %[ld_map_fd]; \ + .8byte 0; \ + call %[bpf_get_local_storage]; \ + r0 &= 1; \ + exit; \ +" : + : __imm(bpf_get_local_storage), + __imm_insn(ld_map_fd, BPF_RAW_INSN(BPF_LD | BPF_DW | BPF_IMM, BPF_REG_1, BPF_PSEUDO_MAP_FD, 0, 1)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid cgroup storage access 3") +__failure __msg("invalid access to map value, value_size=64 off=256 size=4") +__failure_unpriv +__naked void invalid_cgroup_storage_access_3(void) +{ + asm volatile (" \ + r2 = 0; \ + r1 = %[cgroup_storage] ll; \ + call %[bpf_get_local_storage]; \ + r1 = *(u32*)(r0 + 256); \ + r1 += 1; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_local_storage), + __imm_addr(cgroup_storage) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid cgroup storage access 4") +__failure __msg("invalid access to map value, value_size=64 off=-2 size=4") +__failure_unpriv +__flag(BPF_F_ANY_ALIGNMENT) +__naked void invalid_cgroup_storage_access_4(void) +{ + asm volatile (" \ + r2 = 0; \ + r1 = %[cgroup_storage] ll; \ + call %[bpf_get_local_storage]; \ + r1 = *(u32*)(r0 - 2); \ + r0 = r1; \ + r1 += 1; \ + exit; \ +" : + : __imm(bpf_get_local_storage), + __imm_addr(cgroup_storage) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid cgroup storage access 5") +__failure __msg("get_local_storage() doesn't support non-zero flags") +__failure_unpriv +__naked void invalid_cgroup_storage_access_5(void) +{ + asm volatile (" \ + r2 = 7; \ + r1 = %[cgroup_storage] ll; \ + call %[bpf_get_local_storage]; \ + r1 = *(u32*)(r0 + 0); \ + r0 = r1; \ + r0 &= 1; \ + exit; \ +" : + : __imm(bpf_get_local_storage), + __imm_addr(cgroup_storage) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid cgroup storage access 6") +__failure __msg("get_local_storage() doesn't support non-zero flags") +__msg_unpriv("R2 leaks addr into helper function") +__naked void invalid_cgroup_storage_access_6(void) +{ + asm volatile (" \ + r2 = r1; \ + r1 = %[cgroup_storage] ll; \ + call %[bpf_get_local_storage]; \ + r1 = *(u32*)(r0 + 0); \ + r0 = r1; \ + r0 &= 1; \ + exit; \ +" : + : __imm(bpf_get_local_storage), + __imm_addr(cgroup_storage) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("valid per-cpu cgroup storage access") +__success __success_unpriv __retval(0) +__naked void per_cpu_cgroup_storage_access(void) +{ + asm volatile (" \ + r2 = 0; \ + r1 = %[percpu_cgroup_storage] ll; \ + call %[bpf_get_local_storage]; \ + r1 = *(u32*)(r0 + 0); \ + r0 = r1; \ + r0 &= 1; \ + exit; \ +" : + : __imm(bpf_get_local_storage), + __imm_addr(percpu_cgroup_storage) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid per-cpu cgroup storage access 1") +__failure __msg("cannot pass map_type 1 into func bpf_get_local_storage") +__failure_unpriv +__naked void cpu_cgroup_storage_access_1(void) +{ + asm volatile (" \ + r2 = 0; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_get_local_storage]; \ + r1 = *(u32*)(r0 + 0); \ + r0 = r1; \ + r0 &= 1; \ + exit; \ +" : + : __imm(bpf_get_local_storage), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid per-cpu cgroup storage access 2") +__failure __msg("fd 1 is not pointing to valid bpf_map") +__failure_unpriv +__naked void cpu_cgroup_storage_access_2(void) +{ + asm volatile (" \ + r2 = 0; \ + .8byte %[ld_map_fd]; \ + .8byte 0; \ + call %[bpf_get_local_storage]; \ + r0 &= 1; \ + exit; \ +" : + : __imm(bpf_get_local_storage), + __imm_insn(ld_map_fd, BPF_RAW_INSN(BPF_LD | BPF_DW | BPF_IMM, BPF_REG_1, BPF_PSEUDO_MAP_FD, 0, 1)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid per-cpu cgroup storage access 3") +__failure __msg("invalid access to map value, value_size=64 off=256 size=4") +__failure_unpriv +__naked void cpu_cgroup_storage_access_3(void) +{ + asm volatile (" \ + r2 = 0; \ + r1 = %[percpu_cgroup_storage] ll; \ + call %[bpf_get_local_storage]; \ + r1 = *(u32*)(r0 + 256); \ + r1 += 1; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_local_storage), + __imm_addr(percpu_cgroup_storage) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid per-cpu cgroup storage access 4") +__failure __msg("invalid access to map value, value_size=64 off=-2 size=4") +__failure_unpriv +__flag(BPF_F_ANY_ALIGNMENT) +__naked void cpu_cgroup_storage_access_4(void) +{ + asm volatile (" \ + r2 = 0; \ + r1 = %[cgroup_storage] ll; \ + call %[bpf_get_local_storage]; \ + r1 = *(u32*)(r0 - 2); \ + r0 = r1; \ + r1 += 1; \ + exit; \ +" : + : __imm(bpf_get_local_storage), + __imm_addr(cgroup_storage) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid per-cpu cgroup storage access 5") +__failure __msg("get_local_storage() doesn't support non-zero flags") +__failure_unpriv +__naked void cpu_cgroup_storage_access_5(void) +{ + asm volatile (" \ + r2 = 7; \ + r1 = %[percpu_cgroup_storage] ll; \ + call %[bpf_get_local_storage]; \ + r1 = *(u32*)(r0 + 0); \ + r0 = r1; \ + r0 &= 1; \ + exit; \ +" : + : __imm(bpf_get_local_storage), + __imm_addr(percpu_cgroup_storage) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("invalid per-cpu cgroup storage access 6") +__failure __msg("get_local_storage() doesn't support non-zero flags") +__msg_unpriv("R2 leaks addr into helper function") +__naked void cpu_cgroup_storage_access_6(void) +{ + asm volatile (" \ + r2 = r1; \ + r1 = %[percpu_cgroup_storage] ll; \ + call %[bpf_get_local_storage]; \ + r1 = *(u32*)(r0 + 0); \ + r0 = r1; \ + r0 &= 1; \ + exit; \ +" : + : __imm(bpf_get_local_storage), + __imm_addr(percpu_cgroup_storage) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_const_or.c b/tools/testing/selftests/bpf/progs/verifier_const_or.c new file mode 100644 index 0000000000..ba8922b2ee --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_const_or.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/const_or.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("tracepoint") +__description("constant register |= constant should keep constant type") +__success +__naked void constant_should_keep_constant_type(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -48; \ + r2 = 34; \ + r2 |= 13; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +SEC("tracepoint") +__description("constant register |= constant should not bypass stack boundary checks") +__failure __msg("invalid indirect access to stack R1 off=-48 size=58") +__naked void not_bypass_stack_boundary_checks_1(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -48; \ + r2 = 34; \ + r2 |= 24; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +SEC("tracepoint") +__description("constant register |= constant register should keep constant type") +__success +__naked void register_should_keep_constant_type(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -48; \ + r2 = 34; \ + r4 = 13; \ + r2 |= r4; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +SEC("tracepoint") +__description("constant register |= constant register should not bypass stack boundary checks") +__failure __msg("invalid indirect access to stack R1 off=-48 size=58") +__naked void not_bypass_stack_boundary_checks_2(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -48; \ + r2 = 34; \ + r4 = 24; \ + r2 |= r4; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_ctx.c b/tools/testing/selftests/bpf/progs/verifier_ctx.c new file mode 100644 index 0000000000..a83809a1db --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_ctx.c @@ -0,0 +1,221 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/ctx.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("tc") +__description("context stores via BPF_ATOMIC") +__failure __msg("BPF_ATOMIC stores into R1 ctx is not allowed") +__naked void context_stores_via_bpf_atomic(void) +{ + asm volatile (" \ + r0 = 0; \ + lock *(u32 *)(r1 + %[__sk_buff_mark]) += w0; \ + exit; \ +" : + : __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +SEC("tc") +__description("arithmetic ops make PTR_TO_CTX unusable") +__failure __msg("dereference of modified ctx ptr") +__naked void make_ptr_to_ctx_unusable(void) +{ + asm volatile (" \ + r1 += %[__imm_0]; \ + r0 = *(u32*)(r1 + %[__sk_buff_mark]); \ + exit; \ +" : + : __imm_const(__imm_0, + offsetof(struct __sk_buff, data) - offsetof(struct __sk_buff, mark)), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +SEC("tc") +__description("pass unmodified ctx pointer to helper") +__success __retval(0) +__naked void unmodified_ctx_pointer_to_helper(void) +{ + asm volatile (" \ + r2 = 0; \ + call %[bpf_csum_update]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_csum_update) + : __clobber_all); +} + +SEC("tc") +__description("pass modified ctx pointer to helper, 1") +__failure __msg("negative offset ctx ptr R1 off=-612 disallowed") +__naked void ctx_pointer_to_helper_1(void) +{ + asm volatile (" \ + r1 += -612; \ + r2 = 0; \ + call %[bpf_csum_update]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_csum_update) + : __clobber_all); +} + +SEC("socket") +__description("pass modified ctx pointer to helper, 2") +__failure __msg("negative offset ctx ptr R1 off=-612 disallowed") +__failure_unpriv __msg_unpriv("negative offset ctx ptr R1 off=-612 disallowed") +__naked void ctx_pointer_to_helper_2(void) +{ + asm volatile (" \ + r1 += -612; \ + call %[bpf_get_socket_cookie]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_socket_cookie) + : __clobber_all); +} + +SEC("tc") +__description("pass modified ctx pointer to helper, 3") +__failure __msg("variable ctx access var_off=(0x0; 0x4)") +__naked void ctx_pointer_to_helper_3(void) +{ + asm volatile (" \ + r3 = *(u32*)(r1 + 0); \ + r3 &= 4; \ + r1 += r3; \ + r2 = 0; \ + call %[bpf_csum_update]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_csum_update) + : __clobber_all); +} + +SEC("cgroup/sendmsg6") +__description("pass ctx or null check, 1: ctx") +__success +__naked void or_null_check_1_ctx(void) +{ + asm volatile (" \ + call %[bpf_get_netns_cookie]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_netns_cookie) + : __clobber_all); +} + +SEC("cgroup/sendmsg6") +__description("pass ctx or null check, 2: null") +__success +__naked void or_null_check_2_null(void) +{ + asm volatile (" \ + r1 = 0; \ + call %[bpf_get_netns_cookie]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_netns_cookie) + : __clobber_all); +} + +SEC("cgroup/sendmsg6") +__description("pass ctx or null check, 3: 1") +__failure __msg("R1 type=scalar expected=ctx") +__naked void or_null_check_3_1(void) +{ + asm volatile (" \ + r1 = 1; \ + call %[bpf_get_netns_cookie]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_netns_cookie) + : __clobber_all); +} + +SEC("cgroup/sendmsg6") +__description("pass ctx or null check, 4: ctx - const") +__failure __msg("negative offset ctx ptr R1 off=-612 disallowed") +__naked void null_check_4_ctx_const(void) +{ + asm volatile (" \ + r1 += -612; \ + call %[bpf_get_netns_cookie]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_netns_cookie) + : __clobber_all); +} + +SEC("cgroup/connect4") +__description("pass ctx or null check, 5: null (connect)") +__success +__naked void null_check_5_null_connect(void) +{ + asm volatile (" \ + r1 = 0; \ + call %[bpf_get_netns_cookie]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_netns_cookie) + : __clobber_all); +} + +SEC("cgroup/post_bind4") +__description("pass ctx or null check, 6: null (bind)") +__success +__naked void null_check_6_null_bind(void) +{ + asm volatile (" \ + r1 = 0; \ + call %[bpf_get_netns_cookie]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_netns_cookie) + : __clobber_all); +} + +SEC("cgroup/post_bind4") +__description("pass ctx or null check, 7: ctx (bind)") +__success +__naked void null_check_7_ctx_bind(void) +{ + asm volatile (" \ + call %[bpf_get_socket_cookie]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_socket_cookie) + : __clobber_all); +} + +SEC("cgroup/post_bind4") +__description("pass ctx or null check, 8: null (bind)") +__failure __msg("R1 type=scalar expected=ctx") +__naked void null_check_8_null_bind(void) +{ + asm volatile (" \ + r1 = 0; \ + call %[bpf_get_socket_cookie]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_socket_cookie) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_ctx_sk_msg.c b/tools/testing/selftests/bpf/progs/verifier_ctx_sk_msg.c new file mode 100644 index 0000000000..65edc89799 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_ctx_sk_msg.c @@ -0,0 +1,228 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/ctx_sk_msg.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("sk_msg") +__description("valid access family in SK_MSG") +__success +__naked void access_family_in_sk_msg(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[sk_msg_md_family]); \ + exit; \ +" : + : __imm_const(sk_msg_md_family, offsetof(struct sk_msg_md, family)) + : __clobber_all); +} + +SEC("sk_msg") +__description("valid access remote_ip4 in SK_MSG") +__success +__naked void remote_ip4_in_sk_msg(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[sk_msg_md_remote_ip4]); \ + exit; \ +" : + : __imm_const(sk_msg_md_remote_ip4, offsetof(struct sk_msg_md, remote_ip4)) + : __clobber_all); +} + +SEC("sk_msg") +__description("valid access local_ip4 in SK_MSG") +__success +__naked void local_ip4_in_sk_msg(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[sk_msg_md_local_ip4]); \ + exit; \ +" : + : __imm_const(sk_msg_md_local_ip4, offsetof(struct sk_msg_md, local_ip4)) + : __clobber_all); +} + +SEC("sk_msg") +__description("valid access remote_port in SK_MSG") +__success +__naked void remote_port_in_sk_msg(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[sk_msg_md_remote_port]); \ + exit; \ +" : + : __imm_const(sk_msg_md_remote_port, offsetof(struct sk_msg_md, remote_port)) + : __clobber_all); +} + +SEC("sk_msg") +__description("valid access local_port in SK_MSG") +__success +__naked void local_port_in_sk_msg(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[sk_msg_md_local_port]); \ + exit; \ +" : + : __imm_const(sk_msg_md_local_port, offsetof(struct sk_msg_md, local_port)) + : __clobber_all); +} + +SEC("sk_skb") +__description("valid access remote_ip6 in SK_MSG") +__success +__naked void remote_ip6_in_sk_msg(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[sk_msg_md_remote_ip6_0]); \ + r0 = *(u32*)(r1 + %[sk_msg_md_remote_ip6_1]); \ + r0 = *(u32*)(r1 + %[sk_msg_md_remote_ip6_2]); \ + r0 = *(u32*)(r1 + %[sk_msg_md_remote_ip6_3]); \ + exit; \ +" : + : __imm_const(sk_msg_md_remote_ip6_0, offsetof(struct sk_msg_md, remote_ip6[0])), + __imm_const(sk_msg_md_remote_ip6_1, offsetof(struct sk_msg_md, remote_ip6[1])), + __imm_const(sk_msg_md_remote_ip6_2, offsetof(struct sk_msg_md, remote_ip6[2])), + __imm_const(sk_msg_md_remote_ip6_3, offsetof(struct sk_msg_md, remote_ip6[3])) + : __clobber_all); +} + +SEC("sk_skb") +__description("valid access local_ip6 in SK_MSG") +__success +__naked void local_ip6_in_sk_msg(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[sk_msg_md_local_ip6_0]); \ + r0 = *(u32*)(r1 + %[sk_msg_md_local_ip6_1]); \ + r0 = *(u32*)(r1 + %[sk_msg_md_local_ip6_2]); \ + r0 = *(u32*)(r1 + %[sk_msg_md_local_ip6_3]); \ + exit; \ +" : + : __imm_const(sk_msg_md_local_ip6_0, offsetof(struct sk_msg_md, local_ip6[0])), + __imm_const(sk_msg_md_local_ip6_1, offsetof(struct sk_msg_md, local_ip6[1])), + __imm_const(sk_msg_md_local_ip6_2, offsetof(struct sk_msg_md, local_ip6[2])), + __imm_const(sk_msg_md_local_ip6_3, offsetof(struct sk_msg_md, local_ip6[3])) + : __clobber_all); +} + +SEC("sk_msg") +__description("valid access size in SK_MSG") +__success +__naked void access_size_in_sk_msg(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[sk_msg_md_size]); \ + exit; \ +" : + : __imm_const(sk_msg_md_size, offsetof(struct sk_msg_md, size)) + : __clobber_all); +} + +SEC("sk_msg") +__description("invalid 64B read of size in SK_MSG") +__failure __msg("invalid bpf_context access") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void of_size_in_sk_msg(void) +{ + asm volatile (" \ + r2 = *(u64*)(r1 + %[sk_msg_md_size]); \ + exit; \ +" : + : __imm_const(sk_msg_md_size, offsetof(struct sk_msg_md, size)) + : __clobber_all); +} + +SEC("sk_msg") +__description("invalid read past end of SK_MSG") +__failure __msg("invalid bpf_context access") +__naked void past_end_of_sk_msg(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__imm_0]); \ + exit; \ +" : + : __imm_const(__imm_0, offsetof(struct sk_msg_md, size) + 4) + : __clobber_all); +} + +SEC("sk_msg") +__description("invalid read offset in SK_MSG") +__failure __msg("invalid bpf_context access") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void read_offset_in_sk_msg(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__imm_0]); \ + exit; \ +" : + : __imm_const(__imm_0, offsetof(struct sk_msg_md, family) + 1) + : __clobber_all); +} + +SEC("sk_msg") +__description("direct packet read for SK_MSG") +__success +__naked void packet_read_for_sk_msg(void) +{ + asm volatile (" \ + r2 = *(u64*)(r1 + %[sk_msg_md_data]); \ + r3 = *(u64*)(r1 + %[sk_msg_md_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(sk_msg_md_data, offsetof(struct sk_msg_md, data)), + __imm_const(sk_msg_md_data_end, offsetof(struct sk_msg_md, data_end)) + : __clobber_all); +} + +SEC("sk_msg") +__description("direct packet write for SK_MSG") +__success +__naked void packet_write_for_sk_msg(void) +{ + asm volatile (" \ + r2 = *(u64*)(r1 + %[sk_msg_md_data]); \ + r3 = *(u64*)(r1 + %[sk_msg_md_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + *(u8*)(r2 + 0) = r2; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(sk_msg_md_data, offsetof(struct sk_msg_md, data)), + __imm_const(sk_msg_md_data_end, offsetof(struct sk_msg_md, data_end)) + : __clobber_all); +} + +SEC("sk_msg") +__description("overlapping checks for direct packet access SK_MSG") +__success +__naked void direct_packet_access_sk_msg(void) +{ + asm volatile (" \ + r2 = *(u64*)(r1 + %[sk_msg_md_data]); \ + r3 = *(u64*)(r1 + %[sk_msg_md_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r1 = r2; \ + r1 += 6; \ + if r1 > r3 goto l0_%=; \ + r0 = *(u16*)(r2 + 6); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(sk_msg_md_data, offsetof(struct sk_msg_md, data)), + __imm_const(sk_msg_md_data_end, offsetof(struct sk_msg_md, data_end)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_d_path.c b/tools/testing/selftests/bpf/progs/verifier_d_path.c new file mode 100644 index 0000000000..ec79cbcfde --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_d_path.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/d_path.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("fentry/dentry_open") +__description("d_path accept") +__success __retval(0) +__naked void d_path_accept(void) +{ + asm volatile (" \ + r1 = *(u32*)(r1 + 0); \ + r2 = r10; \ + r2 += -8; \ + r6 = 0; \ + *(u64*)(r2 + 0) = r6; \ + r3 = 8 ll; \ + call %[bpf_d_path]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_d_path) + : __clobber_all); +} + +SEC("fentry/d_path") +__description("d_path reject") +__failure __msg("helper call is not allowed in probe") +__naked void d_path_reject(void) +{ + asm volatile (" \ + r1 = *(u32*)(r1 + 0); \ + r2 = r10; \ + r2 += -8; \ + r6 = 0; \ + *(u64*)(r2 + 0) = r6; \ + r3 = 8 ll; \ + call %[bpf_d_path]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_d_path) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c new file mode 100644 index 0000000000..99a23dea82 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c @@ -0,0 +1,803 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/direct_packet_access.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("tc") +__description("pkt_end - pkt_start is allowed") +__success __retval(TEST_DATA_LEN) +__naked void end_pkt_start_is_allowed(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r0 -= r2; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test1") +__success __retval(0) +__naked void direct_packet_access_test1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test2") +__success __retval(0) +__naked void direct_packet_access_test2(void) +{ + asm volatile (" \ + r0 = 1; \ + r4 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data]); \ + r5 = r3; \ + r5 += 14; \ + if r5 > r4 goto l0_%=; \ + r0 = *(u8*)(r3 + 7); \ + r4 = *(u8*)(r3 + 12); \ + r4 *= 14; \ + r3 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 += r4; \ + r2 = *(u32*)(r1 + %[__sk_buff_len]); \ + r2 <<= 49; \ + r2 >>= 49; \ + r3 += r2; \ + r2 = r3; \ + r2 += 8; \ + r1 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + if r2 > r1 goto l1_%=; \ + r1 = *(u8*)(r3 + 4); \ +l1_%=: r0 = 0; \ +l0_%=: exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)), + __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)) + : __clobber_all); +} + +SEC("socket") +__description("direct packet access: test3") +__failure __msg("invalid bpf_context access off=76") +__failure_unpriv +__naked void direct_packet_access_test3(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test4 (write)") +__success __retval(0) +__naked void direct_packet_access_test4_write(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + *(u8*)(r2 + 0) = r2; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test5 (pkt_end >= reg, good access)") +__success __retval(0) +__naked void pkt_end_reg_good_access(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r3 >= r0 goto l0_%=; \ + r0 = 1; \ + exit; \ +l0_%=: r0 = *(u8*)(r2 + 0); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test6 (pkt_end >= reg, bad access)") +__failure __msg("invalid access to packet") +__naked void pkt_end_reg_bad_access(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r3 >= r0 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ + r0 = 1; \ + exit; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test7 (pkt_end >= reg, both accesses)") +__failure __msg("invalid access to packet") +__naked void pkt_end_reg_both_accesses(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r3 >= r0 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ + r0 = 1; \ + exit; \ +l0_%=: r0 = *(u8*)(r2 + 0); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test8 (double test, variant 1)") +__success __retval(0) +__naked void test8_double_test_variant_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r3 >= r0 goto l0_%=; \ + if r0 > r3 goto l1_%=; \ + r0 = *(u8*)(r2 + 0); \ +l1_%=: r0 = 1; \ + exit; \ +l0_%=: r0 = *(u8*)(r2 + 0); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test9 (double test, variant 2)") +__success __retval(0) +__naked void test9_double_test_variant_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r3 >= r0 goto l0_%=; \ + r0 = 1; \ + exit; \ +l0_%=: if r0 > r3 goto l1_%=; \ + r0 = *(u8*)(r2 + 0); \ +l1_%=: r0 = *(u8*)(r2 + 0); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test10 (write invalid)") +__failure __msg("invalid access to packet") +__naked void packet_access_test10_write_invalid(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: *(u8*)(r2 + 0) = r2; \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test11 (shift, good access)") +__success __retval(1) +__naked void access_test11_shift_good_access(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 22; \ + if r0 > r3 goto l0_%=; \ + r3 = 144; \ + r5 = r3; \ + r5 += 23; \ + r5 >>= 3; \ + r6 = r2; \ + r6 += r5; \ + r0 = 1; \ + exit; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test12 (and, good access)") +__success __retval(1) +__naked void access_test12_and_good_access(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 22; \ + if r0 > r3 goto l0_%=; \ + r3 = 144; \ + r5 = r3; \ + r5 += 23; \ + r5 &= 15; \ + r6 = r2; \ + r6 += r5; \ + r0 = 1; \ + exit; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test13 (branches, good access)") +__success __retval(1) +__naked void access_test13_branches_good_access(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 22; \ + if r0 > r3 goto l0_%=; \ + r3 = *(u32*)(r1 + %[__sk_buff_mark]); \ + r4 = 1; \ + if r3 > r4 goto l1_%=; \ + r3 = 14; \ + goto l2_%=; \ +l1_%=: r3 = 24; \ +l2_%=: r5 = r3; \ + r5 += 23; \ + r5 &= 15; \ + r6 = r2; \ + r6 += r5; \ + r0 = 1; \ + exit; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test14 (pkt_ptr += 0, CONST_IMM, good access)") +__success __retval(1) +__naked void _0_const_imm_good_access(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 22; \ + if r0 > r3 goto l0_%=; \ + r5 = 12; \ + r5 >>= 4; \ + r6 = r2; \ + r6 += r5; \ + r0 = *(u8*)(r6 + 0); \ + r0 = 1; \ + exit; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test15 (spill with xadd)") +__failure __msg("R2 invalid mem access 'scalar'") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void access_test15_spill_with_xadd(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r5 = 4096; \ + r4 = r10; \ + r4 += -8; \ + *(u64*)(r4 + 0) = r2; \ + lock *(u64 *)(r4 + 0) += r5; \ + r2 = *(u64*)(r4 + 0); \ + *(u32*)(r2 + 0) = r5; \ + r0 = 0; \ +l0_%=: exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test16 (arith on data_end)") +__failure __msg("R3 pointer arithmetic on pkt_end") +__naked void test16_arith_on_data_end(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + r3 += 16; \ + if r0 > r3 goto l0_%=; \ + *(u8*)(r2 + 0) = r2; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test17 (pruning, alignment)") +__failure __msg("misaligned packet access off 2+(0x0; 0x0)+15+-4 size 4") +__flag(BPF_F_STRICT_ALIGNMENT) +__naked void packet_access_test17_pruning_alignment(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r7 = *(u32*)(r1 + %[__sk_buff_mark]); \ + r0 = r2; \ + r0 += 14; \ + if r7 > 1 goto l0_%=; \ +l2_%=: if r0 > r3 goto l1_%=; \ + *(u32*)(r0 - 4) = r0; \ +l1_%=: r0 = 0; \ + exit; \ +l0_%=: r0 += 1; \ + goto l2_%=; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test18 (imm += pkt_ptr, 1)") +__success __retval(0) +__naked void test18_imm_pkt_ptr_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = 8; \ + r0 += r2; \ + if r0 > r3 goto l0_%=; \ + *(u8*)(r2 + 0) = r2; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test19 (imm += pkt_ptr, 2)") +__success __retval(0) +__naked void test19_imm_pkt_ptr_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r4 = 4; \ + r4 += r2; \ + *(u8*)(r4 + 0) = r4; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test20 (x += pkt_ptr, 1)") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void test20_x_pkt_ptr_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = 0xffffffff; \ + *(u64*)(r10 - 8) = r0; \ + r0 = *(u64*)(r10 - 8); \ + r0 &= 0x7fff; \ + r4 = r0; \ + r4 += r2; \ + r5 = r4; \ + r4 += %[__imm_0]; \ + if r4 > r3 goto l0_%=; \ + *(u64*)(r5 + 0) = r4; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__imm_0, 0x7fff - 1), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test21 (x += pkt_ptr, 2)") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void test21_x_pkt_ptr_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r4 = 0xffffffff; \ + *(u64*)(r10 - 8) = r4; \ + r4 = *(u64*)(r10 - 8); \ + r4 &= 0x7fff; \ + r4 += r2; \ + r5 = r4; \ + r4 += %[__imm_0]; \ + if r4 > r3 goto l0_%=; \ + *(u64*)(r5 + 0) = r4; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__imm_0, 0x7fff - 1), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test22 (x += pkt_ptr, 3)") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void test22_x_pkt_ptr_3(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + *(u64*)(r10 - 8) = r2; \ + *(u64*)(r10 - 16) = r3; \ + r3 = *(u64*)(r10 - 16); \ + if r0 > r3 goto l0_%=; \ + r2 = *(u64*)(r10 - 8); \ + r4 = 0xffffffff; \ + lock *(u64 *)(r10 - 8) += r4; \ + r4 = *(u64*)(r10 - 8); \ + r4 >>= 49; \ + r4 += r2; \ + r0 = r4; \ + r0 += 2; \ + if r0 > r3 goto l0_%=; \ + r2 = 1; \ + *(u16*)(r4 + 0) = r2; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test23 (x += pkt_ptr, 4)") +__failure __msg("invalid access to packet, off=0 size=8, R5(id=2,off=0,r=0)") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void test23_x_pkt_ptr_4(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = *(u32*)(r1 + %[__sk_buff_mark]); \ + *(u64*)(r10 - 8) = r0; \ + r0 = *(u64*)(r10 - 8); \ + r0 &= 0xffff; \ + r4 = r0; \ + r0 = 31; \ + r0 += r4; \ + r0 += r2; \ + r5 = r0; \ + r0 += %[__imm_0]; \ + if r0 > r3 goto l0_%=; \ + *(u64*)(r5 + 0) = r0; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__imm_0, 0xffff - 1), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test24 (x += pkt_ptr, 5)") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void test24_x_pkt_ptr_5(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = 0xffffffff; \ + *(u64*)(r10 - 8) = r0; \ + r0 = *(u64*)(r10 - 8); \ + r0 &= 0xff; \ + r4 = r0; \ + r0 = 64; \ + r0 += r4; \ + r0 += r2; \ + r5 = r0; \ + r0 += %[__imm_0]; \ + if r0 > r3 goto l0_%=; \ + *(u64*)(r5 + 0) = r0; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__imm_0, 0x7fff - 1), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test25 (marking on <, good access)") +__success __retval(0) +__naked void test25_marking_on_good_access(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 < r3 goto l0_%=; \ +l1_%=: r0 = 0; \ + exit; \ +l0_%=: r0 = *(u8*)(r2 + 0); \ + goto l1_%=; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test26 (marking on <, bad access)") +__failure __msg("invalid access to packet") +__naked void test26_marking_on_bad_access(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 < r3 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l1_%=: r0 = 0; \ + exit; \ +l0_%=: goto l1_%=; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test27 (marking on <=, good access)") +__success __retval(1) +__naked void test27_marking_on_good_access(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r3 <= r0 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test28 (marking on <=, bad access)") +__failure __msg("invalid access to packet") +__naked void test28_marking_on_bad_access(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r3 <= r0 goto l0_%=; \ +l1_%=: r0 = 1; \ + exit; \ +l0_%=: r0 = *(u8*)(r2 + 0); \ + goto l1_%=; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("direct packet access: test29 (reg > pkt_end in subprog)") +__success __retval(0) +__naked void reg_pkt_end_in_subprog(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_data]); \ + r2 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r3 = r6; \ + r3 += 8; \ + call reg_pkt_end_in_subprog__1; \ + if r0 == 0 goto l0_%=; \ + r0 = *(u8*)(r6 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void reg_pkt_end_in_subprog__1(void) +{ + asm volatile (" \ + r0 = 0; \ + if r3 > r2 goto l0_%=; \ + r0 = 1; \ +l0_%=: exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("direct packet access: test30 (check_id() in regsafe(), bad access)") +__failure __msg("invalid access to packet, off=0 size=1, R2") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void id_in_regsafe_bad_access(void) +{ + asm volatile (" \ + /* r9 = ctx */ \ + r9 = r1; \ + /* r7 = ktime_get_ns() */ \ + call %[bpf_ktime_get_ns]; \ + r7 = r0; \ + /* r6 = ktime_get_ns() */ \ + call %[bpf_ktime_get_ns]; \ + r6 = r0; \ + /* r2 = ctx->data \ + * r3 = ctx->data \ + * r4 = ctx->data_end \ + */ \ + r2 = *(u32*)(r9 + %[__sk_buff_data]); \ + r3 = *(u32*)(r9 + %[__sk_buff_data]); \ + r4 = *(u32*)(r9 + %[__sk_buff_data_end]); \ + /* if r6 > 100 goto exit \ + * if r7 > 100 goto exit \ + */ \ + if r6 > 100 goto l0_%=; \ + if r7 > 100 goto l0_%=; \ + /* r2 += r6 ; this forces assignment of ID to r2\ + * r2 += 1 ; get some fixed off for r2\ + * r3 += r7 ; this forces assignment of ID to r3\ + * r3 += 1 ; get some fixed off for r3\ + */ \ + r2 += r6; \ + r2 += 1; \ + r3 += r7; \ + r3 += 1; \ + /* if r6 > r7 goto +1 ; no new information about the state is derived from\ + * ; this check, thus produced verifier states differ\ + * ; only in 'insn_idx' \ + * r2 = r3 ; optionally share ID between r2 and r3\ + */ \ + if r6 != r7 goto l1_%=; \ + r2 = r3; \ +l1_%=: /* if r3 > ctx->data_end goto exit */ \ + if r3 > r4 goto l0_%=; \ + /* r5 = *(u8 *) (r2 - 1) ; access packet memory using r2,\ + * ; this is not always safe\ + */ \ + r5 = *(u8*)(r2 - 1); \ +l0_%=: /* exit(0) */ \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_direct_stack_access_wraparound.c b/tools/testing/selftests/bpf/progs/verifier_direct_stack_access_wraparound.c new file mode 100644 index 0000000000..c538c68935 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_direct_stack_access_wraparound.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/direct_stack_access_wraparound.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("socket") +__description("direct stack access with 32-bit wraparound. test1") +__failure __msg("fp pointer and 2147483647") +__failure_unpriv +__naked void with_32_bit_wraparound_test1(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += 0x7fffffff; \ + r1 += 0x7fffffff; \ + w0 = 0; \ + *(u8*)(r1 + 0) = r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("direct stack access with 32-bit wraparound. test2") +__failure __msg("fp pointer and 1073741823") +__failure_unpriv +__naked void with_32_bit_wraparound_test2(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += 0x3fffffff; \ + r1 += 0x3fffffff; \ + w0 = 0; \ + *(u8*)(r1 + 0) = r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("direct stack access with 32-bit wraparound. test3") +__failure __msg("fp pointer offset 1073741822") +__msg_unpriv("R1 stack pointer arithmetic goes out of range") +__naked void with_32_bit_wraparound_test3(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += 0x1fffffff; \ + r1 += 0x1fffffff; \ + w0 = 0; \ + *(u8*)(r1 + 0) = r0; \ + exit; \ +" ::: __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_div0.c b/tools/testing/selftests/bpf/progs/verifier_div0.c new file mode 100644 index 0000000000..cca5ea18fc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_div0.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/div0.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("socket") +__description("DIV32 by 0, zero check 1") +__success __success_unpriv __retval(42) +__naked void by_0_zero_check_1_1(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = 0; \ + w2 = 1; \ + w2 /= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("DIV32 by 0, zero check 2") +__success __success_unpriv __retval(42) +__naked void by_0_zero_check_2_1(void) +{ + asm volatile (" \ + w0 = 42; \ + r1 = 0xffffffff00000000LL ll; \ + w2 = 1; \ + w2 /= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("DIV64 by 0, zero check") +__success __success_unpriv __retval(42) +__naked void div64_by_0_zero_check(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = 0; \ + w2 = 1; \ + r2 /= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("MOD32 by 0, zero check 1") +__success __success_unpriv __retval(42) +__naked void by_0_zero_check_1_2(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = 0; \ + w2 = 1; \ + w2 %%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("MOD32 by 0, zero check 2") +__success __success_unpriv __retval(42) +__naked void by_0_zero_check_2_2(void) +{ + asm volatile (" \ + w0 = 42; \ + r1 = 0xffffffff00000000LL ll; \ + w2 = 1; \ + w2 %%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("MOD64 by 0, zero check") +__success __success_unpriv __retval(42) +__naked void mod64_by_0_zero_check(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = 0; \ + w2 = 1; \ + r2 %%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("DIV32 by 0, zero check ok, cls") +__success __retval(8) +__naked void _0_zero_check_ok_cls_1(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = 2; \ + w2 = 16; \ + w2 /= w1; \ + r0 = r2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("DIV32 by 0, zero check 1, cls") +__success __retval(0) +__naked void _0_zero_check_1_cls_1(void) +{ + asm volatile (" \ + w1 = 0; \ + w0 = 1; \ + w0 /= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("DIV32 by 0, zero check 2, cls") +__success __retval(0) +__naked void _0_zero_check_2_cls_1(void) +{ + asm volatile (" \ + r1 = 0xffffffff00000000LL ll; \ + w0 = 1; \ + w0 /= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("DIV64 by 0, zero check, cls") +__success __retval(0) +__naked void by_0_zero_check_cls(void) +{ + asm volatile (" \ + w1 = 0; \ + w0 = 1; \ + r0 /= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("MOD32 by 0, zero check ok, cls") +__success __retval(2) +__naked void _0_zero_check_ok_cls_2(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = 3; \ + w2 = 5; \ + w2 %%= w1; \ + r0 = r2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("MOD32 by 0, zero check 1, cls") +__success __retval(1) +__naked void _0_zero_check_1_cls_2(void) +{ + asm volatile (" \ + w1 = 0; \ + w0 = 1; \ + w0 %%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("MOD32 by 0, zero check 2, cls") +__success __retval(1) +__naked void _0_zero_check_2_cls_2(void) +{ + asm volatile (" \ + r1 = 0xffffffff00000000LL ll; \ + w0 = 1; \ + w0 %%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("MOD64 by 0, zero check 1, cls") +__success __retval(2) +__naked void _0_zero_check_1_cls_3(void) +{ + asm volatile (" \ + w1 = 0; \ + w0 = 2; \ + r0 %%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("MOD64 by 0, zero check 2, cls") +__success __retval(-1) +__naked void _0_zero_check_2_cls_3(void) +{ + asm volatile (" \ + w1 = 0; \ + w0 = -1; \ + r0 %%= r1; \ + exit; \ +" ::: __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_div_overflow.c b/tools/testing/selftests/bpf/progs/verifier_div_overflow.c new file mode 100644 index 0000000000..458984da80 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_div_overflow.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/div_overflow.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <limits.h> +#include "bpf_misc.h" + +/* Just make sure that JITs used udiv/umod as otherwise we get + * an exception from INT_MIN/-1 overflow similarly as with div + * by zero. + */ + +SEC("tc") +__description("DIV32 overflow, check 1") +__success __retval(0) +__naked void div32_overflow_check_1(void) +{ + asm volatile (" \ + w1 = -1; \ + w0 = %[int_min]; \ + w0 /= w1; \ + exit; \ +" : + : __imm_const(int_min, INT_MIN) + : __clobber_all); +} + +SEC("tc") +__description("DIV32 overflow, check 2") +__success __retval(0) +__naked void div32_overflow_check_2(void) +{ + asm volatile (" \ + w0 = %[int_min]; \ + w0 /= -1; \ + exit; \ +" : + : __imm_const(int_min, INT_MIN) + : __clobber_all); +} + +SEC("tc") +__description("DIV64 overflow, check 1") +__success __retval(0) +__naked void div64_overflow_check_1(void) +{ + asm volatile (" \ + r1 = -1; \ + r2 = %[llong_min] ll; \ + r2 /= r1; \ + w0 = 0; \ + if r0 == r2 goto l0_%=; \ + w0 = 1; \ +l0_%=: exit; \ +" : + : __imm_const(llong_min, LLONG_MIN) + : __clobber_all); +} + +SEC("tc") +__description("DIV64 overflow, check 2") +__success __retval(0) +__naked void div64_overflow_check_2(void) +{ + asm volatile (" \ + r1 = %[llong_min] ll; \ + r1 /= -1; \ + w0 = 0; \ + if r0 == r1 goto l0_%=; \ + w0 = 1; \ +l0_%=: exit; \ +" : + : __imm_const(llong_min, LLONG_MIN) + : __clobber_all); +} + +SEC("tc") +__description("MOD32 overflow, check 1") +__success __retval(INT_MIN) +__naked void mod32_overflow_check_1(void) +{ + asm volatile (" \ + w1 = -1; \ + w0 = %[int_min]; \ + w0 %%= w1; \ + exit; \ +" : + : __imm_const(int_min, INT_MIN) + : __clobber_all); +} + +SEC("tc") +__description("MOD32 overflow, check 2") +__success __retval(INT_MIN) +__naked void mod32_overflow_check_2(void) +{ + asm volatile (" \ + w0 = %[int_min]; \ + w0 %%= -1; \ + exit; \ +" : + : __imm_const(int_min, INT_MIN) + : __clobber_all); +} + +SEC("tc") +__description("MOD64 overflow, check 1") +__success __retval(1) +__naked void mod64_overflow_check_1(void) +{ + asm volatile (" \ + r1 = -1; \ + r2 = %[llong_min] ll; \ + r3 = r2; \ + r2 %%= r1; \ + w0 = 0; \ + if r3 != r2 goto l0_%=; \ + w0 = 1; \ +l0_%=: exit; \ +" : + : __imm_const(llong_min, LLONG_MIN) + : __clobber_all); +} + +SEC("tc") +__description("MOD64 overflow, check 2") +__success __retval(1) +__naked void mod64_overflow_check_2(void) +{ + asm volatile (" \ + r2 = %[llong_min] ll; \ + r3 = r2; \ + r2 %%= -1; \ + w0 = 0; \ + if r3 != r2 goto l0_%=; \ + w0 = 1; \ +l0_%=: exit; \ +" : + : __imm_const(llong_min, LLONG_MIN) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c new file mode 100644 index 0000000000..2dae5322a1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18 + +SEC("socket") +__description("gotol, small_imm") +__success __success_unpriv __retval(1) +__naked void gotol_small_imm(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 == 0 goto l0_%=; \ + gotol l1_%=; \ +l2_%=: \ + gotol l3_%=; \ +l1_%=: \ + r0 = 1; \ + gotol l2_%=; \ +l0_%=: \ + r0 = 2; \ +l3_%=: \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +#else + +SEC("socket") +__description("cpuv4 is not supported by compiler or jit, use a dummy test") +__success +int dummy_test(void) +{ + return 0; +} + +#endif + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_helper_access_var_len.c b/tools/testing/selftests/bpf/progs/verifier_helper_access_var_len.c new file mode 100644 index 0000000000..50c6b22606 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_helper_access_var_len.c @@ -0,0 +1,825 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/helper_access_var_len.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct test_val); +} map_hash_48b SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 4096); +} map_ringbuf SEC(".maps"); + +SEC("tracepoint") +__description("helper access to variable memory: stack, bitwise AND + JMP, correct bounds") +__success +__naked void bitwise_and_jmp_correct_bounds(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -64; \ + r0 = 0; \ + *(u64*)(r10 - 64) = r0; \ + *(u64*)(r10 - 56) = r0; \ + *(u64*)(r10 - 48) = r0; \ + *(u64*)(r10 - 40) = r0; \ + *(u64*)(r10 - 32) = r0; \ + *(u64*)(r10 - 24) = r0; \ + *(u64*)(r10 - 16) = r0; \ + *(u64*)(r10 - 8) = r0; \ + r2 = 16; \ + *(u64*)(r1 - 128) = r2; \ + r2 = *(u64*)(r1 - 128); \ + r2 &= 64; \ + r4 = 0; \ + if r4 >= r2 goto l0_%=; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +SEC("socket") +__description("helper access to variable memory: stack, bitwise AND, zero included") +/* in privileged mode reads from uninitialized stack locations are permitted */ +__success __failure_unpriv +__msg_unpriv("invalid indirect read from stack R2 off -64+0 size 64") +__retval(0) +__naked void stack_bitwise_and_zero_included(void) +{ + asm volatile (" \ + /* set max stack size */ \ + r6 = 0; \ + *(u64*)(r10 - 128) = r6; \ + /* set r3 to a random value */ \ + call %[bpf_get_prandom_u32]; \ + r3 = r0; \ + /* use bitwise AND to limit r3 range to [0, 64] */\ + r3 &= 64; \ + r1 = %[map_ringbuf] ll; \ + r2 = r10; \ + r2 += -64; \ + r4 = 0; \ + /* Call bpf_ringbuf_output(), it is one of a few helper functions with\ + * ARG_CONST_SIZE_OR_ZERO parameter allowed in unpriv mode.\ + * For unpriv this should signal an error, because memory at &fp[-64] is\ + * not initialized. \ + */ \ + call %[bpf_ringbuf_output]; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_ringbuf_output), + __imm_addr(map_ringbuf) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: stack, bitwise AND + JMP, wrong max") +__failure __msg("invalid indirect access to stack R1 off=-64 size=65") +__naked void bitwise_and_jmp_wrong_max(void) +{ + asm volatile (" \ + r2 = *(u64*)(r1 + 8); \ + r1 = r10; \ + r1 += -64; \ + *(u64*)(r1 - 128) = r2; \ + r2 = *(u64*)(r1 - 128); \ + r2 &= 65; \ + r4 = 0; \ + if r4 >= r2 goto l0_%=; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: stack, JMP, correct bounds") +__success +__naked void memory_stack_jmp_correct_bounds(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -64; \ + r0 = 0; \ + *(u64*)(r10 - 64) = r0; \ + *(u64*)(r10 - 56) = r0; \ + *(u64*)(r10 - 48) = r0; \ + *(u64*)(r10 - 40) = r0; \ + *(u64*)(r10 - 32) = r0; \ + *(u64*)(r10 - 24) = r0; \ + *(u64*)(r10 - 16) = r0; \ + *(u64*)(r10 - 8) = r0; \ + r2 = 16; \ + *(u64*)(r1 - 128) = r2; \ + r2 = *(u64*)(r1 - 128); \ + if r2 > 64 goto l0_%=; \ + r4 = 0; \ + if r4 >= r2 goto l0_%=; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: stack, JMP (signed), correct bounds") +__success +__naked void stack_jmp_signed_correct_bounds(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -64; \ + r0 = 0; \ + *(u64*)(r10 - 64) = r0; \ + *(u64*)(r10 - 56) = r0; \ + *(u64*)(r10 - 48) = r0; \ + *(u64*)(r10 - 40) = r0; \ + *(u64*)(r10 - 32) = r0; \ + *(u64*)(r10 - 24) = r0; \ + *(u64*)(r10 - 16) = r0; \ + *(u64*)(r10 - 8) = r0; \ + r2 = 16; \ + *(u64*)(r1 - 128) = r2; \ + r2 = *(u64*)(r1 - 128); \ + if r2 s> 64 goto l0_%=; \ + r4 = 0; \ + if r4 s>= r2 goto l0_%=; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: stack, JMP, bounds + offset") +__failure __msg("invalid indirect access to stack R1 off=-64 size=65") +__naked void memory_stack_jmp_bounds_offset(void) +{ + asm volatile (" \ + r2 = *(u64*)(r1 + 8); \ + r1 = r10; \ + r1 += -64; \ + *(u64*)(r1 - 128) = r2; \ + r2 = *(u64*)(r1 - 128); \ + if r2 > 64 goto l0_%=; \ + r4 = 0; \ + if r4 >= r2 goto l0_%=; \ + r2 += 1; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: stack, JMP, wrong max") +__failure __msg("invalid indirect access to stack R1 off=-64 size=65") +__naked void memory_stack_jmp_wrong_max(void) +{ + asm volatile (" \ + r2 = *(u64*)(r1 + 8); \ + r1 = r10; \ + r1 += -64; \ + *(u64*)(r1 - 128) = r2; \ + r2 = *(u64*)(r1 - 128); \ + if r2 > 65 goto l0_%=; \ + r4 = 0; \ + if r4 >= r2 goto l0_%=; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: stack, JMP, no max check") +__failure +/* because max wasn't checked, signed min is negative */ +__msg("R2 min value is negative, either use unsigned or 'var &= const'") +__naked void stack_jmp_no_max_check(void) +{ + asm volatile (" \ + r2 = *(u64*)(r1 + 8); \ + r1 = r10; \ + r1 += -64; \ + *(u64*)(r1 - 128) = r2; \ + r2 = *(u64*)(r1 - 128); \ + r4 = 0; \ + if r4 >= r2 goto l0_%=; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +SEC("socket") +__description("helper access to variable memory: stack, JMP, no min check") +/* in privileged mode reads from uninitialized stack locations are permitted */ +__success __failure_unpriv +__msg_unpriv("invalid indirect read from stack R2 off -64+0 size 64") +__retval(0) +__naked void stack_jmp_no_min_check(void) +{ + asm volatile (" \ + /* set max stack size */ \ + r6 = 0; \ + *(u64*)(r10 - 128) = r6; \ + /* set r3 to a random value */ \ + call %[bpf_get_prandom_u32]; \ + r3 = r0; \ + /* use JMP to limit r3 range to [0, 64] */ \ + if r3 > 64 goto l0_%=; \ + r1 = %[map_ringbuf] ll; \ + r2 = r10; \ + r2 += -64; \ + r4 = 0; \ + /* Call bpf_ringbuf_output(), it is one of a few helper functions with\ + * ARG_CONST_SIZE_OR_ZERO parameter allowed in unpriv mode.\ + * For unpriv this should signal an error, because memory at &fp[-64] is\ + * not initialized. \ + */ \ + call %[bpf_ringbuf_output]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_ringbuf_output), + __imm_addr(map_ringbuf) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: stack, JMP (signed), no min check") +__failure __msg("R2 min value is negative") +__naked void jmp_signed_no_min_check(void) +{ + asm volatile (" \ + r2 = *(u64*)(r1 + 8); \ + r1 = r10; \ + r1 += -64; \ + *(u64*)(r1 - 128) = r2; \ + r2 = *(u64*)(r1 - 128); \ + if r2 s> 64 goto l0_%=; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ + r0 = 0; \ +l0_%=: exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: map, JMP, correct bounds") +__success +__naked void memory_map_jmp_correct_bounds(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = %[sizeof_test_val]; \ + *(u64*)(r10 - 128) = r2; \ + r2 = *(u64*)(r10 - 128); \ + if r2 s> %[sizeof_test_val] goto l1_%=; \ + r4 = 0; \ + if r4 s>= r2 goto l1_%=; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l1_%=: r0 = 0; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(sizeof_test_val, sizeof(struct test_val)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: map, JMP, wrong max") +__failure __msg("invalid access to map value, value_size=48 off=0 size=49") +__naked void memory_map_jmp_wrong_max(void) +{ + asm volatile (" \ + r6 = *(u64*)(r1 + 8); \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = r6; \ + *(u64*)(r10 - 128) = r2; \ + r2 = *(u64*)(r10 - 128); \ + if r2 s> %[__imm_0] goto l1_%=; \ + r4 = 0; \ + if r4 s>= r2 goto l1_%=; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l1_%=: r0 = 0; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(__imm_0, sizeof(struct test_val) + 1) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: map adjusted, JMP, correct bounds") +__success +__naked void map_adjusted_jmp_correct_bounds(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r1 += 20; \ + r2 = %[sizeof_test_val]; \ + *(u64*)(r10 - 128) = r2; \ + r2 = *(u64*)(r10 - 128); \ + if r2 s> %[__imm_0] goto l1_%=; \ + r4 = 0; \ + if r4 s>= r2 goto l1_%=; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l1_%=: r0 = 0; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(__imm_0, sizeof(struct test_val) - 20), + __imm_const(sizeof_test_val, sizeof(struct test_val)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: map adjusted, JMP, wrong max") +__failure __msg("R1 min value is outside of the allowed memory range") +__naked void map_adjusted_jmp_wrong_max(void) +{ + asm volatile (" \ + r6 = *(u64*)(r1 + 8); \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r1 += 20; \ + r2 = r6; \ + *(u64*)(r10 - 128) = r2; \ + r2 = *(u64*)(r10 - 128); \ + if r2 s> %[__imm_0] goto l1_%=; \ + r4 = 0; \ + if r4 s>= r2 goto l1_%=; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l1_%=: r0 = 0; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(__imm_0, sizeof(struct test_val) - 19) + : __clobber_all); +} + +SEC("tc") +__description("helper access to variable memory: size = 0 allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)") +__success __retval(0) +__naked void ptr_to_mem_or_null_1(void) +{ + asm volatile (" \ + r1 = 0; \ + r2 = 0; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ + exit; \ +" : + : __imm(bpf_csum_diff) + : __clobber_all); +} + +SEC("tc") +__description("helper access to variable memory: size > 0 not allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)") +__failure __msg("R1 type=scalar expected=fp") +__naked void ptr_to_mem_or_null_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + 0); \ + r1 = 0; \ + *(u64*)(r10 - 128) = r2; \ + r2 = *(u64*)(r10 - 128); \ + r2 &= 64; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ + exit; \ +" : + : __imm(bpf_csum_diff) + : __clobber_all); +} + +SEC("tc") +__description("helper access to variable memory: size = 0 allowed on != NULL stack pointer (ARG_PTR_TO_MEM_OR_NULL)") +__success __retval(0) +__naked void ptr_to_mem_or_null_3(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -8; \ + r2 = 0; \ + *(u64*)(r1 + 0) = r2; \ + r2 &= 8; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ + exit; \ +" : + : __imm(bpf_csum_diff) + : __clobber_all); +} + +SEC("tc") +__description("helper access to variable memory: size = 0 allowed on != NULL map pointer (ARG_PTR_TO_MEM_OR_NULL)") +__success __retval(0) +__naked void ptr_to_mem_or_null_4(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = 0; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ +l0_%=: exit; \ +" : + : __imm(bpf_csum_diff), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("tc") +__description("helper access to variable memory: size possible = 0 allowed on != NULL stack pointer (ARG_PTR_TO_MEM_OR_NULL)") +__success __retval(0) +__naked void ptr_to_mem_or_null_5(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r2 = *(u64*)(r0 + 0); \ + if r2 > 8 goto l0_%=; \ + r1 = r10; \ + r1 += -8; \ + *(u64*)(r1 + 0) = r2; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ +l0_%=: exit; \ +" : + : __imm(bpf_csum_diff), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("tc") +__description("helper access to variable memory: size possible = 0 allowed on != NULL map pointer (ARG_PTR_TO_MEM_OR_NULL)") +__success __retval(0) +__naked void ptr_to_mem_or_null_6(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = *(u64*)(r0 + 0); \ + if r2 > 8 goto l0_%=; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ +l0_%=: exit; \ +" : + : __imm(bpf_csum_diff), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("tc") +__description("helper access to variable memory: size possible = 0 allowed on != NULL packet pointer (ARG_PTR_TO_MEM_OR_NULL)") +__success __retval(0) +/* csum_diff of 64-byte packet */ +__flag(BPF_F_ANY_ALIGNMENT) +__naked void ptr_to_mem_or_null_7(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r6; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r1 = r6; \ + r2 = *(u64*)(r6 + 0); \ + if r2 > 8 goto l0_%=; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ +l0_%=: exit; \ +" : + : __imm(bpf_csum_diff), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: size = 0 not allowed on NULL (!ARG_PTR_TO_MEM_OR_NULL)") +__failure __msg("R1 type=scalar expected=fp") +__naked void ptr_to_mem_or_null_8(void) +{ + asm volatile (" \ + r1 = 0; \ + r2 = 0; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: size > 0 not allowed on NULL (!ARG_PTR_TO_MEM_OR_NULL)") +__failure __msg("R1 type=scalar expected=fp") +__naked void ptr_to_mem_or_null_9(void) +{ + asm volatile (" \ + r1 = 0; \ + r2 = 1; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: size = 0 allowed on != NULL stack pointer (!ARG_PTR_TO_MEM_OR_NULL)") +__success +__naked void ptr_to_mem_or_null_10(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -8; \ + r2 = 0; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: size = 0 allowed on != NULL map pointer (!ARG_PTR_TO_MEM_OR_NULL)") +__success +__naked void ptr_to_mem_or_null_11(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = 0; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: size possible = 0 allowed on != NULL stack pointer (!ARG_PTR_TO_MEM_OR_NULL)") +__success +__naked void ptr_to_mem_or_null_12(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r2 = *(u64*)(r0 + 0); \ + if r2 > 8 goto l0_%=; \ + r1 = r10; \ + r1 += -8; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: size possible = 0 allowed on != NULL map pointer (!ARG_PTR_TO_MEM_OR_NULL)") +__success +__naked void ptr_to_mem_or_null_13(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = *(u64*)(r0 + 0); \ + if r2 > 8 goto l0_%=; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("helper access to variable memory: 8 bytes leak") +/* in privileged mode reads from uninitialized stack locations are permitted */ +__success __failure_unpriv +__msg_unpriv("invalid indirect read from stack R2 off -64+32 size 64") +__retval(0) +__naked void variable_memory_8_bytes_leak(void) +{ + asm volatile (" \ + /* set max stack size */ \ + r6 = 0; \ + *(u64*)(r10 - 128) = r6; \ + /* set r3 to a random value */ \ + call %[bpf_get_prandom_u32]; \ + r3 = r0; \ + r1 = %[map_ringbuf] ll; \ + r2 = r10; \ + r2 += -64; \ + r0 = 0; \ + *(u64*)(r10 - 64) = r0; \ + *(u64*)(r10 - 56) = r0; \ + *(u64*)(r10 - 48) = r0; \ + *(u64*)(r10 - 40) = r0; \ + /* Note: fp[-32] left uninitialized */ \ + *(u64*)(r10 - 24) = r0; \ + *(u64*)(r10 - 16) = r0; \ + *(u64*)(r10 - 8) = r0; \ + /* Limit r3 range to [1, 64] */ \ + r3 &= 63; \ + r3 += 1; \ + r4 = 0; \ + /* Call bpf_ringbuf_output(), it is one of a few helper functions with\ + * ARG_CONST_SIZE_OR_ZERO parameter allowed in unpriv mode.\ + * For unpriv this should signal an error, because memory region [1, 64]\ + * at &fp[-64] is not fully initialized. \ + */ \ + call %[bpf_ringbuf_output]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_ringbuf_output), + __imm_addr(map_ringbuf) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to variable memory: 8 bytes no leak (init memory)") +__success +__naked void bytes_no_leak_init_memory(void) +{ + asm volatile (" \ + r1 = r10; \ + r0 = 0; \ + r0 = 0; \ + *(u64*)(r10 - 64) = r0; \ + *(u64*)(r10 - 56) = r0; \ + *(u64*)(r10 - 48) = r0; \ + *(u64*)(r10 - 40) = r0; \ + *(u64*)(r10 - 32) = r0; \ + *(u64*)(r10 - 24) = r0; \ + *(u64*)(r10 - 16) = r0; \ + *(u64*)(r10 - 8) = r0; \ + r1 += -64; \ + r2 = 0; \ + r2 &= 32; \ + r2 += 32; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ + r1 = *(u64*)(r10 - 16); \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_helper_packet_access.c b/tools/testing/selftests/bpf/progs/verifier_helper_packet_access.c new file mode 100644 index 0000000000..74f5f9cd15 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_helper_packet_access.c @@ -0,0 +1,550 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/helper_packet_access.