From e8e36984080b55ac5e57bdb09a5b570f2fc8e963 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Fri, 4 Jan 2019 01:07:07 -0800 Subject: [PATCH 1/7] bpf: Fix [::] -> [::1] rewrite in sys_sendmsg sys_sendmsg has supported unspecified destination IPv6 (wildcard) for unconnected UDP sockets since 876c7f41. When [::] is passed by user as destination, sys_sendmsg rewrites it with [::1] to be consistent with BSD (see "BSD'ism" comment in the code). This didn't work when cgroup-bpf was enabled though since the rewrite [::] -> [::1] happened before passing control to cgroup-bpf block where fl6.daddr was updated with passed by user sockaddr_in6.sin6_addr (that might or might not be changed by BPF program). That way if user passed [::] as dst IPv6 it was first rewritten with [::1] by original code from 876c7f41, but then rewritten back with [::] by cgroup-bpf block. It happened even when BPF_CGROUP_UDP6_SENDMSG program was not present (CONFIG_CGROUP_BPF=y was enough). The fix is to apply BSD'ism after cgroup-bpf block so that [::] is replaced with [::1] no matter where it came from: passed by user to sys_sendmsg or set by BPF_CGROUP_UDP6_SENDMSG program. Fixes: 1cedee13d25a ("bpf: Hooks for sys_sendmsg") Reported-by: Nitin Rawat Signed-off-by: Andrey Ignatov Signed-off-by: Alexei Starovoitov --- net/ipv6/udp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9cbf363172bd..7c3505006f8e 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1390,10 +1390,7 @@ do_udp_sendmsg: ipc6.opt = opt; fl6.flowi6_proto = sk->sk_protocol; - if (!ipv6_addr_any(daddr)) - fl6.daddr = *daddr; - else - fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ + fl6.daddr = *daddr; if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) fl6.saddr = np->saddr; fl6.fl6_sport = inet->inet_sport; @@ -1421,6 +1418,9 @@ do_udp_sendmsg: } } + if (ipv6_addr_any(&fl6.daddr)) + fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ + final_p = fl6_update_dst(&fl6, opt, &final); if (final_p) connected = false; From 976b4f3a4646fbf0d189caca25f91f82e4be4b5a Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Fri, 4 Jan 2019 01:07:08 -0800 Subject: [PATCH 2/7] selftests/bpf: Test [::] -> [::1] rewrite in sys_sendmsg in test_sock_addr Test that sys_sendmsg BPF hook doesn't break sys_sendmsg behaviour to rewrite destination IPv6 = [::] with [::1] (BSD'ism). Two test cases are added: 1) User passes dst IPv6 = [::] and BPF_CGROUP_UDP6_SENDMSG program doesn't touch it. 2) User passes dst IPv6 != [::], but BPF_CGROUP_UDP6_SENDMSG program rewrites it with [::]. In both cases [::1] is used by sys_sendmsg code eventually and datagram is sent successfully for unconnected UDP socket. Example of relevant output: Test case: sendmsg6: set dst IP = [::] (BSD'ism) .. [PASS] Test case: sendmsg6: preserve dst IP = [::] (BSD'ism) .. [PASS] Signed-off-by: Andrey Ignatov Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/test_sock_addr.c | 53 ++++++++++++++++++-- 1 file changed, 50 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index 73b7493d4120..d94336cbd8bd 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -44,6 +44,7 @@ #define SERV6_V4MAPPED_IP "::ffff:192.168.0.4" #define SRC6_IP "::1" #define SRC6_REWRITE_IP "::6" +#define WILDCARD6_IP "::" #define SERV6_PORT 6060 #define SERV6_REWRITE_PORT 6666 @@ -85,12 +86,14 @@ static int bind4_prog_load(const struct sock_addr_test *test); static int bind6_prog_load(const struct sock_addr_test *test); static int connect4_prog_load(const struct sock_addr_test *test); static int connect6_prog_load(const struct sock_addr_test *test); +static int sendmsg_allow_prog_load(const struct sock_addr_test *test); static int sendmsg_deny_prog_load(const struct sock_addr_test *test); static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test); static int sendmsg4_rw_c_prog_load(const struct sock_addr_test *test); static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test); static int sendmsg6_rw_c_prog_load(const struct sock_addr_test *test); static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test); +static int sendmsg6_rw_wildcard_prog_load(const struct sock_addr_test *test); static struct sock_addr_test tests[] = { /* bind */ @@ -462,6 +465,34 @@ static