From d6f1837107c00fa7b2fdb606acf65b33b455dbfd Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 11 Mar 2019 22:21:09 -0700 Subject: selftests/bpf: fix segfault of test_progs when prog loading failed The test_progs subtests, test_spin_lock() and test_map_lock(), requires BTF present to run successfully. Currently, when BTF failed to load, test_progs will segfault, $ ./test_progs ... 12: (bf) r1 = r8 13: (85) call bpf_spin_lock#93 map 'hash_map' has to have BTF in order to use bpf_spin_lock libbpf: -- END LOG -- libbpf: failed to load program 'map_lock_demo' libbpf: failed to load object './test_map_lock.o' test_map_lock:bpf_prog_load errno 13 Segmentation fault The segfault is caused by uninitialized variable "obj", which is used in bpf_object__close(obj), when bpf prog failed to load. Initializing variable "obj" to NULL in two occasions fixed the problem. $ ./test_progs ... Summary: 219 PASSED, 2 FAILED Fixes: b4d4556c3266 ("selftests/bpf: add bpf_spin_lock verifier tests") Fixes: ba72a7b4badb ("selftests/bpf: test for BPF_F_LOCK") Reported-by: Daniel Borkmann Signed-off-by: Yonghong Song Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/prog_tests/map_lock.c | 2 +- tools/testing/selftests/bpf/prog_tests/spinlock.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/map_lock.c b/tools/testing/selftests/bpf/prog_tests/map_lock.c index 90f8a206340a..ee99368c595c 100644 --- a/tools/testing/selftests/bpf/prog_tests/map_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/map_lock.c @@ -37,7 +37,7 @@ void test_map_lock(void) const char *file = "./test_map_lock.o"; int prog_fd, map_fd[2], vars[17] = {}; pthread_t thread_id[6]; - struct bpf_object *obj; + struct bpf_object *obj = NULL; int err = 0, key = 0, i; void *ret; diff --git a/tools/testing/selftests/bpf/prog_tests/spinlock.c b/tools/testing/selftests/bpf/prog_tests/spinlock.c index 9a573a9675d7..114ebe6a438e 100644 --- a/tools/testing/selftests/bpf/prog_tests/spinlock.c +++ b/tools/testing/selftests/bpf/prog_tests/spinlock.c @@ -5,7 +5,7 @@ void test_spinlock(void) { const char *file = "./test_spin_lock.o"; pthread_t thread_id[4]; - struct bpf_object *obj; + struct bpf_object *obj = NULL; int prog_fd; int err = 0, i; void *ret; -- cgit From b55aa7b04bb42274b4a894020b5b2fa059c3527e Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 12 Mar 2019 10:23:09 -0700 Subject: bpf: Test ref release issue in bpf_tcp_sock and bpf_sk_fullsock Adding verifier tests to ensure the ptr returned from bpf_tcp_sock() and bpf_sk_fullsock() cannot be accessed after bpf_sk_release() is called. A few of the tests are derived from a reproducer test by Lorenz Bauer. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- .../testing/selftests/bpf/verifier/ref_tracking.c | 168 +++++++++++++++++++++ tools/testing/selftests/bpf/verifier/sock.c | 4 +- 2 files changed, 170 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index 3ed3593bd8b6..923f2110072d 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -605,3 +605,171 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = ACCEPT, }, +{ + "reference tracking: use ptr from bpf_tcp_sock() after release", + .insns = { + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_tcp_sock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_tcp_sock, snd_cwnd)), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "invalid mem access", +}, +{ + "reference tracking: use ptr from bpf_sk_fullsock() after release", + .insns = { + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_sock, type)), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "invalid mem access", +}, +{ + "reference tracking: use ptr from bpf_sk_fullsock(tp) after release", + .insns = { + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_tcp_sock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "invalid mem access", +}, +{ + "reference tracking: use sk after bpf_sk_release(tp)", + .insns = { + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_tcp_sock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "invalid mem access", +}, +{ + "reference tracking: use ptr from bpf_get_listener_sock() after bpf_sk_release(sk)", + .insns = { + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_get_listener_sock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, src_port)), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, +}, +{ + "reference tracking: bpf_sk_release(listen_sk)", + .insns = { + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_get_listener_sock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "reference has not been acquired before", +}, +{ + /* !bpf_sk_fullsock(sk) is checked but !bpf_tcp_sock(sk) is not checked */ + "reference tracking: tp->snd_cwnd after bpf_sk_fullsock(sk) and bpf_tcp_sock(sk)", + .insns = { + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_tcp_sock), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_8, offsetof(struct bpf_tcp_sock, snd_cwnd)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "invalid mem access", +}, diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c index 0ddfdf76aba5..416436231fab 100644 --- a/tools/testing/selftests/bpf/verifier/sock.c +++ b/tools/testing/selftests/bpf/verifier/sock.c @@ -342,7 +342,7 @@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "type=sock_common expected=sock", + .errstr = "reference has not been acquired before", }, { "bpf_sk_release(bpf_sk_fullsock(skb->sk))", @@ -380,5 +380,5 @@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "type=tcp_sock expected=sock", + .errstr = "reference has not been acquired before", }, -- cgit From 7681e7b2fbe2a78806423810c0d84dd230b96f94 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 12 Mar 2019 10:23:11 -0700 Subject: bpf: Add an example for bpf_get_listener_sock This patch adds an example in using the new helper bpf_get_listener_sock(). Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/bpf_helpers.h | 2 + .../selftests/bpf/progs/test_sock_fields_kern.c | 88 +++++++++++--- tools/testing/selftests/bpf/test_sock_fields.c | 134 ++++++++++++++++----- 3 files changed, 180 insertions(+), 44 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index c9433a496d54..c81fc350f7ad 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -180,6 +180,8 @@ static struct bpf_sock *(*bpf_sk_fullsock)(struct bpf_sock *sk) = (void *) BPF_FUNC_sk_fullsock; static struct bpf_tcp_sock *(*bpf_tcp_sock)(struct bpf_sock *sk) = (void *) BPF_FUNC_tcp_sock; +static struct bpf_sock *(*bpf_get_listener_sock)(struct bpf_sock *sk) = + (void *) BPF_FUNC_get_listener_sock; static int (*bpf_skb_ecn_set_ce)(void *ctx) = (void *) BPF_FUNC_skb_ecn_set_ce; diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c index de1a43e8f610..37328f148538 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c @@ -8,38 +8,51 @@ #include "bpf_helpers.h" #include "bpf_endian.h" -enum bpf_array_idx { - SRV_IDX, - CLI_IDX, - __NR_BPF_ARRAY_IDX, +enum bpf_addr_array_idx { + ADDR_SRV_IDX, + ADDR_CLI_IDX, + __NR_BPF_ADDR_ARRAY_IDX, +}; + +enum bpf_result_array_idx { + EGRESS_SRV_IDX, + EGRESS_CLI_IDX, + INGRESS_LISTEN_IDX, + __NR_BPF_RESULT_ARRAY_IDX, +}; + +enum bpf_linum_array_idx { + EGRESS_LINUM_IDX, + INGRESS_LINUM_IDX, + __NR_BPF_LINUM_ARRAY_IDX, }; struct bpf_map_def SEC("maps") addr_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(__u32), .value_size = sizeof(struct sockaddr_in6), - .max_entries = __NR_BPF_ARRAY_IDX, + .max_entries = __NR_BPF_ADDR_ARRAY_IDX, }; struct bpf_map_def SEC("maps") sock_result_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(__u32), .value_size = sizeof(struct bpf_sock), - .max_entries = __NR_BPF_ARRAY_IDX, + .max_entries = __NR_BPF_RESULT_ARRAY_IDX, }; struct bpf_map_def SEC("maps") tcp_sock_result_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(__u32), .value_size = sizeof(struct bpf_tcp_sock), - .max_entries = __NR_BPF_ARRAY_IDX, + .max_entries = __NR_BPF_RESULT_ARRAY_IDX, }; struct bpf_map_def SEC("maps") linum_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(__u32), .value_size = sizeof(__u32), - .max_entries = 1, + .max_entries = __NR_BPF_LINUM_ARRAY_IDX, }; static bool is_loopback6(__u32 *a6) @@ -100,18 +113,20 @@ static void tpcpy(struct bpf_tcp_sock *dst, #define RETURN { \ linum = __LINE__; \ - bpf_map_update_elem(&linum_map, &idx0, &linum, 0); \ + bpf_map_update_elem(&linum_map, &linum_idx, &linum, 0); \ return 1; \ } SEC("cgroup_skb/egress") -int read_sock_fields(struct __sk_buff *skb) +int egress_read_sock_fields(struct __sk_buff *skb) { - __u32 srv_idx = SRV_IDX, cli_idx = CLI_IDX, idx; + __u32 srv_idx = ADDR_SRV_IDX, cli_idx = ADDR_CLI_IDX, result_idx; struct sockaddr_in6 *srv_sa6, *cli_sa6; struct bpf_tcp_sock *tp, *tp_ret; struct bpf_sock *sk, *sk_ret; - __u32 linum, idx0 = 0; + __u32 linum, linum_idx; + + linum_idx = EGRESS_LINUM_IDX; sk = skb->sk; if (!sk || sk->state == 10) @@ -132,14 +147,55 @@ int read_sock_fields(struct __sk_buff *skb) RETURN; if (sk->src_port == bpf_ntohs(srv_sa6->sin6_port)) - idx = srv_idx; + result_idx = EGRESS_SRV_IDX; else if (sk->src_port == bpf_ntohs(cli_sa6->sin6_port)) - idx = cli_idx; + result_idx = EGRESS_CLI_IDX; else RETURN; - sk_ret = bpf_map_lookup_elem(&sock_result_map, &idx); - tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &idx); + sk_ret = bpf_map_lookup_elem(&sock_result_map, &result_idx); + tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &result_idx); + if (!sk_ret || !tp_ret) + RETURN; + + skcpy(sk_ret, sk); + tpcpy(tp_ret, tp); + + RETURN; +} + +SEC("cgroup_skb/ingress") +int ingress_read_sock_fields(struct __sk_buff *skb) +{ + __u32 srv_idx = ADDR_SRV_IDX, result_idx = INGRESS_LISTEN_IDX; + struct bpf_tcp_sock *tp, *tp_ret; + struct bpf_sock *sk, *sk_ret; + struct sockaddr_in6 *srv_sa6; + __u32 linum, linum_idx; + + linum_idx = INGRESS_LINUM_IDX; + + sk = skb->sk; + if (!sk || sk->family != AF_INET6 || !is_loopback6(sk->src_ip6)) + RETURN; + + srv_sa6 = bpf_map_lookup_elem(&addr_map, &srv_idx); + if (!srv_sa6 || sk->src_port != bpf_ntohs(srv_sa6->sin6_port)) + RETURN; + + if (sk->state != 10 && sk->state != 12) + RETURN; + + sk = bpf_get_listener_sock(sk); + if (!sk) + RETURN; + + tp = bpf_tcp_sock(sk); + if (!tp) + RETURN; + + sk_ret = bpf_map_lookup_elem(&sock_result_map, &result_idx); + tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &result_idx); if (!sk_ret || !tp_ret) RETURN; diff --git a/tools/testing/selftests/bpf/test_sock_fields.c b/tools/testing/selftests/bpf/test_sock_fields.c index bc8943938bf5..dcae7f664dce 100644 --- a/tools/testing/selftests/bpf/test_sock_fields.c +++ b/tools/testing/selftests/bpf/test_sock_fields.c @@ -16,10 +16,23 @@ #include "cgroup_helpers.h" #include "bpf_rlimit.h" -enum bpf_array_idx { - SRV_IDX, - CLI_IDX, - __NR_BPF_ARRAY_IDX, +enum bpf_addr_array_idx { + ADDR_SRV_IDX, + ADDR_CLI_IDX, + __NR_BPF_ADDR_ARRAY_IDX, +}; + +enum bpf_result_array_idx { + EGRESS_SRV_IDX, + EGRESS_CLI_IDX, + INGRESS_LISTEN_IDX, + __NR_BPF_RESULT_ARRAY_IDX, +}; + +enum bpf_linum_array_idx { + EGRESS_LINUM_IDX, + INGRESS_LINUM_IDX, + __NR_BPF_LINUM_ARRAY_IDX, }; #define CHECK(condition, tag, format...) ({ \ @@ -41,8 +54,16 @@ static int linum_map_fd; static int addr_map_fd; static int tp_map_fd; static int sk_map_fd; -static __u32 srv_idx = SRV_IDX; -static __u32 cli_idx = CLI_IDX; + +static __u32 addr_srv_idx = ADDR_SRV_IDX; +static __u32 addr_cli_idx = ADDR_CLI_IDX; + +static __u32 egress_srv_idx = EGRESS_SRV_IDX; +static __u32 egress_cli_idx = EGRESS_CLI_IDX; +static __u32 ingress_listen_idx = INGRESS_LISTEN_IDX; + +static __u32 egress_linum_idx = EGRESS_LINUM_IDX; +static __u32 ingress_linum_idx = INGRESS_LINUM_IDX; static void init_loopback6(struct sockaddr_in6 *sa6) { @@ -93,29 +114,46 @@ static void print_tp(const struct bpf_tcp_sock *tp) static void check_result(void) { - struct bpf_tcp_sock srv_tp, cli_tp; - struct bpf_sock srv_sk, cli_sk; - __u32 linum, idx0 = 0; + struct bpf_tcp_sock srv_tp, cli_tp, listen_tp; + struct bpf_sock srv_sk, cli_sk, listen_sk; + __u32 ingress_linum, egress_linum; int err; - err = bpf_map_lookup_elem(linum_map_fd, &idx0, &linum); + err = bpf_map_lookup_elem(linum_map_fd, &egress_linum_idx, + &egress_linum); CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)", "err:%d errno:%d", err, errno); - err = bpf_map_lookup_elem(sk_map_fd, &srv_idx, &srv_sk); - CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &srv_idx)", + err = bpf_map_lookup_elem(linum_map_fd, &ingress_linum_idx, + &ingress_linum); + CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)", + "err:%d errno:%d", err, errno); + + err = bpf_map_lookup_elem(sk_map_fd, &egress_srv_idx, &srv_sk); + CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &egress_srv_idx)", + "err:%d errno:%d", err, errno); + err = bpf_map_lookup_elem(tp_map_fd, &egress_srv_idx, &srv_tp); + CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &egress_srv_idx)", + "err:%d errno:%d", err, errno); + + err = bpf_map_lookup_elem(sk_map_fd, &egress_cli_idx, &cli_sk); + CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &egress_cli_idx)", "err:%d errno:%d", err, errno); - err = bpf_map_lookup_elem(tp_map_fd, &srv_idx, &srv_tp); - CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &srv_idx)", + err = bpf_map_lookup_elem(tp_map_fd, &egress_cli_idx, &cli_tp); + CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &egress_cli_idx)", "err:%d errno:%d", err, errno); - err = bpf_map_lookup_elem(sk_map_fd, &cli_idx, &cli_sk); - CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &cli_idx)", + err = bpf_map_lookup_elem(sk_map_fd, &ingress_listen_idx, &listen_sk); + CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &ingress_listen_idx)", "err:%d errno:%d", err, errno); - err = bpf_map_lookup_elem(tp_map_fd, &cli_idx, &cli_tp); - CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &cli_idx)", + err = bpf_map_lookup_elem(tp_map_fd, &ingress_listen_idx, &listen_tp); + CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &ingress_listen_idx)", "err:%d errno:%d", err, errno); + printf("listen_sk: "); + print_sk(&listen_sk); + printf("\n"); + printf("srv_sk: "); print_sk(&srv_sk); printf("\n"); @@ -124,6 +162,10 @@ static void check_result(void) print_sk(&cli_sk); printf("\n"); + printf("listen_tp: "); + print_tp(&listen_tp); + printf("\n"); + printf("srv_tp: "); print_tp(&srv_tp); printf("\n"); @@ -132,6 +174,19 @@ static void check_result(void) print_tp(&cli_tp); printf("\n"); + CHECK(listen_sk.state != 10 || + listen_sk.family != AF_INET6 || + listen_sk.protocol != IPPROTO_TCP || + memcmp(listen_sk.src_ip6, &in6addr_loopback, + sizeof(listen_sk.src_ip6)) || + listen_sk.dst_ip6[0] || listen_sk.dst_ip6[1] || + listen_sk.dst_ip6[2] || listen_sk.dst_ip6[3] || + listen_sk.src_port != ntohs(srv_sa6.sin6_port) || + listen_sk.dst_port, + "Unexpected listen_sk", + "Check listen_sk output. ingress_linum:%u", + ingress_linum); + CHECK(srv_sk.state == 10 || !srv_sk.state || srv_sk.family != AF_INET6 || @@ -142,7 +197,8 @@ static void check_result(void) sizeof(srv_sk.dst_ip6)) || srv_sk.src_port != ntohs(srv_sa6.sin6_port) || srv_sk.dst_port != cli_sa6.sin6_port, - "Unexpected srv_sk", "Check srv_sk output. linum:%u", linum); + "Unexpected srv_sk", "Check srv_sk output. egress_linum:%u", + egress_linum); CHECK(cli_sk.state == 10 || !cli_sk.state || @@ -154,21 +210,31 @@ static void check_result(void) sizeof(cli_sk.dst_ip6)) || cli_sk.src_port != ntohs(cli_sa6.sin6_port) || cli_sk.dst_port != srv_sa6.sin6_port, - "Unexpected cli_sk", "Check cli_sk output. linum:%u", linum); + "Unexpected cli_sk", "Check cli_sk output. egress_linum:%u", + egress_linum); + + CHECK(listen_tp.data_segs_out || + listen_tp.data_segs_in || + listen_tp.total_retrans || + listen_tp.bytes_acked, + "Unexpected listen_tp", "Check listen_tp output. ingress_linum:%u", + ingress_linum); CHECK(srv_tp.data_segs_out != 1 || srv_tp.data_segs_in || srv_tp.snd_cwnd != 10 || srv_tp.total_retrans || srv_tp.bytes_acked != DATA_LEN, - "Unexpected srv_tp", "Check srv_tp output. linum:%u", linum); + "Unexpected srv_tp", "Check srv_tp output. egress_linum:%u", + egress_linum); CHECK(cli_tp.data_segs_out || cli_tp.data_segs_in != 1 || cli_tp.snd_cwnd != 10 || cli_tp.total_retrans || cli_tp.bytes_received != DATA_LEN, - "Unexpected cli_tp", "Check cli_tp output. linum:%u", linum); + "Unexpected cli_tp", "Check cli_tp output. egress_linum:%u", + egress_linum); } static void test(void) @@ -211,10 +277,10 @@ static void test(void) err, errno); /* Update addr_map with srv_sa6 and cli_sa6 */ - err = bpf_map_update_elem(addr_map_fd, &srv_idx, &srv_sa6, 0); + err = bpf_map_update_elem(addr_map_fd, &addr_srv_idx, &srv_sa6, 0); CHECK(err, "map_update", "err:%d errno:%d", err, errno); - err = bpf_map_update_elem(addr_map_fd, &cli_idx, &cli_sa6, 0); + err = bpf_map_update_elem(addr_map_fd, &addr_cli_idx, &cli_sa6, 0); CHECK(err, "map_update", "err:%d errno:%d", err, errno); /* Connect from cli_sa6 to srv_sa6 */ @@ -273,9 +339,9 @@ int main(int argc, char **argv) struct bpf_prog_load_attr attr = { .file = "test_sock_fields_kern.o", .prog_type = BPF_PROG_TYPE_CGROUP_SKB, - .expected_attach_type = BPF_CGROUP_INET_EGRESS, }; - int cgroup_fd, prog_fd, err; + int cgroup_fd, egress_fd, ingress_fd, err; + struct bpf_program *ingress_prog; struct bpf_object *obj; struct bpf_map *map; @@ -293,12 +359,24 @@ int main(int argc, char **argv) err = join_cgroup(TEST_CGROUP); CHECK(err, "join_cgroup", "err:%d errno:%d", err, errno); - err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); + err = bpf_prog_load_xattr(&attr, &obj, &egress_fd); CHECK(err, "bpf_prog_load_xattr()", "err:%d", err); - err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0); + ingress_prog = bpf_object__find_program_by_title(obj, + "cgroup_skb/ingress"); + CHECK(!ingress_prog, + "bpf_object__find_program_by_title(cgroup_skb/ingress)", + "not found"); + ingress_fd = bpf_program__fd(ingress_prog); + + err = bpf_prog_attach(egress_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0); CHECK(err == -1, "bpf_prog_attach(CPF_CGROUP_INET_EGRESS)", "err:%d errno%d", err, errno); + + err = bpf_prog_attach(ingress_fd, cgroup_fd, + BPF_CGROUP_INET_INGRESS, 0); + CHECK(err == -1, "bpf_prog_attach(CPF_CGROUP_INET_INGRESS)", + "err:%d errno%d", err, errno); close(cgroup_fd); map = bpf_object__find_map_by_name(obj, "addr_map"); -- cgit From 8fd7a61aa556ad518e897f58264a2e67f9c527f5 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Sun, 10 Mar 2019 17:44:10 -0700 Subject: selftests/bpf: add fwd enum resolution test for btf_dedup This patch adds test verifying new btf_dedup logic of resolving forward-declared enums. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/test_btf.c | 44 ++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 38797aa627a7..23e3b314ca60 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -5874,6 +5874,50 @@ const struct btf_dedup_test dedup_tests[] = { .dont_resolve_fwds = false, }, }, +{ + .descr = "dedup: enum fwd resolution", + .input = { + .raw_types = { + /* [1] fwd enum 'e1' before full enum */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 4), + /* [2] full enum 'e1' after fwd */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), + BTF_ENUM_ENC(NAME_NTH(2), 123), + /* [3] full enum 'e2' before fwd */ + BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), + BTF_ENUM_ENC(NAME_NTH(4), 456), + /* [4] fwd enum 'e2' after full enum */ + BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 4), + /* [5] incompatible fwd enum with different size */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 1), + /* [6] incompatible full enum with different value */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), + BTF_ENUM_ENC(NAME_NTH(2), 321), + BTF_END_RAW, + }, + BTF_STR_SEC("\0e1\0e1_val\0e2\0e2_val"), + }, + .expect = { + .raw_types = { + /* [1] full enum 'e1' */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), + BTF_ENUM_ENC(NAME_NTH(2), 123), + /* [2] full enum 'e2' */ + BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), + BTF_ENUM_ENC(NAME_NTH(4), 456), + /* [3] incompatible fwd enum with different size */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 1), + /* [4] incompatible full enum with different value */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), + BTF_ENUM_ENC(NAME_NTH(2), 321), + BTF_END_RAW, + }, + BTF_STR_SEC("\0e1\0e1_val\0e2\0e2_val"), + }, + .opts = { + .dont_resolve_fwds = false, + }, +}, }; -- cgit From 4e1810049c267c203c19130301203d0591174535 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 20 Mar 2019 15:00:00 +0100 Subject: net/sched: act_bpf: validate the control action inside init() the following script: # tc filter add dev crash0 egress matchall \ > action bpf bytecode '1,6 0 0 4294967295' pass index 90 # tc actions replace action bpf \ > bytecode '1,6 0 0 4294967295' goto chain 42 index 90 cookie c1a0c1a0 # tc action show action bpf had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: bpf bytecode '1,6 0 0 4294967295' default-action goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffb3a0803dfa90 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff942b347ada00 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffb3a08034d038 RDI: ffff942b347ada00 RBP: ffffb3a0803dfb30 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: ffffb3a0803dfb0c R12: ffff942b3b682b00 R13: ffff942b3b682b08 R14: 0000000000000001 R15: ffff942b3b682f00 FS: 00007f6160a72740(0000) GS:ffff942b3da80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000795a4002 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip_finish_output2+0x16f/0x430 ip_finish_output2+0x16f/0x430 ? ip_output+0x69/0xe0 ip_output+0x69/0xe0 ? ip_forward_options+0x1a0/0x1a0 ip_send_skb+0x15/0x40 raw_sendmsg+0x8e1/0xbd0 ? sched_clock+0x5/0x10 ? sched_clock_cpu+0xc/0xa0 ? try_to_wake_up+0x54/0x480 ? ldsem_down_read+0x3f/0x280 ? _cond_resched+0x15/0x40 ? down_read+0xe/0x30 ? copy_termios+0x1e/0x70 ? tty_mode_ioctl+0x1b6/0x4c0 ? sock_sendmsg+0x36/0x40 sock_sendmsg+0x36/0x40 __sys_sendto+0x10e/0x140 ? do_vfs_ioctl+0xa4/0x640 ? handle_mm_fault+0xdc/0x210 ? syscall_trace_enter+0x1df/0x2e0 ? __audit_syscall_exit+0x216/0x260 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f615f7e3c03 Code: 48 8b 0d 90 62 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 9d c3 2c 00 00 75 13 49 89 ca b8 2c 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 4b cc 00 00 48 89 04 24 RSP: 002b:00007ffee5d8cc28 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 000055a4f28f1700 RCX: 00007f615f7e3c03 RDX: 0000000000000040 RSI: 000055a4f28f1700 RDI: 0000000000000003 RBP: 00007ffee5d8e340 R08: 000055a4f28ee510 R09: 0000000000000010 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000040 R13: 000055a4f28f16c0 R14: 000055a4f28ef69c R15: 0000000000000080 Modules linked in: act_bpf veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache crct10dif_pclmul jbd2 crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper pcspkr joydev virtio_balloon snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper virtio_blk virtio_net virtio_console net_failover failover syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm crc32c_intel ata_piix serio_raw libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_bpf_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- .../selftests/tc-testing/tc-tests/actions/bpf.json | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json index 5970cee6d05f..b074ea9b6fe8 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json @@ -286,5 +286,30 @@ "teardown": [ "$TC action flush action bpf" ] + }, + { + "id": "b8a1", + "name": "Replace bpf action with invalid goto_chain control", + "category": [ + "actions", + "bpf" + ], + "setup": [ + [ + "$TC actions flush action bpf", + 0, + 1, + 255 + ], + "$TC action add action bpf bytecode '1,6 0 0 4294967295' pass index 90" + ], + "cmdUnderTest": "$TC action replace action bpf bytecode '1,6 0 0 4294967295' goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC action list action bpf", + "matchPattern": "action order [0-9]*: bpf.* default-action pass.*index 90", + "matchCount": "1", + "teardown": [ + "$TC action flush action bpf" + ] } ] -- cgit From f5c29d83866d75585f9c89754de0b86b45ceab89 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 20 Mar 2019 15:00:01 +0100 Subject: net/sched: act_csum: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall action csum icmp pass index 90 # tc actions replace action csum icmp goto chain 42 index 90 \ > cookie c1a0c1a0 # tc actions show action csum had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: csum (icmp) action goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 8000000074692067 P4D 8000000074692067 PUD 2e210067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff93153da03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9314ee40f700 RCX: 0000000000003a00 RDX: 0000000000000000 RSI: ffff931537c87828 RDI: ffff931537c87818 RBP: ffff93153da03c80 R08: 00000000527cffff R09: 0000000000000003 R10: 000000000000003f R11: 0000000000000028 R12: ffff9314edf68400 R13: ffff9314edf68408 R14: 0000000000000001 R15: ffff9314ed67b600 FS: 0000000000000000(0000) GS:ffff93153da00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000073e32003 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 RIP: 0010:native_safe_halt+0x2/0x10 Code: 66 ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffffffff9a803e98 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff99e184f0 RBX: 0000000000000000 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000000 RBP: 0000000000000000 R08: 000eb5c4572376b3 R09: 0000000000000000 R10: ffffa53e806a3ca0 R11: 00000000000f4240 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_kernel+0x49e/0x4be secondary_startup_64+0xa4/0xb0 Modules linked in: act_csum veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel mbcache snd_hda_codec jbd2 snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt net_failover fb_sys_fops virtio_console virtio_blk ttm failover drm ata_piix crc32c_intel floppy virtio_pci serio_raw libata virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_csum_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/csum.json | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json index a022792d392a..ddabb2fbb7c7 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json @@ -500,5 +500,30 @@ "matchPattern": "^[ \t]+index [0-9]+ ref", "matchCount": "0", "teardown": [] + }, + { + "id": "d128", + "name": "Replace csum action with invalid goto chain control", + "category": [ + "actions", + "csum" + ], + "setup": [ + [ + "$TC actions flush action csum", + 0, + 1, + 255 + ], + "$TC actions add action csum iph index 90" + ], + "cmdUnderTest": "$TC actions replace action csum iph goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action csum index 90", + "matchPattern": "action order [0-9]*: csum \\(iph\\) action pass.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action csum" + ] } ] -- cgit From 0da2dbd6029c2be4191651bafa57c3c006eff63c Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 20 Mar 2019 15:00:02 +0100 Subject: net/sched: act_gact: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action gact pass index 90 # tc actions replace action gact \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action gact had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: gact action goto chain 42 random type none pass val 0 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff8c2434703be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c23ed6d7e00 RCX: 000000000000005a RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8c23ed6d7e00 RBP: ffff8c2434703c80 R08: ffff8c243b639ac8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8c2429e68b00 R13: ffff8c2429e68b08 R14: 0000000000000001 R15: ffff8c2429c5a480 FS: 0000000000000000(0000) GS:ffff8c2434700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000002dc0e005 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 RIP: 0010:native_safe_halt+0x2/0x10 Code: 74 ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffff9c8640387eb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff8b2184f0 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000002 RBP: 0000000000000002 R08: 000eb57882b36cc3 R09: 0000000000000020 R10: 0000000000000004 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_gact act_bpf veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic ext4 snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core mbcache jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper virtio_balloon joydev pcspkr snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea virtio_net sysfillrect net_failover virtio_blk sysimgblt fb_sys_fops virtio_console ttm failover drm crc32c_intel serio_raw ata_piix libata floppy virtio_pci virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_bpf] CR2: 0000000000000000 Validating the control action within tcf_gact_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/gact.json | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json index 89189a03ce3d..814b7a8a478b 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json @@ -560,5 +560,30 @@ "teardown": [ "$TC actions flush action gact" ] + }, + { + "id": "ca89", + "name": "Replace gact action with invalid goto chain control", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action pass random determ drop 2 index 90" + ], + "cmdUnderTest": "$TC actions replace action goto chain 42 random determ drop 5 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action pass.*random type determ drop val 2.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] } ] -- cgit From 11a94d7fd80f92325e7b8653290ad3d2cd67f119 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 20 Mar 2019 15:00:03 +0100 Subject: net/sched: act_ife: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action ife encode allow mark pass index 90 # tc actions replace action ife \ > encode allow mark goto chain 42 index 90 cookie c1a0c1a0 # tc action show action ife had the following output: IFE type 0xED3E IFE type 0xED3E Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: ife encode action goto chain 42 type 0XED3E allow mark index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 800000007b4e7067 P4D 800000007b4e7067 PUD 7b4e6067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 164 Comm: kworker/2:1 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffa6a7c0553ad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9796ee1bbd00 RCX: 0000000000000001 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffa6a7c0553b70 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: ffff9797385bb038 R12: ffff9796ead9d700 R13: ffff9796ead9d708 R14: 0000000000000001 R15: ffff9796ead9d800 FS: 0000000000000000(0000) GS:ffff97973db00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007c41e006 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_gact act_meta_mark act_ife dummy veth ip6table_filter ip6_tables iptable_filter binfmt_misc snd_hda_codec_generic ext4 snd_hda_intel snd_hda_codec crct10dif_pclmul mbcache crc32_pclmul jbd2 snd_hwdep snd_hda_core ghash_clmulni_intel snd_seq snd_seq_device snd_pcm snd_timer aesni_intel crypto_simd snd cryptd glue_helper virtio_balloon joydev pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl virtio_net drm_kms_helper virtio_blk net_failover syscopyarea failover sysfillrect virtio_console sysimgblt fb_sys_fops ttm drm crc32c_intel serio_raw ata_piix virtio_pci virtio_ring libata virtio floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_ife] CR2: 0000000000000000 Validating the control action within tcf_ife_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- .../selftests/tc-testing/tc-tests/actions/ife.json | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json index 0da3545cabdb..c13a68b98fc7 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json @@ -1060,5 +1060,30 @@ "matchPattern": "action order [0-9]*: ife encode action pipe.*allow prio.*index 4", "matchCount": "0", "teardown": [] + }, + { + "id": "a0e2", + "name": "Replace ife encode action with invalid goto chain control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife encode allow mark pass index 90" + ], + "cmdUnderTest": "$TC actions replace action ife encode allow mark goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 90", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0[xX]ED3E .*allow mark.