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +SEC("xdp") +__description("helper access to packet: test1, valid packet_ptr range") +__success __retval(0) +__naked void test1_valid_packet_ptr_range(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r1 > r3 goto l0_%=; \ + r1 = %[map_hash_8b] ll; \ + r3 = r2; \ + r4 = 0; \ + call %[bpf_map_update_elem]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_update_elem), + __imm_addr(map_hash_8b), + __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("helper access to packet: test2, unchecked packet_ptr") +__failure __msg("invalid access to packet") +__naked void packet_test2_unchecked_packet_ptr(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm_const(xdp_md_data, offsetof(struct xdp_md, data)) + : __clobber_all); +} + +SEC("xdp") +__description("helper access to packet: test3, variable add") +__success __retval(0) +__naked void to_packet_test3_variable_add(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r4 = r2; \ + r4 += 8; \ + if r4 > r3 goto l0_%=; \ + r5 = *(u8*)(r2 + 0); \ + r4 = r2; \ + r4 += r5; \ + r5 = r4; \ + r5 += 8; \ + if r5 > r3 goto l0_%=; \ + r1 = %[map_hash_8b] ll; \ + r2 = r4; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("helper access to packet: test4, packet_ptr with bad range") +__failure __msg("invalid access to packet") +__naked void packet_ptr_with_bad_range_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r4 = r2; \ + r4 += 4; \ + if r4 > r3 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("helper access to packet: test5, packet_ptr with too short range") +__failure __msg("invalid access to packet") +__naked void ptr_with_too_short_range_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r2 += 1; \ + r4 = r2; \ + r4 += 7; \ + if r4 > r3 goto l0_%=; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test6, cls valid packet_ptr range") +__success __retval(0) +__naked void cls_valid_packet_ptr_range(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r1 > r3 goto l0_%=; \ + r1 = %[map_hash_8b] ll; \ + r3 = r2; \ + r4 = 0; \ + call %[bpf_map_update_elem]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_update_elem), + __imm_addr(map_hash_8b), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test7, cls unchecked packet_ptr") +__failure __msg("invalid access to packet") +__naked void test7_cls_unchecked_packet_ptr(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test8, cls variable add") +__success __retval(0) +__naked void packet_test8_cls_variable_add(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r4 = r2; \ + r4 += 8; \ + if r4 > r3 goto l0_%=; \ + r5 = *(u8*)(r2 + 0); \ + r4 = r2; \ + r4 += r5; \ + r5 = r4; \ + r5 += 8; \ + if r5 > r3 goto l0_%=; \ + r1 = %[map_hash_8b] ll; \ + r2 = r4; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test9, cls packet_ptr with bad range") +__failure __msg("invalid access to packet") +__naked void packet_ptr_with_bad_range_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r4 = r2; \ + r4 += 4; \ + if r4 > r3 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test10, cls packet_ptr with too short range") +__failure __msg("invalid access to packet") +__naked void ptr_with_too_short_range_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r2 += 1; \ + r4 = r2; \ + r4 += 7; \ + if r4 > r3 goto l0_%=; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test11, cls unsuitable helper 1") +__failure __msg("helper access to the packet") +__naked void test11_cls_unsuitable_helper_1(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_data]); \ + r7 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r6 += 1; \ + r3 = r6; \ + r3 += 7; \ + if r3 > r7 goto l0_%=; \ + r2 = 0; \ + r4 = 42; \ + r5 = 0; \ + call %[bpf_skb_store_bytes]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_skb_store_bytes), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test12, cls unsuitable helper 2") +__failure __msg("helper access to the packet") +__naked void test12_cls_unsuitable_helper_2(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_data]); \ + r7 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r3 = r6; \ + r6 += 8; \ + if r6 > r7 goto l0_%=; \ + r2 = 0; \ + r4 = 4; \ + call %[bpf_skb_load_bytes]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_skb_load_bytes), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test13, cls helper ok") +__success __retval(0) +__naked void packet_test13_cls_helper_ok(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_data]); \ + r7 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r6 += 1; \ + r1 = r6; \ + r1 += 7; \ + if r1 > r7 goto l0_%=; \ + r1 = r6; \ + r2 = 4; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_csum_diff), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test14, cls helper ok sub") +__success __retval(0) +__naked void test14_cls_helper_ok_sub(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_data]); \ + r7 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r6 += 1; \ + r1 = r6; \ + r1 += 7; \ + if r1 > r7 goto l0_%=; \ + r1 -= 4; \ + r2 = 4; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_csum_diff), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test15, cls helper fail sub") +__failure __msg("invalid access to packet") +__naked void test15_cls_helper_fail_sub(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_data]); \ + r7 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r6 += 1; \ + r1 = r6; \ + r1 += 7; \ + if r1 > r7 goto l0_%=; \ + r1 -= 12; \ + r2 = 4; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_csum_diff), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test16, cls helper fail range 1") +__failure __msg("invalid access to packet") +__naked void cls_helper_fail_range_1(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_data]); \ + r7 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r6 += 1; \ + r1 = r6; \ + r1 += 7; \ + if r1 > r7 goto l0_%=; \ + r1 = r6; \ + r2 = 8; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_csum_diff), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test17, cls helper fail range 2") +__failure __msg("R2 min value is negative") +__naked void cls_helper_fail_range_2(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_data]); \ + r7 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r6 += 1; \ + r1 = r6; \ + r1 += 7; \ + if r1 > r7 goto l0_%=; \ + r1 = r6; \ + r2 = -9; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_csum_diff), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test18, cls helper fail range 3") +__failure __msg("R2 min value is negative") +__naked void cls_helper_fail_range_3(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_data]); \ + r7 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r6 += 1; \ + r1 = r6; \ + r1 += 7; \ + if r1 > r7 goto l0_%=; \ + r1 = r6; \ + r2 = %[__imm_0]; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_csum_diff), + __imm_const(__imm_0, ~0), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test19, cls helper range zero") +__success __retval(0) +__naked void test19_cls_helper_range_zero(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_data]); \ + r7 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r6 += 1; \ + r1 = r6; \ + r1 += 7; \ + if r1 > r7 goto l0_%=; \ + r1 = r6; \ + r2 = 0; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_csum_diff), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test20, pkt end as input") +__failure __msg("R1 type=pkt_end expected=fp") +__naked void test20_pkt_end_as_input(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_data]); \ + r7 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r6 += 1; \ + r1 = r6; \ + r1 += 7; \ + if r1 > r7 goto l0_%=; \ + r1 = r7; \ + r2 = 4; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_csum_diff), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("helper access to packet: test21, wrong reg") +__failure __msg("invalid access to packet") +__naked void to_packet_test21_wrong_reg(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_data]); \ + r7 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r6 += 1; \ + r1 = r6; \ + r1 += 7; \ + if r1 > r7 goto l0_%=; \ + r2 = 4; \ + r3 = 0; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_csum_diff]; \ + r0 = 0; \ +l0_%=: exit; \ +" : + : __imm(bpf_csum_diff), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_helper_restricted.c b/tools/testing/selftests/bpf/progs/verifier_helper_restricted.c new file mode 100644 index 0000000000..0ede0ccd09 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_helper_restricted.c @@ -0,0 +1,279 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/helper_restricted.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct val { + int cnt; + struct bpf_spin_lock l; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct val); +} map_spin_lock SEC(".maps"); + +struct timer { + struct bpf_timer t; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct timer); +} map_timer SEC(".maps"); + +SEC("kprobe") +__description("bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_KPROBE") +__failure __msg("unknown func bpf_ktime_get_coarse_ns") +__naked void in_bpf_prog_type_kprobe_1(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_coarse_ns]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_coarse_ns) + : __clobber_all); +} + +SEC("tracepoint") +__description("bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_TRACEPOINT") +__failure __msg("unknown func bpf_ktime_get_coarse_ns") +__naked void in_bpf_prog_type_tracepoint_1(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_coarse_ns]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_coarse_ns) + : __clobber_all); +} + +SEC("perf_event") +__description("bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_PERF_EVENT") +__failure __msg("unknown func bpf_ktime_get_coarse_ns") +__naked void bpf_prog_type_perf_event_1(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_coarse_ns]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_coarse_ns) + : __clobber_all); +} + +SEC("raw_tracepoint") +__description("bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT") +__failure __msg("unknown func bpf_ktime_get_coarse_ns") +__naked void bpf_prog_type_raw_tracepoint_1(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_coarse_ns]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_coarse_ns) + : __clobber_all); +} + +SEC("kprobe") +__description("bpf_timer_init isn restricted in BPF_PROG_TYPE_KPROBE") +__failure __msg("tracing progs cannot use bpf_timer yet") +__naked void in_bpf_prog_type_kprobe_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_timer] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = %[map_timer] ll; \ + r3 = 1; \ +l0_%=: call %[bpf_timer_init]; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_timer_init), + __imm_addr(map_timer) + : __clobber_all); +} + +SEC("perf_event") +__description("bpf_timer_init is forbidden in BPF_PROG_TYPE_PERF_EVENT") +__failure __msg("tracing progs cannot use bpf_timer yet") +__naked void bpf_prog_type_perf_event_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_timer] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = %[map_timer] ll; \ + r3 = 1; \ +l0_%=: call %[bpf_timer_init]; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_timer_init), + __imm_addr(map_timer) + : __clobber_all); +} + +SEC("tracepoint") +__description("bpf_timer_init is forbidden in BPF_PROG_TYPE_TRACEPOINT") +__failure __msg("tracing progs cannot use bpf_timer yet") +__naked void in_bpf_prog_type_tracepoint_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_timer] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = %[map_timer] ll; \ + r3 = 1; \ +l0_%=: call %[bpf_timer_init]; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_timer_init), + __imm_addr(map_timer) + : __clobber_all); +} + +SEC("raw_tracepoint") +__description("bpf_timer_init is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT") +__failure __msg("tracing progs cannot use bpf_timer yet") +__naked void bpf_prog_type_raw_tracepoint_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_timer] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = %[map_timer] ll; \ + r3 = 1; \ +l0_%=: call %[bpf_timer_init]; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_timer_init), + __imm_addr(map_timer) + : __clobber_all); +} + +SEC("kprobe") +__description("bpf_spin_lock is forbidden in BPF_PROG_TYPE_KPROBE") +__failure __msg("tracing progs cannot use bpf_spin_lock yet") +__naked void in_bpf_prog_type_kprobe_3(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + call %[bpf_spin_lock]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +SEC("tracepoint") +__description("bpf_spin_lock is forbidden in BPF_PROG_TYPE_TRACEPOINT") +__failure __msg("tracing progs cannot use bpf_spin_lock yet") +__naked void in_bpf_prog_type_tracepoint_3(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + call %[bpf_spin_lock]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +SEC("perf_event") +__description("bpf_spin_lock is forbidden in BPF_PROG_TYPE_PERF_EVENT") +__failure __msg("tracing progs cannot use bpf_spin_lock yet") +__naked void bpf_prog_type_perf_event_3(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + call %[bpf_spin_lock]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +SEC("raw_tracepoint") +__description("bpf_spin_lock is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT") +__failure __msg("tracing progs cannot use bpf_spin_lock yet") +__naked void bpf_prog_type_raw_tracepoint_3(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + call %[bpf_spin_lock]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c b/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c new file mode 100644 index 0000000000..692216c0ad --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c @@ -0,0 +1,1245 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/helper_value_access.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct other_val { + long long foo; + long long bar; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct other_val); +} map_hash_16b SEC(".maps"); + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct test_val); +} map_hash_48b SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +SEC("tracepoint") +__description("helper access to map: full range") +__success +__naked void access_to_map_full_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = %[sizeof_test_val]; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(sizeof_test_val, sizeof(struct test_val)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to map: partial range") +__success +__naked void access_to_map_partial_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = 8; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to map: empty range") +__failure __msg("invalid access to map value, value_size=48 off=0 size=0") +__naked void access_to_map_empty_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = 0; \ + call %[bpf_trace_printk]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_trace_printk), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to map: out-of-bound range") +__failure __msg("invalid access to map value, value_size=48 off=0 size=56") +__naked void map_out_of_bound_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = %[__imm_0]; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(__imm_0, sizeof(struct test_val) + 8) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to map: negative range") +__failure __msg("R2 min value is negative") +__naked void access_to_map_negative_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r2 = -8; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via const imm): full range") +__success +__naked void via_const_imm_full_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r1 += %[test_val_foo]; \ + r2 = %[__imm_0]; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(__imm_0, sizeof(struct test_val) - offsetof(struct test_val, foo)), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via const imm): partial range") +__success +__naked void via_const_imm_partial_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r1 += %[test_val_foo]; \ + r2 = 8; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via const imm): empty range") +__failure __msg("invalid access to map value, value_size=48 off=4 size=0") +__naked void via_const_imm_empty_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r1 += %[test_val_foo]; \ + r2 = 0; \ + call %[bpf_trace_printk]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_trace_printk), + __imm_addr(map_hash_48b), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via const imm): out-of-bound range") +__failure __msg("invalid access to map value, value_size=48 off=4 size=52") +__naked void imm_out_of_bound_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r1 += %[test_val_foo]; \ + r2 = %[__imm_0]; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(__imm_0, sizeof(struct test_val) - offsetof(struct test_val, foo) + 8), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via const imm): negative range (> adjustment)") +__failure __msg("R2 min value is negative") +__naked void const_imm_negative_range_adjustment_1(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r1 += %[test_val_foo]; \ + r2 = -8; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via const imm): negative range (< adjustment)") +__failure __msg("R2 min value is negative") +__naked void const_imm_negative_range_adjustment_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r1 += %[test_val_foo]; \ + r2 = -1; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via const reg): full range") +__success +__naked void via_const_reg_full_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = %[test_val_foo]; \ + r1 += r3; \ + r2 = %[__imm_0]; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(__imm_0, sizeof(struct test_val) - offsetof(struct test_val, foo)), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via const reg): partial range") +__success +__naked void via_const_reg_partial_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = %[test_val_foo]; \ + r1 += r3; \ + r2 = 8; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via const reg): empty range") +__failure __msg("R1 min value is outside of the allowed memory range") +__naked void via_const_reg_empty_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = 0; \ + r1 += r3; \ + r2 = 0; \ + call %[bpf_trace_printk]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_trace_printk), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via const reg): out-of-bound range") +__failure __msg("invalid access to map value, value_size=48 off=4 size=52") +__naked void reg_out_of_bound_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = %[test_val_foo]; \ + r1 += r3; \ + r2 = %[__imm_0]; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(__imm_0, sizeof(struct test_val) - offsetof(struct test_val, foo) + 8), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via const reg): negative range (> adjustment)") +__failure __msg("R2 min value is negative") +__naked void const_reg_negative_range_adjustment_1(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = %[test_val_foo]; \ + r1 += r3; \ + r2 = -8; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via const reg): negative range (< adjustment)") +__failure __msg("R2 min value is negative") +__naked void const_reg_negative_range_adjustment_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = %[test_val_foo]; \ + r1 += r3; \ + r2 = -1; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via variable): full range") +__success +__naked void map_via_variable_full_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = *(u32*)(r0 + 0); \ + if r3 > %[test_val_foo] goto l0_%=; \ + r1 += r3; \ + r2 = %[__imm_0]; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(__imm_0, sizeof(struct test_val) - offsetof(struct test_val, foo)), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via variable): partial range") +__success +__naked void map_via_variable_partial_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = *(u32*)(r0 + 0); \ + if r3 > %[test_val_foo] goto l0_%=; \ + r1 += r3; \ + r2 = 8; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via variable): empty range") +__failure __msg("R1 min value is outside of the allowed memory range") +__naked void map_via_variable_empty_range(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = *(u32*)(r0 + 0); \ + if r3 > %[test_val_foo] goto l0_%=; \ + r1 += r3; \ + r2 = 0; \ + call %[bpf_trace_printk]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_trace_printk), + __imm_addr(map_hash_48b), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via variable): no max check") +__failure __msg("R1 unbounded memory access") +__naked void via_variable_no_max_check_1(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = *(u32*)(r0 + 0); \ + r1 += r3; \ + r2 = 1; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to adjusted map (via variable): wrong max check") +__failure __msg("invalid access to map value, value_size=48 off=4 size=45") +__naked void via_variable_wrong_max_check_1(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = *(u32*)(r0 + 0); \ + if r3 > %[test_val_foo] goto l0_%=; \ + r1 += r3; \ + r2 = %[__imm_0]; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_probe_read_kernel), + __imm_addr(map_hash_48b), + __imm_const(__imm_0, sizeof(struct test_val) - offsetof(struct test_val, foo) + 1), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to map: bounds check using <, good access") +__success +__naked void bounds_check_using_good_access_1(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = *(u32*)(r0 + 0); \ + if r3 < 32 goto l1_%=; \ + r0 = 0; \ +l0_%=: exit; \ +l1_%=: r1 += r3; \ + r0 = 0; \ + *(u8*)(r1 + 0) = r0; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to map: bounds check using <, bad access") +__failure __msg("R1 unbounded memory access") +__naked void bounds_check_using_bad_access_1(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = *(u32*)(r0 + 0); \ + if r3 < 32 goto l1_%=; \ + r1 += r3; \ +l0_%=: r0 = 0; \ + *(u8*)(r1 + 0) = r0; \ + r0 = 0; \ + exit; \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to map: bounds check using <=, good access") +__success +__naked void bounds_check_using_good_access_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = *(u32*)(r0 + 0); \ + if r3 <= 32 goto l1_%=; \ + r0 = 0; \ +l0_%=: exit; \ +l1_%=: r1 += r3; \ + r0 = 0; \ + *(u8*)(r1 + 0) = r0; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to map: bounds check using <=, bad access") +__failure __msg("R1 unbounded memory access") +__naked void bounds_check_using_bad_access_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = *(u32*)(r0 + 0); \ + if r3 <= 32 goto l1_%=; \ + r1 += r3; \ +l0_%=: r0 = 0; \ + *(u8*)(r1 + 0) = r0; \ + r0 = 0; \ + exit; \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to map: bounds check using s<, good access") +__success +__naked void check_using_s_good_access_1(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = *(u32*)(r0 + 0); \ + if r3 s< 32 goto l1_%=; \ +l2_%=: r0 = 0; \ +l0_%=: exit; \ +l1_%=: if r3 s< 0 goto l2_%=; \ + r1 += r3; \ + r0 = 0; \ + *(u8*)(r1 + 0) = r0; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to map: bounds check using s<, good access 2") +__success +__naked void using_s_good_access_2_1(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = *(u32*)(r0 + 0); \ + if r3 s< 32 goto l1_%=; \ +l2_%=: r0 = 0; \ +l0_%=: exit; \ +l1_%=: if r3 s< -3 goto l2_%=; \ + r1 += r3; \ + r0 = 0; \ + *(u8*)(r1 + 0) = r0; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to map: bounds check using s<, bad access") +__failure __msg("R1 min value is negative") +__naked void check_using_s_bad_access_1(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = *(u64*)(r0 + 0); \ + if r3 s< 32 goto l1_%=; \ +l2_%=: r0 = 0; \ +l0_%=: exit; \ +l1_%=: if r3 s< -3 goto l2_%=; \ + r1 += r3; \ + r0 = 0; \ + *(u8*)(r1 + 0) = r0; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to map: bounds check using s<=, good access") +__success +__naked void check_using_s_good_access_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = *(u32*)(r0 + 0); \ + if r3 s<= 32 goto l1_%=; \ +l2_%=: r0 = 0; \ +l0_%=: exit; \ +l1_%=: if r3 s<= 0 goto l2_%=; \ + r1 += r3; \ + r0 = 0; \ + *(u8*)(r1 + 0) = r0; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to map: bounds check using s<=, good access 2") +__success +__naked void using_s_good_access_2_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = *(u32*)(r0 + 0); \ + if r3 s<= 32 goto l1_%=; \ +l2_%=: r0 = 0; \ +l0_%=: exit; \ +l1_%=: if r3 s<= -3 goto l2_%=; \ + r1 += r3; \ + r0 = 0; \ + *(u8*)(r1 + 0) = r0; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("helper access to map: bounds check using s<=, bad access") +__failure __msg("R1 min value is negative") +__naked void check_using_s_bad_access_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + r3 = *(u64*)(r0 + 0); \ + if r3 s<= 32 goto l1_%=; \ +l2_%=: r0 = 0; \ +l0_%=: exit; \ +l1_%=: if r3 s<= -3 goto l2_%=; \ + r1 += r3; \ + r0 = 0; \ + *(u8*)(r1 + 0) = r0; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("map lookup helper access to map") +__success +__naked void lookup_helper_access_to_map(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r2 = r0; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_16b) + : __clobber_all); +} + +SEC("tracepoint") +__description("map update helper access to map") +__success +__naked void update_helper_access_to_map(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r4 = 0; \ + r3 = r0; \ + r2 = r0; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_update_elem]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_map_update_elem), + __imm_addr(map_hash_16b) + : __clobber_all); +} + +SEC("tracepoint") +__description("map update helper access to map: wrong size") +__failure __msg("invalid access to map value, value_size=8 off=0 size=16") +__naked void access_to_map_wrong_size(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r4 = 0; \ + r3 = r0; \ + r2 = r0; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_update_elem]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_map_update_elem), + __imm_addr(map_hash_16b), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("tracepoint") +__description("map helper access to adjusted map (via const imm)") +__success +__naked void adjusted_map_via_const_imm(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r2 = r0; \ + r2 += %[other_val_bar]; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_16b), + __imm_const(other_val_bar, offsetof(struct other_val, bar)) + : __clobber_all); +} + +SEC("tracepoint") +__description("map helper access to adjusted map (via const imm): out-of-bound 1") +__failure __msg("invalid access to map value, value_size=16 off=12 size=8") +__naked void imm_out_of_bound_1(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r2 = r0; \ + r2 += %[__imm_0]; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_16b), + __imm_const(__imm_0, sizeof(struct other_val) - 4) + : __clobber_all); +} + +SEC("tracepoint") +__description("map helper access to adjusted map (via const imm): out-of-bound 2") +__failure __msg("invalid access to map value, value_size=16 off=-4 size=8") +__naked void imm_out_of_bound_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r2 = r0; \ + r2 += -4; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_16b) + : __clobber_all); +} + +SEC("tracepoint") +__description("map helper access to adjusted map (via const reg)") +__success +__naked void adjusted_map_via_const_reg(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r2 = r0; \ + r3 = %[other_val_bar]; \ + r2 += r3; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_16b), + __imm_const(other_val_bar, offsetof(struct other_val, bar)) + : __clobber_all); +} + +SEC("tracepoint") +__description("map helper access to adjusted map (via const reg): out-of-bound 1") +__failure __msg("invalid access to map value, value_size=16 off=12 size=8") +__naked void reg_out_of_bound_1(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r2 = r0; \ + r3 = %[__imm_0]; \ + r2 += r3; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_16b), + __imm_const(__imm_0, sizeof(struct other_val) - 4) + : __clobber_all); +} + +SEC("tracepoint") +__description("map helper access to adjusted map (via const reg): out-of-bound 2") +__failure __msg("invalid access to map value, value_size=16 off=-4 size=8") +__naked void reg_out_of_bound_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r2 = r0; \ + r3 = -4; \ + r2 += r3; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_16b) + : __clobber_all); +} + +SEC("tracepoint") +__description("map helper access to adjusted map (via variable)") +__success +__naked void to_adjusted_map_via_variable(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r2 = r0; \ + r3 = *(u32*)(r0 + 0); \ + if r3 > %[other_val_bar] goto l0_%=; \ + r2 += r3; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_16b), + __imm_const(other_val_bar, offsetof(struct other_val, bar)) + : __clobber_all); +} + +SEC("tracepoint") +__description("map helper access to adjusted map (via variable): no max check") +__failure +__msg("R2 unbounded memory access, make sure to bounds check any such access") +__naked void via_variable_no_max_check_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r2 = r0; \ + r3 = *(u32*)(r0 + 0); \ + r2 += r3; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_16b) + : __clobber_all); +} + +SEC("tracepoint") +__description("map helper access to adjusted map (via variable): wrong max check") +__failure __msg("invalid access to map value, value_size=16 off=9 size=8") +__naked void via_variable_wrong_max_check_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r2 = r0; \ + r3 = *(u32*)(r0 + 0); \ + if r3 > %[__imm_0] goto l0_%=; \ + r2 += r3; \ + r1 = %[map_hash_16b] ll; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_16b), + __imm_const(__imm_0, offsetof(struct other_val, bar) + 1) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_int_ptr.c b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c new file mode 100644 index 0000000000..589e8270de --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/int_ptr.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("socket") +__description("ARG_PTR_TO_LONG uninitialized") +__success +__failure_unpriv __msg_unpriv("invalid indirect read from stack R4 off -16+0 size 8") +__naked void arg_ptr_to_long_uninitialized(void) +{ + asm volatile (" \ + /* bpf_strtoul arg1 (buf) */ \ + r7 = r10; \ + r7 += -8; \ + r0 = 0x00303036; \ + *(u64*)(r7 + 0) = r0; \ + r1 = r7; \ + /* bpf_strtoul arg2 (buf_len) */ \ + r2 = 4; \ + /* bpf_strtoul arg3 (flags) */ \ + r3 = 0; \ + /* bpf_strtoul arg4 (res) */ \ + r7 += -8; \ + r4 = r7; \ + /* bpf_strtoul() */ \ + call %[bpf_strtoul]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_strtoul) + : __clobber_all); +} + +SEC("socket") +__description("ARG_PTR_TO_LONG half-uninitialized") +/* in privileged mode reads from uninitialized stack locations are permitted */ +__success __failure_unpriv +__msg_unpriv("invalid indirect read from stack R4 off -16+4 size 8") +__retval(0) +__naked void ptr_to_long_half_uninitialized(void) +{ + asm volatile (" \ + /* bpf_strtoul arg1 (buf) */ \ + r7 = r10; \ + r7 += -8; \ + r0 = 0x00303036; \ + *(u64*)(r7 + 0) = r0; \ + r1 = r7; \ + /* bpf_strtoul arg2 (buf_len) */ \ + r2 = 4; \ + /* bpf_strtoul arg3 (flags) */ \ + r3 = 0; \ + /* bpf_strtoul arg4 (res) */ \ + r7 += -8; \ + *(u32*)(r7 + 0) = r0; \ + r4 = r7; \ + /* bpf_strtoul() */ \ + call %[bpf_strtoul]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_strtoul) + : __clobber_all); +} + +SEC("cgroup/sysctl") +__description("ARG_PTR_TO_LONG misaligned") +__failure __msg("misaligned stack access off (0x0; 0x0)+-20+0 size 8") +__naked void arg_ptr_to_long_misaligned(void) +{ + asm volatile (" \ + /* bpf_strtoul arg1 (buf) */ \ + r7 = r10; \ + r7 += -8; \ + r0 = 0x00303036; \ + *(u64*)(r7 + 0) = r0; \ + r1 = r7; \ + /* bpf_strtoul arg2 (buf_len) */ \ + r2 = 4; \ + /* bpf_strtoul arg3 (flags) */ \ + r3 = 0; \ + /* bpf_strtoul arg4 (res) */ \ + r7 += -12; \ + r0 = 0; \ + *(u32*)(r7 + 0) = r0; \ + *(u64*)(r7 + 4) = r0; \ + r4 = r7; \ + /* bpf_strtoul() */ \ + call %[bpf_strtoul]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_strtoul) + : __clobber_all); +} + +SEC("cgroup/sysctl") +__description("ARG_PTR_TO_LONG size < sizeof(long)") +__failure __msg("invalid indirect access to stack R4 off=-4 size=8") +__naked void to_long_size_sizeof_long(void) +{ + asm volatile (" \ + /* bpf_strtoul arg1 (buf) */ \ + r7 = r10; \ + r7 += -16; \ + r0 = 0x00303036; \ + *(u64*)(r7 + 0) = r0; \ + r1 = r7; \ + /* bpf_strtoul arg2 (buf_len) */ \ + r2 = 4; \ + /* bpf_strtoul arg3 (flags) */ \ + r3 = 0; \ + /* bpf_strtoul arg4 (res) */ \ + r7 += 12; \ + *(u32*)(r7 + 0) = r0; \ + r4 = r7; \ + /* bpf_strtoul() */ \ + call %[bpf_strtoul]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_strtoul) + : __clobber_all); +} + +SEC("cgroup/sysctl") +__description("ARG_PTR_TO_LONG initialized") +__success +__naked void arg_ptr_to_long_initialized(void) +{ + asm volatile (" \ + /* bpf_strtoul arg1 (buf) */ \ + r7 = r10; \ + r7 += -8; \ + r0 = 0x00303036; \ + *(u64*)(r7 + 0) = r0; \ + r1 = r7; \ + /* bpf_strtoul arg2 (buf_len) */ \ + r2 = 4; \ + /* bpf_strtoul arg3 (flags) */ \ + r3 = 0; \ + /* bpf_strtoul arg4 (res) */ \ + r7 += -8; \ + *(u64*)(r7 + 0) = r0; \ + r4 = r7; \ + /* bpf_strtoul() */ \ + call %[bpf_strtoul]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_strtoul) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c new file mode 100644 index 0000000000..5905e036e0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c @@ -0,0 +1,242 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 8); + __type(key, __u32); + __type(value, __u64); +} map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_USER_RINGBUF); + __uint(max_entries, 8); +} ringbuf SEC(".maps"); + +struct vm_area_struct; +struct bpf_map; + +struct buf_context { + char *buf; +}; + +struct num_context { + __u64 i; + __u64 j; +}; + +__u8 choice_arr[2] = { 0, 1 }; + +static int unsafe_on_2nd_iter_cb(__u32 idx, struct buf_context *ctx) +{ + if (idx == 0) { + ctx->buf = (char *)(0xDEAD); + return 0; + } + + if (bpf_probe_read_user(ctx->buf, 8, (void *)(0xBADC0FFEE))) + return 1; + + return 0; +} + +SEC("?raw_tp") +__failure __msg("R1 type=scalar expected=fp") +int unsafe_on_2nd_iter(void *unused) +{ + char buf[4]; + struct buf_context loop_ctx = { .buf = buf }; + + bpf_loop(100, unsafe_on_2nd_iter_cb, &loop_ctx, 0); + return 0; +} + +static int unsafe_on_zero_iter_cb(__u32 idx, struct num_context *ctx) +{ + ctx->i = 0; + return 0; +} + +SEC("?raw_tp") +__failure __msg("invalid access to map value, value_size=2 off=32 size=1") +int unsafe_on_zero_iter(void *unused) +{ + struct num_context loop_ctx = { .i = 32 }; + + bpf_loop(100, unsafe_on_zero_iter_cb, &loop_ctx, 0); + return choice_arr[loop_ctx.i]; +} + +static int widening_cb(__u32 idx, struct num_context *ctx) +{ + ++ctx->i; + return 0; +} + +SEC("?raw_tp") +__success +int widening(void *unused) +{ + struct num_context loop_ctx = { .i = 0, .j = 1 }; + + bpf_loop(100, widening_cb, &loop_ctx, 0); + /* loop_ctx.j is not changed during callback iteration, + * verifier should not apply widening to it. + */ + return choice_arr[loop_ctx.j]; +} + +static int loop_detection_cb(__u32 idx, struct num_context *ctx) +{ + for (;;) {} + return 0; +} + +SEC("?raw_tp") +__failure __msg("infinite loop detected") +int loop_detection(void *unused) +{ + struct num_context loop_ctx = { .i = 0 }; + + bpf_loop(100, loop_detection_cb, &loop_ctx, 0); + return 0; +} + +static __always_inline __u64 oob_state_machine(struct num_context *ctx) +{ + switch (ctx->i) { + case 0: + ctx->i = 1; + break; + case 1: + ctx->i = 32; + break; + } + return 0; +} + +static __u64 for_each_map_elem_cb(struct bpf_map *map, __u32 *key, __u64 *val, void *data) +{ + return oob_state_machine(data); +} + +SEC("?raw_tp") +__failure __msg("invalid access to map value, value_size=2 off=32 size=1") +int unsafe_for_each_map_elem(void *unused) +{ + struct num_context loop_ctx = { .i = 0 }; + + bpf_for_each_map_elem(&map, for_each_map_elem_cb, &loop_ctx, 0); + return choice_arr[loop_ctx.i]; +} + +static __u64 ringbuf_drain_cb(struct bpf_dynptr *dynptr, void *data) +{ + return oob_state_machine(data); +} + +SEC("?raw_tp") +__failure __msg("invalid access to map value, value_size=2 off=32 size=1") +int unsafe_ringbuf_drain(void *unused) +{ + struct num_context loop_ctx = { .i = 0 }; + + bpf_user_ringbuf_drain(&ringbuf, ringbuf_drain_cb, &loop_ctx, 0); + return choice_arr[loop_ctx.i]; +} + +static __u64 find_vma_cb(struct task_struct *task, struct vm_area_struct *vma, void *data) +{ + return oob_state_machine(data); +} + +SEC("?raw_tp") +__failure __msg("invalid access to map value, value_size=2 off=32 size=1") +int unsafe_find_vma(void *unused) +{ + struct task_struct *task = bpf_get_current_task_btf(); + struct num_context loop_ctx = { .i = 0 }; + + bpf_find_vma(task, 0, find_vma_cb, &loop_ctx, 0); + return choice_arr[loop_ctx.i]; +} + +static int iter_limit_cb(__u32 idx, struct num_context *ctx) +{ + ctx->i++; + return 0; +} + +SEC("?raw_tp") +__success +int bpf_loop_iter_limit_ok(void *unused) +{ + struct num_context ctx = { .i = 0 }; + + bpf_loop(1, iter_limit_cb, &ctx, 0); + return choice_arr[ctx.i]; +} + +SEC("?raw_tp") +__failure __msg("invalid access to map value, value_size=2 off=2 size=1") +int bpf_loop_iter_limit_overflow(void *unused) +{ + struct num_context ctx = { .i = 0 }; + + bpf_loop(2, iter_limit_cb, &ctx, 0); + return choice_arr[ctx.i]; +} + +static int iter_limit_level2a_cb(__u32 idx, struct num_context *ctx) +{ + ctx->i += 100; + return 0; +} + +static int iter_limit_level2b_cb(__u32 idx, struct num_context *ctx) +{ + ctx->i += 10; + return 0; +} + +static int iter_limit_level1_cb(__u32 idx, struct num_context *ctx) +{ + ctx->i += 1; + bpf_loop(1, iter_limit_level2a_cb, ctx, 0); + bpf_loop(1, iter_limit_level2b_cb, ctx, 0); + return 0; +} + +/* Check that path visiting every callback function once had been + * reached by verifier. Variables 'ctx{1,2}i' below serve as flags, + * with each decimal digit corresponding to a callback visit marker. + */ +SEC("socket") +__success __retval(111111) +int bpf_loop_iter_limit_nested(void *unused) +{ + struct num_context ctx1 = { .i = 0 }; + struct num_context ctx2 = { .i = 0 }; + __u64 a, b, c; + + bpf_loop(1, iter_limit_level1_cb, &ctx1, 0); + bpf_loop(1, iter_limit_level1_cb, &ctx2, 0); + a = ctx1.i; + b = ctx2.i; + /* Force 'ctx1.i' and 'ctx2.i' precise. */ + c = choice_arr[(a + b) % 2]; + /* This makes 'c' zero, but neither clang nor verifier know it. */ + c /= 10; + /* Make sure that verifier does not visit 'impossible' states: + * enumerate all possible callback visit masks. + */ + if (a != 0 && a != 1 && a != 11 && a != 101 && a != 111 && + b != 0 && b != 1 && b != 11 && b != 101 && b != 111) + asm volatile ("r0 /= 0;" ::: "r0"); + return 1000 * a + b + c; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c b/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c new file mode 100644 index 0000000000..bf16b00502 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/jeq_infer_not_null.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_XSKMAP); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} map_xskmap SEC(".maps"); + +/* This is equivalent to the following program: + * + * r6 = skb->sk; + * r7 = sk_fullsock(r6); + * r0 = sk_fullsock(r6); + * if (r0 == 0) return 0; (a) + * if (r0 != r7) return 0; (b) + * *r7->type; (c) + * return 0; + * + * It is safe to dereference r7 at point (c), because of (a) and (b). + * The test verifies that relation r0 == r7 is propagated from (b) to (c). + */ +SEC("cgroup/skb") +__description("jne/jeq infer not null, PTR_TO_SOCKET_OR_NULL -> PTR_TO_SOCKET for JNE false branch") +__success __failure_unpriv __msg_unpriv("R7 pointer comparison") +__retval(0) +__naked void socket_for_jne_false_branch(void) +{ + asm volatile (" \ + /* r6 = skb->sk; */ \ + r6 = *(u64*)(r1 + %[__sk_buff_sk]); \ + /* if (r6 == 0) return 0; */ \ + if r6 == 0 goto l0_%=; \ + /* r7 = sk_fullsock(skb); */ \ + r1 = r6; \ + call %[bpf_sk_fullsock]; \ + r7 = r0; \ + /* r0 = sk_fullsock(skb); */ \ + r1 = r6; \ + call %[bpf_sk_fullsock]; \ + /* if (r0 == null) return 0; */ \ + if r0 == 0 goto l0_%=; \ + /* if (r0 == r7) r0 = *(r7->type); */ \ + if r0 != r7 goto l0_%=; /* Use ! JNE ! */\ + r0 = *(u32*)(r7 + %[bpf_sock_type]); \ +l0_%=: /* return 0 */ \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)) + : __clobber_all); +} + +/* Same as above, but verify that another branch of JNE still + * prohibits access to PTR_MAYBE_NULL. + */ +SEC("cgroup/skb") +__description("jne/jeq infer not null, PTR_TO_SOCKET_OR_NULL unchanged for JNE true branch") +__failure __msg("R7 invalid mem access 'sock_or_null'") +__failure_unpriv __msg_unpriv("R7 pointer comparison") +__naked void unchanged_for_jne_true_branch(void) +{ + asm volatile (" \ + /* r6 = skb->sk */ \ + r6 = *(u64*)(r1 + %[__sk_buff_sk]); \ + /* if (r6 == 0) return 0; */ \ + if r6 == 0 goto l0_%=; \ + /* r7 = sk_fullsock(skb); */ \ + r1 = r6; \ + call %[bpf_sk_fullsock]; \ + r7 = r0; \ + /* r0 = sk_fullsock(skb); */ \ + r1 = r6; \ + call %[bpf_sk_fullsock]; \ + /* if (r0 == null) return 0; */ \ + if r0 != 0 goto l0_%=; \ + /* if (r0 == r7) return 0; */ \ + if r0 != r7 goto l1_%=; /* Use ! JNE ! */\ + goto l0_%=; \ +l1_%=: /* r0 = *(r7->type); */ \ + r0 = *(u32*)(r7 + %[bpf_sock_type]); \ +l0_%=: /* return 0 */ \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)) + : __clobber_all); +} + +/* Same as a first test, but not null should be inferred for JEQ branch */ +SEC("cgroup/skb") +__description("jne/jeq infer not null, PTR_TO_SOCKET_OR_NULL -> PTR_TO_SOCKET for JEQ true branch") +__success __failure_unpriv __msg_unpriv("R7 pointer comparison") +__retval(0) +__naked void socket_for_jeq_true_branch(void) +{ + asm volatile (" \ + /* r6 = skb->sk; */ \ + r6 = *(u64*)(r1 + %[__sk_buff_sk]); \ + /* if (r6 == null) return 0; */ \ + if r6 == 0 goto l0_%=; \ + /* r7 = sk_fullsock(skb); */ \ + r1 = r6; \ + call %[bpf_sk_fullsock]; \ + r7 = r0; \ + /* r0 = sk_fullsock(skb); */ \ + r1 = r6; \ + call %[bpf_sk_fullsock]; \ + /* if (r0 == null) return 0; */ \ + if r0 == 0 goto l0_%=; \ + /* if (r0 != r7) return 0; */ \ + if r0 == r7 goto l1_%=; /* Use ! JEQ ! */\ + goto l0_%=; \ +l1_%=: /* r0 = *(r7->type); */ \ + r0 = *(u32*)(r7 + %[bpf_sock_type]); \ +l0_%=: /* return 0; */ \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)) + : __clobber_all); +} + +/* Same as above, but verify that another branch of JNE still + * prohibits access to PTR_MAYBE_NULL. + */ +SEC("cgroup/skb") +__description("jne/jeq infer not null, PTR_TO_SOCKET_OR_NULL unchanged for JEQ false branch") +__failure __msg("R7 invalid mem access 'sock_or_null'") +__failure_unpriv __msg_unpriv("R7 pointer comparison") +__naked void unchanged_for_jeq_false_branch(void) +{ + asm volatile (" \ + /* r6 = skb->sk; */ \ + r6 = *(u64*)(r1 + %[__sk_buff_sk]); \ + /* if (r6 == null) return 0; */ \ + if r6 == 0 goto l0_%=; \ + /* r7 = sk_fullsock(skb); */ \ + r1 = r6; \ + call %[bpf_sk_fullsock]; \ + r7 = r0; \ + /* r0 = sk_fullsock(skb); */ \ + r1 = r6; \ + call %[bpf_sk_fullsock]; \ + /* if (r0 == null) return 0; */ \ + if r0 == 0 goto l0_%=; \ + /* if (r0 != r7) r0 = *(r7->type); */ \ + if r0 == r7 goto l0_%=; /* Use ! JEQ ! */\ + r0 = *(u32*)(r7 + %[bpf_sock_type]); \ +l0_%=: /* return 0; */ \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)) + : __clobber_all); +} + +/* Maps are treated in a different branch of `mark_ptr_not_null_reg`, + * so separate test for maps case. + */ +SEC("xdp") +__description("jne/jeq infer not null, PTR_TO_MAP_VALUE_OR_NULL -> PTR_TO_MAP_VALUE") +__success __retval(0) +__naked void null_ptr_to_map_value(void) +{ + asm volatile (" \ + /* r9 = &some stack to use as key */ \ + r1 = 0; \ + *(u32*)(r10 - 8) = r1; \ + r9 = r10; \ + r9 += -8; \ + /* r8 = process local map */ \ + r8 = %[map_xskmap] ll; \ + /* r6 = map_lookup_elem(r8, r9); */ \ + r1 = r8; \ + r2 = r9; \ + call %[bpf_map_lookup_elem]; \ + r6 = r0; \ + /* r7 = map_lookup_elem(r8, r9); */ \ + r1 = r8; \ + r2 = r9; \ + call %[bpf_map_lookup_elem]; \ + r7 = r0; \ + /* if (r6 == 0) return 0; */ \ + if r6 == 0 goto l0_%=; \ + /* if (r6 != r7) return 0; */ \ + if r6 != r7 goto l0_%=; \ + /* read *r7; */ \ + r0 = *(u32*)(r7 + %[bpf_xdp_sock_queue_id]); \ +l0_%=: /* return 0; */ \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_xskmap), + __imm_const(bpf_xdp_sock_queue_id, offsetof(struct bpf_xdp_sock, queue_id)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_ld_ind.c b/tools/testing/selftests/bpf/progs/verifier_ld_ind.c new file mode 100644 index 0000000000..c925ba9a2e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_ld_ind.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/ld_ind.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "../../../include/linux/filter.h" +#include "bpf_misc.h" + +SEC("socket") +__description("ld_ind: check calling conv, r1") +__failure __msg("R1 !read_ok") +__failure_unpriv +__naked void ind_check_calling_conv_r1(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 1; \ + .8byte %[ld_ind]; \ + r0 = r1; \ + exit; \ +" : + : __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_1, -0x200000)) + : __clobber_all); +} + +SEC("socket") +__description("ld_ind: check calling conv, r2") +__failure __msg("R2 !read_ok") +__failure_unpriv +__naked void ind_check_calling_conv_r2(void) +{ + asm volatile (" \ + r6 = r1; \ + r2 = 1; \ + .8byte %[ld_ind]; \ + r0 = r2; \ + exit; \ +" : + : __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_2, -0x200000)) + : __clobber_all); +} + +SEC("socket") +__description("ld_ind: check calling conv, r3") +__failure __msg("R3 !read_ok") +__failure_unpriv +__naked void ind_check_calling_conv_r3(void) +{ + asm volatile (" \ + r6 = r1; \ + r3 = 1; \ + .8byte %[ld_ind]; \ + r0 = r3; \ + exit; \ +" : + : __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_3, -0x200000)) + : __clobber_all); +} + +SEC("socket") +__description("ld_ind: check calling conv, r4") +__failure __msg("R4 !read_ok") +__failure_unpriv +__naked void ind_check_calling_conv_r4(void) +{ + asm volatile (" \ + r6 = r1; \ + r4 = 1; \ + .8byte %[ld_ind]; \ + r0 = r4; \ + exit; \ +" : + : __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_4, -0x200000)) + : __clobber_all); +} + +SEC("socket") +__description("ld_ind: check calling conv, r5") +__failure __msg("R5 !read_ok") +__failure_unpriv +__naked void ind_check_calling_conv_r5(void) +{ + asm volatile (" \ + r6 = r1; \ + r5 = 1; \ + .8byte %[ld_ind]; \ + r0 = r5; \ + exit; \ +" : + : __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_5, -0x200000)) + : __clobber_all); +} + +SEC("socket") +__description("ld_ind: check calling conv, r7") +__success __success_unpriv __retval(1) +__naked void ind_check_calling_conv_r7(void) +{ + asm volatile (" \ + r6 = r1; \ + r7 = 1; \ + .8byte %[ld_ind]; \ + r0 = r7; \ + exit; \ +" : + : __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c new file mode 100644 index 0000000000..0c638f45aa --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18 + +SEC("socket") +__description("LDSX, S8") +__success __success_unpriv __retval(-2) +__naked void ldsx_s8(void) +{ + asm volatile (" \ + r1 = 0x3fe; \ + *(u64 *)(r10 - 8) = r1; \ + r0 = *(s8 *)(r10 - 8); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("LDSX, S16") +__success __success_unpriv __retval(-2) +__naked void ldsx_s16(void) +{ + asm volatile (" \ + r1 = 0x3fffe; \ + *(u64 *)(r10 - 8) = r1; \ + r0 = *(s16 *)(r10 - 8); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("LDSX, S32") +__success __success_unpriv __retval(-1) +__naked void ldsx_s32(void) +{ + asm volatile (" \ + r1 = 0xfffffffe; \ + *(u64 *)(r10 - 8) = r1; \ + r0 = *(s32 *)(r10 - 8); \ + r0 >>= 1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("LDSX, S8 range checking, privileged") +__log_level(2) __success __retval(1) +__msg("R1_w=scalar(smin=-128,smax=127)") +__naked void ldsx_s8_range_priv(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + *(u64 *)(r10 - 8) = r0; \ + r1 = *(s8 *)(r10 - 8); \ + /* r1 with s8 range */ \ + if r1 s> 0x7f goto l0_%=; \ + if r1 s< -0x80 goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("LDSX, S16 range checking") +__success __success_unpriv __retval(1) +__naked void ldsx_s16_range(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + *(u64 *)(r10 - 8) = r0; \ + r1 = *(s16 *)(r10 - 8); \ + /* r1 with s16 range */ \ + if r1 s> 0x7fff goto l0_%=; \ + if r1 s< -0x8000 goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("LDSX, S32 range checking") +__success __success_unpriv __retval(1) +__naked void ldsx_s32_range(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + *(u64 *)(r10 - 8) = r0; \ + r1 = *(s32 *)(r10 - 8); \ + /* r1 with s16 range */ \ + if r1 s> 0x7fffFFFF goto l0_%=; \ + if r1 s< -0x80000000 goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +#else + +SEC("socket") +__description("cpuv4 is not supported by compiler or jit, use a dummy test") +__success +int dummy_test(void) +{ + return 0; +} + +#endif + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_leak_ptr.c b/tools/testing/selftests/bpf/progs/verifier_leak_ptr.c new file mode 100644 index 0000000000..d153fbe500 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_leak_ptr.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/leak_ptr.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +SEC("socket") +__description("leak pointer into ctx 1") +__failure __msg("BPF_ATOMIC stores into R1 ctx is not allowed") +__failure_unpriv __msg_unpriv("R2 leaks addr into mem") +__naked void leak_pointer_into_ctx_1(void) +{ + asm volatile (" \ + r0 = 0; \ + *(u64*)(r1 + %[__sk_buff_cb_0]) = r0; \ + r2 = %[map_hash_8b] ll; \ + lock *(u64 *)(r1 + %[__sk_buff_cb_0]) += r2; \ + exit; \ +" : + : __imm_addr(map_hash_8b), + __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0])) + : __clobber_all); +} + +SEC("socket") +__description("leak pointer into ctx 2") +__failure __msg("BPF_ATOMIC stores into R1 ctx is not allowed") +__failure_unpriv __msg_unpriv("R10 leaks addr into mem") +__naked void leak_pointer_into_ctx_2(void) +{ + asm volatile (" \ + r0 = 0; \ + *(u64*)(r1 + %[__sk_buff_cb_0]) = r0; \ + lock *(u64 *)(r1 + %[__sk_buff_cb_0]) += r10; \ + exit; \ +" : + : __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0])) + : __clobber_all); +} + +SEC("socket") +__description("leak pointer into ctx 3") +__success __failure_unpriv __msg_unpriv("R2 leaks addr into ctx") +__retval(0) +__naked void leak_pointer_into_ctx_3(void) +{ + asm volatile (" \ + r0 = 0; \ + r2 = %[map_hash_8b] ll; \ + *(u64*)(r1 + %[__sk_buff_cb_0]) = r2; \ + exit; \ +" : + : __imm_addr(map_hash_8b), + __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0])) + : __clobber_all); +} + +SEC("socket") +__description("leak pointer into map val") +__success __failure_unpriv __msg_unpriv("R6 leaks addr into mem") +__retval(0) +__naked void leak_pointer_into_map_val(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r3 = 0; \ + *(u64*)(r0 + 0) = r3; \ + lock *(u64 *)(r0 + 0) += r6; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_loops1.c b/tools/testing/selftests/bpf/progs/verifier_loops1.c new file mode 100644 index 0000000000..71735dbf33 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_loops1.c @@ -0,0 +1,262 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/loops1.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("xdp") +__description("bounded loop, count to 4") +__success __retval(4) +__naked void bounded_loop_count_to_4(void) +{ + asm volatile (" \ + r0 = 0; \ +l0_%=: r0 += 1; \ + if r0 < 4 goto l0_%=; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tracepoint") +__description("bounded loop, count to 20") +__success +__naked void bounded_loop_count_to_20(void) +{ + asm volatile (" \ + r0 = 0; \ +l0_%=: r0 += 3; \ + if r0 < 20 goto l0_%=; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tracepoint") +__description("bounded loop, count from positive unknown to 4") +__success +__naked void from_positive_unknown_to_4(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + if r0 s< 0 goto l0_%=; \ +l1_%=: r0 += 1; \ + if r0 < 4 goto l1_%=; \ +l0_%=: exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("tracepoint") +__description("bounded loop, count from totally unknown to 4") +__success +__naked void from_totally_unknown_to_4(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ +l0_%=: r0 += 1; \ + if r0 < 4 goto l0_%=; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("tracepoint") +__description("bounded loop, count to 4 with equality") +__success +__naked void count_to_4_with_equality(void) +{ + asm volatile (" \ + r0 = 0; \ +l0_%=: r0 += 1; \ + if r0 != 4 goto l0_%=; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("bounded loop, start in the middle") +__success +__failure_unpriv __msg_unpriv("back-edge") +__naked void loop_start_in_the_middle(void) +{ + asm volatile (" \ + r0 = 0; \ + goto l0_%=; \ +l1_%=: r0 += 1; \ +l0_%=: if r0 < 4 goto l1_%=; \ + exit; \ +" ::: __clobber_all); +} + +SEC("xdp") +__description("bounded loop containing a forward jump") +__success __retval(4) +__naked void loop_containing_a_forward_jump(void) +{ + asm volatile (" \ + r0 = 0; \ +l1_%=: r0 += 1; \ + if r0 == r0 goto l0_%=; \ +l0_%=: if r0 < 4 goto l1_%=; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tracepoint") +__description("bounded loop that jumps out rather than in") +__success +__naked void jumps_out_rather_than_in(void) +{ + asm volatile (" \ + r6 = 0; \ +l1_%=: r6 += 1; \ + if r6 > 10000 goto l0_%=; \ + call %[bpf_get_prandom_u32]; \ + goto l1_%=; \ +l0_%=: exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("tracepoint") +__description("infinite loop after a conditional jump") +__failure __msg("program is too large") +__naked void loop_after_a_conditional_jump(void) +{ + asm volatile (" \ + r0 = 5; \ + if r0 < 4 goto l0_%=; \ +l1_%=: r0 += 1; \ + goto l1_%=; \ +l0_%=: exit; \ +" ::: __clobber_all); +} + +SEC("tracepoint") +__description("bounded recursion") +__failure +/* verifier limitation in detecting max stack depth */ +__msg("the call stack of 8 frames is too deep !") +__naked void bounded_recursion(void) +{ + asm volatile (" \ + r1 = 0; \ + call bounded_recursion__1; \ + exit; \ +" ::: __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void bounded_recursion__1(void) +{ + asm volatile (" \ + r1 += 1; \ + r0 = r1; \ + if r1 < 4 goto l0_%=; \ + exit; \ +l0_%=: call bounded_recursion__1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tracepoint") +__description("infinite loop in two jumps") +__failure __msg("loop detected") +__naked void infinite_loop_in_two_jumps(void) +{ + asm volatile (" \ + r0 = 0; \ +l1_%=: goto l0_%=; \ +l0_%=: if r0 < 4 goto l1_%=; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tracepoint") +__description("infinite loop: three-jump trick") +__failure __msg("loop detected") +__naked void infinite_loop_three_jump_trick(void) +{ + asm volatile (" \ + r0 = 0; \ +l2_%=: r0 += 1; \ + r0 &= 1; \ + if r0 < 2 goto l0_%=; \ + exit; \ +l0_%=: r0 += 1; \ + r0 &= 1; \ + if r0 < 2 goto l1_%=; \ + exit; \ +l1_%=: r0 += 1; \ + r0 &= 1; \ + if r0 < 2 goto l2_%=; \ + exit; \ +" ::: __clobber_all); +} + +SEC("xdp") +__description("not-taken loop with back jump to 1st insn") +__success __retval(123) +__naked void back_jump_to_1st_insn_1(void) +{ + asm volatile (" \ +l0_%=: r0 = 123; \ + if r0 == 4 goto l0_%=; \ + exit; \ +" ::: __clobber_all); +} + +SEC("xdp") +__description("taken loop with back jump to 1st insn") +__success __retval(55) +__naked void back_jump_to_1st_insn_2(void) +{ + asm volatile (" \ + r1 = 10; \ + r2 = 0; \ + call back_jump_to_1st_insn_2__1; \ + exit; \ +" ::: __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void back_jump_to_1st_insn_2__1(void) +{ + asm volatile (" \ +l0_%=: r2 += r1; \ + r1 -= 1; \ + if r1 != 0 goto l0_%=; \ + r0 = r2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("xdp") +__description("taken loop with back jump to 1st insn, 2") +__success __retval(55) +__naked void jump_to_1st_insn_2(void) +{ + asm volatile (" \ + r1 = 10; \ + r2 = 0; \ + call jump_to_1st_insn_2__1; \ + exit; \ +" ::: __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void jump_to_1st_insn_2__1(void) +{ + asm volatile (" \ +l0_%=: r2 += r1; \ + r1 -= 1; \ + if w1 != 0 goto l0_%=; \ + r0 = r2; \ + exit; \ +" ::: __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_lwt.c b/tools/testing/selftests/bpf/progs/verifier_lwt.c new file mode 100644 index 0000000000..5ab7463073 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_lwt.c @@ -0,0 +1,234 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/lwt.