struct sock_addr_test tests[] = { SRC6_REWRITE_IP, SYSCALL_ENOTSUPP, }, + { + "sendmsg6: set dst IP = [::] (BSD'ism)", + sendmsg6_rw_wildcard_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + "sendmsg6: preserve dst IP = [::] (BSD'ism)", + sendmsg_allow_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + WILDCARD6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_PORT, + SRC6_IP, + SUCCESS, + }, { "sendmsg6: deny call", sendmsg_deny_prog_load, @@ -734,16 +765,27 @@ static int connect6_prog_load(const struct sock_addr_test *test) return load_path(test, CONNECT6_PROG_PATH); } -static int sendmsg_deny_prog_load(const struct sock_addr_test *test) +static int sendmsg_ret_only_prog_load(const struct sock_addr_test *test, + int32_t rc) { struct bpf_insn insns[] = { - /* return 0 */ - BPF_MOV64_IMM(BPF_REG_0, 0), + /* return rc */ + BPF_MOV64_IMM(BPF_REG_0, rc), BPF_EXIT_INSN(), }; return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); } +static int sendmsg_allow_prog_load(const struct sock_addr_test *test) +{ + return sendmsg_ret_only_prog_load(test, /*rc*/ 1); +} + +static int sendmsg_deny_prog_load(const struct sock_addr_test *test) +{ + return sendmsg_ret_only_prog_load(test, /*rc*/ 0); +} + static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test) { struct sockaddr_in dst4_rw_addr; @@ -864,6 +906,11 @@ static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test) return sendmsg6_rw_dst_asm_prog_load(test, SERV6_V4MAPPED_IP); } +static int sendmsg6_rw_wildcard_prog_load(const struct sock_addr_test *test) +{ + return sendmsg6_rw_dst_asm_prog_load(test, WILDCARD6_IP); +} + static int sendmsg6_rw_c_prog_load(const struct sock_addr_test *test) { return load_path(test, SENDMSG6_PROG_PATH); From d3bd7413e0ca40b60cf60d4003246d067cafdeda Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 6 Jan 2019 00:54:37 +0100 Subject: [PATCH 3/7] bpf: fix sanitation of alu op with pointer / scalar type from different paths While 979d63d50c0c ("bpf: prevent out of bounds speculation on pointer arithmetic") took care of rejecting alu op on pointer when e.g. pointer came from two different map values with different map properties such as value size, Jann reported that a case was not covered yet when a given alu op is used in both "ptr_reg += reg" and "numeric_reg += reg" from different branches where we would incorrectly try to sanitize based on the pointer's limit. Catch this corner case and reject the program instead. Fixes: 979d63d50c0c ("bpf: prevent out of bounds speculation on pointer arithmetic") Reported-by: Jann Horn Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + kernel/bpf/verifier.c | 61 ++++++++++++++++++++++++++++-------- 2 files changed, 49 insertions(+), 13 deletions(-) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 27b74947cd2b..573cca00a0e6 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -172,6 +172,7 @@ struct bpf_verifier_state_list { #define BPF_ALU_SANITIZE_SRC 1U #define BPF_ALU_SANITIZE_DST 2U #define BPF_ALU_NEG_VALUE (1U << 2) +#define BPF_ALU_NON_POINTER (1U << 3) #define BPF_ALU_SANITIZE (BPF_ALU_SANITIZE_SRC | \ BPF_ALU_SANITIZE_DST) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f6bc62a9ee8e..56674a7c3778 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3103,6 +3103,40 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, } } +static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env, + const struct bpf_insn *insn) +{ + return env->allow_ptr_leaks || BPF_SRC(insn->code) == BPF_K; +} + +static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux, + u32 alu_state, u32 alu_limit) +{ + /* If we arrived here from different branches with different + * state or limits to sanitize, then this won't work. + */ + if (aux->alu_state && + (aux->alu_state != alu_state || + aux->alu_limit != alu_limit)) + return -EACCES; + + /* Corresponding fixup done in fixup_bpf_calls(). */ + aux->alu_state = alu_state; + aux->alu_limit = alu_limit; + return 0; +} + +static int sanitize_val_alu(struct bpf_verifier_env *env, + struct bpf_insn *insn) +{ + struct bpf_insn_aux_data *aux = cur_aux(env); + + if (can_skip_alu_sanitation(env, insn)) + return 0; + + return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0); +} + static