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] } ] -- cgit From ff9721d32b1aba8bf46a06df20827d0a5d52ec48 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 20 Mar 2019 15:00:04 +0100 Subject: net/sched: act_mirred: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action mirred ingress mirror dev lo pass # tc actions replace action mirred \ > ingress mirror dev lo goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action mirred had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: mirred (Ingress Mirror to device lo) goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: Mirror/redirect action on BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 3 PID: 47 Comm: kworker/3:1 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffa772404b7ad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9c5afc3f4300 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff9c5afdba9380 RDI: 0000000000029380 RBP: ffffa772404b7b70 R08: ffff9c5af7010028 R09: ffff9c5af7010029 R10: 0000000000000000 R11: ffff9c5af94c6a38 R12: ffff9c5af7953000 R13: ffff9c5af7953008 R14: 0000000000000001 R15: ffff9c5af7953d00 FS: 0000000000000000(0000) GS:ffff9c5afdb80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007c514004 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_mirred veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul snd_hda_codec_generic crc32_pclmul snd_hda_intel snd_hda_codec mbcache ghash_clmulni_intel jbd2 snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel snd_timer snd crypto_simd cryptd glue_helper soundcore virtio_balloon joydev pcspkr i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops virtio_net ttm virtio_blk net_failover virtio_console failover drm ata_piix crc32c_intel virtio_pci serio_raw libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_mirred_init() proved to fix the above issue. For the same reason, postpone the assignment of tcfa_action and tcfm_eaction to avoid partial reconfiguration of a mirred rule when it's replaced by another one that mirrors to a device that does not exist. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/mirred.json | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json index db49fd0f8445..6e5fb3d25681 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json @@ -434,5 +434,30 @@ "teardown": [ "$TC actions flush action mirred" ] + }, + { + "id": "2a9a", + "name": "Replace mirred action with invalid goto chain control", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + "$TC actions add action mirred ingress mirror dev lo drop index 90" + ], + "cmdUnderTest": "$TC actions replace action mirred ingress mirror dev lo goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action mirred index 90", + "matchPattern": "action order [0-9]*: mirred \\(Ingress Mirror to device lo\\) drop.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action mirred" + ] } ] -- cgit From c53075ea5d3c44849992523d5d83e2810d05a00e Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 20 Mar 2019 15:00:05 +0100 Subject: net/sched: act_connmark: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action connmark pass index 90 # tc actions replace action connmark \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action connmark had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: connmark zone 0 goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 302 Comm: kworker/0:2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff9bea406c3ad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c5dfc009f00 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff9bea406c3a80 RDI: ffff8c5dfb9d6ec0 RBP: ffff9bea406c3b70 R08: ffff8c5dfda222a0 R09: ffffffff90933c3c R10: 0000000000000000 R11: 0000000092793f7d R12: ffff8c5df48b3c00 R13: ffff8c5df48b3c08 R14: 0000000000000001 R15: ffff8c5dfb9d6e40 FS: 0000000000000000(0000) GS:ffff8c5dfda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000062e0e006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_connmark nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul mbcache crc32_pclmul jbd2 snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel snd_timer crypto_simd cryptd snd glue_helper joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper virtio_net net_failover syscopyarea virtio_blk failover virtio_console sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix crc32c_intel serio_raw libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_connmark_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/connmark.json | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json index 13147a1f5731..cadde8f41fcd 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json @@ -287,5 +287,30 @@ "teardown": [ "$TC actions flush action connmark" ] + }, + { + "id": "c506", + "name": "Replace connmark with invalid goto chain control", + "category": [ + "actions", + "connmark" + ], + "setup": [ + [ + "$TC actions flush action connmark", + 0, + 1, + 255 + ], + "$TC actions add action connmark pass index 90" + ], + "cmdUnderTest": "$TC actions replace action connmark goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action connmark index 90", + "matchPattern": "action order [0-9]+: connmark zone 0 pass.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action connmark" + ] } ] -- cgit From 1e45d043a8bb2ed8a541384db3cc133e92001f0c Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 20 Mar 2019 15:00:06 +0100 Subject: net/sched: act_nat: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action nat ingress 1.18.1.1 1.18.2.2 pass index 90 # tc actions replace action nat \ > ingress 1.18.1.1 1.18.2.2 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action nat had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: nat ingress 1.18.1.1/32 1.18.2.2 goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 800000002d180067 P4D 800000002d180067 PUD 7cb8b067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 3 PID: 164 Comm: kworker/3:1 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffae4500e2fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9fa52e28c800 RCX: 0000000001011201 RDX: 0000000000000000 RSI: 0000000000000056 RDI: ffff9fa52ca12800 RBP: ffffae4500e2fb70 R08: 0000000000000022 R09: 000000000000000e R10: 00000000ffffffff R11: 0000000001011201 R12: ffff9fa52cbc9c00 R13: ffff9fa52cbc9c08 R14: 0000000000000001 R15: ffff9fa52ca12780 FS: 0000000000000000(0000) GS:ffff9fa57db80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000073f8c004 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_nat veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper snd_timer snd joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs qxl ata_generic pata_acpi drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_net virtio_blk net_failover failover virtio_console drm crc32c_intel floppy ata_piix libata virtio_pci virtio_ring virtio serio_raw dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_nat_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- .../selftests/tc-testing/tc-tests/actions/nat.json | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json index 0080dc2fd41c..bc12c1ccad30 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json @@ -589,5 +589,30 @@ "teardown": [ "$TC actions flush action nat" ] + }, + { + "id": "4b12", + "name": "Replace nat action with invalid goto chain control", + "category": [ + "actions", + "nat" + ], + "setup": [ + [ + "$TC actions flush action nat", + 0, + 1, + 255 + ], + "$TC actions add action nat ingress 1.18.1.1 1.18.2.2 drop index 90" + ], + "cmdUnderTest": "$TC actions replace action nat ingress 1.18.1.1 1.18.2.2 goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action nat index 90", + "matchPattern": "action order [0-9]+: nat ingress 1.18.1.1/32 1.18.2.2 drop.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action nat" + ] } ] -- cgit From 6ac86ca3524b4549d31c45d11487b0626c334f10 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 20 Mar 2019 15:00:07 +0100 Subject: net/sched: act_pedit: validate the control action inside init() the following script: # tc filter add dev crash0 egress matchall \ > action pedit ex munge ip ttl set 10 pass index 90 # tc actions replace action pedit \ > ex munge ip ttl set 10 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action pedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: pedit action goto chain 42 keys 1 index 90 ref 2 bind 1 key #0 at ipv4+8: val 0a000000 mask 00ffffff cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff94a73db03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff94a6ee4c0700 RCX: 000000000000000a RDX: 0000000000000000 RSI: ffff94a6ed22c800 RDI: 0000000000000000 RBP: ffff94a73db03c80 R08: ffff94a7386fa4c8 R09: ffff94a73229ea20 R10: 0000000000000000 R11: 0000000000000000 R12: ffff94a6ed22cb00 R13: ffff94a6ed22cb08 R14: 0000000000000001 R15: ffff94a6ed22c800 FS: 0000000000000000(0000) GS:ffff94a73db00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007120e002 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 RIP: 0010:native_safe_halt+0x2/0x10 Code: 4e ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffffab1740387eb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffb18184f0 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000002 RBP: 0000000000000002 R08: 000f168fa695f9a9 R09: 0000000000000020 R10: 0000000000000004 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_pedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep aesni_intel snd_hda_core crypto_simd snd_seq cryptd glue_helper snd_seq_device snd_pcm joydev snd_timer pcspkr virtio_balloon snd soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs qxl ata_generic pata_acpi drm_kms_helper virtio_net net_failover syscopyarea sysfillrect sysimgblt failover virtio_blk fb_sys_fops virtio_console ttm drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_pedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/pedit.json | 51 ++++++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json new file mode 100644 index 000000000000..b73ceb9e28b1 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json @@ -0,0 +1,51 @@ +[ + { + "id": "319a", + "name": "Add pedit action that mangles IP TTL", + "category": [ + "actions", + "pedit" + ], + "setup": [ + [ + "$TC actions flush action pedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action pedit ex munge ip ttl set 10", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action pedit", + "matchPattern": "action order [0-9]+: pedit action pass keys 1.*index 1 ref.*key #0 at ipv4\\+8: val 0a000000 mask 00ffffff", + "matchCount": "1", + "teardown": [ + "$TC actions flush action pedit" + ] + }, + { + "id": "7e67", + "name": "Replace pedit action with invalid goto chain", + "category": [ + "actions", + "pedit" + ], + "setup": [ + [ + "$TC actions flush action pedit", + 0, + 1, + 255 + ], + "$TC actions add action pedit ex munge ip ttl set 10 pass index 90" + ], + "cmdUnderTest": "$TC actions replace action pedit ex munge ip ttl set 10 goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action pedit", + "matchPattern": "action order [0-9]+: pedit action pass keys 1.*index 90 ref.*key #0 at ipv4\\+8: val 0a000000 mask 00ffffff", + "matchCount": "1", + "teardown": [ + "$TC actions flush action pedit" + ] + } +] -- cgit From d6124d6ba697413efc53ff6919b1e0c250f1902a Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 20 Mar 2019 15:00:08 +0100 Subject: net/sched: act_police: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action police rate 3mbit burst 250k pass index 90 # tc actions replace action police \ > rate 3mbit burst 250k goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action police rate 3mbit burst had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: police 0x5a rate 3Mbit burst 250Kb mtu 2Kb action goto chain 42 overhead 0b ref 2 bind 1 cookie c1a0c1a0 Then, when crash0 starts transmitting more than 3Mbit/s, the following kernel crash is observed: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 800000007a779067 P4D 800000007a779067 PUD 2ad96067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 3 PID: 5032 Comm: netperf Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffb0e04064fa60 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff93bb3322cce0 RCX: 0000000000000005 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff93bb3322cce0 RBP: ffffb0e04064fb00 R08: 0000000000000022 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000001 R12: ffff93bb3beed300 R13: ffff93bb3beed308 R14: 0000000000000001 R15: ffff93bb3b64d000 FS: 00007f0bc6be5740(0000) GS:ffff93bb3db80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000746a8001 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ipt_do_table+0x31c/0x420 [ip_tables] ? ip_finish_output2+0x16f/0x430 ip_finish_output2+0x16f/0x430 ? ip_output+0x69/0xe0 ip_output+0x69/0xe0 ? ip_forward_options+0x1a0/0x1a0 __tcp_transmit_skb+0x563/0xa40 tcp_write_xmit+0x243/0xfa0 __tcp_push_pending_frames+0x32/0xf0 tcp_sendmsg_locked+0x404/0xd30 tcp_sendmsg+0x27/0x40 sock_sendmsg+0x36/0x40 __sys_sendto+0x10e/0x140 ? __sys_connect+0x87/0xf0 ? syscall_trace_enter+0x1df/0x2e0 ? __audit_syscall_exit+0x216/0x260 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f0bc5ffbafd Code: 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 8b 05 ae c4 2c 00 85 c0 75 2d 45 31 c9 45 31 c0 4c 63 d1 48 63 ff b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 01 c3 48 8b 15 63 63 2c 00 f7 d8 64 89 02 48 RSP: 002b:00007fffef94b7f8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000000004000 RCX: 00007f0bc5ffbafd RDX: 0000000000004000 RSI: 00000000017e5420 RDI: 0000000000000004 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000004 R13: 00000000017e51d0 R14: 0000000000000010 R15: 0000000000000006 Modules linked in: act_police veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 snd_hda_codec_generic mbcache crct10dif_pclmul jbd2 crc32_pclmul ghash_clmulni_intel snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper snd_timer snd joydev pcspkr virtio_balloon soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm virtio_blk virtio_net virtio_console net_failover failover crc32c_intel ata_piix libata serio_raw virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_police_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/police.json | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json index 4086a50a670e..b8268da5adaa 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json @@ -739,5 +739,30 @@ "teardown": [ "$TC actions flush action police" ] + }, + { + "id": "689e", + "name": "Replace police action with invalid goto chain control", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ], + "$TC actions add action police rate 3mbit burst 250k drop index 90" + ], + "cmdUnderTest": "$TC actions replace action police rate 3mbit burst 250k goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action police index 90", + "matchPattern": "action order [0-9]*: police 0x5a rate 3Mbit burst 250Kb mtu 2Kb action drop", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] } ] -- cgit From e8c87c643ef3603c6e63bdecb67b03d794648493 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 20 Mar 2019 15:00:09 +0100 Subject: net/sched: act_sample: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action sample rate 1024 group 4 pass index 90 # tc actions replace action sample \ > rate 1024 group 4 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action sample had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: sample rate 1/1024 group 4 goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 8000000079966067 P4D 8000000079966067 PUD 7987b067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 5 Comm: kworker/0:0 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffbee60033fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff99d7ae6e3b00 RCX: 00000000e555df9b RDX: 0000000000000000 RSI: 00000000b0352718 RDI: ffff99d7fda1fcf0 RBP: ffffbee60033fb70 R08: 0000000070731ab1 R09: 0000000000000400 R10: 0000000000000000 R11: ffff99d7ac733838 R12: ffff99d7f3c2be00 R13: ffff99d7f3c2be08 R14: 0000000000000001 R15: ffff99d7f3c2b600 FS: 0000000000000000(0000) GS:ffff99d7fda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000797de006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_sample psample veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd snd_pcm cryptd glue_helper snd_timer joydev snd pcspkr virtio_balloon i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover ttm failover virtio_blk virtio_console drm ata_piix serio_raw crc32c_intel libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_sample_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/sample.json | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json index 3aca33c00039..27f0acaed880 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json @@ -584,5 +584,30 @@ "teardown": [ "$TC actions flush action sample" ] + }, + { + "id": "0a6e", + "name": "Replace sample action with invalid goto chain control", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ], + "$TC actions add action sample rate 1024 group 4 pass index 90" + ], + "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pass.