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("lwt_in") +__description("invalid direct packet write for LWT_IN") +__failure __msg("cannot write into packet") +__naked void packet_write_for_lwt_in(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + *(u8*)(r2 + 0) = r2; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("lwt_out") +__description("invalid direct packet write for LWT_OUT") +__failure __msg("cannot write into packet") +__naked void packet_write_for_lwt_out(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + *(u8*)(r2 + 0) = r2; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("lwt_xmit") +__description("direct packet write for LWT_XMIT") +__success __retval(0) +__naked void packet_write_for_lwt_xmit(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + *(u8*)(r2 + 0) = r2; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("lwt_in") +__description("direct packet read for LWT_IN") +__success __retval(0) +__naked void packet_read_for_lwt_in(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("lwt_out") +__description("direct packet read for LWT_OUT") +__success __retval(0) +__naked void packet_read_for_lwt_out(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("lwt_xmit") +__description("direct packet read for LWT_XMIT") +__success __retval(0) +__naked void packet_read_for_lwt_xmit(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("lwt_xmit") +__description("overlapping checks for direct packet access") +__success __retval(0) +__naked void checks_for_direct_packet_access(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r1 = r2; \ + r1 += 6; \ + if r1 > r3 goto l0_%=; \ + r0 = *(u16*)(r2 + 6); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("lwt_xmit") +__description("make headroom for LWT_XMIT") +__success __retval(0) +__naked void make_headroom_for_lwt_xmit(void) +{ + asm volatile (" \ + r6 = r1; \ + r2 = 34; \ + r3 = 0; \ + call %[bpf_skb_change_head]; \ + /* split for s390 to succeed */ \ + r1 = r6; \ + r2 = 42; \ + r3 = 0; \ + call %[bpf_skb_change_head]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_skb_change_head) + : __clobber_all); +} + +SEC("socket") +__description("invalid access of tc_classid for LWT_IN") +__failure __msg("invalid bpf_context access") +__failure_unpriv +__naked void tc_classid_for_lwt_in(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_tc_classid]); \ + exit; \ +" : + : __imm_const(__sk_buff_tc_classid, offsetof(struct __sk_buff, tc_classid)) + : __clobber_all); +} + +SEC("socket") +__description("invalid access of tc_classid for LWT_OUT") +__failure __msg("invalid bpf_context access") +__failure_unpriv +__naked void tc_classid_for_lwt_out(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_tc_classid]); \ + exit; \ +" : + : __imm_const(__sk_buff_tc_classid, offsetof(struct __sk_buff, tc_classid)) + : __clobber_all); +} + +SEC("socket") +__description("invalid access of tc_classid for LWT_XMIT") +__failure __msg("invalid bpf_context access") +__failure_unpriv +__naked void tc_classid_for_lwt_xmit(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_tc_classid]); \ + exit; \ +" : + : __imm_const(__sk_buff_tc_classid, offsetof(struct __sk_buff, tc_classid)) + : __clobber_all); +} + +SEC("lwt_in") +__description("check skb->tc_classid half load not permitted for lwt prog") +__failure __msg("invalid bpf_context access") +__naked void not_permitted_for_lwt_prog(void) +{ + asm volatile ( + "r0 = 0;" +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + "r0 = *(u16*)(r1 + %[__sk_buff_tc_classid]);" +#else + "r0 = *(u16*)(r1 + %[__imm_0]);" +#endif + "exit;" + : + : __imm_const(__imm_0, offsetof(struct __sk_buff, tc_classid) + 2), + __imm_const(__sk_buff_tc_classid, offsetof(struct __sk_buff, tc_classid)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_map_in_map.c b/tools/testing/selftests/bpf/progs/verifier_map_in_map.c new file mode 100644 index 0000000000..4eaab1468e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_map_in_map.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/map_in_map.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); + __array(values, struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); + }); +} map_in_map SEC(".maps"); + +SEC("socket") +__description("map in map access") +__success __success_unpriv __retval(0) +__naked void map_in_map_access(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_in_map] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = r0; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_in_map) + : __clobber_all); +} + +SEC("xdp") +__description("map in map state pruning") +__success __msg("processed 26 insns") +__log_level(2) __retval(0) __flag(BPF_F_TEST_STATE_FREQ) +__naked void map_in_map_state_pruning(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r6 = r10; \ + r6 += -4; \ + r2 = r6; \ + r1 = %[map_in_map] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r2 = r6; \ + r1 = r0; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l1_%=; \ + r2 = r6; \ + r1 = %[map_in_map] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l2_%=; \ + exit; \ +l2_%=: r2 = r6; \ + r1 = r0; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l1_%=; \ + exit; \ +l1_%=: r0 = *(u32*)(r0 + 0); \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_in_map) + : __clobber_all); +} + +SEC("socket") +__description("invalid inner map pointer") +__failure __msg("R1 pointer arithmetic on map_ptr prohibited") +__failure_unpriv +__naked void invalid_inner_map_pointer(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_in_map] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = r0; \ + r1 += 8; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_in_map) + : __clobber_all); +} + +SEC("socket") +__description("forgot null checking on the inner map pointer") +__failure __msg("R1 type=map_value_or_null expected=map_ptr") +__failure_unpriv +__naked void on_the_inner_map_pointer(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_in_map] ll; \ + call %[bpf_map_lookup_elem]; \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = r0; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_in_map) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_map_ptr.c b/tools/testing/selftests/bpf/progs/verifier_map_ptr.c new file mode 100644 index 0000000000..11a0791459 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_map_ptr.c @@ -0,0 +1,159 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/map_ptr.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct test_val); +} map_array_48b SEC(".maps"); + +struct other_val { + long long foo; + long long bar; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct other_val); +} map_hash_16b SEC(".maps"); + +SEC("socket") +__description("bpf_map_ptr: read with negative offset rejected") +__failure __msg("R1 is bpf_array invalid negative access: off=-8") +__failure_unpriv +__msg_unpriv("access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN") +__naked void read_with_negative_offset_rejected(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 = %[map_array_48b] ll; \ + r6 = *(u64*)(r1 - 8); \ + r0 = 1; \ + exit; \ +" : + : __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("bpf_map_ptr: write rejected") +__failure __msg("only read from bpf_array is supported") +__failure_unpriv +__msg_unpriv("access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN") +__naked void bpf_map_ptr_write_rejected(void) +{ + asm volatile (" \ + r0 = 0; \ + *(u64*)(r10 - 8) = r0; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + *(u64*)(r1 + 0) = r2; \ + r0 = 1; \ + exit; \ +" : + : __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("bpf_map_ptr: read non-existent field rejected") +__failure +__msg("cannot access ptr member ops with moff 0 in struct bpf_map with off 1 size 4") +__failure_unpriv +__msg_unpriv("access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void read_non_existent_field_rejected(void) +{ + asm volatile (" \ + r6 = 0; \ + r1 = %[map_array_48b] ll; \ + r6 = *(u32*)(r1 + 1); \ + r0 = 1; \ + exit; \ +" : + : __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("bpf_map_ptr: read ops field accepted") +__success __failure_unpriv +__msg_unpriv("access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN") +__retval(1) +__naked void ptr_read_ops_field_accepted(void) +{ + asm volatile (" \ + r6 = 0; \ + r1 = %[map_array_48b] ll; \ + r6 = *(u64*)(r1 + 0); \ + r0 = 1; \ + exit; \ +" : + : __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("bpf_map_ptr: r = 0, map_ptr = map_ptr + r") +__success __failure_unpriv +__msg_unpriv("R1 has pointer with unsupported alu operation") +__retval(0) +__naked void map_ptr_map_ptr_r(void) +{ + asm volatile (" \ + r0 = 0; \ + *(u64*)(r10 - 8) = r0; \ + r2 = r10; \ + r2 += -8; \ + r0 = 0; \ + r1 = %[map_hash_16b] ll; \ + r1 += r0; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_16b) + : __clobber_all); +} + +SEC("socket") +__description("bpf_map_ptr: r = 0, r = r + map_ptr") +__success __failure_unpriv +__msg_unpriv("R0 has pointer with unsupported alu operation") +__retval(0) +__naked void _0_r_r_map_ptr(void) +{ + asm volatile (" \ + r0 = 0; \ + *(u64*)(r10 - 8) = r0; \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + r0 = %[map_hash_16b] ll; \ + r1 += r0; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_16b) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_map_ptr_mixing.c b/tools/testing/selftests/bpf/progs/verifier_map_ptr_mixing.c new file mode 100644 index 0000000000..c5a7c1ddc5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_map_ptr_mixing.c @@ -0,0 +1,265 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/map_ptr_mixing.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct test_val); +} map_array_48b SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct test_val); +} map_hash_48b SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); + __array(values, struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); + }); +} map_in_map SEC(".maps"); + +void dummy_prog_42_socket(void); +void dummy_prog_24_socket(void); +void dummy_prog_loop1_socket(void); +void dummy_prog_loop2_socket(void); + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 4); + __uint(key_size, sizeof(int)); + __array(values, void (void)); +} map_prog1_socket SEC(".maps") = { + .values = { + [0] = (void *)&dummy_prog_42_socket, + [1] = (void *)&dummy_prog_loop1_socket, + [2] = (void *)&dummy_prog_24_socket, + }, +}; + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 8); + __uint(key_size, sizeof(int)); + __array(values, void (void)); +} map_prog2_socket SEC(".maps") = { + .values = { + [1] = (void *)&dummy_prog_loop2_socket, + [2] = (void *)&dummy_prog_24_socket, + [7] = (void *)&dummy_prog_42_socket, + }, +}; + +SEC("socket") +__auxiliary __auxiliary_unpriv +__naked void dummy_prog_42_socket(void) +{ + asm volatile ("r0 = 42; exit;"); +} + +SEC("socket") +__auxiliary __auxiliary_unpriv +__naked void dummy_prog_24_socket(void) +{ + asm volatile ("r0 = 24; exit;"); +} + +SEC("socket") +__auxiliary __auxiliary_unpriv +__naked void dummy_prog_loop1_socket(void) +{ + asm volatile (" \ + r3 = 1; \ + r2 = %[map_prog1_socket] ll; \ + call %[bpf_tail_call]; \ + r0 = 41; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket) + : __clobber_all); +} + +SEC("socket") +__auxiliary __auxiliary_unpriv +__naked void dummy_prog_loop2_socket(void) +{ + asm volatile (" \ + r3 = 1; \ + r2 = %[map_prog2_socket] ll; \ + call %[bpf_tail_call]; \ + r0 = 41; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog2_socket) + : __clobber_all); +} + +SEC("tc") +__description("calls: two calls returning different map pointers for lookup (hash, array)") +__success __retval(1) +__naked void pointers_for_lookup_hash_array(void) +{ + asm volatile (" \ + /* main prog */ \ + if r1 != 0 goto l0_%=; \ + call pointers_for_lookup_hash_array__1; \ + goto l1_%=; \ +l0_%=: call pointers_for_lookup_hash_array__2; \ +l1_%=: r1 = r0; \ + r2 = 0; \ + *(u64*)(r10 - 8) = r2; \ + r2 = r10; \ + r2 += -8; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l2_%=; \ + r1 = %[test_val_foo]; \ + *(u64*)(r0 + 0) = r1; \ + r0 = 1; \ +l2_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void pointers_for_lookup_hash_array__1(void) +{ + asm volatile (" \ + r0 = %[map_hash_48b] ll; \ + exit; \ +" : + : __imm_addr(map_hash_48b) + : __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void pointers_for_lookup_hash_array__2(void) +{ + asm volatile (" \ + r0 = %[map_array_48b] ll; \ + exit; \ +" : + : __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("tc") +__description("calls: two calls returning different map pointers for lookup (hash, map in map)") +__failure __msg("only read from bpf_array is supported") +__naked void lookup_hash_map_in_map(void) +{ + asm volatile (" \ + /* main prog */ \ + if r1 != 0 goto l0_%=; \ + call lookup_hash_map_in_map__1; \ + goto l1_%=; \ +l0_%=: call lookup_hash_map_in_map__2; \ +l1_%=: r1 = r0; \ + r2 = 0; \ + *(u64*)(r10 - 8) = r2; \ + r2 = r10; \ + r2 += -8; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l2_%=; \ + r1 = %[test_val_foo]; \ + *(u64*)(r0 + 0) = r1; \ + r0 = 1; \ +l2_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void lookup_hash_map_in_map__1(void) +{ + asm volatile (" \ + r0 = %[map_array_48b] ll; \ + exit; \ +" : + : __imm_addr(map_array_48b) + : __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void lookup_hash_map_in_map__2(void) +{ + asm volatile (" \ + r0 = %[map_in_map] ll; \ + exit; \ +" : + : __imm_addr(map_in_map) + : __clobber_all); +} + +SEC("socket") +__description("cond: two branches returning different map pointers for lookup (tail, tail)") +__success __failure_unpriv __msg_unpriv("tail_call abusing map_ptr") +__retval(42) +__naked void pointers_for_lookup_tail_tail_1(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_mark]); \ + if r6 != 0 goto l0_%=; \ + r2 = %[map_prog2_socket] ll; \ + goto l1_%=; \ +l0_%=: r2 = %[map_prog1_socket] ll; \ +l1_%=: r3 = 7; \ + call %[bpf_tail_call]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket), + __imm_addr(map_prog2_socket), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +SEC("socket") +__description("cond: two branches returning same map pointers for lookup (tail, tail)") +__success __success_unpriv __retval(42) +__naked void pointers_for_lookup_tail_tail_2(void) +{ + asm volatile (" \ + r6 = *(u32*)(r1 + %[__sk_buff_mark]); \ + if r6 == 0 goto l0_%=; \ + r2 = %[map_prog2_socket] ll; \ + goto l1_%=; \ +l0_%=: r2 = %[map_prog2_socket] ll; \ +l1_%=: r3 = 7; \ + call %[bpf_tail_call]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog2_socket), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_map_ret_val.c b/tools/testing/selftests/bpf/progs/verifier_map_ret_val.c new file mode 100644 index 0000000000..1639628b83 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_map_ret_val.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/map_ret_val.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "../../../include/linux/filter.h" +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +SEC("socket") +__description("invalid map_fd for function call") +__failure __msg("fd 0 is not pointing to valid bpf_map") +__failure_unpriv +__naked void map_fd_for_function_call(void) +{ + asm volatile (" \ + r2 = 0; \ + *(u64*)(r10 - 8) = r2; \ + r2 = r10; \ + r2 += -8; \ + .8byte %[ld_map_fd]; \ + .8byte 0; \ + call %[bpf_map_delete_elem]; \ + exit; \ +" : + : __imm(bpf_map_delete_elem), + __imm_insn(ld_map_fd, BPF_RAW_INSN(BPF_LD | BPF_DW | BPF_IMM, BPF_REG_1, BPF_PSEUDO_MAP_FD, 0, 0)) + : __clobber_all); +} + +SEC("socket") +__description("don't check return value before access") +__failure __msg("R0 invalid mem access 'map_value_or_null'") +__failure_unpriv +__naked void check_return_value_before_access(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r1 = 0; \ + *(u64*)(r0 + 0) = r1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("access memory with incorrect alignment") +__failure __msg("misaligned value access") +__failure_unpriv +__flag(BPF_F_STRICT_ALIGNMENT) +__naked void access_memory_with_incorrect_alignment_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 0; \ + *(u64*)(r0 + 4) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("sometimes access memory with incorrect alignment") +__failure __msg("R0 invalid mem access") +__msg_unpriv("R0 leaks addr") +__flag(BPF_F_STRICT_ALIGNMENT) +__naked void access_memory_with_incorrect_alignment_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 0; \ + *(u64*)(r0 + 0) = r1; \ + exit; \ +l0_%=: r1 = 1; \ + *(u64*)(r0 + 0) = r1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_masking.c b/tools/testing/selftests/bpf/progs/verifier_masking.c new file mode 100644 index 0000000000..5732cc1b4c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_masking.c @@ -0,0 +1,410 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/masking.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("socket") +__description("masking, test out of bounds 1") +__success __success_unpriv __retval(0) +__naked void test_out_of_bounds_1(void) +{ + asm volatile (" \ + w1 = 5; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 5 - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test out of bounds 2") +__success __success_unpriv __retval(0) +__naked void test_out_of_bounds_2(void) +{ + asm volatile (" \ + w1 = 1; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 1 - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test out of bounds 3") +__success __success_unpriv __retval(0) +__naked void test_out_of_bounds_3(void) +{ + asm volatile (" \ + w1 = 0xffffffff; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 0xffffffff - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test out of bounds 4") +__success __success_unpriv __retval(0) +__naked void test_out_of_bounds_4(void) +{ + asm volatile (" \ + w1 = 0xffffffff; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 1 - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test out of bounds 5") +__success __success_unpriv __retval(0) +__naked void test_out_of_bounds_5(void) +{ + asm volatile (" \ + w1 = -1; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 1 - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test out of bounds 6") +__success __success_unpriv __retval(0) +__naked void test_out_of_bounds_6(void) +{ + asm volatile (" \ + w1 = -1; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 0xffffffff - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test out of bounds 7") +__success __success_unpriv __retval(0) +__naked void test_out_of_bounds_7(void) +{ + asm volatile (" \ + r1 = 5; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 5 - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test out of bounds 8") +__success __success_unpriv __retval(0) +__naked void test_out_of_bounds_8(void) +{ + asm volatile (" \ + r1 = 1; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 1 - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test out of bounds 9") +__success __success_unpriv __retval(0) +__naked void test_out_of_bounds_9(void) +{ + asm volatile (" \ + r1 = 0xffffffff; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 0xffffffff - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test out of bounds 10") +__success __success_unpriv __retval(0) +__naked void test_out_of_bounds_10(void) +{ + asm volatile (" \ + r1 = 0xffffffff; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 1 - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test out of bounds 11") +__success __success_unpriv __retval(0) +__naked void test_out_of_bounds_11(void) +{ + asm volatile (" \ + r1 = -1; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 1 - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test out of bounds 12") +__success __success_unpriv __retval(0) +__naked void test_out_of_bounds_12(void) +{ + asm volatile (" \ + r1 = -1; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 0xffffffff - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test in bounds 1") +__success __success_unpriv __retval(4) +__naked void masking_test_in_bounds_1(void) +{ + asm volatile (" \ + w1 = 4; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 5 - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test in bounds 2") +__success __success_unpriv __retval(0) +__naked void masking_test_in_bounds_2(void) +{ + asm volatile (" \ + w1 = 0; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 0xffffffff - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test in bounds 3") +__success __success_unpriv __retval(0xfffffffe) +__naked void masking_test_in_bounds_3(void) +{ + asm volatile (" \ + w1 = 0xfffffffe; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 0xffffffff - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test in bounds 4") +__success __success_unpriv __retval(0xabcde) +__naked void masking_test_in_bounds_4(void) +{ + asm volatile (" \ + w1 = 0xabcde; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 0xabcdef - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test in bounds 5") +__success __success_unpriv __retval(0) +__naked void masking_test_in_bounds_5(void) +{ + asm volatile (" \ + w1 = 0; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 1 - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test in bounds 6") +__success __success_unpriv __retval(46) +__naked void masking_test_in_bounds_6(void) +{ + asm volatile (" \ + w1 = 46; \ + w2 = %[__imm_0]; \ + r2 -= r1; \ + r2 |= r1; \ + r2 = -r2; \ + r2 s>>= 63; \ + r1 &= r2; \ + r0 = r1; \ + exit; \ +" : + : __imm_const(__imm_0, 47 - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test in bounds 7") +__success __success_unpriv __retval(46) +__naked void masking_test_in_bounds_7(void) +{ + asm volatile (" \ + r3 = -46; \ + r3 *= -1; \ + w2 = %[__imm_0]; \ + r2 -= r3; \ + r2 |= r3; \ + r2 = -r2; \ + r2 s>>= 63; \ + r3 &= r2; \ + r0 = r3; \ + exit; \ +" : + : __imm_const(__imm_0, 47 - 1) + : __clobber_all); +} + +SEC("socket") +__description("masking, test in bounds 8") +__success __success_unpriv __retval(0) +__naked void masking_test_in_bounds_8(void) +{ + asm volatile (" \ + r3 = -47; \ + r3 *= -1; \ + w2 = %[__imm_0]; \ + r2 -= r3; \ + r2 |= r3; \ + r2 = -r2; \ + r2 s>>= 63; \ + r3 &= r2; \ + r0 = r3; \ + exit; \ +" : + : __imm_const(__imm_0, 47 - 1) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_meta_access.c b/tools/testing/selftests/bpf/progs/verifier_meta_access.c new file mode 100644 index 0000000000..d81722fb5f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_meta_access.c @@ -0,0 +1,284 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/meta_access.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("xdp") +__description("meta access, test1") +__success __retval(0) +__naked void meta_access_test1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("meta access, test2") +__failure __msg("invalid access to packet, off=-8") +__naked void meta_access_test2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r0 = r2; \ + r0 -= 8; \ + r4 = r2; \ + r4 += 8; \ + if r4 > r3 goto l0_%=; \ + r0 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("meta access, test3") +__failure __msg("invalid access to packet") +__naked void meta_access_test3(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r0 = r2; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("meta access, test4") +__failure __msg("invalid access to packet") +__naked void meta_access_test4(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r4 = *(u32*)(r1 + %[xdp_md_data]); \ + r0 = r4; \ + r0 += 8; \ + if r0 > r3 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("meta access, test5") +__failure __msg("R3 !read_ok") +__naked void meta_access_test5(void) +{ + asm volatile (" \ + r3 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r4 = *(u32*)(r1 + %[xdp_md_data]); \ + r0 = r3; \ + r0 += 8; \ + if r0 > r4 goto l0_%=; \ + r2 = -8; \ + call %[bpf_xdp_adjust_meta]; \ + r0 = *(u8*)(r3 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_xdp_adjust_meta), + __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("meta access, test6") +__failure __msg("invalid access to packet") +__naked void meta_access_test6(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r0 = r3; \ + r0 += 8; \ + r4 = r2; \ + r4 += 8; \ + if r4 > r0 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("meta access, test7") +__success __retval(0) +__naked void meta_access_test7(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r0 = r3; \ + r0 += 8; \ + r4 = r2; \ + r4 += 8; \ + if r4 > r3 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("meta access, test8") +__success __retval(0) +__naked void meta_access_test8(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r4 = r2; \ + r4 += 0xFFFF; \ + if r4 > r3 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("meta access, test9") +__failure __msg("invalid access to packet") +__naked void meta_access_test9(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r4 = r2; \ + r4 += 0xFFFF; \ + r4 += 1; \ + if r4 > r3 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("meta access, test10") +__failure __msg("invalid access to packet") +__naked void meta_access_test10(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r4 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r5 = 42; \ + r6 = 24; \ + *(u64*)(r10 - 8) = r5; \ + lock *(u64 *)(r10 - 8) += r6; \ + r5 = *(u64*)(r10 - 8); \ + if r5 > 100 goto l0_%=; \ + r3 += r5; \ + r5 = r3; \ + r6 = r2; \ + r6 += 8; \ + if r6 > r5 goto l0_%=; \ + r2 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("meta access, test11") +__success __retval(0) +__naked void meta_access_test11(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r5 = 42; \ + r6 = 24; \ + *(u64*)(r10 - 8) = r5; \ + lock *(u64 *)(r10 - 8) += r6; \ + r5 = *(u64*)(r10 - 8); \ + if r5 > 100 goto l0_%=; \ + r2 += r5; \ + r5 = r2; \ + r6 = r2; \ + r6 += 8; \ + if r6 > r3 goto l0_%=; \ + r5 = *(u8*)(r5 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("meta access, test12") +__success __retval(0) +__naked void meta_access_test12(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r4 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r5 = r3; \ + r5 += 16; \ + if r5 > r4 goto l0_%=; \ + r0 = *(u8*)(r3 + 0); \ + r5 = r2; \ + r5 += 16; \ + if r5 > r3 goto l0_%=; \ + r0 = *(u8*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c new file mode 100644 index 0000000000..3c8ac2c57b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c @@ -0,0 +1,236 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18 + +SEC("socket") +__description("MOV32SX, S8") +__success __success_unpriv __retval(0x23) +__naked void mov32sx_s8(void) +{ + asm volatile (" \ + w0 = 0xff23; \ + w0 = (s8)w0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("MOV32SX, S16") +__success __success_unpriv __retval(0xFFFFff23) +__naked void mov32sx_s16(void) +{ + asm volatile (" \ + w0 = 0xff23; \ + w0 = (s16)w0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("MOV64SX, S8") +__success __success_unpriv __retval(-2) +__naked void mov64sx_s8(void) +{ + asm volatile (" \ + r0 = 0x1fe; \ + r0 = (s8)r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("MOV64SX, S16") +__success __success_unpriv __retval(0xf23) +__naked void mov64sx_s16(void) +{ + asm volatile (" \ + r0 = 0xf0f23; \ + r0 = (s16)r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("MOV64SX, S32") +__success __success_unpriv __retval(-1) +__naked void mov64sx_s32(void) +{ + asm volatile (" \ + r0 = 0xfffffffe; \ + r0 = (s32)r0; \ + r0 >>= 1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("MOV32SX, S8, range_check") +__success __success_unpriv __retval(1) +__naked void mov32sx_s8_range(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + w1 = (s8)w0; \ + /* w1 with s8 range */ \ + if w1 s> 0x7f goto l0_%=; \ + if w1 s< -0x80 goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("MOV32SX, S16, range_check") +__success __success_unpriv __retval(1) +__naked void mov32sx_s16_range(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + w1 = (s16)w0; \ + /* w1 with s16 range */ \ + if w1 s> 0x7fff goto l0_%=; \ + if w1 s< -0x80ff goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("MOV32SX, S16, range_check 2") +__success __success_unpriv __retval(1) +__naked void mov32sx_s16_range_2(void) +{ + asm volatile (" \ + r1 = 65535; \ + w2 = (s16)w1; \ + r2 >>= 1; \ + if r2 != 0x7fffFFFF goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 0; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("MOV64SX, S8, range_check") +__success __success_unpriv __retval(1) +__naked void mov64sx_s8_range(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = (s8)r0; \ + /* r1 with s8 range */ \ + if r1 s> 0x7f goto l0_%=; \ + if r1 s< -0x80 goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("MOV64SX, S16, range_check") +__success __success_unpriv __retval(1) +__naked void mov64sx_s16_range(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = (s16)r0; \ + /* r1 with s16 range */ \ + if r1 s> 0x7fff goto l0_%=; \ + if r1 s< -0x8000 goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("MOV64SX, S32, range_check") +__success __success_unpriv __retval(1) +__naked void mov64sx_s32_range(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = (s32)r0; \ + /* r1 with s32 range */ \ + if r1 s> 0x7fffffff goto l0_%=; \ + if r1 s< -0x80000000 goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("MOV64SX, S16, R10 Sign Extension") +__failure __msg("R1 type=scalar expected=fp, pkt, pkt_meta, map_key, map_value, mem, ringbuf_mem, buf, trusted_ptr_") +__failure_unpriv __msg_unpriv("R10 sign-extension part of pointer") +__naked void mov64sx_s16_r10(void) +{ + asm volatile (" \ + r1 = 553656332; \ + *(u32 *)(r10 - 8) = r1; \ + r1 = (s16)r10; \ + r1 += -8; \ + r2 = 3; \ + if r2 <= r1 goto l0_%=; \ +l0_%=: \ + call %[bpf_trace_printk]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_trace_printk) + : __clobber_all); +} + +#else + +SEC("socket") +__description("cpuv4 is not supported by compiler or jit, use a dummy test") +__success +int dummy_test(void) +{ + return 0; +} + +#endif + +char _license[] SEC("license") = "GPL"; 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 0000000000..65bba330e7 --- /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 0000000000..353ae6da00 --- /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); +} diff --git a/tools/testing/selftests/bpf/progs/verifier_prevent_map_lookup.c b/tools/testing/selftests/bpf/progs/verifier_prevent_map_lookup.c new file mode 100644 index 0000000000..8d27c78099 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_prevent_map_lookup.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/prevent_map_lookup.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} map_stacktrace SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 8); + __uint(key_size, sizeof(int)); + __array(values, void (void)); +} map_prog2_socket SEC(".maps"); + +SEC("perf_event") +__description("prevent map lookup in stack trace") +__failure __msg("cannot pass map_type 7 into func bpf_map_lookup_elem") +__naked void map_lookup_in_stack_trace(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_stacktrace] ll; \ + call %[bpf_map_lookup_elem]; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_stacktrace) + : __clobber_all); +} + +SEC("socket") +__description("prevent map lookup in prog array") +__failure __msg("cannot pass map_type 3 into func bpf_map_lookup_elem") +__failure_unpriv +__naked void map_lookup_in_prog_array(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_prog2_socket] ll; \ + call %[bpf_map_lookup_elem]; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_prog2_socket) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c new file mode 100644 index 0000000000..f67390224a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c @@ -0,0 +1,372 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/raw_stack.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("socket") +__description("raw_stack: no skb_load_bytes") +__success +__failure_unpriv __msg_unpriv("invalid read from stack R6 off=-8 size=8") +__naked void stack_no_skb_load_bytes(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -8; \ + r3 = r6; \ + r4 = 8; \ + /* Call to skb_load_bytes() omitted. */ \ + r0 = *(u64*)(r6 + 0); \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, negative len") +__failure __msg("R4 min value is negative") +__naked void skb_load_bytes_negative_len(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -8; \ + r3 = r6; \ + r4 = -8; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_skb_load_bytes) + : __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, negative len 2") +__failure __msg("R4 min value is negative") +__naked void load_bytes_negative_len_2(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -8; \ + r3 = r6; \ + r4 = %[__imm_0]; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_skb_load_bytes), + __imm_const(__imm_0, ~0) + : __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, zero len") +__failure __msg("invalid zero-sized read") +__naked void skb_load_bytes_zero_len(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -8; \ + r3 = r6; \ + r4 = 0; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_skb_load_bytes) + : __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, no init") +__success __retval(0) +__naked void skb_load_bytes_no_init(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -8; \ + r3 = r6; \ + r4 = 8; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_skb_load_bytes) + : __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, init") +__success __retval(0) +__naked void stack_skb_load_bytes_init(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -8; \ + r3 = 0xcafe; \ + *(u64*)(r6 + 0) = r3; \ + r3 = r6; \ + r4 = 8; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_skb_load_bytes) + : __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, spilled regs around bounds") +__success __retval(0) +__naked void bytes_spilled_regs_around_bounds(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -16; \ + *(u64*)(r6 - 8) = r1; \ + *(u64*)(r6 + 8) = r1; \ + r3 = r6; \ + r4 = 8; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 - 8); \ + r2 = *(u64*)(r6 + 8); \ + r0 = *(u32*)(r0 + %[__sk_buff_mark]); \ + r2 = *(u32*)(r2 + %[__sk_buff_priority]); \ + r0 += r2; \ + exit; \ +" : + : __imm(bpf_skb_load_bytes), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)), + __imm_const(__sk_buff_priority, offsetof(struct __sk_buff, priority)) + : __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, spilled regs corruption") +__failure __msg("R0 invalid mem access 'scalar'") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void load_bytes_spilled_regs_corruption(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -8; \ + *(u64*)(r6 + 0) = r1; \ + r3 = r6; \ + r4 = 8; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 + 0); \ + r0 = *(u32*)(r0 + %[__sk_buff_mark]); \ + exit; \ +" : + : __imm(bpf_skb_load_bytes), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, spilled regs corruption 2") +__failure __msg("R3 invalid mem access 'scalar'") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void bytes_spilled_regs_corruption_2(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -16; \ + *(u64*)(r6 - 8) = r1; \ + *(u64*)(r6 + 0) = r1; \ + *(u64*)(r6 + 8) = r1; \ + r3 = r6; \ + r4 = 8; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 - 8); \ + r2 = *(u64*)(r6 + 8); \ + r3 = *(u64*)(r6 + 0); \ + r0 = *(u32*)(r0 + %[__sk_buff_mark]); \ + r2 = *(u32*)(r2 + %[__sk_buff_priority]); \ + r0 += r2; \ + r3 = *(u32*)(r3 + %[__sk_buff_pkt_type]); \ + r0 += r3; \ + exit; \ +" : + : __imm(bpf_skb_load_bytes), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)), + __imm_const(__sk_buff_pkt_type, offsetof(struct __sk_buff, pkt_type)), + __imm_const(__sk_buff_priority, offsetof(struct __sk_buff, priority)) + : __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, spilled regs + data") +__success __retval(0) +__naked void load_bytes_spilled_regs_data(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -16; \ + *(u64*)(r6 - 8) = r1; \ + *(u64*)(r6 + 0) = r1; \ + *(u64*)(r6 + 8) = r1; \ + r3 = r6; \ + r4 = 8; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 - 8); \ + r2 = *(u64*)(r6 + 8); \ + r3 = *(u64*)(r6 + 0); \ + r0 = *(u32*)(r0 + %[__sk_buff_mark]); \ + r2 = *(u32*)(r2 + %[__sk_buff_priority]); \ + r0 += r2; \ + r0 += r3; \ + exit; \ +" : + : __imm(bpf_skb_load_bytes), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)), + __imm_const(__sk_buff_priority, offsetof(struct __sk_buff, priority)) + : __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, invalid access 1") +__failure __msg("invalid indirect access to stack R3 off=-513 size=8") +__naked void load_bytes_invalid_access_1(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -513; \ + r3 = r6; \ + r4 = 8; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_skb_load_bytes) + : __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, invalid access 2") +__failure __msg("invalid indirect access to stack R3 off=-1 size=8") +__naked void load_bytes_invalid_access_2(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -1; \ + r3 = r6; \ + r4 = 8; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_skb_load_bytes) + : __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, invalid access 3") +__failure __msg("R4 min value is negative") +__naked void load_bytes_invalid_access_3(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += 0xffffffff; \ + r3 = r6; \ + r4 = 0xffffffff; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_skb_load_bytes) + : __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, invalid access 4") +__failure +__msg("R4 unbounded memory access, use 'var &= const' or 'if (var < const)'") +__naked void load_bytes_invalid_access_4(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -1; \ + r3 = r6; \ + r4 = 0x7fffffff; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_skb_load_bytes) + : __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, invalid access 5") +__failure +__msg("R4 unbounded memory access, use 'var &= const' or 'if (var < const)'") +__naked void load_bytes_invalid_access_5(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -512; \ + r3 = r6; \ + r4 = 0x7fffffff; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_skb_load_bytes) + : __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, invalid access 6") +__failure __msg("invalid zero-sized read") +__naked void load_bytes_invalid_access_6(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -512; \ + r3 = r6; \ + r4 = 0; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_skb_load_bytes) + : __clobber_all); +} + +SEC("tc") +__description("raw_stack: skb_load_bytes, large access") +__success __retval(0) +__naked void skb_load_bytes_large_access(void) +{ + asm volatile (" \ + r2 = 4; \ + r6 = r10; \ + r6 += -512; \ + r3 = r6; \ + r4 = 512; \ + call %[bpf_skb_load_bytes]; \ + r0 = *(u64*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_skb_load_bytes) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_raw_tp_writable.c b/tools/testing/selftests/bpf/progs/verifier_raw_tp_writable.c new file mode 100644 index 0000000000..14a0172e21 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_raw_tp_writable.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/raw_tp_writable.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +SEC("raw_tracepoint.w") +__description("raw_tracepoint_writable: reject variable offset") +__failure +__msg("R6 invalid variable buffer offset: off=0, var_off=(0x0; 0xffffffff)") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void tracepoint_writable_reject_variable_offset(void) +{ + asm volatile (" \ + /* r6 is our tp buffer */ \ + r6 = *(u64*)(r1 + 0); \ + r1 = %[map_hash_8b] ll; \ + /* move the key (== 0) to r10-8 */ \ + w0 = 0; \ + r2 = r10; \ + r2 += -8; \ + *(u64*)(r2 + 0) = r0; \ + /* lookup in the map */ \ + call %[bpf_map_lookup_elem]; \ + /* exit clean if null */ \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: /* shift the buffer pointer to a variable location */\ + r0 = *(u32*)(r0 + 0); \ + r6 += r0; \ + /* clobber whatever's there */ \ + r7 = 4242; \ + *(u64*)(r6 + 0) = r7; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_ref_tracking.c b/tools/testing/selftests/bpf/progs/verifier_ref_tracking.c new file mode 100644 index 0000000000..c4c6da2126 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_ref_tracking.c @@ -0,0 +1,1495 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/ref_tracking.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "../../../include/linux/filter.h" +#include "bpf_misc.h" + +#define BPF_SK_LOOKUP(func) \ + /* struct bpf_sock_tuple tuple = {} */ \ + "r2 = 0;" \ + "*(u32*)(r10 - 8) = r2;" \ + "*(u64*)(r10 - 16) = r2;" \ + "*(u64*)(r10 - 24) = r2;" \ + "*(u64*)(r10 - 32) = r2;" \ + "*(u64*)(r10 - 40) = r2;" \ + "*(u64*)(r10 - 48) = r2;" \ + /* sk = func(ctx, &tuple, sizeof tuple, 0, 0) */ \ + "r2 = r10;" \ + "r2 += -48;" \ + "r3 = %[sizeof_bpf_sock_tuple];"\ + "r4 = 0;" \ + "r5 = 0;" \ + "call %[" #func "];" + +struct bpf_key {} __attribute__((preserve_access_index)); + +extern void bpf_key_put(struct bpf_key *key) __ksym; +extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym; +extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym; + +/* BTF FUNC records are not generated for kfuncs referenced + * from inline assembly. These records are necessary for + * libbpf to link the program. The function below is a hack + * to ensure that BTF FUNC records are generated. + */ +void __kfunc_btf_root(void) +{ + bpf_key_put(0); + bpf_lookup_system_key(0); + bpf_lookup_user_key(0, 0); +} + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct test_val); +} map_array_48b SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 4096); +} map_ringbuf SEC(".maps"); + +void dummy_prog_42_tc(void); +void dummy_prog_24_tc(void); +void dummy_prog_loop1_tc(void); + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 4); + __uint(key_size, sizeof(int)); + __array(values, void (void)); +} map_prog1_tc SEC(".maps") = { + .values = { + [0] = (void *)&dummy_prog_42_tc, + [1] = (void *)&dummy_prog_loop1_tc, + [2] = (void *)&dummy_prog_24_tc, + }, +}; + +SEC("tc") +__auxiliary +__naked void dummy_prog_42_tc(void) +{ + asm volatile ("r0 = 42; exit;"); +} + +SEC("tc") +__auxiliary +__naked void dummy_prog_24_tc(void) +{ + asm volatile ("r0 = 24; exit;"); +} + +SEC("tc") +__auxiliary +__naked void dummy_prog_loop1_tc(void) +{ + asm volatile (" \ + r3 = 1; \ + r2 = %[map_prog1_tc] ll; \ + call %[bpf_tail_call]; \ + r0 = 41; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_tc) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: leak potential reference") +__failure __msg("Unreleased reference") +__naked void reference_tracking_leak_potential_reference(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r6 = r0; /* leak reference */ \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: leak potential reference to sock_common") +__failure __msg("Unreleased reference") +__naked void potential_reference_to_sock_common_1(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_skc_lookup_tcp) +" r6 = r0; /* leak reference */ \ + exit; \ +" : + : __imm(bpf_skc_lookup_tcp), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: leak potential reference on stack") +__failure __msg("Unreleased reference") +__naked void leak_potential_reference_on_stack(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r4 = r10; \ + r4 += -8; \ + *(u64*)(r4 + 0) = r0; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: leak potential reference on stack 2") +__failure __msg("Unreleased reference") +__naked void potential_reference_on_stack_2(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r4 = r10; \ + r4 += -8; \ + *(u64*)(r4 + 0) = r0; \ + r0 = 0; \ + r1 = 0; \ + *(u64*)(r4 + 0) = r1; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: zero potential reference") +__failure __msg("Unreleased reference") +__naked void reference_tracking_zero_potential_reference(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r0 = 0; /* leak reference */ \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: zero potential reference to sock_common") +__failure __msg("Unreleased reference") +__naked void potential_reference_to_sock_common_2(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_skc_lookup_tcp) +" r0 = 0; /* leak reference */ \ + exit; \ +" : + : __imm(bpf_skc_lookup_tcp), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: copy and zero potential references") +__failure __msg("Unreleased reference") +__naked void copy_and_zero_potential_references(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r7 = r0; \ + r0 = 0; \ + r7 = 0; /* leak reference */ \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("lsm.s/bpf") +__description("reference tracking: acquire/release user key reference") +__success +__naked void acquire_release_user_key_reference(void) +{ + asm volatile (" \ + r1 = -3; \ + r2 = 0; \ + call %[bpf_lookup_user_key]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + call %[bpf_key_put]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_key_put), + __imm(bpf_lookup_user_key) + : __clobber_all); +} + +SEC("lsm.s/bpf") +__description("reference tracking: acquire/release system key reference") +__success +__naked void acquire_release_system_key_reference(void) +{ + asm volatile (" \ + r1 = 1; \ + call %[bpf_lookup_system_key]; \ + if r0 == 0 goto l0_%=; \ + r1 = r0; \ + call %[bpf_key_put]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_key_put), + __imm(bpf_lookup_system_key) + : __clobber_all); +} + +SEC("lsm.s/bpf") +__description("reference tracking: release user key reference without check") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +__naked void user_key_reference_without_check(void) +{ + asm volatile (" \ + r1 = -3; \ + r2 = 0; \ + call %[bpf_lookup_user_key]; \ + r1 = r0; \ + call %[bpf_key_put]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_key_put), + __imm(bpf_lookup_user_key) + : __clobber_all); +} + +SEC("lsm.s/bpf") +__description("reference tracking: release system key reference without check") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +__naked void system_key_reference_without_check(void) +{ + asm volatile (" \ + r1 = 1; \ + call %[bpf_lookup_system_key]; \ + r1 = r0; \ + call %[bpf_key_put]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_key_put), + __imm(bpf_lookup_system_key) + : __clobber_all); +} + +SEC("lsm.s/bpf") +__description("reference tracking: release with NULL key pointer") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +__naked void release_with_null_key_pointer(void) +{ + asm volatile (" \ + r1 = 0; \ + call %[bpf_key_put]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_key_put) + : __clobber_all); +} + +SEC("lsm.s/bpf") +__description("reference tracking: leak potential reference to user key") +__failure __msg("Unreleased reference") +__naked void potential_reference_to_user_key(void) +{ + asm volatile (" \ + r1 = -3; \ + r2 = 0; \ + call %[bpf_lookup_user_key]; \ + exit; \ +" : + : __imm(bpf_lookup_user_key) + : __clobber_all); +} + +SEC("lsm.s/bpf") +__description("reference tracking: leak potential reference to system key") +__failure __msg("Unreleased reference") +__naked void potential_reference_to_system_key(void) +{ + asm volatile (" \ + r1 = 1; \ + call %[bpf_lookup_system_key]; \ + exit; \ +" : + : __imm(bpf_lookup_system_key) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: release reference without check") +__failure __msg("type=sock_or_null expected=sock") +__naked void tracking_release_reference_without_check(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" /* reference in r0 may be NULL */ \ + r1 = r0; \ + r2 = 0; \ + call %[bpf_sk_release]; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: release reference to sock_common without check") +__failure __msg("type=sock_common_or_null expected=sock") +__naked void to_sock_common_without_check(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_skc_lookup_tcp) +" /* reference in r0 may be NULL */ \ + r1 = r0; \ + r2 = 0; \ + call %[bpf_sk_release]; \ + exit; \ +" : + : __imm(bpf_sk_release), + __imm(bpf_skc_lookup_tcp), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: release reference") +__success __retval(0) +__naked void reference_tracking_release_reference(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r1 = r0; \ + if r0 == 0 goto l0_%=; \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: release reference to sock_common") +__success __retval(0) +__naked void release_reference_to_sock_common(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_skc_lookup_tcp) +" r1 = r0; \ + if r0 == 0 goto l0_%=; \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_release), + __imm(bpf_skc_lookup_tcp), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: release reference 2") +__success __retval(0) +__naked void reference_tracking_release_reference_2(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r1 = r0; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: call %[bpf_sk_release]; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: release reference twice") +__failure __msg("type=scalar expected=sock") +__naked void reference_tracking_release_reference_twice(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r1 = r0; \ + r6 = r0; \ + if r0 == 0 goto l0_%=; \ + call %[bpf_sk_release]; \ +l0_%=: r1 = r6; \ + call %[bpf_sk_release]; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: release reference twice inside branch") +__failure __msg("type=scalar expected=sock") +__naked void release_reference_twice_inside_branch(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r1 = r0; \ + r6 = r0; \ + if r0 == 0 goto l0_%=; /* goto end */ \ + call %[bpf_sk_release]; \ + r1 = r6; \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: alloc, check, free in one subbranch") +__failure __msg("Unreleased reference") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void check_free_in_one_subbranch(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 16; \ + /* if (offsetof(skb, mark) > data_len) exit; */ \ + if r0 <= r3 goto l0_%=; \ + exit; \ +l0_%=: r6 = *(u32*)(r2 + %[__sk_buff_mark]); \ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" if r6 == 0 goto l1_%=; /* mark == 0? */\ + /* Leak reference in R0 */ \ + exit; \ +l1_%=: if r0 == 0 goto l2_%=; /* sk NULL? */ \ + r1 = r0; \ + call %[bpf_sk_release]; \ +l2_%=: exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: alloc, check, free in both subbranches") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void check_free_in_both_subbranches(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 16; \ + /* if (offsetof(skb, mark) > data_len) exit; */ \ + if r0 <= r3 goto l0_%=; \ + exit; \ +l0_%=: r6 = *(u32*)(r2 + %[__sk_buff_mark]); \ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" if r6 == 0 goto l1_%=; /* mark == 0? */\ + if r0 == 0 goto l2_%=; /* sk NULL? */ \ + r1 = r0; \ + call %[bpf_sk_release]; \ +l2_%=: exit; \ +l1_%=: if r0 == 0 goto l3_%=; /* sk NULL? */ \ + r1 = r0; \ + call %[bpf_sk_release]; \ +l3_%=: exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking in call: free reference in subprog") +__success __retval(0) +__naked void call_free_reference_in_subprog(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r1 = r0; /* unchecked reference */ \ + call call_free_reference_in_subprog__1; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void call_free_reference_in_subprog__1(void) +{ + asm volatile (" \ + /* subprog 1 */ \ + r2 = r1; \ + if r2 == 0 goto l0_%=; \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_release) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking in call: free reference in subprog and outside") +__failure __msg("type=scalar expected=sock") +__naked void reference_in_subprog_and_outside(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r1 = r0; /* unchecked reference */ \ + r6 = r0; \ + call reference_in_subprog_and_outside__1; \ + r1 = r6; \ + call %[bpf_sk_release]; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void reference_in_subprog_and_outside__1(void) +{ + asm volatile (" \ + /* subprog 1 */ \ + r2 = r1; \ + if r2 == 0 goto l0_%=; \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_release) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking in call: alloc & leak reference in subprog") +__failure __msg("Unreleased reference") +__naked void alloc_leak_reference_in_subprog(void) +{ + asm volatile (" \ + r4 = r10; \ + r4 += -8; \ + call alloc_leak_reference_in_subprog__1; \ + r1 = r0; \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void alloc_leak_reference_in_subprog__1(void) +{ + asm volatile (" \ + /* subprog 1 */ \ + r6 = r4; \ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" /* spill unchecked sk_ptr into stack of caller */\ + *(u64*)(r6 + 0) = r0; \ + r1 = r0; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking in call: alloc in subprog, release outside") +__success __retval(POINTER_VALUE) +__naked void alloc_in_subprog_release_outside(void) +{ + asm volatile (" \ + r4 = r10; \ + call alloc_in_subprog_release_outside__1; \ + r1 = r0; \ + if r0 == 0 goto l0_%=; \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_release) + : __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void alloc_in_subprog_release_outside__1(void) +{ + asm volatile (" \ + /* subprog 1 */ \ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" exit; /* return sk */ \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking in call: sk_ptr leak into caller stack") +__failure __msg("Unreleased reference") +__naked void ptr_leak_into_caller_stack(void) +{ + asm volatile (" \ + r4 = r10; \ + r4 += -8; \ + call ptr_leak_into_caller_stack__1; \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void ptr_leak_into_caller_stack__1(void) +{ + asm volatile (" \ + /* subprog 1 */ \ + r5 = r10; \ + r5 += -8; \ + *(u64*)(r5 + 0) = r4; \ + call ptr_leak_into_caller_stack__2; \ + /* spill unchecked sk_ptr into stack of caller */\ + r5 = r10; \ + r5 += -8; \ + r4 = *(u64*)(r5 + 0); \ + *(u64*)(r4 + 0) = r0; \ + exit; \ +" ::: __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void ptr_leak_into_caller_stack__2(void) +{ + asm volatile (" \ + /* subprog 2 */ \ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking in call: sk_ptr spill into caller stack") +__success __retval(0) +__naked void ptr_spill_into_caller_stack(void) +{ + asm volatile (" \ + r4 = r10; \ + r4 += -8; \ + call ptr_spill_into_caller_stack__1; \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void ptr_spill_into_caller_stack__1(void) +{ + asm volatile (" \ + /* subprog 1 */ \ + r5 = r10; \ + r5 += -8; \ + *(u64*)(r5 + 0) = r4; \ + call ptr_spill_into_caller_stack__2; \ + /* spill unchecked sk_ptr into stack of caller */\ + r5 = r10; \ + r5 += -8; \ + r4 = *(u64*)(r5 + 0); \ + *(u64*)(r4 + 0) = r0; \ + if r0 == 0 goto l0_%=; \ + /* now the sk_ptr is verified, free the reference */\ + r1 = *(u64*)(r4 + 0); \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_release) + : __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void ptr_spill_into_caller_stack__2(void) +{ + asm volatile (" \ + /* subprog 2 */ \ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: allow LD_ABS") +__success __retval(0) +__naked void reference_tracking_allow_ld_abs(void) +{ + asm volatile (" \ + r6 = r1; \ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r1 = r0; \ + if r0 == 0 goto l0_%=; \ + call %[bpf_sk_release]; \ +l0_%=: r0 = *(u8*)skb[0]; \ + r0 = *(u16*)skb[0]; \ + r0 = *(u32*)skb[0]; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: forbid LD_ABS while holding reference") +__failure __msg("BPF_LD_[ABS|IND] cannot be mixed with socket references") +__naked void ld_abs_while_holding_reference(void) +{ + asm volatile (" \ + r6 = r1; \ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r0 = *(u8*)skb[0]; \ + r0 = *(u16*)skb[0]; \ + r0 = *(u32*)skb[0]; \ + r1 = r0; \ + if r0 == 0 goto l0_%=; \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: allow LD_IND") +__success __retval(1) +__naked void reference_tracking_allow_ld_ind(void) +{ + asm volatile (" \ + r6 = r1; \ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r1 = r0; \ + if r0 == 0 goto l0_%=; \ + call %[bpf_sk_release]; \ +l0_%=: r7 = 1; \ + .8byte %[ld_ind]; \ + r0 = r7; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)), + __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: forbid LD_IND while holding reference") +__failure __msg("BPF_LD_[ABS|IND] cannot be mixed with socket references") +__naked void ld_ind_while_holding_reference(void) +{ + asm volatile (" \ + r6 = r1; \ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r4 = r0; \ + r7 = 1; \ + .8byte %[ld_ind]; \ + r0 = r7; \ + r1 = r4; \ + if r1 == 0 goto l0_%=; \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)), + __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: check reference or tail call") +__success __retval(0) +__naked void check_reference_or_tail_call(void) +{ + asm volatile (" \ + r7 = r1; \ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" /* if (sk) bpf_sk_release() */ \ + r1 = r0; \ + if r1 != 0 goto l0_%=; \ + /* bpf_tail_call() */ \ + r3 = 3; \ + r2 = %[map_prog1_tc] ll; \ + r1 = r7; \ + call %[bpf_tail_call]; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_release]; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm(bpf_tail_call), + __imm_addr(map_prog1_tc), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: release reference then tail call") +__success __retval(0) +__naked void release_reference_then_tail_call(void) +{ + asm volatile (" \ + r7 = r1; \ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" /* if (sk) bpf_sk_release() */ \ + r1 = r0; \ + if r1 == 0 goto l0_%=; \ + call %[bpf_sk_release]; \ +l0_%=: /* bpf_tail_call() */ \ + r3 = 3; \ + r2 = %[map_prog1_tc] ll; \ + r1 = r7; \ + call %[bpf_tail_call]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm(bpf_tail_call), + __imm_addr(map_prog1_tc), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: leak possible reference over tail call") +__failure __msg("tail_call would lead to reference leak") +__naked void possible_reference_over_tail_call(void) +{ + asm volatile (" \ + r7 = r1; \ + /* Look up socket and store in REG_6 */ \ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" /* bpf_tail_call() */ \ + r6 = r0; \ + r3 = 3; \ + r2 = %[map_prog1_tc] ll; \ + r1 = r7; \ + call %[bpf_tail_call]; \ + r0 = 0; \ + /* if (sk) bpf_sk_release() */ \ + r1 = r6; \ + if r1 == 0 goto l0_%=; \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm(bpf_tail_call), + __imm_addr(map_prog1_tc), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: leak checked reference over tail call") +__failure __msg("tail_call would lead to reference leak") +__naked void checked_reference_over_tail_call(void) +{ + asm volatile (" \ + r7 = r1; \ + /* Look up socket and store in REG_6 */ \ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r6 = r0; \ + /* if (!sk) goto end */ \ + if r0 == 0 goto l0_%=; \ + /* bpf_tail_call() */ \ + r3 = 0; \ + r2 = %[map_prog1_tc] ll; \ + r1 = r7; \ + call %[bpf_tail_call]; \ + r0 = 0; \ + r1 = r6; \ +l0_%=: call %[bpf_sk_release]; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm(bpf_tail_call), + __imm_addr(map_prog1_tc), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: mangle and release sock_or_null") +__failure __msg("R1 pointer arithmetic on sock_or_null prohibited") +__naked void and_release_sock_or_null(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r1 = r0; \ + r1 += 5; \ + if r0 == 0 goto l0_%=; \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: mangle and release sock") +__failure __msg("R1 pointer arithmetic on sock prohibited") +__naked void tracking_mangle_and_release_sock(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r1 = r0; \ + if r0 == 0 goto l0_%=; \ + r1 += 5; \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: access member") +__success __retval(0) +__naked void reference_tracking_access_member(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r6 = r0; \ + if r0 == 0 goto l0_%=; \ + r2 = *(u32*)(r0 + 4); \ + r1 = r6; \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: write to member") +__failure __msg("cannot write into sock") +__naked void reference_tracking_write_to_member(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r6 = r0; \ + if r0 == 0 goto l0_%=; \ + r1 = r6; \ + r2 = 42 ll; \ + *(u32*)(r1 + %[bpf_sock_mark]) = r2; \ + r1 = r6; \ +l0_%=: call %[bpf_sk_release]; \ + r0 = 0 ll; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(bpf_sock_mark, offsetof(struct bpf_sock, mark)), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: invalid 64-bit access of member") +__failure __msg("invalid sock access off=0 size=8") +__naked void _64_bit_access_of_member(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r6 = r0; \ + if r0 == 0 goto l0_%=; \ + r2 = *(u64*)(r0 + 0); \ + r1 = r6; \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: access after release") +__failure __msg("!read_ok") +__naked void reference_tracking_access_after_release(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r1 = r0; \ + if r0 == 0 goto l0_%=; \ + call %[bpf_sk_release]; \ + r2 = *(u32*)(r1 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: direct access for lookup") +__success __retval(0) +__naked void tracking_direct_access_for_lookup(void) +{ + asm volatile (" \ + /* Check that the packet is at least 64B long */\ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r0 = r2; \ + r0 += 64; \ + if r0 > r3 goto l0_%=; \ + /* sk = sk_lookup_tcp(ctx, skb->data, ...) */ \ + r3 = %[sizeof_bpf_sock_tuple]; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_sk_lookup_tcp]; \ + r6 = r0; \ + if r0 == 0 goto l0_%=; \ + r2 = *(u32*)(r0 + 4); \ + r1 = r6; \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: use ptr from bpf_tcp_sock() after release") +__failure __msg("invalid mem access") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void bpf_tcp_sock_after_release(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + call %[bpf_tcp_sock]; \ + if r0 != 0 goto l1_%=; \ + r1 = r6; \ + call %[bpf_sk_release]; \ + exit; \ +l1_%=: r7 = r0; \ + r1 = r6; \ + call %[bpf_sk_release]; \ + r0 = *(u32*)(r7 + %[bpf_tcp_sock_snd_cwnd]); \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm(bpf_tcp_sock), + __imm_const(bpf_tcp_sock_snd_cwnd, offsetof(struct bpf_tcp_sock, snd_cwnd)), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: use ptr from bpf_sk_fullsock() after release") +__failure __msg("invalid mem access") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void bpf_sk_fullsock_after_release(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r1 = r6; \ + call %[bpf_sk_release]; \ + exit; \ +l1_%=: r7 = r0; \ + r1 = r6; \ + call %[bpf_sk_release]; \ + r0 = *(u32*)(r7 + %[bpf_sock_type]); \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: use ptr from bpf_sk_fullsock(tp) after release") +__failure __msg("invalid mem access") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void sk_fullsock_tp_after_release(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + call %[bpf_tcp_sock]; \ + if r0 != 0 goto l1_%=; \ + r1 = r6; \ + call %[bpf_sk_release]; \ + exit; \ +l1_%=: r1 = r0; \ + call %[bpf_sk_fullsock]; \ + r1 = r6; \ + r6 = r0; \ + call %[bpf_sk_release]; \ + if r6 != 0 goto l2_%=; \ + exit; \ +l2_%=: r0 = *(u32*)(r6 + %[bpf_sock_type]); \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm(bpf_tcp_sock), + __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: use sk after bpf_sk_release(tp)") +__failure __msg("invalid mem access") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void after_bpf_sk_release_tp(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + call %[bpf_tcp_sock]; \ + if r0 != 0 goto l1_%=; \ + r1 = r6; \ + call %[bpf_sk_release]; \ + exit; \ +l1_%=: r1 = r0; \ + call %[bpf_sk_release]; \ + r0 = *(u32*)(r6 + %[bpf_sock_type]); \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm(bpf_tcp_sock), + __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: use ptr from bpf_get_listener_sock() after bpf_sk_release(sk)") +__success __retval(0) +__naked void after_bpf_sk_release_sk(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + call %[bpf_get_listener_sock]; \ + if r0 != 0 goto l1_%=; \ + r1 = r6; \ + call %[bpf_sk_release]; \ + exit; \ +l1_%=: r1 = r6; \ + r6 = r0; \ + call %[bpf_sk_release]; \ + r0 = *(u32*)(r6 + %[bpf_sock_src_port]); \ + exit; \ +" : + : __imm(bpf_get_listener_sock), + __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(bpf_sock_src_port, offsetof(struct bpf_sock, src_port)), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: bpf_sk_release(listen_sk)") +__failure __msg("R1 must be referenced when passed to release function") +__naked void bpf_sk_release_listen_sk(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + call %[bpf_get_listener_sock]; \ + if r0 != 0 goto l1_%=; \ + r1 = r6; \ + call %[bpf_sk_release]; \ + exit; \ +l1_%=: r1 = r0; \ + call %[bpf_sk_release]; \ + r0 = *(u32*)(r6 + %[bpf_sock_type]); \ + r1 = r6; \ + call %[bpf_sk_release]; \ + exit; \ +" : + : __imm(bpf_get_listener_sock), + __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +/* !bpf_sk_fullsock(sk) is checked but !bpf_tcp_sock(sk) is not checked */ +SEC("tc") +__description("reference tracking: tp->snd_cwnd after bpf_sk_fullsock(sk) and bpf_tcp_sock(sk)") +__failure __msg("invalid mem access") +__naked void and_bpf_tcp_sock_sk(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + call %[bpf_sk_fullsock]; \ + r7 = r0; \ + r1 = r6; \ + call %[bpf_tcp_sock]; \ + r8 = r0; \ + if r7 != 0 goto l1_%=; \ + r1 = r6; \ + call %[bpf_sk_release]; \ + exit; \ +l1_%=: r0 = *(u32*)(r8 + %[bpf_tcp_sock_snd_cwnd]); \ + r1 = r6; \ + call %[bpf_sk_release]; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm(bpf_tcp_sock), + __imm_const(bpf_tcp_sock_snd_cwnd, offsetof(struct bpf_tcp_sock, snd_cwnd)), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: branch tracking valid pointer null comparison") +__success __retval(0) +__naked void tracking_valid_pointer_null_comparison(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r6 = r0; \ + r3 = 1; \ + if r6 != 0 goto l0_%=; \ + r3 = 0; \ +l0_%=: if r6 == 0 goto l1_%=; \ + r1 = r6; \ + call %[bpf_sk_release]; \ +l1_%=: exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: branch tracking valid pointer value comparison") +__failure __msg("Unreleased reference") +__naked void tracking_valid_pointer_value_comparison(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r6 = r0; \ + r3 = 1; \ + if r6 == 0 goto l0_%=; \ + r3 = 0; \ + if r6 == 1234 goto l0_%=; \ + r1 = r6; \ + call %[bpf_sk_release]; \ +l0_%=: exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: bpf_sk_release(btf_tcp_sock)") +__success +__retval(0) +__naked void sk_release_btf_tcp_sock(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + call %[bpf_skc_to_tcp_sock]; \ + if r0 != 0 goto l1_%=; \ + r1 = r6; \ + call %[bpf_sk_release]; \ + exit; \ +l1_%=: r1 = r0; \ + call %[bpf_sk_release]; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm(bpf_skc_to_tcp_sock), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("reference tracking: use ptr from bpf_skc_to_tcp_sock() after release") +__failure __msg("invalid mem access") +__naked void to_tcp_sock_after_release(void) +{ + asm volatile ( + BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + call %[bpf_skc_to_tcp_sock]; \ + if r0 != 0 goto l1_%=; \ + r1 = r6; \ + call %[bpf_sk_release]; \ + exit; \ +l1_%=: r7 = r0; \ + r1 = r6; \ + call %[bpf_sk_release]; \ + r0 = *(u8*)(r7 + 0); \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm(bpf_skc_to_tcp_sock), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("socket") +__description("reference tracking: try to leak released ptr reg") +__success __failure_unpriv __msg_unpriv("R8 !read_ok") +__retval(0) +__naked void to_leak_released_ptr_reg(void) +{ + asm volatile (" \ + r0 = 0; \ + *(u32*)(r10 - 4) = r0; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r9 = r0; \ + r0 = 0; \ + r1 = %[map_ringbuf] ll; \ + r2 = 8; \ + r3 = 0; \ + call %[bpf_ringbuf_reserve]; \ + if r0 != 0 goto l1_%=; \ + exit; \ +l1_%=: r8 = r0; \ + r1 = r8; \ + r2 = 0; \ + call %[bpf_ringbuf_discard]; \ + r0 = 0; \ + *(u64*)(r9 + 0) = r8; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_ringbuf_discard), + __imm(bpf_ringbuf_reserve), + __imm_addr(map_array_48b), + __imm_addr(map_ringbuf) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_reg_equal.c b/tools/testing/selftests/bpf/progs/verifier_reg_equal.c new file mode 100644 index 0000000000..dc1d8c30fb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_reg_equal.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("socket") +__description("check w reg equal if r reg upper32 bits 0") +__success +__naked void subreg_equality_1(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64 *)(r10 - 8) = r0; \ + r2 = *(u32 *)(r10 - 8); \ + /* At this point upper 4-bytes of r2 are 0, \ + * thus insn w3 = w2 should propagate reg id, \ + * and w2 < 9 comparison would also propagate \ + * the range for r3. \ + */ \ + w3 = w2; \ + if w2 < 9 goto l0_%=; \ + exit; \ +l0_%=: if r3 < 9 goto l1_%=; \ + /* r1 read is illegal at this point */ \ + r0 -= r1; \ +l1_%=: exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("socket") +__description("check w reg not equal if r reg upper32 bits not 0") +__failure __msg("R1 !read_ok") +__naked void subreg_equality_2(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + r2 = r0; \ + /* Upper 4-bytes of r2 may not be 0, thus insn \ + * w3 = w2 should not propagate reg id, and \ + * w2 < 9 comparison should not propagate \ + * the range for r3 either. \ + */ \ + w3 = w2; \ + if w2 < 9 goto l0_%=; \ + exit; \ +l0_%=: if r3 < 9 goto l1_%=; \ + /* r1 read is illegal at this point */ \ + r0 -= r1; \ +l1_%=: exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_regalloc.c b/tools/testing/selftests/bpf/progs/verifier_regalloc.c new file mode 100644 index 0000000000..ee5ddea87c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_regalloc.c @@ -0,0 +1,364 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/regalloc.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct test_val); +} map_hash_48b SEC(".maps"); + +SEC("tracepoint") +__description("regalloc basic") +__success __flag(BPF_F_ANY_ALIGNMENT) +__naked void regalloc_basic(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r7 = r0; \ + call %[bpf_get_prandom_u32]; \ + r2 = r0; \ + if r0 s> 20 goto l0_%=; \ + if r2 s< 0 goto l0_%=; \ + r7 += r0; \ + r7 += r2; \ + r0 = *(u64*)(r7 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("regalloc negative") +__failure __msg("invalid access to map value, value_size=48 off=48 size=1") +__naked void regalloc_negative(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r7 = r0; \ + call %[bpf_get_prandom_u32]; \ + r2 = r0; \ + if r0 s> 24 goto l0_%=; \ + if r2 s< 0 goto l0_%=; \ + r7 += r0; \ + r7 += r2; \ + r0 = *(u8*)(r7 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("regalloc src_reg mark") +__success __flag(BPF_F_ANY_ALIGNMENT) +__naked void regalloc_src_reg_mark(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r7 = r0; \ + call %[bpf_get_prandom_u32]; \ + r2 = r0; \ + if r0 s> 20 goto l0_%=; \ + r3 = 0; \ + if r3 s>= r2 goto l0_%=; \ + r7 += r0; \ + r7 += r2; \ + r0 = *(u64*)(r7 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("regalloc src_reg negative") +__failure __msg("invalid access to map value, value_size=48 off=44 size=8") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void regalloc_src_reg_negative(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r7 = r0; \ + call %[bpf_get_prandom_u32]; \ + r2 = r0; \ + if r0 s> 22 goto l0_%=; \ + r3 = 0; \ + if r3 s>= r2 goto l0_%=; \ + r7 += r0; \ + r7 += r2; \ + r0 = *(u64*)(r7 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("regalloc and spill") +__success __flag(BPF_F_ANY_ALIGNMENT) +__naked void regalloc_and_spill(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r7 = r0; \ + call %[bpf_get_prandom_u32]; \ + r2 = r0; \ + if r0 s> 20 goto l0_%=; \ + /* r0 has upper bound that should propagate into r2 */\ + *(u64*)(r10 - 8) = r2; /* spill r2 */ \ + r0 = 0; \ + r2 = 0; /* clear r0 and r2 */\ + r3 = *(u64*)(r10 - 8); /* fill r3 */ \ + if r0 s>= r3 goto l0_%=; \ + /* r3 has lower and upper bounds */ \ + r7 += r3; \ + r0 = *(u64*)(r7 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("regalloc and spill negative") +__failure __msg("invalid access to map value, value_size=48 off=48 size=8") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void regalloc_and_spill_negative(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r7 = r0; \ + call %[bpf_get_prandom_u32]; \ + r2 = r0; \ + if r0 s> 48 goto l0_%=; \ + /* r0 has upper bound that should propagate into r2 */\ + *(u64*)(r10 - 8) = r2; /* spill r2 */ \ + r0 = 0; \ + r2 = 0; /* clear r0 and r2 */\ + r3 = *(u64*)(r10 - 8); /* fill r3 */\ + if r0 s>= r3 goto l0_%=; \ + /* r3 has lower and upper bounds */ \ + r7 += r3; \ + r0 = *(u64*)(r7 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("regalloc three regs") +__success __flag(BPF_F_ANY_ALIGNMENT) +__naked void regalloc_three_regs(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r7 = r0; \ + call %[bpf_get_prandom_u32]; \ + r2 = r0; \ + r4 = r2; \ + if r0 s> 12 goto l0_%=; \ + if r2 s< 0 goto l0_%=; \ + r7 += r0; \ + r7 += r2; \ + r7 += r4; \ + r0 = *(u64*)(r7 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("tracepoint") +__description("regalloc after call") +__success __flag(BPF_F_ANY_ALIGNMENT) +__naked void regalloc_after_call(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r7 = r0; \ + call %[bpf_get_prandom_u32]; \ + r8 = r0; \ + r9 = r0; \ + call regalloc_after_call__1; \ + if r8 s> 20 goto l0_%=; \ + if r9 s< 0 goto l0_%=; \ + r7 += r8; \ + r7 += r9; \ + r0 = *(u64*)(r7 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void regalloc_after_call__1(void) +{ + asm volatile (" \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tracepoint") +__description("regalloc in callee") +__success __flag(BPF_F_ANY_ALIGNMENT) +__naked void regalloc_in_callee(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r7 = r0; \ + call %[bpf_get_prandom_u32]; \ + r1 = r0; \ + r2 = r0; \ + r3 = r7; \ + call regalloc_in_callee__1; \ +l0_%=: exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void regalloc_in_callee__1(void) +{ + asm volatile (" \ + if r1 s> 20 goto l0_%=; \ + if r2 s< 0 goto l0_%=; \ + r3 += r1; \ + r3 += r2; \ + r0 = *(u64*)(r3 + 0); \ + exit; \ +l0_%=: r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tracepoint") +__description("regalloc, spill, JEQ") +__success +__naked void regalloc_spill_jeq(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + *(u64*)(r10 - 8) = r0; /* spill r0 */ \ + if r0 == 0 goto l0_%=; \ +l0_%=: /* The verifier will walk the rest twice with r0 == 0 and r0 == map_value */\ + call %[bpf_get_prandom_u32]; \ + r2 = r0; \ + if r2 == 20 goto l1_%=; \ +l1_%=: /* The verifier will walk the rest two more times with r0 == 20 and r0 == unknown */\ + r3 = *(u64*)(r10 - 8); /* fill r3 with map_value */\ + if r3 == 0 goto l2_%=; /* skip ldx if map_value == NULL */\ + /* Buggy verifier will think that r3 == 20 here */\ + r0 = *(u64*)(r3 + 0); /* read from map_value */\ +l2_%=: exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_ringbuf.c b/tools/testing/selftests/bpf/progs/verifier_ringbuf.c new file mode 100644 index 0000000000..ae1d521f32 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_ringbuf.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/ringbuf.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 4096); +} map_ringbuf SEC(".maps"); + +SEC("socket") +__description("ringbuf: invalid reservation offset 1") +__failure __msg("R1 must have zero offset when passed to release func") +__failure_unpriv +__naked void ringbuf_invalid_reservation_offset_1(void) +{ + asm volatile (" \ + /* reserve 8 byte ringbuf memory */ \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r1 = %[map_ringbuf] ll; \ + r2 = 8; \ + r3 = 0; \ + call %[bpf_ringbuf_reserve]; \ + /* store a pointer to the reserved memory in R6 */\ + r6 = r0; \ + /* check whether the reservation was successful */\ + if r0 == 0 goto l0_%=; \ + /* spill R6(mem) into the stack */ \ + *(u64*)(r10 - 8) = r6; \ + /* fill it back in R7 */ \ + r7 = *(u64*)(r10 - 8); \ + /* should be able to access *(R7) = 0 */ \ + r1 = 0; \ + *(u64*)(r7 + 0) = r1; \ + /* submit the reserved ringbuf memory */ \ + r1 = r7; \ + /* add invalid offset to reserved ringbuf memory */\ + r1 += 0xcafe; \ + r2 = 0; \ + call %[bpf_ringbuf_submit]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ringbuf_reserve), + __imm(bpf_ringbuf_submit), + __imm_addr(map_ringbuf) + : __clobber_all); +} + +SEC("socket") +__description("ringbuf: invalid reservation offset 2") +__failure __msg("R7 min value is outside of the allowed memory range") +__failure_unpriv +__naked void ringbuf_invalid_reservation_offset_2(void) +{ + asm volatile (" \ + /* reserve 8 byte ringbuf memory */ \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r1 = %[map_ringbuf] ll; \ + r2 = 8; \ + r3 = 0; \ + call %[bpf_ringbuf_reserve]; \ + /* store a pointer to the reserved memory in R6 */\ + r6 = r0; \ + /* check whether the reservation was successful */\ + if r0 == 0 goto l0_%=; \ + /* spill R6(mem) into the stack */ \ + *(u64*)(r10 - 8) = r6; \ + /* fill it back in R7 */ \ + r7 = *(u64*)(r10 - 8); \ + /* add invalid offset to reserved ringbuf memory */\ + r7 += 0xcafe; \ + /* should be able to access *(R7) = 0 */ \ + r1 = 0; \ + *(u64*)(r7 + 0) = r1; \ + /* submit the reserved ringbuf memory */ \ + r1 = r7; \ + r2 = 0; \ + call %[bpf_ringbuf_submit]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ringbuf_reserve), + __imm(bpf_ringbuf_submit), + __imm_addr(map_ringbuf) + : __clobber_all); +} + +SEC("xdp") +__description("ringbuf: check passing rb mem to helpers") +__success __retval(0) +__naked void passing_rb_mem_to_helpers(void) +{ + asm volatile (" \ + r6 = r1; \ + /* reserve 8 byte ringbuf memory */ \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r1 = %[map_ringbuf] ll; \ + r2 = 8; \ + r3 = 0; \ + call %[bpf_ringbuf_reserve]; \ + r7 = r0; \ + /* check whether the reservation was successful */\ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: /* pass allocated ring buffer memory to fib lookup */\ + r1 = r6; \ + r2 = r0; \ + r3 = 8; \ + r4 = 0; \ + call %[bpf_fib_lookup]; \ + /* submit the ringbuf memory */ \ + r1 = r7; \ + r2 = 0; \ + call %[bpf_ringbuf_submit]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_fib_lookup), + __imm(bpf_ringbuf_reserve), + __imm(bpf_ringbuf_submit), + __imm_addr(map_ringbuf) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_runtime_jit.c b/tools/testing/selftests/bpf/progs/verifier_runtime_jit.c new file mode 100644 index 0000000000..27ebfc1fd9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_runtime_jit.c @@ -0,0 +1,360 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/runtime_jit.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +void dummy_prog_42_socket(void); +void dummy_prog_24_socket(void); +void dummy_prog_loop1_socket(void); +void dummy_prog_loop2_socket(void); + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 4); + __uint(key_size, sizeof(int)); + __array(values, void (void)); +} map_prog1_socket SEC(".maps") = { + .values = { + [0] = (void *)&dummy_prog_42_socket, + [1] = (void *)&dummy_prog_loop1_socket, + [2] = (void *)&dummy_prog_24_socket, + }, +}; + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 8); + __uint(key_size, sizeof(int)); + __array(values, void (void)); +} map_prog2_socket SEC(".maps") = { + .values = { + [1] = (void *)&dummy_prog_loop2_socket, + [2] = (void *)&dummy_prog_24_socket, + [7] = (void *)&dummy_prog_42_socket, + }, +}; + +SEC("socket") +__auxiliary __auxiliary_unpriv +__naked void dummy_prog_42_socket(void) +{ + asm volatile ("r0 = 42; exit;"); +} + +SEC("socket") +__auxiliary __auxiliary_unpriv +__naked void dummy_prog_24_socket(void) +{ + asm volatile ("r0 = 24; exit;"); +} + +SEC("socket") +__auxiliary __auxiliary_unpriv +__naked void dummy_prog_loop1_socket(void) +{ + asm volatile (" \ + r3 = 1; \ + r2 = %[map_prog1_socket] ll; \ + call %[bpf_tail_call]; \ + r0 = 41; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket) + : __clobber_all); +} + +SEC("socket") +__auxiliary __auxiliary_unpriv +__naked void dummy_prog_loop2_socket(void) +{ + asm volatile (" \ + r3 = 1; \ + r2 = %[map_prog2_socket] ll; \ + call %[bpf_tail_call]; \ + r0 = 41; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog2_socket) + : __clobber_all); +} + +SEC("socket") +__description("runtime/jit: tail_call within bounds, prog once") +__success __success_unpriv __retval(42) +__naked void call_within_bounds_prog_once(void) +{ + asm volatile (" \ + r3 = 0; \ + r2 = %[map_prog1_socket] ll; \ + call %[bpf_tail_call]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket) + : __clobber_all); +} + +SEC("socket") +__description("runtime/jit: tail_call within bounds, prog loop") +__success __success_unpriv __retval(41) +__naked void call_within_bounds_prog_loop(void) +{ + asm volatile (" \ + r3 = 1; \ + r2 = %[map_prog1_socket] ll; \ + call %[bpf_tail_call]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket) + : __clobber_all); +} + +SEC("socket") +__description("runtime/jit: tail_call within bounds, no prog") +__success __success_unpriv __retval(1) +__naked void call_within_bounds_no_prog(void) +{ + asm volatile (" \ + r3 = 3; \ + r2 = %[map_prog1_socket] ll; \ + call %[bpf_tail_call]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket) + : __clobber_all); +} + +SEC("socket") +__description("runtime/jit: tail_call within bounds, key 2") +__success __success_unpriv __retval(24) +__naked void call_within_bounds_key_2(void) +{ + asm volatile (" \ + r3 = 2; \ + r2 = %[map_prog1_socket] ll; \ + call %[bpf_tail_call]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket) + : __clobber_all); +} + +SEC("socket") +__description("runtime/jit: tail_call within bounds, key 2 / key 2, first branch") +__success __success_unpriv __retval(24) +__naked void _2_key_2_first_branch(void) +{ + asm volatile (" \ + r0 = 13; \ + *(u8*)(r1 + %[__sk_buff_cb_0]) = r0; \ + r0 = *(u8*)(r1 + %[__sk_buff_cb_0]); \ + if r0 == 13 goto l0_%=; \ + r3 = 2; \ + r2 = %[map_prog1_socket] ll; \ + goto l1_%=; \ +l0_%=: r3 = 2; \ + r2 = %[map_prog1_socket] ll; \ +l1_%=: call %[bpf_tail_call]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket), + __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0])) + : __clobber_all); +} + +SEC("socket") +__description("runtime/jit: tail_call within bounds, key 2 / key 2, second branch") +__success __success_unpriv __retval(24) +__naked void _2_key_2_second_branch(void) +{ + asm volatile (" \ + r0 = 14; \ + *(u8*)(r1 + %[__sk_buff_cb_0]) = r0; \ + r0 = *(u8*)(r1 + %[__sk_buff_cb_0]); \ + if r0 == 13 goto l0_%=; \ + r3 = 2; \ + r2 = %[map_prog1_socket] ll; \ + goto l1_%=; \ +l0_%=: r3 = 2; \ + r2 = %[map_prog1_socket] ll; \ +l1_%=: call %[bpf_tail_call]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket), + __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0])) + : __clobber_all); +} + +SEC("socket") +__description("runtime/jit: tail_call within bounds, key 0 / key 2, first branch") +__success __success_unpriv __retval(24) +__naked void _0_key_2_first_branch(void) +{ + asm volatile (" \ + r0 = 13; \ + *(u8*)(r1 + %[__sk_buff_cb_0]) = r0; \ + r0 = *(u8*)(r1 + %[__sk_buff_cb_0]); \ + if r0 == 13 goto l0_%=; \ + r3 = 0; \ + r2 = %[map_prog1_socket] ll; \ + goto l1_%=; \ +l0_%=: r3 = 2; \ + r2 = %[map_prog1_socket] ll; \ +l1_%=: call %[bpf_tail_call]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket), + __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0])) + : __clobber_all); +} + +SEC("socket") +__description("runtime/jit: tail_call within bounds, key 0 / key 2, second branch") +__success __success_unpriv __retval(42) +__naked void _0_key_2_second_branch(void) +{ + asm volatile (" \ + r0 = 14; \ + *(u8*)(r1 + %[__sk_buff_cb_0]) = r0; \ + r0 = *(u8*)(r1 + %[__sk_buff_cb_0]); \ + if r0 == 13 goto l0_%=; \ + r3 = 0; \ + r2 = %[map_prog1_socket] ll; \ + goto l1_%=; \ +l0_%=: r3 = 2; \ + r2 = %[map_prog1_socket] ll; \ +l1_%=: call %[bpf_tail_call]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket), + __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0])) + : __clobber_all); +} + +SEC("socket") +__description("runtime/jit: tail_call within bounds, different maps, first branch") +__success __failure_unpriv __msg_unpriv("tail_call abusing map_ptr") +__retval(1) +__naked void bounds_different_maps_first_branch(void) +{ + asm volatile (" \ + r0 = 13; \ + *(u8*)(r1 + %[__sk_buff_cb_0]) = r0; \ + r0 = *(u8*)(r1 + %[__sk_buff_cb_0]); \ + if r0 == 13 goto l0_%=; \ + r3 = 0; \ + r2 = %[map_prog1_socket] ll; \ + goto l1_%=; \ +l0_%=: r3 = 0; \ + r2 = %[map_prog2_socket] ll; \ +l1_%=: call %[bpf_tail_call]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket), + __imm_addr(map_prog2_socket), + __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0])) + : __clobber_all); +} + +SEC("socket") +__description("runtime/jit: tail_call within bounds, different maps, second branch") +__success __failure_unpriv __msg_unpriv("tail_call abusing map_ptr") +__retval(42) +__naked void bounds_different_maps_second_branch(void) +{ + asm volatile (" \ + r0 = 14; \ + *(u8*)(r1 + %[__sk_buff_cb_0]) = r0; \ + r0 = *(u8*)(r1 + %[__sk_buff_cb_0]); \ + if r0 == 13 goto l0_%=; \ + r3 = 0; \ + r2 = %[map_prog1_socket] ll; \ + goto l1_%=; \ +l0_%=: r3 = 0; \ + r2 = %[map_prog2_socket] ll; \ +l1_%=: call %[bpf_tail_call]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket), + __imm_addr(map_prog2_socket), + __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0])) + : __clobber_all); +} + +SEC("socket") +__description("runtime/jit: tail_call out of bounds") +__success __success_unpriv __retval(2) +__naked void tail_call_out_of_bounds(void) +{ + asm volatile (" \ + r3 = 256; \ + r2 = %[map_prog1_socket] ll; \ + call %[bpf_tail_call]; \ + r0 = 2; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket) + : __clobber_all); +} + +SEC("socket") +__description("runtime/jit: pass negative index to tail_call") +__success __success_unpriv __retval(2) +__naked void negative_index_to_tail_call(void) +{ + asm volatile (" \ + r3 = -1; \ + r2 = %[map_prog1_socket] ll; \ + call %[bpf_tail_call]; \ + r0 = 2; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket) + : __clobber_all); +} + +SEC("socket") +__description("runtime/jit: pass > 32bit index to tail_call") +__success __success_unpriv __retval(42) +/* Verifier rewrite for unpriv skips tail call here. */ +__retval_unpriv(2) +__naked void _32bit_index_to_tail_call(void) +{ + asm volatile (" \ + r3 = 0x100000000 ll; \ + r2 = %[map_prog1_socket] ll; \ + call %[bpf_tail_call]; \ + r0 = 2; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c new file mode 100644 index 0000000000..13b29a7faa --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c @@ -0,0 +1,659 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +/* Check that precision marks propagate through scalar IDs. + * Registers r{0,1,2} have the same scalar ID at the moment when r0 is + * marked to be precise, this mark is immediately propagated to r{1,2}. + */ +SEC("socket") +__success __log_level(2) +__msg("frame0: regs=r0,r1,r2 stack= before 4: (bf) r3 = r10") +__msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0") +__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_same_state(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == r2.id */ + "r1 = r0;" + "r2 = r0;" + /* force r0 to be precise, this immediately marks r1 and r2 as + * precise as well because of shared IDs + */ + "r3 = r10;" + "r3 += r0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Same as precision_same_state, but mark propagates through state / + * parent state boundary. + */ +SEC("socket") +__success __log_level(2) +__msg("frame0: last_idx 6 first_idx 5 subseq_idx -1") +__msg("frame0: regs=r0,r1,r2 stack= before 5: (bf) r3 = r10") +__msg("frame0: parent state regs=r0,r1,r2 stack=:") +__msg("frame0: regs=r0,r1,r2 stack= before 4: (05) goto pc+0") +__msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0") +__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__msg("frame0: parent state regs=r0 stack=:") +__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_cross_state(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == r2.id */ + "r1 = r0;" + "r2 = r0;" + /* force checkpoint */ + "goto +0;" + /* force r0 to be precise, this immediately marks r1 and r2 as + * precise as well because of shared IDs + */ + "r3 = r10;" + "r3 += r0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Same as precision_same_state, but break one of the + * links, note that r1 is absent from regs=... in __msg below. + */ +SEC("socket") +__success __log_level(2) +__msg("frame0: regs=r0,r2 stack= before 5: (bf) r3 = r10") +__msg("frame0: regs=r0,r2 stack= before 4: (b7) r1 = 0") +__msg("frame0: regs=r0,r2 stack= before 3: (bf) r2 = r0") +__msg("frame0: regs=r0 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_same_state_broken_link(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == r2.id */ + "r1 = r0;" + "r2 = r0;" + /* break link for r1, this is the only line that differs + * compared to the previous test + */ + "r1 = 0;" + /* force r0 to be precise, this immediately marks r1 and r2 as + * precise as well because of shared IDs + */ + "r3 = r10;" + "r3 += r0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Same as precision_same_state_broken_link, but with state / + * parent state boundary. + */ +SEC("socket") +__success __log_level(2) +__msg("frame0: regs=r0,r2 stack= before 6: (bf) r3 = r10") +__msg("frame0: regs=r0,r2 stack= before 5: (b7) r1 = 0") +__msg("frame0: parent state regs=r0,r2 stack=:") +__msg("frame0: regs=r0,r1,r2 stack= before 4: (05) goto pc+0") +__msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0") +__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__msg("frame0: parent state regs=r0 stack=:") +__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_cross_state_broken_link(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == r2.id */ + "r1 = r0;" + "r2 = r0;" + /* force checkpoint, although link between r1 and r{0,2} is + * broken by the next statement current precision tracking + * algorithm can't react to it and propagates mark for r1 to + * the parent state. + */ + "goto +0;" + /* break link for r1, this is the only line that differs + * compared to precision_cross_state() + */ + "r1 = 0;" + /* force r0 to be precise, this immediately marks r1 and r2 as + * precise as well because of shared IDs + */ + "r3 = r10;" + "r3 += r0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Check that precision marks propagate through scalar IDs. + * Use the same scalar ID in multiple stack frames, check that + * precision information is propagated up the call stack. + */ +SEC("socket") +__success __log_level(2) +__msg("11: (0f) r2 += r1") +/* Current state */ +__msg("frame2: last_idx 11 first_idx 10 subseq_idx -1") +__msg("frame2: regs=r1 stack= before 10: (bf) r2 = r10") +__msg("frame2: parent state regs=r1 stack=") +/* frame1.r{6,7} are marked because mark_precise_scalar_ids() + * looks for all registers with frame2.r1.id in the current state + */ +__msg("frame1: parent state regs=r6,r7 stack=") +__msg("frame0: parent state regs=r6 stack=") +/* Parent state */ +__msg("frame2: last_idx 8 first_idx 8 subseq_idx 10") +__msg("frame2: regs=r1 stack= before 8: (85) call pc+1") +/* frame1.r1 is marked because of backtracking of call instruction */ +__msg("frame1: parent state regs=r1,r6,r7 stack=") +__msg("frame0: parent state regs=r6 stack=") +/* Parent state */ +__msg("frame1: last_idx 7 first_idx 6 subseq_idx 8") +__msg("frame1: regs=r1,r6,r7 stack= before 7: (bf) r7 = r1") +__msg("frame1: regs=r1,r6 stack= before 6: (bf) r6 = r1") +__msg("frame1: parent state regs=r1 stack=") +__msg("frame0: parent state regs=r6 stack=") +/* Parent state */ +__msg("frame1: last_idx 4 first_idx 4 subseq_idx 6") +__msg("frame1: regs=r1 stack= before 4: (85) call pc+1") +__msg("frame0: parent state regs=r1,r6 stack=") +/* Parent state */ +__msg("frame0: last_idx 3 first_idx 1 subseq_idx 4") +__msg("frame0: regs=r0,r1,r6 stack= before 3: (bf) r6 = r0") +__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_many_frames(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == r6.id */ + "r1 = r0;" + "r6 = r0;" + "call precision_many_frames__foo;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +static __naked __noinline __used +void precision_many_frames__foo(void) +{ + asm volatile ( + /* conflate one of the register numbers (r6) with outer frame, + * to verify that those are tracked independently + */ + "r6 = r1;" + "r7 = r1;" + "call precision_many_frames__bar;" + "exit" + ::: __clobber_all); +} + +static __naked __noinline __used +void precision_many_frames__bar(void) +{ + asm volatile ( + /* force r1 to be precise, this immediately marks: + * - bar frame r1 + * - foo frame r{1,6,7} + * - main frame r{1,6} + */ + "r2 = r10;" + "r2 += r1;" + "r0 = 0;" + "exit;" + ::: __clobber_all); +} + +/* Check that scalars with the same IDs are marked precise on stack as + * well as in registers. + */ +SEC("socket") +__success __log_level(2) +/* foo frame */ +__msg("frame1: regs=r1 stack=-8,-16 before 9: (bf) r2 = r10") +__msg("frame1: regs=r1 stack=-8,-16 before 8: (7b) *(u64 *)(r10 -16) = r1") +__msg("frame1: regs=r1 stack=-8 before 7: (7b) *(u64 *)(r10 -8) = r1") +__msg("frame1: regs=r1 stack= before 4: (85) call pc+2") +/* main frame */ +__msg("frame0: regs=r0,r1 stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r1") +__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_stack(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == fp[-8].id */ + "r1 = r0;" + "*(u64*)(r10 - 8) = r1;" + "call precision_stack__foo;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +static __naked __noinline __used +void precision_stack__foo(void) +{ + asm volatile ( + /* conflate one of the register numbers (r6) with outer frame, + * to verify that those are tracked independently + */ + "*(u64*)(r10 - 8) = r1;" + "*(u64*)(r10 - 16) = r1;" + /* force r1 to be precise, this immediately marks: + * - foo frame r1,fp{-8,-16} + * - main frame r1,fp{-8} + */ + "r2 = r10;" + "r2 += r1;" + "exit" + ::: __clobber_all); +} + +/* Use two separate scalar IDs to check that these are propagated + * independently. + */ +SEC("socket") +__success __log_level(2) +/* r{6,7} */ +__msg("11: (0f) r3 += r7") +__msg("frame0: regs=r6,r7 stack= before 10: (bf) r3 = r10") +/* ... skip some insns ... */ +__msg("frame0: regs=r6,r7 stack= before 3: (bf) r7 = r0") +__msg("frame0: regs=r0,r6 stack= before 2: (bf) r6 = r0") +/* r{8,9} */ +__msg("12: (0f) r3 += r9") +__msg("frame0: regs=r8,r9 stack= before 11: (0f) r3 += r7") +/* ... skip some insns ... */ +__msg("frame0: regs=r8,r9 stack= before 7: (bf) r9 = r0") +__msg("frame0: regs=r0,r8 stack= before 6: (bf) r8 = r0") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_two_ids(void) +{ + asm volatile ( + /* r6 = random number up to 0xff + * r6.id == r7.id + */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + "r6 = r0;" + "r7 = r0;" + /* same, but for r{8,9} */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + "r8 = r0;" + "r9 = r0;" + /* clear r0 id */ + "r0 = 0;" + /* force checkpoint */ + "goto +0;" + "r3 = r10;" + /* force r7 to be precise, this also marks r6 */ + "r3 += r7;" + /* force r9 to be precise, this also marks r8 */ + "r3 += r9;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Verify that check_ids() is used by regsafe() for scalars. + * + * r9 = ... some pointer with range X ... + * r6 = ... unbound scalar ID=a ... + * r7 = ... unbound scalar ID=b ... + * if (r6 > r7) goto +1 + * r7 = r6 + * if (r7 > X) goto exit + * r9 += r6 + * ... access memory using r9 ... + * + * The memory access is safe only if r7 is bounded, + * which is true for one branch and not true for another. + */ +SEC("socket") +__failure __msg("register with unbounded min value") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void check_ids_in_regsafe(void) +{ + asm volatile ( + /* Bump allocated stack */ + "r1 = 0;" + "*(u64*)(r10 - 8) = r1;" + /* r9 = pointer to stack */ + "r9 = r10;" + "r9 += -8;" + /* r7 = ktime_get_ns() */ + "call %[bpf_ktime_get_ns];" + "r7 = r0;" + /* r6 = ktime_get_ns() */ + "call %[bpf_ktime_get_ns];" + "r6 = r0;" + /* if r6 > r7 is an unpredictable jump */ + "if r6 > r7 goto l1_%=;" + "r7 = r6;" +"l1_%=:" + /* if r7 > 4 ...; transfers range to r6 on one execution path + * but does not transfer on another + */ + "if r7 > 4 goto l2_%=;" + /* Access memory at r9[r6], r6 is not always bounded */ + "r9 += r6;" + "r0 = *(u8*)(r9 + 0);" +"l2_%=:" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Similar to check_ids_in_regsafe. + * The l0 could be reached in two states: + * + * (1) r6{.id=A}, r7{.id=A}, r8{.id=B} + * (2) r6{.id=B}, r7{.id=A}, r8{.id=B} + * + * Where (2) is not safe, as "r7 > 4" check won't propagate range for it. + * This example would be considered safe without changes to + * mark_chain_precision() to track scalar values with equal IDs. + */ +SEC("socket") +__failure __msg("register with unbounded min value") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void check_ids_in_regsafe_2(void) +{ + asm volatile ( + /* Bump allocated stack */ + "r1 = 0;" + "*(u64*)(r10 - 8) = r1;" + /* r9 = pointer to stack */ + "r9 = r10;" + "r9 += -8;" + /* r8 = ktime_get_ns() */ + "call %[bpf_ktime_get_ns];" + "r8 = r0;" + /* r7 = ktime_get_ns() */ + "call %[bpf_ktime_get_ns];" + "r7 = r0;" + /* r6 = ktime_get_ns() */ + "call %[bpf_ktime_get_ns];" + "r6 = r0;" + /* scratch .id from r0 */ + "r0 = 0;" + /* if r6 > r7 is an unpredictable jump */ + "if r6 > r7 goto l1_%=;" + /* tie r6 and r7 .id */ + "r6 = r7;" +"l0_%=:" + /* if r7 > 4 exit(0) */ + "if r7 > 4 goto l2_%=;" + /* Access memory at r9[r6] */ + "r9 += r6;" + "r0 = *(u8*)(r9 + 0);" +"l2_%=:" + "r0 = 0;" + "exit;" +"l1_%=:" + /* tie r6 and r8 .id */ + "r6 = r8;" + "goto l0_%=;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Check that scalar IDs *are not* generated on register to register + * assignments if source register is a constant. + * + * If such IDs *are* generated the 'l1' below would be reached in + * two states: + * + * (1) r1{.id=A}, r2{.id=A} + * (2) r1{.id=C}, r2{.id=C} + * + * Thus forcing 'if r1 == r2' verification twice. + */ +SEC("socket") +__success __log_level(2) +__msg("11: (1d) if r3 == r4 goto pc+0") +__msg("frame 0: propagating r3,r4") +__msg("11: safe") +__msg("processed 15 insns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void no_scalar_id_for_const(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + /* unpredictable jump */ + "if r0 > 7 goto l0_%=;" + /* possibly generate same scalar ids for r3 and r4 */ + "r1 = 0;" + "r1 = r1;" + "r3 = r1;" + "r4 = r1;" + "goto l1_%=;" +"l0_%=:" + /* possibly generate different scalar ids for r3 and r4 */ + "r1 = 0;" + "r2 = 0;" + "r3 = r1;" + "r4 = r2;" +"l1_%=:" + /* predictable jump, marks r3 and r4 precise */ + "if r3 == r4 goto +0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Same as no_scalar_id_for_const() but for 32-bit values */ +SEC("socket") +__success __log_level(2) +__msg("11: (1e) if w3 == w4 goto pc+0") +__msg("frame 0: propagating r3,r4") +__msg("11: safe") +__msg("processed 15 insns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void no_scalar_id_for_const32(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + /* unpredictable jump */ + "if r0 > 7 goto l0_%=;" + /* possibly generate same scalar ids for r3 and r4 */ + "w1 = 0;" + "w1 = w1;" + "w3 = w1;" + "w4 = w1;" + "goto l1_%=;" +"l0_%=:" + /* possibly generate different scalar ids for r3 and r4 */ + "w1 = 0;" + "w2 = 0;" + "w3 = w1;" + "w4 = w2;" +"l1_%=:" + /* predictable jump, marks r1 and r2 precise */ + "if w3 == w4 goto +0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Check that unique scalar IDs are ignored when new verifier state is + * compared to cached verifier state. For this test: + * - cached state has no id on r1 + * - new state has a unique id on r1 + */ +SEC("socket") +__success __log_level(2) +__msg("6: (25) if r6 > 0x7 goto pc+1") +__msg("7: (57) r1 &= 255") +__msg("8: (bf) r2 = r10") +__msg("from 6 to 8: safe") +__msg("processed 12 insns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void ignore_unique_scalar_ids_cur(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + "r6 = r0;" + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* r1.id == r0.id */ + "r1 = r0;" + /* make r1.id unique */ + "r0 = 0;" + "if r6 > 7 goto l0_%=;" + /* clear r1 id, but keep the range compatible */ + "r1 &= 0xff;" +"l0_%=:" + /* get here in two states: + * - first: r1 has no id (cached state) + * - second: r1 has a unique id (should be considered equivalent) + */ + "r2 = r10;" + "r2 += r1;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Check that unique scalar IDs are ignored when new verifier state is + * compared to cached verifier state. For this test: + * - cached state has a unique id on r1 + * - new state has no id on r1 + */ +SEC("socket") +__success __log_level(2) +__msg("6: (25) if r6 > 0x7 goto pc+1") +__msg("7: (05) goto pc+1") +__msg("9: (bf) r2 = r10") +__msg("9: safe") +__msg("processed 13 insns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void ignore_unique_scalar_ids_old(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + "r6 = r0;" + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* r1.id == r0.id */ + "r1 = r0;" + /* make r1.id unique */ + "r0 = 0;" + "if r6 > 7 goto l1_%=;" + "goto l0_%=;" +"l1_%=:" + /* clear r1 id, but keep the range compatible */ + "r1 &= 0xff;" +"l0_%=:" + /* get here in two states: + * - first: r1 has a unique id (cached state) + * - second: r1 has no id (should be considered equivalent) + */ + "r2 = r10;" + "r2 += r1;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Check that two different scalar IDs in a verified state can't be + * mapped to the same scalar ID in current state. + */ +SEC("socket") +__success __log_level(2) +/* The exit instruction should be reachable from two states, + * use two matches and "processed .. insns" to ensure this. + */ +__msg("13: (95) exit") +__msg("13: (95) exit") +__msg("processed 18 insns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void two_old_ids_one_cur_id(void) +{ + asm volatile ( + /* Give unique scalar IDs to r{6,7} */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + "r6 = r0;" + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + "r7 = r0;" + "r0 = 0;" + /* Maybe make r{6,7} IDs identical */ + "if r6 > r7 goto l0_%=;" + "goto l1_%=;" +"l0_%=:" + "r6 = r7;" +"l1_%=:" + /* Mark r{6,7} precise. + * Get here in two states: + * - first: r6{.id=A}, r7{.id=B} (cached state) + * - second: r6{.id=A}, r7{.id=A} + * Currently we don't want to consider such states equivalent. + * Thus "exit;" would be verified twice. + */ + "r2 = r10;" + "r2 += r6;" + "r2 += r7;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_sdiv.c b/tools/testing/selftests/bpf/progs/verifier_sdiv.c new file mode 100644 index 0000000000..0990f88256 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_sdiv.c @@ -0,0 +1,782 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18 + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 1") +__success __success_unpriv __retval(-20) +__naked void sdiv32_non_zero_imm_1(void) +{ + asm volatile (" \ + w0 = -41; \ + w0 s/= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 2") +__success __success_unpriv __retval(-20) +__naked void sdiv32_non_zero_imm_2(void) +{ + asm volatile (" \ + w0 = 41; \ + w0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 3") +__success __success_unpriv __retval(20) +__naked void sdiv32_non_zero_imm_3(void) +{ + asm volatile (" \ + w0 = -41; \ + w0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 4") +__success __success_unpriv __retval(-21) +__naked void sdiv32_non_zero_imm_4(void) +{ + asm volatile (" \ + w0 = -42; \ + w0 s/= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 5") +__success __success_unpriv __retval(-21) +__naked void sdiv32_non_zero_imm_5(void) +{ + asm volatile (" \ + w0 = 42; \ + w0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 6") +__success __success_unpriv __retval(21) +__naked void sdiv32_non_zero_imm_6(void) +{ + asm volatile (" \ + w0 = -42; \ + w0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 7") +__success __success_unpriv __retval(21) +__naked void sdiv32_non_zero_imm_7(void) +{ + asm volatile (" \ + w0 = 42; \ + w0 s/= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 8") +__success __success_unpriv __retval(20) +__naked void sdiv32_non_zero_imm_8(void) +{ + asm volatile (" \ + w0 = 41; \ + w0 s/= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 1") +__success __success_unpriv __retval(-20) +__naked void sdiv32_non_zero_reg_1(void) +{ + asm volatile (" \ + w0 = -41; \ + w1 = 2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 2") +__success __success_unpriv __retval(-20) +__naked void sdiv32_non_zero_reg_2(void) +{ + asm volatile (" \ + w0 = 41; \ + w1 = -2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 3") +__success __success_unpriv __retval(20) +__naked void sdiv32_non_zero_reg_3(void) +{ + asm volatile (" \ + w0 = -41; \ + w1 = -2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 4") +__success __success_unpriv __retval(-21) +__naked void sdiv32_non_zero_reg_4(void) +{ + asm volatile (" \ + w0 = -42; \ + w1 = 2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 5") +__success __success_unpriv __retval(-21) +__naked void sdiv32_non_zero_reg_5(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = -2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 6") +__success __success_unpriv __retval(21) +__naked void sdiv32_non_zero_reg_6(void) +{ + asm volatile (" \ + w0 = -42; \ + w1 = -2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 7") +__success __success_unpriv __retval(21) +__naked void sdiv32_non_zero_reg_7(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = 2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 8") +__success __success_unpriv __retval(20) +__naked void sdiv32_non_zero_reg_8(void) +{ + asm volatile (" \ + w0 = 41; \ + w1 = 2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero imm divisor, check 1") +__success __success_unpriv __retval(-20) +__naked void sdiv64_non_zero_imm_1(void) +{ + asm volatile (" \ + r0 = -41; \ + r0 s/= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero imm divisor, check 2") +__success __success_unpriv __retval(-20) +__naked void sdiv64_non_zero_imm_2(void) +{ + asm volatile (" \ + r0 = 41; \ + r0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero imm divisor, check 3") +__success __success_unpriv __retval(20) +__naked void sdiv64_non_zero_imm_3(void) +{ + asm volatile (" \ + r0 = -41; \ + r0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero imm divisor, check 4") +__success __success_unpriv __retval(-21) +__naked void sdiv64_non_zero_imm_4(void) +{ + asm volatile (" \ + r0 = -42; \ + r0 s/= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero imm divisor, check 5") +__success __success_unpriv __retval(-21) +__naked void sdiv64_non_zero_imm_5(void) +{ + asm volatile (" \ + r0 = 42; \ + r0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero imm divisor, check 6") +__success __success_unpriv __retval(21) +__naked void sdiv64_non_zero_imm_6(void) +{ + asm volatile (" \ + r0 = -42; \ + r0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero reg divisor, check 1") +__success __success_unpriv __retval(-20) +__naked void sdiv64_non_zero_reg_1(void) +{ + asm volatile (" \ + r0 = -41; \ + r1 = 2; \ + r0 s/= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero reg divisor, check 2") +__success __success_unpriv __retval(-20) +__naked void sdiv64_non_zero_reg_2(void) +{ + asm volatile (" \ + r0 = 41; \ + r1 = -2; \ + r0 s/= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero reg divisor, check 3") +__success __success_unpriv __retval(20) +__naked void sdiv64_non_zero_reg_3(void) +{ + asm volatile (" \ + r0 = -41; \ + r1 = -2; \ + r0 s/= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero reg divisor, check 4") +__success __success_unpriv __retval(-21) +__naked void sdiv64_non_zero_reg_4(void) +{ + asm volatile (" \ + r0 = -42; \ + r1 = 2; \ + r0 s/= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero reg divisor, check 5") +__success __success_unpriv __retval(-21) +__naked void sdiv64_non_zero_reg_5(void) +{ + asm volatile (" \ + r0 = 42; \ + r1 = -2; \ + r0 s/= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero reg divisor, check 6") +__success __success_unpriv __retval(21) +__naked void sdiv64_non_zero_reg_6(void) +{ + asm volatile (" \ + r0 = -42; \ + r1 = -2; \ + r0 s/= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero imm divisor, check 1") +__success __success_unpriv __retval(-1) +__naked void smod32_non_zero_imm_1(void) +{ + asm volatile (" \ + w0 = -41; \ + w0 s%%= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero imm divisor, check 2") +__success __success_unpriv __retval(1) +__naked void smod32_non_zero_imm_2(void) +{ + asm volatile (" \ + w0 = 41; \ + w0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero imm divisor, check 3") +__success __success_unpriv __retval(-1) +__naked void smod32_non_zero_imm_3(void) +{ + asm volatile (" \ + w0 = -41; \ + w0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero imm divisor, check 4") +__success __success_unpriv __retval(0) +__naked void smod32_non_zero_imm_4(void) +{ + asm volatile (" \ + w0 = -42; \ + w0 s%%= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero imm divisor, check 5") +__success __success_unpriv __retval(0) +__naked void smod32_non_zero_imm_5(void) +{ + asm volatile (" \ + w0 = 42; \ + w0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero imm divisor, check 6") +__success __success_unpriv __retval(0) +__naked void smod32_non_zero_imm_6(void) +{ + asm volatile (" \ + w0 = -42; \ + w0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero reg divisor, check 1") +__success __success_unpriv __retval(-1) +__naked void smod32_non_zero_reg_1(void) +{ + asm volatile (" \ + w0 = -41; \ + w1 = 2; \ + w0 s%%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero reg divisor, check 2") +__success __success_unpriv __retval(1) +__naked void smod32_non_zero_reg_2(void) +{ + asm volatile (" \ + w0 = 41; \ + w1 = -2; \ + w0 s%%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero reg divisor, check 3") +__success __success_unpriv __retval(-1) +__naked void smod32_non_zero_reg_3(void) +{ + asm volatile (" \ + w0 = -41; \ + w1 = -2; \ + w0 s%%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero reg divisor, check 4") +__success __success_unpriv __retval(0) +__naked void smod32_non_zero_reg_4(void) +{ + asm volatile (" \ + w0 = -42; \ + w1 = 2; \ + w0 s%%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero reg divisor, check 5") +__success __success_unpriv __retval(0) +__naked void smod32_non_zero_reg_5(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = -2; \ + w0 s%%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero reg divisor, check 6") +__success __success_unpriv __retval(0) +__naked void smod32_non_zero_reg_6(void) +{ + asm volatile (" \ + w0 = -42; \ + w1 = -2; \ + w0 s%%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 1") +__success __success_unpriv __retval(-1) +__naked void smod64_non_zero_imm_1(void) +{ + asm volatile (" \ + r0 = -41; \ + r0 s%%= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 2") +__success __success_unpriv __retval(1) +__naked void smod64_non_zero_imm_2(void) +{ + asm volatile (" \ + r0 = 41; \ + r0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 3") +__success __success_unpriv __retval(-1) +__naked void smod64_non_zero_imm_3(void) +{ + asm volatile (" \ + r0 = -41; \ + r0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 4") +__success __success_unpriv __retval(0) +__naked void smod64_non_zero_imm_4(void) +{ + asm volatile (" \ + r0 = -42; \ + r0 s%%= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 5") +__success __success_unpriv __retval(-0) +__naked void smod64_non_zero_imm_5(void) +{ + asm volatile (" \ + r0 = 42; \ + r0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 6") +__success __success_unpriv __retval(0) +__naked void smod64_non_zero_imm_6(void) +{ + asm volatile (" \ + r0 = -42; \ + r0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 7") +__success __success_unpriv __retval(0) +__naked void smod64_non_zero_imm_7(void) +{ + asm volatile (" \ + r0 = 42; \ + r0 s%%= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 8") +__success __success_unpriv __retval(1) +__naked void smod64_non_zero_imm_8(void) +{ + asm volatile (" \ + r0 = 41; \ + r0 s%%= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 1") +__success __success_unpriv __retval(-1) +__naked void smod64_non_zero_reg_1(void) +{ + asm volatile (" \ + r0 = -41; \ + r1 = 2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 2") +__success __success_unpriv __retval(1) +__naked void smod64_non_zero_reg_2(void) +{ + asm volatile (" \ + r0 = 41; \ + r1 = -2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 3") +__success __success_unpriv __retval(-1) +__naked void smod64_non_zero_reg_3(void) +{ + asm volatile (" \ + r0 = -41; \ + r1 = -2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 4") +__success __success_unpriv __retval(0) +__naked void smod64_non_zero_reg_4(void) +{ + asm volatile (" \ + r0 = -42; \ + r1 = 2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 5") +__success __success_unpriv __retval(0) +__naked void smod64_non_zero_reg_5(void) +{ + asm volatile (" \ + r0 = 42; \ + r1 = -2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 6") +__success __success_unpriv __retval(0) +__naked void smod64_non_zero_reg_6(void) +{ + asm volatile (" \ + r0 = -42; \ + r1 = -2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 7") +__success __success_unpriv __retval(0) +__naked void smod64_non_zero_reg_7(void) +{ + asm volatile (" \ + r0 = 42; \ + r1 = 2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 8") +__success __success_unpriv __retval(1) +__naked void smod64_non_zero_reg_8(void) +{ + asm volatile (" \ + r0 = 41; \ + r1 = 2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, zero divisor") +__success __success_unpriv __retval(0) +__naked void sdiv32_zero_divisor(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = 0; \ + w2 = -1; \ + w2 s/= w1; \ + w0 = w2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, zero divisor") +__success __success_unpriv __retval(0) +__naked void sdiv64_zero_divisor(void) +{ + asm volatile (" \ + r0 = 42; \ + r1 = 0; \ + r2 = -1; \ + r2 s/= r1; \ + r0 = r2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, zero divisor") +__success __success_unpriv __retval(-1) +__naked void smod32_zero_divisor(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = 0; \ + w2 = -1; \ + w2 s%%= w1; \ + w0 = w2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, zero divisor") +__success __success_unpriv __retval(-1) +__naked void smod64_zero_divisor(void) +{ + asm volatile (" \ + r0 = 42; \ + r1 = 0; \ + r2 = -1; \ + r2 s%%= r1; \ + r0 = r2; \ + exit; \ +" ::: __clobber_all); +} + +#else + +SEC("socket") +__description("cpuv4 is not supported by compiler or jit, use a dummy test") +__success +int dummy_test(void) +{ + return 0; +} + +#endif + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_search_pruning.c b/tools/testing/selftests/bpf/progs/verifier_search_pruning.c new file mode 100644 index 0000000000..5a14498d35 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_search_pruning.c @@ -0,0 +1,339 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/search_pruning.