int sanitize_ptr_alu(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, @@ -3117,7 +3151,7 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, struct bpf_reg_state tmp; bool ret; - if (env->allow_ptr_leaks || BPF_SRC(insn->code) == BPF_K) + if (can_skip_alu_sanitation(env, insn)) return 0; /* We already marked aux for masking from non-speculative @@ -3133,19 +3167,8 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, if (retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg)) return 0; - - /* If we arrived here from different branches with different - * limits to sanitize, then this won't work. - */ - if (aux->alu_state && - (aux->alu_state != alu_state || - aux->alu_limit != alu_limit)) + if (update_alu_sanitation_state(aux, alu_state, alu_limit)) return -EACCES; - - /* Corresponding fixup done in fixup_bpf_calls(). */ - aux->alu_state = alu_state; - aux->alu_limit = alu_limit; - do_sim: /* Simulate and find potential out-of-bounds access under * speculative execution from truncation as a result of @@ -3418,6 +3441,8 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, s64 smin_val, smax_val; u64 umin_val, umax_val; u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; + u32 dst = insn->dst_reg; + int ret; if (insn_bitness == 32) { /* Relevant for 32-bit RSH: Information can propagate towards @@ -3452,6 +3477,11 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, switch (opcode) { case BPF_ADD: + ret = sanitize_val_alu(env, insn); + if (ret < 0) { + verbose(env, "R%d tried to add from different pointers or scalars\n", dst); + return ret; + } if (signed_add_overflows(dst_reg->smin_value, smin_val) || signed_add_overflows(dst_reg->smax_value, smax_val)) { dst_reg->smin_value = S64_MIN; @@ -3471,6 +3501,11 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off); break; case BPF_SUB: + ret = sanitize_val_alu(env, insn); + if (ret < 0) { + verbose(env, "R%d tried to sub from different pointers or scalars\n", dst); + return ret; + } if (signed_sub_overflows(dst_reg->smin_value, smax_val) || signed_sub_overflows(dst_reg->smax_value, smin_val)) { /* Overflow possible, we know nothing */ From 1cbbcfbbd56efd994d643428c69467fe3c8ab672 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 6 Jan 2019 00:54:38 +0100 Subject: [PATCH 4/7] bpf: add various test cases for alu op on mixed dst register types Add couple of test_verifier tests to check sanitation of alu op insn with pointer and scalar type coming from different paths. This also includes BPF insns of the test reproducer provided by Jann Horn. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/test_verifier.c | 120 ++++++++++++++++++++ 1 file changed, 120 insertions(+) diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 10d44446e801..2fd90d456892 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -6933,6 +6933,126 @@ static struct bpf_test tests[] = { .result = ACCEPT, .retval = 1, }, + { + "map access: mixing value pointer and scalar, 1", + .insns = { + // load map value pointer into r0 and r2 + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_FD(BPF_REG_ARG1, 0), + BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_FP), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG2, -16), + BPF_ST_MEM(BPF_DW, BPF_REG_FP, -16, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + // load some number from the map into r1 + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + // depending on r1, branch: + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 3), + // branch A + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_JMP_A(2), + // branch B + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 0x100000), + // common instruction + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + // depending on r1, branch: + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1), + // branch A + BPF_JMP_A(4), + // branch B + BPF_MOV64_IMM(BPF_REG_0, 0x13371337), + // verifier follows fall-through + BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 0x100000, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + // fake-dead code; targeted from branch A to + // prevent dead code sanitization + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R2 