From f38a1f0a5a5710b14c0e899628c815522c6111cf Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 8 Mar 2019 15:58:20 -0800 Subject: libbpf: handle BTF parsing and loading properly This patch splits and cleans up error handling logic for loading BTF data. Previously, if BTF data was parsed successfully, but failed to load into kernel, we'd report nonsensical error code, instead of error returned from btf__load(). Now btf__new() and btf__load() are handled separately with proper cleanup and warning reporting. Fixes: d29d87f7e612 ("btf: separate btf creation and loading") Reported-by: Martin KaFai Lau Signed-off-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- tools/lib/bpf/libbpf.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index d5b830d60601..5e977d2688da 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -835,12 +835,19 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) obj->efile.maps_shndx = idx; else if (strcmp(name, BTF_ELF_SEC) == 0) { obj->btf = btf__new(data->d_buf, data->d_size); - if (IS_ERR(obj->btf) || btf__load(obj->btf)) { + if (IS_ERR(obj->btf)) { pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", BTF_ELF_SEC, PTR_ERR(obj->btf)); - if (!IS_ERR(obj->btf)) - btf__free(obj->btf); obj->btf = NULL; + continue; + } + err = btf__load(obj->btf); + if (err) { + pr_warning("Error loading %s into kernel: %d. Ignored and continue.\n", + BTF_ELF_SEC, err); + btf__free(obj->btf); + obj->btf = NULL; + err = 0; } } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) { btf_ext_data = data; -- cgit v1.2.2 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') 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 v1.2.2 From 6bf21b54a596d60905cfc7e8af8e2fe16d9fe7e9 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Tue, 12 Mar 2019 09:59:45 +0100 Subject: libbpf: fix to reject unknown flags in xsk_socket__create() In xsk_socket__create(), the libbpf_flags field was not checked for setting currently unused/unknown flags. This patch fixes that by returning -EINVAL if the user has set any flag that is not in use at this point in time. Fixes: 1cad07884239 ("libbpf: add support for using AF_XDP sockets") Signed-off-by: Magnus Karlsson Reviewed-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann --- tools/lib/bpf/xsk.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index f98ac82c9aea..8d0078b65486 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -126,8 +126,8 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg, cfg->frame_headroom = usr_cfg->frame_headroom; } -static void xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, - const struct xsk_socket_config *usr_cfg) +static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, + const struct xsk_socket_config *usr_cfg) { if (!usr_cfg) { cfg->rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS; @@ -135,14 +135,19 @@ static void xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, cfg->libbpf_flags = 0; cfg->xdp_flags = 0; cfg->bind_flags = 0; - return; + return 0; } + if (usr_cfg->libbpf_flags & ~XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD) + return -EINVAL; + cfg->rx_size = usr_cfg->rx_size; cfg->tx_size = usr_cfg->tx_size; cfg->libbpf_flags = usr_cfg->libbpf_flags; cfg->xdp_flags = usr_cfg->xdp_flags; cfg->bind_flags = usr_cfg->bind_flags; + + return 0; } int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, @@ -557,7 +562,9 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, } strncpy(xsk->ifname, ifname, IFNAMSIZ); - xsk_set_xdp_socket_config(&xsk->config, usr_config); + err = xsk_set_xdp_socket_config(&xsk->config, usr_config); + if (err) + goto out_socket; if (rx) { err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING, -- cgit v1.2.2 From ef776a272b093fb52612e6d8f4b3e77f9bb49554 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 12 Mar 2019 10:23:06 -0700 Subject: bpf: Sync bpf.h to tools/ This patch sync the uapi bpf.h to tools/. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- tools/include/uapi/linux/bpf.