*index 90", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] } ] -- cgit From 4b006b0c139e486773335f4c23b4d82348cfeb04 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 20 Mar 2019 15:00:10 +0100 Subject: net/sched: act_simple: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action simple sdata hello pass index 90 # tc actions replace action simple \ > sdata world goto chain 42 index 90 cookie c1a0c1a0 # tc action show action simple had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: Simple index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 800000006a6fb067 P4D 800000006a6fb067 PUD 6aed6067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 3241 Comm: kworker/2:0 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffbe6781763ad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9e59bdb80e00 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff9e59b4716738 RDI: ffff9e59ab12d140 RBP: ffffbe6781763b70 R08: 0000000000000234 R09: 0000000000aaaaaa R10: 0000000000000000 R11: ffff9e59b247cd50 R12: ffff9e59b112f100 R13: ffff9e59b112f108 R14: 0000000000000001 R15: ffff9e59ab12d0c0 FS: 0000000000000000(0000) GS:ffff9e59b4700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000006af92004 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_simple veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ext4 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep mbcache snd_hda_core jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops virtio_net ttm net_failover virtio_console virtio_blk failover drm crc32c_intel serio_raw floppy ata_piix libata virtio_pci virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_simple_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/simple.json | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json index e89a7aa4012d..8e8c1ae12260 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json @@ -126,5 +126,30 @@ "teardown": [ "" ] + }, + { + "id": "b776", + "name": "Replace simple action with invalid goto chain control", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ], + "$TC actions add action simple sdata \"hello\" pass index 90" + ], + "cmdUnderTest": "$TC actions replace action simple sdata \"world\" goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple .*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action simple" + ] } ] -- cgit From ec7727bb24b01e96b0c46068addf355ee4f794d8 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 20 Mar 2019 15:00:11 +0100 Subject: net/sched: act_skbedit: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbedit ptype host pass index 90 # tc actions replace action skbedit \ > ptype host goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbedit ptype host goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 3 PID: 3467 Comm: kworker/3:3 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffb50a81e1fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9aa47ba4ea00 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffff9aa469eeb3c0 RDI: ffff9aa47ba4ea00 RBP: ffffb50a81e1fb70 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: ffff9aa47bce0638 R12: ffff9aa4793b0c00 R13: ffff9aa4793b0c08 R14: 0000000000000001 R15: ffff9aa469eeb3c0 FS: 0000000000000000(0000) GS:ffff9aa474780000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007360e005 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_skbedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ext4 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep mbcache snd_hda_core jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev soundcore pcspkr virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_net net_failover drm failover virtio_blk virtio_console ata_piix virtio_pci crc32c_intel serio_raw libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/skbedit.json | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json index 5aaf593b914a..ecd96eda7f6a 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json @@ -484,5 +484,30 @@ "teardown": [ "$TC actions flush action skbedit" ] + }, + { + "id": "1b2b", + "name": "Replace skbedit action with invalid goto_chain control", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ], + "$TC actions add action skbedit ptype host pass index 90" + ], + "cmdUnderTest": "$TC actions replace action skbedit ptype host goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit ptype host pass.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] } ] -- cgit From 7c3d825d12c5e6056ea73c0a202cbdef9d9ab9e6 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 20 Mar 2019 15:00:12 +0100 Subject: net/sched: act_skbmod: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbmod set smac 00:c1:a0:c1:a0:00 pass index 90 # tc actions replace action skbmod \ > set smac 00:c1:a0:c1:a0:00 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbmod had the following output: src MAC address <00:c1:a0:c1:a0:00> src MAC address <00:c1:a0:c1:a0:00> Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbmod goto chain 42 set smac 00:c1:a0:c1:a0:00 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 800000002d5c7067 P4D 800000002d5c7067 PUD 77e16067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 3 PID: 0 Comm: swapper/3 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff8987ffd83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8987aeb68800 RCX: ffff8987fa263640 RDX: 0000000000000000 RSI: ffff8987f51c8802 RDI: 00000000000000a0 RBP: ffff8987ffd83c80 R08: ffff8987f939bac8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8987f5c77d00 R13: ffff8987f5c77d08 R14: 0000000000000001 R15: ffff8987f0c29f00 FS: 0000000000000000(0000) GS:ffff8987ffd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007832c004 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 RIP: 0010:native_safe_halt+0x2/0x10 Code: 56 ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffffa2a1c038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffa94184f0 RBX: 0000000000000003 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 001123cfc2ba71ac R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000f4240 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_skbmod veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd cryptd glue_helper snd_pcm joydev pcspkr virtio_balloon snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover virtio_console ttm virtio_blk failover drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbmod_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/skbmod.json | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json index fe3326e939c1..6eb4c4f97060 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json @@ -392,5 +392,30 @@ "teardown": [ "$TC actions flush action skbmod" ] + }, + { + "id": "b651", + "name": "Replace skbmod action with invalid goto_chain control", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ], + "$TC actions add action skbmod set etype 0x1111 pass index 90" + ], + "cmdUnderTest": "$TC actions replace action skbmod set etype 0x1111 goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pass set etype 0x1111\\s+index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] } ] -- cgit From e5fdabacbffc5d321bf9f51410fe0db0834606eb Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 20 Mar 2019 15:00:13 +0100 Subject: net/sched: act_tunnel_key: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 \ > nocsum id 1 pass index 90 # tc actions replace action tunnel_key \ > set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 nocsum id 1 \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action tunnel_key had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2.0 key_id 1 dst_port 3128 nocsum goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 800000002aba4067 P4D 800000002aba4067 PUD 795f9067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 3 PID: 0 Comm: swapper/3 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff9346bdb83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9346bb795c00 RCX: 0000000000000002 RDX: 0000000000000000 RSI: ffff93466c881700 RDI: 0000000000000246 RBP: ffff9346bdb83c80 R08: ffff9346b3e1e0c8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff9346b978f000 R13: ffff9346b978f008 R14: 0000000000000001 R15: ffff93466dceeb40 FS: 0000000000000000(0000) GS:ffff9346bdb80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007a6c2002 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 RIP: 0010:native_safe_halt+0x2/0x10 Code: 55 ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffffa48a8038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffaa8184f0 RBX: 0000000000000003 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 0011251c6fcfac49 R09: ffff9346b995be00 R10: ffffa48a805e7ce8 R11: 00000000024c38dd R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_tunnel_key veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel mbcache snd_hda_intel jbd2 snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper joydev snd_timer snd pcspkr virtio_balloon soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops ttm net_failover virtio_console virtio_blk failover drm serio_raw crc32c_intel ata_piix virtio_pci floppy virtio_ring libata virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_tunnel_key_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/tunnel_key.json | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json index e7e15a7336b6..28453a445fdb 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json @@ -884,5 +884,30 @@ "teardown": [ "$TC actions flush action tunnel_key" ] + }, + { + "id": "8242", + "name": "Replace tunnel_key set action with invalid goto chain", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ], + "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 pass index 90" + ], + "cmdUnderTest": "$TC actions replace action tunnel_key set src_ip 10.10.10.2 dst_ip 20.20.20.1 dst_port 3129 id 2 csum goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action tunnel_key index 90", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1.*dst_port 3128.*csum pass.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] } ] -- cgit From 7e0c8892df7d0316ec853adbf84db536cd53258c Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 20 Mar 2019 15:00:14 +0100 Subject: net/sched: act_vlan: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action vlan pop pass index 90 # tc actions replace action vlan \ > pop goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action vlan had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: vlan pop goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 800000007974f067 P4D 800000007974f067 PUD 79638067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 3 PID: 0 Comm: swapper/3 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff982dfdb83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff982dfc55db00 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff982df97099c0 RDI: ffff982dfc55db00 RBP: ffff982dfdb83c80 R08: ffff982df983fec8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff982df5aacd00 R13: ffff982df5aacd08 R14: 0000000000000001 R15: ffff982df97099c0 FS: 0000000000000000(0000) GS:ffff982dfdb80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000796d0005 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? enqueue_hrtimer+0x39/0x90 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 RIP: 0010:native_safe_halt+0x2/0x10 Code: 7b ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffffa4714038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff840184f0 RBX: 0000000000000003 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000001e57d3f387 RBP: 0000000000000003 R08: 001125d9ca39e1eb R09: 0000000000000000 R10: 000000000000027d R11: 000000000009f400 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_vlan veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 snd_hda_codec_generic mbcache crct10dif_pclmul jbd2 snd_hda_intel crc32_pclmul snd_hda_codec ghash_clmulni_intel snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper joydev snd_timer virtio_balloon snd pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt virtio_net fb_sys_fops virtio_blk ttm net_failover virtio_console failover ata_piix drm libata crc32c_intel virtio_pci serio_raw virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_vlan_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/vlan.json | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json index 69ea09eefffc..cc7c7d758008 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json @@ -688,5 +688,30 @@ "teardown": [ "$TC actions flush action vlan" ] + }, + { + "id": "e394", + "name": "Replace vlan push action with invalid goto chain control", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "$TC actions add action vlan push id 500 pass index 90" + ], + "cmdUnderTest": "$TC actions replace action vlan push id 500 goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action vlan index 90", + "matchPattern": "action order [0-9]+: vlan.*push id 500 protocol 802.1Q priority 0 pass.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] } ] -- cgit From 83d163124cf1104cca5b668d5fe6325715a60855 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 21 Mar 2019 14:34:36 -0700 Subject: bpf: verifier: propagate liveness on all frames Commit 7640ead93924 ("bpf: verifier: make sure callees don't prune with caller differences") connected up parentage chains of all frames of the stack. It didn't, however, ensure propagate_liveness() propagates all liveness information along those chains. This means pruning happening in the callee may generate explored states with incomplete liveness for the chains in lower frames of the stack. The included selftest is similar to the prior one from commit 7640ead93924 ("bpf: verifier: make sure callees don't prune with caller differences"), where callee would prune regardless of the difference in r8 state. Now we also initialize r9 to 0 or 1 based on a result from get_random(). r9 is never read so the walk with r9 = 0 gets pruned (correctly) after the walk with r9 = 1 completes. The selftest is so arranged that the pruning will happen in the callee. Since callee does not propagate read marks of r8, the explored state at the pruning point prior to the callee will now ignore r8. Propagate liveness on all frames of the stack when pruning. Fixes: f4d7e40a5b71 ("bpf: introduce function calls (verification)") Signed-off-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/verifier/calls.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 4004891afa9c..f2ccae39ee66 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -1940,3 +1940,28 @@ .errstr = "!read_ok", .result = REJECT, }, +{ + "calls: cross frame pruning - liveness propagation", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), + BPF_MOV64_IMM(BPF_REG_8, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_8, 1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), + BPF_MOV64_IMM(BPF_REG_9, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_9, 1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_8, 1, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, + .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .errstr = "!read_ok", + .result = REJECT, +}, -- cgit From cabacfbbe54ec6730b3c147599763892c6c03525 Mon Sep 17 00:00:00 2001 From: Paul Chaignon Date: Wed, 20 Mar 2019 13:58:50 +0100 Subject: selftests/bpf: test case for invalid call stack in dead code This patch adds a test case with an excessive number of call stack frames in dead code. Signed-off-by: Paul Chaignon Tested-by: Xiao Han Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/verifier/calls.c | 38 ++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index f2ccae39ee66..fb11240b758b 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -907,6 +907,44 @@ .errstr = "call stack", .result = REJECT, }, +{ + "calls: stack depth check in dead code", + .insns = { + /* main */ + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call A */ + BPF_EXIT_INSN(), + /* A */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 2), /* call B */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + /* B */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call C */ + BPF_EXIT_INSN(), + /* C */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call D */ + BPF_EXIT_INSN(), + /* D */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call E */ + BPF_EXIT_INSN(), + /* E */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call F */ + BPF_EXIT_INSN(), + /* F */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call G */ + BPF_EXIT_INSN(), + /* G */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call H */ + BPF_EXIT_INSN(), + /* H */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_XDP, + .errstr = "call stack", + .result = REJECT, +}, { "calls: spill into caller stack frame", .insns = { -- cgit From eb76899ce749507e09cad6816f32cede14a9b7ee Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 26 Mar 2019 22:00:07 -0700 Subject: selftests/bpf: add btf_dedup test for VOID equivalence check This patch adds specific test exposing bug in btf_dedup_is_equiv() when comparing candidate VOID type to a non-VOID canonical type. It's important for canonical type to be anonymous, otherwise name equality check will do the right thing and will exit early. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/test_btf.c | 47 ++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 23e3b314ca60..ec5794e4205b 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -5776,6 +5776,53 @@ const struct btf_dedup_test dedup_tests[] = { .dedup_table_size = 1, /* force hash collisions */ }, }, +{ + .descr = "dedup: void equiv check", + /* + * // CU 1: + * struct s { + * struct {} *x; + * }; + * // CU 2: + * struct s { + * int *x; + * }; + */ + .input = { + .raw_types = { + /* CU 1 */ + BTF_STRUCT_ENC(0, 0, 1), /* [1] struct {} */ + BTF_PTR_ENC(1), /* [2] ptr -> [1] */ + BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [3] struct s */ + BTF_MEMBER_ENC(NAME_NTH(2), 2, 0), + /* CU 2 */ + BTF_PTR_ENC(0), /* [4] ptr -> void */ + BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [5] struct s */ + BTF_MEMBER_ENC(NAME_NTH(2), 4, 0), + BTF_END_RAW, + }, + BTF_STR_SEC("\0s\0x"), + }, + .expect = { + .raw_types = { + /* CU 1 */ + BTF_STRUCT_ENC(0, 0, 1), /* [1] struct {} */ + BTF_PTR_ENC(1), /* [2] ptr -> [1] */ + BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [3] struct s */ + BTF_MEMBER_ENC(NAME_NTH(2), 2, 0), + /* CU 2 */ + BTF_PTR_ENC(0), /* [4] ptr -> void */ + BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [5] struct s */ + BTF_MEMBER_ENC(NAME_NTH(2), 4, 0), + BTF_END_RAW, + }, + BTF_STR_SEC("\0s\0x"), + }, + .opts = { + .dont_resolve_fwds = false, + .dedup_table_size = 1, /* force hash collisions */ + }, +}, { .descr = "dedup: all possible kinds (no duplicates)", .input = { -- cgit From 8df98ae0ab2ead9a02228756eec26f8d7b17f499 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 13 Mar 2019 13:19:26 -0700 Subject: KVM: selftests: assert on exit reason in CR4/cpuid sync test ...so that the test doesn't end up in an infinite loop if it fails for whatever reason, e.g. SHUTDOWN due to gcc inserting stack canary code into ucall() and attempting to derefence a null segment. Fixes: ca359066889f7 ("kvm: selftests: add cr4_cpuid_sync_test") Cc: Wei Huang Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- .../selftests/kvm/x86_64/cr4_cpuid_sync_test.c | 35 ++++++++++++---------- 1 file changed, 19 insertions(+), 16 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c index d503a51fad30..7c2c4d4055a8 100644 --- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c +++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c @@ -87,22 +87,25 @@ int main(int argc, char *argv[]) while (1) { rc = _vcpu_run(vm, VCPU_ID); - if (run->exit_reason == KVM_EXIT_IO) { - switch (get_ucall(vm, VCPU_ID, &uc)) { - case UCALL_SYNC: - /* emulate hypervisor clearing CR4.OSXSAVE */ - vcpu_sregs_get(vm, VCPU_ID, &sregs); - sregs.cr4 &= ~X86_CR4_OSXSAVE; - vcpu_sregs_set(vm, VCPU_ID, &sregs); - break; - case UCALL_ABORT: - TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit."); - break; - case UCALL_DONE: - goto done; - default: - TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); - } + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_SYNC: + /* emulate hypervisor clearing CR4.OSXSAVE */ + vcpu_sregs_get(vm, VCPU_ID, &sregs); + sregs.cr4 &= ~X86_CR4_OSXSAVE; + vcpu_sregs_set(vm, VCPU_ID, &sregs); + break; + case UCALL_ABORT: + TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit."); + break; + case UCALL_DONE: + goto done; + default: + TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); } } -- cgit From 0a3f29b5a77d6c27796d7a7adabafd199dc066d5 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 13 Mar 2019 16:19:30 -0700 Subject: KVM: selftests: explicitly disable PIE for tests KVM selftests embed the guest "image" as a function in the test itself and extract the guest code at runtime by manually parsing the elf headers. The parsing is very simple and doesn't supporting fancy things like position independent executables. Recent versions of gcc enable pie by default, which results in triple fault shutdowns in the guest due to the virtual address in the headers not matching up with the virtual address retrieved from the function pointer. Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 3c1f4bdf9000..73d59c9d94a3 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -29,7 +29,7 @@ LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include -CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$( Date: Wed, 13 Mar 2019 12:43:14 -0700 Subject: KVM: selftests: disable stack protector for all KVM tests Since 4.8.3, gcc has enabled -fstack-protector by default. This is problematic for the KVM selftests as they do not configure fs or gs segments (the stack canary is pulled from fs:0x28). With the default behavior, gcc will insert a stack canary on any function that creates buffers of 8 bytes or more. As a result, ucall() will hit a triple fault shutdown due to reading a bad fs segment when inserting its stack canary, i.e. every test fails with an unexpected SHUTDOWN. Fixes: 14c47b7530e2d ("kvm: selftests: introduce ucall") Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 73d59c9d94a3..7514fcea91a7 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -29,8 +29,8 @@ LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include -CFLAGS += -O2 -g -std=gnu99 -no-pie -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$( Date: Wed, 13 Mar 2019 16:49:31 -0700 Subject: KVM: selftests: complete IO before migrating guest state Documentation/virtual/kvm/api.txt states: NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR and KVM_EXIT_EPR the corresponding operations are complete (and guest state is consistent) only after userspace has re-entered the kernel with KVM_RUN. The kernel side will first finish incomplete operations and then check for pending signals. Userspace can re-enter the guest with an unmasked signal pending to complete pending operations. Because guest state may be inconsistent, starting state migration after an IO exit without first completing IO may result in test failures, e.g. a proposed change to KVM's handling of %rip in its fast PIO handling[1] will cause the new VM, i.e. the post-migration VM, to have its %rip set to the IN instruction that triggered KVM_EXIT_IO, leading to a test assertion due to a stage mismatch. For simplicitly, require KVM_CAP_IMMEDIATE_EXIT to complete IO and skip the test if it's not available. The addition of KVM_CAP_IMMEDIATE_EXIT predates the state selftest by more than a year. [1] https://patchwork.kernel.org/patch/10848545/ Fixes: fa3899add1056 ("kvm: selftests: add basic test for state save and restore") Reported-by: Jim Mattson Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/include/kvm_util.h | 1 + tools/testing/selftests/kvm/lib/kvm_util.c | 16 ++++++++++++++++ tools/testing/selftests/kvm/x86_64/state_test.c | 18 ++++++++++++++++-- 3 files changed, 33 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index a84785b02557..07b71ad9734a 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -102,6 +102,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); +void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_mp_state *mp_state); void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index b52cfdefecbf..efa0aad8b3c6 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1121,6 +1121,22 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) return rc; } +void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + int ret; + + TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + + vcpu->state->immediate_exit = 1; + ret = ioctl(vcpu->fd, KVM_RUN, NULL); + vcpu->state->immediate_exit = 0; + + TEST_ASSERT(ret == -1 && errno == EINTR, + "KVM_RUN IOCTL didn't exit immediately, rc: %i, errno: %i", + ret, errno); +} + /* * VM VCPU Set MP State * diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index 4b3f556265f1..30f75856cf39 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -134,6 +134,11 @@ int main(int argc, char *argv[]) struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); + if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) { + fprintf(stderr, "immediate_exit not available, skipping test\n"); + exit(KSFT_SKIP); + } + /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); @@ -156,8 +161,6 @@ int main(int argc, char *argv[]) stage, run->exit_reason, exit_reason_str(run->exit_reason)); - memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, ®s1); switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_ABORT: TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0], @@ -176,6 +179,17 @@ int main(int argc, char *argv[]) uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx", stage, (ulong)uc.args[1]); + /* + * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees + * guest state is consistent only after userspace re-enters the + * kernel with KVM_RUN. Complete IO prior to migrating state + * to a new VM. + */ + vcpu_run_complete_io(vm, VCPU_ID); + + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vm, VCPU_ID, ®s1); + state = vcpu_save_state(vm, VCPU_ID); kvm_vm_release(vm); -- cgit From 2c3af7d901c61c101c02f431cfb520af9ff56ab4 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 1 Apr 2019 13:57:30 -0700 Subject: selftests/bpf: fix vlan handling in flow dissector program When we tail call PROG(VLAN) from parse_eth_proto we don't need to peek back to handle vlan proto because we didn't adjust nhoff/thoff yet. Use flow_keys->n_proto, that we set in parse_eth_proto instead and properly increment nhoff as well. Also, always use skb->protocol and don't look at skb->vlan_present. skb->vlan_present indicates that vlan information is stored out-of-band in skb->vlan_{tci,proto} and vlan header is already pulled from skb. That means, skb->vlan_present == true is not relevant for BPF flow dissector. Add simple test cases with VLAN tagged frames: * single vlan for ipv4 * double vlan for ipv6 Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- .../selftests/bpf/prog_tests/flow_dissector.c | 68 ++++++++++++++++++++++ tools/testing/selftests/bpf/progs/bpf_flow.c | 15 ++--- 2 files changed, 72 insertions(+), 11 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index bcbd928c96ab..fc818bc1d729 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -39,6 +39,58 @@ static struct bpf_flow_keys pkt_v6_flow_keys = { .n_proto = __bpf_constant_htons(ETH_P_IPV6), }; +#define VLAN_HLEN 4 + +static struct { + struct ethhdr eth; + __u16 vlan_tci; + __u16 vlan_proto; + struct iphdr iph; + struct tcphdr tcp; +} __packed pkt_vlan_v4 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_8021Q), + .vlan_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_TCP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .tcp.urg_ptr = 123, + .tcp.doff = 5, +}; + +static struct bpf_flow_keys pkt_vlan_v4_flow_keys = { + .nhoff = VLAN_HLEN, + .thoff = VLAN_HLEN + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), +}; + +static struct { + struct ethhdr eth; + __u16 vlan_tci; + __u16 vlan_proto; + __u16 vlan_tci2; + __u16 vlan_proto2; + struct ipv6hdr iph; + struct tcphdr tcp; +} __packed pkt_vlan_v6 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_8021AD), + .vlan_proto = __bpf_constant_htons(ETH_P_8021Q), + .vlan_proto2 = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_TCP, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .tcp.urg_ptr = 123, + .tcp.doff = 5, +}; + +static struct bpf_flow_keys pkt_vlan_v6_flow_keys = { + .nhoff = VLAN_HLEN * 2, + .thoff = VLAN_HLEN * 2 + sizeof(struct ipv6hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), +}; + void test_flow_dissector(void) { struct bpf_flow_keys flow_keys; @@ -68,5 +120,21 @@ void test_flow_dissector(void) err, errno, retval, duration, size, sizeof(flow_keys)); CHECK_FLOW_KEYS("ipv6_flow_keys", flow_keys, pkt_v6_flow_keys); + err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v4, sizeof(pkt_vlan_v4), + &flow_keys, &size, &retval, &duration); + CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv4", + "err %d errno %d retval %d duration %d size %u/%lu\n", + err, errno, retval, duration, size, sizeof(flow_keys)); + CHECK_FLOW_KEYS("vlan_ipv4_flow_keys", flow_keys, + pkt_vlan_v4_flow_keys); + + err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v6, sizeof(pkt_vlan_v6), + &flow_keys, &size, &retval, &duration); + CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv6", + "err %d errno %d retval %d duration %d size %u/%lu\n", + err, errno, retval, duration, size, sizeof(flow_keys)); + CHECK_FLOW_KEYS("vlan_ipv6_flow_keys", flow_keys, + pkt_vlan_v6_flow_keys); + bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 284660f5aa95..f177c7a6a6c7 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -119,10 +119,7 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto) SEC("flow_dissector") int _dissect(struct __sk_buff *skb) { - if (!skb->vlan_present) - return parse_eth_proto(skb, skb->protocol); - else - return parse_eth_proto(skb, skb->vlan_proto); + return parse_eth_proto(skb, skb->protocol); } /* Parses on IPPROTO_* */ @@ -336,15 +333,9 @@ PROG(VLAN)(struct __sk_buff *skb) { struct bpf_flow_keys *keys = skb->flow_keys; struct vlan_hdr *vlan, _vlan; - __be16 proto; - - /* Peek back to see if single or double-tagging */ - if (bpf_skb_load_bytes(skb, keys->thoff - sizeof(proto), &proto, - sizeof(proto))) - return BPF_DROP; /* Account for double-tagging */ - if (proto == bpf_htons(ETH_P_8021AD)) { + if (keys->n_proto == bpf_htons(ETH_P_8021AD)) { vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan); if (!vlan) return BPF_DROP; @@ -352,6 +343,7 @@ PROG(VLAN)(struct __sk_buff *skb) if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q)) return BPF_DROP; + keys->nhoff += sizeof(*vlan); keys->thoff += sizeof(*vlan); } @@ -359,6 +351,7 @@ PROG(VLAN)(struct __sk_buff *skb) if (!vlan) return 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) || -- cgit From 822fe61795018265ae14731d4e5399e5bde36864 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 1 Apr 2019 13:57:31 -0700 Subject: net/flow_dissector: pass flow_keys->n_proto to BPF programs This is a preparation for the next commit that would prohibit access to the most fields of __sk_buff from the BPF programs. Instead of requiring BPF flow dissector programs to look into skb, pass all input data in the flow_keys. Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/progs/bpf_flow.