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct test_val); +} map_hash_48b SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +SEC("socket") +__description("pointer/scalar confusion in state equality check (way 1)") +__success __failure_unpriv __msg_unpriv("R0 leaks addr as return value") +__retval(POINTER_VALUE) +__naked void state_equality_check_way_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r0 = *(u64*)(r0 + 0); \ + goto l1_%=; \ +l0_%=: r0 = r10; \ +l1_%=: goto l2_%=; \ +l2_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("pointer/scalar confusion in state equality check (way 2)") +__success __failure_unpriv __msg_unpriv("R0 leaks addr as return value") +__retval(POINTER_VALUE) +__naked void state_equality_check_way_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + r0 = r10; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r0 + 0); \ +l1_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("lwt_in") +__description("liveness pruning and write screening") +__failure __msg("R0 !read_ok") +__naked void liveness_pruning_and_write_screening(void) +{ + asm volatile (" \ + /* Get an unknown value */ \ + r2 = *(u32*)(r1 + 0); \ + /* branch conditions teach us nothing about R2 */\ + if r2 >= 0 goto l0_%=; \ + r0 = 0; \ +l0_%=: if r2 >= 0 goto l1_%=; \ + r0 = 0; \ +l1_%=: exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("varlen_map_value_access pruning") +__failure __msg("R0 unbounded memory access") +__failure_unpriv __msg_unpriv("R0 leaks addr") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void varlen_map_value_access_pruning(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r0 + 0); \ + w2 = %[max_entries]; \ + if r2 s> r1 goto l1_%=; \ + w1 = 0; \ +l1_%=: w1 <<= 2; \ + r0 += r1; \ + goto l2_%=; \ +l2_%=: r1 = %[test_val_foo]; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(max_entries, MAX_ENTRIES), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tracepoint") +__description("search pruning: all branches should be verified (nop operation)") +__failure __msg("R6 invalid mem access 'scalar'") +__naked void should_be_verified_nop_operation(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r3 = *(u64*)(r0 + 0); \ + if r3 == 0xbeef goto l1_%=; \ + r4 = 0; \ + goto l2_%=; \ +l1_%=: r4 = 1; \ +l2_%=: *(u64*)(r10 - 16) = r4; \ + call %[bpf_ktime_get_ns]; \ + r5 = *(u64*)(r10 - 16); \ + if r5 == 0 goto l0_%=; \ + r6 = 0; \ + r1 = 0xdead; \ + *(u64*)(r6 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("search pruning: all branches should be verified (invalid stack access)") +/* in privileged mode reads from uninitialized stack locations are permitted */ +__success __failure_unpriv +__msg_unpriv("invalid read from stack off -16+0 size 8") +__retval(0) +__naked void be_verified_invalid_stack_access(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r3 = *(u64*)(r0 + 0); \ + r4 = 0; \ + if r3 == 0xbeef goto l1_%=; \ + *(u64*)(r10 - 16) = r4; \ + goto l2_%=; \ +l1_%=: *(u64*)(r10 - 24) = r4; \ +l2_%=: call %[bpf_ktime_get_ns]; \ + r5 = *(u64*)(r10 - 16); \ +l0_%=: exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("tracepoint") +__description("precision tracking for u32 spill/fill") +__failure __msg("R0 min value is outside of the allowed memory range") +__naked void tracking_for_u32_spill_fill(void) +{ + asm volatile (" \ + r7 = r1; \ + call %[bpf_get_prandom_u32]; \ + w6 = 32; \ + if r0 == 0 goto l0_%=; \ + w6 = 4; \ +l0_%=: /* Additional insns to introduce a pruning point. */\ + call %[bpf_get_prandom_u32]; \ + r3 = 0; \ + r3 = 0; \ + if r0 == 0 goto l1_%=; \ + r3 = 0; \ +l1_%=: /* u32 spill/fill */ \ + *(u32*)(r10 - 8) = r6; \ + r8 = *(u32*)(r10 - 8); \ + /* out-of-bound map value access for r6=32 */ \ + r1 = 0; \ + *(u64*)(r10 - 16) = r1; \ + r2 = r10; \ + r2 += -16; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l2_%=; \ + r0 += r8; \ + r1 = *(u32*)(r0 + 0); \ +l2_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("tracepoint") +__description("precision tracking for u32 spills, u64 fill") +__failure __msg("div by zero") +__naked void for_u32_spills_u64_fill(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r6 = r0; \ + w7 = 0xffffffff; \ + /* Additional insns to introduce a pruning point. */\ + r3 = 1; \ + r3 = 1; \ + r3 = 1; \ + r3 = 1; \ + call %[bpf_get_prandom_u32]; \ + if r0 == 0 goto l0_%=; \ + r3 = 1; \ +l0_%=: w3 /= 0; \ + /* u32 spills, u64 fill */ \ + *(u32*)(r10 - 4) = r6; \ + *(u32*)(r10 - 8) = r7; \ + r8 = *(u64*)(r10 - 8); \ + /* if r8 != X goto pc+1 r8 known in fallthrough branch */\ + if r8 != 0xffffffff goto l1_%=; \ + r3 = 1; \ +l1_%=: /* if r8 == X goto pc+1 condition always true on first\ + * traversal, so starts backtracking to mark r8 as requiring\ + * precision. r7 marked as needing precision. r6 not marked\ + * since it's not tracked. \ + */ \ + if r8 == 0xffffffff goto l2_%=; \ + /* fails if r8 correctly marked unknown after fill. */\ + w3 /= 0; \ +l2_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("allocated_stack") +__success __msg("processed 15 insns") +__success_unpriv __msg_unpriv("") __log_level(1) __retval(0) +__naked void allocated_stack(void) +{ + asm volatile (" \ + r6 = r1; \ + call %[bpf_get_prandom_u32]; \ + r7 = r0; \ + if r0 == 0 goto l0_%=; \ + r0 = 0; \ + *(u64*)(r10 - 8) = r6; \ + r6 = *(u64*)(r10 - 8); \ + *(u8*)(r10 - 9) = r7; \ + r7 = *(u8*)(r10 - 9); \ +l0_%=: if r0 != 0 goto l1_%=; \ +l1_%=: if r0 != 0 goto l2_%=; \ +l2_%=: if r0 != 0 goto l3_%=; \ +l3_%=: if r0 != 0 goto l4_%=; \ +l4_%=: exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +/* The test performs a conditional 64-bit write to a stack location + * fp[-8], this is followed by an unconditional 8-bit write to fp[-8], + * then data is read from fp[-8]. This sequence is unsafe. + * + * The test would be mistakenly marked as safe w/o dst register parent + * preservation in verifier.c:copy_register_state() function. + * + * Note the usage of BPF_F_TEST_STATE_FREQ to force creation of the + * checkpoint state after conditional 64-bit assignment. + */ + +SEC("socket") +__description("write tracking and register parent chain bug") +/* in privileged mode reads from uninitialized stack locations are permitted */ +__success __failure_unpriv +__msg_unpriv("invalid read from stack off -8+1 size 8") +__retval(0) __flag(BPF_F_TEST_STATE_FREQ) +__naked void and_register_parent_chain_bug(void) +{ + asm volatile (" \ + /* r6 = ktime_get_ns() */ \ + call %[bpf_ktime_get_ns]; \ + r6 = r0; \ + /* r0 = ktime_get_ns() */ \ + call %[bpf_ktime_get_ns]; \ + /* if r0 > r6 goto +1 */ \ + if r0 > r6 goto l0_%=; \ + /* *(u64 *)(r10 - 8) = 0xdeadbeef */ \ + r0 = 0xdeadbeef; \ + *(u64*)(r10 - 8) = r0; \ +l0_%=: r1 = 42; \ + *(u8*)(r10 - 8) = r1; \ + r2 = *(u64*)(r10 - 8); \ + /* exit(0) */ \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_sock.c b/tools/testing/selftests/bpf/progs/verifier_sock.c new file mode 100644 index 0000000000..ee76b51005 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_sock.c @@ -0,0 +1,980 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/sock.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER)) +#define offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER)) + +struct { + __uint(type, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} map_reuseport_array SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} map_sockhash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} map_sockmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_XSKMAP); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} map_xskmap SEC(".maps"); + +struct val { + int cnt; + struct bpf_spin_lock l; +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(max_entries, 0); + __type(key, int); + __type(value, struct val); + __uint(map_flags, BPF_F_NO_PREALLOC); +} sk_storage_map SEC(".maps"); + +SEC("cgroup/skb") +__description("skb->sk: no NULL check") +__failure __msg("invalid mem access 'sock_common_or_null'") +__failure_unpriv +__naked void skb_sk_no_null_check(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + r0 = *(u32*)(r1 + 0); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("skb->sk: sk->family [non fullsock field]") +__success __success_unpriv __retval(0) +__naked void sk_family_non_fullsock_field_1(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: r0 = *(u32*)(r1 + %[bpf_sock_family]); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_family, offsetof(struct bpf_sock, family)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("skb->sk: sk->type [fullsock field]") +__failure __msg("invalid sock_common access") +__failure_unpriv +__naked void sk_sk_type_fullsock_field_1(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: r0 = *(u32*)(r1 + %[bpf_sock_type]); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("bpf_sk_fullsock(skb->sk): no !skb->sk check") +__failure __msg("type=sock_common_or_null expected=sock_common") +__failure_unpriv +__naked void sk_no_skb_sk_check_1(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + call %[bpf_sk_fullsock]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("sk_fullsock(skb->sk): no NULL check on ret") +__failure __msg("invalid mem access 'sock_or_null'") +__failure_unpriv +__naked void no_null_check_on_ret_1(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + r0 = *(u32*)(r0 + %[bpf_sock_type]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("sk_fullsock(skb->sk): sk->type [fullsock field]") +__success __success_unpriv __retval(0) +__naked void sk_sk_type_fullsock_field_2(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r0 = *(u32*)(r0 + %[bpf_sock_type]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("sk_fullsock(skb->sk): sk->family [non fullsock field]") +__success __success_unpriv __retval(0) +__naked void sk_family_non_fullsock_field_2(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + exit; \ +l1_%=: r0 = *(u32*)(r0 + %[bpf_sock_family]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_family, offsetof(struct bpf_sock, family)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("sk_fullsock(skb->sk): sk->state [narrow load]") +__success __success_unpriv __retval(0) +__naked void sk_sk_state_narrow_load(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r0 = *(u8*)(r0 + %[bpf_sock_state]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_state, offsetof(struct bpf_sock, state)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("sk_fullsock(skb->sk): sk->dst_port [word load] (backward compatibility)") +__success __success_unpriv __retval(0) +__naked void port_word_load_backward_compatibility(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r0 = *(u32*)(r0 + %[bpf_sock_dst_port]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_dst_port, offsetof(struct bpf_sock, dst_port)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("sk_fullsock(skb->sk): sk->dst_port [half load]") +__success __success_unpriv __retval(0) +__naked void sk_dst_port_half_load(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r0 = *(u16*)(r0 + %[bpf_sock_dst_port]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_dst_port, offsetof(struct bpf_sock, dst_port)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("sk_fullsock(skb->sk): sk->dst_port [half load] (invalid)") +__failure __msg("invalid sock access") +__failure_unpriv +__naked void dst_port_half_load_invalid_1(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r0 = *(u16*)(r0 + %[__imm_0]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__imm_0, offsetof(struct bpf_sock, dst_port) + 2), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("sk_fullsock(skb->sk): sk->dst_port [byte load]") +__success __success_unpriv __retval(0) +__naked void sk_dst_port_byte_load(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r2 = *(u8*)(r0 + %[bpf_sock_dst_port]); \ + r2 = *(u8*)(r0 + %[__imm_0]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__imm_0, offsetof(struct bpf_sock, dst_port) + 1), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_dst_port, offsetof(struct bpf_sock, dst_port)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("sk_fullsock(skb->sk): sk->dst_port [byte load] (invalid)") +__failure __msg("invalid sock access") +__failure_unpriv +__naked void dst_port_byte_load_invalid(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r0 = *(u8*)(r0 + %[__imm_0]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__imm_0, offsetof(struct bpf_sock, dst_port) + 2), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("sk_fullsock(skb->sk): past sk->dst_port [half load] (invalid)") +__failure __msg("invalid sock access") +__failure_unpriv +__naked void dst_port_half_load_invalid_2(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r0 = *(u16*)(r0 + %[bpf_sock_dst_port__end]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_dst_port__end, offsetofend(struct bpf_sock, dst_port)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("sk_fullsock(skb->sk): sk->dst_ip6 [load 2nd byte]") +__success __success_unpriv __retval(0) +__naked void dst_ip6_load_2nd_byte(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r0 = *(u8*)(r0 + %[__imm_0]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__imm_0, offsetof(struct bpf_sock, dst_ip6[0]) + 1), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("sk_fullsock(skb->sk): sk->type [narrow load]") +__success __success_unpriv __retval(0) +__naked void sk_sk_type_narrow_load(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r0 = *(u8*)(r0 + %[bpf_sock_type]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("sk_fullsock(skb->sk): sk->protocol [narrow load]") +__success __success_unpriv __retval(0) +__naked void sk_sk_protocol_narrow_load(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r0 = *(u8*)(r0 + %[bpf_sock_protocol]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_protocol, offsetof(struct bpf_sock, protocol)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("sk_fullsock(skb->sk): beyond last field") +__failure __msg("invalid sock access") +__failure_unpriv +__naked void skb_sk_beyond_last_field_1(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r0 = *(u32*)(r0 + %[bpf_sock_rx_queue_mapping__end]);\ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_sock_rx_queue_mapping__end, offsetofend(struct bpf_sock, rx_queue_mapping)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("bpf_tcp_sock(skb->sk): no !skb->sk check") +__failure __msg("type=sock_common_or_null expected=sock_common") +__failure_unpriv +__naked void sk_no_skb_sk_check_2(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + call %[bpf_tcp_sock]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_tcp_sock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("bpf_tcp_sock(skb->sk): no NULL check on ret") +__failure __msg("invalid mem access 'tcp_sock_or_null'") +__failure_unpriv +__naked void no_null_check_on_ret_2(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_tcp_sock]; \ + r0 = *(u32*)(r0 + %[bpf_tcp_sock_snd_cwnd]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_tcp_sock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_tcp_sock_snd_cwnd, offsetof(struct bpf_tcp_sock, snd_cwnd)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("bpf_tcp_sock(skb->sk): tp->snd_cwnd") +__success __success_unpriv __retval(0) +__naked void skb_sk_tp_snd_cwnd_1(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_tcp_sock]; \ + if r0 != 0 goto l1_%=; \ + exit; \ +l1_%=: r0 = *(u32*)(r0 + %[bpf_tcp_sock_snd_cwnd]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_tcp_sock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_tcp_sock_snd_cwnd, offsetof(struct bpf_tcp_sock, snd_cwnd)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("bpf_tcp_sock(skb->sk): tp->bytes_acked") +__success __success_unpriv __retval(0) +__naked void skb_sk_tp_bytes_acked(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_tcp_sock]; \ + if r0 != 0 goto l1_%=; \ + exit; \ +l1_%=: r0 = *(u64*)(r0 + %[bpf_tcp_sock_bytes_acked]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_tcp_sock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_tcp_sock_bytes_acked, offsetof(struct bpf_tcp_sock, bytes_acked)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("bpf_tcp_sock(skb->sk): beyond last field") +__failure __msg("invalid tcp_sock access") +__failure_unpriv +__naked void skb_sk_beyond_last_field_2(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_tcp_sock]; \ + if r0 != 0 goto l1_%=; \ + exit; \ +l1_%=: r0 = *(u64*)(r0 + %[bpf_tcp_sock_bytes_acked__end]);\ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_tcp_sock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_tcp_sock_bytes_acked__end, offsetofend(struct bpf_tcp_sock, bytes_acked)) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("bpf_tcp_sock(bpf_sk_fullsock(skb->sk)): tp->snd_cwnd") +__success __success_unpriv __retval(0) +__naked void skb_sk_tp_snd_cwnd_2(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + exit; \ +l1_%=: r1 = r0; \ + call %[bpf_tcp_sock]; \ + if r0 != 0 goto l2_%=; \ + exit; \ +l2_%=: r0 = *(u32*)(r0 + %[bpf_tcp_sock_snd_cwnd]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm(bpf_tcp_sock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)), + __imm_const(bpf_tcp_sock_snd_cwnd, offsetof(struct bpf_tcp_sock, snd_cwnd)) + : __clobber_all); +} + +SEC("tc") +__description("bpf_sk_release(skb->sk)") +__failure __msg("R1 must be referenced when passed to release function") +__naked void bpf_sk_release_skb_sk(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 == 0 goto l0_%=; \ + call %[bpf_sk_release]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_release), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)) + : __clobber_all); +} + +SEC("tc") +__description("bpf_sk_release(bpf_sk_fullsock(skb->sk))") +__failure __msg("R1 must be referenced when passed to release function") +__naked void bpf_sk_fullsock_skb_sk(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + exit; \ +l1_%=: r1 = r0; \ + call %[bpf_sk_release]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm(bpf_sk_release), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)) + : __clobber_all); +} + +SEC("tc") +__description("bpf_sk_release(bpf_tcp_sock(skb->sk))") +__failure __msg("R1 must be referenced when passed to release function") +__naked void bpf_tcp_sock_skb_sk(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_tcp_sock]; \ + if r0 != 0 goto l1_%=; \ + exit; \ +l1_%=: r1 = r0; \ + call %[bpf_sk_release]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_sk_release), + __imm(bpf_tcp_sock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)) + : __clobber_all); +} + +SEC("tc") +__description("sk_storage_get(map, skb->sk, NULL, 0): value == NULL") +__success __retval(0) +__naked void sk_null_0_value_null(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r4 = 0; \ + r3 = 0; \ + r2 = r0; \ + r1 = %[sk_storage_map] ll; \ + call %[bpf_sk_storage_get]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm(bpf_sk_storage_get), + __imm_addr(sk_storage_map), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)) + : __clobber_all); +} + +SEC("tc") +__description("sk_storage_get(map, skb->sk, 1, 1): value == 1") +__failure __msg("R3 type=scalar expected=fp") +__naked void sk_1_1_value_1(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r4 = 1; \ + r3 = 1; \ + r2 = r0; \ + r1 = %[sk_storage_map] ll; \ + call %[bpf_sk_storage_get]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm(bpf_sk_storage_get), + __imm_addr(sk_storage_map), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)) + : __clobber_all); +} + +SEC("tc") +__description("sk_storage_get(map, skb->sk, &stack_value, 1): stack_value") +__success __retval(0) +__naked void stack_value_1_stack_value(void) +{ + asm volatile (" \ + r2 = 0; \ + *(u64*)(r10 - 8) = r2; \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: call %[bpf_sk_fullsock]; \ + if r0 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r4 = 1; \ + r3 = r10; \ + r3 += -8; \ + r2 = r0; \ + r1 = %[sk_storage_map] ll; \ + call %[bpf_sk_storage_get]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_fullsock), + __imm(bpf_sk_storage_get), + __imm_addr(sk_storage_map), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)) + : __clobber_all); +} + +SEC("tc") +__description("bpf_map_lookup_elem(smap, &key)") +__failure __msg("cannot pass map_type 24 into func bpf_map_lookup_elem") +__naked void map_lookup_elem_smap_key(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[sk_storage_map] ll; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(sk_storage_map) + : __clobber_all); +} + +SEC("xdp") +__description("bpf_map_lookup_elem(xskmap, &key); xs->queue_id") +__success __retval(0) +__naked void xskmap_key_xs_queue_id(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_xskmap] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r0 = *(u32*)(r0 + %[bpf_xdp_sock_queue_id]); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_xskmap), + __imm_const(bpf_xdp_sock_queue_id, offsetof(struct bpf_xdp_sock, queue_id)) + : __clobber_all); +} + +SEC("sk_skb") +__description("bpf_map_lookup_elem(sockmap, &key)") +__failure __msg("Unreleased reference id=2 alloc_insn=6") +__naked void map_lookup_elem_sockmap_key(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_sockmap] ll; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_sockmap) + : __clobber_all); +} + +SEC("sk_skb") +__description("bpf_map_lookup_elem(sockhash, &key)") +__failure __msg("Unreleased reference id=2 alloc_insn=6") +__naked void map_lookup_elem_sockhash_key(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_sockhash] ll; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_sockhash) + : __clobber_all); +} + +SEC("sk_skb") +__description("bpf_map_lookup_elem(sockmap, &key); sk->type [fullsock field]; bpf_sk_release(sk)") +__success +__naked void field_bpf_sk_release_sk_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_sockmap] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r1 = r0; \ + r0 = *(u32*)(r0 + %[bpf_sock_type]); \ + call %[bpf_sk_release]; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_sk_release), + __imm_addr(map_sockmap), + __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)) + : __clobber_all); +} + +SEC("sk_skb") +__description("bpf_map_lookup_elem(sockhash, &key); sk->type [fullsock field]; bpf_sk_release(sk)") +__success +__naked void field_bpf_sk_release_sk_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_sockhash] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r1 = r0; \ + r0 = *(u32*)(r0 + %[bpf_sock_type]); \ + call %[bpf_sk_release]; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_sk_release), + __imm_addr(map_sockhash), + __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)) + : __clobber_all); +} + +SEC("sk_reuseport") +__description("bpf_sk_select_reuseport(ctx, reuseport_array, &key, flags)") +__success +__naked void ctx_reuseport_array_key_flags(void) +{ + asm volatile (" \ + r4 = 0; \ + r2 = 0; \ + *(u32*)(r10 - 4) = r2; \ + r3 = r10; \ + r3 += -4; \ + r2 = %[map_reuseport_array] ll; \ + call %[bpf_sk_select_reuseport]; \ + exit; \ +" : + : __imm(bpf_sk_select_reuseport), + __imm_addr(map_reuseport_array) + : __clobber_all); +} + +SEC("sk_reuseport") +__description("bpf_sk_select_reuseport(ctx, sockmap, &key, flags)") +__success +__naked void reuseport_ctx_sockmap_key_flags(void) +{ + asm volatile (" \ + r4 = 0; \ + r2 = 0; \ + *(u32*)(r10 - 4) = r2; \ + r3 = r10; \ + r3 += -4; \ + r2 = %[map_sockmap] ll; \ + call %[bpf_sk_select_reuseport]; \ + exit; \ +" : + : __imm(bpf_sk_select_reuseport), + __imm_addr(map_sockmap) + : __clobber_all); +} + +SEC("sk_reuseport") +__description("bpf_sk_select_reuseport(ctx, sockhash, &key, flags)") +__success +__naked void reuseport_ctx_sockhash_key_flags(void) +{ + asm volatile (" \ + r4 = 0; \ + r2 = 0; \ + *(u32*)(r10 - 4) = r2; \ + r3 = r10; \ + r3 += -4; \ + r2 = %[map_sockmap] ll; \ + call %[bpf_sk_select_reuseport]; \ + exit; \ +" : + : __imm(bpf_sk_select_reuseport), + __imm_addr(map_sockmap) + : __clobber_all); +} + +SEC("tc") +__description("mark null check on return value of bpf_skc_to helpers") +__failure __msg("invalid mem access") +__naked void of_bpf_skc_to_helpers(void) +{ + asm volatile (" \ + r1 = *(u64*)(r1 + %[__sk_buff_sk]); \ + if r1 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: r6 = r1; \ + call %[bpf_skc_to_tcp_sock]; \ + r7 = r0; \ + r1 = r6; \ + call %[bpf_skc_to_tcp_request_sock]; \ + r8 = r0; \ + if r8 != 0 goto l1_%=; \ + r0 = 0; \ + exit; \ +l1_%=: r0 = *(u8*)(r7 + 0); \ + exit; \ +" : + : __imm(bpf_skc_to_tcp_request_sock), + __imm(bpf_skc_to_tcp_sock), + __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c new file mode 100644 index 0000000000..6115520154 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c @@ -0,0 +1,453 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/spill_fill.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 4096); +} map_ringbuf SEC(".maps"); + +SEC("socket") +__description("check valid spill/fill") +__success __failure_unpriv __msg_unpriv("R0 leaks addr") +__retval(POINTER_VALUE) +__naked void check_valid_spill_fill(void) +{ + asm volatile (" \ + /* spill R1(ctx) into stack */ \ + *(u64*)(r10 - 8) = r1; \ + /* fill it back into R2 */ \ + r2 = *(u64*)(r10 - 8); \ + /* should be able to access R0 = *(R2 + 8) */ \ + /* BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 8), */\ + r0 = r2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("check valid spill/fill, skb mark") +__success __success_unpriv __retval(0) +__naked void valid_spill_fill_skb_mark(void) +{ + asm volatile (" \ + r6 = r1; \ + *(u64*)(r10 - 8) = r6; \ + r0 = *(u64*)(r10 - 8); \ + r0 = *(u32*)(r0 + %[__sk_buff_mark]); \ + exit; \ +" : + : __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +SEC("socket") +__description("check valid spill/fill, ptr to mem") +__success __success_unpriv __retval(0) +__naked void spill_fill_ptr_to_mem(void) +{ + asm volatile (" \ + /* reserve 8 byte ringbuf memory */ \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r1 = %[map_ringbuf] ll; \ + r2 = 8; \ + r3 = 0; \ + call %[bpf_ringbuf_reserve]; \ + /* store a pointer to the reserved memory in R6 */\ + r6 = r0; \ + /* check whether the reservation was successful */\ + if r0 == 0 goto l0_%=; \ + /* spill R6(mem) into the stack */ \ + *(u64*)(r10 - 8) = r6; \ + /* fill it back in R7 */ \ + r7 = *(u64*)(r10 - 8); \ + /* should be able to access *(R7) = 0 */ \ + r1 = 0; \ + *(u64*)(r7 + 0) = r1; \ + /* submit the reserved ringbuf memory */ \ + r1 = r7; \ + r2 = 0; \ + call %[bpf_ringbuf_submit]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ringbuf_reserve), + __imm(bpf_ringbuf_submit), + __imm_addr(map_ringbuf) + : __clobber_all); +} + +SEC("socket") +__description("check with invalid reg offset 0") +__failure __msg("R0 pointer arithmetic on ringbuf_mem_or_null prohibited") +__failure_unpriv +__naked void with_invalid_reg_offset_0(void) +{ + asm volatile (" \ + /* reserve 8 byte ringbuf memory */ \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r1 = %[map_ringbuf] ll; \ + r2 = 8; \ + r3 = 0; \ + call %[bpf_ringbuf_reserve]; \ + /* store a pointer to the reserved memory in R6 */\ + r6 = r0; \ + /* add invalid offset to memory or NULL */ \ + r0 += 1; \ + /* check whether the reservation was successful */\ + if r0 == 0 goto l0_%=; \ + /* should not be able to access *(R7) = 0 */ \ + r1 = 0; \ + *(u32*)(r6 + 0) = r1; \ + /* submit the reserved ringbuf memory */ \ + r1 = r6; \ + r2 = 0; \ + call %[bpf_ringbuf_submit]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ringbuf_reserve), + __imm(bpf_ringbuf_submit), + __imm_addr(map_ringbuf) + : __clobber_all); +} + +SEC("socket") +__description("check corrupted spill/fill") +__failure __msg("R0 invalid mem access 'scalar'") +__msg_unpriv("attempt to corrupt spilled") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void check_corrupted_spill_fill(void) +{ + asm volatile (" \ + /* spill R1(ctx) into stack */ \ + *(u64*)(r10 - 8) = r1; \ + /* mess up with R1 pointer on stack */ \ + r0 = 0x23; \ + *(u8*)(r10 - 7) = r0; \ + /* fill back into R0 is fine for priv. \ + * R0 now becomes SCALAR_VALUE. \ + */ \ + r0 = *(u64*)(r10 - 8); \ + /* Load from R0 should fail. */ \ + r0 = *(u64*)(r0 + 8); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("check corrupted spill/fill, LSB") +__success __failure_unpriv __msg_unpriv("attempt to corrupt spilled") +__retval(POINTER_VALUE) +__naked void check_corrupted_spill_fill_lsb(void) +{ + asm volatile (" \ + *(u64*)(r10 - 8) = r1; \ + r0 = 0xcafe; \ + *(u16*)(r10 - 8) = r0; \ + r0 = *(u64*)(r10 - 8); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("check corrupted spill/fill, MSB") +__success __failure_unpriv __msg_unpriv("attempt to corrupt spilled") +__retval(POINTER_VALUE) +__naked void check_corrupted_spill_fill_msb(void) +{ + asm volatile (" \ + *(u64*)(r10 - 8) = r1; \ + r0 = 0x12345678; \ + *(u32*)(r10 - 4) = r0; \ + r0 = *(u64*)(r10 - 8); \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("Spill and refill a u32 const scalar. Offset to skb->data") +__success __retval(0) +__naked void scalar_offset_to_skb_data_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + w4 = 20; \ + *(u32*)(r10 - 8) = r4; \ + r4 = *(u32*)(r10 - 8); \ + r0 = r2; \ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=20 */ \ + r0 += r4; \ + /* if (r0 > r3) R0=pkt,off=20 R2=pkt R3=pkt_end R4=20 */\ + if r0 > r3 goto l0_%=; \ + /* r0 = *(u32 *)r2 R0=pkt,off=20,r=20 R2=pkt,r=20 R3=pkt_end R4=20 */\ + r0 = *(u32*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("socket") +__description("Spill a u32 const, refill from another half of the uninit u32 from the stack") +/* in privileged mode reads from uninitialized stack locations are permitted */ +__success __failure_unpriv +__msg_unpriv("invalid read from stack off -4+0 size 4") +__retval(0) +__naked void uninit_u32_from_the_stack(void) +{ + asm volatile (" \ + w4 = 20; \ + *(u32*)(r10 - 8) = r4; \ + /* r4 = *(u32 *)(r10 -4) fp-8=????rrrr*/ \ + r4 = *(u32*)(r10 - 4); \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("Spill a u32 const scalar. Refill as u16. Offset to skb->data") +__failure __msg("invalid access to packet") +__naked void u16_offset_to_skb_data(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + w4 = 20; \ + *(u32*)(r10 - 8) = r4; \ + r4 = *(u16*)(r10 - 8); \ + r0 = r2; \ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */\ + r0 += r4; \ + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */\ + if r0 > r3 goto l0_%=; \ + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */\ + r0 = *(u32*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("Spill u32 const scalars. Refill as u64. Offset to skb->data") +__failure __msg("invalid access to packet") +__naked void u64_offset_to_skb_data(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + w6 = 0; \ + w7 = 20; \ + *(u32*)(r10 - 4) = r6; \ + *(u32*)(r10 - 8) = r7; \ + r4 = *(u16*)(r10 - 8); \ + r0 = r2; \ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */\ + r0 += r4; \ + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */\ + if r0 > r3 goto l0_%=; \ + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */\ + r0 = *(u32*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("Spill a u32 const scalar. Refill as u16 from fp-6. Offset to skb->data") +__failure __msg("invalid access to packet") +__naked void _6_offset_to_skb_data(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + w4 = 20; \ + *(u32*)(r10 - 8) = r4; \ + r4 = *(u16*)(r10 - 6); \ + r0 = r2; \ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */\ + r0 += r4; \ + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */\ + if r0 > r3 goto l0_%=; \ + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */\ + r0 = *(u32*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("Spill and refill a u32 const scalar at non 8byte aligned stack addr. Offset to skb->data") +__failure __msg("invalid access to packet") +__naked void addr_offset_to_skb_data(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + w4 = 20; \ + *(u32*)(r10 - 8) = r4; \ + *(u32*)(r10 - 4) = r4; \ + r4 = *(u32*)(r10 - 4); \ + r0 = r2; \ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=U32_MAX */\ + r0 += r4; \ + /* if (r0 > r3) R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4= */\ + if r0 > r3 goto l0_%=; \ + /* r0 = *(u32 *)r2 R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4= */\ + r0 = *(u32*)(r2 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("Spill and refill a umax=40 bounded scalar. Offset to skb->data") +__success __retval(0) +__naked void scalar_offset_to_skb_data_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[__sk_buff_data]); \ + r3 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r4 = *(u64*)(r1 + %[__sk_buff_tstamp]); \ + if r4 <= 40 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: /* *(u32 *)(r10 -8) = r4 R4=umax=40 */ \ + *(u32*)(r10 - 8) = r4; \ + /* r4 = (*u32 *)(r10 - 8) */ \ + r4 = *(u32*)(r10 - 8); \ + /* r2 += r4 R2=pkt R4=umax=40 */ \ + r2 += r4; \ + /* r0 = r2 R2=pkt,umax=40 R4=umax=40 */ \ + r0 = r2; \ + /* r2 += 20 R0=pkt,umax=40 R2=pkt,umax=40 */ \ + r2 += 20; \ + /* if (r2 > r3) R0=pkt,umax=40 R2=pkt,off=20,umax=40 */\ + if r2 > r3 goto l1_%=; \ + /* r0 = *(u32 *)r0 R0=pkt,r=20,umax=40 R2=pkt,off=20,r=20,umax=40 */\ + r0 = *(u32*)(r0 + 0); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)), + __imm_const(__sk_buff_tstamp, offsetof(struct __sk_buff, tstamp)) + : __clobber_all); +} + +SEC("tc") +__description("Spill a u32 scalar at fp-4 and then at fp-8") +__success __retval(0) +__naked void and_then_at_fp_8(void) +{ + asm volatile (" \ + w4 = 4321; \ + *(u32*)(r10 - 4) = r4; \ + *(u32*)(r10 - 8) = r4; \ + r4 = *(u64*)(r10 - 8); \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("xdp") +__description("32-bit spill of 64-bit reg should clear ID") +__failure __msg("math between ctx pointer and 4294967295 is not allowed") +__naked void spill_32bit_of_64bit_fail(void) +{ + asm volatile (" \ + r6 = r1; \ + /* Roll one bit to force the verifier to track both branches. */\ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x8; \ + /* Put a large number into r1. */ \ + r1 = 0xffffffff; \ + r1 <<= 32; \ + r1 += r0; \ + /* Assign an ID to r1. */ \ + r2 = r1; \ + /* 32-bit spill r1 to stack - should clear the ID! */\ + *(u32*)(r10 - 8) = r1; \ + /* 32-bit fill r2 from stack. */ \ + r2 = *(u32*)(r10 - 8); \ + /* Compare r2 with another register to trigger find_equal_scalars.\ + * Having one random bit is important here, otherwise the verifier cuts\ + * the corners. If the ID was mistakenly preserved on spill, this would\ + * cause the verifier to think that r1 is also equal to zero in one of\ + * the branches, and equal to eight on the other branch.\ + */ \ + r3 = 0; \ + if r2 != r3 goto l0_%=; \ +l0_%=: r1 >>= 32; \ + /* At this point, if the verifier thinks that r1 is 0, an out-of-bounds\ + * read will happen, because it actually contains 0xffffffff.\ + */ \ + r6 += r1; \ + r0 = *(u32*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("xdp") +__description("16-bit spill of 32-bit reg should clear ID") +__failure __msg("dereference of modified ctx ptr R6 off=65535 disallowed") +__naked void spill_16bit_of_32bit_fail(void) +{ + asm volatile (" \ + r6 = r1; \ + /* Roll one bit to force the verifier to track both branches. */\ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x8; \ + /* Put a large number into r1. */ \ + w1 = 0xffff0000; \ + r1 += r0; \ + /* Assign an ID to r1. */ \ + r2 = r1; \ + /* 16-bit spill r1 to stack - should clear the ID! */\ + *(u16*)(r10 - 8) = r1; \ + /* 16-bit fill r2 from stack. */ \ + r2 = *(u16*)(r10 - 8); \ + /* Compare r2 with another register to trigger find_equal_scalars.\ + * Having one random bit is important here, otherwise the verifier cuts\ + * the corners. If the ID was mistakenly preserved on spill, this would\ + * cause the verifier to think that r1 is also equal to zero in one of\ + * the branches, and equal to eight on the other branch.\ + */ \ + r3 = 0; \ + if r2 != r3 goto l0_%=; \ +l0_%=: r1 >>= 16; \ + /* At this point, if the verifier thinks that r1 is 0, an out-of-bounds\ + * read will happen, because it actually contains 0xffff.\ + */ \ + r6 += r1; \ + r0 = *(u32*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_spin_lock.c b/tools/testing/selftests/bpf/progs/verifier_spin_lock.c new file mode 100644 index 0000000000..9c1aa69650 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_spin_lock.c @@ -0,0 +1,533 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/spin_lock.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct val { + int cnt; + struct bpf_spin_lock l; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct val); +} map_spin_lock SEC(".maps"); + +SEC("cgroup/skb") +__description("spin_lock: test1 success") +__success __failure_unpriv __msg_unpriv("") +__retval(0) +__naked void spin_lock_test1_success(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + r1 += 4; \ + call %[bpf_spin_lock]; \ + r1 = r6; \ + r1 += 4; \ + r0 = *(u32*)(r6 + 0); \ + call %[bpf_spin_unlock]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm(bpf_spin_unlock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("spin_lock: test2 direct ld/st") +__failure __msg("cannot be accessed directly") +__failure_unpriv __msg_unpriv("") +__naked void lock_test2_direct_ld_st(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + r1 += 4; \ + call %[bpf_spin_lock]; \ + r1 = r6; \ + r1 += 4; \ + r0 = *(u32*)(r1 + 0); \ + call %[bpf_spin_unlock]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm(bpf_spin_unlock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("spin_lock: test3 direct ld/st") +__failure __msg("cannot be accessed directly") +__failure_unpriv __msg_unpriv("") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void lock_test3_direct_ld_st(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + r1 += 4; \ + call %[bpf_spin_lock]; \ + r1 = r6; \ + r1 += 4; \ + r0 = *(u32*)(r6 + 1); \ + call %[bpf_spin_unlock]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm(bpf_spin_unlock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("spin_lock: test4 direct ld/st") +__failure __msg("cannot be accessed directly") +__failure_unpriv __msg_unpriv("") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void lock_test4_direct_ld_st(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + r1 += 4; \ + call %[bpf_spin_lock]; \ + r1 = r6; \ + r1 += 4; \ + r0 = *(u16*)(r6 + 3); \ + call %[bpf_spin_unlock]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm(bpf_spin_unlock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("spin_lock: test5 call within a locked region") +__failure __msg("calls are not allowed") +__failure_unpriv __msg_unpriv("") +__naked void call_within_a_locked_region(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + r1 += 4; \ + call %[bpf_spin_lock]; \ + call %[bpf_get_prandom_u32]; \ + r1 = r6; \ + r1 += 4; \ + call %[bpf_spin_unlock]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm(bpf_spin_unlock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("spin_lock: test6 missing unlock") +__failure __msg("unlock is missing") +__failure_unpriv __msg_unpriv("") +__naked void spin_lock_test6_missing_unlock(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + r1 += 4; \ + call %[bpf_spin_lock]; \ + r1 = r6; \ + r1 += 4; \ + r0 = *(u32*)(r6 + 0); \ + if r0 != 0 goto l1_%=; \ + call %[bpf_spin_unlock]; \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm(bpf_spin_unlock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("spin_lock: test7 unlock without lock") +__failure __msg("without taking a lock") +__failure_unpriv __msg_unpriv("") +__naked void lock_test7_unlock_without_lock(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + r1 += 4; \ + if r1 != 0 goto l1_%=; \ + call %[bpf_spin_lock]; \ +l1_%=: r1 = r6; \ + r1 += 4; \ + r0 = *(u32*)(r6 + 0); \ + call %[bpf_spin_unlock]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm(bpf_spin_unlock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("spin_lock: test8 double lock") +__failure __msg("calls are not allowed") +__failure_unpriv __msg_unpriv("") +__naked void spin_lock_test8_double_lock(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + r1 += 4; \ + call %[bpf_spin_lock]; \ + r1 = r6; \ + r1 += 4; \ + call %[bpf_spin_lock]; \ + r1 = r6; \ + r1 += 4; \ + r0 = *(u32*)(r6 + 0); \ + call %[bpf_spin_unlock]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm(bpf_spin_unlock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("spin_lock: test9 different lock") +__failure __msg("unlock of different lock") +__failure_unpriv __msg_unpriv("") +__naked void spin_lock_test9_different_lock(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l1_%=; \ + exit; \ +l1_%=: r7 = r0; \ + r1 = r6; \ + r1 += 4; \ + call %[bpf_spin_lock]; \ + r1 = r7; \ + r1 += 4; \ + call %[bpf_spin_unlock]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm(bpf_spin_unlock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("spin_lock: test10 lock in subprog without unlock") +__failure __msg("unlock is missing") +__failure_unpriv __msg_unpriv("") +__naked void lock_in_subprog_without_unlock(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r6 = r0; \ + r1 = r0; \ + r1 += 4; \ + call lock_in_subprog_without_unlock__1; \ + r1 = r6; \ + r1 += 4; \ + call %[bpf_spin_unlock]; \ + r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_spin_unlock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +static __naked __noinline __attribute__((used)) +void lock_in_subprog_without_unlock__1(void) +{ + asm volatile (" \ + call %[bpf_spin_lock]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_spin_lock) + : __clobber_all); +} + +SEC("tc") +__description("spin_lock: test11 ld_abs under lock") +__failure __msg("inside bpf_spin_lock") +__naked void test11_ld_abs_under_lock(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r7 = r0; \ + r1 = r0; \ + r1 += 4; \ + call %[bpf_spin_lock]; \ + r0 = *(u8*)skb[0]; \ + r1 = r7; \ + r1 += 4; \ + call %[bpf_spin_unlock]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm(bpf_spin_unlock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +SEC("tc") +__description("spin_lock: regsafe compare reg->id for map value") +__failure __msg("bpf_spin_unlock of different lock") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void reg_id_for_map_value(void) +{ + asm volatile (" \ + r6 = r1; \ + r6 = *(u32*)(r6 + %[__sk_buff_mark]); \ + r1 = %[map_spin_lock] ll; \ + r9 = r1; \ + r2 = 0; \ + *(u32*)(r10 - 4) = r2; \ + r2 = r10; \ + r2 += -4; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r7 = r0; \ + r1 = r9; \ + r2 = r10; \ + r2 += -4; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l1_%=; \ + exit; \ +l1_%=: r8 = r0; \ + r1 = r7; \ + r1 += 4; \ + call %[bpf_spin_lock]; \ + if r6 == 0 goto l2_%=; \ + goto l3_%=; \ +l2_%=: r7 = r8; \ +l3_%=: r1 = r7; \ + r1 += 4; \ + call %[bpf_spin_unlock]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm(bpf_spin_unlock), + __imm_addr(map_spin_lock), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +/* Make sure that regsafe() compares ids for spin lock records using + * check_ids(): + * 1: r9 = map_lookup_elem(...) ; r9.id == 1 + * 2: r8 = map_lookup_elem(...) ; r8.id == 2 + * 3: r7 = ktime_get_ns() + * 4: r6 = ktime_get_ns() + * 5: if r6 > r7 goto <9> + * 6: spin_lock(r8) + * 7: r9 = r8 + * 8: goto <10> + * 9: spin_lock(r9) + * 10: spin_unlock(r9) ; r9.id == 1 || r9.id == 2 and lock is active, + * ; second visit to (10) should be considered safe + * ; if check_ids() is used. + * 11: exit(0) + */ + +SEC("cgroup/skb") +__description("spin_lock: regsafe() check_ids() similar id mappings") +__success __msg("29: safe") +__failure_unpriv __msg_unpriv("") +__log_level(2) __retval(0) __flag(BPF_F_TEST_STATE_FREQ) +__naked void check_ids_similar_id_mappings(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + /* r9 = map_lookup_elem(...) */ \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r9 = r0; \ + /* r8 = map_lookup_elem(...) */ \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_spin_lock] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l1_%=; \ + r8 = r0; \ + /* r7 = ktime_get_ns() */ \ + call %[bpf_ktime_get_ns]; \ + r7 = r0; \ + /* r6 = ktime_get_ns() */ \ + call %[bpf_ktime_get_ns]; \ + r6 = r0; \ + /* if r6 > r7 goto +5 ; no new information about the state is derived from\ + * ; this check, thus produced verifier states differ\ + * ; only in 'insn_idx' \ + * spin_lock(r8) \ + * r9 = r8 \ + * goto unlock \ + */ \ + if r6 > r7 goto l2_%=; \ + r1 = r8; \ + r1 += 4; \ + call %[bpf_spin_lock]; \ + r9 = r8; \ + goto l3_%=; \ +l2_%=: /* spin_lock(r9) */ \ + r1 = r9; \ + r1 += 4; \ + call %[bpf_spin_lock]; \ +l3_%=: /* spin_unlock(r9) */ \ + r1 = r9; \ + r1 += 4; \ + call %[bpf_spin_unlock]; \ +l0_%=: /* exit(0) */ \ + r0 = 0; \ +l1_%=: exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm(bpf_spin_lock), + __imm(bpf_spin_unlock), + __imm_addr(map_spin_lock) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c new file mode 100644 index 0000000000..e0f77e3e78 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c @@ -0,0 +1,484 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/stack_ptr.