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3c38ac9a92a7..983b25cb608d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2366,6 +2366,14 @@ union bpf_attr { * current value is ect (ECN capable). Works with IPv6 and IPv4. * Return * 1 if set, 0 if not set. + * + * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk) + * Description + * Return a **struct bpf_sock** pointer in TCP_LISTEN state. + * bpf_sk_release() is unnecessary and not allowed. + * Return + * A **struct bpf_sock** pointer on success, or NULL in + * case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2465,7 +2473,8 @@ union bpf_attr { FN(spin_unlock), \ FN(sk_fullsock), \ FN(tcp_sock), \ - FN(skb_ecn_set_ce), + FN(skb_ecn_set_ce), \ + FN(get_listener_sock), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call -- cgit v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 From 9768095ba97ce946838e8210f0b44f2fd36ec31d Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Sun, 10 Mar 2019 17:44:09 -0700 Subject: btf: resolve enum fwds in btf_dedup GCC and clang support enum forward declarations as an extension. Such forward-declared enums will be represented as normal BTF_KIND_ENUM types with vlen=0. This patch adds ability to resolve such enums to their corresponding fully defined enums. This helps to avoid duplicated BTF type graphs which only differ by some types referencing forward-declared enum vs full enum. One such example in kernel is enum irqchip_irq_state, defined in include/linux/interrupt.h and forward-declared in include/linux/irq.h. This causes entire struct task_struct and all referenced types to be duplicated in btf_dedup output. This patch eliminates such duplication cases. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/btf.c | 51 ++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 38 insertions(+), 13 deletions(-) (limited to 'tools') diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 1b8d8cdd3575..87e3020ac1bc 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1602,16 +1602,12 @@ static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2) /* Calculate type signature hash of ENUM. */ static __u32 btf_hash_enum(struct btf_type *t) { - struct btf_enum *member = (struct btf_enum *)(t + 1); - __u32 vlen = BTF_INFO_VLEN(t->info); - __u32 h = btf_hash_common(t); - int i; + __u32 h; - for (i = 0; i < vlen; i++) { - h = hash_combine(h, member->name_off); - h = hash_combine(h, member->val); - member++; - } + /* don't hash vlen and enum members to support enum fwd resolving */ + h = hash_combine(0, t->name_off); + h = hash_combine(h, t->info & ~0xffff); + h = hash_combine(h, t->size); return h; } @@ -1637,6 +1633,22 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) return true; } +static inline bool btf_is_enum_fwd(struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM && + BTF_INFO_VLEN(t->info) == 0; +} + +static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) +{ + if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2)) + return btf_equal_enum(t1, t2); + /* ignore vlen when comparing */ + return t1->name_off == t2->name_off && + (t1->info & ~0xffff) == (t2->info & ~0xffff) && + t1->size == t2->size; +} + /* * Calculate type signature hash of STRUCT/UNION, ignoring referenced type IDs, * as referenced type IDs equivalence is established separately during type @@ -1860,6 +1872,17 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) new_id = cand_node->type_id; break; } + if (d->opts.dont_resolve_fwds) + continue; + if (btf_compat_enum(t, cand)) { + if (btf_is_enum_fwd(t)) { + /* resolve fwd to full enum */ + new_id = cand_node->type_id; + break; + } + /* resolve canonical enum fwd to full enum */ + d->map[cand_node->type_id] = type_id; + } } break; @@ -2084,15 +2107,15 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, return fwd_kind == real_kind; } - if (cand_type->info != canon_type->info) - return 0; - switch (cand_kind) { case BTF_KIND_INT: return btf_equal_int(cand_type, canon_type); case BTF_KIND_ENUM: - return btf_equal_enum(cand_type, canon_type); + if (d->opts.dont_resolve_fwds) + return btf_equal_enum(cand_type, canon_type); + else + return btf_compat_enum(cand_type, canon_type); case BTF_KIND_FWD: return btf_equal_common(cand_type, canon_type); @@ -2103,6 +2126,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, case BTF_KIND_PTR: case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: + if (cand_type->info != canon_type->info) + return 0; return btf_dedup_is_equiv(d, cand_type->type, canon_type->type); case BTF_KIND_ARRAY: { -- cgit v1.2.2 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') 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 v1.2.2 From ea6eced00e4b28821804eee24e80d9528f48972a Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Thu, 14 Mar 2019 12:38:41 +0000 Subject: tools: bpf: synchronise BPF UAPI header with tools Synchronise the bpf.h header under tools, to report the latest fixes and additions to the documentation for the BPF helpers. Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov --- tools/include/uapi/linux/bpf.h | 183 +++++++++++++++++++++++++++-------------- 1 file changed, 120 insertions(+), 63 deletions(-) (limited to 'tools') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 983b25cb608d..929c8e537a14 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -502,16 +502,6 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) - * Description - * Push an element *value* in *map*. *flags* is one of: - * - * **BPF_EXIST** - * If the queue/stack is full, the oldest element is removed to - * make room for this. - * Return - * 0 on success, or a negative error in case of failure. - * * int bpf_probe_read(void *dst, u32 size, const void *src) * Description * For tracing programs, safely attempt to read *size* bytes from @@ -1435,14 +1425,14 @@ union bpf_attr { * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx) * Description * Equivalent to bpf_get_socket_cookie() helper that accepts - * *skb*, but gets socket from **struct bpf_sock_addr** contex. + * *skb*, but gets socket from **struct bpf_sock_addr** context. * Return * A 8-byte long non-decreasing number. * * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) * Description * Equivalent to bpf_get_socket_cookie() helper that accepts - * *skb*, but gets socket from **struct bpf_sock_ops** contex. + * *skb*, but gets socket from **struct bpf_sock_ops** context. * Return * A 8-byte long non-decreasing number. * @@ -2098,52 +2088,52 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * int bpf_rc_repeat(void *ctx) * Description * This helper is used in programs implementing IR decoding, to - * report a successfully decoded key press with *scancode*, - * *toggle* value in the given *protocol*. The scancode will be - * translated to a keycode using the rc keymap, and reported as - * an input key down event. After a period a key up event is - * generated. This period can be extended by calling either - * **bpf_rc_keydown**\ () again with the same values, or calling - * **bpf_rc_repeat**\ (). + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. * - * Some protocols include a toggle bit, in case the button was - * released and pressed again between consecutive scancodes. + * Some IR protocols like NEC have a special IR message for + * repeating last button, for when a button is held down. * * The *ctx* should point to the lirc sample as passed into * the program. * - * The *protocol* is the decoded protocol number (see - * **enum rc_proto** for some predefined values). - * * This helper is only available is the kernel was compiled with * the **CONFIG_BPF_LIRC_MODE2** configuration option set to * "**y**". * Return * 0 * - * int bpf_rc_repeat(void *ctx) + * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) * Description * This helper is used in programs implementing IR decoding, to - * report a successfully decoded repeat key message. This delays - * the generation of a key up event for previously generated - * key down event. + * report a successfully decoded key press with *scancode*, + * *toggle* value in the given *protocol*. The scancode will be + * translated to a keycode using the rc keymap, and reported as + * an input key down event. After a period a key up event is + * generated. This period can be extended by calling either + * **bpf_rc_keydown**\ () again with the same values, or calling + * **bpf_rc_repeat**\ (). * - * Some IR protocols like NEC have a special IR message for - * repeating last button, for when a button is held down. + * Some protocols include a toggle bit, in case the button was + * released and pressed again between consecutive scancodes. * * The *ctx* should point to the lirc sample as passed into * the program. * + * The *protocol* is the decoded protocol number (see + * **enum rc_proto** for some predefined values). + * * This helper is only available is the kernel was compiled with * the **CONFIG_BPF_LIRC_MODE2** configuration option set to * "**y**". * Return * 0 * - * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb) + * u64 bpf_skb_cgroup_id(struct sk_buff *skb) * Description * Return the cgroup v2 id of the socket associated with the *skb*. * This is roughly similar to the **bpf_get_cgroup_classid**\ () @@ -2159,30 +2149,12 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) - * Description - * Return id of cgroup v2 that is ancestor of cgroup associated - * with the *skb* at the *ancestor_level*. The root cgroup is at - * *ancestor_level* zero and each step down the hierarchy - * increments the level. If *ancestor_level* == level of cgroup - * associated with *skb*, then return value will be same as that - * of **bpf_skb_cgroup_id**\ (). - * - * The helper is useful to implement policies based on cgroups - * that are upper in hierarchy than immediate cgroup associated - * with *skb*. - * - * The format of returned id and helper limitations are same as in - * **bpf_skb_cgroup_id**\ (). - * Return - * The id is returned or 0 in case the id could not be retrieved. - * * u64 bpf_get_current_cgroup_id(void) * Return * A 64-bit integer containing the current cgroup id based * on the cgroup within which the current task is running. * - * void* get_local_storage(void *map, u64 flags) + * void *bpf_get_local_storage(void *map, u64 flags) * Description * Get the pointer to the local storage area. * The type and the size of the local storage is defined @@ -2209,6 +2181,24 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * + * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *skb* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *skb*, then return value will be same as that + * of **bpf_skb_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *skb*. + * + * The format of returned id and helper limitations are same as in + * **bpf_skb_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. + * * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) * Description * Look for TCP socket matching *tuple*, optionally in a child @@ -2289,6 +2279,16 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * + * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is + * removed to make room for this. + * Return + * 0 on success, or a negative error in case of failure. + * * int bpf_map_pop_elem(struct bpf_map *map, void *value) * Description * Pop an element from *map*. @@ -2343,36 +2343,93 @@ union bpf_attr { * Return * 0 * + * int bpf_spin_lock(struct bpf_spin_lock *lock) + * Description + * Acquire a spinlock represented by the pointer *lock*, which is + * stored as part of a value of a map. Taking the lock allows to + * safely update the rest of the fields in that value. The + * spinlock can (and must) later be released with a call to + * **bpf_spin_unlock**\ (\ *lock*\ ). + * + * Spinlocks in BPF programs come with a number of restrictions + * and constraints: + * + * * **bpf_spin_lock** objects are only allowed inside maps of + * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this + * list could be extended in the future). + * * BTF description of the map is mandatory. + * * The BPF program can take ONE lock at a time, since taking two + * or more could cause dead locks. + * * Only one **struct bpf_spin_lock** is allowed per map element. + * * When the lock is taken, calls (either BPF to BPF or helpers) + * are not allowed. + * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not + * allowed inside a spinlock-ed region. + * * The BPF program MUST call **bpf_spin_unlock**\ () to release + * the lock, on all execution paths, before it returns. + * * The BPF program can access **struct bpf_spin_lock** only via + * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ () + * helpers. Loading or storing data into the **struct + * bpf_spin_lock** *lock*\ **;** field of a map is not allowed. + * * To use the **bpf_spin_lock**\ () helper, the BTF description + * of the map value must be a struct and have **struct + * bpf_spin_lock** *anyname*\ **;** field at the top level. + * Nested lock inside another struct is not allowed. + * * The **struct bpf_spin_lock** *lock* field in a map value must + * be aligned on a multiple of 4 bytes in that value. + * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy + * the **bpf_spin_lock** field to user space. + * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from + * a BPF program, do not update the **bpf_spin_lock** field. + * * **bpf_spin_lock** cannot be on the stack or inside a + * networking packet (it can only be inside of a map values). + * * **bpf_spin_lock** is available to root only. + * * Tracing programs and socket filter programs cannot use + * **bpf_spin_lock**\ () due to insufficient preemption checks + * (but this may change in the future). + * * **bpf_spin_lock** is not allowed in inner maps of map-in-map. + * Return + * 0 + * + * int bpf_spin_unlock(struct bpf_spin_lock *lock) + * Description + * Release the *lock* previously locked by a call to + * **bpf_spin_lock**\ (\ *lock*\ ). + * Return + * 0 + * * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk) * Description * This helper gets a **struct bpf_sock** pointer such - * that all the fields in bpf_sock can be accessed. + * that all the fields in this **bpf_sock** can be accessed. * Return - * A **struct bpf_sock** pointer on success, or NULL in + * A **struct bpf_sock** pointer on success, or **NULL** in * case of failure. * * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk) * Description * This helper gets a **struct bpf_tcp_sock** pointer from a * **struct bpf_sock** pointer. - * * Return - * A **struct bpf_tcp_sock** pointer on success, or NULL in + * A **struct bpf_tcp_sock** pointer on success, or **NULL** in * case of failure. * * int bpf_skb_ecn_set_ce(struct sk_buf *skb) - * Description - * Sets ECN of IP header to ce (congestion encountered) if - * current value is ect (ECN capable). Works with IPv6 and IPv4. - * Return - * 1 if set, 0 if not set. + * Description + * Set ECN (Explicit Congestion Notification) field of IP header + * to **CE** (Congestion Encountered) if current value is **ECT** + * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6 + * and IPv4. + * Return + * 1 if the **CE** flag is set (either by the current helper call + * or because it was already present), 0 if it is not set. * * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk) * Description - * Return a **struct bpf_sock** pointer in TCP_LISTEN state. - * bpf_sk_release() is unnecessary and not allowed. + * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state. + * **bpf_sk_release**\ () is unnecessary and not allowed. * Return - * A **struct bpf_sock** pointer on success, or NULL in + * A **struct bpf_sock** pointer on success, or **NULL** in * case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ -- cgit v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 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') 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 v1.2.2 From 1d382264d911d91a8be5dbed1f0e053eb3245d81 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 23 Mar 2019 01:49:10 +0100 Subject: bpf, libbpf: fix version info and add it to shared object Even though libbpf's versioning script for the linker (libbpf.map) is pointing to 0.0.2, the BPF_EXTRAVERSION in the Makefile has not been updated along with it and is therefore still on 0.0.1. While fixing up, I also noticed that the generated shared object versioning information is missing, typical convention is to have a linker name (libbpf.so), soname (libbpf.so.0) and real name (libbpf.so.0.0.2) for library management. This is based upon the LIBBPF_VERSION as well. The build will then produce the following bpf libraries: # ll libbpf* libbpf.a libbpf.so -> libbpf.so.0.0.2 libbpf.so.0 -> libbpf.so.0.0.2 libbpf.so.0.0.2 # readelf -d libbpf.so.0.0.2 | grep SONAME 0x000000000000000e (SONAME) Library soname: [libbpf.so.0] And install them accordingly: # rm -rf /tmp/bld; mkdir /tmp/bld; make -j$(nproc) O=/tmp/bld install Auto-detecting system features: ... libelf: [ on ] ... bpf: [ on ] CC /tmp/bld/libbpf.o CC /tmp/bld/bpf.o CC /tmp/bld/nlattr.o CC /tmp/bld/btf.o CC /tmp/bld/libbpf_errno.o CC /tmp/bld/str_error.o CC /tmp/bld/netlink.o CC /tmp/bld/bpf_prog_linfo.o CC /tmp/bld/libbpf_probes.o CC /tmp/bld/xsk.o LD /tmp/bld/libbpf-in.o LINK /tmp/bld/libbpf.a LINK /tmp/bld/libbpf.so.0.0.2 LINK /tmp/bld/test_libbpf INSTALL /tmp/bld/libbpf.a INSTALL /tmp/bld/libbpf.so.0.0.2 # ll /usr/local/lib64/libbpf.