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index f177c7a6a6c7..75b17cada539 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -92,7 +92,6 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto) { struct bpf_flow_keys *keys = skb->flow_keys; - keys->n_proto = proto; switch (proto) { case bpf_htons(ETH_P_IP): bpf_tail_call(skb, &jmp_table, IP); @@ -119,7 +118,9 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto) SEC("flow_dissector") int _dissect(struct __sk_buff *skb) { - return parse_eth_proto(skb, skb->protocol); + struct bpf_flow_keys *keys = skb->flow_keys; + + return parse_eth_proto(skb, keys->n_proto); } /* Parses on IPPROTO_* */ @@ -358,6 +359,7 @@ PROG(VLAN)(struct __sk_buff *skb) vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q)) return BPF_DROP; + keys->n_proto = vlan->h_vlan_encapsulated_proto; return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto); } -- cgit From fae2708174ae95d98d19f194e03d6e8f688ae195 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Thu, 4 Apr 2019 12:31:35 +0200 Subject: net/sched: act_sample: fix divide by zero in the traffic path the control path of 'sample' action does not validate the value of 'rate' provided by the user, but then it uses it as divisor in the traffic path. Validate it in tcf_sample_init(), and return -EINVAL with a proper extack message in case that value is zero, to fix a splat with the script below: # tc f a dev test0 egress matchall action sample rate 0 group 1 index 2 # tc -s a s action sample total acts 1 action order 0: sample rate 1/0 group 1 pipe index 2 ref 1 bind 1 installed 19 sec used 19 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 # ping 192.0.2.1 -I test0 -c1 -q divide error: 0000 [#1] SMP PTI CPU: 1 PID: 6192 Comm: ping Not tainted 5.1.0-rc2.diag2+ #591 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_sample_act+0x9e/0x1e0 [act_sample] Code: 6a f1 85 c0 74 0d 80 3d 83 1a 00 00 00 0f 84 9c 00 00 00 4d 85 e4 0f 84 85 00 00 00 e8 9b d7 9c f1 44 8b 8b e0 00 00 00 31 d2 <41> f7 f1 85 d2 75 70 f6 85 83 00 00 00 10 48 8b 45 10 8b 88 08 01 RSP: 0018:ffffae320190ba30 EFLAGS: 00010246 RAX: 00000000b0677d21 RBX: ffff8af1ed9ec000 RCX: 0000000059a9fe49 RDX: 0000000000000000 RSI: 000000000c7e33b7 RDI: ffff8af23daa0af0 RBP: ffff8af1ee11b200 R08: 0000000074fcaf7e R09: 0000000000000000 R10: 0000000000000050 R11: ffffffffb3088680 R12: ffff8af232307f80 R13: 0000000000000003 R14: ffff8af1ed9ec000 R15: 0000000000000000 FS: 00007fe9c6d2f740(0000) GS:ffff8af23da80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fff6772f000 CR3: 00000000746a2004 CR4: 00000000001606e0 Call Trace: tcf_action_exec+0x7c/0x1c0 tcf_classify+0x57/0x160 __dev_queue_xmit+0x3dc/0xd10 ip_finish_output2+0x257/0x6d0 ip_output+0x75/0x280 ip_send_skb+0x15/0x40 raw_sendmsg+0xae3/0x1410 sock_sendmsg+0x36/0x40 __sys_sendto+0x10e/0x140 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x60/0x210 entry_SYSCALL_64_after_hwframe+0x49/0xbe [...] Kernel panic - not syncing: Fatal exception in interrupt Add a TDC selftest to document that 'rate' is now being validated. Reported-by: Matteo Croce Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action") Signed-off-by: Davide Caratti Acked-by: Yotam Gigi Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/sample.json | 24 ++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json index 27f0acaed880..ddabb160a11b 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json @@ -143,6 +143,30 @@ "$TC actions flush action sample" ] }, + { + "id": "7571", + "name": "Add sample action with invalid rate", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 0 group 1 index 2", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 2", + "matchPattern": "action order [0-9]+: sample rate 1/0 group 1.*index 2 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action sample" + ] + }, { "id": "b6d4", "name": "Add sample action with mandatory arguments and invalid control action", -- cgit From b959ecf8f953701a19970e5db7e427c05143f303 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 5 Apr 2019 14:20:24 +0200 Subject: selftests: add a tc matchall test case This is a follow up of the commit 0db6f8befc32 ("net/sched: fix ->get helper of the matchall cls"). To test it: $ cd tools/testing/selftests/tc-testing $ ln -s ../plugin-lib/nsPlugin.py plugins/20-nsPlugin.py $ ./tdc.py -n -e 2638 Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- .../selftests/tc-testing/tc-tests/filters/tests.json | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json index 99a5ffca1088..2d096b2abf2c 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json @@ -18,6 +18,26 @@ "$TC qdisc del dev $DEV1 ingress" ] }, + { + "id": "2638", + "name": "Add matchall and try to get it", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$TC qdisc add dev $DEV1 clsact", + "$TC filter add dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall action ok" + ], + "cmdUnderTest": "$TC filter get dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "filter protocol all pref 1 matchall chain 0 handle 0x1234", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 clsact" + ] + }, { "id": "d052", "name": "Add 1M filters with the same action", -- cgit From f1a0ba6cccff75d882204cae1f154f17620b3c4a Mon Sep 17 00:00:00 2001 From: Tadeusz Struk Date: Tue, 12 Feb 2019 15:42:10 -0800 Subject: selftests/tpm2: Extend tests to cover partial reads Three new tests added: 1. Send get random cmd, read header in 1st read, read the rest in second read - expect success 2. Send get random cmd, read only part of the response, send another get random command, read the response - expect success 3. Send get random cmd followed by another get random cmd, without reading the first response - expect the second cmd to fail with -EBUSY Signed-off-by: Tadeusz Struk Reviewed-by: Jarkko Sakkinen Tested-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: James Morris --- tools/testing/selftests/tpm2/tpm2.py | 1 + tools/testing/selftests/tpm2/tpm2_tests.py | 63 ++++++++++++++++++++++++++++++ 2 files changed, 64 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py index 40ea95ce2ead..6fc99ce025b5 100644 --- a/tools/testing/selftests/tpm2/tpm2.py +++ b/tools/testing/selftests/tpm2/tpm2.py @@ -22,6 +22,7 @@ TPM2_CC_UNSEAL = 0x015E TPM2_CC_FLUSH_CONTEXT = 0x0165 TPM2_CC_START_AUTH_SESSION = 0x0176 TPM2_CC_GET_CAPABILITY = 0x017A +TPM2_CC_GET_RANDOM = 0x017B TPM2_CC_PCR_READ = 0x017E TPM2_CC_POLICY_PCR = 0x017F TPM2_CC_PCR_EXTEND = 0x0182 diff --git a/tools/testing/selftests/tpm2/tpm2_tests.py b/tools/testing/selftests/tpm2/tpm2_tests.py index 3bb066fea4a0..d4973be53493 100644 --- a/tools/testing/selftests/tpm2/tpm2_tests.py +++ b/tools/testing/selftests/tpm2/tpm2_tests.py @@ -158,6 +158,69 @@ class SmokeTest(unittest.TestCase): pass self.assertEqual(rejected, True) + def test_read_partial_resp(self): + try: + fmt = '>HIIH' + cmd = struct.pack(fmt, + tpm2.TPM2_ST_NO_SESSIONS, + struct.calcsize(fmt), + tpm2.TPM2_CC_GET_RANDOM, + 0x20) + self.client.tpm.write(cmd) + hdr = self.client.tpm.read(10) + sz = struct.unpack('>I', hdr[2:6])[0] + rsp = self.client.tpm.read() + except: + pass + self.assertEqual(sz, 10 + 2 + 32) + self.assertEqual(len(rsp), 2 + 32) + + def test_read_partial_overwrite(self): + try: + fmt = '>HIIH' + cmd = struct.pack(fmt, + tpm2.TPM2_ST_NO_SESSIONS, + struct.calcsize(fmt), + tpm2.TPM2_CC_GET_RANDOM, + 0x20) + self.client.tpm.write(cmd) + # Read part of the respone + rsp1 = self.client.tpm.read(15) + + # Send a new cmd + self.client.tpm.write(cmd) + + # Read the whole respone + rsp2 = self.client.tpm.read() + except: + pass + self.assertEqual(len(rsp1), 15) + self.assertEqual(len(rsp2), 10 + 2 + 32) + + def test_send_two_cmds(self): + rejected = False + try: + fmt = '>HIIH' + cmd = struct.pack(fmt, + tpm2.TPM2_ST_NO_SESSIONS, + struct.calcsize(fmt), + tpm2.TPM2_CC_GET_RANDOM, + 0x20) + self.client.tpm.write(cmd) + + # expect the second one to raise -EBUSY error + self.client.tpm.write(cmd) + rsp = self.client.tpm.read() + + except IOError, e: + # read the response + rsp = self.client.tpm.read() + rejected = True + pass + except: + pass + self.assertEqual(rejected, True) + class SpaceTest(unittest.TestCase): def setUp(self): logging.basicConfig(filename='SpaceTest.log', level=logging.DEBUG) -- cgit From 6da70580af9612accf042b37564d73e787af39b4 Mon Sep 17 00:00:00 2001 From: Tadeusz Struk Date: Tue, 12 Feb 2019 15:42:05 -0800 Subject: selftests/tpm2: Open tpm dev in unbuffered mode In order to have control over how many bytes are read or written the device needs to be opened in unbuffered mode. Signed-off-by: Tadeusz Struk Reviewed-by: Jarkko Sakkinen Tested-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: James Morris --- tools/testing/selftests/tpm2/tpm2.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py index 6fc99ce025b5..828c18584624 100644 --- a/tools/testing/selftests/tpm2/tpm2.py +++ b/tools/testing/selftests/tpm2/tpm2.py @@ -358,9 +358,9 @@ class Client: self.flags = flags if (self.flags & Client.FLAG_SPACE) == 0: - self.tpm = open('/dev/tpm0', 'r+b') + self.tpm = open('/dev/tpm0', 'r+b', buffering=0) else: - self.tpm = open('/dev/tpmrm0', 'r+b') + self.tpm = open('/dev/tpmrm0', 'r+b', buffering=0) def close(self): self.tpm.close() -- cgit From 7052e2436373cc2c46981e165d1cbc5023f20dd7 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 10 Apr 2019 06:58:16 +0000 Subject: selftests: mlxsw: Test VRF MAC vetoing Test that it is possible to set an IP address on a VRF and that it is not vetoed. Signed-off-by: Ido Schimmel Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- .../testing/selftests/drivers/net/mlxsw/rtnetlink.sh | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh index c4cf6e6d800e..a6c196c8534c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh @@ -11,6 +11,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding ALL_TESTS=" rif_set_addr_test + rif_vrf_set_addr_test rif_inherit_bridge_addr_test rif_non_inherit_bridge_addr_test vlan_interface_deletion_test @@ -98,6 +99,25 @@ rif_set_addr_test() ip link set dev $swp1 addr $swp1_mac } +rif_vrf_set_addr_test() +{ + # Test that it is possible to set an IP address on a VRF upper despite + # its random MAC address. + RET=0 + + ip link add name vrf-test type vrf table 10 + ip link set dev $swp1 master vrf-test + + ip -4 address add 192.0.2.1/24 dev vrf-test + check_err $? "failed to set IPv4 address on VRF" + ip -6 address add 2001:db8:1::1/64 dev vrf-test + check_err $? "failed to set IPv6 address on VRF" + + log_test "RIF - setting IP address on VRF" + + ip link del dev vrf-test +} + rif_inherit_bridge_addr_test() { RET=0 -- cgit From a5f622984a623df9a84cf43f6b098d8dd76fbe05 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 9 Apr 2019 14:23:10 -0700 Subject: selftests: fib_tests: Fix 'Command line is not complete' errors A couple of tests are verifying a route has been removed. The helper expects the prefix as the first part of the expected output. When checking that a route has been deleted the prefix is empty leading to an invalid ip command: $ ip ro ls match Command line is not complete. Try option "help" Fix by moving the comparison of expected output and output to a new function that is used by both check_route and check_route6. Use the new helper for the 2 checks on route removal. Also, remove the reset of 'set -x' in route_setup which overrides the user managed setting. Fixes: d69faad76584c ("selftests: fib_tests: Add prefix route tests with metric") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- tools/testing/selftests/net/fib_tests.sh | 94 ++++++++++++++------------------ 1 file changed, 40 insertions(+), 54 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 1080ff55a788..0d2a5f4f1e63 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -605,6 +605,39 @@ run_cmd() return $rc } +check_expected() +{ + local out="$1" + local expected="$2" + local rc=0 + + [ "${out}" = "${expected}" ] && return 0 + + if [ -z "${out}" ]; then + if [ "$VERBOSE" = "1" ]; then + printf "\nNo route entry found\n" + printf "Expected:\n" + printf " ${expected}\n" + fi + return 1 + fi + + # tricky way to convert output to 1-line without ip's + # messy '\'; this drops all extra white space + out=$(echo ${out}) + if [ "${out}" != "${expected}" ]; then + rc=1 + if [ "${VERBOSE}" = "1" ]; then + printf " Unexpected route entry. Have:\n" + printf " ${out}\n" + printf " Expected:\n" + printf " ${expected}\n\n" + fi + fi + + return $rc +} + # add route for a prefix, flushing any existing routes first # expected to be the first step of a test add_route6() @@ -652,31 +685,7 @@ check_route6() pfx=$1 out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//') - [ "${out}" = "${expected}" ] && return 0 - - if [ -z "${out}" ]; then - if [ "$VERBOSE" = "1" ]; then - printf "\nNo route entry found\n" - printf "Expected:\n" - printf " ${expected}\n" - fi - return 1 - fi - - # tricky way to convert output to 1-line without ip's - # messy '\'; this drops all extra white space - out=$(echo ${out}) - if [ "${out}" != "${expected}" ]; then - rc=1 - if [ "${VERBOSE}" = "1" ]; then - printf " Unexpected route entry. Have:\n" - printf " ${out}\n" - printf " Expected:\n" - printf " ${expected}\n\n" - fi - fi - - return $rc + check_expected "${out}" "${expected}" } route_cleanup() @@ -725,7 +734,7 @@ route_setup() ip -netns ns2 addr add 172.16.103.2/24 dev veth4 ip -netns ns2 addr add 172.16.104.1/24 dev dummy1 - set +ex + set +e } # assumption is that basic add of a single path route works @@ -960,7 +969,8 @@ ipv6_addr_metric_test() run_cmd "$IP li set dev dummy2 down" rc=$? if [ $rc -eq 0 ]; then - check_route6 "" + out=$($IP -6 ro ls match 2001:db8:104::/64) + check_expected "${out}" "" rc=$? fi log_test $rc 0 "Prefix route removed on link down" @@ -1091,38 +1101,13 @@ check_route() local pfx local expected="$1" local out - local rc=0 set -- $expected pfx=$1 [ "${pfx}" = "unreachable" ] && pfx=$2 out=$($IP ro ls match ${pfx}) - [ "${out}" = "${expected}" ] && return 0 - - if [ -z "${out}" ]; then - if [ "$VERBOSE" = "1" ]; then - printf "\nNo route entry found\n" - printf "Expected:\n" - printf " ${expected}\n" - fi - return 1 - fi - - # tricky way to convert output to 1-line without ip's - # messy '\'; this drops all extra white space - out=$(echo ${out}) - if [ "${out}" != "${expected}" ]; then - rc=1 - if [ "${VERBOSE}" = "1" ]; then - printf " Unexpected route entry. Have:\n" - printf " ${out}\n" - printf " Expected:\n" - printf " ${expected}\n\n" - fi - fi - - return $rc + check_expected "${out}" "${expected}" } # assumption is that basic add of a single path route works @@ -1387,7 +1372,8 @@ ipv4_addr_metric_test() run_cmd "$IP li set dev dummy2 down" rc=$? if [ $rc -eq 0 ]; then - check_route "" + out=$($IP ro ls match 172.16.104.0/24) + check_expected "${out}" "" rc=$? fi log_test $rc 0 "Prefix route removed on link down" -- cgit From becf2319f320cae43e20cf179cc51a355a0deb5f Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 25 Mar 2019 23:11:53 +0100 Subject: selftests: netfilter: check icmp pkttoobig errors are set as related When an icmp error such as pkttoobig is received, conntrack checks if the "inner" header (header of packet that did not fit link mtu) is matches an existing connection, and, if so, sets that packet as being related to the conntrack entry it found. It was recently reported that this "related" setting also works if the inner header is from another, different connection (i.e., artificial/forged icmp error). Add a test, followup patch will add additional "inner dst matches outer dst in reverse direction" check before setting related state. Link: https://www.synacktiv.com/posts/systems/icmp-reachable.html Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/Makefile | 2 +- .../selftests/netfilter/conntrack_icmp_related.sh | 283 +++++++++++++++++++++ 2 files changed, 284 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/netfilter/conntrack_icmp_related.sh (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index c9ff2b47bd1c..a37cb1192c6a 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for netfilter selftests -TEST_PROGS := nft_trans_stress.sh nft_nat.sh +TEST_PROGS := nft_trans_stress.sh nft_nat.sh conntrack_icmp_related.sh include ../lib.mk diff --git a/tools/testing/selftests/netfilter/conntrack_icmp_related.sh b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh new file mode 100755 index 000000000000..b48e1833bc89 --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh @@ -0,0 +1,283 @@ +#!/bin/bash +# +# check that ICMP df-needed/pkttoobig icmp are set are set as related +# state +# +# Setup is: +# +# nsclient1 -> nsrouter1 -> nsrouter2 -> nsclient2 +# MTU 1500, except for nsrouter2 <-> nsclient2 link (1280). +# ping nsclient2 from nsclient1, checking that conntrack did set RELATED +# 'fragmentation needed' icmp packet. +# +# In addition, nsrouter1 will perform IP masquerading, i.e. also +# check the icmp errors are propagated to the correct host as per +# nat of "established" icmp-echo "connection". + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +cleanup() { + for i in 1 2;do ip netns del nsclient$i;done + for i in 1 2;do ip netns del nsrouter$i;done +} + +ipv4() { + echo -n 192.168.