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <limits.h> +#include "bpf_misc.h" + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct test_val); +} map_array_48b SEC(".maps"); + +SEC("socket") +__description("PTR_TO_STACK store/load") +__success __success_unpriv __retval(0xfaceb00c) +__naked void ptr_to_stack_store_load(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -10; \ + r0 = 0xfaceb00c; \ + *(u64*)(r1 + 2) = r0; \ + r0 = *(u64*)(r1 + 2); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK store/load - bad alignment on off") +__failure __msg("misaligned stack access off (0x0; 0x0)+-8+2 size 8") +__failure_unpriv +__naked void load_bad_alignment_on_off(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -8; \ + r0 = 0xfaceb00c; \ + *(u64*)(r1 + 2) = r0; \ + r0 = *(u64*)(r1 + 2); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK store/load - bad alignment on reg") +__failure __msg("misaligned stack access off (0x0; 0x0)+-10+8 size 8") +__failure_unpriv +__naked void load_bad_alignment_on_reg(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -10; \ + r0 = 0xfaceb00c; \ + *(u64*)(r1 + 8) = r0; \ + r0 = *(u64*)(r1 + 8); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK store/load - out of bounds low") +__failure __msg("invalid write to stack R1 off=-79992 size=8") +__msg_unpriv("R1 stack pointer arithmetic goes out of range") +__naked void load_out_of_bounds_low(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -80000; \ + r0 = 0xfaceb00c; \ + *(u64*)(r1 + 8) = r0; \ + r0 = *(u64*)(r1 + 8); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK store/load - out of bounds high") +__failure __msg("invalid write to stack R1 off=0 size=8") +__failure_unpriv +__naked void load_out_of_bounds_high(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -8; \ + r0 = 0xfaceb00c; \ + *(u64*)(r1 + 8) = r0; \ + r0 = *(u64*)(r1 + 8); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK check high 1") +__success __success_unpriv __retval(42) +__naked void to_stack_check_high_1(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -1; \ + r0 = 42; \ + *(u8*)(r1 + 0) = r0; \ + r0 = *(u8*)(r1 + 0); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK check high 2") +__success __success_unpriv __retval(42) +__naked void to_stack_check_high_2(void) +{ + asm volatile (" \ + r1 = r10; \ + r0 = 42; \ + *(u8*)(r1 - 1) = r0; \ + r0 = *(u8*)(r1 - 1); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK check high 3") +__success __failure_unpriv +__msg_unpriv("R1 stack pointer arithmetic goes out of range") +__retval(42) +__naked void to_stack_check_high_3(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += 0; \ + r0 = 42; \ + *(u8*)(r1 - 1) = r0; \ + r0 = *(u8*)(r1 - 1); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK check high 4") +__failure __msg("invalid write to stack R1 off=0 size=1") +__msg_unpriv("R1 stack pointer arithmetic goes out of range") +__naked void to_stack_check_high_4(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += 0; \ + r0 = 42; \ + *(u8*)(r1 + 0) = r0; \ + r0 = *(u8*)(r1 + 0); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK check high 5") +__failure __msg("invalid write to stack R1") +__msg_unpriv("R1 stack pointer arithmetic goes out of range") +__naked void to_stack_check_high_5(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += %[__imm_0]; \ + r0 = 42; \ + *(u8*)(r1 + 0) = r0; \ + r0 = *(u8*)(r1 + 0); \ + exit; \ +" : + : __imm_const(__imm_0, (1 << 29) - 1) + : __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK check high 6") +__failure __msg("invalid write to stack") +__msg_unpriv("R1 stack pointer arithmetic goes out of range") +__naked void to_stack_check_high_6(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += %[__imm_0]; \ + r0 = 42; \ + *(u8*)(r1 + %[shrt_max]) = r0; \ + r0 = *(u8*)(r1 + %[shrt_max]); \ + exit; \ +" : + : __imm_const(__imm_0, (1 << 29) - 1), + __imm_const(shrt_max, SHRT_MAX) + : __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK check high 7") +__failure __msg("fp pointer offset") +__msg_unpriv("R1 stack pointer arithmetic goes out of range") +__naked void to_stack_check_high_7(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += %[__imm_0]; \ + r1 += %[__imm_0]; \ + r0 = 42; \ + *(u8*)(r1 + %[shrt_max]) = r0; \ + r0 = *(u8*)(r1 + %[shrt_max]); \ + exit; \ +" : + : __imm_const(__imm_0, (1 << 29) - 1), + __imm_const(shrt_max, SHRT_MAX) + : __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK check low 1") +__success __success_unpriv __retval(42) +__naked void to_stack_check_low_1(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -512; \ + r0 = 42; \ + *(u8*)(r1 + 0) = r0; \ + r0 = *(u8*)(r1 + 0); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK check low 2") +__success __failure_unpriv +__msg_unpriv("R1 stack pointer arithmetic goes out of range") +__retval(42) +__naked void to_stack_check_low_2(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -513; \ + r0 = 42; \ + *(u8*)(r1 + 1) = r0; \ + r0 = *(u8*)(r1 + 1); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK check low 3") +__failure __msg("invalid write to stack R1 off=-513 size=1") +__msg_unpriv("R1 stack pointer arithmetic goes out of range") +__naked void to_stack_check_low_3(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -513; \ + r0 = 42; \ + *(u8*)(r1 + 0) = r0; \ + r0 = *(u8*)(r1 + 0); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK check low 4") +__failure __msg("math between fp pointer") +__failure_unpriv +__naked void to_stack_check_low_4(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += %[int_min]; \ + r0 = 42; \ + *(u8*)(r1 + 0) = r0; \ + r0 = *(u8*)(r1 + 0); \ + exit; \ +" : + : __imm_const(int_min, INT_MIN) + : __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK check low 5") +__failure __msg("invalid write to stack") +__msg_unpriv("R1 stack pointer arithmetic goes out of range") +__naked void to_stack_check_low_5(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += %[__imm_0]; \ + r0 = 42; \ + *(u8*)(r1 + 0) = r0; \ + r0 = *(u8*)(r1 + 0); \ + exit; \ +" : + : __imm_const(__imm_0, -((1 << 29) - 1)) + : __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK check low 6") +__failure __msg("invalid write to stack") +__msg_unpriv("R1 stack pointer arithmetic goes out of range") +__naked void to_stack_check_low_6(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += %[__imm_0]; \ + r0 = 42; \ + *(u8*)(r1 %[shrt_min]) = r0; \ + r0 = *(u8*)(r1 %[shrt_min]); \ + exit; \ +" : + : __imm_const(__imm_0, -((1 << 29) - 1)), + __imm_const(shrt_min, SHRT_MIN) + : __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK check low 7") +__failure __msg("fp pointer offset") +__msg_unpriv("R1 stack pointer arithmetic goes out of range") +__naked void to_stack_check_low_7(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += %[__imm_0]; \ + r1 += %[__imm_0]; \ + r0 = 42; \ + *(u8*)(r1 %[shrt_min]) = r0; \ + r0 = *(u8*)(r1 %[shrt_min]); \ + exit; \ +" : + : __imm_const(__imm_0, -((1 << 29) - 1)), + __imm_const(shrt_min, SHRT_MIN) + : __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK mixed reg/k, 1") +__success __success_unpriv __retval(42) +__naked void stack_mixed_reg_k_1(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -3; \ + r2 = -3; \ + r1 += r2; \ + r0 = 42; \ + *(u8*)(r1 + 0) = r0; \ + r0 = *(u8*)(r1 + 0); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK mixed reg/k, 2") +__success __success_unpriv __retval(42) +__naked void stack_mixed_reg_k_2(void) +{ + asm volatile (" \ + r0 = 0; \ + *(u64*)(r10 - 8) = r0; \ + r0 = 0; \ + *(u64*)(r10 - 16) = r0; \ + r1 = r10; \ + r1 += -3; \ + r2 = -3; \ + r1 += r2; \ + r0 = 42; \ + *(u8*)(r1 + 0) = r0; \ + r5 = r10; \ + r0 = *(u8*)(r5 - 6); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK mixed reg/k, 3") +__success __success_unpriv __retval(-3) +__naked void stack_mixed_reg_k_3(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -3; \ + r2 = -3; \ + r1 += r2; \ + r0 = 42; \ + *(u8*)(r1 + 0) = r0; \ + r0 = r2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK reg") +__success __success_unpriv __retval(42) +__naked void ptr_to_stack_reg(void) +{ + asm volatile (" \ + r1 = r10; \ + r2 = -3; \ + r1 += r2; \ + r0 = 42; \ + *(u8*)(r1 + 0) = r0; \ + r0 = *(u8*)(r1 + 0); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("stack pointer arithmetic") +__success __success_unpriv __retval(0) +__naked void stack_pointer_arithmetic(void) +{ + asm volatile (" \ + r1 = 4; \ + goto l0_%=; \ +l0_%=: r7 = r10; \ + r7 += -10; \ + r7 += -10; \ + r2 = r7; \ + r2 += r1; \ + r0 = 0; \ + *(u32*)(r2 + 4) = r0; \ + r2 = r7; \ + r2 += 8; \ + r0 = 0; \ + *(u32*)(r2 + 4) = r0; \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("store PTR_TO_STACK in R10 to array map using BPF_B") +__success __retval(42) +__naked void array_map_using_bpf_b(void) +{ + asm volatile (" \ + /* Load pointer to map. */ \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + r0 = 2; \ + exit; \ +l0_%=: r1 = r0; \ + /* Copy R10 to R9. */ \ + r9 = r10; \ + /* Pollute other registers with unaligned values. */\ + r2 = -1; \ + r3 = -1; \ + r4 = -1; \ + r5 = -1; \ + r6 = -1; \ + r7 = -1; \ + r8 = -1; \ + /* Store both R9 and R10 with BPF_B and read back. */\ + *(u8*)(r1 + 0) = r10; \ + r2 = *(u8*)(r1 + 0); \ + *(u8*)(r1 + 0) = r9; \ + r3 = *(u8*)(r1 + 0); \ + /* Should read back as same value. */ \ + if r2 == r3 goto l1_%=; \ + r0 = 1; \ + exit; \ +l1_%=: r0 = 42; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c new file mode 100644 index 0000000000..f61d623b1c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -0,0 +1,594 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <errno.h> +#include <string.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof(x[0])) + +int vals[] SEC(".data.vals") = {1, 2, 3, 4}; + +__naked __noinline __used +static unsigned long identity_subprog() +{ + /* the simplest *static* 64-bit identity function */ + asm volatile ( + "r0 = r1;" + "exit;" + ); +} + +__noinline __used +unsigned long global_identity_subprog(__u64 x) +{ + /* the simplest *global* 64-bit identity function */ + return x; +} + +__naked __noinline __used +static unsigned long callback_subprog() +{ + /* the simplest callback function */ + asm volatile ( + "r0 = 0;" + "exit;" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("7: (0f) r1 += r0") +__msg("mark_precise: frame0: regs=r0 stack= before 6: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r0 stack= before 5: (27) r0 *= 4") +__msg("mark_precise: frame0: regs=r0 stack= before 11: (95) exit") +__msg("mark_precise: frame1: regs=r0 stack= before 10: (bf) r0 = r1") +__msg("mark_precise: frame1: regs=r1 stack= before 4: (85) call pc+5") +__msg("mark_precise: frame0: regs=r1 stack= before 3: (bf) r1 = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int subprog_result_precise(void) +{ + asm volatile ( + "r6 = 3;" + /* pass r6 through r1 into subprog to get it back as r0; + * this whole chain will have to be marked as precise later + */ + "r1 = r6;" + "call identity_subprog;" + /* now use subprog's returned value (which is a + * r6 -> r1 -> r0 chain), as index into vals array, forcing + * all of that to be known precisely + */ + "r0 *= 4;" + "r1 = %[vals];" + /* here r0->r1->r6 chain is forced to be precise and has to be + * propagated back to the beginning, including through the + * subprog call + */ + "r1 += r0;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("9: (0f) r1 += r0") +__msg("mark_precise: frame0: last_idx 9 first_idx 0") +__msg("mark_precise: frame0: regs=r0 stack= before 8: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r0 stack= before 7: (27) r0 *= 4") +__msg("mark_precise: frame0: regs=r0 stack= before 5: (a5) if r0 < 0x4 goto pc+1") +__msg("mark_precise: frame0: regs=r0 stack= before 4: (85) call pc+7") +__naked int global_subprog_result_precise(void) +{ + asm volatile ( + "r6 = 3;" + /* pass r6 through r1 into subprog to get it back as r0; + * given global_identity_subprog is global, precision won't + * propagate all the way back to r6 + */ + "r1 = r6;" + "call global_identity_subprog;" + /* now use subprog's returned value (which is unknown now, so + * we need to clamp it), as index into vals array, forcing r0 + * to be marked precise (with no effect on r6, though) + */ + "if r0 < %[vals_arr_sz] goto 1f;" + "r0 = %[vals_arr_sz] - 1;" + "1:" + "r0 *= 4;" + "r1 = %[vals];" + /* here r0 is forced to be precise and has to be + * propagated back to the global subprog call, but it + * shouldn't go all the way to mark r6 as precise + */ + "r1 += r0;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals), + __imm_const(vals_arr_sz, ARRAY_SIZE(vals)) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +/* First simulated path does not include callback body, + * r1 and r4 are always precise for bpf_loop() calls. + */ +__msg("9: (85) call bpf_loop#181") +__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") +__msg("mark_precise: frame0: parent state regs=r4 stack=:") +__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9") +__msg("mark_precise: frame0: regs=r4 stack= before 8: (b7) r4 = 0") +__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") +__msg("mark_precise: frame0: parent state regs=r1 stack=:") +__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9") +__msg("mark_precise: frame0: regs=r1 stack= before 8: (b7) r4 = 0") +__msg("mark_precise: frame0: regs=r1 stack= before 7: (b7) r3 = 0") +__msg("mark_precise: frame0: regs=r1 stack= before 6: (bf) r2 = r8") +__msg("mark_precise: frame0: regs=r1 stack= before 5: (bf) r1 = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +/* r6 precision propagation */ +__msg("14: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 14 first_idx 9") +__msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (25) if r6 > 0x3 goto pc+4") +__msg("mark_precise: frame0: regs=r6 stack= before 10: (bf) r6 = r0") +__msg("mark_precise: frame0: regs=r0 stack= before 9: (85) call bpf_loop") +/* State entering callback body popped from states stack */ +__msg("from 9 to 17: frame1:") +__msg("17: frame1: R1=scalar() R2=0 R10=fp0 cb") +__msg("17: (b7) r0 = 0") +__msg("18: (95) exit") +__msg("returning from callee:") +__msg("to caller at 9:") +__msg("frame 0: propagating r1,r4") +__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") +__msg("mark_precise: frame0: regs=r1,r4 stack= before 18: (95) exit") +__msg("from 18 to 9: safe") +__naked int callback_result_precise(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and use result; r0 shouldn't propagate back to + * callback_subprog + */ + "r1 = r6;" /* nr_loops */ + "r2 = %[callback_subprog];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + "r6 = r0;" + "if r6 > 3 goto 1f;" + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the bpf_loop() call, but not beyond + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "1:" + "exit;" + : + : __imm_ptr(vals), + __imm_ptr(callback_subprog), + __imm(bpf_loop) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("7: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 7 first_idx 0") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 5: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 10: (bf) r0 = r1") +__msg("mark_precise: frame1: regs= stack= before 4: (85) call pc+5") +__msg("mark_precise: frame0: regs=r6 stack= before 3: (b7) r1 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_callee_saved_reg_precise(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call identity_subprog;" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("7: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 7 first_idx 0") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 5: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (85) call pc+5") +__msg("mark_precise: frame0: regs=r6 stack= before 3: (b7) r1 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_callee_saved_reg_precise_global(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call global_identity_subprog;" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +/* First simulated path does not include callback body */ +__msg("12: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 12 first_idx 9") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 10: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 9: (85) call bpf_loop") +__msg("mark_precise: frame0: parent state regs=r6 stack=:") +__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9") +__msg("mark_precise: frame0: regs=r6 stack= before 8: (b7) r4 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 7: (b7) r3 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r2 = r8") +__msg("mark_precise: frame0: regs=r6 stack= before 5: (b7) r1 = 1") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +/* State entering callback body popped from states stack */ +__msg("from 9 to 15: frame1:") +__msg("15: frame1: R1=scalar() R2=0 R10=fp0 cb") +__msg("15: (b7) r0 = 0") +__msg("16: (95) exit") +__msg("returning from callee:") +__msg("to caller at 9:") +/* r1, r4 are always precise for bpf_loop(), + * r6 was marked before backtracking to callback body. + */ +__msg("frame 0: propagating r1,r4,r6") +__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") +__msg("mark_precise: frame0: regs=r1,r4,r6 stack= before 16: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0") +__msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop") +__msg("mark_precise: frame0: parent state regs= stack=:") +__msg("from 16 to 9: safe") +__naked int parent_callee_saved_reg_precise_with_callback(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 1;" /* nr_loops */ + "r2 = %[callback_subprog];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) callback call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals), + __imm_ptr(callback_subprog), + __imm(bpf_loop) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("9: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 9 first_idx 6") +__msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: parent state regs= stack=-8:") +__msg("mark_precise: frame0: last_idx 13 first_idx 0") +__msg("mark_precise: frame0: regs= stack=-8 before 13: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 12: (bf) r0 = r1") +__msg("mark_precise: frame1: regs= stack= before 5: (85) call pc+6") +__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_stack_slot_precise(void) +{ + asm volatile ( + /* spill reg */ + "r6 = 3;" + "*(u64 *)(r10 - 8) = r6;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call identity_subprog;" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r6 = *(u64 *)(r10 - 8);" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("9: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 9 first_idx 6") +__msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: parent state regs= stack=-8:") +__msg("mark_precise: frame0: last_idx 5 first_idx 0") +__msg("mark_precise: frame0: regs= stack=-8 before 5: (85) call pc+6") +__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_stack_slot_precise_global(void) +{ + asm volatile ( + /* spill reg */ + "r6 = 3;" + "*(u64 *)(r10 - 8) = r6;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call global_identity_subprog;" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r6 = *(u64 *)(r10 - 8);" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +/* First simulated path does not include callback body */ +__msg("14: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 14 first_idx 10") +__msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: regs= stack=-8 before 10: (85) call bpf_loop") +__msg("mark_precise: frame0: parent state regs= stack=-8:") +__msg("mark_precise: frame0: last_idx 9 first_idx 0 subseq_idx 10") +__msg("mark_precise: frame0: regs= stack=-8 before 9: (b7) r4 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 8: (b7) r3 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r2 = r8") +__msg("mark_precise: frame0: regs= stack=-8 before 6: (bf) r1 = r6") +__msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -8) = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +/* State entering callback body popped from states stack */ +__msg("from 10 to 17: frame1:") +__msg("17: frame1: R1=scalar() R2=0 R10=fp0 cb") +__msg("17: (b7) r0 = 0") +__msg("18: (95) exit") +__msg("returning from callee:") +__msg("to caller at 10:") +/* r1, r4 are always precise for bpf_loop(), + * fp-8 was marked before backtracking to callback body. + */ +__msg("frame 0: propagating r1,r4,fp-8") +__msg("mark_precise: frame0: last_idx 10 first_idx 10 subseq_idx -1") +__msg("mark_precise: frame0: regs=r1,r4 stack=-8 before 18: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0") +__msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181") +__msg("mark_precise: frame0: parent state regs= stack=:") +__msg("from 18 to 10: safe") +__naked int parent_stack_slot_precise_with_callback(void) +{ + asm volatile ( + /* spill reg */ + "r6 = 3;" + "*(u64 *)(r10 - 8) = r6;" + + /* ensure we have callback frame in jump history */ + "r1 = r6;" /* nr_loops */ + "r2 = %[callback_subprog];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r6 = *(u64 *)(r10 - 8);" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals), + __imm_ptr(callback_subprog), + __imm(bpf_loop) + : __clobber_common, "r6" + ); +} + +__noinline __used +static __u64 subprog_with_precise_arg(__u64 x) +{ + return vals[x]; /* x is forced to be precise */ +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("8: (0f) r2 += r1") +__msg("mark_precise: frame1: last_idx 8 first_idx 0") +__msg("mark_precise: frame1: regs=r1 stack= before 6: (18) r2 = ") +__msg("mark_precise: frame1: regs=r1 stack= before 5: (67) r1 <<= 2") +__msg("mark_precise: frame1: regs=r1 stack= before 2: (85) call pc+2") +__msg("mark_precise: frame0: regs=r1 stack= before 1: (bf) r1 = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 0: (b7) r6 = 3") +__naked int subprog_arg_precise(void) +{ + asm volatile ( + "r6 = 3;" + "r1 = r6;" + /* subprog_with_precise_arg expects its argument to be + * precise, so r1->r6 will be marked precise from inside the + * subprog + */ + "call subprog_with_precise_arg;" + "r0 += r6;" + "exit;" + : + : + : __clobber_common, "r6" + ); +} + +/* r1 is pointer to stack slot; + * r2 is a register to spill into that slot + * subprog also spills r2 into its own stack slot + */ +__naked __noinline __used +static __u64 subprog_spill_reg_precise(void) +{ + asm volatile ( + /* spill to parent stack */ + "*(u64 *)(r1 + 0) = r2;" + /* spill to subprog stack (we use -16 offset to avoid + * accidental confusion with parent's -8 stack slot in + * verifier log output) + */ + "*(u64 *)(r10 - 16) = r2;" + /* use both spills as return result to propagete precision everywhere */ + "r0 = *(u64 *)(r10 - 16);" + "r2 = *(u64 *)(r1 + 0);" + "r0 += r2;" + "exit;" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +/* precision backtracking can't currently handle stack access not through r10, + * so we won't be able to mark stack slot fp-8 as precise, and so will + * fallback to forcing all as precise + */ +__msg("mark_precise: frame0: falling back to forcing all scalars precise") +__naked int subprog_spill_into_parent_stack_slot_precise(void) +{ + asm volatile ( + "r6 = 1;" + + /* pass pointer to stack slot and r6 to subprog; + * r6 will be marked precise and spilled into fp-8 slot, which + * also should be marked precise + */ + "r1 = r10;" + "r1 += -8;" + "r2 = r6;" + "call subprog_spill_reg_precise;" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r7 = *(u64 *)(r10 - 8);" + + "r7 *= 4;" + "r1 = %[vals];" + /* here r7 is forced to be precise and has to be propagated + * back to the beginning, handling subprog call and logic + */ + "r1 += r7;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6", "r7" + ); +} + +__naked __noinline __used +static __u64 subprog_with_checkpoint(void) +{ + asm volatile ( + "r0 = 0;" + /* guaranteed checkpoint if BPF_F_TEST_STATE_FREQ is used */ + "goto +0;" + "exit;" + ); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_subreg.c b/tools/testing/selftests/bpf/progs/verifier_subreg.c new file mode 100644 index 0000000000..8613ea160d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_subreg.c @@ -0,0 +1,673 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/subreg.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +/* This file contains sub-register zero extension checks for insns defining + * sub-registers, meaning: + * - All insns under BPF_ALU class. Their BPF_ALU32 variants or narrow width + * forms (BPF_END) could define sub-registers. + * - Narrow direct loads, BPF_B/H/W | BPF_LDX. + * - BPF_LD is not exposed to JIT back-ends, so no need for testing. + * + * "get_prandom_u32" is used to initialize low 32-bit of some registers to + * prevent potential optimizations done by verifier or JIT back-ends which could + * optimize register back into constant when range info shows one register is a + * constant. + */ + +SEC("socket") +__description("add32 reg zero extend check") +__success __success_unpriv __retval(0) +__naked void add32_reg_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = r0; \ + r0 = 0x100000000 ll; \ + w0 += w1; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("add32 imm zero extend check") +__success __success_unpriv __retval(0) +__naked void add32_imm_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + /* An insn could have no effect on the low 32-bit, for example:\ + * a = a + 0 \ + * a = a | 0 \ + * a = a & -1 \ + * But, they should still zero high 32-bit. \ + */ \ + w0 += 0; \ + r0 >>= 32; \ + r6 = r0; \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 += -2; \ + r0 >>= 32; \ + r0 |= r6; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("sub32 reg zero extend check") +__success __success_unpriv __retval(0) +__naked void sub32_reg_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = r0; \ + r0 = 0x1ffffffff ll; \ + w0 -= w1; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("sub32 imm zero extend check") +__success __success_unpriv __retval(0) +__naked void sub32_imm_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 -= 0; \ + r0 >>= 32; \ + r6 = r0; \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 -= 1; \ + r0 >>= 32; \ + r0 |= r6; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("mul32 reg zero extend check") +__success __success_unpriv __retval(0) +__naked void mul32_reg_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = r0; \ + r0 = 0x100000001 ll; \ + w0 *= w1; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("mul32 imm zero extend check") +__success __success_unpriv __retval(0) +__naked void mul32_imm_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 *= 1; \ + r0 >>= 32; \ + r6 = r0; \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 *= -1; \ + r0 >>= 32; \ + r0 |= r6; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("div32 reg zero extend check") +__success __success_unpriv __retval(0) +__naked void div32_reg_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = r0; \ + r0 = -1; \ + w0 /= w1; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("div32 imm zero extend check") +__success __success_unpriv __retval(0) +__naked void div32_imm_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 /= 1; \ + r0 >>= 32; \ + r6 = r0; \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 /= 2; \ + r0 >>= 32; \ + r0 |= r6; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("or32 reg zero extend check") +__success __success_unpriv __retval(0) +__naked void or32_reg_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = r0; \ + r0 = 0x100000001 ll; \ + w0 |= w1; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("or32 imm zero extend check") +__success __success_unpriv __retval(0) +__naked void or32_imm_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 |= 0; \ + r0 >>= 32; \ + r6 = r0; \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 |= 1; \ + r0 >>= 32; \ + r0 |= r6; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("and32 reg zero extend check") +__success __success_unpriv __retval(0) +__naked void and32_reg_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x100000000 ll; \ + r1 |= r0; \ + r0 = 0x1ffffffff ll; \ + w0 &= w1; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("and32 imm zero extend check") +__success __success_unpriv __retval(0) +__naked void and32_imm_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 &= -1; \ + r0 >>= 32; \ + r6 = r0; \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 &= -2; \ + r0 >>= 32; \ + r0 |= r6; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("lsh32 reg zero extend check") +__success __success_unpriv __retval(0) +__naked void lsh32_reg_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x100000000 ll; \ + r0 |= r1; \ + r1 = 1; \ + w0 <<= w1; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("lsh32 imm zero extend check") +__success __success_unpriv __retval(0) +__naked void lsh32_imm_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 <<= 0; \ + r0 >>= 32; \ + r6 = r0; \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 <<= 1; \ + r0 >>= 32; \ + r0 |= r6; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("rsh32 reg zero extend check") +__success __success_unpriv __retval(0) +__naked void rsh32_reg_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + r1 = 1; \ + w0 >>= w1; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("rsh32 imm zero extend check") +__success __success_unpriv __retval(0) +__naked void rsh32_imm_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 >>= 0; \ + r0 >>= 32; \ + r6 = r0; \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 >>= 1; \ + r0 >>= 32; \ + r0 |= r6; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("neg32 reg zero extend check") +__success __success_unpriv __retval(0) +__naked void neg32_reg_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 = -w0; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("mod32 reg zero extend check") +__success __success_unpriv __retval(0) +__naked void mod32_reg_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = r0; \ + r0 = -1; \ + w0 %%= w1; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("mod32 imm zero extend check") +__success __success_unpriv __retval(0) +__naked void mod32_imm_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 %%= 1; \ + r0 >>= 32; \ + r6 = r0; \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 %%= 2; \ + r0 >>= 32; \ + r0 |= r6; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("xor32 reg zero extend check") +__success __success_unpriv __retval(0) +__naked void xor32_reg_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = r0; \ + r0 = 0x100000000 ll; \ + w0 ^= w1; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("xor32 imm zero extend check") +__success __success_unpriv __retval(0) +__naked void xor32_imm_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 ^= 1; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("mov32 reg zero extend check") +__success __success_unpriv __retval(0) +__naked void mov32_reg_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x100000000 ll; \ + r1 |= r0; \ + r0 = 0x100000000 ll; \ + w0 = w1; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("mov32 imm zero extend check") +__success __success_unpriv __retval(0) +__naked void mov32_imm_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 = 0; \ + r0 >>= 32; \ + r6 = r0; \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 = 1; \ + r0 >>= 32; \ + r0 |= r6; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("arsh32 reg zero extend check") +__success __success_unpriv __retval(0) +__naked void arsh32_reg_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + r1 = 1; \ + w0 s>>= w1; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("arsh32 imm zero extend check") +__success __success_unpriv __retval(0) +__naked void arsh32_imm_zero_extend_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 s>>= 0; \ + r0 >>= 32; \ + r6 = r0; \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + w0 s>>= 1; \ + r0 >>= 32; \ + r0 |= r6; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("end16 (to_le) reg zero extend check") +__success __success_unpriv __retval(0) +__naked void le_reg_zero_extend_check_1(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r6 = r0; \ + r6 <<= 32; \ + call %[bpf_get_prandom_u32]; \ + r0 |= r6; \ + r0 = le16 r0; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("end32 (to_le) reg zero extend check") +__success __success_unpriv __retval(0) +__naked void le_reg_zero_extend_check_2(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r6 = r0; \ + r6 <<= 32; \ + call %[bpf_get_prandom_u32]; \ + r0 |= r6; \ + r0 = le32 r0; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("end16 (to_be) reg zero extend check") +__success __success_unpriv __retval(0) +__naked void be_reg_zero_extend_check_1(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r6 = r0; \ + r6 <<= 32; \ + call %[bpf_get_prandom_u32]; \ + r0 |= r6; \ + r0 = be16 r0; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("end32 (to_be) reg zero extend check") +__success __success_unpriv __retval(0) +__naked void be_reg_zero_extend_check_2(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r6 = r0; \ + r6 <<= 32; \ + call %[bpf_get_prandom_u32]; \ + r0 |= r6; \ + r0 = be32 r0; \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("ldx_b zero extend check") +__success __success_unpriv __retval(0) +__naked void ldx_b_zero_extend_check(void) +{ + asm volatile (" \ + r6 = r10; \ + r6 += -4; \ + r7 = 0xfaceb00c; \ + *(u32*)(r6 + 0) = r7; \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + r0 = *(u8*)(r6 + 0); \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("ldx_h zero extend check") +__success __success_unpriv __retval(0) +__naked void ldx_h_zero_extend_check(void) +{ + asm volatile (" \ + r6 = r10; \ + r6 += -4; \ + r7 = 0xfaceb00c; \ + *(u32*)(r6 + 0) = r7; \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + r0 = *(u16*)(r6 + 0); \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("ldx_w zero extend check") +__success __success_unpriv __retval(0) +__naked void ldx_w_zero_extend_check(void) +{ + asm volatile (" \ + r6 = r10; \ + r6 += -4; \ + r7 = 0xfaceb00c; \ + *(u32*)(r6 + 0) = r7; \ + call %[bpf_get_prandom_u32]; \ + r1 = 0x1000000000 ll; \ + r0 |= r1; \ + r0 = *(u32*)(r6 + 0); \ + r0 >>= 32; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_typedef.c b/tools/testing/selftests/bpf/progs/verifier_typedef.c new file mode 100644 index 0000000000..08481cfaac --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_typedef.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("fentry/bpf_fentry_test_sinfo") +__description("typedef: resolve") +__success __retval(0) +__naked void resolve_typedef(void) +{ + asm volatile (" \ + r1 = *(u64 *)(r1 +0); \ + r2 = *(u64 *)(r1 +%[frags_offs]); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(frags_offs, + offsetof(struct skb_shared_info, frags)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_uninit.c b/tools/testing/selftests/bpf/progs/verifier_uninit.c new file mode 100644 index 0000000000..7718cd7d19 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_uninit.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/uninit.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "../../../include/linux/filter.h" +#include "bpf_misc.h" + +SEC("socket") +__description("read uninitialized register") +__failure __msg("R2 !read_ok") +__failure_unpriv +__naked void read_uninitialized_register(void) +{ + asm volatile (" \ + r0 = r2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("read invalid register") +__failure __msg("R15 is invalid") +__failure_unpriv +__naked void read_invalid_register(void) +{ + asm volatile (" \ + .8byte %[mov64_reg]; \ + exit; \ +" : + : __imm_insn(mov64_reg, BPF_MOV64_REG(BPF_REG_0, -1)) + : __clobber_all); +} + +SEC("socket") +__description("program doesn't init R0 before exit") +__failure __msg("R0 !read_ok") +__failure_unpriv +__naked void t_init_r0_before_exit(void) +{ + asm volatile (" \ + r2 = r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("program doesn't init R0 before exit in all branches") +__failure __msg("R0 !read_ok") +__msg_unpriv("R1 pointer comparison") +__naked void before_exit_in_all_branches(void) +{ + asm volatile (" \ + if r1 >= 0 goto l0_%=; \ + r0 = 1; \ + r0 += 2; \ +l0_%=: exit; \ +" ::: __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_unpriv.c b/tools/testing/selftests/bpf/progs/verifier_unpriv.c new file mode 100644 index 0000000000..7ea535bfba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_unpriv.c @@ -0,0 +1,726 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/unpriv.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "../../../include/linux/filter.h" +#include "bpf_misc.h" + +#define BPF_SK_LOOKUP(func) \ + /* struct bpf_sock_tuple tuple = {} */ \ + "r2 = 0;" \ + "*(u32*)(r10 - 8) = r2;" \ + "*(u64*)(r10 - 16) = r2;" \ + "*(u64*)(r10 - 24) = r2;" \ + "*(u64*)(r10 - 32) = r2;" \ + "*(u64*)(r10 - 40) = r2;" \ + "*(u64*)(r10 - 48) = r2;" \ + /* sk = func(ctx, &tuple, sizeof tuple, 0, 0) */ \ + "r2 = r10;" \ + "r2 += -48;" \ + "r3 = %[sizeof_bpf_sock_tuple];"\ + "r4 = 0;" \ + "r5 = 0;" \ + "call %[" #func "];" + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +void dummy_prog_42_socket(void); +void dummy_prog_24_socket(void); +void dummy_prog_loop1_socket(void); + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 4); + __uint(key_size, sizeof(int)); + __array(values, void (void)); +} map_prog1_socket SEC(".maps") = { + .values = { + [0] = (void *)&dummy_prog_42_socket, + [1] = (void *)&dummy_prog_loop1_socket, + [2] = (void *)&dummy_prog_24_socket, + }, +}; + +SEC("socket") +__auxiliary __auxiliary_unpriv +__naked void dummy_prog_42_socket(void) +{ + asm volatile ("r0 = 42; exit;"); +} + +SEC("socket") +__auxiliary __auxiliary_unpriv +__naked void dummy_prog_24_socket(void) +{ + asm volatile ("r0 = 24; exit;"); +} + +SEC("socket") +__auxiliary __auxiliary_unpriv +__naked void dummy_prog_loop1_socket(void) +{ + asm volatile (" \ + r3 = 1; \ + r2 = %[map_prog1_socket] ll; \ + call %[bpf_tail_call]; \ + r0 = 41; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket) + : __clobber_all); +} + +SEC("socket") +__description("unpriv: return pointer") +__success __failure_unpriv __msg_unpriv("R0 leaks addr") +__retval(POINTER_VALUE) +__naked void unpriv_return_pointer(void) +{ + asm volatile (" \ + r0 = r10; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: add const to pointer") +__success __success_unpriv __retval(0) +__naked void unpriv_add_const_to_pointer(void) +{ + asm volatile (" \ + r1 += 8; \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: add pointer to pointer") +__failure __msg("R1 pointer += pointer") +__failure_unpriv +__naked void unpriv_add_pointer_to_pointer(void) +{ + asm volatile (" \ + r1 += r10; \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: neg pointer") +__success __failure_unpriv __msg_unpriv("R1 pointer arithmetic") +__retval(0) +__naked void unpriv_neg_pointer(void) +{ + asm volatile (" \ + r1 = -r1; \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: cmp pointer with const") +__success __failure_unpriv __msg_unpriv("R1 pointer comparison") +__retval(0) +__naked void unpriv_cmp_pointer_with_const(void) +{ + asm volatile (" \ + if r1 == 0 goto l0_%=; \ +l0_%=: r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: cmp pointer with pointer") +__success __failure_unpriv __msg_unpriv("R10 pointer comparison") +__retval(0) +__naked void unpriv_cmp_pointer_with_pointer(void) +{ + asm volatile (" \ + if r1 == r10 goto l0_%=; \ +l0_%=: r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tracepoint") +__description("unpriv: check that printk is disallowed") +__success +__naked void check_that_printk_is_disallowed(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r1 = r10; \ + r1 += -8; \ + r2 = 8; \ + r3 = r1; \ + call %[bpf_trace_printk]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_trace_printk) + : __clobber_all); +} + +SEC("socket") +__description("unpriv: pass pointer to helper function") +__success __failure_unpriv __msg_unpriv("R4 leaks addr") +__retval(0) +__naked void pass_pointer_to_helper_function(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + r3 = r2; \ + r4 = r2; \ + call %[bpf_map_update_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_update_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("unpriv: indirectly pass pointer on stack to helper function") +__success __failure_unpriv +__msg_unpriv("invalid indirect read from stack R2 off -8+0 size 8") +__retval(0) +__naked void on_stack_to_helper_function(void) +{ + asm volatile (" \ + *(u64*)(r10 - 8) = r10; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("unpriv: mangle pointer on stack 1") +__success __failure_unpriv __msg_unpriv("attempt to corrupt spilled") +__retval(0) +__naked void mangle_pointer_on_stack_1(void) +{ + asm volatile (" \ + *(u64*)(r10 - 8) = r10; \ + r0 = 0; \ + *(u32*)(r10 - 8) = r0; \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: mangle pointer on stack 2") +__success __failure_unpriv __msg_unpriv("attempt to corrupt spilled") +__retval(0) +__naked void mangle_pointer_on_stack_2(void) +{ + asm volatile (" \ + *(u64*)(r10 - 8) = r10; \ + r0 = 0; \ + *(u8*)(r10 - 1) = r0; \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: read pointer from stack in small chunks") +__failure __msg("invalid size") +__failure_unpriv +__naked void from_stack_in_small_chunks(void) +{ + asm volatile (" \ + *(u64*)(r10 - 8) = r10; \ + r0 = *(u32*)(r10 - 8); \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: write pointer into ctx") +__failure __msg("invalid bpf_context access") +__failure_unpriv __msg_unpriv("R1 leaks addr") +__naked void unpriv_write_pointer_into_ctx(void) +{ + asm volatile (" \ + *(u64*)(r1 + 0) = r1; \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: spill/fill of ctx") +__success __success_unpriv __retval(0) +__naked void unpriv_spill_fill_of_ctx(void) +{ + asm volatile (" \ + r6 = r10; \ + r6 += -8; \ + *(u64*)(r6 + 0) = r1; \ + r1 = *(u64*)(r6 + 0); \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("unpriv: spill/fill of ctx 2") +__success __retval(0) +__naked void spill_fill_of_ctx_2(void) +{ + asm volatile (" \ + r6 = r10; \ + r6 += -8; \ + *(u64*)(r6 + 0) = r1; \ + r1 = *(u64*)(r6 + 0); \ + call %[bpf_get_hash_recalc]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_hash_recalc) + : __clobber_all); +} + +SEC("tc") +__description("unpriv: spill/fill of ctx 3") +__failure __msg("R1 type=fp expected=ctx") +__naked void spill_fill_of_ctx_3(void) +{ + asm volatile (" \ + r6 = r10; \ + r6 += -8; \ + *(u64*)(r6 + 0) = r1; \ + *(u64*)(r6 + 0) = r10; \ + r1 = *(u64*)(r6 + 0); \ + call %[bpf_get_hash_recalc]; \ + exit; \ +" : + : __imm(bpf_get_hash_recalc) + : __clobber_all); +} + +SEC("tc") +__description("unpriv: spill/fill of ctx 4") +__failure __msg("R1 type=scalar expected=ctx") +__naked void spill_fill_of_ctx_4(void) +{ + asm volatile (" \ + r6 = r10; \ + r6 += -8; \ + *(u64*)(r6 + 0) = r1; \ + r0 = 1; \ + lock *(u64 *)(r10 - 8) += r0; \ + r1 = *(u64*)(r6 + 0); \ + call %[bpf_get_hash_recalc]; \ + exit; \ +" : + : __imm(bpf_get_hash_recalc) + : __clobber_all); +} + +SEC("tc") +__description("unpriv: spill/fill of different pointers stx") +__failure __msg("same insn cannot be used with different pointers") +__naked void fill_of_different_pointers_stx(void) +{ + asm volatile (" \ + r3 = 42; \ + r6 = r10; \ + r6 += -8; \ + if r1 == 0 goto l0_%=; \ + r2 = r10; \ + r2 += -16; \ + *(u64*)(r6 + 0) = r2; \ +l0_%=: if r1 != 0 goto l1_%=; \ + *(u64*)(r6 + 0) = r1; \ +l1_%=: r1 = *(u64*)(r6 + 0); \ + *(u32*)(r1 + %[__sk_buff_mark]) = r3; \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)) + : __clobber_all); +} + +/* Same as above, but use BPF_ST_MEM to save 42 + * instead of BPF_STX_MEM. + */ +SEC("tc") +__description("unpriv: spill/fill of different pointers st") +__failure __msg("same insn cannot be used with different pointers") +__naked void fill_of_different_pointers_st(void) +{ + asm volatile (" \ + r6 = r10; \ + r6 += -8; \ + if r1 == 0 goto l0_%=; \ + r2 = r10; \ + r2 += -16; \ + *(u64*)(r6 + 0) = r2; \ +l0_%=: if r1 != 0 goto l1_%=; \ + *(u64*)(r6 + 0) = r1; \ +l1_%=: r1 = *(u64*)(r6 + 0); \ + .8byte %[st_mem]; \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)), + __imm_insn(st_mem, + BPF_ST_MEM(BPF_W, BPF_REG_1, offsetof(struct __sk_buff, mark), 42)) + : __clobber_all); +} + +SEC("tc") +__description("unpriv: spill/fill of different pointers stx - ctx and sock") +__failure __msg("type=ctx expected=sock") +__naked void pointers_stx_ctx_and_sock(void) +{ + asm volatile (" \ + r8 = r1; \ + /* struct bpf_sock *sock = bpf_sock_lookup(...); */\ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r2 = r0; \ + /* u64 foo; */ \ + /* void *target = &foo; */ \ + r6 = r10; \ + r6 += -8; \ + r1 = r8; \ + /* if (skb == NULL) *target = sock; */ \ + if r1 == 0 goto l0_%=; \ + *(u64*)(r6 + 0) = r2; \ +l0_%=: /* else *target = skb; */ \ + if r1 != 0 goto l1_%=; \ + *(u64*)(r6 + 0) = r1; \ +l1_%=: /* struct __sk_buff *skb = *target; */ \ + r1 = *(u64*)(r6 + 0); \ + /* skb->mark = 42; */ \ + r3 = 42; \ + *(u32*)(r1 + %[__sk_buff_mark]) = r3; \ + /* if (sk) bpf_sk_release(sk) */ \ + if r1 == 0 goto l2_%=; \ + call %[bpf_sk_release]; \ +l2_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("unpriv: spill/fill of different pointers stx - leak sock") +__failure +//.errstr = "same insn cannot be used with different pointers", +__msg("Unreleased reference") +__naked void different_pointers_stx_leak_sock(void) +{ + asm volatile (" \ + r8 = r1; \ + /* struct bpf_sock *sock = bpf_sock_lookup(...); */\ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r2 = r0; \ + /* u64 foo; */ \ + /* void *target = &foo; */ \ + r6 = r10; \ + r6 += -8; \ + r1 = r8; \ + /* if (skb == NULL) *target = sock; */ \ + if r1 == 0 goto l0_%=; \ + *(u64*)(r6 + 0) = r2; \ +l0_%=: /* else *target = skb; */ \ + if r1 != 0 goto l1_%=; \ + *(u64*)(r6 + 0) = r1; \ +l1_%=: /* struct __sk_buff *skb = *target; */ \ + r1 = *(u64*)(r6 + 0); \ + /* skb->mark = 42; */ \ + r3 = 42; \ + *(u32*)(r1 + %[__sk_buff_mark]) = r3; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("unpriv: spill/fill of different pointers stx - sock and ctx (read)") +__failure __msg("same insn cannot be used with different pointers") +__naked void stx_sock_and_ctx_read(void) +{ + asm volatile (" \ + r8 = r1; \ + /* struct bpf_sock *sock = bpf_sock_lookup(...); */\ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r2 = r0; \ + /* u64 foo; */ \ + /* void *target = &foo; */ \ + r6 = r10; \ + r6 += -8; \ + r1 = r8; \ + /* if (skb) *target = skb */ \ + if r1 == 0 goto l0_%=; \ + *(u64*)(r6 + 0) = r1; \ +l0_%=: /* else *target = sock */ \ + if r1 != 0 goto l1_%=; \ + *(u64*)(r6 + 0) = r2; \ +l1_%=: /* struct bpf_sock *sk = *target; */ \ + r1 = *(u64*)(r6 + 0); \ + /* if (sk) u32 foo = sk->mark; bpf_sk_release(sk); */\ + if r1 == 0 goto l2_%=; \ + r3 = *(u32*)(r1 + %[bpf_sock_mark]); \ + call %[bpf_sk_release]; \ +l2_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(bpf_sock_mark, offsetof(struct bpf_sock, mark)), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("tc") +__description("unpriv: spill/fill of different pointers stx - sock and ctx (write)") +__failure +//.errstr = "same insn cannot be used with different pointers", +__msg("cannot write into sock") +__naked void stx_sock_and_ctx_write(void) +{ + asm volatile (" \ + r8 = r1; \ + /* struct bpf_sock *sock = bpf_sock_lookup(...); */\ +" BPF_SK_LOOKUP(bpf_sk_lookup_tcp) +" r2 = r0; \ + /* u64 foo; */ \ + /* void *target = &foo; */ \ + r6 = r10; \ + r6 += -8; \ + r1 = r8; \ + /* if (skb) *target = skb */ \ + if r1 == 0 goto l0_%=; \ + *(u64*)(r6 + 0) = r1; \ +l0_%=: /* else *target = sock */ \ + if r1 != 0 goto l1_%=; \ + *(u64*)(r6 + 0) = r2; \ +l1_%=: /* struct bpf_sock *sk = *target; */ \ + r1 = *(u64*)(r6 + 0); \ + /* if (sk) sk->mark = 42; bpf_sk_release(sk); */\ + if r1 == 0 goto l2_%=; \ + r3 = 42; \ + *(u32*)(r1 + %[bpf_sock_mark]) = r3; \ + call %[bpf_sk_release]; \ +l2_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_sk_lookup_tcp), + __imm(bpf_sk_release), + __imm_const(bpf_sock_mark, offsetof(struct bpf_sock, mark)), + __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)) + : __clobber_all); +} + +SEC("socket") +__description("unpriv: write pointer into map elem value") +__success __failure_unpriv __msg_unpriv("R0 leaks addr") +__retval(0) +__naked void pointer_into_map_elem_value(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + *(u64*)(r0 + 0) = r0; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("alu32: mov u32 const") +__success __failure_unpriv __msg_unpriv("R7 invalid mem access 'scalar'") +__retval(0) +__naked void alu32_mov_u32_const(void) +{ + asm volatile (" \ + w7 = 0; \ + w7 &= 1; \ + w0 = w7; \ + if r0 == 0 goto l0_%=; \ + r0 = *(u64*)(r7 + 0); \ +l0_%=: exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: partial copy of pointer") +__success __failure_unpriv __msg_unpriv("R10 partial copy") +__retval(0) +__naked void unpriv_partial_copy_of_pointer(void) +{ + asm volatile (" \ + w1 = w10; \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: pass pointer to tail_call") +__success __failure_unpriv __msg_unpriv("R3 leaks addr into helper") +__retval(0) +__naked void pass_pointer_to_tail_call(void) +{ + asm volatile (" \ + r3 = r1; \ + r2 = %[map_prog1_socket] ll; \ + call %[bpf_tail_call]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_prog1_socket) + : __clobber_all); +} + +SEC("socket") +__description("unpriv: cmp map pointer with zero") +__success __failure_unpriv __msg_unpriv("R1 pointer comparison") +__retval(0) +__naked void cmp_map_pointer_with_zero(void) +{ + asm volatile (" \ + r1 = 0; \ + r1 = %[map_hash_8b] ll; \ + if r1 == 0 goto l0_%=; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("unpriv: write into frame pointer") +__failure __msg("frame pointer is read only") +__failure_unpriv +__naked void unpriv_write_into_frame_pointer(void) +{ + asm volatile (" \ + r10 = r1; \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: spill/fill frame pointer") +__failure __msg("frame pointer is read only") +__failure_unpriv +__naked void unpriv_spill_fill_frame_pointer(void) +{ + asm volatile (" \ + r6 = r10; \ + r6 += -8; \ + *(u64*)(r6 + 0) = r10; \ + r10 = *(u64*)(r6 + 0); \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: cmp of frame pointer") +__success __failure_unpriv __msg_unpriv("R10 pointer comparison") +__retval(0) +__naked void unpriv_cmp_of_frame_pointer(void) +{ + asm volatile (" \ + if r10 == 0 goto l0_%=; \ +l0_%=: r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: adding of fp, reg") +__success __failure_unpriv +__msg_unpriv("R1 stack pointer arithmetic goes out of range") +__retval(0) +__naked void unpriv_adding_of_fp_reg(void) +{ + asm volatile (" \ + r0 = 0; \ + r1 = 0; \ + r1 += r10; \ + *(u64*)(r1 - 8) = r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: adding of fp, imm") +__success __failure_unpriv +__msg_unpriv("R1 stack pointer arithmetic goes out of range") +__retval(0) +__naked void unpriv_adding_of_fp_imm(void) +{ + asm volatile (" \ + r0 = 0; \ + r1 = r10; \ + r1 += 0; \ + *(u64*)(r1 - 8) = r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: cmp of stack pointer") +__success __failure_unpriv __msg_unpriv("R2 pointer comparison") +__retval(0) +__naked void unpriv_cmp_of_stack_pointer(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + if r2 == 0 goto l0_%=; \ +l0_%=: r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_unpriv_perf.c b/tools/testing/selftests/bpf/progs/verifier_unpriv_perf.c new file mode 100644 index 0000000000..4d77407a0a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_unpriv_perf.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/unpriv.c */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("perf_event") +__description("unpriv: spill/fill of different pointers ldx") +__failure __msg("same insn cannot be used with different pointers") +__naked void fill_of_different_pointers_ldx(void) +{ + asm volatile (" \ + r6 = r10; \ + r6 += -8; \ + if r1 == 0 goto l0_%=; \ + r2 = r10; \ + r2 += %[__imm_0]; \ + *(u64*)(r6 + 0) = r2; \ +l0_%=: if r1 != 0 goto l1_%=; \ + *(u64*)(r6 + 0) = r1; \ +l1_%=: r1 = *(u64*)(r6 + 0); \ + r1 = *(u64*)(r1 + %[sample_period]); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(__imm_0, + -(__s32) offsetof(struct bpf_perf_event_data, sample_period) - 8), + __imm_const(sample_period, + offsetof(struct bpf_perf_event_data, sample_period)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_value.c b/tools/testing/selftests/bpf/progs/verifier_value.c new file mode 100644 index 0000000000..b5af6b6f5a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_value.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/value.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct test_val); +} map_hash_48b SEC(".maps"); + +SEC("socket") +__description("map element value store of cleared call register") +__failure __msg("R1 !read_ok") +__failure_unpriv __msg_unpriv("R1 !read_ok") +__naked void store_of_cleared_call_register(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("socket") +__description("map element value with unaligned store") +__success __failure_unpriv __msg_unpriv("R0 leaks addr") +__retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void element_value_with_unaligned_store(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r0 += 3; \ + r1 = 42; \ + *(u64*)(r0 + 0) = r1; \ + r1 = 43; \ + *(u64*)(r0 + 2) = r1; \ + r1 = 44; \ + *(u64*)(r0 - 2) = r1; \ + r8 = r0; \ + r1 = 32; \ + *(u64*)(r8 + 0) = r1; \ + r1 = 33; \ + *(u64*)(r8 + 2) = r1; \ + r1 = 34; \ + *(u64*)(r8 - 2) = r1; \ + r8 += 5; \ + r1 = 22; \ + *(u64*)(r8 + 0) = r1; \ + r1 = 23; \ + *(u64*)(r8 + 4) = r1; \ + r1 = 24; \ + *(u64*)(r8 - 7) = r1; \ + r7 = r8; \ + r7 += 3; \ + r1 = 22; \ + *(u64*)(r7 + 0) = r1; \ + r1 = 23; \ + *(u64*)(r7 + 4) = r1; \ + r1 = 24; \ + *(u64*)(r7 - 4) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("socket") +__description("map element value with unaligned load") +__success __failure_unpriv __msg_unpriv("R0 leaks addr") +__retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void element_value_with_unaligned_load(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u32*)(r0 + 0); \ + if r1 >= %[max_entries] goto l0_%=; \ + r0 += 3; \ + r7 = *(u64*)(r0 + 0); \ + r7 = *(u64*)(r0 + 2); \ + r8 = r0; \ + r7 = *(u64*)(r8 + 0); \ + r7 = *(u64*)(r8 + 2); \ + r0 += 5; \ + r7 = *(u64*)(r0 + 0); \ + r7 = *(u64*)(r0 + 4); \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(max_entries, MAX_ENTRIES) + : __clobber_all); +} + +SEC("socket") +__description("map element value is preserved across register spilling") +__success __failure_unpriv __msg_unpriv("R0 leaks addr") +__retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void is_preserved_across_register_spilling(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r0 += %[test_val_foo]; \ + r1 = 42; \ + *(u64*)(r0 + 0) = r1; \ + r1 = r10; \ + r1 += -184; \ + *(u64*)(r1 + 0) = r0; \ + r3 = *(u64*)(r1 + 0); \ + r1 = 42; \ + *(u64*)(r3 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_value_adj_spill.c b/tools/testing/selftests/bpf/progs/verifier_value_adj_spill.c new file mode 100644 index 0000000000..d7a5ba9bbe --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_value_adj_spill.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/value_adj_spill.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct test_val); +} map_hash_48b SEC(".maps"); + +SEC("socket") +__description("map element value is preserved across register spilling") +__success __failure_unpriv __msg_unpriv("R0 leaks addr") +__retval(0) +__naked void is_preserved_across_register_spilling(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 42; \ + *(u64*)(r0 + 0) = r1; \ + r1 = r10; \ + r1 += -184; \ + *(u64*)(r1 + 0) = r0; \ + r3 = *(u64*)(r1 + 0); \ + r1 = 42; \ + *(u64*)(r3 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("socket") +__description("map element value or null is marked on register spilling") +__success __failure_unpriv __msg_unpriv("R0 leaks addr") +__retval(0) +__naked void is_marked_on_register_spilling(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + r1 = r10; \ + r1 += -152; \ + *(u64*)(r1 + 0) = r0; \ + if r0 == 0 goto l0_%=; \ + r3 = *(u64*)(r1 + 0); \ + r1 = 42; \ + *(u64*)(r3 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c new file mode 100644 index 0000000000..71814a7532 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/value_illegal_alu.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct test_val); +} map_hash_48b SEC(".maps"); + +SEC("socket") +__description("map element value illegal alu op, 1") +__failure __msg("R0 bitwise operator &= on pointer") +__failure_unpriv +__naked void value_illegal_alu_op_1(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r0 &= 8; \ + r1 = 22; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("socket") +__description("map element value illegal alu op, 2") +__failure __msg("R0 32-bit pointer arithmetic prohibited") +__failure_unpriv +__naked void value_illegal_alu_op_2(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + w0 += 0; \ + r1 = 22; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("socket") +__description("map element value illegal alu op, 3") +__failure __msg("R0 pointer arithmetic with /= operator") +__failure_unpriv +__naked void value_illegal_alu_op_3(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r0 /= 42; \ + r1 = 22; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("socket") +__description("map element value illegal alu op, 4") +__failure __msg("invalid mem access 'scalar'") +__failure_unpriv __msg_unpriv("R0 pointer arithmetic prohibited") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void value_illegal_alu_op_4(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r0 = be64 r0; \ + r1 = 22; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +SEC("socket") +__description("map element value illegal alu op, 5") +__failure __msg("R0 invalid mem access 'scalar'") +__msg_unpriv("leaking pointer from stack off -8") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void value_illegal_alu_op_5(void) +{ + asm volatile (" \ + r2 = r10; \ + r2 += -8; \ + r1 = 0; \ + *(u64*)(r2 + 0) = r1; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r3 = 4096; \ + r2 = r10; \ + r2 += -8; \ + *(u64*)(r2 + 0) = r0; \ + lock *(u64 *)(r2 + 0) += r3; \ + r0 = *(u64*)(r2 + 0); \ + r1 = 22; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_value_or_null.c b/tools/testing/selftests/bpf/progs/verifier_value_or_null.c new file mode 100644 index 0000000000..8ff668a242 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_value_or_null.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/value_or_null.