tried to add from different pointers or scalars", + .retval = 0, + }, + { + "map access: mixing value pointer and scalar, 2", + .insns = { + // load map value pointer into r0 and r2 + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_FD(BPF_REG_ARG1, 0), + BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_FP), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG2, -16), + BPF_ST_MEM(BPF_DW, BPF_REG_FP, -16, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + // load some number from the map into r1 + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + // depending on r1, branch: + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3), + // branch A + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 0x100000), + BPF_JMP_A(2), + // branch B + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, 0), + // common instruction + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + // depending on r1, branch: + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1), + // branch A + BPF_JMP_A(4), + // branch B + BPF_MOV64_IMM(BPF_REG_0, 0x13371337), + // verifier follows fall-through + BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 0x100000, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + // fake-dead code; targeted from branch A to + // prevent dead code sanitization + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R2 tried to add from different maps or paths", + .retval = 0, + }, + { + "sanitation: alu with different scalars", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_FD(BPF_REG_ARG1, 0), + BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_FP), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG2, -16), + BPF_ST_MEM(BPF_DW, BPF_REG_FP, -16, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 0x100000), + BPF_JMP_A(2), + BPF_MOV64_IMM(BPF_REG_2, 42), + BPF_MOV64_IMM(BPF_REG_3, 0x100001), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = ACCEPT, + .retval = 0x100000, + }, { "map access: value_ptr += known scalar, upper oob arith, test 1", .insns = { From a8911d6d5878587767a78c6bde371298ca2a3be3 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 7 Jan 2019 09:46:46 -0800 Subject: [PATCH 5/7] selftests/bpf: fix incorrect users of create_and_get_cgroup We have some tests that assume create_and_get_cgroup returns -1 on error which is incorrect (it returns 0 on error). Since fd might be zero in general case, change create_and_get_cgroup to return -1 on error and fix the users that assume 0 on error. Fixes: f269099a7e7a ("tools/bpf: add a selftest for bpf_get_current_cgroup_id() helper") Fixes: 7d2c6cfc5411 ("bpf: use --cgroup in test_suite if supplied") v2: - instead of fixing the uses that assume -1 on error, convert the users that assume 0 on error (fd might be zero in general case) Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov --- samples/bpf/test_cgrp2_attach2.c | 14 +++++++------- samples/bpf/test_current_task_under_cgroup_user.c | 2 +- tools/testing/selftests/bpf/cgroup_helpers.c | 6 +++--- tools/testing/selftests/bpf/test_cgroup_storage.c | 2 +- tools/testing/selftests/bpf/test_dev_cgroup.c | 2 +- tools/testing/selftests/bpf/test_netcnt.c | 2 +- .../selftests/bpf/test_skb_cgroup_id_user.c | 2 +- tools/testing/selftests/bpf/test_sock.c | 2 +- tools/testing/selftests/bpf/test_sock_addr.c | 2 +- tools/testing/selftests/bpf/test_socket_cookie.c | 2 +- tools/testing/selftests/bpf/test_tcpbpf_user.c | 2 +- tools/testing/selftests/bpf/test_tcpnotify_user.c | 2 +- 12 files changed, 20 insertions(+), 20 deletions(-) diff --git a/samples/bpf/test_cgrp2_attach2.c b/samples/bpf/test_cgrp2_attach2.c index d7b68ef5ba79..0bb6507256b7 100644 --- a/samples/bpf/test_cgrp2_attach2.c +++ b/samples/bpf/test_cgrp2_attach2.c @@ -77,7 +77,7 @@ static int test_foo_bar(void) /* Create cgroup /foo, get fd, and join it */ foo = create_and_get_cgroup(FOO); - if (!foo) + if (foo < 0) goto err; if (join_cgroup(FOO)) @@ -94,7 +94,7 @@ static int test_foo_bar(void) /* Create cgroup /foo/bar, get fd, and join it */ bar = create_and_get_cgroup(BAR); - if (!bar) + if (bar < 0) goto err; if (join_cgroup(BAR)) @@ -298,19 +298,19 @@ static int test_multiprog(void) goto err; cg1 = create_and_get_cgroup("/cg1"); - if (!cg1) + if (cg1 < 0) goto err; cg2 = create_and_get_cgroup("/cg1/cg2"); - if (!cg2) + if (cg2 < 0) goto err; cg3 = create_and_get_cgroup("/cg1/cg2/cg3"); - if (!cg3) + if (cg3 < 0) goto err; cg4 = create_and_get_cgroup("/cg1/cg2/cg3/cg4"); - if (!cg4) + if (cg4 < 0) goto err; cg5 = create_and_get_cgroup("/cg1/cg2/cg3/cg4/cg5"); - if (!cg5) + if (cg5 < 0) goto err; if (join_cgroup("/cg1/cg2/cg3/cg4/cg5")) diff --git a/samples/bpf/test_current_task_under_cgroup_user.c b/samples/bpf/test_current_task_under_cgroup_user.c index 2259f997a26c..f082d6ac59f0 100644 --- a/samples/bpf/test_current_task_under_cgroup_user.c +++ b/samples/bpf/test_current_task_under_cgroup_user.c @@ -32,7 +32,7 @@ int main(int argc, char **argv) cg2 = create_and_get_cgroup(CGROUP_PATH); - if (!cg2) + if (cg2 < 0) goto err; if (bpf_map_update_elem(map_fd[0], &idx, &cg2, BPF_ANY)) { diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index cf16948aad4a..6692a40a6979 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -155,7 +155,7 @@ void cleanup_cgroup_environment(void) * This function creates a cgroup under the top level workdir and returns the * file descriptor. It is idempotent. * - * On success, it returns the file descriptor. On failure it returns 0. + * On success, it returns the file descriptor. On failure it returns -1. * If there is a failure, it prints the error to stderr. */ int create_and_get_cgroup(const char *path) @@ -166,13 +166,13 @@ int create_and_get_cgroup(const char *path) format_cgroup_path(cgroup_path, path); if (mkdir(cgroup_path, 0777) && errno != EEXIST) { log_err("mkdiring cgroup %s .. %s", path, cgroup_path); - return 0; + return -1; } fd = open(cgroup_path, O_RDONLY); if (fd < 0) { log_err("Opening Cgroup"); - return 0; + return -1; } return fd; diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c index f44834155f25..2fc4625c1a15 100644 --- a/tools/testing/selftests/bpf/test_cgroup_storage.c +++ b/tools/testing/selftests/bpf/test_cgroup_storage.c @@ -81,7 +81,7 @@ int main(int argc, char **argv) /* Create a cgroup, get fd, and join it */ cgroup_fd = create_and_get_cgroup(TEST_CGROUP); - if (!cgroup_fd) { + if (cgroup_fd < 0) { printf("Failed to create test cgroup\n"); goto err; } diff --git a/tools/testing/selftests/bpf/test_dev_cgroup.c b/tools/testing/selftests/bpf/test_dev_cgroup.c index 9c8b50bac7e0..76e4993b7c16 100644 --- a/tools/testing/selftests/bpf/test_dev_cgroup.c +++ b/tools/testing/selftests/bpf/test_dev_cgroup.c @@ -43,7 +43,7 @@ int main(int argc, char **argv) /* Create a cgroup, get fd, and join it */ cgroup_fd = create_and_get_cgroup(TEST_CGROUP); - if (!cgroup_fd) { + if (cgroup_fd < 0) { printf("Failed to create test cgroup\n"); goto err; } diff --git a/tools/testing/selftests/bpf/test_netcnt.c b/tools/testing/selftests/bpf/test_netcnt.c index 44ed7f29f8ab..c1da5404454a 100644 --- a/tools/testing/selftests/bpf/test_netcnt.c +++ b/tools/testing/selftests/bpf/test_netcnt.c @@ -65,7 +65,7 @@ int main(int argc, char **argv) /* Create a cgroup, get fd, and join it */ cgroup_fd = create_and_get_cgroup(TEST_CGROUP); - if (!cgroup_fd) { + if (cgroup_fd < 0) { printf("Failed to create test cgroup\n"); goto err; } diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c index c121cc59f314..9220747c069d 100644 --- a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c +++ b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c @@ -164,7 +164,7 @@ int main(int argc, char **argv) goto err; cgfd = create_and_get_cgroup(CGROUP_PATH); - if (!cgfd) + if (cgfd < 0) goto err; if (join_cgroup(CGROUP_PATH)) diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c index b8ebe2f58074..561ffb6d6433 100644 --- a/tools/testing/selftests/bpf/test_sock.c +++ b/tools/testing/selftests/bpf/test_sock.c @@ -458,7 +458,7 @@ int main(int argc, char **argv) goto err; cgfd = create_and_get_cgroup(CG_PATH); - if (!cgfd) + if (cgfd < 0) goto err; if (join_cgroup(CG_PATH)) diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index d94336cbd8bd..3f110eaaf29c 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -1442,7 +1442,7 @@ int main(int argc, char **argv) goto err; cgfd = create_and_get_cgroup(CG_PATH); - if (!cgfd) + if (cgfd < 0) goto err; if (join_cgroup(CG_PATH)) diff --git a/tools/testing/selftests/bpf/test_socket_cookie.c b/tools/testing/selftests/bpf/test_socket_cookie.c index b6c2c605d8c0..fc7832ee566b 100644 --- a/tools/testing/selftests/bpf/test_socket_cookie.c +++ b/tools/testing/selftests/bpf/test_socket_cookie.c @@ -202,7 +202,7 @@ int main(int argc, char **argv) goto err; cgfd = create_and_get_cgroup(CG_PATH); - if (!cgfd) + if (cgfd < 0) goto err; if (join_cgroup(CG_PATH)) diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c index e6eebda7d112..716b4e3be581 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_user.