$1.2 +} + +ipv6 () { + echo -n dead:$1::2 +} + +check_counter() +{ + ns=$1 + name=$2 + expect=$3 + local lret=0 + + cnt=$(ip netns exec $ns nft list counter inet filter "$name" | grep -q "$expect") + if [ $? -ne 0 ]; then + echo "ERROR: counter $name in $ns has unexpected value (expected $expect)" 1>&2 + ip netns exec $ns nft list counter inet filter "$name" 1>&2 + lret=1 + fi + + return $lret +} + +check_unknown() +{ + expect="packets 0 bytes 0" + for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do + check_counter $n "unknown" "$expect" + if [ $? -ne 0 ] ;then + return 1 + fi + done + + return 0 +} + +for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do + ip netns add $n + ip -net $n link set lo up +done + +DEV=veth0 +ip link add $DEV netns nsclient1 type veth peer name eth1 netns nsrouter1 +DEV=veth0 +ip link add $DEV netns nsclient2 type veth peer name eth1 netns nsrouter2 + +DEV=veth0 +ip link add $DEV netns nsrouter1 type veth peer name eth2 netns nsrouter2 + +DEV=veth0 +for i in 1 2; do + ip -net nsclient$i link set $DEV up + ip -net nsclient$i addr add $(ipv4 $i)/24 dev $DEV + ip -net nsclient$i addr add $(ipv6 $i)/64 dev $DEV +done + +ip -net nsrouter1 link set eth1 up +ip -net nsrouter1 link set veth0 up + +ip -net nsrouter2 link set eth1 up +ip -net nsrouter2 link set eth2 up + +ip -net nsclient1 route add default via 192.168.1.1 +ip -net nsclient1 -6 route add default via dead:1::1 + +ip -net nsclient2 route add default via 192.168.2.1 +ip -net nsclient2 route add default via dead:2::1 + +i=3 +ip -net nsrouter1 addr add 192.168.1.1/24 dev eth1 +ip -net nsrouter1 addr add 192.168.3.1/24 dev veth0 +ip -net nsrouter1 addr add dead:1::1/64 dev eth1 +ip -net nsrouter1 addr add dead:3::1/64 dev veth0 +ip -net nsrouter1 route add default via 192.168.3.10 +ip -net nsrouter1 -6 route add default via dead:3::10 + +ip -net nsrouter2 addr add 192.168.2.1/24 dev eth1 +ip -net nsrouter2 addr add 192.168.3.10/24 dev eth2 +ip -net nsrouter2 addr add dead:2::1/64 dev eth1 +ip -net nsrouter2 addr add dead:3::10/64 dev eth2 +ip -net nsrouter2 route add default via 192.168.3.1 +ip -net nsrouter2 route add default via dead:3::1 + +sleep 2 +for i in 4 6; do + ip netns exec nsrouter1 sysctl -q net.ipv$i.conf.all.forwarding=1 + ip netns exec nsrouter2 sysctl -q net.ipv$i.conf.all.forwarding=1 +done + +for netns in nsrouter1 nsrouter2; do +ip netns exec $netns nft -f - </dev/null +if [ $? -ne 0 ]; then + echo "ERROR: netns ip routing/connectivity broken" 1>&2 + cleanup + exit 1 +fi +ip netns exec nsclient1 ping6 -q -c 1 -s 1000 dead:2::2 >/dev/null +if [ $? -ne 0 ]; then + echo "ERROR: netns ipv6 routing/connectivity broken" 1>&2 + cleanup + exit 1 +fi + +check_unknown +if [ $? -ne 0 ]; then + ret=1 +fi + +expect="packets 0 bytes 0" +for netns in nsrouter1 nsrouter2 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +expect="packets 2 bytes 2076" +check_counter nsclient2 "new" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +ip netns exec nsclient1 ping -q -c 1 -s 1300 -M do 192.168.2.2 > /dev/null +if [ $? -eq 0 ]; then + echo "ERROR: ping should have failed with PMTU too big error" 1>&2 + ret=1 +fi + +# nsrouter2 should have generated the icmp error, so +# related counter should be 0 (its in forward). +expect="packets 0 bytes 0" +check_counter "nsrouter2" "related" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +# but nsrouter1 should have seen it, same for nsclient1. +expect="packets 1 bytes 576" +for netns in nsrouter1 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +ip netns exec nsclient1 ping6 -c 1 -s 1300 dead:2::2 > /dev/null +if [ $? -eq 0 ]; then + echo "ERROR: ping6 should have failed with PMTU too big error" 1>&2 + ret=1 +fi + +expect="packets 2 bytes 1856" +for netns in nsrouter1 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +if [ $ret -eq 0 ];then + echo "PASS: icmp mtu error had RELATED state" +else + echo "ERROR: icmp error RELATED state test has failed" +fi + +cleanup +exit $ret -- cgit From 5bdac418f33f60b07a34e01e722889140ee8fac9 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 9 Apr 2019 14:45:20 +0200 Subject: netfilter: nat: fix icmp id randomization Sven Auhagen reported that a 2nd ping request will fail if 'fully-random' mode is used. Reason is that if no proto information is given, min/max are both 0, so we set the icmp id to 0 instead of chosing a random value between 0 and 65535. Update test case as well to catch this, without fix this yields: [..] ERROR: cannot ping ns1 from ns2 with ip masquerade fully-random (attempt 2) ERROR: cannot ping ns1 from ns2 with ipv6 masquerade fully-random (attempt 2) ... becaus 2nd ping clashes with existing 'id 0' icmp conntrack and gets dropped. Fixes: 203f2e78200c27e ("netfilter: nat: remove l4proto->unique_tuple") Reported-by: Sven Auhagen Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/nft_nat.sh | 36 +++++++++++++++++++++------- 1 file changed, 27 insertions(+), 9 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 8ec76681605c..3194007cf8d1 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -321,6 +321,7 @@ EOF test_masquerade6() { + local natflags=$1 local lret=0 ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null @@ -354,13 +355,13 @@ ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading" + echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags" lret=1 fi @@ -397,19 +398,26 @@ EOF fi done + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags (attempt 2)" + lret=1 + fi + ip netns exec ns0 nft flush chain ip6 nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush ip6 nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2" + test $lret -eq 0 && echo "PASS: IPv6 masquerade $natflags for ns2" return $lret } test_masquerade() { + local natflags=$1 local lret=0 ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null @@ -417,7 +425,7 @@ test_masquerade() ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: canot ping ns1 from ns2" + echo "ERROR: cannot ping ns1 from ns2 $natflags" lret=1 fi @@ -443,13 +451,13 @@ ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading" + echo "ERROR: cannot ping ns1 from ns2 with active ip masquere $natflags" lret=1 fi @@ -485,13 +493,19 @@ EOF fi done + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip masquerade $natflags (attempt 2)" + lret=1 + fi + ip netns exec ns0 nft flush chain ip nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: IP masquerade for ns2" + test $lret -eq 0 && echo "PASS: IP masquerade $natflags for ns2" return $lret } @@ -750,8 +764,12 @@ test_local_dnat test_local_dnat6 reset_counters -test_masquerade -test_masquerade6 +test_masquerade "" +test_masquerade6 "" + +reset_counters +test_masquerade "fully-random" +test_masquerade6 "fully-random" reset_counters test_redirect -- cgit From c68c21ca929771a1f128d886359f9229d31cf80c Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Apr 2019 15:57:14 +0200 Subject: selftests: kvm/evmcs_test: complete I/O before migrating guest state Starting state migration after an IO exit without first completing IO may result in test failures. We already have two tests that need this (this patch in fact fixes evmcs_test, similar to what was fixed for state_test in commit 0f73bbc851ed, "KVM: selftests: complete IO before migrating guest state", 2019-03-13) and a third is coming. So, move the code to vcpu_save_state, and while at it do not access register state until after I/O is complete. Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/lib/kvm_util.c | 5 +++++ tools/testing/selftests/kvm/lib/x86_64/processor.c | 8 ++++++++ tools/testing/selftests/kvm/x86_64/evmcs_test.c | 5 +++-- tools/testing/selftests/kvm/x86_64/state_test.c | 15 +-------------- 4 files changed, 17 insertions(+), 16 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index efa0aad8b3c6..4ca96b228e46 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -91,6 +91,11 @@ static void vm_open(struct kvm_vm *vm, int perm, unsigned long type) if (vm->kvm_fd < 0) exit(KSFT_SKIP); + if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) { + fprintf(stderr, "immediate_exit not available, skipping test\n"); + exit(KSFT_SKIP); + } + vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, type); TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, " "rc: %i errno: %i", vm->fd, errno); diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index f28127f4a3af..b363c9611bd6 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1030,6 +1030,14 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) nested_size, sizeof(state->nested_)); } + /* + * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees + * guest state is consistent only after userspace re-enters the + * kernel with KVM_RUN. Complete IO prior to migrating state + * to a new VM. + */ + vcpu_run_complete_io(vm, vcpuid); + nmsrs = kvm_get_num_msrs(vm); list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); list->nmsrs = nmsrs; diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index c49c2a28b0eb..36669684eca5 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -123,8 +123,6 @@ int main(int argc, char *argv[]) stage, run->exit_reason, exit_reason_str(run->exit_reason)); - memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, ®s1); switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_ABORT: TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0], @@ -144,6 +142,9 @@ int main(int argc, char *argv[]) stage, (ulong)uc.args[1]); state = vcpu_save_state(vm, VCPU_ID); + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vm, VCPU_ID, ®s1); + kvm_vm_release(vm); /* Restore state in a new VM. */ diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index 30f75856cf39..e0a3c0204b7c 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -134,11 +134,6 @@ int main(int argc, char *argv[]) struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); - if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) { - fprintf(stderr, "immediate_exit not available, skipping test\n"); - exit(KSFT_SKIP); - } - /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); @@ -179,18 +174,10 @@ int main(int argc, char *argv[]) uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx", stage, (ulong)uc.args[1]); - /* - * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees - * guest state is consistent only after userspace re-enters the - * kernel with KVM_RUN. Complete IO prior to migrating state - * to a new VM. - */ - vcpu_run_complete_io(vm, VCPU_ID); - + state = vcpu_save_state(vm, VCPU_ID); memset(®s1, 0, sizeof(regs1)); vcpu_regs_get(vm, VCPU_ID, ®s1); - state = vcpu_save_state(vm, VCPU_ID); kvm_vm_release(vm); /* Restore state in a new VM. */ -- cgit From c2390f16fc5b847a22f442a190d459beba07e86f Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Apr 2019 15:51:19 +0200 Subject: selftests: kvm: fix for compilers that do not support -no-pie -no-pie was added to GCC at the same time as their configuration option --enable-default-pie. Compilers that were built before do not have -no-pie, but they also do not need it. Detect the option at build time. Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/Makefile | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 7514fcea91a7..2d2e10b219d5 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -1,3 +1,5 @@ +include ../../../../scripts/Kbuild.include + all: top_srcdir = ../../../.. @@ -30,7 +32,11 @@ INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include CFLAGS += -O2 -g -std=gnu99 -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$( Date: Wed, 10 Apr 2019 11:38:33 +0200 Subject: selftests: kvm: add a selftest for SMM Add a simple test for SMM, based on VMX. The test implements its own sync between the guest and the host as using our ucall library seems to be too cumbersome: SMI handler is happening in real-address mode. This patch also fixes KVM_SET_NESTED_STATE to happen after KVM_SET_VCPU_EVENTS, in fact it places it last. This is because KVM needs to know whether the processor is in SMM or not. Signed-off-by: Vitaly Kuznetsov Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/include/x86_64/processor.h | 27 ++++ tools/testing/selftests/kvm/lib/x86_64/processor.c | 12 +- tools/testing/selftests/kvm/x86_64/smm_test.c | 157 +++++++++++++++++++++ 4 files changed, 191 insertions(+), 6 deletions(-) create mode 100644 tools/testing/selftests/kvm/x86_64/smm_test.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 2d2e10b219d5..f8588cca2bef 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -19,6 +19,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test +TEST_GEN_PROGS_x86_64 += x86_64/smm_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += clear_dirty_log_test diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index e2884c2b81ff..6063d5b2f356 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -778,6 +778,33 @@ void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, #define MSR_IA32_APICBASE_ENABLE (1<<11) #define MSR_IA32_APICBASE_BASE (0xfffff<<12) +#define APIC_BASE_MSR 0x800 +#define X2APIC_ENABLE (1UL << 10) +#define APIC_ICR 0x300 +#define APIC_DEST_SELF 0x40000 +#define APIC_DEST_ALLINC 0x80000 +#define APIC_DEST_ALLBUT 0xC0000 +#define APIC_ICR_RR_MASK 0x30000 +#define APIC_ICR_RR_INVALID 0x00000 +#define APIC_ICR_RR_INPROG 0x10000 +#define APIC_ICR_RR_VALID 0x20000 +#define APIC_INT_LEVELTRIG 0x08000 +#define APIC_INT_ASSERT 0x04000 +#define APIC_ICR_BUSY 0x01000 +#define APIC_DEST_LOGICAL 0x00800 +#define APIC_DEST_PHYSICAL 0x00000 +#define APIC_DM_FIXED 0x00000 +#define APIC_DM_FIXED_MASK 0x00700 +#define APIC_DM_LOWEST 0x00100 +#define APIC_DM_SMI 0x00200 +#define APIC_DM_REMRD 0x00300 +#define APIC_DM_NMI 0x00400 +#define APIC_DM_INIT 0x00500 +#define APIC_DM_STARTUP 0x00600 +#define APIC_DM_EXTINT 0x00700 +#define APIC_VECTOR_MASK 0x000FF +#define APIC_ICR2 0x310 + #define MSR_IA32_TSCDEADLINE 0x000006e0 #define MSR_IA32_UCODE_WRITE 0x00000079 diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index b363c9611bd6..dc7fae9fa424 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1101,12 +1101,6 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s struct vcpu *vcpu = vcpu_find(vm, vcpuid); int r; - if (state->nested.size) { - r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i", - r); - } - r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave); TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i", r); @@ -1138,4 +1132,10 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs); TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i", r); + + if (state->nested.size) { + r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i", + r); + } } diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c new file mode 100644 index 000000000000..fb8086964d83 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2018, Red Hat, Inc. + * + * Tests for SMM. + */ +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include +#include +#include +#include +#include +#include + +#include "test_util.h" + +#include "kvm_util.h" + +#include "vmx.h" + +#define VCPU_ID 1 + +#define PAGE_SIZE 4096 + +#define SMRAM_SIZE 65536 +#define SMRAM_MEMSLOT ((1 << 16) | 1) +#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) +#define SMRAM_GPA 0x1000000 +#define SMRAM_STAGE 0xfe + +#define STR(x) #x +#define XSTR(s) STR(s) + +#define SYNC_PORT 0xe +#define DONE 0xff + +/* + * This is compiled as normal 64-bit code, however, SMI handler is executed + * in real-address mode. To stay simple we're limiting ourselves to a mode + * independent subset of asm here. + * SMI handler always report back fixed stage SMRAM_STAGE. + */ +uint8_t smi_handler[] = { + 0xb0, SMRAM_STAGE, /* mov $SMRAM_STAGE, %al */ + 0xe4, SYNC_PORT, /* in $SYNC_PORT, %al */ + 0x0f, 0xaa, /* rsm */ +}; + +void sync_with_host(uint64_t phase) +{ + asm volatile("in $" XSTR(SYNC_PORT)", %%al \n" + : : "a" (phase)); +} + +void self_smi(void) +{ + wrmsr(APIC_BASE_MSR + (APIC_ICR >> 4), + APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI); +} + +void guest_code(struct vmx_pages *vmx_pages) +{ + uint64_t apicbase = rdmsr(MSR_IA32_APICBASE); + + sync_with_host(1); + + wrmsr(MSR_IA32_APICBASE, apicbase | X2APIC_ENABLE); + + sync_with_host(2); + + self_smi(); + + sync_with_host(4); + + if (vmx_pages) { + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + + sync_with_host(5); + + self_smi(); + + sync_with_host(7); + } + + sync_with_host(DONE); +} + +int main(int argc, char *argv[]) +{ + struct vmx_pages *vmx_pages = NULL; + vm_vaddr_t vmx_pages_gva = 0; + + struct kvm_regs regs; + struct kvm_vm *vm; + struct kvm_run *run; + struct kvm_x86_state *state; + int stage, stage_reported; + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + run = vcpu_state(vm, VCPU_ID); + + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA, + SMRAM_MEMSLOT, SMRAM_PAGES, 0); + TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, SMRAM_GPA, SMRAM_MEMSLOT) + == SMRAM_GPA, "could not allocate guest physical addresses?"); + + memset(addr_gpa2hva(vm, SMRAM_GPA), 0x0, SMRAM_SIZE); + memcpy(addr_gpa2hva(vm, SMRAM_GPA) + 0x8000, smi_handler, + sizeof(smi_handler)); + + vcpu_set_msr(vm, VCPU_ID, MSR_IA32_SMBASE, SMRAM_GPA); + + if (kvm_check_cap(KVM_CAP_NESTED_STATE)) { + vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + } else { + printf("will skip SMM test with VMX enabled\n"); + vcpu_args_set(vm, VCPU_ID, 1, 0); + } + + for (stage = 1;; stage++) { + _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Stage %d: unexpected exit reason: %u (%s),\n", + stage, run->exit_reason, + exit_reason_str(run->exit_reason)); + + memset(®s, 0, sizeof(regs)); + vcpu_regs_get(vm, VCPU_ID, ®s); + + stage_reported = regs.rax & 0xff; + + if (stage_reported == DONE) + goto done; + + TEST_ASSERT(stage_reported == stage || + stage_reported == SMRAM_STAGE, + "Unexpected stage: #%x, got %x", + stage, stage_reported); + + state = vcpu_save_state(vm, VCPU_ID); + kvm_vm_release(vm); + kvm_vm_restart(vm, O_RDWR); + vm_vcpu_add(vm, VCPU_ID, 0, 0); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vcpu_load_state(vm, VCPU_ID, state); + run = vcpu_state(vm, VCPU_ID); + free(state); + } + +done: + kvm_vm_free(vm); +} -- cgit From 8cd40d1d41ffc305d9aed77937896e1712b2490c Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 18 Apr 2019 17:50:23 -0700 Subject: proc: fix map_files test on F29 F29 bans mapping first 64KB even for root making test fail. Iterate from address 0 until mmap() works. Gentoo (root): openat(AT_FDCWD, "/dev/zero", O_RDONLY) = 3 mmap(NULL, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = 0 Gentoo (non-root): openat(AT_FDCWD, "/dev/zero", O_RDONLY) = 3 mmap(NULL, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EPERM (Operation not permitted) mmap(0x1000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = 0x1000 F29 (root): openat(AT_FDCWD, "/dev/zero", O_RDONLY) = 3 mmap(NULL, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x1000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x2000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x3000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x4000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x5000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x6000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x7000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x8000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x9000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0xa000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0xb000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0xc000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0xd000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0xe000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0xf000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x10000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = 0x10000 Now all proc tests succeed on F29 if run as root, at last! Link: http://lkml.kernel.org/r/20190414123612.GB12971@avx2 Signed-off-by: Alexey Dobriyan Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .../testing/selftests/proc/proc-self-map-files-002.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/proc/proc-self-map-files-002.c b/tools/testing/selftests/proc/proc-self-map-files-002.c index 762cb01f2ca7..47b7473dedef 100644 --- a/tools/testing/selftests/proc/proc-self-map-files-002.c +++ b/tools/testing/selftests/proc/proc-self-map-files-002.c @@ -46,12 +46,9 @@ static void fail(const char *fmt, unsigned long a, unsigned long b) int main(void) { - const unsigned int PAGE_SIZE = sysconf(_SC_PAGESIZE); -#ifdef __arm__ - unsigned long va = 2 * PAGE_SIZE; -#else - unsigned long va = 0; -#endif + const int PAGE_SIZE = sysconf(_SC_PAGESIZE); + const unsigned long va_max = 1UL << 32; + unsigned long va; void *p; int fd; unsigned long a, b; @@ -60,10 +57,13 @@ int main(void) if (fd == -1) return 1; - p = mmap((void *)va, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0); - if (p == MAP_FAILED) { - if (errno == EPERM) - return 4; + for (va = 0; va < va_max; va += PAGE_SIZE) { + p = mmap((void *)va, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0); + if (p == (void *)va) + break; + } + if (va == va_max) { + fprintf(stderr, "error: mmap doesn't like you\n"); return 1; } -- cgit From 68545aa1cda847c4fdda7e49331807f99f799838 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 18 Apr 2019 17:50:27 -0700 Subject: proc: fixup proc-pid-vm test Silly sizeof(pointer) vs sizeof(uint8_t[]) bug. Link: http://lkml.kernel.org/r/20190414123009.GA12971@avx2 Fixes: e483b0208784 ("proc: test /proc/*/maps, smaps, smaps_rollup, statm") Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/proc/proc-pid-vm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c index 7202bbac976e..853aa164a401 100644 --- a/tools/testing/selftests/proc/proc-pid-vm.c +++ b/tools/testing/selftests/proc/proc-pid-vm.c @@ -187,8 +187,8 @@ static int make_exe(const uint8_t *payload, size_t len) ph.p_offset = 0; ph.p_vaddr = VADDR; ph.p_paddr = 0; - ph.p_filesz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + sizeof(payload); - ph.p_memsz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + sizeof(payload); + ph.p_filesz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + len; + ph.p_memsz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + len; ph.p_align = 4096; fd = openat(AT_FDCWD, "/tmp", O_WRONLY|O_EXCL|O_TMPFILE, 0700); -- cgit From 30c04d796b693e22405c38e9b78e9a364e4c77e6 Mon Sep 17 00:00:00 2001 From: Po-Hsu Lin Date: Thu, 18 Apr 2019 19:57:25 +0800 Subject: selftests/net: correct the return value for run_netsocktests The run_netsocktests will be marked as passed regardless the actual test result from the ./socket: selftests: net: run_netsocktests ======================================== -------------------- running socket test -------------------- [FAIL] ok 1..6 selftests: net: run_netsocktests [PASS] This is because the test script itself has been successfully executed. Fix this by exit 1 when the test failed. Signed-off-by: Po-Hsu Lin Signed-off-by: David S. Miller --- tools/testing/selftests/net/run_netsocktests | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/run_netsocktests b/tools/testing/selftests/net/run_netsocktests index b093f39c298c..14e41faf2c57 100755 --- a/tools/testing/selftests/net/run_netsocktests +++ b/tools/testing/selftests/net/run_netsocktests @@ -7,7 +7,7 @@ echo "--------------------" ./socket if [ $? -ne 0 ]; then echo "[FAIL]" + exit 1 else echo "[PASS]" fi - -- cgit From 8c03557c3f25271e62e39154af66ebdd1b59c9ca Mon Sep 17 00:00:00 2001 From: Po-Hsu Lin Date: Fri, 19 Apr 2019 19:01:13 +0800 Subject: selftests/net: correct the return value for run_afpackettests The run_afpackettests will be marked as passed regardless the return value of those sub-tests in the script: -------------------- running psock_tpacket test -------------------- [FAIL] selftests: run_afpackettests [PASS] Fix this by changing the return value for each tests. Signed-off-by: Po-Hsu Lin Signed-off-by: David S. Miller --- tools/testing/selftests/net/run_afpackettests | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests index 2dc95fda7ef7..ea5938ec009a 100755 --- a/tools/testing/selftests/net/run_afpackettests +++ b/tools/testing/selftests/net/run_afpackettests @@ -6,12 +6,14 @@ if [ $(id -u) != 0 ]; then exit 0 fi +ret=0 echo "--------------------" echo "running psock_fanout test" echo "--------------------" ./in_netns.sh ./psock_fanout if [ $? -ne 0 ]; then echo "[FAIL]" + ret=1 else echo "[PASS]" fi @@ -22,6 +24,7 @@ echo "--------------------" ./in_netns.sh ./psock_tpacket if [ $? -ne 0 ]; then echo "[FAIL]" + ret=1 else echo "[PASS]" fi @@ -32,6 +35,8 @@ echo "--------------------" ./in_netns.sh ./txring_overwrite if [ $? -ne 0 ]; then echo "[FAIL]" + ret=1 else echo "[PASS]" fi +exit $ret -- cgit From 4ee0776760af03f181e6b80baf5fb1cc1a980f50 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 24 Apr 2019 09:32:55 -0700 Subject: selftests/seccomp: Prepare for exclusive seccomp flags Some seccomp flags will become exclusive, so the selftest needs to be adjusted to mask those out and test them individually for the "all flags" tests. Cc: stable@vger.kernel.org # v5.0+ Signed-off-by: Kees Cook Reviewed-by: Tycho Andersen Acked-by: James Morris --- tools/testing/selftests/seccomp/seccomp_bpf.c | 34 ++++++++++++++++++++------- 1 file changed, 25 insertions(+), 9 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index f69d2ee29742..5019cdae5d0b 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -2166,11 +2166,14 @@ TEST(detect_seccomp_filter_flags) SECCOMP_FILTER_FLAG_LOG, SECCOMP_FILTER_FLAG_SPEC_ALLOW, SECCOMP_FILTER_FLAG_NEW_LISTENER }; - unsigned int flag, all_flags; + unsigned int exclusive[] = { + SECCOMP_FILTER_FLAG_TSYNC, + SECCOMP_FILTER_FLAG_NEW_LISTENER }; + unsigned int flag, all_flags, exclusive_mask; int i; long ret; - /* Test detection of known-good filter flags */ + /* Test detection of individual known-good filter flags */ for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) { int bits = 0; @@ -2197,16 +2200,29 @@ TEST(detect_seccomp_filter_flags) all_flags |= flag; } - /* Test detection of all known-good filter flags */ - ret = seccomp(SECCOMP_SET_MODE_FILTER, all_flags, NULL); - EXPECT_EQ(-1, ret); - EXPECT_EQ(EFAULT, errno) { - TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!", - all_flags); + /* + * Test detection of all known-good filter flags combined. But + * for the exclusive flags we need to mask them out and try them + * individually for the "all flags" testing. + */ + exclusive_mask = 0; + for (i = 0; i < ARRAY_SIZE(exclusive); i++) + exclusive_mask |= exclusive[i]; + for (i = 0; i < ARRAY_SIZE(exclusive); i++) { + flag = all_flags & ~exclusive_mask; + flag |= exclusive[i]; + + ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EFAULT, errno) { + TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!", + flag); + } } - /* Test detection of an unknown filter flag */ + /* Test detection of an unknown filter flags, without exclusives. */ flag = -1; + flag &= ~exclusive_mask; ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL); EXPECT_EQ(-1, ret); EXPECT_EQ(EINVAL, errno) { -- cgit From 6dd7f14080473b655c247863e61b7c34424f0c83 Mon Sep 17 00:00:00 2001 From: Paul Chaignon Date: Wed, 24 Apr 2019 21:51:26 +0200 Subject: selftests/bpf: test cases for pkt/null checks in subprogs The first test case, for pointer null checks, is equivalent to the following pseudo-code. It checks that the verifier does not complain on line 6 and recognizes that ptr isn't null. 1: ptr = bpf_map_lookup_elem(map, &key); 2: ret = subprog(ptr) { 3: return ptr != NULL; 4: } 5: if (ret) 6: value = *ptr; The second test case, for packet bound checks, is equivalent to the following pseudo-code. It checks that the verifier does not complain on line 7 and recognizes that the packet is at least 1 byte long. 1: pkt_end = ctx.pkt_end; 2: ptr = ctx.pkt + 8; 3: ret = subprog(ptr, pkt_end) { 4: return ptr <= pkt_end; 5: } 6: if (ret) 7: value = *(u8 *)ctx.pkt; Signed-off-by: Paul Chaignon Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/verifier/calls.c | 25 ++++++++++++++++++++++ .../selftests/bpf/verifier/direct_packet_access.c | 22 +++++++++++++++++++ 2 files changed, 47 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index fb11240b758b..9093a8f64dc6 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -374,6 +374,31 @@ .prog_type = BPF_PROG_TYPE_XDP, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, +{ + "calls: ptr null check in subprog", + .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_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .fixup_map_hash_48b = { 3 }, + .result_unpriv = REJECT, + .result = ACCEPT, + .retval = 0, +}, { "calls: two calls with args", .insns = { diff --git a/tools/testing/selftests/bpf/verifier/direct_packet_access.c b/tools/testing/selftests/bpf/verifier/direct_packet_access.c index e3fc22e672c2..d5c596fdc4b9 100644 --- a/tools/testing/selftests/bpf/verifier/direct_packet_access.c +++ b/tools/testing/selftests/bpf/verifier/direct_packet_access.c @@ -631,3 +631,25 @@ .errstr = "invalid access to packet", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, +{ + "direct packet access: test29 (reg > pkt_end in subprog)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_2, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, -- cgit From 76d58e0f07ec203bbdfcaabd9a9fc10a5a3ed5ea Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 17 Apr 2019 15:28:44 +0200 Subject: KVM: fix KVM_CLEAR_DIRTY_LOG for memory slots of unaligned size If a memory slot's size is not a multiple of 64 pages (256K), then the KVM_CLEAR_DIRTY_LOG API is unusable: clearing the final 64 pages either requires the requested page range to go beyond memslot->npages, or requires log->num_pages to be unaligned, and kvm_clear_dirty_log_protect requires log->num_pages to be both in range and aligned. To allow this case, allow log->num_pages not to be a multiple of 64 if it ends exactly on the last page of the slot. Reported-by: Peter Xu Fixes: 98938aa8edd6 ("KVM: validate userspace input in kvm_clear_dirty_log_protect()", 2019-01-02) Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/dirty_log_test.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 4715cfba20dc..93f99c6b7d79 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -288,8 +288,11 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, #endif max_gfn = (1ul << (guest_pa_bits - guest_page_shift)) - 1; guest_page_size = (1ul << guest_page_shift); - /* 1G of guest page sized pages */ - guest_num_pages = (1ul << (30 - guest_page_shift)); + /* + * A little more than 1G of guest page sized pages. Cover the + * case where the size is not aligned to 64 pages. + */ + guest_num_pages = (1ul << (30 - guest_page_shift)) + 3; host_page_size = getpagesize(); host_num_pages = (guest_num_pages * guest_page_size) / host_page_size + !!((guest_num_pages * guest_page_size) % host_page_size); @@ -359,7 +362,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); #ifdef USE_CLEAR_DIRTY_LOG kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, - DIV_ROUND_UP(host_num_pages, 64) * 64); + host_num_pages); #endif vm_dirty_log_verify(bmap); iteration++; -- cgit From eba3afde1cea7dbd7881683232f2a85e2ed86bfe Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 26 Apr 2019 15:27:11 +0200 Subject: KVM: selftests: make hyperv_cpuid test pass on AMD Enlightened VMCS is only supported on Intel CPUs but the test shouldn't fail completely. Signed-off-by: Vitaly Kuznetsov Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c index 264425f75806..9a21e912097c 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c @@ -141,7 +141,13 @@ int main(int argc, char *argv[]) free(hv_cpuid_entries); - vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap); + rv = _vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap); + + if (rv) { + fprintf(stderr, + "Enlightened VMCS is unsupported, skip related test\n"); + goto vm_free; + } hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm); if (!hv_cpuid_entries) @@ -151,6 +157,7 @@ int main(int argc, char *argv[]) free(hv_cpuid_entries); +vm_free: kvm_vm_free(vm); return 0; -- cgit From 15d55bae4e3c43cd9f87fd93c73a263e172d34e1 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 29 Apr 2019 10:30:09 -0700 Subject: selftests: fib_rule_tests: Fix icmp proto with ipv6 A recent commit returns an error if icmp is used as the ip-proto for IPv6 fib rules. Update fib_rule_tests to send ipv6-icmp instead of icmp. Fixes: 5e1a99eae8499 ("ipv4: Add ICMPv6 support when parse route ipproto") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- tools/testing/selftests/net/fib_rule_tests.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index d4cfb6a7a086..5b92c1f4dc04 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -147,8 +147,8 @@ fib_rule6_test() fib_check_iproute_support "ipproto" "ipproto" if [ $? -eq 0 ]; then - match="ipproto icmp" - fib_rule6_test_match_n_redirect "$match" "$match" "ipproto icmp match" + match="ipproto ipv6-icmp" + fib_rule6_test_match_n_redirect "$match" "$match" "ipproto ipv6-icmp match" fi } -- cgit From f68d7c44e76532e46f292ad941aa3706cb9e6e40 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 30 Apr 2019 10:46:10 +0800 Subject: selftests: fib_rule_tests: print the result and return 1 if any tests failed Fixes: 65b2b4939a64 ("selftests: net: initial fib rule tests") Signed-off-by: Hangbin Liu Reviewed-by: David Ahern Signed-off-by: David S. Miller --- tools/testing/selftests/net/fib_rule_tests.sh | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 5b92c1f4dc04..4b7e107865bf 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -27,6 +27,7 @@ log_test() nsuccess=$((nsuccess+1)) printf "\n TEST: %-50s [ OK ]\n" "${msg}" else + ret=1 nfail=$((nfail+1)) printf "\n TEST: %-50s [FAIL]\n" "${msg}" if [ "${PAUSE_ON_FAIL}" = "yes" ]; then @@ -245,4 +246,9 @@ setup run_fibrule_tests cleanup +if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} +fi + exit $ret -- cgit