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct test_val); +} map_hash_48b SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +SEC("tc") +__description("multiple registers share map_lookup_elem result") +__success __retval(0) +__naked void share_map_lookup_elem_result(void) +{ + asm volatile (" \ + r1 = 10; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r4 = r0; \ + if r0 == 0 goto l0_%=; \ + r1 = 0; \ + *(u64*)(r4 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("tc") +__description("alu ops on ptr_to_map_value_or_null, 1") +__failure __msg("R4 pointer arithmetic on map_value_or_null") +__naked void map_value_or_null_1(void) +{ + asm volatile (" \ + r1 = 10; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r4 = r0; \ + r4 += -2; \ + r4 += 2; \ + if r0 == 0 goto l0_%=; \ + r1 = 0; \ + *(u64*)(r4 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("tc") +__description("alu ops on ptr_to_map_value_or_null, 2") +__failure __msg("R4 pointer arithmetic on map_value_or_null") +__naked void map_value_or_null_2(void) +{ + asm volatile (" \ + r1 = 10; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r4 = r0; \ + r4 &= -1; \ + if r0 == 0 goto l0_%=; \ + r1 = 0; \ + *(u64*)(r4 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("tc") +__description("alu ops on ptr_to_map_value_or_null, 3") +__failure __msg("R4 pointer arithmetic on map_value_or_null") +__naked void map_value_or_null_3(void) +{ + asm volatile (" \ + r1 = 10; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r4 = r0; \ + r4 <<= 1; \ + if r0 == 0 goto l0_%=; \ + r1 = 0; \ + *(u64*)(r4 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("tc") +__description("invalid memory access with multiple map_lookup_elem calls") +__failure __msg("R4 !read_ok") +__naked void multiple_map_lookup_elem_calls(void) +{ + asm volatile (" \ + r1 = 10; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + r8 = r1; \ + r7 = r2; \ + call %[bpf_map_lookup_elem]; \ + r4 = r0; \ + r1 = r8; \ + r2 = r7; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 0; \ + *(u64*)(r4 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("tc") +__description("valid indirect map_lookup_elem access with 2nd lookup in branch") +__success __retval(0) +__naked void with_2nd_lookup_in_branch(void) +{ + asm volatile (" \ + r1 = 10; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + r8 = r1; \ + r7 = r2; \ + call %[bpf_map_lookup_elem]; \ + r2 = 10; \ + if r2 != 0 goto l0_%=; \ + r1 = r8; \ + r2 = r7; \ + call %[bpf_map_lookup_elem]; \ +l0_%=: r4 = r0; \ + if r0 == 0 goto l1_%=; \ + r1 = 0; \ + *(u64*)(r4 + 0) = r1; \ +l1_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("invalid map access from else condition") +__failure __msg("R0 unbounded memory access") +__failure_unpriv __msg_unpriv("R0 leaks addr") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void map_access_from_else_condition(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u32*)(r0 + 0); \ + if r1 >= %[__imm_0] goto l1_%=; \ + r1 += 1; \ +l1_%=: r1 <<= 2; \ + r0 += r1; \ + r1 = %[test_val_foo]; \ + *(u64*)(r0 + 0) = r1; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_48b), + __imm_const(__imm_0, MAX_ENTRIES-1), + __imm_const(test_val_foo, offsetof(struct test_val, foo)) + : __clobber_all); +} + +SEC("tc") +__description("map lookup and null branch prediction") +__success __retval(0) +__naked void lookup_and_null_branch_prediction(void) +{ + asm volatile (" \ + r1 = 10; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r6 = r0; \ + if r6 == 0 goto l0_%=; \ + if r6 != 0 goto l0_%=; \ + r10 += 10; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("MAP_VALUE_OR_NULL check_ids() in regsafe()") +__failure __msg("R8 invalid mem access 'map_value_or_null'") +__failure_unpriv __msg_unpriv("") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void null_check_ids_in_regsafe(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + /* r9 = map_lookup_elem(...) */ \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r9 = r0; \ + /* r8 = map_lookup_elem(...) */ \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r8 = r0; \ + /* r7 = ktime_get_ns() */ \ + call %[bpf_ktime_get_ns]; \ + r7 = r0; \ + /* r6 = ktime_get_ns() */ \ + call %[bpf_ktime_get_ns]; \ + r6 = r0; \ + /* if r6 > r7 goto +1 ; no new information about the state is derived from\ + * ; this check, thus produced verifier states differ\ + * ; only in 'insn_idx' \ + * r9 = r8 ; optionally share ID between r9 and r8\ + */ \ + if r6 > r7 goto l0_%=; \ + r9 = r8; \ +l0_%=: /* if r9 == 0 goto <exit> */ \ + if r9 == 0 goto l1_%=; \ + /* read map value via r8, this is not always \ + * safe because r8 might be not equal to r9. \ + */ \ + r0 = *(u64*)(r8 + 0); \ +l1_%=: /* exit 0 */ \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c b/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c new file mode 100644 index 0000000000..5ba6e53571 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c @@ -0,0 +1,1423 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/value_ptr_arith.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <errno.h> +#include "bpf_misc.h" + +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct test_val); +} map_array_48b SEC(".maps"); + +struct other_val { + long long foo; + long long bar; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct other_val); +} map_hash_16b SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, struct test_val); +} map_hash_48b SEC(".maps"); + +SEC("socket") +__description("map access: known scalar += value_ptr unknown vs const") +__success __failure_unpriv +__msg_unpriv("R1 tried to add from different maps, paths or scalars") +__retval(1) +__naked void value_ptr_unknown_vs_const(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_len]); \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + if r0 == 1 goto l0_%=; \ + r1 = %[map_hash_16b] ll; \ + if r0 != 1 goto l1_%=; \ +l0_%=: r1 = %[map_array_48b] ll; \ +l1_%=: call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l2_%=; \ + r4 = *(u8*)(r0 + 0); \ + if r4 == 1 goto l3_%=; \ + r1 = 6; \ + r1 = -r1; \ + r1 &= 0x7; \ + goto l4_%=; \ +l3_%=: r1 = 3; \ +l4_%=: r1 += r0; \ + r0 = *(u8*)(r1 + 0); \ +l2_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b), + __imm_addr(map_hash_16b), + __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)) + : __clobber_all); +} + +SEC("socket") +__description("map access: known scalar += value_ptr const vs unknown") +__success __failure_unpriv +__msg_unpriv("R1 tried to add from different maps, paths or scalars") +__retval(1) +__naked void value_ptr_const_vs_unknown(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_len]); \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + if r0 == 1 goto l0_%=; \ + r1 = %[map_hash_16b] ll; \ + if r0 != 1 goto l1_%=; \ +l0_%=: r1 = %[map_array_48b] ll; \ +l1_%=: call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l2_%=; \ + r4 = *(u8*)(r0 + 0); \ + if r4 == 1 goto l3_%=; \ + r1 = 3; \ + goto l4_%=; \ +l3_%=: r1 = 6; \ + r1 = -r1; \ + r1 &= 0x7; \ +l4_%=: r1 += r0; \ + r0 = *(u8*)(r1 + 0); \ +l2_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b), + __imm_addr(map_hash_16b), + __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)) + : __clobber_all); +} + +SEC("socket") +__description("map access: known scalar += value_ptr const vs const (ne)") +__success __failure_unpriv +__msg_unpriv("R1 tried to add from different maps, paths or scalars") +__retval(1) +__naked void ptr_const_vs_const_ne(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_len]); \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + if r0 == 1 goto l0_%=; \ + r1 = %[map_hash_16b] ll; \ + if r0 != 1 goto l1_%=; \ +l0_%=: r1 = %[map_array_48b] ll; \ +l1_%=: call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l2_%=; \ + r4 = *(u8*)(r0 + 0); \ + if r4 == 1 goto l3_%=; \ + r1 = 3; \ + goto l4_%=; \ +l3_%=: r1 = 5; \ +l4_%=: r1 += r0; \ + r0 = *(u8*)(r1 + 0); \ +l2_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b), + __imm_addr(map_hash_16b), + __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)) + : __clobber_all); +} + +SEC("socket") +__description("map access: known scalar += value_ptr const vs const (eq)") +__success __success_unpriv __retval(1) +__naked void ptr_const_vs_const_eq(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_len]); \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + if r0 == 1 goto l0_%=; \ + r1 = %[map_hash_16b] ll; \ + if r0 != 1 goto l1_%=; \ +l0_%=: r1 = %[map_array_48b] ll; \ +l1_%=: call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l2_%=; \ + r4 = *(u8*)(r0 + 0); \ + if r4 == 1 goto l3_%=; \ + r1 = 5; \ + goto l4_%=; \ +l3_%=: r1 = 5; \ +l4_%=: r1 += r0; \ + r0 = *(u8*)(r1 + 0); \ +l2_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b), + __imm_addr(map_hash_16b), + __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)) + : __clobber_all); +} + +SEC("socket") +__description("map access: known scalar += value_ptr unknown vs unknown (eq)") +__success __success_unpriv __retval(1) +__naked void ptr_unknown_vs_unknown_eq(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_len]); \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + if r0 == 1 goto l0_%=; \ + r1 = %[map_hash_16b] ll; \ + if r0 != 1 goto l1_%=; \ +l0_%=: r1 = %[map_array_48b] ll; \ +l1_%=: call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l2_%=; \ + r4 = *(u8*)(r0 + 0); \ + if r4 == 1 goto l3_%=; \ + r1 = 6; \ + r1 = -r1; \ + r1 &= 0x7; \ + goto l4_%=; \ +l3_%=: r1 = 6; \ + r1 = -r1; \ + r1 &= 0x7; \ +l4_%=: r1 += r0; \ + r0 = *(u8*)(r1 + 0); \ +l2_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b), + __imm_addr(map_hash_16b), + __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)) + : __clobber_all); +} + +SEC("socket") +__description("map access: known scalar += value_ptr unknown vs unknown (lt)") +__success __failure_unpriv +__msg_unpriv("R1 tried to add from different maps, paths or scalars") +__retval(1) +__naked void ptr_unknown_vs_unknown_lt(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_len]); \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + if r0 == 1 goto l0_%=; \ + r1 = %[map_hash_16b] ll; \ + if r0 != 1 goto l1_%=; \ +l0_%=: r1 = %[map_array_48b] ll; \ +l1_%=: call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l2_%=; \ + r4 = *(u8*)(r0 + 0); \ + if r4 == 1 goto l3_%=; \ + r1 = 6; \ + r1 = -r1; \ + r1 &= 0x3; \ + goto l4_%=; \ +l3_%=: r1 = 6; \ + r1 = -r1; \ + r1 &= 0x7; \ +l4_%=: r1 += r0; \ + r0 = *(u8*)(r1 + 0); \ +l2_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b), + __imm_addr(map_hash_16b), + __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)) + : __clobber_all); +} + +SEC("socket") +__description("map access: known scalar += value_ptr unknown vs unknown (gt)") +__success __failure_unpriv +__msg_unpriv("R1 tried to add from different maps, paths or scalars") +__retval(1) +__naked void ptr_unknown_vs_unknown_gt(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_len]); \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + if r0 == 1 goto l0_%=; \ + r1 = %[map_hash_16b] ll; \ + if r0 != 1 goto l1_%=; \ +l0_%=: r1 = %[map_array_48b] ll; \ +l1_%=: call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l2_%=; \ + r4 = *(u8*)(r0 + 0); \ + if r4 == 1 goto l3_%=; \ + r1 = 6; \ + r1 = -r1; \ + r1 &= 0x7; \ + goto l4_%=; \ +l3_%=: r1 = 6; \ + r1 = -r1; \ + r1 &= 0x3; \ +l4_%=: r1 += r0; \ + r0 = *(u8*)(r1 + 0); \ +l2_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b), + __imm_addr(map_hash_16b), + __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)) + : __clobber_all); +} + +SEC("socket") +__description("map access: known scalar += value_ptr from different maps") +__success __success_unpriv __retval(1) +__naked void value_ptr_from_different_maps(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_len]); \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + if r0 == 1 goto l0_%=; \ + r1 = %[map_hash_16b] ll; \ + if r0 != 1 goto l1_%=; \ +l0_%=: r1 = %[map_array_48b] ll; \ +l1_%=: call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l2_%=; \ + r1 = 4; \ + r1 += r0; \ + r0 = *(u8*)(r1 + 0); \ +l2_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b), + __imm_addr(map_hash_16b), + __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr -= known scalar from different maps") +__success __failure_unpriv +__msg_unpriv("R0 min value is outside of the allowed memory range") +__retval(1) +__naked void known_scalar_from_different_maps(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_len]); \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + if r0 == 1 goto l0_%=; \ + r1 = %[map_hash_16b] ll; \ + if r0 != 1 goto l1_%=; \ +l0_%=: r1 = %[map_array_48b] ll; \ +l1_%=: call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l2_%=; \ + r1 = 4; \ + r0 -= r1; \ + r0 += r1; \ + r0 = *(u8*)(r0 + 0); \ +l2_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b), + __imm_addr(map_hash_16b), + __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)) + : __clobber_all); +} + +SEC("socket") +__description("map access: known scalar += value_ptr from different maps, but same value properties") +__success __success_unpriv __retval(1) +__naked void maps_but_same_value_properties(void) +{ + asm volatile (" \ + r0 = *(u32*)(r1 + %[__sk_buff_len]); \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + if r0 == 1 goto l0_%=; \ + r1 = %[map_hash_48b] ll; \ + if r0 != 1 goto l1_%=; \ +l0_%=: r1 = %[map_array_48b] ll; \ +l1_%=: call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l2_%=; \ + r1 = 4; \ + r1 += r0; \ + r0 = *(u8*)(r1 + 0); \ +l2_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b), + __imm_addr(map_hash_48b), + __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)) + : __clobber_all); +} + +SEC("socket") +__description("map access: mixing value pointer and scalar, 1") +__success __failure_unpriv __msg_unpriv("R2 pointer comparison prohibited") +__retval(0) +__naked void value_pointer_and_scalar_1(void) +{ + asm volatile (" \ + /* load map value pointer into r0 and r2 */ \ + r0 = 1; \ + r1 = %[map_array_48b] ll; \ + r2 = r10; \ + r2 += -16; \ + r6 = 0; \ + *(u64*)(r10 - 16) = r6; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: /* load some number from the map into r1 */ \ + r1 = *(u8*)(r0 + 0); \ + /* depending on r1, branch: */ \ + if r1 != 0 goto l1_%=; \ + /* branch A */ \ + r2 = r0; \ + r3 = 0; \ + goto l2_%=; \ +l1_%=: /* branch B */ \ + r2 = 0; \ + r3 = 0x100000; \ +l2_%=: /* common instruction */ \ + r2 += r3; \ + /* depending on r1, branch: */ \ + if r1 != 0 goto l3_%=; \ + /* branch A */ \ + goto l4_%=; \ +l3_%=: /* branch B */ \ + r0 = 0x13371337; \ + /* verifier follows fall-through */ \ + if r2 != 0x100000 goto l4_%=; \ + r0 = 0; \ + exit; \ +l4_%=: /* fake-dead code; targeted from branch A to \ + * prevent dead code sanitization \ + */ \ + r0 = *(u8*)(r0 + 0); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: mixing value pointer and scalar, 2") +__success __failure_unpriv __msg_unpriv("R0 invalid mem access 'scalar'") +__retval(0) +__naked void value_pointer_and_scalar_2(void) +{ + asm volatile (" \ + /* load map value pointer into r0 and r2 */ \ + r0 = 1; \ + r1 = %[map_array_48b] ll; \ + r2 = r10; \ + r2 += -16; \ + r6 = 0; \ + *(u64*)(r10 - 16) = r6; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: /* load some number from the map into r1 */ \ + r1 = *(u8*)(r0 + 0); \ + /* depending on r1, branch: */ \ + if r1 == 0 goto l1_%=; \ + /* branch A */ \ + r2 = 0; \ + r3 = 0x100000; \ + goto l2_%=; \ +l1_%=: /* branch B */ \ + r2 = r0; \ + r3 = 0; \ +l2_%=: /* common instruction */ \ + r2 += r3; \ + /* depending on r1, branch: */ \ + if r1 != 0 goto l3_%=; \ + /* branch A */ \ + goto l4_%=; \ +l3_%=: /* branch B */ \ + r0 = 0x13371337; \ + /* verifier follows fall-through */ \ + if r2 != 0x100000 goto l4_%=; \ + r0 = 0; \ + exit; \ +l4_%=: /* fake-dead code; targeted from branch A to \ + * prevent dead code sanitization, rejected \ + * via branch B however \ + */ \ + r0 = *(u8*)(r0 + 0); \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("sanitation: alu with different scalars 1") +__success __success_unpriv __retval(0x100000) +__naked void alu_with_different_scalars_1(void) +{ + asm volatile (" \ + r0 = 1; \ + r1 = %[map_array_48b] ll; \ + r2 = r10; \ + r2 += -16; \ + r6 = 0; \ + *(u64*)(r10 - 16) = r6; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r1 = *(u32*)(r0 + 0); \ + if r1 == 0 goto l1_%=; \ + r2 = 0; \ + r3 = 0x100000; \ + goto l2_%=; \ +l1_%=: r2 = 42; \ + r3 = 0x100001; \ +l2_%=: r2 += r3; \ + r0 = r2; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("sanitation: alu with different scalars 2") +__success __success_unpriv __retval(0) +__naked void alu_with_different_scalars_2(void) +{ + asm volatile (" \ + r0 = 1; \ + r1 = %[map_array_48b] ll; \ + r6 = r1; \ + r2 = r10; \ + r2 += -16; \ + r7 = 0; \ + *(u64*)(r10 - 16) = r7; \ + call %[bpf_map_delete_elem]; \ + r7 = r0; \ + r1 = r6; \ + r2 = r10; \ + r2 += -16; \ + call %[bpf_map_delete_elem]; \ + r6 = r0; \ + r8 = r6; \ + r8 += r7; \ + r0 = r8; \ + r0 += %[einval]; \ + r0 += %[einval]; \ + exit; \ +" : + : __imm(bpf_map_delete_elem), + __imm_addr(map_array_48b), + __imm_const(einval, EINVAL) + : __clobber_all); +} + +SEC("socket") +__description("sanitation: alu with different scalars 3") +__success __success_unpriv __retval(0) +__naked void alu_with_different_scalars_3(void) +{ + asm volatile (" \ + r0 = %[einval]; \ + r0 *= -1; \ + r7 = r0; \ + r0 = %[einval]; \ + r0 *= -1; \ + r6 = r0; \ + r8 = r6; \ + r8 += r7; \ + r0 = r8; \ + r0 += %[einval]; \ + r0 += %[einval]; \ + exit; \ +" : + : __imm_const(einval, EINVAL) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr += known scalar, upper oob arith, test 1") +__success __failure_unpriv +__msg_unpriv("R0 pointer arithmetic of map value goes out of range") +__retval(1) +__naked void upper_oob_arith_test_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 48; \ + r0 += r1; \ + r0 -= r1; \ + r0 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr += known scalar, upper oob arith, test 2") +__success __failure_unpriv +__msg_unpriv("R0 pointer arithmetic of map value goes out of range") +__retval(1) +__naked void upper_oob_arith_test_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 49; \ + r0 += r1; \ + r0 -= r1; \ + r0 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr += known scalar, upper oob arith, test 3") +__success __success_unpriv __retval(1) +__naked void upper_oob_arith_test_3(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 47; \ + r0 += r1; \ + r0 -= r1; \ + r0 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr -= known scalar, lower oob arith, test 1") +__failure __msg("R0 min value is outside of the allowed memory range") +__failure_unpriv +__msg_unpriv("R0 pointer arithmetic of map value goes out of range") +__naked void lower_oob_arith_test_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 47; \ + r0 += r1; \ + r1 = 48; \ + r0 -= r1; \ + r0 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr -= known scalar, lower oob arith, test 2") +__success __failure_unpriv +__msg_unpriv("R0 pointer arithmetic of map value goes out of range") +__retval(1) +__naked void lower_oob_arith_test_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 47; \ + r0 += r1; \ + r1 = 48; \ + r0 -= r1; \ + r1 = 1; \ + r0 += r1; \ + r0 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr -= known scalar, lower oob arith, test 3") +__success __success_unpriv __retval(1) +__naked void lower_oob_arith_test_3(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 47; \ + r0 += r1; \ + r1 = 47; \ + r0 -= r1; \ + r0 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: known scalar += value_ptr") +__success __success_unpriv __retval(1) +__naked void access_known_scalar_value_ptr_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 4; \ + r1 += r0; \ + r0 = *(u8*)(r1 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr += known scalar, 1") +__success __success_unpriv __retval(1) +__naked void value_ptr_known_scalar_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 4; \ + r0 += r1; \ + r1 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr += known scalar, 2") +__failure __msg("invalid access to map value") +__failure_unpriv +__naked void value_ptr_known_scalar_2_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 49; \ + r0 += r1; \ + r1 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr += known scalar, 3") +__failure __msg("invalid access to map value") +__failure_unpriv +__naked void value_ptr_known_scalar_3(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = -1; \ + r0 += r1; \ + r1 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr += known scalar, 4") +__success __success_unpriv __retval(1) +__naked void value_ptr_known_scalar_4(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 5; \ + r0 += r1; \ + r1 = -2; \ + r0 += r1; \ + r1 = -1; \ + r0 += r1; \ + r1 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr += known scalar, 5") +__success __success_unpriv __retval(0xabcdef12) +__naked void value_ptr_known_scalar_5(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = %[__imm_0]; \ + r1 += r0; \ + r0 = *(u32*)(r1 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b), + __imm_const(__imm_0, (6 + 1) * sizeof(int)) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr += known scalar, 6") +__success __success_unpriv __retval(0xabcdef12) +__naked void value_ptr_known_scalar_6(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = %[__imm_0]; \ + r0 += r1; \ + r1 = %[__imm_1]; \ + r0 += r1; \ + r0 = *(u32*)(r0 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b), + __imm_const(__imm_0, (3 + 1) * sizeof(int)), + __imm_const(__imm_1, 3 * sizeof(int)) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr += N, value_ptr -= N known scalar") +__success __success_unpriv __retval(0x12345678) +__naked void value_ptr_n_known_scalar(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + w1 = 0x12345678; \ + *(u32*)(r0 + 0) = r1; \ + r0 += 2; \ + r1 = 2; \ + r0 -= r1; \ + r0 = *(u32*)(r0 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: unknown scalar += value_ptr, 1") +__success __success_unpriv __retval(1) +__naked void unknown_scalar_value_ptr_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u8*)(r0 + 0); \ + r1 &= 0xf; \ + r1 += r0; \ + r0 = *(u8*)(r1 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: unknown scalar += value_ptr, 2") +__success __success_unpriv __retval(0xabcdef12) __flag(BPF_F_ANY_ALIGNMENT) +__naked void unknown_scalar_value_ptr_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u32*)(r0 + 0); \ + r1 &= 31; \ + r1 += r0; \ + r0 = *(u32*)(r1 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: unknown scalar += value_ptr, 3") +__success __failure_unpriv +__msg_unpriv("R0 pointer arithmetic of map value goes out of range") +__retval(0xabcdef12) __flag(BPF_F_ANY_ALIGNMENT) +__naked void unknown_scalar_value_ptr_3(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = -1; \ + r0 += r1; \ + r1 = 1; \ + r0 += r1; \ + r1 = *(u32*)(r0 + 0); \ + r1 &= 31; \ + r1 += r0; \ + r0 = *(u32*)(r1 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: unknown scalar += value_ptr, 4") +__failure __msg("R1 max value is outside of the allowed memory range") +__msg_unpriv("R1 pointer arithmetic of map value goes out of range") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void unknown_scalar_value_ptr_4(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 19; \ + r0 += r1; \ + r1 = *(u32*)(r0 + 0); \ + r1 &= 31; \ + r1 += r0; \ + r0 = *(u32*)(r1 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr += unknown scalar, 1") +__success __success_unpriv __retval(1) +__naked void value_ptr_unknown_scalar_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u8*)(r0 + 0); \ + r1 &= 0xf; \ + r0 += r1; \ + r1 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr += unknown scalar, 2") +__success __success_unpriv __retval(0xabcdef12) __flag(BPF_F_ANY_ALIGNMENT) +__naked void value_ptr_unknown_scalar_2_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u32*)(r0 + 0); \ + r1 &= 31; \ + r0 += r1; \ + r0 = *(u32*)(r0 + 0); \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr += unknown scalar, 3") +__success __success_unpriv __retval(1) +__naked void value_ptr_unknown_scalar_3(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r0 + 0); \ + r2 = *(u64*)(r0 + 8); \ + r3 = *(u64*)(r0 + 16); \ + r1 &= 0xf; \ + r3 &= 1; \ + r3 |= 1; \ + if r2 > r3 goto l0_%=; \ + r0 += r3; \ + r0 = *(u8*)(r0 + 0); \ + r0 = 1; \ +l1_%=: exit; \ +l0_%=: r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr += value_ptr") +__failure __msg("R0 pointer += pointer prohibited") +__failure_unpriv +__naked void access_value_ptr_value_ptr_1(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r0 += r0; \ + r1 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: known scalar -= value_ptr") +__failure __msg("R1 tried to subtract pointer from scalar") +__failure_unpriv +__naked void access_known_scalar_value_ptr_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 4; \ + r1 -= r0; \ + r0 = *(u8*)(r1 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr -= known scalar") +__failure __msg("R0 min value is outside of the allowed memory range") +__failure_unpriv +__naked void access_value_ptr_known_scalar(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 4; \ + r0 -= r1; \ + r1 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr -= known scalar, 2") +__success __success_unpriv __retval(1) +__naked void value_ptr_known_scalar_2_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = 6; \ + r2 = 4; \ + r0 += r1; \ + r0 -= r2; \ + r1 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: unknown scalar -= value_ptr") +__failure __msg("R1 tried to subtract pointer from scalar") +__failure_unpriv +__naked void access_unknown_scalar_value_ptr(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u8*)(r0 + 0); \ + r1 &= 0xf; \ + r1 -= r0; \ + r0 = *(u8*)(r1 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr -= unknown scalar") +__failure __msg("R0 min value is negative") +__failure_unpriv +__naked void access_value_ptr_unknown_scalar(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u8*)(r0 + 0); \ + r1 &= 0xf; \ + r0 -= r1; \ + r1 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr -= unknown scalar, 2") +__success __failure_unpriv +__msg_unpriv("R0 pointer arithmetic of map value goes out of range") +__retval(1) +__naked void value_ptr_unknown_scalar_2_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u8*)(r0 + 0); \ + r1 &= 0xf; \ + r1 |= 0x7; \ + r0 += r1; \ + r1 = *(u8*)(r0 + 0); \ + r1 &= 0x7; \ + r0 -= r1; \ + r1 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: value_ptr -= value_ptr") +__failure __msg("R0 invalid mem access 'scalar'") +__msg_unpriv("R0 pointer -= pointer prohibited") +__naked void access_value_ptr_value_ptr_2(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r0 -= r0; \ + r1 = *(u8*)(r0 + 0); \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("socket") +__description("map access: trying to leak tainted dst reg") +__failure __msg("math between map_value pointer and 4294967295 is not allowed") +__failure_unpriv +__naked void to_leak_tainted_dst_reg(void) +{ + asm volatile (" \ + r0 = 0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_array_48b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r2 = r0; \ + w1 = 0xFFFFFFFF; \ + w1 = w1; \ + r2 -= r1; \ + *(u64*)(r0 + 0) = r2; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array_48b) + : __clobber_all); +} + +SEC("tc") +__description("32bit pkt_ptr -= scalar") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void _32bit_pkt_ptr_scalar(void) +{ + asm volatile (" \ + r8 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r7 = *(u32*)(r1 + %[__sk_buff_data]); \ + r6 = r7; \ + r6 += 40; \ + if r6 > r8 goto l0_%=; \ + w4 = w7; \ + w6 -= w4; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("32bit scalar -= pkt_ptr") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void _32bit_scalar_pkt_ptr(void) +{ + asm volatile (" \ + r8 = *(u32*)(r1 + %[__sk_buff_data_end]); \ + r7 = *(u32*)(r1 + %[__sk_buff_data]); \ + r6 = r7; \ + r6 += 40; \ + if r6 > r8 goto l0_%=; \ + w4 = w6; \ + w4 -= w7; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)), + __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_var_off.c b/tools/testing/selftests/bpf/progs/verifier_var_off.c new file mode 100644 index 0000000000..d1f23c1a7c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_var_off.c @@ -0,0 +1,389 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/var_off.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +SEC("lwt_in") +__description("variable-offset ctx access") +__failure __msg("variable ctx access var_off=(0x0; 0x4)") +__naked void variable_offset_ctx_access(void) +{ + asm volatile (" \ + /* Get an unknown value */ \ + r2 = *(u32*)(r1 + 0); \ + /* Make it small and 4-byte aligned */ \ + r2 &= 4; \ + /* add it to skb. We now have either &skb->len or\ + * &skb->pkt_type, but we don't know which \ + */ \ + r1 += r2; \ + /* dereference it */ \ + r0 = *(u32*)(r1 + 0); \ + exit; \ +" ::: __clobber_all); +} + +SEC("cgroup/skb") +__description("variable-offset stack read, priv vs unpriv") +__success __failure_unpriv +__msg_unpriv("R2 variable stack access prohibited for !root") +__retval(0) +__naked void stack_read_priv_vs_unpriv(void) +{ + asm volatile (" \ + /* Fill the top 8 bytes of the stack */ \ + r0 = 0; \ + *(u64*)(r10 - 8) = r0; \ + /* Get an unknown value */ \ + r2 = *(u32*)(r1 + 0); \ + /* Make it small and 4-byte aligned */ \ + r2 &= 4; \ + r2 -= 8; \ + /* add it to fp. We now have either fp-4 or fp-8, but\ + * we don't know which \ + */ \ + r2 += r10; \ + /* dereference it for a stack read */ \ + r0 = *(u32*)(r2 + 0); \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("cgroup/skb") +__description("variable-offset stack read, uninitialized") +__success +__failure_unpriv __msg_unpriv("R2 variable stack access prohibited for !root") +__naked void variable_offset_stack_read_uninitialized(void) +{ + asm volatile (" \ + /* Get an unknown value */ \ + r2 = *(u32*)(r1 + 0); \ + /* Make it small and 4-byte aligned */ \ + r2 &= 4; \ + r2 -= 8; \ + /* add it to fp. We now have either fp-4 or fp-8, but\ + * we don't know which \ + */ \ + r2 += r10; \ + /* dereference it for a stack read */ \ + r0 = *(u32*)(r2 + 0); \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("variable-offset stack write, priv vs unpriv") +__success +/* Check that the maximum stack depth is correctly maintained according to the + * maximum possible variable offset. + */ +__log_level(4) __msg("stack depth 16") +__failure_unpriv +/* Variable stack access is rejected for unprivileged. + */ +__msg_unpriv("R2 variable stack access prohibited for !root") +__retval(0) +__naked void stack_write_priv_vs_unpriv(void) +{ + asm volatile (" \ + /* Get an unknown value */ \ + r2 = *(u32*)(r1 + 0); \ + /* Make it small and 8-byte aligned */ \ + r2 &= 8; \ + r2 -= 16; \ + /* Add it to fp. We now have either fp-8 or \ + * fp-16, but we don't know which \ + */ \ + r2 += r10; \ + /* Dereference it for a stack write */ \ + r0 = 0; \ + *(u64*)(r2 + 0) = r0; \ + exit; \ +" ::: __clobber_all); +} + +/* Similar to the previous test, but this time also perform a read from the + * address written to with a variable offset. The read is allowed, showing that, + * after a variable-offset write, a priviledged program can read the slots that + * were in the range of that write (even if the verifier doesn't actually know if + * the slot being read was really written to or not. + * + * Despite this test being mostly a superset, the previous test is also kept for + * the sake of it checking the stack depth in the case where there is no read. + */ +SEC("socket") +__description("variable-offset stack write followed by read") +__success +/* Check that the maximum stack depth is correctly maintained according to the + * maximum possible variable offset. + */ +__log_level(4) __msg("stack depth 16") +__failure_unpriv +__msg_unpriv("R2 variable stack access prohibited for !root") +__retval(0) +__naked void stack_write_followed_by_read(void) +{ + asm volatile (" \ + /* Get an unknown value */ \ + r2 = *(u32*)(r1 + 0); \ + /* Make it small and 8-byte aligned */ \ + r2 &= 8; \ + r2 -= 16; \ + /* Add it to fp. We now have either fp-8 or fp-16, but\ + * we don't know which \ + */ \ + r2 += r10; \ + /* Dereference it for a stack write */ \ + r0 = 0; \ + *(u64*)(r2 + 0) = r0; \ + /* Now read from the address we just wrote. */ \ + r3 = *(u64*)(r2 + 0); \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("variable-offset stack write clobbers spilled regs") +__failure +/* In the priviledged case, dereferencing a spilled-and-then-filled + * register is rejected because the previous variable offset stack + * write might have overwritten the spilled pointer (i.e. we lose track + * of the spilled register when we analyze the write). + */ +__msg("R2 invalid mem access 'scalar'") +__failure_unpriv +/* The unprivileged case is not too interesting; variable + * stack access is rejected. + */ +__msg_unpriv("R2 variable stack access prohibited for !root") +__naked void stack_write_clobbers_spilled_regs(void) +{ + asm volatile (" \ + /* Dummy instruction; needed because we need to patch the next one\ + * and we can't patch the first instruction. \ + */ \ + r6 = 0; \ + /* Make R0 a map ptr */ \ + r0 = %[map_hash_8b] ll; \ + /* Get an unknown value */ \ + r2 = *(u32*)(r1 + 0); \ + /* Make it small and 8-byte aligned */ \ + r2 &= 8; \ + r2 -= 16; \ + /* Add it to fp. We now have either fp-8 or fp-16, but\ + * we don't know which. \ + */ \ + r2 += r10; \ + /* Spill R0(map ptr) into stack */ \ + *(u64*)(r10 - 8) = r0; \ + /* Dereference the unknown value for a stack write */\ + r0 = 0; \ + *(u64*)(r2 + 0) = r0; \ + /* Fill the register back into R2 */ \ + r2 = *(u64*)(r10 - 8); \ + /* Try to dereference R2 for a memory load */ \ + r0 = *(u64*)(r2 + 8); \ + exit; \ +" : + : __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("sockops") +__description("indirect variable-offset stack access, unbounded") +__failure __msg("invalid unbounded variable-offset indirect access to stack R4") +__naked void variable_offset_stack_access_unbounded(void) +{ + asm volatile (" \ + r2 = 6; \ + r3 = 28; \ + /* Fill the top 16 bytes of the stack. */ \ + r4 = 0; \ + *(u64*)(r10 - 16) = r4; \ + r4 = 0; \ + *(u64*)(r10 - 8) = r4; \ + /* Get an unknown value. */ \ + r4 = *(u64*)(r1 + %[bpf_sock_ops_bytes_received]);\ + /* Check the lower bound but don't check the upper one. */\ + if r4 s< 0 goto l0_%=; \ + /* Point the lower bound to initialized stack. Offset is now in range\ + * from fp-16 to fp+0x7fffffffffffffef, i.e. max value is unbounded.\ + */ \ + r4 -= 16; \ + r4 += r10; \ + r5 = 8; \ + /* Dereference it indirectly. */ \ + call %[bpf_getsockopt]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_getsockopt), + __imm_const(bpf_sock_ops_bytes_received, offsetof(struct bpf_sock_ops, bytes_received)) + : __clobber_all); +} + +SEC("lwt_in") +__description("indirect variable-offset stack access, max out of bound") +__failure __msg("invalid variable-offset indirect access to stack R2") +__naked void access_max_out_of_bound(void) +{ + asm volatile (" \ + /* Fill the top 8 bytes of the stack */ \ + r2 = 0; \ + *(u64*)(r10 - 8) = r2; \ + /* Get an unknown value */ \ + r2 = *(u32*)(r1 + 0); \ + /* Make it small and 4-byte aligned */ \ + r2 &= 4; \ + r2 -= 8; \ + /* add it to fp. We now have either fp-4 or fp-8, but\ + * we don't know which \ + */ \ + r2 += r10; \ + /* dereference it indirectly */ \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("lwt_in") +__description("indirect variable-offset stack access, min out of bound") +__failure __msg("invalid variable-offset indirect access to stack R2") +__naked void access_min_out_of_bound(void) +{ + asm volatile (" \ + /* Fill the top 8 bytes of the stack */ \ + r2 = 0; \ + *(u64*)(r10 - 8) = r2; \ + /* Get an unknown value */ \ + r2 = *(u32*)(r1 + 0); \ + /* Make it small and 4-byte aligned */ \ + r2 &= 4; \ + r2 -= 516; \ + /* add it to fp. We now have either fp-516 or fp-512, but\ + * we don't know which \ + */ \ + r2 += r10; \ + /* dereference it indirectly */ \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("indirect variable-offset stack access, min_off < min_initialized") +__success +__failure_unpriv __msg_unpriv("R2 variable stack access prohibited for !root") +__naked void access_min_off_min_initialized(void) +{ + asm volatile (" \ + /* Fill only the top 8 bytes of the stack. */ \ + r2 = 0; \ + *(u64*)(r10 - 8) = r2; \ + /* Get an unknown value */ \ + r2 = *(u32*)(r1 + 0); \ + /* Make it small and 4-byte aligned. */ \ + r2 &= 4; \ + r2 -= 16; \ + /* Add it to fp. We now have either fp-12 or fp-16, but we don't know\ + * which. fp-16 size 8 is partially uninitialized stack.\ + */ \ + r2 += r10; \ + /* Dereference it indirectly. */ \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("cgroup/skb") +__description("indirect variable-offset stack access, priv vs unpriv") +__success __failure_unpriv +__msg_unpriv("R2 variable stack access prohibited for !root") +__retval(0) +__naked void stack_access_priv_vs_unpriv(void) +{ + asm volatile (" \ + /* Fill the top 16 bytes of the stack. */ \ + r2 = 0; \ + *(u64*)(r10 - 16) = r2; \ + r2 = 0; \ + *(u64*)(r10 - 8) = r2; \ + /* Get an unknown value. */ \ + r2 = *(u32*)(r1 + 0); \ + /* Make it small and 4-byte aligned. */ \ + r2 &= 4; \ + r2 -= 16; \ + /* Add it to fp. We now have either fp-12 or fp-16, we don't know\ + * which, but either way it points to initialized stack.\ + */ \ + r2 += r10; \ + /* Dereference it indirectly. */ \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("lwt_in") +__description("indirect variable-offset stack access, ok") +__success __retval(0) +__naked void variable_offset_stack_access_ok(void) +{ + asm volatile (" \ + /* Fill the top 16 bytes of the stack. */ \ + r2 = 0; \ + *(u64*)(r10 - 16) = r2; \ + r2 = 0; \ + *(u64*)(r10 - 8) = r2; \ + /* Get an unknown value. */ \ + r2 = *(u32*)(r1 + 0); \ + /* Make it small and 4-byte aligned. */ \ + r2 &= 4; \ + r2 -= 16; \ + /* Add it to fp. We now have either fp-12 or fp-16, we don't know\ + * which, but either way it points to initialized stack.\ + */ \ + r2 += r10; \ + /* Dereference it indirectly. */ \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_xadd.c b/tools/testing/selftests/bpf/progs/verifier_xadd.c new file mode 100644 index 0000000000..05a0a55adb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_xadd.c @@ -0,0 +1,124 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/xadd.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +SEC("tc") +__description("xadd/w check unaligned stack") +__failure __msg("misaligned stack access off") +__naked void xadd_w_check_unaligned_stack(void) +{ + asm volatile (" \ + r0 = 1; \ + *(u64*)(r10 - 8) = r0; \ + lock *(u32 *)(r10 - 7) += w0; \ + r0 = *(u64*)(r10 - 8); \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("xadd/w check unaligned map") +__failure __msg("misaligned value access off") +__naked void xadd_w_check_unaligned_map(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: r1 = 1; \ + lock *(u32 *)(r0 + 3) += w1; \ + r0 = *(u32*)(r0 + 3); \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("xdp") +__description("xadd/w check unaligned pkt") +__failure __msg("BPF_ATOMIC stores into R2 pkt is not allowed") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void xadd_w_check_unaligned_pkt(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r1 < r3 goto l0_%=; \ + r0 = 99; \ + goto l1_%=; \ +l0_%=: r0 = 1; \ + r1 = 0; \ + *(u32*)(r2 + 0) = r1; \ + r1 = 0; \ + *(u32*)(r2 + 3) = r1; \ + lock *(u32 *)(r2 + 1) += w0; \ + lock *(u32 *)(r2 + 2) += w0; \ + r0 = *(u32*)(r2 + 1); \ +l1_%=: exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("tc") +__description("xadd/w check whether src/dst got mangled, 1") +__success __retval(3) +__naked void src_dst_got_mangled_1(void) +{ + asm volatile (" \ + r0 = 1; \ + r6 = r0; \ + r7 = r10; \ + *(u64*)(r10 - 8) = r0; \ + lock *(u64 *)(r10 - 8) += r0; \ + lock *(u64 *)(r10 - 8) += r0; \ + if r6 != r0 goto l0_%=; \ + if r7 != r10 goto l0_%=; \ + r0 = *(u64*)(r10 - 8); \ + exit; \ +l0_%=: r0 = 42; \ + exit; \ +" ::: __clobber_all); +} + +SEC("tc") +__description("xadd/w check whether src/dst got mangled, 2") +__success __retval(3) +__naked void src_dst_got_mangled_2(void) +{ + asm volatile (" \ + r0 = 1; \ + r6 = r0; \ + r7 = r10; \ + *(u32*)(r10 - 8) = r0; \ + lock *(u32 *)(r10 - 8) += w0; \ + lock *(u32 *)(r10 - 8) += w0; \ + if r6 != r0 goto l0_%=; \ + if r7 != r10 goto l0_%=; \ + r0 = *(u32*)(r10 - 8); \ + exit; \ +l0_%=: r0 = 42; \ + exit; \ +" ::: __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_xdp.c b/tools/testing/selftests/bpf/progs/verifier_xdp.c new file mode 100644 index 0000000000..50768ed179 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_xdp.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/xdp.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("xdp") +__description("XDP, using ifindex from netdev") +__success __retval(1) +__naked void xdp_using_ifindex_from_netdev(void) +{ + asm volatile (" \ + r0 = 0; \ + r2 = *(u32*)(r1 + %[xdp_md_ingress_ifindex]); \ + if r2 < 1 goto l0_%=; \ + r0 = 1; \ +l0_%=: exit; \ +" : + : __imm_const(xdp_md_ingress_ifindex, offsetof(struct xdp_md, ingress_ifindex)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_xdp_direct_packet_access.c b/tools/testing/selftests/bpf/progs/verifier_xdp_direct_packet_access.c new file mode 100644 index 0000000000..df2dfd1b15 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_xdp_direct_packet_access.c @@ -0,0 +1,1722 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Converted from tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("xdp") +__description("XDP pkt read, pkt_end mangling, bad access 1") +__failure __msg("R3 pointer arithmetic on pkt_end") +__naked void end_mangling_bad_access_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + r3 += 8; \ + if r1 > r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end mangling, bad access 2") +__failure __msg("R3 pointer arithmetic on pkt_end") +__naked void end_mangling_bad_access_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + r3 -= 8; \ + if r1 > r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' > pkt_end, corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void end_corner_case_good_access_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r1 > r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' > pkt_end, bad access 1") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_end_bad_access_1_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r1 > r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 4); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' > pkt_end, bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_end_bad_access_2_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r1 > r3 goto l0_%=; \ +l0_%=: r0 = *(u64*)(r1 - 8); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' > pkt_end, corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 9; \ + if r1 > r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 9); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' > pkt_end, corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 7; \ + if r1 > r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 7); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end > pkt_data', good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void end_pkt_data_good_access_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r3 > r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u32*)(r1 - 5); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end > pkt_data', corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 6; \ + if r3 > r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 6); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end > pkt_data', bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_data_bad_access_2_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r3 > r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end > pkt_data', corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void data_corner_case_good_access_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 7; \ + if r3 > r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 7); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end > pkt_data', corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r3 > r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 8); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' < pkt_end, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void data_pkt_end_good_access_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r1 < r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u32*)(r1 - 5); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' < pkt_end, corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_3(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 6; \ + if r1 < r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 6); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' < pkt_end, bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_end_bad_access_2_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r1 < r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' < pkt_end, corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void end_corner_case_good_access_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 7; \ + if r1 < r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 7); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' < pkt_end, corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_3(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r1 < r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 8); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end < pkt_data', corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void data_corner_case_good_access_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r3 < r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end < pkt_data', bad access 1") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_data_bad_access_1_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r3 < r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 4); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end < pkt_data', bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_data_bad_access_2_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r3 < r1 goto l0_%=; \ +l0_%=: r0 = *(u64*)(r1 - 8); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end < pkt_data', corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_4(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 9; \ + if r3 < r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 9); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end < pkt_data', corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_4(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 7; \ + if r3 < r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 7); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' >= pkt_end, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void data_pkt_end_good_access_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r1 >= r3 goto l0_%=; \ + r0 = *(u32*)(r1 - 5); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' >= pkt_end, corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_5(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 6; \ + if r1 >= r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 6); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' >= pkt_end, bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_end_bad_access_2_3(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r1 >= r3 goto l0_%=; \ +l0_%=: r0 = *(u32*)(r1 - 5); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' >= pkt_end, corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void end_corner_case_good_access_3(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 7; \ + if r1 >= r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 7); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' >= pkt_end, corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_5(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r1 >= r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end >= pkt_data', corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void data_corner_case_good_access_3(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r3 >= r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 8); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end >= pkt_data', bad access 1") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_data_bad_access_1_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r3 >= r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 4); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end >= pkt_data', bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_data_bad_access_2_3(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r3 >= r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end >= pkt_data', corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_6(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 9; \ + if r3 >= r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 9); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end >= pkt_data', corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_6(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 7; \ + if r3 >= r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 7); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' <= pkt_end, corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void end_corner_case_good_access_4(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r1 <= r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 8); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' <= pkt_end, bad access 1") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_end_bad_access_1_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r1 <= r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 4); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' <= pkt_end, bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_end_bad_access_2_4(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r1 <= r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' <= pkt_end, corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_7(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 9; \ + if r1 <= r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 9); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data' <= pkt_end, corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_7(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 7; \ + if r1 <= r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 7); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end <= pkt_data', good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void end_pkt_data_good_access_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r3 <= r1 goto l0_%=; \ + r0 = *(u32*)(r1 - 5); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end <= pkt_data', corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_8(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 6; \ + if r3 <= r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 6); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end <= pkt_data', bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_data_bad_access_2_4(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r3 <= r1 goto l0_%=; \ +l0_%=: r0 = *(u32*)(r1 - 5); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end <= pkt_data', corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void data_corner_case_good_access_4(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 7; \ + if r3 <= r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 7); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_end <= pkt_data', corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_8(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data]); \ + r3 = *(u32*)(r1 + %[xdp_md_data_end]); \ + r1 = r2; \ + r1 += 8; \ + if r3 <= r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' > pkt_data, corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void data_corner_case_good_access_5(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r1 > r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' > pkt_data, bad access 1") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_data_bad_access_1_3(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r1 > r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 4); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' > pkt_data, bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_data_bad_access_2_5(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r1 > r3 goto l0_%=; \ +l0_%=: r0 = *(u64*)(r1 - 8); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' > pkt_data, corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_9(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 9; \ + if r1 > r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 9); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' > pkt_data, corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_9(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 7; \ + if r1 > r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 7); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data > pkt_meta', good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void data_pkt_meta_good_access_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r3 > r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u32*)(r1 - 5); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data > pkt_meta', corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_10(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 6; \ + if r3 > r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 6); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data > pkt_meta', bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_meta_bad_access_2_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r3 > r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data > pkt_meta', corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void meta_corner_case_good_access_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 7; \ + if r3 > r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 7); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data > pkt_meta', corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_10(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r3 > r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 8); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' < pkt_data, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void meta_pkt_data_good_access_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r1 < r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u32*)(r1 - 5); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' < pkt_data, corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_11(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 6; \ + if r1 < r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 6); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' < pkt_data, bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_data_bad_access_2_6(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r1 < r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' < pkt_data, corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void data_corner_case_good_access_6(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 7; \ + if r1 < r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 7); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' < pkt_data, corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_11(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r1 < r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 8); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data < pkt_meta', corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void meta_corner_case_good_access_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r3 < r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data < pkt_meta', bad access 1") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_meta_bad_access_1_1(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r3 < r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 4); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data < pkt_meta', bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_meta_bad_access_2_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r3 < r1 goto l0_%=; \ +l0_%=: r0 = *(u64*)(r1 - 8); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data < pkt_meta', corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_12(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 9; \ + if r3 < r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 9); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data < pkt_meta', corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_12(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 7; \ + if r3 < r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 7); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' >= pkt_data, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void meta_pkt_data_good_access_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r1 >= r3 goto l0_%=; \ + r0 = *(u32*)(r1 - 5); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' >= pkt_data, corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_13(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 6; \ + if r1 >= r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 6); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' >= pkt_data, bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_data_bad_access_2_7(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r1 >= r3 goto l0_%=; \ +l0_%=: r0 = *(u32*)(r1 - 5); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' >= pkt_data, corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void data_corner_case_good_access_7(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 7; \ + if r1 >= r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 7); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' >= pkt_data, corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_13(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r1 >= r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data >= pkt_meta', corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void meta_corner_case_good_access_3(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r3 >= r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 8); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data >= pkt_meta', bad access 1") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_meta_bad_access_1_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r3 >= r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 4); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data >= pkt_meta', bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_meta_bad_access_2_3(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r3 >= r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data >= pkt_meta', corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_14(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 9; \ + if r3 >= r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 9); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data >= pkt_meta', corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_14(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 7; \ + if r3 >= r1 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 7); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' <= pkt_data, corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void data_corner_case_good_access_8(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r1 <= r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 8); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' <= pkt_data, bad access 1") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_data_bad_access_1_4(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r1 <= r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 4); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' <= pkt_data, bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_data_bad_access_2_8(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r1 <= r3 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' <= pkt_data, corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_15(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 9; \ + if r1 <= r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 9); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_meta' <= pkt_data, corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_15(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 7; \ + if r1 <= r3 goto l0_%=; \ + goto l1_%=; \ +l0_%=: r0 = *(u64*)(r1 - 7); \ +l1_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data <= pkt_meta', good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void data_pkt_meta_good_access_2(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r3 <= r1 goto l0_%=; \ + r0 = *(u32*)(r1 - 5); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data <= pkt_meta', corner case -1, bad access") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_bad_access_16(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 6; \ + if r3 <= r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 6); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data <= pkt_meta', bad access 2") +__failure __msg("R1 offset is outside of the packet") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void pkt_meta_bad_access_2_4(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r3 <= r1 goto l0_%=; \ +l0_%=: r0 = *(u32*)(r1 - 5); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data <= pkt_meta', corner case, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void meta_corner_case_good_access_4(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 7; \ + if r3 <= r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 7); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +SEC("xdp") +__description("XDP pkt read, pkt_data <= pkt_meta', corner case +1, good access") +__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT) +__naked void corner_case_1_good_access_16(void) +{ + asm volatile (" \ + r2 = *(u32*)(r1 + %[xdp_md_data_meta]); \ + r3 = *(u32*)(r1 + %[xdp_md_data]); \ + r1 = r2; \ + r1 += 8; \ + if r3 <= r1 goto l0_%=; \ + r0 = *(u64*)(r1 - 8); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/vrf_socket_lookup.c b/tools/testing/selftests/bpf/progs/vrf_socket_lookup.c new file mode 100644 index 0000000000..bcfb6feb38 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/vrf_socket_lookup.