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c @@ -103,7 +103,7 @@ int main(int argc, char **argv) goto err; cg_fd = create_and_get_cgroup(cg_path); - if (!cg_fd) + if (cg_fd < 0) goto err; if (join_cgroup(cg_path)) diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c index ff3c4522aed6..4e4353711a86 100644 --- a/tools/testing/selftests/bpf/test_tcpnotify_user.c +++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c @@ -115,7 +115,7 @@ int main(int argc, char **argv) goto err; cg_fd = create_and_get_cgroup(cg_path); - if (!cg_fd) + if (cg_fd < 0) goto err; if (join_cgroup(cg_path)) From a769fa7208b94f37b6240215dc6970f9d76fc58c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 7 Jan 2019 22:57:17 +0100 Subject: [PATCH 6/7] bpf, doc: update design qa to reflect kern_version requirement Update the bpf_design_QA.rst to also reflect recent changes in 6c4fc209fcf9 ("bpf: remove useless version check for prog load"). Suggested-by: Quentin Monnet Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- Documentation/bpf/bpf_design_QA.rst | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/Documentation/bpf/bpf_design_QA.rst b/Documentation/bpf/bpf_design_QA.rst index 6780a6d81745..7cc9e368c1e9 100644 --- a/Documentation/bpf/bpf_design_QA.rst +++ b/Documentation/bpf/bpf_design_QA.rst @@ -157,12 +157,11 @@ Q: Does BPF have a stable ABI? ------------------------------ A: YES. BPF instructions, arguments to BPF programs, set of helper functions and their arguments, recognized return codes are all part -of ABI. However when tracing programs are using bpf_probe_read() helper -to walk kernel internal datastructures and compile with kernel -internal headers these accesses can and will break with newer -kernels. The union bpf_attr -> kern_version is checked at load time -to prevent accidentally loading kprobe-based bpf programs written -for a different kernel. Networking programs don't do kern_version check. +of ABI. However there is one specific exception to tracing programs +which are using helpers like bpf_probe_read() to walk kernel internal +data structures and compile with kernel internal headers. Both of these +kernel internals are subject to change and can break with newer kernels +such that the program needs to be adapted accordingly. Q: How much stack space a BPF program uses? ------------------------------------------- From 80f21ff987eb377140d27102285f8dd1167b335c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 7 Jan 2019 22:57:18 +0100 Subject: [PATCH 7/7] bpf, doc: add note for libbpf's stand-alone build Given this came up couple of times, add a note to libbpf's readme about the semi-automated mirror for a stand-alone build which is officially managed by BPF folks. While at it, also explicitly state the libbpf license in the readme file. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/README.rst | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/tools/lib/bpf/README.rst b/tools/lib/bpf/README.rst index 056f38310722..607aae40f4ed 100644 --- a/tools/lib/bpf/README.rst +++ b/tools/lib/bpf/README.rst @@ -132,6 +132,20 @@ For example, if current state of ``libbpf.map`` is: Format of version script and ways to handle ABI changes, including incompatible ones, described in details in [1]. +Stand-alone build +================= + +Under https://github.com/libbpf/libbpf there is a (semi-)automated +mirror of the mainline's version of libbpf for a stand-alone build. + +However, all changes to libbpf's code base must be upstreamed through +the mainline kernel tree. + +License +======= + +libbpf is dual-licensed under LGPL 2.1 and BSD 2-Clause. + Links =====