* /usr/local/lib64/libbpf.a /usr/local/lib64/libbpf.so -> libbpf.so.0.0.2 /usr/local/lib64/libbpf.so.0 -> libbpf.so.0.0.2 /usr/local/lib64/libbpf.so.0.0.2 Fixes: 1bf4b05810fe ("tools: bpftool: add probes for eBPF program types") Fixes: 1b76c13e4b36 ("bpf tools: Introduce 'bpf' library and add bpf feature check") Reported-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/Makefile | 42 ++++++++++++++++++++++++++++-------------- 1 file changed, 28 insertions(+), 14 deletions(-) (limited to 'tools') diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 61aaacf0cfa1..5bf8e52c41fc 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -3,7 +3,7 @@ BPF_VERSION = 0 BPF_PATCHLEVEL = 0 -BPF_EXTRAVERSION = 1 +BPF_EXTRAVERSION = 2 MAKEFLAGS += --no-print-directory @@ -79,8 +79,6 @@ export prefix libdir src obj libdir_SQ = $(subst ','\'',$(libdir)) libdir_relative_SQ = $(subst ','\'',$(libdir_relative)) -LIB_FILE = libbpf.a libbpf.so - VERSION = $(BPF_VERSION) PATCHLEVEL = $(BPF_PATCHLEVEL) EXTRAVERSION = $(BPF_EXTRAVERSION) @@ -88,7 +86,10 @@ EXTRAVERSION = $(BPF_EXTRAVERSION) OBJ = $@ N = -LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION) +LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION) + +LIB_TARGET = libbpf.a libbpf.so.$(LIBBPF_VERSION) +LIB_FILE = libbpf.a libbpf.so* # Set compile option CFLAGS ifdef EXTRA_CFLAGS @@ -128,16 +129,18 @@ all: export srctree OUTPUT CC LD CFLAGS V include $(srctree)/tools/build/Makefile.include -BPF_IN := $(OUTPUT)libbpf-in.o -LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) -VERSION_SCRIPT := libbpf.map +BPF_IN := $(OUTPUT)libbpf-in.o +VERSION_SCRIPT := libbpf.map + +LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) +LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}') VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) -CMD_TARGETS = $(LIB_FILE) +CMD_TARGETS = $(LIB_TARGET) CXX_TEST_TARGET = $(OUTPUT)test_libbpf @@ -170,9 +173,13 @@ $(BPF_IN): force elfdep bpfdep echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf -$(OUTPUT)libbpf.so: $(BPF_IN) - $(QUIET_LINK)$(CC) --shared -Wl,--version-script=$(VERSION_SCRIPT) \ - $^ -o $@ +$(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) + +$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN) + $(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(VERSION) \ + -Wl,--version-script=$(VERSION_SCRIPT) $^ -o $@ + @ln -sf $(@F) $(OUTPUT)libbpf.so + @ln -sf $(@F) $(OUTPUT)libbpf.so.$(VERSION) $(OUTPUT)libbpf.a: $(BPF_IN) $(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^ @@ -192,6 +199,12 @@ check_abi: $(OUTPUT)libbpf.so exit 1; \ fi +define do_install_mkdir + if [ ! -d '$(DESTDIR_SQ)$1' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \ + fi +endef + define do_install if [ ! -d '$(DESTDIR_SQ)$2' ]; then \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \ @@ -200,8 +213,9 @@ define do_install endef install_lib: all_cmd - $(call QUIET_INSTALL, $(LIB_FILE)) \ - $(call do_install,$(LIB_FILE),$(libdir_SQ)) + $(call QUIET_INSTALL, $(LIB_TARGET)) \ + $(call do_install_mkdir,$(libdir_SQ)); \ + cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ) install_headers: $(call QUIET_INSTALL, headers) \ @@ -219,7 +233,7 @@ config-clean: clean: $(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \ - *.o *~ *.a *.so .*.d .*.cmd LIBBPF-CFLAGS + *.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd LIBBPF-CFLAGS $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf -- cgit v1.2.2 From 63197f78bca2d86093126783b0ee6519bd652435 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 23 Mar 2019 01:49:11 +0100 Subject: bpf, libbpf: clarify bump in libbpf version info The current documentation suggests that we would need to bump the libbpf version on every change. Lets clarify this a bit more and reflect what we do today in practice, that is, bumping it once per development cycle. Fixes: 76d1b894c515 ("libbpf: Document API and ABI conventions") Reported-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/README.rst | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/lib/bpf/README.rst b/tools/lib/bpf/README.rst index 5788479384ca..cef7b77eab69 100644 --- a/tools/lib/bpf/README.rst +++ b/tools/lib/bpf/README.rst @@ -111,6 +111,7 @@ starting from ``0.0.1``. Every time ABI is being changed, e.g. because a new symbol is added or semantic of existing symbol is changed, ABI version should be bumped. +This bump in ABI version is at most once per kernel development cycle. For example, if current state of ``libbpf.map`` is: -- cgit v1.2.2