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include <linux/ip.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/pkt_cls.h> +#include <stdbool.h> + +int lookup_status; +bool test_xdp; +bool tcp_skc; + +#define CUR_NS BPF_F_CURRENT_NETNS + +static void socket_lookup(void *ctx, void *data_end, void *data) +{ + struct ethhdr *eth = data; + struct bpf_sock_tuple *tp; + struct bpf_sock *sk; + struct iphdr *iph; + int tplen; + + if (eth + 1 > data_end) + return; + + if (eth->h_proto != bpf_htons(ETH_P_IP)) + return; + + iph = (struct iphdr *)(eth + 1); + if (iph + 1 > data_end) + return; + + tp = (struct bpf_sock_tuple *)&iph->saddr; + tplen = sizeof(tp->ipv4); + if ((void *)tp + tplen > data_end) + return; + + switch (iph->protocol) { + case IPPROTO_TCP: + if (tcp_skc) + sk = bpf_skc_lookup_tcp(ctx, tp, tplen, CUR_NS, 0); + else + sk = bpf_sk_lookup_tcp(ctx, tp, tplen, CUR_NS, 0); + break; + case IPPROTO_UDP: + sk = bpf_sk_lookup_udp(ctx, tp, tplen, CUR_NS, 0); + break; + default: + return; + } + + lookup_status = 0; + + if (sk) { + bpf_sk_release(sk); + lookup_status = 1; + } +} + +SEC("tc") +int tc_socket_lookup(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + + if (test_xdp) + return TC_ACT_UNSPEC; + + socket_lookup(skb, data_end, data); + return TC_ACT_UNSPEC; +} + +SEC("xdp") +int xdp_socket_lookup(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + + if (!test_xdp) + return XDP_PASS; + + socket_lookup(xdp, data_end, data); + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_dummy.c b/tools/testing/selftests/bpf/progs/xdp_dummy.c new file mode 100644 index 0000000000..d988b2e0ce --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_dummy.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define KBUILD_MODNAME "xdp_dummy" +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("xdp") +int xdp_dummy_prog(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_features.c b/tools/testing/selftests/bpf/progs/xdp_features.c new file mode 100644 index 0000000000..67424084a3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_features.c @@ -0,0 +1,268 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdbool.h> +#include <linux/bpf.h> +#include <linux/netdev.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_tracing.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/udp.h> +#include <asm-generic/errno-base.h> + +#include "xdp_features.h" + +#define ipv6_addr_equal(a, b) ((a).s6_addr32[0] == (b).s6_addr32[0] && \ + (a).s6_addr32[1] == (b).s6_addr32[1] && \ + (a).s6_addr32[2] == (b).s6_addr32[2] && \ + (a).s6_addr32[3] == (b).s6_addr32[3]) + +struct net_device; +struct bpf_prog; + +struct xdp_cpumap_stats { + unsigned int redirect; + unsigned int pass; + unsigned int drop; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 1); +} stats SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 1); +} dut_stats SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_cpumap_val)); + __uint(max_entries, 1); +} cpu_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 1); +} dev_map SEC(".maps"); + +const volatile struct in6_addr tester_addr; +const volatile struct in6_addr dut_addr; + +static __always_inline int +xdp_process_echo_packet(struct xdp_md *xdp, bool dut) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eh = data; + struct tlv_hdr *tlv; + struct udphdr *uh; + __be16 port; + + if (eh + 1 > (struct ethhdr *)data_end) + return -EINVAL; + + if (eh->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *ih = (struct iphdr *)(eh + 1); + __be32 saddr = dut ? tester_addr.s6_addr32[3] + : dut_addr.s6_addr32[3]; + __be32 daddr = dut ? dut_addr.s6_addr32[3] + : tester_addr.s6_addr32[3]; + + ih = (struct iphdr *)(eh + 1); + if (ih + 1 > (struct iphdr *)data_end) + return -EINVAL; + + if (saddr != ih->saddr) + return -EINVAL; + + if (daddr != ih->daddr) + return -EINVAL; + + if (ih->protocol != IPPROTO_UDP) + return -EINVAL; + + uh = (struct udphdr *)(ih + 1); + } else if (eh->h_proto == bpf_htons(ETH_P_IPV6)) { + struct in6_addr saddr = dut ? tester_addr : dut_addr; + struct in6_addr daddr = dut ? dut_addr : tester_addr; + struct ipv6hdr *ih6 = (struct ipv6hdr *)(eh + 1); + + if (ih6 + 1 > (struct ipv6hdr *)data_end) + return -EINVAL; + + if (!ipv6_addr_equal(saddr, ih6->saddr)) + return -EINVAL; + + if (!ipv6_addr_equal(daddr, ih6->daddr)) + return -EINVAL; + + if (ih6->nexthdr != IPPROTO_UDP) + return -EINVAL; + + uh = (struct udphdr *)(ih6 + 1); + } else { + return -EINVAL; + } + + if (uh + 1 > (struct udphdr *)data_end) + return -EINVAL; + + port = dut ? uh->dest : uh->source; + if (port != bpf_htons(DUT_ECHO_PORT)) + return -EINVAL; + + tlv = (struct tlv_hdr *)(uh + 1); + if (tlv + 1 > data_end) + return -EINVAL; + + return bpf_htons(tlv->type) == CMD_ECHO ? 0 : -EINVAL; +} + +static __always_inline int +xdp_update_stats(struct xdp_md *xdp, bool tx, bool dut) +{ + __u32 *val, key = 0; + + if (xdp_process_echo_packet(xdp, tx)) + return -EINVAL; + + if (dut) + val = bpf_map_lookup_elem(&dut_stats, &key); + else + val = bpf_map_lookup_elem(&stats, &key); + + if (val) + __sync_add_and_fetch(val, 1); + + return 0; +} + +/* Tester */ + +SEC("xdp") +int xdp_tester_check_tx(struct xdp_md *xdp) +{ + xdp_update_stats(xdp, true, false); + + return XDP_PASS; +} + +SEC("xdp") +int xdp_tester_check_rx(struct xdp_md *xdp) +{ + xdp_update_stats(xdp, false, false); + + return XDP_PASS; +} + +/* DUT */ + +SEC("xdp") +int xdp_do_pass(struct xdp_md *xdp) +{ + xdp_update_stats(xdp, true, true); + + return XDP_PASS; +} + +SEC("xdp") +int xdp_do_drop(struct xdp_md *xdp) +{ + if (xdp_update_stats(xdp, true, true)) + return XDP_PASS; + + return XDP_DROP; +} + +SEC("xdp") +int xdp_do_aborted(struct xdp_md *xdp) +{ + if (xdp_process_echo_packet(xdp, true)) + return XDP_PASS; + + return XDP_ABORTED; +} + +SEC("xdp") +int xdp_do_tx(struct xdp_md *xdp) +{ + void *data = (void *)(long)xdp->data; + struct ethhdr *eh = data; + __u8 tmp_mac[ETH_ALEN]; + + if (xdp_update_stats(xdp, true, true)) + return XDP_PASS; + + __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN); + __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN); + __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN); + + return XDP_TX; +} + +SEC("xdp") +int xdp_do_redirect(struct xdp_md *xdp) +{ + if (xdp_process_echo_packet(xdp, true)) + return XDP_PASS; + + return bpf_redirect_map(&cpu_map, 0, 0); +} + +SEC("tp_btf/xdp_exception") +int BPF_PROG(xdp_exception, const struct net_device *dev, + const struct bpf_prog *xdp, __u32 act) +{ + __u32 *val, key = 0; + + val = bpf_map_lookup_elem(&dut_stats, &key); + if (val) + __sync_add_and_fetch(val, 1); + + return 0; +} + +SEC("tp_btf/xdp_cpumap_kthread") +int BPF_PROG(tp_xdp_cpumap_kthread, int map_id, unsigned int processed, + unsigned int drops, int sched, struct xdp_cpumap_stats *xdp_stats) +{ + __u32 *val, key = 0; + + val = bpf_map_lookup_elem(&dut_stats, &key); + if (val) + __sync_add_and_fetch(val, 1); + + return 0; +} + +SEC("xdp/cpumap") +int xdp_do_redirect_cpumap(struct xdp_md *xdp) +{ + void *data = (void *)(long)xdp->data; + struct ethhdr *eh = data; + __u8 tmp_mac[ETH_ALEN]; + + if (xdp_process_echo_packet(xdp, true)) + return XDP_PASS; + + __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN); + __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN); + __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN); + + return bpf_redirect_map(&dev_map, 0, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c new file mode 100644 index 0000000000..b2dfd7066c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include "xdp_metadata.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_XSKMAP); + __uint(max_entries, 256); + __type(key, __u32); + __type(value, __u32); +} xsk SEC(".maps"); + +__u64 pkts_skip = 0; +__u64 pkts_fail = 0; +__u64 pkts_redir = 0; + +extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, + __u64 *timestamp) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; + +SEC("xdp") +int rx(struct xdp_md *ctx) +{ + void *data, *data_meta, *data_end; + struct ipv6hdr *ip6h = NULL; + struct ethhdr *eth = NULL; + struct udphdr *udp = NULL; + struct iphdr *iph = NULL; + struct xdp_meta *meta; + int err; + + data = (void *)(long)ctx->data; + data_end = (void *)(long)ctx->data_end; + eth = data; + if (eth + 1 < data_end) { + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + iph = (void *)(eth + 1); + if (iph + 1 < data_end && iph->protocol == IPPROTO_UDP) + udp = (void *)(iph + 1); + } + if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + ip6h = (void *)(eth + 1); + if (ip6h + 1 < data_end && ip6h->nexthdr == IPPROTO_UDP) + udp = (void *)(ip6h + 1); + } + if (udp && udp + 1 > data_end) + udp = NULL; + } + + if (!udp) { + __sync_add_and_fetch(&pkts_skip, 1); + return XDP_PASS; + } + + /* Forwarding UDP:9091 to AF_XDP */ + if (udp->dest != bpf_htons(9091)) { + __sync_add_and_fetch(&pkts_skip, 1); + return XDP_PASS; + } + + err = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta)); + if (err) { + __sync_add_and_fetch(&pkts_fail, 1); + return XDP_PASS; + } + + data = (void *)(long)ctx->data; + data_meta = (void *)(long)ctx->data_meta; + meta = data_meta; + + if (meta + 1 > data) { + __sync_add_and_fetch(&pkts_fail, 1); + return XDP_PASS; + } + + err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp); + if (!err) + meta->xdp_timestamp = bpf_ktime_get_tai_ns(); + else + meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */ + + err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); + if (err < 0) + meta->rx_hash_err = err; /* Used by AF_XDP as no hash signal */ + + __sync_add_and_fetch(&pkts_redir, 1); + return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c new file mode 100644 index 0000000000..d151d406a1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include "xdp_metadata.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_XSKMAP); + __uint(max_entries, 4); + __type(key, __u32); + __type(value, __u32); +} xsk SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} prog_arr SEC(".maps"); + +extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, + __u64 *timestamp) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; + +SEC("xdp") +int rx(struct xdp_md *ctx) +{ + void *data, *data_meta; + struct xdp_meta *meta; + u64 timestamp = -1; + int ret; + + /* Reserve enough for all custom metadata. */ + + ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta)); + if (ret != 0) + return XDP_DROP; + + data = (void *)(long)ctx->data; + data_meta = (void *)(long)ctx->data_meta; + + if (data_meta + sizeof(struct xdp_meta) > data) + return XDP_DROP; + + meta = data_meta; + + /* Export metadata. */ + + /* We expect veth bpf_xdp_metadata_rx_timestamp to return 0 HW + * timestamp, so put some non-zero value into AF_XDP frame for + * the userspace. + */ + bpf_xdp_metadata_rx_timestamp(ctx, ×tamp); + if (timestamp == 0) + meta->rx_timestamp = 1; + + bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); + + return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata2.c b/tools/testing/selftests/bpf/progs/xdp_metadata2.c new file mode 100644 index 0000000000..85f88d9d7a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_metadata2.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include "xdp_metadata.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; + +int called; + +SEC("freplace/rx") +int freplace_rx(struct xdp_md *ctx) +{ + enum xdp_rss_hash_type type = 0; + u32 hash = 0; + /* Call _any_ metadata function to make sure we don't crash. */ + bpf_xdp_metadata_rx_hash(ctx, &hash, &type); + called++; + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c new file mode 100644 index 0000000000..d037262c89 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(max_entries, 8); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); +} tx_port SEC(".maps"); + +SEC("redirect_map_0") +int xdp_redirect_map_0(struct xdp_md *xdp) +{ + return bpf_redirect_map(&tx_port, 0, 0); +} + +SEC("redirect_map_1") +int xdp_redirect_map_1(struct xdp_md *xdp) +{ + return bpf_redirect_map(&tx_port, 1, 0); +} + +SEC("redirect_map_2") +int xdp_redirect_map_2(struct xdp_md *xdp) +{ + return bpf_redirect_map(&tx_port, 2, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c new file mode 100644 index 0000000000..97b26a30b5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0 +#define KBUILD_MODNAME "foo" +#include <string.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +/* One map use devmap, another one use devmap_hash for testing */ +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); + __uint(max_entries, 1024); +} map_all SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP_HASH); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 128); +} map_egress SEC(".maps"); + +/* map to store egress interfaces mac addresses */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __be64); + __uint(max_entries, 128); +} mac_map SEC(".maps"); + +SEC("xdp") +int xdp_redirect_map_multi_prog(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + int if_index = ctx->ingress_ifindex; + struct ethhdr *eth = data; + __u16 h_proto; + __u64 nh_off; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return XDP_DROP; + + h_proto = eth->h_proto; + + /* Using IPv4 for (BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) testing */ + if (h_proto == bpf_htons(ETH_P_IP)) + return bpf_redirect_map(&map_all, 0, + BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS); + /* Using IPv6 for none flag testing */ + else if (h_proto == bpf_htons(ETH_P_IPV6)) + return bpf_redirect_map(&map_all, if_index, 0); + /* All others for BPF_F_BROADCAST testing */ + else + return bpf_redirect_map(&map_all, 0, BPF_F_BROADCAST); +} + +/* The following 2 progs are for 2nd devmap prog testing */ +SEC("xdp") +int xdp_redirect_map_all_prog(struct xdp_md *ctx) +{ + return bpf_redirect_map(&map_egress, 0, + BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS); +} + +SEC("xdp/devmap") +int xdp_devmap_prog(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + __u32 key = ctx->egress_ifindex; + struct ethhdr *eth = data; + __u64 nh_off; + __be64 *mac; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return XDP_DROP; + + mac = bpf_map_lookup_elem(&mac_map, &key); + if (mac) + __builtin_memcpy(eth->h_source, mac, ETH_ALEN); + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c new file mode 100644 index 0000000000..e4c729768b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c @@ -0,0 +1,863 @@ +// SPDX-License-Identifier: LGPL-2.1 OR BSD-2-Clause +/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include <asm/errno.h> + +#define TC_ACT_OK 0 +#define TC_ACT_SHOT 2 + +#define NSEC_PER_SEC 1000000000L + +#define ETH_ALEN 6 +#define ETH_P_IP 0x0800 +#define ETH_P_IPV6 0x86DD + +#define tcp_flag_word(tp) (((union tcp_word_hdr *)(tp))->words[3]) + +#define IP_DF 0x4000 +#define IP_MF 0x2000 +#define IP_OFFSET 0x1fff + +#define NEXTHDR_TCP 6 + +#define TCPOPT_NOP 1 +#define TCPOPT_EOL 0 +#define TCPOPT_MSS 2 +#define TCPOPT_WINDOW 3 +#define TCPOPT_SACK_PERM 4 +#define TCPOPT_TIMESTAMP 8 + +#define TCPOLEN_MSS 4 +#define TCPOLEN_WINDOW 3 +#define TCPOLEN_SACK_PERM 2 +#define TCPOLEN_TIMESTAMP 10 + +#define TCP_TS_HZ 1000 +#define TS_OPT_WSCALE_MASK 0xf +#define TS_OPT_SACK (1 << 4) +#define TS_OPT_ECN (1 << 5) +#define TSBITS 6 +#define TSMASK (((__u32)1 << TSBITS) - 1) +#define TCP_MAX_WSCALE 14U + +#define IPV4_MAXLEN 60 +#define TCP_MAXLEN 60 + +#define DEFAULT_MSS4 1460 +#define DEFAULT_MSS6 1440 +#define DEFAULT_WSCALE 7 +#define DEFAULT_TTL 64 +#define MAX_ALLOWED_PORTS 8 + +#define MAX_PACKET_OFF 0xffff + +#define swap(a, b) \ + do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) + +#define __get_unaligned_t(type, ptr) ({ \ + const struct { type x; } __attribute__((__packed__)) *__pptr = (typeof(__pptr))(ptr); \ + __pptr->x; \ +}) + +#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u64); + __uint(max_entries, 2); +} values SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u16); + __uint(max_entries, MAX_ALLOWED_PORTS); +} allowed_ports SEC(".maps"); + +/* Some symbols defined in net/netfilter/nf_conntrack_bpf.c are unavailable in + * vmlinux.h if CONFIG_NF_CONNTRACK=m, so they are redefined locally. + */ + +struct bpf_ct_opts___local { + s32 netns_id; + s32 error; + u8 l4proto; + u8 dir; + u8 reserved[2]; +} __attribute__((preserve_access_index)); + +#define BPF_F_CURRENT_NETNS (-1) + +extern struct nf_conn *bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, + struct bpf_sock_tuple *bpf_tuple, + __u32 len_tuple, + struct bpf_ct_opts___local *opts, + __u32 len_opts) __ksym; + +extern struct nf_conn *bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, + struct bpf_sock_tuple *bpf_tuple, + u32 len_tuple, + struct bpf_ct_opts___local *opts, + u32 len_opts) __ksym; + +extern void bpf_ct_release(struct nf_conn *ct) __ksym; + +static __always_inline void swap_eth_addr(__u8 *a, __u8 *b) +{ + __u8 tmp[ETH_ALEN]; + + __builtin_memcpy(tmp, a, ETH_ALEN); + __builtin_memcpy(a, b, ETH_ALEN); + __builtin_memcpy(b, tmp, ETH_ALEN); +} + +static __always_inline __u16 csum_fold(__u32 csum) +{ + csum = (csum & 0xffff) + (csum >> 16); + csum = (csum & 0xffff) + (csum >> 16); + return (__u16)~csum; +} + +static __always_inline __u16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, + __u32 len, __u8 proto, + __u32 csum) +{ + __u64 s = csum; + + s += (__u32)saddr; + s += (__u32)daddr; +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + s += proto + len; +#elif __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + s += (proto + len) << 8; +#else +#error Unknown endian +#endif + s = (s & 0xffffffff) + (s >> 32); + s = (s & 0xffffffff) + (s >> 32); + + return csum_fold((__u32)s); +} + +static __always_inline __u16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, __u8 proto, __u32 csum) +{ + __u64 sum = csum; + int i; + +#pragma unroll + for (i = 0; i < 4; i++) + sum += (__u32)saddr->in6_u.u6_addr32[i]; + +#pragma unroll + for (i = 0; i < 4; i++) + sum += (__u32)daddr->in6_u.u6_addr32[i]; + + /* Don't combine additions to avoid 32-bit overflow. */ + sum += bpf_htonl(len); + sum += bpf_htonl(proto); + + sum = (sum & 0xffffffff) + (sum >> 32); + sum = (sum & 0xffffffff) + (sum >> 32); + + return csum_fold((__u32)sum); +} + +static __always_inline __u64 tcp_clock_ns(void) +{ + return bpf_ktime_get_ns(); +} + +static __always_inline __u32 tcp_ns_to_ts(__u64 ns) +{ + return ns / (NSEC_PER_SEC / TCP_TS_HZ); +} + +static __always_inline __u32 tcp_time_stamp_raw(void) +{ + return tcp_ns_to_ts(tcp_clock_ns()); +} + +struct tcpopt_context { + void *data; + void *data_end; + __be32 *tsecr; + __u8 wscale; + bool option_timestamp; + bool option_sack; + __u32 off; +}; + +static __always_inline u8 *next(struct tcpopt_context *ctx, __u32 sz) +{ + __u64 off = ctx->off; + __u8 *data; + + /* Verifier forbids access to packet when offset exceeds MAX_PACKET_OFF */ + if (off > MAX_PACKET_OFF - sz) + return NULL; + + data = ctx->data + off; + barrier_var(data); + if (data + sz >= ctx->data_end) + return NULL; + + ctx->off += sz; + return data; +} + +static int tscookie_tcpopt_parse(struct tcpopt_context *ctx) +{ + __u8 *opcode, *opsize, *wscale, *tsecr; + __u32 off = ctx->off; + + opcode = next(ctx, 1); + if (!opcode) + return 1; + + if (*opcode == TCPOPT_EOL) + return 1; + if (*opcode == TCPOPT_NOP) + return 0; + + opsize = next(ctx, 1); + if (!opsize || *opsize < 2) + return 1; + + switch (*opcode) { + case TCPOPT_WINDOW: + wscale = next(ctx, 1); + if (!wscale) + return 1; + if (*opsize == TCPOLEN_WINDOW) + ctx->wscale = *wscale < TCP_MAX_WSCALE ? *wscale : TCP_MAX_WSCALE; + break; + case TCPOPT_TIMESTAMP: + tsecr = next(ctx, 4); + if (!tsecr) + return 1; + if (*opsize == TCPOLEN_TIMESTAMP) { + ctx->option_timestamp = true; + /* Client's tsval becomes our tsecr. */ + *ctx->tsecr = get_unaligned((__be32 *)tsecr); + } + break; + case TCPOPT_SACK_PERM: + if (*opsize == TCPOLEN_SACK_PERM) + ctx->option_sack = true; + break; + } + + ctx->off = off + *opsize; + + return 0; +} + +static int tscookie_tcpopt_parse_batch(__u32 index, void *context) +{ + int i; + + for (i = 0; i < 7; i++) + if (tscookie_tcpopt_parse(context)) + return 1; + return 0; +} + +static __always_inline bool tscookie_init(struct tcphdr *tcp_header, + __u16 tcp_len, __be32 *tsval, + __be32 *tsecr, void *data, void *data_end) +{ + struct tcpopt_context loop_ctx = { + .data = data, + .data_end = data_end, + .tsecr = tsecr, + .wscale = TS_OPT_WSCALE_MASK, + .option_timestamp = false, + .option_sack = false, + /* Note: currently verifier would track .off as unbound scalar. + * In case if verifier would at some point get smarter and + * compute bounded value for this var, beware that it might + * hinder bpf_loop() convergence validation. + */ + .off = (__u8 *)(tcp_header + 1) - (__u8 *)data, + }; + u32 cookie; + + bpf_loop(6, tscookie_tcpopt_parse_batch, &loop_ctx, 0); + + if (!loop_ctx.option_timestamp) + return false; + + cookie = tcp_time_stamp_raw() & ~TSMASK; + cookie |= loop_ctx.wscale & TS_OPT_WSCALE_MASK; + if (loop_ctx.option_sack) + cookie |= TS_OPT_SACK; + if (tcp_header->ece && tcp_header->cwr) + cookie |= TS_OPT_ECN; + *tsval = bpf_htonl(cookie); + + return true; +} + +static __always_inline void values_get_tcpipopts(__u16 *mss, __u8 *wscale, + __u8 *ttl, bool ipv6) +{ + __u32 key = 0; + __u64 *value; + + value = bpf_map_lookup_elem(&values, &key); + if (value && *value != 0) { + if (ipv6) + *mss = (*value >> 32) & 0xffff; + else + *mss = *value & 0xffff; + *wscale = (*value >> 16) & 0xf; + *ttl = (*value >> 24) & 0xff; + return; + } + + *mss = ipv6 ? DEFAULT_MSS6 : DEFAULT_MSS4; + *wscale = DEFAULT_WSCALE; + *ttl = DEFAULT_TTL; +} + +static __always_inline void values_inc_synacks(void) +{ + __u32 key = 1; + __u64 *value; + + value = bpf_map_lookup_elem(&values, &key); + if (value) + __sync_fetch_and_add(value, 1); +} + +static __always_inline bool check_port_allowed(__u16 port) +{ + __u32 i; + + for (i = 0; i < MAX_ALLOWED_PORTS; i++) { + __u32 key = i; + __u16 *value; + + value = bpf_map_lookup_elem(&allowed_ports, &key); + + if (!value) + break; + /* 0 is a terminator value. Check it first to avoid matching on + * a forbidden port == 0 and returning true. + */ + if (*value == 0) + break; + + if (*value == port) + return true; + } + + return false; +} + +struct header_pointers { + struct ethhdr *eth; + struct iphdr *ipv4; + struct ipv6hdr *ipv6; + struct tcphdr *tcp; + __u16 tcp_len; +}; + +static __always_inline int tcp_dissect(void *data, void *data_end, + struct header_pointers *hdr) +{ + hdr->eth = data; + if (hdr->eth + 1 > data_end) + return XDP_DROP; + + switch (bpf_ntohs(hdr->eth->h_proto)) { + case ETH_P_IP: + hdr->ipv6 = NULL; + + hdr->ipv4 = (void *)hdr->eth + sizeof(*hdr->eth); + if (hdr->ipv4 + 1 > data_end) + return XDP_DROP; + if (hdr->ipv4->ihl * 4 < sizeof(*hdr->ipv4)) + return XDP_DROP; + if (hdr->ipv4->version != 4) + return XDP_DROP; + + if (hdr->ipv4->protocol != IPPROTO_TCP) + return XDP_PASS; + + hdr->tcp = (void *)hdr->ipv4 + hdr->ipv4->ihl * 4; + break; + case ETH_P_IPV6: + hdr->ipv4 = NULL; + + hdr->ipv6 = (void *)hdr->eth + sizeof(*hdr->eth); + if (hdr->ipv6 + 1 > data_end) + return XDP_DROP; + if (hdr->ipv6->version != 6) + return XDP_DROP; + + /* XXX: Extension headers are not supported and could circumvent + * XDP SYN flood protection. + */ + if (hdr->ipv6->nexthdr != NEXTHDR_TCP) + return XDP_PASS; + + hdr->tcp = (void *)hdr->ipv6 + sizeof(*hdr->ipv6); + break; + default: + /* XXX: VLANs will circumvent XDP SYN flood protection. */ + return XDP_PASS; + } + + if (hdr->tcp + 1 > data_end) + return XDP_DROP; + hdr->tcp_len = hdr->tcp->doff * 4; + if (hdr->tcp_len < sizeof(*hdr->tcp)) + return XDP_DROP; + + return XDP_TX; +} + +static __always_inline int tcp_lookup(void *ctx, struct header_pointers *hdr, bool xdp) +{ + struct bpf_ct_opts___local ct_lookup_opts = { + .netns_id = BPF_F_CURRENT_NETNS, + .l4proto = IPPROTO_TCP, + }; + struct bpf_sock_tuple tup = {}; + struct nf_conn *ct; + __u32 tup_size; + + if (hdr->ipv4) { + /* TCP doesn't normally use fragments, and XDP can't reassemble + * them. + */ + if ((hdr->ipv4->frag_off & bpf_htons(IP_DF | IP_MF | IP_OFFSET)) != bpf_htons(IP_DF)) + return XDP_DROP; + + tup.ipv4.saddr = hdr->ipv4->saddr; + tup.ipv4.daddr = hdr->ipv4->daddr; + tup.ipv4.sport = hdr->tcp->source; + tup.ipv4.dport = hdr->tcp->dest; + tup_size = sizeof(tup.ipv4); + } else if (hdr->ipv6) { + __builtin_memcpy(tup.ipv6.saddr, &hdr->ipv6->saddr, sizeof(tup.ipv6.saddr)); + __builtin_memcpy(tup.ipv6.daddr, &hdr->ipv6->daddr, sizeof(tup.ipv6.daddr)); + tup.ipv6.sport = hdr->tcp->source; + tup.ipv6.dport = hdr->tcp->dest; + tup_size = sizeof(tup.ipv6); + } else { + /* The verifier can't track that either ipv4 or ipv6 is not + * NULL. + */ + return XDP_ABORTED; + } + if (xdp) + ct = bpf_xdp_ct_lookup(ctx, &tup, tup_size, &ct_lookup_opts, sizeof(ct_lookup_opts)); + else + ct = bpf_skb_ct_lookup(ctx, &tup, tup_size, &ct_lookup_opts, sizeof(ct_lookup_opts)); + if (ct) { + unsigned long status = ct->status; + + bpf_ct_release(ct); + if (status & IPS_CONFIRMED) + return XDP_PASS; + } else if (ct_lookup_opts.error != -ENOENT) { + return XDP_ABORTED; + } + + /* error == -ENOENT || !(status & IPS_CONFIRMED) */ + return XDP_TX; +} + +static __always_inline __u8 tcp_mkoptions(__be32 *buf, __be32 *tsopt, __u16 mss, + __u8 wscale) +{ + __be32 *start = buf; + + *buf++ = bpf_htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | mss); + + if (!tsopt) + return buf - start; + + if (tsopt[0] & bpf_htonl(1 << 4)) + *buf++ = bpf_htonl((TCPOPT_SACK_PERM << 24) | + (TCPOLEN_SACK_PERM << 16) | + (TCPOPT_TIMESTAMP << 8) | + TCPOLEN_TIMESTAMP); + else + *buf++ = bpf_htonl((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_TIMESTAMP << 8) | + TCPOLEN_TIMESTAMP); + *buf++ = tsopt[0]; + *buf++ = tsopt[1]; + + if ((tsopt[0] & bpf_htonl(0xf)) != bpf_htonl(0xf)) + *buf++ = bpf_htonl((TCPOPT_NOP << 24) | + (TCPOPT_WINDOW << 16) | + (TCPOLEN_WINDOW << 8) | + wscale); + + return buf - start; +} + +static __always_inline void tcp_gen_synack(struct tcphdr *tcp_header, + __u32 cookie, __be32 *tsopt, + __u16 mss, __u8 wscale) +{ + void *tcp_options; + + tcp_flag_word(tcp_header) = TCP_FLAG_SYN | TCP_FLAG_ACK; + if (tsopt && (tsopt[0] & bpf_htonl(1 << 5))) + tcp_flag_word(tcp_header) |= TCP_FLAG_ECE; + tcp_header->doff = 5; /* doff is part of tcp_flag_word. */ + swap(tcp_header->source, tcp_header->dest); + tcp_header->ack_seq = bpf_htonl(bpf_ntohl(tcp_header->seq) + 1); + tcp_header->seq = bpf_htonl(cookie); + tcp_header->window = 0; + tcp_header->urg_ptr = 0; + tcp_header->check = 0; /* Calculate checksum later. */ + + tcp_options = (void *)(tcp_header + 1); + tcp_header->doff += tcp_mkoptions(tcp_options, tsopt, mss, wscale); +} + +static __always_inline void tcpv4_gen_synack(struct header_pointers *hdr, + __u32 cookie, __be32 *tsopt) +{ + __u8 wscale; + __u16 mss; + __u8 ttl; + + values_get_tcpipopts(&mss, &wscale, &ttl, false); + + swap_eth_addr(hdr->eth->h_source, hdr->eth->h_dest); + + swap(hdr->ipv4->saddr, hdr->ipv4->daddr); + hdr->ipv4->check = 0; /* Calculate checksum later. */ + hdr->ipv4->tos = 0; + hdr->ipv4->id = 0; + hdr->ipv4->ttl = ttl; + + tcp_gen_synack(hdr->tcp, cookie, tsopt, mss, wscale); + + hdr->tcp_len = hdr->tcp->doff * 4; + hdr->ipv4->tot_len = bpf_htons(sizeof(*hdr->ipv4) + hdr->tcp_len); +} + +static __always_inline void tcpv6_gen_synack(struct header_pointers *hdr, + __u32 cookie, __be32 *tsopt) +{ + __u8 wscale; + __u16 mss; + __u8 ttl; + + values_get_tcpipopts(&mss, &wscale, &ttl, true); + + swap_eth_addr(hdr->eth->h_source, hdr->eth->h_dest); + + swap(hdr->ipv6->saddr, hdr->ipv6->daddr); + *(__be32 *)hdr->ipv6 = bpf_htonl(0x60000000); + hdr->ipv6->hop_limit = ttl; + + tcp_gen_synack(hdr->tcp, cookie, tsopt, mss, wscale); + + hdr->tcp_len = hdr->tcp->doff * 4; + hdr->ipv6->payload_len = bpf_htons(hdr->tcp_len); +} + +static __always_inline int syncookie_handle_syn(struct header_pointers *hdr, + void *ctx, + void *data, void *data_end, + bool xdp) +{ + __u32 old_pkt_size, new_pkt_size; + /* Unlike clang 10, clang 11 and 12 generate code that doesn't pass the + * BPF verifier if tsopt is not volatile. Volatile forces it to store + * the pointer value and use it directly, otherwise tcp_mkoptions is + * (mis)compiled like this: + * if (!tsopt) + * return buf - start; + * reg = stored_return_value_of_tscookie_init; + * if (reg) + * tsopt = tsopt_buf; + * else + * tsopt = NULL; + * ... + * *buf++ = tsopt[1]; + * It creates a dead branch where tsopt is assigned NULL, but the + * verifier can't prove it's dead and blocks the program. + */ + __be32 * volatile tsopt = NULL; + __be32 tsopt_buf[2] = {}; + __u16 ip_len; + __u32 cookie; + __s64 value; + + /* Checksum is not yet verified, but both checksum failure and TCP + * header checks return XDP_DROP, so the order doesn't matter. + */ + if (hdr->tcp->fin || hdr->tcp->rst) + return XDP_DROP; + + /* Issue SYN cookies on allowed ports, drop SYN packets on blocked + * ports. + */ + if (!check_port_allowed(bpf_ntohs(hdr->tcp->dest))) + return XDP_DROP; + + if (hdr->ipv4) { + /* Check the IPv4 and TCP checksums before creating a SYNACK. */ + value = bpf_csum_diff(0, 0, (void *)hdr->ipv4, hdr->ipv4->ihl * 4, 0); + if (value < 0) + return XDP_ABORTED; + if (csum_fold(value) != 0) + return XDP_DROP; /* Bad IPv4 checksum. */ + + value = bpf_csum_diff(0, 0, (void *)hdr->tcp, hdr->tcp_len, 0); + if (value < 0) + return XDP_ABORTED; + if (csum_tcpudp_magic(hdr->ipv4->saddr, hdr->ipv4->daddr, + hdr->tcp_len, IPPROTO_TCP, value) != 0) + return XDP_DROP; /* Bad TCP checksum. */ + + ip_len = sizeof(*hdr->ipv4); + + value = bpf_tcp_raw_gen_syncookie_ipv4(hdr->ipv4, hdr->tcp, + hdr->tcp_len); + } else if (hdr->ipv6) { + /* Check the TCP checksum before creating a SYNACK. */ + value = bpf_csum_diff(0, 0, (void *)hdr->tcp, hdr->tcp_len, 0); + if (value < 0) + return XDP_ABORTED; + if (csum_ipv6_magic(&hdr->ipv6->saddr, &hdr->ipv6->daddr, + hdr->tcp_len, IPPROTO_TCP, value) != 0) + return XDP_DROP; /* Bad TCP checksum. */ + + ip_len = sizeof(*hdr->ipv6); + + value = bpf_tcp_raw_gen_syncookie_ipv6(hdr->ipv6, hdr->tcp, + hdr->tcp_len); + } else { + return XDP_ABORTED; + } + + if (value < 0) + return XDP_ABORTED; + cookie = (__u32)value; + + if (tscookie_init((void *)hdr->tcp, hdr->tcp_len, + &tsopt_buf[0], &tsopt_buf[1], data, data_end)) + tsopt = tsopt_buf; + + /* Check that there is enough space for a SYNACK. It also covers + * the check that the destination of the __builtin_memmove below + * doesn't overflow. + */ + if (data + sizeof(*hdr->eth) + ip_len + TCP_MAXLEN > data_end) + return XDP_ABORTED; + + if (hdr->ipv4) { + if (hdr->ipv4->ihl * 4 > sizeof(*hdr->ipv4)) { + struct tcphdr *new_tcp_header; + + new_tcp_header = data + sizeof(*hdr->eth) + sizeof(*hdr->ipv4); + __builtin_memmove(new_tcp_header, hdr->tcp, sizeof(*hdr->tcp)); + hdr->tcp = new_tcp_header; + + hdr->ipv4->ihl = sizeof(*hdr->ipv4) / 4; + } + + tcpv4_gen_synack(hdr, cookie, tsopt); + } else if (hdr->ipv6) { + tcpv6_gen_synack(hdr, cookie, tsopt); + } else { + return XDP_ABORTED; + } + + /* Recalculate checksums. */ + hdr->tcp->check = 0; + value = bpf_csum_diff(0, 0, (void *)hdr->tcp, hdr->tcp_len, 0); + if (value < 0) + return XDP_ABORTED; + if (hdr->ipv4) { + hdr->tcp->check = csum_tcpudp_magic(hdr->ipv4->saddr, + hdr->ipv4->daddr, + hdr->tcp_len, + IPPROTO_TCP, + value); + + hdr->ipv4->check = 0; + value = bpf_csum_diff(0, 0, (void *)hdr->ipv4, sizeof(*hdr->ipv4), 0); + if (value < 0) + return XDP_ABORTED; + hdr->ipv4->check = csum_fold(value); + } else if (hdr->ipv6) { + hdr->tcp->check = csum_ipv6_magic(&hdr->ipv6->saddr, + &hdr->ipv6->daddr, + hdr->tcp_len, + IPPROTO_TCP, + value); + } else { + return XDP_ABORTED; + } + + /* Set the new packet size. */ + old_pkt_size = data_end - data; + new_pkt_size = sizeof(*hdr->eth) + ip_len + hdr->tcp->doff * 4; + if (xdp) { + if (bpf_xdp_adjust_tail(ctx, new_pkt_size - old_pkt_size)) + return XDP_ABORTED; + } else { + if (bpf_skb_change_tail(ctx, new_pkt_size, 0)) + return XDP_ABORTED; + } + + values_inc_synacks(); + + return XDP_TX; +} + +static __always_inline int syncookie_handle_ack(struct header_pointers *hdr) +{ + int err; + + if (hdr->tcp->rst) + return XDP_DROP; + + if (hdr->ipv4) + err = bpf_tcp_raw_check_syncookie_ipv4(hdr->ipv4, hdr->tcp); + else if (hdr->ipv6) + err = bpf_tcp_raw_check_syncookie_ipv6(hdr->ipv6, hdr->tcp); + else + return XDP_ABORTED; + if (err) + return XDP_DROP; + + return XDP_PASS; +} + +static __always_inline int syncookie_part1(void *ctx, void *data, void *data_end, + struct header_pointers *hdr, bool xdp) +{ + int ret; + + ret = tcp_dissect(data, data_end, hdr); + if (ret != XDP_TX) + return ret; + + ret = tcp_lookup(ctx, hdr, xdp); + if (ret != XDP_TX) + return ret; + + /* Packet is TCP and doesn't belong to an established connection. */ + + if ((hdr->tcp->syn ^ hdr->tcp->ack) != 1) + return XDP_DROP; + + /* Grow the TCP header to TCP_MAXLEN to be able to pass any hdr->tcp_len + * to bpf_tcp_raw_gen_syncookie_ipv{4,6} and pass the verifier. + */ + if (xdp) { + if (bpf_xdp_adjust_tail(ctx, TCP_MAXLEN - hdr->tcp_len)) + return XDP_ABORTED; + } else { + /* Without volatile the verifier throws this error: + * R9 32-bit pointer arithmetic prohibited + */ + volatile u64 old_len = data_end - data; + + if (bpf_skb_change_tail(ctx, old_len + TCP_MAXLEN - hdr->tcp_len, 0)) + return XDP_ABORTED; + } + + return XDP_TX; +} + +static __always_inline int syncookie_part2(void *ctx, void *data, void *data_end, + struct header_pointers *hdr, bool xdp) +{ + if (hdr->ipv4) { + hdr->eth = data; + hdr->ipv4 = (void *)hdr->eth + sizeof(*hdr->eth); + /* IPV4_MAXLEN is needed when calculating checksum. + * At least sizeof(struct iphdr) is needed here to access ihl. + */ + if ((void *)hdr->ipv4 + IPV4_MAXLEN > data_end) + return XDP_ABORTED; + hdr->tcp = (void *)hdr->ipv4 + hdr->ipv4->ihl * 4; + } else if (hdr->ipv6) { + hdr->eth = data; + hdr->ipv6 = (void *)hdr->eth + sizeof(*hdr->eth); + hdr->tcp = (void *)hdr->ipv6 + sizeof(*hdr->ipv6); + } else { + return XDP_ABORTED; + } + + if ((void *)hdr->tcp + TCP_MAXLEN > data_end) + return XDP_ABORTED; + + /* We run out of registers, tcp_len gets spilled to the stack, and the + * verifier forgets its min and max values checked above in tcp_dissect. + */ + hdr->tcp_len = hdr->tcp->doff * 4; + if (hdr->tcp_len < sizeof(*hdr->tcp)) + return XDP_ABORTED; + + return hdr->tcp->syn ? syncookie_handle_syn(hdr, ctx, data, data_end, xdp) : + syncookie_handle_ack(hdr); +} + +SEC("xdp") +int syncookie_xdp(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct header_pointers hdr; + int ret; + + ret = syncookie_part1(ctx, data, data_end, &hdr, true); + if (ret != XDP_TX) + return ret; + + data_end = (void *)(long)ctx->data_end; + data = (void *)(long)ctx->data; + + return syncookie_part2(ctx, data, data_end, &hdr, true); +} + +SEC("tc") +int syncookie_tc(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct header_pointers hdr; + int ret; + + ret = syncookie_part1(skb, data, data_end, &hdr, false); + if (ret != XDP_TX) + return ret == XDP_PASS ? TC_ACT_OK : TC_ACT_SHOT; + + data_end = (void *)(long)skb->data_end; + data = (void *)(long)skb->data; + + ret = syncookie_part2(skb, data, data_end, &hdr, false); + switch (ret) { + case XDP_PASS: + return TC_ACT_OK; + case XDP_TX: + return bpf_redirect(skb->ifindex, 0); + default: + return TC_ACT_SHOT; + } +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_tx.c b/tools/testing/selftests/bpf/progs/xdp_tx.c new file mode 100644 index 0000000000..5f725c720e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_tx.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("xdp") +int xdp_tx(struct xdp_md *xdp) +{ + return XDP_TX; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdping_kern.c b/tools/testing/selftests/bpf/progs/xdping_kern.c new file mode 100644 index 0000000000..54cf176511 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdping_kern.c @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved. */ + +#define KBUILD_MODNAME "foo" +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/icmp.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include "xdping.h" + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 256); + __type(key, __u32); + __type(value, struct pinginfo); +} ping_map SEC(".maps"); + +static __always_inline void swap_src_dst_mac(void *data) +{ + unsigned short *p = data; + unsigned short dst[3]; + + dst[0] = p[0]; + dst[1] = p[1]; + dst[2] = p[2]; + p[0] = p[3]; + p[1] = p[4]; + p[2] = p[5]; + p[3] = dst[0]; + p[4] = dst[1]; + p[5] = dst[2]; +} + +static __always_inline __u16 csum_fold_helper(__wsum sum) +{ + sum = (sum & 0xffff) + (sum >> 16); + return ~((sum & 0xffff) + (sum >> 16)); +} + +static __always_inline __u16 ipv4_csum(void *data_start, int data_size) +{ + __wsum sum; + + sum = bpf_csum_diff(0, 0, data_start, data_size, 0); + return csum_fold_helper(sum); +} + +#define ICMP_ECHO_LEN 64 + +static __always_inline int icmp_check(struct xdp_md *ctx, int type) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + struct icmphdr *icmph; + struct iphdr *iph; + + if (data + sizeof(*eth) + sizeof(*iph) + ICMP_ECHO_LEN > data_end) + return XDP_PASS; + + if (eth->h_proto != bpf_htons(ETH_P_IP)) + return XDP_PASS; + + iph = data + sizeof(*eth); + + if (iph->protocol != IPPROTO_ICMP) + return XDP_PASS; + + if (bpf_ntohs(iph->tot_len) - sizeof(*iph) != ICMP_ECHO_LEN) + return XDP_PASS; + + icmph = data + sizeof(*eth) + sizeof(*iph); + + if (icmph->type != type) + return XDP_PASS; + + return XDP_TX; +} + +SEC("xdp") +int xdping_client(struct xdp_md *ctx) +{ + void *data = (void *)(long)ctx->data; + struct pinginfo *pinginfo = NULL; + struct ethhdr *eth = data; + struct icmphdr *icmph; + struct iphdr *iph; + __u64 recvtime; + __be32 raddr; + __be16 seq; + int ret; + __u8 i; + + ret = icmp_check(ctx, ICMP_ECHOREPLY); + + if (ret != XDP_TX) + return ret; + + iph = data + sizeof(*eth); + icmph = data + sizeof(*eth) + sizeof(*iph); + raddr = iph->saddr; + + /* Record time reply received. */ + recvtime = bpf_ktime_get_ns(); + pinginfo = bpf_map_lookup_elem(&ping_map, &raddr); + if (!pinginfo || pinginfo->seq != icmph->un.echo.sequence) + return XDP_PASS; + + if (pinginfo->start) { +#pragma clang loop unroll(full) + for (i = 0; i < XDPING_MAX_COUNT; i++) { + if (pinginfo->times[i] == 0) + break; + } + /* verifier is fussy here... */ + if (i < XDPING_MAX_COUNT) { + pinginfo->times[i] = recvtime - + pinginfo->start; + pinginfo->start = 0; + i++; + } + /* No more space for values? */ + if (i == pinginfo->count || i == XDPING_MAX_COUNT) + return XDP_PASS; + } + + /* Now convert reply back into echo request. */ + swap_src_dst_mac(data); + iph->saddr = iph->daddr; + iph->daddr = raddr; + icmph->type = ICMP_ECHO; + seq = bpf_htons(bpf_ntohs(icmph->un.echo.sequence) + 1); + icmph->un.echo.sequence = seq; + icmph->checksum = 0; + icmph->checksum = ipv4_csum(icmph, ICMP_ECHO_LEN); + + pinginfo->seq = seq; + pinginfo->start = bpf_ktime_get_ns(); + + return XDP_TX; +} + +SEC("xdp") +int xdping_server(struct xdp_md *ctx) +{ + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + struct icmphdr *icmph; + struct iphdr *iph; + __be32 raddr; + int ret; + + ret = icmp_check(ctx, ICMP_ECHO); + + if (ret != XDP_TX) + return ret; + + iph = data + sizeof(*eth); + icmph = data + sizeof(*eth) + sizeof(*iph); + raddr = iph->saddr; + + /* Now convert request into echo reply. */ + swap_src_dst_mac(data); + iph->saddr = iph->daddr; + iph->daddr = raddr; + icmph->type = ICMP_ECHOREPLY; + icmph->checksum = 0; + icmph->checksum = ipv4_csum(icmph, ICMP_ECHO_LEN); + + return XDP_TX; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdpwall.c b/tools/testing/selftests/bpf/progs/xdpwall.c new file mode 100644 index 0000000000..c2dd0c2823 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdpwall.c @@ -0,0 +1,364 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <stdbool.h> +#include <stdint.h> +#include <linux/stddef.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/bpf.h> +#include <linux/types.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +enum pkt_parse_err { + NO_ERR, + BAD_IP6_HDR, + BAD_IP4GUE_HDR, + BAD_IP6GUE_HDR, +}; + +enum pkt_flag { + TUNNEL = 0x1, + TCP_SYN = 0x2, + QUIC_INITIAL_FLAG = 0x4, + TCP_ACK = 0x8, + TCP_RST = 0x10 +}; + +struct v4_lpm_key { + __u32 prefixlen; + __u32 src; +}; + +struct v4_lpm_val { + struct v4_lpm_key key; + __u8 val; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 16); + __type(key, struct in6_addr); + __type(value, bool); +} v6_addr_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 16); + __type(key, __u32); + __type(value, bool); +} v4_addr_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __uint(max_entries, 16); + __uint(key_size, sizeof(struct v4_lpm_key)); + __uint(value_size, sizeof(struct v4_lpm_val)); + __uint(map_flags, BPF_F_NO_PREALLOC); +} v4_lpm_val_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 16); + __type(key, int); + __type(value, __u8); +} tcp_port_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 16); + __type(key, int); + __type(value, __u16); +} udp_port_map SEC(".maps"); + +enum ip_type { V4 = 1, V6 = 2 }; + +struct fw_match_info { + __u8 v4_src_ip_match; + __u8 v6_src_ip_match; + __u8 v4_src_prefix_match; + __u8 v4_dst_prefix_match; + __u8 tcp_dp_match; + __u16 udp_sp_match; + __u16 udp_dp_match; + bool is_tcp; + bool is_tcp_syn; +}; + +struct pkt_info { + enum ip_type type; + union { + struct iphdr *ipv4; + struct ipv6hdr *ipv6; + } ip; + int sport; + int dport; + __u16 trans_hdr_offset; + __u8 proto; + __u8 flags; +}; + +static __always_inline struct ethhdr *parse_ethhdr(void *data, void *data_end) +{ + struct ethhdr *eth = data; + + if (eth + 1 > data_end) + return NULL; + + return eth; +} + +static __always_inline __u8 filter_ipv6_addr(const struct in6_addr *ipv6addr) +{ + __u8 *leaf; + + leaf = bpf_map_lookup_elem(&v6_addr_map, ipv6addr); + + return leaf ? *leaf : 0; +} + +static __always_inline __u8 filter_ipv4_addr(const __u32 ipaddr) +{ + __u8 *leaf; + + leaf = bpf_map_lookup_elem(&v4_addr_map, &ipaddr); + + return leaf ? *leaf : 0; +} + +static __always_inline __u8 filter_ipv4_lpm(const __u32 ipaddr) +{ + struct v4_lpm_key v4_key = {}; + struct v4_lpm_val *lpm_val; + + v4_key.src = ipaddr; + v4_key.prefixlen = 32; + + lpm_val = bpf_map_lookup_elem(&v4_lpm_val_map, &v4_key); + + return lpm_val ? lpm_val->val : 0; +} + + +static __always_inline void +filter_src_dst_ip(struct pkt_info* info, struct fw_match_info* match_info) +{ + if (info->type == V6) { + match_info->v6_src_ip_match = + filter_ipv6_addr(&info->ip.ipv6->saddr); + } else if (info->type == V4) { + match_info->v4_src_ip_match = + filter_ipv4_addr(info->ip.ipv4->saddr); + match_info->v4_src_prefix_match = + filter_ipv4_lpm(info->ip.ipv4->saddr); + match_info->v4_dst_prefix_match = + filter_ipv4_lpm(info->ip.ipv4->daddr); + } +} + +static __always_inline void * +get_transport_hdr(__u16 offset, void *data, void *data_end) +{ + if (offset > 255 || data + offset > data_end) + return NULL; + + return data + offset; +} + +static __always_inline bool tcphdr_only_contains_flag(struct tcphdr *tcp, + __u32 FLAG) +{ + return (tcp_flag_word(tcp) & + (TCP_FLAG_ACK | TCP_FLAG_RST | TCP_FLAG_SYN | TCP_FLAG_FIN)) == FLAG; +} + +static __always_inline void set_tcp_flags(struct pkt_info *info, + struct tcphdr *tcp) { + if (tcphdr_only_contains_flag(tcp, TCP_FLAG_SYN)) + info->flags |= TCP_SYN; + else if (tcphdr_only_contains_flag(tcp, TCP_FLAG_ACK)) + info->flags |= TCP_ACK; + else if (tcphdr_only_contains_flag(tcp, TCP_FLAG_RST)) + info->flags |= TCP_RST; +} + +static __always_inline bool +parse_tcp(struct pkt_info *info, void *transport_hdr, void *data_end) +{ + struct tcphdr *tcp = transport_hdr; + + if (tcp + 1 > data_end) + return false; + + info->sport = bpf_ntohs(tcp->source); + info->dport = bpf_ntohs(tcp->dest); + set_tcp_flags(info, tcp); + + return true; +} + +static __always_inline bool +parse_udp(struct pkt_info *info, void *transport_hdr, void *data_end) +{ + struct udphdr *udp = transport_hdr; + + if (udp + 1 > data_end) + return false; + + info->sport = bpf_ntohs(udp->source); + info->dport = bpf_ntohs(udp->dest); + + return true; +} + +static __always_inline __u8 filter_tcp_port(int port) +{ + __u8 *leaf = bpf_map_lookup_elem(&tcp_port_map, &port); + + return leaf ? *leaf : 0; +} + +static __always_inline __u16 filter_udp_port(int port) +{ + __u16 *leaf = bpf_map_lookup_elem(&udp_port_map, &port); + + return leaf ? *leaf : 0; +} + +static __always_inline bool +filter_transport_hdr(void *transport_hdr, void *data_end, + struct pkt_info *info, struct fw_match_info *match_info) +{ + if (info->proto == IPPROTO_TCP) { + if (!parse_tcp(info, transport_hdr, data_end)) + return false; + + match_info->is_tcp = true; + match_info->is_tcp_syn = (info->flags & TCP_SYN) > 0; + + match_info->tcp_dp_match = filter_tcp_port(info->dport); + } else if (info->proto == IPPROTO_UDP) { + if (!parse_udp(info, transport_hdr, data_end)) + return false; + + match_info->udp_dp_match = filter_udp_port(info->dport); + match_info->udp_sp_match = filter_udp_port(info->sport); + } + + return true; +} + +static __always_inline __u8 +parse_gue_v6(struct pkt_info *info, struct ipv6hdr *ip6h, void *data_end) +{ + struct udphdr *udp = (struct udphdr *)(ip6h + 1); + void *encap_data = udp + 1; + + if (udp + 1 > data_end) + return BAD_IP6_HDR; + + if (udp->dest != bpf_htons(6666)) + return NO_ERR; + + info->flags |= TUNNEL; + + if (encap_data + 1 > data_end) + return BAD_IP6GUE_HDR; + + if (*(__u8 *)encap_data & 0x30) { + struct ipv6hdr *inner_ip6h = encap_data; + + if (inner_ip6h + 1 > data_end) + return BAD_IP6GUE_HDR; + + info->type = V6; + info->proto = inner_ip6h->nexthdr; + info->ip.ipv6 = inner_ip6h; + info->trans_hdr_offset += sizeof(struct ipv6hdr) + sizeof(struct udphdr); + } else { + struct iphdr *inner_ip4h = encap_data; + + if (inner_ip4h + 1 > data_end) + return BAD_IP6GUE_HDR; + + info->type = V4; + info->proto = inner_ip4h->protocol; + info->ip.ipv4 = inner_ip4h; + info->trans_hdr_offset += sizeof(struct iphdr) + sizeof(struct udphdr); + } + + return NO_ERR; +} + +static __always_inline __u8 parse_ipv6_gue(struct pkt_info *info, + void *data, void *data_end) +{ + struct ipv6hdr *ip6h = data + sizeof(struct ethhdr); + + if (ip6h + 1 > data_end) + return BAD_IP6_HDR; + + info->proto = ip6h->nexthdr; + info->ip.ipv6 = ip6h; + info->type = V6; + info->trans_hdr_offset = sizeof(struct ethhdr) + sizeof(struct ipv6hdr); + + if (info->proto == IPPROTO_UDP) + return parse_gue_v6(info, ip6h, data_end); + + return NO_ERR; +} + +SEC("xdp") +int edgewall(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)(ctx->data_end); + void *data = (void *)(long)(ctx->data); + struct fw_match_info match_info = {}; + struct pkt_info info = {}; + void *transport_hdr; + struct ethhdr *eth; + bool filter_res; + __u32 proto; + + eth = parse_ethhdr(data, data_end); + if (!eth) + return XDP_DROP; + + proto = eth->h_proto; + if (proto != bpf_htons(ETH_P_IPV6)) + return XDP_DROP; + + if (parse_ipv6_gue(&info, data, data_end)) + return XDP_DROP; + + if (info.proto == IPPROTO_ICMPV6) + return XDP_PASS; + + if (info.proto != IPPROTO_TCP && info.proto != IPPROTO_UDP) + return XDP_DROP; + + filter_src_dst_ip(&info, &match_info); + + transport_hdr = get_transport_hdr(info.trans_hdr_offset, data, + data_end); + if (!transport_hdr) + return XDP_DROP; + + filter_res = filter_transport_hdr(transport_hdr, data_end, + &info, &match_info); + if (!filter_res) + return XDP_DROP; + + if (match_info.is_tcp && !match_info.is_tcp_syn) + return XDP_PASS; + + return XDP_DROP; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xfrm_info.c b/tools/testing/selftests/bpf/progs/xfrm_info.c new file mode 100644 index 0000000000..f6a501fbba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xfrm_info.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> + +struct bpf_xfrm_info___local { + u32 if_id; + int link; +} __attribute__((preserve_access_index)); + +__u32 req_if_id; +__u32 resp_if_id; + +int bpf_skb_set_xfrm_info(struct __sk_buff *skb_ctx, + const struct bpf_xfrm_info___local *from) __ksym; +int bpf_skb_get_xfrm_info(struct __sk_buff *skb_ctx, + struct bpf_xfrm_info___local *to) __ksym; + +SEC("tc") +int set_xfrm_info(struct __sk_buff *skb) +{ + struct bpf_xfrm_info___local info = { .if_id = req_if_id }; + + return bpf_skb_set_xfrm_info(skb, &info) ? TC_ACT_SHOT : TC_ACT_UNSPEC; +} + +SEC("tc") +int get_xfrm_info(struct __sk_buff *skb) +{ + struct bpf_xfrm_info___local info = {}; + + if (bpf_skb_get_xfrm_info(skb, &info) < 0) + return TC_ACT_SHOT; + + resp_if_id = info.if_id; + + return TC_ACT_UNSPEC; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c new file mode 100644 index 0000000000..24369f2428 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Intel */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "xsk_xdp_metadata.h" + +struct { + __uint(type, BPF_MAP_TYPE_XSKMAP); + __uint(max_entries, 1); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); +} xsk SEC(".maps"); + +static unsigned int idx; +int count = 0; + +SEC("xdp.frags") int xsk_def_prog(struct xdp_md *xdp) +{ + return bpf_redirect_map(&xsk, 0, XDP_DROP); +} + +SEC("xdp.frags") int xsk_xdp_drop(struct xdp_md *xdp) +{ + /* Drop every other packet */ + if (idx++ % 2) + return XDP_DROP; + + return bpf_redirect_map(&xsk, 0, XDP_DROP); +} + +SEC("xdp.frags") int xsk_xdp_populate_metadata(struct xdp_md *xdp) +{ + void *data, *data_meta; + struct xdp_info *meta; + int err; + + /* Reserve enough for all custom metadata. */ + err = bpf_xdp_adjust_meta(xdp, -(int)sizeof(struct xdp_info)); + if (err) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_meta = (void *)(long)xdp->data_meta; + + if (data_meta + sizeof(struct xdp_info) > data) + return XDP_DROP; + + meta = data_meta; + meta->count = count++; + + return bpf_redirect_map(&xsk, 0, XDP_DROP); +} + +char _license[] SEC("license") = "GPL"; |